You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by sh...@apache.org on 2017/06/21 07:10:27 UTC
[01/50] [abbrv] lucene-solr:feature/autoscaling: Ref Guide: Add pow
evaluator docs
Repository: lucene-solr
Updated Branches:
refs/heads/feature/autoscaling b7ea70349 -> fb7803d9a
Ref Guide: Add pow evaluator docs
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/a5b1327a
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/a5b1327a
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/a5b1327a
Branch: refs/heads/feature/autoscaling
Commit: a5b1327aec3648f1582562ca5cfdcf024fa14a38
Parents: e2d8f94
Author: Joel Bernstein <jb...@apache.org>
Authored: Fri Jun 16 14:03:13 2017 -0400
Committer: Joel Bernstein <jb...@apache.org>
Committed: Fri Jun 16 14:03:13 2017 -0400
----------------------------------------------------------------------
solr/solr-ref-guide/src/stream-evaluators.adoc | 19 ++++++++++++++++++-
1 file changed, 18 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/a5b1327a/solr/solr-ref-guide/src/stream-evaluators.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/stream-evaluators.adoc b/solr/solr-ref-guide/src/stream-evaluators.adoc
index 3702f39..aec9bd2 100644
--- a/solr/solr-ref-guide/src/stream-evaluators.adoc
+++ b/solr/solr-ref-guide/src/stream-evaluators.adoc
@@ -192,7 +192,24 @@ if(gt(fieldA,fieldB),sub(fieldA,fieldB),sub(fieldB,fieldA)) // if fieldA > field
----
== pow
-//TODO
+The `pow` function returns the value of its first parameter raised to the power of its second parameter.
+
+=== pow Parameters
+
+* `Field Name | Raw Number | Number Evaluator`: Parameter 1
+* `Field Name | Raw Number | Number Evaluator`: Parameter 2
+
+=== pow Syntax
+
+The expressions below show the various ways in which you can use the `pow` evaluator.
+
+[source,text]
+----
+pow(2,3) // returns 2 raised to the 3rd power.
+pow(4,fieldA) // returns 4 raised by the value of fieldA.
+pow(fieldA,1.4) // returns the value of fieldA raised by 1.4.
+if(gt(fieldA,fieldB),pow(fieldA,fieldB),pow(fieldB,fieldA)) // if fieldA > fieldB then raise fieldA by fieldB, else raise fieldB by fieldA.
+----
== mod
//TODO
[45/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/solrconfig.xml b/solr/server/solr/configsets/_default/conf/solrconfig.xml
deleted file mode 100644
index 1b55374..0000000
--- a/solr/server/solr/configsets/_default/conf/solrconfig.xml
+++ /dev/null
@@ -1,1408 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>7.0.0</luceneMatchVersion>
-
- <!-- <lib/> directives can be used to instruct Solr to load any Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- Please note that <lib/> directives are processed in the order
- that they appear in your solrconfig.xml file, and are "stacked"
- on top of each other when building a ClassLoader - so if you have
- plugin jars with dependencies on other jars, the "lower level"
- dependency jars should be loaded first.
-
- If a "./lib" directory exists in your instanceDir, all files
- found in it are included as if you had used the following
- syntax...
-
- <lib dir="./lib" />
- -->
-
- <!-- A 'dir' option by itself adds any files found in the directory
- to the classpath, this is useful for including all jars in a
- directory.
-
- When a 'regex' is specified in addition to a 'dir', only the
- files in that directory which completely match the regex
- (anchored on both ends) will be included.
-
- If a 'dir' option (with or without a regex) is used and nothing
- is found that matches, a warning will be logged.
-
- The examples below can be used to load some solr-contribs along
- with their external dependencies.
- -->
- <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
- <!-- an exact 'path' can be used instead of a 'dir' to specify a
- specific jar file. This will cause a serious error to be logged
- if it can't be loaded.
- -->
- <!--
- <lib path="../a-jar-that-does-not-exist.jar" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:}</dataDir>
-
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory is filesystem
- based and tries to pick the best implementation for the current
- JVM and platform. solr.NRTCachingDirectoryFactory, the default,
- wraps solr.StandardDirectoryFactory and caches small files in memory
- for better NRT performance.
-
- One can force a particular implementation via solr.MMapDirectoryFactory,
- solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
-
- solr.RAMDirectoryFactory is memory based and not persistent.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
-
- <!-- The CodecFactory for defining the format of the inverted index.
- The default implementation is SchemaCodecFactory, which is the official Lucene
- index format, but hooks into the schema to provide per-field customization of
- the postings lists and per-document values in the fieldType element
- (postingsFormat/docValuesFormat). Note that most of the alternative implementations
- are experimental, so if you choose to customize the index format, it's a good
- idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
- before upgrading to a newer version to avoid unnecessary reindexing.
- A "compressionMode" string element can be added to <codecFactory> to choose
- between the existing compression modes in the default codec: "BEST_SPEED" (default)
- or "BEST_COMPRESSION".
- -->
- <codecFactory class="solr.SchemaCodecFactory"/>
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Index Config - These settings control low-level behavior of indexing
- Most example settings here show the default value, but are commented
- out, to more easily see where customizations have been made.
-
- Note: This replaces <indexDefaults> and <mainIndex> from older versions
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <indexConfig>
- <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
- LimitTokenCountFilterFactory in your fieldType definition. E.g.
- <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
- -->
- <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
- <!-- <writeLockTimeout>1000</writeLockTimeout> -->
-
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
- Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
- <!-- <useCompoundFile>false</useCompoundFile> -->
-
- <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
- indexing for buffering added documents and deletions before they are
- flushed to the Directory.
- maxBufferedDocs sets a limit on the number of documents buffered
- before flushing.
- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first. -->
- <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <!-- Expert: Merge Policy
- The Merge Policy in Lucene controls how merging of segments is done.
- The default since Solr/Lucene 3.3 is TieredMergePolicy.
- The default since Lucene 2.3 was the LogByteSizeMergePolicy,
- Even older versions of Lucene used LogDocMergePolicy.
- -->
- <!--
- <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
- <int name="maxMergeAtOnce">10</int>
- <int name="segmentsPerTier">10</int>
- <double name="noCFSRatio">0.1</double>
- </mergePolicyFactory>
- -->
-
- <!-- Expert: Merge Scheduler
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- can perform merges in the background using separate threads.
- The SerialMergeScheduler (Lucene 2.2 default) does not.
- -->
- <!--
- <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
- -->
-
- <!-- LockFactory
-
- This option specifies which Lucene LockFactory implementation
- to use.
-
- single = SingleInstanceLockFactory - suggested for a
- read-only index or when there is no possibility of
- another process trying to modify the index.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- Defaults: 'native' is default for Solr3.6 and later, otherwise
- 'simple' is the default
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>${solr.lock.type:native}</lockType>
-
- <!-- Commit Deletion Policy
- Custom deletion policies can be specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- The default Solr IndexDeletionPolicy implementation supports
- deleting index commit points on number of commits, age of
- commit point and optimized status.
-
- The latest commit point should always be preserved regardless
- of the criteria.
- -->
- <!--
- <deletionPolicy class="solr.SolrDeletionPolicy">
- -->
- <!-- The number of commit points to be kept -->
- <!-- <str name="maxCommitsToKeep">1</str> -->
- <!-- The number of optimized commit points to be kept -->
- <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <str name="maxCommitAge">30MINUTES</str>
- <str name="maxCommitAge">1DAY</str>
- -->
- <!--
- </deletionPolicy>
- -->
-
- <!-- Lucene Infostream
-
- To aid in advanced debugging, Lucene provides an "InfoStream"
- of detailed information when indexing.
-
- Setting The value to true will instruct the underlying Lucene
- IndexWriter to write its debugging info the specified file
- -->
- <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
- </indexConfig>
-
-
- <!-- JMX
-
- This example enables JMX if and only if an existing MBeanServer
- is found, use this if you want to configure JMX through JVM
- parameters. Remove this to disable exposing Solr configuration
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- Enables a transaction log, used for real-time get, durability, and
- and solr cloud replica recovery. The log can grow as big as
- uncommitted changes to the index, so use of a hard autoCommit
- is recommended (see below).
- "dir" - the target directory for transaction logs, defaults to the
- solr data directory.
- "numVersionBuckets" - sets the number of buckets used to keep
- track of max version values when checking for re-ordered
- updates; increase this value to reduce the cost of
- synchronizing access to version buckets during high-volume
- indexing, this requires 8 bytes (long) * numVersionBuckets
- of heap space per Solr core.
- -->
- <updateLog>
- <str name="dir">${solr.ulog.dir:}</str>
- <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
- </updateLog>
-
- <!-- AutoCommit
-
- Perform a hard commit automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time in ms that is allowed to pass
- since a document was added before automatically
- triggering a new commit.
- openSearcher - if false, the commit causes recent index changes
- to be flushed to stable storage, but does not cause a new
- searcher to be opened to make those changes visible.
-
- If the updateLog is enabled, then it's highly recommended to
- have some sort of hard autoCommit to limit the log size.
- -->
- <autoCommit>
- <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
-
- <!-- softAutoCommit is like autoCommit except it causes a
- 'soft' commit which only ensures that changes are visible
- but does not ensure that data is synced to disk. This is
- faster and more near-realtime friendly than a hard commit.
- -->
-
- <autoSoftCommit>
- <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
- </autoSoftCommit>
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- The RunExecutableListener executes an external command from a
- hook such as postCommit or postOptimize.
-
- exe - the name of the executable to run
- dir - dir to use as the current working directory. (default=".")
- wait - the calling thread waits until the executable returns.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
-
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Query section - these settings control query time things like caches
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded.
-
- ** WARNING **
-
- This option actually modifies a global Lucene property that
- will affect all SolrCores. If multiple solrconfig.xml files
- disagree on this property, the value at any given moment will
- be based on the last SolrCore to be initialized.
-
- -->
- <maxBooleanClauses>1024</maxBooleanClauses>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (see java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
- to occupy. Note that when this option is specified, the size
- and initialSize parameters are ignored.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Query Result Cache
-
- Caches results of searches - ordered lists of document ids
- (DocList) based on a query, a sort, and the range of documents requested.
- Additional supported parameter by LRUCache:
- maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
- to occupy
- -->
- <queryResultCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Document Cache
-
- Caches Lucene Document objects (the stored fields for each
- document). Since Lucene internal document ids are transient,
- this cache will not be autowarmed.
- -->
- <documentCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- custom cache currently used by block join -->
- <cache name="perSegFilter"
- class="solr.search.LRUCache"
- size="10"
- initialSize="0"
- autowarmCount="10"
- regenerator="solr.NoOpRegenerator" />
-
- <!-- Field Value Cache
-
- Cache used to hold field values that are quickly accessible
- by document id. The fieldValueCache is created by default
- even if not configured here.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- name through SolrIndexSearcher.getCache(),cacheLookup(), and
- cacheInsert(). The purpose is to enable easy caching of
- user/application level data. The regenerator argument should
- be specified as an implementation of solr.CacheRegenerator
- if autowarming is desired.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- are collected. For example, if a search for a particular query
- requests matching documents 10 through 19, and queryWindowSize is 50,
- then documents 0 through 49 will be collected and cached. Any further
- requests in that range can be satisfied via the cache.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- prepared but there is no current registered searcher to handle
- requests or to gain autowarming data from.
-
-
- -->
- <!-- QuerySenderListener takes an array of NamedList and executes a
- local query request for each NamedList in sequence.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- -->
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <useColdSearcher>false</useColdSearcher>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect is a legacy option that affects the behavior of requests
- such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and dispatch the query to a handler specified by the
- "qt" param, assuming "/select" isn't already registered.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests, resulting in a 404 unless a handler
- is explicitly registered with the name "/select"
-
- handleSelect="true" is not recommended for new users, but is the default
- for backwards compatibility
- -->
- <requestDispatcher handleSelect="false" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- multipartUploadLimitInKB - specifies the max size (in KiB) of
- Multipart File Uploads that Solr will allow in a Request.
-
- formdataUploadLimitInKB - specifies the max size (in KiB) of
- form data (application/x-www-form-urlencoded) sent via
- POST. You can use POST to pass request parameters not
- fitting into the URL.
-
- addHttpRequestToContext - if set to true, it will instruct
- the requestParsers to include the original HttpServletRequest
- object in the context map of the SolrQueryRequest under the
- key "httpRequest". It will not be used by any of the existing
- Solr components, but may be useful when developing custom
- plugins.
-
- *** WARNING ***
- Before enabling remote streaming, you should make sure your
- system has authentication enabled.
-
- <requestParsers enableRemoteStreaming="false"
- multipartUploadLimitInKB="-1"
- formdataUploadLimitInKB="-1"
- addHttpRequestToContext="false"/>
- -->
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- If you include a <cacheControl> directive, it will be used to
- generate a Cache-Control header (as well as an Expires header
- if the value contains "max-age=")
-
- By default, no Cache-Control header is generated.
-
- You can use the <cacheControl> option even if you have set
- never304="true"
- -->
- <!--
- <httpCaching never304="true" >
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- <!-- To enable Solr to respond with automatically generated HTTP
- Caching headers, and to response to Cache Validation requests
- correctly, set the value of never304="false"
-
- This will cause Solr to generate Last-Modified and ETag
- headers based on the properties of the Index.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- Incoming queries will be dispatched to a specific handler by name
- based on the path specified in the request.
-
- Legacy behavior: If the request path uses "/select" but no Request
- Handler has that name, and if handleSelect="true" has been specified in
- the requestDispatcher, then the Request Handler is dispatched based on
- the qt parameter. Handlers without a leading '/' are accessed this way
- like so: http://host/app/[core/]select?qt=name If no qt is
- given, then the requestHandler that declares default="true" will be
- used or the one named "standard".
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="/select" class="solr.SearchHandler">
- <!-- default values for query parameters can be specified, these
- will be overridden by parameters in the request
- -->
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <int name="rows">10</int>
- <!-- <str name="df">text</str> -->
- </lst>
- <!-- In addition to defaults, "appends" params can be specified
- to identify values which should be appended to the list of
- multi-val params from the query (or the existing "defaults").
- -->
- <!-- In this example, the param "fq=instock:true" would be appended to
- any query time fq params the user may specify, as a mechanism for
- partitioning the index, independent of any user selected filtering
- that may also be desired (perhaps as a result of faceted searching).
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "appends" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="appends">
- <str name="fq">inStock:true</str>
- </lst>
- -->
- <!-- "invariants" are a way of letting the Solr maintainer lock down
- the options available to Solr clients. Any params values
- specified here are used regardless of what values may be specified
- in either the query, the "defaults", or the "appends" params.
-
- In this example, the facet.field and facet.query params would
- be fixed, limiting the facets clients can use. Faceting is
- not turned on by default - but if the client does specify
- facet=true in the request, these are the only facets they
- will be able to see counts for; regardless of what other
- facet.field or facet.query params they may specify.
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "invariants" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="invariants">
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">price:[* TO 500]</str>
- <str name="facet.query">price:[500 TO *]</str>
- </lst>
- -->
- <!-- If the default list of SearchComponents is not desired, that
- list can either be overridden completely, or components can be
- prepended or appended to the default list. (see below)
- -->
- <!--
- <arr name="components">
- <str>nameOfCustomComponent1</str>
- <str>nameOfCustomComponent2</str>
- </arr>
- -->
- </requestHandler>
-
- <!-- A request handler that returns indented JSON by default -->
- <requestHandler name="/query" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- </lst>
- </requestHandler>
-
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- </requestHandler>
-
- <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
- <lst name="defaults">
- <str name="df">_text_</str>
- </lst>
- </initParams>
-
- <!-- This enabled schemaless mode
- <initParams path="/update/**">
- <lst name="defaults">
- <str name="update.chain">add-unknown-fields-to-the-schema</str>
- </lst>
- </initParams>
- -->
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <str name="lowernames">true</str>
- <str name="fmap.meta">ignored_</str>
- <str name="fmap.content">_text_</str>
- </lst>
- </requestHandler>
- <!-- Search Components
-
- Search components are registered to SolrCore and used by
- instances of SearchHandler (which can access them by name)
-
- By default, the following components are available:
-
- <searchComponent name="query" class="solr.QueryComponent" />
- <searchComponent name="facet" class="solr.FacetComponent" />
- <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
- <searchComponent name="highlight" class="solr.HighlightComponent" />
- <searchComponent name="stats" class="solr.StatsComponent" />
- <searchComponent name="debug" class="solr.DebugComponent" />
-
- Default configuration in a requestHandler would look like:
-
- <arr name="components">
- <str>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- If you register a searchComponent to one of the standard names,
- that will be used instead of the default.
-
- To insert components before or after the 'standard' components, use:
-
- <arr name="first-components">
- <str>myFirstComponentName</str>
- </arr>
-
- <arr name="last-components">
- <str>myLastComponentName</str>
- </arr>
-
- NOTE: The component registered with the name "debug" will
- always be executed after the "last-components"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text_general</str>
-
- <!-- Multiple "Spell Checkers" can be declared and used by this
- component
- -->
-
- <!-- a spellchecker built from a field of the main index -->
- <lst name="spellchecker">
- <str name="name">default</str>
- <str name="field">_text_</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
- <str name="distanceMeasure">internal</str>
- <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
- <float name="accuracy">0.5</float>
- <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
- <int name="maxEdits">2</int>
- <!-- the minimum shared prefix when enumerating terms -->
- <int name="minPrefix">1</int>
- <!-- maximum number of inspections per result. -->
- <int name="maxInspections">5</int>
- <!-- minimum length of a query term to be considered for correction -->
- <int name="minQueryLength">4</int>
- <!-- maximum threshold of documents a query term can appear to be considered for correction -->
- <float name="maxQueryFrequency">0.01</float>
- <!-- uncomment this to require suggestions to occur in 1% of the documents
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
- <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
- <!--
- <lst name="spellchecker">
- <str name="name">wordbreak</str>
- <str name="classname">solr.WordBreakSolrSpellChecker</str>
- <str name="field">name</str>
- <str name="combineWords">true</str>
- <str name="breakWords">true</str>
- <int name="maxChanges">10</int>
- </lst>
- -->
- </searchComponent>
-
- <!-- A request handler for demonstrating the spellcheck component.
-
- NOTE: This is purely as an example. The whole purpose of the
- SpellCheckComponent is to hook it into the request handler that
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
- NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
-
- See http://wiki.apache.org/solr/SpellCheckComponent for details
- on the request parameters.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <!-- Solr will use suggestions from both the 'default' spellchecker
- and from the 'wordbreak' spellchecker and combine them.
- collations (re-written queries) can include a combination of
- corrections from both spellcheckers -->
- <str name="spellcheck.dictionary">default</str>
- <str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">true</str>
- <str name="spellcheck.count">10</str>
- <str name="spellcheck.alternativeTermCount">5</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
- <str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
- <str name="spellcheck.maxCollationTries">10</str>
- <str name="spellcheck.maxCollations">5</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component. (Omitted here. See the default Solr example for a typical configuration.) -->
-
- <!-- Terms Component
-
- http://wiki.apache.org/solr/TermsComponent
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- <bool name="distrib">false</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- Configure the weighted fragListBuilder -->
- <fragListBuilder name="weighted"
- default="true"
- class="solr.highlight.WeightedFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <fragmentsBuilder name="default"
- default="true"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <!--
- <lst name="defaults">
- <str name="hl.multiValuedSeparatorChar">/</str>
- </lst>
- -->
- </fragmentsBuilder>
-
- <!-- multi-colored tag FragmentsBuilder -->
- <fragmentsBuilder name="colored"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
-
- <boundaryScanner name="default"
- default="true"
- class="solr.highlight.SimpleBoundaryScanner">
- <lst name="defaults">
- <str name="hl.bs.maxScan">10</str>
- <str name="hl.bs.chars">.,!? 	 </str>
- </lst>
- </boundaryScanner>
-
- <boundaryScanner name="breakIterator"
- class="solr.highlight.BreakIteratorBoundaryScanner">
- <lst name="defaults">
- <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
- <str name="hl.bs.type">WORD</str>
- <!-- language and country are used when constructing Locale object. -->
- <!-- And the Locale object will be used when getting instance of BreakIterator -->
- <str name="hl.bs.language">en</str>
- <str name="hl.bs.country">US</str>
- </lst>
- </boundaryScanner>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- http://wiki.apache.org/solr/UpdateRequestProcessor
-
- -->
-
- <!-- Add unknown fields to the schema
-
- Field type guessing update processors that will
- attempt to parse string-typed field values as Booleans, Longs,
- Doubles, or Dates, and then add schema fields with the guessed
- field types.
-
- These require that the schema is both managed and mutable, by
- declaring schemaFactory as ManagedIndexSchemaFactory, with
- mutable specified as true.
-
- See http://wiki.apache.org/solr/GuessingFieldTypes
- -->
- <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
- <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
- <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
- <str name="pattern">[^\w-\.]</str>
- <str name="replacement">_</str>
- </updateProcessor>
- <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
- <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
- <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
- <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
- <arr name="format">
- <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss</str>
- <str>yyyy-MM-dd'T'HH:mmZ</str>
- <str>yyyy-MM-dd'T'HH:mm</str>
- <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd HH:mm:ssZ</str>
- <str>yyyy-MM-dd HH:mm:ss</str>
- <str>yyyy-MM-dd HH:mmZ</str>
- <str>yyyy-MM-dd HH:mm</str>
- <str>yyyy-MM-dd</str>
- </arr>
- </updateProcessor>
- <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
- <str name="defaultFieldType">strings</str>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Boolean</str>
- <str name="fieldType">booleans</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.util.Date</str>
- <str name="fieldType">tdates</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Long</str>
- <str name="valueClass">java.lang.Integer</str>
- <str name="fieldType">tlongs</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Number</str>
- <str name="fieldType">tdoubles</str>
- </lst>
- </updateProcessor>
-
- <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:true}"
- processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
- <processor class="solr.LogUpdateProcessorFactory"/>
- <processor class="solr.DistributedUpdateProcessorFactory"/>
- <processor class="solr.RunUpdateProcessorFactory"/>
- </updateRequestProcessorChain>
-
- <!-- Deduplication
-
- An example dedup update processor that creates the "id" field
- on the fly based on the hash code of some other fields. This
- example has overwriteDupes set to false since we are using the
- id field as the signatureField and Solr will maintain
- uniqueness based on that anyway.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Language identification
-
- This example update chain identifies the language of the incoming
- documents using the langid contrib. The detected language is
- written to field language_s. No field name mapping is done.
- The fields used for detection are text, title, subject and description,
- making this example suitable for detecting languages form full-text
- rich documents injected via ExtractingRequestHandler.
- See more about langId at http://wiki.apache.org/solr/LanguageDetection
- -->
- <!--
- <updateRequestProcessorChain name="langid">
- <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
- <str name="langid.fl">text,title,subject,description</str>
- <str name="langid.langField">language_s</str>
- <str name="langid.fallback">en</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Script update processor
-
- This example hooks in an update processor implemented using JavaScript.
-
- See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
- -->
- <!--
- <updateRequestProcessorChain name="script">
- <processor class="solr.StatelessScriptUpdateProcessorFactory">
- <str name="script">update-script.js</str>
- <lst name="params">
- <str name="config_param">example config parameter</str>
- </lst>
- </processor>
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
- -->
-
- <queryResponseWriter name="json" class="solr.JSONResponseWriter">
- <!-- For the purposes of the tutorial, JSON responses are written as
- plain text so that they are easy to read in *any* browser.
- If you expect a MIME type of "application/json" just remove this override.
- -->
- <str name="content-type">text/plain; charset=UTF-8</str>
- </queryResponseWriter>
-
- <!--
- Custom response writers can be declared as needed...
- -->
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
- <str name="template.base.dir">${velocity.template.base.dir:}</str>
- <str name="solr.resource.loader.enabled">${velocity.solr.resource.loader.enabled:true}</str>
- <str name="params.resource.loader.enabled">${velocity.params.resource.loader.enabled:false}</str>
- </queryResponseWriter>
-
- <!-- XSLT response writer transforms the XML output by any xslt file found
- in Solr's conf/xslt directory. Changes to xslt files are checked for
- every xsltCacheLifetimeSeconds.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- https://cwiki.apache.org/confluence/display/solr/Query+Syntax+and+Parsing
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
-
- <!-- Document Transformers
- http://wiki.apache.org/solr/DocTransformers
- -->
- <!--
- Could be something like:
- <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
- <int name="connection">jdbc://....</int>
- </transformer>
-
- To add a constant value to all docs, use:
- <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <int name="value">5</int>
- </transformer>
-
- If you want the user to still be able to change it with _value:something_ use this:
- <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <double name="defaultValue">5</double>
- </transformer>
-
- If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
- EditorialMarkerFactory will do exactly that:
- <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
- -->
-</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/stopwords.txt b/solr/server/solr/configsets/_default/conf/stopwords.txt
deleted file mode 100644
index ae1e83e..0000000
--- a/solr/server/solr/configsets/_default/conf/stopwords.txt
+++ /dev/null
@@ -1,14 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/synonyms.txt b/solr/server/solr/configsets/_default/conf/synonyms.txt
deleted file mode 100644
index eab4ee8..0000000
--- a/solr/server/solr/configsets/_default/conf/synonyms.txt
+++ /dev/null
@@ -1,29 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-#some test synonym mappings unlikely to appear in real input text
-aaafoo => aaabar
-bbbfoo => bbbfoo bbbbar
-cccfoo => cccbar cccbaz
-fooaaa,baraaa,bazaaa
-
-# Some synonym groups specific to this example
-GB,gib,gigabyte,gigabytes
-MB,mib,megabyte,megabytes
-Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
-#after us won't split it into two words.
-
-# Synonym mappings can be used for spelling correction too
-pixima => pixma
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/currency.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/currency.xml b/solr/server/solr/configsets/basic_configs/conf/currency.xml
new file mode 100644
index 0000000..3a9c58a
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/currency.xml
@@ -0,0 +1,67 @@
+<?xml version="1.0" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!-- Example exchange rates file for CurrencyField type named "currency" in example schema -->
+
+<currencyConfig version="1.0">
+ <rates>
+ <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 -->
+ <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" />
+ <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" />
+ <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" />
+ <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" />
+ <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" />
+ <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" />
+ <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" />
+ <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" />
+ <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" />
+ <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" />
+ <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" />
+ <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" />
+ <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" />
+ <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" />
+ <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" />
+ <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" />
+ <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" />
+ <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" />
+ <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" />
+ <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" />
+ <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" />
+ <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" />
+ <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" />
+ <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" />
+ <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" />
+ <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" />
+ <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" />
+ <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" />
+ <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" />
+ <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" />
+ <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" />
+ <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" />
+ <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" />
+ <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" />
+ <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" />
+ <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" />
+ <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" />
+
+ <!-- Cross-rates for some common currencies -->
+ <rate from="EUR" to="GBP" rate="0.869914" />
+ <rate from="EUR" to="NOK" rate="7.800095" />
+ <rate from="GBP" to="NOK" rate="8.966508" />
+ </rates>
+</currencyConfig>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/elevate.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/elevate.xml b/solr/server/solr/configsets/basic_configs/conf/elevate.xml
new file mode 100644
index 0000000..2c09ebe
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/elevate.xml
@@ -0,0 +1,42 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!-- If this file is found in the config directory, it will only be
+ loaded once at startup. If it is found in Solr's data
+ directory, it will be re-loaded every commit.
+
+ See http://wiki.apache.org/solr/QueryElevationComponent for more info
+
+-->
+<elevate>
+ <!-- Query elevation examples
+ <query text="foo bar">
+ <doc id="1" />
+ <doc id="2" />
+ <doc id="3" />
+ </query>
+
+for use with techproducts example
+
+ <query text="ipod">
+ <doc id="MA147LL/A" /> put the actual ipod at the top
+ <doc id="IW-02" exclude="true" /> exclude this cable
+ </query>
+-->
+
+</elevate>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt
new file mode 100644
index 0000000..307a85f
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt
@@ -0,0 +1,8 @@
+# Set of Catalan contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+l
+m
+n
+s
+t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt
new file mode 100644
index 0000000..f1bba51
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt
@@ -0,0 +1,15 @@
+# Set of French contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+l
+m
+t
+qu
+n
+s
+j
+d
+c
+jusqu
+quoiqu
+lorsqu
+puisqu
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt
new file mode 100644
index 0000000..9ebe7fa
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+m
+b
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt
new file mode 100644
index 0000000..cac0409
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt
@@ -0,0 +1,23 @@
+# Set of Italian contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+c
+l
+all
+dall
+dell
+nell
+sull
+coll
+pell
+gl
+agl
+dagl
+degl
+negl
+sugl
+un
+m
+t
+s
+v
+d
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt b/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt
new file mode 100644
index 0000000..4d2642c
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish hyphenations for StopFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+h
+n
+t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt
new file mode 100644
index 0000000..4410729
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt
@@ -0,0 +1,6 @@
+# Set of overrides for the dutch stemmer
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+fiets fiets
+bromfiets bromfiets
+ei eier
+kind kinder
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt
new file mode 100644
index 0000000..71b7508
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt
@@ -0,0 +1,420 @@
+#
+# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
+#
+# Any token with a part-of-speech tag that exactly matches those defined in this
+# file are removed from the token stream.
+#
+# Set your own stoptags by uncommenting the lines below. Note that comments are
+# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
+# etc. that can be useful for building you own stoptag set.
+#
+# The entire possible tagset is provided below for convenience.
+#
+#####
+# noun: unclassified nouns
+#名詞
+#
+# noun-common: Common nouns or nouns where the sub-classification is undefined
+#名詞-一般
+#
+# noun-proper: Proper nouns where the sub-classification is undefined
+#名詞-固有名詞
+#
+# noun-proper-misc: miscellaneous proper nouns
+#名詞-固有名詞-一般
+#
+# noun-proper-person: Personal names where the sub-classification is undefined
+#名詞-固有名詞-人名
+#
+# noun-proper-person-misc: names that cannot be divided into surname and
+# given name; foreign names; names where the surname or given name is unknown.
+# e.g. お市の方
+#名詞-固有名詞-人名-一般
+#
+# noun-proper-person-surname: Mainly Japanese surnames.
+# e.g. 山田
+#名詞-固有名詞-人名-姓
+#
+# noun-proper-person-given_name: Mainly Japanese given names.
+# e.g. 太郎
+#名詞-固有名詞-人名-名
+#
+# noun-proper-organization: Names representing organizations.
+# e.g. 通産省, NHK
+#名詞-固有名詞-組織
+#
+# noun-proper-place: Place names where the sub-classification is undefined
+#名詞-固有名詞-地域
+#
+# noun-proper-place-misc: Place names excluding countries.
+# e.g. アジア, バルセロナ, 京都
+#名詞-固有名詞-地域-一般
+#
+# noun-proper-place-country: Country names.
+# e.g. 日本, オーストラリア
+#名詞-固有名詞-地域-国
+#
+# noun-pronoun: Pronouns where the sub-classification is undefined
+#名詞-代名詞
+#
+# noun-pronoun-misc: miscellaneous pronouns:
+# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
+#名詞-代名詞-一般
+#
+# noun-pronoun-contraction: Spoken language contraction made by combining a
+# pronoun and the particle 'wa'.
+# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
+#名詞-代名詞-縮約
+#
+# noun-adverbial: Temporal nouns such as names of days or months that behave
+# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
+# e.g. 金曜, 一月, 午後, 少量
+#名詞-副詞可能
+#
+# noun-verbal: Nouns that take arguments with case and can appear followed by
+# 'suru' and related verbs (する, できる, なさる, くださる)
+# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
+#名詞-サ変接続
+#
+# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
+# e.g. 健康, 安易, 駄目, だめ
+#名詞-形容動詞語幹
+#
+# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
+# e.g. 0, 1, 2, 何, 数, 幾
+#名詞-数
+#
+# noun-affix: noun affixes where the sub-classification is undefined
+#名詞-非自立
+#
+# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
+# attach to the base form of inflectional words, words that cannot be classified
+# into any of the other categories below. This category includes indefinite nouns.
+# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
+# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
+# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
+# わり, 割り, 割, ん-口語/, もん-口語/
+#名詞-非自立-一般
+#
+# noun-affix-adverbial: noun affixes that that can behave as adverbs.
+# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
+# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
+# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
+# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
+# 儘, 侭, みぎり, 矢先
+#名詞-非自立-副詞可能
+#
+# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
+# with the stem よう(だ) ("you(da)").
+# e.g. よう, やう, 様 (よう)
+#名詞-非自立-助動詞語幹
+#
+# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
+# connection form な (aux "da").
+# e.g. みたい, ふう
+#名詞-非自立-形容動詞語幹
+#
+# noun-special: special nouns where the sub-classification is undefined.
+#名詞-特殊
+#
+# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
+# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
+# form of inflectional words.
+# e.g. そう
+#名詞-特殊-助動詞語幹
+#
+# noun-suffix: noun suffixes where the sub-classification is undefined.
+#名詞-接尾
+#
+# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
+# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
+# any of the other categories below. In general, this category is more inclusive than
+# 接尾語 ("suffix") and is usually the last element in a compound noun.
+# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
+# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
+#名詞-接尾-一般
+#
+# noun-suffix-person: Suffixes that form nouns and attach to person names more often
+# than other nouns.
+# e.g. 君, 様, 著
+#名詞-接尾-人名
+#
+# noun-suffix-place: Suffixes that form nouns and attach to place names more often
+# than other nouns.
+# e.g. 町, 市, 県
+#名詞-接尾-地域
+#
+# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
+# can appear before スル ("suru").
+# e.g. 化, 視, 分け, 入り, 落ち, 買い
+#名詞-接尾-サ変接続
+#
+# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
+# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
+# conjunctive form of inflectional words.
+# e.g. そう
+#名詞-接尾-助動詞語幹
+#
+# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
+# form of inflectional words and appear before the copula だ ("da").
+# e.g. 的, げ, がち
+#名詞-接尾-形容動詞語幹
+#
+# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
+# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
+#名詞-接尾-副詞可能
+#
+# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
+# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
+# to numbers.
+# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
+#名詞-接尾-助数詞
+#
+# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
+# e.g. (楽し) さ, (考え) 方
+#名詞-接尾-特殊
+#
+# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
+# together.
+# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
+#名詞-接続詞的
+#
+# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
+# semantically verb-like.
+# e.g. ごらん, ご覧, 御覧, 頂戴
+#名詞-動詞非自立的
+#
+# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
+# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
+# is いわく ("iwaku").
+#名詞-引用文字列
+#
+# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
+# behave like an adjective.
+# e.g. 申し訳, 仕方, とんでも, 違い
+#名詞-ナイ形容詞語幹
+#
+#####
+# prefix: unclassified prefixes
+#接頭詞
+#
+# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
+# excluding numerical expressions.
+# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
+#接頭詞-名詞接続
+#
+# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
+# in conjunctive form followed by なる/なさる/くださる.
+# e.g. お (読みなさい), お (座り)
+#接頭詞-動詞接続
+#
+# prefix-adjectival: Prefixes that attach to adjectives.
+# e.g. お (寒いですねえ), バカ (でかい)
+#接頭詞-形容詞接続
+#
+# prefix-numerical: Prefixes that attach to numerical expressions.
+# e.g. 約, およそ, 毎時
+#接頭詞-数接続
+#
+#####
+# verb: unclassified verbs
+#動詞
+#
+# verb-main:
+#動詞-自立
+#
+# verb-auxiliary:
+#動詞-非自立
+#
+# verb-suffix:
+#動詞-接尾
+#
+#####
+# adjective: unclassified adjectives
+#形容詞
+#
+# adjective-main:
+#形容詞-自立
+#
+# adjective-auxiliary:
+#形容詞-非自立
+#
+# adjective-suffix:
+#形容詞-接尾
+#
+#####
+# adverb: unclassified adverbs
+#副詞
+#
+# adverb-misc: Words that can be segmented into one unit and where adnominal
+# modification is not possible.
+# e.g. あいかわらず, 多分
+#副詞-一般
+#
+# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
+# な, する, だ, etc.
+# e.g. こんなに, そんなに, あんなに, なにか, なんでも
+#副詞-助詞類接続
+#
+#####
+# adnominal: Words that only have noun-modifying forms.
+# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
+# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
+# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
+#連体詞
+#
+#####
+# conjunction: Conjunctions that can occur independently.
+# e.g. が, けれども, そして, じゃあ, それどころか
+接続詞
+#
+#####
+# particle: unclassified particles.
+助詞
+#
+# particle-case: case particles where the subclassification is undefined.
+助詞-格助詞
+#
+# particle-case-misc: Case particles.
+# e.g. から, が, で, と, に, へ, より, を, の, にて
+助詞-格助詞-一般
+#
+# particle-case-quote: the "to" that appears after nouns, a person’s speech,
+# quotation marks, expressions of decisions from a meeting, reasons, judgements,
+# conjectures, etc.
+# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
+助詞-格助詞-引用
+#
+# particle-case-compound: Compounds of particles and verbs that mainly behave
+# like case particles.
+# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
+# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
+# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
+# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
+# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
+# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
+# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
+# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
+助詞-格助詞-連語
+#
+# particle-conjunctive:
+# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
+# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
+# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
+助詞-接続助詞
+#
+# particle-dependency:
+# e.g. こそ, さえ, しか, すら, は, も, ぞ
+助詞-係助詞
+#
+# particle-adverbial:
+# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
+# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
+# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
+# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
+# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
+助詞-副助詞
+#
+# particle-interjective: particles with interjective grammatical roles.
+# e.g. (松島) や
+助詞-間投助詞
+#
+# particle-coordinate:
+# e.g. と, たり, だの, だり, とか, なり, や, やら
+助詞-並立助詞
+#
+# particle-final:
+# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
+# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
+助詞-終助詞
+#
+# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
+# adverbial, conjunctive, or sentence final. For example:
+# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
+# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
+# 「(祈りが届いたせい) か (, 試験に合格した.)」
+# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
+# e.g. か
+助詞-副助詞／並立助詞／終助詞
+#
+# particle-adnominalizer: The "no" that attaches to nouns and modifies
+# non-inflectional words.
+助詞-連体化
+#
+# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
+# that are giongo, giseigo, or gitaigo.
+# e.g. に, と
+助詞-副詞化
+#
+# particle-special: A particle that does not fit into one of the above classifications.
+# This includes particles that are used in Tanka, Haiku, and other poetry.
+# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
+助詞-特殊
+#
+#####
+# auxiliary-verb:
+助動詞
+#
+#####
+# interjection: Greetings and other exclamations.
+# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
+# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
+#感動詞
+#
+#####
+# symbol: unclassified Symbols.
+記号
+#
+# symbol-misc: A general symbol not in one of the categories below.
+# e.g. [○◎@$〒→+]
+記号-一般
+#
+# symbol-comma: Commas
+# e.g. [,、]
+記号-読点
+#
+# symbol-period: Periods and full stops.
+# e.g. [.．。]
+記号-句点
+#
+# symbol-space: Full-width whitespace.
+記号-空白
+#
+# symbol-open_bracket:
+# e.g. [({‘“『【]
+記号-括弧開
+#
+# symbol-close_bracket:
+# e.g. [)}’”』」】]
+記号-括弧閉
+#
+# symbol-alphabetic:
+#記号-アルファベット
+#
+#####
+# other: unclassified other
+#その他
+#
+# other-interjection: Words that are hard to classify as noun-suffixes or
+# sentence-final particles.
+# e.g. (だ)ァ
+その他-間投
+#
+#####
+# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
+# e.g. あの, うんと, えと
+フィラー
+#
+#####
+# non-verbal: non-verbal sound.
+非言語音
+#
+#####
+# fragment:
+#語断片
+#
+#####
+# unknown: unknown part of speech.
+#未知語
+#
+##### End of file
[38/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-9623: Fix test
errors related to some test expecting streaming to be enabled
Posted by sh...@apache.org.
SOLR-9623: Fix test errors related to some test expecting streaming to be enabled
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/a4f27bbf
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/a4f27bbf
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/a4f27bbf
Branch: refs/heads/feature/autoscaling
Commit: a4f27bbfbb1d0542a95e13507555cf74ebccbe45
Parents: 63a4005
Author: Jan Høydahl <ja...@apache.org>
Authored: Tue Jun 20 21:03:12 2017 +0200
Committer: Jan Høydahl <ja...@apache.org>
Committed: Tue Jun 20 21:03:12 2017 +0200
----------------------------------------------------------------------
solr/core/src/test-files/solr/collection1/conf/solrconfig.xml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/a4f27bbf/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml
index afbef84..5de3e64 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml
@@ -461,7 +461,7 @@
</searchComponent>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
+ <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
[30/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/managed-schema b/solr/server/solr/configsets/_default/conf/managed-schema
new file mode 100644
index 0000000..f1017af
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/managed-schema
@@ -0,0 +1,1069 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking. To improve performance one could
+ - set stored="false" for all fields possible (esp large fields) when you
+ only need to search on the field but don't need to return the original
+ value.
+ - set indexed="false" if you don't need to search on the field, but only
+ return the field as a result of searching on other indexed fields.
+ - remove all unneeded copyField statements
+ - for best index size and searching performance, set "index" to false
+ for all general text fields, use copyField to copy them to the
+ catchall "text" field, and use that for searching.
+ - For maximum indexing performance, use the ConcurrentUpdateSolrServer
+ java client.
+ - Remember to run the JVM in server mode, and use a higher logging level
+ that avoids logging every request
+-->
+
+<schema name="default-config" version="2.0">
+ <!-- attribute "name" is the name of this schema and is only used for display purposes.
+ version="x.y" is Solr's version number for the schema syntax and
+ semantics. It should not normally be changed by applications.
+
+ 1.0: multiValued attribute did not exist, all fields are multiValued
+ by nature
+ 1.1: multiValued attribute introduced, false by default
+ 1.2: omitTermFreqAndPositions attribute introduced, true by default
+ except for text fields.
+ 1.3: removed optional field compress feature
+ 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+ behavior when a single string produces multiple tokens. Defaults
+ to off for version >= 1.4
+ 1.5: omitNorms defaults to true for primitive field types
+ (int, float, boolean, string...)
+ 1.6: useDocValuesAsStored defaults to true.
+ -->
+
+ <!-- Valid attributes for fields:
+ name: mandatory - the name for the field
+ type: mandatory - the name of a field type from the
+ fieldTypes section
+ indexed: true if this field should be indexed (searchable or sortable)
+ stored: true if this field should be retrievable
+ docValues: true if this field should have doc values. Doc values are
+ useful (required, if you are using *Point fields) for faceting,
+ grouping, sorting and function queries. Doc values will make the index
+ faster to load, more NRT-friendly and more memory-efficient.
+ They however come with some limitations: they are currently only
+ supported by StrField, UUIDField, all Trie*Fields and *PointFields,
+ and depending on the field type, they might require the field to be
+ single-valued, be required or have a default value (check the
+ documentation of the field type you're interested in for more information)
+ multiValued: true if this field may contain multiple values per document
+ omitNorms: (expert) set to true to omit the norms associated with
+ this field (this disables length normalization and index-time
+ boosting for the field, and saves some memory). Only full-text
+ fields or fields that need an index-time boost need norms.
+ Norms are omitted for primitive (non-analyzed) types by default.
+ termVectors: [false] set to true to store the term vector for a
+ given field.
+ When using MoreLikeThis, fields used for similarity should be
+ stored for best performance.
+ termPositions: Store position information with the term vector.
+ This will increase storage costs.
+ termOffsets: Store offset information with the term vector. This
+ will increase storage costs.
+ required: The field is required. It will throw an error if the
+ value does not exist
+ default: a value that should be used if no value is specified
+ when adding a document.
+ -->
+
+ <!-- field names should consist of alphanumeric or underscore characters only and
+ not start with a digit. This is not currently strictly enforced,
+ but other field names will not have first class support from all components
+ and back compatibility is not guaranteed. Names with both leading and
+ trailing underscores (e.g. _version_) are reserved.
+ -->
+
+ <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
+ id, _version_, and _text_. All other fields will be type guessed and added via the
+ "add-unknown-fields-to-the-schema" update request processor chain declared
+ in solrconfig.xml.
+
+ Note that many dynamic fields are also defined - you can use them to specify a
+ field's type via field naming conventions - see below.
+
+ WARNING: The _text_ catch-all field will significantly increase your index size.
+ If you don't need it, consider removing it and the corresponding copyField directive.
+ -->
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <!-- doc values are enabled by default for primitive types such as long so we don't index the version field -->
+ <field name="_version_" type="long" indexed="false" stored="false"/>
+ <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+ <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+ <!-- Only enabled in the "schemaless" data-driven example (assuming the client
+ does not know what fields may be searched) because it's very expensive to index everything twice. -->
+ <!-- <copyField source="*" dest="_text_"/> -->
+
+ <!-- Dynamic field definitions allow using convention over configuration
+ for fields via the specification of patterns to match field names.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end. -->
+
+ <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+ <dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true" />
+ <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
+
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+ <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
+ <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
+
+ <!-- KD-tree (point) numerics -->
+ <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
+ <dynamicField name="*_pis" type="pints" indexed="true" stored="true"/>
+ <dynamicField name="*_pl" type="plong" indexed="true" stored="true"/>
+ <dynamicField name="*_pls" type="plongs" indexed="true" stored="true"/>
+ <dynamicField name="*_pf" type="pfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_pfs" type="pfloats" indexed="true" stored="true"/>
+ <dynamicField name="*_pd" type="pdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_pds" type="pdoubles" indexed="true" stored="true"/>
+ <dynamicField name="*_pdt" type="pdate" indexed="true" stored="true"/>
+ <dynamicField name="*_pdts" type="pdates" indexed="true" stored="true"/>
+
+ <!-- some trie-coded dynamic fields -->
+ <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
+ <dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
+ <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
+ <dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
+ <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
+ <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
+ <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
+ <dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
+
+ <!-- payloaded dynamic fields -->
+ <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true" stored="true"/>
+ <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true" stored="true"/>
+ <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true" stored="true"/>
+
+ <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
+
+ <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+ <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+ <dynamicField name="random_*" type="random" />
+
+ <!-- uncomment the following to ignore any fields that don't already match an existing
+ field name or dynamic field, rather than reporting them as an error.
+ alternately, change the type="ignored" to some other type e.g. "text" if you want
+ unknown fields indexed and/or stored by default
+
+ NB: use of "*" dynamic fields will disable field type guessing and adding
+ unknown fields to the schema. -->
+ <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+ <!-- Field to use to determine and enforce document uniqueness.
+ Unless this field is marked with required="false", it will be a required field
+ -->
+ <uniqueKey>id</uniqueKey>
+
+ <!-- copyField commands copy one field to another at the time a document
+ is added to the index. It's used either to index the same field differently,
+ or to add multiple fields to the same field for easier/faster searching.
+
+ <copyField source="sourceFieldName" dest="destinationFieldName"/>
+ -->
+
+ <!-- field type definitions. The "name" attribute is
+ just a label to be used by field definitions. The "class"
+ attribute and any other attributes determine the real
+ behavior of the fieldType.
+ Class names starting with "solr" refer to java classes in a
+ standard package such as org.apache.solr.analysis
+ -->
+
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+ It supports doc values but in that case the field needs to be
+ single-valued and either required or have a default value.
+ -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+ <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+ <!-- boolean type: "true" or "false" -->
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+ <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+ <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+ currently supported on types that are sorted internally as strings
+ and on numeric types.
+ This includes "string","boolean", "int", "float", "long", "date", "double",
+ including the "Trie" and "Point" variants.
+ - If sortMissingLast="true", then a sort on this field will cause documents
+ without the field to come after documents with the field,
+ regardless of the requested sort order (asc or desc).
+ - If sortMissingFirst="true", then a sort on this field will cause documents
+ without the field to come before documents with the field,
+ regardless of the requested sort order.
+ - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+ then default lucene sorting will be used which places docs without the
+ field first in an ascending sort and last in a descending sort.
+ -->
+
+ <!--
+ Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
+ search time and at index time, but some features are still not supported.
+ Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+ -->
+ <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+ <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+ <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+ <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+ <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+ <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+ <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+ <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+
+ <!--
+ Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
+ tint/tfloat/tlong/tdouble types.
+ -->
+ <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+
+ <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
+ <!--
+ Numeric field types that index each value at various levels of precision
+ to accelerate range queries when the number of values between the range
+ endpoints is large. See the javadoc for NumericRangeQuery for internal
+ implementation details.
+
+ Smaller precisionStep values (specified in bits) will lead to more tokens
+ indexed per value, slightly larger index size, and faster range queries.
+ A precisionStep of 0 disables indexing at different precision levels.
+
+ Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
+ -->
+ <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+
+ <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+ is a more restricted form of the canonical representation of dateTime
+ http://www.w3.org/TR/xmlschema-2/#dateTime
+ The trailing "Z" designates UTC time and is mandatory.
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+ All other components are mandatory.
+
+ Expressions can also be used to denote calculations that should be
+ performed relative to "NOW" to determine the value, ie...
+
+ NOW/HOUR
+ ... Round to the start of the current hour
+ NOW-1DAY
+ ... Exactly 1 day prior to now
+ NOW/DAY+6MONTHS+3DAYS
+ ... 6 months and 3 days in the future from the start of
+ the current day
+
+ Consult the TrieDateField javadocs for more information.
+ -->
+ <!-- KD-tree versions of date fields -->
+ <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+ <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+
+ <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
+ <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
+
+
+ <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+ <fieldType name="binary" class="solr.BinaryField"/>
+
+ <!-- The "RandomSortField" is not used to store or search any
+ data. You can declare fields of this type it in your schema
+ to generate pseudo-random orderings of your docs for sorting
+ or function purposes. The ordering is generated based on the field
+ name and the version of the index. As long as the index version
+ remains unchanged, and the same field name is reused,
+ the ordering of the docs will be consistent.
+ If you want different psuedo-random orderings of documents,
+ for the same version of the index, use a dynamicField and
+ change the field name in the request.
+ -->
+ <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+
+ <!-- solr.TextField allows the specification of custom text analyzers
+ specified as a tokenizer and a list of token filters. Different
+ analyzers may be specified for indexing and querying.
+
+ The optional positionIncrementGap puts space between multiple fields of
+ this type on the same document, with the purpose of preventing false phrase
+ matching across fields.
+
+ For more info on customizing your analyzer chain, please see
+ http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+ -->
+
+ <!-- One can also specify an existing Analyzer class that has a
+ default constructor via the class attribute on the analyzer element.
+ Example:
+ <fieldType name="text_greek" class="solr.TextField">
+ <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+ </fieldType>
+ -->
+
+ <!-- A text field that only splits on whitespace for exact matching of words -->
+ <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
+ <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A general text field that has reasonable, generic
+ cross-language defaults: it tokenizes with StandardTokenizer,
+ removes stop words from case-insensitive "stopwords.txt"
+ (empty by default), and down cases. At query time only, it
+ also applies synonyms.
+ -->
+ <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English: it
+ tokenizes with StandardTokenizer, removes English stop words
+ (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+ finally applies Porter's stemming. The query time analyzer
+ also applies synonyms from synonyms.txt. -->
+ <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
+ <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English, plus
+ aggressive word-splitting and autophrase features enabled.
+ This field is just like text_en, except it adds
+ WordDelimiterGraphFilter to enable splitting and matching of
+ words on case-change, alpha numeric boundaries, and
+ non-alphanumeric chars. This means certain compound word
+ cases will work, for example query "wi fi" will match
+ document "WiFi" or "wi-fi".
+ -->
+ <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
+ <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
+ but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
+ <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
+ <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+ possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+ possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Just like text_general except it reverses the characters of
+ each token, to enable more efficient leading wildcard queries.
+ -->
+ <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
+ <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+ maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
+ <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- lowercases the entire field value, keeping it as a single token. -->
+ <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
+ <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at index time, so
+ queries for paths match documents at that path, or in descendent paths
+ -->
+ <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
+ <fieldType name="descendent_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at query time, so
+ queries for paths match documents at that path, or in ancestor paths
+ -->
+ <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
+ <fieldType name="ancestor_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ </fieldType>
+
+ <!-- since fields of this type are by default not stored or indexed,
+ any data added to them will be ignored outright. -->
+ <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
+
+ <!-- This point type indexes the coordinates as separate fields (subFields)
+ If subFieldType is defined, it references a type, and a dynamic field
+ definition is created matching *___<typename>. Alternately, if
+ subFieldSuffix is defined, that is used to create the subFields.
+ Example: if subFieldType="double", then the coordinates would be
+ indexed in fields myloc_0___double,myloc_1___double.
+ Example: if subFieldSuffix="_d" then the coordinates would be indexed
+ in fields myloc_0_d,myloc_1_d
+ The subFields are an implementation detail of the fieldType, and end
+ users normally should not need to know about them.
+ -->
+ <dynamicField name="*_point" type="point" indexed="true" stored="true"/>
+ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+ <!-- A specialized field for geospatial search filters and distance sorting. -->
+ <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+ <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
+ For more information about this and other Spatial fields new to Solr 4, see:
+ http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+ -->
+ <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+ geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+ <!-- Payloaded field types -->
+ <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
+ Parameters:
+ defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
+ precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
+ providerClass: Lets you plug in other exchange provider backend:
+ solr.FileExchangeRateProvider is the default and takes one parameter:
+ currencyConfig: name of an xml file holding exchange rates
+ solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
+ ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
+ refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
+ -->
+ <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
+
+
+
+ <!-- some examples for different languages (generally ordered by ISO code) -->
+
+ <!-- Arabic -->
+ <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
+ <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- for any non-arabic -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+ <!-- normalizes ﻯ to ﻱ, etc -->
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.ArabicStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Bulgarian -->
+ <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
+ <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+ <filter class="solr.BulgarianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Catalan -->
+ <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
+ <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+ <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
+ <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- for any non-CJK -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.CJKBigramFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Czech -->
+ <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
+ <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+ <filter class="solr.CzechStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Danish -->
+ <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
+ <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- German -->
+ <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
+ <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+ <filter class="solr.GermanNormalizationFilterFactory"/>
+ <filter class="solr.GermanLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Greek -->
+ <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
+ <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- greek specific lowercase for sigma -->
+ <filter class="solr.GreekLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+ <filter class="solr.GreekStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Spanish -->
+ <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
+ <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+ <filter class="solr.SpanishLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Basque -->
+ <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
+ <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Persian -->
+ <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
+ <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <!-- for ZWNJ -->
+ <charFilter class="solr.PersianCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.PersianNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Finnish -->
+ <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
+ <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+ <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- French -->
+ <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
+ <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+ <filter class="solr.FrenchLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Irish -->
+ <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
+ <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes d', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+ <!-- removes n-, etc. position increments is intentionally false! -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+ <filter class="solr.IrishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Galician -->
+ <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
+ <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+ <filter class="solr.GalicianStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Hindi -->
+ <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
+ <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- normalizes unicode representation -->
+ <filter class="solr.IndicNormalizationFilterFactory"/>
+ <!-- normalizes variation in spelling -->
+ <filter class="solr.HindiNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+ <filter class="solr.HindiStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Hungarian -->
+ <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
+ <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Armenian -->
+ <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
+ <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Indonesian -->
+ <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
+ <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+ <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+ <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Italian -->
+ <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
+ <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+ <filter class="solr.ItalianLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+ NOTE: If you want to optimize search for precision, use default operator AND in your request
+ handler config (q.op) Use OR if you would like to optimize for recall (default).
+ -->
+ <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
+ <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+ <analyzer>
+ <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+ Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
+ is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+ Valid values for attribute mode are:
+ normal: regular segmentation
+ search: segmentation useful for search with synonyms compounds (default)
+ extended: same as search mode, but unigrams unknown words (experimental)
+
+ For some applications it might be good to use search mode for indexing and normal mode for
+ queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+ Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+ Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+ model with your own entries for segmentation, part-of-speech tags and readings without a need
+ to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+ User dictionary attributes are:
+ userDictionary: user dictionary filename
+ userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+ See lang/userdict_ja.txt for a sample user dictionary file.
+
+ Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
+
+ See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+ -->
+ <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+ <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+ <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+ <filter class="solr.JapaneseBaseFormFilterFactory"/>
+ <!-- Removes tokens with certain part-of-speech tags -->
+ <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+ <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+ <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+ <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+ <!-- Lower-cases romaji characters -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Latvian -->
+ <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
+ <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+ <filter class="solr.LatvianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Dutch -->
+ <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
+ <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+ <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Norwegian -->
+ <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
+ <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+ <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+ <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Portuguese -->
+ <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
+ <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+ <filter class="solr.PortugueseLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+ <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Romanian -->
+ <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
+ <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Russian -->
+ <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
+ <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+ <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Swedish -->
+ <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
+ <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+ <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Thai -->
+ <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
+ <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.ThaiTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Turkish -->
+ <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
+ <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.TurkishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Similarity is the scoring routine for each document vs. a query.
+ A custom Similarity or SimilarityFactory may be specified here, but
+ the default is fine for most applications.
+ For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+ -->
+ <!--
+ <similarity class="com.example.solr.CustomSimilarityFactory">
+ <str name="paramkey">param value</str>
+ </similarity>
+ -->
+
+</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/params.json
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/params.json b/solr/server/solr/configsets/_default/conf/params.json
new file mode 100644
index 0000000..06114ef
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/params.json
@@ -0,0 +1,20 @@
+{"params":{
+ "query":{
+ "defType":"edismax",
+ "q.alt":"*:*",
+ "rows":"10",
+ "fl":"*,score",
+ "":{"v":0}
+ },
+ "facets":{
+ "facet":"on",
+ "facet.mincount": "1",
+ "":{"v":0}
+ },
+ "velocity":{
+ "wt": "velocity",
+ "v.template":"browse",
+ "v.layout": "layout",
+ "":{"v":0}
+ }
+}}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/protwords.txt b/solr/server/solr/configsets/_default/conf/protwords.txt
new file mode 100644
index 0000000..1dfc0ab
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/protwords.txt
@@ -0,0 +1,21 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+# Use a protected word file to protect against the stemmer reducing two
+# unrelated words to the same base word.
+
+# Some non-words that normally won't be encountered,
+# just to test that they won't be stemmed.
+dontstems
+zwhacky
+
[35/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-4646: eDismax
lowercaseOperators now defaults to "false" for luceneMatchVersion >= 7.0.0
Posted by sh...@apache.org.
SOLR-4646: eDismax lowercaseOperators now defaults to "false" for luceneMatchVersion >= 7.0.0
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/8648b005
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/8648b005
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/8648b005
Branch: refs/heads/feature/autoscaling
Commit: 8648b005e28d24b7e18726502ae1ea5fffa44a5c
Parents: 39dfb78
Author: Jan Høydahl <ja...@apache.org>
Authored: Tue Jun 20 13:39:36 2017 +0200
Committer: Jan Høydahl <ja...@apache.org>
Committed: Tue Jun 20 13:39:36 2017 +0200
----------------------------------------------------------------------
solr/CHANGES.txt | 5 +++++
.../org/apache/solr/search/ExtendedDismaxQParser.java | 7 +++++--
.../org/apache/solr/search/TestExtendedDismaxParser.java | 10 +++++++++-
.../src/the-extended-dismax-query-parser.adoc | 1 +
solr/webapp/web/js/angular/controllers/query.js | 2 +-
5 files changed, 21 insertions(+), 4 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/8648b005/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 9267039..a201d1e 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -102,6 +102,9 @@ Upgrading from Solr 6.x
curl http://host:8983/solr/mycollection/config -d '{"set-user-property": {"update.autoCreateFields":"false"}}'
Please see SOLR-10574 for details.
+* The default for eDismax parameter 'lowercaseOperators' now depends on the luceneMatchVersion setting in solrconfig.
+ It remains 'true' for luceneMatchVersion < 7.0.0 and changes to 'false' from 7.0.0. See also SOLR-4646
+
New Features
----------------------
* SOLR-9857, SOLR-9858: Collect aggregated metrics from nodes and shard leaders in overseer. (ab)
@@ -293,6 +296,8 @@ Other Changes
* SOLR-9623: Disable remote streaming in example configs by default. Adjust Upload Limit defaults (janhoy, yonik)
+* SOLR-4646: eDismax lowercaseOperators now defaults to "false" for luceneMatchVersion >= 7.0.0 (janhoy, David Smiley)
+
================== 6.7.0 ==================
Consult the LUCENE_CHANGES.txt file for additional, low level, changes in this release.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/8648b005/solr/core/src/java/org/apache/solr/search/ExtendedDismaxQParser.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/search/ExtendedDismaxQParser.java b/solr/core/src/java/org/apache/solr/search/ExtendedDismaxQParser.java
index a68836c..9ec07e8 100644
--- a/solr/core/src/java/org/apache/solr/search/ExtendedDismaxQParser.java
+++ b/solr/core/src/java/org/apache/solr/search/ExtendedDismaxQParser.java
@@ -46,6 +46,7 @@ import org.apache.lucene.search.MatchAllDocsQuery;
import org.apache.lucene.search.MultiPhraseQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
+import org.apache.lucene.util.Version;
import org.apache.solr.analysis.TokenizerChain;
import org.apache.solr.common.params.DisMaxParams;
import org.apache.solr.common.params.SolrParams;
@@ -1703,8 +1704,10 @@ public class ExtendedDismaxQParser extends QParser {
mmAutoRelax = solrParams.getBool(DMP.MM_AUTORELAX, false);
altQ = solrParams.get( DisMaxParams.ALTQ );
-
- lowercaseOperators = solrParams.getBool(DMP.LOWERCASE_OPS, true);
+
+ // lowercaseOperators defaults to true for luceneMatchVersion < 7.0 and to false for >= 7.0
+ lowercaseOperators = solrParams.getBool(DMP.LOWERCASE_OPS,
+ !req.getCore().getSolrConfig().luceneMatchVersion.onOrAfter(Version.LUCENE_7_0_0));
/* * * Boosting Query * * */
boostParams = solrParams.getParams(DisMaxParams.BQ);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/8648b005/solr/core/src/test/org/apache/solr/search/TestExtendedDismaxParser.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/search/TestExtendedDismaxParser.java b/solr/core/src/test/org/apache/solr/search/TestExtendedDismaxParser.java
index 46bebb3..0dc327d 100644
--- a/solr/core/src/test/org/apache/solr/search/TestExtendedDismaxParser.java
+++ b/solr/core/src/test/org/apache/solr/search/TestExtendedDismaxParser.java
@@ -189,6 +189,14 @@ public class TestExtendedDismaxParser extends SolrTestCaseJ4 {
"defType", "edismax")
, "*[count(//doc)=0]");
+ assertQ("The default for lowercaseOperators should not allow lower case and",
+ req("q", "Zapp and Brannigan",
+ "qf", "name",
+ "q.op", "AND",
+ "sow", sow,
+ "defType", "edismax")
+ , "*[count(//doc)=0]");
+
assertQ("Lower case operator, allow lower case operators",
req("q", "Zapp and Brannigan",
"qf", "name",
@@ -284,7 +292,7 @@ public class TestExtendedDismaxParser extends SolrTestCaseJ4 {
"q","Order AND op"), oner
);
assertQ(req("defType", "edismax", "qf", "name title subject text",
- "q","Order and op"), oner
+ "q","Order and op"), twor
);
assertQ(req("defType", "edismax", "qf", "name title subject text",
"q","+Order op"), oner
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/8648b005/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc b/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc
index c0fdcae..e949a61 100644
--- a/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc
+++ b/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc
@@ -59,6 +59,7 @@ A multivalued list of strings parsed as queries with scores multiplied by the sc
=== The lowercaseOperators Parameter
A Boolean parameter indicating if lowercase "and" and "or" should be treated the same as operators "AND" and "OR".
+Defaults to `false`.
[[TheExtendedDisMaxQueryParser-ThepsParameter]]
=== The ps Parameter
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/8648b005/solr/webapp/web/js/angular/controllers/query.js
----------------------------------------------------------------------
diff --git a/solr/webapp/web/js/angular/controllers/query.js b/solr/webapp/web/js/angular/controllers/query.js
index 5dd105b..3a44cbd 100644
--- a/solr/webapp/web/js/angular/controllers/query.js
+++ b/solr/webapp/web/js/angular/controllers/query.js
@@ -23,7 +23,7 @@ solrAdminApp.controller('QueryController',
$scope.query = {wt: 'json', q:'*:*', indent:'on'};
$scope.filters = [{fq:""}];
$scope.dismax = {defType: "dismax"};
- $scope.edismax = {defType: "edismax", stopwords: true, lowercaseOperators: true};
+ $scope.edismax = {defType: "edismax", stopwords: true, lowercaseOperators: false};
$scope.hl = {hl:"on"};
$scope.facet = {facet: "on"};
$scope.spatial = {};
[19/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-9989: Add
support for PointFields in FacetModule (JSON Facets)
Posted by sh...@apache.org.
SOLR-9989: Add support for PointFields in FacetModule (JSON Facets)
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/294026ff
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/294026ff
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/294026ff
Branch: refs/heads/feature/autoscaling
Commit: 294026ffa8bbef46b65e4a517fa018ae1250903a
Parents: 3ff8c87
Author: Cao Manh Dat <da...@apache.org>
Authored: Tue Jun 20 10:42:59 2017 +0700
Committer: Cao Manh Dat <da...@apache.org>
Committed: Tue Jun 20 10:42:59 2017 +0700
----------------------------------------------------------------------
solr/CHANGES.txt | 1 +
.../apache/solr/search/facet/FacetField.java | 6 +-
.../facet/FacetFieldProcessorByHashDV.java | 33 +++++++-
.../apache/solr/search/facet/FacetRange.java | 16 +++-
.../org/apache/solr/search/facet/FieldUtil.java | 6 ++
.../org/apache/solr/search/facet/HLLAgg.java | 83 ++++++++++++++++----
.../org/apache/solr/search/facet/UniqueAgg.java | 76 ++++++++++++++----
.../solr/search/facet/TestJsonFacets.java | 6 +-
8 files changed, 186 insertions(+), 41 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/294026ff/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index c65db37..15b86a2 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -147,6 +147,7 @@ New Features
* SOLR-10433: CollectionAdmin requests in SolrJ to support V2 calls (noble)
+* SOLR-9989: Add support for PointFields in FacetModule (JSON Facets) (Cao Manh Dat)
Bug Fixes
----------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/294026ff/solr/core/src/java/org/apache/solr/search/facet/FacetField.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/search/facet/FacetField.java b/solr/core/src/java/org/apache/solr/search/facet/FacetField.java
index 42f791c..f4f9b14 100644
--- a/solr/core/src/java/org/apache/solr/search/facet/FacetField.java
+++ b/solr/core/src/java/org/apache/solr/search/facet/FacetField.java
@@ -122,7 +122,7 @@ public class FacetField extends FacetRequestSorted {
method = FacetMethod.STREAM;
}
if (method == FacetMethod.STREAM && sf.indexed() &&
- "index".equals(sortVariable) && sortDirection == SortDirection.asc) {
+ "index".equals(sortVariable) && sortDirection == SortDirection.asc && !ft.isPointField()) {
return new FacetFieldProcessorByEnumTermsStream(fcontext, this, sf);
}
@@ -142,6 +142,10 @@ public class FacetField extends FacetRequestSorted {
}
}
+ if (sf.hasDocValues() && sf.getType().isPointField()) {
+ return new FacetFieldProcessorByHashDV(fcontext, this, sf);
+ }
+
// multi-valued after this point
if (sf.hasDocValues() || method == FacetMethod.DV) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/294026ff/solr/core/src/java/org/apache/solr/search/facet/FacetFieldProcessorByHashDV.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/search/facet/FacetFieldProcessorByHashDV.java b/solr/core/src/java/org/apache/solr/search/facet/FacetFieldProcessorByHashDV.java
index 71ff690..4237c31 100644
--- a/solr/core/src/java/org/apache/solr/search/facet/FacetFieldProcessorByHashDV.java
+++ b/solr/core/src/java/org/apache/solr/search/facet/FacetFieldProcessorByHashDV.java
@@ -27,6 +27,7 @@ import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.MultiDocValues;
import org.apache.lucene.index.NumericDocValues;
import org.apache.lucene.index.SortedDocValues;
+import org.apache.lucene.index.SortedNumericDocValues;
import org.apache.lucene.search.SimpleCollector;
import org.apache.lucene.util.BitUtil;
import org.apache.lucene.util.BytesRef;
@@ -200,7 +201,8 @@ class FacetFieldProcessorByHashDV extends FacetFieldProcessor {
FieldInfo fieldInfo = fcontext.searcher.getSlowAtomicReader().getFieldInfos().fieldInfo(sf.getName());
if (fieldInfo != null &&
fieldInfo.getDocValuesType() != DocValuesType.NUMERIC &&
- fieldInfo.getDocValuesType() != DocValuesType.SORTED) {
+ fieldInfo.getDocValuesType() != DocValuesType.SORTED &&
+ fieldInfo.getDocValuesType() != DocValuesType.SORTED_NUMERIC) {
throw new SolrException(SolrException.ErrorCode.BAD_REQUEST,
getClass()+" only support single valued number/string with docValues");
}
@@ -370,8 +372,32 @@ class FacetFieldProcessorByHashDV extends FacetFieldProcessor {
} else { // Numeric:
- // TODO support SortedNumericDocValues
- DocSetUtil.collectSortedDocSet(fcontext.base, fcontext.searcher.getIndexReader(), new SimpleCollector() {
+ if (sf.multiValued()) {
+ DocSetUtil.collectSortedDocSet(fcontext.base, fcontext.searcher.getIndexReader(), new SimpleCollector() {
+ SortedNumericDocValues values = null; //NN
+
+ @Override public boolean needsScores() { return false; }
+
+ @Override
+ protected void doSetNextReader(LeafReaderContext ctx) throws IOException {
+ setNextReaderFirstPhase(ctx);
+ values = DocValues.getSortedNumeric(ctx.reader(), sf.getName());
+ }
+
+ @Override
+ public void collect(int segDoc) throws IOException {
+ if (segDoc > values.docID()) {
+ values.advance(segDoc);
+ }
+ if (segDoc == values.docID()) {
+ for (int i = 0; i < values.docValueCount(); i++) {
+ collectValFirstPhase(segDoc, values.nextValue());
+ }
+ }
+ }
+ });
+ } else {
+ DocSetUtil.collectSortedDocSet(fcontext.base, fcontext.searcher.getIndexReader(), new SimpleCollector() {
NumericDocValues values = null; //NN
@Override public boolean needsScores() { return false; }
@@ -392,6 +418,7 @@ class FacetFieldProcessorByHashDV extends FacetFieldProcessor {
}
}
});
+ }
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/294026ff/solr/core/src/java/org/apache/solr/search/facet/FacetRange.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/search/facet/FacetRange.java b/solr/core/src/java/org/apache/solr/search/facet/FacetRange.java
index f627348..5bd8899 100644
--- a/solr/core/src/java/org/apache/solr/search/facet/FacetRange.java
+++ b/solr/core/src/java/org/apache/solr/search/facet/FacetRange.java
@@ -177,7 +177,7 @@ class FacetRangeProcessor extends FacetProcessor<FacetRange> {
private SimpleOrderedMap<Object> getRangeCounts() throws IOException {
final FieldType ft = sf.getType();
- if (ft instanceof TrieField) {
+ if (ft instanceof TrieField || ft.isPointField()) {
switch (ft.getNumberType()) {
case FLOAT:
calc = new FloatCalc(sf);
@@ -490,7 +490,11 @@ class FacetRangeProcessor extends FacetProcessor<FacetRange> {
@Override
public Comparable bitsToValue(long bits) {
- return Float.intBitsToFloat( (int)bits );
+ if (field.getType().isPointField() && field.multiValued()) {
+ return NumericUtils.sortableIntToFloat((int)bits);
+ } else {
+ return Float.intBitsToFloat( (int)bits );
+ }
}
@Override
@@ -511,7 +515,11 @@ class FacetRangeProcessor extends FacetProcessor<FacetRange> {
private static class DoubleCalc extends Calc {
@Override
public Comparable bitsToValue(long bits) {
- return Double.longBitsToDouble(bits);
+ if (field.getType().isPointField() && field.multiValued()) {
+ return NumericUtils.sortableLongToDouble(bits);
+ } else {
+ return Double.longBitsToDouble(bits);
+ }
}
@Override
@@ -563,7 +571,7 @@ class FacetRangeProcessor extends FacetProcessor<FacetRange> {
final Date now) {
super(f);
this.now = now;
- if (! (field.getType() instanceof TrieDateField) ) {
+ if (! (field.getType() instanceof TrieDateField) && !(field.getType().isPointField()) ) {
throw new IllegalArgumentException("SchemaField must use field type extending TrieDateField or DateRangeField");
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/294026ff/solr/core/src/java/org/apache/solr/search/facet/FieldUtil.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/search/facet/FieldUtil.java b/solr/core/src/java/org/apache/solr/search/facet/FieldUtil.java
index 389b6d7..10a3d2e 100644
--- a/solr/core/src/java/org/apache/solr/search/facet/FieldUtil.java
+++ b/solr/core/src/java/org/apache/solr/search/facet/FieldUtil.java
@@ -19,6 +19,7 @@ package org.apache.solr.search.facet;
import java.io.IOException;
import org.apache.lucene.index.DocValues;
+import org.apache.lucene.index.NumericDocValues;
import org.apache.lucene.index.SortedDocValues;
import org.apache.lucene.index.SortedSetDocValues;
import org.apache.lucene.search.DocIdSetIterator;
@@ -55,6 +56,11 @@ public class FieldUtil {
return si == null ? DocValues.emptySortedSet() : si;
}
+ public static NumericDocValues getNumericDocValues(QueryContext context, SchemaField field, QParser qparser) throws IOException {
+ SolrIndexSearcher searcher = context.searcher();
+ NumericDocValues si = searcher.getSlowAtomicReader().getNumericDocValues(field.getName());
+ return si == null ? DocValues.emptyNumeric() : si;
+ }
/** The following ord visitors and wrappers are a work in progress and experimental
* @lucene.experimental */
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/294026ff/solr/core/src/java/org/apache/solr/search/facet/HLLAgg.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/search/facet/HLLAgg.java b/solr/core/src/java/org/apache/solr/search/facet/HLLAgg.java
index 0bd1d84..3c55329 100644
--- a/solr/core/src/java/org/apache/solr/search/facet/HLLAgg.java
+++ b/solr/core/src/java/org/apache/solr/search/facet/HLLAgg.java
@@ -17,6 +17,9 @@
package org.apache.solr.search.facet;
import java.io.IOException;
+
+import org.apache.lucene.index.SortedNumericDocValues;
+import org.apache.lucene.search.DocIdSetIterator;
import org.apache.solr.util.hll.HLL;
import org.apache.solr.util.hll.HLLType;
import org.apache.lucene.index.DocValues;
@@ -51,7 +54,9 @@ public class HLLAgg extends StrAggValueSource {
public SlotAcc createSlotAcc(FacetContext fcontext, int numDocs, int numSlots) throws IOException {
SchemaField sf = fcontext.qcontext.searcher().getSchema().getField(getArg());
if (sf.multiValued() || sf.getType().multiValuedFieldCache()) {
- if (sf.hasDocValues()) {
+ if (sf.getType().isPointField()) {
+ return new SortedNumericAcc(fcontext, getArg(), numSlots);
+ } else if (sf.hasDocValues()) {
return new UniqueMultiDvSlotAcc(fcontext, sf, numSlots, fcontext.isShard() ? factory : null);
} else {
return new UniqueMultivaluedSlotAcc(fcontext, sf, numSlots, fcontext.isShard() ? factory : null);
@@ -114,12 +119,11 @@ public class HLLAgg extends StrAggValueSource {
// TODO: hybrid model for non-distrib numbers?
// todo - better efficiency for sorting?
- class NumericAcc extends SlotAcc {
+ abstract class BaseNumericAcc extends SlotAcc {
SchemaField sf;
HLL[] sets;
- NumericDocValues values;
- public NumericAcc(FacetContext fcontext, String field, int numSlots) throws IOException {
+ public BaseNumericAcc(FacetContext fcontext, String field, int numSlots) throws IOException {
super(fcontext);
sf = fcontext.searcher.getSchema().getField(field);
sets = new HLL[numSlots];
@@ -136,32 +140,27 @@ public class HLLAgg extends StrAggValueSource {
}
@Override
- public void setNextReader(LeafReaderContext readerContext) throws IOException {
- values = DocValues.getNumeric(readerContext.reader(), sf.getName());
- }
-
- @Override
public void collect(int doc, int slot) throws IOException {
- int valuesDocID = values.docID();
+ int valuesDocID = docIdSetIterator().docID();
if (valuesDocID < doc) {
- valuesDocID = values.advance(doc);
+ valuesDocID = docIdSetIterator().advance(doc);
}
if (valuesDocID > doc) {
return;
}
assert valuesDocID == doc;
- long val = values.longValue();
-
- long hash = Hash.fmix64(val);
-
HLL hll = sets[slot];
if (hll == null) {
hll = sets[slot] = factory.getHLL();
}
- hll.addRaw(hash);
+ collectValues(doc, hll);
}
+ protected abstract DocIdSetIterator docIdSetIterator();
+
+ protected abstract void collectValues(int doc, HLL hll) throws IOException;
+
@Override
public Object getValue(int slot) throws IOException {
if (fcontext.isShard()) {
@@ -191,5 +190,57 @@ public class HLLAgg extends StrAggValueSource {
}
+ class NumericAcc extends BaseNumericAcc {
+ NumericDocValues values;
+
+ public NumericAcc(FacetContext fcontext, String field, int numSlots) throws IOException {
+ super(fcontext, field, numSlots);
+ }
+
+ @Override
+ public void setNextReader(LeafReaderContext readerContext) throws IOException {
+ values = DocValues.getNumeric(readerContext.reader(), sf.getName());
+ }
+
+ @Override
+ protected DocIdSetIterator docIdSetIterator() {
+ return values;
+ }
+
+ @Override
+ protected void collectValues(int doc, HLL hll) throws IOException {
+ long val = values.longValue();
+ long hash = Hash.fmix64(val);
+ hll.addRaw(hash);
+ }
+ }
+
+ class SortedNumericAcc extends BaseNumericAcc {
+ SortedNumericDocValues values;
+
+ public SortedNumericAcc(FacetContext fcontext, String field, int numSlots) throws IOException {
+ super(fcontext, field, numSlots);
+ }
+
+ @Override
+ public void setNextReader(LeafReaderContext readerContext) throws IOException {
+ values = DocValues.getSortedNumeric(readerContext.reader(), sf.getName());
+ }
+
+ @Override
+ protected DocIdSetIterator docIdSetIterator() {
+ return values;
+ }
+
+ @Override
+ protected void collectValues(int doc, HLL hll) throws IOException {
+ for (int i = 0; i < values.docValueCount(); i++) {
+ long val = values.nextValue();
+ long hash = Hash.fmix64(val);
+ hll.addRaw(hash);
+ }
+ }
+ }
+
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/294026ff/solr/core/src/java/org/apache/solr/search/facet/UniqueAgg.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/search/facet/UniqueAgg.java b/solr/core/src/java/org/apache/solr/search/facet/UniqueAgg.java
index 4775e5f..dba410a 100644
--- a/solr/core/src/java/org/apache/solr/search/facet/UniqueAgg.java
+++ b/solr/core/src/java/org/apache/solr/search/facet/UniqueAgg.java
@@ -25,6 +25,8 @@ import java.util.Set;
import org.apache.lucene.index.DocValues;
import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.NumericDocValues;
+import org.apache.lucene.index.SortedNumericDocValues;
+import org.apache.lucene.search.DocIdSetIterator;
import org.apache.solr.common.util.SimpleOrderedMap;
import org.apache.solr.schema.SchemaField;
@@ -42,7 +44,9 @@ public class UniqueAgg extends StrAggValueSource {
public SlotAcc createSlotAcc(FacetContext fcontext, int numDocs, int numSlots) throws IOException {
SchemaField sf = fcontext.qcontext.searcher().getSchema().getField(getArg());
if (sf.multiValued() || sf.getType().multiValuedFieldCache()) {
- if (sf.hasDocValues()) {
+ if (sf.getType().isPointField()) {
+ return new SortedNumericAcc(fcontext, getArg(), numSlots);
+ } else if (sf.hasDocValues()) {
return new UniqueMultiDvSlotAcc(fcontext, sf, numSlots, null);
} else {
return new UniqueMultivaluedSlotAcc(fcontext, sf, numSlots, null);
@@ -187,12 +191,11 @@ public class UniqueAgg extends StrAggValueSource {
}
- static class NumericAcc extends SlotAcc {
+ static abstract class BaseNumericAcc extends SlotAcc {
SchemaField sf;
LongSet[] sets;
- NumericDocValues values;
- public NumericAcc(FacetContext fcontext, String field, int numSlots) throws IOException {
+ public BaseNumericAcc(FacetContext fcontext, String field, int numSlots) throws IOException {
super(fcontext);
sf = fcontext.searcher.getSchema().getField(field);
sets = new LongSet[numSlots];
@@ -209,30 +212,27 @@ public class UniqueAgg extends StrAggValueSource {
}
@Override
- public void setNextReader(LeafReaderContext readerContext) throws IOException {
- values = DocValues.getNumeric(readerContext.reader(), sf.getName());
- }
-
- @Override
public void collect(int doc, int slot) throws IOException {
- int valuesDocID = values.docID();
+ int valuesDocID = docIdSetIterator().docID();
if (valuesDocID < doc) {
- valuesDocID = values.advance(doc);
+ valuesDocID = docIdSetIterator().advance(doc);
}
if (valuesDocID > doc) {
// missing
return;
}
- long val = values.longValue();
LongSet set = sets[slot];
if (set == null) {
set = sets[slot] = new LongSet(16);
}
- // TODO: could handle 0s at this level too
- set.add(val);
+ collectValues(doc, set);
}
+ protected abstract DocIdSetIterator docIdSetIterator();
+
+ protected abstract void collectValues(int doc, LongSet set) throws IOException;
+
@Override
public Object getValue(int slot) throws IOException {
if (fcontext.isShard()) {
@@ -283,5 +283,53 @@ public class UniqueAgg extends StrAggValueSource {
}
+ static class NumericAcc extends BaseNumericAcc {
+ NumericDocValues values;
+
+ public NumericAcc(FacetContext fcontext, String field, int numSlots) throws IOException {
+ super(fcontext, field, numSlots);
+ }
+
+ @Override
+ protected DocIdSetIterator docIdSetIterator() {
+ return values;
+ }
+
+ @Override
+ public void setNextReader(LeafReaderContext readerContext) throws IOException {
+ values = DocValues.getNumeric(readerContext.reader(), sf.getName());
+ }
+
+ @Override
+ protected void collectValues(int doc, LongSet set) throws IOException {
+ set.add(values.longValue());
+ }
+ }
+
+ static class SortedNumericAcc extends BaseNumericAcc {
+ SortedNumericDocValues values;
+
+ public SortedNumericAcc(FacetContext fcontext, String field, int numSlots) throws IOException {
+ super(fcontext, field, numSlots);
+ }
+
+ @Override
+ protected DocIdSetIterator docIdSetIterator() {
+ return values;
+ }
+
+ @Override
+ public void setNextReader(LeafReaderContext readerContext) throws IOException {
+ values = DocValues.getSortedNumeric(readerContext.reader(), sf.getName());
+ }
+
+ @Override
+ protected void collectValues(int doc, LongSet set) throws IOException {
+ for (int i = 0; i < values.docValueCount(); i++) {
+ set.add(values.nextValue());
+ }
+ }
+ }
+
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/294026ff/solr/core/src/test/org/apache/solr/search/facet/TestJsonFacets.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/search/facet/TestJsonFacets.java b/solr/core/src/test/org/apache/solr/search/facet/TestJsonFacets.java
index 2f73b50..57b3b9e 100644
--- a/solr/core/src/test/org/apache/solr/search/facet/TestJsonFacets.java
+++ b/solr/core/src/test/org/apache/solr/search/facet/TestJsonFacets.java
@@ -35,7 +35,6 @@ import org.apache.lucene.util.LuceneTestCase;
import org.apache.solr.JSONTestUtil;
import org.apache.solr.SolrTestCaseHS;
import org.apache.solr.common.SolrInputDocument;
-import org.apache.solr.SolrTestCaseJ4.SuppressPointFields;
import org.apache.solr.common.params.ModifiableSolrParams;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.request.macro.MacroExpander;
@@ -44,7 +43,6 @@ import org.junit.BeforeClass;
import org.junit.Test;
@LuceneTestCase.SuppressCodecs({"Lucene3x","Lucene40","Lucene41","Lucene42","Lucene45","Appending"})
-@SuppressPointFields
public class TestJsonFacets extends SolrTestCaseHS {
private static SolrInstances servers; // for distributed testing
@@ -87,7 +85,9 @@ public class TestJsonFacets extends SolrTestCaseHS {
@ParametersFactory
public static Iterable<Object[]> parameters() {
// wrap each enum val in an Object[] and return as Iterable
- return () -> Arrays.stream(FacetField.FacetMethod.values()).map(it -> new Object[]{it}).iterator();
+ return () -> Arrays.stream(FacetField.FacetMethod.values())
+ .filter(m -> m == FacetField.FacetMethod.ENUM)
+ .map(it -> new Object[]{it}).iterator();
}
public TestJsonFacets(FacetField.FacetMethod defMethod) {
[16/50] [abbrv] lucene-solr:feature/autoscaling: SOLR:10779:
JavaBinCodec should use close consistently rather than having marshal() and
close() call finish() (which closes the underlying stream)
Posted by sh...@apache.org.
SOLR:10779: JavaBinCodec should use close consistently rather than having marshal() and close() call finish() (which closes the underlying stream)
commit b31178e0c33dbfe81fbc1aec705b3dae3cc895ad
Author: Erick <er...@apache.org>
Date: Sun Jun 18 22:34:21 2017 -0700
SOLR-10779: JavaBinCodec should use close consistently rather than having marshal() and close() call finish() (which closes the underlying stream)
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/64093d6d
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/64093d6d
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/64093d6d
Branch: refs/heads/feature/autoscaling
Commit: 64093d6df10a426551a0aeb4c157f9e05e5bf7bf
Parents: 943bf5a
Author: Erick <er...@apache.org>
Authored: Sun Jun 18 22:35:57 2017 -0700
Committer: Erick <er...@apache.org>
Committed: Sun Jun 18 22:35:57 2017 -0700
----------------------------------------------------------------------
solr/CHANGES.txt | 3 +
.../solr/response/BinaryResponseWriter.java | 12 ++-
.../java/org/apache/solr/search/CursorMark.java | 21 ++---
.../solr/response/TestBinaryResponseWriter.java | 5 +-
.../response/TestJavabinTupleStreamParser.java | 20 +++--
.../apache/solr/response/TestPushWriter.java | 8 +-
.../transform/TestSubQueryTransformer.java | 28 +++---
.../apache/solr/update/AddBlockUpdateTest.java | 10 ++-
.../impl/StreamingBinaryResponseParser.java | 5 +-
.../request/JavaBinUpdateRequestCodec.java | 12 +--
.../apache/solr/common/util/JavaBinCodec.java | 17 ++--
.../solr/common/util/TestJavaBinCodec.java | 95 ++++++++++----------
.../solr/common/util/TestNamedListCodec.java | 57 +++++++-----
13 files changed, 160 insertions(+), 133 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 82e2033..c65db37 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -277,6 +277,9 @@ Other Changes
* SOLR-10800: Factor out HttpShardHandler.transformReplicasToShardUrls from HttpShardHandler.prepDistributed.
(Domenico Fabio Marino, Christine Poerschke)
+* SOLR-10779: JavaBinCodec should use close consistently rather than having marshal() and close() call finish()
+ (which closes the underlying stream). (Erick Erickson)
+
================== 6.7.0 ==================
Consult the LUCENE_CHANGES.txt file for additional, low level, changes in this release.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/core/src/java/org/apache/solr/response/BinaryResponseWriter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/response/BinaryResponseWriter.java b/solr/core/src/java/org/apache/solr/response/BinaryResponseWriter.java
index 11c6074..b841a03 100644
--- a/solr/core/src/java/org/apache/solr/response/BinaryResponseWriter.java
+++ b/solr/core/src/java/org/apache/solr/response/BinaryResponseWriter.java
@@ -48,7 +48,9 @@ public class BinaryResponseWriter implements BinaryQueryResponseWriter {
public void write(OutputStream out, SolrQueryRequest req, SolrQueryResponse response) throws IOException {
Resolver resolver = new Resolver(req, response.getReturnFields());
if (req.getParams().getBool(CommonParams.OMIT_HEADER, false)) response.removeResponseHeader();
- new JavaBinCodec(resolver).setWritableDocFields(resolver).marshal(response.getValues(), out);
+ try (JavaBinCodec jbc = new JavaBinCodec(resolver)) {
+ jbc.setWritableDocFields(resolver).marshal(response.getValues(), out);
+ }
}
@Override
@@ -160,10 +162,14 @@ public class BinaryResponseWriter implements BinaryQueryResponseWriter {
Resolver resolver = new Resolver(req, rsp.getReturnFields());
ByteArrayOutputStream out = new ByteArrayOutputStream();
- new JavaBinCodec(resolver).setWritableDocFields(resolver).marshal(rsp.getValues(), out);
+ try (JavaBinCodec jbc = new JavaBinCodec(resolver)) {
+ jbc.setWritableDocFields(resolver).marshal(rsp.getValues(), out);
+ }
InputStream in = out.toInputStream();
- return (NamedList<Object>) new JavaBinCodec(resolver).unmarshal(in);
+ try (JavaBinCodec jbc = new JavaBinCodec(resolver)) {
+ return (NamedList<Object>) jbc.unmarshal(in);
+ }
}
catch (Exception ex) {
throw new RuntimeException(ex);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/core/src/java/org/apache/solr/search/CursorMark.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/search/CursorMark.java b/solr/core/src/java/org/apache/solr/search/CursorMark.java
index 38fced5..2a63da5 100644
--- a/solr/core/src/java/org/apache/solr/search/CursorMark.java
+++ b/solr/core/src/java/org/apache/solr/search/CursorMark.java
@@ -183,9 +183,8 @@ public final class CursorMark {
List<Object> pieces = null;
try {
final byte[] rawData = Base64.base64ToByteArray(serialized);
- ByteArrayInputStream in = new ByteArrayInputStream(rawData);
- try {
- pieces = (List<Object>) new JavaBinCodec().unmarshal(in);
+ try (JavaBinCodec jbc = new JavaBinCodec(); ByteArrayInputStream in = new ByteArrayInputStream(rawData)){
+ pieces = (List<Object>) jbc.unmarshal(in);
boolean b = false;
for (Object o : pieces) {
if (o instanceof BytesRefBuilder || o instanceof BytesRef || o instanceof String) {
@@ -196,8 +195,6 @@ public final class CursorMark {
in.reset();
pieces = (List<Object>) new JavaBinCodec().unmarshal(in);
}
- } finally {
- in.close();
}
} catch (Exception ex) {
throw new SolrException(ErrorCode.BAD_REQUEST,
@@ -259,19 +256,13 @@ public final class CursorMark {
// the type/name/dir from the SortFields (or a hashCode to act as a checksum)
// could help provide more validation beyond just the number of clauses.
- try {
- ByteArrayOutputStream out = new ByteArrayOutputStream(256);
- try {
- new JavaBinCodec().marshal(marshalledValues, out);
- byte[] rawData = out.toByteArray();
- return Base64.byteArrayToBase64(rawData, 0, rawData.length);
- } finally {
- out.close();
- }
+ try (JavaBinCodec jbc = new JavaBinCodec(); ByteArrayOutputStream out = new ByteArrayOutputStream(256)) {
+ jbc.marshal(marshalledValues, out);
+ byte[] rawData = out.toByteArray();
+ return Base64.byteArrayToBase64(rawData, 0, rawData.length);
} catch (Exception ex) {
throw new SolrException(ErrorCode.SERVER_ERROR,
"Unable to format search after totem", ex);
-
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/core/src/test/org/apache/solr/response/TestBinaryResponseWriter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/response/TestBinaryResponseWriter.java b/solr/core/src/test/org/apache/solr/response/TestBinaryResponseWriter.java
index 05bf153..ae85d52 100644
--- a/solr/core/src/test/org/apache/solr/response/TestBinaryResponseWriter.java
+++ b/solr/core/src/test/org/apache/solr/response/TestBinaryResponseWriter.java
@@ -60,7 +60,10 @@ public class TestBinaryResponseWriter extends AbstractSolrTestCase {
BinaryQueryResponseWriter writer = (BinaryQueryResponseWriter) h.getCore().getQueryResponseWriter("javabin");
ByteArrayOutputStream baos = new ByteArrayOutputStream();
writer.write(baos, req, rsp);
- NamedList res = (NamedList) new JavaBinCodec().unmarshal(new ByteArrayInputStream(baos.toByteArray()));
+ NamedList res;
+ try (JavaBinCodec jbc = new JavaBinCodec()) {
+ res = (NamedList) jbc.unmarshal(new ByteArrayInputStream(baos.toByteArray()));
+ }
SolrDocumentList docs = (SolrDocumentList) res.get("response");
for (Object doc : docs) {
SolrDocument document = (SolrDocument) doc;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/core/src/test/org/apache/solr/response/TestJavabinTupleStreamParser.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/response/TestJavabinTupleStreamParser.java b/solr/core/src/test/org/apache/solr/response/TestJavabinTupleStreamParser.java
index d710446..2652314 100644
--- a/solr/core/src/test/org/apache/solr/response/TestJavabinTupleStreamParser.java
+++ b/solr/core/src/test/org/apache/solr/response/TestJavabinTupleStreamParser.java
@@ -169,15 +169,19 @@ public class TestJavabinTupleStreamParser extends SolrTestCaseJ4 {
public void testSolrDocumentList() throws IOException {
SolrQueryResponse response = new SolrQueryResponse();
SolrDocumentList l = constructSolrDocList(response);
- ByteArrayOutputStream baos = new ByteArrayOutputStream();
- new JavaBinCodec().marshal(response.getValues(), baos);
+ try (JavaBinCodec jbc = new JavaBinCodec(); ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
+ jbc.marshal(response.getValues(), baos);
+ }
byte[] bytes = serialize(response.getValues());
- Object o = new JavaBinCodec().unmarshal(new ByteArrayInputStream(bytes));
+ try (JavaBinCodec jbc = new JavaBinCodec()) {
+ jbc.unmarshal(new ByteArrayInputStream(bytes));
+ }
List list = new ArrayList<>();
Map m = null;
- JavabinTupleStreamParser parser = new JavabinTupleStreamParser(new ByteArrayInputStream(bytes), false);
- while ((m = parser.next()) != null) {
- list.add(m);
+ try (JavabinTupleStreamParser parser = new JavabinTupleStreamParser(new ByteArrayInputStream(bytes), false)) {
+ while ((m = parser.next()) != null) {
+ list.add(m);
+ }
}
assertEquals(l.size(), list.size());
for(int i =0;i<list.size();i++){
@@ -189,7 +193,9 @@ public class TestJavabinTupleStreamParser extends SolrTestCaseJ4 {
SolrQueryResponse response = new SolrQueryResponse();
response.getValues().add("results", o);
ByteArrayOutputStream baos = new ByteArrayOutputStream();
- new JavaBinCodec().marshal(response.getValues(), baos);
+ try (JavaBinCodec jbc = new JavaBinCodec()) {
+ jbc.marshal(response.getValues(), baos);
+ }
return baos.toByteArray();
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/core/src/test/org/apache/solr/response/TestPushWriter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/response/TestPushWriter.java b/solr/core/src/test/org/apache/solr/response/TestPushWriter.java
index 043fe92..9a02ee9 100644
--- a/solr/core/src/test/org/apache/solr/response/TestPushWriter.java
+++ b/solr/core/src/test/org/apache/solr/response/TestPushWriter.java
@@ -53,8 +53,12 @@ public class TestPushWriter extends SolrTestCaseJ4 {
log.info(new String(baos.toByteArray(), "UTF-8"));
Map m = (Map) Utils.fromJSON(baos.toByteArray());
checkValues(m);
- writeData(new JavaBinCodec(baos= new ByteArrayOutputStream(), null));
- m = (Map) new JavaBinCodec().unmarshal(new ByteArrayInputStream(baos.toByteArray()));
+ try (JavaBinCodec jbc = new JavaBinCodec(baos= new ByteArrayOutputStream(), null)) {
+ writeData(jbc);
+ try (JavaBinCodec jbcUn = new JavaBinCodec()) {
+ m = (Map) jbcUn.unmarshal(new ByteArrayInputStream(baos.toByteArray()));
+ }
+ }
checkValues(m);
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/core/src/test/org/apache/solr/response/transform/TestSubQueryTransformer.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/response/transform/TestSubQueryTransformer.java b/solr/core/src/test/org/apache/solr/response/transform/TestSubQueryTransformer.java
index e9af1cf..a9e5fa9 100644
--- a/solr/core/src/test/org/apache/solr/response/transform/TestSubQueryTransformer.java
+++ b/solr/core/src/test/org/apache/solr/response/transform/TestSubQueryTransformer.java
@@ -372,28 +372,27 @@ public class TestSubQueryTransformer extends SolrTestCaseJ4 {
johnTwoFL.setParams(params);
final NamedList<Object> unmarshalled;
- {
- SolrCore core = johnTwoFL.getCore();
- SolrQueryResponse rsp = new SolrQueryResponse();
- SolrRequestInfo.setRequestInfo(new SolrRequestInfo(johnTwoFL, rsp));
-
+ SolrCore core = johnTwoFL.getCore();
+ SolrQueryResponse rsp = new SolrQueryResponse();
+ SolrRequestInfo.setRequestInfo(new SolrRequestInfo(johnTwoFL, rsp));
+
SolrQueryResponse response = h.queryAndResponse(
johnTwoFL.getParams().get(CommonParams.QT), johnTwoFL);
-
+
BinaryQueryResponseWriter responseWriter = (BinaryQueryResponseWriter) core.getQueryResponseWriter(johnTwoFL);
ByteArrayOutputStream bytes = new ByteArrayOutputStream();
- responseWriter.write(bytes,johnTwoFL,response);
-
- unmarshalled = (NamedList<Object>) new JavaBinCodec().unmarshal(
- new ByteArrayInputStream(bytes.toByteArray()));
-
- johnTwoFL.close();
- SolrRequestInfo.clearRequestInfo();
+ responseWriter.write(bytes, johnTwoFL, response);
+
+ try (JavaBinCodec jbc = new JavaBinCodec()) {
+ unmarshalled = (NamedList<Object>) jbc.unmarshal(
+ new ByteArrayInputStream(bytes.toByteArray()));
}
+
+ johnTwoFL.close();
+ SolrRequestInfo.clearRequestInfo();
SolrDocumentList resultDocs = (SolrDocumentList)(unmarshalled.get("response"));
- {
Map<String,String> engText = new HashMap<>();
engText.put("text_t", "These guys develop stuff");
@@ -415,7 +414,6 @@ public class TestSubQueryTransformer extends SolrTestCaseJ4 {
}
}
}
- }
}
@Test
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/core/src/test/org/apache/solr/update/AddBlockUpdateTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/update/AddBlockUpdateTest.java b/solr/core/src/test/org/apache/solr/update/AddBlockUpdateTest.java
index 9c791c2..cbd91c6 100644
--- a/solr/core/src/test/org/apache/solr/update/AddBlockUpdateTest.java
+++ b/solr/core/src/test/org/apache/solr/update/AddBlockUpdateTest.java
@@ -412,11 +412,15 @@ public class AddBlockUpdateTest extends SolrTestCaseJ4 {
}
ByteArrayOutputStream os = new ByteArrayOutputStream();
- new JavaBinCodec().marshal(topDocument, os);
+ try (JavaBinCodec jbc = new JavaBinCodec()) {
+ jbc.marshal(topDocument, os);
+ }
byte[] buffer = os.toByteArray();
//now read the Object back
- InputStream is = new ByteArrayInputStream(buffer);
- SolrInputDocument result = (SolrInputDocument) new JavaBinCodec().unmarshal(is);
+ SolrInputDocument result;
+ try (JavaBinCodec jbc = new JavaBinCodec(); InputStream is = new ByteArrayInputStream(buffer)) {
+ result = (SolrInputDocument) jbc.unmarshal(is);
+ }
assertEquals(2, result.size());
assertEquals("v1", result.getFieldValue("parent_f1"));
assertEquals("v2", result.getFieldValue("parent_f2"));
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/solrj/src/java/org/apache/solr/client/solrj/impl/StreamingBinaryResponseParser.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/impl/StreamingBinaryResponseParser.java b/solr/solrj/src/java/org/apache/solr/client/solrj/impl/StreamingBinaryResponseParser.java
index 14be1f3..5f88672 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/impl/StreamingBinaryResponseParser.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/impl/StreamingBinaryResponseParser.java
@@ -45,8 +45,7 @@ public class StreamingBinaryResponseParser extends BinaryResponseParser {
@Override
public NamedList<Object> processResponse(InputStream body, String encoding) {
- try {
- JavaBinCodec codec = new JavaBinCodec() {
+ try (JavaBinCodec codec = new JavaBinCodec() {
@Override
public SolrDocument readSolrDocument(DataInputInputStream dis) throws IOException {
@@ -80,7 +79,7 @@ public class StreamingBinaryResponseParser extends BinaryResponseParser {
}
return solrDocs;
}
- };
+ };) {
return (NamedList<Object>) codec.unmarshal(body);
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/solrj/src/java/org/apache/solr/client/solrj/request/JavaBinUpdateRequestCodec.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/request/JavaBinUpdateRequestCodec.java b/solr/solrj/src/java/org/apache/solr/client/solrj/request/JavaBinUpdateRequestCodec.java
index afa746e..5759a6c 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/request/JavaBinUpdateRequestCodec.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/request/JavaBinUpdateRequestCodec.java
@@ -87,8 +87,9 @@ public class JavaBinUpdateRequestCodec {
}
nl.add("docs", docIter);
}
- JavaBinCodec codec = new JavaBinCodec();
- codec.marshal(nl, os);
+ try (JavaBinCodec codec = new JavaBinCodec()) {
+ codec.marshal(nl, os);
+ }
}
/**
@@ -110,7 +111,7 @@ public class JavaBinUpdateRequestCodec {
Map<String,Map<String,Object>> delByIdMap;
List<String> delByQ;
final NamedList[] namedList = new NamedList[1];
- JavaBinCodec codec = new JavaBinCodec() {
+ try (JavaBinCodec codec = new JavaBinCodec() {
// NOTE: this only works because this is an anonymous inner class
// which will only ever be used on a single stream -- if this class
@@ -189,9 +190,10 @@ public class JavaBinUpdateRequestCodec {
return Collections.EMPTY_LIST;
}
- };
+ };) {
- codec.unmarshal(is);
+ codec.unmarshal(is);
+ }
// NOTE: if the update request contains only delete commands the params
// must be loaded now
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/solrj/src/java/org/apache/solr/common/util/JavaBinCodec.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/common/util/JavaBinCodec.java b/solr/solrj/src/java/org/apache/solr/common/util/JavaBinCodec.java
index a2400f3..8f86e4c 100644
--- a/solr/solrj/src/java/org/apache/solr/common/util/JavaBinCodec.java
+++ b/solr/solrj/src/java/org/apache/solr/common/util/JavaBinCodec.java
@@ -150,11 +150,12 @@ public class JavaBinCodec implements PushWriter {
}
public void marshal(Object nl, OutputStream os) throws IOException {
- initWrite(os);
try {
+ initWrite(os);
writeVal(nl);
} finally {
- finish();
+ alreadyMarshalled = true;
+ daos.flushBuffer();
}
}
@@ -164,11 +165,6 @@ public class JavaBinCodec implements PushWriter {
daos.writeByte(VERSION);
}
- protected void finish() throws IOException {
- closed = true;
- daos.flushBuffer();
- alreadyMarshalled = true;
- }
/** expert: sets a new output stream */
public void init(FastOutputStream os) {
@@ -1199,11 +1195,10 @@ public class JavaBinCodec implements PushWriter {
}
}
- private boolean closed;
-
@Override
public void close() throws IOException {
- if (closed) return;
- finish();
+ if (daos != null) {
+ daos.flushBuffer();
+ }
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/solrj/src/test/org/apache/solr/common/util/TestJavaBinCodec.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/common/util/TestJavaBinCodec.java b/solr/solrj/src/test/org/apache/solr/common/util/TestJavaBinCodec.java
index 16ace15..e60d8c7 100644
--- a/solr/solrj/src/test/org/apache/solr/common/util/TestJavaBinCodec.java
+++ b/solr/solrj/src/test/org/apache/solr/common/util/TestJavaBinCodec.java
@@ -55,11 +55,13 @@ public class TestJavaBinCodec extends SolrTestCaseJ4 {
public void testStrings() throws Exception {
for (int i = 0; i < 10000 * RANDOM_MULTIPLIER; i++) {
String s = TestUtil.randomUnicodeString(random());
- ByteArrayOutputStream os = new ByteArrayOutputStream();
- new JavaBinCodec().marshal(s, os);
- ByteArrayInputStream is = new ByteArrayInputStream(os.toByteArray());
- Object o = new JavaBinCodec().unmarshal(is);
- assertEquals(s, o);
+ try (JavaBinCodec jbcO = new JavaBinCodec(); ByteArrayOutputStream os = new ByteArrayOutputStream()) {
+ jbcO.marshal(s, os);
+ try (JavaBinCodec jbcI = new JavaBinCodec(); ByteArrayInputStream is = new ByteArrayInputStream(os.toByteArray())) {
+ Object o = jbcI.unmarshal(is);
+ assertEquals(s, o);
+ }
+ }
}
}
@@ -165,14 +167,13 @@ public class TestJavaBinCodec extends SolrTestCaseJ4 {
@Test
public void testBackCompat() throws IOException {
- JavaBinCodec javabin = new JavaBinCodec(){
+ try (InputStream is = getClass().getResourceAsStream(SOLRJ_JAVABIN_BACKCOMPAT_BIN); JavaBinCodec javabin = new JavaBinCodec(){
@Override
public List<Object> readIterator(DataInputInputStream fis) throws IOException {
return super.readIterator(fis);
}
- };
- try {
- InputStream is = getClass().getResourceAsStream(SOLRJ_JAVABIN_BACKCOMPAT_BIN);
+ };)
+ {
List<Object> unmarshaledObj = (List<Object>) javabin.unmarshal(is);
List<Object> matchObj = generateAllDataTypes();
compareObjects(unmarshaledObj, matchObj);
@@ -207,13 +208,13 @@ public class TestJavaBinCodec extends SolrTestCaseJ4 {
@Test
public void testBackCompatForSolrDocumentWithChildDocs() throws IOException {
- JavaBinCodec javabin = new JavaBinCodec(){
+ try (JavaBinCodec javabin = new JavaBinCodec(){
@Override
public List<Object> readIterator(DataInputInputStream fis) throws IOException {
return super.readIterator(fis);
}
- };
- try {
+ };)
+ {
InputStream is = getClass().getResourceAsStream(SOLRJ_JAVABIN_BACKCOMPAT_BIN_CHILD_DOCS);
SolrDocument sdoc = (SolrDocument) javabin.unmarshal(is);
SolrDocument matchSolrDoc = generateSolrDocumentWithChildDocs();
@@ -225,34 +226,30 @@ public class TestJavaBinCodec extends SolrTestCaseJ4 {
@Test
public void testForwardCompat() throws IOException {
- JavaBinCodec javabin = new JavaBinCodec();
- ByteArrayOutputStream os = new ByteArrayOutputStream();
+ try (JavaBinCodec javabin = new JavaBinCodec(); ByteArrayOutputStream os = new ByteArrayOutputStream()) {
- Object data = generateAllDataTypes();
- try {
- javabin.marshal(data, os);
- byte[] newFormatBytes = os.toByteArray();
+ Object data = generateAllDataTypes();
+ try {
+ javabin.marshal(data, os);
+ byte[] newFormatBytes = os.toByteArray();
- InputStream is = getClass().getResourceAsStream(SOLRJ_JAVABIN_BACKCOMPAT_BIN);
- byte[] currentFormatBytes = IOUtils.toByteArray(is);
+ InputStream is = getClass().getResourceAsStream(SOLRJ_JAVABIN_BACKCOMPAT_BIN);
+ byte[] currentFormatBytes = IOUtils.toByteArray(is);
- for (int i = 1; i < currentFormatBytes.length; i++) {//ignore the first byte. It is version information
- assertEquals(newFormatBytes[i], currentFormatBytes[i]);
- }
+ for (int i = 1; i < currentFormatBytes.length; i++) {//ignore the first byte. It is version information
+ assertEquals(newFormatBytes[i], currentFormatBytes[i]);
+ }
- } catch (IOException e) {
- throw e;
+ } catch (IOException e) {
+ throw e;
+ }
}
-
}
@Test
public void testForwardCompatForSolrDocumentWithChildDocs() throws IOException {
- JavaBinCodec javabin = new JavaBinCodec();
- ByteArrayOutputStream os = new ByteArrayOutputStream();
-
SolrDocument sdoc = generateSolrDocumentWithChildDocs();
- try {
+ try (JavaBinCodec javabin = new JavaBinCodec(); ByteArrayOutputStream os = new ByteArrayOutputStream()) {
javabin.marshal(sdoc, os);
byte[] newFormatBytes = os.toByteArray();
@@ -262,11 +259,9 @@ public class TestJavaBinCodec extends SolrTestCaseJ4 {
for (int i = 1; i < currentFormatBytes.length; i++) {//ignore the first byte. It is version information
assertEquals(newFormatBytes[i], currentFormatBytes[i]);
}
-
} catch (IOException e) {
throw e;
}
-
}
@Test
@@ -283,14 +278,16 @@ public class TestJavaBinCodec extends SolrTestCaseJ4 {
return getObject(getBytes(o));
}
private static byte[] getBytes(Object o) throws IOException {
- JavaBinCodec javabin = new JavaBinCodec();
- ByteArrayOutputStream baos = new ByteArrayOutputStream();
- javabin.marshal(o, baos);
- return baos.toByteArray();
+ try (JavaBinCodec javabin = new JavaBinCodec(); ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
+ javabin.marshal(o, baos);
+ return baos.toByteArray();
+ }
}
private static Object getObject(byte[] bytes) throws IOException {
- return new JavaBinCodec().unmarshal(new ByteArrayInputStream(bytes));
+ try (JavaBinCodec jbc = new JavaBinCodec()) {
+ return jbc.unmarshal(new ByteArrayInputStream(bytes));
+ }
}
@@ -343,10 +340,15 @@ public class TestJavaBinCodec extends SolrTestCaseJ4 {
JavaBinCodec.StringCache stringCache = new JavaBinCodec.StringCache(new MapBackedCache<>(new HashMap<>()));
- m1 = (Map) new JavaBinCodec(null, stringCache).unmarshal(new ByteArrayInputStream(b1));
- m2 = (Map) new JavaBinCodec(null, stringCache).unmarshal(new ByteArrayInputStream(b2));
- l1 = new ArrayList<>(m1.keySet());
- l2 = new ArrayList<>(m2.keySet());
+ try (JavaBinCodec c1 = new JavaBinCodec(null, stringCache);
+ JavaBinCodec c2 = new JavaBinCodec(null, stringCache)) {
+
+ m1 = (Map) c1.unmarshal(new ByteArrayInputStream(b1));
+ m2 = (Map) c2.unmarshal(new ByteArrayInputStream(b2));
+
+ l1 = new ArrayList<>(m1.keySet());
+ l2 = new ArrayList<>(m2.keySet());
+ }
assertTrue(l1.get(0).equals(l2.get(0)));
assertTrue(l1.get(0) == l2.get(0));
assertTrue(l1.get(1).equals(l2.get(1)));
@@ -556,11 +558,12 @@ public class TestJavaBinCodec extends SolrTestCaseJ4 {
while (--iter >= 0) {
if (++bufnum >= buffers.length) bufnum = 0;
byte[] buf = buffers[bufnum];
- JavaBinCodec javabin = new JavaBinCodec(null, stringCache);
- FastInputStream in = new FastInputStream(empty, buf, 0, buf.length);
- Object o = javabin.unmarshal( in );
- if (o instanceof SolrDocument) {
- ret += ((SolrDocument) o).size();
+ try (JavaBinCodec javabin = new JavaBinCodec(null, stringCache)) {
+ FastInputStream in = new FastInputStream(empty, buf, 0, buf.length);
+ Object o = javabin.unmarshal(in);
+ if (o instanceof SolrDocument) {
+ ret += ((SolrDocument) o).size();
+ }
}
}
return ret;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/64093d6d/solr/solrj/src/test/org/apache/solr/common/util/TestNamedListCodec.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/common/util/TestNamedListCodec.java b/solr/solrj/src/test/org/apache/solr/common/util/TestNamedListCodec.java
index ae2a036..5637ec5 100644
--- a/solr/solrj/src/test/org/apache/solr/common/util/TestNamedListCodec.java
+++ b/solr/solrj/src/test/org/apache/solr/common/util/TestNamedListCodec.java
@@ -31,7 +31,7 @@ import java.util.HashMap;
public class TestNamedListCodec extends LuceneTestCase {
public void testSimple() throws Exception{
- ByteArrayOutputStream baos = new ByteArrayOutputStream();
+
NamedList nl = new NamedList();
Float fval = new Float( 10.01f );
Boolean bval = Boolean.TRUE;
@@ -74,10 +74,14 @@ public class TestNamedListCodec extends LuceneTestCase {
list.add(doc);
nl.add("zzz",doc);
-
- new JavaBinCodec(null).marshal(nl,baos);
- byte[] arr = baos.toByteArray();
- nl = (NamedList) new JavaBinCodec().unmarshal(new ByteArrayInputStream(arr));
+ byte[] arr;
+ try (JavaBinCodec jbc = new JavaBinCodec(null); ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
+ jbc.marshal(nl, baos);
+ arr = baos.toByteArray();
+ }
+ try (JavaBinCodec jbc = new JavaBinCodec(); ByteArrayInputStream bais = new ByteArrayInputStream(arr)) {
+ nl = (NamedList) jbc.unmarshal(bais);
+ }
assertEquals(3, nl.size());
@@ -89,7 +93,7 @@ public class TestNamedListCodec extends LuceneTestCase {
}
public void testIterator() throws Exception{
- ByteArrayOutputStream baos = new ByteArrayOutputStream();
+
NamedList nl = new NamedList();
Float fval = new Float( 10.01f );
Boolean bval = Boolean.TRUE;
@@ -114,17 +118,21 @@ public class TestNamedListCodec extends LuceneTestCase {
list.add(doc);
nl.add("zzz",list.iterator());
-
- new JavaBinCodec(null).marshal(nl,baos);
- byte[] arr = baos.toByteArray();
- nl = (NamedList) new JavaBinCodec().unmarshal(new ByteArrayInputStream(arr));
+ byte[] arr;
+ try (JavaBinCodec jbc = new JavaBinCodec(null); ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
+ jbc.marshal(nl, baos);
+ arr = baos.toByteArray();
+ }
+ try (JavaBinCodec jbc = new JavaBinCodec(); ByteArrayInputStream bais = new ByteArrayInputStream(arr)) {
+ nl = (NamedList) jbc.unmarshal(bais);
+ }
List l = (List) nl.get("zzz");
assertEquals(list.size(), l.size());
}
public void testIterable() throws Exception {
- ByteArrayOutputStream baos = new ByteArrayOutputStream();
+
NamedList r = new NamedList();
@@ -137,11 +145,14 @@ public class TestNamedListCodec extends LuceneTestCase {
r.add("more", "less");
r.add("values", map.values());
r.add("finally", "the end");
- new JavaBinCodec(null).marshal(r,baos);
- byte[] arr = baos.toByteArray();
+ byte[] arr;
+ try (JavaBinCodec jbc = new JavaBinCodec(null); ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
+ jbc.marshal(r,baos);
+ arr = baos.toByteArray();
+ }
- try {
- NamedList result = (NamedList) new JavaBinCodec().unmarshal(new ByteArrayInputStream(arr));
+ try (JavaBinCodec jbc = new JavaBinCodec(); ByteArrayInputStream bais = new ByteArrayInputStream(arr)) {
+ NamedList result = (NamedList) jbc.unmarshal(bais);
assertTrue("result is null and it shouldn't be", result != null);
List keys = (List) result.get("keys");
assertTrue("keys is null and it shouldn't be", keys != null);
@@ -247,13 +258,16 @@ public class TestNamedListCodec extends LuceneTestCase {
for (int i=0; i<10000; i++) { // pump up the iterations for good stress testing
nl = rNamedList(3);
- ByteArrayOutputStream baos = new ByteArrayOutputStream();
- new JavaBinCodec(null).marshal(nl,baos);
- byte[] arr = baos.toByteArray();
+ byte[] arr;
+ try (JavaBinCodec jbc = new JavaBinCodec(); ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
+ jbc.marshal(nl, baos);
+ arr = baos.toByteArray();
+ }
// System.out.println(arr.length);
- res = (NamedList) new JavaBinCodec().unmarshal(new ByteArrayInputStream(arr));
- cmp = BaseDistributedSearchTestCase.compare(nl, res, 0, null);
-
+ try (JavaBinCodec jbc = new JavaBinCodec(); ByteArrayInputStream bais = new ByteArrayInputStream(arr)) {
+ res = (NamedList) jbc.unmarshal(bais);
+ cmp = BaseDistributedSearchTestCase.compare(nl, res, 0, null);
+ }
if (cmp != null) {
System.out.println(nl);
System.out.println(res);
@@ -261,5 +275,4 @@ public class TestNamedListCodec extends LuceneTestCase {
}
}
}
-
}
[04/50] [abbrv] lucene-solr:feature/autoscaling: Ref Guide: Format
ceil evaluator docs
Posted by sh...@apache.org.
Ref Guide: Format ceil evaluator docs
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/c24e401d
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/c24e401d
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/c24e401d
Branch: refs/heads/feature/autoscaling
Commit: c24e401d7c391b0da47a94012a131b07e2584566
Parents: 1a00950
Author: Joel Bernstein <jb...@apache.org>
Authored: Fri Jun 16 14:32:18 2017 -0400
Committer: Joel Bernstein <jb...@apache.org>
Committed: Fri Jun 16 14:32:18 2017 -0400
----------------------------------------------------------------------
solr/solr-ref-guide/src/stream-evaluators.adoc | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/c24e401d/solr/solr-ref-guide/src/stream-evaluators.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/stream-evaluators.adoc b/solr/solr-ref-guide/src/stream-evaluators.adoc
index 7f46312..f10bca3 100644
--- a/solr/solr-ref-guide/src/stream-evaluators.adoc
+++ b/solr/solr-ref-guide/src/stream-evaluators.adoc
@@ -231,7 +231,7 @@ mod(fieldA,1.4) // returns the remainder of fieldA divided by 1.4.
if(gt(fieldA,fieldB),mod(fieldA,fieldB),mod(fieldB,fieldA)) // if fieldA > fieldB then return the remainder of fieldA/fieldB, else return the remainder of fieldB/fieldA.
----
-=== ceil
+== ceil
The `ceil` function rounds a decimal value to the next highest whole number.
=== ceil Parameters
[40/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ru.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ru.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ru.txt
new file mode 100644
index 0000000..5527140
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ru.txt
@@ -0,0 +1,243 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | a russian stop word list. comments begin with vertical bar. each stop
+ | word is at the start of a line.
+
+ | this is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | letter `ё' is translated to `е'.
+
+и | and
+в | in/into
+во | alternative form
+не | not
+что | what/that
+он | he
+на | on/onto
+я | i
+с | from
+со | alternative form
+как | how
+а | milder form of `no' (but)
+то | conjunction and form of `that'
+все | all
+она | she
+так | so, thus
+его | him
+но | but
+да | yes/and
+ты | thou
+к | towards, by
+у | around, chez
+же | intensifier particle
+вы | you
+за | beyond, behind
+бы | conditional/subj. particle
+по | up to, along
+только | only
+ее | her
+мне | to me
+было | it was
+вот | here is/are, particle
+от | away from
+меня | me
+еще | still, yet, more
+нет | no, there isnt/arent
+о | about
+из | out of
+ему | to him
+теперь | now
+когда | when
+даже | even
+ну | so, well
+вдруг | suddenly
+ли | interrogative particle
+если | if
+уже | already, but homonym of `narrower'
+или | or
+ни | neither
+быть | to be
+был | he was
+него | prepositional form of его
+до | up to
+вас | you accusative
+нибудь | indef. suffix preceded by hyphen
+опять | again
+уж | already, but homonym of `adder'
+вам | to you
+сказал | he said
+ведь | particle `after all'
+там | there
+потом | then
+себя | oneself
+ничего | nothing
+ей | to her
+может | usually with `быть' as `maybe'
+они | they
+тут | here
+где | where
+есть | there is/are
+надо | got to, must
+ней | prepositional form of ей
+для | for
+мы | we
+тебя | thee
+их | them, their
+чем | than
+была | she was
+сам | self
+чтоб | in order to
+без | without
+будто | as if
+человек | man, person, one
+чего | genitive form of `what'
+раз | once
+тоже | also
+себе | to oneself
+под | beneath
+жизнь | life
+будет | will be
+ж | short form of intensifer particle `же'
+тогда | then
+кто | who
+этот | this
+говорил | was saying
+того | genitive form of `that'
+потому | for that reason
+этого | genitive form of `this'
+какой | which
+совсем | altogether
+ним | prepositional form of `его', `они'
+здесь | here
+этом | prepositional form of `этот'
+один | one
+почти | almost
+мой | my
+тем | instrumental/dative plural of `тот', `то'
+чтобы | full form of `in order that'
+нее | her (acc.)
+кажется | it seems
+сейчас | now
+были | they were
+куда | where to
+зачем | why
+сказать | to say
+всех | all (acc., gen. preposn. plural)
+никогда | never
+сегодня | today
+можно | possible, one can
+при | by
+наконец | finally
+два | two
+об | alternative form of `о', about
+другой | another
+хоть | even
+после | after
+над | above
+больше | more
+тот | that one (masc.)
+через | across, in
+эти | these
+нас | us
+про | about
+всего | in all, only, of all
+них | prepositional form of `они' (they)
+какая | which, feminine
+много | lots
+разве | interrogative particle
+сказала | she said
+три | three
+эту | this, acc. fem. sing.
+моя | my, feminine
+впрочем | moreover, besides
+хорошо | good
+свою | ones own, acc. fem. sing.
+этой | oblique form of `эта', fem. `this'
+перед | in front of
+иногда | sometimes
+лучше | better
+чуть | a little
+том | preposn. form of `that one'
+нельзя | one must not
+такой | such a one
+им | to them
+более | more
+всегда | always
+конечно | of course
+всю | acc. fem. sing of `all'
+между | between
+
+
+ | b: some paradigms
+ |
+ | personal pronouns
+ |
+ | я меня мне мной [мною]
+ | ты тебя тебе тобой [тобою]
+ | он его ему им [него, нему, ним]
+ | она ее эи ею [нее, нэи, нею]
+ | оно его ему им [него, нему, ним]
+ |
+ | мы нас нам нами
+ | вы вас вам вами
+ | они их им ими [них, ним, ними]
+ |
+ | себя себе собой [собою]
+ |
+ | demonstrative pronouns: этот (this), тот (that)
+ |
+ | этот эта это эти
+ | этого эты это эти
+ | этого этой этого этих
+ | этому этой этому этим
+ | этим этой этим [этою] этими
+ | этом этой этом этих
+ |
+ | тот та то те
+ | того ту то те
+ | того той того тех
+ | тому той тому тем
+ | тем той тем [тою] теми
+ | том той том тех
+ |
+ | determinative pronouns
+ |
+ | (a) весь (all)
+ |
+ | весь вся все все
+ | всего всю все все
+ | всего всей всего всех
+ | всему всей всему всем
+ | всем всей всем [всею] всеми
+ | всем всей всем всех
+ |
+ | (b) сам (himself etc)
+ |
+ | сам сама само сами
+ | самого саму само самих
+ | самого самой самого самих
+ | самому самой самому самим
+ | самим самой самим [самою] самими
+ | самом самой самом самих
+ |
+ | stems of verbs `to be', `to have', `to do' and modal
+ |
+ | быть бы буд быв есть суть
+ | име
+ | дел
+ | мог мож мочь
+ | уме
+ | хоч хот
+ | долж
+ | можн
+ | нужн
+ | нельзя
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_sv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_sv.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_sv.txt
new file mode 100644
index 0000000..096f87f
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_sv.txt
@@ -0,0 +1,133 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Swedish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | Swedish stop words occasionally exhibit homonym clashes. For example
+ | så = so, but also seed. These are indicated clearly below.
+
+och | and
+det | it, this/that
+att | to (with infinitive)
+i | in, at
+en | a
+jag | I
+hon | she
+som | who, that
+han | he
+på | on
+den | it, this/that
+med | with
+var | where, each
+sig | him(self) etc
+för | for
+så | so (also: seed)
+till | to
+är | is
+men | but
+ett | a
+om | if; around, about
+hade | had
+de | they, these/those
+av | of
+icke | not, no
+mig | me
+du | you
+henne | her
+då | then, when
+sin | his
+nu | now
+har | have
+inte | inte någon = no one
+hans | his
+honom | him
+skulle | 'sake'
+hennes | her
+där | there
+min | my
+man | one (pronoun)
+ej | nor
+vid | at, by, on (also: vast)
+kunde | could
+något | some etc
+från | from, off
+ut | out
+när | when
+efter | after, behind
+upp | up
+vi | we
+dem | them
+vara | be
+vad | what
+över | over
+än | than
+dig | you
+kan | can
+sina | his
+här | here
+ha | have
+mot | towards
+alla | all
+under | under (also: wonder)
+någon | some etc
+eller | or (else)
+allt | all
+mycket | much
+sedan | since
+ju | why
+denna | this/that
+själv | myself, yourself etc
+detta | this/that
+åt | to
+utan | without
+varit | was
+hur | how
+ingen | no
+mitt | my
+ni | you
+bli | to be, become
+blev | from bli
+oss | us
+din | thy
+dessa | these/those
+några | some etc
+deras | their
+blir | from bli
+mina | my
+samma | (the) same
+vilken | who, that
+er | you, your
+sådan | such a
+vår | our
+blivit | from bli
+dess | its
+inom | within
+mellan | between
+sådant | such a
+varför | why
+varje | each
+vilka | who, that
+ditt | thy
+vem | who
+vilket | who, that
+sitta | his
+sådana | such a
+vart | each
+dina | thy
+vars | whose
+vårt | our
+våra | our
+ert | your
+era | your
+vilkas | whose
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_th.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_th.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_th.txt
new file mode 100644
index 0000000..07f0fab
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_th.txt
@@ -0,0 +1,119 @@
+# Thai stopwords from:
+# "Opinion Detection in Thai Political News Columns
+# Based on Subjectivity Analysis"
+# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
+ไว้
+ไม่
+ไป
+ได้
+ให้
+ใน
+โดย
+แห่ง
+แล้ว
+และ
+แรก
+แบบ
+แต่
+เอง
+เห็น
+เลย
+เริ่ม
+เรา
+เมื่อ
+เพื่อ
+เพราะ
+เป็นการ
+เป็น
+เปิดเผย
+เปิด
+เนื่องจาก
+เดียวกัน
+เดียว
+เช่น
+เฉพาะ
+เคย
+เข้า
+เขา
+อีก
+อาจ
+อะไร
+ออก
+อย่าง
+อยู่
+อยาก
+หาก
+หลาย
+หลังจาก
+หลัง
+หรือ
+หนึ่ง
+ส่วน
+ส่ง
+สุด
+สําหรับ
+ว่า
+วัน
+ลง
+ร่วม
+ราย
+รับ
+ระหว่าง
+รวม
+ยัง
+มี
+มาก
+มา
+พร้อม
+พบ
+ผ่าน
+ผล
+บาง
+น่า
+นี้
+นํา
+นั้น
+นัก
+นอกจาก
+ทุก
+ที่สุด
+ที่
+ทําให้
+ทํา
+ทาง
+ทั้งนี้
+ทั้ง
+ถ้า
+ถูก
+ถึง
+ต้อง
+ต่างๆ
+ต่าง
+ต่อ
+ตาม
+ตั้งแต่
+ตั้ง
+ด้าน
+ด้วย
+ดัง
+ซึ่ง
+ช่วง
+จึง
+จาก
+จัด
+จะ
+คือ
+ความ
+ครั้ง
+คง
+ขึ้น
+ของ
+ขอ
+ขณะ
+ก่อน
+ก็
+การ
+กับ
+กัน
+กว่า
+กล่าว
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_tr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_tr.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_tr.txt
new file mode 100644
index 0000000..84d9408
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_tr.txt
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+altmış
+altı
+ama
+ancak
+arada
+aslında
+ayrıca
+bana
+bazı
+belki
+ben
+benden
+beni
+benim
+beri
+beş
+bile
+bin
+bir
+birçok
+biri
+birkaç
+birkez
+birşey
+birşeyi
+biz
+bize
+bizden
+bizi
+bizim
+böyle
+böylece
+bu
+buna
+bunda
+bundan
+bunlar
+bunları
+bunların
+bunu
+bunun
+burada
+çok
+çünkü
+da
+daha
+dahi
+de
+defa
+değil
+diğer
+diye
+doksan
+dokuz
+dolayı
+dolayısıyla
+dört
+edecek
+eden
+ederek
+edilecek
+ediliyor
+edilmesi
+ediyor
+eğer
+elli
+en
+etmesi
+etti
+ettiği
+ettiğini
+gibi
+göre
+halen
+hangi
+hatta
+hem
+henüz
+hep
+hepsi
+her
+herhangi
+herkesin
+hiç
+hiçbir
+için
+iki
+ile
+ilgili
+ise
+işte
+itibaren
+itibariyle
+kadar
+karşın
+katrilyon
+kendi
+kendilerine
+kendini
+kendisi
+kendisine
+kendisini
+kez
+ki
+kim
+kimden
+kime
+kimi
+kimse
+kırk
+milyar
+milyon
+mu
+mü
+mı
+nasıl
+ne
+neden
+nedenle
+nerde
+nerede
+nereye
+niye
+niçin
+o
+olan
+olarak
+oldu
+olduğu
+olduğunu
+olduklarını
+olmadı
+olmadığı
+olmak
+olması
+olmayan
+olmaz
+olsa
+olsun
+olup
+olur
+olursa
+oluyor
+on
+ona
+ondan
+onlar
+onlardan
+onları
+onların
+onu
+onun
+otuz
+oysa
+öyle
+pek
+rağmen
+sadece
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+şey
+şeyden
+şeyi
+şeyler
+şöyle
+şu
+şuna
+şunda
+şundan
+şunları
+şunu
+tarafından
+trilyon
+tüm
+üç
+üzere
+var
+vardı
+ve
+veya
+ya
+yani
+yapacak
+yapılan
+yapılması
+yapıyor
+yapmak
+yaptı
+yaptığı
+yaptığını
+yaptıkları
+yedi
+yerine
+yetmiş
+yine
+yirmi
+yoksa
+yüz
+zaten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/userdict_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/userdict_ja.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/userdict_ja.txt
new file mode 100644
index 0000000..6f0368e
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/userdict_ja.txt
@@ -0,0 +1,29 @@
+#
+# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
+#
+# Add entries to this file in order to override the statistical model in terms
+# of segmentation, readings and part-of-speech tags. Notice that entries do
+# not have weights since they are always used when found. This is by-design
+# in order to maximize ease-of-use.
+#
+# Entries are defined using the following CSV format:
+# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
+#
+# Notice that a single half-width space separates tokens and readings, and
+# that the number tokens and readings must match exactly.
+#
+# Also notice that multiple entries with the same <text> is undefined.
+#
+# Whitespace only lines are ignored. Comments are not allowed on entry lines.
+#
+
+# Custom segmentation for kanji compounds
+日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
+関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
+
+# Custom segmentation for compound katakana
+トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
+ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
+
+# Custom reading for former sumo wrestler
+朝青龍,朝青龍,アサショウリュウ,カスタム人名
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema b/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
new file mode 100644
index 0000000..80a58fb
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
@@ -0,0 +1,1069 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking. To improve performance one could
+ - set stored="false" for all fields possible (esp large fields) when you
+ only need to search on the field but don't need to return the original
+ value.
+ - set indexed="false" if you don't need to search on the field, but only
+ return the field as a result of searching on other indexed fields.
+ - remove all unneeded copyField statements
+ - for best index size and searching performance, set "index" to false
+ for all general text fields, use copyField to copy them to the
+ catchall "text" field, and use that for searching.
+ - For maximum indexing performance, use the ConcurrentUpdateSolrServer
+ java client.
+ - Remember to run the JVM in server mode, and use a higher logging level
+ that avoids logging every request
+-->
+
+<schema name="example-data-driven-schema" version="1.6">
+ <!-- attribute "name" is the name of this schema and is only used for display purposes.
+ version="x.y" is Solr's version number for the schema syntax and
+ semantics. It should not normally be changed by applications.
+
+ 1.0: multiValued attribute did not exist, all fields are multiValued
+ by nature
+ 1.1: multiValued attribute introduced, false by default
+ 1.2: omitTermFreqAndPositions attribute introduced, true by default
+ except for text fields.
+ 1.3: removed optional field compress feature
+ 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+ behavior when a single string produces multiple tokens. Defaults
+ to off for version >= 1.4
+ 1.5: omitNorms defaults to true for primitive field types
+ (int, float, boolean, string...)
+ 1.6: useDocValuesAsStored defaults to true.
+ -->
+
+ <!-- Valid attributes for fields:
+ name: mandatory - the name for the field
+ type: mandatory - the name of a field type from the
+ fieldTypes section
+ indexed: true if this field should be indexed (searchable or sortable)
+ stored: true if this field should be retrievable
+ docValues: true if this field should have doc values. Doc values are
+ useful (required, if you are using *Point fields) for faceting,
+ grouping, sorting and function queries. Doc values will make the index
+ faster to load, more NRT-friendly and more memory-efficient.
+ They however come with some limitations: they are currently only
+ supported by StrField, UUIDField, all Trie*Fields and *PointFields,
+ and depending on the field type, they might require the field to be
+ single-valued, be required or have a default value (check the
+ documentation of the field type you're interested in for more information)
+ multiValued: true if this field may contain multiple values per document
+ omitNorms: (expert) set to true to omit the norms associated with
+ this field (this disables length normalization and index-time
+ boosting for the field, and saves some memory). Only full-text
+ fields or fields that need an index-time boost need norms.
+ Norms are omitted for primitive (non-analyzed) types by default.
+ termVectors: [false] set to true to store the term vector for a
+ given field.
+ When using MoreLikeThis, fields used for similarity should be
+ stored for best performance.
+ termPositions: Store position information with the term vector.
+ This will increase storage costs.
+ termOffsets: Store offset information with the term vector. This
+ will increase storage costs.
+ required: The field is required. It will throw an error if the
+ value does not exist
+ default: a value that should be used if no value is specified
+ when adding a document.
+ -->
+
+ <!-- field names should consist of alphanumeric or underscore characters only and
+ not start with a digit. This is not currently strictly enforced,
+ but other field names will not have first class support from all components
+ and back compatibility is not guaranteed. Names with both leading and
+ trailing underscores (e.g. _version_) are reserved.
+ -->
+
+ <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
+ id, _version_, and _text_. All other fields will be type guessed and added via the
+ "add-unknown-fields-to-the-schema" update request processor chain declared
+ in solrconfig.xml.
+
+ Note that many dynamic fields are also defined - you can use them to specify a
+ field's type via field naming conventions - see below.
+
+ WARNING: The _text_ catch-all field will significantly increase your index size.
+ If you don't need it, consider removing it and the corresponding copyField directive.
+ -->
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <!-- doc values are enabled by default for primitive types such as long so we don't index the version field -->
+ <field name="_version_" type="long" indexed="false" stored="false"/>
+ <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+ <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+ <!-- Only enabled in the "schemaless" data-driven example (assuming the client
+ does not know what fields may be searched) because it's very expensive to index everything twice. -->
+ <copyField source="*" dest="_text_"/>
+
+ <!-- Dynamic field definitions allow using convention over configuration
+ for fields via the specification of patterns to match field names.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end. -->
+
+ <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+ <dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true" />
+ <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
+
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+ <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
+ <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
+
+ <!-- KD-tree (point) numerics -->
+ <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
+ <dynamicField name="*_pis" type="pints" indexed="true" stored="true"/>
+ <dynamicField name="*_pl" type="plong" indexed="true" stored="true"/>
+ <dynamicField name="*_pls" type="plongs" indexed="true" stored="true"/>
+ <dynamicField name="*_pf" type="pfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_pfs" type="pfloats" indexed="true" stored="true"/>
+ <dynamicField name="*_pd" type="pdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_pds" type="pdoubles" indexed="true" stored="true"/>
+ <dynamicField name="*_pdt" type="pdate" indexed="true" stored="true"/>
+ <dynamicField name="*_pdts" type="pdates" indexed="true" stored="true"/>
+
+ <!-- some trie-coded dynamic fields -->
+ <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
+ <dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
+ <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
+ <dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
+ <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
+ <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
+ <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
+ <dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
+
+ <!-- payloaded dynamic fields -->
+ <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true" stored="true"/>
+ <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true" stored="true"/>
+ <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true" stored="true"/>
+
+ <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
+
+ <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+ <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+ <dynamicField name="random_*" type="random" />
+
+ <!-- uncomment the following to ignore any fields that don't already match an existing
+ field name or dynamic field, rather than reporting them as an error.
+ alternately, change the type="ignored" to some other type e.g. "text" if you want
+ unknown fields indexed and/or stored by default
+
+ NB: use of "*" dynamic fields will disable field type guessing and adding
+ unknown fields to the schema. -->
+ <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+ <!-- Field to use to determine and enforce document uniqueness.
+ Unless this field is marked with required="false", it will be a required field
+ -->
+ <uniqueKey>id</uniqueKey>
+
+ <!-- copyField commands copy one field to another at the time a document
+ is added to the index. It's used either to index the same field differently,
+ or to add multiple fields to the same field for easier/faster searching.
+
+ <copyField source="sourceFieldName" dest="destinationFieldName"/>
+ -->
+
+ <!-- field type definitions. The "name" attribute is
+ just a label to be used by field definitions. The "class"
+ attribute and any other attributes determine the real
+ behavior of the fieldType.
+ Class names starting with "solr" refer to java classes in a
+ standard package such as org.apache.solr.analysis
+ -->
+
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+ It supports doc values but in that case the field needs to be
+ single-valued and either required or have a default value.
+ -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+ <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+ <!-- boolean type: "true" or "false" -->
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+ <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+ <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+ currently supported on types that are sorted internally as strings
+ and on numeric types.
+ This includes "string","boolean", "int", "float", "long", "date", "double",
+ including the "Trie" and "Point" variants.
+ - If sortMissingLast="true", then a sort on this field will cause documents
+ without the field to come after documents with the field,
+ regardless of the requested sort order (asc or desc).
+ - If sortMissingFirst="true", then a sort on this field will cause documents
+ without the field to come before documents with the field,
+ regardless of the requested sort order.
+ - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+ then default lucene sorting will be used which places docs without the
+ field first in an ascending sort and last in a descending sort.
+ -->
+
+ <!--
+ Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
+ search time and at index time, but some features are still not supported.
+ Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+ -->
+ <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+ <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+ <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+ <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+ <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+ <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+ <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+ <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+
+ <!--
+ Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
+ tint/tfloat/tlong/tdouble types.
+ -->
+ <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+
+ <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
+ <!--
+ Numeric field types that index each value at various levels of precision
+ to accelerate range queries when the number of values between the range
+ endpoints is large. See the javadoc for NumericRangeQuery for internal
+ implementation details.
+
+ Smaller precisionStep values (specified in bits) will lead to more tokens
+ indexed per value, slightly larger index size, and faster range queries.
+ A precisionStep of 0 disables indexing at different precision levels.
+
+ Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
+ -->
+ <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+
+ <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+ is a more restricted form of the canonical representation of dateTime
+ http://www.w3.org/TR/xmlschema-2/#dateTime
+ The trailing "Z" designates UTC time and is mandatory.
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+ All other components are mandatory.
+
+ Expressions can also be used to denote calculations that should be
+ performed relative to "NOW" to determine the value, ie...
+
+ NOW/HOUR
+ ... Round to the start of the current hour
+ NOW-1DAY
+ ... Exactly 1 day prior to now
+ NOW/DAY+6MONTHS+3DAYS
+ ... 6 months and 3 days in the future from the start of
+ the current day
+
+ Consult the TrieDateField javadocs for more information.
+ -->
+ <!-- KD-tree versions of date fields -->
+ <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+ <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+
+ <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
+ <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
+
+
+ <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+ <fieldType name="binary" class="solr.BinaryField"/>
+
+ <!-- The "RandomSortField" is not used to store or search any
+ data. You can declare fields of this type it in your schema
+ to generate pseudo-random orderings of your docs for sorting
+ or function purposes. The ordering is generated based on the field
+ name and the version of the index. As long as the index version
+ remains unchanged, and the same field name is reused,
+ the ordering of the docs will be consistent.
+ If you want different psuedo-random orderings of documents,
+ for the same version of the index, use a dynamicField and
+ change the field name in the request.
+ -->
+ <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+
+ <!-- solr.TextField allows the specification of custom text analyzers
+ specified as a tokenizer and a list of token filters. Different
+ analyzers may be specified for indexing and querying.
+
+ The optional positionIncrementGap puts space between multiple fields of
+ this type on the same document, with the purpose of preventing false phrase
+ matching across fields.
+
+ For more info on customizing your analyzer chain, please see
+ http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+ -->
+
+ <!-- One can also specify an existing Analyzer class that has a
+ default constructor via the class attribute on the analyzer element.
+ Example:
+ <fieldType name="text_greek" class="solr.TextField">
+ <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+ </fieldType>
+ -->
+
+ <!-- A text field that only splits on whitespace for exact matching of words -->
+ <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
+ <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A general text field that has reasonable, generic
+ cross-language defaults: it tokenizes with StandardTokenizer,
+ removes stop words from case-insensitive "stopwords.txt"
+ (empty by default), and down cases. At query time only, it
+ also applies synonyms.
+ -->
+ <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English: it
+ tokenizes with StandardTokenizer, removes English stop words
+ (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+ finally applies Porter's stemming. The query time analyzer
+ also applies synonyms from synonyms.txt. -->
+ <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
+ <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English, plus
+ aggressive word-splitting and autophrase features enabled.
+ This field is just like text_en, except it adds
+ WordDelimiterGraphFilter to enable splitting and matching of
+ words on case-change, alpha numeric boundaries, and
+ non-alphanumeric chars. This means certain compound word
+ cases will work, for example query "wi fi" will match
+ document "WiFi" or "wi-fi".
+ -->
+ <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
+ <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
+ but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
+ <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
+ <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+ possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+ possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Just like text_general except it reverses the characters of
+ each token, to enable more efficient leading wildcard queries.
+ -->
+ <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
+ <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+ maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
+ <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- lowercases the entire field value, keeping it as a single token. -->
+ <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
+ <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at index time, so
+ queries for paths match documents at that path, or in descendent paths
+ -->
+ <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
+ <fieldType name="descendent_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at query time, so
+ queries for paths match documents at that path, or in ancestor paths
+ -->
+ <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
+ <fieldType name="ancestor_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ </fieldType>
+
+ <!-- since fields of this type are by default not stored or indexed,
+ any data added to them will be ignored outright. -->
+ <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
+
+ <!-- This point type indexes the coordinates as separate fields (subFields)
+ If subFieldType is defined, it references a type, and a dynamic field
+ definition is created matching *___<typename>. Alternately, if
+ subFieldSuffix is defined, that is used to create the subFields.
+ Example: if subFieldType="double", then the coordinates would be
+ indexed in fields myloc_0___double,myloc_1___double.
+ Example: if subFieldSuffix="_d" then the coordinates would be indexed
+ in fields myloc_0_d,myloc_1_d
+ The subFields are an implementation detail of the fieldType, and end
+ users normally should not need to know about them.
+ -->
+ <dynamicField name="*_point" type="point" indexed="true" stored="true"/>
+ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+ <!-- A specialized field for geospatial search filters and distance sorting. -->
+ <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+ <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
+ For more information about this and other Spatial fields new to Solr 4, see:
+ http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+ -->
+ <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+ geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+ <!-- Payloaded field types -->
+ <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
+ Parameters:
+ defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
+ precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
+ providerClass: Lets you plug in other exchange provider backend:
+ solr.FileExchangeRateProvider is the default and takes one parameter:
+ currencyConfig: name of an xml file holding exchange rates
+ solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
+ ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
+ refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
+ -->
+ <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
+
+
+
+ <!-- some examples for different languages (generally ordered by ISO code) -->
+
+ <!-- Arabic -->
+ <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
+ <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- for any non-arabic -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+ <!-- normalizes ﻯ to ﻱ, etc -->
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.ArabicStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Bulgarian -->
+ <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
+ <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+ <filter class="solr.BulgarianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Catalan -->
+ <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
+ <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+ <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
+ <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- for any non-CJK -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.CJKBigramFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Czech -->
+ <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
+ <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+ <filter class="solr.CzechStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Danish -->
+ <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
+ <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- German -->
+ <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
+ <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+ <filter class="solr.GermanNormalizationFilterFactory"/>
+ <filter class="solr.GermanLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Greek -->
+ <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
+ <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- greek specific lowercase for sigma -->
+ <filter class="solr.GreekLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+ <filter class="solr.GreekStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Spanish -->
+ <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
+ <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+ <filter class="solr.SpanishLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Basque -->
+ <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
+ <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Persian -->
+ <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
+ <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <!-- for ZWNJ -->
+ <charFilter class="solr.PersianCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.PersianNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Finnish -->
+ <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
+ <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+ <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- French -->
+ <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
+ <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+ <filter class="solr.FrenchLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Irish -->
+ <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
+ <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes d', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+ <!-- removes n-, etc. position increments is intentionally false! -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+ <filter class="solr.IrishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Galician -->
+ <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
+ <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+ <filter class="solr.GalicianStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Hindi -->
+ <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
+ <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- normalizes unicode representation -->
+ <filter class="solr.IndicNormalizationFilterFactory"/>
+ <!-- normalizes variation in spelling -->
+ <filter class="solr.HindiNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+ <filter class="solr.HindiStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Hungarian -->
+ <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
+ <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Armenian -->
+ <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
+ <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Indonesian -->
+ <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
+ <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+ <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+ <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Italian -->
+ <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
+ <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+ <filter class="solr.ItalianLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+ NOTE: If you want to optimize search for precision, use default operator AND in your request
+ handler config (q.op) Use OR if you would like to optimize for recall (default).
+ -->
+ <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
+ <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+ <analyzer>
+ <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+ Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
+ is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+ Valid values for attribute mode are:
+ normal: regular segmentation
+ search: segmentation useful for search with synonyms compounds (default)
+ extended: same as search mode, but unigrams unknown words (experimental)
+
+ For some applications it might be good to use search mode for indexing and normal mode for
+ queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+ Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+ Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+ model with your own entries for segmentation, part-of-speech tags and readings without a need
+ to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+ User dictionary attributes are:
+ userDictionary: user dictionary filename
+ userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+ See lang/userdict_ja.txt for a sample user dictionary file.
+
+ Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
+
+ See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+ -->
+ <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+ <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+ <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+ <filter class="solr.JapaneseBaseFormFilterFactory"/>
+ <!-- Removes tokens with certain part-of-speech tags -->
+ <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+ <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+ <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+ <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+ <!-- Lower-cases romaji characters -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Latvian -->
+ <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
+ <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+ <filter class="solr.LatvianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Dutch -->
+ <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
+ <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+ <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Norwegian -->
+ <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
+ <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+ <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+ <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Portuguese -->
+ <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
+ <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+ <filter class="solr.PortugueseLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+ <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Romanian -->
+ <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
+ <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Russian -->
+ <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
+ <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+ <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Swedish -->
+ <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
+ <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+ <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Thai -->
+ <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
+ <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.ThaiTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Turkish -->
+ <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
+ <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.TurkishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Similarity is the scoring routine for each document vs. a query.
+ A custom Similarity or SimilarityFactory may be specified here, but
+ the default is fine for most applications.
+ For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+ -->
+ <!--
+ <similarity class="com.example.solr.CustomSimilarityFactory">
+ <str name="paramkey">param value</str>
+ </similarity>
+ -->
+
+</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/params.json
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/params.json b/solr/server/solr/configsets/data_driven_schema_configs/conf/params.json
new file mode 100644
index 0000000..06114ef
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/params.json
@@ -0,0 +1,20 @@
+{"params":{
+ "query":{
+ "defType":"edismax",
+ "q.alt":"*:*",
+ "rows":"10",
+ "fl":"*,score",
+ "":{"v":0}
+ },
+ "facets":{
+ "facet":"on",
+ "facet.mincount": "1",
+ "":{"v":0}
+ },
+ "velocity":{
+ "wt": "velocity",
+ "v.template":"browse",
+ "v.layout": "layout",
+ "":{"v":0}
+ }
+}}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/protwords.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/protwords.txt
new file mode 100644
index 0000000..1dfc0ab
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/protwords.txt
@@ -0,0 +1,21 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+# Use a protected word file to protect against the stemmer reducing two
+# unrelated words to the same base word.
+
+# Some non-words that normally won't be encountered,
+# just to test that they won't be stemmed.
+dontstems
+zwhacky
+
[12/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10882:
ArrayEvaluator now supports values of any type
Posted by sh...@apache.org.
SOLR-10882: ArrayEvaluator now supports values of any type
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/606824ac
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/606824ac
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/606824ac
Branch: refs/heads/feature/autoscaling
Commit: 606824acaf6e0479cc1b29f57266ade18aed3d08
Parents: 8988862
Author: Dennis Gove <dp...@gmail.com>
Authored: Tue Jun 13 09:19:45 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Sun Jun 18 11:50:57 2017 -0400
----------------------------------------------------------------------
.../org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/606824ac/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
index 31d89a2..ed45ee9 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
@@ -36,11 +36,11 @@ public class ArrayEvaluator extends ComplexEvaluator implements Expressible {
super(expression, factory);
}
- public List<Number> evaluate(Tuple tuple) throws IOException {
- List<Number> list = new ArrayList();
+ public List<Object> evaluate(Tuple tuple) throws IOException {
+ List<Object> list = new ArrayList<>();
for(StreamEvaluator subEvaluator : subEvaluators) {
- Number num = (Number)subEvaluator.evaluate(tuple);
- list.add(num);
+ Object value = (Number)subEvaluator.evaluate(tuple);
+ list.add(value);
}
return list;
[25/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ar.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ar.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ar.txt
deleted file mode 100644
index 046829d..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ar.txt
+++ /dev/null
@@ -1,125 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Cleaned on October 11, 2009 (not normalized, so use before normalization)
-# This means that when modifying this list, you might need to add some
-# redundant entries, for example containing forms with both أ and ا
-من
-ومن
-منها
-منه
-في
-وفي
-فيها
-فيه
-و
-ف
-ثم
-او
-أو
-ب
-بها
-به
-ا
-أ
-اى
-اي
-أي
-أى
-لا
-ولا
-الا
-ألا
-إلا
-لكن
-ما
-وما
-كما
-فما
-عن
-مع
-اذا
-إذا
-ان
-أن
-إن
-انها
-أنها
-إنها
-انه
-أنه
-إنه
-بان
-بأن
-فان
-فأن
-وان
-وأن
-وإن
-التى
-التي
-الذى
-الذي
-الذين
-الى
-الي
-إلى
-إلي
-على
-عليها
-عليه
-اما
-أما
-إما
-ايضا
-أيضا
-كل
-وكل
-لم
-ولم
-لن
-ولن
-هى
-هي
-هو
-وهى
-وهي
-وهو
-فهى
-فهي
-فهو
-انت
-أنت
-لك
-لها
-له
-هذه
-هذا
-تلك
-ذلك
-هناك
-كانت
-كان
-يكون
-تكون
-وكانت
-وكان
-غير
-بعض
-قد
-نحو
-بين
-بينما
-منذ
-ضمن
-حيث
-الان
-الآن
-خلال
-بعد
-قبل
-حتى
-عند
-عندما
-لدى
-جميع
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_bg.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_bg.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_bg.txt
deleted file mode 100644
index 1ae4ba2..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_bg.txt
+++ /dev/null
@@ -1,193 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-а
-аз
-ако
-ала
-бе
-без
-беше
-би
-бил
-била
-били
-било
-близо
-бъдат
-бъде
-бяха
-в
-вас
-ваш
-ваша
-вероятно
-вече
-взема
-ви
-вие
-винаги
-все
-всеки
-всички
-всичко
-всяка
-във
-въпреки
-върху
-г
-ги
-главно
-го
-д
-да
-дали
-до
-докато
-докога
-дори
-досега
-доста
-е
-едва
-един
-ето
-за
-зад
-заедно
-заради
-засега
-затова
-защо
-защото
-и
-из
-или
-им
-има
-имат
-иска
-й
-каза
-как
-каква
-какво
-както
-какъв
-като
-кога
-когато
-което
-които
-кой
-който
-колко
-която
-къде
-където
-към
-ли
-м
-ме
-между
-мен
-ми
-мнозина
-мога
-могат
-може
-моля
-момента
-му
-н
-на
-над
-назад
-най
-направи
-напред
-например
-нас
-не
-него
-нея
-ни
-ние
-никой
-нито
-но
-някои
-някой
-няма
-обаче
-около
-освен
-особено
-от
-отгоре
-отново
-още
-пак
-по
-повече
-повечето
-под
-поне
-поради
-после
-почти
-прави
-пред
-преди
-през
-при
-пък
-първо
-с
-са
-само
-се
-сега
-си
-скоро
-след
-сме
-според
-сред
-срещу
-сте
-съм
-със
-също
-т
-тази
-така
-такива
-такъв
-там
-твой
-те
-тези
-ти
-тн
-то
-това
-тогава
-този
-той
-толкова
-точно
-трябва
-тук
-тъй
-тя
-тях
-у
-харесва
-ч
-че
-често
-чрез
-ще
-щом
-я
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ca.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ca.txt
deleted file mode 100644
index 3da65de..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ca.txt
+++ /dev/null
@@ -1,220 +0,0 @@
-# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
-a
-abans
-ací
-ah
-així
-això
-al
-als
-aleshores
-algun
-alguna
-algunes
-alguns
-alhora
-allà
-allí
-allò
-altra
-altre
-altres
-amb
-ambdós
-ambdues
-apa
-aquell
-aquella
-aquelles
-aquells
-aquest
-aquesta
-aquestes
-aquests
-aquí
-baix
-cada
-cadascú
-cadascuna
-cadascunes
-cadascuns
-com
-contra
-d'un
-d'una
-d'unes
-d'uns
-dalt
-de
-del
-dels
-des
-després
-dins
-dintre
-donat
-doncs
-durant
-e
-eh
-el
-els
-em
-en
-encara
-ens
-entre
-érem
-eren
-éreu
-es
-és
-esta
-està
-estàvem
-estaven
-estàveu
-esteu
-et
-etc
-ets
-fins
-fora
-gairebé
-ha
-han
-has
-havia
-he
-hem
-heu
-hi
-ho
-i
-igual
-iguals
-ja
-l'hi
-la
-les
-li
-li'n
-llavors
-m'he
-ma
-mal
-malgrat
-mateix
-mateixa
-mateixes
-mateixos
-me
-mentre
-més
-meu
-meus
-meva
-meves
-molt
-molta
-moltes
-molts
-mon
-mons
-n'he
-n'hi
-ne
-ni
-no
-nogensmenys
-només
-nosaltres
-nostra
-nostre
-nostres
-o
-oh
-oi
-on
-pas
-pel
-pels
-per
-però
-perquè
-poc
-poca
-pocs
-poques
-potser
-propi
-qual
-quals
-quan
-quant
-que
-què
-quelcom
-qui
-quin
-quina
-quines
-quins
-s'ha
-s'han
-sa
-semblant
-semblants
-ses
-seu
-seus
-seva
-seva
-seves
-si
-sobre
-sobretot
-sóc
-solament
-sols
-son
-són
-sons
-sota
-sou
-t'ha
-t'han
-t'he
-ta
-tal
-també
-tampoc
-tan
-tant
-tanta
-tantes
-teu
-teus
-teva
-teves
-ton
-tons
-tot
-tota
-totes
-tots
-un
-una
-unes
-uns
-us
-va
-vaig
-vam
-van
-vas
-veu
-vosaltres
-vostra
-vostre
-vostres
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_cz.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_cz.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_cz.txt
deleted file mode 100644
index 53c6097..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_cz.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-a
-s
-k
-o
-i
-u
-v
-z
-dnes
-cz
-tímto
-budeš
-budem
-byli
-jseš
-můj
-svým
-ta
-tomto
-tohle
-tuto
-tyto
-jej
-zda
-proč
-máte
-tato
-kam
-tohoto
-kdo
-kteří
-mi
-nám
-tom
-tomuto
-mít
-nic
-proto
-kterou
-byla
-toho
-protože
-asi
-ho
-naši
-napište
-re
-což
-tím
-takže
-svých
-její
-svými
-jste
-aj
-tu
-tedy
-teto
-bylo
-kde
-ke
-pravé
-ji
-nad
-nejsou
-či
-pod
-téma
-mezi
-přes
-ty
-pak
-vám
-ani
-když
-však
-neg
-jsem
-tento
-článku
-články
-aby
-jsme
-před
-pta
-jejich
-byl
-ještě
-až
-bez
-také
-pouze
-první
-vaše
-která
-nás
-nový
-tipy
-pokud
-může
-strana
-jeho
-své
-jiné
-zprávy
-nové
-není
-vás
-jen
-podle
-zde
-už
-být
-více
-bude
-již
-než
-který
-by
-které
-co
-nebo
-ten
-tak
-má
-při
-od
-po
-jsou
-jak
-další
-ale
-si
-se
-ve
-to
-jako
-za
-zpět
-ze
-do
-pro
-je
-na
-atd
-atp
-jakmile
-přičemž
-já
-on
-ona
-ono
-oni
-ony
-my
-vy
-jí
-ji
-mě
-mne
-jemu
-tomu
-těm
-těmu
-němu
-němuž
-jehož
-jíž
-jelikož
-jež
-jakož
-načež
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_da.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_da.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_da.txt
deleted file mode 100644
index 42e6145..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_da.txt
+++ /dev/null
@@ -1,110 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Danish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
-
-og | and
-i | in
-jeg | I
-det | that (dem. pronoun)/it (pers. pronoun)
-at | that (in front of a sentence)/to (with infinitive)
-en | a/an
-den | it (pers. pronoun)/that (dem. pronoun)
-til | to/at/for/until/against/by/of/into, more
-er | present tense of "to be"
-som | who, as
-på | on/upon/in/on/at/to/after/of/with/for, on
-de | they
-med | with/by/in, along
-han | he
-af | of/by/from/off/for/in/with/on, off
-for | at/for/to/from/by/of/ago, in front/before, because
-ikke | not
-der | who/which, there/those
-var | past tense of "to be"
-mig | me/myself
-sig | oneself/himself/herself/itself/themselves
-men | but
-et | a/an/one, one (number), someone/somebody/one
-har | present tense of "to have"
-om | round/about/for/in/a, about/around/down, if
-vi | we
-min | my
-havde | past tense of "to have"
-ham | him
-hun | she
-nu | now
-over | over/above/across/by/beyond/past/on/about, over/past
-da | then, when/as/since
-fra | from/off/since, off, since
-du | you
-ud | out
-sin | his/her/its/one's
-dem | them
-os | us/ourselves
-op | up
-man | you/one
-hans | his
-hvor | where
-eller | or
-hvad | what
-skal | must/shall etc.
-selv | myself/youself/herself/ourselves etc., even
-her | here
-alle | all/everyone/everybody etc.
-vil | will (verb)
-blev | past tense of "to stay/to remain/to get/to become"
-kunne | could
-ind | in
-når | when
-være | present tense of "to be"
-dog | however/yet/after all
-noget | something
-ville | would
-jo | you know/you see (adv), yes
-deres | their/theirs
-efter | after/behind/according to/for/by/from, later/afterwards
-ned | down
-skulle | should
-denne | this
-end | than
-dette | this
-mit | my/mine
-også | also
-under | under/beneath/below/during, below/underneath
-have | have
-dig | you
-anden | other
-hende | her
-mine | my
-alt | everything
-meget | much/very, plenty of
-sit | his, her, its, one's
-sine | his, her, its, one's
-vor | our
-mod | against
-disse | these
-hvis | if
-din | your/yours
-nogle | some
-hos | by/at
-blive | be/become
-mange | many
-ad | by/through
-bliver | present tense of "to be/to become"
-hendes | her/hers
-været | be
-thi | for (conj)
-jer | you
-sådan | such, like this/like that
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_de.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_de.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_de.txt
deleted file mode 100644
index 86525e7..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_de.txt
+++ /dev/null
@@ -1,294 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A German stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | The number of forms in this list is reduced significantly by passing it
- | through the German stemmer.
-
-
-aber | but
-
-alle | all
-allem
-allen
-aller
-alles
-
-als | than, as
-also | so
-am | an + dem
-an | at
-
-ander | other
-andere
-anderem
-anderen
-anderer
-anderes
-anderm
-andern
-anderr
-anders
-
-auch | also
-auf | on
-aus | out of
-bei | by
-bin | am
-bis | until
-bist | art
-da | there
-damit | with it
-dann | then
-
-der | the
-den
-des
-dem
-die
-das
-
-daß | that
-
-derselbe | the same
-derselben
-denselben
-desselben
-demselben
-dieselbe
-dieselben
-dasselbe
-
-dazu | to that
-
-dein | thy
-deine
-deinem
-deinen
-deiner
-deines
-
-denn | because
-
-derer | of those
-dessen | of him
-
-dich | thee
-dir | to thee
-du | thou
-
-dies | this
-diese
-diesem
-diesen
-dieser
-dieses
-
-
-doch | (several meanings)
-dort | (over) there
-
-
-durch | through
-
-ein | a
-eine
-einem
-einen
-einer
-eines
-
-einig | some
-einige
-einigem
-einigen
-einiger
-einiges
-
-einmal | once
-
-er | he
-ihn | him
-ihm | to him
-
-es | it
-etwas | something
-
-euer | your
-eure
-eurem
-euren
-eurer
-eures
-
-für | for
-gegen | towards
-gewesen | p.p. of sein
-hab | have
-habe | have
-haben | have
-hat | has
-hatte | had
-hatten | had
-hier | here
-hin | there
-hinter | behind
-
-ich | I
-mich | me
-mir | to me
-
-
-ihr | you, to her
-ihre
-ihrem
-ihren
-ihrer
-ihres
-euch | to you
-
-im | in + dem
-in | in
-indem | while
-ins | in + das
-ist | is
-
-jede | each, every
-jedem
-jeden
-jeder
-jedes
-
-jene | that
-jenem
-jenen
-jener
-jenes
-
-jetzt | now
-kann | can
-
-kein | no
-keine
-keinem
-keinen
-keiner
-keines
-
-können | can
-könnte | could
-machen | do
-man | one
-
-manche | some, many a
-manchem
-manchen
-mancher
-manches
-
-mein | my
-meine
-meinem
-meinen
-meiner
-meines
-
-mit | with
-muss | must
-musste | had to
-nach | to(wards)
-nicht | not
-nichts | nothing
-noch | still, yet
-nun | now
-nur | only
-ob | whether
-oder | or
-ohne | without
-sehr | very
-
-sein | his
-seine
-seinem
-seinen
-seiner
-seines
-
-selbst | self
-sich | herself
-
-sie | they, she
-ihnen | to them
-
-sind | are
-so | so
-
-solche | such
-solchem
-solchen
-solcher
-solches
-
-soll | shall
-sollte | should
-sondern | but
-sonst | else
-über | over
-um | about, around
-und | and
-
-uns | us
-unse
-unsem
-unsen
-unser
-unses
-
-unter | under
-viel | much
-vom | von + dem
-von | from
-vor | before
-während | while
-war | was
-waren | were
-warst | wast
-was | what
-weg | away, off
-weil | because
-weiter | further
-
-welche | which
-welchem
-welchen
-welcher
-welches
-
-wenn | when
-werde | will
-werden | will
-wie | how
-wieder | again
-will | want
-wir | we
-wird | will
-wirst | willst
-wo | where
-wollen | want
-wollte | wanted
-würde | would
-würden | would
-zu | to
-zum | zu + dem
-zur | zu + der
-zwar | indeed
-zwischen | between
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_el.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_el.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_el.txt
deleted file mode 100644
index 232681f..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_el.txt
+++ /dev/null
@@ -1,78 +0,0 @@
-# Lucene Greek Stopwords list
-# Note: by default this file is used after GreekLowerCaseFilter,
-# so when modifying this file use 'σ' instead of 'ς'
-ο
-η
-το
-οι
-τα
-του
-τησ
-των
-τον
-την
-και
-κι
-κ
-ειμαι
-εισαι
-ειναι
-ειμαστε
-ειστε
-στο
-στον
-στη
-στην
-μα
-αλλα
-απο
-για
-προσ
-με
-σε
-ωσ
-παρα
-αντι
-κατα
-μετα
-θα
-να
-δε
-δεν
-μη
-μην
-επι
-ενω
-εαν
-αν
-τοτε
-που
-πωσ
-ποιοσ
-ποια
-ποιο
-ποιοι
-ποιεσ
-ποιων
-ποιουσ
-αυτοσ
-αυτη
-αυτο
-αυτοι
-αυτων
-αυτουσ
-αυτεσ
-αυτα
-εκεινοσ
-εκεινη
-εκεινο
-εκεινοι
-εκεινεσ
-εκεινα
-εκεινων
-εκεινουσ
-οπωσ
-ομωσ
-ισωσ
-οσο
-οτι
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_en.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_en.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_en.txt
deleted file mode 100644
index 2c164c0..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_en.txt
+++ /dev/null
@@ -1,54 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# a couple of test stopwords to test that the words are really being
-# configured from this file:
-stopworda
-stopwordb
-
-# Standard english stop words taken from Lucene's StopAnalyzer
-a
-an
-and
-are
-as
-at
-be
-but
-by
-for
-if
-in
-into
-is
-it
-no
-not
-of
-on
-or
-such
-that
-the
-their
-then
-there
-these
-they
-this
-to
-was
-will
-with
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_es.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_es.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_es.txt
deleted file mode 100644
index 487d78c..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_es.txt
+++ /dev/null
@@ -1,356 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Spanish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-
- | The following is a ranked list (commonest to rarest) of stopwords
- | deriving from a large sample of text.
-
- | Extra words have been added at the end.
-
-de | from, of
-la | the, her
-que | who, that
-el | the
-en | in
-y | and
-a | to
-los | the, them
-del | de + el
-se | himself, from him etc
-las | the, them
-por | for, by, etc
-un | a
-para | for
-con | with
-no | no
-una | a
-su | his, her
-al | a + el
- | es from SER
-lo | him
-como | how
-más | more
-pero | pero
-sus | su plural
-le | to him, her
-ya | already
-o | or
- | fue from SER
-este | this
- | ha from HABER
-sí | himself etc
-porque | because
-esta | this
- | son from SER
-entre | between
- | está from ESTAR
-cuando | when
-muy | very
-sin | without
-sobre | on
- | ser from SER
- | tiene from TENER
-también | also
-me | me
-hasta | until
-hay | there is/are
-donde | where
- | han from HABER
-quien | whom, that
- | están from ESTAR
- | estado from ESTAR
-desde | from
-todo | all
-nos | us
-durante | during
- | estados from ESTAR
-todos | all
-uno | a
-les | to them
-ni | nor
-contra | against
-otros | other
- | fueron from SER
-ese | that
-eso | that
- | había from HABER
-ante | before
-ellos | they
-e | and (variant of y)
-esto | this
-mí | me
-antes | before
-algunos | some
-qué | what?
-unos | a
-yo | I
-otro | other
-otras | other
-otra | other
-él | he
-tanto | so much, many
-esa | that
-estos | these
-mucho | much, many
-quienes | who
-nada | nothing
-muchos | many
-cual | who
- | sea from SER
-poco | few
-ella | she
-estar | to be
- | haber from HABER
-estas | these
- | estaba from ESTAR
- | estamos from ESTAR
-algunas | some
-algo | something
-nosotros | we
-
- | other forms
-
-mi | me
-mis | mi plural
-tú | thou
-te | thee
-ti | thee
-tu | thy
-tus | tu plural
-ellas | they
-nosotras | we
-vosotros | you
-vosotras | you
-os | you
-mío | mine
-mía |
-míos |
-mías |
-tuyo | thine
-tuya |
-tuyos |
-tuyas |
-suyo | his, hers, theirs
-suya |
-suyos |
-suyas |
-nuestro | ours
-nuestra |
-nuestros |
-nuestras |
-vuestro | yours
-vuestra |
-vuestros |
-vuestras |
-esos | those
-esas | those
-
- | forms of estar, to be (not including the infinitive):
-estoy
-estás
-está
-estamos
-estáis
-están
-esté
-estés
-estemos
-estéis
-estén
-estaré
-estarás
-estará
-estaremos
-estaréis
-estarán
-estaría
-estarías
-estaríamos
-estaríais
-estarían
-estaba
-estabas
-estábamos
-estabais
-estaban
-estuve
-estuviste
-estuvo
-estuvimos
-estuvisteis
-estuvieron
-estuviera
-estuvieras
-estuviéramos
-estuvierais
-estuvieran
-estuviese
-estuvieses
-estuviésemos
-estuvieseis
-estuviesen
-estando
-estado
-estada
-estados
-estadas
-estad
-
- | forms of haber, to have (not including the infinitive):
-he
-has
-ha
-hemos
-habéis
-han
-haya
-hayas
-hayamos
-hayáis
-hayan
-habré
-habrás
-habrá
-habremos
-habréis
-habrán
-habría
-habrías
-habríamos
-habríais
-habrían
-había
-habías
-habíamos
-habíais
-habían
-hube
-hubiste
-hubo
-hubimos
-hubisteis
-hubieron
-hubiera
-hubieras
-hubiéramos
-hubierais
-hubieran
-hubiese
-hubieses
-hubiésemos
-hubieseis
-hubiesen
-habiendo
-habido
-habida
-habidos
-habidas
-
- | forms of ser, to be (not including the infinitive):
-soy
-eres
-es
-somos
-sois
-son
-sea
-seas
-seamos
-seáis
-sean
-seré
-serás
-será
-seremos
-seréis
-serán
-sería
-serías
-seríamos
-seríais
-serían
-era
-eras
-éramos
-erais
-eran
-fui
-fuiste
-fue
-fuimos
-fuisteis
-fueron
-fuera
-fueras
-fuéramos
-fuerais
-fueran
-fuese
-fueses
-fuésemos
-fueseis
-fuesen
-siendo
-sido
- | sed also means 'thirst'
-
- | forms of tener, to have (not including the infinitive):
-tengo
-tienes
-tiene
-tenemos
-tenéis
-tienen
-tenga
-tengas
-tengamos
-tengáis
-tengan
-tendré
-tendrás
-tendrá
-tendremos
-tendréis
-tendrán
-tendría
-tendrías
-tendríamos
-tendríais
-tendrían
-tenía
-tenías
-teníamos
-teníais
-tenían
-tuve
-tuviste
-tuvo
-tuvimos
-tuvisteis
-tuvieron
-tuviera
-tuvieras
-tuviéramos
-tuvierais
-tuvieran
-tuviese
-tuvieses
-tuviésemos
-tuvieseis
-tuviesen
-teniendo
-tenido
-tenida
-tenidos
-tenidas
-tened
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_eu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_eu.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_eu.txt
deleted file mode 100644
index 25f1db9..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_eu.txt
+++ /dev/null
@@ -1,99 +0,0 @@
-# example set of basque stopwords
-al
-anitz
-arabera
-asko
-baina
-bat
-batean
-batek
-bati
-batzuei
-batzuek
-batzuetan
-batzuk
-bera
-beraiek
-berau
-berauek
-bere
-berori
-beroriek
-beste
-bezala
-da
-dago
-dira
-ditu
-du
-dute
-edo
-egin
-ere
-eta
-eurak
-ez
-gainera
-gu
-gutxi
-guzti
-haiei
-haiek
-haietan
-hainbeste
-hala
-han
-handik
-hango
-hara
-hari
-hark
-hartan
-hau
-hauei
-hauek
-hauetan
-hemen
-hemendik
-hemengo
-hi
-hona
-honek
-honela
-honetan
-honi
-hor
-hori
-horiei
-horiek
-horietan
-horko
-horra
-horrek
-horrela
-horretan
-horri
-hortik
-hura
-izan
-ni
-noiz
-nola
-non
-nondik
-nongo
-nor
-nora
-ze
-zein
-zen
-zenbait
-zenbat
-zer
-zergatik
-ziren
-zituen
-zu
-zuek
-zuen
-zuten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fa.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fa.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fa.txt
deleted file mode 100644
index 723641c..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fa.txt
+++ /dev/null
@@ -1,313 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Note: by default this file is used after normalization, so when adding entries
-# to this file, use the arabic 'ي' instead of 'ی'
-انان
-نداشته
-سراسر
-خياه
-ايشان
-وي
-تاكنون
-بيشتري
-دوم
-پس
-ناشي
-وگو
-يا
-داشتند
-سپس
-هنگام
-هرگز
-پنج
-نشان
-امسال
-ديگر
-گروهي
-شدند
-چطور
-ده
-و
-دو
-نخستين
-ولي
-چرا
-چه
-وسط
-ه
-كدام
-قابل
-يك
-رفت
-هفت
-همچنين
-در
-هزار
-بله
-بلي
-شايد
-اما
-شناسي
-گرفته
-دهد
-داشته
-دانست
-داشتن
-خواهيم
-ميليارد
-وقتيكه
-امد
-خواهد
-جز
-اورده
-شده
-بلكه
-خدمات
-شدن
-برخي
-نبود
-بسياري
-جلوگيري
-حق
-كردند
-نوعي
-بعري
-نكرده
-نظير
-نبايد
-بوده
-بودن
-داد
-اورد
-هست
-جايي
-شود
-دنبال
-داده
-بايد
-سابق
-هيچ
-همان
-انجا
-كمتر
-كجاست
-گردد
-كسي
-تر
-مردم
-تان
-دادن
-بودند
-سري
-جدا
-ندارند
-مگر
-يكديگر
-دارد
-دهند
-بنابراين
-هنگامي
-سمت
-جا
-انچه
-خود
-دادند
-زياد
-دارند
-اثر
-بدون
-بهترين
-بيشتر
-البته
-به
-براساس
-بيرون
-كرد
-بعضي
-گرفت
-توي
-اي
-ميليون
-او
-جريان
-تول
-بر
-مانند
-برابر
-باشيم
-مدتي
-گويند
-اكنون
-تا
-تنها
-جديد
-چند
-بي
-نشده
-كردن
-كردم
-گويد
-كرده
-كنيم
-نمي
-نزد
-روي
-قصد
-فقط
-بالاي
-ديگران
-اين
-ديروز
-توسط
-سوم
-ايم
-دانند
-سوي
-استفاده
-شما
-كنار
-داريم
-ساخته
-طور
-امده
-رفته
-نخست
-بيست
-نزديك
-طي
-كنيد
-از
-انها
-تمامي
-داشت
-يكي
-طريق
-اش
-چيست
-روب
-نمايد
-گفت
-چندين
-چيزي
-تواند
-ام
-ايا
-با
-ان
-ايد
-ترين
-اينكه
-ديگري
-راه
-هايي
-بروز
-همچنان
-پاعين
-كس
-حدود
-مختلف
-مقابل
-چيز
-گيرد
-ندارد
-ضد
-همچون
-سازي
-شان
-مورد
-باره
-مرسي
-خويش
-برخوردار
-چون
-خارج
-شش
-هنوز
-تحت
-ضمن
-هستيم
-گفته
-فكر
-بسيار
-پيش
-براي
-روزهاي
-انكه
-نخواهد
-بالا
-كل
-وقتي
-كي
-چنين
-كه
-گيري
-نيست
-است
-كجا
-كند
-نيز
-يابد
-بندي
-حتي
-توانند
-عقب
-خواست
-كنند
-بين
-تمام
-همه
-ما
-باشند
-مثل
-شد
-اري
-باشد
-اره
-طبق
-بعد
-اگر
-صورت
-غير
-جاي
-بيش
-ريزي
-اند
-زيرا
-چگونه
-بار
-لطفا
-مي
-درباره
-من
-ديده
-همين
-گذاري
-برداري
-علت
-گذاشته
-هم
-فوق
-نه
-ها
-شوند
-اباد
-همواره
-هر
-اول
-خواهند
-چهار
-نام
-امروز
-مان
-هاي
-قبل
-كنم
-سعي
-تازه
-را
-هستند
-زير
-جلوي
-عنوان
-بود
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fi.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fi.txt
deleted file mode 100644
index 4372c9a..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fi.txt
+++ /dev/null
@@ -1,97 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
-| forms of BE
-
-olla
-olen
-olet
-on
-olemme
-olette
-ovat
-ole | negative form
-
-oli
-olisi
-olisit
-olisin
-olisimme
-olisitte
-olisivat
-olit
-olin
-olimme
-olitte
-olivat
-ollut
-olleet
-
-en | negation
-et
-ei
-emme
-ette
-eivät
-
-|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
-minä minun minut minua minussa minusta minuun minulla minulta minulle | I
-sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
-hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she
-me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we
-te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you
-he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they
-
-tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this
-tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
-se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it
-nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these
-nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
-ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they
-
-kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
-ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl)
-mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what
-mitkä | (pl)
-
-joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which
-jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl)
-
-| conjunctions
-
-että | that
-ja | and
-jos | if
-koska | because
-kuin | than
-mutta | but
-niin | so
-sekä | and
-sillä | for
-tai | or
-vaan | but
-vai | or
-vaikka | although
-
-
-| prepositions
-
-kanssa | with
-mukaan | according to
-noin | about
-poikki | across
-yli | over, across
-
-| other
-
-kun | when
-niin | so
-nyt | now
-itse | self
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fr.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fr.txt
deleted file mode 100644
index 749abae..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fr.txt
+++ /dev/null
@@ -1,186 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A French stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-au | a + le
-aux | a + les
-avec | with
-ce | this
-ces | these
-dans | with
-de | of
-des | de + les
-du | de + le
-elle | she
-en | `of them' etc
-et | and
-eux | them
-il | he
-je | I
-la | the
-le | the
-leur | their
-lui | him
-ma | my (fem)
-mais | but
-me | me
-même | same; as in moi-même (myself) etc
-mes | me (pl)
-moi | me
-mon | my (masc)
-ne | not
-nos | our (pl)
-notre | our
-nous | we
-on | one
-ou | where
-par | by
-pas | not
-pour | for
-qu | que before vowel
-que | that
-qui | who
-sa | his, her (fem)
-se | oneself
-ses | his (pl)
-son | his, her (masc)
-sur | on
-ta | thy (fem)
-te | thee
-tes | thy (pl)
-toi | thee
-ton | thy (masc)
-tu | thou
-un | a
-une | a
-vos | your (pl)
-votre | your
-vous | you
-
- | single letter forms
-
-c | c'
-d | d'
-j | j'
-l | l'
-à | to, at
-m | m'
-n | n'
-s | s'
-t | t'
-y | there
-
- | forms of être (not including the infinitive):
-été
-étée
-étées
-étés
-étant
-suis
-es
-est
-sommes
-êtes
-sont
-serai
-seras
-sera
-serons
-serez
-seront
-serais
-serait
-serions
-seriez
-seraient
-étais
-était
-étions
-étiez
-étaient
-fus
-fut
-fûmes
-fûtes
-furent
-sois
-soit
-soyons
-soyez
-soient
-fusse
-fusses
-fût
-fussions
-fussiez
-fussent
-
- | forms of avoir (not including the infinitive):
-ayant
-eu
-eue
-eues
-eus
-ai
-as
-avons
-avez
-ont
-aurai
-auras
-aura
-aurons
-aurez
-auront
-aurais
-aurait
-aurions
-auriez
-auraient
-avais
-avait
-avions
-aviez
-avaient
-eut
-eûmes
-eûtes
-eurent
-aie
-aies
-ait
-ayons
-ayez
-aient
-eusse
-eusses
-eût
-eussions
-eussiez
-eussent
-
- | Later additions (from Jean-Christophe Deschamps)
-ceci | this
-cela | that
-celà | that
-cet | this
-cette | this
-ici | here
-ils | they
-les | the (pl)
-leurs | their (pl)
-quel | which
-quels | which
-quelle | which
-quelles | which
-sans | without
-soi | oneself
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ga.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ga.txt
deleted file mode 100644
index 9ff88d7..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ga.txt
+++ /dev/null
@@ -1,110 +0,0 @@
-
-a
-ach
-ag
-agus
-an
-aon
-ar
-arna
-as
-b'
-ba
-beirt
-bhúr
-caoga
-ceathair
-ceathrar
-chomh
-chtó
-chuig
-chun
-cois
-céad
-cúig
-cúigear
-d'
-daichead
-dar
-de
-deich
-deichniúr
-den
-dhá
-do
-don
-dtí
-dá
-dár
-dó
-faoi
-faoin
-faoina
-faoinár
-fara
-fiche
-gach
-gan
-go
-gur
-haon
-hocht
-i
-iad
-idir
-in
-ina
-ins
-inár
-is
-le
-leis
-lena
-lenár
-m'
-mar
-mo
-mé
-na
-nach
-naoi
-naonúr
-ná
-ní
-níor
-nó
-nócha
-ocht
-ochtar
-os
-roimh
-sa
-seacht
-seachtar
-seachtó
-seasca
-seisear
-siad
-sibh
-sinn
-sna
-sé
-sí
-tar
-thar
-thú
-triúr
-trí
-trína
-trínár
-tríocha
-tú
-um
-ár
-é
-éis
-í
-ó
-ón
-óna
-ónár
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_gl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_gl.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_gl.txt
deleted file mode 100644
index d8760b1..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_gl.txt
+++ /dev/null
@@ -1,161 +0,0 @@
-# galican stopwords
-a
-aínda
-alí
-aquel
-aquela
-aquelas
-aqueles
-aquilo
-aquí
-ao
-aos
-as
-así
-á
-ben
-cando
-che
-co
-coa
-comigo
-con
-connosco
-contigo
-convosco
-coas
-cos
-cun
-cuns
-cunha
-cunhas
-da
-dalgunha
-dalgunhas
-dalgún
-dalgúns
-das
-de
-del
-dela
-delas
-deles
-desde
-deste
-do
-dos
-dun
-duns
-dunha
-dunhas
-e
-el
-ela
-elas
-eles
-en
-era
-eran
-esa
-esas
-ese
-eses
-esta
-estar
-estaba
-está
-están
-este
-estes
-estiven
-estou
-eu
-é
-facer
-foi
-foron
-fun
-había
-hai
-iso
-isto
-la
-las
-lle
-lles
-lo
-los
-mais
-me
-meu
-meus
-min
-miña
-miñas
-moi
-na
-nas
-neste
-nin
-no
-non
-nos
-nosa
-nosas
-noso
-nosos
-nós
-nun
-nunha
-nuns
-nunhas
-o
-os
-ou
-ó
-ós
-para
-pero
-pode
-pois
-pola
-polas
-polo
-polos
-por
-que
-se
-senón
-ser
-seu
-seus
-sexa
-sido
-sobre
-súa
-súas
-tamén
-tan
-te
-ten
-teñen
-teño
-ter
-teu
-teus
-ti
-tido
-tiña
-tiven
-túa
-túas
-un
-unha
-unhas
-uns
-vos
-vosa
-vosas
-voso
-vosos
-vós
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hi.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hi.txt
deleted file mode 100644
index 86286bb..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hi.txt
+++ /dev/null
@@ -1,235 +0,0 @@
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# Note: by default this file also contains forms normalized by HindiNormalizer
-# for spelling variation (see section below), such that it can be used whether or
-# not you enable that feature. When adding additional entries to this list,
-# please add the normalized form as well.
-अंदर
-अत
-अपना
-अपनी
-अपने
-अभी
-आदि
-आप
-इत्यादि
-इन
-इनका
-इन्हीं
-इन्हें
-इन्हों
-इस
-इसका
-इसकी
-इसके
-इसमें
-इसी
-इसे
-उन
-उनका
-उनकी
-उनके
-उनको
-उन्हीं
-उन्हें
-उन्हों
-उस
-उसके
-उसी
-उसे
-एक
-एवं
-एस
-ऐसे
-और
-कई
-कर
-करता
-करते
-करना
-करने
-करें
-कहते
-कहा
-का
-काफ़ी
-कि
-कितना
-किन्हें
-किन्हों
-किया
-किर
-किस
-किसी
-किसे
-की
-कुछ
-कुल
-के
-को
-कोई
-कौन
-कौनसा
-गया
-घर
-जब
-जहाँ
-जा
-जितना
-जिन
-जिन्हें
-जिन्हों
-जिस
-जिसे
-जीधर
-जैसा
-जैसे
-जो
-तक
-तब
-तरह
-तिन
-तिन्हें
-तिन्हों
-तिस
-तिसे
-तो
-था
-थी
-थे
-दबारा
-दिया
-दुसरा
-दूसरे
-दो
-द्वारा
-न
-नहीं
-ना
-निहायत
-नीचे
-ने
-पर
-पर
-पहले
-पूरा
-पे
-फिर
-बनी
-बही
-बहुत
-बाद
-बाला
-बिलकुल
-भी
-भीतर
-मगर
-मानो
-मे
-में
-यदि
-यह
-यहाँ
-यही
-या
-यिह
-ये
-रखें
-रहा
-रहे
-ऱ्वासा
-लिए
-लिये
-लेकिन
-व
-वर्ग
-वह
-वह
-वहाँ
-वहीं
-वाले
-वुह
-वे
-वग़ैरह
-संग
-सकता
-सकते
-सबसे
-सभी
-साथ
-साबुत
-साभ
-सारा
-से
-सो
-ही
-हुआ
-हुई
-हुए
-है
-हैं
-हो
-होता
-होती
-होते
-होना
-होने
-# additional normalized forms of the above
-अपनि
-जेसे
-होति
-सभि
-तिंहों
-इंहों
-दवारा
-इसि
-किंहें
-थि
-उंहों
-ओर
-जिंहें
-वहिं
-अभि
-बनि
-हि
-उंहिं
-उंहें
-हें
-वगेरह
-एसे
-रवासा
-कोन
-निचे
-काफि
-उसि
-पुरा
-भितर
-हे
-बहि
-वहां
-कोइ
-यहां
-जिंहों
-तिंहें
-किसि
-कइ
-यहि
-इंहिं
-जिधर
-इंहें
-अदि
-इतयादि
-हुइ
-कोनसा
-इसकि
-दुसरे
-जहां
-अप
-किंहों
-उनकि
-भि
-वरग
-हुअ
-जेसा
-नहिं
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hu.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hu.txt
deleted file mode 100644
index 37526da..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hu.txt
+++ /dev/null
@@ -1,211 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
-| Hungarian stop word list
-| prepared by Anna Tordai
-
-a
-ahogy
-ahol
-aki
-akik
-akkor
-alatt
-által
-általában
-amely
-amelyek
-amelyekben
-amelyeket
-amelyet
-amelynek
-ami
-amit
-amolyan
-amíg
-amikor
-át
-abban
-ahhoz
-annak
-arra
-arról
-az
-azok
-azon
-azt
-azzal
-azért
-aztán
-azután
-azonban
-bár
-be
-belül
-benne
-cikk
-cikkek
-cikkeket
-csak
-de
-e
-eddig
-egész
-egy
-egyes
-egyetlen
-egyéb
-egyik
-egyre
-ekkor
-el
-elég
-ellen
-elő
-először
-előtt
-első
-én
-éppen
-ebben
-ehhez
-emilyen
-ennek
-erre
-ez
-ezt
-ezek
-ezen
-ezzel
-ezért
-és
-fel
-felé
-hanem
-hiszen
-hogy
-hogyan
-igen
-így
-illetve
-ill.
-ill
-ilyen
-ilyenkor
-ison
-ismét
-itt
-jó
-jól
-jobban
-kell
-kellett
-keresztül
-keressünk
-ki
-kívül
-között
-közül
-legalább
-lehet
-lehetett
-legyen
-lenne
-lenni
-lesz
-lett
-maga
-magát
-majd
-majd
-már
-más
-másik
-meg
-még
-mellett
-mert
-mely
-melyek
-mi
-mit
-míg
-miért
-milyen
-mikor
-minden
-mindent
-mindenki
-mindig
-mint
-mintha
-mivel
-most
-nagy
-nagyobb
-nagyon
-ne
-néha
-nekem
-neki
-nem
-néhány
-nélkül
-nincs
-olyan
-ott
-össze
-ő
-ők
-őket
-pedig
-persze
-rá
-s
-saját
-sem
-semmi
-sok
-sokat
-sokkal
-számára
-szemben
-szerint
-szinte
-talán
-tehát
-teljes
-tovább
-továbbá
-több
-úgy
-ugyanis
-új
-újabb
-újra
-után
-utána
-utolsó
-vagy
-vagyis
-valaki
-valami
-valamint
-való
-vagyok
-van
-vannak
-volt
-voltam
-voltak
-voltunk
-vissza
-vele
-viszont
-volna
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hy.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hy.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hy.txt
deleted file mode 100644
index 60c1c50..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hy.txt
+++ /dev/null
@@ -1,46 +0,0 @@
-# example set of Armenian stopwords.
-այդ
-այլ
-այն
-այս
-դու
-դուք
-եմ
-են
-ենք
-ես
-եք
-է
-էի
-էին
-էինք
-էիր
-էիք
-էր
-ըստ
-թ
-ի
-ին
-իսկ
-իր
-կամ
-համար
-հետ
-հետո
-մենք
-մեջ
-մի
-ն
-նա
-նաև
-նրա
-նրանք
-որ
-որը
-որոնք
-որպես
-ու
-ում
-պիտի
-վրա
-և
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_id.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_id.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_id.txt
deleted file mode 100644
index 4617f83..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_id.txt
+++ /dev/null
@@ -1,359 +0,0 @@
-# from appendix D of: A Study of Stemming Effects on Information
-# Retrieval in Bahasa Indonesia
-ada
-adanya
-adalah
-adapun
-agak
-agaknya
-agar
-akan
-akankah
-akhirnya
-aku
-akulah
-amat
-amatlah
-anda
-andalah
-antar
-diantaranya
-antara
-antaranya
-diantara
-apa
-apaan
-mengapa
-apabila
-apakah
-apalagi
-apatah
-atau
-ataukah
-ataupun
-bagai
-bagaikan
-sebagai
-sebagainya
-bagaimana
-bagaimanapun
-sebagaimana
-bagaimanakah
-bagi
-bahkan
-bahwa
-bahwasanya
-sebaliknya
-banyak
-sebanyak
-beberapa
-seberapa
-begini
-beginian
-beginikah
-beginilah
-sebegini
-begitu
-begitukah
-begitulah
-begitupun
-sebegitu
-belum
-belumlah
-sebelum
-sebelumnya
-sebenarnya
-berapa
-berapakah
-berapalah
-berapapun
-betulkah
-sebetulnya
-biasa
-biasanya
-bila
-bilakah
-bisa
-bisakah
-sebisanya
-boleh
-bolehkah
-bolehlah
-buat
-bukan
-bukankah
-bukanlah
-bukannya
-cuma
-percuma
-dahulu
-dalam
-dan
-dapat
-dari
-daripada
-dekat
-demi
-demikian
-demikianlah
-sedemikian
-dengan
-depan
-di
-dia
-dialah
-dini
-diri
-dirinya
-terdiri
-dong
-dulu
-enggak
-enggaknya
-entah
-entahlah
-terhadap
-terhadapnya
-hal
-hampir
-hanya
-hanyalah
-harus
-haruslah
-harusnya
-seharusnya
-hendak
-hendaklah
-hendaknya
-hingga
-sehingga
-ia
-ialah
-ibarat
-ingin
-inginkah
-inginkan
-ini
-inikah
-inilah
-itu
-itukah
-itulah
-jangan
-jangankan
-janganlah
-jika
-jikalau
-juga
-justru
-kala
-kalau
-kalaulah
-kalaupun
-kalian
-kami
-kamilah
-kamu
-kamulah
-kan
-kapan
-kapankah
-kapanpun
-dikarenakan
-karena
-karenanya
-ke
-kecil
-kemudian
-kenapa
-kepada
-kepadanya
-ketika
-seketika
-khususnya
-kini
-kinilah
-kiranya
-sekiranya
-kita
-kitalah
-kok
-lagi
-lagian
-selagi
-lah
-lain
-lainnya
-melainkan
-selaku
-lalu
-melalui
-terlalu
-lama
-lamanya
-selama
-selama
-selamanya
-lebih
-terlebih
-bermacam
-macam
-semacam
-maka
-makanya
-makin
-malah
-malahan
-mampu
-mampukah
-mana
-manakala
-manalagi
-masih
-masihkah
-semasih
-masing
-mau
-maupun
-semaunya
-memang
-mereka
-merekalah
-meski
-meskipun
-semula
-mungkin
-mungkinkah
-nah
-namun
-nanti
-nantinya
-nyaris
-oleh
-olehnya
-seorang
-seseorang
-pada
-padanya
-padahal
-paling
-sepanjang
-pantas
-sepantasnya
-sepantasnyalah
-para
-pasti
-pastilah
-per
-pernah
-pula
-pun
-merupakan
-rupanya
-serupa
-saat
-saatnya
-sesaat
-saja
-sajalah
-saling
-bersama
-sama
-sesama
-sambil
-sampai
-sana
-sangat
-sangatlah
-saya
-sayalah
-se
-sebab
-sebabnya
-sebuah
-tersebut
-tersebutlah
-sedang
-sedangkan
-sedikit
-sedikitnya
-segala
-segalanya
-segera
-sesegera
-sejak
-sejenak
-sekali
-sekalian
-sekalipun
-sesekali
-sekaligus
-sekarang
-sekarang
-sekitar
-sekitarnya
-sela
-selain
-selalu
-seluruh
-seluruhnya
-semakin
-sementara
-sempat
-semua
-semuanya
-sendiri
-sendirinya
-seolah
-seperti
-sepertinya
-sering
-seringnya
-serta
-siapa
-siapakah
-siapapun
-disini
-disinilah
-sini
-sinilah
-sesuatu
-sesuatunya
-suatu
-sesudah
-sesudahnya
-sudah
-sudahkah
-sudahlah
-supaya
-tadi
-tadinya
-tak
-tanpa
-setelah
-telah
-tentang
-tentu
-tentulah
-tentunya
-tertentu
-seterusnya
-tapi
-tetapi
-setiap
-tiap
-setidaknya
-tidak
-tidakkah
-tidaklah
-toh
-waduh
-wah
-wahai
-sewaktu
-walau
-walaupun
-wong
-yaitu
-yakni
-yang
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_it.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_it.txt
deleted file mode 100644
index 1219cc7..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_it.txt
+++ /dev/null
@@ -1,303 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | An Italian stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-ad | a (to) before vowel
-al | a + il
-allo | a + lo
-ai | a + i
-agli | a + gli
-all | a + l'
-agl | a + gl'
-alla | a + la
-alle | a + le
-con | with
-col | con + il
-coi | con + i (forms collo, cogli etc are now very rare)
-da | from
-dal | da + il
-dallo | da + lo
-dai | da + i
-dagli | da + gli
-dall | da + l'
-dagl | da + gll'
-dalla | da + la
-dalle | da + le
-di | of
-del | di + il
-dello | di + lo
-dei | di + i
-degli | di + gli
-dell | di + l'
-degl | di + gl'
-della | di + la
-delle | di + le
-in | in
-nel | in + el
-nello | in + lo
-nei | in + i
-negli | in + gli
-nell | in + l'
-negl | in + gl'
-nella | in + la
-nelle | in + le
-su | on
-sul | su + il
-sullo | su + lo
-sui | su + i
-sugli | su + gli
-sull | su + l'
-sugl | su + gl'
-sulla | su + la
-sulle | su + le
-per | through, by
-tra | among
-contro | against
-io | I
-tu | thou
-lui | he
-lei | she
-noi | we
-voi | you
-loro | they
-mio | my
-mia |
-miei |
-mie |
-tuo |
-tua |
-tuoi | thy
-tue |
-suo |
-sua |
-suoi | his, her
-sue |
-nostro | our
-nostra |
-nostri |
-nostre |
-vostro | your
-vostra |
-vostri |
-vostre |
-mi | me
-ti | thee
-ci | us, there
-vi | you, there
-lo | him, the
-la | her, the
-li | them
-le | them, the
-gli | to him, the
-ne | from there etc
-il | the
-un | a
-uno | a
-una | a
-ma | but
-ed | and
-se | if
-perché | why, because
-anche | also
-come | how
-dov | where (as dov')
-dove | where
-che | who, that
-chi | who
-cui | whom
-non | not
-più | more
-quale | who, that
-quanto | how much
-quanti |
-quanta |
-quante |
-quello | that
-quelli |
-quella |
-quelle |
-questo | this
-questi |
-questa |
-queste |
-si | yes
-tutto | all
-tutti | all
-
- | single letter forms:
-
-a | at
-c | as c' for ce or ci
-e | and
-i | the
-l | as l'
-o | or
-
- | forms of avere, to have (not including the infinitive):
-
-ho
-hai
-ha
-abbiamo
-avete
-hanno
-abbia
-abbiate
-abbiano
-avrò
-avrai
-avrà
-avremo
-avrete
-avranno
-avrei
-avresti
-avrebbe
-avremmo
-avreste
-avrebbero
-avevo
-avevi
-aveva
-avevamo
-avevate
-avevano
-ebbi
-avesti
-ebbe
-avemmo
-aveste
-ebbero
-avessi
-avesse
-avessimo
-avessero
-avendo
-avuto
-avuta
-avuti
-avute
-
- | forms of essere, to be (not including the infinitive):
-sono
-sei
-è
-siamo
-siete
-sia
-siate
-siano
-sarò
-sarai
-sarà
-saremo
-sarete
-saranno
-sarei
-saresti
-sarebbe
-saremmo
-sareste
-sarebbero
-ero
-eri
-era
-eravamo
-eravate
-erano
-fui
-fosti
-fu
-fummo
-foste
-furono
-fossi
-fosse
-fossimo
-fossero
-essendo
-
- | forms of fare, to do (not including the infinitive, fa, fat-):
-faccio
-fai
-facciamo
-fanno
-faccia
-facciate
-facciano
-farò
-farai
-farà
-faremo
-farete
-faranno
-farei
-faresti
-farebbe
-faremmo
-fareste
-farebbero
-facevo
-facevi
-faceva
-facevamo
-facevate
-facevano
-feci
-facesti
-fece
-facemmo
-faceste
-fecero
-facessi
-facesse
-facessimo
-facessero
-facendo
-
- | forms of stare, to be (not including the infinitive):
-sto
-stai
-sta
-stiamo
-stanno
-stia
-stiate
-stiano
-starò
-starai
-starà
-staremo
-starete
-staranno
-starei
-staresti
-starebbe
-staremmo
-stareste
-starebbero
-stavo
-stavi
-stava
-stavamo
-stavate
-stavano
-stetti
-stesti
-stette
-stemmo
-steste
-stettero
-stessi
-stesse
-stessimo
-stessero
-stando
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ja.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ja.txt
deleted file mode 100644
index d4321be..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ja.txt
+++ /dev/null
@@ -1,127 +0,0 @@
-#
-# This file defines a stopword set for Japanese.
-#
-# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
-# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
-# for frequency lists, etc. that can be useful for making your own set (if desired)
-#
-# Note that there is an overlap between these stopwords and the terms stopped when used
-# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
-# that comments are not allowed on the same line as stopwords.
-#
-# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
-# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
-# using the same character width as the entries in this file. Since this StopFilter is
-# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
-# entries to be in half-width and your kana entries to be in full-width.
-#
-の
-に
-は
-を
-た
-が
-で
-て
-と
-し
-れ
-さ
-ある
-いる
-も
-する
-から
-な
-こと
-として
-い
-や
-れる
-など
-なっ
-ない
-この
-ため
-その
-あっ
-よう
-また
-もの
-という
-あり
-まで
-られ
-なる
-へ
-か
-だ
-これ
-によって
-により
-おり
-より
-による
-ず
-なり
-られる
-において
-ば
-なかっ
-なく
-しかし
-について
-せ
-だっ
-その後
-できる
-それ
-う
-ので
-なお
-のみ
-でき
-き
-つ
-における
-および
-いう
-さらに
-でも
-ら
-たり
-その他
-に関する
-たち
-ます
-ん
-なら
-に対して
-特に
-せる
-及び
-これら
-とき
-では
-にて
-ほか
-ながら
-うち
-そして
-とともに
-ただし
-かつて
-それぞれ
-または
-お
-ほど
-ものの
-に対する
-ほとんど
-と共に
-といった
-です
-とも
-ところ
-ここ
-##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_lv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_lv.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_lv.txt
deleted file mode 100644
index e21a23c..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_lv.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
-# the original list of over 800 forms was refined:
-# pronouns, adverbs, interjections were removed
-#
-# prepositions
-aiz
-ap
-ar
-apakš
-ārpus
-augšpus
-bez
-caur
-dēļ
-gar
-iekš
-iz
-kopš
-labad
-lejpus
-līdz
-no
-otrpus
-pa
-par
-pār
-pēc
-pie
-pirms
-pret
-priekš
-starp
-šaipus
-uz
-viņpus
-virs
-virspus
-zem
-apakšpus
-# Conjunctions
-un
-bet
-jo
-ja
-ka
-lai
-tomēr
-tikko
-turpretī
-arī
-kaut
-gan
-tādēļ
-tā
-ne
-tikvien
-vien
-kā
-ir
-te
-vai
-kamēr
-# Particles
-ar
-diezin
-droši
-diemžēl
-nebūt
-ik
-it
-taču
-nu
-pat
-tiklab
-iekšpus
-nedz
-tik
-nevis
-turpretim
-jeb
-iekam
-iekām
-iekāms
-kolīdz
-līdzko
-tiklīdz
-jebšu
-tālab
-tāpēc
-nekā
-itin
-jā
-jau
-jel
-nē
-nezin
-tad
-tikai
-vis
-tak
-iekams
-vien
-# modal verbs
-būt
-biju
-biji
-bija
-bijām
-bijāt
-esmu
-esi
-esam
-esat
-būšu
-būsi
-būs
-būsim
-būsiet
-tikt
-tiku
-tiki
-tika
-tikām
-tikāt
-tieku
-tiec
-tiek
-tiekam
-tiekat
-tikšu
-tiks
-tiksim
-tiksiet
-tapt
-tapi
-tapāt
-topat
-tapšu
-tapsi
-taps
-tapsim
-tapsiet
-kļūt
-kļuvu
-kļuvi
-kļuva
-kļuvām
-kļuvāt
-kļūstu
-kļūsti
-kļūst
-kļūstam
-kļūstat
-kļūšu
-kļūsi
-kļūs
-kļūsim
-kļūsiet
-# verbs
-varēt
-varēju
-varējām
-varēšu
-varēsim
-var
-varēji
-varējāt
-varēsi
-varēsiet
-varat
-varēja
-varēs
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_nl.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_nl.txt
deleted file mode 100644
index 47a2aea..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_nl.txt
+++ /dev/null
@@ -1,119 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Dutch stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large sample of Dutch text.
-
- | Dutch stop words frequently exhibit homonym clashes. These are indicated
- | clearly below.
-
-de | the
-en | and
-van | of, from
-ik | I, the ego
-te | (1) chez, at etc, (2) to, (3) too
-dat | that, which
-die | that, those, who, which
-in | in, inside
-een | a, an, one
-hij | he
-het | the, it
-niet | not, nothing, naught
-zijn | (1) to be, being, (2) his, one's, its
-is | is
-was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
-op | on, upon, at, in, up, used up
-aan | on, upon, to (as dative)
-met | with, by
-als | like, such as, when
-voor | (1) before, in front of, (2) furrow
-had | had, past tense all persons sing. of 'hebben' (have)
-er | there
-maar | but, only
-om | round, about, for etc
-hem | him
-dan | then
-zou | should/would, past tense all persons sing. of 'zullen'
-of | or, whether, if
-wat | what, something, anything
-mijn | possessive and noun 'mine'
-men | people, 'one'
-dit | this
-zo | so, thus, in this way
-door | through by
-over | over, across
-ze | she, her, they, them
-zich | oneself
-bij | (1) a bee, (2) by, near, at
-ook | also, too
-tot | till, until
-je | you
-mij | me
-uit | out of, from
-der | Old Dutch form of 'van der' still found in surnames
-daar | (1) there, (2) because
-haar | (1) her, their, them, (2) hair
-naar | (1) unpleasant, unwell etc, (2) towards, (3) as
-heb | present first person sing. of 'to have'
-hoe | how, why
-heeft | present third person sing. of 'to have'
-hebben | 'to have' and various parts thereof
-deze | this
-u | you
-want | (1) for, (2) mitten, (3) rigging
-nog | yet, still
-zal | 'shall', first and third person sing. of verb 'zullen' (will)
-me | me
-zij | she, they
-nu | now
-ge | 'thou', still used in Belgium and south Netherlands
-geen | none
-omdat | because
-iets | something, somewhat
-worden | to become, grow, get
-toch | yet, still
-al | all, every, each
-waren | (1) 'were' (2) to wander, (3) wares, (3)
-veel | much, many
-meer | (1) more, (2) lake
-doen | to do, to make
-toen | then, when
-moet | noun 'spot/mote' and present form of 'to must'
-ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
-zonder | without
-kan | noun 'can' and present form of 'to be able'
-hun | their, them
-dus | so, consequently
-alles | all, everything, anything
-onder | under, beneath
-ja | yes, of course
-eens | once, one day
-hier | here
-wie | who
-werd | imperfect third person sing. of 'become'
-altijd | always
-doch | yet, but etc
-wordt | present third person sing. of 'become'
-wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
-kunnen | to be able
-ons | us/our
-zelf | self
-tegen | against, towards, at
-na | after, near
-reeds | already
-wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
-kon | could; past tense of 'to be able'
-niets | nothing
-uw | your
-iemand | somebody
-geweest | been; past participle of 'be'
-andere | other
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_no.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_no.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_no.txt
deleted file mode 100644
index a7a2c28..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_no.txt
+++ /dev/null
@@ -1,194 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Norwegian stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This stop word list is for the dominant bokmål dialect. Words unique
- | to nynorsk are marked *.
-
- | Revised by Jan Bruusgaard <Ja...@ssb.no>, Jan 2005
-
-og | and
-i | in
-jeg | I
-det | it/this/that
-at | to (w. inf.)
-en | a/an
-et | a/an
-den | it/this/that
-til | to
-er | is/am/are
-som | who/that
-på | on
-de | they / you(formal)
-med | with
-han | he
-av | of
-ikke | not
-ikkje | not *
-der | there
-så | so
-var | was/were
-meg | me
-seg | you
-men | but
-ett | one
-har | have
-om | about
-vi | we
-min | my
-mitt | my
-ha | have
-hadde | had
-hun | she
-nå | now
-over | over
-da | when/as
-ved | by/know
-fra | from
-du | you
-ut | out
-sin | your
-dem | them
-oss | us
-opp | up
-man | you/one
-kan | can
-hans | his
-hvor | where
-eller | or
-hva | what
-skal | shall/must
-selv | self (reflective)
-sjøl | self (reflective)
-her | here
-alle | all
-vil | will
-bli | become
-ble | became
-blei | became *
-blitt | have become
-kunne | could
-inn | in
-når | when
-være | be
-kom | come
-noen | some
-noe | some
-ville | would
-dere | you
-som | who/which/that
-deres | their/theirs
-kun | only/just
-ja | yes
-etter | after
-ned | down
-skulle | should
-denne | this
-for | for/because
-deg | you
-si | hers/his
-sine | hers/his
-sitt | hers/his
-mot | against
-å | to
-meget | much
-hvorfor | why
-dette | this
-disse | these/those
-uten | without
-hvordan | how
-ingen | none
-din | your
-ditt | your
-blir | become
-samme | same
-hvilken | which
-hvilke | which (plural)
-sånn | such a
-inni | inside/within
-mellom | between
-vår | our
-hver | each
-hvem | who
-vors | us/ours
-hvis | whose
-både | both
-bare | only/just
-enn | than
-fordi | as/because
-før | before
-mange | many
-også | also
-slik | just
-vært | been
-være | to be
-båe | both *
-begge | both
-siden | since
-dykk | your *
-dykkar | yours *
-dei | they *
-deira | them *
-deires | theirs *
-deim | them *
-di | your (fem.) *
-då | as/when *
-eg | I *
-ein | a/an *
-eit | a/an *
-eitt | a/an *
-elles | or *
-honom | he *
-hjå | at *
-ho | she *
-hoe | she *
-henne | her
-hennar | her/hers
-hennes | hers
-hoss | how *
-hossen | how *
-ikkje | not *
-ingi | noone *
-inkje | noone *
-korleis | how *
-korso | how *
-kva | what/which *
-kvar | where *
-kvarhelst | where *
-kven | who/whom *
-kvi | why *
-kvifor | why *
-me | we *
-medan | while *
-mi | my *
-mine | my *
-mykje | much *
-no | now *
-nokon | some (masc./neut.) *
-noka | some (fem.) *
-nokor | some *
-noko | some *
-nokre | some *
-si | his/hers *
-sia | since *
-sidan | since *
-so | so *
-somt | some *
-somme | some *
-um | about*
-upp | up *
-vere | be *
-vore | was *
-verte | become *
-vort | become *
-varte | became *
-vart | became *
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_pt.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_pt.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_pt.txt
deleted file mode 100644
index acfeb01..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_pt.txt
+++ /dev/null
@@ -1,253 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Portuguese stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-
- | The following is a ranked list (commonest to rarest) of stopwords
- | deriving from a large sample of text.
-
- | Extra words have been added at the end.
-
-de | of, from
-a | the; to, at; her
-o | the; him
-que | who, that
-e | and
-do | de + o
-da | de + a
-em | in
-um | a
-para | for
- | é from SER
-com | with
-não | not, no
-uma | a
-os | the; them
-no | em + o
-se | himself etc
-na | em + a
-por | for
-mais | more
-as | the; them
-dos | de + os
-como | as, like
-mas | but
- | foi from SER
-ao | a + o
-ele | he
-das | de + as
- | tem from TER
-à | a + a
-seu | his
-sua | her
-ou | or
- | ser from SER
-quando | when
-muito | much
- | há from HAV
-nos | em + os; us
-já | already, now
- | está from EST
-eu | I
-também | also
-só | only, just
-pelo | per + o
-pela | per + a
-até | up to
-isso | that
-ela | he
-entre | between
- | era from SER
-depois | after
-sem | without
-mesmo | same
-aos | a + os
- | ter from TER
-seus | his
-quem | whom
-nas | em + as
-me | me
-esse | that
-eles | they
- | estão from EST
-você | you
- | tinha from TER
- | foram from SER
-essa | that
-num | em + um
-nem | nor
-suas | her
-meu | my
-às | a + as
-minha | my
- | têm from TER
-numa | em + uma
-pelos | per + os
-elas | they
- | havia from HAV
- | seja from SER
-qual | which
- | será from SER
-nós | we
- | tenho from TER
-lhe | to him, her
-deles | of them
-essas | those
-esses | those
-pelas | per + as
-este | this
- | fosse from SER
-dele | of him
-
- | other words. There are many contractions such as naquele = em+aquele,
- | mo = me+o, but they are rare.
- | Indefinite article plural forms are also rare.
-
-tu | thou
-te | thee
-vocês | you (plural)
-vos | you
-lhes | to them
-meus | my
-minhas
-teu | thy
-tua
-teus
-tuas
-nosso | our
-nossa
-nossos
-nossas
-
-dela | of her
-delas | of them
-
-esta | this
-estes | these
-estas | these
-aquele | that
-aquela | that
-aqueles | those
-aquelas | those
-isto | this
-aquilo | that
-
- | forms of estar, to be (not including the infinitive):
-estou
-está
-estamos
-estão
-estive
-esteve
-estivemos
-estiveram
-estava
-estávamos
-estavam
-estivera
-estivéramos
-esteja
-estejamos
-estejam
-estivesse
-estivéssemos
-estivessem
-estiver
-estivermos
-estiverem
-
- | forms of haver, to have (not including the infinitive):
-hei
-há
-havemos
-hão
-houve
-houvemos
-houveram
-houvera
-houvéramos
-haja
-hajamos
-hajam
-houvesse
-houvéssemos
-houvessem
-houver
-houvermos
-houverem
-houverei
-houverá
-houveremos
-houverão
-houveria
-houveríamos
-houveriam
-
- | forms of ser, to be (not including the infinitive):
-sou
-somos
-são
-era
-éramos
-eram
-fui
-foi
-fomos
-foram
-fora
-fôramos
-seja
-sejamos
-sejam
-fosse
-fôssemos
-fossem
-for
-formos
-forem
-serei
-será
-seremos
-serão
-seria
-seríamos
-seriam
-
- | forms of ter, to have (not including the infinitive):
-tenho
-tem
-temos
-tém
-tinha
-tínhamos
-tinham
-tive
-teve
-tivemos
-tiveram
-tivera
-tivéramos
-tenha
-tenhamos
-tenham
-tivesse
-tivéssemos
-tivessem
-tiver
-tivermos
-tiverem
-terei
-terá
-teremos
-terão
-teria
-teríamos
-teriam
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ro.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ro.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ro.txt
deleted file mode 100644
index 4fdee90..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ro.txt
+++ /dev/null
@@ -1,233 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-acea
-aceasta
-această
-aceea
-acei
-aceia
-acel
-acela
-acele
-acelea
-acest
-acesta
-aceste
-acestea
-aceşti
-aceştia
-acolo
-acum
-ai
-aia
-aibă
-aici
-al
-ăla
-ale
-alea
-ălea
-altceva
-altcineva
-am
-ar
-are
-aş
-aşadar
-asemenea
-asta
-ăsta
-astăzi
-astea
-ăstea
-ăştia
-asupra
-aţi
-au
-avea
-avem
-aveţi
-azi
-bine
-bucur
-bună
-ca
-că
-căci
-când
-care
-cărei
-căror
-cărui
-cât
-câte
-câţi
-către
-câtva
-ce
-cel
-ceva
-chiar
-cînd
-cine
-cineva
-cît
-cîte
-cîţi
-cîtva
-contra
-cu
-cum
-cumva
-curând
-curînd
-da
-dă
-dacă
-dar
-datorită
-de
-deci
-deja
-deoarece
-departe
-deşi
-din
-dinaintea
-dintr
-dintre
-drept
-după
-ea
-ei
-el
-ele
-eram
-este
-eşti
-eu
-face
-fără
-fi
-fie
-fiecare
-fii
-fim
-fiţi
-iar
-ieri
-îi
-îl
-îmi
-împotriva
-în
-înainte
-înaintea
-încât
-încît
-încotro
-între
-întrucât
-întrucît
-îţi
-la
-lângă
-le
-li
-lîngă
-lor
-lui
-mă
-mâine
-mea
-mei
-mele
-mereu
-meu
-mi
-mine
-mult
-multă
-mulţi
-ne
-nicăieri
-nici
-nimeni
-nişte
-noastră
-noastre
-noi
-noştri
-nostru
-nu
-ori
-oricând
-oricare
-oricât
-orice
-oricînd
-oricine
-oricît
-oricum
-oriunde
-până
-pe
-pentru
-peste
-pînă
-poate
-pot
-prea
-prima
-primul
-prin
-printr
-sa
-să
-săi
-sale
-sau
-său
-se
-şi
-sînt
-sîntem
-sînteţi
-spre
-sub
-sunt
-suntem
-sunteţi
-ta
-tăi
-tale
-tău
-te
-ţi
-ţie
-tine
-toată
-toate
-tot
-toţi
-totuşi
-tu
-un
-una
-unde
-undeva
-unei
-unele
-uneori
-unor
-vă
-vi
-voastră
-voastre
-voi
-voştri
-vostru
-vouă
-vreo
-vreun
[02/50] [abbrv] lucene-solr:feature/autoscaling: Ref Guide: Add mod
evaluator docs
Posted by sh...@apache.org.
Ref Guide: Add mod evaluator docs
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/584b69d3
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/584b69d3
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/584b69d3
Branch: refs/heads/feature/autoscaling
Commit: 584b69d3f20c7afa7c9af53bf0eac0eebc140b0c
Parents: a5b1327
Author: Joel Bernstein <jb...@apache.org>
Authored: Fri Jun 16 14:18:54 2017 -0400
Committer: Joel Bernstein <jb...@apache.org>
Committed: Fri Jun 16 14:18:54 2017 -0400
----------------------------------------------------------------------
solr/solr-ref-guide/src/stream-evaluators.adoc | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/584b69d3/solr/solr-ref-guide/src/stream-evaluators.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/stream-evaluators.adoc b/solr/solr-ref-guide/src/stream-evaluators.adoc
index aec9bd2..bc6d13e 100644
--- a/solr/solr-ref-guide/src/stream-evaluators.adoc
+++ b/solr/solr-ref-guide/src/stream-evaluators.adoc
@@ -212,7 +212,23 @@ if(gt(fieldA,fieldB),pow(fieldA,fieldB),pow(fieldB,fieldA)) // if fieldA > field
----
== mod
-//TODO
+The `mod` function returns the remainder (modulo) of the first parameter divided by the second parameter.
+
+=== mod Parameters
+
+* `Field Name | Raw Number | Number Evaluator`: Parameter 1
+* `Field Name | Raw Number | Number Evaluator`: Parameter 2
+
+=== mod Syntax
+
+The expressions below show the various ways in which you can use the `mod` evaluator.
+
+[source,text]
+----
+mod(100,3) // returns the remainder of 100 / 3 .
+mod(100,fieldA) // returns the remainder of 100 divided by the value of fieldA.
+mod(fieldA,1.4) // returns the remainder of fieldA divided by 1.4.
+if(gt(fieldA,fieldB),mod(fieldA,fieldB),mod(fieldB,fieldA)) // if fieldA > fieldB then return the remainder of fieldA/fieldB, else return the remainder of fieldB/fieldA.
=== ceil
//TODO
[39/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml b/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
new file mode 100644
index 0000000..1cb477b
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
@@ -0,0 +1,1406 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ For more details about configurations options that may appear in
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+ <!-- In all configuration below, a prefix of "solr." for class names
+ is an alias that causes solr to search appropriate packages,
+ including org.apache.solr.(search|update|request|core|analysis)
+
+ You may also specify a fully qualified Java classname if you
+ have your own custom plugins.
+ -->
+
+ <!-- Controls what version of Lucene various components of Solr
+ adhere to. Generally, you want to use the latest version to
+ get all bug fixes and improvements. It is highly recommended
+ that you fully re-index after changing this setting as it can
+ affect both how text is indexed and queried.
+ -->
+ <luceneMatchVersion>7.0.0</luceneMatchVersion>
+
+ <!-- <lib/> directives can be used to instruct Solr to load any Jars
+ identified and use them to resolve any "plugins" specified in
+ your solrconfig.xml or schema.xml (ie: Analyzers, Request
+ Handlers, etc...).
+
+ All directories and paths are resolved relative to the
+ instanceDir.
+
+ Please note that <lib/> directives are processed in the order
+ that they appear in your solrconfig.xml file, and are "stacked"
+ on top of each other when building a ClassLoader - so if you have
+ plugin jars with dependencies on other jars, the "lower level"
+ dependency jars should be loaded first.
+
+ If a "./lib" directory exists in your instanceDir, all files
+ found in it are included as if you had used the following
+ syntax...
+
+ <lib dir="./lib" />
+ -->
+
+ <!-- A 'dir' option by itself adds any files found in the directory
+ to the classpath, this is useful for including all jars in a
+ directory.
+
+ When a 'regex' is specified in addition to a 'dir', only the
+ files in that directory which completely match the regex
+ (anchored on both ends) will be included.
+
+ If a 'dir' option (with or without a regex) is used and nothing
+ is found that matches, a warning will be logged.
+
+ The examples below can be used to load some solr-contribs along
+ with their external dependencies.
+ -->
+ <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
+ <!-- an exact 'path' can be used instead of a 'dir' to specify a
+ specific jar file. This will cause a serious error to be logged
+ if it can't be loaded.
+ -->
+ <!--
+ <lib path="../a-jar-that-does-not-exist.jar" />
+ -->
+
+ <!-- Data Directory
+
+ Used to specify an alternate directory to hold all index data
+ other than the default ./data under the Solr home. If
+ replication is in use, this should match the replication
+ configuration.
+ -->
+ <dataDir>${solr.data.dir:}</dataDir>
+
+
+ <!-- The DirectoryFactory to use for indexes.
+
+ solr.StandardDirectoryFactory is filesystem
+ based and tries to pick the best implementation for the current
+ JVM and platform. solr.NRTCachingDirectoryFactory, the default,
+ wraps solr.StandardDirectoryFactory and caches small files in memory
+ for better NRT performance.
+
+ One can force a particular implementation via solr.MMapDirectoryFactory,
+ solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+ solr.RAMDirectoryFactory is memory based and not persistent.
+ -->
+ <directoryFactory name="DirectoryFactory"
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
+
+ <!-- The CodecFactory for defining the format of the inverted index.
+ The default implementation is SchemaCodecFactory, which is the official Lucene
+ index format, but hooks into the schema to provide per-field customization of
+ the postings lists and per-document values in the fieldType element
+ (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+ are experimental, so if you choose to customize the index format, it's a good
+ idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+ before upgrading to a newer version to avoid unnecessary reindexing.
+ A "compressionMode" string element can be added to <codecFactory> to choose
+ between the existing compression modes in the default codec: "BEST_SPEED" (default)
+ or "BEST_COMPRESSION".
+ -->
+ <codecFactory class="solr.SchemaCodecFactory"/>
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Index Config - These settings control low-level behavior of indexing
+ Most example settings here show the default value, but are commented
+ out, to more easily see where customizations have been made.
+
+ Note: This replaces <indexDefaults> and <mainIndex> from older versions
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+ <indexConfig>
+ <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+ LimitTokenCountFilterFactory in your fieldType definition. E.g.
+ <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+ -->
+ <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+ <!-- <writeLockTimeout>1000</writeLockTimeout> -->
+
+ <!-- Expert: Enabling compound file will use less files for the index,
+ using fewer file descriptors on the expense of performance decrease.
+ Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+ <!-- <useCompoundFile>false</useCompoundFile> -->
+
+ <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+ indexing for buffering added documents and deletions before they are
+ flushed to the Directory.
+ maxBufferedDocs sets a limit on the number of documents buffered
+ before flushing.
+ If both ramBufferSizeMB and maxBufferedDocs is set, then
+ Lucene will flush based on whichever limit is hit first. -->
+ <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
+ <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+ <!-- Expert: Merge Policy
+ The Merge Policy in Lucene controls how merging of segments is done.
+ The default since Solr/Lucene 3.3 is TieredMergePolicy.
+ The default since Lucene 2.3 was the LogByteSizeMergePolicy,
+ Even older versions of Lucene used LogDocMergePolicy.
+ -->
+ <!--
+ <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
+ <int name="maxMergeAtOnce">10</int>
+ <int name="segmentsPerTier">10</int>
+ <double name="noCFSRatio">0.1</double>
+ </mergePolicyFactory>
+ -->
+
+ <!-- Expert: Merge Scheduler
+ The Merge Scheduler in Lucene controls how merges are
+ performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
+ can perform merges in the background using separate threads.
+ The SerialMergeScheduler (Lucene 2.2 default) does not.
+ -->
+ <!--
+ <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+ -->
+
+ <!-- LockFactory
+
+ This option specifies which Lucene LockFactory implementation
+ to use.
+
+ single = SingleInstanceLockFactory - suggested for a
+ read-only index or when there is no possibility of
+ another process trying to modify the index.
+ native = NativeFSLockFactory - uses OS native file locking.
+ Do not use when multiple solr webapps in the same
+ JVM are attempting to share a single index.
+ simple = SimpleFSLockFactory - uses a plain file for locking
+
+ Defaults: 'native' is default for Solr3.6 and later, otherwise
+ 'simple' is the default
+
+ More details on the nuances of each LockFactory...
+ http://wiki.apache.org/lucene-java/AvailableLockFactories
+ -->
+ <lockType>${solr.lock.type:native}</lockType>
+
+ <!-- Commit Deletion Policy
+ Custom deletion policies can be specified here. The class must
+ implement org.apache.lucene.index.IndexDeletionPolicy.
+
+ The default Solr IndexDeletionPolicy implementation supports
+ deleting index commit points on number of commits, age of
+ commit point and optimized status.
+
+ The latest commit point should always be preserved regardless
+ of the criteria.
+ -->
+ <!--
+ <deletionPolicy class="solr.SolrDeletionPolicy">
+ -->
+ <!-- The number of commit points to be kept -->
+ <!-- <str name="maxCommitsToKeep">1</str> -->
+ <!-- The number of optimized commit points to be kept -->
+ <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+ <!--
+ Delete all commit points once they have reached the given age.
+ Supports DateMathParser syntax e.g.
+ -->
+ <!--
+ <str name="maxCommitAge">30MINUTES</str>
+ <str name="maxCommitAge">1DAY</str>
+ -->
+ <!--
+ </deletionPolicy>
+ -->
+
+ <!-- Lucene Infostream
+
+ To aid in advanced debugging, Lucene provides an "InfoStream"
+ of detailed information when indexing.
+
+ Setting The value to true will instruct the underlying Lucene
+ IndexWriter to write its debugging info the specified file
+ -->
+ <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
+ </indexConfig>
+
+
+ <!-- JMX
+
+ This example enables JMX if and only if an existing MBeanServer
+ is found, use this if you want to configure JMX through JVM
+ parameters. Remove this to disable exposing Solr configuration
+ and statistics to JMX.
+
+ For more details see http://wiki.apache.org/solr/SolrJmx
+ -->
+ <jmx />
+ <!-- If you want to connect to a particular server, specify the
+ agentId
+ -->
+ <!-- <jmx agentId="myAgent" /> -->
+ <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+ <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+ -->
+
+ <!-- The default high-performance update handler -->
+ <updateHandler class="solr.DirectUpdateHandler2">
+
+ <!-- Enables a transaction log, used for real-time get, durability, and
+ and solr cloud replica recovery. The log can grow as big as
+ uncommitted changes to the index, so use of a hard autoCommit
+ is recommended (see below).
+ "dir" - the target directory for transaction logs, defaults to the
+ solr data directory.
+ "numVersionBuckets" - sets the number of buckets used to keep
+ track of max version values when checking for re-ordered
+ updates; increase this value to reduce the cost of
+ synchronizing access to version buckets during high-volume
+ indexing, this requires 8 bytes (long) * numVersionBuckets
+ of heap space per Solr core.
+ -->
+ <updateLog>
+ <str name="dir">${solr.ulog.dir:}</str>
+ <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
+ </updateLog>
+
+ <!-- AutoCommit
+
+ Perform a hard commit automatically under certain conditions.
+ Instead of enabling autoCommit, consider using "commitWithin"
+ when adding documents.
+
+ http://wiki.apache.org/solr/UpdateXmlMessages
+
+ maxDocs - Maximum number of documents to add since the last
+ commit before automatically triggering a new commit.
+
+ maxTime - Maximum amount of time in ms that is allowed to pass
+ since a document was added before automatically
+ triggering a new commit.
+ openSearcher - if false, the commit causes recent index changes
+ to be flushed to stable storage, but does not cause a new
+ searcher to be opened to make those changes visible.
+
+ If the updateLog is enabled, then it's highly recommended to
+ have some sort of hard autoCommit to limit the log size.
+ -->
+ <autoCommit>
+ <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+ <openSearcher>false</openSearcher>
+ </autoCommit>
+
+ <!-- softAutoCommit is like autoCommit except it causes a
+ 'soft' commit which only ensures that changes are visible
+ but does not ensure that data is synced to disk. This is
+ faster and more near-realtime friendly than a hard commit.
+ -->
+
+ <autoSoftCommit>
+ <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+ </autoSoftCommit>
+
+ <!-- Update Related Event Listeners
+
+ Various IndexWriter related events can trigger Listeners to
+ take actions.
+
+ postCommit - fired after every commit or optimize command
+ postOptimize - fired after every optimize command
+ -->
+ <!-- The RunExecutableListener executes an external command from a
+ hook such as postCommit or postOptimize.
+
+ exe - the name of the executable to run
+ dir - dir to use as the current working directory. (default=".")
+ wait - the calling thread waits until the executable returns.
+ (default="true")
+ args - the arguments to pass to the program. (default is none)
+ env - environment variables to set. (default is none)
+ -->
+ <!-- This example shows how RunExecutableListener could be used
+ with the script based replication...
+ http://wiki.apache.org/solr/CollectionDistribution
+ -->
+ <!--
+ <listener event="postCommit" class="solr.RunExecutableListener">
+ <str name="exe">solr/bin/snapshooter</str>
+ <str name="dir">.</str>
+ <bool name="wait">true</bool>
+ <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
+ <arr name="env"> <str>MYVAR=val1</str> </arr>
+ </listener>
+ -->
+
+ </updateHandler>
+
+ <!-- IndexReaderFactory
+
+ Use the following format to specify a custom IndexReaderFactory,
+ which allows for alternate IndexReader implementations.
+
+ ** Experimental Feature **
+
+ Please note - Using a custom IndexReaderFactory may prevent
+ certain other features from working. The API to
+ IndexReaderFactory may change without warning or may even be
+ removed from future releases if the problems cannot be
+ resolved.
+
+
+ ** Features that may not work with custom IndexReaderFactory **
+
+ The ReplicationHandler assumes a disk-resident index. Using a
+ custom IndexReader implementation may cause incompatibility
+ with ReplicationHandler and may cause replication to not work
+ correctly. See SOLR-1366 for details.
+
+ -->
+ <!--
+ <indexReaderFactory name="IndexReaderFactory" class="package.class">
+ <str name="someArg">Some Value</str>
+ </indexReaderFactory >
+ -->
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Query section - these settings control query time things like caches
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+ <query>
+ <!-- Max Boolean Clauses
+
+ Maximum number of clauses in each BooleanQuery, an exception
+ is thrown if exceeded.
+
+ ** WARNING **
+
+ This option actually modifies a global Lucene property that
+ will affect all SolrCores. If multiple solrconfig.xml files
+ disagree on this property, the value at any given moment will
+ be based on the last SolrCore to be initialized.
+
+ -->
+ <maxBooleanClauses>1024</maxBooleanClauses>
+
+
+ <!-- Solr Internal Query Caches
+
+ There are two implementations of cache available for Solr,
+ LRUCache, based on a synchronized LinkedHashMap, and
+ FastLRUCache, based on a ConcurrentHashMap.
+
+ FastLRUCache has faster gets and slower puts in single
+ threaded operation and thus is generally faster than LRUCache
+ when the hit ratio of the cache is high (> 75%), and may be
+ faster under other scenarios on multi-cpu systems.
+ -->
+
+ <!-- Filter Cache
+
+ Cache used by SolrIndexSearcher for filters (DocSets),
+ unordered sets of *all* documents that match a query. When a
+ new searcher is opened, its caches may be prepopulated or
+ "autowarmed" using data from caches in the old searcher.
+ autowarmCount is the number of items to prepopulate. For
+ LRUCache, the autowarmed items will be the most recently
+ accessed items.
+
+ Parameters:
+ class - the SolrCache implementation LRUCache or
+ (LRUCache or FastLRUCache)
+ size - the maximum number of entries in the cache
+ initialSize - the initial capacity (number of entries) of
+ the cache. (see java.util.HashMap)
+ autowarmCount - the number of entries to prepopulate from
+ and old cache.
+ maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+ to occupy. Note that when this option is specified, the size
+ and initialSize parameters are ignored.
+ -->
+ <filterCache class="solr.FastLRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- Query Result Cache
+
+ Caches results of searches - ordered lists of document ids
+ (DocList) based on a query, a sort, and the range of documents requested.
+ Additional supported parameter by LRUCache:
+ maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+ to occupy
+ -->
+ <queryResultCache class="solr.LRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- Document Cache
+
+ Caches Lucene Document objects (the stored fields for each
+ document). Since Lucene internal document ids are transient,
+ this cache will not be autowarmed.
+ -->
+ <documentCache class="solr.LRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- custom cache currently used by block join -->
+ <cache name="perSegFilter"
+ class="solr.search.LRUCache"
+ size="10"
+ initialSize="0"
+ autowarmCount="10"
+ regenerator="solr.NoOpRegenerator" />
+
+ <!-- Field Value Cache
+
+ Cache used to hold field values that are quickly accessible
+ by document id. The fieldValueCache is created by default
+ even if not configured here.
+ -->
+ <!--
+ <fieldValueCache class="solr.FastLRUCache"
+ size="512"
+ autowarmCount="128"
+ showItems="32" />
+ -->
+
+ <!-- Custom Cache
+
+ Example of a generic cache. These caches may be accessed by
+ name through SolrIndexSearcher.getCache(),cacheLookup(), and
+ cacheInsert(). The purpose is to enable easy caching of
+ user/application level data. The regenerator argument should
+ be specified as an implementation of solr.CacheRegenerator
+ if autowarming is desired.
+ -->
+ <!--
+ <cache name="myUserCache"
+ class="solr.LRUCache"
+ size="4096"
+ initialSize="1024"
+ autowarmCount="1024"
+ regenerator="com.mycompany.MyRegenerator"
+ />
+ -->
+
+
+ <!-- Lazy Field Loading
+
+ If true, stored fields that are not requested will be loaded
+ lazily. This can result in a significant speed improvement
+ if the usual case is to not load all stored fields,
+ especially if the skipped fields are large compressed text
+ fields.
+ -->
+ <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+ <!-- Use Filter For Sorted Query
+
+ A possible optimization that attempts to use a filter to
+ satisfy a search. If the requested sort does not include
+ score, then the filterCache will be checked for a filter
+ matching the query. If found, the filter will be used as the
+ source of document ids, and then the sort will be applied to
+ that.
+
+ For most situations, this will not be useful unless you
+ frequently get the same search repeatedly with different sort
+ options, and none of them ever use "score"
+ -->
+ <!--
+ <useFilterForSortedQuery>true</useFilterForSortedQuery>
+ -->
+
+ <!-- Result Window Size
+
+ An optimization for use with the queryResultCache. When a search
+ is requested, a superset of the requested number of document ids
+ are collected. For example, if a search for a particular query
+ requests matching documents 10 through 19, and queryWindowSize is 50,
+ then documents 0 through 49 will be collected and cached. Any further
+ requests in that range can be satisfied via the cache.
+ -->
+ <queryResultWindowSize>20</queryResultWindowSize>
+
+ <!-- Maximum number of documents to cache for any entry in the
+ queryResultCache.
+ -->
+ <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+ <!-- Query Related Event Listeners
+
+ Various IndexSearcher related events can trigger Listeners to
+ take actions.
+
+ newSearcher - fired whenever a new searcher is being prepared
+ and there is a current searcher handling requests (aka
+ registered). It can be used to prime certain caches to
+ prevent long request times for certain requests.
+
+ firstSearcher - fired whenever a new searcher is being
+ prepared but there is no current registered searcher to handle
+ requests or to gain autowarming data from.
+
+
+ -->
+ <!-- QuerySenderListener takes an array of NamedList and executes a
+ local query request for each NamedList in sequence.
+ -->
+ <listener event="newSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <!--
+ <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
+ <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+ -->
+ </arr>
+ </listener>
+ <listener event="firstSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <!--
+ <lst>
+ <str name="q">static firstSearcher warming in solrconfig.xml</str>
+ </lst>
+ -->
+ </arr>
+ </listener>
+
+ <!-- Use Cold Searcher
+
+ If a search request comes in and there is no current
+ registered searcher, then immediately register the still
+ warming searcher and use it. If "false" then all requests
+ will block until the first searcher is done warming.
+ -->
+ <useColdSearcher>false</useColdSearcher>
+
+ </query>
+
+
+ <!-- Request Dispatcher
+
+ This section contains instructions for how the SolrDispatchFilter
+ should behave when processing requests for this SolrCore.
+
+ handleSelect is a legacy option that affects the behavior of requests
+ such as /select?qt=XXX
+
+ handleSelect="true" will cause the SolrDispatchFilter to process
+ the request and dispatch the query to a handler specified by the
+ "qt" param, assuming "/select" isn't already registered.
+
+ handleSelect="false" will cause the SolrDispatchFilter to
+ ignore "/select" requests, resulting in a 404 unless a handler
+ is explicitly registered with the name "/select"
+
+ handleSelect="true" is not recommended for new users, but is the default
+ for backwards compatibility
+ -->
+ <requestDispatcher handleSelect="false" >
+ <!-- Request Parsing
+
+ These settings indicate how Solr Requests may be parsed, and
+ what restrictions may be placed on the ContentStreams from
+ those requests
+
+ enableRemoteStreaming - enables use of the stream.file
+ and stream.url parameters for specifying remote streams.
+
+ multipartUploadLimitInKB - specifies the max size (in KiB) of
+ Multipart File Uploads that Solr will allow in a Request.
+
+ formdataUploadLimitInKB - specifies the max size (in KiB) of
+ form data (application/x-www-form-urlencoded) sent via
+ POST. You can use POST to pass request parameters not
+ fitting into the URL.
+
+ addHttpRequestToContext - if set to true, it will instruct
+ the requestParsers to include the original HttpServletRequest
+ object in the context map of the SolrQueryRequest under the
+ key "httpRequest". It will not be used by any of the existing
+ Solr components, but may be useful when developing custom
+ plugins.
+
+ *** WARNING ***
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
+
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
+ addHttpRequestToContext="false"/>
+ -->
+
+ <!-- HTTP Caching
+
+ Set HTTP caching related parameters (for proxy caches and clients).
+
+ The options below instruct Solr not to output any HTTP Caching
+ related headers
+ -->
+ <httpCaching never304="true" />
+ <!-- If you include a <cacheControl> directive, it will be used to
+ generate a Cache-Control header (as well as an Expires header
+ if the value contains "max-age=")
+
+ By default, no Cache-Control header is generated.
+
+ You can use the <cacheControl> option even if you have set
+ never304="true"
+ -->
+ <!--
+ <httpCaching never304="true" >
+ <cacheControl>max-age=30, public</cacheControl>
+ </httpCaching>
+ -->
+ <!-- To enable Solr to respond with automatically generated HTTP
+ Caching headers, and to response to Cache Validation requests
+ correctly, set the value of never304="false"
+
+ This will cause Solr to generate Last-Modified and ETag
+ headers based on the properties of the Index.
+
+ The following options can also be specified to affect the
+ values of these headers...
+
+ lastModFrom - the default value is "openTime" which means the
+ Last-Modified value (and validation against If-Modified-Since
+ requests) will all be relative to when the current Searcher
+ was opened. You can change it to lastModFrom="dirLastMod" if
+ you want the value to exactly correspond to when the physical
+ index was last modified.
+
+ etagSeed="..." is an option you can change to force the ETag
+ header (and validation against If-None-Match requests) to be
+ different even if the index has not changed (ie: when making
+ significant changes to your config file)
+
+ (lastModifiedFrom and etagSeed are both ignored if you use
+ the never304="true" option)
+ -->
+ <!--
+ <httpCaching lastModifiedFrom="openTime"
+ etagSeed="Solr">
+ <cacheControl>max-age=30, public</cacheControl>
+ </httpCaching>
+ -->
+ </requestDispatcher>
+
+ <!-- Request Handlers
+
+ http://wiki.apache.org/solr/SolrRequestHandler
+
+ Incoming queries will be dispatched to a specific handler by name
+ based on the path specified in the request.
+
+ Legacy behavior: If the request path uses "/select" but no Request
+ Handler has that name, and if handleSelect="true" has been specified in
+ the requestDispatcher, then the Request Handler is dispatched based on
+ the qt parameter. Handlers without a leading '/' are accessed this way
+ like so: http://host/app/[core/]select?qt=name If no qt is
+ given, then the requestHandler that declares default="true" will be
+ used or the one named "standard".
+
+ If a Request Handler is declared with startup="lazy", then it will
+ not be initialized until the first request that uses it.
+
+ -->
+ <!-- SearchHandler
+
+ http://wiki.apache.org/solr/SearchHandler
+
+ For processing Search Queries, the primary Request Handler
+ provided with Solr is "SearchHandler" It delegates to a sequent
+ of SearchComponents (see below) and supports distributed
+ queries across multiple shards
+ -->
+ <requestHandler name="/select" class="solr.SearchHandler">
+ <!-- default values for query parameters can be specified, these
+ will be overridden by parameters in the request
+ -->
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <int name="rows">10</int>
+ <!-- <str name="df">text</str> -->
+ </lst>
+ <!-- In addition to defaults, "appends" params can be specified
+ to identify values which should be appended to the list of
+ multi-val params from the query (or the existing "defaults").
+ -->
+ <!-- In this example, the param "fq=instock:true" would be appended to
+ any query time fq params the user may specify, as a mechanism for
+ partitioning the index, independent of any user selected filtering
+ that may also be desired (perhaps as a result of faceted searching).
+
+ NOTE: there is *absolutely* nothing a client can do to prevent these
+ "appends" values from being used, so don't use this mechanism
+ unless you are sure you always want it.
+ -->
+ <!--
+ <lst name="appends">
+ <str name="fq">inStock:true</str>
+ </lst>
+ -->
+ <!-- "invariants" are a way of letting the Solr maintainer lock down
+ the options available to Solr clients. Any params values
+ specified here are used regardless of what values may be specified
+ in either the query, the "defaults", or the "appends" params.
+
+ In this example, the facet.field and facet.query params would
+ be fixed, limiting the facets clients can use. Faceting is
+ not turned on by default - but if the client does specify
+ facet=true in the request, these are the only facets they
+ will be able to see counts for; regardless of what other
+ facet.field or facet.query params they may specify.
+
+ NOTE: there is *absolutely* nothing a client can do to prevent these
+ "invariants" values from being used, so don't use this mechanism
+ unless you are sure you always want it.
+ -->
+ <!--
+ <lst name="invariants">
+ <str name="facet.field">cat</str>
+ <str name="facet.field">manu_exact</str>
+ <str name="facet.query">price:[* TO 500]</str>
+ <str name="facet.query">price:[500 TO *]</str>
+ </lst>
+ -->
+ <!-- If the default list of SearchComponents is not desired, that
+ list can either be overridden completely, or components can be
+ prepended or appended to the default list. (see below)
+ -->
+ <!--
+ <arr name="components">
+ <str>nameOfCustomComponent1</str>
+ <str>nameOfCustomComponent2</str>
+ </arr>
+ -->
+ </requestHandler>
+
+ <!-- A request handler that returns indented JSON by default -->
+ <requestHandler name="/query" class="solr.SearchHandler">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="wt">json</str>
+ <str name="indent">true</str>
+ </lst>
+ </requestHandler>
+
+
+ <!-- A Robust Example
+
+ This example SearchHandler declaration shows off usage of the
+ SearchHandler with many defaults declared
+
+ Note that multiple instances of the same Request Handler
+ (SearchHandler) can be registered multiple times with different
+ names (and different init parameters)
+ -->
+ <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
+ </requestHandler>
+
+ <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
+ <lst name="defaults">
+ <str name="df">_text_</str>
+ </lst>
+ </initParams>
+
+ <initParams path="/update/**">
+ <lst name="defaults">
+ <str name="update.chain">add-unknown-fields-to-the-schema</str>
+ </lst>
+ </initParams>
+
+ <!-- Solr Cell Update Request Handler
+
+ http://wiki.apache.org/solr/ExtractingRequestHandler
+
+ -->
+ <requestHandler name="/update/extract"
+ startup="lazy"
+ class="solr.extraction.ExtractingRequestHandler" >
+ <lst name="defaults">
+ <str name="lowernames">true</str>
+ <str name="fmap.meta">ignored_</str>
+ <str name="fmap.content">_text_</str>
+ </lst>
+ </requestHandler>
+
+ <!-- Search Components
+
+ Search components are registered to SolrCore and used by
+ instances of SearchHandler (which can access them by name)
+
+ By default, the following components are available:
+
+ <searchComponent name="query" class="solr.QueryComponent" />
+ <searchComponent name="facet" class="solr.FacetComponent" />
+ <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
+ <searchComponent name="highlight" class="solr.HighlightComponent" />
+ <searchComponent name="stats" class="solr.StatsComponent" />
+ <searchComponent name="debug" class="solr.DebugComponent" />
+
+ Default configuration in a requestHandler would look like:
+
+ <arr name="components">
+ <str>query</str>
+ <str>facet</str>
+ <str>mlt</str>
+ <str>highlight</str>
+ <str>stats</str>
+ <str>debug</str>
+ </arr>
+
+ If you register a searchComponent to one of the standard names,
+ that will be used instead of the default.
+
+ To insert components before or after the 'standard' components, use:
+
+ <arr name="first-components">
+ <str>myFirstComponentName</str>
+ </arr>
+
+ <arr name="last-components">
+ <str>myLastComponentName</str>
+ </arr>
+
+ NOTE: The component registered with the name "debug" will
+ always be executed after the "last-components"
+
+ -->
+
+ <!-- Spell Check
+
+ The spell check component can return a list of alternative spelling
+ suggestions.
+
+ http://wiki.apache.org/solr/SpellCheckComponent
+ -->
+ <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+ <str name="queryAnalyzerFieldType">text_general</str>
+
+ <!-- Multiple "Spell Checkers" can be declared and used by this
+ component
+ -->
+
+ <!-- a spellchecker built from a field of the main index -->
+ <lst name="spellchecker">
+ <str name="name">default</str>
+ <str name="field">_text_</str>
+ <str name="classname">solr.DirectSolrSpellChecker</str>
+ <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+ <str name="distanceMeasure">internal</str>
+ <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+ <float name="accuracy">0.5</float>
+ <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+ <int name="maxEdits">2</int>
+ <!-- the minimum shared prefix when enumerating terms -->
+ <int name="minPrefix">1</int>
+ <!-- maximum number of inspections per result. -->
+ <int name="maxInspections">5</int>
+ <!-- minimum length of a query term to be considered for correction -->
+ <int name="minQueryLength">4</int>
+ <!-- maximum threshold of documents a query term can appear to be considered for correction -->
+ <float name="maxQueryFrequency">0.01</float>
+ <!-- uncomment this to require suggestions to occur in 1% of the documents
+ <float name="thresholdTokenFrequency">.01</float>
+ -->
+ </lst>
+
+ <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
+ <!--
+ <lst name="spellchecker">
+ <str name="name">wordbreak</str>
+ <str name="classname">solr.WordBreakSolrSpellChecker</str>
+ <str name="field">name</str>
+ <str name="combineWords">true</str>
+ <str name="breakWords">true</str>
+ <int name="maxChanges">10</int>
+ </lst>
+ -->
+ </searchComponent>
+
+ <!-- A request handler for demonstrating the spellcheck component.
+
+ NOTE: This is purely as an example. The whole purpose of the
+ SpellCheckComponent is to hook it into the request handler that
+ handles your normal user queries so that a separate request is
+ not needed to get suggestions.
+
+ IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+ NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+ See http://wiki.apache.org/solr/SpellCheckComponent for details
+ on the request parameters.
+ -->
+ <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <!-- Solr will use suggestions from both the 'default' spellchecker
+ and from the 'wordbreak' spellchecker and combine them.
+ collations (re-written queries) can include a combination of
+ corrections from both spellcheckers -->
+ <str name="spellcheck.dictionary">default</str>
+ <str name="spellcheck">on</str>
+ <str name="spellcheck.extendedResults">true</str>
+ <str name="spellcheck.count">10</str>
+ <str name="spellcheck.alternativeTermCount">5</str>
+ <str name="spellcheck.maxResultsForSuggest">5</str>
+ <str name="spellcheck.collate">true</str>
+ <str name="spellcheck.collateExtendedResults">true</str>
+ <str name="spellcheck.maxCollationTries">10</str>
+ <str name="spellcheck.maxCollations">5</str>
+ </lst>
+ <arr name="last-components">
+ <str>spellcheck</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Term Vector Component
+
+ http://wiki.apache.org/solr/TermVectorComponent
+ -->
+ <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
+
+ <!-- A request handler for demonstrating the term vector component
+
+ This is purely as an example.
+
+ In reality you will likely want to add the component to your
+ already specified request handlers.
+ -->
+ <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <bool name="tv">true</bool>
+ </lst>
+ <arr name="last-components">
+ <str>tvComponent</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Clustering Component. (Omitted here. See the default Solr example for a typical configuration.) -->
+
+ <!-- Terms Component
+
+ http://wiki.apache.org/solr/TermsComponent
+
+ A component to return terms and document frequency of those
+ terms
+ -->
+ <searchComponent name="terms" class="solr.TermsComponent"/>
+
+ <!-- A request handler for demonstrating the terms component -->
+ <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <bool name="terms">true</bool>
+ <bool name="distrib">false</bool>
+ </lst>
+ <arr name="components">
+ <str>terms</str>
+ </arr>
+ </requestHandler>
+
+
+ <!-- Query Elevation Component
+
+ http://wiki.apache.org/solr/QueryElevationComponent
+
+ a search component that enables you to configure the top
+ results for a given query regardless of the normal lucene
+ scoring.
+ -->
+ <searchComponent name="elevator" class="solr.QueryElevationComponent" >
+ <!-- pick a fieldType to analyze queries -->
+ <str name="queryFieldType">string</str>
+ <str name="config-file">elevate.xml</str>
+ </searchComponent>
+
+ <!-- A request handler for demonstrating the elevator component -->
+ <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
+ <arr name="last-components">
+ <str>elevator</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Highlighting Component
+
+ http://wiki.apache.org/solr/HighlightingParameters
+ -->
+ <searchComponent class="solr.HighlightComponent" name="highlight">
+ <highlighting>
+ <!-- Configure the standard fragmenter -->
+ <!-- This could most likely be commented out in the "default" case -->
+ <fragmenter name="gap"
+ default="true"
+ class="solr.highlight.GapFragmenter">
+ <lst name="defaults">
+ <int name="hl.fragsize">100</int>
+ </lst>
+ </fragmenter>
+
+ <!-- A regular-expression-based fragmenter
+ (for sentence extraction)
+ -->
+ <fragmenter name="regex"
+ class="solr.highlight.RegexFragmenter">
+ <lst name="defaults">
+ <!-- slightly smaller fragsizes work better because of slop -->
+ <int name="hl.fragsize">70</int>
+ <!-- allow 50% slop on fragment sizes -->
+ <float name="hl.regex.slop">0.5</float>
+ <!-- a basic sentence pattern -->
+ <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
+ </lst>
+ </fragmenter>
+
+ <!-- Configure the standard formatter -->
+ <formatter name="html"
+ default="true"
+ class="solr.highlight.HtmlFormatter">
+ <lst name="defaults">
+ <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+ <str name="hl.simple.post"><![CDATA[</em>]]></str>
+ </lst>
+ </formatter>
+
+ <!-- Configure the standard encoder -->
+ <encoder name="html"
+ class="solr.highlight.HtmlEncoder" />
+
+ <!-- Configure the standard fragListBuilder -->
+ <fragListBuilder name="simple"
+ class="solr.highlight.SimpleFragListBuilder"/>
+
+ <!-- Configure the single fragListBuilder -->
+ <fragListBuilder name="single"
+ class="solr.highlight.SingleFragListBuilder"/>
+
+ <!-- Configure the weighted fragListBuilder -->
+ <fragListBuilder name="weighted"
+ default="true"
+ class="solr.highlight.WeightedFragListBuilder"/>
+
+ <!-- default tag FragmentsBuilder -->
+ <fragmentsBuilder name="default"
+ default="true"
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
+ <!--
+ <lst name="defaults">
+ <str name="hl.multiValuedSeparatorChar">/</str>
+ </lst>
+ -->
+ </fragmentsBuilder>
+
+ <!-- multi-colored tag FragmentsBuilder -->
+ <fragmentsBuilder name="colored"
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
+ <lst name="defaults">
+ <str name="hl.tag.pre"><![CDATA[
+ <b style="background:yellow">,<b style="background:lawgreen">,
+ <b style="background:aquamarine">,<b style="background:magenta">,
+ <b style="background:palegreen">,<b style="background:coral">,
+ <b style="background:wheat">,<b style="background:khaki">,
+ <b style="background:lime">,<b style="background:deepskyblue">]]></str>
+ <str name="hl.tag.post"><![CDATA[</b>]]></str>
+ </lst>
+ </fragmentsBuilder>
+
+ <boundaryScanner name="default"
+ default="true"
+ class="solr.highlight.SimpleBoundaryScanner">
+ <lst name="defaults">
+ <str name="hl.bs.maxScan">10</str>
+ <str name="hl.bs.chars">.,!? 	 </str>
+ </lst>
+ </boundaryScanner>
+
+ <boundaryScanner name="breakIterator"
+ class="solr.highlight.BreakIteratorBoundaryScanner">
+ <lst name="defaults">
+ <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
+ <str name="hl.bs.type">WORD</str>
+ <!-- language and country are used when constructing Locale object. -->
+ <!-- And the Locale object will be used when getting instance of BreakIterator -->
+ <str name="hl.bs.language">en</str>
+ <str name="hl.bs.country">US</str>
+ </lst>
+ </boundaryScanner>
+ </highlighting>
+ </searchComponent>
+
+ <!-- Update Processors
+
+ Chains of Update Processor Factories for dealing with Update
+ Requests can be declared, and then used by name in Update
+ Request Processors
+
+ http://wiki.apache.org/solr/UpdateRequestProcessor
+
+ -->
+
+ <!-- Add unknown fields to the schema
+
+ An example field type guessing update processor that will
+ attempt to parse string-typed field values as Booleans, Longs,
+ Doubles, or Dates, and then add schema fields with the guessed
+ field types.
+
+ This requires that the schema is both managed and mutable, by
+ declaring schemaFactory as ManagedIndexSchemaFactory, with
+ mutable specified as true.
+
+ See http://wiki.apache.org/solr/GuessingFieldTypes
+ -->
+ <updateRequestProcessorChain name="add-unknown-fields-to-the-schema">
+ <!-- UUIDUpdateProcessorFactory will generate an id if none is present in the incoming document -->
+ <processor class="solr.UUIDUpdateProcessorFactory" />
+ <processor class="solr.RemoveBlankFieldUpdateProcessorFactory"/>
+ <processor class="solr.FieldNameMutatingUpdateProcessorFactory">
+ <str name="pattern">[^\w-\.]</str>
+ <str name="replacement">_</str>
+ </processor>
+ <processor class="solr.ParseBooleanFieldUpdateProcessorFactory"/>
+ <processor class="solr.ParseLongFieldUpdateProcessorFactory"/>
+ <processor class="solr.ParseDoubleFieldUpdateProcessorFactory"/>
+ <processor class="solr.ParseDateFieldUpdateProcessorFactory">
+ <arr name="format">
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss</str>
+ <str>yyyy-MM-dd'T'HH:mmZ</str>
+ <str>yyyy-MM-dd'T'HH:mm</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd HH:mm:ssZ</str>
+ <str>yyyy-MM-dd HH:mm:ss</str>
+ <str>yyyy-MM-dd HH:mmZ</str>
+ <str>yyyy-MM-dd HH:mm</str>
+ <str>yyyy-MM-dd</str>
+ </arr>
+ </processor>
+ <processor class="solr.AddSchemaFieldsUpdateProcessorFactory">
+ <str name="defaultFieldType">strings</str>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Boolean</str>
+ <str name="fieldType">booleans</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.util.Date</str>
+ <str name="fieldType">pdates</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Long</str>
+ <str name="valueClass">java.lang.Integer</str>
+ <str name="fieldType">plongs</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Number</str>
+ <str name="fieldType">pdoubles</str>
+ </lst>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory"/>
+ <processor class="solr.DistributedUpdateProcessorFactory"/>
+ <processor class="solr.RunUpdateProcessorFactory"/>
+ </updateRequestProcessorChain>
+
+ <!-- Deduplication
+
+ An example dedup update processor that creates the "id" field
+ on the fly based on the hash code of some other fields. This
+ example has overwriteDupes set to false since we are using the
+ id field as the signatureField and Solr will maintain
+ uniqueness based on that anyway.
+
+ -->
+ <!--
+ <updateRequestProcessorChain name="dedupe">
+ <processor class="solr.processor.SignatureUpdateProcessorFactory">
+ <bool name="enabled">true</bool>
+ <str name="signatureField">id</str>
+ <bool name="overwriteDupes">false</bool>
+ <str name="fields">name,features,cat</str>
+ <str name="signatureClass">solr.processor.Lookup3Signature</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Language identification
+
+ This example update chain identifies the language of the incoming
+ documents using the langid contrib. The detected language is
+ written to field language_s. No field name mapping is done.
+ The fields used for detection are text, title, subject and description,
+ making this example suitable for detecting languages form full-text
+ rich documents injected via ExtractingRequestHandler.
+ See more about langId at http://wiki.apache.org/solr/LanguageDetection
+ -->
+ <!--
+ <updateRequestProcessorChain name="langid">
+ <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
+ <str name="langid.fl">text,title,subject,description</str>
+ <str name="langid.langField">language_s</str>
+ <str name="langid.fallback">en</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Script update processor
+
+ This example hooks in an update processor implemented using JavaScript.
+
+ See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
+ -->
+ <!--
+ <updateRequestProcessorChain name="script">
+ <processor class="solr.StatelessScriptUpdateProcessorFactory">
+ <str name="script">update-script.js</str>
+ <lst name="params">
+ <str name="config_param">example config parameter</str>
+ </lst>
+ </processor>
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Response Writers
+
+ http://wiki.apache.org/solr/QueryResponseWriter
+
+ Request responses will be written using the writer specified by
+ the 'wt' request parameter matching the name of a registered
+ writer.
+
+ The "default" writer is the default and will be used if 'wt' is
+ not specified in the request.
+ -->
+ <!-- The following response writers are implicitly configured unless
+ overridden...
+ -->
+ <!--
+ <queryResponseWriter name="xml"
+ default="true"
+ class="solr.XMLResponseWriter" />
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+ <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+ <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+ <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+ <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+ <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+ <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+ -->
+
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+ <!-- For the purposes of the tutorial, JSON responses are written as
+ plain text so that they are easy to read in *any* browser.
+ If you expect a MIME type of "application/json" just remove this override.
+ -->
+ <str name="content-type">text/plain; charset=UTF-8</str>
+ </queryResponseWriter>
+
+ <!--
+ Custom response writers can be declared as needed...
+ -->
+ <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
+ <str name="template.base.dir">${velocity.template.base.dir:}</str>
+ <str name="solr.resource.loader.enabled">${velocity.solr.resource.loader.enabled:true}</str>
+ <str name="params.resource.loader.enabled">${velocity.params.resource.loader.enabled:false}</str>
+ </queryResponseWriter>
+
+ <!-- XSLT response writer transforms the XML output by any xslt file found
+ in Solr's conf/xslt directory. Changes to xslt files are checked for
+ every xsltCacheLifetimeSeconds.
+ -->
+ <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
+ <int name="xsltCacheLifetimeSeconds">5</int>
+ </queryResponseWriter>
+
+ <!-- Query Parsers
+
+ https://cwiki.apache.org/confluence/display/solr/Query+Syntax+and+Parsing
+
+ Multiple QParserPlugins can be registered by name, and then
+ used in either the "defType" param for the QueryComponent (used
+ by SearchHandler) or in LocalParams
+ -->
+ <!-- example of registering a query parser -->
+ <!--
+ <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+ -->
+
+ <!-- Function Parsers
+
+ http://wiki.apache.org/solr/FunctionQuery
+
+ Multiple ValueSourceParsers can be registered by name, and then
+ used as function names when using the "func" QParser.
+ -->
+ <!-- example of registering a custom function parser -->
+ <!--
+ <valueSourceParser name="myfunc"
+ class="com.mycompany.MyValueSourceParser" />
+ -->
+
+
+ <!-- Document Transformers
+ http://wiki.apache.org/solr/DocTransformers
+ -->
+ <!--
+ Could be something like:
+ <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+ <int name="connection">jdbc://....</int>
+ </transformer>
+
+ To add a constant value to all docs, use:
+ <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <int name="value">5</int>
+ </transformer>
+
+ If you want the user to still be able to change it with _value:something_ use this:
+ <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <double name="defaultValue">5</double>
+ </transformer>
+
+ If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
+ EditorialMarkerFactory will do exactly that:
+ <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+ -->
+</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/stopwords.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/stopwords.txt
new file mode 100644
index 0000000..ae1e83e
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/stopwords.txt
@@ -0,0 +1,14 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/synonyms.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/synonyms.txt
new file mode 100644
index 0000000..eab4ee8
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/synonyms.txt
@@ -0,0 +1,29 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+#some test synonym mappings unlikely to appear in real input text
+aaafoo => aaabar
+bbbfoo => bbbfoo bbbbar
+cccfoo => cccbar cccbaz
+fooaaa,baraaa,bazaaa
+
+# Some synonym groups specific to this example
+GB,gib,gigabyte,gigabytes
+MB,mib,megabyte,megabytes
+Television, Televisions, TV, TVs
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
+#after us won't split it into two words.
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+
[13/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10882: Moves
sub evaluator check to the constructors to catch errors earlier
Posted by sh...@apache.org.
SOLR-10882: Moves sub evaluator check to the constructors to catch errors earlier
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/aeec043e
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/aeec043e
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/aeec043e
Branch: refs/heads/feature/autoscaling
Commit: aeec043ed1cdf6ffd2b92811adde162eab06debd
Parents: 113459a
Author: Dennis Gove <dp...@gmail.com>
Authored: Fri Jun 16 20:10:28 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Sun Jun 18 11:50:58 2017 -0400
----------------------------------------------------------------------
.../solr/client/solrj/io/eval/ConvolutionEvaluator.java | 10 +++++-----
.../solr/client/solrj/io/eval/CorrelationEvaluator.java | 9 +++++----
.../solr/client/solrj/io/eval/CovarianceEvaluator.java | 9 +++++----
.../solrj/io/eval/CumulativeProbabilityEvaluator.java | 9 +++++----
.../solr/client/solrj/io/eval/DescribeEvaluator.java | 10 ++++++----
.../solr/client/solrj/io/eval/DistanceEvaluator.java | 10 ++++++----
.../solrj/io/eval/EmpiricalDistributionEvaluator.java | 9 +++++----
.../solr/client/solrj/io/eval/FindDelayEvaluator.java | 9 +++++----
.../solr/client/solrj/io/eval/HistogramEvaluator.java | 9 +++++----
.../solr/client/solrj/io/eval/MovingAverageEvaluator.java | 9 +++++----
.../solr/client/solrj/io/eval/PercentileEvaluator.java | 9 +++++----
.../solr/client/solrj/io/eval/PredictEvaluator.java | 10 ++++++----
.../apache/solr/client/solrj/io/eval/RankEvaluator.java | 10 ++++++----
.../solr/client/solrj/io/eval/RegressionEvaluator.java | 10 ++++++----
.../solr/client/solrj/io/eval/ReverseEvaluator.java | 10 ++++++----
.../apache/solr/client/solrj/io/eval/ScaleEvaluator.java | 10 ++++++----
.../solr/client/solrj/io/eval/SequenceEvaluator.java | 10 ++++++----
17 files changed, 93 insertions(+), 69 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ConvolutionEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ConvolutionEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ConvolutionEvaluator.java
index 000fa0d..e91620e 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ConvolutionEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ConvolutionEvaluator.java
@@ -18,6 +18,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.List;
+import java.util.Locale;
import java.util.ArrayList;
import org.apache.commons.math3.util.MathArrays;
@@ -35,15 +36,14 @@ public class ConvolutionEvaluator extends ComplexEvaluator implements Expressibl
public ConvolutionEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values but found %d",expression,subEvaluators.size()));
+ }
}
public List<Number> evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Convolution evaluator expects 2 parameters found: "+subEvaluators.size());
- }
-
-
StreamEvaluator colEval1 = subEvaluators.get(0);
StreamEvaluator colEval2 = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CorrelationEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CorrelationEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CorrelationEvaluator.java
index 05db16f..73c9f39 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CorrelationEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CorrelationEvaluator.java
@@ -18,6 +18,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.List;
+import java.util.Locale;
import org.apache.commons.math3.stat.correlation.PearsonsCorrelation;
import org.apache.solr.client.solrj.io.Tuple;
@@ -34,14 +35,14 @@ public class CorrelationEvaluator extends ComplexEvaluator implements Expressibl
public CorrelationEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values but found %d",expression,subEvaluators.size()));
+ }
}
public Number evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Correlation evaluator expects 2 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator colEval1 = subEvaluators.get(0);
StreamEvaluator colEval2 = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CovarianceEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CovarianceEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CovarianceEvaluator.java
index 5778289..9371d78 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CovarianceEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CovarianceEvaluator.java
@@ -18,6 +18,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.List;
+import java.util.Locale;
import org.apache.commons.math3.stat.correlation.Covariance;
import org.apache.solr.client.solrj.io.Tuple;
@@ -34,14 +35,14 @@ public class CovarianceEvaluator extends ComplexEvaluator implements Expressible
public CovarianceEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values but found %d",expression,subEvaluators.size()));
+ }
}
public Number evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Covariance evaluator expects 2 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator colEval1 = subEvaluators.get(0);
StreamEvaluator colEval2 = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CumulativeProbabilityEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CumulativeProbabilityEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CumulativeProbabilityEvaluator.java
index 469e983..9e2bbaf 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CumulativeProbabilityEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/CumulativeProbabilityEvaluator.java
@@ -18,6 +18,7 @@
package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
+import java.util.Locale;
import org.apache.solr.client.solrj.io.Tuple;
import org.apache.solr.client.solrj.io.stream.expr.Explanation;
@@ -33,14 +34,14 @@ public class CumulativeProbabilityEvaluator extends ComplexEvaluator implements
public CumulativeProbabilityEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values (emperical distribution and a number) but found %d",expression,subEvaluators.size()));
+ }
}
public Number evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Cumulative probability expects 2 parameters: an emperical distribution and a number");
- }
-
StreamEvaluator r = subEvaluators.get(0);
StreamEvaluator d = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DescribeEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DescribeEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DescribeEvaluator.java
index 196afe5..e4c7523 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DescribeEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DescribeEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.HashMap;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
import org.apache.commons.math3.stat.descriptive.DescriptiveStatistics;
@@ -36,14 +37,15 @@ public class DescribeEvaluator extends ComplexEvaluator implements Expressible {
public DescribeEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(1 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting one column but found %d",expression,subEvaluators.size()));
+ }
+
}
public Tuple evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 1) {
- throw new IOException("describe expects 1 column as a parameters");
- }
-
StreamEvaluator colEval = subEvaluators.get(0);
List<Number> numbers = (List<Number>)colEval.evaluate(tuple);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DistanceEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DistanceEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DistanceEvaluator.java
index f4ac319..12591ad 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DistanceEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/DistanceEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.List;
+import java.util.Locale;
import org.apache.commons.math3.ml.distance.EuclideanDistance;
import org.apache.solr.client.solrj.io.Tuple;
@@ -35,14 +36,15 @@ public class DistanceEvaluator extends ComplexEvaluator implements Expressible {
public DistanceEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values but found %d",expression,subEvaluators.size()));
+ }
+
}
public Number evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Distance evaluator expects 2 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator colEval1 = subEvaluators.get(0);
StreamEvaluator colEval2 = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/EmpiricalDistributionEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/EmpiricalDistributionEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/EmpiricalDistributionEvaluator.java
index 6885352..8456b4d 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/EmpiricalDistributionEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/EmpiricalDistributionEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.HashMap;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
import java.util.Arrays;
@@ -38,14 +39,14 @@ public class EmpiricalDistributionEvaluator extends ComplexEvaluator implements
public EmpiricalDistributionEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(1 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting one column but found %d",expression,subEvaluators.size()));
+ }
}
public Tuple evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 1) {
- throw new IOException("Empirical dist expects 1 column as a parameters");
- }
-
StreamEvaluator colEval1 = subEvaluators.get(0);
List<Number> numbers1 = (List<Number>)colEval1.evaluate(tuple);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/FindDelayEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/FindDelayEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/FindDelayEvaluator.java
index 0cdd153..4ffaee5 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/FindDelayEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/FindDelayEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.List;
+import java.util.Locale;
import org.apache.commons.math3.util.MathArrays;
import org.apache.solr.client.solrj.io.Tuple;
@@ -35,14 +36,14 @@ public class FindDelayEvaluator extends ComplexEvaluator implements Expressible
public FindDelayEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values but found %d",expression,subEvaluators.size()));
+ }
}
public Number evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Finddelay evaluator expects 2 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator colEval1 = subEvaluators.get(0);
StreamEvaluator colEval2 = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/HistogramEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/HistogramEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/HistogramEvaluator.java
index aa8408b..0217bae 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/HistogramEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/HistogramEvaluator.java
@@ -20,6 +20,7 @@ import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
import org.apache.commons.math3.random.EmpiricalDistribution;
@@ -38,14 +39,14 @@ public class HistogramEvaluator extends ComplexEvaluator implements Expressible
public HistogramEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values but found %d",expression,subEvaluators.size()));
+ }
}
public List<Map> evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Histogram evaluator expects 2 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator colEval1 = subEvaluators.get(0);
List<Number> numbers1 = (List<Number>)colEval1.evaluate(tuple);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/MovingAverageEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/MovingAverageEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/MovingAverageEvaluator.java
index 783116e..bb4909b 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/MovingAverageEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/MovingAverageEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
+import java.util.Locale;
import org.apache.commons.math3.stat.descriptive.DescriptiveStatistics;
import org.apache.solr.client.solrj.io.Tuple;
@@ -35,14 +36,14 @@ public class MovingAverageEvaluator extends ComplexEvaluator implements Expressi
public MovingAverageEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values but found %d",expression,subEvaluators.size()));
+ }
}
public List<Number> evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Moving average evaluator expects 2 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator colEval = subEvaluators.get(0);
StreamEvaluator windowEval = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PercentileEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PercentileEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PercentileEvaluator.java
index 658e66a..6a51360 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PercentileEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PercentileEvaluator.java
@@ -18,6 +18,7 @@
package org.apache.solr.client.solrj.io.eval;
import java.util.List;
+import java.util.Locale;
import java.io.IOException;
import org.apache.solr.client.solrj.io.Tuple;
@@ -35,13 +36,13 @@ public class PercentileEvaluator extends ComplexEvaluator implements Expressible
public PercentileEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values (array and number) but found %d",expression,subEvaluators.size()));
+ }
}
public Number evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Percentile expects 2 parameters: an array and a number");
- }
-
StreamEvaluator colEval = subEvaluators.get(0);
List<Number> column = (List<Number>)colEval.evaluate(tuple);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PredictEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PredictEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PredictEvaluator.java
index 0d1e763..af8a7f0 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PredictEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/PredictEvaluator.java
@@ -18,6 +18,7 @@
package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
+import java.util.Locale;
import org.apache.solr.client.solrj.io.Tuple;
import org.apache.solr.client.solrj.io.stream.expr.Explanation;
@@ -33,14 +34,15 @@ public class PredictEvaluator extends ComplexEvaluator implements Expressible {
public PredictEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values (regression result and a number) but found %d",expression,subEvaluators.size()));
+ }
+
}
public Number evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Predict expects 2 parameters: a regression result and a number");
- }
-
StreamEvaluator r = subEvaluators.get(0);
StreamEvaluator d = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RankEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RankEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RankEvaluator.java
index 2086c92..88a730d 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RankEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RankEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
+import java.util.Locale;
import org.apache.commons.math3.stat.ranking.NaturalRanking;
import org.apache.solr.client.solrj.io.Tuple;
@@ -35,14 +36,15 @@ public class RankEvaluator extends ComplexEvaluator implements Expressible {
public RankEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(1 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting one value but found %d",expression,subEvaluators.size()));
+ }
+
}
public List<Number> evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 1) {
- throw new IOException("Rank evaluator expects 1 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator colEval = subEvaluators.get(0);
List<Number> numbers = (List<Number>)colEval.evaluate(tuple);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RegressionEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RegressionEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RegressionEvaluator.java
index 42a6955..263a69a 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RegressionEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/RegressionEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.HashMap;
import java.util.List;
+import java.util.Locale;
import java.util.Map;
import org.apache.commons.math3.stat.regression.SimpleRegression;
@@ -36,14 +37,15 @@ public class RegressionEvaluator extends ComplexEvaluator implements Expressible
public RegressionEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two columns but found %d",expression,subEvaluators.size()));
+ }
+
}
public Tuple evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Regress expects 2 columns as parameters");
- }
-
StreamEvaluator colEval1 = subEvaluators.get(0);
StreamEvaluator colEval2 = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ReverseEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ReverseEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ReverseEvaluator.java
index cb11c91..56e0b63 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ReverseEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ReverseEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
+import java.util.Locale;
import org.apache.solr.client.solrj.io.Tuple;
import org.apache.solr.client.solrj.io.stream.expr.Explanation;
@@ -34,14 +35,15 @@ public class ReverseEvaluator extends ComplexEvaluator implements Expressible {
public ReverseEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(1 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting one value but found %d",expression,subEvaluators.size()));
+ }
+
}
public List<Number> evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 1) {
- throw new IOException("Reverse evaluator expects 1 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator colEval1 = subEvaluators.get(0);
List<Number> numbers1 = (List<Number>)colEval1.evaluate(tuple);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ScaleEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ScaleEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ScaleEvaluator.java
index f45e2c4..806e6f6 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ScaleEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ScaleEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
+import java.util.Locale;
import org.apache.commons.math3.util.MathArrays;
import org.apache.solr.client.solrj.io.Tuple;
@@ -35,14 +36,15 @@ public class ScaleEvaluator extends ComplexEvaluator implements Expressible {
public ScaleEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(2 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting two values but found %d",expression,subEvaluators.size()));
+ }
+
}
public List<Number> evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 2) {
- throw new IOException("Scale evaluator expects 2 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator numEval = subEvaluators.get(0);
StreamEvaluator colEval1 = subEvaluators.get(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/aeec043e/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/SequenceEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/SequenceEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/SequenceEvaluator.java
index c45e551..c6db106 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/SequenceEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/SequenceEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
+import java.util.Locale;
import org.apache.commons.math3.util.MathArrays;
import org.apache.solr.client.solrj.io.Tuple;
@@ -35,14 +36,15 @@ public class SequenceEvaluator extends ComplexEvaluator implements Expressible {
public SequenceEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(3 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting three values but found %d",expression,subEvaluators.size()));
+ }
+
}
public List<Number> evaluate(Tuple tuple) throws IOException {
- if(subEvaluators.size() != 3) {
- throw new IOException("Sequence evaluator expects 3 parameters found: "+subEvaluators.size());
- }
-
StreamEvaluator sizeEval = subEvaluators.get(0);
StreamEvaluator startEval = subEvaluators.get(1);
StreamEvaluator strideEval = subEvaluators.get(2);
[47/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_hy.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_hy.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_hy.txt
deleted file mode 100644
index 60c1c50..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_hy.txt
+++ /dev/null
@@ -1,46 +0,0 @@
-# example set of Armenian stopwords.
-այդ
-այլ
-այն
-այս
-դու
-դուք
-եմ
-են
-ենք
-ես
-եք
-է
-էի
-էին
-էինք
-էիր
-էիք
-էր
-ըստ
-թ
-ի
-ին
-իսկ
-իր
-կամ
-համար
-հետ
-հետո
-մենք
-մեջ
-մի
-ն
-նա
-նաև
-նրա
-նրանք
-որ
-որը
-որոնք
-որպես
-ու
-ում
-պիտի
-վրա
-և
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_id.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_id.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_id.txt
deleted file mode 100644
index 4617f83..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_id.txt
+++ /dev/null
@@ -1,359 +0,0 @@
-# from appendix D of: A Study of Stemming Effects on Information
-# Retrieval in Bahasa Indonesia
-ada
-adanya
-adalah
-adapun
-agak
-agaknya
-agar
-akan
-akankah
-akhirnya
-aku
-akulah
-amat
-amatlah
-anda
-andalah
-antar
-diantaranya
-antara
-antaranya
-diantara
-apa
-apaan
-mengapa
-apabila
-apakah
-apalagi
-apatah
-atau
-ataukah
-ataupun
-bagai
-bagaikan
-sebagai
-sebagainya
-bagaimana
-bagaimanapun
-sebagaimana
-bagaimanakah
-bagi
-bahkan
-bahwa
-bahwasanya
-sebaliknya
-banyak
-sebanyak
-beberapa
-seberapa
-begini
-beginian
-beginikah
-beginilah
-sebegini
-begitu
-begitukah
-begitulah
-begitupun
-sebegitu
-belum
-belumlah
-sebelum
-sebelumnya
-sebenarnya
-berapa
-berapakah
-berapalah
-berapapun
-betulkah
-sebetulnya
-biasa
-biasanya
-bila
-bilakah
-bisa
-bisakah
-sebisanya
-boleh
-bolehkah
-bolehlah
-buat
-bukan
-bukankah
-bukanlah
-bukannya
-cuma
-percuma
-dahulu
-dalam
-dan
-dapat
-dari
-daripada
-dekat
-demi
-demikian
-demikianlah
-sedemikian
-dengan
-depan
-di
-dia
-dialah
-dini
-diri
-dirinya
-terdiri
-dong
-dulu
-enggak
-enggaknya
-entah
-entahlah
-terhadap
-terhadapnya
-hal
-hampir
-hanya
-hanyalah
-harus
-haruslah
-harusnya
-seharusnya
-hendak
-hendaklah
-hendaknya
-hingga
-sehingga
-ia
-ialah
-ibarat
-ingin
-inginkah
-inginkan
-ini
-inikah
-inilah
-itu
-itukah
-itulah
-jangan
-jangankan
-janganlah
-jika
-jikalau
-juga
-justru
-kala
-kalau
-kalaulah
-kalaupun
-kalian
-kami
-kamilah
-kamu
-kamulah
-kan
-kapan
-kapankah
-kapanpun
-dikarenakan
-karena
-karenanya
-ke
-kecil
-kemudian
-kenapa
-kepada
-kepadanya
-ketika
-seketika
-khususnya
-kini
-kinilah
-kiranya
-sekiranya
-kita
-kitalah
-kok
-lagi
-lagian
-selagi
-lah
-lain
-lainnya
-melainkan
-selaku
-lalu
-melalui
-terlalu
-lama
-lamanya
-selama
-selama
-selamanya
-lebih
-terlebih
-bermacam
-macam
-semacam
-maka
-makanya
-makin
-malah
-malahan
-mampu
-mampukah
-mana
-manakala
-manalagi
-masih
-masihkah
-semasih
-masing
-mau
-maupun
-semaunya
-memang
-mereka
-merekalah
-meski
-meskipun
-semula
-mungkin
-mungkinkah
-nah
-namun
-nanti
-nantinya
-nyaris
-oleh
-olehnya
-seorang
-seseorang
-pada
-padanya
-padahal
-paling
-sepanjang
-pantas
-sepantasnya
-sepantasnyalah
-para
-pasti
-pastilah
-per
-pernah
-pula
-pun
-merupakan
-rupanya
-serupa
-saat
-saatnya
-sesaat
-saja
-sajalah
-saling
-bersama
-sama
-sesama
-sambil
-sampai
-sana
-sangat
-sangatlah
-saya
-sayalah
-se
-sebab
-sebabnya
-sebuah
-tersebut
-tersebutlah
-sedang
-sedangkan
-sedikit
-sedikitnya
-segala
-segalanya
-segera
-sesegera
-sejak
-sejenak
-sekali
-sekalian
-sekalipun
-sesekali
-sekaligus
-sekarang
-sekarang
-sekitar
-sekitarnya
-sela
-selain
-selalu
-seluruh
-seluruhnya
-semakin
-sementara
-sempat
-semua
-semuanya
-sendiri
-sendirinya
-seolah
-seperti
-sepertinya
-sering
-seringnya
-serta
-siapa
-siapakah
-siapapun
-disini
-disinilah
-sini
-sinilah
-sesuatu
-sesuatunya
-suatu
-sesudah
-sesudahnya
-sudah
-sudahkah
-sudahlah
-supaya
-tadi
-tadinya
-tak
-tanpa
-setelah
-telah
-tentang
-tentu
-tentulah
-tentunya
-tertentu
-seterusnya
-tapi
-tetapi
-setiap
-tiap
-setidaknya
-tidak
-tidakkah
-tidaklah
-toh
-waduh
-wah
-wahai
-sewaktu
-walau
-walaupun
-wong
-yaitu
-yakni
-yang
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_it.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_it.txt
deleted file mode 100644
index 1219cc7..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_it.txt
+++ /dev/null
@@ -1,303 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | An Italian stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-ad | a (to) before vowel
-al | a + il
-allo | a + lo
-ai | a + i
-agli | a + gli
-all | a + l'
-agl | a + gl'
-alla | a + la
-alle | a + le
-con | with
-col | con + il
-coi | con + i (forms collo, cogli etc are now very rare)
-da | from
-dal | da + il
-dallo | da + lo
-dai | da + i
-dagli | da + gli
-dall | da + l'
-dagl | da + gll'
-dalla | da + la
-dalle | da + le
-di | of
-del | di + il
-dello | di + lo
-dei | di + i
-degli | di + gli
-dell | di + l'
-degl | di + gl'
-della | di + la
-delle | di + le
-in | in
-nel | in + el
-nello | in + lo
-nei | in + i
-negli | in + gli
-nell | in + l'
-negl | in + gl'
-nella | in + la
-nelle | in + le
-su | on
-sul | su + il
-sullo | su + lo
-sui | su + i
-sugli | su + gli
-sull | su + l'
-sugl | su + gl'
-sulla | su + la
-sulle | su + le
-per | through, by
-tra | among
-contro | against
-io | I
-tu | thou
-lui | he
-lei | she
-noi | we
-voi | you
-loro | they
-mio | my
-mia |
-miei |
-mie |
-tuo |
-tua |
-tuoi | thy
-tue |
-suo |
-sua |
-suoi | his, her
-sue |
-nostro | our
-nostra |
-nostri |
-nostre |
-vostro | your
-vostra |
-vostri |
-vostre |
-mi | me
-ti | thee
-ci | us, there
-vi | you, there
-lo | him, the
-la | her, the
-li | them
-le | them, the
-gli | to him, the
-ne | from there etc
-il | the
-un | a
-uno | a
-una | a
-ma | but
-ed | and
-se | if
-perché | why, because
-anche | also
-come | how
-dov | where (as dov')
-dove | where
-che | who, that
-chi | who
-cui | whom
-non | not
-più | more
-quale | who, that
-quanto | how much
-quanti |
-quanta |
-quante |
-quello | that
-quelli |
-quella |
-quelle |
-questo | this
-questi |
-questa |
-queste |
-si | yes
-tutto | all
-tutti | all
-
- | single letter forms:
-
-a | at
-c | as c' for ce or ci
-e | and
-i | the
-l | as l'
-o | or
-
- | forms of avere, to have (not including the infinitive):
-
-ho
-hai
-ha
-abbiamo
-avete
-hanno
-abbia
-abbiate
-abbiano
-avrò
-avrai
-avrà
-avremo
-avrete
-avranno
-avrei
-avresti
-avrebbe
-avremmo
-avreste
-avrebbero
-avevo
-avevi
-aveva
-avevamo
-avevate
-avevano
-ebbi
-avesti
-ebbe
-avemmo
-aveste
-ebbero
-avessi
-avesse
-avessimo
-avessero
-avendo
-avuto
-avuta
-avuti
-avute
-
- | forms of essere, to be (not including the infinitive):
-sono
-sei
-è
-siamo
-siete
-sia
-siate
-siano
-sarò
-sarai
-sarà
-saremo
-sarete
-saranno
-sarei
-saresti
-sarebbe
-saremmo
-sareste
-sarebbero
-ero
-eri
-era
-eravamo
-eravate
-erano
-fui
-fosti
-fu
-fummo
-foste
-furono
-fossi
-fosse
-fossimo
-fossero
-essendo
-
- | forms of fare, to do (not including the infinitive, fa, fat-):
-faccio
-fai
-facciamo
-fanno
-faccia
-facciate
-facciano
-farò
-farai
-farà
-faremo
-farete
-faranno
-farei
-faresti
-farebbe
-faremmo
-fareste
-farebbero
-facevo
-facevi
-faceva
-facevamo
-facevate
-facevano
-feci
-facesti
-fece
-facemmo
-faceste
-fecero
-facessi
-facesse
-facessimo
-facessero
-facendo
-
- | forms of stare, to be (not including the infinitive):
-sto
-stai
-sta
-stiamo
-stanno
-stia
-stiate
-stiano
-starò
-starai
-starà
-staremo
-starete
-staranno
-starei
-staresti
-starebbe
-staremmo
-stareste
-starebbero
-stavo
-stavi
-stava
-stavamo
-stavate
-stavano
-stetti
-stesti
-stette
-stemmo
-steste
-stettero
-stessi
-stesse
-stessimo
-stessero
-stando
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ja.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ja.txt
deleted file mode 100644
index d4321be..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_ja.txt
+++ /dev/null
@@ -1,127 +0,0 @@
-#
-# This file defines a stopword set for Japanese.
-#
-# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
-# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
-# for frequency lists, etc. that can be useful for making your own set (if desired)
-#
-# Note that there is an overlap between these stopwords and the terms stopped when used
-# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
-# that comments are not allowed on the same line as stopwords.
-#
-# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
-# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
-# using the same character width as the entries in this file. Since this StopFilter is
-# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
-# entries to be in half-width and your kana entries to be in full-width.
-#
-の
-に
-は
-を
-た
-が
-で
-て
-と
-し
-れ
-さ
-ある
-いる
-も
-する
-から
-な
-こと
-として
-い
-や
-れる
-など
-なっ
-ない
-この
-ため
-その
-あっ
-よう
-また
-もの
-という
-あり
-まで
-られ
-なる
-へ
-か
-だ
-これ
-によって
-により
-おり
-より
-による
-ず
-なり
-られる
-において
-ば
-なかっ
-なく
-しかし
-について
-せ
-だっ
-その後
-できる
-それ
-う
-ので
-なお
-のみ
-でき
-き
-つ
-における
-および
-いう
-さらに
-でも
-ら
-たり
-その他
-に関する
-たち
-ます
-ん
-なら
-に対して
-特に
-せる
-及び
-これら
-とき
-では
-にて
-ほか
-ながら
-うち
-そして
-とともに
-ただし
-かつて
-それぞれ
-または
-お
-ほど
-ものの
-に対する
-ほとんど
-と共に
-といった
-です
-とも
-ところ
-ここ
-##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_lv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_lv.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_lv.txt
deleted file mode 100644
index e21a23c..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_lv.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
-# the original list of over 800 forms was refined:
-# pronouns, adverbs, interjections were removed
-#
-# prepositions
-aiz
-ap
-ar
-apakš
-ārpus
-augšpus
-bez
-caur
-dēļ
-gar
-iekš
-iz
-kopš
-labad
-lejpus
-līdz
-no
-otrpus
-pa
-par
-pār
-pēc
-pie
-pirms
-pret
-priekš
-starp
-šaipus
-uz
-viņpus
-virs
-virspus
-zem
-apakšpus
-# Conjunctions
-un
-bet
-jo
-ja
-ka
-lai
-tomēr
-tikko
-turpretī
-arī
-kaut
-gan
-tādēļ
-tā
-ne
-tikvien
-vien
-kā
-ir
-te
-vai
-kamēr
-# Particles
-ar
-diezin
-droši
-diemžēl
-nebūt
-ik
-it
-taču
-nu
-pat
-tiklab
-iekšpus
-nedz
-tik
-nevis
-turpretim
-jeb
-iekam
-iekām
-iekāms
-kolīdz
-līdzko
-tiklīdz
-jebšu
-tālab
-tāpēc
-nekā
-itin
-jā
-jau
-jel
-nē
-nezin
-tad
-tikai
-vis
-tak
-iekams
-vien
-# modal verbs
-būt
-biju
-biji
-bija
-bijām
-bijāt
-esmu
-esi
-esam
-esat
-būšu
-būsi
-būs
-būsim
-būsiet
-tikt
-tiku
-tiki
-tika
-tikām
-tikāt
-tieku
-tiec
-tiek
-tiekam
-tiekat
-tikšu
-tiks
-tiksim
-tiksiet
-tapt
-tapi
-tapāt
-topat
-tapšu
-tapsi
-taps
-tapsim
-tapsiet
-kļūt
-kļuvu
-kļuvi
-kļuva
-kļuvām
-kļuvāt
-kļūstu
-kļūsti
-kļūst
-kļūstam
-kļūstat
-kļūšu
-kļūsi
-kļūs
-kļūsim
-kļūsiet
-# verbs
-varēt
-varēju
-varējām
-varēšu
-varēsim
-var
-varēji
-varējāt
-varēsi
-varēsiet
-varat
-varēja
-varēs
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_nl.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_nl.txt
deleted file mode 100644
index 47a2aea..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_nl.txt
+++ /dev/null
@@ -1,119 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Dutch stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large sample of Dutch text.
-
- | Dutch stop words frequently exhibit homonym clashes. These are indicated
- | clearly below.
-
-de | the
-en | and
-van | of, from
-ik | I, the ego
-te | (1) chez, at etc, (2) to, (3) too
-dat | that, which
-die | that, those, who, which
-in | in, inside
-een | a, an, one
-hij | he
-het | the, it
-niet | not, nothing, naught
-zijn | (1) to be, being, (2) his, one's, its
-is | is
-was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
-op | on, upon, at, in, up, used up
-aan | on, upon, to (as dative)
-met | with, by
-als | like, such as, when
-voor | (1) before, in front of, (2) furrow
-had | had, past tense all persons sing. of 'hebben' (have)
-er | there
-maar | but, only
-om | round, about, for etc
-hem | him
-dan | then
-zou | should/would, past tense all persons sing. of 'zullen'
-of | or, whether, if
-wat | what, something, anything
-mijn | possessive and noun 'mine'
-men | people, 'one'
-dit | this
-zo | so, thus, in this way
-door | through by
-over | over, across
-ze | she, her, they, them
-zich | oneself
-bij | (1) a bee, (2) by, near, at
-ook | also, too
-tot | till, until
-je | you
-mij | me
-uit | out of, from
-der | Old Dutch form of 'van der' still found in surnames
-daar | (1) there, (2) because
-haar | (1) her, their, them, (2) hair
-naar | (1) unpleasant, unwell etc, (2) towards, (3) as
-heb | present first person sing. of 'to have'
-hoe | how, why
-heeft | present third person sing. of 'to have'
-hebben | 'to have' and various parts thereof
-deze | this
-u | you
-want | (1) for, (2) mitten, (3) rigging
-nog | yet, still
-zal | 'shall', first and third person sing. of verb 'zullen' (will)
-me | me
-zij | she, they
-nu | now
-ge | 'thou', still used in Belgium and south Netherlands
-geen | none
-omdat | because
-iets | something, somewhat
-worden | to become, grow, get
-toch | yet, still
-al | all, every, each
-waren | (1) 'were' (2) to wander, (3) wares, (3)
-veel | much, many
-meer | (1) more, (2) lake
-doen | to do, to make
-toen | then, when
-moet | noun 'spot/mote' and present form of 'to must'
-ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
-zonder | without
-kan | noun 'can' and present form of 'to be able'
-hun | their, them
-dus | so, consequently
-alles | all, everything, anything
-onder | under, beneath
-ja | yes, of course
-eens | once, one day
-hier | here
-wie | who
-werd | imperfect third person sing. of 'become'
-altijd | always
-doch | yet, but etc
-wordt | present third person sing. of 'become'
-wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
-kunnen | to be able
-ons | us/our
-zelf | self
-tegen | against, towards, at
-na | after, near
-reeds | already
-wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
-kon | could; past tense of 'to be able'
-niets | nothing
-uw | your
-iemand | somebody
-geweest | been; past participle of 'be'
-andere | other
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_no.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_no.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_no.txt
deleted file mode 100644
index a7a2c28..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_no.txt
+++ /dev/null
@@ -1,194 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Norwegian stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This stop word list is for the dominant bokmål dialect. Words unique
- | to nynorsk are marked *.
-
- | Revised by Jan Bruusgaard <Ja...@ssb.no>, Jan 2005
-
-og | and
-i | in
-jeg | I
-det | it/this/that
-at | to (w. inf.)
-en | a/an
-et | a/an
-den | it/this/that
-til | to
-er | is/am/are
-som | who/that
-på | on
-de | they / you(formal)
-med | with
-han | he
-av | of
-ikke | not
-ikkje | not *
-der | there
-så | so
-var | was/were
-meg | me
-seg | you
-men | but
-ett | one
-har | have
-om | about
-vi | we
-min | my
-mitt | my
-ha | have
-hadde | had
-hun | she
-nå | now
-over | over
-da | when/as
-ved | by/know
-fra | from
-du | you
-ut | out
-sin | your
-dem | them
-oss | us
-opp | up
-man | you/one
-kan | can
-hans | his
-hvor | where
-eller | or
-hva | what
-skal | shall/must
-selv | self (reflective)
-sjøl | self (reflective)
-her | here
-alle | all
-vil | will
-bli | become
-ble | became
-blei | became *
-blitt | have become
-kunne | could
-inn | in
-når | when
-være | be
-kom | come
-noen | some
-noe | some
-ville | would
-dere | you
-som | who/which/that
-deres | their/theirs
-kun | only/just
-ja | yes
-etter | after
-ned | down
-skulle | should
-denne | this
-for | for/because
-deg | you
-si | hers/his
-sine | hers/his
-sitt | hers/his
-mot | against
-å | to
-meget | much
-hvorfor | why
-dette | this
-disse | these/those
-uten | without
-hvordan | how
-ingen | none
-din | your
-ditt | your
-blir | become
-samme | same
-hvilken | which
-hvilke | which (plural)
-sånn | such a
-inni | inside/within
-mellom | between
-vår | our
-hver | each
-hvem | who
-vors | us/ours
-hvis | whose
-både | both
-bare | only/just
-enn | than
-fordi | as/because
-før | before
-mange | many
-også | also
-slik | just
-vært | been
-være | to be
-båe | both *
-begge | both
-siden | since
-dykk | your *
-dykkar | yours *
-dei | they *
-deira | them *
-deires | theirs *
-deim | them *
-di | your (fem.) *
-då | as/when *
-eg | I *
-ein | a/an *
-eit | a/an *
-eitt | a/an *
-elles | or *
-honom | he *
-hjå | at *
-ho | she *
-hoe | she *
-henne | her
-hennar | her/hers
-hennes | hers
-hoss | how *
-hossen | how *
-ikkje | not *
-ingi | noone *
-inkje | noone *
-korleis | how *
-korso | how *
-kva | what/which *
-kvar | where *
-kvarhelst | where *
-kven | who/whom *
-kvi | why *
-kvifor | why *
-me | we *
-medan | while *
-mi | my *
-mine | my *
-mykje | much *
-no | now *
-nokon | some (masc./neut.) *
-noka | some (fem.) *
-nokor | some *
-noko | some *
-nokre | some *
-si | his/hers *
-sia | since *
-sidan | since *
-so | so *
-somt | some *
-somme | some *
-um | about*
-upp | up *
-vere | be *
-vore | was *
-verte | become *
-vort | become *
-varte | became *
-vart | became *
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_pt.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_pt.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_pt.txt
deleted file mode 100644
index acfeb01..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_pt.txt
+++ /dev/null
@@ -1,253 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Portuguese stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-
- | The following is a ranked list (commonest to rarest) of stopwords
- | deriving from a large sample of text.
-
- | Extra words have been added at the end.
-
-de | of, from
-a | the; to, at; her
-o | the; him
-que | who, that
-e | and
-do | de + o
-da | de + a
-em | in
-um | a
-para | for
- | é from SER
-com | with
-não | not, no
-uma | a
-os | the; them
-no | em + o
-se | himself etc
-na | em + a
-por | for
-mais | more
-as | the; them
-dos | de + os
-como | as, like
-mas | but
- | foi from SER
-ao | a + o
-ele | he
-das | de + as
- | tem from TER
-à | a + a
-seu | his
-sua | her
-ou | or
- | ser from SER
-quando | when
-muito | much
- | há from HAV
-nos | em + os; us
-já | already, now
- | está from EST
-eu | I
-também | also
-só | only, just
-pelo | per + o
-pela | per + a
-até | up to
-isso | that
-ela | he
-entre | between
- | era from SER
-depois | after
-sem | without
-mesmo | same
-aos | a + os
- | ter from TER
-seus | his
-quem | whom
-nas | em + as
-me | me
-esse | that
-eles | they
- | estão from EST
-você | you
- | tinha from TER
- | foram from SER
-essa | that
-num | em + um
-nem | nor
-suas | her
-meu | my
-às | a + as
-minha | my
- | têm from TER
-numa | em + uma
-pelos | per + os
-elas | they
- | havia from HAV
- | seja from SER
-qual | which
- | será from SER
-nós | we
- | tenho from TER
-lhe | to him, her
-deles | of them
-essas | those
-esses | those
-pelas | per + as
-este | this
- | fosse from SER
-dele | of him
-
- | other words. There are many contractions such as naquele = em+aquele,
- | mo = me+o, but they are rare.
- | Indefinite article plural forms are also rare.
-
-tu | thou
-te | thee
-vocês | you (plural)
-vos | you
-lhes | to them
-meus | my
-minhas
-teu | thy
-tua
-teus
-tuas
-nosso | our
-nossa
-nossos
-nossas
-
-dela | of her
-delas | of them
-
-esta | this
-estes | these
-estas | these
-aquele | that
-aquela | that
-aqueles | those
-aquelas | those
-isto | this
-aquilo | that
-
- | forms of estar, to be (not including the infinitive):
-estou
-está
-estamos
-estão
-estive
-esteve
-estivemos
-estiveram
-estava
-estávamos
-estavam
-estivera
-estivéramos
-esteja
-estejamos
-estejam
-estivesse
-estivéssemos
-estivessem
-estiver
-estivermos
-estiverem
-
- | forms of haver, to have (not including the infinitive):
-hei
-há
-havemos
-hão
-houve
-houvemos
-houveram
-houvera
-houvéramos
-haja
-hajamos
-hajam
-houvesse
-houvéssemos
-houvessem
-houver
-houvermos
-houverem
-houverei
-houverá
-houveremos
-houverão
-houveria
-houveríamos
-houveriam
-
- | forms of ser, to be (not including the infinitive):
-sou
-somos
-são
-era
-éramos
-eram
-fui
-foi
-fomos
-foram
-fora
-fôramos
-seja
-sejamos
-sejam
-fosse
-fôssemos
-fossem
-for
-formos
-forem
-serei
-será
-seremos
-serão
-seria
-seríamos
-seriam
-
- | forms of ter, to have (not including the infinitive):
-tenho
-tem
-temos
-tém
-tinha
-tínhamos
-tinham
-tive
-teve
-tivemos
-tiveram
-tivera
-tivéramos
-tenha
-tenhamos
-tenham
-tivesse
-tivéssemos
-tivessem
-tiver
-tivermos
-tiverem
-terei
-terá
-teremos
-terão
-teria
-teríamos
-teriam
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_ro.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ro.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ro.txt
deleted file mode 100644
index 4fdee90..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_ro.txt
+++ /dev/null
@@ -1,233 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-acea
-aceasta
-această
-aceea
-acei
-aceia
-acel
-acela
-acele
-acelea
-acest
-acesta
-aceste
-acestea
-aceşti
-aceştia
-acolo
-acum
-ai
-aia
-aibă
-aici
-al
-ăla
-ale
-alea
-ălea
-altceva
-altcineva
-am
-ar
-are
-aş
-aşadar
-asemenea
-asta
-ăsta
-astăzi
-astea
-ăstea
-ăştia
-asupra
-aţi
-au
-avea
-avem
-aveţi
-azi
-bine
-bucur
-bună
-ca
-că
-căci
-când
-care
-cărei
-căror
-cărui
-cât
-câte
-câţi
-către
-câtva
-ce
-cel
-ceva
-chiar
-cînd
-cine
-cineva
-cît
-cîte
-cîţi
-cîtva
-contra
-cu
-cum
-cumva
-curând
-curînd
-da
-dă
-dacă
-dar
-datorită
-de
-deci
-deja
-deoarece
-departe
-deşi
-din
-dinaintea
-dintr
-dintre
-drept
-după
-ea
-ei
-el
-ele
-eram
-este
-eşti
-eu
-face
-fără
-fi
-fie
-fiecare
-fii
-fim
-fiţi
-iar
-ieri
-îi
-îl
-îmi
-împotriva
-în
-înainte
-înaintea
-încât
-încît
-încotro
-între
-întrucât
-întrucît
-îţi
-la
-lângă
-le
-li
-lîngă
-lor
-lui
-mă
-mâine
-mea
-mei
-mele
-mereu
-meu
-mi
-mine
-mult
-multă
-mulţi
-ne
-nicăieri
-nici
-nimeni
-nişte
-noastră
-noastre
-noi
-noştri
-nostru
-nu
-ori
-oricând
-oricare
-oricât
-orice
-oricînd
-oricine
-oricît
-oricum
-oriunde
-până
-pe
-pentru
-peste
-pînă
-poate
-pot
-prea
-prima
-primul
-prin
-printr
-sa
-să
-săi
-sale
-sau
-său
-se
-şi
-sînt
-sîntem
-sînteţi
-spre
-sub
-sunt
-suntem
-sunteţi
-ta
-tăi
-tale
-tău
-te
-ţi
-ţie
-tine
-toată
-toate
-tot
-toţi
-totuşi
-tu
-un
-una
-unde
-undeva
-unei
-unele
-uneori
-unor
-vă
-vi
-voastră
-voastre
-voi
-voştri
-vostru
-vouă
-vreo
-vreun
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_ru.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ru.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ru.txt
deleted file mode 100644
index 5527140..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_ru.txt
+++ /dev/null
@@ -1,243 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | a russian stop word list. comments begin with vertical bar. each stop
- | word is at the start of a line.
-
- | this is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
- | letter `ё' is translated to `е'.
-
-и | and
-в | in/into
-во | alternative form
-не | not
-что | what/that
-он | he
-на | on/onto
-я | i
-с | from
-со | alternative form
-как | how
-а | milder form of `no' (but)
-то | conjunction and form of `that'
-все | all
-она | she
-так | so, thus
-его | him
-но | but
-да | yes/and
-ты | thou
-к | towards, by
-у | around, chez
-же | intensifier particle
-вы | you
-за | beyond, behind
-бы | conditional/subj. particle
-по | up to, along
-только | only
-ее | her
-мне | to me
-было | it was
-вот | here is/are, particle
-от | away from
-меня | me
-еще | still, yet, more
-нет | no, there isnt/arent
-о | about
-из | out of
-ему | to him
-теперь | now
-когда | when
-даже | even
-ну | so, well
-вдруг | suddenly
-ли | interrogative particle
-если | if
-уже | already, but homonym of `narrower'
-или | or
-ни | neither
-быть | to be
-был | he was
-него | prepositional form of его
-до | up to
-вас | you accusative
-нибудь | indef. suffix preceded by hyphen
-опять | again
-уж | already, but homonym of `adder'
-вам | to you
-сказал | he said
-ведь | particle `after all'
-там | there
-потом | then
-себя | oneself
-ничего | nothing
-ей | to her
-может | usually with `быть' as `maybe'
-они | they
-тут | here
-где | where
-есть | there is/are
-надо | got to, must
-ней | prepositional form of ей
-для | for
-мы | we
-тебя | thee
-их | them, their
-чем | than
-была | she was
-сам | self
-чтоб | in order to
-без | without
-будто | as if
-человек | man, person, one
-чего | genitive form of `what'
-раз | once
-тоже | also
-себе | to oneself
-под | beneath
-жизнь | life
-будет | will be
-ж | short form of intensifer particle `же'
-тогда | then
-кто | who
-этот | this
-говорил | was saying
-того | genitive form of `that'
-потому | for that reason
-этого | genitive form of `this'
-какой | which
-совсем | altogether
-ним | prepositional form of `его', `они'
-здесь | here
-этом | prepositional form of `этот'
-один | one
-почти | almost
-мой | my
-тем | instrumental/dative plural of `тот', `то'
-чтобы | full form of `in order that'
-нее | her (acc.)
-кажется | it seems
-сейчас | now
-были | they were
-куда | where to
-зачем | why
-сказать | to say
-всех | all (acc., gen. preposn. plural)
-никогда | never
-сегодня | today
-можно | possible, one can
-при | by
-наконец | finally
-два | two
-об | alternative form of `о', about
-другой | another
-хоть | even
-после | after
-над | above
-больше | more
-тот | that one (masc.)
-через | across, in
-эти | these
-нас | us
-про | about
-всего | in all, only, of all
-них | prepositional form of `они' (they)
-какая | which, feminine
-много | lots
-разве | interrogative particle
-сказала | she said
-три | three
-эту | this, acc. fem. sing.
-моя | my, feminine
-впрочем | moreover, besides
-хорошо | good
-свою | ones own, acc. fem. sing.
-этой | oblique form of `эта', fem. `this'
-перед | in front of
-иногда | sometimes
-лучше | better
-чуть | a little
-том | preposn. form of `that one'
-нельзя | one must not
-такой | such a one
-им | to them
-более | more
-всегда | always
-конечно | of course
-всю | acc. fem. sing of `all'
-между | between
-
-
- | b: some paradigms
- |
- | personal pronouns
- |
- | я меня мне мной [мною]
- | ты тебя тебе тобой [тобою]
- | он его ему им [него, нему, ним]
- | она ее эи ею [нее, нэи, нею]
- | оно его ему им [него, нему, ним]
- |
- | мы нас нам нами
- | вы вас вам вами
- | они их им ими [них, ним, ними]
- |
- | себя себе собой [собою]
- |
- | demonstrative pronouns: этот (this), тот (that)
- |
- | этот эта это эти
- | этого эты это эти
- | этого этой этого этих
- | этому этой этому этим
- | этим этой этим [этою] этими
- | этом этой этом этих
- |
- | тот та то те
- | того ту то те
- | того той того тех
- | тому той тому тем
- | тем той тем [тою] теми
- | том той том тех
- |
- | determinative pronouns
- |
- | (a) весь (all)
- |
- | весь вся все все
- | всего всю все все
- | всего всей всего всех
- | всему всей всему всем
- | всем всей всем [всею] всеми
- | всем всей всем всех
- |
- | (b) сам (himself etc)
- |
- | сам сама само сами
- | самого саму само самих
- | самого самой самого самих
- | самому самой самому самим
- | самим самой самим [самою] самими
- | самом самой самом самих
- |
- | stems of verbs `to be', `to have', `to do' and modal
- |
- | быть бы буд быв есть суть
- | име
- | дел
- | мог мож мочь
- | уме
- | хоч хот
- | долж
- | можн
- | нужн
- | нельзя
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_sv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_sv.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_sv.txt
deleted file mode 100644
index 096f87f..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_sv.txt
+++ /dev/null
@@ -1,133 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Swedish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
- | Swedish stop words occasionally exhibit homonym clashes. For example
- | så = so, but also seed. These are indicated clearly below.
-
-och | and
-det | it, this/that
-att | to (with infinitive)
-i | in, at
-en | a
-jag | I
-hon | she
-som | who, that
-han | he
-på | on
-den | it, this/that
-med | with
-var | where, each
-sig | him(self) etc
-för | for
-så | so (also: seed)
-till | to
-är | is
-men | but
-ett | a
-om | if; around, about
-hade | had
-de | they, these/those
-av | of
-icke | not, no
-mig | me
-du | you
-henne | her
-då | then, when
-sin | his
-nu | now
-har | have
-inte | inte någon = no one
-hans | his
-honom | him
-skulle | 'sake'
-hennes | her
-där | there
-min | my
-man | one (pronoun)
-ej | nor
-vid | at, by, on (also: vast)
-kunde | could
-något | some etc
-från | from, off
-ut | out
-när | when
-efter | after, behind
-upp | up
-vi | we
-dem | them
-vara | be
-vad | what
-över | over
-än | than
-dig | you
-kan | can
-sina | his
-här | here
-ha | have
-mot | towards
-alla | all
-under | under (also: wonder)
-någon | some etc
-eller | or (else)
-allt | all
-mycket | much
-sedan | since
-ju | why
-denna | this/that
-själv | myself, yourself etc
-detta | this/that
-åt | to
-utan | without
-varit | was
-hur | how
-ingen | no
-mitt | my
-ni | you
-bli | to be, become
-blev | from bli
-oss | us
-din | thy
-dessa | these/those
-några | some etc
-deras | their
-blir | from bli
-mina | my
-samma | (the) same
-vilken | who, that
-er | you, your
-sådan | such a
-vår | our
-blivit | from bli
-dess | its
-inom | within
-mellan | between
-sådant | such a
-varför | why
-varje | each
-vilka | who, that
-ditt | thy
-vem | who
-vilket | who, that
-sitta | his
-sådana | such a
-vart | each
-dina | thy
-vars | whose
-vårt | our
-våra | our
-ert | your
-era | your
-vilkas | whose
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_th.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_th.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_th.txt
deleted file mode 100644
index 07f0fab..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_th.txt
+++ /dev/null
@@ -1,119 +0,0 @@
-# Thai stopwords from:
-# "Opinion Detection in Thai Political News Columns
-# Based on Subjectivity Analysis"
-# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
-ไว้
-ไม่
-ไป
-ได้
-ให้
-ใน
-โดย
-แห่ง
-แล้ว
-และ
-แรก
-แบบ
-แต่
-เอง
-เห็น
-เลย
-เริ่ม
-เรา
-เมื่อ
-เพื่อ
-เพราะ
-เป็นการ
-เป็น
-เปิดเผย
-เปิด
-เนื่องจาก
-เดียวกัน
-เดียว
-เช่น
-เฉพาะ
-เคย
-เข้า
-เขา
-อีก
-อาจ
-อะไร
-ออก
-อย่าง
-อยู่
-อยาก
-หาก
-หลาย
-หลังจาก
-หลัง
-หรือ
-หนึ่ง
-ส่วน
-ส่ง
-สุด
-สําหรับ
-ว่า
-วัน
-ลง
-ร่วม
-ราย
-รับ
-ระหว่าง
-รวม
-ยัง
-มี
-มาก
-มา
-พร้อม
-พบ
-ผ่าน
-ผล
-บาง
-น่า
-นี้
-นํา
-นั้น
-นัก
-นอกจาก
-ทุก
-ที่สุด
-ที่
-ทําให้
-ทํา
-ทาง
-ทั้งนี้
-ทั้ง
-ถ้า
-ถูก
-ถึง
-ต้อง
-ต่างๆ
-ต่าง
-ต่อ
-ตาม
-ตั้งแต่
-ตั้ง
-ด้าน
-ด้วย
-ดัง
-ซึ่ง
-ช่วง
-จึง
-จาก
-จัด
-จะ
-คือ
-ความ
-ครั้ง
-คง
-ขึ้น
-ของ
-ขอ
-ขณะ
-ก่อน
-ก็
-การ
-กับ
-กัน
-กว่า
-กล่าว
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_tr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_tr.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_tr.txt
deleted file mode 100644
index 84d9408..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_tr.txt
+++ /dev/null
@@ -1,212 +0,0 @@
-# Turkish stopwords from LUCENE-559
-# merged with the list from "Information Retrieval on Turkish Texts"
-# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
-acaba
-altmış
-altı
-ama
-ancak
-arada
-aslında
-ayrıca
-bana
-bazı
-belki
-ben
-benden
-beni
-benim
-beri
-beş
-bile
-bin
-bir
-birçok
-biri
-birkaç
-birkez
-birşey
-birşeyi
-biz
-bize
-bizden
-bizi
-bizim
-böyle
-böylece
-bu
-buna
-bunda
-bundan
-bunlar
-bunları
-bunların
-bunu
-bunun
-burada
-çok
-çünkü
-da
-daha
-dahi
-de
-defa
-değil
-diğer
-diye
-doksan
-dokuz
-dolayı
-dolayısıyla
-dört
-edecek
-eden
-ederek
-edilecek
-ediliyor
-edilmesi
-ediyor
-eğer
-elli
-en
-etmesi
-etti
-ettiği
-ettiğini
-gibi
-göre
-halen
-hangi
-hatta
-hem
-henüz
-hep
-hepsi
-her
-herhangi
-herkesin
-hiç
-hiçbir
-için
-iki
-ile
-ilgili
-ise
-işte
-itibaren
-itibariyle
-kadar
-karşın
-katrilyon
-kendi
-kendilerine
-kendini
-kendisi
-kendisine
-kendisini
-kez
-ki
-kim
-kimden
-kime
-kimi
-kimse
-kırk
-milyar
-milyon
-mu
-mü
-mı
-nasıl
-ne
-neden
-nedenle
-nerde
-nerede
-nereye
-niye
-niçin
-o
-olan
-olarak
-oldu
-olduğu
-olduğunu
-olduklarını
-olmadı
-olmadığı
-olmak
-olması
-olmayan
-olmaz
-olsa
-olsun
-olup
-olur
-olursa
-oluyor
-on
-ona
-ondan
-onlar
-onlardan
-onları
-onların
-onu
-onun
-otuz
-oysa
-öyle
-pek
-rağmen
-sadece
-sanki
-sekiz
-seksen
-sen
-senden
-seni
-senin
-siz
-sizden
-sizi
-sizin
-şey
-şeyden
-şeyi
-şeyler
-şöyle
-şu
-şuna
-şunda
-şundan
-şunları
-şunu
-tarafından
-trilyon
-tüm
-üç
-üzere
-var
-vardı
-ve
-veya
-ya
-yani
-yapacak
-yapılan
-yapılması
-yapıyor
-yapmak
-yaptı
-yaptığı
-yaptığını
-yaptıkları
-yedi
-yerine
-yetmiş
-yine
-yirmi
-yoksa
-yüz
-zaten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/userdict_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/userdict_ja.txt b/solr/server/solr/configsets/_default/conf/lang/userdict_ja.txt
deleted file mode 100644
index 6f0368e..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/userdict_ja.txt
+++ /dev/null
@@ -1,29 +0,0 @@
-#
-# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
-#
-# Add entries to this file in order to override the statistical model in terms
-# of segmentation, readings and part-of-speech tags. Notice that entries do
-# not have weights since they are always used when found. This is by-design
-# in order to maximize ease-of-use.
-#
-# Entries are defined using the following CSV format:
-# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
-#
-# Notice that a single half-width space separates tokens and readings, and
-# that the number tokens and readings must match exactly.
-#
-# Also notice that multiple entries with the same <text> is undefined.
-#
-# Whitespace only lines are ignored. Comments are not allowed on entry lines.
-#
-
-# Custom segmentation for kanji compounds
-日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
-関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
-
-# Custom segmentation for compound katakana
-トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
-ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
-
-# Custom reading for former sumo wrestler
-朝青龍,朝青龍,アサショウリュウ,カスタム人名
[32/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
SOLR-10574: Adding unified _default config set
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/d1c807dd
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/d1c807dd
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/d1c807dd
Branch: refs/heads/feature/autoscaling
Commit: d1c807dd70ea77963877d753050e15512eb698a0
Parents: 7c2429b
Author: Ishan Chattopadhyaya <is...@apache.org>
Authored: Mon Jun 19 10:45:45 2017 +0000
Committer: Ishan Chattopadhyaya <is...@apache.org>
Committed: Tue Jun 20 11:05:07 2017 +0000
----------------------------------------------------------------------
solr/bin/solr | 11 +-
.../solr/configsets/_default/conf/currency.xml | 67 +
.../solr/configsets/_default/conf/elevate.xml | 42 +
.../_default/conf/lang/contractions_ca.txt | 8 +
.../_default/conf/lang/contractions_fr.txt | 15 +
.../_default/conf/lang/contractions_ga.txt | 5 +
.../_default/conf/lang/contractions_it.txt | 23 +
.../_default/conf/lang/hyphenations_ga.txt | 5 +
.../_default/conf/lang/stemdict_nl.txt | 6 +
.../_default/conf/lang/stoptags_ja.txt | 420 ++++++
.../_default/conf/lang/stopwords_ar.txt | 125 ++
.../_default/conf/lang/stopwords_bg.txt | 193 +++
.../_default/conf/lang/stopwords_ca.txt | 220 +++
.../_default/conf/lang/stopwords_cz.txt | 172 +++
.../_default/conf/lang/stopwords_da.txt | 110 ++
.../_default/conf/lang/stopwords_de.txt | 294 ++++
.../_default/conf/lang/stopwords_el.txt | 78 +
.../_default/conf/lang/stopwords_en.txt | 54 +
.../_default/conf/lang/stopwords_es.txt | 356 +++++
.../_default/conf/lang/stopwords_eu.txt | 99 ++
.../_default/conf/lang/stopwords_fa.txt | 313 ++++
.../_default/conf/lang/stopwords_fi.txt | 97 ++
.../_default/conf/lang/stopwords_fr.txt | 186 +++
.../_default/conf/lang/stopwords_ga.txt | 110 ++
.../_default/conf/lang/stopwords_gl.txt | 161 ++
.../_default/conf/lang/stopwords_hi.txt | 235 +++
.../_default/conf/lang/stopwords_hu.txt | 211 +++
.../_default/conf/lang/stopwords_hy.txt | 46 +
.../_default/conf/lang/stopwords_id.txt | 359 +++++
.../_default/conf/lang/stopwords_it.txt | 303 ++++
.../_default/conf/lang/stopwords_ja.txt | 127 ++
.../_default/conf/lang/stopwords_lv.txt | 172 +++
.../_default/conf/lang/stopwords_nl.txt | 119 ++
.../_default/conf/lang/stopwords_no.txt | 194 +++
.../_default/conf/lang/stopwords_pt.txt | 253 ++++
.../_default/conf/lang/stopwords_ro.txt | 233 +++
.../_default/conf/lang/stopwords_ru.txt | 243 +++
.../_default/conf/lang/stopwords_sv.txt | 133 ++
.../_default/conf/lang/stopwords_th.txt | 119 ++
.../_default/conf/lang/stopwords_tr.txt | 212 +++
.../_default/conf/lang/userdict_ja.txt | 29 +
.../configsets/_default/conf/managed-schema | 1069 +++++++++++++
.../solr/configsets/_default/conf/params.json | 20 +
.../solr/configsets/_default/conf/protwords.txt | 21 +
.../configsets/_default/conf/solrconfig.xml | 1408 ++++++++++++++++++
.../solr/configsets/_default/conf/stopwords.txt | 14 +
.../solr/configsets/_default/conf/synonyms.txt | 29 +
.../configsets/basic_configs/conf/currency.xml | 67 -
.../configsets/basic_configs/conf/elevate.xml | 42 -
.../basic_configs/conf/lang/contractions_ca.txt | 8 -
.../basic_configs/conf/lang/contractions_fr.txt | 15 -
.../basic_configs/conf/lang/contractions_ga.txt | 5 -
.../basic_configs/conf/lang/contractions_it.txt | 23 -
.../basic_configs/conf/lang/hyphenations_ga.txt | 5 -
.../basic_configs/conf/lang/stemdict_nl.txt | 6 -
.../basic_configs/conf/lang/stoptags_ja.txt | 420 ------
.../basic_configs/conf/lang/stopwords_ar.txt | 125 --
.../basic_configs/conf/lang/stopwords_bg.txt | 193 ---
.../basic_configs/conf/lang/stopwords_ca.txt | 220 ---
.../basic_configs/conf/lang/stopwords_cz.txt | 172 ---
.../basic_configs/conf/lang/stopwords_da.txt | 110 --
.../basic_configs/conf/lang/stopwords_de.txt | 294 ----
.../basic_configs/conf/lang/stopwords_el.txt | 78 -
.../basic_configs/conf/lang/stopwords_en.txt | 54 -
.../basic_configs/conf/lang/stopwords_es.txt | 356 -----
.../basic_configs/conf/lang/stopwords_eu.txt | 99 --
.../basic_configs/conf/lang/stopwords_fa.txt | 313 ----
.../basic_configs/conf/lang/stopwords_fi.txt | 97 --
.../basic_configs/conf/lang/stopwords_fr.txt | 186 ---
.../basic_configs/conf/lang/stopwords_ga.txt | 110 --
.../basic_configs/conf/lang/stopwords_gl.txt | 161 --
.../basic_configs/conf/lang/stopwords_hi.txt | 235 ---
.../basic_configs/conf/lang/stopwords_hu.txt | 211 ---
.../basic_configs/conf/lang/stopwords_hy.txt | 46 -
.../basic_configs/conf/lang/stopwords_id.txt | 359 -----
.../basic_configs/conf/lang/stopwords_it.txt | 303 ----
.../basic_configs/conf/lang/stopwords_ja.txt | 127 --
.../basic_configs/conf/lang/stopwords_lv.txt | 172 ---
.../basic_configs/conf/lang/stopwords_nl.txt | 119 --
.../basic_configs/conf/lang/stopwords_no.txt | 194 ---
.../basic_configs/conf/lang/stopwords_pt.txt | 253 ----
.../basic_configs/conf/lang/stopwords_ro.txt | 233 ---
.../basic_configs/conf/lang/stopwords_ru.txt | 243 ---
.../basic_configs/conf/lang/stopwords_sv.txt | 133 --
.../basic_configs/conf/lang/stopwords_th.txt | 119 --
.../basic_configs/conf/lang/stopwords_tr.txt | 212 ---
.../basic_configs/conf/lang/userdict_ja.txt | 29 -
.../basic_configs/conf/managed-schema | 1069 -------------
.../configsets/basic_configs/conf/params.json | 20 -
.../configsets/basic_configs/conf/protwords.txt | 21 -
.../basic_configs/conf/solrconfig.xml | 1408 ------------------
.../configsets/basic_configs/conf/stopwords.txt | 14 -
.../configsets/basic_configs/conf/synonyms.txt | 29 -
.../conf/currency.xml | 67 -
.../data_driven_schema_configs/conf/elevate.xml | 42 -
.../conf/lang/contractions_ca.txt | 8 -
.../conf/lang/contractions_fr.txt | 15 -
.../conf/lang/contractions_ga.txt | 5 -
.../conf/lang/contractions_it.txt | 23 -
.../conf/lang/hyphenations_ga.txt | 5 -
.../conf/lang/stemdict_nl.txt | 6 -
.../conf/lang/stoptags_ja.txt | 420 ------
.../conf/lang/stopwords_ar.txt | 125 --
.../conf/lang/stopwords_bg.txt | 193 ---
.../conf/lang/stopwords_ca.txt | 220 ---
.../conf/lang/stopwords_cz.txt | 172 ---
.../conf/lang/stopwords_da.txt | 110 --
.../conf/lang/stopwords_de.txt | 294 ----
.../conf/lang/stopwords_el.txt | 78 -
.../conf/lang/stopwords_en.txt | 54 -
.../conf/lang/stopwords_es.txt | 356 -----
.../conf/lang/stopwords_eu.txt | 99 --
.../conf/lang/stopwords_fa.txt | 313 ----
.../conf/lang/stopwords_fi.txt | 97 --
.../conf/lang/stopwords_fr.txt | 186 ---
.../conf/lang/stopwords_ga.txt | 110 --
.../conf/lang/stopwords_gl.txt | 161 --
.../conf/lang/stopwords_hi.txt | 235 ---
.../conf/lang/stopwords_hu.txt | 211 ---
.../conf/lang/stopwords_hy.txt | 46 -
.../conf/lang/stopwords_id.txt | 359 -----
.../conf/lang/stopwords_it.txt | 303 ----
.../conf/lang/stopwords_ja.txt | 127 --
.../conf/lang/stopwords_lv.txt | 172 ---
.../conf/lang/stopwords_nl.txt | 119 --
.../conf/lang/stopwords_no.txt | 194 ---
.../conf/lang/stopwords_pt.txt | 253 ----
.../conf/lang/stopwords_ro.txt | 233 ---
.../conf/lang/stopwords_ru.txt | 243 ---
.../conf/lang/stopwords_sv.txt | 133 --
.../conf/lang/stopwords_th.txt | 119 --
.../conf/lang/stopwords_tr.txt | 212 ---
.../conf/lang/userdict_ja.txt | 29 -
.../conf/managed-schema | 1069 -------------
.../data_driven_schema_configs/conf/params.json | 20 -
.../conf/protwords.txt | 21 -
.../conf/solrconfig.xml | 1406 -----------------
.../conf/stopwords.txt | 14 -
.../conf/synonyms.txt | 29 -
139 files changed, 8713 insertions(+), 17420 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/bin/solr
----------------------------------------------------------------------
diff --git a/solr/bin/solr b/solr/bin/solr
index 6b2b806..d21167e1 100755
--- a/solr/bin/solr
+++ b/solr/bin/solr
@@ -416,12 +416,11 @@ function print_usage() {
echo ""
echo " -d <confdir> Configuration directory to copy when creating the new core, built-in options are:"
echo ""
- echo " basic_configs: Minimal Solr configuration"
- echo " data_driven_schema_configs: Managed schema with field-guessing support enabled"
+ echo " _default: Minimal configuration, which supports enabling/disabling field-guessing support"
echo " sample_techproducts_configs: Example configuration with many optional features enabled to"
echo " demonstrate the full power of Solr"
echo ""
- echo " If not specified, default is: data_driven_schema_configs"
+ echo " If not specified, default is: _default"
echo ""
echo " Alternatively, you can pass the path to your own configuration directory instead of using"
echo " one of the built-in configurations, such as: bin/solr create_core -c mycore -d /tmp/myconfig"
@@ -438,12 +437,12 @@ function print_usage() {
echo ""
echo " -d <confdir> Configuration directory to copy when creating the new collection, built-in options are:"
echo ""
- echo " basic_configs: Minimal Solr configuration"
+ echo " _default: Minimal configuration, which supports enabling/disabling field-guessing support"
echo " data_driven_schema_configs: Managed schema with field-guessing support enabled"
echo " sample_techproducts_configs: Example configuration with many optional features enabled to"
echo " demonstrate the full power of Solr"
echo ""
- echo " If not specified, default is: data_driven_schema_configs"
+ echo " If not specified, default is: _default"
echo ""
echo " Alternatively, you can pass the path to your own configuration directory instead of using"
echo " one of the built-in configurations, such as: bin/solr create_collection -c mycoll -d /tmp/myconfig"
@@ -932,7 +931,7 @@ if [[ "$SCRIPT_CMD" == "create" || "$SCRIPT_CMD" == "create_core" || "$SCRIPT_CM
fi
if [ -z "$CREATE_CONFDIR" ]; then
- CREATE_CONFDIR='data_driven_schema_configs'
+ CREATE_CONFDIR='_default'
fi
# validate the confdir arg
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/currency.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/currency.xml b/solr/server/solr/configsets/_default/conf/currency.xml
new file mode 100644
index 0000000..3a9c58a
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/currency.xml
@@ -0,0 +1,67 @@
+<?xml version="1.0" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!-- Example exchange rates file for CurrencyField type named "currency" in example schema -->
+
+<currencyConfig version="1.0">
+ <rates>
+ <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 -->
+ <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" />
+ <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" />
+ <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" />
+ <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" />
+ <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" />
+ <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" />
+ <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" />
+ <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" />
+ <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" />
+ <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" />
+ <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" />
+ <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" />
+ <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" />
+ <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" />
+ <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" />
+ <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" />
+ <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" />
+ <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" />
+ <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" />
+ <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" />
+ <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" />
+ <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" />
+ <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" />
+ <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" />
+ <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" />
+ <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" />
+ <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" />
+ <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" />
+ <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" />
+ <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" />
+ <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" />
+ <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" />
+ <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" />
+ <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" />
+ <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" />
+ <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" />
+ <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" />
+
+ <!-- Cross-rates for some common currencies -->
+ <rate from="EUR" to="GBP" rate="0.869914" />
+ <rate from="EUR" to="NOK" rate="7.800095" />
+ <rate from="GBP" to="NOK" rate="8.966508" />
+ </rates>
+</currencyConfig>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/elevate.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/elevate.xml b/solr/server/solr/configsets/_default/conf/elevate.xml
new file mode 100644
index 0000000..2c09ebe
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/elevate.xml
@@ -0,0 +1,42 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!-- If this file is found in the config directory, it will only be
+ loaded once at startup. If it is found in Solr's data
+ directory, it will be re-loaded every commit.
+
+ See http://wiki.apache.org/solr/QueryElevationComponent for more info
+
+-->
+<elevate>
+ <!-- Query elevation examples
+ <query text="foo bar">
+ <doc id="1" />
+ <doc id="2" />
+ <doc id="3" />
+ </query>
+
+for use with techproducts example
+
+ <query text="ipod">
+ <doc id="MA147LL/A" /> put the actual ipod at the top
+ <doc id="IW-02" exclude="true" /> exclude this cable
+ </query>
+-->
+
+</elevate>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/contractions_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/contractions_ca.txt b/solr/server/solr/configsets/_default/conf/lang/contractions_ca.txt
new file mode 100644
index 0000000..307a85f
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/contractions_ca.txt
@@ -0,0 +1,8 @@
+# Set of Catalan contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+l
+m
+n
+s
+t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/contractions_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/contractions_fr.txt b/solr/server/solr/configsets/_default/conf/lang/contractions_fr.txt
new file mode 100644
index 0000000..f1bba51
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/contractions_fr.txt
@@ -0,0 +1,15 @@
+# Set of French contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+l
+m
+t
+qu
+n
+s
+j
+d
+c
+jusqu
+quoiqu
+lorsqu
+puisqu
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/contractions_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/contractions_ga.txt b/solr/server/solr/configsets/_default/conf/lang/contractions_ga.txt
new file mode 100644
index 0000000..9ebe7fa
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/contractions_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+m
+b
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/contractions_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/contractions_it.txt b/solr/server/solr/configsets/_default/conf/lang/contractions_it.txt
new file mode 100644
index 0000000..cac0409
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/contractions_it.txt
@@ -0,0 +1,23 @@
+# Set of Italian contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+c
+l
+all
+dall
+dell
+nell
+sull
+coll
+pell
+gl
+agl
+dagl
+degl
+negl
+sugl
+un
+m
+t
+s
+v
+d
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/hyphenations_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/hyphenations_ga.txt b/solr/server/solr/configsets/_default/conf/lang/hyphenations_ga.txt
new file mode 100644
index 0000000..4d2642c
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/hyphenations_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish hyphenations for StopFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+h
+n
+t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stemdict_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stemdict_nl.txt b/solr/server/solr/configsets/_default/conf/lang/stemdict_nl.txt
new file mode 100644
index 0000000..4410729
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stemdict_nl.txt
@@ -0,0 +1,6 @@
+# Set of overrides for the dutch stemmer
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+fiets fiets
+bromfiets bromfiets
+ei eier
+kind kinder
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stoptags_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stoptags_ja.txt b/solr/server/solr/configsets/_default/conf/lang/stoptags_ja.txt
new file mode 100644
index 0000000..71b7508
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stoptags_ja.txt
@@ -0,0 +1,420 @@
+#
+# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
+#
+# Any token with a part-of-speech tag that exactly matches those defined in this
+# file are removed from the token stream.
+#
+# Set your own stoptags by uncommenting the lines below. Note that comments are
+# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
+# etc. that can be useful for building you own stoptag set.
+#
+# The entire possible tagset is provided below for convenience.
+#
+#####
+# noun: unclassified nouns
+#名詞
+#
+# noun-common: Common nouns or nouns where the sub-classification is undefined
+#名詞-一般
+#
+# noun-proper: Proper nouns where the sub-classification is undefined
+#名詞-固有名詞
+#
+# noun-proper-misc: miscellaneous proper nouns
+#名詞-固有名詞-一般
+#
+# noun-proper-person: Personal names where the sub-classification is undefined
+#名詞-固有名詞-人名
+#
+# noun-proper-person-misc: names that cannot be divided into surname and
+# given name; foreign names; names where the surname or given name is unknown.
+# e.g. お市の方
+#名詞-固有名詞-人名-一般
+#
+# noun-proper-person-surname: Mainly Japanese surnames.
+# e.g. 山田
+#名詞-固有名詞-人名-姓
+#
+# noun-proper-person-given_name: Mainly Japanese given names.
+# e.g. 太郎
+#名詞-固有名詞-人名-名
+#
+# noun-proper-organization: Names representing organizations.
+# e.g. 通産省, NHK
+#名詞-固有名詞-組織
+#
+# noun-proper-place: Place names where the sub-classification is undefined
+#名詞-固有名詞-地域
+#
+# noun-proper-place-misc: Place names excluding countries.
+# e.g. アジア, バルセロナ, 京都
+#名詞-固有名詞-地域-一般
+#
+# noun-proper-place-country: Country names.
+# e.g. 日本, オーストラリア
+#名詞-固有名詞-地域-国
+#
+# noun-pronoun: Pronouns where the sub-classification is undefined
+#名詞-代名詞
+#
+# noun-pronoun-misc: miscellaneous pronouns:
+# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
+#名詞-代名詞-一般
+#
+# noun-pronoun-contraction: Spoken language contraction made by combining a
+# pronoun and the particle 'wa'.
+# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
+#名詞-代名詞-縮約
+#
+# noun-adverbial: Temporal nouns such as names of days or months that behave
+# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
+# e.g. 金曜, 一月, 午後, 少量
+#名詞-副詞可能
+#
+# noun-verbal: Nouns that take arguments with case and can appear followed by
+# 'suru' and related verbs (する, できる, なさる, くださる)
+# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
+#名詞-サ変接続
+#
+# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
+# e.g. 健康, 安易, 駄目, だめ
+#名詞-形容動詞語幹
+#
+# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
+# e.g. 0, 1, 2, 何, 数, 幾
+#名詞-数
+#
+# noun-affix: noun affixes where the sub-classification is undefined
+#名詞-非自立
+#
+# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
+# attach to the base form of inflectional words, words that cannot be classified
+# into any of the other categories below. This category includes indefinite nouns.
+# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
+# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
+# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
+# わり, 割り, 割, ん-口語/, もん-口語/
+#名詞-非自立-一般
+#
+# noun-affix-adverbial: noun affixes that that can behave as adverbs.
+# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
+# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
+# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
+# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
+# 儘, 侭, みぎり, 矢先
+#名詞-非自立-副詞可能
+#
+# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
+# with the stem よう(だ) ("you(da)").
+# e.g. よう, やう, 様 (よう)
+#名詞-非自立-助動詞語幹
+#
+# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
+# connection form な (aux "da").
+# e.g. みたい, ふう
+#名詞-非自立-形容動詞語幹
+#
+# noun-special: special nouns where the sub-classification is undefined.
+#名詞-特殊
+#
+# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
+# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
+# form of inflectional words.
+# e.g. そう
+#名詞-特殊-助動詞語幹
+#
+# noun-suffix: noun suffixes where the sub-classification is undefined.
+#名詞-接尾
+#
+# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
+# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
+# any of the other categories below. In general, this category is more inclusive than
+# 接尾語 ("suffix") and is usually the last element in a compound noun.
+# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
+# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
+#名詞-接尾-一般
+#
+# noun-suffix-person: Suffixes that form nouns and attach to person names more often
+# than other nouns.
+# e.g. 君, 様, 著
+#名詞-接尾-人名
+#
+# noun-suffix-place: Suffixes that form nouns and attach to place names more often
+# than other nouns.
+# e.g. 町, 市, 県
+#名詞-接尾-地域
+#
+# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
+# can appear before スル ("suru").
+# e.g. 化, 視, 分け, 入り, 落ち, 買い
+#名詞-接尾-サ変接続
+#
+# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
+# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
+# conjunctive form of inflectional words.
+# e.g. そう
+#名詞-接尾-助動詞語幹
+#
+# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
+# form of inflectional words and appear before the copula だ ("da").
+# e.g. 的, げ, がち
+#名詞-接尾-形容動詞語幹
+#
+# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
+# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
+#名詞-接尾-副詞可能
+#
+# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
+# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
+# to numbers.
+# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
+#名詞-接尾-助数詞
+#
+# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
+# e.g. (楽し) さ, (考え) 方
+#名詞-接尾-特殊
+#
+# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
+# together.
+# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
+#名詞-接続詞的
+#
+# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
+# semantically verb-like.
+# e.g. ごらん, ご覧, 御覧, 頂戴
+#名詞-動詞非自立的
+#
+# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
+# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
+# is いわく ("iwaku").
+#名詞-引用文字列
+#
+# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
+# behave like an adjective.
+# e.g. 申し訳, 仕方, とんでも, 違い
+#名詞-ナイ形容詞語幹
+#
+#####
+# prefix: unclassified prefixes
+#接頭詞
+#
+# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
+# excluding numerical expressions.
+# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
+#接頭詞-名詞接続
+#
+# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
+# in conjunctive form followed by なる/なさる/くださる.
+# e.g. お (読みなさい), お (座り)
+#接頭詞-動詞接続
+#
+# prefix-adjectival: Prefixes that attach to adjectives.
+# e.g. お (寒いですねえ), バカ (でかい)
+#接頭詞-形容詞接続
+#
+# prefix-numerical: Prefixes that attach to numerical expressions.
+# e.g. 約, およそ, 毎時
+#接頭詞-数接続
+#
+#####
+# verb: unclassified verbs
+#動詞
+#
+# verb-main:
+#動詞-自立
+#
+# verb-auxiliary:
+#動詞-非自立
+#
+# verb-suffix:
+#動詞-接尾
+#
+#####
+# adjective: unclassified adjectives
+#形容詞
+#
+# adjective-main:
+#形容詞-自立
+#
+# adjective-auxiliary:
+#形容詞-非自立
+#
+# adjective-suffix:
+#形容詞-接尾
+#
+#####
+# adverb: unclassified adverbs
+#副詞
+#
+# adverb-misc: Words that can be segmented into one unit and where adnominal
+# modification is not possible.
+# e.g. あいかわらず, 多分
+#副詞-一般
+#
+# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
+# な, する, だ, etc.
+# e.g. こんなに, そんなに, あんなに, なにか, なんでも
+#副詞-助詞類接続
+#
+#####
+# adnominal: Words that only have noun-modifying forms.
+# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
+# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
+# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
+#連体詞
+#
+#####
+# conjunction: Conjunctions that can occur independently.
+# e.g. が, けれども, そして, じゃあ, それどころか
+接続詞
+#
+#####
+# particle: unclassified particles.
+助詞
+#
+# particle-case: case particles where the subclassification is undefined.
+助詞-格助詞
+#
+# particle-case-misc: Case particles.
+# e.g. から, が, で, と, に, へ, より, を, の, にて
+助詞-格助詞-一般
+#
+# particle-case-quote: the "to" that appears after nouns, a person’s speech,
+# quotation marks, expressions of decisions from a meeting, reasons, judgements,
+# conjectures, etc.
+# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
+助詞-格助詞-引用
+#
+# particle-case-compound: Compounds of particles and verbs that mainly behave
+# like case particles.
+# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
+# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
+# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
+# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
+# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
+# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
+# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
+# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
+助詞-格助詞-連語
+#
+# particle-conjunctive:
+# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
+# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
+# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
+助詞-接続助詞
+#
+# particle-dependency:
+# e.g. こそ, さえ, しか, すら, は, も, ぞ
+助詞-係助詞
+#
+# particle-adverbial:
+# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
+# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
+# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
+# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
+# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
+助詞-副助詞
+#
+# particle-interjective: particles with interjective grammatical roles.
+# e.g. (松島) や
+助詞-間投助詞
+#
+# particle-coordinate:
+# e.g. と, たり, だの, だり, とか, なり, や, やら
+助詞-並立助詞
+#
+# particle-final:
+# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
+# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
+助詞-終助詞
+#
+# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
+# adverbial, conjunctive, or sentence final. For example:
+# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
+# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
+# 「(祈りが届いたせい) か (, 試験に合格した.)」
+# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
+# e.g. か
+助詞-副助詞／並立助詞／終助詞
+#
+# particle-adnominalizer: The "no" that attaches to nouns and modifies
+# non-inflectional words.
+助詞-連体化
+#
+# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
+# that are giongo, giseigo, or gitaigo.
+# e.g. に, と
+助詞-副詞化
+#
+# particle-special: A particle that does not fit into one of the above classifications.
+# This includes particles that are used in Tanka, Haiku, and other poetry.
+# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
+助詞-特殊
+#
+#####
+# auxiliary-verb:
+助動詞
+#
+#####
+# interjection: Greetings and other exclamations.
+# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
+# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
+#感動詞
+#
+#####
+# symbol: unclassified Symbols.
+記号
+#
+# symbol-misc: A general symbol not in one of the categories below.
+# e.g. [○◎@$〒→+]
+記号-一般
+#
+# symbol-comma: Commas
+# e.g. [,、]
+記号-読点
+#
+# symbol-period: Periods and full stops.
+# e.g. [.．。]
+記号-句点
+#
+# symbol-space: Full-width whitespace.
+記号-空白
+#
+# symbol-open_bracket:
+# e.g. [({‘“『【]
+記号-括弧開
+#
+# symbol-close_bracket:
+# e.g. [)}’”』」】]
+記号-括弧閉
+#
+# symbol-alphabetic:
+#記号-アルファベット
+#
+#####
+# other: unclassified other
+#その他
+#
+# other-interjection: Words that are hard to classify as noun-suffixes or
+# sentence-final particles.
+# e.g. (だ)ァ
+その他-間投
+#
+#####
+# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
+# e.g. あの, うんと, えと
+フィラー
+#
+#####
+# non-verbal: non-verbal sound.
+非言語音
+#
+#####
+# fragment:
+#語断片
+#
+#####
+# unknown: unknown part of speech.
+#未知語
+#
+##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_ar.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ar.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ar.txt
new file mode 100644
index 0000000..046829d
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_ar.txt
@@ -0,0 +1,125 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Cleaned on October 11, 2009 (not normalized, so use before normalization)
+# This means that when modifying this list, you might need to add some
+# redundant entries, for example containing forms with both أ and ا
+من
+ومن
+منها
+منه
+في
+وفي
+فيها
+فيه
+و
+ف
+ثم
+او
+أو
+ب
+بها
+به
+ا
+أ
+اى
+اي
+أي
+أى
+لا
+ولا
+الا
+ألا
+إلا
+لكن
+ما
+وما
+كما
+فما
+عن
+مع
+اذا
+إذا
+ان
+أن
+إن
+انها
+أنها
+إنها
+انه
+أنه
+إنه
+بان
+بأن
+فان
+فأن
+وان
+وأن
+وإن
+التى
+التي
+الذى
+الذي
+الذين
+الى
+الي
+إلى
+إلي
+على
+عليها
+عليه
+اما
+أما
+إما
+ايضا
+أيضا
+كل
+وكل
+لم
+ولم
+لن
+ولن
+هى
+هي
+هو
+وهى
+وهي
+وهو
+فهى
+فهي
+فهو
+انت
+أنت
+لك
+لها
+له
+هذه
+هذا
+تلك
+ذلك
+هناك
+كانت
+كان
+يكون
+تكون
+وكانت
+وكان
+غير
+بعض
+قد
+نحو
+بين
+بينما
+منذ
+ضمن
+حيث
+الان
+الآن
+خلال
+بعد
+قبل
+حتى
+عند
+عندما
+لدى
+جميع
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_bg.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_bg.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_bg.txt
new file mode 100644
index 0000000..1ae4ba2
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_bg.txt
@@ -0,0 +1,193 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+а
+аз
+ако
+ала
+бе
+без
+беше
+би
+бил
+била
+били
+било
+близо
+бъдат
+бъде
+бяха
+в
+вас
+ваш
+ваша
+вероятно
+вече
+взема
+ви
+вие
+винаги
+все
+всеки
+всички
+всичко
+всяка
+във
+въпреки
+върху
+г
+ги
+главно
+го
+д
+да
+дали
+до
+докато
+докога
+дори
+досега
+доста
+е
+едва
+един
+ето
+за
+зад
+заедно
+заради
+засега
+затова
+защо
+защото
+и
+из
+или
+им
+има
+имат
+иска
+й
+каза
+как
+каква
+какво
+както
+какъв
+като
+кога
+когато
+което
+които
+кой
+който
+колко
+която
+къде
+където
+към
+ли
+м
+ме
+между
+мен
+ми
+мнозина
+мога
+могат
+може
+моля
+момента
+му
+н
+на
+над
+назад
+най
+направи
+напред
+например
+нас
+не
+него
+нея
+ни
+ние
+никой
+нито
+но
+някои
+някой
+няма
+обаче
+около
+освен
+особено
+от
+отгоре
+отново
+още
+пак
+по
+повече
+повечето
+под
+поне
+поради
+после
+почти
+прави
+пред
+преди
+през
+при
+пък
+първо
+с
+са
+само
+се
+сега
+си
+скоро
+след
+сме
+според
+сред
+срещу
+сте
+съм
+със
+също
+т
+тази
+така
+такива
+такъв
+там
+твой
+те
+тези
+ти
+тн
+то
+това
+тогава
+този
+той
+толкова
+точно
+трябва
+тук
+тъй
+тя
+тях
+у
+харесва
+ч
+че
+често
+чрез
+ще
+щом
+я
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ca.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ca.txt
new file mode 100644
index 0000000..3da65de
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_ca.txt
@@ -0,0 +1,220 @@
+# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
+a
+abans
+ací
+ah
+així
+això
+al
+als
+aleshores
+algun
+alguna
+algunes
+alguns
+alhora
+allà
+allí
+allò
+altra
+altre
+altres
+amb
+ambdós
+ambdues
+apa
+aquell
+aquella
+aquelles
+aquells
+aquest
+aquesta
+aquestes
+aquests
+aquí
+baix
+cada
+cadascú
+cadascuna
+cadascunes
+cadascuns
+com
+contra
+d'un
+d'una
+d'unes
+d'uns
+dalt
+de
+del
+dels
+des
+després
+dins
+dintre
+donat
+doncs
+durant
+e
+eh
+el
+els
+em
+en
+encara
+ens
+entre
+érem
+eren
+éreu
+es
+és
+esta
+està
+estàvem
+estaven
+estàveu
+esteu
+et
+etc
+ets
+fins
+fora
+gairebé
+ha
+han
+has
+havia
+he
+hem
+heu
+hi
+ho
+i
+igual
+iguals
+ja
+l'hi
+la
+les
+li
+li'n
+llavors
+m'he
+ma
+mal
+malgrat
+mateix
+mateixa
+mateixes
+mateixos
+me
+mentre
+més
+meu
+meus
+meva
+meves
+molt
+molta
+moltes
+molts
+mon
+mons
+n'he
+n'hi
+ne
+ni
+no
+nogensmenys
+només
+nosaltres
+nostra
+nostre
+nostres
+o
+oh
+oi
+on
+pas
+pel
+pels
+per
+però
+perquè
+poc
+poca
+pocs
+poques
+potser
+propi
+qual
+quals
+quan
+quant
+que
+què
+quelcom
+qui
+quin
+quina
+quines
+quins
+s'ha
+s'han
+sa
+semblant
+semblants
+ses
+seu
+seus
+seva
+seva
+seves
+si
+sobre
+sobretot
+sóc
+solament
+sols
+son
+són
+sons
+sota
+sou
+t'ha
+t'han
+t'he
+ta
+tal
+també
+tampoc
+tan
+tant
+tanta
+tantes
+teu
+teus
+teva
+teves
+ton
+tons
+tot
+tota
+totes
+tots
+un
+una
+unes
+uns
+us
+va
+vaig
+vam
+van
+vas
+veu
+vosaltres
+vostra
+vostre
+vostres
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_cz.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_cz.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_cz.txt
new file mode 100644
index 0000000..53c6097
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_cz.txt
@@ -0,0 +1,172 @@
+a
+s
+k
+o
+i
+u
+v
+z
+dnes
+cz
+tímto
+budeš
+budem
+byli
+jseš
+můj
+svým
+ta
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proč
+máte
+tato
+kam
+tohoto
+kdo
+kteří
+mi
+nám
+tom
+tomuto
+mít
+nic
+proto
+kterou
+byla
+toho
+protože
+asi
+ho
+naši
+napište
+re
+což
+tím
+takže
+svých
+její
+svými
+jste
+aj
+tu
+tedy
+teto
+bylo
+kde
+ke
+pravé
+ji
+nad
+nejsou
+či
+pod
+téma
+mezi
+přes
+ty
+pak
+vám
+ani
+když
+však
+neg
+jsem
+tento
+článku
+články
+aby
+jsme
+před
+pta
+jejich
+byl
+ještě
+až
+bez
+také
+pouze
+první
+vaše
+která
+nás
+nový
+tipy
+pokud
+může
+strana
+jeho
+své
+jiné
+zprávy
+nové
+není
+vás
+jen
+podle
+zde
+už
+být
+více
+bude
+již
+než
+který
+by
+které
+co
+nebo
+ten
+tak
+má
+při
+od
+po
+jsou
+jak
+další
+ale
+si
+se
+ve
+to
+jako
+za
+zpět
+ze
+do
+pro
+je
+na
+atd
+atp
+jakmile
+přičemž
+já
+on
+ona
+ono
+oni
+ony
+my
+vy
+jí
+ji
+mě
+mne
+jemu
+tomu
+těm
+těmu
+němu
+němuž
+jehož
+jíž
+jelikož
+jež
+jakož
+načež
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_da.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_da.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_da.txt
new file mode 100644
index 0000000..42e6145
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_da.txt
@@ -0,0 +1,110 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Danish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+
+og | and
+i | in
+jeg | I
+det | that (dem. pronoun)/it (pers. pronoun)
+at | that (in front of a sentence)/to (with infinitive)
+en | a/an
+den | it (pers. pronoun)/that (dem. pronoun)
+til | to/at/for/until/against/by/of/into, more
+er | present tense of "to be"
+som | who, as
+på | on/upon/in/on/at/to/after/of/with/for, on
+de | they
+med | with/by/in, along
+han | he
+af | of/by/from/off/for/in/with/on, off
+for | at/for/to/from/by/of/ago, in front/before, because
+ikke | not
+der | who/which, there/those
+var | past tense of "to be"
+mig | me/myself
+sig | oneself/himself/herself/itself/themselves
+men | but
+et | a/an/one, one (number), someone/somebody/one
+har | present tense of "to have"
+om | round/about/for/in/a, about/around/down, if
+vi | we
+min | my
+havde | past tense of "to have"
+ham | him
+hun | she
+nu | now
+over | over/above/across/by/beyond/past/on/about, over/past
+da | then, when/as/since
+fra | from/off/since, off, since
+du | you
+ud | out
+sin | his/her/its/one's
+dem | them
+os | us/ourselves
+op | up
+man | you/one
+hans | his
+hvor | where
+eller | or
+hvad | what
+skal | must/shall etc.
+selv | myself/youself/herself/ourselves etc., even
+her | here
+alle | all/everyone/everybody etc.
+vil | will (verb)
+blev | past tense of "to stay/to remain/to get/to become"
+kunne | could
+ind | in
+når | when
+være | present tense of "to be"
+dog | however/yet/after all
+noget | something
+ville | would
+jo | you know/you see (adv), yes
+deres | their/theirs
+efter | after/behind/according to/for/by/from, later/afterwards
+ned | down
+skulle | should
+denne | this
+end | than
+dette | this
+mit | my/mine
+også | also
+under | under/beneath/below/during, below/underneath
+have | have
+dig | you
+anden | other
+hende | her
+mine | my
+alt | everything
+meget | much/very, plenty of
+sit | his, her, its, one's
+sine | his, her, its, one's
+vor | our
+mod | against
+disse | these
+hvis | if
+din | your/yours
+nogle | some
+hos | by/at
+blive | be/become
+mange | many
+ad | by/through
+bliver | present tense of "to be/to become"
+hendes | her/hers
+været | be
+thi | for (conj)
+jer | you
+sådan | such, like this/like that
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_de.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_de.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_de.txt
new file mode 100644
index 0000000..86525e7
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_de.txt
@@ -0,0 +1,294 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A German stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | The number of forms in this list is reduced significantly by passing it
+ | through the German stemmer.
+
+
+aber | but
+
+alle | all
+allem
+allen
+aller
+alles
+
+als | than, as
+also | so
+am | an + dem
+an | at
+
+ander | other
+andere
+anderem
+anderen
+anderer
+anderes
+anderm
+andern
+anderr
+anders
+
+auch | also
+auf | on
+aus | out of
+bei | by
+bin | am
+bis | until
+bist | art
+da | there
+damit | with it
+dann | then
+
+der | the
+den
+des
+dem
+die
+das
+
+daß | that
+
+derselbe | the same
+derselben
+denselben
+desselben
+demselben
+dieselbe
+dieselben
+dasselbe
+
+dazu | to that
+
+dein | thy
+deine
+deinem
+deinen
+deiner
+deines
+
+denn | because
+
+derer | of those
+dessen | of him
+
+dich | thee
+dir | to thee
+du | thou
+
+dies | this
+diese
+diesem
+diesen
+dieser
+dieses
+
+
+doch | (several meanings)
+dort | (over) there
+
+
+durch | through
+
+ein | a
+eine
+einem
+einen
+einer
+eines
+
+einig | some
+einige
+einigem
+einigen
+einiger
+einiges
+
+einmal | once
+
+er | he
+ihn | him
+ihm | to him
+
+es | it
+etwas | something
+
+euer | your
+eure
+eurem
+euren
+eurer
+eures
+
+für | for
+gegen | towards
+gewesen | p.p. of sein
+hab | have
+habe | have
+haben | have
+hat | has
+hatte | had
+hatten | had
+hier | here
+hin | there
+hinter | behind
+
+ich | I
+mich | me
+mir | to me
+
+
+ihr | you, to her
+ihre
+ihrem
+ihren
+ihrer
+ihres
+euch | to you
+
+im | in + dem
+in | in
+indem | while
+ins | in + das
+ist | is
+
+jede | each, every
+jedem
+jeden
+jeder
+jedes
+
+jene | that
+jenem
+jenen
+jener
+jenes
+
+jetzt | now
+kann | can
+
+kein | no
+keine
+keinem
+keinen
+keiner
+keines
+
+können | can
+könnte | could
+machen | do
+man | one
+
+manche | some, many a
+manchem
+manchen
+mancher
+manches
+
+mein | my
+meine
+meinem
+meinen
+meiner
+meines
+
+mit | with
+muss | must
+musste | had to
+nach | to(wards)
+nicht | not
+nichts | nothing
+noch | still, yet
+nun | now
+nur | only
+ob | whether
+oder | or
+ohne | without
+sehr | very
+
+sein | his
+seine
+seinem
+seinen
+seiner
+seines
+
+selbst | self
+sich | herself
+
+sie | they, she
+ihnen | to them
+
+sind | are
+so | so
+
+solche | such
+solchem
+solchen
+solcher
+solches
+
+soll | shall
+sollte | should
+sondern | but
+sonst | else
+über | over
+um | about, around
+und | and
+
+uns | us
+unse
+unsem
+unsen
+unser
+unses
+
+unter | under
+viel | much
+vom | von + dem
+von | from
+vor | before
+während | while
+war | was
+waren | were
+warst | wast
+was | what
+weg | away, off
+weil | because
+weiter | further
+
+welche | which
+welchem
+welchen
+welcher
+welches
+
+wenn | when
+werde | will
+werden | will
+wie | how
+wieder | again
+will | want
+wir | we
+wird | will
+wirst | willst
+wo | where
+wollen | want
+wollte | wanted
+würde | would
+würden | would
+zu | to
+zum | zu + dem
+zur | zu + der
+zwar | indeed
+zwischen | between
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_el.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_el.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_el.txt
new file mode 100644
index 0000000..232681f
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_el.txt
@@ -0,0 +1,78 @@
+# Lucene Greek Stopwords list
+# Note: by default this file is used after GreekLowerCaseFilter,
+# so when modifying this file use 'σ' instead of 'ς'
+ο
+η
+το
+οι
+τα
+του
+τησ
+των
+τον
+την
+και
+κι
+κ
+ειμαι
+εισαι
+ειναι
+ειμαστε
+ειστε
+στο
+στον
+στη
+στην
+μα
+αλλα
+απο
+για
+προσ
+με
+σε
+ωσ
+παρα
+αντι
+κατα
+μετα
+θα
+να
+δε
+δεν
+μη
+μην
+επι
+ενω
+εαν
+αν
+τοτε
+που
+πωσ
+ποιοσ
+ποια
+ποιο
+ποιοι
+ποιεσ
+ποιων
+ποιουσ
+αυτοσ
+αυτη
+αυτο
+αυτοι
+αυτων
+αυτουσ
+αυτεσ
+αυτα
+εκεινοσ
+εκεινη
+εκεινο
+εκεινοι
+εκεινεσ
+εκεινα
+εκεινων
+εκεινουσ
+οπωσ
+ομωσ
+ισωσ
+οσο
+οτι
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_en.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_en.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_en.txt
new file mode 100644
index 0000000..2c164c0
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_en.txt
@@ -0,0 +1,54 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+# Standard english stop words taken from Lucene's StopAnalyzer
+a
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+of
+on
+or
+such
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_es.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_es.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_es.txt
new file mode 100644
index 0000000..487d78c
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_es.txt
@@ -0,0 +1,356 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Spanish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | from, of
+la | the, her
+que | who, that
+el | the
+en | in
+y | and
+a | to
+los | the, them
+del | de + el
+se | himself, from him etc
+las | the, them
+por | for, by, etc
+un | a
+para | for
+con | with
+no | no
+una | a
+su | his, her
+al | a + el
+ | es from SER
+lo | him
+como | how
+más | more
+pero | pero
+sus | su plural
+le | to him, her
+ya | already
+o | or
+ | fue from SER
+este | this
+ | ha from HABER
+sí | himself etc
+porque | because
+esta | this
+ | son from SER
+entre | between
+ | está from ESTAR
+cuando | when
+muy | very
+sin | without
+sobre | on
+ | ser from SER
+ | tiene from TENER
+también | also
+me | me
+hasta | until
+hay | there is/are
+donde | where
+ | han from HABER
+quien | whom, that
+ | están from ESTAR
+ | estado from ESTAR
+desde | from
+todo | all
+nos | us
+durante | during
+ | estados from ESTAR
+todos | all
+uno | a
+les | to them
+ni | nor
+contra | against
+otros | other
+ | fueron from SER
+ese | that
+eso | that
+ | había from HABER
+ante | before
+ellos | they
+e | and (variant of y)
+esto | this
+mí | me
+antes | before
+algunos | some
+qué | what?
+unos | a
+yo | I
+otro | other
+otras | other
+otra | other
+él | he
+tanto | so much, many
+esa | that
+estos | these
+mucho | much, many
+quienes | who
+nada | nothing
+muchos | many
+cual | who
+ | sea from SER
+poco | few
+ella | she
+estar | to be
+ | haber from HABER
+estas | these
+ | estaba from ESTAR
+ | estamos from ESTAR
+algunas | some
+algo | something
+nosotros | we
+
+ | other forms
+
+mi | me
+mis | mi plural
+tú | thou
+te | thee
+ti | thee
+tu | thy
+tus | tu plural
+ellas | they
+nosotras | we
+vosotros | you
+vosotras | you
+os | you
+mío | mine
+mía |
+míos |
+mías |
+tuyo | thine
+tuya |
+tuyos |
+tuyas |
+suyo | his, hers, theirs
+suya |
+suyos |
+suyas |
+nuestro | ours
+nuestra |
+nuestros |
+nuestras |
+vuestro | yours
+vuestra |
+vuestros |
+vuestras |
+esos | those
+esas | those
+
+ | forms of estar, to be (not including the infinitive):
+estoy
+estás
+está
+estamos
+estáis
+están
+esté
+estés
+estemos
+estéis
+estén
+estaré
+estarás
+estará
+estaremos
+estaréis
+estarán
+estaría
+estarías
+estaríamos
+estaríais
+estarían
+estaba
+estabas
+estábamos
+estabais
+estaban
+estuve
+estuviste
+estuvo
+estuvimos
+estuvisteis
+estuvieron
+estuviera
+estuvieras
+estuviéramos
+estuvierais
+estuvieran
+estuviese
+estuvieses
+estuviésemos
+estuvieseis
+estuviesen
+estando
+estado
+estada
+estados
+estadas
+estad
+
+ | forms of haber, to have (not including the infinitive):
+he
+has
+ha
+hemos
+habéis
+han
+haya
+hayas
+hayamos
+hayáis
+hayan
+habré
+habrás
+habrá
+habremos
+habréis
+habrán
+habría
+habrías
+habríamos
+habríais
+habrían
+había
+habías
+habíamos
+habíais
+habían
+hube
+hubiste
+hubo
+hubimos
+hubisteis
+hubieron
+hubiera
+hubieras
+hubiéramos
+hubierais
+hubieran
+hubiese
+hubieses
+hubiésemos
+hubieseis
+hubiesen
+habiendo
+habido
+habida
+habidos
+habidas
+
+ | forms of ser, to be (not including the infinitive):
+soy
+eres
+es
+somos
+sois
+son
+sea
+seas
+seamos
+seáis
+sean
+seré
+serás
+será
+seremos
+seréis
+serán
+sería
+serías
+seríamos
+seríais
+serían
+era
+eras
+éramos
+erais
+eran
+fui
+fuiste
+fue
+fuimos
+fuisteis
+fueron
+fuera
+fueras
+fuéramos
+fuerais
+fueran
+fuese
+fueses
+fuésemos
+fueseis
+fuesen
+siendo
+sido
+ | sed also means 'thirst'
+
+ | forms of tener, to have (not including the infinitive):
+tengo
+tienes
+tiene
+tenemos
+tenéis
+tienen
+tenga
+tengas
+tengamos
+tengáis
+tengan
+tendré
+tendrás
+tendrá
+tendremos
+tendréis
+tendrán
+tendría
+tendrías
+tendríamos
+tendríais
+tendrían
+tenía
+tenías
+teníamos
+teníais
+tenían
+tuve
+tuviste
+tuvo
+tuvimos
+tuvisteis
+tuvieron
+tuviera
+tuvieras
+tuviéramos
+tuvierais
+tuvieran
+tuviese
+tuvieses
+tuviésemos
+tuvieseis
+tuviesen
+teniendo
+tenido
+tenida
+tenidos
+tenidas
+tened
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_eu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_eu.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_eu.txt
new file mode 100644
index 0000000..25f1db9
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_eu.txt
@@ -0,0 +1,99 @@
+# example set of basque stopwords
+al
+anitz
+arabera
+asko
+baina
+bat
+batean
+batek
+bati
+batzuei
+batzuek
+batzuetan
+batzuk
+bera
+beraiek
+berau
+berauek
+bere
+berori
+beroriek
+beste
+bezala
+da
+dago
+dira
+ditu
+du
+dute
+edo
+egin
+ere
+eta
+eurak
+ez
+gainera
+gu
+gutxi
+guzti
+haiei
+haiek
+haietan
+hainbeste
+hala
+han
+handik
+hango
+hara
+hari
+hark
+hartan
+hau
+hauei
+hauek
+hauetan
+hemen
+hemendik
+hemengo
+hi
+hona
+honek
+honela
+honetan
+honi
+hor
+hori
+horiei
+horiek
+horietan
+horko
+horra
+horrek
+horrela
+horretan
+horri
+hortik
+hura
+izan
+ni
+noiz
+nola
+non
+nondik
+nongo
+nor
+nora
+ze
+zein
+zen
+zenbait
+zenbat
+zer
+zergatik
+ziren
+zituen
+zu
+zuek
+zuen
+zuten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_fa.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_fa.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_fa.txt
new file mode 100644
index 0000000..723641c
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_fa.txt
@@ -0,0 +1,313 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Note: by default this file is used after normalization, so when adding entries
+# to this file, use the arabic 'ي' instead of 'ی'
+انان
+نداشته
+سراسر
+خياه
+ايشان
+وي
+تاكنون
+بيشتري
+دوم
+پس
+ناشي
+وگو
+يا
+داشتند
+سپس
+هنگام
+هرگز
+پنج
+نشان
+امسال
+ديگر
+گروهي
+شدند
+چطور
+ده
+و
+دو
+نخستين
+ولي
+چرا
+چه
+وسط
+ه
+كدام
+قابل
+يك
+رفت
+هفت
+همچنين
+در
+هزار
+بله
+بلي
+شايد
+اما
+شناسي
+گرفته
+دهد
+داشته
+دانست
+داشتن
+خواهيم
+ميليارد
+وقتيكه
+امد
+خواهد
+جز
+اورده
+شده
+بلكه
+خدمات
+شدن
+برخي
+نبود
+بسياري
+جلوگيري
+حق
+كردند
+نوعي
+بعري
+نكرده
+نظير
+نبايد
+بوده
+بودن
+داد
+اورد
+هست
+جايي
+شود
+دنبال
+داده
+بايد
+سابق
+هيچ
+همان
+انجا
+كمتر
+كجاست
+گردد
+كسي
+تر
+مردم
+تان
+دادن
+بودند
+سري
+جدا
+ندارند
+مگر
+يكديگر
+دارد
+دهند
+بنابراين
+هنگامي
+سمت
+جا
+انچه
+خود
+دادند
+زياد
+دارند
+اثر
+بدون
+بهترين
+بيشتر
+البته
+به
+براساس
+بيرون
+كرد
+بعضي
+گرفت
+توي
+اي
+ميليون
+او
+جريان
+تول
+بر
+مانند
+برابر
+باشيم
+مدتي
+گويند
+اكنون
+تا
+تنها
+جديد
+چند
+بي
+نشده
+كردن
+كردم
+گويد
+كرده
+كنيم
+نمي
+نزد
+روي
+قصد
+فقط
+بالاي
+ديگران
+اين
+ديروز
+توسط
+سوم
+ايم
+دانند
+سوي
+استفاده
+شما
+كنار
+داريم
+ساخته
+طور
+امده
+رفته
+نخست
+بيست
+نزديك
+طي
+كنيد
+از
+انها
+تمامي
+داشت
+يكي
+طريق
+اش
+چيست
+روب
+نمايد
+گفت
+چندين
+چيزي
+تواند
+ام
+ايا
+با
+ان
+ايد
+ترين
+اينكه
+ديگري
+راه
+هايي
+بروز
+همچنان
+پاعين
+كس
+حدود
+مختلف
+مقابل
+چيز
+گيرد
+ندارد
+ضد
+همچون
+سازي
+شان
+مورد
+باره
+مرسي
+خويش
+برخوردار
+چون
+خارج
+شش
+هنوز
+تحت
+ضمن
+هستيم
+گفته
+فكر
+بسيار
+پيش
+براي
+روزهاي
+انكه
+نخواهد
+بالا
+كل
+وقتي
+كي
+چنين
+كه
+گيري
+نيست
+است
+كجا
+كند
+نيز
+يابد
+بندي
+حتي
+توانند
+عقب
+خواست
+كنند
+بين
+تمام
+همه
+ما
+باشند
+مثل
+شد
+اري
+باشد
+اره
+طبق
+بعد
+اگر
+صورت
+غير
+جاي
+بيش
+ريزي
+اند
+زيرا
+چگونه
+بار
+لطفا
+مي
+درباره
+من
+ديده
+همين
+گذاري
+برداري
+علت
+گذاشته
+هم
+فوق
+نه
+ها
+شوند
+اباد
+همواره
+هر
+اول
+خواهند
+چهار
+نام
+امروز
+مان
+هاي
+قبل
+كنم
+سعي
+تازه
+را
+هستند
+زير
+جلوي
+عنوان
+بود
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_fi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_fi.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_fi.txt
new file mode 100644
index 0000000..4372c9a
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_fi.txt
@@ -0,0 +1,97 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+| forms of BE
+
+olla
+olen
+olet
+on
+olemme
+olette
+ovat
+ole | negative form
+
+oli
+olisi
+olisit
+olisin
+olisimme
+olisitte
+olisivat
+olit
+olin
+olimme
+olitte
+olivat
+ollut
+olleet
+
+en | negation
+et
+ei
+emme
+ette
+eivät
+
+|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
+minä minun minut minua minussa minusta minuun minulla minulta minulle | I
+sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
+hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she
+me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we
+te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you
+he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they
+
+tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this
+tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
+se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it
+nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these
+nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
+ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they
+
+kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
+ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl)
+mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what
+mitkä | (pl)
+
+joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which
+jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl)
+
+| conjunctions
+
+että | that
+ja | and
+jos | if
+koska | because
+kuin | than
+mutta | but
+niin | so
+sekä | and
+sillä | for
+tai | or
+vaan | but
+vai | or
+vaikka | although
+
+
+| prepositions
+
+kanssa | with
+mukaan | according to
+noin | about
+poikki | across
+yli | over, across
+
+| other
+
+kun | when
+niin | so
+nyt | now
+itse | self
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_fr.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_fr.txt
new file mode 100644
index 0000000..749abae
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_fr.txt
@@ -0,0 +1,186 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A French stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+au | a + le
+aux | a + les
+avec | with
+ce | this
+ces | these
+dans | with
+de | of
+des | de + les
+du | de + le
+elle | she
+en | `of them' etc
+et | and
+eux | them
+il | he
+je | I
+la | the
+le | the
+leur | their
+lui | him
+ma | my (fem)
+mais | but
+me | me
+même | same; as in moi-même (myself) etc
+mes | me (pl)
+moi | me
+mon | my (masc)
+ne | not
+nos | our (pl)
+notre | our
+nous | we
+on | one
+ou | where
+par | by
+pas | not
+pour | for
+qu | que before vowel
+que | that
+qui | who
+sa | his, her (fem)
+se | oneself
+ses | his (pl)
+son | his, her (masc)
+sur | on
+ta | thy (fem)
+te | thee
+tes | thy (pl)
+toi | thee
+ton | thy (masc)
+tu | thou
+un | a
+une | a
+vos | your (pl)
+votre | your
+vous | you
+
+ | single letter forms
+
+c | c'
+d | d'
+j | j'
+l | l'
+à | to, at
+m | m'
+n | n'
+s | s'
+t | t'
+y | there
+
+ | forms of être (not including the infinitive):
+été
+étée
+étées
+étés
+étant
+suis
+es
+est
+sommes
+êtes
+sont
+serai
+seras
+sera
+serons
+serez
+seront
+serais
+serait
+serions
+seriez
+seraient
+étais
+était
+étions
+étiez
+étaient
+fus
+fut
+fûmes
+fûtes
+furent
+sois
+soit
+soyons
+soyez
+soient
+fusse
+fusses
+fût
+fussions
+fussiez
+fussent
+
+ | forms of avoir (not including the infinitive):
+ayant
+eu
+eue
+eues
+eus
+ai
+as
+avons
+avez
+ont
+aurai
+auras
+aura
+aurons
+aurez
+auront
+aurais
+aurait
+aurions
+auriez
+auraient
+avais
+avait
+avions
+aviez
+avaient
+eut
+eûmes
+eûtes
+eurent
+aie
+aies
+ait
+ayons
+ayez
+aient
+eusse
+eusses
+eût
+eussions
+eussiez
+eussent
+
+ | Later additions (from Jean-Christophe Deschamps)
+ceci | this
+cela | that
+celà | that
+cet | this
+cette | this
+ici | here
+ils | they
+les | the (pl)
+leurs | their (pl)
+quel | which
+quels | which
+quelle | which
+quelles | which
+sans | without
+soi | oneself
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ga.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ga.txt
new file mode 100644
index 0000000..9ff88d7
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_ga.txt
@@ -0,0 +1,110 @@
+
+a
+ach
+ag
+agus
+an
+aon
+ar
+arna
+as
+b'
+ba
+beirt
+bhúr
+caoga
+ceathair
+ceathrar
+chomh
+chtó
+chuig
+chun
+cois
+céad
+cúig
+cúigear
+d'
+daichead
+dar
+de
+deich
+deichniúr
+den
+dhá
+do
+don
+dtí
+dá
+dár
+dó
+faoi
+faoin
+faoina
+faoinár
+fara
+fiche
+gach
+gan
+go
+gur
+haon
+hocht
+i
+iad
+idir
+in
+ina
+ins
+inár
+is
+le
+leis
+lena
+lenár
+m'
+mar
+mo
+mé
+na
+nach
+naoi
+naonúr
+ná
+ní
+níor
+nó
+nócha
+ocht
+ochtar
+os
+roimh
+sa
+seacht
+seachtar
+seachtó
+seasca
+seisear
+siad
+sibh
+sinn
+sna
+sé
+sí
+tar
+thar
+thú
+triúr
+trí
+trína
+trínár
+tríocha
+tú
+um
+ár
+é
+éis
+í
+ó
+ón
+óna
+ónár
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_gl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_gl.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_gl.txt
new file mode 100644
index 0000000..d8760b1
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_gl.txt
@@ -0,0 +1,161 @@
+# galican stopwords
+a
+aínda
+alí
+aquel
+aquela
+aquelas
+aqueles
+aquilo
+aquí
+ao
+aos
+as
+así
+á
+ben
+cando
+che
+co
+coa
+comigo
+con
+connosco
+contigo
+convosco
+coas
+cos
+cun
+cuns
+cunha
+cunhas
+da
+dalgunha
+dalgunhas
+dalgún
+dalgúns
+das
+de
+del
+dela
+delas
+deles
+desde
+deste
+do
+dos
+dun
+duns
+dunha
+dunhas
+e
+el
+ela
+elas
+eles
+en
+era
+eran
+esa
+esas
+ese
+eses
+esta
+estar
+estaba
+está
+están
+este
+estes
+estiven
+estou
+eu
+é
+facer
+foi
+foron
+fun
+había
+hai
+iso
+isto
+la
+las
+lle
+lles
+lo
+los
+mais
+me
+meu
+meus
+min
+miña
+miñas
+moi
+na
+nas
+neste
+nin
+no
+non
+nos
+nosa
+nosas
+noso
+nosos
+nós
+nun
+nunha
+nuns
+nunhas
+o
+os
+ou
+ó
+ós
+para
+pero
+pode
+pois
+pola
+polas
+polo
+polos
+por
+que
+se
+senón
+ser
+seu
+seus
+sexa
+sido
+sobre
+súa
+súas
+tamén
+tan
+te
+ten
+teñen
+teño
+ter
+teu
+teus
+ti
+tido
+tiña
+tiven
+túa
+túas
+un
+unha
+unhas
+uns
+vos
+vosa
+vosas
+voso
+vosos
+vós
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_hi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_hi.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_hi.txt
new file mode 100644
index 0000000..86286bb
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_hi.txt
@@ -0,0 +1,235 @@
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# Note: by default this file also contains forms normalized by HindiNormalizer
+# for spelling variation (see section below), such that it can be used whether or
+# not you enable that feature. When adding additional entries to this list,
+# please add the normalized form as well.
+अंदर
+अत
+अपना
+अपनी
+अपने
+अभी
+आदि
+आप
+इत्यादि
+इन
+इनका
+इन्हीं
+इन्हें
+इन्हों
+इस
+इसका
+इसकी
+इसके
+इसमें
+इसी
+इसे
+उन
+उनका
+उनकी
+उनके
+उनको
+उन्हीं
+उन्हें
+उन्हों
+उस
+उसके
+उसी
+उसे
+एक
+एवं
+एस
+ऐसे
+और
+कई
+कर
+करता
+करते
+करना
+करने
+करें
+कहते
+कहा
+का
+काफ़ी
+कि
+कितना
+किन्हें
+किन्हों
+किया
+किर
+किस
+किसी
+किसे
+की
+कुछ
+कुल
+के
+को
+कोई
+कौन
+कौनसा
+गया
+घर
+जब
+जहाँ
+जा
+जितना
+जिन
+जिन्हें
+जिन्हों
+जिस
+जिसे
+जीधर
+जैसा
+जैसे
+जो
+तक
+तब
+तरह
+तिन
+तिन्हें
+तिन्हों
+तिस
+तिसे
+तो
+था
+थी
+थे
+दबारा
+दिया
+दुसरा
+दूसरे
+दो
+द्वारा
+न
+नहीं
+ना
+निहायत
+नीचे
+ने
+पर
+पर
+पहले
+पूरा
+पे
+फिर
+बनी
+बही
+बहुत
+बाद
+बाला
+बिलकुल
+भी
+भीतर
+मगर
+मानो
+मे
+में
+यदि
+यह
+यहाँ
+यही
+या
+यिह
+ये
+रखें
+रहा
+रहे
+ऱ्वासा
+लिए
+लिये
+लेकिन
+व
+वर्ग
+वह
+वह
+वहाँ
+वहीं
+वाले
+वुह
+वे
+वग़ैरह
+संग
+सकता
+सकते
+सबसे
+सभी
+साथ
+साबुत
+साभ
+सारा
+से
+सो
+ही
+हुआ
+हुई
+हुए
+है
+हैं
+हो
+होता
+होती
+होते
+होना
+होने
+# additional normalized forms of the above
+अपनि
+जेसे
+होति
+सभि
+तिंहों
+इंहों
+दवारा
+इसि
+किंहें
+थि
+उंहों
+ओर
+जिंहें
+वहिं
+अभि
+बनि
+हि
+उंहिं
+उंहें
+हें
+वगेरह
+एसे
+रवासा
+कोन
+निचे
+काफि
+उसि
+पुरा
+भितर
+हे
+बहि
+वहां
+कोइ
+यहां
+जिंहों
+तिंहें
+किसि
+कइ
+यहि
+इंहिं
+जिधर
+इंहें
+अदि
+इतयादि
+हुइ
+कोनसा
+इसकि
+दुसरे
+जहां
+अप
+किंहों
+उनकि
+भि
+वरग
+हुअ
+जेसा
+नहिं
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_hu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_hu.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_hu.txt
new file mode 100644
index 0000000..37526da
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_hu.txt
@@ -0,0 +1,211 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+| Hungarian stop word list
+| prepared by Anna Tordai
+
+a
+ahogy
+ahol
+aki
+akik
+akkor
+alatt
+által
+általában
+amely
+amelyek
+amelyekben
+amelyeket
+amelyet
+amelynek
+ami
+amit
+amolyan
+amíg
+amikor
+át
+abban
+ahhoz
+annak
+arra
+arról
+az
+azok
+azon
+azt
+azzal
+azért
+aztán
+azután
+azonban
+bár
+be
+belül
+benne
+cikk
+cikkek
+cikkeket
+csak
+de
+e
+eddig
+egész
+egy
+egyes
+egyetlen
+egyéb
+egyik
+egyre
+ekkor
+el
+elég
+ellen
+elő
+először
+előtt
+első
+én
+éppen
+ebben
+ehhez
+emilyen
+ennek
+erre
+ez
+ezt
+ezek
+ezen
+ezzel
+ezért
+és
+fel
+felé
+hanem
+hiszen
+hogy
+hogyan
+igen
+így
+illetve
+ill.
+ill
+ilyen
+ilyenkor
+ison
+ismét
+itt
+jó
+jól
+jobban
+kell
+kellett
+keresztül
+keressünk
+ki
+kívül
+között
+közül
+legalább
+lehet
+lehetett
+legyen
+lenne
+lenni
+lesz
+lett
+maga
+magát
+majd
+majd
+már
+más
+másik
+meg
+még
+mellett
+mert
+mely
+melyek
+mi
+mit
+míg
+miért
+milyen
+mikor
+minden
+mindent
+mindenki
+mindig
+mint
+mintha
+mivel
+most
+nagy
+nagyobb
+nagyon
+ne
+néha
+nekem
+neki
+nem
+néhány
+nélkül
+nincs
+olyan
+ott
+össze
+ő
+ők
+őket
+pedig
+persze
+rá
+s
+saját
+sem
+semmi
+sok
+sokat
+sokkal
+számára
+szemben
+szerint
+szinte
+talán
+tehát
+teljes
+tovább
+továbbá
+több
+úgy
+ugyanis
+új
+újabb
+újra
+után
+utána
+utolsó
+vagy
+vagyis
+valaki
+valami
+valamint
+való
+vagyok
+van
+vannak
+volt
+voltam
+voltak
+voltunk
+vissza
+vele
+viszont
+volna
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_hy.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_hy.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_hy.txt
new file mode 100644
index 0000000..60c1c50
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_hy.txt
@@ -0,0 +1,46 @@
+# example set of Armenian stopwords.
+այդ
+այլ
+այն
+այս
+դու
+դուք
+եմ
+են
+ենք
+ես
+եք
+է
+էի
+էին
+էինք
+էիր
+էիք
+էր
+ըստ
+թ
+ի
+ին
+իսկ
+իր
+կամ
+համար
+հետ
+հետո
+մենք
+մեջ
+մի
+ն
+նա
+նաև
+նրա
+նրանք
+որ
+որը
+որոնք
+որպես
+ու
+ում
+պիտի
+վրա
+և
[33/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Changes
and upgrade notes
Posted by sh...@apache.org.
SOLR-10574: Changes and upgrade notes
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/0ec9d64d
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/0ec9d64d
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/0ec9d64d
Branch: refs/heads/feature/autoscaling
Commit: 0ec9d64d816ec907235cddef972d7c45fc78f332
Parents: d1c807d
Author: Ishan Chattopadhyaya <is...@apache.org>
Authored: Tue Jun 20 11:14:28 2017 +0000
Committer: Ishan Chattopadhyaya <is...@apache.org>
Committed: Tue Jun 20 11:14:28 2017 +0000
----------------------------------------------------------------------
solr/CHANGES.txt | 8 ++++++++
1 file changed, 8 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/0ec9d64d/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index cc67391..5c865a1 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -97,6 +97,11 @@ Upgrading from Solr 6.x
* SOLR-9565: The name of TemplateUpdateRequestProcessorFactory' is changed to 'template' from 'Template' and the
name of 'AtomicUpdateProcessorFactory' is changed to 'atomic' from 'Atomic'
+* SOLR-10574: basic_configs and data_driven_schema_configs have now been merged into _default. It has data driven nature
+ enabled by default, and can be turned off (after creating a collection) with:
+ curl http://host:8983/solr/mycollection/config -d '{"set-user-property": {"update.autoCreateFields":"false"}}'
+ Please see SOLR-10574 for details.
+
New Features
----------------------
* SOLR-9857, SOLR-9858: Collect aggregated metrics from nodes and shard leaders in overseer. (ab)
@@ -151,6 +156,9 @@ New Features
* SOLR-10406: v2 API error messages list the URL request path as /solr/____v2/... when the original path was /v2/... (Cao Manh Dat, noble)
+* SOLR-10574: New _default config set replacing basic_configs and data_driven_schema_configs.
+ (Ishan Chattopadhyaya, noble, shalin, hossman, David Smiley, Jan Hoydahl, Alexandre Rafalovich)
+
Bug Fixes
----------------------
* SOLR-9262: Connection and read timeouts are being ignored by UpdateShardHandler after SOLR-4509.
[27/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt
deleted file mode 100644
index 5527140..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt
+++ /dev/null
@@ -1,243 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | a russian stop word list. comments begin with vertical bar. each stop
- | word is at the start of a line.
-
- | this is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
- | letter `ё' is translated to `е'.
-
-и | and
-в | in/into
-во | alternative form
-не | not
-что | what/that
-он | he
-на | on/onto
-я | i
-с | from
-со | alternative form
-как | how
-а | milder form of `no' (but)
-то | conjunction and form of `that'
-все | all
-она | she
-так | so, thus
-его | him
-но | but
-да | yes/and
-ты | thou
-к | towards, by
-у | around, chez
-же | intensifier particle
-вы | you
-за | beyond, behind
-бы | conditional/subj. particle
-по | up to, along
-только | only
-ее | her
-мне | to me
-было | it was
-вот | here is/are, particle
-от | away from
-меня | me
-еще | still, yet, more
-нет | no, there isnt/arent
-о | about
-из | out of
-ему | to him
-теперь | now
-когда | when
-даже | even
-ну | so, well
-вдруг | suddenly
-ли | interrogative particle
-если | if
-уже | already, but homonym of `narrower'
-или | or
-ни | neither
-быть | to be
-был | he was
-него | prepositional form of его
-до | up to
-вас | you accusative
-нибудь | indef. suffix preceded by hyphen
-опять | again
-уж | already, but homonym of `adder'
-вам | to you
-сказал | he said
-ведь | particle `after all'
-там | there
-потом | then
-себя | oneself
-ничего | nothing
-ей | to her
-может | usually with `быть' as `maybe'
-они | they
-тут | here
-где | where
-есть | there is/are
-надо | got to, must
-ней | prepositional form of ей
-для | for
-мы | we
-тебя | thee
-их | them, their
-чем | than
-была | she was
-сам | self
-чтоб | in order to
-без | without
-будто | as if
-человек | man, person, one
-чего | genitive form of `what'
-раз | once
-тоже | also
-себе | to oneself
-под | beneath
-жизнь | life
-будет | will be
-ж | short form of intensifer particle `же'
-тогда | then
-кто | who
-этот | this
-говорил | was saying
-того | genitive form of `that'
-потому | for that reason
-этого | genitive form of `this'
-какой | which
-совсем | altogether
-ним | prepositional form of `его', `они'
-здесь | here
-этом | prepositional form of `этот'
-один | one
-почти | almost
-мой | my
-тем | instrumental/dative plural of `тот', `то'
-чтобы | full form of `in order that'
-нее | her (acc.)
-кажется | it seems
-сейчас | now
-были | they were
-куда | where to
-зачем | why
-сказать | to say
-всех | all (acc., gen. preposn. plural)
-никогда | never
-сегодня | today
-можно | possible, one can
-при | by
-наконец | finally
-два | two
-об | alternative form of `о', about
-другой | another
-хоть | even
-после | after
-над | above
-больше | more
-тот | that one (masc.)
-через | across, in
-эти | these
-нас | us
-про | about
-всего | in all, only, of all
-них | prepositional form of `они' (they)
-какая | which, feminine
-много | lots
-разве | interrogative particle
-сказала | she said
-три | three
-эту | this, acc. fem. sing.
-моя | my, feminine
-впрочем | moreover, besides
-хорошо | good
-свою | ones own, acc. fem. sing.
-этой | oblique form of `эта', fem. `this'
-перед | in front of
-иногда | sometimes
-лучше | better
-чуть | a little
-том | preposn. form of `that one'
-нельзя | one must not
-такой | such a one
-им | to them
-более | more
-всегда | always
-конечно | of course
-всю | acc. fem. sing of `all'
-между | between
-
-
- | b: some paradigms
- |
- | personal pronouns
- |
- | я меня мне мной [мною]
- | ты тебя тебе тобой [тобою]
- | он его ему им [него, нему, ним]
- | она ее эи ею [нее, нэи, нею]
- | оно его ему им [него, нему, ним]
- |
- | мы нас нам нами
- | вы вас вам вами
- | они их им ими [них, ним, ними]
- |
- | себя себе собой [собою]
- |
- | demonstrative pronouns: этот (this), тот (that)
- |
- | этот эта это эти
- | этого эты это эти
- | этого этой этого этих
- | этому этой этому этим
- | этим этой этим [этою] этими
- | этом этой этом этих
- |
- | тот та то те
- | того ту то те
- | того той того тех
- | тому той тому тем
- | тем той тем [тою] теми
- | том той том тех
- |
- | determinative pronouns
- |
- | (a) весь (all)
- |
- | весь вся все все
- | всего всю все все
- | всего всей всего всех
- | всему всей всему всем
- | всем всей всем [всею] всеми
- | всем всей всем всех
- |
- | (b) сам (himself etc)
- |
- | сам сама само сами
- | самого саму само самих
- | самого самой самого самих
- | самому самой самому самим
- | самим самой самим [самою] самими
- | самом самой самом самих
- |
- | stems of verbs `to be', `to have', `to do' and modal
- |
- | быть бы буд быв есть суть
- | име
- | дел
- | мог мож мочь
- | уме
- | хоч хот
- | долж
- | можн
- | нужн
- | нельзя
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt
deleted file mode 100644
index 096f87f..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt
+++ /dev/null
@@ -1,133 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Swedish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
- | Swedish stop words occasionally exhibit homonym clashes. For example
- | så = so, but also seed. These are indicated clearly below.
-
-och | and
-det | it, this/that
-att | to (with infinitive)
-i | in, at
-en | a
-jag | I
-hon | she
-som | who, that
-han | he
-på | on
-den | it, this/that
-med | with
-var | where, each
-sig | him(self) etc
-för | for
-så | so (also: seed)
-till | to
-är | is
-men | but
-ett | a
-om | if; around, about
-hade | had
-de | they, these/those
-av | of
-icke | not, no
-mig | me
-du | you
-henne | her
-då | then, when
-sin | his
-nu | now
-har | have
-inte | inte någon = no one
-hans | his
-honom | him
-skulle | 'sake'
-hennes | her
-där | there
-min | my
-man | one (pronoun)
-ej | nor
-vid | at, by, on (also: vast)
-kunde | could
-något | some etc
-från | from, off
-ut | out
-när | when
-efter | after, behind
-upp | up
-vi | we
-dem | them
-vara | be
-vad | what
-över | over
-än | than
-dig | you
-kan | can
-sina | his
-här | here
-ha | have
-mot | towards
-alla | all
-under | under (also: wonder)
-någon | some etc
-eller | or (else)
-allt | all
-mycket | much
-sedan | since
-ju | why
-denna | this/that
-själv | myself, yourself etc
-detta | this/that
-åt | to
-utan | without
-varit | was
-hur | how
-ingen | no
-mitt | my
-ni | you
-bli | to be, become
-blev | from bli
-oss | us
-din | thy
-dessa | these/those
-några | some etc
-deras | their
-blir | from bli
-mina | my
-samma | (the) same
-vilken | who, that
-er | you, your
-sådan | such a
-vår | our
-blivit | from bli
-dess | its
-inom | within
-mellan | between
-sådant | such a
-varför | why
-varje | each
-vilka | who, that
-ditt | thy
-vem | who
-vilket | who, that
-sitta | his
-sådana | such a
-vart | each
-dina | thy
-vars | whose
-vårt | our
-våra | our
-ert | your
-era | your
-vilkas | whose
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt
deleted file mode 100644
index 07f0fab..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt
+++ /dev/null
@@ -1,119 +0,0 @@
-# Thai stopwords from:
-# "Opinion Detection in Thai Political News Columns
-# Based on Subjectivity Analysis"
-# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
-ไว้
-ไม่
-ไป
-ได้
-ให้
-ใน
-โดย
-แห่ง
-แล้ว
-และ
-แรก
-แบบ
-แต่
-เอง
-เห็น
-เลย
-เริ่ม
-เรา
-เมื่อ
-เพื่อ
-เพราะ
-เป็นการ
-เป็น
-เปิดเผย
-เปิด
-เนื่องจาก
-เดียวกัน
-เดียว
-เช่น
-เฉพาะ
-เคย
-เข้า
-เขา
-อีก
-อาจ
-อะไร
-ออก
-อย่าง
-อยู่
-อยาก
-หาก
-หลาย
-หลังจาก
-หลัง
-หรือ
-หนึ่ง
-ส่วน
-ส่ง
-สุด
-สําหรับ
-ว่า
-วัน
-ลง
-ร่วม
-ราย
-รับ
-ระหว่าง
-รวม
-ยัง
-มี
-มาก
-มา
-พร้อม
-พบ
-ผ่าน
-ผล
-บาง
-น่า
-นี้
-นํา
-นั้น
-นัก
-นอกจาก
-ทุก
-ที่สุด
-ที่
-ทําให้
-ทํา
-ทาง
-ทั้งนี้
-ทั้ง
-ถ้า
-ถูก
-ถึง
-ต้อง
-ต่างๆ
-ต่าง
-ต่อ
-ตาม
-ตั้งแต่
-ตั้ง
-ด้าน
-ด้วย
-ดัง
-ซึ่ง
-ช่วง
-จึง
-จาก
-จัด
-จะ
-คือ
-ความ
-ครั้ง
-คง
-ขึ้น
-ของ
-ขอ
-ขณะ
-ก่อน
-ก็
-การ
-กับ
-กัน
-กว่า
-กล่าว
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt
deleted file mode 100644
index 84d9408..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt
+++ /dev/null
@@ -1,212 +0,0 @@
-# Turkish stopwords from LUCENE-559
-# merged with the list from "Information Retrieval on Turkish Texts"
-# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
-acaba
-altmış
-altı
-ama
-ancak
-arada
-aslında
-ayrıca
-bana
-bazı
-belki
-ben
-benden
-beni
-benim
-beri
-beş
-bile
-bin
-bir
-birçok
-biri
-birkaç
-birkez
-birşey
-birşeyi
-biz
-bize
-bizden
-bizi
-bizim
-böyle
-böylece
-bu
-buna
-bunda
-bundan
-bunlar
-bunları
-bunların
-bunu
-bunun
-burada
-çok
-çünkü
-da
-daha
-dahi
-de
-defa
-değil
-diğer
-diye
-doksan
-dokuz
-dolayı
-dolayısıyla
-dört
-edecek
-eden
-ederek
-edilecek
-ediliyor
-edilmesi
-ediyor
-eğer
-elli
-en
-etmesi
-etti
-ettiği
-ettiğini
-gibi
-göre
-halen
-hangi
-hatta
-hem
-henüz
-hep
-hepsi
-her
-herhangi
-herkesin
-hiç
-hiçbir
-için
-iki
-ile
-ilgili
-ise
-işte
-itibaren
-itibariyle
-kadar
-karşın
-katrilyon
-kendi
-kendilerine
-kendini
-kendisi
-kendisine
-kendisini
-kez
-ki
-kim
-kimden
-kime
-kimi
-kimse
-kırk
-milyar
-milyon
-mu
-mü
-mı
-nasıl
-ne
-neden
-nedenle
-nerde
-nerede
-nereye
-niye
-niçin
-o
-olan
-olarak
-oldu
-olduğu
-olduğunu
-olduklarını
-olmadı
-olmadığı
-olmak
-olması
-olmayan
-olmaz
-olsa
-olsun
-olup
-olur
-olursa
-oluyor
-on
-ona
-ondan
-onlar
-onlardan
-onları
-onların
-onu
-onun
-otuz
-oysa
-öyle
-pek
-rağmen
-sadece
-sanki
-sekiz
-seksen
-sen
-senden
-seni
-senin
-siz
-sizden
-sizi
-sizin
-şey
-şeyden
-şeyi
-şeyler
-şöyle
-şu
-şuna
-şunda
-şundan
-şunları
-şunu
-tarafından
-trilyon
-tüm
-üç
-üzere
-var
-vardı
-ve
-veya
-ya
-yani
-yapacak
-yapılan
-yapılması
-yapıyor
-yapmak
-yaptı
-yaptığı
-yaptığını
-yaptıkları
-yedi
-yerine
-yetmiş
-yine
-yirmi
-yoksa
-yüz
-zaten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt b/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt
deleted file mode 100644
index 6f0368e..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt
+++ /dev/null
@@ -1,29 +0,0 @@
-#
-# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
-#
-# Add entries to this file in order to override the statistical model in terms
-# of segmentation, readings and part-of-speech tags. Notice that entries do
-# not have weights since they are always used when found. This is by-design
-# in order to maximize ease-of-use.
-#
-# Entries are defined using the following CSV format:
-# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
-#
-# Notice that a single half-width space separates tokens and readings, and
-# that the number tokens and readings must match exactly.
-#
-# Also notice that multiple entries with the same <text> is undefined.
-#
-# Whitespace only lines are ignored. Comments are not allowed on entry lines.
-#
-
-# Custom segmentation for kanji compounds
-日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
-関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
-
-# Custom segmentation for compound katakana
-トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
-ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
-
-# Custom reading for former sumo wrestler
-朝青龍,朝青龍,アサショウリュウ,カスタム人名
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/managed-schema b/solr/server/solr/configsets/basic_configs/conf/managed-schema
deleted file mode 100644
index f1017af..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/managed-schema
+++ /dev/null
@@ -1,1069 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default)
- or located where the classloader for the Solr webapp can find it.
-
- This example schema is the recommended starting point for users.
- It should be kept correct and concise, usable out-of-the-box.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
-
- PERFORMANCE NOTE: this schema includes many optional features and should not
- be used for benchmarking. To improve performance one could
- - set stored="false" for all fields possible (esp large fields) when you
- only need to search on the field but don't need to return the original
- value.
- - set indexed="false" if you don't need to search on the field, but only
- return the field as a result of searching on other indexed fields.
- - remove all unneeded copyField statements
- - for best index size and searching performance, set "index" to false
- for all general text fields, use copyField to copy them to the
- catchall "text" field, and use that for searching.
- - For maximum indexing performance, use the ConcurrentUpdateSolrServer
- java client.
- - Remember to run the JVM in server mode, and use a higher logging level
- that avoids logging every request
--->
-
-<schema name="default-config" version="2.0">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
- version="x.y" is Solr's version number for the schema syntax and
- semantics. It should not normally be changed by applications.
-
- 1.0: multiValued attribute did not exist, all fields are multiValued
- by nature
- 1.1: multiValued attribute introduced, false by default
- 1.2: omitTermFreqAndPositions attribute introduced, true by default
- except for text fields.
- 1.3: removed optional field compress feature
- 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
- behavior when a single string produces multiple tokens. Defaults
- to off for version >= 1.4
- 1.5: omitNorms defaults to true for primitive field types
- (int, float, boolean, string...)
- 1.6: useDocValuesAsStored defaults to true.
- -->
-
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a field type from the
- fieldTypes section
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- docValues: true if this field should have doc values. Doc values are
- useful (required, if you are using *Point fields) for faceting,
- grouping, sorting and function queries. Doc values will make the index
- faster to load, more NRT-friendly and more memory-efficient.
- They however come with some limitations: they are currently only
- supported by StrField, UUIDField, all Trie*Fields and *PointFields,
- and depending on the field type, they might require the field to be
- single-valued, be required or have a default value (check the
- documentation of the field type you're interested in for more information)
- multiValued: true if this field may contain multiple values per document
- omitNorms: (expert) set to true to omit the norms associated with
- this field (this disables length normalization and index-time
- boosting for the field, and saves some memory). Only full-text
- fields or fields that need an index-time boost need norms.
- Norms are omitted for primitive (non-analyzed) types by default.
- termVectors: [false] set to true to store the term vector for a
- given field.
- When using MoreLikeThis, fields used for similarity should be
- stored for best performance.
- termPositions: Store position information with the term vector.
- This will increase storage costs.
- termOffsets: Store offset information with the term vector. This
- will increase storage costs.
- required: The field is required. It will throw an error if the
- value does not exist
- default: a value that should be used if no value is specified
- when adding a document.
- -->
-
- <!-- field names should consist of alphanumeric or underscore characters only and
- not start with a digit. This is not currently strictly enforced,
- but other field names will not have first class support from all components
- and back compatibility is not guaranteed. Names with both leading and
- trailing underscores (e.g. _version_) are reserved.
- -->
-
- <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
- id, _version_, and _text_. All other fields will be type guessed and added via the
- "add-unknown-fields-to-the-schema" update request processor chain declared
- in solrconfig.xml.
-
- Note that many dynamic fields are also defined - you can use them to specify a
- field's type via field naming conventions - see below.
-
- WARNING: The _text_ catch-all field will significantly increase your index size.
- If you don't need it, consider removing it and the corresponding copyField directive.
- -->
- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
- <!-- doc values are enabled by default for primitive types such as long so we don't index the version field -->
- <field name="_version_" type="long" indexed="false" stored="false"/>
- <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
- <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
-
- <!-- Only enabled in the "schemaless" data-driven example (assuming the client
- does not know what fields may be searched) because it's very expensive to index everything twice. -->
- <!-- <copyField source="*" dest="_text_"/> -->
-
- <!-- Dynamic field definitions allow using convention over configuration
- for fields via the specification of patterns to match field names.
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
- RESTRICTION: the glob-like pattern in the name attribute must have
- a "*" only at the start or the end. -->
-
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true" />
- <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
-
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
- <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
- <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
-
- <!-- KD-tree (point) numerics -->
- <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
- <dynamicField name="*_pis" type="pints" indexed="true" stored="true"/>
- <dynamicField name="*_pl" type="plong" indexed="true" stored="true"/>
- <dynamicField name="*_pls" type="plongs" indexed="true" stored="true"/>
- <dynamicField name="*_pf" type="pfloat" indexed="true" stored="true"/>
- <dynamicField name="*_pfs" type="pfloats" indexed="true" stored="true"/>
- <dynamicField name="*_pd" type="pdouble" indexed="true" stored="true"/>
- <dynamicField name="*_pds" type="pdoubles" indexed="true" stored="true"/>
- <dynamicField name="*_pdt" type="pdate" indexed="true" stored="true"/>
- <dynamicField name="*_pdts" type="pdates" indexed="true" stored="true"/>
-
- <!-- some trie-coded dynamic fields -->
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
- <dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
-
- <!-- payloaded dynamic fields -->
- <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true" stored="true"/>
- <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true" stored="true"/>
- <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true" stored="true"/>
-
- <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
-
- <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
- <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
-
- <dynamicField name="random_*" type="random" />
-
- <!-- uncomment the following to ignore any fields that don't already match an existing
- field name or dynamic field, rather than reporting them as an error.
- alternately, change the type="ignored" to some other type e.g. "text" if you want
- unknown fields indexed and/or stored by default
-
- NB: use of "*" dynamic fields will disable field type guessing and adding
- unknown fields to the schema. -->
- <!--dynamicField name="*" type="ignored" multiValued="true" /-->
-
- <!-- Field to use to determine and enforce document uniqueness.
- Unless this field is marked with required="false", it will be a required field
- -->
- <uniqueKey>id</uniqueKey>
-
- <!-- copyField commands copy one field to another at the time a document
- is added to the index. It's used either to index the same field differently,
- or to add multiple fields to the same field for easier/faster searching.
-
- <copyField source="sourceFieldName" dest="destinationFieldName"/>
- -->
-
- <!-- field type definitions. The "name" attribute is
- just a label to be used by field definitions. The "class"
- attribute and any other attributes determine the real
- behavior of the fieldType.
- Class names starting with "solr" refer to java classes in a
- standard package such as org.apache.solr.analysis
- -->
-
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- It supports doc values but in that case the field needs to be
- single-valued and either required or have a default value.
- -->
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
- <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
-
- <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
-
- <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
- currently supported on types that are sorted internally as strings
- and on numeric types.
- This includes "string","boolean", "int", "float", "long", "date", "double",
- including the "Trie" and "Point" variants.
- - If sortMissingLast="true", then a sort on this field will cause documents
- without the field to come after documents with the field,
- regardless of the requested sort order (asc or desc).
- - If sortMissingFirst="true", then a sort on this field will cause documents
- without the field to come before documents with the field,
- regardless of the requested sort order.
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
- then default lucene sorting will be used which places docs without the
- field first in an ascending sort and last in a descending sort.
- -->
-
- <!--
- Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
- search time and at index time, but some features are still not supported.
- Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
- -->
- <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
- <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
- <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
- <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
-
- <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
- <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
- <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
- <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
-
- <!--
- Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
- tint/tfloat/tlong/tdouble types.
- -->
- <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-
- <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-
- <!--
- Numeric field types that index each value at various levels of precision
- to accelerate range queries when the number of values between the range
- endpoints is large. See the javadoc for NumericRangeQuery for internal
- implementation details.
-
- Smaller precisionStep values (specified in bits) will lead to more tokens
- indexed per value, slightly larger index size, and faster range queries.
- A precisionStep of 0 disables indexing at different precision levels.
-
- Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
- -->
- <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-
- <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-
- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
- is a more restricted form of the canonical representation of dateTime
- http://www.w3.org/TR/xmlschema-2/#dateTime
- The trailing "Z" designates UTC time and is mandatory.
- Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
- All other components are mandatory.
-
- Expressions can also be used to denote calculations that should be
- performed relative to "NOW" to determine the value, ie...
-
- NOW/HOUR
- ... Round to the start of the current hour
- NOW-1DAY
- ... Exactly 1 day prior to now
- NOW/DAY+6MONTHS+3DAYS
- ... 6 months and 3 days in the future from the start of
- the current day
-
- Consult the TrieDateField javadocs for more information.
- -->
- <!-- KD-tree versions of date fields -->
- <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
- <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
-
- <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
- <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
-
-
- <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
- <fieldType name="binary" class="solr.BinaryField"/>
-
- <!-- The "RandomSortField" is not used to store or search any
- data. You can declare fields of this type it in your schema
- to generate pseudo-random orderings of your docs for sorting
- or function purposes. The ordering is generated based on the field
- name and the version of the index. As long as the index version
- remains unchanged, and the same field name is reused,
- the ordering of the docs will be consistent.
- If you want different psuedo-random orderings of documents,
- for the same version of the index, use a dynamicField and
- change the field name in the request.
- -->
- <fieldType name="random" class="solr.RandomSortField" indexed="true" />
-
- <!-- solr.TextField allows the specification of custom text analyzers
- specified as a tokenizer and a list of token filters. Different
- analyzers may be specified for indexing and querying.
-
- The optional positionIncrementGap puts space between multiple fields of
- this type on the same document, with the purpose of preventing false phrase
- matching across fields.
-
- For more info on customizing your analyzer chain, please see
- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
- -->
-
- <!-- One can also specify an existing Analyzer class that has a
- default constructor via the class attribute on the analyzer element.
- Example:
- <fieldType name="text_greek" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
- </fieldType>
- -->
-
- <!-- A text field that only splits on whitespace for exact matching of words -->
- <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
- <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A general text field that has reasonable, generic
- cross-language defaults: it tokenizes with StandardTokenizer,
- removes stop words from case-insensitive "stopwords.txt"
- (empty by default), and down cases. At query time only, it
- also applies synonyms.
- -->
- <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.FlattenGraphFilterFactory"/>
- -->
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English: it
- tokenizes with StandardTokenizer, removes English stop words
- (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
- finally applies Porter's stemming. The query time analyzer
- also applies synonyms from synonyms.txt. -->
- <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
- <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.FlattenGraphFilterFactory"/>
- -->
- <!-- Case insensitive stop word removal.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English, plus
- aggressive word-splitting and autophrase features enabled.
- This field is just like text_en, except it adds
- WordDelimiterGraphFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and
- non-alphanumeric chars. This means certain compound word
- cases will work, for example query "wi fi" will match
- document "WiFi" or "wi-fi".
- -->
- <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
- <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- -->
- <!-- Case insensitive stop word removal.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- <filter class="solr.FlattenGraphFilterFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
- <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
- <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- <filter class="solr.FlattenGraphFilterFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Just like text_general except it reverses the characters of
- each token, to enable more efficient leading wildcard queries.
- -->
- <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
- <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
- <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
- </analyzer>
- </fieldType>
-
- <!-- lowercases the entire field value, keeping it as a single token. -->
- <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Example of using PathHierarchyTokenizerFactory at index time, so
- queries for paths match documents at that path, or in descendent paths
- -->
- <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
- <fieldType name="descendent_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Example of using PathHierarchyTokenizerFactory at query time, so
- queries for paths match documents at that path, or in ancestor paths
- -->
- <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
- <fieldType name="ancestor_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- </fieldType>
-
- <!-- since fields of this type are by default not stored or indexed,
- any data added to them will be ignored outright. -->
- <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
-
- <!-- This point type indexes the coordinates as separate fields (subFields)
- If subFieldType is defined, it references a type, and a dynamic field
- definition is created matching *___<typename>. Alternately, if
- subFieldSuffix is defined, that is used to create the subFields.
- Example: if subFieldType="double", then the coordinates would be
- indexed in fields myloc_0___double,myloc_1___double.
- Example: if subFieldSuffix="_d" then the coordinates would be indexed
- in fields myloc_0_d,myloc_1_d
- The subFields are an implementation detail of the fieldType, and end
- users normally should not need to know about them.
- -->
- <dynamicField name="*_point" type="point" indexed="true" stored="true"/>
- <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
-
- <!-- A specialized field for geospatial search filters and distance sorting. -->
- <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
-
- <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
- For more information about this and other Spatial fields new to Solr 4, see:
- http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
- -->
- <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
- geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
-
- <!-- Payloaded field types -->
- <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </analyzer>
- </fieldType>
- <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
- </analyzer>
- </fieldType>
- <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
- </analyzer>
- </fieldType>
-
- <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
- Parameters:
- defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
- precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
- providerClass: Lets you plug in other exchange provider backend:
- solr.FileExchangeRateProvider is the default and takes one parameter:
- currencyConfig: name of an xml file holding exchange rates
- solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
- ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
- refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
- -->
- <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
-
-
-
- <!-- some examples for different languages (generally ordered by ISO code) -->
-
- <!-- Arabic -->
- <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
- <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- for any non-arabic -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
- <!-- normalizes ﻯ to ﻱ, etc -->
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.ArabicStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Bulgarian -->
- <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
- <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
- <filter class="solr.BulgarianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Catalan -->
- <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
- <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
- </analyzer>
- </fieldType>
-
- <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
- <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
- <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- for any non-CJK -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.CJKBigramFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Czech -->
- <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
- <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
- <filter class="solr.CzechStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Danish -->
- <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
- <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
- </analyzer>
- </fieldType>
-
- <!-- German -->
- <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
- <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
- <filter class="solr.GermanNormalizationFilterFactory"/>
- <filter class="solr.GermanLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Greek -->
- <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
- <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- greek specific lowercase for sigma -->
- <filter class="solr.GreekLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
- <filter class="solr.GreekStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Spanish -->
- <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
- <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
- <filter class="solr.SpanishLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Basque -->
- <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
- <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
- </analyzer>
- </fieldType>
-
- <!-- Persian -->
- <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
- <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <!-- for ZWNJ -->
- <charFilter class="solr.PersianCharFilterFactory"/>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.PersianNormalizationFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
- </analyzer>
- </fieldType>
-
- <!-- Finnish -->
- <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
- <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
- <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- French -->
- <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
- <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
- <filter class="solr.FrenchLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Irish -->
- <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
- <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes d', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
- <!-- removes n-, etc. position increments is intentionally false! -->
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
- <filter class="solr.IrishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
- </analyzer>
- </fieldType>
-
- <!-- Galician -->
- <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
- <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
- <filter class="solr.GalicianStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Hindi -->
- <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
- <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <!-- normalizes unicode representation -->
- <filter class="solr.IndicNormalizationFilterFactory"/>
- <!-- normalizes variation in spelling -->
- <filter class="solr.HindiNormalizationFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
- <filter class="solr.HindiStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Hungarian -->
- <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
- <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
- <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Armenian -->
- <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
- <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
- </analyzer>
- </fieldType>
-
- <!-- Indonesian -->
- <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
- <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
- <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
- <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
- </analyzer>
- </fieldType>
-
- <!-- Italian -->
- <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
- <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
- <filter class="solr.ItalianLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
-
- NOTE: If you want to optimize search for precision, use default operator AND in your request
- handler config (q.op) Use OR if you would like to optimize for recall (default).
- -->
- <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
- <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
- <analyzer>
- <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
-
- Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
- is used to segment compounds into its parts and the compound itself is kept as synonym.
-
- Valid values for attribute mode are:
- normal: regular segmentation
- search: segmentation useful for search with synonyms compounds (default)
- extended: same as search mode, but unigrams unknown words (experimental)
-
- For some applications it might be good to use search mode for indexing and normal mode for
- queries to reduce recall and prevent parts of compounds from being matched and highlighted.
- Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
-
- Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
- model with your own entries for segmentation, part-of-speech tags and readings without a need
- to specify weights. Notice that user dictionaries have not been subject to extensive testing.
-
- User dictionary attributes are:
- userDictionary: user dictionary filename
- userDictionaryEncoding: user dictionary encoding (default is UTF-8)
-
- See lang/userdict_ja.txt for a sample user dictionary file.
-
- Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
-
- See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
- -->
- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
- <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
- <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
- <!-- Removes tokens with certain part-of-speech tags -->
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
- <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
- <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
- <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
- <!-- Lower-cases romaji characters -->
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Latvian -->
- <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
- <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
- <filter class="solr.LatvianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Dutch -->
- <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
- <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
- <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
- </analyzer>
- </fieldType>
-
- <!-- Norwegian -->
- <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
- <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
- <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
- <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Portuguese -->
- <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
- <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
- <filter class="solr.PortugueseLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
- <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Romanian -->
- <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
- <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
- </analyzer>
- </fieldType>
-
- <!-- Russian -->
- <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
- <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
- <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Swedish -->
- <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
- <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
- <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Thai -->
- <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
- <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.ThaiTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
- </analyzer>
- </fieldType>
-
- <!-- Turkish -->
- <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
- <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
- </analyzer>
- </fieldType>
-
- <!-- Similarity is the scoring routine for each document vs. a query.
- A custom Similarity or SimilarityFactory may be specified here, but
- the default is fine for most applications.
- For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
- -->
- <!--
- <similarity class="com.example.solr.CustomSimilarityFactory">
- <str name="paramkey">param value</str>
- </similarity>
- -->
-
-</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/params.json
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/params.json b/solr/server/solr/configsets/basic_configs/conf/params.json
deleted file mode 100644
index 06114ef..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/params.json
+++ /dev/null
@@ -1,20 +0,0 @@
-{"params":{
- "query":{
- "defType":"edismax",
- "q.alt":"*:*",
- "rows":"10",
- "fl":"*,score",
- "":{"v":0}
- },
- "facets":{
- "facet":"on",
- "facet.mincount": "1",
- "":{"v":0}
- },
- "velocity":{
- "wt": "velocity",
- "v.template":"browse",
- "v.layout": "layout",
- "":{"v":0}
- }
-}}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/protwords.txt b/solr/server/solr/configsets/basic_configs/conf/protwords.txt
deleted file mode 100644
index 1dfc0ab..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/protwords.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# Use a protected word file to protect against the stemmer reducing two
-# unrelated words to the same base word.
-
-# Some non-words that normally won't be encountered,
-# just to test that they won't be stemmed.
-dontstems
-zwhacky
-
[07/50] [abbrv] lucene-solr:feature/autoscaling: LUCENE-7719: tests:
Eliminate needless SuppressSysoutChecks and address lint warning
Posted by sh...@apache.org.
LUCENE-7719: tests: Eliminate needless SuppressSysoutChecks and address lint warning
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/42fdb549
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/42fdb549
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/42fdb549
Branch: refs/heads/feature/autoscaling
Commit: 42fdb549270b41ae164b90ea7bc001ceb7848b6d
Parents: d0b9d34
Author: David Smiley <ds...@apache.org>
Authored: Fri Jun 16 22:58:59 2017 -0400
Committer: David Smiley <ds...@apache.org>
Committed: Fri Jun 16 22:58:59 2017 -0400
----------------------------------------------------------------------
.../uhighlight/TestSplittingBreakIterator.java | 1 -
.../uhighlight/TestUnifiedHighlighter.java | 3 ---
.../TestUnifiedHighlighterRanking.java | 3 ---
.../TestUnifiedHighlighterReanalysis.java | 2 --
.../TestUnifiedHighlighterStrictPhrases.java | 2 --
.../TestUnifiedHighlighterTermVec.java | 2 --
.../TestUnifiedHighlighterExtensibility.java | 26 +++++++++++---------
7 files changed, 14 insertions(+), 25 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/42fdb549/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestSplittingBreakIterator.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestSplittingBreakIterator.java b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestSplittingBreakIterator.java
index b78f329..2fd305c 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestSplittingBreakIterator.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestSplittingBreakIterator.java
@@ -24,7 +24,6 @@ import java.util.Locale;
import org.apache.lucene.util.LuceneTestCase;
-@LuceneTestCase.SuppressSysoutChecks(bugUrl = "")//Gradle interferes with this Lucene test rule
public class TestSplittingBreakIterator extends LuceneTestCase {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/42fdb549/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighter.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighter.java b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighter.java
index 3ffe95a..96ec155 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighter.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighter.java
@@ -51,12 +51,9 @@ import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.LuceneTestCase;
-import org.apache.lucene.util.LuceneTestCase.SuppressCodecs;
import org.junit.After;
import org.junit.Before;
-@SuppressCodecs({"MockFixedIntBlock", "MockVariableIntBlock", "MockSep", "MockRandom", "Lucene3x"})
-@LuceneTestCase.SuppressSysoutChecks(bugUrl = "")//Gradle interferes with this Lucene test rule
public class TestUnifiedHighlighter extends LuceneTestCase {
private final FieldType fieldType; // for "body" generally, but not necessarily others. See constructor
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/42fdb549/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterRanking.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterRanking.java b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterRanking.java
index 64570ae..e539263 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterRanking.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterRanking.java
@@ -37,15 +37,12 @@ import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.LuceneTestCase;
-import org.apache.lucene.util.LuceneTestCase.SuppressCodecs;
import org.apache.lucene.util.TestUtil;
import java.io.IOException;
import java.util.HashSet;
import java.util.Random;
-@SuppressCodecs({"MockFixedIntBlock", "MockVariableIntBlock", "MockSep", "MockRandom", "Lucene3x"})
-@LuceneTestCase.SuppressSysoutChecks(bugUrl = "")//Gradle interferes with this Lucene test rule
public class TestUnifiedHighlighterRanking extends LuceneTestCase {
Analyzer indexAnalyzer;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/42fdb549/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterReanalysis.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterReanalysis.java b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterReanalysis.java
index c881269..04ab011 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterReanalysis.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterReanalysis.java
@@ -32,8 +32,6 @@ import org.apache.lucene.store.Directory;
import org.apache.lucene.util.LuceneTestCase;
import org.junit.Test;
-@LuceneTestCase.SuppressCodecs({"MockFixedIntBlock", "MockVariableIntBlock", "MockSep", "MockRandom", "Lucene3x"})
-@LuceneTestCase.SuppressSysoutChecks(bugUrl = "")//Gradle interferes with this Lucene test rule
public class TestUnifiedHighlighterReanalysis extends LuceneTestCase {
private MockAnalyzer indexAnalyzer =
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/42fdb549/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterStrictPhrases.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterStrictPhrases.java b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterStrictPhrases.java
index dafb6e2..e56679e 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterStrictPhrases.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterStrictPhrases.java
@@ -54,8 +54,6 @@ import org.apache.lucene.util.QueryBuilder;
import org.junit.After;
import org.junit.Before;
-@LuceneTestCase.SuppressCodecs({"MockFixedIntBlock", "MockVariableIntBlock", "MockSep", "MockRandom", "Lucene3x"})
-@LuceneTestCase.SuppressSysoutChecks(bugUrl = "")//Gradle interferes with this Lucene test rule
public class TestUnifiedHighlighterStrictPhrases extends LuceneTestCase {
final FieldType fieldType;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/42fdb549/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterTermVec.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterTermVec.java b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterTermVec.java
index c462aee..89332e2 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterTermVec.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterTermVec.java
@@ -48,8 +48,6 @@ import java.util.Map;
* This test DOES NOT represent all testing for highlighting when term vectors are used. Other tests pick the offset
* source at random (to include term vectors) and in-effect test term vectors generally.
*/
-@LuceneTestCase.SuppressCodecs({"MockFixedIntBlock", "MockVariableIntBlock", "MockSep", "MockRandom", "Lucene3x"})
-@LuceneTestCase.SuppressSysoutChecks(bugUrl = "")//Gradle interferes with this Lucene test rule
public class TestUnifiedHighlighterTermVec extends LuceneTestCase {
private Analyzer indexAnalyzer;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/42fdb549/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/visibility/TestUnifiedHighlighterExtensibility.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/visibility/TestUnifiedHighlighterExtensibility.java b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/visibility/TestUnifiedHighlighterExtensibility.java
index e5d7e82..738a0b9 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/visibility/TestUnifiedHighlighterExtensibility.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/visibility/TestUnifiedHighlighterExtensibility.java
@@ -217,18 +217,20 @@ public class TestUnifiedHighlighterExtensibility extends LuceneTestCase {
// TEST OffsetsEnums & Passage visibility
// this code never runs; just for compilation
- OffsetsEnum oe = new OffsetsEnum(null, EMPTY);
- oe.getTerm();
- oe.getPostingsEnum();
- oe.freq();
- oe.hasMorePositions();
- oe.nextPosition();
- oe.startOffset();
- oe.endOffset();
- oe.getWeight();
- oe.setWeight(2f);
-
- Passage p = new Passage();
+ Passage p;
+ try (OffsetsEnum oe = new OffsetsEnum(null, EMPTY)) {
+ oe.getTerm();
+ oe.getPostingsEnum();
+ oe.freq();
+ oe.hasMorePositions();
+ oe.nextPosition();
+ oe.startOffset();
+ oe.endOffset();
+ oe.getWeight();
+ oe.setWeight(2f);
+ }
+
+ p = new Passage();
p.setStartOffset(0);
p.setEndOffset(9);
p.setScore(1f);
[20/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10406: v2 API
error messages list the URL request path as /solr/____v2/... when the
original path was /v2/...
Posted by sh...@apache.org.
SOLR-10406: v2 API error messages list the URL request path as /solr/____v2/... when the original path was /v2/...
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/b1b566f5
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/b1b566f5
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/b1b566f5
Branch: refs/heads/feature/autoscaling
Commit: b1b566f57bba46cadae33bc8198246fa05609287
Parents: 294026f
Author: Cao Manh Dat <da...@apache.org>
Authored: Tue Jun 20 12:46:33 2017 +0700
Committer: Cao Manh Dat <da...@apache.org>
Committed: Tue Jun 20 12:46:33 2017 +0700
----------------------------------------------------------------------
solr/CHANGES.txt | 2 ++
.../java/org/apache/solr/api/V2HttpCall.java | 27 +++++++++-----
.../org/apache/solr/servlet/HttpSolrCall.java | 2 +-
.../solr/handler/V2ApiIntegrationTest.java | 38 ++++++++++++++++++++
.../solr/client/solrj/impl/HttpSolrClient.java | 12 ++++---
5 files changed, 68 insertions(+), 13 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1b566f5/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 15b86a2..b163a7f 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -149,6 +149,8 @@ New Features
* SOLR-9989: Add support for PointFields in FacetModule (JSON Facets) (Cao Manh Dat)
+* SOLR-10406: v2 API error messages list the URL request path as /solr/____v2/... when the original path was /v2/... (Cao Manh Dat, noble)
+
Bug Fixes
----------------------
* SOLR-9262: Connection and read timeouts are being ignored by UpdateShardHandler after SOLR-4509.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1b566f5/solr/core/src/java/org/apache/solr/api/V2HttpCall.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/api/V2HttpCall.java b/solr/core/src/java/org/apache/solr/api/V2HttpCall.java
index 5e7c0b1..49d50e9 100644
--- a/solr/core/src/java/org/apache/solr/api/V2HttpCall.java
+++ b/solr/core/src/java/org/apache/solr/api/V2HttpCall.java
@@ -56,7 +56,6 @@ import org.slf4j.LoggerFactory;
import static org.apache.solr.common.params.CommonParams.JSON;
import static org.apache.solr.common.params.CommonParams.WT;
import static org.apache.solr.servlet.SolrDispatchFilter.Action.ADMIN;
-import static org.apache.solr.servlet.SolrDispatchFilter.Action.PASSTHROUGH;
import static org.apache.solr.servlet.SolrDispatchFilter.Action.PROCESS;
import static org.apache.solr.common.util.PathTrie.getPathSegments;
@@ -76,7 +75,7 @@ public class V2HttpCall extends HttpSolrCall {
protected void init() throws Exception {
String path = this.path;
- String fullPath = path = path.substring(7);//strip off '/____v2'
+ final String fullPath = path = path.substring(7);//strip off '/____v2'
try {
pieces = getPathSegments(path);
if (pieces.size() == 0 || (pieces.size() == 1 && path.endsWith(CommonParams.INTROSPECT))) {
@@ -159,7 +158,7 @@ public class V2HttpCall extends HttpSolrCall {
log.error("Error in init()", rte);
throw rte;
} finally {
- if (api == null) action = PASSTHROUGH;
+ if (api == null) action = PROCESS;
if (solrReq != null) solrReq.getContext().put(CommonParams.PATH, path);
}
}
@@ -309,16 +308,28 @@ public class V2HttpCall extends HttpSolrCall {
@Override
protected void handleAdmin(SolrQueryResponse solrResp) {
- api.call(this.solrReq, solrResp);
+ try {
+ api.call(this.solrReq, solrResp);
+ } catch (Exception e) {
+ solrResp.setException(e);
+ }
}
@Override
protected void execute(SolrQueryResponse rsp) {
- try {
- api.call(solrReq, rsp);
- } catch (RuntimeException e) {
- throw e;
+ SolrCore.preDecorateResponse(solrReq, rsp);
+ if (api == null) {
+ rsp.setException(new SolrException(SolrException.ErrorCode.NOT_FOUND,
+ "Cannot find correspond api for the path : " + solrReq.getContext().get(CommonParams.PATH)));
+ } else {
+ try {
+ api.call(solrReq, rsp);
+ } catch (Exception e) {
+ rsp.setException(e);
+ }
}
+
+ SolrCore.postDecorateResponse(handler, solrReq, rsp);
}
@Override
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1b566f5/solr/core/src/java/org/apache/solr/servlet/HttpSolrCall.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/servlet/HttpSolrCall.java b/solr/core/src/java/org/apache/solr/servlet/HttpSolrCall.java
index bf6c553..5542d4c 100644
--- a/solr/core/src/java/org/apache/solr/servlet/HttpSolrCall.java
+++ b/solr/core/src/java/org/apache/solr/servlet/HttpSolrCall.java
@@ -687,7 +687,7 @@ public class HttpSolrCall {
solrReq = new SolrQueryRequestBase(core, solrParams) {
};
}
- QueryResponseWriter writer = core.getQueryResponseWriter(solrReq);
+ QueryResponseWriter writer = getResponseWriter();
writeResponse(solrResp, writer, Method.GET);
} catch (Exception e) { // This error really does not matter
exp = e;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1b566f5/solr/core/src/test/org/apache/solr/handler/V2ApiIntegrationTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/handler/V2ApiIntegrationTest.java b/solr/core/src/test/org/apache/solr/handler/V2ApiIntegrationTest.java
index 5a8d482..dac495e 100644
--- a/solr/core/src/test/org/apache/solr/handler/V2ApiIntegrationTest.java
+++ b/solr/core/src/test/org/apache/solr/handler/V2ApiIntegrationTest.java
@@ -22,11 +22,15 @@ import java.io.IOException;
import java.util.List;
import java.util.Map;
+import org.apache.solr.client.solrj.ResponseParser;
import org.apache.solr.client.solrj.SolrRequest;
import org.apache.solr.client.solrj.SolrServerException;
+import org.apache.solr.client.solrj.impl.BinaryResponseParser;
import org.apache.solr.client.solrj.impl.CloudSolrClient;
+import org.apache.solr.client.solrj.impl.XMLResponseParser;
import org.apache.solr.client.solrj.request.CollectionAdminRequest;
import org.apache.solr.client.solrj.request.V2Request;
+import org.apache.solr.client.solrj.response.DelegationTokenResponse;
import org.apache.solr.client.solrj.response.V2Response;
import org.apache.solr.cloud.SolrCloudTestCase;
import org.apache.solr.common.params.ModifiableSolrParams;
@@ -57,6 +61,40 @@ public class V2ApiIntegrationTest extends SolrCloudTestCase {
assertEquals(0, res.getStatus());
}
+ private void testException(ResponseParser responseParser, int expectedCode, String path, String payload) throws IOException, SolrServerException {
+ V2Request v2Request = new V2Request.Builder(path)
+ .withMethod(SolrRequest.METHOD.POST)
+ .withPayload(payload)
+ .build();
+ v2Request.setResponseParser(responseParser);
+ V2Response response = v2Request.process(cluster.getSolrClient());
+ assertEquals(getStatus(response), expectedCode);
+ }
+
+ @Test
+ public void testException() throws Exception {
+ String notFoundPath = "/c/" + COLL_NAME + "/abccdef";
+ String incorrectPayload = "{rebalance-leaders: {maxAtOnce: abc, maxWaitSeconds: xyz}}";
+ testException(new XMLResponseParser(),404,
+ notFoundPath, incorrectPayload);
+ testException(new DelegationTokenResponse.JsonMapResponseParser(),404,
+ notFoundPath, incorrectPayload);
+ testException(new BinaryResponseParser(),404,
+ notFoundPath, incorrectPayload);
+ testException(new XMLResponseParser(), 400, "/c/" + COLL_NAME, incorrectPayload);
+ testException(new BinaryResponseParser(), 400, "/c/" + COLL_NAME, incorrectPayload);
+ testException(new DelegationTokenResponse.JsonMapResponseParser(), 400, "/c/" + COLL_NAME, incorrectPayload);
+ }
+
+ private long getStatus(V2Response response) {
+ Object header = response.getResponse().get("responseHeader");
+ if (header instanceof NamedList) {
+ return (int) ((NamedList) header).get("status");
+ } else {
+ return (long) ((Map) header).get("status");
+ }
+ }
+
@Test
public void testIntrospect() throws Exception {
ModifiableSolrParams params = new ModifiableSolrParams();
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b1b566f5/solr/solrj/src/java/org/apache/solr/client/solrj/impl/HttpSolrClient.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/impl/HttpSolrClient.java b/solr/solrj/src/java/org/apache/solr/client/solrj/impl/HttpSolrClient.java
index 104ab1f..fa1ccf1 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/impl/HttpSolrClient.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/impl/HttpSolrClient.java
@@ -228,7 +228,11 @@ public class HttpSolrClient extends SolrClient {
throws SolrServerException, IOException {
HttpRequestBase method = createMethod(request, collection);
setBasicAuthHeader(request, method);
- return executeMethod(method, processor);
+ return executeMethod(method, processor, isV2ApiRequest(request));
+ }
+
+ private boolean isV2ApiRequest(final SolrRequest request) {
+ return request instanceof V2Request || request.getPath().contains("/____v2");
}
private void setBasicAuthHeader(SolrRequest request, HttpRequestBase method) throws UnsupportedEncodingException {
@@ -268,7 +272,7 @@ public class HttpSolrClient extends SolrClient {
ExecutorService pool = ExecutorUtil.newMDCAwareFixedThreadPool(1, new SolrjNamedThreadFactory("httpUriRequest"));
try {
MDC.put("HttpSolrClient.url", baseUrl);
- mrr.future = pool.submit(() -> executeMethod(method, processor));
+ mrr.future = pool.submit(() -> executeMethod(method, processor, isV2ApiRequest(request)));
} finally {
pool.shutdown();
@@ -473,7 +477,7 @@ public class HttpSolrClient extends SolrClient {
}
- protected NamedList<Object> executeMethod(HttpRequestBase method, final ResponseParser processor) throws SolrServerException {
+ protected NamedList<Object> executeMethod(HttpRequestBase method, final ResponseParser processor, final boolean isV2Api) throws SolrServerException {
method.addHeader("User-Agent", AGENT);
org.apache.http.client.config.RequestConfig.Builder requestConfigBuilder = HttpClientUtil.createDefaultRequestConfigBuilder();
@@ -571,7 +575,7 @@ public class HttpSolrClient extends SolrClient {
} catch (Exception e) {
throw new RemoteSolrException(baseUrl, httpStatus, e.getMessage(), e);
}
- if (httpStatus != HttpStatus.SC_OK) {
+ if (httpStatus != HttpStatus.SC_OK && !isV2Api) {
NamedList<String> metadata = null;
String reason = null;
try {
[18/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10882: Comment
out broken test case
Posted by sh...@apache.org.
SOLR-10882: Comment out broken test case
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/3ff8c870
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/3ff8c870
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/3ff8c870
Branch: refs/heads/feature/autoscaling
Commit: 3ff8c870243c576f73650309715f6cbd3bc8c869
Parents: 09b0eee
Author: Joel Bernstein <jb...@apache.org>
Authored: Mon Jun 19 09:16:23 2017 -0400
Committer: Joel Bernstein <jb...@apache.org>
Committed: Mon Jun 19 09:16:23 2017 -0400
----------------------------------------------------------------------
.../apache/solr/client/solrj/io/stream/StreamExpressionTest.java | 2 ++
1 file changed, 2 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/3ff8c870/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/StreamExpressionTest.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/StreamExpressionTest.java b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/StreamExpressionTest.java
index 75f3637..f58a19e 100644
--- a/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/StreamExpressionTest.java
+++ b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/StreamExpressionTest.java
@@ -5825,6 +5825,7 @@ public class StreamExpressionTest extends SolrCloudTestCase {
assertEquals(p, 2.4, 0.001);
}
+ /*
@Test
public void testArraySort() throws Exception {
String cexpr = "arraySort(array(11.5, 12.3, 4, 3, 1, 0))";
@@ -5850,6 +5851,7 @@ public class StreamExpressionTest extends SolrCloudTestCase {
assertEquals(asort.get(5).doubleValue(), 12.3, 0.0);
}
+*/
@Test
public void testCumulativeProbability() throws Exception {
UpdateRequest updateRequest = new UpdateRequest();
[29/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/solrconfig.xml b/solr/server/solr/configsets/_default/conf/solrconfig.xml
new file mode 100644
index 0000000..1b55374
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/solrconfig.xml
@@ -0,0 +1,1408 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ For more details about configurations options that may appear in
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+ <!-- In all configuration below, a prefix of "solr." for class names
+ is an alias that causes solr to search appropriate packages,
+ including org.apache.solr.(search|update|request|core|analysis)
+
+ You may also specify a fully qualified Java classname if you
+ have your own custom plugins.
+ -->
+
+ <!-- Controls what version of Lucene various components of Solr
+ adhere to. Generally, you want to use the latest version to
+ get all bug fixes and improvements. It is highly recommended
+ that you fully re-index after changing this setting as it can
+ affect both how text is indexed and queried.
+ -->
+ <luceneMatchVersion>7.0.0</luceneMatchVersion>
+
+ <!-- <lib/> directives can be used to instruct Solr to load any Jars
+ identified and use them to resolve any "plugins" specified in
+ your solrconfig.xml or schema.xml (ie: Analyzers, Request
+ Handlers, etc...).
+
+ All directories and paths are resolved relative to the
+ instanceDir.
+
+ Please note that <lib/> directives are processed in the order
+ that they appear in your solrconfig.xml file, and are "stacked"
+ on top of each other when building a ClassLoader - so if you have
+ plugin jars with dependencies on other jars, the "lower level"
+ dependency jars should be loaded first.
+
+ If a "./lib" directory exists in your instanceDir, all files
+ found in it are included as if you had used the following
+ syntax...
+
+ <lib dir="./lib" />
+ -->
+
+ <!-- A 'dir' option by itself adds any files found in the directory
+ to the classpath, this is useful for including all jars in a
+ directory.
+
+ When a 'regex' is specified in addition to a 'dir', only the
+ files in that directory which completely match the regex
+ (anchored on both ends) will be included.
+
+ If a 'dir' option (with or without a regex) is used and nothing
+ is found that matches, a warning will be logged.
+
+ The examples below can be used to load some solr-contribs along
+ with their external dependencies.
+ -->
+ <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
+ <!-- an exact 'path' can be used instead of a 'dir' to specify a
+ specific jar file. This will cause a serious error to be logged
+ if it can't be loaded.
+ -->
+ <!--
+ <lib path="../a-jar-that-does-not-exist.jar" />
+ -->
+
+ <!-- Data Directory
+
+ Used to specify an alternate directory to hold all index data
+ other than the default ./data under the Solr home. If
+ replication is in use, this should match the replication
+ configuration.
+ -->
+ <dataDir>${solr.data.dir:}</dataDir>
+
+
+ <!-- The DirectoryFactory to use for indexes.
+
+ solr.StandardDirectoryFactory is filesystem
+ based and tries to pick the best implementation for the current
+ JVM and platform. solr.NRTCachingDirectoryFactory, the default,
+ wraps solr.StandardDirectoryFactory and caches small files in memory
+ for better NRT performance.
+
+ One can force a particular implementation via solr.MMapDirectoryFactory,
+ solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+ solr.RAMDirectoryFactory is memory based and not persistent.
+ -->
+ <directoryFactory name="DirectoryFactory"
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
+
+ <!-- The CodecFactory for defining the format of the inverted index.
+ The default implementation is SchemaCodecFactory, which is the official Lucene
+ index format, but hooks into the schema to provide per-field customization of
+ the postings lists and per-document values in the fieldType element
+ (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+ are experimental, so if you choose to customize the index format, it's a good
+ idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+ before upgrading to a newer version to avoid unnecessary reindexing.
+ A "compressionMode" string element can be added to <codecFactory> to choose
+ between the existing compression modes in the default codec: "BEST_SPEED" (default)
+ or "BEST_COMPRESSION".
+ -->
+ <codecFactory class="solr.SchemaCodecFactory"/>
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Index Config - These settings control low-level behavior of indexing
+ Most example settings here show the default value, but are commented
+ out, to more easily see where customizations have been made.
+
+ Note: This replaces <indexDefaults> and <mainIndex> from older versions
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+ <indexConfig>
+ <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+ LimitTokenCountFilterFactory in your fieldType definition. E.g.
+ <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+ -->
+ <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+ <!-- <writeLockTimeout>1000</writeLockTimeout> -->
+
+ <!-- Expert: Enabling compound file will use less files for the index,
+ using fewer file descriptors on the expense of performance decrease.
+ Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+ <!-- <useCompoundFile>false</useCompoundFile> -->
+
+ <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+ indexing for buffering added documents and deletions before they are
+ flushed to the Directory.
+ maxBufferedDocs sets a limit on the number of documents buffered
+ before flushing.
+ If both ramBufferSizeMB and maxBufferedDocs is set, then
+ Lucene will flush based on whichever limit is hit first. -->
+ <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
+ <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+ <!-- Expert: Merge Policy
+ The Merge Policy in Lucene controls how merging of segments is done.
+ The default since Solr/Lucene 3.3 is TieredMergePolicy.
+ The default since Lucene 2.3 was the LogByteSizeMergePolicy,
+ Even older versions of Lucene used LogDocMergePolicy.
+ -->
+ <!--
+ <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
+ <int name="maxMergeAtOnce">10</int>
+ <int name="segmentsPerTier">10</int>
+ <double name="noCFSRatio">0.1</double>
+ </mergePolicyFactory>
+ -->
+
+ <!-- Expert: Merge Scheduler
+ The Merge Scheduler in Lucene controls how merges are
+ performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
+ can perform merges in the background using separate threads.
+ The SerialMergeScheduler (Lucene 2.2 default) does not.
+ -->
+ <!--
+ <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+ -->
+
+ <!-- LockFactory
+
+ This option specifies which Lucene LockFactory implementation
+ to use.
+
+ single = SingleInstanceLockFactory - suggested for a
+ read-only index or when there is no possibility of
+ another process trying to modify the index.
+ native = NativeFSLockFactory - uses OS native file locking.
+ Do not use when multiple solr webapps in the same
+ JVM are attempting to share a single index.
+ simple = SimpleFSLockFactory - uses a plain file for locking
+
+ Defaults: 'native' is default for Solr3.6 and later, otherwise
+ 'simple' is the default
+
+ More details on the nuances of each LockFactory...
+ http://wiki.apache.org/lucene-java/AvailableLockFactories
+ -->
+ <lockType>${solr.lock.type:native}</lockType>
+
+ <!-- Commit Deletion Policy
+ Custom deletion policies can be specified here. The class must
+ implement org.apache.lucene.index.IndexDeletionPolicy.
+
+ The default Solr IndexDeletionPolicy implementation supports
+ deleting index commit points on number of commits, age of
+ commit point and optimized status.
+
+ The latest commit point should always be preserved regardless
+ of the criteria.
+ -->
+ <!--
+ <deletionPolicy class="solr.SolrDeletionPolicy">
+ -->
+ <!-- The number of commit points to be kept -->
+ <!-- <str name="maxCommitsToKeep">1</str> -->
+ <!-- The number of optimized commit points to be kept -->
+ <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+ <!--
+ Delete all commit points once they have reached the given age.
+ Supports DateMathParser syntax e.g.
+ -->
+ <!--
+ <str name="maxCommitAge">30MINUTES</str>
+ <str name="maxCommitAge">1DAY</str>
+ -->
+ <!--
+ </deletionPolicy>
+ -->
+
+ <!-- Lucene Infostream
+
+ To aid in advanced debugging, Lucene provides an "InfoStream"
+ of detailed information when indexing.
+
+ Setting The value to true will instruct the underlying Lucene
+ IndexWriter to write its debugging info the specified file
+ -->
+ <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
+ </indexConfig>
+
+
+ <!-- JMX
+
+ This example enables JMX if and only if an existing MBeanServer
+ is found, use this if you want to configure JMX through JVM
+ parameters. Remove this to disable exposing Solr configuration
+ and statistics to JMX.
+
+ For more details see http://wiki.apache.org/solr/SolrJmx
+ -->
+ <jmx />
+ <!-- If you want to connect to a particular server, specify the
+ agentId
+ -->
+ <!-- <jmx agentId="myAgent" /> -->
+ <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+ <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+ -->
+
+ <!-- The default high-performance update handler -->
+ <updateHandler class="solr.DirectUpdateHandler2">
+
+ <!-- Enables a transaction log, used for real-time get, durability, and
+ and solr cloud replica recovery. The log can grow as big as
+ uncommitted changes to the index, so use of a hard autoCommit
+ is recommended (see below).
+ "dir" - the target directory for transaction logs, defaults to the
+ solr data directory.
+ "numVersionBuckets" - sets the number of buckets used to keep
+ track of max version values when checking for re-ordered
+ updates; increase this value to reduce the cost of
+ synchronizing access to version buckets during high-volume
+ indexing, this requires 8 bytes (long) * numVersionBuckets
+ of heap space per Solr core.
+ -->
+ <updateLog>
+ <str name="dir">${solr.ulog.dir:}</str>
+ <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
+ </updateLog>
+
+ <!-- AutoCommit
+
+ Perform a hard commit automatically under certain conditions.
+ Instead of enabling autoCommit, consider using "commitWithin"
+ when adding documents.
+
+ http://wiki.apache.org/solr/UpdateXmlMessages
+
+ maxDocs - Maximum number of documents to add since the last
+ commit before automatically triggering a new commit.
+
+ maxTime - Maximum amount of time in ms that is allowed to pass
+ since a document was added before automatically
+ triggering a new commit.
+ openSearcher - if false, the commit causes recent index changes
+ to be flushed to stable storage, but does not cause a new
+ searcher to be opened to make those changes visible.
+
+ If the updateLog is enabled, then it's highly recommended to
+ have some sort of hard autoCommit to limit the log size.
+ -->
+ <autoCommit>
+ <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+ <openSearcher>false</openSearcher>
+ </autoCommit>
+
+ <!-- softAutoCommit is like autoCommit except it causes a
+ 'soft' commit which only ensures that changes are visible
+ but does not ensure that data is synced to disk. This is
+ faster and more near-realtime friendly than a hard commit.
+ -->
+
+ <autoSoftCommit>
+ <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+ </autoSoftCommit>
+
+ <!-- Update Related Event Listeners
+
+ Various IndexWriter related events can trigger Listeners to
+ take actions.
+
+ postCommit - fired after every commit or optimize command
+ postOptimize - fired after every optimize command
+ -->
+ <!-- The RunExecutableListener executes an external command from a
+ hook such as postCommit or postOptimize.
+
+ exe - the name of the executable to run
+ dir - dir to use as the current working directory. (default=".")
+ wait - the calling thread waits until the executable returns.
+ (default="true")
+ args - the arguments to pass to the program. (default is none)
+ env - environment variables to set. (default is none)
+ -->
+ <!-- This example shows how RunExecutableListener could be used
+ with the script based replication...
+ http://wiki.apache.org/solr/CollectionDistribution
+ -->
+ <!--
+ <listener event="postCommit" class="solr.RunExecutableListener">
+ <str name="exe">solr/bin/snapshooter</str>
+ <str name="dir">.</str>
+ <bool name="wait">true</bool>
+ <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
+ <arr name="env"> <str>MYVAR=val1</str> </arr>
+ </listener>
+ -->
+
+ </updateHandler>
+
+ <!-- IndexReaderFactory
+
+ Use the following format to specify a custom IndexReaderFactory,
+ which allows for alternate IndexReader implementations.
+
+ ** Experimental Feature **
+
+ Please note - Using a custom IndexReaderFactory may prevent
+ certain other features from working. The API to
+ IndexReaderFactory may change without warning or may even be
+ removed from future releases if the problems cannot be
+ resolved.
+
+
+ ** Features that may not work with custom IndexReaderFactory **
+
+ The ReplicationHandler assumes a disk-resident index. Using a
+ custom IndexReader implementation may cause incompatibility
+ with ReplicationHandler and may cause replication to not work
+ correctly. See SOLR-1366 for details.
+
+ -->
+ <!--
+ <indexReaderFactory name="IndexReaderFactory" class="package.class">
+ <str name="someArg">Some Value</str>
+ </indexReaderFactory >
+ -->
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Query section - these settings control query time things like caches
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+ <query>
+ <!-- Max Boolean Clauses
+
+ Maximum number of clauses in each BooleanQuery, an exception
+ is thrown if exceeded.
+
+ ** WARNING **
+
+ This option actually modifies a global Lucene property that
+ will affect all SolrCores. If multiple solrconfig.xml files
+ disagree on this property, the value at any given moment will
+ be based on the last SolrCore to be initialized.
+
+ -->
+ <maxBooleanClauses>1024</maxBooleanClauses>
+
+
+ <!-- Solr Internal Query Caches
+
+ There are two implementations of cache available for Solr,
+ LRUCache, based on a synchronized LinkedHashMap, and
+ FastLRUCache, based on a ConcurrentHashMap.
+
+ FastLRUCache has faster gets and slower puts in single
+ threaded operation and thus is generally faster than LRUCache
+ when the hit ratio of the cache is high (> 75%), and may be
+ faster under other scenarios on multi-cpu systems.
+ -->
+
+ <!-- Filter Cache
+
+ Cache used by SolrIndexSearcher for filters (DocSets),
+ unordered sets of *all* documents that match a query. When a
+ new searcher is opened, its caches may be prepopulated or
+ "autowarmed" using data from caches in the old searcher.
+ autowarmCount is the number of items to prepopulate. For
+ LRUCache, the autowarmed items will be the most recently
+ accessed items.
+
+ Parameters:
+ class - the SolrCache implementation LRUCache or
+ (LRUCache or FastLRUCache)
+ size - the maximum number of entries in the cache
+ initialSize - the initial capacity (number of entries) of
+ the cache. (see java.util.HashMap)
+ autowarmCount - the number of entries to prepopulate from
+ and old cache.
+ maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+ to occupy. Note that when this option is specified, the size
+ and initialSize parameters are ignored.
+ -->
+ <filterCache class="solr.FastLRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- Query Result Cache
+
+ Caches results of searches - ordered lists of document ids
+ (DocList) based on a query, a sort, and the range of documents requested.
+ Additional supported parameter by LRUCache:
+ maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+ to occupy
+ -->
+ <queryResultCache class="solr.LRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- Document Cache
+
+ Caches Lucene Document objects (the stored fields for each
+ document). Since Lucene internal document ids are transient,
+ this cache will not be autowarmed.
+ -->
+ <documentCache class="solr.LRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- custom cache currently used by block join -->
+ <cache name="perSegFilter"
+ class="solr.search.LRUCache"
+ size="10"
+ initialSize="0"
+ autowarmCount="10"
+ regenerator="solr.NoOpRegenerator" />
+
+ <!-- Field Value Cache
+
+ Cache used to hold field values that are quickly accessible
+ by document id. The fieldValueCache is created by default
+ even if not configured here.
+ -->
+ <!--
+ <fieldValueCache class="solr.FastLRUCache"
+ size="512"
+ autowarmCount="128"
+ showItems="32" />
+ -->
+
+ <!-- Custom Cache
+
+ Example of a generic cache. These caches may be accessed by
+ name through SolrIndexSearcher.getCache(),cacheLookup(), and
+ cacheInsert(). The purpose is to enable easy caching of
+ user/application level data. The regenerator argument should
+ be specified as an implementation of solr.CacheRegenerator
+ if autowarming is desired.
+ -->
+ <!--
+ <cache name="myUserCache"
+ class="solr.LRUCache"
+ size="4096"
+ initialSize="1024"
+ autowarmCount="1024"
+ regenerator="com.mycompany.MyRegenerator"
+ />
+ -->
+
+
+ <!-- Lazy Field Loading
+
+ If true, stored fields that are not requested will be loaded
+ lazily. This can result in a significant speed improvement
+ if the usual case is to not load all stored fields,
+ especially if the skipped fields are large compressed text
+ fields.
+ -->
+ <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+ <!-- Use Filter For Sorted Query
+
+ A possible optimization that attempts to use a filter to
+ satisfy a search. If the requested sort does not include
+ score, then the filterCache will be checked for a filter
+ matching the query. If found, the filter will be used as the
+ source of document ids, and then the sort will be applied to
+ that.
+
+ For most situations, this will not be useful unless you
+ frequently get the same search repeatedly with different sort
+ options, and none of them ever use "score"
+ -->
+ <!--
+ <useFilterForSortedQuery>true</useFilterForSortedQuery>
+ -->
+
+ <!-- Result Window Size
+
+ An optimization for use with the queryResultCache. When a search
+ is requested, a superset of the requested number of document ids
+ are collected. For example, if a search for a particular query
+ requests matching documents 10 through 19, and queryWindowSize is 50,
+ then documents 0 through 49 will be collected and cached. Any further
+ requests in that range can be satisfied via the cache.
+ -->
+ <queryResultWindowSize>20</queryResultWindowSize>
+
+ <!-- Maximum number of documents to cache for any entry in the
+ queryResultCache.
+ -->
+ <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+ <!-- Query Related Event Listeners
+
+ Various IndexSearcher related events can trigger Listeners to
+ take actions.
+
+ newSearcher - fired whenever a new searcher is being prepared
+ and there is a current searcher handling requests (aka
+ registered). It can be used to prime certain caches to
+ prevent long request times for certain requests.
+
+ firstSearcher - fired whenever a new searcher is being
+ prepared but there is no current registered searcher to handle
+ requests or to gain autowarming data from.
+
+
+ -->
+ <!-- QuerySenderListener takes an array of NamedList and executes a
+ local query request for each NamedList in sequence.
+ -->
+ <listener event="newSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <!--
+ <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
+ <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+ -->
+ </arr>
+ </listener>
+ <listener event="firstSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <!--
+ <lst>
+ <str name="q">static firstSearcher warming in solrconfig.xml</str>
+ </lst>
+ -->
+ </arr>
+ </listener>
+
+ <!-- Use Cold Searcher
+
+ If a search request comes in and there is no current
+ registered searcher, then immediately register the still
+ warming searcher and use it. If "false" then all requests
+ will block until the first searcher is done warming.
+ -->
+ <useColdSearcher>false</useColdSearcher>
+
+ </query>
+
+
+ <!-- Request Dispatcher
+
+ This section contains instructions for how the SolrDispatchFilter
+ should behave when processing requests for this SolrCore.
+
+ handleSelect is a legacy option that affects the behavior of requests
+ such as /select?qt=XXX
+
+ handleSelect="true" will cause the SolrDispatchFilter to process
+ the request and dispatch the query to a handler specified by the
+ "qt" param, assuming "/select" isn't already registered.
+
+ handleSelect="false" will cause the SolrDispatchFilter to
+ ignore "/select" requests, resulting in a 404 unless a handler
+ is explicitly registered with the name "/select"
+
+ handleSelect="true" is not recommended for new users, but is the default
+ for backwards compatibility
+ -->
+ <requestDispatcher handleSelect="false" >
+ <!-- Request Parsing
+
+ These settings indicate how Solr Requests may be parsed, and
+ what restrictions may be placed on the ContentStreams from
+ those requests
+
+ enableRemoteStreaming - enables use of the stream.file
+ and stream.url parameters for specifying remote streams.
+
+ multipartUploadLimitInKB - specifies the max size (in KiB) of
+ Multipart File Uploads that Solr will allow in a Request.
+
+ formdataUploadLimitInKB - specifies the max size (in KiB) of
+ form data (application/x-www-form-urlencoded) sent via
+ POST. You can use POST to pass request parameters not
+ fitting into the URL.
+
+ addHttpRequestToContext - if set to true, it will instruct
+ the requestParsers to include the original HttpServletRequest
+ object in the context map of the SolrQueryRequest under the
+ key "httpRequest". It will not be used by any of the existing
+ Solr components, but may be useful when developing custom
+ plugins.
+
+ *** WARNING ***
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
+
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
+ addHttpRequestToContext="false"/>
+ -->
+
+ <!-- HTTP Caching
+
+ Set HTTP caching related parameters (for proxy caches and clients).
+
+ The options below instruct Solr not to output any HTTP Caching
+ related headers
+ -->
+ <httpCaching never304="true" />
+ <!-- If you include a <cacheControl> directive, it will be used to
+ generate a Cache-Control header (as well as an Expires header
+ if the value contains "max-age=")
+
+ By default, no Cache-Control header is generated.
+
+ You can use the <cacheControl> option even if you have set
+ never304="true"
+ -->
+ <!--
+ <httpCaching never304="true" >
+ <cacheControl>max-age=30, public</cacheControl>
+ </httpCaching>
+ -->
+ <!-- To enable Solr to respond with automatically generated HTTP
+ Caching headers, and to response to Cache Validation requests
+ correctly, set the value of never304="false"
+
+ This will cause Solr to generate Last-Modified and ETag
+ headers based on the properties of the Index.
+
+ The following options can also be specified to affect the
+ values of these headers...
+
+ lastModFrom - the default value is "openTime" which means the
+ Last-Modified value (and validation against If-Modified-Since
+ requests) will all be relative to when the current Searcher
+ was opened. You can change it to lastModFrom="dirLastMod" if
+ you want the value to exactly correspond to when the physical
+ index was last modified.
+
+ etagSeed="..." is an option you can change to force the ETag
+ header (and validation against If-None-Match requests) to be
+ different even if the index has not changed (ie: when making
+ significant changes to your config file)
+
+ (lastModifiedFrom and etagSeed are both ignored if you use
+ the never304="true" option)
+ -->
+ <!--
+ <httpCaching lastModifiedFrom="openTime"
+ etagSeed="Solr">
+ <cacheControl>max-age=30, public</cacheControl>
+ </httpCaching>
+ -->
+ </requestDispatcher>
+
+ <!-- Request Handlers
+
+ http://wiki.apache.org/solr/SolrRequestHandler
+
+ Incoming queries will be dispatched to a specific handler by name
+ based on the path specified in the request.
+
+ Legacy behavior: If the request path uses "/select" but no Request
+ Handler has that name, and if handleSelect="true" has been specified in
+ the requestDispatcher, then the Request Handler is dispatched based on
+ the qt parameter. Handlers without a leading '/' are accessed this way
+ like so: http://host/app/[core/]select?qt=name If no qt is
+ given, then the requestHandler that declares default="true" will be
+ used or the one named "standard".
+
+ If a Request Handler is declared with startup="lazy", then it will
+ not be initialized until the first request that uses it.
+
+ -->
+ <!-- SearchHandler
+
+ http://wiki.apache.org/solr/SearchHandler
+
+ For processing Search Queries, the primary Request Handler
+ provided with Solr is "SearchHandler" It delegates to a sequent
+ of SearchComponents (see below) and supports distributed
+ queries across multiple shards
+ -->
+ <requestHandler name="/select" class="solr.SearchHandler">
+ <!-- default values for query parameters can be specified, these
+ will be overridden by parameters in the request
+ -->
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <int name="rows">10</int>
+ <!-- <str name="df">text</str> -->
+ </lst>
+ <!-- In addition to defaults, "appends" params can be specified
+ to identify values which should be appended to the list of
+ multi-val params from the query (or the existing "defaults").
+ -->
+ <!-- In this example, the param "fq=instock:true" would be appended to
+ any query time fq params the user may specify, as a mechanism for
+ partitioning the index, independent of any user selected filtering
+ that may also be desired (perhaps as a result of faceted searching).
+
+ NOTE: there is *absolutely* nothing a client can do to prevent these
+ "appends" values from being used, so don't use this mechanism
+ unless you are sure you always want it.
+ -->
+ <!--
+ <lst name="appends">
+ <str name="fq">inStock:true</str>
+ </lst>
+ -->
+ <!-- "invariants" are a way of letting the Solr maintainer lock down
+ the options available to Solr clients. Any params values
+ specified here are used regardless of what values may be specified
+ in either the query, the "defaults", or the "appends" params.
+
+ In this example, the facet.field and facet.query params would
+ be fixed, limiting the facets clients can use. Faceting is
+ not turned on by default - but if the client does specify
+ facet=true in the request, these are the only facets they
+ will be able to see counts for; regardless of what other
+ facet.field or facet.query params they may specify.
+
+ NOTE: there is *absolutely* nothing a client can do to prevent these
+ "invariants" values from being used, so don't use this mechanism
+ unless you are sure you always want it.
+ -->
+ <!--
+ <lst name="invariants">
+ <str name="facet.field">cat</str>
+ <str name="facet.field">manu_exact</str>
+ <str name="facet.query">price:[* TO 500]</str>
+ <str name="facet.query">price:[500 TO *]</str>
+ </lst>
+ -->
+ <!-- If the default list of SearchComponents is not desired, that
+ list can either be overridden completely, or components can be
+ prepended or appended to the default list. (see below)
+ -->
+ <!--
+ <arr name="components">
+ <str>nameOfCustomComponent1</str>
+ <str>nameOfCustomComponent2</str>
+ </arr>
+ -->
+ </requestHandler>
+
+ <!-- A request handler that returns indented JSON by default -->
+ <requestHandler name="/query" class="solr.SearchHandler">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="wt">json</str>
+ <str name="indent">true</str>
+ </lst>
+ </requestHandler>
+
+
+ <!-- A Robust Example
+
+ This example SearchHandler declaration shows off usage of the
+ SearchHandler with many defaults declared
+
+ Note that multiple instances of the same Request Handler
+ (SearchHandler) can be registered multiple times with different
+ names (and different init parameters)
+ -->
+ <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
+ </requestHandler>
+
+ <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
+ <lst name="defaults">
+ <str name="df">_text_</str>
+ </lst>
+ </initParams>
+
+ <!-- This enabled schemaless mode
+ <initParams path="/update/**">
+ <lst name="defaults">
+ <str name="update.chain">add-unknown-fields-to-the-schema</str>
+ </lst>
+ </initParams>
+ -->
+
+ <!-- Solr Cell Update Request Handler
+
+ http://wiki.apache.org/solr/ExtractingRequestHandler
+
+ -->
+ <requestHandler name="/update/extract"
+ startup="lazy"
+ class="solr.extraction.ExtractingRequestHandler" >
+ <lst name="defaults">
+ <str name="lowernames">true</str>
+ <str name="fmap.meta">ignored_</str>
+ <str name="fmap.content">_text_</str>
+ </lst>
+ </requestHandler>
+ <!-- Search Components
+
+ Search components are registered to SolrCore and used by
+ instances of SearchHandler (which can access them by name)
+
+ By default, the following components are available:
+
+ <searchComponent name="query" class="solr.QueryComponent" />
+ <searchComponent name="facet" class="solr.FacetComponent" />
+ <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
+ <searchComponent name="highlight" class="solr.HighlightComponent" />
+ <searchComponent name="stats" class="solr.StatsComponent" />
+ <searchComponent name="debug" class="solr.DebugComponent" />
+
+ Default configuration in a requestHandler would look like:
+
+ <arr name="components">
+ <str>query</str>
+ <str>facet</str>
+ <str>mlt</str>
+ <str>highlight</str>
+ <str>stats</str>
+ <str>debug</str>
+ </arr>
+
+ If you register a searchComponent to one of the standard names,
+ that will be used instead of the default.
+
+ To insert components before or after the 'standard' components, use:
+
+ <arr name="first-components">
+ <str>myFirstComponentName</str>
+ </arr>
+
+ <arr name="last-components">
+ <str>myLastComponentName</str>
+ </arr>
+
+ NOTE: The component registered with the name "debug" will
+ always be executed after the "last-components"
+
+ -->
+
+ <!-- Spell Check
+
+ The spell check component can return a list of alternative spelling
+ suggestions.
+
+ http://wiki.apache.org/solr/SpellCheckComponent
+ -->
+ <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+ <str name="queryAnalyzerFieldType">text_general</str>
+
+ <!-- Multiple "Spell Checkers" can be declared and used by this
+ component
+ -->
+
+ <!-- a spellchecker built from a field of the main index -->
+ <lst name="spellchecker">
+ <str name="name">default</str>
+ <str name="field">_text_</str>
+ <str name="classname">solr.DirectSolrSpellChecker</str>
+ <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+ <str name="distanceMeasure">internal</str>
+ <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+ <float name="accuracy">0.5</float>
+ <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+ <int name="maxEdits">2</int>
+ <!-- the minimum shared prefix when enumerating terms -->
+ <int name="minPrefix">1</int>
+ <!-- maximum number of inspections per result. -->
+ <int name="maxInspections">5</int>
+ <!-- minimum length of a query term to be considered for correction -->
+ <int name="minQueryLength">4</int>
+ <!-- maximum threshold of documents a query term can appear to be considered for correction -->
+ <float name="maxQueryFrequency">0.01</float>
+ <!-- uncomment this to require suggestions to occur in 1% of the documents
+ <float name="thresholdTokenFrequency">.01</float>
+ -->
+ </lst>
+
+ <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
+ <!--
+ <lst name="spellchecker">
+ <str name="name">wordbreak</str>
+ <str name="classname">solr.WordBreakSolrSpellChecker</str>
+ <str name="field">name</str>
+ <str name="combineWords">true</str>
+ <str name="breakWords">true</str>
+ <int name="maxChanges">10</int>
+ </lst>
+ -->
+ </searchComponent>
+
+ <!-- A request handler for demonstrating the spellcheck component.
+
+ NOTE: This is purely as an example. The whole purpose of the
+ SpellCheckComponent is to hook it into the request handler that
+ handles your normal user queries so that a separate request is
+ not needed to get suggestions.
+
+ IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+ NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+ See http://wiki.apache.org/solr/SpellCheckComponent for details
+ on the request parameters.
+ -->
+ <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <!-- Solr will use suggestions from both the 'default' spellchecker
+ and from the 'wordbreak' spellchecker and combine them.
+ collations (re-written queries) can include a combination of
+ corrections from both spellcheckers -->
+ <str name="spellcheck.dictionary">default</str>
+ <str name="spellcheck">on</str>
+ <str name="spellcheck.extendedResults">true</str>
+ <str name="spellcheck.count">10</str>
+ <str name="spellcheck.alternativeTermCount">5</str>
+ <str name="spellcheck.maxResultsForSuggest">5</str>
+ <str name="spellcheck.collate">true</str>
+ <str name="spellcheck.collateExtendedResults">true</str>
+ <str name="spellcheck.maxCollationTries">10</str>
+ <str name="spellcheck.maxCollations">5</str>
+ </lst>
+ <arr name="last-components">
+ <str>spellcheck</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Term Vector Component
+
+ http://wiki.apache.org/solr/TermVectorComponent
+ -->
+ <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
+
+ <!-- A request handler for demonstrating the term vector component
+
+ This is purely as an example.
+
+ In reality you will likely want to add the component to your
+ already specified request handlers.
+ -->
+ <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <bool name="tv">true</bool>
+ </lst>
+ <arr name="last-components">
+ <str>tvComponent</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Clustering Component. (Omitted here. See the default Solr example for a typical configuration.) -->
+
+ <!-- Terms Component
+
+ http://wiki.apache.org/solr/TermsComponent
+
+ A component to return terms and document frequency of those
+ terms
+ -->
+ <searchComponent name="terms" class="solr.TermsComponent"/>
+
+ <!-- A request handler for demonstrating the terms component -->
+ <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <bool name="terms">true</bool>
+ <bool name="distrib">false</bool>
+ </lst>
+ <arr name="components">
+ <str>terms</str>
+ </arr>
+ </requestHandler>
+
+
+ <!-- Query Elevation Component
+
+ http://wiki.apache.org/solr/QueryElevationComponent
+
+ a search component that enables you to configure the top
+ results for a given query regardless of the normal lucene
+ scoring.
+ -->
+ <searchComponent name="elevator" class="solr.QueryElevationComponent" >
+ <!-- pick a fieldType to analyze queries -->
+ <str name="queryFieldType">string</str>
+ <str name="config-file">elevate.xml</str>
+ </searchComponent>
+
+ <!-- A request handler for demonstrating the elevator component -->
+ <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
+ <arr name="last-components">
+ <str>elevator</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Highlighting Component
+
+ http://wiki.apache.org/solr/HighlightingParameters
+ -->
+ <searchComponent class="solr.HighlightComponent" name="highlight">
+ <highlighting>
+ <!-- Configure the standard fragmenter -->
+ <!-- This could most likely be commented out in the "default" case -->
+ <fragmenter name="gap"
+ default="true"
+ class="solr.highlight.GapFragmenter">
+ <lst name="defaults">
+ <int name="hl.fragsize">100</int>
+ </lst>
+ </fragmenter>
+
+ <!-- A regular-expression-based fragmenter
+ (for sentence extraction)
+ -->
+ <fragmenter name="regex"
+ class="solr.highlight.RegexFragmenter">
+ <lst name="defaults">
+ <!-- slightly smaller fragsizes work better because of slop -->
+ <int name="hl.fragsize">70</int>
+ <!-- allow 50% slop on fragment sizes -->
+ <float name="hl.regex.slop">0.5</float>
+ <!-- a basic sentence pattern -->
+ <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
+ </lst>
+ </fragmenter>
+
+ <!-- Configure the standard formatter -->
+ <formatter name="html"
+ default="true"
+ class="solr.highlight.HtmlFormatter">
+ <lst name="defaults">
+ <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+ <str name="hl.simple.post"><![CDATA[</em>]]></str>
+ </lst>
+ </formatter>
+
+ <!-- Configure the standard encoder -->
+ <encoder name="html"
+ class="solr.highlight.HtmlEncoder" />
+
+ <!-- Configure the standard fragListBuilder -->
+ <fragListBuilder name="simple"
+ class="solr.highlight.SimpleFragListBuilder"/>
+
+ <!-- Configure the single fragListBuilder -->
+ <fragListBuilder name="single"
+ class="solr.highlight.SingleFragListBuilder"/>
+
+ <!-- Configure the weighted fragListBuilder -->
+ <fragListBuilder name="weighted"
+ default="true"
+ class="solr.highlight.WeightedFragListBuilder"/>
+
+ <!-- default tag FragmentsBuilder -->
+ <fragmentsBuilder name="default"
+ default="true"
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
+ <!--
+ <lst name="defaults">
+ <str name="hl.multiValuedSeparatorChar">/</str>
+ </lst>
+ -->
+ </fragmentsBuilder>
+
+ <!-- multi-colored tag FragmentsBuilder -->
+ <fragmentsBuilder name="colored"
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
+ <lst name="defaults">
+ <str name="hl.tag.pre"><![CDATA[
+ <b style="background:yellow">,<b style="background:lawgreen">,
+ <b style="background:aquamarine">,<b style="background:magenta">,
+ <b style="background:palegreen">,<b style="background:coral">,
+ <b style="background:wheat">,<b style="background:khaki">,
+ <b style="background:lime">,<b style="background:deepskyblue">]]></str>
+ <str name="hl.tag.post"><![CDATA[</b>]]></str>
+ </lst>
+ </fragmentsBuilder>
+
+ <boundaryScanner name="default"
+ default="true"
+ class="solr.highlight.SimpleBoundaryScanner">
+ <lst name="defaults">
+ <str name="hl.bs.maxScan">10</str>
+ <str name="hl.bs.chars">.,!? 	 </str>
+ </lst>
+ </boundaryScanner>
+
+ <boundaryScanner name="breakIterator"
+ class="solr.highlight.BreakIteratorBoundaryScanner">
+ <lst name="defaults">
+ <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
+ <str name="hl.bs.type">WORD</str>
+ <!-- language and country are used when constructing Locale object. -->
+ <!-- And the Locale object will be used when getting instance of BreakIterator -->
+ <str name="hl.bs.language">en</str>
+ <str name="hl.bs.country">US</str>
+ </lst>
+ </boundaryScanner>
+ </highlighting>
+ </searchComponent>
+
+ <!-- Update Processors
+
+ Chains of Update Processor Factories for dealing with Update
+ Requests can be declared, and then used by name in Update
+ Request Processors
+
+ http://wiki.apache.org/solr/UpdateRequestProcessor
+
+ -->
+
+ <!-- Add unknown fields to the schema
+
+ Field type guessing update processors that will
+ attempt to parse string-typed field values as Booleans, Longs,
+ Doubles, or Dates, and then add schema fields with the guessed
+ field types.
+
+ These require that the schema is both managed and mutable, by
+ declaring schemaFactory as ManagedIndexSchemaFactory, with
+ mutable specified as true.
+
+ See http://wiki.apache.org/solr/GuessingFieldTypes
+ -->
+ <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
+ <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
+ <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
+ <str name="pattern">[^\w-\.]</str>
+ <str name="replacement">_</str>
+ </updateProcessor>
+ <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
+ <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
+ <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
+ <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
+ <arr name="format">
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss</str>
+ <str>yyyy-MM-dd'T'HH:mmZ</str>
+ <str>yyyy-MM-dd'T'HH:mm</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd HH:mm:ssZ</str>
+ <str>yyyy-MM-dd HH:mm:ss</str>
+ <str>yyyy-MM-dd HH:mmZ</str>
+ <str>yyyy-MM-dd HH:mm</str>
+ <str>yyyy-MM-dd</str>
+ </arr>
+ </updateProcessor>
+ <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
+ <str name="defaultFieldType">strings</str>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Boolean</str>
+ <str name="fieldType">booleans</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.util.Date</str>
+ <str name="fieldType">tdates</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Long</str>
+ <str name="valueClass">java.lang.Integer</str>
+ <str name="fieldType">tlongs</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Number</str>
+ <str name="fieldType">tdoubles</str>
+ </lst>
+ </updateProcessor>
+
+ <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:true}"
+ processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
+ <processor class="solr.LogUpdateProcessorFactory"/>
+ <processor class="solr.DistributedUpdateProcessorFactory"/>
+ <processor class="solr.RunUpdateProcessorFactory"/>
+ </updateRequestProcessorChain>
+
+ <!-- Deduplication
+
+ An example dedup update processor that creates the "id" field
+ on the fly based on the hash code of some other fields. This
+ example has overwriteDupes set to false since we are using the
+ id field as the signatureField and Solr will maintain
+ uniqueness based on that anyway.
+
+ -->
+ <!--
+ <updateRequestProcessorChain name="dedupe">
+ <processor class="solr.processor.SignatureUpdateProcessorFactory">
+ <bool name="enabled">true</bool>
+ <str name="signatureField">id</str>
+ <bool name="overwriteDupes">false</bool>
+ <str name="fields">name,features,cat</str>
+ <str name="signatureClass">solr.processor.Lookup3Signature</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Language identification
+
+ This example update chain identifies the language of the incoming
+ documents using the langid contrib. The detected language is
+ written to field language_s. No field name mapping is done.
+ The fields used for detection are text, title, subject and description,
+ making this example suitable for detecting languages form full-text
+ rich documents injected via ExtractingRequestHandler.
+ See more about langId at http://wiki.apache.org/solr/LanguageDetection
+ -->
+ <!--
+ <updateRequestProcessorChain name="langid">
+ <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
+ <str name="langid.fl">text,title,subject,description</str>
+ <str name="langid.langField">language_s</str>
+ <str name="langid.fallback">en</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Script update processor
+
+ This example hooks in an update processor implemented using JavaScript.
+
+ See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
+ -->
+ <!--
+ <updateRequestProcessorChain name="script">
+ <processor class="solr.StatelessScriptUpdateProcessorFactory">
+ <str name="script">update-script.js</str>
+ <lst name="params">
+ <str name="config_param">example config parameter</str>
+ </lst>
+ </processor>
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Response Writers
+
+ http://wiki.apache.org/solr/QueryResponseWriter
+
+ Request responses will be written using the writer specified by
+ the 'wt' request parameter matching the name of a registered
+ writer.
+
+ The "default" writer is the default and will be used if 'wt' is
+ not specified in the request.
+ -->
+ <!-- The following response writers are implicitly configured unless
+ overridden...
+ -->
+ <!--
+ <queryResponseWriter name="xml"
+ default="true"
+ class="solr.XMLResponseWriter" />
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+ <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+ <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+ <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+ <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+ <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+ <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+ -->
+
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+ <!-- For the purposes of the tutorial, JSON responses are written as
+ plain text so that they are easy to read in *any* browser.
+ If you expect a MIME type of "application/json" just remove this override.
+ -->
+ <str name="content-type">text/plain; charset=UTF-8</str>
+ </queryResponseWriter>
+
+ <!--
+ Custom response writers can be declared as needed...
+ -->
+ <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
+ <str name="template.base.dir">${velocity.template.base.dir:}</str>
+ <str name="solr.resource.loader.enabled">${velocity.solr.resource.loader.enabled:true}</str>
+ <str name="params.resource.loader.enabled">${velocity.params.resource.loader.enabled:false}</str>
+ </queryResponseWriter>
+
+ <!-- XSLT response writer transforms the XML output by any xslt file found
+ in Solr's conf/xslt directory. Changes to xslt files are checked for
+ every xsltCacheLifetimeSeconds.
+ -->
+ <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
+ <int name="xsltCacheLifetimeSeconds">5</int>
+ </queryResponseWriter>
+
+ <!-- Query Parsers
+
+ https://cwiki.apache.org/confluence/display/solr/Query+Syntax+and+Parsing
+
+ Multiple QParserPlugins can be registered by name, and then
+ used in either the "defType" param for the QueryComponent (used
+ by SearchHandler) or in LocalParams
+ -->
+ <!-- example of registering a query parser -->
+ <!--
+ <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+ -->
+
+ <!-- Function Parsers
+
+ http://wiki.apache.org/solr/FunctionQuery
+
+ Multiple ValueSourceParsers can be registered by name, and then
+ used as function names when using the "func" QParser.
+ -->
+ <!-- example of registering a custom function parser -->
+ <!--
+ <valueSourceParser name="myfunc"
+ class="com.mycompany.MyValueSourceParser" />
+ -->
+
+
+ <!-- Document Transformers
+ http://wiki.apache.org/solr/DocTransformers
+ -->
+ <!--
+ Could be something like:
+ <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+ <int name="connection">jdbc://....</int>
+ </transformer>
+
+ To add a constant value to all docs, use:
+ <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <int name="value">5</int>
+ </transformer>
+
+ If you want the user to still be able to change it with _value:something_ use this:
+ <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <double name="defaultValue">5</double>
+ </transformer>
+
+ If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
+ EditorialMarkerFactory will do exactly that:
+ <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+ -->
+</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/stopwords.txt b/solr/server/solr/configsets/_default/conf/stopwords.txt
new file mode 100644
index 0000000..ae1e83e
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/stopwords.txt
@@ -0,0 +1,14 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/synonyms.txt b/solr/server/solr/configsets/_default/conf/synonyms.txt
new file mode 100644
index 0000000..eab4ee8
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/synonyms.txt
@@ -0,0 +1,29 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+#some test synonym mappings unlikely to appear in real input text
+aaafoo => aaabar
+bbbfoo => bbbfoo bbbbar
+cccfoo => cccbar cccbaz
+fooaaa,baraaa,bazaaa
+
+# Some synonym groups specific to this example
+GB,gib,gigabyte,gigabytes
+MB,mib,megabyte,megabytes
+Television, Televisions, TV, TVs
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
+#after us won't split it into two words.
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/currency.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/currency.xml b/solr/server/solr/configsets/basic_configs/conf/currency.xml
deleted file mode 100644
index 3a9c58a..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/currency.xml
+++ /dev/null
@@ -1,67 +0,0 @@
-<?xml version="1.0" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- Example exchange rates file for CurrencyField type named "currency" in example schema -->
-
-<currencyConfig version="1.0">
- <rates>
- <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 -->
- <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" />
- <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" />
- <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" />
- <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" />
- <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" />
- <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" />
- <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" />
- <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" />
- <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" />
- <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" />
- <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" />
- <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" />
- <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" />
- <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" />
- <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" />
- <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" />
- <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" />
- <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" />
- <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" />
- <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" />
- <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" />
- <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" />
- <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" />
- <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" />
- <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" />
- <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" />
- <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" />
- <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" />
- <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" />
- <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" />
- <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" />
- <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" />
- <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" />
- <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" />
- <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" />
- <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" />
- <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" />
-
- <!-- Cross-rates for some common currencies -->
- <rate from="EUR" to="GBP" rate="0.869914" />
- <rate from="EUR" to="NOK" rate="7.800095" />
- <rate from="GBP" to="NOK" rate="8.966508" />
- </rates>
-</currencyConfig>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/elevate.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/elevate.xml b/solr/server/solr/configsets/basic_configs/conf/elevate.xml
deleted file mode 100644
index 2c09ebe..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/elevate.xml
+++ /dev/null
@@ -1,42 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- If this file is found in the config directory, it will only be
- loaded once at startup. If it is found in Solr's data
- directory, it will be re-loaded every commit.
-
- See http://wiki.apache.org/solr/QueryElevationComponent for more info
-
--->
-<elevate>
- <!-- Query elevation examples
- <query text="foo bar">
- <doc id="1" />
- <doc id="2" />
- <doc id="3" />
- </query>
-
-for use with techproducts example
-
- <query text="ipod">
- <doc id="MA147LL/A" /> put the actual ipod at the top
- <doc id="IW-02" exclude="true" /> exclude this cable
- </query>
--->
-
-</elevate>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt
deleted file mode 100644
index 307a85f..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-# Set of Catalan contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-l
-m
-n
-s
-t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt
deleted file mode 100644
index f1bba51..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-# Set of French contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-l
-m
-t
-qu
-n
-s
-j
-d
-c
-jusqu
-quoiqu
-lorsqu
-puisqu
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt
deleted file mode 100644
index 9ebe7fa..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-# Set of Irish contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-m
-b
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt
deleted file mode 100644
index cac0409..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt
+++ /dev/null
@@ -1,23 +0,0 @@
-# Set of Italian contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-c
-l
-all
-dall
-dell
-nell
-sull
-coll
-pell
-gl
-agl
-dagl
-degl
-negl
-sugl
-un
-m
-t
-s
-v
-d
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt b/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt
deleted file mode 100644
index 4d2642c..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-# Set of Irish hyphenations for StopFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-h
-n
-t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt
deleted file mode 100644
index 4410729..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt
+++ /dev/null
@@ -1,6 +0,0 @@
-# Set of overrides for the dutch stemmer
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-fiets fiets
-bromfiets bromfiets
-ei eier
-kind kinder
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt
deleted file mode 100644
index 71b7508..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt
+++ /dev/null
@@ -1,420 +0,0 @@
-#
-# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
-#
-# Any token with a part-of-speech tag that exactly matches those defined in this
-# file are removed from the token stream.
-#
-# Set your own stoptags by uncommenting the lines below. Note that comments are
-# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
-# etc. that can be useful for building you own stoptag set.
-#
-# The entire possible tagset is provided below for convenience.
-#
-#####
-# noun: unclassified nouns
-#名詞
-#
-# noun-common: Common nouns or nouns where the sub-classification is undefined
-#名詞-一般
-#
-# noun-proper: Proper nouns where the sub-classification is undefined
-#名詞-固有名詞
-#
-# noun-proper-misc: miscellaneous proper nouns
-#名詞-固有名詞-一般
-#
-# noun-proper-person: Personal names where the sub-classification is undefined
-#名詞-固有名詞-人名
-#
-# noun-proper-person-misc: names that cannot be divided into surname and
-# given name; foreign names; names where the surname or given name is unknown.
-# e.g. お市の方
-#名詞-固有名詞-人名-一般
-#
-# noun-proper-person-surname: Mainly Japanese surnames.
-# e.g. 山田
-#名詞-固有名詞-人名-姓
-#
-# noun-proper-person-given_name: Mainly Japanese given names.
-# e.g. 太郎
-#名詞-固有名詞-人名-名
-#
-# noun-proper-organization: Names representing organizations.
-# e.g. 通産省, NHK
-#名詞-固有名詞-組織
-#
-# noun-proper-place: Place names where the sub-classification is undefined
-#名詞-固有名詞-地域
-#
-# noun-proper-place-misc: Place names excluding countries.
-# e.g. アジア, バルセロナ, 京都
-#名詞-固有名詞-地域-一般
-#
-# noun-proper-place-country: Country names.
-# e.g. 日本, オーストラリア
-#名詞-固有名詞-地域-国
-#
-# noun-pronoun: Pronouns where the sub-classification is undefined
-#名詞-代名詞
-#
-# noun-pronoun-misc: miscellaneous pronouns:
-# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
-#名詞-代名詞-一般
-#
-# noun-pronoun-contraction: Spoken language contraction made by combining a
-# pronoun and the particle 'wa'.
-# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
-#名詞-代名詞-縮約
-#
-# noun-adverbial: Temporal nouns such as names of days or months that behave
-# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
-# e.g. 金曜, 一月, 午後, 少量
-#名詞-副詞可能
-#
-# noun-verbal: Nouns that take arguments with case and can appear followed by
-# 'suru' and related verbs (する, できる, なさる, くださる)
-# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
-#名詞-サ変接続
-#
-# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
-# e.g. 健康, 安易, 駄目, だめ
-#名詞-形容動詞語幹
-#
-# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
-# e.g. 0, 1, 2, 何, 数, 幾
-#名詞-数
-#
-# noun-affix: noun affixes where the sub-classification is undefined
-#名詞-非自立
-#
-# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
-# attach to the base form of inflectional words, words that cannot be classified
-# into any of the other categories below. This category includes indefinite nouns.
-# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
-# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
-# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
-# わり, 割り, 割, ん-口語/, もん-口語/
-#名詞-非自立-一般
-#
-# noun-affix-adverbial: noun affixes that that can behave as adverbs.
-# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
-# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
-# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
-# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
-# 儘, 侭, みぎり, 矢先
-#名詞-非自立-副詞可能
-#
-# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
-# with the stem よう(だ) ("you(da)").
-# e.g. よう, やう, 様 (よう)
-#名詞-非自立-助動詞語幹
-#
-# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
-# connection form な (aux "da").
-# e.g. みたい, ふう
-#名詞-非自立-形容動詞語幹
-#
-# noun-special: special nouns where the sub-classification is undefined.
-#名詞-特殊
-#
-# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
-# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
-# form of inflectional words.
-# e.g. そう
-#名詞-特殊-助動詞語幹
-#
-# noun-suffix: noun suffixes where the sub-classification is undefined.
-#名詞-接尾
-#
-# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
-# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
-# any of the other categories below. In general, this category is more inclusive than
-# 接尾語 ("suffix") and is usually the last element in a compound noun.
-# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
-# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
-#名詞-接尾-一般
-#
-# noun-suffix-person: Suffixes that form nouns and attach to person names more often
-# than other nouns.
-# e.g. 君, 様, 著
-#名詞-接尾-人名
-#
-# noun-suffix-place: Suffixes that form nouns and attach to place names more often
-# than other nouns.
-# e.g. 町, 市, 県
-#名詞-接尾-地域
-#
-# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
-# can appear before スル ("suru").
-# e.g. 化, 視, 分け, 入り, 落ち, 買い
-#名詞-接尾-サ変接続
-#
-# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
-# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
-# conjunctive form of inflectional words.
-# e.g. そう
-#名詞-接尾-助動詞語幹
-#
-# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
-# form of inflectional words and appear before the copula だ ("da").
-# e.g. 的, げ, がち
-#名詞-接尾-形容動詞語幹
-#
-# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
-# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
-#名詞-接尾-副詞可能
-#
-# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
-# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
-# to numbers.
-# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
-#名詞-接尾-助数詞
-#
-# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
-# e.g. (楽し) さ, (考え) 方
-#名詞-接尾-特殊
-#
-# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
-# together.
-# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
-#名詞-接続詞的
-#
-# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
-# semantically verb-like.
-# e.g. ごらん, ご覧, 御覧, 頂戴
-#名詞-動詞非自立的
-#
-# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
-# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
-# is いわく ("iwaku").
-#名詞-引用文字列
-#
-# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
-# behave like an adjective.
-# e.g. 申し訳, 仕方, とんでも, 違い
-#名詞-ナイ形容詞語幹
-#
-#####
-# prefix: unclassified prefixes
-#接頭詞
-#
-# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
-# excluding numerical expressions.
-# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
-#接頭詞-名詞接続
-#
-# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
-# in conjunctive form followed by なる/なさる/くださる.
-# e.g. お (読みなさい), お (座り)
-#接頭詞-動詞接続
-#
-# prefix-adjectival: Prefixes that attach to adjectives.
-# e.g. お (寒いですねえ), バカ (でかい)
-#接頭詞-形容詞接続
-#
-# prefix-numerical: Prefixes that attach to numerical expressions.
-# e.g. 約, およそ, 毎時
-#接頭詞-数接続
-#
-#####
-# verb: unclassified verbs
-#動詞
-#
-# verb-main:
-#動詞-自立
-#
-# verb-auxiliary:
-#動詞-非自立
-#
-# verb-suffix:
-#動詞-接尾
-#
-#####
-# adjective: unclassified adjectives
-#形容詞
-#
-# adjective-main:
-#形容詞-自立
-#
-# adjective-auxiliary:
-#形容詞-非自立
-#
-# adjective-suffix:
-#形容詞-接尾
-#
-#####
-# adverb: unclassified adverbs
-#副詞
-#
-# adverb-misc: Words that can be segmented into one unit and where adnominal
-# modification is not possible.
-# e.g. あいかわらず, 多分
-#副詞-一般
-#
-# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
-# な, する, だ, etc.
-# e.g. こんなに, そんなに, あんなに, なにか, なんでも
-#副詞-助詞類接続
-#
-#####
-# adnominal: Words that only have noun-modifying forms.
-# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
-# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
-# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
-#連体詞
-#
-#####
-# conjunction: Conjunctions that can occur independently.
-# e.g. が, けれども, そして, じゃあ, それどころか
-接続詞
-#
-#####
-# particle: unclassified particles.
-助詞
-#
-# particle-case: case particles where the subclassification is undefined.
-助詞-格助詞
-#
-# particle-case-misc: Case particles.
-# e.g. から, が, で, と, に, へ, より, を, の, にて
-助詞-格助詞-一般
-#
-# particle-case-quote: the "to" that appears after nouns, a person’s speech,
-# quotation marks, expressions of decisions from a meeting, reasons, judgements,
-# conjectures, etc.
-# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
-助詞-格助詞-引用
-#
-# particle-case-compound: Compounds of particles and verbs that mainly behave
-# like case particles.
-# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
-# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
-# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
-# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
-# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
-# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
-# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
-# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
-助詞-格助詞-連語
-#
-# particle-conjunctive:
-# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
-# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
-# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
-助詞-接続助詞
-#
-# particle-dependency:
-# e.g. こそ, さえ, しか, すら, は, も, ぞ
-助詞-係助詞
-#
-# particle-adverbial:
-# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
-# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
-# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
-# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
-# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
-助詞-副助詞
-#
-# particle-interjective: particles with interjective grammatical roles.
-# e.g. (松島) や
-助詞-間投助詞
-#
-# particle-coordinate:
-# e.g. と, たり, だの, だり, とか, なり, や, やら
-助詞-並立助詞
-#
-# particle-final:
-# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
-# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
-助詞-終助詞
-#
-# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
-# adverbial, conjunctive, or sentence final. For example:
-# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
-# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
-# 「(祈りが届いたせい) か (, 試験に合格した.)」
-# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
-# e.g. か
-助詞-副助詞／並立助詞／終助詞
-#
-# particle-adnominalizer: The "no" that attaches to nouns and modifies
-# non-inflectional words.
-助詞-連体化
-#
-# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
-# that are giongo, giseigo, or gitaigo.
-# e.g. に, と
-助詞-副詞化
-#
-# particle-special: A particle that does not fit into one of the above classifications.
-# This includes particles that are used in Tanka, Haiku, and other poetry.
-# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
-助詞-特殊
-#
-#####
-# auxiliary-verb:
-助動詞
-#
-#####
-# interjection: Greetings and other exclamations.
-# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
-# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
-#感動詞
-#
-#####
-# symbol: unclassified Symbols.
-記号
-#
-# symbol-misc: A general symbol not in one of the categories below.
-# e.g. [○◎@$〒→+]
-記号-一般
-#
-# symbol-comma: Commas
-# e.g. [,、]
-記号-読点
-#
-# symbol-period: Periods and full stops.
-# e.g. [.．。]
-記号-句点
-#
-# symbol-space: Full-width whitespace.
-記号-空白
-#
-# symbol-open_bracket:
-# e.g. [({‘“『【]
-記号-括弧開
-#
-# symbol-close_bracket:
-# e.g. [)}’”』」】]
-記号-括弧閉
-#
-# symbol-alphabetic:
-#記号-アルファベット
-#
-#####
-# other: unclassified other
-#その他
-#
-# other-interjection: Words that are hard to classify as noun-suffixes or
-# sentence-final particles.
-# e.g. (だ)ァ
-その他-間投
-#
-#####
-# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
-# e.g. あの, うんと, えと
-フィラー
-#
-#####
-# non-verbal: non-verbal sound.
-非言語音
-#
-#####
-# fragment:
-#語断片
-#
-#####
-# unknown: unknown part of speech.
-#未知語
-#
-##### End of file
[31/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_id.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_id.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_id.txt
new file mode 100644
index 0000000..4617f83
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_id.txt
@@ -0,0 +1,359 @@
+# from appendix D of: A Study of Stemming Effects on Information
+# Retrieval in Bahasa Indonesia
+ada
+adanya
+adalah
+adapun
+agak
+agaknya
+agar
+akan
+akankah
+akhirnya
+aku
+akulah
+amat
+amatlah
+anda
+andalah
+antar
+diantaranya
+antara
+antaranya
+diantara
+apa
+apaan
+mengapa
+apabila
+apakah
+apalagi
+apatah
+atau
+ataukah
+ataupun
+bagai
+bagaikan
+sebagai
+sebagainya
+bagaimana
+bagaimanapun
+sebagaimana
+bagaimanakah
+bagi
+bahkan
+bahwa
+bahwasanya
+sebaliknya
+banyak
+sebanyak
+beberapa
+seberapa
+begini
+beginian
+beginikah
+beginilah
+sebegini
+begitu
+begitukah
+begitulah
+begitupun
+sebegitu
+belum
+belumlah
+sebelum
+sebelumnya
+sebenarnya
+berapa
+berapakah
+berapalah
+berapapun
+betulkah
+sebetulnya
+biasa
+biasanya
+bila
+bilakah
+bisa
+bisakah
+sebisanya
+boleh
+bolehkah
+bolehlah
+buat
+bukan
+bukankah
+bukanlah
+bukannya
+cuma
+percuma
+dahulu
+dalam
+dan
+dapat
+dari
+daripada
+dekat
+demi
+demikian
+demikianlah
+sedemikian
+dengan
+depan
+di
+dia
+dialah
+dini
+diri
+dirinya
+terdiri
+dong
+dulu
+enggak
+enggaknya
+entah
+entahlah
+terhadap
+terhadapnya
+hal
+hampir
+hanya
+hanyalah
+harus
+haruslah
+harusnya
+seharusnya
+hendak
+hendaklah
+hendaknya
+hingga
+sehingga
+ia
+ialah
+ibarat
+ingin
+inginkah
+inginkan
+ini
+inikah
+inilah
+itu
+itukah
+itulah
+jangan
+jangankan
+janganlah
+jika
+jikalau
+juga
+justru
+kala
+kalau
+kalaulah
+kalaupun
+kalian
+kami
+kamilah
+kamu
+kamulah
+kan
+kapan
+kapankah
+kapanpun
+dikarenakan
+karena
+karenanya
+ke
+kecil
+kemudian
+kenapa
+kepada
+kepadanya
+ketika
+seketika
+khususnya
+kini
+kinilah
+kiranya
+sekiranya
+kita
+kitalah
+kok
+lagi
+lagian
+selagi
+lah
+lain
+lainnya
+melainkan
+selaku
+lalu
+melalui
+terlalu
+lama
+lamanya
+selama
+selama
+selamanya
+lebih
+terlebih
+bermacam
+macam
+semacam
+maka
+makanya
+makin
+malah
+malahan
+mampu
+mampukah
+mana
+manakala
+manalagi
+masih
+masihkah
+semasih
+masing
+mau
+maupun
+semaunya
+memang
+mereka
+merekalah
+meski
+meskipun
+semula
+mungkin
+mungkinkah
+nah
+namun
+nanti
+nantinya
+nyaris
+oleh
+olehnya
+seorang
+seseorang
+pada
+padanya
+padahal
+paling
+sepanjang
+pantas
+sepantasnya
+sepantasnyalah
+para
+pasti
+pastilah
+per
+pernah
+pula
+pun
+merupakan
+rupanya
+serupa
+saat
+saatnya
+sesaat
+saja
+sajalah
+saling
+bersama
+sama
+sesama
+sambil
+sampai
+sana
+sangat
+sangatlah
+saya
+sayalah
+se
+sebab
+sebabnya
+sebuah
+tersebut
+tersebutlah
+sedang
+sedangkan
+sedikit
+sedikitnya
+segala
+segalanya
+segera
+sesegera
+sejak
+sejenak
+sekali
+sekalian
+sekalipun
+sesekali
+sekaligus
+sekarang
+sekarang
+sekitar
+sekitarnya
+sela
+selain
+selalu
+seluruh
+seluruhnya
+semakin
+sementara
+sempat
+semua
+semuanya
+sendiri
+sendirinya
+seolah
+seperti
+sepertinya
+sering
+seringnya
+serta
+siapa
+siapakah
+siapapun
+disini
+disinilah
+sini
+sinilah
+sesuatu
+sesuatunya
+suatu
+sesudah
+sesudahnya
+sudah
+sudahkah
+sudahlah
+supaya
+tadi
+tadinya
+tak
+tanpa
+setelah
+telah
+tentang
+tentu
+tentulah
+tentunya
+tertentu
+seterusnya
+tapi
+tetapi
+setiap
+tiap
+setidaknya
+tidak
+tidakkah
+tidaklah
+toh
+waduh
+wah
+wahai
+sewaktu
+walau
+walaupun
+wong
+yaitu
+yakni
+yang
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_it.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_it.txt
new file mode 100644
index 0000000..1219cc7
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_it.txt
@@ -0,0 +1,303 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | An Italian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ad | a (to) before vowel
+al | a + il
+allo | a + lo
+ai | a + i
+agli | a + gli
+all | a + l'
+agl | a + gl'
+alla | a + la
+alle | a + le
+con | with
+col | con + il
+coi | con + i (forms collo, cogli etc are now very rare)
+da | from
+dal | da + il
+dallo | da + lo
+dai | da + i
+dagli | da + gli
+dall | da + l'
+dagl | da + gll'
+dalla | da + la
+dalle | da + le
+di | of
+del | di + il
+dello | di + lo
+dei | di + i
+degli | di + gli
+dell | di + l'
+degl | di + gl'
+della | di + la
+delle | di + le
+in | in
+nel | in + el
+nello | in + lo
+nei | in + i
+negli | in + gli
+nell | in + l'
+negl | in + gl'
+nella | in + la
+nelle | in + le
+su | on
+sul | su + il
+sullo | su + lo
+sui | su + i
+sugli | su + gli
+sull | su + l'
+sugl | su + gl'
+sulla | su + la
+sulle | su + le
+per | through, by
+tra | among
+contro | against
+io | I
+tu | thou
+lui | he
+lei | she
+noi | we
+voi | you
+loro | they
+mio | my
+mia |
+miei |
+mie |
+tuo |
+tua |
+tuoi | thy
+tue |
+suo |
+sua |
+suoi | his, her
+sue |
+nostro | our
+nostra |
+nostri |
+nostre |
+vostro | your
+vostra |
+vostri |
+vostre |
+mi | me
+ti | thee
+ci | us, there
+vi | you, there
+lo | him, the
+la | her, the
+li | them
+le | them, the
+gli | to him, the
+ne | from there etc
+il | the
+un | a
+uno | a
+una | a
+ma | but
+ed | and
+se | if
+perché | why, because
+anche | also
+come | how
+dov | where (as dov')
+dove | where
+che | who, that
+chi | who
+cui | whom
+non | not
+più | more
+quale | who, that
+quanto | how much
+quanti |
+quanta |
+quante |
+quello | that
+quelli |
+quella |
+quelle |
+questo | this
+questi |
+questa |
+queste |
+si | yes
+tutto | all
+tutti | all
+
+ | single letter forms:
+
+a | at
+c | as c' for ce or ci
+e | and
+i | the
+l | as l'
+o | or
+
+ | forms of avere, to have (not including the infinitive):
+
+ho
+hai
+ha
+abbiamo
+avete
+hanno
+abbia
+abbiate
+abbiano
+avrò
+avrai
+avrà
+avremo
+avrete
+avranno
+avrei
+avresti
+avrebbe
+avremmo
+avreste
+avrebbero
+avevo
+avevi
+aveva
+avevamo
+avevate
+avevano
+ebbi
+avesti
+ebbe
+avemmo
+aveste
+ebbero
+avessi
+avesse
+avessimo
+avessero
+avendo
+avuto
+avuta
+avuti
+avute
+
+ | forms of essere, to be (not including the infinitive):
+sono
+sei
+è
+siamo
+siete
+sia
+siate
+siano
+sarò
+sarai
+sarà
+saremo
+sarete
+saranno
+sarei
+saresti
+sarebbe
+saremmo
+sareste
+sarebbero
+ero
+eri
+era
+eravamo
+eravate
+erano
+fui
+fosti
+fu
+fummo
+foste
+furono
+fossi
+fosse
+fossimo
+fossero
+essendo
+
+ | forms of fare, to do (not including the infinitive, fa, fat-):
+faccio
+fai
+facciamo
+fanno
+faccia
+facciate
+facciano
+farò
+farai
+farà
+faremo
+farete
+faranno
+farei
+faresti
+farebbe
+faremmo
+fareste
+farebbero
+facevo
+facevi
+faceva
+facevamo
+facevate
+facevano
+feci
+facesti
+fece
+facemmo
+faceste
+fecero
+facessi
+facesse
+facessimo
+facessero
+facendo
+
+ | forms of stare, to be (not including the infinitive):
+sto
+stai
+sta
+stiamo
+stanno
+stia
+stiate
+stiano
+starò
+starai
+starà
+staremo
+starete
+staranno
+starei
+staresti
+starebbe
+staremmo
+stareste
+starebbero
+stavo
+stavi
+stava
+stavamo
+stavate
+stavano
+stetti
+stesti
+stette
+stemmo
+steste
+stettero
+stessi
+stesse
+stessimo
+stessero
+stando
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ja.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ja.txt
new file mode 100644
index 0000000..d4321be
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_ja.txt
@@ -0,0 +1,127 @@
+#
+# This file defines a stopword set for Japanese.
+#
+# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
+# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
+# for frequency lists, etc. that can be useful for making your own set (if desired)
+#
+# Note that there is an overlap between these stopwords and the terms stopped when used
+# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
+# that comments are not allowed on the same line as stopwords.
+#
+# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
+# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
+# using the same character width as the entries in this file. Since this StopFilter is
+# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
+# entries to be in half-width and your kana entries to be in full-width.
+#
+の
+に
+は
+を
+た
+が
+で
+て
+と
+し
+れ
+さ
+ある
+いる
+も
+する
+から
+な
+こと
+として
+い
+や
+れる
+など
+なっ
+ない
+この
+ため
+その
+あっ
+よう
+また
+もの
+という
+あり
+まで
+られ
+なる
+へ
+か
+だ
+これ
+によって
+により
+おり
+より
+による
+ず
+なり
+られる
+において
+ば
+なかっ
+なく
+しかし
+について
+せ
+だっ
+その後
+できる
+それ
+う
+ので
+なお
+のみ
+でき
+き
+つ
+における
+および
+いう
+さらに
+でも
+ら
+たり
+その他
+に関する
+たち
+ます
+ん
+なら
+に対して
+特に
+せる
+及び
+これら
+とき
+では
+にて
+ほか
+ながら
+うち
+そして
+とともに
+ただし
+かつて
+それぞれ
+または
+お
+ほど
+ものの
+に対する
+ほとんど
+と共に
+といった
+です
+とも
+ところ
+ここ
+##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_lv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_lv.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_lv.txt
new file mode 100644
index 0000000..e21a23c
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_lv.txt
@@ -0,0 +1,172 @@
+# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
+# the original list of over 800 forms was refined:
+# pronouns, adverbs, interjections were removed
+#
+# prepositions
+aiz
+ap
+ar
+apakš
+ārpus
+augšpus
+bez
+caur
+dēļ
+gar
+iekš
+iz
+kopš
+labad
+lejpus
+līdz
+no
+otrpus
+pa
+par
+pār
+pēc
+pie
+pirms
+pret
+priekš
+starp
+šaipus
+uz
+viņpus
+virs
+virspus
+zem
+apakšpus
+# Conjunctions
+un
+bet
+jo
+ja
+ka
+lai
+tomēr
+tikko
+turpretī
+arī
+kaut
+gan
+tādēļ
+tā
+ne
+tikvien
+vien
+kā
+ir
+te
+vai
+kamēr
+# Particles
+ar
+diezin
+droši
+diemžēl
+nebūt
+ik
+it
+taču
+nu
+pat
+tiklab
+iekšpus
+nedz
+tik
+nevis
+turpretim
+jeb
+iekam
+iekām
+iekāms
+kolīdz
+līdzko
+tiklīdz
+jebšu
+tālab
+tāpēc
+nekā
+itin
+jā
+jau
+jel
+nē
+nezin
+tad
+tikai
+vis
+tak
+iekams
+vien
+# modal verbs
+būt
+biju
+biji
+bija
+bijām
+bijāt
+esmu
+esi
+esam
+esat
+būšu
+būsi
+būs
+būsim
+būsiet
+tikt
+tiku
+tiki
+tika
+tikām
+tikāt
+tieku
+tiec
+tiek
+tiekam
+tiekat
+tikšu
+tiks
+tiksim
+tiksiet
+tapt
+tapi
+tapāt
+topat
+tapšu
+tapsi
+taps
+tapsim
+tapsiet
+kļūt
+kļuvu
+kļuvi
+kļuva
+kļuvām
+kļuvāt
+kļūstu
+kļūsti
+kļūst
+kļūstam
+kļūstat
+kļūšu
+kļūsi
+kļūs
+kļūsim
+kļūsiet
+# verbs
+varēt
+varēju
+varējām
+varēšu
+varēsim
+var
+varēji
+varējāt
+varēsi
+varēsiet
+varat
+varēja
+varēs
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_nl.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_nl.txt
new file mode 100644
index 0000000..47a2aea
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_nl.txt
@@ -0,0 +1,119 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Dutch stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large sample of Dutch text.
+
+ | Dutch stop words frequently exhibit homonym clashes. These are indicated
+ | clearly below.
+
+de | the
+en | and
+van | of, from
+ik | I, the ego
+te | (1) chez, at etc, (2) to, (3) too
+dat | that, which
+die | that, those, who, which
+in | in, inside
+een | a, an, one
+hij | he
+het | the, it
+niet | not, nothing, naught
+zijn | (1) to be, being, (2) his, one's, its
+is | is
+was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
+op | on, upon, at, in, up, used up
+aan | on, upon, to (as dative)
+met | with, by
+als | like, such as, when
+voor | (1) before, in front of, (2) furrow
+had | had, past tense all persons sing. of 'hebben' (have)
+er | there
+maar | but, only
+om | round, about, for etc
+hem | him
+dan | then
+zou | should/would, past tense all persons sing. of 'zullen'
+of | or, whether, if
+wat | what, something, anything
+mijn | possessive and noun 'mine'
+men | people, 'one'
+dit | this
+zo | so, thus, in this way
+door | through by
+over | over, across
+ze | she, her, they, them
+zich | oneself
+bij | (1) a bee, (2) by, near, at
+ook | also, too
+tot | till, until
+je | you
+mij | me
+uit | out of, from
+der | Old Dutch form of 'van der' still found in surnames
+daar | (1) there, (2) because
+haar | (1) her, their, them, (2) hair
+naar | (1) unpleasant, unwell etc, (2) towards, (3) as
+heb | present first person sing. of 'to have'
+hoe | how, why
+heeft | present third person sing. of 'to have'
+hebben | 'to have' and various parts thereof
+deze | this
+u | you
+want | (1) for, (2) mitten, (3) rigging
+nog | yet, still
+zal | 'shall', first and third person sing. of verb 'zullen' (will)
+me | me
+zij | she, they
+nu | now
+ge | 'thou', still used in Belgium and south Netherlands
+geen | none
+omdat | because
+iets | something, somewhat
+worden | to become, grow, get
+toch | yet, still
+al | all, every, each
+waren | (1) 'were' (2) to wander, (3) wares, (3)
+veel | much, many
+meer | (1) more, (2) lake
+doen | to do, to make
+toen | then, when
+moet | noun 'spot/mote' and present form of 'to must'
+ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
+zonder | without
+kan | noun 'can' and present form of 'to be able'
+hun | their, them
+dus | so, consequently
+alles | all, everything, anything
+onder | under, beneath
+ja | yes, of course
+eens | once, one day
+hier | here
+wie | who
+werd | imperfect third person sing. of 'become'
+altijd | always
+doch | yet, but etc
+wordt | present third person sing. of 'become'
+wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
+kunnen | to be able
+ons | us/our
+zelf | self
+tegen | against, towards, at
+na | after, near
+reeds | already
+wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
+kon | could; past tense of 'to be able'
+niets | nothing
+uw | your
+iemand | somebody
+geweest | been; past participle of 'be'
+andere | other
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_no.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_no.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_no.txt
new file mode 100644
index 0000000..a7a2c28
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_no.txt
@@ -0,0 +1,194 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Norwegian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This stop word list is for the dominant bokmål dialect. Words unique
+ | to nynorsk are marked *.
+
+ | Revised by Jan Bruusgaard <Ja...@ssb.no>, Jan 2005
+
+og | and
+i | in
+jeg | I
+det | it/this/that
+at | to (w. inf.)
+en | a/an
+et | a/an
+den | it/this/that
+til | to
+er | is/am/are
+som | who/that
+på | on
+de | they / you(formal)
+med | with
+han | he
+av | of
+ikke | not
+ikkje | not *
+der | there
+så | so
+var | was/were
+meg | me
+seg | you
+men | but
+ett | one
+har | have
+om | about
+vi | we
+min | my
+mitt | my
+ha | have
+hadde | had
+hun | she
+nå | now
+over | over
+da | when/as
+ved | by/know
+fra | from
+du | you
+ut | out
+sin | your
+dem | them
+oss | us
+opp | up
+man | you/one
+kan | can
+hans | his
+hvor | where
+eller | or
+hva | what
+skal | shall/must
+selv | self (reflective)
+sjøl | self (reflective)
+her | here
+alle | all
+vil | will
+bli | become
+ble | became
+blei | became *
+blitt | have become
+kunne | could
+inn | in
+når | when
+være | be
+kom | come
+noen | some
+noe | some
+ville | would
+dere | you
+som | who/which/that
+deres | their/theirs
+kun | only/just
+ja | yes
+etter | after
+ned | down
+skulle | should
+denne | this
+for | for/because
+deg | you
+si | hers/his
+sine | hers/his
+sitt | hers/his
+mot | against
+å | to
+meget | much
+hvorfor | why
+dette | this
+disse | these/those
+uten | without
+hvordan | how
+ingen | none
+din | your
+ditt | your
+blir | become
+samme | same
+hvilken | which
+hvilke | which (plural)
+sånn | such a
+inni | inside/within
+mellom | between
+vår | our
+hver | each
+hvem | who
+vors | us/ours
+hvis | whose
+både | both
+bare | only/just
+enn | than
+fordi | as/because
+før | before
+mange | many
+også | also
+slik | just
+vært | been
+være | to be
+båe | both *
+begge | both
+siden | since
+dykk | your *
+dykkar | yours *
+dei | they *
+deira | them *
+deires | theirs *
+deim | them *
+di | your (fem.) *
+då | as/when *
+eg | I *
+ein | a/an *
+eit | a/an *
+eitt | a/an *
+elles | or *
+honom | he *
+hjå | at *
+ho | she *
+hoe | she *
+henne | her
+hennar | her/hers
+hennes | hers
+hoss | how *
+hossen | how *
+ikkje | not *
+ingi | noone *
+inkje | noone *
+korleis | how *
+korso | how *
+kva | what/which *
+kvar | where *
+kvarhelst | where *
+kven | who/whom *
+kvi | why *
+kvifor | why *
+me | we *
+medan | while *
+mi | my *
+mine | my *
+mykje | much *
+no | now *
+nokon | some (masc./neut.) *
+noka | some (fem.) *
+nokor | some *
+noko | some *
+nokre | some *
+si | his/hers *
+sia | since *
+sidan | since *
+so | so *
+somt | some *
+somme | some *
+um | about*
+upp | up *
+vere | be *
+vore | was *
+verte | become *
+vort | become *
+varte | became *
+vart | became *
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_pt.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_pt.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_pt.txt
new file mode 100644
index 0000000..acfeb01
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_pt.txt
@@ -0,0 +1,253 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Portuguese stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | of, from
+a | the; to, at; her
+o | the; him
+que | who, that
+e | and
+do | de + o
+da | de + a
+em | in
+um | a
+para | for
+ | é from SER
+com | with
+não | not, no
+uma | a
+os | the; them
+no | em + o
+se | himself etc
+na | em + a
+por | for
+mais | more
+as | the; them
+dos | de + os
+como | as, like
+mas | but
+ | foi from SER
+ao | a + o
+ele | he
+das | de + as
+ | tem from TER
+à | a + a
+seu | his
+sua | her
+ou | or
+ | ser from SER
+quando | when
+muito | much
+ | há from HAV
+nos | em + os; us
+já | already, now
+ | está from EST
+eu | I
+também | also
+só | only, just
+pelo | per + o
+pela | per + a
+até | up to
+isso | that
+ela | he
+entre | between
+ | era from SER
+depois | after
+sem | without
+mesmo | same
+aos | a + os
+ | ter from TER
+seus | his
+quem | whom
+nas | em + as
+me | me
+esse | that
+eles | they
+ | estão from EST
+você | you
+ | tinha from TER
+ | foram from SER
+essa | that
+num | em + um
+nem | nor
+suas | her
+meu | my
+às | a + as
+minha | my
+ | têm from TER
+numa | em + uma
+pelos | per + os
+elas | they
+ | havia from HAV
+ | seja from SER
+qual | which
+ | será from SER
+nós | we
+ | tenho from TER
+lhe | to him, her
+deles | of them
+essas | those
+esses | those
+pelas | per + as
+este | this
+ | fosse from SER
+dele | of him
+
+ | other words. There are many contractions such as naquele = em+aquele,
+ | mo = me+o, but they are rare.
+ | Indefinite article plural forms are also rare.
+
+tu | thou
+te | thee
+vocês | you (plural)
+vos | you
+lhes | to them
+meus | my
+minhas
+teu | thy
+tua
+teus
+tuas
+nosso | our
+nossa
+nossos
+nossas
+
+dela | of her
+delas | of them
+
+esta | this
+estes | these
+estas | these
+aquele | that
+aquela | that
+aqueles | those
+aquelas | those
+isto | this
+aquilo | that
+
+ | forms of estar, to be (not including the infinitive):
+estou
+está
+estamos
+estão
+estive
+esteve
+estivemos
+estiveram
+estava
+estávamos
+estavam
+estivera
+estivéramos
+esteja
+estejamos
+estejam
+estivesse
+estivéssemos
+estivessem
+estiver
+estivermos
+estiverem
+
+ | forms of haver, to have (not including the infinitive):
+hei
+há
+havemos
+hão
+houve
+houvemos
+houveram
+houvera
+houvéramos
+haja
+hajamos
+hajam
+houvesse
+houvéssemos
+houvessem
+houver
+houvermos
+houverem
+houverei
+houverá
+houveremos
+houverão
+houveria
+houveríamos
+houveriam
+
+ | forms of ser, to be (not including the infinitive):
+sou
+somos
+são
+era
+éramos
+eram
+fui
+foi
+fomos
+foram
+fora
+fôramos
+seja
+sejamos
+sejam
+fosse
+fôssemos
+fossem
+for
+formos
+forem
+serei
+será
+seremos
+serão
+seria
+seríamos
+seriam
+
+ | forms of ter, to have (not including the infinitive):
+tenho
+tem
+temos
+tém
+tinha
+tínhamos
+tinham
+tive
+teve
+tivemos
+tiveram
+tivera
+tivéramos
+tenha
+tenhamos
+tenham
+tivesse
+tivéssemos
+tivessem
+tiver
+tivermos
+tiverem
+terei
+terá
+teremos
+terão
+teria
+teríamos
+teriam
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_ro.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ro.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ro.txt
new file mode 100644
index 0000000..4fdee90
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_ro.txt
@@ -0,0 +1,233 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+acea
+aceasta
+această
+aceea
+acei
+aceia
+acel
+acela
+acele
+acelea
+acest
+acesta
+aceste
+acestea
+aceşti
+aceştia
+acolo
+acum
+ai
+aia
+aibă
+aici
+al
+ăla
+ale
+alea
+ălea
+altceva
+altcineva
+am
+ar
+are
+aş
+aşadar
+asemenea
+asta
+ăsta
+astăzi
+astea
+ăstea
+ăştia
+asupra
+aţi
+au
+avea
+avem
+aveţi
+azi
+bine
+bucur
+bună
+ca
+că
+căci
+când
+care
+cărei
+căror
+cărui
+cât
+câte
+câţi
+către
+câtva
+ce
+cel
+ceva
+chiar
+cînd
+cine
+cineva
+cît
+cîte
+cîţi
+cîtva
+contra
+cu
+cum
+cumva
+curând
+curînd
+da
+dă
+dacă
+dar
+datorită
+de
+deci
+deja
+deoarece
+departe
+deşi
+din
+dinaintea
+dintr
+dintre
+drept
+după
+ea
+ei
+el
+ele
+eram
+este
+eşti
+eu
+face
+fără
+fi
+fie
+fiecare
+fii
+fim
+fiţi
+iar
+ieri
+îi
+îl
+îmi
+împotriva
+în
+înainte
+înaintea
+încât
+încît
+încotro
+între
+întrucât
+întrucît
+îţi
+la
+lângă
+le
+li
+lîngă
+lor
+lui
+mă
+mâine
+mea
+mei
+mele
+mereu
+meu
+mi
+mine
+mult
+multă
+mulţi
+ne
+nicăieri
+nici
+nimeni
+nişte
+noastră
+noastre
+noi
+noştri
+nostru
+nu
+ori
+oricând
+oricare
+oricât
+orice
+oricînd
+oricine
+oricît
+oricum
+oriunde
+până
+pe
+pentru
+peste
+pînă
+poate
+pot
+prea
+prima
+primul
+prin
+printr
+sa
+să
+săi
+sale
+sau
+său
+se
+şi
+sînt
+sîntem
+sînteţi
+spre
+sub
+sunt
+suntem
+sunteţi
+ta
+tăi
+tale
+tău
+te
+ţi
+ţie
+tine
+toată
+toate
+tot
+toţi
+totuşi
+tu
+un
+una
+unde
+undeva
+unei
+unele
+uneori
+unor
+vă
+vi
+voastră
+voastre
+voi
+voştri
+vostru
+vouă
+vreo
+vreun
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_ru.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ru.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ru.txt
new file mode 100644
index 0000000..5527140
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_ru.txt
@@ -0,0 +1,243 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | a russian stop word list. comments begin with vertical bar. each stop
+ | word is at the start of a line.
+
+ | this is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | letter `ё' is translated to `е'.
+
+и | and
+в | in/into
+во | alternative form
+не | not
+что | what/that
+он | he
+на | on/onto
+я | i
+с | from
+со | alternative form
+как | how
+а | milder form of `no' (but)
+то | conjunction and form of `that'
+все | all
+она | she
+так | so, thus
+его | him
+но | but
+да | yes/and
+ты | thou
+к | towards, by
+у | around, chez
+же | intensifier particle
+вы | you
+за | beyond, behind
+бы | conditional/subj. particle
+по | up to, along
+только | only
+ее | her
+мне | to me
+было | it was
+вот | here is/are, particle
+от | away from
+меня | me
+еще | still, yet, more
+нет | no, there isnt/arent
+о | about
+из | out of
+ему | to him
+теперь | now
+когда | when
+даже | even
+ну | so, well
+вдруг | suddenly
+ли | interrogative particle
+если | if
+уже | already, but homonym of `narrower'
+или | or
+ни | neither
+быть | to be
+был | he was
+него | prepositional form of его
+до | up to
+вас | you accusative
+нибудь | indef. suffix preceded by hyphen
+опять | again
+уж | already, but homonym of `adder'
+вам | to you
+сказал | he said
+ведь | particle `after all'
+там | there
+потом | then
+себя | oneself
+ничего | nothing
+ей | to her
+может | usually with `быть' as `maybe'
+они | they
+тут | here
+где | where
+есть | there is/are
+надо | got to, must
+ней | prepositional form of ей
+для | for
+мы | we
+тебя | thee
+их | them, their
+чем | than
+была | she was
+сам | self
+чтоб | in order to
+без | without
+будто | as if
+человек | man, person, one
+чего | genitive form of `what'
+раз | once
+тоже | also
+себе | to oneself
+под | beneath
+жизнь | life
+будет | will be
+ж | short form of intensifer particle `же'
+тогда | then
+кто | who
+этот | this
+говорил | was saying
+того | genitive form of `that'
+потому | for that reason
+этого | genitive form of `this'
+какой | which
+совсем | altogether
+ним | prepositional form of `его', `они'
+здесь | here
+этом | prepositional form of `этот'
+один | one
+почти | almost
+мой | my
+тем | instrumental/dative plural of `тот', `то'
+чтобы | full form of `in order that'
+нее | her (acc.)
+кажется | it seems
+сейчас | now
+были | they were
+куда | where to
+зачем | why
+сказать | to say
+всех | all (acc., gen. preposn. plural)
+никогда | never
+сегодня | today
+можно | possible, one can
+при | by
+наконец | finally
+два | two
+об | alternative form of `о', about
+другой | another
+хоть | even
+после | after
+над | above
+больше | more
+тот | that one (masc.)
+через | across, in
+эти | these
+нас | us
+про | about
+всего | in all, only, of all
+них | prepositional form of `они' (they)
+какая | which, feminine
+много | lots
+разве | interrogative particle
+сказала | she said
+три | three
+эту | this, acc. fem. sing.
+моя | my, feminine
+впрочем | moreover, besides
+хорошо | good
+свою | ones own, acc. fem. sing.
+этой | oblique form of `эта', fem. `this'
+перед | in front of
+иногда | sometimes
+лучше | better
+чуть | a little
+том | preposn. form of `that one'
+нельзя | one must not
+такой | such a one
+им | to them
+более | more
+всегда | always
+конечно | of course
+всю | acc. fem. sing of `all'
+между | between
+
+
+ | b: some paradigms
+ |
+ | personal pronouns
+ |
+ | я меня мне мной [мною]
+ | ты тебя тебе тобой [тобою]
+ | он его ему им [него, нему, ним]
+ | она ее эи ею [нее, нэи, нею]
+ | оно его ему им [него, нему, ним]
+ |
+ | мы нас нам нами
+ | вы вас вам вами
+ | они их им ими [них, ним, ними]
+ |
+ | себя себе собой [собою]
+ |
+ | demonstrative pronouns: этот (this), тот (that)
+ |
+ | этот эта это эти
+ | этого эты это эти
+ | этого этой этого этих
+ | этому этой этому этим
+ | этим этой этим [этою] этими
+ | этом этой этом этих
+ |
+ | тот та то те
+ | того ту то те
+ | того той того тех
+ | тому той тому тем
+ | тем той тем [тою] теми
+ | том той том тех
+ |
+ | determinative pronouns
+ |
+ | (a) весь (all)
+ |
+ | весь вся все все
+ | всего всю все все
+ | всего всей всего всех
+ | всему всей всему всем
+ | всем всей всем [всею] всеми
+ | всем всей всем всех
+ |
+ | (b) сам (himself etc)
+ |
+ | сам сама само сами
+ | самого саму само самих
+ | самого самой самого самих
+ | самому самой самому самим
+ | самим самой самим [самою] самими
+ | самом самой самом самих
+ |
+ | stems of verbs `to be', `to have', `to do' and modal
+ |
+ | быть бы буд быв есть суть
+ | име
+ | дел
+ | мог мож мочь
+ | уме
+ | хоч хот
+ | долж
+ | можн
+ | нужн
+ | нельзя
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_sv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_sv.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_sv.txt
new file mode 100644
index 0000000..096f87f
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_sv.txt
@@ -0,0 +1,133 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Swedish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | Swedish stop words occasionally exhibit homonym clashes. For example
+ | så = so, but also seed. These are indicated clearly below.
+
+och | and
+det | it, this/that
+att | to (with infinitive)
+i | in, at
+en | a
+jag | I
+hon | she
+som | who, that
+han | he
+på | on
+den | it, this/that
+med | with
+var | where, each
+sig | him(self) etc
+för | for
+så | so (also: seed)
+till | to
+är | is
+men | but
+ett | a
+om | if; around, about
+hade | had
+de | they, these/those
+av | of
+icke | not, no
+mig | me
+du | you
+henne | her
+då | then, when
+sin | his
+nu | now
+har | have
+inte | inte någon = no one
+hans | his
+honom | him
+skulle | 'sake'
+hennes | her
+där | there
+min | my
+man | one (pronoun)
+ej | nor
+vid | at, by, on (also: vast)
+kunde | could
+något | some etc
+från | from, off
+ut | out
+när | when
+efter | after, behind
+upp | up
+vi | we
+dem | them
+vara | be
+vad | what
+över | over
+än | than
+dig | you
+kan | can
+sina | his
+här | here
+ha | have
+mot | towards
+alla | all
+under | under (also: wonder)
+någon | some etc
+eller | or (else)
+allt | all
+mycket | much
+sedan | since
+ju | why
+denna | this/that
+själv | myself, yourself etc
+detta | this/that
+åt | to
+utan | without
+varit | was
+hur | how
+ingen | no
+mitt | my
+ni | you
+bli | to be, become
+blev | from bli
+oss | us
+din | thy
+dessa | these/those
+några | some etc
+deras | their
+blir | from bli
+mina | my
+samma | (the) same
+vilken | who, that
+er | you, your
+sådan | such a
+vår | our
+blivit | from bli
+dess | its
+inom | within
+mellan | between
+sådant | such a
+varför | why
+varje | each
+vilka | who, that
+ditt | thy
+vem | who
+vilket | who, that
+sitta | his
+sådana | such a
+vart | each
+dina | thy
+vars | whose
+vårt | our
+våra | our
+ert | your
+era | your
+vilkas | whose
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_th.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_th.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_th.txt
new file mode 100644
index 0000000..07f0fab
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_th.txt
@@ -0,0 +1,119 @@
+# Thai stopwords from:
+# "Opinion Detection in Thai Political News Columns
+# Based on Subjectivity Analysis"
+# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
+ไว้
+ไม่
+ไป
+ได้
+ให้
+ใน
+โดย
+แห่ง
+แล้ว
+และ
+แรก
+แบบ
+แต่
+เอง
+เห็น
+เลย
+เริ่ม
+เรา
+เมื่อ
+เพื่อ
+เพราะ
+เป็นการ
+เป็น
+เปิดเผย
+เปิด
+เนื่องจาก
+เดียวกัน
+เดียว
+เช่น
+เฉพาะ
+เคย
+เข้า
+เขา
+อีก
+อาจ
+อะไร
+ออก
+อย่าง
+อยู่
+อยาก
+หาก
+หลาย
+หลังจาก
+หลัง
+หรือ
+หนึ่ง
+ส่วน
+ส่ง
+สุด
+สําหรับ
+ว่า
+วัน
+ลง
+ร่วม
+ราย
+รับ
+ระหว่าง
+รวม
+ยัง
+มี
+มาก
+มา
+พร้อม
+พบ
+ผ่าน
+ผล
+บาง
+น่า
+นี้
+นํา
+นั้น
+นัก
+นอกจาก
+ทุก
+ที่สุด
+ที่
+ทําให้
+ทํา
+ทาง
+ทั้งนี้
+ทั้ง
+ถ้า
+ถูก
+ถึง
+ต้อง
+ต่างๆ
+ต่าง
+ต่อ
+ตาม
+ตั้งแต่
+ตั้ง
+ด้าน
+ด้วย
+ดัง
+ซึ่ง
+ช่วง
+จึง
+จาก
+จัด
+จะ
+คือ
+ความ
+ครั้ง
+คง
+ขึ้น
+ของ
+ขอ
+ขณะ
+ก่อน
+ก็
+การ
+กับ
+กัน
+กว่า
+กล่าว
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/stopwords_tr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_tr.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_tr.txt
new file mode 100644
index 0000000..84d9408
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/stopwords_tr.txt
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+altmış
+altı
+ama
+ancak
+arada
+aslında
+ayrıca
+bana
+bazı
+belki
+ben
+benden
+beni
+benim
+beri
+beş
+bile
+bin
+bir
+birçok
+biri
+birkaç
+birkez
+birşey
+birşeyi
+biz
+bize
+bizden
+bizi
+bizim
+böyle
+böylece
+bu
+buna
+bunda
+bundan
+bunlar
+bunları
+bunların
+bunu
+bunun
+burada
+çok
+çünkü
+da
+daha
+dahi
+de
+defa
+değil
+diğer
+diye
+doksan
+dokuz
+dolayı
+dolayısıyla
+dört
+edecek
+eden
+ederek
+edilecek
+ediliyor
+edilmesi
+ediyor
+eğer
+elli
+en
+etmesi
+etti
+ettiği
+ettiğini
+gibi
+göre
+halen
+hangi
+hatta
+hem
+henüz
+hep
+hepsi
+her
+herhangi
+herkesin
+hiç
+hiçbir
+için
+iki
+ile
+ilgili
+ise
+işte
+itibaren
+itibariyle
+kadar
+karşın
+katrilyon
+kendi
+kendilerine
+kendini
+kendisi
+kendisine
+kendisini
+kez
+ki
+kim
+kimden
+kime
+kimi
+kimse
+kırk
+milyar
+milyon
+mu
+mü
+mı
+nasıl
+ne
+neden
+nedenle
+nerde
+nerede
+nereye
+niye
+niçin
+o
+olan
+olarak
+oldu
+olduğu
+olduğunu
+olduklarını
+olmadı
+olmadığı
+olmak
+olması
+olmayan
+olmaz
+olsa
+olsun
+olup
+olur
+olursa
+oluyor
+on
+ona
+ondan
+onlar
+onlardan
+onları
+onların
+onu
+onun
+otuz
+oysa
+öyle
+pek
+rağmen
+sadece
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+şey
+şeyden
+şeyi
+şeyler
+şöyle
+şu
+şuna
+şunda
+şundan
+şunları
+şunu
+tarafından
+trilyon
+tüm
+üç
+üzere
+var
+vardı
+ve
+veya
+ya
+yani
+yapacak
+yapılan
+yapılması
+yapıyor
+yapmak
+yaptı
+yaptığı
+yaptığını
+yaptıkları
+yedi
+yerine
+yetmiş
+yine
+yirmi
+yoksa
+yüz
+zaten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/_default/conf/lang/userdict_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/userdict_ja.txt b/solr/server/solr/configsets/_default/conf/lang/userdict_ja.txt
new file mode 100644
index 0000000..6f0368e
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/lang/userdict_ja.txt
@@ -0,0 +1,29 @@
+#
+# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
+#
+# Add entries to this file in order to override the statistical model in terms
+# of segmentation, readings and part-of-speech tags. Notice that entries do
+# not have weights since they are always used when found. This is by-design
+# in order to maximize ease-of-use.
+#
+# Entries are defined using the following CSV format:
+# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
+#
+# Notice that a single half-width space separates tokens and readings, and
+# that the number tokens and readings must match exactly.
+#
+# Also notice that multiple entries with the same <text> is undefined.
+#
+# Whitespace only lines are ignored. Comments are not allowed on entry lines.
+#
+
+# Custom segmentation for kanji compounds
+日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
+関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
+
+# Custom segmentation for compound katakana
+トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
+ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
+
+# Custom reading for former sumo wrestler
+朝青龍,朝青龍,アサショウリュウ,カスタム人名
[48/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
SOLR-10574: Reverting previous commits to tackle test failues
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/1a58412e
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/1a58412e
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/1a58412e
Branch: refs/heads/feature/autoscaling
Commit: 1a58412e4ac9ff85f82696da8f3b0597ca45617e
Parents: a4f27bb
Author: Ishan Chattopadhyaya <is...@apache.org>
Authored: Tue Jun 20 23:14:24 2017 +0000
Committer: Ishan Chattopadhyaya <is...@apache.org>
Committed: Tue Jun 20 23:14:24 2017 +0000
----------------------------------------------------------------------
solr/CHANGES.txt | 8 -
solr/bin/solr | 11 +-
.../solr/configsets/_default/conf/currency.xml | 67 -
.../solr/configsets/_default/conf/elevate.xml | 42 -
.../_default/conf/lang/contractions_ca.txt | 8 -
.../_default/conf/lang/contractions_fr.txt | 15 -
.../_default/conf/lang/contractions_ga.txt | 5 -
.../_default/conf/lang/contractions_it.txt | 23 -
.../_default/conf/lang/hyphenations_ga.txt | 5 -
.../_default/conf/lang/stemdict_nl.txt | 6 -
.../_default/conf/lang/stoptags_ja.txt | 420 ------
.../_default/conf/lang/stopwords_ar.txt | 125 --
.../_default/conf/lang/stopwords_bg.txt | 193 ---
.../_default/conf/lang/stopwords_ca.txt | 220 ---
.../_default/conf/lang/stopwords_cz.txt | 172 ---
.../_default/conf/lang/stopwords_da.txt | 110 --
.../_default/conf/lang/stopwords_de.txt | 294 ----
.../_default/conf/lang/stopwords_el.txt | 78 -
.../_default/conf/lang/stopwords_en.txt | 54 -
.../_default/conf/lang/stopwords_es.txt | 356 -----
.../_default/conf/lang/stopwords_eu.txt | 99 --
.../_default/conf/lang/stopwords_fa.txt | 313 ----
.../_default/conf/lang/stopwords_fi.txt | 97 --
.../_default/conf/lang/stopwords_fr.txt | 186 ---
.../_default/conf/lang/stopwords_ga.txt | 110 --
.../_default/conf/lang/stopwords_gl.txt | 161 --
.../_default/conf/lang/stopwords_hi.txt | 235 ---
.../_default/conf/lang/stopwords_hu.txt | 211 ---
.../_default/conf/lang/stopwords_hy.txt | 46 -
.../_default/conf/lang/stopwords_id.txt | 359 -----
.../_default/conf/lang/stopwords_it.txt | 303 ----
.../_default/conf/lang/stopwords_ja.txt | 127 --
.../_default/conf/lang/stopwords_lv.txt | 172 ---
.../_default/conf/lang/stopwords_nl.txt | 119 --
.../_default/conf/lang/stopwords_no.txt | 194 ---
.../_default/conf/lang/stopwords_pt.txt | 253 ----
.../_default/conf/lang/stopwords_ro.txt | 233 ---
.../_default/conf/lang/stopwords_ru.txt | 243 ---
.../_default/conf/lang/stopwords_sv.txt | 133 --
.../_default/conf/lang/stopwords_th.txt | 119 --
.../_default/conf/lang/stopwords_tr.txt | 212 ---
.../_default/conf/lang/userdict_ja.txt | 29 -
.../configsets/_default/conf/managed-schema | 1069 -------------
.../solr/configsets/_default/conf/params.json | 20 -
.../solr/configsets/_default/conf/protwords.txt | 21 -
.../configsets/_default/conf/solrconfig.xml | 1408 ------------------
.../solr/configsets/_default/conf/stopwords.txt | 14 -
.../solr/configsets/_default/conf/synonyms.txt | 29 -
.../configsets/basic_configs/conf/currency.xml | 67 +
.../configsets/basic_configs/conf/elevate.xml | 42 +
.../basic_configs/conf/lang/contractions_ca.txt | 8 +
.../basic_configs/conf/lang/contractions_fr.txt | 15 +
.../basic_configs/conf/lang/contractions_ga.txt | 5 +
.../basic_configs/conf/lang/contractions_it.txt | 23 +
.../basic_configs/conf/lang/hyphenations_ga.txt | 5 +
.../basic_configs/conf/lang/stemdict_nl.txt | 6 +
.../basic_configs/conf/lang/stoptags_ja.txt | 420 ++++++
.../basic_configs/conf/lang/stopwords_ar.txt | 125 ++
.../basic_configs/conf/lang/stopwords_bg.txt | 193 +++
.../basic_configs/conf/lang/stopwords_ca.txt | 220 +++
.../basic_configs/conf/lang/stopwords_cz.txt | 172 +++
.../basic_configs/conf/lang/stopwords_da.txt | 110 ++
.../basic_configs/conf/lang/stopwords_de.txt | 294 ++++
.../basic_configs/conf/lang/stopwords_el.txt | 78 +
.../basic_configs/conf/lang/stopwords_en.txt | 54 +
.../basic_configs/conf/lang/stopwords_es.txt | 356 +++++
.../basic_configs/conf/lang/stopwords_eu.txt | 99 ++
.../basic_configs/conf/lang/stopwords_fa.txt | 313 ++++
.../basic_configs/conf/lang/stopwords_fi.txt | 97 ++
.../basic_configs/conf/lang/stopwords_fr.txt | 186 +++
.../basic_configs/conf/lang/stopwords_ga.txt | 110 ++
.../basic_configs/conf/lang/stopwords_gl.txt | 161 ++
.../basic_configs/conf/lang/stopwords_hi.txt | 235 +++
.../basic_configs/conf/lang/stopwords_hu.txt | 211 +++
.../basic_configs/conf/lang/stopwords_hy.txt | 46 +
.../basic_configs/conf/lang/stopwords_id.txt | 359 +++++
.../basic_configs/conf/lang/stopwords_it.txt | 303 ++++
.../basic_configs/conf/lang/stopwords_ja.txt | 127 ++
.../basic_configs/conf/lang/stopwords_lv.txt | 172 +++
.../basic_configs/conf/lang/stopwords_nl.txt | 119 ++
.../basic_configs/conf/lang/stopwords_no.txt | 194 +++
.../basic_configs/conf/lang/stopwords_pt.txt | 253 ++++
.../basic_configs/conf/lang/stopwords_ro.txt | 233 +++
.../basic_configs/conf/lang/stopwords_ru.txt | 243 +++
.../basic_configs/conf/lang/stopwords_sv.txt | 133 ++
.../basic_configs/conf/lang/stopwords_th.txt | 119 ++
.../basic_configs/conf/lang/stopwords_tr.txt | 212 +++
.../basic_configs/conf/lang/userdict_ja.txt | 29 +
.../basic_configs/conf/managed-schema | 1045 +++++++++++++
.../configsets/basic_configs/conf/params.json | 20 +
.../configsets/basic_configs/conf/protwords.txt | 21 +
.../basic_configs/conf/solrconfig.xml | 1408 ++++++++++++++++++
.../configsets/basic_configs/conf/stopwords.txt | 14 +
.../configsets/basic_configs/conf/synonyms.txt | 29 +
.../conf/currency.xml | 67 +
.../data_driven_schema_configs/conf/elevate.xml | 42 +
.../conf/lang/contractions_ca.txt | 8 +
.../conf/lang/contractions_fr.txt | 15 +
.../conf/lang/contractions_ga.txt | 5 +
.../conf/lang/contractions_it.txt | 23 +
.../conf/lang/hyphenations_ga.txt | 5 +
.../conf/lang/stemdict_nl.txt | 6 +
.../conf/lang/stoptags_ja.txt | 420 ++++++
.../conf/lang/stopwords_ar.txt | 125 ++
.../conf/lang/stopwords_bg.txt | 193 +++
.../conf/lang/stopwords_ca.txt | 220 +++
.../conf/lang/stopwords_cz.txt | 172 +++
.../conf/lang/stopwords_da.txt | 110 ++
.../conf/lang/stopwords_de.txt | 294 ++++
.../conf/lang/stopwords_el.txt | 78 +
.../conf/lang/stopwords_en.txt | 54 +
.../conf/lang/stopwords_es.txt | 356 +++++
.../conf/lang/stopwords_eu.txt | 99 ++
.../conf/lang/stopwords_fa.txt | 313 ++++
.../conf/lang/stopwords_fi.txt | 97 ++
.../conf/lang/stopwords_fr.txt | 186 +++
.../conf/lang/stopwords_ga.txt | 110 ++
.../conf/lang/stopwords_gl.txt | 161 ++
.../conf/lang/stopwords_hi.txt | 235 +++
.../conf/lang/stopwords_hu.txt | 211 +++
.../conf/lang/stopwords_hy.txt | 46 +
.../conf/lang/stopwords_id.txt | 359 +++++
.../conf/lang/stopwords_it.txt | 303 ++++
.../conf/lang/stopwords_ja.txt | 127 ++
.../conf/lang/stopwords_lv.txt | 172 +++
.../conf/lang/stopwords_nl.txt | 119 ++
.../conf/lang/stopwords_no.txt | 194 +++
.../conf/lang/stopwords_pt.txt | 253 ++++
.../conf/lang/stopwords_ro.txt | 233 +++
.../conf/lang/stopwords_ru.txt | 243 +++
.../conf/lang/stopwords_sv.txt | 133 ++
.../conf/lang/stopwords_th.txt | 119 ++
.../conf/lang/stopwords_tr.txt | 212 +++
.../conf/lang/userdict_ja.txt | 29 +
.../conf/managed-schema | 1069 +++++++++++++
.../data_driven_schema_configs/conf/params.json | 20 +
.../conf/protwords.txt | 21 +
.../conf/solrconfig.xml | 1406 +++++++++++++++++
.../conf/stopwords.txt | 14 +
.../conf/synonyms.txt | 29 +
140 files changed, 17396 insertions(+), 8721 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index a201d1e..f15fa45 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -97,11 +97,6 @@ Upgrading from Solr 6.x
* SOLR-9565: The name of TemplateUpdateRequestProcessorFactory' is changed to 'template' from 'Template' and the
name of 'AtomicUpdateProcessorFactory' is changed to 'atomic' from 'Atomic'
-* SOLR-10574: basic_configs and data_driven_schema_configs have now been merged into _default. It has data driven nature
- enabled by default, and can be turned off (after creating a collection) with:
- curl http://host:8983/solr/mycollection/config -d '{"set-user-property": {"update.autoCreateFields":"false"}}'
- Please see SOLR-10574 for details.
-
* The default for eDismax parameter 'lowercaseOperators' now depends on the luceneMatchVersion setting in solrconfig.
It remains 'true' for luceneMatchVersion < 7.0.0 and changes to 'false' from 7.0.0. See also SOLR-4646
@@ -159,9 +154,6 @@ New Features
* SOLR-10406: v2 API error messages list the URL request path as /solr/____v2/... when the original path was /v2/... (Cao Manh Dat, noble)
-* SOLR-10574: New _default config set replacing basic_configs and data_driven_schema_configs.
- (Ishan Chattopadhyaya, noble, shalin, hossman, David Smiley, Jan Hoydahl, Alexandre Rafalovich)
-
Bug Fixes
----------------------
* SOLR-9262: Connection and read timeouts are being ignored by UpdateShardHandler after SOLR-4509.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/bin/solr
----------------------------------------------------------------------
diff --git a/solr/bin/solr b/solr/bin/solr
index a22ef93..cd50828 100755
--- a/solr/bin/solr
+++ b/solr/bin/solr
@@ -419,11 +419,12 @@ function print_usage() {
echo ""
echo " -d <confdir> Configuration directory to copy when creating the new core, built-in options are:"
echo ""
- echo " _default: Minimal configuration, which supports enabling/disabling field-guessing support"
+ echo " basic_configs: Minimal Solr configuration"
+ echo " data_driven_schema_configs: Managed schema with field-guessing support enabled"
echo " sample_techproducts_configs: Example configuration with many optional features enabled to"
echo " demonstrate the full power of Solr"
echo ""
- echo " If not specified, default is: _default"
+ echo " If not specified, default is: data_driven_schema_configs"
echo ""
echo " Alternatively, you can pass the path to your own configuration directory instead of using"
echo " one of the built-in configurations, such as: bin/solr create_core -c mycore -d /tmp/myconfig"
@@ -440,12 +441,12 @@ function print_usage() {
echo ""
echo " -d <confdir> Configuration directory to copy when creating the new collection, built-in options are:"
echo ""
- echo " _default: Minimal configuration, which supports enabling/disabling field-guessing support"
+ echo " basic_configs: Minimal Solr configuration"
echo " data_driven_schema_configs: Managed schema with field-guessing support enabled"
echo " sample_techproducts_configs: Example configuration with many optional features enabled to"
echo " demonstrate the full power of Solr"
echo ""
- echo " If not specified, default is: _default"
+ echo " If not specified, default is: data_driven_schema_configs"
echo ""
echo " Alternatively, you can pass the path to your own configuration directory instead of using"
echo " one of the built-in configurations, such as: bin/solr create_collection -c mycoll -d /tmp/myconfig"
@@ -934,7 +935,7 @@ if [[ "$SCRIPT_CMD" == "create" || "$SCRIPT_CMD" == "create_core" || "$SCRIPT_CM
fi
if [ -z "$CREATE_CONFDIR" ]; then
- CREATE_CONFDIR='_default'
+ CREATE_CONFDIR='data_driven_schema_configs'
fi
# validate the confdir arg
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/currency.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/currency.xml b/solr/server/solr/configsets/_default/conf/currency.xml
deleted file mode 100644
index 3a9c58a..0000000
--- a/solr/server/solr/configsets/_default/conf/currency.xml
+++ /dev/null
@@ -1,67 +0,0 @@
-<?xml version="1.0" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- Example exchange rates file for CurrencyField type named "currency" in example schema -->
-
-<currencyConfig version="1.0">
- <rates>
- <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 -->
- <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" />
- <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" />
- <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" />
- <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" />
- <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" />
- <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" />
- <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" />
- <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" />
- <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" />
- <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" />
- <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" />
- <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" />
- <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" />
- <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" />
- <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" />
- <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" />
- <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" />
- <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" />
- <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" />
- <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" />
- <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" />
- <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" />
- <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" />
- <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" />
- <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" />
- <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" />
- <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" />
- <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" />
- <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" />
- <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" />
- <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" />
- <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" />
- <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" />
- <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" />
- <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" />
- <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" />
- <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" />
-
- <!-- Cross-rates for some common currencies -->
- <rate from="EUR" to="GBP" rate="0.869914" />
- <rate from="EUR" to="NOK" rate="7.800095" />
- <rate from="GBP" to="NOK" rate="8.966508" />
- </rates>
-</currencyConfig>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/elevate.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/elevate.xml b/solr/server/solr/configsets/_default/conf/elevate.xml
deleted file mode 100644
index 2c09ebe..0000000
--- a/solr/server/solr/configsets/_default/conf/elevate.xml
+++ /dev/null
@@ -1,42 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- If this file is found in the config directory, it will only be
- loaded once at startup. If it is found in Solr's data
- directory, it will be re-loaded every commit.
-
- See http://wiki.apache.org/solr/QueryElevationComponent for more info
-
--->
-<elevate>
- <!-- Query elevation examples
- <query text="foo bar">
- <doc id="1" />
- <doc id="2" />
- <doc id="3" />
- </query>
-
-for use with techproducts example
-
- <query text="ipod">
- <doc id="MA147LL/A" /> put the actual ipod at the top
- <doc id="IW-02" exclude="true" /> exclude this cable
- </query>
--->
-
-</elevate>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/contractions_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/contractions_ca.txt b/solr/server/solr/configsets/_default/conf/lang/contractions_ca.txt
deleted file mode 100644
index 307a85f..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/contractions_ca.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-# Set of Catalan contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-l
-m
-n
-s
-t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/contractions_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/contractions_fr.txt b/solr/server/solr/configsets/_default/conf/lang/contractions_fr.txt
deleted file mode 100644
index f1bba51..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/contractions_fr.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-# Set of French contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-l
-m
-t
-qu
-n
-s
-j
-d
-c
-jusqu
-quoiqu
-lorsqu
-puisqu
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/contractions_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/contractions_ga.txt b/solr/server/solr/configsets/_default/conf/lang/contractions_ga.txt
deleted file mode 100644
index 9ebe7fa..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/contractions_ga.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-# Set of Irish contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-m
-b
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/contractions_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/contractions_it.txt b/solr/server/solr/configsets/_default/conf/lang/contractions_it.txt
deleted file mode 100644
index cac0409..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/contractions_it.txt
+++ /dev/null
@@ -1,23 +0,0 @@
-# Set of Italian contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-c
-l
-all
-dall
-dell
-nell
-sull
-coll
-pell
-gl
-agl
-dagl
-degl
-negl
-sugl
-un
-m
-t
-s
-v
-d
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/hyphenations_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/hyphenations_ga.txt b/solr/server/solr/configsets/_default/conf/lang/hyphenations_ga.txt
deleted file mode 100644
index 4d2642c..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/hyphenations_ga.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-# Set of Irish hyphenations for StopFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-h
-n
-t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stemdict_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stemdict_nl.txt b/solr/server/solr/configsets/_default/conf/lang/stemdict_nl.txt
deleted file mode 100644
index 4410729..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stemdict_nl.txt
+++ /dev/null
@@ -1,6 +0,0 @@
-# Set of overrides for the dutch stemmer
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-fiets fiets
-bromfiets bromfiets
-ei eier
-kind kinder
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stoptags_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stoptags_ja.txt b/solr/server/solr/configsets/_default/conf/lang/stoptags_ja.txt
deleted file mode 100644
index 71b7508..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stoptags_ja.txt
+++ /dev/null
@@ -1,420 +0,0 @@
-#
-# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
-#
-# Any token with a part-of-speech tag that exactly matches those defined in this
-# file are removed from the token stream.
-#
-# Set your own stoptags by uncommenting the lines below. Note that comments are
-# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
-# etc. that can be useful for building you own stoptag set.
-#
-# The entire possible tagset is provided below for convenience.
-#
-#####
-# noun: unclassified nouns
-#名詞
-#
-# noun-common: Common nouns or nouns where the sub-classification is undefined
-#名詞-一般
-#
-# noun-proper: Proper nouns where the sub-classification is undefined
-#名詞-固有名詞
-#
-# noun-proper-misc: miscellaneous proper nouns
-#名詞-固有名詞-一般
-#
-# noun-proper-person: Personal names where the sub-classification is undefined
-#名詞-固有名詞-人名
-#
-# noun-proper-person-misc: names that cannot be divided into surname and
-# given name; foreign names; names where the surname or given name is unknown.
-# e.g. お市の方
-#名詞-固有名詞-人名-一般
-#
-# noun-proper-person-surname: Mainly Japanese surnames.
-# e.g. 山田
-#名詞-固有名詞-人名-姓
-#
-# noun-proper-person-given_name: Mainly Japanese given names.
-# e.g. 太郎
-#名詞-固有名詞-人名-名
-#
-# noun-proper-organization: Names representing organizations.
-# e.g. 通産省, NHK
-#名詞-固有名詞-組織
-#
-# noun-proper-place: Place names where the sub-classification is undefined
-#名詞-固有名詞-地域
-#
-# noun-proper-place-misc: Place names excluding countries.
-# e.g. アジア, バルセロナ, 京都
-#名詞-固有名詞-地域-一般
-#
-# noun-proper-place-country: Country names.
-# e.g. 日本, オーストラリア
-#名詞-固有名詞-地域-国
-#
-# noun-pronoun: Pronouns where the sub-classification is undefined
-#名詞-代名詞
-#
-# noun-pronoun-misc: miscellaneous pronouns:
-# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
-#名詞-代名詞-一般
-#
-# noun-pronoun-contraction: Spoken language contraction made by combining a
-# pronoun and the particle 'wa'.
-# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
-#名詞-代名詞-縮約
-#
-# noun-adverbial: Temporal nouns such as names of days or months that behave
-# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
-# e.g. 金曜, 一月, 午後, 少量
-#名詞-副詞可能
-#
-# noun-verbal: Nouns that take arguments with case and can appear followed by
-# 'suru' and related verbs (する, できる, なさる, くださる)
-# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
-#名詞-サ変接続
-#
-# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
-# e.g. 健康, 安易, 駄目, だめ
-#名詞-形容動詞語幹
-#
-# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
-# e.g. 0, 1, 2, 何, 数, 幾
-#名詞-数
-#
-# noun-affix: noun affixes where the sub-classification is undefined
-#名詞-非自立
-#
-# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
-# attach to the base form of inflectional words, words that cannot be classified
-# into any of the other categories below. This category includes indefinite nouns.
-# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
-# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
-# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
-# わり, 割り, 割, ん-口語/, もん-口語/
-#名詞-非自立-一般
-#
-# noun-affix-adverbial: noun affixes that that can behave as adverbs.
-# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
-# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
-# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
-# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
-# 儘, 侭, みぎり, 矢先
-#名詞-非自立-副詞可能
-#
-# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
-# with the stem よう(だ) ("you(da)").
-# e.g. よう, やう, 様 (よう)
-#名詞-非自立-助動詞語幹
-#
-# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
-# connection form な (aux "da").
-# e.g. みたい, ふう
-#名詞-非自立-形容動詞語幹
-#
-# noun-special: special nouns where the sub-classification is undefined.
-#名詞-特殊
-#
-# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
-# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
-# form of inflectional words.
-# e.g. そう
-#名詞-特殊-助動詞語幹
-#
-# noun-suffix: noun suffixes where the sub-classification is undefined.
-#名詞-接尾
-#
-# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
-# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
-# any of the other categories below. In general, this category is more inclusive than
-# 接尾語 ("suffix") and is usually the last element in a compound noun.
-# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
-# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
-#名詞-接尾-一般
-#
-# noun-suffix-person: Suffixes that form nouns and attach to person names more often
-# than other nouns.
-# e.g. 君, 様, 著
-#名詞-接尾-人名
-#
-# noun-suffix-place: Suffixes that form nouns and attach to place names more often
-# than other nouns.
-# e.g. 町, 市, 県
-#名詞-接尾-地域
-#
-# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
-# can appear before スル ("suru").
-# e.g. 化, 視, 分け, 入り, 落ち, 買い
-#名詞-接尾-サ変接続
-#
-# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
-# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
-# conjunctive form of inflectional words.
-# e.g. そう
-#名詞-接尾-助動詞語幹
-#
-# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
-# form of inflectional words and appear before the copula だ ("da").
-# e.g. 的, げ, がち
-#名詞-接尾-形容動詞語幹
-#
-# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
-# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
-#名詞-接尾-副詞可能
-#
-# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
-# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
-# to numbers.
-# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
-#名詞-接尾-助数詞
-#
-# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
-# e.g. (楽し) さ, (考え) 方
-#名詞-接尾-特殊
-#
-# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
-# together.
-# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
-#名詞-接続詞的
-#
-# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
-# semantically verb-like.
-# e.g. ごらん, ご覧, 御覧, 頂戴
-#名詞-動詞非自立的
-#
-# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
-# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
-# is いわく ("iwaku").
-#名詞-引用文字列
-#
-# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
-# behave like an adjective.
-# e.g. 申し訳, 仕方, とんでも, 違い
-#名詞-ナイ形容詞語幹
-#
-#####
-# prefix: unclassified prefixes
-#接頭詞
-#
-# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
-# excluding numerical expressions.
-# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
-#接頭詞-名詞接続
-#
-# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
-# in conjunctive form followed by なる/なさる/くださる.
-# e.g. お (読みなさい), お (座り)
-#接頭詞-動詞接続
-#
-# prefix-adjectival: Prefixes that attach to adjectives.
-# e.g. お (寒いですねえ), バカ (でかい)
-#接頭詞-形容詞接続
-#
-# prefix-numerical: Prefixes that attach to numerical expressions.
-# e.g. 約, およそ, 毎時
-#接頭詞-数接続
-#
-#####
-# verb: unclassified verbs
-#動詞
-#
-# verb-main:
-#動詞-自立
-#
-# verb-auxiliary:
-#動詞-非自立
-#
-# verb-suffix:
-#動詞-接尾
-#
-#####
-# adjective: unclassified adjectives
-#形容詞
-#
-# adjective-main:
-#形容詞-自立
-#
-# adjective-auxiliary:
-#形容詞-非自立
-#
-# adjective-suffix:
-#形容詞-接尾
-#
-#####
-# adverb: unclassified adverbs
-#副詞
-#
-# adverb-misc: Words that can be segmented into one unit and where adnominal
-# modification is not possible.
-# e.g. あいかわらず, 多分
-#副詞-一般
-#
-# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
-# な, する, だ, etc.
-# e.g. こんなに, そんなに, あんなに, なにか, なんでも
-#副詞-助詞類接続
-#
-#####
-# adnominal: Words that only have noun-modifying forms.
-# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
-# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
-# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
-#連体詞
-#
-#####
-# conjunction: Conjunctions that can occur independently.
-# e.g. が, けれども, そして, じゃあ, それどころか
-接続詞
-#
-#####
-# particle: unclassified particles.
-助詞
-#
-# particle-case: case particles where the subclassification is undefined.
-助詞-格助詞
-#
-# particle-case-misc: Case particles.
-# e.g. から, が, で, と, に, へ, より, を, の, にて
-助詞-格助詞-一般
-#
-# particle-case-quote: the "to" that appears after nouns, a person’s speech,
-# quotation marks, expressions of decisions from a meeting, reasons, judgements,
-# conjectures, etc.
-# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
-助詞-格助詞-引用
-#
-# particle-case-compound: Compounds of particles and verbs that mainly behave
-# like case particles.
-# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
-# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
-# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
-# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
-# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
-# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
-# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
-# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
-助詞-格助詞-連語
-#
-# particle-conjunctive:
-# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
-# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
-# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
-助詞-接続助詞
-#
-# particle-dependency:
-# e.g. こそ, さえ, しか, すら, は, も, ぞ
-助詞-係助詞
-#
-# particle-adverbial:
-# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
-# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
-# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
-# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
-# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
-助詞-副助詞
-#
-# particle-interjective: particles with interjective grammatical roles.
-# e.g. (松島) や
-助詞-間投助詞
-#
-# particle-coordinate:
-# e.g. と, たり, だの, だり, とか, なり, や, やら
-助詞-並立助詞
-#
-# particle-final:
-# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
-# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
-助詞-終助詞
-#
-# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
-# adverbial, conjunctive, or sentence final. For example:
-# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
-# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
-# 「(祈りが届いたせい) か (, 試験に合格した.)」
-# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
-# e.g. か
-助詞-副助詞／並立助詞／終助詞
-#
-# particle-adnominalizer: The "no" that attaches to nouns and modifies
-# non-inflectional words.
-助詞-連体化
-#
-# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
-# that are giongo, giseigo, or gitaigo.
-# e.g. に, と
-助詞-副詞化
-#
-# particle-special: A particle that does not fit into one of the above classifications.
-# This includes particles that are used in Tanka, Haiku, and other poetry.
-# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
-助詞-特殊
-#
-#####
-# auxiliary-verb:
-助動詞
-#
-#####
-# interjection: Greetings and other exclamations.
-# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
-# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
-#感動詞
-#
-#####
-# symbol: unclassified Symbols.
-記号
-#
-# symbol-misc: A general symbol not in one of the categories below.
-# e.g. [○◎@$〒→+]
-記号-一般
-#
-# symbol-comma: Commas
-# e.g. [,、]
-記号-読点
-#
-# symbol-period: Periods and full stops.
-# e.g. [.．。]
-記号-句点
-#
-# symbol-space: Full-width whitespace.
-記号-空白
-#
-# symbol-open_bracket:
-# e.g. [({‘“『【]
-記号-括弧開
-#
-# symbol-close_bracket:
-# e.g. [)}’”』」】]
-記号-括弧閉
-#
-# symbol-alphabetic:
-#記号-アルファベット
-#
-#####
-# other: unclassified other
-#その他
-#
-# other-interjection: Words that are hard to classify as noun-suffixes or
-# sentence-final particles.
-# e.g. (だ)ァ
-その他-間投
-#
-#####
-# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
-# e.g. あの, うんと, えと
-フィラー
-#
-#####
-# non-verbal: non-verbal sound.
-非言語音
-#
-#####
-# fragment:
-#語断片
-#
-#####
-# unknown: unknown part of speech.
-#未知語
-#
-##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_ar.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ar.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ar.txt
deleted file mode 100644
index 046829d..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_ar.txt
+++ /dev/null
@@ -1,125 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Cleaned on October 11, 2009 (not normalized, so use before normalization)
-# This means that when modifying this list, you might need to add some
-# redundant entries, for example containing forms with both أ and ا
-من
-ومن
-منها
-منه
-في
-وفي
-فيها
-فيه
-و
-ف
-ثم
-او
-أو
-ب
-بها
-به
-ا
-أ
-اى
-اي
-أي
-أى
-لا
-ولا
-الا
-ألا
-إلا
-لكن
-ما
-وما
-كما
-فما
-عن
-مع
-اذا
-إذا
-ان
-أن
-إن
-انها
-أنها
-إنها
-انه
-أنه
-إنه
-بان
-بأن
-فان
-فأن
-وان
-وأن
-وإن
-التى
-التي
-الذى
-الذي
-الذين
-الى
-الي
-إلى
-إلي
-على
-عليها
-عليه
-اما
-أما
-إما
-ايضا
-أيضا
-كل
-وكل
-لم
-ولم
-لن
-ولن
-هى
-هي
-هو
-وهى
-وهي
-وهو
-فهى
-فهي
-فهو
-انت
-أنت
-لك
-لها
-له
-هذه
-هذا
-تلك
-ذلك
-هناك
-كانت
-كان
-يكون
-تكون
-وكانت
-وكان
-غير
-بعض
-قد
-نحو
-بين
-بينما
-منذ
-ضمن
-حيث
-الان
-الآن
-خلال
-بعد
-قبل
-حتى
-عند
-عندما
-لدى
-جميع
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_bg.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_bg.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_bg.txt
deleted file mode 100644
index 1ae4ba2..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_bg.txt
+++ /dev/null
@@ -1,193 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-а
-аз
-ако
-ала
-бе
-без
-беше
-би
-бил
-била
-били
-било
-близо
-бъдат
-бъде
-бяха
-в
-вас
-ваш
-ваша
-вероятно
-вече
-взема
-ви
-вие
-винаги
-все
-всеки
-всички
-всичко
-всяка
-във
-въпреки
-върху
-г
-ги
-главно
-го
-д
-да
-дали
-до
-докато
-докога
-дори
-досега
-доста
-е
-едва
-един
-ето
-за
-зад
-заедно
-заради
-засега
-затова
-защо
-защото
-и
-из
-или
-им
-има
-имат
-иска
-й
-каза
-как
-каква
-какво
-както
-какъв
-като
-кога
-когато
-което
-които
-кой
-който
-колко
-която
-къде
-където
-към
-ли
-м
-ме
-между
-мен
-ми
-мнозина
-мога
-могат
-може
-моля
-момента
-му
-н
-на
-над
-назад
-най
-направи
-напред
-например
-нас
-не
-него
-нея
-ни
-ние
-никой
-нито
-но
-някои
-някой
-няма
-обаче
-около
-освен
-особено
-от
-отгоре
-отново
-още
-пак
-по
-повече
-повечето
-под
-поне
-поради
-после
-почти
-прави
-пред
-преди
-през
-при
-пък
-първо
-с
-са
-само
-се
-сега
-си
-скоро
-след
-сме
-според
-сред
-срещу
-сте
-съм
-със
-също
-т
-тази
-така
-такива
-такъв
-там
-твой
-те
-тези
-ти
-тн
-то
-това
-тогава
-този
-той
-толкова
-точно
-трябва
-тук
-тъй
-тя
-тях
-у
-харесва
-ч
-че
-често
-чрез
-ще
-щом
-я
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ca.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ca.txt
deleted file mode 100644
index 3da65de..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_ca.txt
+++ /dev/null
@@ -1,220 +0,0 @@
-# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
-a
-abans
-ací
-ah
-així
-això
-al
-als
-aleshores
-algun
-alguna
-algunes
-alguns
-alhora
-allà
-allí
-allò
-altra
-altre
-altres
-amb
-ambdós
-ambdues
-apa
-aquell
-aquella
-aquelles
-aquells
-aquest
-aquesta
-aquestes
-aquests
-aquí
-baix
-cada
-cadascú
-cadascuna
-cadascunes
-cadascuns
-com
-contra
-d'un
-d'una
-d'unes
-d'uns
-dalt
-de
-del
-dels
-des
-després
-dins
-dintre
-donat
-doncs
-durant
-e
-eh
-el
-els
-em
-en
-encara
-ens
-entre
-érem
-eren
-éreu
-es
-és
-esta
-està
-estàvem
-estaven
-estàveu
-esteu
-et
-etc
-ets
-fins
-fora
-gairebé
-ha
-han
-has
-havia
-he
-hem
-heu
-hi
-ho
-i
-igual
-iguals
-ja
-l'hi
-la
-les
-li
-li'n
-llavors
-m'he
-ma
-mal
-malgrat
-mateix
-mateixa
-mateixes
-mateixos
-me
-mentre
-més
-meu
-meus
-meva
-meves
-molt
-molta
-moltes
-molts
-mon
-mons
-n'he
-n'hi
-ne
-ni
-no
-nogensmenys
-només
-nosaltres
-nostra
-nostre
-nostres
-o
-oh
-oi
-on
-pas
-pel
-pels
-per
-però
-perquè
-poc
-poca
-pocs
-poques
-potser
-propi
-qual
-quals
-quan
-quant
-que
-què
-quelcom
-qui
-quin
-quina
-quines
-quins
-s'ha
-s'han
-sa
-semblant
-semblants
-ses
-seu
-seus
-seva
-seva
-seves
-si
-sobre
-sobretot
-sóc
-solament
-sols
-son
-són
-sons
-sota
-sou
-t'ha
-t'han
-t'he
-ta
-tal
-també
-tampoc
-tan
-tant
-tanta
-tantes
-teu
-teus
-teva
-teves
-ton
-tons
-tot
-tota
-totes
-tots
-un
-una
-unes
-uns
-us
-va
-vaig
-vam
-van
-vas
-veu
-vosaltres
-vostra
-vostre
-vostres
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_cz.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_cz.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_cz.txt
deleted file mode 100644
index 53c6097..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_cz.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-a
-s
-k
-o
-i
-u
-v
-z
-dnes
-cz
-tímto
-budeš
-budem
-byli
-jseš
-můj
-svým
-ta
-tomto
-tohle
-tuto
-tyto
-jej
-zda
-proč
-máte
-tato
-kam
-tohoto
-kdo
-kteří
-mi
-nám
-tom
-tomuto
-mít
-nic
-proto
-kterou
-byla
-toho
-protože
-asi
-ho
-naši
-napište
-re
-což
-tím
-takže
-svých
-její
-svými
-jste
-aj
-tu
-tedy
-teto
-bylo
-kde
-ke
-pravé
-ji
-nad
-nejsou
-či
-pod
-téma
-mezi
-přes
-ty
-pak
-vám
-ani
-když
-však
-neg
-jsem
-tento
-článku
-články
-aby
-jsme
-před
-pta
-jejich
-byl
-ještě
-až
-bez
-také
-pouze
-první
-vaše
-která
-nás
-nový
-tipy
-pokud
-může
-strana
-jeho
-své
-jiné
-zprávy
-nové
-není
-vás
-jen
-podle
-zde
-už
-být
-více
-bude
-již
-než
-který
-by
-které
-co
-nebo
-ten
-tak
-má
-při
-od
-po
-jsou
-jak
-další
-ale
-si
-se
-ve
-to
-jako
-za
-zpět
-ze
-do
-pro
-je
-na
-atd
-atp
-jakmile
-přičemž
-já
-on
-ona
-ono
-oni
-ony
-my
-vy
-jí
-ji
-mě
-mne
-jemu
-tomu
-těm
-těmu
-němu
-němuž
-jehož
-jíž
-jelikož
-jež
-jakož
-načež
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_da.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_da.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_da.txt
deleted file mode 100644
index 42e6145..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_da.txt
+++ /dev/null
@@ -1,110 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Danish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
-
-og | and
-i | in
-jeg | I
-det | that (dem. pronoun)/it (pers. pronoun)
-at | that (in front of a sentence)/to (with infinitive)
-en | a/an
-den | it (pers. pronoun)/that (dem. pronoun)
-til | to/at/for/until/against/by/of/into, more
-er | present tense of "to be"
-som | who, as
-på | on/upon/in/on/at/to/after/of/with/for, on
-de | they
-med | with/by/in, along
-han | he
-af | of/by/from/off/for/in/with/on, off
-for | at/for/to/from/by/of/ago, in front/before, because
-ikke | not
-der | who/which, there/those
-var | past tense of "to be"
-mig | me/myself
-sig | oneself/himself/herself/itself/themselves
-men | but
-et | a/an/one, one (number), someone/somebody/one
-har | present tense of "to have"
-om | round/about/for/in/a, about/around/down, if
-vi | we
-min | my
-havde | past tense of "to have"
-ham | him
-hun | she
-nu | now
-over | over/above/across/by/beyond/past/on/about, over/past
-da | then, when/as/since
-fra | from/off/since, off, since
-du | you
-ud | out
-sin | his/her/its/one's
-dem | them
-os | us/ourselves
-op | up
-man | you/one
-hans | his
-hvor | where
-eller | or
-hvad | what
-skal | must/shall etc.
-selv | myself/youself/herself/ourselves etc., even
-her | here
-alle | all/everyone/everybody etc.
-vil | will (verb)
-blev | past tense of "to stay/to remain/to get/to become"
-kunne | could
-ind | in
-når | when
-være | present tense of "to be"
-dog | however/yet/after all
-noget | something
-ville | would
-jo | you know/you see (adv), yes
-deres | their/theirs
-efter | after/behind/according to/for/by/from, later/afterwards
-ned | down
-skulle | should
-denne | this
-end | than
-dette | this
-mit | my/mine
-også | also
-under | under/beneath/below/during, below/underneath
-have | have
-dig | you
-anden | other
-hende | her
-mine | my
-alt | everything
-meget | much/very, plenty of
-sit | his, her, its, one's
-sine | his, her, its, one's
-vor | our
-mod | against
-disse | these
-hvis | if
-din | your/yours
-nogle | some
-hos | by/at
-blive | be/become
-mange | many
-ad | by/through
-bliver | present tense of "to be/to become"
-hendes | her/hers
-været | be
-thi | for (conj)
-jer | you
-sådan | such, like this/like that
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_de.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_de.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_de.txt
deleted file mode 100644
index 86525e7..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_de.txt
+++ /dev/null
@@ -1,294 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A German stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | The number of forms in this list is reduced significantly by passing it
- | through the German stemmer.
-
-
-aber | but
-
-alle | all
-allem
-allen
-aller
-alles
-
-als | than, as
-also | so
-am | an + dem
-an | at
-
-ander | other
-andere
-anderem
-anderen
-anderer
-anderes
-anderm
-andern
-anderr
-anders
-
-auch | also
-auf | on
-aus | out of
-bei | by
-bin | am
-bis | until
-bist | art
-da | there
-damit | with it
-dann | then
-
-der | the
-den
-des
-dem
-die
-das
-
-daß | that
-
-derselbe | the same
-derselben
-denselben
-desselben
-demselben
-dieselbe
-dieselben
-dasselbe
-
-dazu | to that
-
-dein | thy
-deine
-deinem
-deinen
-deiner
-deines
-
-denn | because
-
-derer | of those
-dessen | of him
-
-dich | thee
-dir | to thee
-du | thou
-
-dies | this
-diese
-diesem
-diesen
-dieser
-dieses
-
-
-doch | (several meanings)
-dort | (over) there
-
-
-durch | through
-
-ein | a
-eine
-einem
-einen
-einer
-eines
-
-einig | some
-einige
-einigem
-einigen
-einiger
-einiges
-
-einmal | once
-
-er | he
-ihn | him
-ihm | to him
-
-es | it
-etwas | something
-
-euer | your
-eure
-eurem
-euren
-eurer
-eures
-
-für | for
-gegen | towards
-gewesen | p.p. of sein
-hab | have
-habe | have
-haben | have
-hat | has
-hatte | had
-hatten | had
-hier | here
-hin | there
-hinter | behind
-
-ich | I
-mich | me
-mir | to me
-
-
-ihr | you, to her
-ihre
-ihrem
-ihren
-ihrer
-ihres
-euch | to you
-
-im | in + dem
-in | in
-indem | while
-ins | in + das
-ist | is
-
-jede | each, every
-jedem
-jeden
-jeder
-jedes
-
-jene | that
-jenem
-jenen
-jener
-jenes
-
-jetzt | now
-kann | can
-
-kein | no
-keine
-keinem
-keinen
-keiner
-keines
-
-können | can
-könnte | could
-machen | do
-man | one
-
-manche | some, many a
-manchem
-manchen
-mancher
-manches
-
-mein | my
-meine
-meinem
-meinen
-meiner
-meines
-
-mit | with
-muss | must
-musste | had to
-nach | to(wards)
-nicht | not
-nichts | nothing
-noch | still, yet
-nun | now
-nur | only
-ob | whether
-oder | or
-ohne | without
-sehr | very
-
-sein | his
-seine
-seinem
-seinen
-seiner
-seines
-
-selbst | self
-sich | herself
-
-sie | they, she
-ihnen | to them
-
-sind | are
-so | so
-
-solche | such
-solchem
-solchen
-solcher
-solches
-
-soll | shall
-sollte | should
-sondern | but
-sonst | else
-über | over
-um | about, around
-und | and
-
-uns | us
-unse
-unsem
-unsen
-unser
-unses
-
-unter | under
-viel | much
-vom | von + dem
-von | from
-vor | before
-während | while
-war | was
-waren | were
-warst | wast
-was | what
-weg | away, off
-weil | because
-weiter | further
-
-welche | which
-welchem
-welchen
-welcher
-welches
-
-wenn | when
-werde | will
-werden | will
-wie | how
-wieder | again
-will | want
-wir | we
-wird | will
-wirst | willst
-wo | where
-wollen | want
-wollte | wanted
-würde | would
-würden | would
-zu | to
-zum | zu + dem
-zur | zu + der
-zwar | indeed
-zwischen | between
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_el.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_el.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_el.txt
deleted file mode 100644
index 232681f..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_el.txt
+++ /dev/null
@@ -1,78 +0,0 @@
-# Lucene Greek Stopwords list
-# Note: by default this file is used after GreekLowerCaseFilter,
-# so when modifying this file use 'σ' instead of 'ς'
-ο
-η
-το
-οι
-τα
-του
-τησ
-των
-τον
-την
-και
-κι
-κ
-ειμαι
-εισαι
-ειναι
-ειμαστε
-ειστε
-στο
-στον
-στη
-στην
-μα
-αλλα
-απο
-για
-προσ
-με
-σε
-ωσ
-παρα
-αντι
-κατα
-μετα
-θα
-να
-δε
-δεν
-μη
-μην
-επι
-ενω
-εαν
-αν
-τοτε
-που
-πωσ
-ποιοσ
-ποια
-ποιο
-ποιοι
-ποιεσ
-ποιων
-ποιουσ
-αυτοσ
-αυτη
-αυτο
-αυτοι
-αυτων
-αυτουσ
-αυτεσ
-αυτα
-εκεινοσ
-εκεινη
-εκεινο
-εκεινοι
-εκεινεσ
-εκεινα
-εκεινων
-εκεινουσ
-οπωσ
-ομωσ
-ισωσ
-οσο
-οτι
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_en.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_en.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_en.txt
deleted file mode 100644
index 2c164c0..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_en.txt
+++ /dev/null
@@ -1,54 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# a couple of test stopwords to test that the words are really being
-# configured from this file:
-stopworda
-stopwordb
-
-# Standard english stop words taken from Lucene's StopAnalyzer
-a
-an
-and
-are
-as
-at
-be
-but
-by
-for
-if
-in
-into
-is
-it
-no
-not
-of
-on
-or
-such
-that
-the
-their
-then
-there
-these
-they
-this
-to
-was
-will
-with
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_es.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_es.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_es.txt
deleted file mode 100644
index 487d78c..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_es.txt
+++ /dev/null
@@ -1,356 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Spanish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-
- | The following is a ranked list (commonest to rarest) of stopwords
- | deriving from a large sample of text.
-
- | Extra words have been added at the end.
-
-de | from, of
-la | the, her
-que | who, that
-el | the
-en | in
-y | and
-a | to
-los | the, them
-del | de + el
-se | himself, from him etc
-las | the, them
-por | for, by, etc
-un | a
-para | for
-con | with
-no | no
-una | a
-su | his, her
-al | a + el
- | es from SER
-lo | him
-como | how
-más | more
-pero | pero
-sus | su plural
-le | to him, her
-ya | already
-o | or
- | fue from SER
-este | this
- | ha from HABER
-sí | himself etc
-porque | because
-esta | this
- | son from SER
-entre | between
- | está from ESTAR
-cuando | when
-muy | very
-sin | without
-sobre | on
- | ser from SER
- | tiene from TENER
-también | also
-me | me
-hasta | until
-hay | there is/are
-donde | where
- | han from HABER
-quien | whom, that
- | están from ESTAR
- | estado from ESTAR
-desde | from
-todo | all
-nos | us
-durante | during
- | estados from ESTAR
-todos | all
-uno | a
-les | to them
-ni | nor
-contra | against
-otros | other
- | fueron from SER
-ese | that
-eso | that
- | había from HABER
-ante | before
-ellos | they
-e | and (variant of y)
-esto | this
-mí | me
-antes | before
-algunos | some
-qué | what?
-unos | a
-yo | I
-otro | other
-otras | other
-otra | other
-él | he
-tanto | so much, many
-esa | that
-estos | these
-mucho | much, many
-quienes | who
-nada | nothing
-muchos | many
-cual | who
- | sea from SER
-poco | few
-ella | she
-estar | to be
- | haber from HABER
-estas | these
- | estaba from ESTAR
- | estamos from ESTAR
-algunas | some
-algo | something
-nosotros | we
-
- | other forms
-
-mi | me
-mis | mi plural
-tú | thou
-te | thee
-ti | thee
-tu | thy
-tus | tu plural
-ellas | they
-nosotras | we
-vosotros | you
-vosotras | you
-os | you
-mío | mine
-mía |
-míos |
-mías |
-tuyo | thine
-tuya |
-tuyos |
-tuyas |
-suyo | his, hers, theirs
-suya |
-suyos |
-suyas |
-nuestro | ours
-nuestra |
-nuestros |
-nuestras |
-vuestro | yours
-vuestra |
-vuestros |
-vuestras |
-esos | those
-esas | those
-
- | forms of estar, to be (not including the infinitive):
-estoy
-estás
-está
-estamos
-estáis
-están
-esté
-estés
-estemos
-estéis
-estén
-estaré
-estarás
-estará
-estaremos
-estaréis
-estarán
-estaría
-estarías
-estaríamos
-estaríais
-estarían
-estaba
-estabas
-estábamos
-estabais
-estaban
-estuve
-estuviste
-estuvo
-estuvimos
-estuvisteis
-estuvieron
-estuviera
-estuvieras
-estuviéramos
-estuvierais
-estuvieran
-estuviese
-estuvieses
-estuviésemos
-estuvieseis
-estuviesen
-estando
-estado
-estada
-estados
-estadas
-estad
-
- | forms of haber, to have (not including the infinitive):
-he
-has
-ha
-hemos
-habéis
-han
-haya
-hayas
-hayamos
-hayáis
-hayan
-habré
-habrás
-habrá
-habremos
-habréis
-habrán
-habría
-habrías
-habríamos
-habríais
-habrían
-había
-habías
-habíamos
-habíais
-habían
-hube
-hubiste
-hubo
-hubimos
-hubisteis
-hubieron
-hubiera
-hubieras
-hubiéramos
-hubierais
-hubieran
-hubiese
-hubieses
-hubiésemos
-hubieseis
-hubiesen
-habiendo
-habido
-habida
-habidos
-habidas
-
- | forms of ser, to be (not including the infinitive):
-soy
-eres
-es
-somos
-sois
-son
-sea
-seas
-seamos
-seáis
-sean
-seré
-serás
-será
-seremos
-seréis
-serán
-sería
-serías
-seríamos
-seríais
-serían
-era
-eras
-éramos
-erais
-eran
-fui
-fuiste
-fue
-fuimos
-fuisteis
-fueron
-fuera
-fueras
-fuéramos
-fuerais
-fueran
-fuese
-fueses
-fuésemos
-fueseis
-fuesen
-siendo
-sido
- | sed also means 'thirst'
-
- | forms of tener, to have (not including the infinitive):
-tengo
-tienes
-tiene
-tenemos
-tenéis
-tienen
-tenga
-tengas
-tengamos
-tengáis
-tengan
-tendré
-tendrás
-tendrá
-tendremos
-tendréis
-tendrán
-tendría
-tendrías
-tendríamos
-tendríais
-tendrían
-tenía
-tenías
-teníamos
-teníais
-tenían
-tuve
-tuviste
-tuvo
-tuvimos
-tuvisteis
-tuvieron
-tuviera
-tuvieras
-tuviéramos
-tuvierais
-tuvieran
-tuviese
-tuvieses
-tuviésemos
-tuvieseis
-tuviesen
-teniendo
-tenido
-tenida
-tenidos
-tenidas
-tened
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_eu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_eu.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_eu.txt
deleted file mode 100644
index 25f1db9..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_eu.txt
+++ /dev/null
@@ -1,99 +0,0 @@
-# example set of basque stopwords
-al
-anitz
-arabera
-asko
-baina
-bat
-batean
-batek
-bati
-batzuei
-batzuek
-batzuetan
-batzuk
-bera
-beraiek
-berau
-berauek
-bere
-berori
-beroriek
-beste
-bezala
-da
-dago
-dira
-ditu
-du
-dute
-edo
-egin
-ere
-eta
-eurak
-ez
-gainera
-gu
-gutxi
-guzti
-haiei
-haiek
-haietan
-hainbeste
-hala
-han
-handik
-hango
-hara
-hari
-hark
-hartan
-hau
-hauei
-hauek
-hauetan
-hemen
-hemendik
-hemengo
-hi
-hona
-honek
-honela
-honetan
-honi
-hor
-hori
-horiei
-horiek
-horietan
-horko
-horra
-horrek
-horrela
-horretan
-horri
-hortik
-hura
-izan
-ni
-noiz
-nola
-non
-nondik
-nongo
-nor
-nora
-ze
-zein
-zen
-zenbait
-zenbat
-zer
-zergatik
-ziren
-zituen
-zu
-zuek
-zuen
-zuten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_fa.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_fa.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_fa.txt
deleted file mode 100644
index 723641c..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_fa.txt
+++ /dev/null
@@ -1,313 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Note: by default this file is used after normalization, so when adding entries
-# to this file, use the arabic 'ي' instead of 'ی'
-انان
-نداشته
-سراسر
-خياه
-ايشان
-وي
-تاكنون
-بيشتري
-دوم
-پس
-ناشي
-وگو
-يا
-داشتند
-سپس
-هنگام
-هرگز
-پنج
-نشان
-امسال
-ديگر
-گروهي
-شدند
-چطور
-ده
-و
-دو
-نخستين
-ولي
-چرا
-چه
-وسط
-ه
-كدام
-قابل
-يك
-رفت
-هفت
-همچنين
-در
-هزار
-بله
-بلي
-شايد
-اما
-شناسي
-گرفته
-دهد
-داشته
-دانست
-داشتن
-خواهيم
-ميليارد
-وقتيكه
-امد
-خواهد
-جز
-اورده
-شده
-بلكه
-خدمات
-شدن
-برخي
-نبود
-بسياري
-جلوگيري
-حق
-كردند
-نوعي
-بعري
-نكرده
-نظير
-نبايد
-بوده
-بودن
-داد
-اورد
-هست
-جايي
-شود
-دنبال
-داده
-بايد
-سابق
-هيچ
-همان
-انجا
-كمتر
-كجاست
-گردد
-كسي
-تر
-مردم
-تان
-دادن
-بودند
-سري
-جدا
-ندارند
-مگر
-يكديگر
-دارد
-دهند
-بنابراين
-هنگامي
-سمت
-جا
-انچه
-خود
-دادند
-زياد
-دارند
-اثر
-بدون
-بهترين
-بيشتر
-البته
-به
-براساس
-بيرون
-كرد
-بعضي
-گرفت
-توي
-اي
-ميليون
-او
-جريان
-تول
-بر
-مانند
-برابر
-باشيم
-مدتي
-گويند
-اكنون
-تا
-تنها
-جديد
-چند
-بي
-نشده
-كردن
-كردم
-گويد
-كرده
-كنيم
-نمي
-نزد
-روي
-قصد
-فقط
-بالاي
-ديگران
-اين
-ديروز
-توسط
-سوم
-ايم
-دانند
-سوي
-استفاده
-شما
-كنار
-داريم
-ساخته
-طور
-امده
-رفته
-نخست
-بيست
-نزديك
-طي
-كنيد
-از
-انها
-تمامي
-داشت
-يكي
-طريق
-اش
-چيست
-روب
-نمايد
-گفت
-چندين
-چيزي
-تواند
-ام
-ايا
-با
-ان
-ايد
-ترين
-اينكه
-ديگري
-راه
-هايي
-بروز
-همچنان
-پاعين
-كس
-حدود
-مختلف
-مقابل
-چيز
-گيرد
-ندارد
-ضد
-همچون
-سازي
-شان
-مورد
-باره
-مرسي
-خويش
-برخوردار
-چون
-خارج
-شش
-هنوز
-تحت
-ضمن
-هستيم
-گفته
-فكر
-بسيار
-پيش
-براي
-روزهاي
-انكه
-نخواهد
-بالا
-كل
-وقتي
-كي
-چنين
-كه
-گيري
-نيست
-است
-كجا
-كند
-نيز
-يابد
-بندي
-حتي
-توانند
-عقب
-خواست
-كنند
-بين
-تمام
-همه
-ما
-باشند
-مثل
-شد
-اري
-باشد
-اره
-طبق
-بعد
-اگر
-صورت
-غير
-جاي
-بيش
-ريزي
-اند
-زيرا
-چگونه
-بار
-لطفا
-مي
-درباره
-من
-ديده
-همين
-گذاري
-برداري
-علت
-گذاشته
-هم
-فوق
-نه
-ها
-شوند
-اباد
-همواره
-هر
-اول
-خواهند
-چهار
-نام
-امروز
-مان
-هاي
-قبل
-كنم
-سعي
-تازه
-را
-هستند
-زير
-جلوي
-عنوان
-بود
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_fi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_fi.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_fi.txt
deleted file mode 100644
index 4372c9a..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_fi.txt
+++ /dev/null
@@ -1,97 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
-| forms of BE
-
-olla
-olen
-olet
-on
-olemme
-olette
-ovat
-ole | negative form
-
-oli
-olisi
-olisit
-olisin
-olisimme
-olisitte
-olisivat
-olit
-olin
-olimme
-olitte
-olivat
-ollut
-olleet
-
-en | negation
-et
-ei
-emme
-ette
-eivät
-
-|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
-minä minun minut minua minussa minusta minuun minulla minulta minulle | I
-sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
-hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she
-me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we
-te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you
-he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they
-
-tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this
-tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
-se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it
-nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these
-nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
-ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they
-
-kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
-ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl)
-mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what
-mitkä | (pl)
-
-joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which
-jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl)
-
-| conjunctions
-
-että | that
-ja | and
-jos | if
-koska | because
-kuin | than
-mutta | but
-niin | so
-sekä | and
-sillä | for
-tai | or
-vaan | but
-vai | or
-vaikka | although
-
-
-| prepositions
-
-kanssa | with
-mukaan | according to
-noin | about
-poikki | across
-yli | over, across
-
-| other
-
-kun | when
-niin | so
-nyt | now
-itse | self
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_fr.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_fr.txt
deleted file mode 100644
index 749abae..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_fr.txt
+++ /dev/null
@@ -1,186 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A French stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-au | a + le
-aux | a + les
-avec | with
-ce | this
-ces | these
-dans | with
-de | of
-des | de + les
-du | de + le
-elle | she
-en | `of them' etc
-et | and
-eux | them
-il | he
-je | I
-la | the
-le | the
-leur | their
-lui | him
-ma | my (fem)
-mais | but
-me | me
-même | same; as in moi-même (myself) etc
-mes | me (pl)
-moi | me
-mon | my (masc)
-ne | not
-nos | our (pl)
-notre | our
-nous | we
-on | one
-ou | where
-par | by
-pas | not
-pour | for
-qu | que before vowel
-que | that
-qui | who
-sa | his, her (fem)
-se | oneself
-ses | his (pl)
-son | his, her (masc)
-sur | on
-ta | thy (fem)
-te | thee
-tes | thy (pl)
-toi | thee
-ton | thy (masc)
-tu | thou
-un | a
-une | a
-vos | your (pl)
-votre | your
-vous | you
-
- | single letter forms
-
-c | c'
-d | d'
-j | j'
-l | l'
-à | to, at
-m | m'
-n | n'
-s | s'
-t | t'
-y | there
-
- | forms of être (not including the infinitive):
-été
-étée
-étées
-étés
-étant
-suis
-es
-est
-sommes
-êtes
-sont
-serai
-seras
-sera
-serons
-serez
-seront
-serais
-serait
-serions
-seriez
-seraient
-étais
-était
-étions
-étiez
-étaient
-fus
-fut
-fûmes
-fûtes
-furent
-sois
-soit
-soyons
-soyez
-soient
-fusse
-fusses
-fût
-fussions
-fussiez
-fussent
-
- | forms of avoir (not including the infinitive):
-ayant
-eu
-eue
-eues
-eus
-ai
-as
-avons
-avez
-ont
-aurai
-auras
-aura
-aurons
-aurez
-auront
-aurais
-aurait
-aurions
-auriez
-auraient
-avais
-avait
-avions
-aviez
-avaient
-eut
-eûmes
-eûtes
-eurent
-aie
-aies
-ait
-ayons
-ayez
-aient
-eusse
-eusses
-eût
-eussions
-eussiez
-eussent
-
- | Later additions (from Jean-Christophe Deschamps)
-ceci | this
-cela | that
-celà | that
-cet | this
-cette | this
-ici | here
-ils | they
-les | the (pl)
-leurs | their (pl)
-quel | which
-quels | which
-quelle | which
-quelles | which
-sans | without
-soi | oneself
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_ga.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_ga.txt
deleted file mode 100644
index 9ff88d7..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_ga.txt
+++ /dev/null
@@ -1,110 +0,0 @@
-
-a
-ach
-ag
-agus
-an
-aon
-ar
-arna
-as
-b'
-ba
-beirt
-bhúr
-caoga
-ceathair
-ceathrar
-chomh
-chtó
-chuig
-chun
-cois
-céad
-cúig
-cúigear
-d'
-daichead
-dar
-de
-deich
-deichniúr
-den
-dhá
-do
-don
-dtí
-dá
-dár
-dó
-faoi
-faoin
-faoina
-faoinár
-fara
-fiche
-gach
-gan
-go
-gur
-haon
-hocht
-i
-iad
-idir
-in
-ina
-ins
-inár
-is
-le
-leis
-lena
-lenár
-m'
-mar
-mo
-mé
-na
-nach
-naoi
-naonúr
-ná
-ní
-níor
-nó
-nócha
-ocht
-ochtar
-os
-roimh
-sa
-seacht
-seachtar
-seachtó
-seasca
-seisear
-siad
-sibh
-sinn
-sna
-sé
-sí
-tar
-thar
-thú
-triúr
-trí
-trína
-trínár
-tríocha
-tú
-um
-ár
-é
-éis
-í
-ó
-ón
-óna
-ónár
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_gl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_gl.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_gl.txt
deleted file mode 100644
index d8760b1..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_gl.txt
+++ /dev/null
@@ -1,161 +0,0 @@
-# galican stopwords
-a
-aínda
-alí
-aquel
-aquela
-aquelas
-aqueles
-aquilo
-aquí
-ao
-aos
-as
-así
-á
-ben
-cando
-che
-co
-coa
-comigo
-con
-connosco
-contigo
-convosco
-coas
-cos
-cun
-cuns
-cunha
-cunhas
-da
-dalgunha
-dalgunhas
-dalgún
-dalgúns
-das
-de
-del
-dela
-delas
-deles
-desde
-deste
-do
-dos
-dun
-duns
-dunha
-dunhas
-e
-el
-ela
-elas
-eles
-en
-era
-eran
-esa
-esas
-ese
-eses
-esta
-estar
-estaba
-está
-están
-este
-estes
-estiven
-estou
-eu
-é
-facer
-foi
-foron
-fun
-había
-hai
-iso
-isto
-la
-las
-lle
-lles
-lo
-los
-mais
-me
-meu
-meus
-min
-miña
-miñas
-moi
-na
-nas
-neste
-nin
-no
-non
-nos
-nosa
-nosas
-noso
-nosos
-nós
-nun
-nunha
-nuns
-nunhas
-o
-os
-ou
-ó
-ós
-para
-pero
-pode
-pois
-pola
-polas
-polo
-polos
-por
-que
-se
-senón
-ser
-seu
-seus
-sexa
-sido
-sobre
-súa
-súas
-tamén
-tan
-te
-ten
-teñen
-teño
-ter
-teu
-teus
-ti
-tido
-tiña
-tiven
-túa
-túas
-un
-unha
-unhas
-uns
-vos
-vosa
-vosas
-voso
-vosos
-vós
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_hi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_hi.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_hi.txt
deleted file mode 100644
index 86286bb..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_hi.txt
+++ /dev/null
@@ -1,235 +0,0 @@
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# Note: by default this file also contains forms normalized by HindiNormalizer
-# for spelling variation (see section below), such that it can be used whether or
-# not you enable that feature. When adding additional entries to this list,
-# please add the normalized form as well.
-अंदर
-अत
-अपना
-अपनी
-अपने
-अभी
-आदि
-आप
-इत्यादि
-इन
-इनका
-इन्हीं
-इन्हें
-इन्हों
-इस
-इसका
-इसकी
-इसके
-इसमें
-इसी
-इसे
-उन
-उनका
-उनकी
-उनके
-उनको
-उन्हीं
-उन्हें
-उन्हों
-उस
-उसके
-उसी
-उसे
-एक
-एवं
-एस
-ऐसे
-और
-कई
-कर
-करता
-करते
-करना
-करने
-करें
-कहते
-कहा
-का
-काफ़ी
-कि
-कितना
-किन्हें
-किन्हों
-किया
-किर
-किस
-किसी
-किसे
-की
-कुछ
-कुल
-के
-को
-कोई
-कौन
-कौनसा
-गया
-घर
-जब
-जहाँ
-जा
-जितना
-जिन
-जिन्हें
-जिन्हों
-जिस
-जिसे
-जीधर
-जैसा
-जैसे
-जो
-तक
-तब
-तरह
-तिन
-तिन्हें
-तिन्हों
-तिस
-तिसे
-तो
-था
-थी
-थे
-दबारा
-दिया
-दुसरा
-दूसरे
-दो
-द्वारा
-न
-नहीं
-ना
-निहायत
-नीचे
-ने
-पर
-पर
-पहले
-पूरा
-पे
-फिर
-बनी
-बही
-बहुत
-बाद
-बाला
-बिलकुल
-भी
-भीतर
-मगर
-मानो
-मे
-में
-यदि
-यह
-यहाँ
-यही
-या
-यिह
-ये
-रखें
-रहा
-रहे
-ऱ्वासा
-लिए
-लिये
-लेकिन
-व
-वर्ग
-वह
-वह
-वहाँ
-वहीं
-वाले
-वुह
-वे
-वग़ैरह
-संग
-सकता
-सकते
-सबसे
-सभी
-साथ
-साबुत
-साभ
-सारा
-से
-सो
-ही
-हुआ
-हुई
-हुए
-है
-हैं
-हो
-होता
-होती
-होते
-होना
-होने
-# additional normalized forms of the above
-अपनि
-जेसे
-होति
-सभि
-तिंहों
-इंहों
-दवारा
-इसि
-किंहें
-थि
-उंहों
-ओर
-जिंहें
-वहिं
-अभि
-बनि
-हि
-उंहिं
-उंहें
-हें
-वगेरह
-एसे
-रवासा
-कोन
-निचे
-काफि
-उसि
-पुरा
-भितर
-हे
-बहि
-वहां
-कोइ
-यहां
-जिंहों
-तिंहें
-किसि
-कइ
-यहि
-इंहिं
-जिधर
-इंहें
-अदि
-इतयादि
-हुइ
-कोनसा
-इसकि
-दुसरे
-जहां
-अप
-किंहों
-उनकि
-भि
-वरग
-हुअ
-जेसा
-नहिं
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/lang/stopwords_hu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/lang/stopwords_hu.txt b/solr/server/solr/configsets/_default/conf/lang/stopwords_hu.txt
deleted file mode 100644
index 37526da..0000000
--- a/solr/server/solr/configsets/_default/conf/lang/stopwords_hu.txt
+++ /dev/null
@@ -1,211 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
-| Hungarian stop word list
-| prepared by Anna Tordai
-
-a
-ahogy
-ahol
-aki
-akik
-akkor
-alatt
-által
-általában
-amely
-amelyek
-amelyekben
-amelyeket
-amelyet
-amelynek
-ami
-amit
-amolyan
-amíg
-amikor
-át
-abban
-ahhoz
-annak
-arra
-arról
-az
-azok
-azon
-azt
-azzal
-azért
-aztán
-azután
-azonban
-bár
-be
-belül
-benne
-cikk
-cikkek
-cikkeket
-csak
-de
-e
-eddig
-egész
-egy
-egyes
-egyetlen
-egyéb
-egyik
-egyre
-ekkor
-el
-elég
-ellen
-elő
-először
-előtt
-első
-én
-éppen
-ebben
-ehhez
-emilyen
-ennek
-erre
-ez
-ezt
-ezek
-ezen
-ezzel
-ezért
-és
-fel
-felé
-hanem
-hiszen
-hogy
-hogyan
-igen
-így
-illetve
-ill.
-ill
-ilyen
-ilyenkor
-ison
-ismét
-itt
-jó
-jól
-jobban
-kell
-kellett
-keresztül
-keressünk
-ki
-kívül
-között
-közül
-legalább
-lehet
-lehetett
-legyen
-lenne
-lenni
-lesz
-lett
-maga
-magát
-majd
-majd
-már
-más
-másik
-meg
-még
-mellett
-mert
-mely
-melyek
-mi
-mit
-míg
-miért
-milyen
-mikor
-minden
-mindent
-mindenki
-mindig
-mint
-mintha
-mivel
-most
-nagy
-nagyobb
-nagyon
-ne
-néha
-nekem
-neki
-nem
-néhány
-nélkül
-nincs
-olyan
-ott
-össze
-ő
-ők
-őket
-pedig
-persze
-rá
-s
-saját
-sem
-semmi
-sok
-sokat
-sokkal
-számára
-szemben
-szerint
-szinte
-talán
-tehát
-teljes
-tovább
-továbbá
-több
-úgy
-ugyanis
-új
-újabb
-újra
-után
-utána
-utolsó
-vagy
-vagyis
-valaki
-valami
-valamint
-való
-vagyok
-van
-vannak
-volt
-voltam
-voltak
-voltunk
-vissza
-vele
-viszont
-volna
[46/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/managed-schema b/solr/server/solr/configsets/_default/conf/managed-schema
deleted file mode 100644
index f1017af..0000000
--- a/solr/server/solr/configsets/_default/conf/managed-schema
+++ /dev/null
@@ -1,1069 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default)
- or located where the classloader for the Solr webapp can find it.
-
- This example schema is the recommended starting point for users.
- It should be kept correct and concise, usable out-of-the-box.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
-
- PERFORMANCE NOTE: this schema includes many optional features and should not
- be used for benchmarking. To improve performance one could
- - set stored="false" for all fields possible (esp large fields) when you
- only need to search on the field but don't need to return the original
- value.
- - set indexed="false" if you don't need to search on the field, but only
- return the field as a result of searching on other indexed fields.
- - remove all unneeded copyField statements
- - for best index size and searching performance, set "index" to false
- for all general text fields, use copyField to copy them to the
- catchall "text" field, and use that for searching.
- - For maximum indexing performance, use the ConcurrentUpdateSolrServer
- java client.
- - Remember to run the JVM in server mode, and use a higher logging level
- that avoids logging every request
--->
-
-<schema name="default-config" version="2.0">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
- version="x.y" is Solr's version number for the schema syntax and
- semantics. It should not normally be changed by applications.
-
- 1.0: multiValued attribute did not exist, all fields are multiValued
- by nature
- 1.1: multiValued attribute introduced, false by default
- 1.2: omitTermFreqAndPositions attribute introduced, true by default
- except for text fields.
- 1.3: removed optional field compress feature
- 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
- behavior when a single string produces multiple tokens. Defaults
- to off for version >= 1.4
- 1.5: omitNorms defaults to true for primitive field types
- (int, float, boolean, string...)
- 1.6: useDocValuesAsStored defaults to true.
- -->
-
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a field type from the
- fieldTypes section
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- docValues: true if this field should have doc values. Doc values are
- useful (required, if you are using *Point fields) for faceting,
- grouping, sorting and function queries. Doc values will make the index
- faster to load, more NRT-friendly and more memory-efficient.
- They however come with some limitations: they are currently only
- supported by StrField, UUIDField, all Trie*Fields and *PointFields,
- and depending on the field type, they might require the field to be
- single-valued, be required or have a default value (check the
- documentation of the field type you're interested in for more information)
- multiValued: true if this field may contain multiple values per document
- omitNorms: (expert) set to true to omit the norms associated with
- this field (this disables length normalization and index-time
- boosting for the field, and saves some memory). Only full-text
- fields or fields that need an index-time boost need norms.
- Norms are omitted for primitive (non-analyzed) types by default.
- termVectors: [false] set to true to store the term vector for a
- given field.
- When using MoreLikeThis, fields used for similarity should be
- stored for best performance.
- termPositions: Store position information with the term vector.
- This will increase storage costs.
- termOffsets: Store offset information with the term vector. This
- will increase storage costs.
- required: The field is required. It will throw an error if the
- value does not exist
- default: a value that should be used if no value is specified
- when adding a document.
- -->
-
- <!-- field names should consist of alphanumeric or underscore characters only and
- not start with a digit. This is not currently strictly enforced,
- but other field names will not have first class support from all components
- and back compatibility is not guaranteed. Names with both leading and
- trailing underscores (e.g. _version_) are reserved.
- -->
-
- <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
- id, _version_, and _text_. All other fields will be type guessed and added via the
- "add-unknown-fields-to-the-schema" update request processor chain declared
- in solrconfig.xml.
-
- Note that many dynamic fields are also defined - you can use them to specify a
- field's type via field naming conventions - see below.
-
- WARNING: The _text_ catch-all field will significantly increase your index size.
- If you don't need it, consider removing it and the corresponding copyField directive.
- -->
- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
- <!-- doc values are enabled by default for primitive types such as long so we don't index the version field -->
- <field name="_version_" type="long" indexed="false" stored="false"/>
- <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
- <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
-
- <!-- Only enabled in the "schemaless" data-driven example (assuming the client
- does not know what fields may be searched) because it's very expensive to index everything twice. -->
- <!-- <copyField source="*" dest="_text_"/> -->
-
- <!-- Dynamic field definitions allow using convention over configuration
- for fields via the specification of patterns to match field names.
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
- RESTRICTION: the glob-like pattern in the name attribute must have
- a "*" only at the start or the end. -->
-
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true" />
- <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
-
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
- <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
- <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
-
- <!-- KD-tree (point) numerics -->
- <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
- <dynamicField name="*_pis" type="pints" indexed="true" stored="true"/>
- <dynamicField name="*_pl" type="plong" indexed="true" stored="true"/>
- <dynamicField name="*_pls" type="plongs" indexed="true" stored="true"/>
- <dynamicField name="*_pf" type="pfloat" indexed="true" stored="true"/>
- <dynamicField name="*_pfs" type="pfloats" indexed="true" stored="true"/>
- <dynamicField name="*_pd" type="pdouble" indexed="true" stored="true"/>
- <dynamicField name="*_pds" type="pdoubles" indexed="true" stored="true"/>
- <dynamicField name="*_pdt" type="pdate" indexed="true" stored="true"/>
- <dynamicField name="*_pdts" type="pdates" indexed="true" stored="true"/>
-
- <!-- some trie-coded dynamic fields -->
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
- <dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
-
- <!-- payloaded dynamic fields -->
- <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true" stored="true"/>
- <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true" stored="true"/>
- <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true" stored="true"/>
-
- <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
-
- <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
- <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
-
- <dynamicField name="random_*" type="random" />
-
- <!-- uncomment the following to ignore any fields that don't already match an existing
- field name or dynamic field, rather than reporting them as an error.
- alternately, change the type="ignored" to some other type e.g. "text" if you want
- unknown fields indexed and/or stored by default
-
- NB: use of "*" dynamic fields will disable field type guessing and adding
- unknown fields to the schema. -->
- <!--dynamicField name="*" type="ignored" multiValued="true" /-->
-
- <!-- Field to use to determine and enforce document uniqueness.
- Unless this field is marked with required="false", it will be a required field
- -->
- <uniqueKey>id</uniqueKey>
-
- <!-- copyField commands copy one field to another at the time a document
- is added to the index. It's used either to index the same field differently,
- or to add multiple fields to the same field for easier/faster searching.
-
- <copyField source="sourceFieldName" dest="destinationFieldName"/>
- -->
-
- <!-- field type definitions. The "name" attribute is
- just a label to be used by field definitions. The "class"
- attribute and any other attributes determine the real
- behavior of the fieldType.
- Class names starting with "solr" refer to java classes in a
- standard package such as org.apache.solr.analysis
- -->
-
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- It supports doc values but in that case the field needs to be
- single-valued and either required or have a default value.
- -->
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
- <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
-
- <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
-
- <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
- currently supported on types that are sorted internally as strings
- and on numeric types.
- This includes "string","boolean", "int", "float", "long", "date", "double",
- including the "Trie" and "Point" variants.
- - If sortMissingLast="true", then a sort on this field will cause documents
- without the field to come after documents with the field,
- regardless of the requested sort order (asc or desc).
- - If sortMissingFirst="true", then a sort on this field will cause documents
- without the field to come before documents with the field,
- regardless of the requested sort order.
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
- then default lucene sorting will be used which places docs without the
- field first in an ascending sort and last in a descending sort.
- -->
-
- <!--
- Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
- search time and at index time, but some features are still not supported.
- Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
- -->
- <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
- <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
- <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
- <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
-
- <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
- <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
- <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
- <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
-
- <!--
- Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
- tint/tfloat/tlong/tdouble types.
- -->
- <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-
- <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-
- <!--
- Numeric field types that index each value at various levels of precision
- to accelerate range queries when the number of values between the range
- endpoints is large. See the javadoc for NumericRangeQuery for internal
- implementation details.
-
- Smaller precisionStep values (specified in bits) will lead to more tokens
- indexed per value, slightly larger index size, and faster range queries.
- A precisionStep of 0 disables indexing at different precision levels.
-
- Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
- -->
- <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-
- <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-
- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
- is a more restricted form of the canonical representation of dateTime
- http://www.w3.org/TR/xmlschema-2/#dateTime
- The trailing "Z" designates UTC time and is mandatory.
- Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
- All other components are mandatory.
-
- Expressions can also be used to denote calculations that should be
- performed relative to "NOW" to determine the value, ie...
-
- NOW/HOUR
- ... Round to the start of the current hour
- NOW-1DAY
- ... Exactly 1 day prior to now
- NOW/DAY+6MONTHS+3DAYS
- ... 6 months and 3 days in the future from the start of
- the current day
-
- Consult the TrieDateField javadocs for more information.
- -->
- <!-- KD-tree versions of date fields -->
- <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
- <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
-
- <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
- <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
-
-
- <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
- <fieldType name="binary" class="solr.BinaryField"/>
-
- <!-- The "RandomSortField" is not used to store or search any
- data. You can declare fields of this type it in your schema
- to generate pseudo-random orderings of your docs for sorting
- or function purposes. The ordering is generated based on the field
- name and the version of the index. As long as the index version
- remains unchanged, and the same field name is reused,
- the ordering of the docs will be consistent.
- If you want different psuedo-random orderings of documents,
- for the same version of the index, use a dynamicField and
- change the field name in the request.
- -->
- <fieldType name="random" class="solr.RandomSortField" indexed="true" />
-
- <!-- solr.TextField allows the specification of custom text analyzers
- specified as a tokenizer and a list of token filters. Different
- analyzers may be specified for indexing and querying.
-
- The optional positionIncrementGap puts space between multiple fields of
- this type on the same document, with the purpose of preventing false phrase
- matching across fields.
-
- For more info on customizing your analyzer chain, please see
- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
- -->
-
- <!-- One can also specify an existing Analyzer class that has a
- default constructor via the class attribute on the analyzer element.
- Example:
- <fieldType name="text_greek" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
- </fieldType>
- -->
-
- <!-- A text field that only splits on whitespace for exact matching of words -->
- <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
- <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A general text field that has reasonable, generic
- cross-language defaults: it tokenizes with StandardTokenizer,
- removes stop words from case-insensitive "stopwords.txt"
- (empty by default), and down cases. At query time only, it
- also applies synonyms.
- -->
- <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.FlattenGraphFilterFactory"/>
- -->
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English: it
- tokenizes with StandardTokenizer, removes English stop words
- (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
- finally applies Porter's stemming. The query time analyzer
- also applies synonyms from synonyms.txt. -->
- <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
- <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.FlattenGraphFilterFactory"/>
- -->
- <!-- Case insensitive stop word removal.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English, plus
- aggressive word-splitting and autophrase features enabled.
- This field is just like text_en, except it adds
- WordDelimiterGraphFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and
- non-alphanumeric chars. This means certain compound word
- cases will work, for example query "wi fi" will match
- document "WiFi" or "wi-fi".
- -->
- <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
- <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- -->
- <!-- Case insensitive stop word removal.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- <filter class="solr.FlattenGraphFilterFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
- <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
- <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- <filter class="solr.FlattenGraphFilterFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Just like text_general except it reverses the characters of
- each token, to enable more efficient leading wildcard queries.
- -->
- <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
- <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
- <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
- </analyzer>
- </fieldType>
-
- <!-- lowercases the entire field value, keeping it as a single token. -->
- <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Example of using PathHierarchyTokenizerFactory at index time, so
- queries for paths match documents at that path, or in descendent paths
- -->
- <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
- <fieldType name="descendent_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Example of using PathHierarchyTokenizerFactory at query time, so
- queries for paths match documents at that path, or in ancestor paths
- -->
- <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
- <fieldType name="ancestor_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- </fieldType>
-
- <!-- since fields of this type are by default not stored or indexed,
- any data added to them will be ignored outright. -->
- <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
-
- <!-- This point type indexes the coordinates as separate fields (subFields)
- If subFieldType is defined, it references a type, and a dynamic field
- definition is created matching *___<typename>. Alternately, if
- subFieldSuffix is defined, that is used to create the subFields.
- Example: if subFieldType="double", then the coordinates would be
- indexed in fields myloc_0___double,myloc_1___double.
- Example: if subFieldSuffix="_d" then the coordinates would be indexed
- in fields myloc_0_d,myloc_1_d
- The subFields are an implementation detail of the fieldType, and end
- users normally should not need to know about them.
- -->
- <dynamicField name="*_point" type="point" indexed="true" stored="true"/>
- <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
-
- <!-- A specialized field for geospatial search filters and distance sorting. -->
- <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
-
- <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
- For more information about this and other Spatial fields new to Solr 4, see:
- http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
- -->
- <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
- geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
-
- <!-- Payloaded field types -->
- <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </analyzer>
- </fieldType>
- <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
- </analyzer>
- </fieldType>
- <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
- </analyzer>
- </fieldType>
-
- <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
- Parameters:
- defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
- precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
- providerClass: Lets you plug in other exchange provider backend:
- solr.FileExchangeRateProvider is the default and takes one parameter:
- currencyConfig: name of an xml file holding exchange rates
- solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
- ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
- refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
- -->
- <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
-
-
-
- <!-- some examples for different languages (generally ordered by ISO code) -->
-
- <!-- Arabic -->
- <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
- <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- for any non-arabic -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
- <!-- normalizes ﻯ to ﻱ, etc -->
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.ArabicStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Bulgarian -->
- <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
- <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
- <filter class="solr.BulgarianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Catalan -->
- <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
- <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
- </analyzer>
- </fieldType>
-
- <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
- <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
- <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- for any non-CJK -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.CJKBigramFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Czech -->
- <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
- <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
- <filter class="solr.CzechStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Danish -->
- <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
- <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
- </analyzer>
- </fieldType>
-
- <!-- German -->
- <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
- <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
- <filter class="solr.GermanNormalizationFilterFactory"/>
- <filter class="solr.GermanLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Greek -->
- <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
- <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- greek specific lowercase for sigma -->
- <filter class="solr.GreekLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
- <filter class="solr.GreekStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Spanish -->
- <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
- <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
- <filter class="solr.SpanishLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Basque -->
- <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
- <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
- </analyzer>
- </fieldType>
-
- <!-- Persian -->
- <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
- <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <!-- for ZWNJ -->
- <charFilter class="solr.PersianCharFilterFactory"/>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.PersianNormalizationFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
- </analyzer>
- </fieldType>
-
- <!-- Finnish -->
- <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
- <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
- <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- French -->
- <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
- <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
- <filter class="solr.FrenchLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Irish -->
- <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
- <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes d', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
- <!-- removes n-, etc. position increments is intentionally false! -->
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
- <filter class="solr.IrishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
- </analyzer>
- </fieldType>
-
- <!-- Galician -->
- <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
- <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
- <filter class="solr.GalicianStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Hindi -->
- <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
- <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <!-- normalizes unicode representation -->
- <filter class="solr.IndicNormalizationFilterFactory"/>
- <!-- normalizes variation in spelling -->
- <filter class="solr.HindiNormalizationFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
- <filter class="solr.HindiStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Hungarian -->
- <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
- <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
- <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Armenian -->
- <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
- <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
- </analyzer>
- </fieldType>
-
- <!-- Indonesian -->
- <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
- <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
- <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
- <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
- </analyzer>
- </fieldType>
-
- <!-- Italian -->
- <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
- <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
- <filter class="solr.ItalianLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
-
- NOTE: If you want to optimize search for precision, use default operator AND in your request
- handler config (q.op) Use OR if you would like to optimize for recall (default).
- -->
- <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
- <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
- <analyzer>
- <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
-
- Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
- is used to segment compounds into its parts and the compound itself is kept as synonym.
-
- Valid values for attribute mode are:
- normal: regular segmentation
- search: segmentation useful for search with synonyms compounds (default)
- extended: same as search mode, but unigrams unknown words (experimental)
-
- For some applications it might be good to use search mode for indexing and normal mode for
- queries to reduce recall and prevent parts of compounds from being matched and highlighted.
- Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
-
- Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
- model with your own entries for segmentation, part-of-speech tags and readings without a need
- to specify weights. Notice that user dictionaries have not been subject to extensive testing.
-
- User dictionary attributes are:
- userDictionary: user dictionary filename
- userDictionaryEncoding: user dictionary encoding (default is UTF-8)
-
- See lang/userdict_ja.txt for a sample user dictionary file.
-
- Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
-
- See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
- -->
- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
- <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
- <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
- <!-- Removes tokens with certain part-of-speech tags -->
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
- <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
- <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
- <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
- <!-- Lower-cases romaji characters -->
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Latvian -->
- <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
- <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
- <filter class="solr.LatvianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Dutch -->
- <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
- <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
- <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
- </analyzer>
- </fieldType>
-
- <!-- Norwegian -->
- <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
- <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
- <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
- <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Portuguese -->
- <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
- <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
- <filter class="solr.PortugueseLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
- <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Romanian -->
- <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
- <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
- </analyzer>
- </fieldType>
-
- <!-- Russian -->
- <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
- <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
- <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Swedish -->
- <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
- <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
- <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Thai -->
- <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
- <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.ThaiTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
- </analyzer>
- </fieldType>
-
- <!-- Turkish -->
- <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
- <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
- </analyzer>
- </fieldType>
-
- <!-- Similarity is the scoring routine for each document vs. a query.
- A custom Similarity or SimilarityFactory may be specified here, but
- the default is fine for most applications.
- For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
- -->
- <!--
- <similarity class="com.example.solr.CustomSimilarityFactory">
- <str name="paramkey">param value</str>
- </similarity>
- -->
-
-</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/params.json
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/params.json b/solr/server/solr/configsets/_default/conf/params.json
deleted file mode 100644
index 06114ef..0000000
--- a/solr/server/solr/configsets/_default/conf/params.json
+++ /dev/null
@@ -1,20 +0,0 @@
-{"params":{
- "query":{
- "defType":"edismax",
- "q.alt":"*:*",
- "rows":"10",
- "fl":"*,score",
- "":{"v":0}
- },
- "facets":{
- "facet":"on",
- "facet.mincount": "1",
- "":{"v":0}
- },
- "velocity":{
- "wt": "velocity",
- "v.template":"browse",
- "v.layout": "layout",
- "":{"v":0}
- }
-}}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/_default/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/_default/conf/protwords.txt b/solr/server/solr/configsets/_default/conf/protwords.txt
deleted file mode 100644
index 1dfc0ab..0000000
--- a/solr/server/solr/configsets/_default/conf/protwords.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# Use a protected word file to protect against the stemmer reducing two
-# unrelated words to the same base word.
-
-# Some non-words that normally won't be encountered,
-# just to test that they won't be stemmed.
-dontstems
-zwhacky
-
[08/50] [abbrv] lucene-solr:feature/autoscaling: Adds documentation
for the cartesianProduct
Posted by sh...@apache.org.
Adds documentation for the cartesianProduct
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/fffbe67b
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/fffbe67b
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/fffbe67b
Branch: refs/heads/feature/autoscaling
Commit: fffbe67b3b0f919f828df294916c071341f473f0
Parents: 42fdb54
Author: Dennis Gove <dp...@gmail.com>
Authored: Tue Jun 13 08:12:32 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Sun Jun 18 11:50:46 2017 -0400
----------------------------------------------------------------------
solr/solr-ref-guide/src/stream-decorators.adoc | 364 ++++++++++++++++++++
1 file changed, 364 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/fffbe67b/solr/solr-ref-guide/src/stream-decorators.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/stream-decorators.adoc b/solr/solr-ref-guide/src/stream-decorators.adoc
index c4ab4f4..e65f18a 100644
--- a/solr/solr-ref-guide/src/stream-decorators.adoc
+++ b/solr/solr-ref-guide/src/stream-decorators.adoc
@@ -20,6 +20,370 @@
// specific language governing permissions and limitations
// under the License.
+== cartesianProduct
+
+The `cartesianProduct` function turns a single tuple with a multi-valued field (ie. an array) into multiple tuples, one for each value in the array field. That is, given a single tuple containing an array of N values for fieldA, the `cartesianProduct` function will output N tuples, each with one value from the original tuple's array. In essence, you can flatten arrays for further processing.
+
+For example, using `cartesianProduct` you can turn this tuple
+[source,text]
+----
+{
+ "fieldA": "foo",
+ "fieldB": ["bar","baz","bat"]
+}
+----
+
+into the following 3 tuples
+[source,text]
+----
+{
+ "fieldA": "foo",
+ "fieldB": "bar"
+}
+{
+ "fieldA": "foo",
+ "fieldB": "baz"
+}
+{
+ "fieldA": "foo",
+ "fieldB": "bat"
+}
+----
+
+=== cartesianProduct Parameters
+
+* `incoming stream`: (Mandatory) A single incoming stream.
+* `fieldName or evaluator`: (Mandatory) Name of field to flatten values for, or evaluator whose result should be flattened.
+* `productSort='fieldName ASC|DESC'`: (Optional) Sort order of the newly generated tuples.
+
+=== cartesianProduct Syntax
+
+[source,text]
+----
+cartesianProduct(
+ <stream>,
+ <fieldName | evaluator> [as newFieldName],
+ productSort='fieldName ASC|DESC'
+)
+----
+
+=== cartesianProduct Examples
+
+The following examples show different outputs for this source tuple
+
+[source,text]
+----
+{
+ "fieldA": "valueA",
+ "fieldB": ["valueB1","valueB2"],
+ "fieldC": [1,2,3]
+}
+----
+
+==== Single Field, No Sorting
+
+[source,text]
+----
+cartesianProduct(
+ search(collection1, q='*:*', fl='fieldA, fieldB, fieldC', sort='fieldA ASC'),
+ fieldB
+)
+
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": [1,2,3]
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": [1,2,3]
+}
+----
+
+==== Single Evaluator, No Sorting
+
+[source,text]
+----
+cartesianProduct(
+ search(collection1, q='*:*', fl='fieldA, fieldB, fieldC', sort='fieldA ASC'),
+ sequence(3,4,5) as fieldE
+)
+
+{
+ "fieldA": "valueA",
+ "fieldB": ["valueB1","valueB2"],
+ "fieldC": [1,2,3],
+ "fieldE": 4
+}
+{
+ "fieldA": "valueA",
+ "fieldB": ["valueB1","valueB2"],
+ "fieldC": [1,2,3],
+ "fieldE": 9
+}
+{
+ "fieldA": "valueA",
+ "fieldB": ["valueB1","valueB2"],
+ "fieldC": [1,2,3],
+ "fieldE": 14
+}
+----
+
+==== Single Field, Sorted by Value
+
+[source,text]
+----
+cartesianProduct(
+ search(collection1, q='*:*', fl='fieldA, fieldB, fieldC', sort='fieldA ASC'),
+ fieldB,
+ productSort="fieldB DESC"
+)
+
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": [1,2,3]
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": [1,2,3]
+}
+----
+
+==== Single Evaluator, Sorted by Evaluator Values
+
+[source,text]
+----
+cartesianProduct(
+ search(collection1, q='*:*', fl='fieldA, fieldB, fieldC', sort='fieldA ASC'),
+ sequence(3,4,5) as fieldE,
+ productSort='newFieldE DESC'
+)
+
+{
+ "fieldA": "valueA",
+ "fieldB": ["valueB1","valueB2"],
+ "fieldC": [1,2,3],
+ "fieldE": 14
+}
+{
+ "fieldA": "valueA",
+ "fieldB": ["valueB1","valueB2"],
+ "fieldC": [1,2,3],
+ "fieldE": 9
+}
+{
+ "fieldA": "valueA",
+ "fieldB": ["valueB1","valueB2"],
+ "fieldC": [1,2,3],
+ "fieldE": 4
+}
+----
+
+==== Renamed Single Field, Sorted by Value
+
+[source,text]
+----
+cartesianProduct(
+ search(collection1, q='*:*', fl='fieldA, fieldB, fieldC', sort='fieldA ASC'),
+ fieldB as newFieldB,
+ productSort="fieldB DESC"
+)
+
+{
+ "fieldA": "valueA",
+ "fieldB": ["valueB1","valueB2"],
+ "fieldC": [1,2,3]
+ "newFieldB": "valueB2",
+}
+{
+ "fieldA": "valueA",
+ "fieldB": ["valueB1","valueB2"],
+ "fieldC": [1,2,3]
+ "newFieldB": "valueB1",
+}
+----
+
+==== Multiple Fields, No Sorting
+
+[source,text]
+----
+cartesianProduct(
+ search(collection1, q='*:*', fl='fieldA, fieldB, fieldC', sort='fieldA ASC'),
+ fieldB,
+ fieldC
+)
+
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": 1
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": 2
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": 3
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": 1
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": 2
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": 3
+}
+----
+
+==== Multiple Fields, Sorted by Single Field
+
+[source,text]
+----
+cartesianProduct(
+ search(collection1, q='*:*', fl='fieldA, fieldB, fieldC', sort='fieldA ASC'),
+ fieldB,
+ fieldC,
+ productSort="fieldC ASC"
+)
+
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": 1
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": 1
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": 2
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": 2
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": 3
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": 3
+}
+----
+
+==== Multiple Fields, Sorted by Multiple Fields
+
+[source,text]
+----
+cartesianProduct(
+ search(collection1, q='*:*', fl='fieldA, fieldB, fieldC', sort='fieldA ASC'),
+ fieldB,
+ fieldC,
+ productSort="fieldC ASC, fieldB DESC"
+)
+
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": 1
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": 1
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": 2
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": 2
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB2",
+ "fieldC": 3
+}
+{
+ "fieldA": "valueA",
+ "fieldB": "valueB1",
+ "fieldC": 3
+}
+----
+
+==== Field and Evaluator, No Sorting
+
+[source,text]
+----
+cartesianProduct(
+ search(collection1, q='*:*', fl='fieldA, fieldB, fieldC', sort='fieldA ASC'),
+ sequence(3,4,5) as fieldE,
+ fieldB
+)
+
+{
+ "fieldA": "valueA",
+ "fieldB": valueB1,
+ "fieldC": [1,2,3],
+ "fieldE": 4
+}
+{
+ "fieldA": "valueA",
+ "fieldB": valueB2,
+ "fieldC": [1,2,3],
+ "fieldE": 4
+}
+{
+ "fieldA": "valueA",
+ "fieldB": valueB1,
+ "fieldC": [1,2,3],
+ "fieldE": 9
+}
+{
+ "fieldA": "valueA",
+ "fieldB": valueB2,
+ "fieldC": [1,2,3],
+ "fieldE": 9
+}
+{
+ "fieldA": "valueA",
+ "fieldB": valueB1,
+ "fieldC": [1,2,3],
+ "fieldE": 14
+}
+{
+ "fieldA": "valueA",
+ "fieldB": valueB2,
+ "fieldC": [1,2,3],
+ "fieldE": 14
+}
+----
+
+As you can see in the examples above, the `cartesianProduct` function does support flattening tuples across multiple fields and/or evaluators.
+
== classify
The `classify` function classifies tuples using a logistic regression text classification model. It was designed specifically to work with models trained using the <<stream-sources.adoc#train,train function>>. The `classify` function uses the <<stream-sources.adoc#model,model function>> to retrieve a stored model and then scores a stream of tuples using the model. The tuples read by the classifier must contain a text field that can be used for classification. The classify function uses a Lucene analyzer to extract the features from the text so the model can be applied. By default the `classify` function looks for the analyzer using the name of text field in the tuple. If the Solr schema on the worker node does not contain this field, the analyzer can be looked up in another field by specifying the `analyzerField` parameter.
[06/50] [abbrv] lucene-solr:feature/autoscaling: LUCENE-7719:
Generalize UnifiedHighlighter's support for AutomatonQuery
Posted by sh...@apache.org.
LUCENE-7719: Generalize UnifiedHighlighter's support for AutomatonQuery
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/d0b9d345
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/d0b9d345
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/d0b9d345
Branch: refs/heads/feature/autoscaling
Commit: d0b9d3459fd097dba677cdda170632f6fca5e042
Parents: b49ce68
Author: David Smiley <ds...@apache.org>
Authored: Fri Jun 16 22:57:51 2017 -0400
Committer: David Smiley <ds...@apache.org>
Committed: Fri Jun 16 22:57:51 2017 -0400
----------------------------------------------------------------------
lucene/CHANGES.txt | 3 +
.../apache/lucene/search/AutomatonQuery.java | 7 ++
.../uhighlight/MemoryIndexOffsetStrategy.java | 3 +-
.../uhighlight/MultiTermHighlighting.java | 124 ++++++++-----------
.../uhighlight/TestUnifiedHighlighterMTQ.java | 69 ++++++++++-
5 files changed, 128 insertions(+), 78 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d0b9d345/lucene/CHANGES.txt
----------------------------------------------------------------------
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index 595ed12..e708888 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -130,6 +130,9 @@ Other
* LUCENE-7852: Correct copyright year(s) in lucene/LICENSE.txt file.
(Christine Poerschke, Steve Rowe)
+* LUCENE-7719: Generalized the UnifiedHighlighter's support for AutomatonQuery
+ for character & binary automata. Added AutomatonQuery.isBinary. (David Smiley)
+
======================= Lucene 6.7.0 =======================
New Features
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d0b9d345/lucene/core/src/java/org/apache/lucene/search/AutomatonQuery.java
----------------------------------------------------------------------
diff --git a/lucene/core/src/java/org/apache/lucene/search/AutomatonQuery.java b/lucene/core/src/java/org/apache/lucene/search/AutomatonQuery.java
index 3b113a2..7fb155d 100644
--- a/lucene/core/src/java/org/apache/lucene/search/AutomatonQuery.java
+++ b/lucene/core/src/java/org/apache/lucene/search/AutomatonQuery.java
@@ -51,6 +51,7 @@ public class AutomatonQuery extends MultiTermQuery {
protected final CompiledAutomaton compiled;
/** term containing the field, and possibly some pattern structure */
protected final Term term;
+ protected final boolean automatonIsBinary;
/**
* Create a new AutomatonQuery from an {@link Automaton}.
@@ -98,6 +99,7 @@ public class AutomatonQuery extends MultiTermQuery {
super(term.field());
this.term = term;
this.automaton = automaton;
+ this.automatonIsBinary = isBinary;
// TODO: we could take isFinite too, to save a bit of CPU in CompiledAutomaton ctor?:
this.compiled = new CompiledAutomaton(automaton, null, true, maxDeterminizedStates, isBinary);
}
@@ -154,4 +156,9 @@ public class AutomatonQuery extends MultiTermQuery {
public Automaton getAutomaton() {
return automaton;
}
+
+ /** Is this a binary (byte) oriented automaton. See the constructor. */
+ public boolean isAutomatonBinary() {
+ return automatonIsBinary;
+ }
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d0b9d345/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MemoryIndexOffsetStrategy.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MemoryIndexOffsetStrategy.java b/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MemoryIndexOffsetStrategy.java
index 0001a80..cf7a3c9 100644
--- a/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MemoryIndexOffsetStrategy.java
+++ b/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MemoryIndexOffsetStrategy.java
@@ -83,8 +83,7 @@ public class MemoryIndexOffsetStrategy extends AnalysisOffsetStrategy {
return allAutomata.get(0);
}
//TODO it'd be nice if we could get at the underlying Automaton in CharacterRunAutomaton so that we
- // could union them all. But it's not exposed, and note TermRangeQuery isn't modelled as an Automaton
- // by MultiTermHighlighting.
+ // could union them all. But it's not exposed, and sometimes the automaton is byte (not char) oriented
// Return an aggregate CharacterRunAutomaton of others
return new CharacterRunAutomaton(Automata.makeEmpty()) {// the makeEmpty() is bogus; won't be used
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d0b9d345/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MultiTermHighlighting.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MultiTermHighlighting.java b/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MultiTermHighlighting.java
index 15f4bdd..e745d78 100644
--- a/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MultiTermHighlighting.java
+++ b/lucene/highlighter/src/java/org/apache/lucene/search/uhighlight/MultiTermHighlighting.java
@@ -19,12 +19,10 @@ package org.apache.lucene.search.uhighlight;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collection;
-import java.util.Comparator;
import java.util.List;
import java.util.function.Function;
import java.util.function.Predicate;
-import org.apache.lucene.index.Term;
import org.apache.lucene.search.AutomatonQuery;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
@@ -32,19 +30,17 @@ import org.apache.lucene.search.BoostQuery;
import org.apache.lucene.search.ConstantScoreQuery;
import org.apache.lucene.search.DisjunctionMaxQuery;
import org.apache.lucene.search.FuzzyQuery;
-import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
-import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.spans.SpanBoostQuery;
import org.apache.lucene.search.spans.SpanMultiTermQueryWrapper;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanNotQuery;
import org.apache.lucene.search.spans.SpanOrQuery;
import org.apache.lucene.search.spans.SpanPositionCheckQuery;
-import org.apache.lucene.util.CharsRef;
import org.apache.lucene.util.UnicodeUtil;
import org.apache.lucene.util.automaton.Automata;
import org.apache.lucene.util.automaton.Automaton;
+import org.apache.lucene.util.automaton.ByteRunAutomaton;
import org.apache.lucene.util.automaton.CharacterRunAutomaton;
import org.apache.lucene.util.automaton.LevenshteinAutomata;
import org.apache.lucene.util.automaton.Operations;
@@ -110,18 +106,6 @@ class MultiTermHighlighting {
} else if (lookInSpan && query instanceof SpanMultiTermQueryWrapper) {
list.addAll(Arrays.asList(extractAutomata(((SpanMultiTermQueryWrapper<?>) query).getWrappedQuery(),
fieldMatcher, lookInSpan, preRewriteFunc)));
- } else if (query instanceof PrefixQuery) {
- final PrefixQuery pq = (PrefixQuery) query;
- Term prefix = pq.getPrefix();
- if (fieldMatcher.test(prefix.field())) {
- list.add(new CharacterRunAutomaton(Operations.concatenate(Automata.makeString(prefix.text()),
- Automata.makeAnyString())) {
- @Override
- public String toString() {
- return pq.toString();
- }
- });
- }
} else if (query instanceof FuzzyQuery) {
final FuzzyQuery fq = (FuzzyQuery) query;
if (fieldMatcher.test(fq.getField())) {
@@ -143,69 +127,63 @@ class MultiTermHighlighting {
}
});
}
- } else if (query instanceof TermRangeQuery) {
- final TermRangeQuery tq = (TermRangeQuery) query;
- if (fieldMatcher.test(tq.getField())) {
- final CharsRef lowerBound;
- if (tq.getLowerTerm() == null) {
- lowerBound = null;
- } else {
- lowerBound = new CharsRef(tq.getLowerTerm().utf8ToString());
- }
-
- final CharsRef upperBound;
- if (tq.getUpperTerm() == null) {
- upperBound = null;
- } else {
- upperBound = new CharsRef(tq.getUpperTerm().utf8ToString());
- }
-
- final boolean includeLower = tq.includesLower();
- final boolean includeUpper = tq.includesUpper();
- final CharsRef scratch = new CharsRef();
-
- @SuppressWarnings("deprecation")
- final Comparator<CharsRef> comparator = CharsRef.getUTF16SortedAsUTF8Comparator();
+ } else if (query instanceof AutomatonQuery) {
+ final AutomatonQuery aq = (AutomatonQuery) query;
+ if (fieldMatcher.test(aq.getField())) {
- // this is *not* an automaton, but its very simple
- list.add(new CharacterRunAutomaton(Automata.makeEmpty()) {
- @Override
- public boolean run(char[] s, int offset, int length) {
- scratch.chars = s;
- scratch.offset = offset;
- scratch.length = length;
+ if (aq.isAutomatonBinary() == false) { // note: is the case for WildcardQuery, RegexpQuery
+ list.add(new CharacterRunAutomaton(aq.getAutomaton()) {
+ @Override
+ public String toString() {
+ return aq.toString();
+ }
+ });
+ } else { // note: is the case for PrefixQuery, TermRangeQuery
+ // byte oriented automaton:
+ list.add(new CharacterRunAutomaton(Automata.makeEmpty()) { // empty here is bogus just to satisfy API
+ // TODO can we get access to the aq.compiledAutomaton.runAutomaton ?
+ ByteRunAutomaton byteRunAutomaton =
+ new ByteRunAutomaton(aq.getAutomaton(), true, Operations.DEFAULT_MAX_DETERMINIZED_STATES);
- if (lowerBound != null) {
- int cmp = comparator.compare(scratch, lowerBound);
- if (cmp < 0 || (!includeLower && cmp == 0)) {
- return false;
+ @Override
+ public boolean run(char[] chars, int offset, int length) {
+ int state = 0;
+ final int maxIdx = offset + length;
+ for (int i = offset; i < maxIdx; i++) {
+ final int code = chars[i];
+ int b;
+ // UTF16 to UTF8 (inlined logic from UnicodeUtil.UTF16toUTF8 )
+ if (code < 0x80) {
+ state = byteRunAutomaton.step(state, code);
+ if (state == -1) return false;
+ } else if (code < 0x800) {
+ b = (0xC0 | (code >> 6));
+ state = byteRunAutomaton.step(state, b);
+ if (state == -1) return false;
+ b = (0x80 | (code & 0x3F));
+ state = byteRunAutomaton.step(state, b);
+ if (state == -1) return false;
+ } else {
+ // more complex
+ byte[] utf8Bytes = new byte[4 * (maxIdx - i)];
+ int utf8Len = UnicodeUtil.UTF16toUTF8(chars, i, maxIdx - i, utf8Bytes);
+ for (int utfIdx = 0; utfIdx < utf8Len; utfIdx++) {
+ state = byteRunAutomaton.step(state, utf8Bytes[utfIdx] & 0xFF);
+ if (state == -1) return false;
+ }
+ break;
+ }
}
+ return byteRunAutomaton.isAccept(state);
}
- if (upperBound != null) {
- int cmp = comparator.compare(scratch, upperBound);
- if (cmp > 0 || (!includeUpper && cmp == 0)) {
- return false;
- }
+ @Override
+ public String toString() {
+ return aq.toString();
}
- return true;
- }
+ });
+ }
- @Override
- public String toString() {
- return tq.toString();
- }
- });
- }
- } else if (query instanceof AutomatonQuery) {
- final AutomatonQuery aq = (AutomatonQuery) query;
- if (fieldMatcher.test(aq.getField())) {
- list.add(new CharacterRunAutomaton(aq.getAutomaton()) {
- @Override
- public String toString() {
- return aq.toString();
- }
- });
}
}
return list.toArray(new CharacterRunAutomaton[list.size()]);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d0b9d345/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterMTQ.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterMTQ.java b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterMTQ.java
index 57f174f..ac99c79 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterMTQ.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/uhighlight/TestUnifiedHighlighterMTQ.java
@@ -24,11 +24,13 @@ import java.util.List;
import java.util.Objects;
import com.carrotsearch.randomizedtesting.annotations.ParametersFactory;
+import com.carrotsearch.randomizedtesting.generators.RandomStrings;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.core.KeywordAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
@@ -63,16 +65,15 @@ import org.apache.lucene.search.spans.SpanQuery;
import org.apache.lucene.search.spans.SpanTermQuery;
import org.apache.lucene.search.spans.SpanWeight;
import org.apache.lucene.store.BaseDirectoryWrapper;
+import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.LuceneTestCase;
-import org.apache.lucene.util.LuceneTestCase.SuppressCodecs;
+import org.apache.lucene.util.UnicodeUtil;
import org.junit.After;
import org.junit.Before;
/**
* Some tests that highlight wildcard, fuzzy, etc queries.
*/
-@SuppressCodecs({"MockFixedIntBlock", "MockVariableIntBlock", "MockSep", "MockRandom", "Lucene3x"})
-@LuceneTestCase.SuppressSysoutChecks(bugUrl = "")//Gradle interferes with this Lucene test rule
public class TestUnifiedHighlighterMTQ extends LuceneTestCase {
final FieldType fieldType;
@@ -1079,4 +1080,66 @@ public class TestUnifiedHighlighterMTQ extends LuceneTestCase {
assertEquals("[<b>я</b>]", Arrays.toString(snippets));
ir.close();
}
+
+ // LUCENE-7719
+ public void testMultiByteMTQ() throws IOException {
+ Analyzer analyzer = new KeywordAnalyzer();
+ try (RandomIndexWriter iw = new RandomIndexWriter(random(), dir, analyzer)) {
+ for (int attempt = 0; attempt < 20; attempt++) {
+ iw.deleteAll();
+ String field = "title";
+ String value = RandomStrings.randomUnicodeOfLength(random(), 3);
+ if (value.contains(UnifiedHighlighter.MULTIVAL_SEP_CHAR+"")) { // will throw things off
+ continue;
+ }
+ int[] valuePoints = value.codePoints().toArray();
+
+ iw.addDocument(Collections.singleton(
+ new Field(field, value, fieldType)));
+ iw.commit();
+ try (IndexReader ir = iw.getReader()) {
+ IndexSearcher searcher = newSearcher(ir);
+ UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, analyzer);
+ highlighter.setBreakIterator(WholeBreakIterator::new);
+
+ // Test PrefixQuery
+ Query query = new PrefixQuery(new Term(field,
+ UnicodeUtil.newString(valuePoints, 0, 1)));
+ highlightAndAssertMatch(searcher, highlighter, query, field, value);
+
+ // Test TermRangeQuery
+ query = new TermRangeQuery(field,
+ new BytesRef(value),
+ new BytesRef(value),
+ true, true );
+ highlightAndAssertMatch(searcher, highlighter, query, field, value);
+
+ // Test FuzzyQuery
+ query = new FuzzyQuery(new Term(field, value + "Z"), 1);
+ highlightAndAssertMatch(searcher, highlighter, query, field, value);
+
+ if (valuePoints.length != 3) {
+ continue; // even though we ask RandomStrings for a String with 3 code points, it seems sometimes it's less
+ }
+
+ // Test WildcardQuery
+ query = new WildcardQuery(new Term(field,
+ new StringBuilder()
+ .append(WildcardQuery.WILDCARD_ESCAPE).appendCodePoint(valuePoints[0])
+ .append(WildcardQuery.WILDCARD_CHAR)
+ .append(WildcardQuery.WILDCARD_ESCAPE).appendCodePoint(valuePoints[2]).toString()));
+ highlightAndAssertMatch(searcher, highlighter, query, field, value);
+
+ //TODO hmmm; how to randomly generate RegexpQuery? Low priority; we've covered the others well.
+ }
+ }
+ }
+ }
+
+ private void highlightAndAssertMatch(IndexSearcher searcher, UnifiedHighlighter highlighter, Query query, String field, String fieldVal) throws IOException {
+ TopDocs topDocs = searcher.search(query, 1);
+ assertEquals(1, topDocs.totalHits);
+ String[] snippets = highlighter.highlight(field, query, topDocs);
+ assertEquals("[<b>"+fieldVal+"</b>]", Arrays.toString(snippets));
+ }
}
[03/50] [abbrv] lucene-solr:feature/autoscaling: Ref Guide: Add ceil
evaluator docs
Posted by sh...@apache.org.
Ref Guide: Add ceil evaluator docs
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/1a009500
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/1a009500
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/1a009500
Branch: refs/heads/feature/autoscaling
Commit: 1a009500212f4ab679f059eec10ba73075d1fb1f
Parents: 584b69d
Author: Joel Bernstein <jb...@apache.org>
Authored: Fri Jun 16 14:29:31 2017 -0400
Committer: Joel Bernstein <jb...@apache.org>
Committed: Fri Jun 16 14:29:31 2017 -0400
----------------------------------------------------------------------
solr/solr-ref-guide/src/stream-evaluators.adoc | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a009500/solr/solr-ref-guide/src/stream-evaluators.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/stream-evaluators.adoc b/solr/solr-ref-guide/src/stream-evaluators.adoc
index bc6d13e..7f46312 100644
--- a/solr/solr-ref-guide/src/stream-evaluators.adoc
+++ b/solr/solr-ref-guide/src/stream-evaluators.adoc
@@ -229,9 +229,25 @@ mod(100,3) // returns the remainder of 100 / 3 .
mod(100,fieldA) // returns the remainder of 100 divided by the value of fieldA.
mod(fieldA,1.4) // returns the remainder of fieldA divided by 1.4.
if(gt(fieldA,fieldB),mod(fieldA,fieldB),mod(fieldB,fieldA)) // if fieldA > fieldB then return the remainder of fieldA/fieldB, else return the remainder of fieldB/fieldA.
+----
=== ceil
-//TODO
+The `ceil` function rounds a decimal value to the next highest whole number.
+
+=== ceil Parameters
+
+* `Field Name | Raw Number | Number Evaluator`: The decimal to round up.
+
+=== ceil Syntax
+
+The expressions below show the various ways in which you can use the `ceil` evaluator.
+
+[source,text]
+----
+ceil(100.4) // returns the remainder of 100.
+ceil(fieldA) // returns the next highest whole number for fieldA.
+if(gt(fieldA,fieldB),ceil(fieldA),ceil(fieldB)) // if fieldA > fieldB then return the ceil of fieldA, else return the ceil of fieldB.
+----
== floor
//TODO
[24/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ru.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ru.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ru.txt
deleted file mode 100644
index 5527140..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ru.txt
+++ /dev/null
@@ -1,243 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | a russian stop word list. comments begin with vertical bar. each stop
- | word is at the start of a line.
-
- | this is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
- | letter `ё' is translated to `е'.
-
-и | and
-в | in/into
-во | alternative form
-не | not
-что | what/that
-он | he
-на | on/onto
-я | i
-с | from
-со | alternative form
-как | how
-а | milder form of `no' (but)
-то | conjunction and form of `that'
-все | all
-она | she
-так | so, thus
-его | him
-но | but
-да | yes/and
-ты | thou
-к | towards, by
-у | around, chez
-же | intensifier particle
-вы | you
-за | beyond, behind
-бы | conditional/subj. particle
-по | up to, along
-только | only
-ее | her
-мне | to me
-было | it was
-вот | here is/are, particle
-от | away from
-меня | me
-еще | still, yet, more
-нет | no, there isnt/arent
-о | about
-из | out of
-ему | to him
-теперь | now
-когда | when
-даже | even
-ну | so, well
-вдруг | suddenly
-ли | interrogative particle
-если | if
-уже | already, but homonym of `narrower'
-или | or
-ни | neither
-быть | to be
-был | he was
-него | prepositional form of его
-до | up to
-вас | you accusative
-нибудь | indef. suffix preceded by hyphen
-опять | again
-уж | already, but homonym of `adder'
-вам | to you
-сказал | he said
-ведь | particle `after all'
-там | there
-потом | then
-себя | oneself
-ничего | nothing
-ей | to her
-может | usually with `быть' as `maybe'
-они | they
-тут | here
-где | where
-есть | there is/are
-надо | got to, must
-ней | prepositional form of ей
-для | for
-мы | we
-тебя | thee
-их | them, their
-чем | than
-была | she was
-сам | self
-чтоб | in order to
-без | without
-будто | as if
-человек | man, person, one
-чего | genitive form of `what'
-раз | once
-тоже | also
-себе | to oneself
-под | beneath
-жизнь | life
-будет | will be
-ж | short form of intensifer particle `же'
-тогда | then
-кто | who
-этот | this
-говорил | was saying
-того | genitive form of `that'
-потому | for that reason
-этого | genitive form of `this'
-какой | which
-совсем | altogether
-ним | prepositional form of `его', `они'
-здесь | here
-этом | prepositional form of `этот'
-один | one
-почти | almost
-мой | my
-тем | instrumental/dative plural of `тот', `то'
-чтобы | full form of `in order that'
-нее | her (acc.)
-кажется | it seems
-сейчас | now
-были | they were
-куда | where to
-зачем | why
-сказать | to say
-всех | all (acc., gen. preposn. plural)
-никогда | never
-сегодня | today
-можно | possible, one can
-при | by
-наконец | finally
-два | two
-об | alternative form of `о', about
-другой | another
-хоть | even
-после | after
-над | above
-больше | more
-тот | that one (masc.)
-через | across, in
-эти | these
-нас | us
-про | about
-всего | in all, only, of all
-них | prepositional form of `они' (they)
-какая | which, feminine
-много | lots
-разве | interrogative particle
-сказала | she said
-три | three
-эту | this, acc. fem. sing.
-моя | my, feminine
-впрочем | moreover, besides
-хорошо | good
-свою | ones own, acc. fem. sing.
-этой | oblique form of `эта', fem. `this'
-перед | in front of
-иногда | sometimes
-лучше | better
-чуть | a little
-том | preposn. form of `that one'
-нельзя | one must not
-такой | such a one
-им | to them
-более | more
-всегда | always
-конечно | of course
-всю | acc. fem. sing of `all'
-между | between
-
-
- | b: some paradigms
- |
- | personal pronouns
- |
- | я меня мне мной [мною]
- | ты тебя тебе тобой [тобою]
- | он его ему им [него, нему, ним]
- | она ее эи ею [нее, нэи, нею]
- | оно его ему им [него, нему, ним]
- |
- | мы нас нам нами
- | вы вас вам вами
- | они их им ими [них, ним, ними]
- |
- | себя себе собой [собою]
- |
- | demonstrative pronouns: этот (this), тот (that)
- |
- | этот эта это эти
- | этого эты это эти
- | этого этой этого этих
- | этому этой этому этим
- | этим этой этим [этою] этими
- | этом этой этом этих
- |
- | тот та то те
- | того ту то те
- | того той того тех
- | тому той тому тем
- | тем той тем [тою] теми
- | том той том тех
- |
- | determinative pronouns
- |
- | (a) весь (all)
- |
- | весь вся все все
- | всего всю все все
- | всего всей всего всех
- | всему всей всему всем
- | всем всей всем [всею] всеми
- | всем всей всем всех
- |
- | (b) сам (himself etc)
- |
- | сам сама само сами
- | самого саму само самих
- | самого самой самого самих
- | самому самой самому самим
- | самим самой самим [самою] самими
- | самом самой самом самих
- |
- | stems of verbs `to be', `to have', `to do' and modal
- |
- | быть бы буд быв есть суть
- | име
- | дел
- | мог мож мочь
- | уме
- | хоч хот
- | долж
- | можн
- | нужн
- | нельзя
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_sv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_sv.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_sv.txt
deleted file mode 100644
index 096f87f..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_sv.txt
+++ /dev/null
@@ -1,133 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Swedish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
- | Swedish stop words occasionally exhibit homonym clashes. For example
- | så = so, but also seed. These are indicated clearly below.
-
-och | and
-det | it, this/that
-att | to (with infinitive)
-i | in, at
-en | a
-jag | I
-hon | she
-som | who, that
-han | he
-på | on
-den | it, this/that
-med | with
-var | where, each
-sig | him(self) etc
-för | for
-så | so (also: seed)
-till | to
-är | is
-men | but
-ett | a
-om | if; around, about
-hade | had
-de | they, these/those
-av | of
-icke | not, no
-mig | me
-du | you
-henne | her
-då | then, when
-sin | his
-nu | now
-har | have
-inte | inte någon = no one
-hans | his
-honom | him
-skulle | 'sake'
-hennes | her
-där | there
-min | my
-man | one (pronoun)
-ej | nor
-vid | at, by, on (also: vast)
-kunde | could
-något | some etc
-från | from, off
-ut | out
-när | when
-efter | after, behind
-upp | up
-vi | we
-dem | them
-vara | be
-vad | what
-över | over
-än | than
-dig | you
-kan | can
-sina | his
-här | here
-ha | have
-mot | towards
-alla | all
-under | under (also: wonder)
-någon | some etc
-eller | or (else)
-allt | all
-mycket | much
-sedan | since
-ju | why
-denna | this/that
-själv | myself, yourself etc
-detta | this/that
-åt | to
-utan | without
-varit | was
-hur | how
-ingen | no
-mitt | my
-ni | you
-bli | to be, become
-blev | from bli
-oss | us
-din | thy
-dessa | these/those
-några | some etc
-deras | their
-blir | from bli
-mina | my
-samma | (the) same
-vilken | who, that
-er | you, your
-sådan | such a
-vår | our
-blivit | from bli
-dess | its
-inom | within
-mellan | between
-sådant | such a
-varför | why
-varje | each
-vilka | who, that
-ditt | thy
-vem | who
-vilket | who, that
-sitta | his
-sådana | such a
-vart | each
-dina | thy
-vars | whose
-vårt | our
-våra | our
-ert | your
-era | your
-vilkas | whose
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_th.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_th.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_th.txt
deleted file mode 100644
index 07f0fab..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_th.txt
+++ /dev/null
@@ -1,119 +0,0 @@
-# Thai stopwords from:
-# "Opinion Detection in Thai Political News Columns
-# Based on Subjectivity Analysis"
-# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
-ไว้
-ไม่
-ไป
-ได้
-ให้
-ใน
-โดย
-แห่ง
-แล้ว
-และ
-แรก
-แบบ
-แต่
-เอง
-เห็น
-เลย
-เริ่ม
-เรา
-เมื่อ
-เพื่อ
-เพราะ
-เป็นการ
-เป็น
-เปิดเผย
-เปิด
-เนื่องจาก
-เดียวกัน
-เดียว
-เช่น
-เฉพาะ
-เคย
-เข้า
-เขา
-อีก
-อาจ
-อะไร
-ออก
-อย่าง
-อยู่
-อยาก
-หาก
-หลาย
-หลังจาก
-หลัง
-หรือ
-หนึ่ง
-ส่วน
-ส่ง
-สุด
-สําหรับ
-ว่า
-วัน
-ลง
-ร่วม
-ราย
-รับ
-ระหว่าง
-รวม
-ยัง
-มี
-มาก
-มา
-พร้อม
-พบ
-ผ่าน
-ผล
-บาง
-น่า
-นี้
-นํา
-นั้น
-นัก
-นอกจาก
-ทุก
-ที่สุด
-ที่
-ทําให้
-ทํา
-ทาง
-ทั้งนี้
-ทั้ง
-ถ้า
-ถูก
-ถึง
-ต้อง
-ต่างๆ
-ต่าง
-ต่อ
-ตาม
-ตั้งแต่
-ตั้ง
-ด้าน
-ด้วย
-ดัง
-ซึ่ง
-ช่วง
-จึง
-จาก
-จัด
-จะ
-คือ
-ความ
-ครั้ง
-คง
-ขึ้น
-ของ
-ขอ
-ขณะ
-ก่อน
-ก็
-การ
-กับ
-กัน
-กว่า
-กล่าว
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_tr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_tr.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_tr.txt
deleted file mode 100644
index 84d9408..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_tr.txt
+++ /dev/null
@@ -1,212 +0,0 @@
-# Turkish stopwords from LUCENE-559
-# merged with the list from "Information Retrieval on Turkish Texts"
-# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
-acaba
-altmış
-altı
-ama
-ancak
-arada
-aslında
-ayrıca
-bana
-bazı
-belki
-ben
-benden
-beni
-benim
-beri
-beş
-bile
-bin
-bir
-birçok
-biri
-birkaç
-birkez
-birşey
-birşeyi
-biz
-bize
-bizden
-bizi
-bizim
-böyle
-böylece
-bu
-buna
-bunda
-bundan
-bunlar
-bunları
-bunların
-bunu
-bunun
-burada
-çok
-çünkü
-da
-daha
-dahi
-de
-defa
-değil
-diğer
-diye
-doksan
-dokuz
-dolayı
-dolayısıyla
-dört
-edecek
-eden
-ederek
-edilecek
-ediliyor
-edilmesi
-ediyor
-eğer
-elli
-en
-etmesi
-etti
-ettiği
-ettiğini
-gibi
-göre
-halen
-hangi
-hatta
-hem
-henüz
-hep
-hepsi
-her
-herhangi
-herkesin
-hiç
-hiçbir
-için
-iki
-ile
-ilgili
-ise
-işte
-itibaren
-itibariyle
-kadar
-karşın
-katrilyon
-kendi
-kendilerine
-kendini
-kendisi
-kendisine
-kendisini
-kez
-ki
-kim
-kimden
-kime
-kimi
-kimse
-kırk
-milyar
-milyon
-mu
-mü
-mı
-nasıl
-ne
-neden
-nedenle
-nerde
-nerede
-nereye
-niye
-niçin
-o
-olan
-olarak
-oldu
-olduğu
-olduğunu
-olduklarını
-olmadı
-olmadığı
-olmak
-olması
-olmayan
-olmaz
-olsa
-olsun
-olup
-olur
-olursa
-oluyor
-on
-ona
-ondan
-onlar
-onlardan
-onları
-onların
-onu
-onun
-otuz
-oysa
-öyle
-pek
-rağmen
-sadece
-sanki
-sekiz
-seksen
-sen
-senden
-seni
-senin
-siz
-sizden
-sizi
-sizin
-şey
-şeyden
-şeyi
-şeyler
-şöyle
-şu
-şuna
-şunda
-şundan
-şunları
-şunu
-tarafından
-trilyon
-tüm
-üç
-üzere
-var
-vardı
-ve
-veya
-ya
-yani
-yapacak
-yapılan
-yapılması
-yapıyor
-yapmak
-yaptı
-yaptığı
-yaptığını
-yaptıkları
-yedi
-yerine
-yetmiş
-yine
-yirmi
-yoksa
-yüz
-zaten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/userdict_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/userdict_ja.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/userdict_ja.txt
deleted file mode 100644
index 6f0368e..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/userdict_ja.txt
+++ /dev/null
@@ -1,29 +0,0 @@
-#
-# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
-#
-# Add entries to this file in order to override the statistical model in terms
-# of segmentation, readings and part-of-speech tags. Notice that entries do
-# not have weights since they are always used when found. This is by-design
-# in order to maximize ease-of-use.
-#
-# Entries are defined using the following CSV format:
-# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
-#
-# Notice that a single half-width space separates tokens and readings, and
-# that the number tokens and readings must match exactly.
-#
-# Also notice that multiple entries with the same <text> is undefined.
-#
-# Whitespace only lines are ignored. Comments are not allowed on entry lines.
-#
-
-# Custom segmentation for kanji compounds
-日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
-関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
-
-# Custom segmentation for compound katakana
-トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
-ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
-
-# Custom reading for former sumo wrestler
-朝青龍,朝青龍,アサショウリュウ,カスタム人名
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema b/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
deleted file mode 100644
index 80a58fb..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
+++ /dev/null
@@ -1,1069 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default)
- or located where the classloader for the Solr webapp can find it.
-
- This example schema is the recommended starting point for users.
- It should be kept correct and concise, usable out-of-the-box.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
-
- PERFORMANCE NOTE: this schema includes many optional features and should not
- be used for benchmarking. To improve performance one could
- - set stored="false" for all fields possible (esp large fields) when you
- only need to search on the field but don't need to return the original
- value.
- - set indexed="false" if you don't need to search on the field, but only
- return the field as a result of searching on other indexed fields.
- - remove all unneeded copyField statements
- - for best index size and searching performance, set "index" to false
- for all general text fields, use copyField to copy them to the
- catchall "text" field, and use that for searching.
- - For maximum indexing performance, use the ConcurrentUpdateSolrServer
- java client.
- - Remember to run the JVM in server mode, and use a higher logging level
- that avoids logging every request
--->
-
-<schema name="example-data-driven-schema" version="1.6">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
- version="x.y" is Solr's version number for the schema syntax and
- semantics. It should not normally be changed by applications.
-
- 1.0: multiValued attribute did not exist, all fields are multiValued
- by nature
- 1.1: multiValued attribute introduced, false by default
- 1.2: omitTermFreqAndPositions attribute introduced, true by default
- except for text fields.
- 1.3: removed optional field compress feature
- 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
- behavior when a single string produces multiple tokens. Defaults
- to off for version >= 1.4
- 1.5: omitNorms defaults to true for primitive field types
- (int, float, boolean, string...)
- 1.6: useDocValuesAsStored defaults to true.
- -->
-
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a field type from the
- fieldTypes section
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- docValues: true if this field should have doc values. Doc values are
- useful (required, if you are using *Point fields) for faceting,
- grouping, sorting and function queries. Doc values will make the index
- faster to load, more NRT-friendly and more memory-efficient.
- They however come with some limitations: they are currently only
- supported by StrField, UUIDField, all Trie*Fields and *PointFields,
- and depending on the field type, they might require the field to be
- single-valued, be required or have a default value (check the
- documentation of the field type you're interested in for more information)
- multiValued: true if this field may contain multiple values per document
- omitNorms: (expert) set to true to omit the norms associated with
- this field (this disables length normalization and index-time
- boosting for the field, and saves some memory). Only full-text
- fields or fields that need an index-time boost need norms.
- Norms are omitted for primitive (non-analyzed) types by default.
- termVectors: [false] set to true to store the term vector for a
- given field.
- When using MoreLikeThis, fields used for similarity should be
- stored for best performance.
- termPositions: Store position information with the term vector.
- This will increase storage costs.
- termOffsets: Store offset information with the term vector. This
- will increase storage costs.
- required: The field is required. It will throw an error if the
- value does not exist
- default: a value that should be used if no value is specified
- when adding a document.
- -->
-
- <!-- field names should consist of alphanumeric or underscore characters only and
- not start with a digit. This is not currently strictly enforced,
- but other field names will not have first class support from all components
- and back compatibility is not guaranteed. Names with both leading and
- trailing underscores (e.g. _version_) are reserved.
- -->
-
- <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
- id, _version_, and _text_. All other fields will be type guessed and added via the
- "add-unknown-fields-to-the-schema" update request processor chain declared
- in solrconfig.xml.
-
- Note that many dynamic fields are also defined - you can use them to specify a
- field's type via field naming conventions - see below.
-
- WARNING: The _text_ catch-all field will significantly increase your index size.
- If you don't need it, consider removing it and the corresponding copyField directive.
- -->
- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
- <!-- doc values are enabled by default for primitive types such as long so we don't index the version field -->
- <field name="_version_" type="long" indexed="false" stored="false"/>
- <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
- <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
-
- <!-- Only enabled in the "schemaless" data-driven example (assuming the client
- does not know what fields may be searched) because it's very expensive to index everything twice. -->
- <copyField source="*" dest="_text_"/>
-
- <!-- Dynamic field definitions allow using convention over configuration
- for fields via the specification of patterns to match field names.
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
- RESTRICTION: the glob-like pattern in the name attribute must have
- a "*" only at the start or the end. -->
-
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true" />
- <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
- <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
-
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
- <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
- <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
-
- <!-- KD-tree (point) numerics -->
- <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
- <dynamicField name="*_pis" type="pints" indexed="true" stored="true"/>
- <dynamicField name="*_pl" type="plong" indexed="true" stored="true"/>
- <dynamicField name="*_pls" type="plongs" indexed="true" stored="true"/>
- <dynamicField name="*_pf" type="pfloat" indexed="true" stored="true"/>
- <dynamicField name="*_pfs" type="pfloats" indexed="true" stored="true"/>
- <dynamicField name="*_pd" type="pdouble" indexed="true" stored="true"/>
- <dynamicField name="*_pds" type="pdoubles" indexed="true" stored="true"/>
- <dynamicField name="*_pdt" type="pdate" indexed="true" stored="true"/>
- <dynamicField name="*_pdts" type="pdates" indexed="true" stored="true"/>
-
- <!-- some trie-coded dynamic fields -->
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
- <dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
-
- <!-- payloaded dynamic fields -->
- <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true" stored="true"/>
- <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true" stored="true"/>
- <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true" stored="true"/>
-
- <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
-
- <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
- <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
-
- <dynamicField name="random_*" type="random" />
-
- <!-- uncomment the following to ignore any fields that don't already match an existing
- field name or dynamic field, rather than reporting them as an error.
- alternately, change the type="ignored" to some other type e.g. "text" if you want
- unknown fields indexed and/or stored by default
-
- NB: use of "*" dynamic fields will disable field type guessing and adding
- unknown fields to the schema. -->
- <!--dynamicField name="*" type="ignored" multiValued="true" /-->
-
- <!-- Field to use to determine and enforce document uniqueness.
- Unless this field is marked with required="false", it will be a required field
- -->
- <uniqueKey>id</uniqueKey>
-
- <!-- copyField commands copy one field to another at the time a document
- is added to the index. It's used either to index the same field differently,
- or to add multiple fields to the same field for easier/faster searching.
-
- <copyField source="sourceFieldName" dest="destinationFieldName"/>
- -->
-
- <!-- field type definitions. The "name" attribute is
- just a label to be used by field definitions. The "class"
- attribute and any other attributes determine the real
- behavior of the fieldType.
- Class names starting with "solr" refer to java classes in a
- standard package such as org.apache.solr.analysis
- -->
-
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- It supports doc values but in that case the field needs to be
- single-valued and either required or have a default value.
- -->
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
- <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
-
- <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
-
- <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
- currently supported on types that are sorted internally as strings
- and on numeric types.
- This includes "string","boolean", "int", "float", "long", "date", "double",
- including the "Trie" and "Point" variants.
- - If sortMissingLast="true", then a sort on this field will cause documents
- without the field to come after documents with the field,
- regardless of the requested sort order (asc or desc).
- - If sortMissingFirst="true", then a sort on this field will cause documents
- without the field to come before documents with the field,
- regardless of the requested sort order.
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
- then default lucene sorting will be used which places docs without the
- field first in an ascending sort and last in a descending sort.
- -->
-
- <!--
- Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
- search time and at index time, but some features are still not supported.
- Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
- -->
- <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
- <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
- <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
- <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
-
- <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
- <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
- <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
- <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
-
- <!--
- Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
- tint/tfloat/tlong/tdouble types.
- -->
- <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-
- <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-
- <!--
- Numeric field types that index each value at various levels of precision
- to accelerate range queries when the number of values between the range
- endpoints is large. See the javadoc for NumericRangeQuery for internal
- implementation details.
-
- Smaller precisionStep values (specified in bits) will lead to more tokens
- indexed per value, slightly larger index size, and faster range queries.
- A precisionStep of 0 disables indexing at different precision levels.
-
- Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
- -->
- <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-
- <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-
- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
- is a more restricted form of the canonical representation of dateTime
- http://www.w3.org/TR/xmlschema-2/#dateTime
- The trailing "Z" designates UTC time and is mandatory.
- Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
- All other components are mandatory.
-
- Expressions can also be used to denote calculations that should be
- performed relative to "NOW" to determine the value, ie...
-
- NOW/HOUR
- ... Round to the start of the current hour
- NOW-1DAY
- ... Exactly 1 day prior to now
- NOW/DAY+6MONTHS+3DAYS
- ... 6 months and 3 days in the future from the start of
- the current day
-
- Consult the TrieDateField javadocs for more information.
- -->
- <!-- KD-tree versions of date fields -->
- <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
- <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
-
- <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
- <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
- <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
-
-
- <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
- <fieldType name="binary" class="solr.BinaryField"/>
-
- <!-- The "RandomSortField" is not used to store or search any
- data. You can declare fields of this type it in your schema
- to generate pseudo-random orderings of your docs for sorting
- or function purposes. The ordering is generated based on the field
- name and the version of the index. As long as the index version
- remains unchanged, and the same field name is reused,
- the ordering of the docs will be consistent.
- If you want different psuedo-random orderings of documents,
- for the same version of the index, use a dynamicField and
- change the field name in the request.
- -->
- <fieldType name="random" class="solr.RandomSortField" indexed="true" />
-
- <!-- solr.TextField allows the specification of custom text analyzers
- specified as a tokenizer and a list of token filters. Different
- analyzers may be specified for indexing and querying.
-
- The optional positionIncrementGap puts space between multiple fields of
- this type on the same document, with the purpose of preventing false phrase
- matching across fields.
-
- For more info on customizing your analyzer chain, please see
- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
- -->
-
- <!-- One can also specify an existing Analyzer class that has a
- default constructor via the class attribute on the analyzer element.
- Example:
- <fieldType name="text_greek" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
- </fieldType>
- -->
-
- <!-- A text field that only splits on whitespace for exact matching of words -->
- <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
- <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A general text field that has reasonable, generic
- cross-language defaults: it tokenizes with StandardTokenizer,
- removes stop words from case-insensitive "stopwords.txt"
- (empty by default), and down cases. At query time only, it
- also applies synonyms.
- -->
- <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.FlattenGraphFilterFactory"/>
- -->
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English: it
- tokenizes with StandardTokenizer, removes English stop words
- (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
- finally applies Porter's stemming. The query time analyzer
- also applies synonyms from synonyms.txt. -->
- <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
- <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.FlattenGraphFilterFactory"/>
- -->
- <!-- Case insensitive stop word removal.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English, plus
- aggressive word-splitting and autophrase features enabled.
- This field is just like text_en, except it adds
- WordDelimiterGraphFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and
- non-alphanumeric chars. This means certain compound word
- cases will work, for example query "wi fi" will match
- document "WiFi" or "wi-fi".
- -->
- <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
- <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!-- in this example, we will only use synonyms at query time
- <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
- -->
- <!-- Case insensitive stop word removal.
- -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- <filter class="solr.FlattenGraphFilterFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="lang/stopwords_en.txt"
- />
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
- <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
- <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- <filter class="solr.FlattenGraphFilterFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Just like text_general except it reverses the characters of
- each token, to enable more efficient leading wildcard queries.
- -->
- <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
- <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
- <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
- </analyzer>
- </fieldType>
-
- <!-- lowercases the entire field value, keeping it as a single token. -->
- <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Example of using PathHierarchyTokenizerFactory at index time, so
- queries for paths match documents at that path, or in descendent paths
- -->
- <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
- <fieldType name="descendent_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Example of using PathHierarchyTokenizerFactory at query time, so
- queries for paths match documents at that path, or in ancestor paths
- -->
- <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
- <fieldType name="ancestor_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- </fieldType>
-
- <!-- since fields of this type are by default not stored or indexed,
- any data added to them will be ignored outright. -->
- <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
-
- <!-- This point type indexes the coordinates as separate fields (subFields)
- If subFieldType is defined, it references a type, and a dynamic field
- definition is created matching *___<typename>. Alternately, if
- subFieldSuffix is defined, that is used to create the subFields.
- Example: if subFieldType="double", then the coordinates would be
- indexed in fields myloc_0___double,myloc_1___double.
- Example: if subFieldSuffix="_d" then the coordinates would be indexed
- in fields myloc_0_d,myloc_1_d
- The subFields are an implementation detail of the fieldType, and end
- users normally should not need to know about them.
- -->
- <dynamicField name="*_point" type="point" indexed="true" stored="true"/>
- <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
-
- <!-- A specialized field for geospatial search filters and distance sorting. -->
- <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
-
- <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
- For more information about this and other Spatial fields new to Solr 4, see:
- http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
- -->
- <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
- geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
-
- <!-- Payloaded field types -->
- <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </analyzer>
- </fieldType>
- <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
- </analyzer>
- </fieldType>
- <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
- </analyzer>
- </fieldType>
-
- <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
- Parameters:
- defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
- precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
- providerClass: Lets you plug in other exchange provider backend:
- solr.FileExchangeRateProvider is the default and takes one parameter:
- currencyConfig: name of an xml file holding exchange rates
- solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
- ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
- refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
- -->
- <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
-
-
-
- <!-- some examples for different languages (generally ordered by ISO code) -->
-
- <!-- Arabic -->
- <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
- <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- for any non-arabic -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
- <!-- normalizes ﻯ to ﻱ, etc -->
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.ArabicStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Bulgarian -->
- <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
- <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
- <filter class="solr.BulgarianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Catalan -->
- <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
- <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
- </analyzer>
- </fieldType>
-
- <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
- <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
- <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- for any non-CJK -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.CJKBigramFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Czech -->
- <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
- <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
- <filter class="solr.CzechStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Danish -->
- <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
- <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
- </analyzer>
- </fieldType>
-
- <!-- German -->
- <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
- <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
- <filter class="solr.GermanNormalizationFilterFactory"/>
- <filter class="solr.GermanLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Greek -->
- <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
- <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- greek specific lowercase for sigma -->
- <filter class="solr.GreekLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
- <filter class="solr.GreekStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Spanish -->
- <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
- <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
- <filter class="solr.SpanishLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Basque -->
- <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
- <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
- </analyzer>
- </fieldType>
-
- <!-- Persian -->
- <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
- <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <!-- for ZWNJ -->
- <charFilter class="solr.PersianCharFilterFactory"/>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.PersianNormalizationFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
- </analyzer>
- </fieldType>
-
- <!-- Finnish -->
- <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
- <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
- <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- French -->
- <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
- <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
- <filter class="solr.FrenchLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Irish -->
- <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
- <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes d', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
- <!-- removes n-, etc. position increments is intentionally false! -->
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
- <filter class="solr.IrishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
- </analyzer>
- </fieldType>
-
- <!-- Galician -->
- <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
- <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
- <filter class="solr.GalicianStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Hindi -->
- <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
- <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <!-- normalizes unicode representation -->
- <filter class="solr.IndicNormalizationFilterFactory"/>
- <!-- normalizes variation in spelling -->
- <filter class="solr.HindiNormalizationFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
- <filter class="solr.HindiStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Hungarian -->
- <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
- <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
- <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Armenian -->
- <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
- <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
- </analyzer>
- </fieldType>
-
- <!-- Indonesian -->
- <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
- <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
- <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
- <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
- </analyzer>
- </fieldType>
-
- <!-- Italian -->
- <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
- <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- removes l', etc -->
- <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
- <filter class="solr.ItalianLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
-
- NOTE: If you want to optimize search for precision, use default operator AND in your request
- handler config (q.op) Use OR if you would like to optimize for recall (default).
- -->
- <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
- <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
- <analyzer>
- <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
-
- Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
- is used to segment compounds into its parts and the compound itself is kept as synonym.
-
- Valid values for attribute mode are:
- normal: regular segmentation
- search: segmentation useful for search with synonyms compounds (default)
- extended: same as search mode, but unigrams unknown words (experimental)
-
- For some applications it might be good to use search mode for indexing and normal mode for
- queries to reduce recall and prevent parts of compounds from being matched and highlighted.
- Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
-
- Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
- model with your own entries for segmentation, part-of-speech tags and readings without a need
- to specify weights. Notice that user dictionaries have not been subject to extensive testing.
-
- User dictionary attributes are:
- userDictionary: user dictionary filename
- userDictionaryEncoding: user dictionary encoding (default is UTF-8)
-
- See lang/userdict_ja.txt for a sample user dictionary file.
-
- Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
-
- See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
- -->
- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
- <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
- <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
- <!-- Removes tokens with certain part-of-speech tags -->
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
- <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
- <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
- <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
- <!-- Lower-cases romaji characters -->
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Latvian -->
- <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
- <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
- <filter class="solr.LatvianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Dutch -->
- <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
- <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
- <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
- </analyzer>
- </fieldType>
-
- <!-- Norwegian -->
- <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
- <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
- <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
- <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Portuguese -->
- <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
- <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
- <filter class="solr.PortugueseLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
- <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Romanian -->
- <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
- <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
- </analyzer>
- </fieldType>
-
- <!-- Russian -->
- <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
- <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
- <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Swedish -->
- <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
- <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
- <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
- <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Thai -->
- <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
- <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.ThaiTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
- </analyzer>
- </fieldType>
-
- <!-- Turkish -->
- <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
- <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
- <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
- </analyzer>
- </fieldType>
-
- <!-- Similarity is the scoring routine for each document vs. a query.
- A custom Similarity or SimilarityFactory may be specified here, but
- the default is fine for most applications.
- For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
- -->
- <!--
- <similarity class="com.example.solr.CustomSimilarityFactory">
- <str name="paramkey">param value</str>
- </similarity>
- -->
-
-</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/params.json
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/params.json b/solr/server/solr/configsets/data_driven_schema_configs/conf/params.json
deleted file mode 100644
index 06114ef..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/params.json
+++ /dev/null
@@ -1,20 +0,0 @@
-{"params":{
- "query":{
- "defType":"edismax",
- "q.alt":"*:*",
- "rows":"10",
- "fl":"*,score",
- "":{"v":0}
- },
- "facets":{
- "facet":"on",
- "facet.mincount": "1",
- "":{"v":0}
- },
- "velocity":{
- "wt": "velocity",
- "v.template":"browse",
- "v.layout": "layout",
- "":{"v":0}
- }
-}}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/protwords.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/protwords.txt
deleted file mode 100644
index 1dfc0ab..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/protwords.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-# Use a protected word file to protect against the stemmer reducing two
-# unrelated words to the same base word.
-
-# Some non-words that normally won't be encountered,
-# just to test that they won't be stemmed.
-dontstems
-zwhacky
-
[05/50] [abbrv] lucene-solr:feature/autoscaling: Ref Guide: Add floor
evaluator docs
Posted by sh...@apache.org.
Ref Guide: Add floor evaluator docs
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/b49ce689
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/b49ce689
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/b49ce689
Branch: refs/heads/feature/autoscaling
Commit: b49ce68935805bdd00bb413291c5fab031a29c00
Parents: c24e401
Author: Joel Bernstein <jb...@apache.org>
Authored: Fri Jun 16 14:35:12 2017 -0400
Committer: Joel Bernstein <jb...@apache.org>
Committed: Fri Jun 16 14:35:12 2017 -0400
----------------------------------------------------------------------
solr/solr-ref-guide/src/stream-evaluators.adoc | 20 ++++++++++++++++++--
1 file changed, 18 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/b49ce689/solr/solr-ref-guide/src/stream-evaluators.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/stream-evaluators.adoc b/solr/solr-ref-guide/src/stream-evaluators.adoc
index f10bca3..5d16fbf 100644
--- a/solr/solr-ref-guide/src/stream-evaluators.adoc
+++ b/solr/solr-ref-guide/src/stream-evaluators.adoc
@@ -244,13 +244,29 @@ The expressions below show the various ways in which you can use the `ceil` eval
[source,text]
----
-ceil(100.4) // returns the remainder of 100.
+ceil(100.4) // returns 101.
ceil(fieldA) // returns the next highest whole number for fieldA.
if(gt(fieldA,fieldB),ceil(fieldA),ceil(fieldB)) // if fieldA > fieldB then return the ceil of fieldA, else return the ceil of fieldB.
----
== floor
-//TODO
+The `floor` function rounds a decimal value to the next lowest whole number.
+
+=== floor Parameters
+
+* `Field Name | Raw Number | Number Evaluator`: The decimal to round down.
+
+=== floor Syntax
+
+The expressions below show the various ways in which you can use the `floor` evaluator.
+
+[source,text]
+----
+floor(100.4) // returns 100.
+ceil(fieldA) // returns the next lowestt whole number for fieldA.
+if(gt(fieldA,fieldB),floor(fieldA),floor(fieldB)) // if fieldA > fieldB then return the floor of fieldA, else return the floor of fieldB.
+----
+
== sin
//TODO
[22/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
data driven support to basic_confs and adding payload fields
Posted by sh...@apache.org.
SOLR-10574: Adding data driven support to basic_confs and adding payload fields
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/7c2429be
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/7c2429be
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/7c2429be
Branch: refs/heads/feature/autoscaling
Commit: 7c2429bebf82d1ff5ab2d4dcabb07e57659c0b0d
Parents: 4746ff0
Author: Ishan Chattopadhyaya <is...@apache.org>
Authored: Fri Jun 16 08:49:21 2017 +0300
Committer: Ishan Chattopadhyaya <is...@apache.org>
Committed: Tue Jun 20 11:03:48 2017 +0000
----------------------------------------------------------------------
.../basic_configs/conf/managed-schema | 32 +++++-
.../basic_configs/conf/solrconfig.xml | 108 +++++++++----------
2 files changed, 82 insertions(+), 58 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/7c2429be/solr/server/solr/configsets/basic_configs/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/managed-schema b/solr/server/solr/configsets/basic_configs/conf/managed-schema
index 599b0cc..f1017af 100644
--- a/solr/server/solr/configsets/basic_configs/conf/managed-schema
+++ b/solr/server/solr/configsets/basic_configs/conf/managed-schema
@@ -45,7 +45,7 @@
that avoids logging every request
-->
-<schema name="example-basic" version="1.6">
+<schema name="default-config" version="2.0">
<!-- attribute "name" is the name of this schema and is only used for display purposes.
version="x.y" is Solr's version number for the schema syntax and
semantics. It should not normally be changed by applications.
@@ -177,6 +177,11 @@
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
<dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
+ <!-- payloaded dynamic fields -->
+ <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true" stored="true"/>
+ <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true" stored="true"/>
+ <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true" stored="true"/>
+
<dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
@@ -239,8 +244,8 @@
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
- -->
-
+ -->
+
<!--
Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
search time and at index time, but some features are still not supported.
@@ -318,7 +323,6 @@
<fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-
<fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
<fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
@@ -601,6 +605,26 @@
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+ <!-- Payloaded field types -->
+ <fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
+ </analyzer>
+ </fieldType>
+ <fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
+ </analyzer>
+ </fieldType>
+
<!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
Parameters:
defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/7c2429be/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml b/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
index 64d59fc..1b55374 100644
--- a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
+++ b/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
@@ -1171,70 +1171,70 @@
<!-- Add unknown fields to the schema
- An example field type guessing update processor that will
+ Field type guessing update processors that will
attempt to parse string-typed field values as Booleans, Longs,
Doubles, or Dates, and then add schema fields with the guessed
field types.
- This requires that the schema is both managed and mutable, by
+ These require that the schema is both managed and mutable, by
declaring schemaFactory as ManagedIndexSchemaFactory, with
mutable specified as true.
See http://wiki.apache.org/solr/GuessingFieldTypes
-->
- <updateRequestProcessorChain name="add-unknown-fields-to-the-schema">
- <!-- UUIDUpdateProcessorFactory will generate an id if none is present in the incoming document -->
- <processor class="solr.UUIDUpdateProcessorFactory" />
- <processor class="solr.RemoveBlankFieldUpdateProcessorFactory"/>
- <processor class="solr.FieldNameMutatingUpdateProcessorFactory">
- <str name="pattern">[^\w-\.]</str>
- <str name="replacement">_</str>
- </processor>
- <processor class="solr.ParseBooleanFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseLongFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseDoubleFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseDateFieldUpdateProcessorFactory">
- <arr name="format">
- <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss</str>
- <str>yyyy-MM-dd'T'HH:mmZ</str>
- <str>yyyy-MM-dd'T'HH:mm</str>
- <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd HH:mm:ssZ</str>
- <str>yyyy-MM-dd HH:mm:ss</str>
- <str>yyyy-MM-dd HH:mmZ</str>
- <str>yyyy-MM-dd HH:mm</str>
- <str>yyyy-MM-dd</str>
- </arr>
- </processor>
- <processor class="solr.AddSchemaFieldsUpdateProcessorFactory">
- <str name="defaultFieldType">strings</str>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Boolean</str>
- <str name="fieldType">booleans</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.util.Date</str>
- <str name="fieldType">pdates</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Long</str>
- <str name="valueClass">java.lang.Integer</str>
- <str name="fieldType">plongs</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Number</str>
- <str name="fieldType">pdoubles</str>
- </lst>
- </processor>
+ <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
+ <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
+ <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
+ <str name="pattern">[^\w-\.]</str>
+ <str name="replacement">_</str>
+ </updateProcessor>
+ <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
+ <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
+ <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
+ <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
+ <arr name="format">
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss</str>
+ <str>yyyy-MM-dd'T'HH:mmZ</str>
+ <str>yyyy-MM-dd'T'HH:mm</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd HH:mm:ssZ</str>
+ <str>yyyy-MM-dd HH:mm:ss</str>
+ <str>yyyy-MM-dd HH:mmZ</str>
+ <str>yyyy-MM-dd HH:mm</str>
+ <str>yyyy-MM-dd</str>
+ </arr>
+ </updateProcessor>
+ <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
+ <str name="defaultFieldType">strings</str>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Boolean</str>
+ <str name="fieldType">booleans</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.util.Date</str>
+ <str name="fieldType">tdates</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Long</str>
+ <str name="valueClass">java.lang.Integer</str>
+ <str name="fieldType">tlongs</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Number</str>
+ <str name="fieldType">tdoubles</str>
+ </lst>
+ </updateProcessor>
+ <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:true}"
+ processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
<processor class="solr.LogUpdateProcessorFactory"/>
<processor class="solr.DistributedUpdateProcessorFactory"/>
<processor class="solr.RunUpdateProcessorFactory"/>
[17/50] [abbrv] lucene-solr:feature/autoscaling: LUCENE-7571: Take
into account float precision loss when generating unique values.
Posted by sh...@apache.org.
LUCENE-7571: Take into account float precision loss when generating unique values.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/09b0eee5
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/09b0eee5
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/09b0eee5
Branch: refs/heads/feature/autoscaling
Commit: 09b0eee5bbc90652b78aece27cba89998dff7816
Parents: 64093d6
Author: Martijn van Groningen <ma...@gmail.com>
Authored: Mon Jun 19 11:41:59 2017 +0200
Committer: Martijn van Groningen <mv...@apache.org>
Committed: Mon Jun 19 11:41:59 2017 +0200
----------------------------------------------------------------------
.../src/test/org/apache/lucene/search/join/TestJoinUtil.java | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/09b0eee5/lucene/join/src/test/org/apache/lucene/search/join/TestJoinUtil.java
----------------------------------------------------------------------
diff --git a/lucene/join/src/test/org/apache/lucene/search/join/TestJoinUtil.java b/lucene/join/src/test/org/apache/lucene/search/join/TestJoinUtil.java
index 49dd333..1503de8 100644
--- a/lucene/join/src/test/org/apache/lucene/search/join/TestJoinUtil.java
+++ b/lucene/join/src/test/org/apache/lucene/search/join/TestJoinUtil.java
@@ -1325,7 +1325,10 @@ public class TestJoinUtil extends LuceneTestCase {
String uniqueRandomValue;
do {
// the trick is to generate values which will be ordered similarly for string, ints&longs, positive nums makes it easier
- final int nextInt = random.nextInt(Integer.MAX_VALUE);
+ //
+ // Additionally in order to avoid precision loss when joining via a float field we can't generate values higher than
+ // 0xFFFFFF, so we can't use Integer#MAX_VALUE as upper bound here:
+ final int nextInt = random.nextInt(0xFFFFFF);
uniqueRandomValue = String.format(Locale.ROOT, "%08x", nextInt);
assert nextInt == Integer.parseUnsignedInt(uniqueRandomValue,16);
} while ("".equals(uniqueRandomValue) || trackSet.contains(uniqueRandomValue));
[14/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10882: Fixes
use of Lists in evaluators
Posted by sh...@apache.org.
SOLR-10882: Fixes use of Lists in evaluators
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/943bf5ab
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/943bf5ab
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/943bf5ab
Branch: refs/heads/feature/autoscaling
Commit: 943bf5ab5bb5d72da3038284a8571c3620413691
Parents: aeec043
Author: Dennis Gove <dp...@gmail.com>
Authored: Sat Jun 17 22:12:23 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Sun Jun 18 11:50:58 2017 -0400
----------------------------------------------------------------------
.../org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/943bf5ab/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
index 065335b..127f587 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
@@ -18,6 +18,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.ArrayList;
+import java.util.Arrays;
import java.util.Comparator;
import java.util.List;
import java.util.Locale;
@@ -33,15 +34,13 @@ import org.apache.solr.client.solrj.io.stream.expr.StreamExpressionParameter;
import org.apache.solr.client.solrj.io.stream.expr.StreamExpressionValue;
import org.apache.solr.client.solrj.io.stream.expr.StreamFactory;
-import com.google.common.collect.Lists;
-
public class ArrayEvaluator extends ComplexEvaluator implements Expressible {
private static final long serialVersionUID = 1;
private String sortOrder;
public ArrayEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
- super(expression, factory, Lists.newArrayList("sort"));
+ super(expression, factory, Arrays.asList("sort"));
sortOrder = extractSortOrder(expression, factory);
}
[23/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml b/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
deleted file mode 100644
index 1cb477b..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
+++ /dev/null
@@ -1,1406 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>7.0.0</luceneMatchVersion>
-
- <!-- <lib/> directives can be used to instruct Solr to load any Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- Please note that <lib/> directives are processed in the order
- that they appear in your solrconfig.xml file, and are "stacked"
- on top of each other when building a ClassLoader - so if you have
- plugin jars with dependencies on other jars, the "lower level"
- dependency jars should be loaded first.
-
- If a "./lib" directory exists in your instanceDir, all files
- found in it are included as if you had used the following
- syntax...
-
- <lib dir="./lib" />
- -->
-
- <!-- A 'dir' option by itself adds any files found in the directory
- to the classpath, this is useful for including all jars in a
- directory.
-
- When a 'regex' is specified in addition to a 'dir', only the
- files in that directory which completely match the regex
- (anchored on both ends) will be included.
-
- If a 'dir' option (with or without a regex) is used and nothing
- is found that matches, a warning will be logged.
-
- The examples below can be used to load some solr-contribs along
- with their external dependencies.
- -->
- <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
- <!-- an exact 'path' can be used instead of a 'dir' to specify a
- specific jar file. This will cause a serious error to be logged
- if it can't be loaded.
- -->
- <!--
- <lib path="../a-jar-that-does-not-exist.jar" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:}</dataDir>
-
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory is filesystem
- based and tries to pick the best implementation for the current
- JVM and platform. solr.NRTCachingDirectoryFactory, the default,
- wraps solr.StandardDirectoryFactory and caches small files in memory
- for better NRT performance.
-
- One can force a particular implementation via solr.MMapDirectoryFactory,
- solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
-
- solr.RAMDirectoryFactory is memory based and not persistent.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
-
- <!-- The CodecFactory for defining the format of the inverted index.
- The default implementation is SchemaCodecFactory, which is the official Lucene
- index format, but hooks into the schema to provide per-field customization of
- the postings lists and per-document values in the fieldType element
- (postingsFormat/docValuesFormat). Note that most of the alternative implementations
- are experimental, so if you choose to customize the index format, it's a good
- idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
- before upgrading to a newer version to avoid unnecessary reindexing.
- A "compressionMode" string element can be added to <codecFactory> to choose
- between the existing compression modes in the default codec: "BEST_SPEED" (default)
- or "BEST_COMPRESSION".
- -->
- <codecFactory class="solr.SchemaCodecFactory"/>
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Index Config - These settings control low-level behavior of indexing
- Most example settings here show the default value, but are commented
- out, to more easily see where customizations have been made.
-
- Note: This replaces <indexDefaults> and <mainIndex> from older versions
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <indexConfig>
- <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
- LimitTokenCountFilterFactory in your fieldType definition. E.g.
- <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
- -->
- <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
- <!-- <writeLockTimeout>1000</writeLockTimeout> -->
-
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
- Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
- <!-- <useCompoundFile>false</useCompoundFile> -->
-
- <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
- indexing for buffering added documents and deletions before they are
- flushed to the Directory.
- maxBufferedDocs sets a limit on the number of documents buffered
- before flushing.
- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first. -->
- <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <!-- Expert: Merge Policy
- The Merge Policy in Lucene controls how merging of segments is done.
- The default since Solr/Lucene 3.3 is TieredMergePolicy.
- The default since Lucene 2.3 was the LogByteSizeMergePolicy,
- Even older versions of Lucene used LogDocMergePolicy.
- -->
- <!--
- <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
- <int name="maxMergeAtOnce">10</int>
- <int name="segmentsPerTier">10</int>
- <double name="noCFSRatio">0.1</double>
- </mergePolicyFactory>
- -->
-
- <!-- Expert: Merge Scheduler
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- can perform merges in the background using separate threads.
- The SerialMergeScheduler (Lucene 2.2 default) does not.
- -->
- <!--
- <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
- -->
-
- <!-- LockFactory
-
- This option specifies which Lucene LockFactory implementation
- to use.
-
- single = SingleInstanceLockFactory - suggested for a
- read-only index or when there is no possibility of
- another process trying to modify the index.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- Defaults: 'native' is default for Solr3.6 and later, otherwise
- 'simple' is the default
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>${solr.lock.type:native}</lockType>
-
- <!-- Commit Deletion Policy
- Custom deletion policies can be specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- The default Solr IndexDeletionPolicy implementation supports
- deleting index commit points on number of commits, age of
- commit point and optimized status.
-
- The latest commit point should always be preserved regardless
- of the criteria.
- -->
- <!--
- <deletionPolicy class="solr.SolrDeletionPolicy">
- -->
- <!-- The number of commit points to be kept -->
- <!-- <str name="maxCommitsToKeep">1</str> -->
- <!-- The number of optimized commit points to be kept -->
- <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <str name="maxCommitAge">30MINUTES</str>
- <str name="maxCommitAge">1DAY</str>
- -->
- <!--
- </deletionPolicy>
- -->
-
- <!-- Lucene Infostream
-
- To aid in advanced debugging, Lucene provides an "InfoStream"
- of detailed information when indexing.
-
- Setting The value to true will instruct the underlying Lucene
- IndexWriter to write its debugging info the specified file
- -->
- <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
- </indexConfig>
-
-
- <!-- JMX
-
- This example enables JMX if and only if an existing MBeanServer
- is found, use this if you want to configure JMX through JVM
- parameters. Remove this to disable exposing Solr configuration
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- Enables a transaction log, used for real-time get, durability, and
- and solr cloud replica recovery. The log can grow as big as
- uncommitted changes to the index, so use of a hard autoCommit
- is recommended (see below).
- "dir" - the target directory for transaction logs, defaults to the
- solr data directory.
- "numVersionBuckets" - sets the number of buckets used to keep
- track of max version values when checking for re-ordered
- updates; increase this value to reduce the cost of
- synchronizing access to version buckets during high-volume
- indexing, this requires 8 bytes (long) * numVersionBuckets
- of heap space per Solr core.
- -->
- <updateLog>
- <str name="dir">${solr.ulog.dir:}</str>
- <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
- </updateLog>
-
- <!-- AutoCommit
-
- Perform a hard commit automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time in ms that is allowed to pass
- since a document was added before automatically
- triggering a new commit.
- openSearcher - if false, the commit causes recent index changes
- to be flushed to stable storage, but does not cause a new
- searcher to be opened to make those changes visible.
-
- If the updateLog is enabled, then it's highly recommended to
- have some sort of hard autoCommit to limit the log size.
- -->
- <autoCommit>
- <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
-
- <!-- softAutoCommit is like autoCommit except it causes a
- 'soft' commit which only ensures that changes are visible
- but does not ensure that data is synced to disk. This is
- faster and more near-realtime friendly than a hard commit.
- -->
-
- <autoSoftCommit>
- <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
- </autoSoftCommit>
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- The RunExecutableListener executes an external command from a
- hook such as postCommit or postOptimize.
-
- exe - the name of the executable to run
- dir - dir to use as the current working directory. (default=".")
- wait - the calling thread waits until the executable returns.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
-
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Query section - these settings control query time things like caches
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded.
-
- ** WARNING **
-
- This option actually modifies a global Lucene property that
- will affect all SolrCores. If multiple solrconfig.xml files
- disagree on this property, the value at any given moment will
- be based on the last SolrCore to be initialized.
-
- -->
- <maxBooleanClauses>1024</maxBooleanClauses>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (see java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
- to occupy. Note that when this option is specified, the size
- and initialSize parameters are ignored.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Query Result Cache
-
- Caches results of searches - ordered lists of document ids
- (DocList) based on a query, a sort, and the range of documents requested.
- Additional supported parameter by LRUCache:
- maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
- to occupy
- -->
- <queryResultCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Document Cache
-
- Caches Lucene Document objects (the stored fields for each
- document). Since Lucene internal document ids are transient,
- this cache will not be autowarmed.
- -->
- <documentCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- custom cache currently used by block join -->
- <cache name="perSegFilter"
- class="solr.search.LRUCache"
- size="10"
- initialSize="0"
- autowarmCount="10"
- regenerator="solr.NoOpRegenerator" />
-
- <!-- Field Value Cache
-
- Cache used to hold field values that are quickly accessible
- by document id. The fieldValueCache is created by default
- even if not configured here.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- name through SolrIndexSearcher.getCache(),cacheLookup(), and
- cacheInsert(). The purpose is to enable easy caching of
- user/application level data. The regenerator argument should
- be specified as an implementation of solr.CacheRegenerator
- if autowarming is desired.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- are collected. For example, if a search for a particular query
- requests matching documents 10 through 19, and queryWindowSize is 50,
- then documents 0 through 49 will be collected and cached. Any further
- requests in that range can be satisfied via the cache.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- prepared but there is no current registered searcher to handle
- requests or to gain autowarming data from.
-
-
- -->
- <!-- QuerySenderListener takes an array of NamedList and executes a
- local query request for each NamedList in sequence.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- -->
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <useColdSearcher>false</useColdSearcher>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect is a legacy option that affects the behavior of requests
- such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and dispatch the query to a handler specified by the
- "qt" param, assuming "/select" isn't already registered.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests, resulting in a 404 unless a handler
- is explicitly registered with the name "/select"
-
- handleSelect="true" is not recommended for new users, but is the default
- for backwards compatibility
- -->
- <requestDispatcher handleSelect="false" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- multipartUploadLimitInKB - specifies the max size (in KiB) of
- Multipart File Uploads that Solr will allow in a Request.
-
- formdataUploadLimitInKB - specifies the max size (in KiB) of
- form data (application/x-www-form-urlencoded) sent via
- POST. You can use POST to pass request parameters not
- fitting into the URL.
-
- addHttpRequestToContext - if set to true, it will instruct
- the requestParsers to include the original HttpServletRequest
- object in the context map of the SolrQueryRequest under the
- key "httpRequest". It will not be used by any of the existing
- Solr components, but may be useful when developing custom
- plugins.
-
- *** WARNING ***
- Before enabling remote streaming, you should make sure your
- system has authentication enabled.
-
- <requestParsers enableRemoteStreaming="false"
- multipartUploadLimitInKB="-1"
- formdataUploadLimitInKB="-1"
- addHttpRequestToContext="false"/>
- -->
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- If you include a <cacheControl> directive, it will be used to
- generate a Cache-Control header (as well as an Expires header
- if the value contains "max-age=")
-
- By default, no Cache-Control header is generated.
-
- You can use the <cacheControl> option even if you have set
- never304="true"
- -->
- <!--
- <httpCaching never304="true" >
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- <!-- To enable Solr to respond with automatically generated HTTP
- Caching headers, and to response to Cache Validation requests
- correctly, set the value of never304="false"
-
- This will cause Solr to generate Last-Modified and ETag
- headers based on the properties of the Index.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- Incoming queries will be dispatched to a specific handler by name
- based on the path specified in the request.
-
- Legacy behavior: If the request path uses "/select" but no Request
- Handler has that name, and if handleSelect="true" has been specified in
- the requestDispatcher, then the Request Handler is dispatched based on
- the qt parameter. Handlers without a leading '/' are accessed this way
- like so: http://host/app/[core/]select?qt=name If no qt is
- given, then the requestHandler that declares default="true" will be
- used or the one named "standard".
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="/select" class="solr.SearchHandler">
- <!-- default values for query parameters can be specified, these
- will be overridden by parameters in the request
- -->
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <int name="rows">10</int>
- <!-- <str name="df">text</str> -->
- </lst>
- <!-- In addition to defaults, "appends" params can be specified
- to identify values which should be appended to the list of
- multi-val params from the query (or the existing "defaults").
- -->
- <!-- In this example, the param "fq=instock:true" would be appended to
- any query time fq params the user may specify, as a mechanism for
- partitioning the index, independent of any user selected filtering
- that may also be desired (perhaps as a result of faceted searching).
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "appends" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="appends">
- <str name="fq">inStock:true</str>
- </lst>
- -->
- <!-- "invariants" are a way of letting the Solr maintainer lock down
- the options available to Solr clients. Any params values
- specified here are used regardless of what values may be specified
- in either the query, the "defaults", or the "appends" params.
-
- In this example, the facet.field and facet.query params would
- be fixed, limiting the facets clients can use. Faceting is
- not turned on by default - but if the client does specify
- facet=true in the request, these are the only facets they
- will be able to see counts for; regardless of what other
- facet.field or facet.query params they may specify.
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "invariants" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="invariants">
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">price:[* TO 500]</str>
- <str name="facet.query">price:[500 TO *]</str>
- </lst>
- -->
- <!-- If the default list of SearchComponents is not desired, that
- list can either be overridden completely, or components can be
- prepended or appended to the default list. (see below)
- -->
- <!--
- <arr name="components">
- <str>nameOfCustomComponent1</str>
- <str>nameOfCustomComponent2</str>
- </arr>
- -->
- </requestHandler>
-
- <!-- A request handler that returns indented JSON by default -->
- <requestHandler name="/query" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- </lst>
- </requestHandler>
-
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- </requestHandler>
-
- <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
- <lst name="defaults">
- <str name="df">_text_</str>
- </lst>
- </initParams>
-
- <initParams path="/update/**">
- <lst name="defaults">
- <str name="update.chain">add-unknown-fields-to-the-schema</str>
- </lst>
- </initParams>
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <str name="lowernames">true</str>
- <str name="fmap.meta">ignored_</str>
- <str name="fmap.content">_text_</str>
- </lst>
- </requestHandler>
-
- <!-- Search Components
-
- Search components are registered to SolrCore and used by
- instances of SearchHandler (which can access them by name)
-
- By default, the following components are available:
-
- <searchComponent name="query" class="solr.QueryComponent" />
- <searchComponent name="facet" class="solr.FacetComponent" />
- <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
- <searchComponent name="highlight" class="solr.HighlightComponent" />
- <searchComponent name="stats" class="solr.StatsComponent" />
- <searchComponent name="debug" class="solr.DebugComponent" />
-
- Default configuration in a requestHandler would look like:
-
- <arr name="components">
- <str>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- If you register a searchComponent to one of the standard names,
- that will be used instead of the default.
-
- To insert components before or after the 'standard' components, use:
-
- <arr name="first-components">
- <str>myFirstComponentName</str>
- </arr>
-
- <arr name="last-components">
- <str>myLastComponentName</str>
- </arr>
-
- NOTE: The component registered with the name "debug" will
- always be executed after the "last-components"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text_general</str>
-
- <!-- Multiple "Spell Checkers" can be declared and used by this
- component
- -->
-
- <!-- a spellchecker built from a field of the main index -->
- <lst name="spellchecker">
- <str name="name">default</str>
- <str name="field">_text_</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
- <str name="distanceMeasure">internal</str>
- <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
- <float name="accuracy">0.5</float>
- <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
- <int name="maxEdits">2</int>
- <!-- the minimum shared prefix when enumerating terms -->
- <int name="minPrefix">1</int>
- <!-- maximum number of inspections per result. -->
- <int name="maxInspections">5</int>
- <!-- minimum length of a query term to be considered for correction -->
- <int name="minQueryLength">4</int>
- <!-- maximum threshold of documents a query term can appear to be considered for correction -->
- <float name="maxQueryFrequency">0.01</float>
- <!-- uncomment this to require suggestions to occur in 1% of the documents
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
- <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
- <!--
- <lst name="spellchecker">
- <str name="name">wordbreak</str>
- <str name="classname">solr.WordBreakSolrSpellChecker</str>
- <str name="field">name</str>
- <str name="combineWords">true</str>
- <str name="breakWords">true</str>
- <int name="maxChanges">10</int>
- </lst>
- -->
- </searchComponent>
-
- <!-- A request handler for demonstrating the spellcheck component.
-
- NOTE: This is purely as an example. The whole purpose of the
- SpellCheckComponent is to hook it into the request handler that
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
- NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
-
- See http://wiki.apache.org/solr/SpellCheckComponent for details
- on the request parameters.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <!-- Solr will use suggestions from both the 'default' spellchecker
- and from the 'wordbreak' spellchecker and combine them.
- collations (re-written queries) can include a combination of
- corrections from both spellcheckers -->
- <str name="spellcheck.dictionary">default</str>
- <str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">true</str>
- <str name="spellcheck.count">10</str>
- <str name="spellcheck.alternativeTermCount">5</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
- <str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
- <str name="spellcheck.maxCollationTries">10</str>
- <str name="spellcheck.maxCollations">5</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component. (Omitted here. See the default Solr example for a typical configuration.) -->
-
- <!-- Terms Component
-
- http://wiki.apache.org/solr/TermsComponent
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- <bool name="distrib">false</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- Configure the weighted fragListBuilder -->
- <fragListBuilder name="weighted"
- default="true"
- class="solr.highlight.WeightedFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <fragmentsBuilder name="default"
- default="true"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <!--
- <lst name="defaults">
- <str name="hl.multiValuedSeparatorChar">/</str>
- </lst>
- -->
- </fragmentsBuilder>
-
- <!-- multi-colored tag FragmentsBuilder -->
- <fragmentsBuilder name="colored"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
-
- <boundaryScanner name="default"
- default="true"
- class="solr.highlight.SimpleBoundaryScanner">
- <lst name="defaults">
- <str name="hl.bs.maxScan">10</str>
- <str name="hl.bs.chars">.,!? 	 </str>
- </lst>
- </boundaryScanner>
-
- <boundaryScanner name="breakIterator"
- class="solr.highlight.BreakIteratorBoundaryScanner">
- <lst name="defaults">
- <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
- <str name="hl.bs.type">WORD</str>
- <!-- language and country are used when constructing Locale object. -->
- <!-- And the Locale object will be used when getting instance of BreakIterator -->
- <str name="hl.bs.language">en</str>
- <str name="hl.bs.country">US</str>
- </lst>
- </boundaryScanner>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- http://wiki.apache.org/solr/UpdateRequestProcessor
-
- -->
-
- <!-- Add unknown fields to the schema
-
- An example field type guessing update processor that will
- attempt to parse string-typed field values as Booleans, Longs,
- Doubles, or Dates, and then add schema fields with the guessed
- field types.
-
- This requires that the schema is both managed and mutable, by
- declaring schemaFactory as ManagedIndexSchemaFactory, with
- mutable specified as true.
-
- See http://wiki.apache.org/solr/GuessingFieldTypes
- -->
- <updateRequestProcessorChain name="add-unknown-fields-to-the-schema">
- <!-- UUIDUpdateProcessorFactory will generate an id if none is present in the incoming document -->
- <processor class="solr.UUIDUpdateProcessorFactory" />
- <processor class="solr.RemoveBlankFieldUpdateProcessorFactory"/>
- <processor class="solr.FieldNameMutatingUpdateProcessorFactory">
- <str name="pattern">[^\w-\.]</str>
- <str name="replacement">_</str>
- </processor>
- <processor class="solr.ParseBooleanFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseLongFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseDoubleFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseDateFieldUpdateProcessorFactory">
- <arr name="format">
- <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss</str>
- <str>yyyy-MM-dd'T'HH:mmZ</str>
- <str>yyyy-MM-dd'T'HH:mm</str>
- <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd HH:mm:ssZ</str>
- <str>yyyy-MM-dd HH:mm:ss</str>
- <str>yyyy-MM-dd HH:mmZ</str>
- <str>yyyy-MM-dd HH:mm</str>
- <str>yyyy-MM-dd</str>
- </arr>
- </processor>
- <processor class="solr.AddSchemaFieldsUpdateProcessorFactory">
- <str name="defaultFieldType">strings</str>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Boolean</str>
- <str name="fieldType">booleans</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.util.Date</str>
- <str name="fieldType">pdates</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Long</str>
- <str name="valueClass">java.lang.Integer</str>
- <str name="fieldType">plongs</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Number</str>
- <str name="fieldType">pdoubles</str>
- </lst>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory"/>
- <processor class="solr.DistributedUpdateProcessorFactory"/>
- <processor class="solr.RunUpdateProcessorFactory"/>
- </updateRequestProcessorChain>
-
- <!-- Deduplication
-
- An example dedup update processor that creates the "id" field
- on the fly based on the hash code of some other fields. This
- example has overwriteDupes set to false since we are using the
- id field as the signatureField and Solr will maintain
- uniqueness based on that anyway.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Language identification
-
- This example update chain identifies the language of the incoming
- documents using the langid contrib. The detected language is
- written to field language_s. No field name mapping is done.
- The fields used for detection are text, title, subject and description,
- making this example suitable for detecting languages form full-text
- rich documents injected via ExtractingRequestHandler.
- See more about langId at http://wiki.apache.org/solr/LanguageDetection
- -->
- <!--
- <updateRequestProcessorChain name="langid">
- <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
- <str name="langid.fl">text,title,subject,description</str>
- <str name="langid.langField">language_s</str>
- <str name="langid.fallback">en</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Script update processor
-
- This example hooks in an update processor implemented using JavaScript.
-
- See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
- -->
- <!--
- <updateRequestProcessorChain name="script">
- <processor class="solr.StatelessScriptUpdateProcessorFactory">
- <str name="script">update-script.js</str>
- <lst name="params">
- <str name="config_param">example config parameter</str>
- </lst>
- </processor>
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
- -->
-
- <queryResponseWriter name="json" class="solr.JSONResponseWriter">
- <!-- For the purposes of the tutorial, JSON responses are written as
- plain text so that they are easy to read in *any* browser.
- If you expect a MIME type of "application/json" just remove this override.
- -->
- <str name="content-type">text/plain; charset=UTF-8</str>
- </queryResponseWriter>
-
- <!--
- Custom response writers can be declared as needed...
- -->
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
- <str name="template.base.dir">${velocity.template.base.dir:}</str>
- <str name="solr.resource.loader.enabled">${velocity.solr.resource.loader.enabled:true}</str>
- <str name="params.resource.loader.enabled">${velocity.params.resource.loader.enabled:false}</str>
- </queryResponseWriter>
-
- <!-- XSLT response writer transforms the XML output by any xslt file found
- in Solr's conf/xslt directory. Changes to xslt files are checked for
- every xsltCacheLifetimeSeconds.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- https://cwiki.apache.org/confluence/display/solr/Query+Syntax+and+Parsing
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
-
- <!-- Document Transformers
- http://wiki.apache.org/solr/DocTransformers
- -->
- <!--
- Could be something like:
- <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
- <int name="connection">jdbc://....</int>
- </transformer>
-
- To add a constant value to all docs, use:
- <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <int name="value">5</int>
- </transformer>
-
- If you want the user to still be able to change it with _value:something_ use this:
- <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <double name="defaultValue">5</double>
- </transformer>
-
- If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
- EditorialMarkerFactory will do exactly that:
- <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
- -->
-</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/stopwords.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/stopwords.txt
deleted file mode 100644
index ae1e83e..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/stopwords.txt
+++ /dev/null
@@ -1,14 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/synonyms.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/synonyms.txt
deleted file mode 100644
index eab4ee8..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/synonyms.txt
+++ /dev/null
@@ -1,29 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-#some test synonym mappings unlikely to appear in real input text
-aaafoo => aaabar
-bbbfoo => bbbfoo bbbbar
-cccfoo => cccbar cccbaz
-fooaaa,baraaa,bazaaa
-
-# Some synonym groups specific to this example
-GB,gib,gigabyte,gigabytes
-MB,mib,megabyte,megabytes
-Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
-#after us won't split it into two words.
-
-# Synonym mappings can be used for spelling correction too
-pixima => pixma
-
[09/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10882: Rewords
error message on Anova evaluator
Posted by sh...@apache.org.
SOLR-10882: Rewords error message on Anova evaluator
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/5fca6a4d
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/5fca6a4d
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/5fca6a4d
Branch: refs/heads/feature/autoscaling
Commit: 5fca6a4d829ad6c77fffd772a4006e885129b79b
Parents: 606824a
Author: Dennis Gove <dp...@gmail.com>
Authored: Tue Jun 13 09:35:16 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Sun Jun 18 11:50:57 2017 -0400
----------------------------------------------------------------------
.../org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/5fca6a4d/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java
index 45c3c3f..ca962f1 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java
@@ -19,6 +19,7 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
+import java.util.Locale;
import java.util.HashMap;
import java.util.Map;
@@ -38,8 +39,8 @@ public class AnovaEvaluator extends ComplexEvaluator implements Expressible {
public AnovaEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
- if(subEvaluators.size() < 2) {
- throw new IOException("ANOVA evaluator expects atleast 2 parameters found: "+subEvaluators.size());
+ if(subEvaluators.size() < 2){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting at least two values but found %d",expression,subEvaluators.size()));
}
}
[37/50] [abbrv] lucene-solr:feature/autoscaling: LUCENE-7873: The SPI
lookup of Codecs, PostingsFormats,
DocValuesFormats and all analysis factories was changed to only inspect the
current classloader that defined the interface class (lucene-core.jar)
Posted by sh...@apache.org.
LUCENE-7873: The SPI lookup of Codecs, PostingsFormats, DocValuesFormats and all analysis factories was changed to only inspect the current classloader that defined the interface class (lucene-core.jar)
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/63a40052
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/63a40052
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/63a40052
Branch: refs/heads/feature/autoscaling
Commit: 63a400528267e1ce396b53b162b64fb49e3e4e45
Parents: 3bb8939
Author: Uwe Schindler <us...@apache.org>
Authored: Tue Jun 20 16:43:54 2017 +0200
Committer: Uwe Schindler <us...@apache.org>
Committed: Tue Jun 20 16:43:54 2017 +0200
----------------------------------------------------------------------
lucene/CHANGES.txt | 6 +++
lucene/MIGRATE.txt | 41 ++++++++++++++++++++
.../lucene/analysis/util/AnalysisSPILoader.java | 2 +-
.../org/apache/lucene/util/NamedSPILoader.java | 2 +-
.../apache/lucene/util/SPIClassIterator.java | 10 ++---
5 files changed, 53 insertions(+), 8 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/63a40052/lucene/CHANGES.txt
----------------------------------------------------------------------
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index e708888..1f53d68 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -133,6 +133,12 @@ Other
* LUCENE-7719: Generalized the UnifiedHighlighter's support for AutomatonQuery
for character & binary automata. Added AutomatonQuery.isBinary. (David Smiley)
+* LUCENE-7873: Due to serious problems with context class loaders in several
+ frameworks (OSGI, Java 9 Jigsaw), the lookup of Codecs, PostingsFormats,
+ DocValuesFormats and all analysis factories was changed to only inspect the
+ current classloader that defined the interface class (lucene-core.jar).
+ See MIGRATE.txt for more information! (Uwe Schindler, Dawid Weiss)
+
======================= Lucene 6.7.0 =======================
New Features
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/63a40052/lucene/MIGRATE.txt
----------------------------------------------------------------------
diff --git a/lucene/MIGRATE.txt b/lucene/MIGRATE.txt
index 89b2d76..117b49c 100644
--- a/lucene/MIGRATE.txt
+++ b/lucene/MIGRATE.txt
@@ -1,5 +1,46 @@
# Apache Lucene Migration Guide
+## Changed SPI lookups for codecs and analysis changed (LUCENE-7873) ##
+
+Due to serious problems with context class loaders in several frameworks
+(OSGI, Java 9 Jigsaw), the lookup of Codecs, PostingsFormats, DocValuesFormats
+and all analysis factories was changed to only inspect the current classloader
+that defined the interface class (`lucene-core.jar`). Normal applications
+should not encounter any issues with that change, because the application
+classloader (unnamed module in Java 9) can load all SPIs from all JARs
+from classpath.
+
+For any code that relies on the old behaviour (e.g., certain web applications
+or components in application servers) one can manually instruct the Lucene
+SPI implementation to also inspect the context classloader. To do this,
+add this code to the early startup phase of your application before any
+Apache Lucene component is used:
+
+ ClassLoader cl = Thread.currentThread().getContextClassLoader();
+ // Codecs:
+ PostingsFormat.reloadPostingsFormats(cl);
+ DocValuesFormat.reloadDocValuesFormats(cl);
+ Codec.reloadCodecs(cl);
+ // Analysis:
+ CharFilterFactory.reloadCharFilters(cl);
+ TokenFilterFactory.reloadTokenFilters(cl);
+ TokenizerFactory.reloadTokenizers(cl);
+
+This code will reload all service providers from the given class loader
+(in our case the context class loader). Of course, instead of specifying
+the context class loader, it is receommended to use the application's main
+class loader or the module class loader.
+
+If you are migrating your project to Java 9 Jigsaw module system, keep in mind
+that Lucene currently does not yet support `module-info.java` declarations of
+service provider impls (`provides` statement). It is therefore recommended
+to keep all of Lucene in one Uber-Module and not try to split Lucene into
+several modules. As soon as Lucene will migrate to Java 9 as minimum requirement,
+we will work on improving that.
+
+For OSGI, the same applies. You have to create a bundle with all of Lucene for
+SPI to work correctly.
+
## Query.hashCode and Query.equals are now abstract methods (LUCENE-7277)
Any custom query subclasses should redeclare equivalence relationship according
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/63a40052/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/AnalysisSPILoader.java
----------------------------------------------------------------------
diff --git a/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/AnalysisSPILoader.java b/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/AnalysisSPILoader.java
index 8dacf63..13f5028 100644
--- a/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/AnalysisSPILoader.java
+++ b/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/AnalysisSPILoader.java
@@ -48,7 +48,7 @@ public final class AnalysisSPILoader<S extends AbstractAnalysisFactory> {
}
public AnalysisSPILoader(Class<S> clazz, String[] suffixes) {
- this(clazz, suffixes, Thread.currentThread().getContextClassLoader());
+ this(clazz, suffixes, null);
}
public AnalysisSPILoader(Class<S> clazz, String[] suffixes, ClassLoader classloader) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/63a40052/lucene/core/src/java/org/apache/lucene/util/NamedSPILoader.java
----------------------------------------------------------------------
diff --git a/lucene/core/src/java/org/apache/lucene/util/NamedSPILoader.java b/lucene/core/src/java/org/apache/lucene/util/NamedSPILoader.java
index b882ec7..56ef574 100644
--- a/lucene/core/src/java/org/apache/lucene/util/NamedSPILoader.java
+++ b/lucene/core/src/java/org/apache/lucene/util/NamedSPILoader.java
@@ -35,7 +35,7 @@ public final class NamedSPILoader<S extends NamedSPILoader.NamedSPI> implements
private final Class<S> clazz;
public NamedSPILoader(Class<S> clazz) {
- this(clazz, Thread.currentThread().getContextClassLoader());
+ this(clazz, null);
}
public NamedSPILoader(Class<S> clazz, ClassLoader classloader) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/63a40052/lucene/core/src/java/org/apache/lucene/util/SPIClassIterator.java
----------------------------------------------------------------------
diff --git a/lucene/core/src/java/org/apache/lucene/util/SPIClassIterator.java b/lucene/core/src/java/org/apache/lucene/util/SPIClassIterator.java
index 79a9573..6c26397 100644
--- a/lucene/core/src/java/org/apache/lucene/util/SPIClassIterator.java
+++ b/lucene/core/src/java/org/apache/lucene/util/SPIClassIterator.java
@@ -48,13 +48,11 @@ public final class SPIClassIterator<S> implements Iterator<Class<? extends S>> {
private final Enumeration<URL> profilesEnum;
private Iterator<String> linesIterator;
- /** Creates a new SPI iterator to lookup services of type {@code clazz} using the context classloader. */
+ /** Creates a new SPI iterator to lookup services of type {@code clazz} using
+ * the same {@link ClassLoader} as the argument. */
public static <S> SPIClassIterator<S> get(Class<S> clazz) {
- ClassLoader cl = Thread.currentThread().getContextClassLoader();
- if (cl == null) {
- cl = clazz.getClassLoader();
- }
- return new SPIClassIterator<>(clazz, cl);
+ return new SPIClassIterator<>(clazz,
+ Objects.requireNonNull(clazz.getClassLoader(), () -> clazz + " has no classloader."));
}
/** Creates a new SPI iterator to lookup services of type {@code clazz} using the given classloader. */
[50/50] [abbrv] lucene-solr:feature/autoscaling: Merge branch
'master' into feature/autoscaling
Posted by sh...@apache.org.
Merge branch 'master' into feature/autoscaling
# Conflicts:
# solr/CHANGES.txt
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/fb7803d9
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/fb7803d9
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/fb7803d9
Branch: refs/heads/feature/autoscaling
Commit: fb7803d9a0322ddc79e0c5f63641186ad5a3577d
Parents: b7ea703 2d26d7e
Author: Shalin Shekhar Mangar <sh...@apache.org>
Authored: Wed Jun 21 12:35:48 2017 +0530
Committer: Shalin Shekhar Mangar <sh...@apache.org>
Committed: Wed Jun 21 12:35:48 2017 +0530
----------------------------------------------------------------------
dev-tools/doap/lucene.rdf | 7 +
dev-tools/doap/solr.rdf | 7 +
dev-tools/idea/solr/solrj/src/java/solrj.iml | 3 +
lucene/CHANGES.txt | 52 ++
lucene/MIGRATE.txt | 41 ++
.../DelimitedTermFrequencyTokenFilter.java | 75 +++
...elimitedTermFrequencyTokenFilterFactory.java | 53 ++
.../lucene/analysis/util/AnalysisSPILoader.java | 2 +-
.../wikipedia/WikipediaTokenizerFactory.java | 21 +-
...ache.lucene.analysis.util.TokenFilterFactory | 1 +
.../lucene/analysis/core/TestFactories.java | 46 +-
.../lucene/analysis/core/TestRandomChains.java | 3 +
.../DelimitedTermFrequencyTokenFilterTest.java | 77 +++
.../TestWikipediaTokenizerFactory.java | 84 ++-
.../lucene/analysis/ja/TestFactories.java | 46 +-
.../index/TestBackwardsCompatibility.java | 6 +-
.../org/apache/lucene/index/index.6.6.0-cfs.zip | Bin 0 -> 15875 bytes
.../apache/lucene/index/index.6.6.0-nocfs.zip | Bin 0 -> 15883 bytes
.../PackedTokenAttributeImpl.java | 29 +-
.../tokenattributes/TermFrequencyAttribute.java | 33 ++
.../TermFrequencyAttributeImpl.java | 82 +++
.../codecs/blocktree/BlockTreeTermsReader.java | 37 +-
.../apache/lucene/document/RangeFieldQuery.java | 377 +++++++-----
.../lucene/index/BufferedUpdatesStream.java | 8 +-
.../org/apache/lucene/index/CodecReader.java | 11 +-
.../lucene/index/DefaultIndexingChain.java | 8 +-
.../lucene/index/ExitableDirectoryReader.java | 40 +-
.../apache/lucene/index/FieldInvertState.java | 3 +
.../java/org/apache/lucene/index/Fields.java | 10 +-
.../apache/lucene/index/FilterLeafReader.java | 6 +-
.../index/FreqProxTermsWriterPerField.java | 27 +-
.../org/apache/lucene/index/LeafReader.java | 15 +-
.../apache/lucene/index/MergeReaderWrapper.java | 7 +-
.../org/apache/lucene/index/MultiFields.java | 69 ++-
.../apache/lucene/index/ParallelLeafReader.java | 33 +-
.../lucene/index/SlowCodecReaderWrapper.java | 16 +-
.../apache/lucene/index/SortingLeafReader.java | 6 +-
.../index/TermVectorsConsumerPerField.java | 19 +-
.../apache/lucene/index/TermsHashPerField.java | 5 +-
.../apache/lucene/search/AutomatonQuery.java | 7 +
.../lucene/search/DisjunctionMaxQuery.java | 8 +
.../apache/lucene/search/TermInSetQuery.java | 4 +-
.../org/apache/lucene/util/NamedSPILoader.java | 2 +-
.../org/apache/lucene/util/QueryBuilder.java | 6 +-
.../apache/lucene/util/SPIClassIterator.java | 10 +-
.../org/apache/lucene/analysis/TestToken.java | 2 +
.../TestPackedTokenAttributeImpl.java | 2 +
.../lucene50/TestBlockPostingsFormat.java | 2 +-
.../org/apache/lucene/index/Test2BDocs.java | 2 +-
.../apache/lucene/index/TestCustomTermFreq.java | 468 +++++++++++++++
.../test/org/apache/lucene/index/TestDoc.java | 10 +-
.../index/TestExitableDirectoryReader.java | 16 +-
.../lucene/index/TestFieldInvertState.java | 139 +++++
.../lucene/index/TestFilterLeafReader.java | 17 +-
.../test/org/apache/lucene/index/TestFlex.java | 13 +-
.../lucene/index/TestIndexReaderClose.java | 8 +-
.../apache/lucene/index/TestIndexWriter.java | 4 +-
.../lucene/index/TestIndexWriterUnicode.java | 2 +-
.../lucene/index/TestParallelTermEnum.java | 20 +-
.../org/apache/lucene/index/TestPayloads.java | 4 +-
.../lucene/index/TestPerSegmentDeletes.java | 4 +-
.../lucene/index/TestPostingsOffsets.java | 2 +-
.../lucene/index/TestSegmentTermDocs.java | 2 +-
.../lucene/index/TestSegmentTermEnum.java | 10 +-
.../apache/lucene/index/TestStressAdvance.java | 11 +-
.../org/apache/lucene/index/TestTermsEnum.java | 23 +-
.../lucene/search/TermInSetQueryTest.java | 24 +-
.../lucene/search/TestDisjunctionMaxQuery.java | 15 +
.../lucene/search/TestMultiPhraseQuery.java | 2 +-
.../lucene/search/TestPhrasePrefixQuery.java | 2 +-
.../search/TestSameScoresWithThreads.java | 2 +-
.../org/apache/lucene/search/TestTermQuery.java | 43 +-
.../apache/lucene/util/TestQueryBuilder.java | 28 +-
.../search/highlight/TermVectorLeafReader.java | 8 +-
.../highlight/WeightedSpanTermExtractor.java | 25 +-
.../uhighlight/MemoryIndexOffsetStrategy.java | 3 +-
.../uhighlight/MultiTermHighlighting.java | 124 ++--
.../lucene/search/uhighlight/PhraseHelper.java | 29 +-
.../TermVectorFilteredLeafReader.java | 22 +-
.../uhighlight/TestSplittingBreakIterator.java | 1 -
.../uhighlight/TestUnifiedHighlighter.java | 3 -
.../uhighlight/TestUnifiedHighlighterMTQ.java | 69 ++-
.../TestUnifiedHighlighterRanking.java | 3 -
.../TestUnifiedHighlighterReanalysis.java | 2 -
.../TestUnifiedHighlighterStrictPhrases.java | 2 -
.../TestUnifiedHighlighterTermVec.java | 2 -
.../TestUnifiedHighlighterExtensibility.java | 26 +-
.../apache/lucene/search/join/TestJoinUtil.java | 5 +-
.../apache/lucene/index/memory/MemoryIndex.java | 43 +-
.../lucene/index/memory/TestMemoryIndex.java | 26 +-
.../memory/TestMemoryIndexAgainstRAMDir.java | 5 +-
.../org/apache/lucene/misc/IndexMergeTool.java | 11 +-
.../apache/lucene/queries/CommonTermsQuery.java | 4 +-
.../function/valuesource/TFValueSource.java | 6 +-
.../valuesource/TermFreqValueSource.java | 6 +-
.../classic/TestMultiFieldQueryParser.java | 2 +-
.../queryparser/classic/TestQueryParser.java | 89 ++-
.../idversion/TestIDVersionPostingsFormat.java | 4 +-
.../lucene/index/AssertingLeafReader.java | 7 +-
.../index/BaseIndexFileFormatTestCase.java | 2 +-
.../index/BasePostingsFormatTestCase.java | 15 +-
.../lucene/index/FieldFilterLeafReader.java | 9 +-
.../ThreadedIndexingAndSearchingTestCase.java | 12 +-
.../org/apache/lucene/search/QueryUtils.java | 26 +-
.../org/apache/lucene/util/LuceneTestCase.java | 4 +-
solr/CHANGES.txt | 130 ++++-
solr/bin/solr | 35 +-
solr/bin/solr.cmd | 54 +-
solr/bin/solr.in.cmd | 4 +
solr/bin/solr.in.sh | 4 +
.../collection1/conf/schema-icucollate-dv.xml | 4 +-
.../solr/collection1/conf/schema-icucollate.xml | 4 +-
.../conf/schema-icucollateoptions.xml | 4 +-
.../solr/schema/TestICUCollationField.java | 28 +-
.../schema/TestICUCollationFieldDocValues.java | 28 +-
.../schema/TestICUCollationFieldOptions.java | 26 +-
.../solr/collection1/conf/solrconfig.xml | 7 +-
.../collection1/conf/dataimport-solrconfig.xml | 5 +-
.../handler/dataimport/VariableResolver.java | 4 +-
.../conf/contentstream-solrconfig.xml | 7 +-
.../conf/dataimport-nodatasource-solrconfig.xml | 5 +-
.../collection1/conf/dataimport-solrconfig.xml | 5 +-
.../solr/collection1/conf/solrconfig.xml | 3 +-
.../conf/solrconfig-languageidentifier.xml | 3 +-
.../apache/solr/ltr/TestLTRScoringQuery.java | 20 +-
.../solr/ltr/TestSelectiveWeightCreation.java | 14 +-
.../apache/solr/ltr/model/TestLinearModel.java | 10 +
.../model/TestMultipleAdditiveTreesModel.java | 17 +-
.../uima/solr/collection1/conf/solrconfig.xml | 4 +-
.../uima/uima-tokenizers-solrconfig.xml | 4 +-
solr/core/src/java/org/apache/solr/api/Api.java | 3 +-
.../src/java/org/apache/solr/api/ApiBag.java | 32 +-
.../java/org/apache/solr/api/SpecProvider.java | 25 -
.../java/org/apache/solr/api/V2HttpCall.java | 60 +-
.../org/apache/solr/cloud/ReplaceNodeCmd.java | 96 ++-
.../apache/solr/cloud/ReplicateFromLeader.java | 6 +-
.../solr/core/CachingDirectoryFactory.java | 10 +
.../org/apache/solr/core/CoreContainer.java | 9 +-
.../org/apache/solr/core/DirectoryFactory.java | 24 +-
.../java/org/apache/solr/core/PluginBag.java | 32 +-
.../java/org/apache/solr/core/SolrConfig.java | 6 +-
.../apache/solr/handler/AnalyzeEvaluator.java | 11 +-
.../org/apache/solr/handler/ExportWriter.java | 105 ++--
.../org/apache/solr/handler/IndexFetcher.java | 2 +-
.../solr/handler/MoreLikeThisHandler.java | 7 +
.../apache/solr/handler/ReplicationHandler.java | 2 +-
.../org/apache/solr/handler/StreamHandler.java | 479 ++++++++-------
.../solr/handler/UpdateRequestHandlerApi.java | 4 +-
.../handler/admin/BaseHandlerApiSupport.java | 3 +-
.../apache/solr/handler/admin/InfoHandler.java | 2 +-
.../solr/handler/admin/LukeRequestHandler.java | 10 +-
.../solr/handler/admin/SecurityConfHandler.java | 12 +-
.../handler/component/HttpShardHandler.java | 31 +-
.../component/QueryElevationComponent.java | 5 +-
.../solr/handler/component/TermsComponent.java | 38 +-
.../solr/highlight/DefaultSolrHighlighter.java | 2 +-
.../solr/highlight/UnifiedSolrHighlighter.java | 7 +
.../solr/index/SlowCompositeReaderWrapper.java | 4 +-
.../metrics/reporters/SolrGangliaReporter.java | 4 -
.../metrics/reporters/SolrGraphiteReporter.java | 4 -
.../metrics/reporters/SolrSlf4jReporter.java | 3 +-
.../org/apache/solr/request/SimpleFacets.java | 4 +-
.../solr/request/SolrQueryRequestBase.java | 21 +-
.../solr/response/BinaryResponseWriter.java | 12 +-
.../java/org/apache/solr/schema/BBoxField.java | 7 +-
.../apache/solr/schema/DoublePointField.java | 10 +-
.../org/apache/solr/schema/FloatPointField.java | 10 +-
.../org/apache/solr/schema/IndexSchema.java | 37 +-
.../org/apache/solr/schema/IntPointField.java | 10 +-
.../org/apache/solr/schema/LongPointField.java | 10 +-
.../apache/solr/schema/NumericFieldType.java | 88 ++-
.../java/org/apache/solr/schema/PointField.java | 7 +-
.../java/org/apache/solr/schema/TrieField.java | 60 +-
.../java/org/apache/solr/search/CursorMark.java | 21 +-
.../java/org/apache/solr/search/DocSetUtil.java | 4 +-
.../solr/search/ExtendedDismaxQParser.java | 7 +-
.../src/java/org/apache/solr/search/Filter.java | 2 +-
.../solr/search/FloatPayloadValueSource.java | 4 +-
.../solr/search/GraphTermsQParserPlugin.java | 16 +-
.../solr/search/IGainTermsQParserPlugin.java | 5 +-
.../apache/solr/search/JoinQParserPlugin.java | 12 +-
.../search/SignificantTermsQParserPlugin.java | 9 +-
.../TextLogisticRegressionQParserPlugin.java | 5 +-
.../apache/solr/search/facet/FacetField.java | 6 +-
.../solr/search/facet/FacetFieldProcessor.java | 1 +
.../FacetFieldProcessorByEnumTermsStream.java | 4 +-
.../facet/FacetFieldProcessorByHashDV.java | 33 +-
.../apache/solr/search/facet/FacetModule.java | 6 +-
.../apache/solr/search/facet/FacetRange.java | 147 ++++-
.../org/apache/solr/search/facet/FieldUtil.java | 6 +
.../org/apache/solr/search/facet/HLLAgg.java | 83 ++-
.../org/apache/solr/search/facet/UniqueAgg.java | 76 ++-
.../apache/solr/security/BasicAuthPlugin.java | 2 +-
.../security/RuleBasedAuthorizationPlugin.java | 6 +-
.../security/Sha256AuthenticationProvider.java | 4 +-
.../org/apache/solr/servlet/HttpSolrCall.java | 13 +-
.../apache/solr/servlet/SolrRequestParsers.java | 13 +-
.../apache/solr/uninverting/DocTermOrds.java | 4 +-
.../apache/solr/update/AddUpdateCommand.java | 8 +-
.../solr/update/DirectUpdateHandler2.java | 3 +-
.../org/apache/solr/update/DocumentBuilder.java | 8 +-
.../apache/solr/update/SolrIndexSplitter.java | 4 +-
.../java/org/apache/solr/update/UpdateLog.java | 22 +-
.../org/apache/solr/update/VersionInfo.java | 76 ++-
.../AddSchemaFieldsUpdateProcessorFactory.java | 12 +-
.../processor/AtomicUpdateProcessorFactory.java | 3 +-
.../processor/SimpleUpdateProcessorFactory.java | 18 +-
.../TemplateUpdateProcessorFactory.java | 23 +-
.../processor/UpdateRequestProcessorChain.java | 19 +-
.../apache/solr/util/JsonSchemaValidator.java | 277 ---------
.../src/java/org/apache/solr/util/PathTrie.java | 195 -------
.../resources/apispec/autoscaling.Commands.json | 194 -------
.../src/resources/apispec/cluster.Commands.json | 74 ---
.../src/resources/apispec/cluster.aliases.json | 12 -
.../apispec/cluster.commandstatus.delete.json | 10 -
.../apispec/cluster.commandstatus.json | 20 -
.../apispec/cluster.configs.Commands.json | 34 --
.../apispec/cluster.configs.delete.json | 12 -
.../src/resources/apispec/cluster.configs.json | 12 -
solr/core/src/resources/apispec/cluster.json | 14 -
.../src/resources/apispec/cluster.nodes.json | 12 -
.../cluster.security.BasicAuth.Commands.json | 23 -
...cluster.security.RuleBasedAuthorization.json | 129 -----
...luster.security.authentication.Commands.json | 12 -
.../cluster.security.authentication.json | 12 -
...cluster.security.authorization.Commands.json | 13 -
.../apispec/cluster.security.authorization.json | 13 -
.../resources/apispec/collections.Commands.json | 218 -------
.../collections.collection.Commands.json | 137 -----
.../collections.collection.Commands.modify.json | 36 --
.../collections.collection.Commands.reload.json | 11 -
.../apispec/collections.collection.delete.json | 13 -
.../apispec/collections.collection.json | 19 -
.../collections.collection.shards.Commands.json | 114 ----
...ctions.collection.shards.shard.Commands.json | 24 -
...lections.collection.shards.shard.delete.json | 27 -
....collection.shards.shard.replica.delete.json | 39 --
.../core/src/resources/apispec/collections.json | 13 -
.../src/resources/apispec/core.RealtimeGet.json | 26 -
.../apispec/core.SchemaEdit.addCopyField.json | 27 -
.../apispec/core.SchemaEdit.addField.json | 98 ----
.../core.SchemaEdit.addFieldType.analyzers.json | 51 --
.../apispec/core.SchemaEdit.addFieldType.json | 53 --
.../core.SchemaEdit.deleteCopyField.json | 19 -
.../core.SchemaEdit.deleteDynamicField.json | 12 -
.../apispec/core.SchemaEdit.deleteField.json | 12 -
.../core.SchemaEdit.deleteFieldType.json | 14 -
.../src/resources/apispec/core.SchemaEdit.json | 47 --
.../apispec/core.SchemaRead.copyFields.json | 26 -
...ore.SchemaRead.dynamicFields_fieldTypes.json | 20 -
.../apispec/core.SchemaRead.fields.json | 34 --
.../src/resources/apispec/core.SchemaRead.json | 17 -
.../core/src/resources/apispec/core.Update.json | 17 -
...g.Commands.addRequestHandler.properties.json | 25 -
.../apispec/core.config.Commands.generic.json | 19 -
.../resources/apispec/core.config.Commands.json | 215 -------
.../core.config.Commands.runtimeLib.json | 23 -
.../apispec/core.config.Params.Commands.json | 31 -
.../resources/apispec/core.config.Params.json | 13 -
.../core/src/resources/apispec/core.config.json | 18 -
.../src/resources/apispec/core.system.blob.json | 20 -
.../apispec/core.system.blob.upload.json | 12 -
.../src/resources/apispec/cores.Commands.json | 85 ---
.../src/resources/apispec/cores.Status.json | 20 -
.../resources/apispec/cores.core.Commands.json | 136 -----
.../apispec/cores.core.Commands.split.json | 34 --
solr/core/src/resources/apispec/emptySpec.json | 11 -
.../src/resources/apispec/node.Commands.json | 24 -
solr/core/src/resources/apispec/node.Info.json | 11 -
.../core/src/resources/apispec/node.invoke.json | 16 -
.../solr/analysisconfs/analysis-err-schema.xml | 4 +-
...-schema-uniquekey-diff-type-dynamic-root.xml | 36 ++
.../bad-schema-uniquekey-diff-type-root.xml | 35 ++
.../conf/bad-schema-uniquekey-uses-points.xml | 28 +
...chema-add-schema-fields-update-processor.xml | 22 +
.../collection1/conf/schema-binaryfield.xml | 2 +-
.../conf/schema-blockjoinfacetcomponent.xml | 4 +-
.../solr/collection1/conf/schema-bm25.xml | 4 +-
.../collection1/conf/schema-charfilters.xml | 4 +-
.../solr/collection1/conf/schema-collate-dv.xml | 4 +-
.../solr/collection1/conf/schema-collate.xml | 4 +-
.../collection1/conf/schema-copyfield-test.xml | 2 +-
.../collection1/conf/schema-custom-field.xml | 6 +-
.../collection1/conf/schema-customfield.xml | 3 +-
.../solr/collection1/conf/schema-dfi.xml | 4 +-
.../solr/collection1/conf/schema-dfr.xml | 4 +-
.../conf/schema-distributed-missing-sort.xml | 6 +-
.../solr/collection1/conf/schema-docValues.xml | 5 +-
.../conf/schema-field-sort-values.xml | 2 +-
.../solr/collection1/conf/schema-hash.xml | 2 +-
.../solr/collection1/conf/schema-ib.xml | 4 +-
.../collection1/conf/schema-lmdirichlet.xml | 4 +-
.../collection1/conf/schema-lmjelinekmercer.xml | 4 +-
.../conf/schema-not-required-unique-key.xml | 2 +-
.../collection1/conf/schema-phrasesuggest.xml | 4 +-
.../solr/collection1/conf/schema-point.xml | 64 +-
.../conf/schema-postingshighlight.xml | 4 +-
.../collection1/conf/schema-replication1.xml | 2 +-
.../collection1/conf/schema-replication2.xml | 2 +-
.../collection1/conf/schema-required-fields.xml | 2 +-
.../solr/collection1/conf/schema-rest.xml | 33 +-
.../solr/collection1/conf/schema-reversed.xml | 2 +-
.../conf/schema-sim-default-override.xml | 4 +-
.../solr/collection1/conf/schema-sim.xml | 4 +-
.../collection1/conf/schema-simpleqpplugin.xml | 4 +-
.../collection1/conf/schema-sortingresponse.xml | 71 ++-
.../solr/collection1/conf/schema-sorts.xml | 2 +-
.../solr/collection1/conf/schema-spatial.xml | 10 +
.../solr/collection1/conf/schema-sql.xml | 2 +-
.../solr/collection1/conf/schema-sweetspot.xml | 4 +-
.../conf/schema-synonym-tokenizer.xml | 6 +-
.../solr/collection1/conf/schema-tfidf.xml | 4 +-
.../collection1/conf/schema-tokenizer-test.xml | 5 +-
.../solr/collection1/conf/schema-trie.xml | 2 +-
.../conf/schema-unifiedhighlight.xml | 4 +-
.../solr/collection1/conf/schema-version-dv.xml | 3 +-
.../collection1/conf/schema-version-indexed.xml | 3 +-
.../test-files/solr/collection1/conf/schema.xml | 21 +-
.../solr/collection1/conf/schema11.xml | 15 +-
.../solr/collection1/conf/schema12.xml | 23 +-
...dd-schema-fields-update-processor-chains.xml | 30 +-
.../conf/solrconfig-analytics-query.xml | 3 +-
.../conf/solrconfig-collapseqparser.xml | 3 +-
.../conf/solrconfig-components-name.xml | 3 +-
.../conf/solrconfig-delaying-component.xml | 2 +-
.../conf/solrconfig-doctransformers.xml | 2 +-
.../collection1/conf/solrconfig-elevate.xml | 3 +-
.../solr/collection1/conf/solrconfig-hash.xml | 2 +-
.../conf/solrconfig-master-throttled.xml | 3 +-
.../solr/collection1/conf/solrconfig-master.xml | 3 +-
.../conf/solrconfig-master1-keepOneBackup.xml | 3 +-
.../collection1/conf/solrconfig-master1.xml | 3 +-
.../collection1/conf/solrconfig-master2.xml | 3 +-
.../collection1/conf/solrconfig-master3.xml | 3 +-
.../collection1/conf/solrconfig-nocache.xml | 2 +-
.../conf/solrconfig-plugcollector.xml | 3 +-
.../collection1/conf/solrconfig-repeater.xml | 3 +-
.../collection1/conf/solrconfig-schemaless.xml | 6 +-
.../solr/collection1/conf/solrconfig-slave.xml | 3 +-
.../solr/collection1/conf/solrconfig-slave1.xml | 3 +-
.../solr/collection1/conf/solrconfig-sql.xml | 2 +-
.../solr/collection1/conf/solrconfig.xml | 3 +-
.../solr/collection1/conf/solrconfig_perf.xml | 2 +-
.../solr/configsets/cloud-hdfs/conf/schema.xml | 2 +-
.../conf/managed-schema | 2 +-
.../cloud-managed-upgrade/conf/schema.xml | 2 +-
.../cloud-managed/conf/managed-schema | 2 +-
.../cloud-minimal-jmx/conf/schema.xml | 2 +-
.../configsets/cloud-minimal/conf/schema.xml | 3 +-
.../configsets/cloud-subdirs/conf/schema.xml | 2 +-
.../solr/configsets/configset-2/conf/schema.xml | 4 +-
.../exitable-directory/conf/schema.xml | 2 +-
.../test-files/solr/crazy-path-to-schema.xml | 4 +-
.../org/apache/solr/BasicFunctionalityTest.java | 113 +++-
.../test/org/apache/solr/CursorPagingTest.java | 58 +-
.../apache/solr/DisMaxRequestHandlerTest.java | 22 +-
.../src/test/org/apache/solr/SampleTest.java | 4 +-
.../apache/solr/TestDistributedGrouping.java | 18 +-
.../apache/solr/TestDistributedMissingSort.java | 60 +-
.../org/apache/solr/TestDistributedSearch.java | 20 +-
.../org/apache/solr/TestTolerantSearch.java | 4 +-
.../PathHierarchyTokenizerFactoryTest.java | 32 +-
.../apache/solr/analysis/TestCharFilters.java | 8 +-
.../test/org/apache/solr/api/TestPathTrie.java | 61 --
.../solr/cloud/BasicDistributedZk2Test.java | 8 +-
.../solr/cloud/BasicDistributedZkTest.java | 10 +-
.../test/org/apache/solr/cloud/BasicZkTest.java | 4 +-
...MonkeyNothingIsSafeWithPullReplicasTest.java | 2 +
...aosMonkeySafeLeaderWithPullReplicasTest.java | 2 +
.../solr/cloud/DistribCursorPagingTest.java | 10 +-
.../cloud/DistribJoinFromCollectionTest.java | 8 +-
.../FullThrottleStoppableIndexingThread.java | 2 +-
.../apache/solr/cloud/HttpPartitionTest.java | 2 +-
.../org/apache/solr/cloud/ReplaceNodeTest.java | 9 +-
.../cloud/SegmentTerminateEarlyTestState.java | 30 +-
.../apache/solr/cloud/TestCollectionAPI.java | 29 +-
.../autoscaling/AutoScalingHandlerTest.java | 5 +-
.../apache/solr/core/DirectoryFactoryTest.java | 61 ++
.../test/org/apache/solr/core/HelloStream.java | 2 +-
.../test/org/apache/solr/core/MockInfoBean.java | 2 +-
.../test/org/apache/solr/core/SOLR749Test.java | 12 +-
.../apache/solr/core/TestJmxIntegration.java | 2 +-
.../core/snapshots/TestSolrCloudSnapshots.java | 2 +-
.../core/snapshots/TestSolrCoreSnapshots.java | 2 +-
.../solr/handler/MoreLikeThisHandlerTest.java | 20 +-
.../handler/StandardRequestHandlerTest.java | 24 +-
.../apache/solr/handler/TestReqParamsAPI.java | 2 +-
.../org/apache/solr/handler/TestSQLHandler.java | 32 +-
.../solr/handler/V2ApiIntegrationTest.java | 57 +-
.../apache/solr/handler/V2StandaloneTest.java | 53 ++
.../handler/XsltUpdateRequestHandlerTest.java | 2 +-
.../handler/admin/CoreAdminHandlerTest.java | 50 ++
.../solr/handler/admin/MBeansHandlerTest.java | 2 +-
.../admin/PropertiesRequestHandlerTest.java | 2 +-
.../solr/handler/admin/TestApiFramework.java | 2 +-
.../solr/handler/admin/TestCollectionAPIs.java | 10 +-
.../DistributedExpandComponentTest.java | 40 +-
.../component/DistributedMLTComponentTest.java | 12 +-
...DistributedQueryComponentCustomSortTest.java | 38 +-
.../DistributedQueryElevationComponentTest.java | 4 +-
.../component/QueryElevationComponentTest.java | 90 +--
.../handler/component/StatsComponentTest.java | 20 +-
...estDistributedStatsComponentCardinality.java | 4 +-
.../handler/component/TestExpandComponent.java | 100 ++--
.../apache/solr/request/SimpleFacetsTest.java | 144 ++---
.../org/apache/solr/request/TestFaceting.java | 14 +-
.../solr/response/TestBinaryResponseWriter.java | 5 +-
.../apache/solr/response/TestExportWriter.java | 199 ++++++-
.../response/TestJavabinTupleStreamParser.java | 20 +-
.../apache/solr/response/TestPushWriter.java | 8 +-
.../transform/TestChildDocTransformer.java | 120 ++--
.../transform/TestSubQueryTransformer.java | 28 +-
.../org/apache/solr/rest/TestRestManager.java | 2 +-
.../schema/TestFieldCollectionResource.java | 10 +-
.../solr/schema/AbstractCurrencyFieldTest.java | 82 +--
.../apache/solr/schema/BadIndexSchemaTest.java | 17 +
.../org/apache/solr/schema/CopyFieldTest.java | 12 +-
.../solr/schema/CurrencyFieldXmlFileTest.java | 4 +-
.../apache/solr/schema/DateRangeFieldTest.java | 2 +-
.../org/apache/solr/schema/DocValuesTest.java | 256 ++++----
.../schema/IndexSchemaRuntimeFieldTest.java | 4 +-
.../org/apache/solr/schema/IndexSchemaTest.java | 6 +-
.../org/apache/solr/schema/TestBinaryField.java | 6 +-
.../apache/solr/schema/TestCollationField.java | 32 +-
.../schema/TestCollationFieldDocValues.java | 32 +-
.../solr/schema/TestHalfAndHalfDocValues.java | 6 +-
.../apache/solr/schema/TestOmitPositions.java | 4 +-
.../org/apache/solr/schema/TestPointFields.java | 578 ++++++++++---------
.../apache/solr/search/SpatialFilterTest.java | 2 +-
.../solr/search/TestCollapseQParserPlugin.java | 280 ++++-----
.../TestComplexPhraseLeadingWildcard.java | 2 +-
.../org/apache/solr/search/TestCustomSort.java | 20 +-
.../test/org/apache/solr/search/TestDocSet.java | 5 +-
.../solr/search/TestExtendedDismaxParser.java | 22 +-
.../apache/solr/search/TestFieldSortValues.java | 10 +-
.../solr/search/TestFoldingMultitermQuery.java | 2 +-
.../search/TestGraphTermsQParserPlugin.java | 34 +-
.../solr/search/TestHashQParserPlugin.java | 14 +-
.../org/apache/solr/search/TestQueryTypes.java | 68 ++-
.../org/apache/solr/search/TestRangeQuery.java | 4 +-
.../solr/search/TestReRankQParserPlugin.java | 208 +++----
.../test/org/apache/solr/search/TestReload.java | 2 +-
.../org/apache/solr/search/TestSearchPerf.java | 2 +-
.../apache/solr/search/TestSolr4Spatial.java | 16 +-
.../apache/solr/search/TestSolrQueryParser.java | 42 +-
.../org/apache/solr/search/facet/DebugAgg.java | 5 +-
.../search/facet/TestJsonFacetRefinement.java | 65 ++-
.../solr/search/facet/TestJsonFacets.java | 12 +-
.../search/function/SortByFunctionTest.java | 68 +--
.../solr/search/function/TestFunctionQuery.java | 43 +-
.../function/TestMinMaxOnMultiValuedField.java | 153 +++--
.../solr/search/mlt/SimpleMLTQParserTest.java | 86 +--
.../solr/search/stats/TestDistribIDF.java | 14 +-
.../solr/security/MockAuthorizationPlugin.java | 2 +-
.../apache/solr/servlet/NoCacheHeaderTest.java | 2 +-
.../solr/spelling/suggest/SuggesterTest.java | 19 +-
.../suggest/TestAnalyzeInfixSuggestions.java | 2 +-
.../suggest/TestFreeTextSuggestions.java | 2 +-
.../apache/solr/update/AddBlockUpdateTest.java | 10 +-
.../org/apache/solr/update/VersionInfoTest.java | 126 ++--
...dSchemaFieldsUpdateProcessorFactoryTest.java | 16 +-
.../AtomicUpdateProcessorFactoryTest.java | 36 +-
.../update/processor/AtomicUpdatesTest.java | 36 +-
.../ClassificationUpdateProcessorTest.java | 2 +-
.../processor/TemplateUpdateProcessorTest.java | 67 ++-
.../UpdateRequestProcessorFactoryTest.java | 8 +-
.../org/apache/solr/util/JsonValidatorTest.java | 196 -------
.../org/apache/solr/util/PrimUtilsTest.java | 2 +-
.../test/org/apache/solr/util/TestUtils.java | 27 +-
.../org/apache/solr/util/UtilsToolTest.java | 2 +-
.../org/apache/solr/util/hll/BitVectorTest.java | 2 +-
.../apache/solr/util/hll/ExplicitHLLTest.java | 2 +-
.../org/apache/solr/util/hll/FullHLLTest.java | 2 +-
.../example-DIH/solr/db/conf/solrconfig.xml | 15 +-
.../example-DIH/solr/mail/conf/solrconfig.xml | 15 +-
.../example-DIH/solr/solr/conf/solrconfig.xml | 15 +-
solr/example/files/conf/managed-schema | 20 +
solr/example/files/conf/solrconfig.xml | 19 +-
.../basic_configs/conf/solrconfig.xml | 19 +-
.../conf/solrconfig.xml | 19 +-
.../conf/solrconfig.xml | 15 +-
solr/solr-ref-guide/build.xml | 31 +-
solr/solr-ref-guide/meta-docs/publish.adoc | 1 -
solr/solr-ref-guide/src/_config.yml.template | 9 +-
solr/solr-ref-guide/src/_includes/head.html | 2 -
...adding-custom-plugins-in-solrcloud-mode.adoc | 2 +-
.../src/basic-authentication-plugin.adoc | 22 +-
solr/solr-ref-guide/src/blockjoin-faceting.adoc | 19 +-
.../solr-ref-guide/src/charfilterfactories.adoc | 2 +-
solr/solr-ref-guide/src/cloud-screens.adoc | 2 +-
solr/solr-ref-guide/src/codec-factory.adoc | 2 +-
.../src/collapse-and-expand-results.adoc | 84 +--
solr/solr-ref-guide/src/collections-api.adoc | 28 +-
.../src/common-query-parameters.adoc | 30 +-
solr/solr-ref-guide/src/config-api.adoc | 2 +-
solr/solr-ref-guide/src/configsets-api.adoc | 30 +-
.../src/configuring-solrconfig-xml.adoc | 3 +-
solr/solr-ref-guide/src/content-streams.adoc | 28 +-
solr/solr-ref-guide/src/coreadmin-api.adoc | 8 +-
.../src/cross-data-center-replication-cdcr.adoc | 49 +-
solr/solr-ref-guide/src/css/ref-guide.css | 2 +-
...adir-and-directoryfactory-in-solrconfig.adoc | 4 +-
solr/solr-ref-guide/src/de-duplication.adoc | 45 +-
.../src/defining-core-properties.adoc | 52 +-
solr/solr-ref-guide/src/defining-fields.adoc | 18 +-
.../detecting-languages-during-indexing.adoc | 99 +++-
.../src/distributed-requests.adoc | 41 +-
.../distributed-search-with-index-sharding.adoc | 2 +-
solr/solr-ref-guide/src/enabling-ssl.adoc | 12 +-
.../src/exporting-result-sets.adoc | 2 +-
solr/solr-ref-guide/src/faceting.adoc | 58 +-
solr/solr-ref-guide/src/feed.xml | 28 -
.../field-type-definitions-and-properties.adoc | 40 +-
.../solr-ref-guide/src/filter-descriptions.adoc | 4 +-
solr/solr-ref-guide/src/format-of-solr-xml.adoc | 2 +-
solr/solr-ref-guide/src/function-queries.adoc | 134 ++++-
.../src/hadoop-authentication-plugin.adoc | 44 +-
solr/solr-ref-guide/src/highlighting.adoc | 4 +-
.../src/images/Solr_Logo_on_white.png | Bin 0 -> 47661 bytes
.../src/implicit-requesthandlers.adoc | 2 +-
solr/solr-ref-guide/src/index-replication.adoc | 194 ++++---
.../src/indexconfig-in-solrconfig.adoc | 29 +-
.../src/initparams-in-solrconfig.adoc | 16 +-
.../src/introduction-to-solr-indexing.adoc | 2 +-
solr/solr-ref-guide/src/jvm-settings.adoc | 2 +-
.../src/kerberos-authentication-plugin.adoc | 72 ++-
solr/solr-ref-guide/src/language-analysis.adoc | 6 +-
solr/solr-ref-guide/src/learning-to-rank.adoc | 2 +-
.../src/local-parameters-in-queries.adoc | 2 +-
.../major-changes-from-solr-5-to-solr-6.adoc | 6 +-
.../src/making-and-restoring-backups.adoc | 102 ++--
.../src/mbean-request-handler.adoc | 21 +-
solr/solr-ref-guide/src/merging-indexes.adoc | 2 +-
solr/solr-ref-guide/src/morelikethis.adoc | 76 ++-
.../src/near-real-time-searching.adoc | 44 +-
solr/solr-ref-guide/src/other-parsers.adoc | 23 +-
.../src/parallel-sql-interface.adoc | 18 +-
.../solr-ref-guide/src/parameter-reference.adoc | 45 +-
.../src/pdf/SolrRefGuide-all.adoc | 6 +-
.../src/pdf/themes/refguide-theme.yml | 17 +-
.../src/performance-statistics-reference.adoc | 2 +-
solr/solr-ref-guide/src/query-screen.adoc | 68 ++-
.../src/query-settings-in-solrconfig.adoc | 22 +-
.../read-and-write-side-fault-tolerance.adoc | 4 +-
solr/solr-ref-guide/src/replication-screen.adoc | 4 +-
.../src/request-parameters-api.adoc | 2 +-
.../src/requestdispatcher-in-solrconfig.adoc | 35 +-
...lers-and-searchcomponents-in-solrconfig.adoc | 14 +-
solr/solr-ref-guide/src/response-writers.adoc | 101 ++--
solr/solr-ref-guide/src/result-clustering.adoc | 82 ++-
solr/solr-ref-guide/src/result-grouping.adoc | 77 ++-
.../src/rule-based-authorization-plugin.adoc | 42 +-
.../src/running-solr-on-hdfs.adoc | 95 ++-
solr/solr-ref-guide/src/schema-api.adoc | 2 +-
...schema-factory-definition-in-solrconfig.adoc | 6 +-
solr/solr-ref-guide/src/schemaless-mode.adoc | 8 +-
...tting-up-an-external-zookeeper-ensemble.adoc | 8 +-
.../shards-and-indexing-data-in-solrcloud.adoc | 2 +-
solr/solr-ref-guide/src/sitemap.xml | 2 +-
.../src/solr-control-script-reference.adoc | 10 +-
.../src/solr-cores-and-solr-xml.adoc | 2 +-
solr/solr-ref-guide/src/spatial-search.adoc | 150 +++--
solr/solr-ref-guide/src/spell-checking.adoc | 40 +-
solr/solr-ref-guide/src/stream-decorators.adoc | 392 ++++++++++++-
solr/solr-ref-guide/src/stream-evaluators.adoc | 137 +++--
solr/solr-ref-guide/src/stream-sources.adoc | 39 +-
.../src/taking-solr-to-production.adoc | 20 +-
.../src/the-dismax-query-parser.adoc | 22 +-
.../src/the-extended-dismax-query-parser.adoc | 29 +-
.../src/the-query-elevation-component.adoc | 31 +-
.../src/the-standard-query-parser.adoc | 14 +-
.../solr-ref-guide/src/the-stats-component.adoc | 75 ++-
.../src/the-term-vector-component.adoc | 55 +-
.../solr-ref-guide/src/the-terms-component.adoc | 115 ++--
.../src/transforming-result-documents.adoc | 31 +-
...anding-analyzers-tokenizers-and-filters.adoc | 8 +-
.../src/update-request-processors.adoc | 24 +-
.../src/updatehandlers-in-solrconfig.adoc | 62 +-
.../src/updating-parts-of-documents.adoc | 54 +-
solr/solr-ref-guide/src/upgrading-solr.adoc | 2 +-
.../src/uploading-data-with-index-handlers.adoc | 130 +++--
...g-data-with-solr-cell-using-apache-tika.adoc | 125 ++--
...store-data-with-the-data-import-handler.adoc | 2 +-
solr/solr-ref-guide/src/using-solrj.adoc | 10 +-
...zookeeper-to-manage-configuration-files.adoc | 2 +-
solr/solr-ref-guide/src/v2-api.adoc | 24 +-
.../src/velocity-response-writer.adoc | 99 ++--
solr/solr-ref-guide/src/working-with-dates.adoc | 11 +-
.../src/working-with-enum-fields.adoc | 6 +-
...rking-with-external-files-and-processes.adoc | 30 +-
.../src/zookeeper-access-control.adoc | 21 +-
.../apache/solr/client/solrj/SolrRequest.java | 18 +
.../solr/client/solrj/V2RequestSupport.java | 30 +
.../solr/client/solrj/impl/CloudSolrClient.java | 15 +-
.../solrj/impl/ConcurrentUpdateSolrClient.java | 18 +-
.../solr/client/solrj/impl/HttpSolrClient.java | 99 +++-
.../client/solrj/impl/LBHttpSolrClient.java | 38 +-
.../impl/StreamingBinaryResponseParser.java | 5 +-
.../client/solrj/io/eval/AnovaEvaluator.java | 9 +-
.../client/solrj/io/eval/ArrayEvaluator.java | 53 +-
.../solrj/io/eval/ArraySortEvaluator.java | 77 ---
.../client/solrj/io/eval/ComplexEvaluator.java | 18 +-
.../solrj/io/eval/ConvolutionEvaluator.java | 10 +-
.../solrj/io/eval/CorrelationEvaluator.java | 9 +-
.../solrj/io/eval/CovarianceEvaluator.java | 9 +-
.../io/eval/CumulativeProbabilityEvaluator.java | 9 +-
.../client/solrj/io/eval/DescribeEvaluator.java | 10 +-
.../client/solrj/io/eval/DistanceEvaluator.java | 10 +-
.../io/eval/EmpiricalDistributionEvaluator.java | 9 +-
.../solrj/io/eval/FindDelayEvaluator.java | 9 +-
.../solrj/io/eval/HistogramEvaluator.java | 9 +-
.../client/solrj/io/eval/LengthEvaluator.java | 23 +-
.../solrj/io/eval/MovingAverageEvaluator.java | 9 +-
.../solrj/io/eval/PercentileEvaluator.java | 9 +-
.../client/solrj/io/eval/PredictEvaluator.java | 10 +-
.../client/solrj/io/eval/RankEvaluator.java | 10 +-
.../solrj/io/eval/RegressionEvaluator.java | 10 +-
.../client/solrj/io/eval/ReverseEvaluator.java | 10 +-
.../client/solrj/io/eval/ScaleEvaluator.java | 10 +-
.../client/solrj/io/eval/SequenceEvaluator.java | 10 +-
.../solrj/io/stream/CartesianProductStream.java | 12 +-
.../client/solrj/io/stream/FacetStream.java | 3 +
.../solr/client/solrj/io/stream/TupStream.java | 3 +-
.../solrj/request/CollectionAdminRequest.java | 10 +-
.../solrj/request/CollectionApiMapping.java | 14 +
.../request/JavaBinUpdateRequestCodec.java | 12 +-
.../client/solrj/request/V1toV2ApiMapper.java | 144 +++++
.../solr/client/solrj/request/V2Request.java | 55 +-
.../solr/client/solrj/response/V2Response.java | 22 +
.../org/apache/solr/common/SpecProvider.java | 25 +
.../apache/solr/common/params/CommonParams.java | 7 +-
.../solr/common/params/MoreLikeThisParams.java | 1 +
.../solr/common/util/CommandOperation.java | 48 +-
.../solr/common/util/ContentStreamBase.java | 7 +-
.../apache/solr/common/util/JavaBinCodec.java | 29 +-
.../solr/common/util/JsonSchemaValidator.java | 298 ++++++++++
.../org/apache/solr/common/util/PathTrie.java | 195 +++++++
.../org/apache/solr/common/util/Template.java | 66 +++
.../java/org/apache/solr/common/util/Utils.java | 17 +
.../resources/apispec/autoscaling.Commands.json | 194 +++++++
.../src/resources/apispec/cluster.Commands.json | 74 +++
.../src/resources/apispec/cluster.aliases.json | 12 +
.../apispec/cluster.commandstatus.delete.json | 10 +
.../apispec/cluster.commandstatus.json | 20 +
.../apispec/cluster.configs.Commands.json | 34 ++
.../apispec/cluster.configs.delete.json | 12 +
.../src/resources/apispec/cluster.configs.json | 12 +
solr/solrj/src/resources/apispec/cluster.json | 14 +
.../src/resources/apispec/cluster.nodes.json | 12 +
.../cluster.security.BasicAuth.Commands.json | 23 +
...cluster.security.RuleBasedAuthorization.json | 129 +++++
...luster.security.authentication.Commands.json | 12 +
.../cluster.security.authentication.json | 12 +
...cluster.security.authorization.Commands.json | 13 +
.../apispec/cluster.security.authorization.json | 13 +
.../resources/apispec/collections.Commands.json | 218 +++++++
.../collections.collection.Commands.json | 137 +++++
.../collections.collection.Commands.modify.json | 36 ++
.../collections.collection.Commands.reload.json | 11 +
.../apispec/collections.collection.delete.json | 13 +
.../apispec/collections.collection.json | 19 +
.../collections.collection.shards.Commands.json | 114 ++++
...ctions.collection.shards.shard.Commands.json | 24 +
...lections.collection.shards.shard.delete.json | 27 +
....collection.shards.shard.replica.delete.json | 39 ++
.../src/resources/apispec/collections.json | 13 +
.../src/resources/apispec/core.RealtimeGet.json | 26 +
.../apispec/core.SchemaEdit.addCopyField.json | 27 +
.../apispec/core.SchemaEdit.addField.json | 98 ++++
.../core.SchemaEdit.addFieldType.analyzers.json | 51 ++
.../apispec/core.SchemaEdit.addFieldType.json | 53 ++
.../core.SchemaEdit.deleteCopyField.json | 19 +
.../core.SchemaEdit.deleteDynamicField.json | 12 +
.../apispec/core.SchemaEdit.deleteField.json | 12 +
.../core.SchemaEdit.deleteFieldType.json | 14 +
.../src/resources/apispec/core.SchemaEdit.json | 47 ++
.../apispec/core.SchemaRead.copyFields.json | 26 +
...ore.SchemaRead.dynamicFields_fieldTypes.json | 20 +
.../apispec/core.SchemaRead.fields.json | 34 ++
.../src/resources/apispec/core.SchemaRead.json | 17 +
.../src/resources/apispec/core.Update.json | 17 +
...g.Commands.addRequestHandler.properties.json | 25 +
.../apispec/core.config.Commands.generic.json | 19 +
.../resources/apispec/core.config.Commands.json | 215 +++++++
.../core.config.Commands.runtimeLib.json | 23 +
.../apispec/core.config.Params.Commands.json | 31 +
.../resources/apispec/core.config.Params.json | 13 +
.../src/resources/apispec/core.config.json | 18 +
.../src/resources/apispec/core.system.blob.json | 20 +
.../apispec/core.system.blob.upload.json | 12 +
.../src/resources/apispec/cores.Commands.json | 85 +++
.../src/resources/apispec/cores.Status.json | 20 +
.../resources/apispec/cores.core.Commands.json | 136 +++++
.../apispec/cores.core.Commands.split.json | 34 ++
solr/solrj/src/resources/apispec/emptySpec.json | 11 +
.../src/resources/apispec/node.Commands.json | 24 +
solr/solrj/src/resources/apispec/node.Info.json | 11 +
.../src/resources/apispec/node.invoke.json | 16 +
.../collection1/conf/schema-replication1.xml | 2 +-
.../solrj/solr/collection1/conf/schema-sql.xml | 2 +-
.../solrj/solr/collection1/conf/schema.xml | 2 +-
.../solr/collection1/conf/solrconfig-slave1.xml | 3 +-
.../solr/collection1/conf/solrconfig-sql.xml | 2 +-
.../solrj/solr/collection1/conf/solrconfig.xml | 2 +-
.../solr/configsets/ml/conf/solrconfig.xml | 2 +-
.../solr/configsets/shared/conf/solrconfig.xml | 2 +-
.../configsets/streaming/conf/solrconfig.xml | 2 +-
.../solrj/solr/crazy-path-to-schema.xml | 4 +-
.../solr/multicore/core0/conf/solrconfig.xml | 2 +-
.../solr/multicore/core1/conf/solrconfig.xml | 2 +-
.../solrj/io/stream/StreamExpressionTest.java | 17 +
.../io/stream/eval/ArrayEvaluatorTest.java | 155 +++++
.../io/stream/eval/LengthEvaluatorTest.java | 119 ++++
.../solrj/request/TestV1toV2ApiMapper.java | 55 ++
.../solr/common/util/JsonValidatorTest.java | 192 ++++++
.../solr/common/util/TestJavaBinCodec.java | 95 +--
.../solr/common/util/TestNamedListCodec.java | 57 +-
.../apache/solr/common/util/TestPathTrie.java | 61 ++
.../cloud/AbstractFullDistribZkTestBase.java | 10 +-
.../solr/cloud/StoppableCommitThread.java | 2 +-
solr/webapp/web/js/angular/controllers/query.js | 2 +-
721 files changed, 13654 insertions(+), 8540 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/fb7803d9/solr/CHANGES.txt
----------------------------------------------------------------------
diff --cc solr/CHANGES.txt
index ed2feac,f15fa45..0d589bb
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@@ -166,13 -176,13 +186,20 @@@ Bug Fixe
* SOLR-10223: Allow running examples as root on Linux with -force option (janhoy)
+ * SOLR-10830: Solr now correctly enforces that the '_root_' field has the same fieldType as the
+ uniqueKey field. With out this enforcement, child document updating was unreliable. (hossman)
+
+ * SOLR-10876: Regression in loading runtime UpdateRequestProcessors like TemplateUpdateProcessorFactory (noble)
+
+ * SOLR-10886: Using V2Request.process(solrClient) method throws NPE if the API returns an error (Cao Manh Dat)
+
+* SOLR-10602: Triggers should be able to restore state from old instances when taking over. (shalin)
+
+* SOLR-10714: OverseerTriggerThread does not start triggers on overseer start until autoscaling
+ config watcher is fired. (shalin)
+
+* SOLR-10738: TriggerAction is initialised even if the trigger is never scheduled. (shalin)
+
Optimizations
----------------------
@@@ -300,6 -318,9 +337,9 @@@ Upgrade Note
New Features
----------------------
-* SOLR-10849: MoreLikeThisComponent should expose setMaxDocFreqPct (maxDoc
++* SOLR-10849: MoreLikeThisComponent should expose setMaxDocFreqPct (maxDoc
+ frequency percentage). (Dawid Weiss)
+
* SOLR-10307: Allow Passing SSL passwords through environment variables. (Mano Kovacs via Mark Miller)
* SOLR-10721: Provide a way to know when Core Discovery is finished and when all async cores are done loading
@@@ -399,6 -444,25 +463,25 @@@ Other Change
* SOLR-8762: return child docs in DIH debug (Gopikannan Venugopalsamy via Mikhail Khludnev)
+ * SOLR-10501: Test sortMissing{First,Last} with points fields. (Steve Rowe)
+
+ * SOLR-10761: Switch trie numeric/date fields to points in data-driven-enabled example and test schemas.
+ (Steve Rowe)
+
-* SOLR-10851: SolrClients should clarify expectations for solrServerUrl parameter (Jason Gerlowski
++* SOLR-10851: SolrClients should clarify expectations for solrServerUrl parameter (Jason Gerlowski
+ via Tomás Fernández Löbbe)
-
++
+ * SOLR-10891: BBoxField should support point-based number sub-fields. (Steve Rowe)
+
+ * SOLR-10834: Fixed tests and test configs to stop using numeric uniqueKey fields (hossman)
+
+ ================== 6.6.1 ==================
+
+ Bug Fixes
+ ----------------------
+
+ * SOLR-10857: standalone Solr loads UNLOADed core on request (Erick Erickson, Mikhail Khludnev)
+
================== 6.6.0 ==================
Consult the LUCENE_CHANGES.txt file for additional, low level, changes in this release.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/fb7803d9/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGangliaReporter.java
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/fb7803d9/solr/core/src/test/org/apache/solr/cloud/autoscaling/AutoScalingHandlerTest.java
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/fb7803d9/solr/core/src/test/org/apache/solr/schema/DocValuesTest.java
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/fb7803d9/solr/solrj/src/resources/apispec/autoscaling.Commands.json
----------------------------------------------------------------------
diff --cc solr/solrj/src/resources/apispec/autoscaling.Commands.json
index 0000000,5ff89ef..6c4b39b
mode 000000,100644..100644
--- a/solr/solrj/src/resources/apispec/autoscaling.Commands.json
+++ b/solr/solrj/src/resources/apispec/autoscaling.Commands.json
@@@ -1,0 -1,47 +1,194 @@@
+ {
+ "documentation": "TODO NOCOMMIT",
+ "description": "The Scaling API provides API for adding cluster level scaling rules, triggers and event listeners",
+ "methods": [
+ "GET",
+ "POST"
+ ],
+ "url": {
+ "paths": [
+ "/cluster/autoscaling",
+ "/cluster/autoscaling/diagnostics"
+ ]
+ },
+ "commands": {
++ "set-trigger": {
++ "type":"object",
++ "description": "The set-trigger command allows you to add and update triggers on various system metrics",
++ "properties": {
++ "name": {
++ "type": "string",
++ "description": "The name of the trigger"
++ },
++ "event": {
++ "type": "string",
++ "description": "The event type on which to set a trigger"
++ },
++ "waitFor": {
++ "type": "string",
++ "description": "The amount of time to wait after the trigger condition is satisfied before trigger is activated"
++ },
++ "lowerBound": {
++ "type": "number",
++ "description": "The lower bound of the condition below which the trigger is activated"
++ },
++ "upperBound": {
++ "type": "number",
++ "description": "The upper bound of the condition below which the trigger is activated"
++ },
++ "enabled": {
++ "type": "boolean",
++ "description": "The state of the trigger"
++ },
++ "actions": {
++ "type": "array",
++ "description": "The actions to be performed in sequence when the trigger is activated",
++ "items": {
++ "type": "object"
++ }
++ }
++ },
++ "required": [
++ "name",
++ "event"
++ ]
++ }
++ },
++ "remove-trigger": {
++ "description": "Remove a trigger",
++ "type": "object",
++ "properties": {
++ "name": {
++ "type": "string",
++ "description": "The name of the trigger to be removed"
++ },
++ "removeListeners": {
++ "type": "boolean",
++ "description": "If true, all listeners of this triggers are deleted together with the trigger"
++ }
++ },
++ "required": [
++ "name"
++ ]
++ },
++ "set-listener": {
++ "description": "The set-listener command lets you add a listener to a trigger",
++ "type": "object",
++ "properties": {
++ "name": {
++ "type": "string",
++ "description": "The name of the listener"
++ },
++ "trigger": {
++ "type": "string",
++ "description": "The name of the trigger to listen to"
++ },
++ "stage": {
++ "type": "array",
++ "description": "The stage of the trigger for which to listen",
++ "items": {
++ "type" : "string"
++ }
++ },
++ "beforeAction": {
++ "type": "array",
++ "description": "The name of the action before which the listener should be notified",
++ "items": {
++ "type" : "string"
++ }
++ },
++ "afterAction": {
++ "type": "array",
++ "description": "The name of the action after which the listener should be notified",
++ "items": {
++ "type" : "string"
++ }
++ },
++ "class": {
++ "type": "string",
++ "description": "The listener class to be notified once the given stage of the given trigger is activated"
++ }
++ },
++ "required": [
++ "name",
++ "trigger",
++ "class"
++ ],
++ "additionalProperties": true
++ },
++ "remove-listener": {
++ "description": "Remove a listener",
++ "type": "object",
++ "properties": {
++ "name": {
++ "type": "string",
++ "description": "The name of the listener to be removed"
++ }
++ },
++ "required": [
++ "name"
++ ]
++ },
++ "suspend-trigger": {
++ "description": "Pauses a trigger until an explicit resume is invoked or if the optional timeout expires",
++ "type": "object",
++ "properties": {
++ "name": {
++ "type": "string",
++ "description": "The name of the trigger to be suspended or '#EACH' to suspend all triggers"
++ },
++ "timeout": {
++ "type": "string",
++ "description": "Optional timeout after which all triggers are resumed automatically"
++ }
++ },
++ "required": [
++ "name"
++ ]
++ },
++ "resume-trigger": {
++ "description": "Resumes a suspended trigger",
++ "type": "object",
++ "properties": {
++ "name": {
++ "type": "string",
++ "description": "The name of the trigger to be resumed or '#EACH' to resume all triggers"
++ }
++ },
++ "required": [
++ "name"
++ ]
++ },
+ "set-policy" : {
+ "type":"object",
+ "description": "The set-policy command allows you to add and update policies that apply to collections",
+ /* "patternProperties": {
+ "^.+$": {
+ "type": "array"
+ }
+ },*/
+ "additionalProperties": true
+ },
+ "set-cluster-policy" : {
+ "type" : "array",
+ "description" : "The set-cluster-policy command allows you to add and update cluster-level policy that acts as the base for all collection level policies, if any"
+ },
+ "set-cluster-preferences" : {
+ "type" : "array",
+ "description" : "The set-cluster-preferences command allows you to add and update cluster-level preferences that are used to sort nodes for selection in cluster operations"
+ },
+ "remove-policy": {
+ "description": "Remove a policy",
+ "type": "object",
+ "properties": {
+ "name": {
+ "type": "string",
+ "description": "The name of the policy to be removed"
+ }
+ },
+ "required": [
+ "name"
+ ]
+ }
+ }
+ }
[41/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ar.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ar.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ar.txt
new file mode 100644
index 0000000..046829d
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ar.txt
@@ -0,0 +1,125 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Cleaned on October 11, 2009 (not normalized, so use before normalization)
+# This means that when modifying this list, you might need to add some
+# redundant entries, for example containing forms with both أ and ا
+من
+ومن
+منها
+منه
+في
+وفي
+فيها
+فيه
+و
+ف
+ثم
+او
+أو
+ب
+بها
+به
+ا
+أ
+اى
+اي
+أي
+أى
+لا
+ولا
+الا
+ألا
+إلا
+لكن
+ما
+وما
+كما
+فما
+عن
+مع
+اذا
+إذا
+ان
+أن
+إن
+انها
+أنها
+إنها
+انه
+أنه
+إنه
+بان
+بأن
+فان
+فأن
+وان
+وأن
+وإن
+التى
+التي
+الذى
+الذي
+الذين
+الى
+الي
+إلى
+إلي
+على
+عليها
+عليه
+اما
+أما
+إما
+ايضا
+أيضا
+كل
+وكل
+لم
+ولم
+لن
+ولن
+هى
+هي
+هو
+وهى
+وهي
+وهو
+فهى
+فهي
+فهو
+انت
+أنت
+لك
+لها
+له
+هذه
+هذا
+تلك
+ذلك
+هناك
+كانت
+كان
+يكون
+تكون
+وكانت
+وكان
+غير
+بعض
+قد
+نحو
+بين
+بينما
+منذ
+ضمن
+حيث
+الان
+الآن
+خلال
+بعد
+قبل
+حتى
+عند
+عندما
+لدى
+جميع
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_bg.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_bg.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_bg.txt
new file mode 100644
index 0000000..1ae4ba2
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_bg.txt
@@ -0,0 +1,193 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+а
+аз
+ако
+ала
+бе
+без
+беше
+би
+бил
+била
+били
+било
+близо
+бъдат
+бъде
+бяха
+в
+вас
+ваш
+ваша
+вероятно
+вече
+взема
+ви
+вие
+винаги
+все
+всеки
+всички
+всичко
+всяка
+във
+въпреки
+върху
+г
+ги
+главно
+го
+д
+да
+дали
+до
+докато
+докога
+дори
+досега
+доста
+е
+едва
+един
+ето
+за
+зад
+заедно
+заради
+засега
+затова
+защо
+защото
+и
+из
+или
+им
+има
+имат
+иска
+й
+каза
+как
+каква
+какво
+както
+какъв
+като
+кога
+когато
+което
+които
+кой
+който
+колко
+която
+къде
+където
+към
+ли
+м
+ме
+между
+мен
+ми
+мнозина
+мога
+могат
+може
+моля
+момента
+му
+н
+на
+над
+назад
+най
+направи
+напред
+например
+нас
+не
+него
+нея
+ни
+ние
+никой
+нито
+но
+някои
+някой
+няма
+обаче
+около
+освен
+особено
+от
+отгоре
+отново
+още
+пак
+по
+повече
+повечето
+под
+поне
+поради
+после
+почти
+прави
+пред
+преди
+през
+при
+пък
+първо
+с
+са
+само
+се
+сега
+си
+скоро
+след
+сме
+според
+сред
+срещу
+сте
+съм
+със
+също
+т
+тази
+така
+такива
+такъв
+там
+твой
+те
+тези
+ти
+тн
+то
+това
+тогава
+този
+той
+толкова
+точно
+трябва
+тук
+тъй
+тя
+тях
+у
+харесва
+ч
+че
+често
+чрез
+ще
+щом
+я
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ca.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ca.txt
new file mode 100644
index 0000000..3da65de
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ca.txt
@@ -0,0 +1,220 @@
+# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
+a
+abans
+ací
+ah
+així
+això
+al
+als
+aleshores
+algun
+alguna
+algunes
+alguns
+alhora
+allà
+allí
+allò
+altra
+altre
+altres
+amb
+ambdós
+ambdues
+apa
+aquell
+aquella
+aquelles
+aquells
+aquest
+aquesta
+aquestes
+aquests
+aquí
+baix
+cada
+cadascú
+cadascuna
+cadascunes
+cadascuns
+com
+contra
+d'un
+d'una
+d'unes
+d'uns
+dalt
+de
+del
+dels
+des
+després
+dins
+dintre
+donat
+doncs
+durant
+e
+eh
+el
+els
+em
+en
+encara
+ens
+entre
+érem
+eren
+éreu
+es
+és
+esta
+està
+estàvem
+estaven
+estàveu
+esteu
+et
+etc
+ets
+fins
+fora
+gairebé
+ha
+han
+has
+havia
+he
+hem
+heu
+hi
+ho
+i
+igual
+iguals
+ja
+l'hi
+la
+les
+li
+li'n
+llavors
+m'he
+ma
+mal
+malgrat
+mateix
+mateixa
+mateixes
+mateixos
+me
+mentre
+més
+meu
+meus
+meva
+meves
+molt
+molta
+moltes
+molts
+mon
+mons
+n'he
+n'hi
+ne
+ni
+no
+nogensmenys
+només
+nosaltres
+nostra
+nostre
+nostres
+o
+oh
+oi
+on
+pas
+pel
+pels
+per
+però
+perquè
+poc
+poca
+pocs
+poques
+potser
+propi
+qual
+quals
+quan
+quant
+que
+què
+quelcom
+qui
+quin
+quina
+quines
+quins
+s'ha
+s'han
+sa
+semblant
+semblants
+ses
+seu
+seus
+seva
+seva
+seves
+si
+sobre
+sobretot
+sóc
+solament
+sols
+son
+són
+sons
+sota
+sou
+t'ha
+t'han
+t'he
+ta
+tal
+també
+tampoc
+tan
+tant
+tanta
+tantes
+teu
+teus
+teva
+teves
+ton
+tons
+tot
+tota
+totes
+tots
+un
+una
+unes
+uns
+us
+va
+vaig
+vam
+van
+vas
+veu
+vosaltres
+vostra
+vostre
+vostres
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_cz.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_cz.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_cz.txt
new file mode 100644
index 0000000..53c6097
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_cz.txt
@@ -0,0 +1,172 @@
+a
+s
+k
+o
+i
+u
+v
+z
+dnes
+cz
+tímto
+budeš
+budem
+byli
+jseš
+můj
+svým
+ta
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proč
+máte
+tato
+kam
+tohoto
+kdo
+kteří
+mi
+nám
+tom
+tomuto
+mít
+nic
+proto
+kterou
+byla
+toho
+protože
+asi
+ho
+naši
+napište
+re
+což
+tím
+takže
+svých
+její
+svými
+jste
+aj
+tu
+tedy
+teto
+bylo
+kde
+ke
+pravé
+ji
+nad
+nejsou
+či
+pod
+téma
+mezi
+přes
+ty
+pak
+vám
+ani
+když
+však
+neg
+jsem
+tento
+článku
+články
+aby
+jsme
+před
+pta
+jejich
+byl
+ještě
+až
+bez
+také
+pouze
+první
+vaše
+která
+nás
+nový
+tipy
+pokud
+může
+strana
+jeho
+své
+jiné
+zprávy
+nové
+není
+vás
+jen
+podle
+zde
+už
+být
+více
+bude
+již
+než
+který
+by
+které
+co
+nebo
+ten
+tak
+má
+při
+od
+po
+jsou
+jak
+další
+ale
+si
+se
+ve
+to
+jako
+za
+zpět
+ze
+do
+pro
+je
+na
+atd
+atp
+jakmile
+přičemž
+já
+on
+ona
+ono
+oni
+ony
+my
+vy
+jí
+ji
+mě
+mne
+jemu
+tomu
+těm
+těmu
+němu
+němuž
+jehož
+jíž
+jelikož
+jež
+jakož
+načež
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_da.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_da.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_da.txt
new file mode 100644
index 0000000..42e6145
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_da.txt
@@ -0,0 +1,110 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Danish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+
+og | and
+i | in
+jeg | I
+det | that (dem. pronoun)/it (pers. pronoun)
+at | that (in front of a sentence)/to (with infinitive)
+en | a/an
+den | it (pers. pronoun)/that (dem. pronoun)
+til | to/at/for/until/against/by/of/into, more
+er | present tense of "to be"
+som | who, as
+på | on/upon/in/on/at/to/after/of/with/for, on
+de | they
+med | with/by/in, along
+han | he
+af | of/by/from/off/for/in/with/on, off
+for | at/for/to/from/by/of/ago, in front/before, because
+ikke | not
+der | who/which, there/those
+var | past tense of "to be"
+mig | me/myself
+sig | oneself/himself/herself/itself/themselves
+men | but
+et | a/an/one, one (number), someone/somebody/one
+har | present tense of "to have"
+om | round/about/for/in/a, about/around/down, if
+vi | we
+min | my
+havde | past tense of "to have"
+ham | him
+hun | she
+nu | now
+over | over/above/across/by/beyond/past/on/about, over/past
+da | then, when/as/since
+fra | from/off/since, off, since
+du | you
+ud | out
+sin | his/her/its/one's
+dem | them
+os | us/ourselves
+op | up
+man | you/one
+hans | his
+hvor | where
+eller | or
+hvad | what
+skal | must/shall etc.
+selv | myself/youself/herself/ourselves etc., even
+her | here
+alle | all/everyone/everybody etc.
+vil | will (verb)
+blev | past tense of "to stay/to remain/to get/to become"
+kunne | could
+ind | in
+når | when
+være | present tense of "to be"
+dog | however/yet/after all
+noget | something
+ville | would
+jo | you know/you see (adv), yes
+deres | their/theirs
+efter | after/behind/according to/for/by/from, later/afterwards
+ned | down
+skulle | should
+denne | this
+end | than
+dette | this
+mit | my/mine
+også | also
+under | under/beneath/below/during, below/underneath
+have | have
+dig | you
+anden | other
+hende | her
+mine | my
+alt | everything
+meget | much/very, plenty of
+sit | his, her, its, one's
+sine | his, her, its, one's
+vor | our
+mod | against
+disse | these
+hvis | if
+din | your/yours
+nogle | some
+hos | by/at
+blive | be/become
+mange | many
+ad | by/through
+bliver | present tense of "to be/to become"
+hendes | her/hers
+været | be
+thi | for (conj)
+jer | you
+sådan | such, like this/like that
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_de.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_de.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_de.txt
new file mode 100644
index 0000000..86525e7
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_de.txt
@@ -0,0 +1,294 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A German stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | The number of forms in this list is reduced significantly by passing it
+ | through the German stemmer.
+
+
+aber | but
+
+alle | all
+allem
+allen
+aller
+alles
+
+als | than, as
+also | so
+am | an + dem
+an | at
+
+ander | other
+andere
+anderem
+anderen
+anderer
+anderes
+anderm
+andern
+anderr
+anders
+
+auch | also
+auf | on
+aus | out of
+bei | by
+bin | am
+bis | until
+bist | art
+da | there
+damit | with it
+dann | then
+
+der | the
+den
+des
+dem
+die
+das
+
+daß | that
+
+derselbe | the same
+derselben
+denselben
+desselben
+demselben
+dieselbe
+dieselben
+dasselbe
+
+dazu | to that
+
+dein | thy
+deine
+deinem
+deinen
+deiner
+deines
+
+denn | because
+
+derer | of those
+dessen | of him
+
+dich | thee
+dir | to thee
+du | thou
+
+dies | this
+diese
+diesem
+diesen
+dieser
+dieses
+
+
+doch | (several meanings)
+dort | (over) there
+
+
+durch | through
+
+ein | a
+eine
+einem
+einen
+einer
+eines
+
+einig | some
+einige
+einigem
+einigen
+einiger
+einiges
+
+einmal | once
+
+er | he
+ihn | him
+ihm | to him
+
+es | it
+etwas | something
+
+euer | your
+eure
+eurem
+euren
+eurer
+eures
+
+für | for
+gegen | towards
+gewesen | p.p. of sein
+hab | have
+habe | have
+haben | have
+hat | has
+hatte | had
+hatten | had
+hier | here
+hin | there
+hinter | behind
+
+ich | I
+mich | me
+mir | to me
+
+
+ihr | you, to her
+ihre
+ihrem
+ihren
+ihrer
+ihres
+euch | to you
+
+im | in + dem
+in | in
+indem | while
+ins | in + das
+ist | is
+
+jede | each, every
+jedem
+jeden
+jeder
+jedes
+
+jene | that
+jenem
+jenen
+jener
+jenes
+
+jetzt | now
+kann | can
+
+kein | no
+keine
+keinem
+keinen
+keiner
+keines
+
+können | can
+könnte | could
+machen | do
+man | one
+
+manche | some, many a
+manchem
+manchen
+mancher
+manches
+
+mein | my
+meine
+meinem
+meinen
+meiner
+meines
+
+mit | with
+muss | must
+musste | had to
+nach | to(wards)
+nicht | not
+nichts | nothing
+noch | still, yet
+nun | now
+nur | only
+ob | whether
+oder | or
+ohne | without
+sehr | very
+
+sein | his
+seine
+seinem
+seinen
+seiner
+seines
+
+selbst | self
+sich | herself
+
+sie | they, she
+ihnen | to them
+
+sind | are
+so | so
+
+solche | such
+solchem
+solchen
+solcher
+solches
+
+soll | shall
+sollte | should
+sondern | but
+sonst | else
+über | over
+um | about, around
+und | and
+
+uns | us
+unse
+unsem
+unsen
+unser
+unses
+
+unter | under
+viel | much
+vom | von + dem
+von | from
+vor | before
+während | while
+war | was
+waren | were
+warst | wast
+was | what
+weg | away, off
+weil | because
+weiter | further
+
+welche | which
+welchem
+welchen
+welcher
+welches
+
+wenn | when
+werde | will
+werden | will
+wie | how
+wieder | again
+will | want
+wir | we
+wird | will
+wirst | willst
+wo | where
+wollen | want
+wollte | wanted
+würde | would
+würden | would
+zu | to
+zum | zu + dem
+zur | zu + der
+zwar | indeed
+zwischen | between
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_el.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_el.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_el.txt
new file mode 100644
index 0000000..232681f
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_el.txt
@@ -0,0 +1,78 @@
+# Lucene Greek Stopwords list
+# Note: by default this file is used after GreekLowerCaseFilter,
+# so when modifying this file use 'σ' instead of 'ς'
+ο
+η
+το
+οι
+τα
+του
+τησ
+των
+τον
+την
+και
+κι
+κ
+ειμαι
+εισαι
+ειναι
+ειμαστε
+ειστε
+στο
+στον
+στη
+στην
+μα
+αλλα
+απο
+για
+προσ
+με
+σε
+ωσ
+παρα
+αντι
+κατα
+μετα
+θα
+να
+δε
+δεν
+μη
+μην
+επι
+ενω
+εαν
+αν
+τοτε
+που
+πωσ
+ποιοσ
+ποια
+ποιο
+ποιοι
+ποιεσ
+ποιων
+ποιουσ
+αυτοσ
+αυτη
+αυτο
+αυτοι
+αυτων
+αυτουσ
+αυτεσ
+αυτα
+εκεινοσ
+εκεινη
+εκεινο
+εκεινοι
+εκεινεσ
+εκεινα
+εκεινων
+εκεινουσ
+οπωσ
+ομωσ
+ισωσ
+οσο
+οτι
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_en.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_en.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_en.txt
new file mode 100644
index 0000000..2c164c0
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_en.txt
@@ -0,0 +1,54 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+# Standard english stop words taken from Lucene's StopAnalyzer
+a
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+of
+on
+or
+such
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_es.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_es.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_es.txt
new file mode 100644
index 0000000..487d78c
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_es.txt
@@ -0,0 +1,356 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Spanish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | from, of
+la | the, her
+que | who, that
+el | the
+en | in
+y | and
+a | to
+los | the, them
+del | de + el
+se | himself, from him etc
+las | the, them
+por | for, by, etc
+un | a
+para | for
+con | with
+no | no
+una | a
+su | his, her
+al | a + el
+ | es from SER
+lo | him
+como | how
+más | more
+pero | pero
+sus | su plural
+le | to him, her
+ya | already
+o | or
+ | fue from SER
+este | this
+ | ha from HABER
+sí | himself etc
+porque | because
+esta | this
+ | son from SER
+entre | between
+ | está from ESTAR
+cuando | when
+muy | very
+sin | without
+sobre | on
+ | ser from SER
+ | tiene from TENER
+también | also
+me | me
+hasta | until
+hay | there is/are
+donde | where
+ | han from HABER
+quien | whom, that
+ | están from ESTAR
+ | estado from ESTAR
+desde | from
+todo | all
+nos | us
+durante | during
+ | estados from ESTAR
+todos | all
+uno | a
+les | to them
+ni | nor
+contra | against
+otros | other
+ | fueron from SER
+ese | that
+eso | that
+ | había from HABER
+ante | before
+ellos | they
+e | and (variant of y)
+esto | this
+mí | me
+antes | before
+algunos | some
+qué | what?
+unos | a
+yo | I
+otro | other
+otras | other
+otra | other
+él | he
+tanto | so much, many
+esa | that
+estos | these
+mucho | much, many
+quienes | who
+nada | nothing
+muchos | many
+cual | who
+ | sea from SER
+poco | few
+ella | she
+estar | to be
+ | haber from HABER
+estas | these
+ | estaba from ESTAR
+ | estamos from ESTAR
+algunas | some
+algo | something
+nosotros | we
+
+ | other forms
+
+mi | me
+mis | mi plural
+tú | thou
+te | thee
+ti | thee
+tu | thy
+tus | tu plural
+ellas | they
+nosotras | we
+vosotros | you
+vosotras | you
+os | you
+mío | mine
+mía |
+míos |
+mías |
+tuyo | thine
+tuya |
+tuyos |
+tuyas |
+suyo | his, hers, theirs
+suya |
+suyos |
+suyas |
+nuestro | ours
+nuestra |
+nuestros |
+nuestras |
+vuestro | yours
+vuestra |
+vuestros |
+vuestras |
+esos | those
+esas | those
+
+ | forms of estar, to be (not including the infinitive):
+estoy
+estás
+está
+estamos
+estáis
+están
+esté
+estés
+estemos
+estéis
+estén
+estaré
+estarás
+estará
+estaremos
+estaréis
+estarán
+estaría
+estarías
+estaríamos
+estaríais
+estarían
+estaba
+estabas
+estábamos
+estabais
+estaban
+estuve
+estuviste
+estuvo
+estuvimos
+estuvisteis
+estuvieron
+estuviera
+estuvieras
+estuviéramos
+estuvierais
+estuvieran
+estuviese
+estuvieses
+estuviésemos
+estuvieseis
+estuviesen
+estando
+estado
+estada
+estados
+estadas
+estad
+
+ | forms of haber, to have (not including the infinitive):
+he
+has
+ha
+hemos
+habéis
+han
+haya
+hayas
+hayamos
+hayáis
+hayan
+habré
+habrás
+habrá
+habremos
+habréis
+habrán
+habría
+habrías
+habríamos
+habríais
+habrían
+había
+habías
+habíamos
+habíais
+habían
+hube
+hubiste
+hubo
+hubimos
+hubisteis
+hubieron
+hubiera
+hubieras
+hubiéramos
+hubierais
+hubieran
+hubiese
+hubieses
+hubiésemos
+hubieseis
+hubiesen
+habiendo
+habido
+habida
+habidos
+habidas
+
+ | forms of ser, to be (not including the infinitive):
+soy
+eres
+es
+somos
+sois
+son
+sea
+seas
+seamos
+seáis
+sean
+seré
+serás
+será
+seremos
+seréis
+serán
+sería
+serías
+seríamos
+seríais
+serían
+era
+eras
+éramos
+erais
+eran
+fui
+fuiste
+fue
+fuimos
+fuisteis
+fueron
+fuera
+fueras
+fuéramos
+fuerais
+fueran
+fuese
+fueses
+fuésemos
+fueseis
+fuesen
+siendo
+sido
+ | sed also means 'thirst'
+
+ | forms of tener, to have (not including the infinitive):
+tengo
+tienes
+tiene
+tenemos
+tenéis
+tienen
+tenga
+tengas
+tengamos
+tengáis
+tengan
+tendré
+tendrás
+tendrá
+tendremos
+tendréis
+tendrán
+tendría
+tendrías
+tendríamos
+tendríais
+tendrían
+tenía
+tenías
+teníamos
+teníais
+tenían
+tuve
+tuviste
+tuvo
+tuvimos
+tuvisteis
+tuvieron
+tuviera
+tuvieras
+tuviéramos
+tuvierais
+tuvieran
+tuviese
+tuvieses
+tuviésemos
+tuvieseis
+tuviesen
+teniendo
+tenido
+tenida
+tenidos
+tenidas
+tened
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_eu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_eu.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_eu.txt
new file mode 100644
index 0000000..25f1db9
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_eu.txt
@@ -0,0 +1,99 @@
+# example set of basque stopwords
+al
+anitz
+arabera
+asko
+baina
+bat
+batean
+batek
+bati
+batzuei
+batzuek
+batzuetan
+batzuk
+bera
+beraiek
+berau
+berauek
+bere
+berori
+beroriek
+beste
+bezala
+da
+dago
+dira
+ditu
+du
+dute
+edo
+egin
+ere
+eta
+eurak
+ez
+gainera
+gu
+gutxi
+guzti
+haiei
+haiek
+haietan
+hainbeste
+hala
+han
+handik
+hango
+hara
+hari
+hark
+hartan
+hau
+hauei
+hauek
+hauetan
+hemen
+hemendik
+hemengo
+hi
+hona
+honek
+honela
+honetan
+honi
+hor
+hori
+horiei
+horiek
+horietan
+horko
+horra
+horrek
+horrela
+horretan
+horri
+hortik
+hura
+izan
+ni
+noiz
+nola
+non
+nondik
+nongo
+nor
+nora
+ze
+zein
+zen
+zenbait
+zenbat
+zer
+zergatik
+ziren
+zituen
+zu
+zuek
+zuen
+zuten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fa.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fa.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fa.txt
new file mode 100644
index 0000000..723641c
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fa.txt
@@ -0,0 +1,313 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Note: by default this file is used after normalization, so when adding entries
+# to this file, use the arabic 'ي' instead of 'ی'
+انان
+نداشته
+سراسر
+خياه
+ايشان
+وي
+تاكنون
+بيشتري
+دوم
+پس
+ناشي
+وگو
+يا
+داشتند
+سپس
+هنگام
+هرگز
+پنج
+نشان
+امسال
+ديگر
+گروهي
+شدند
+چطور
+ده
+و
+دو
+نخستين
+ولي
+چرا
+چه
+وسط
+ه
+كدام
+قابل
+يك
+رفت
+هفت
+همچنين
+در
+هزار
+بله
+بلي
+شايد
+اما
+شناسي
+گرفته
+دهد
+داشته
+دانست
+داشتن
+خواهيم
+ميليارد
+وقتيكه
+امد
+خواهد
+جز
+اورده
+شده
+بلكه
+خدمات
+شدن
+برخي
+نبود
+بسياري
+جلوگيري
+حق
+كردند
+نوعي
+بعري
+نكرده
+نظير
+نبايد
+بوده
+بودن
+داد
+اورد
+هست
+جايي
+شود
+دنبال
+داده
+بايد
+سابق
+هيچ
+همان
+انجا
+كمتر
+كجاست
+گردد
+كسي
+تر
+مردم
+تان
+دادن
+بودند
+سري
+جدا
+ندارند
+مگر
+يكديگر
+دارد
+دهند
+بنابراين
+هنگامي
+سمت
+جا
+انچه
+خود
+دادند
+زياد
+دارند
+اثر
+بدون
+بهترين
+بيشتر
+البته
+به
+براساس
+بيرون
+كرد
+بعضي
+گرفت
+توي
+اي
+ميليون
+او
+جريان
+تول
+بر
+مانند
+برابر
+باشيم
+مدتي
+گويند
+اكنون
+تا
+تنها
+جديد
+چند
+بي
+نشده
+كردن
+كردم
+گويد
+كرده
+كنيم
+نمي
+نزد
+روي
+قصد
+فقط
+بالاي
+ديگران
+اين
+ديروز
+توسط
+سوم
+ايم
+دانند
+سوي
+استفاده
+شما
+كنار
+داريم
+ساخته
+طور
+امده
+رفته
+نخست
+بيست
+نزديك
+طي
+كنيد
+از
+انها
+تمامي
+داشت
+يكي
+طريق
+اش
+چيست
+روب
+نمايد
+گفت
+چندين
+چيزي
+تواند
+ام
+ايا
+با
+ان
+ايد
+ترين
+اينكه
+ديگري
+راه
+هايي
+بروز
+همچنان
+پاعين
+كس
+حدود
+مختلف
+مقابل
+چيز
+گيرد
+ندارد
+ضد
+همچون
+سازي
+شان
+مورد
+باره
+مرسي
+خويش
+برخوردار
+چون
+خارج
+شش
+هنوز
+تحت
+ضمن
+هستيم
+گفته
+فكر
+بسيار
+پيش
+براي
+روزهاي
+انكه
+نخواهد
+بالا
+كل
+وقتي
+كي
+چنين
+كه
+گيري
+نيست
+است
+كجا
+كند
+نيز
+يابد
+بندي
+حتي
+توانند
+عقب
+خواست
+كنند
+بين
+تمام
+همه
+ما
+باشند
+مثل
+شد
+اري
+باشد
+اره
+طبق
+بعد
+اگر
+صورت
+غير
+جاي
+بيش
+ريزي
+اند
+زيرا
+چگونه
+بار
+لطفا
+مي
+درباره
+من
+ديده
+همين
+گذاري
+برداري
+علت
+گذاشته
+هم
+فوق
+نه
+ها
+شوند
+اباد
+همواره
+هر
+اول
+خواهند
+چهار
+نام
+امروز
+مان
+هاي
+قبل
+كنم
+سعي
+تازه
+را
+هستند
+زير
+جلوي
+عنوان
+بود
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fi.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fi.txt
new file mode 100644
index 0000000..4372c9a
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fi.txt
@@ -0,0 +1,97 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+| forms of BE
+
+olla
+olen
+olet
+on
+olemme
+olette
+ovat
+ole | negative form
+
+oli
+olisi
+olisit
+olisin
+olisimme
+olisitte
+olisivat
+olit
+olin
+olimme
+olitte
+olivat
+ollut
+olleet
+
+en | negation
+et
+ei
+emme
+ette
+eivät
+
+|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
+minä minun minut minua minussa minusta minuun minulla minulta minulle | I
+sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
+hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she
+me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we
+te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you
+he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they
+
+tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this
+tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
+se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it
+nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these
+nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
+ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they
+
+kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
+ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl)
+mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what
+mitkä | (pl)
+
+joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which
+jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl)
+
+| conjunctions
+
+että | that
+ja | and
+jos | if
+koska | because
+kuin | than
+mutta | but
+niin | so
+sekä | and
+sillä | for
+tai | or
+vaan | but
+vai | or
+vaikka | although
+
+
+| prepositions
+
+kanssa | with
+mukaan | according to
+noin | about
+poikki | across
+yli | over, across
+
+| other
+
+kun | when
+niin | so
+nyt | now
+itse | self
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fr.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fr.txt
new file mode 100644
index 0000000..749abae
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_fr.txt
@@ -0,0 +1,186 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A French stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+au | a + le
+aux | a + les
+avec | with
+ce | this
+ces | these
+dans | with
+de | of
+des | de + les
+du | de + le
+elle | she
+en | `of them' etc
+et | and
+eux | them
+il | he
+je | I
+la | the
+le | the
+leur | their
+lui | him
+ma | my (fem)
+mais | but
+me | me
+même | same; as in moi-même (myself) etc
+mes | me (pl)
+moi | me
+mon | my (masc)
+ne | not
+nos | our (pl)
+notre | our
+nous | we
+on | one
+ou | where
+par | by
+pas | not
+pour | for
+qu | que before vowel
+que | that
+qui | who
+sa | his, her (fem)
+se | oneself
+ses | his (pl)
+son | his, her (masc)
+sur | on
+ta | thy (fem)
+te | thee
+tes | thy (pl)
+toi | thee
+ton | thy (masc)
+tu | thou
+un | a
+une | a
+vos | your (pl)
+votre | your
+vous | you
+
+ | single letter forms
+
+c | c'
+d | d'
+j | j'
+l | l'
+à | to, at
+m | m'
+n | n'
+s | s'
+t | t'
+y | there
+
+ | forms of être (not including the infinitive):
+été
+étée
+étées
+étés
+étant
+suis
+es
+est
+sommes
+êtes
+sont
+serai
+seras
+sera
+serons
+serez
+seront
+serais
+serait
+serions
+seriez
+seraient
+étais
+était
+étions
+étiez
+étaient
+fus
+fut
+fûmes
+fûtes
+furent
+sois
+soit
+soyons
+soyez
+soient
+fusse
+fusses
+fût
+fussions
+fussiez
+fussent
+
+ | forms of avoir (not including the infinitive):
+ayant
+eu
+eue
+eues
+eus
+ai
+as
+avons
+avez
+ont
+aurai
+auras
+aura
+aurons
+aurez
+auront
+aurais
+aurait
+aurions
+auriez
+auraient
+avais
+avait
+avions
+aviez
+avaient
+eut
+eûmes
+eûtes
+eurent
+aie
+aies
+ait
+ayons
+ayez
+aient
+eusse
+eusses
+eût
+eussions
+eussiez
+eussent
+
+ | Later additions (from Jean-Christophe Deschamps)
+ceci | this
+cela | that
+celà | that
+cet | this
+cette | this
+ici | here
+ils | they
+les | the (pl)
+leurs | their (pl)
+quel | which
+quels | which
+quelle | which
+quelles | which
+sans | without
+soi | oneself
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ga.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ga.txt
new file mode 100644
index 0000000..9ff88d7
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ga.txt
@@ -0,0 +1,110 @@
+
+a
+ach
+ag
+agus
+an
+aon
+ar
+arna
+as
+b'
+ba
+beirt
+bhúr
+caoga
+ceathair
+ceathrar
+chomh
+chtó
+chuig
+chun
+cois
+céad
+cúig
+cúigear
+d'
+daichead
+dar
+de
+deich
+deichniúr
+den
+dhá
+do
+don
+dtí
+dá
+dár
+dó
+faoi
+faoin
+faoina
+faoinár
+fara
+fiche
+gach
+gan
+go
+gur
+haon
+hocht
+i
+iad
+idir
+in
+ina
+ins
+inár
+is
+le
+leis
+lena
+lenár
+m'
+mar
+mo
+mé
+na
+nach
+naoi
+naonúr
+ná
+ní
+níor
+nó
+nócha
+ocht
+ochtar
+os
+roimh
+sa
+seacht
+seachtar
+seachtó
+seasca
+seisear
+siad
+sibh
+sinn
+sna
+sé
+sí
+tar
+thar
+thú
+triúr
+trí
+trína
+trínár
+tríocha
+tú
+um
+ár
+é
+éis
+í
+ó
+ón
+óna
+ónár
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_gl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_gl.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_gl.txt
new file mode 100644
index 0000000..d8760b1
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_gl.txt
@@ -0,0 +1,161 @@
+# galican stopwords
+a
+aínda
+alí
+aquel
+aquela
+aquelas
+aqueles
+aquilo
+aquí
+ao
+aos
+as
+así
+á
+ben
+cando
+che
+co
+coa
+comigo
+con
+connosco
+contigo
+convosco
+coas
+cos
+cun
+cuns
+cunha
+cunhas
+da
+dalgunha
+dalgunhas
+dalgún
+dalgúns
+das
+de
+del
+dela
+delas
+deles
+desde
+deste
+do
+dos
+dun
+duns
+dunha
+dunhas
+e
+el
+ela
+elas
+eles
+en
+era
+eran
+esa
+esas
+ese
+eses
+esta
+estar
+estaba
+está
+están
+este
+estes
+estiven
+estou
+eu
+é
+facer
+foi
+foron
+fun
+había
+hai
+iso
+isto
+la
+las
+lle
+lles
+lo
+los
+mais
+me
+meu
+meus
+min
+miña
+miñas
+moi
+na
+nas
+neste
+nin
+no
+non
+nos
+nosa
+nosas
+noso
+nosos
+nós
+nun
+nunha
+nuns
+nunhas
+o
+os
+ou
+ó
+ós
+para
+pero
+pode
+pois
+pola
+polas
+polo
+polos
+por
+que
+se
+senón
+ser
+seu
+seus
+sexa
+sido
+sobre
+súa
+súas
+tamén
+tan
+te
+ten
+teñen
+teño
+ter
+teu
+teus
+ti
+tido
+tiña
+tiven
+túa
+túas
+un
+unha
+unhas
+uns
+vos
+vosa
+vosas
+voso
+vosos
+vós
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hi.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hi.txt
new file mode 100644
index 0000000..86286bb
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hi.txt
@@ -0,0 +1,235 @@
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# Note: by default this file also contains forms normalized by HindiNormalizer
+# for spelling variation (see section below), such that it can be used whether or
+# not you enable that feature. When adding additional entries to this list,
+# please add the normalized form as well.
+अंदर
+अत
+अपना
+अपनी
+अपने
+अभी
+आदि
+आप
+इत्यादि
+इन
+इनका
+इन्हीं
+इन्हें
+इन्हों
+इस
+इसका
+इसकी
+इसके
+इसमें
+इसी
+इसे
+उन
+उनका
+उनकी
+उनके
+उनको
+उन्हीं
+उन्हें
+उन्हों
+उस
+उसके
+उसी
+उसे
+एक
+एवं
+एस
+ऐसे
+और
+कई
+कर
+करता
+करते
+करना
+करने
+करें
+कहते
+कहा
+का
+काफ़ी
+कि
+कितना
+किन्हें
+किन्हों
+किया
+किर
+किस
+किसी
+किसे
+की
+कुछ
+कुल
+के
+को
+कोई
+कौन
+कौनसा
+गया
+घर
+जब
+जहाँ
+जा
+जितना
+जिन
+जिन्हें
+जिन्हों
+जिस
+जिसे
+जीधर
+जैसा
+जैसे
+जो
+तक
+तब
+तरह
+तिन
+तिन्हें
+तिन्हों
+तिस
+तिसे
+तो
+था
+थी
+थे
+दबारा
+दिया
+दुसरा
+दूसरे
+दो
+द्वारा
+न
+नहीं
+ना
+निहायत
+नीचे
+ने
+पर
+पर
+पहले
+पूरा
+पे
+फिर
+बनी
+बही
+बहुत
+बाद
+बाला
+बिलकुल
+भी
+भीतर
+मगर
+मानो
+मे
+में
+यदि
+यह
+यहाँ
+यही
+या
+यिह
+ये
+रखें
+रहा
+रहे
+ऱ्वासा
+लिए
+लिये
+लेकिन
+व
+वर्ग
+वह
+वह
+वहाँ
+वहीं
+वाले
+वुह
+वे
+वग़ैरह
+संग
+सकता
+सकते
+सबसे
+सभी
+साथ
+साबुत
+साभ
+सारा
+से
+सो
+ही
+हुआ
+हुई
+हुए
+है
+हैं
+हो
+होता
+होती
+होते
+होना
+होने
+# additional normalized forms of the above
+अपनि
+जेसे
+होति
+सभि
+तिंहों
+इंहों
+दवारा
+इसि
+किंहें
+थि
+उंहों
+ओर
+जिंहें
+वहिं
+अभि
+बनि
+हि
+उंहिं
+उंहें
+हें
+वगेरह
+एसे
+रवासा
+कोन
+निचे
+काफि
+उसि
+पुरा
+भितर
+हे
+बहि
+वहां
+कोइ
+यहां
+जिंहों
+तिंहें
+किसि
+कइ
+यहि
+इंहिं
+जिधर
+इंहें
+अदि
+इतयादि
+हुइ
+कोनसा
+इसकि
+दुसरे
+जहां
+अप
+किंहों
+उनकि
+भि
+वरग
+हुअ
+जेसा
+नहिं
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hu.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hu.txt
new file mode 100644
index 0000000..37526da
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hu.txt
@@ -0,0 +1,211 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+| Hungarian stop word list
+| prepared by Anna Tordai
+
+a
+ahogy
+ahol
+aki
+akik
+akkor
+alatt
+által
+általában
+amely
+amelyek
+amelyekben
+amelyeket
+amelyet
+amelynek
+ami
+amit
+amolyan
+amíg
+amikor
+át
+abban
+ahhoz
+annak
+arra
+arról
+az
+azok
+azon
+azt
+azzal
+azért
+aztán
+azután
+azonban
+bár
+be
+belül
+benne
+cikk
+cikkek
+cikkeket
+csak
+de
+e
+eddig
+egész
+egy
+egyes
+egyetlen
+egyéb
+egyik
+egyre
+ekkor
+el
+elég
+ellen
+elő
+először
+előtt
+első
+én
+éppen
+ebben
+ehhez
+emilyen
+ennek
+erre
+ez
+ezt
+ezek
+ezen
+ezzel
+ezért
+és
+fel
+felé
+hanem
+hiszen
+hogy
+hogyan
+igen
+így
+illetve
+ill.
+ill
+ilyen
+ilyenkor
+ison
+ismét
+itt
+jó
+jól
+jobban
+kell
+kellett
+keresztül
+keressünk
+ki
+kívül
+között
+közül
+legalább
+lehet
+lehetett
+legyen
+lenne
+lenni
+lesz
+lett
+maga
+magát
+majd
+majd
+már
+más
+másik
+meg
+még
+mellett
+mert
+mely
+melyek
+mi
+mit
+míg
+miért
+milyen
+mikor
+minden
+mindent
+mindenki
+mindig
+mint
+mintha
+mivel
+most
+nagy
+nagyobb
+nagyon
+ne
+néha
+nekem
+neki
+nem
+néhány
+nélkül
+nincs
+olyan
+ott
+össze
+ő
+ők
+őket
+pedig
+persze
+rá
+s
+saját
+sem
+semmi
+sok
+sokat
+sokkal
+számára
+szemben
+szerint
+szinte
+talán
+tehát
+teljes
+tovább
+továbbá
+több
+úgy
+ugyanis
+új
+újabb
+újra
+után
+utána
+utolsó
+vagy
+vagyis
+valaki
+valami
+valamint
+való
+vagyok
+van
+vannak
+volt
+voltam
+voltak
+voltunk
+vissza
+vele
+viszont
+volna
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hy.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hy.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hy.txt
new file mode 100644
index 0000000..60c1c50
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_hy.txt
@@ -0,0 +1,46 @@
+# example set of Armenian stopwords.
+այդ
+այլ
+այն
+այս
+դու
+դուք
+եմ
+են
+ենք
+ես
+եք
+է
+էի
+էին
+էինք
+էիր
+էիք
+էր
+ըստ
+թ
+ի
+ին
+իսկ
+իր
+կամ
+համար
+հետ
+հետո
+մենք
+մեջ
+մի
+ն
+նա
+նաև
+նրա
+նրանք
+որ
+որը
+որոնք
+որպես
+ու
+ում
+պիտի
+վրա
+և
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_id.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_id.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_id.txt
new file mode 100644
index 0000000..4617f83
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_id.txt
@@ -0,0 +1,359 @@
+# from appendix D of: A Study of Stemming Effects on Information
+# Retrieval in Bahasa Indonesia
+ada
+adanya
+adalah
+adapun
+agak
+agaknya
+agar
+akan
+akankah
+akhirnya
+aku
+akulah
+amat
+amatlah
+anda
+andalah
+antar
+diantaranya
+antara
+antaranya
+diantara
+apa
+apaan
+mengapa
+apabila
+apakah
+apalagi
+apatah
+atau
+ataukah
+ataupun
+bagai
+bagaikan
+sebagai
+sebagainya
+bagaimana
+bagaimanapun
+sebagaimana
+bagaimanakah
+bagi
+bahkan
+bahwa
+bahwasanya
+sebaliknya
+banyak
+sebanyak
+beberapa
+seberapa
+begini
+beginian
+beginikah
+beginilah
+sebegini
+begitu
+begitukah
+begitulah
+begitupun
+sebegitu
+belum
+belumlah
+sebelum
+sebelumnya
+sebenarnya
+berapa
+berapakah
+berapalah
+berapapun
+betulkah
+sebetulnya
+biasa
+biasanya
+bila
+bilakah
+bisa
+bisakah
+sebisanya
+boleh
+bolehkah
+bolehlah
+buat
+bukan
+bukankah
+bukanlah
+bukannya
+cuma
+percuma
+dahulu
+dalam
+dan
+dapat
+dari
+daripada
+dekat
+demi
+demikian
+demikianlah
+sedemikian
+dengan
+depan
+di
+dia
+dialah
+dini
+diri
+dirinya
+terdiri
+dong
+dulu
+enggak
+enggaknya
+entah
+entahlah
+terhadap
+terhadapnya
+hal
+hampir
+hanya
+hanyalah
+harus
+haruslah
+harusnya
+seharusnya
+hendak
+hendaklah
+hendaknya
+hingga
+sehingga
+ia
+ialah
+ibarat
+ingin
+inginkah
+inginkan
+ini
+inikah
+inilah
+itu
+itukah
+itulah
+jangan
+jangankan
+janganlah
+jika
+jikalau
+juga
+justru
+kala
+kalau
+kalaulah
+kalaupun
+kalian
+kami
+kamilah
+kamu
+kamulah
+kan
+kapan
+kapankah
+kapanpun
+dikarenakan
+karena
+karenanya
+ke
+kecil
+kemudian
+kenapa
+kepada
+kepadanya
+ketika
+seketika
+khususnya
+kini
+kinilah
+kiranya
+sekiranya
+kita
+kitalah
+kok
+lagi
+lagian
+selagi
+lah
+lain
+lainnya
+melainkan
+selaku
+lalu
+melalui
+terlalu
+lama
+lamanya
+selama
+selama
+selamanya
+lebih
+terlebih
+bermacam
+macam
+semacam
+maka
+makanya
+makin
+malah
+malahan
+mampu
+mampukah
+mana
+manakala
+manalagi
+masih
+masihkah
+semasih
+masing
+mau
+maupun
+semaunya
+memang
+mereka
+merekalah
+meski
+meskipun
+semula
+mungkin
+mungkinkah
+nah
+namun
+nanti
+nantinya
+nyaris
+oleh
+olehnya
+seorang
+seseorang
+pada
+padanya
+padahal
+paling
+sepanjang
+pantas
+sepantasnya
+sepantasnyalah
+para
+pasti
+pastilah
+per
+pernah
+pula
+pun
+merupakan
+rupanya
+serupa
+saat
+saatnya
+sesaat
+saja
+sajalah
+saling
+bersama
+sama
+sesama
+sambil
+sampai
+sana
+sangat
+sangatlah
+saya
+sayalah
+se
+sebab
+sebabnya
+sebuah
+tersebut
+tersebutlah
+sedang
+sedangkan
+sedikit
+sedikitnya
+segala
+segalanya
+segera
+sesegera
+sejak
+sejenak
+sekali
+sekalian
+sekalipun
+sesekali
+sekaligus
+sekarang
+sekarang
+sekitar
+sekitarnya
+sela
+selain
+selalu
+seluruh
+seluruhnya
+semakin
+sementara
+sempat
+semua
+semuanya
+sendiri
+sendirinya
+seolah
+seperti
+sepertinya
+sering
+seringnya
+serta
+siapa
+siapakah
+siapapun
+disini
+disinilah
+sini
+sinilah
+sesuatu
+sesuatunya
+suatu
+sesudah
+sesudahnya
+sudah
+sudahkah
+sudahlah
+supaya
+tadi
+tadinya
+tak
+tanpa
+setelah
+telah
+tentang
+tentu
+tentulah
+tentunya
+tertentu
+seterusnya
+tapi
+tetapi
+setiap
+tiap
+setidaknya
+tidak
+tidakkah
+tidaklah
+toh
+waduh
+wah
+wahai
+sewaktu
+walau
+walaupun
+wong
+yaitu
+yakni
+yang
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_it.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_it.txt
new file mode 100644
index 0000000..1219cc7
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_it.txt
@@ -0,0 +1,303 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | An Italian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ad | a (to) before vowel
+al | a + il
+allo | a + lo
+ai | a + i
+agli | a + gli
+all | a + l'
+agl | a + gl'
+alla | a + la
+alle | a + le
+con | with
+col | con + il
+coi | con + i (forms collo, cogli etc are now very rare)
+da | from
+dal | da + il
+dallo | da + lo
+dai | da + i
+dagli | da + gli
+dall | da + l'
+dagl | da + gll'
+dalla | da + la
+dalle | da + le
+di | of
+del | di + il
+dello | di + lo
+dei | di + i
+degli | di + gli
+dell | di + l'
+degl | di + gl'
+della | di + la
+delle | di + le
+in | in
+nel | in + el
+nello | in + lo
+nei | in + i
+negli | in + gli
+nell | in + l'
+negl | in + gl'
+nella | in + la
+nelle | in + le
+su | on
+sul | su + il
+sullo | su + lo
+sui | su + i
+sugli | su + gli
+sull | su + l'
+sugl | su + gl'
+sulla | su + la
+sulle | su + le
+per | through, by
+tra | among
+contro | against
+io | I
+tu | thou
+lui | he
+lei | she
+noi | we
+voi | you
+loro | they
+mio | my
+mia |
+miei |
+mie |
+tuo |
+tua |
+tuoi | thy
+tue |
+suo |
+sua |
+suoi | his, her
+sue |
+nostro | our
+nostra |
+nostri |
+nostre |
+vostro | your
+vostra |
+vostri |
+vostre |
+mi | me
+ti | thee
+ci | us, there
+vi | you, there
+lo | him, the
+la | her, the
+li | them
+le | them, the
+gli | to him, the
+ne | from there etc
+il | the
+un | a
+uno | a
+una | a
+ma | but
+ed | and
+se | if
+perché | why, because
+anche | also
+come | how
+dov | where (as dov')
+dove | where
+che | who, that
+chi | who
+cui | whom
+non | not
+più | more
+quale | who, that
+quanto | how much
+quanti |
+quanta |
+quante |
+quello | that
+quelli |
+quella |
+quelle |
+questo | this
+questi |
+questa |
+queste |
+si | yes
+tutto | all
+tutti | all
+
+ | single letter forms:
+
+a | at
+c | as c' for ce or ci
+e | and
+i | the
+l | as l'
+o | or
+
+ | forms of avere, to have (not including the infinitive):
+
+ho
+hai
+ha
+abbiamo
+avete
+hanno
+abbia
+abbiate
+abbiano
+avrò
+avrai
+avrà
+avremo
+avrete
+avranno
+avrei
+avresti
+avrebbe
+avremmo
+avreste
+avrebbero
+avevo
+avevi
+aveva
+avevamo
+avevate
+avevano
+ebbi
+avesti
+ebbe
+avemmo
+aveste
+ebbero
+avessi
+avesse
+avessimo
+avessero
+avendo
+avuto
+avuta
+avuti
+avute
+
+ | forms of essere, to be (not including the infinitive):
+sono
+sei
+è
+siamo
+siete
+sia
+siate
+siano
+sarò
+sarai
+sarà
+saremo
+sarete
+saranno
+sarei
+saresti
+sarebbe
+saremmo
+sareste
+sarebbero
+ero
+eri
+era
+eravamo
+eravate
+erano
+fui
+fosti
+fu
+fummo
+foste
+furono
+fossi
+fosse
+fossimo
+fossero
+essendo
+
+ | forms of fare, to do (not including the infinitive, fa, fat-):
+faccio
+fai
+facciamo
+fanno
+faccia
+facciate
+facciano
+farò
+farai
+farà
+faremo
+farete
+faranno
+farei
+faresti
+farebbe
+faremmo
+fareste
+farebbero
+facevo
+facevi
+faceva
+facevamo
+facevate
+facevano
+feci
+facesti
+fece
+facemmo
+faceste
+fecero
+facessi
+facesse
+facessimo
+facessero
+facendo
+
+ | forms of stare, to be (not including the infinitive):
+sto
+stai
+sta
+stiamo
+stanno
+stia
+stiate
+stiano
+starò
+starai
+starà
+staremo
+starete
+staranno
+starei
+staresti
+starebbe
+staremmo
+stareste
+starebbero
+stavo
+stavi
+stava
+stavamo
+stavate
+stavano
+stetti
+stesti
+stette
+stemmo
+steste
+stettero
+stessi
+stesse
+stessimo
+stessero
+stando
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ja.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ja.txt
new file mode 100644
index 0000000..d4321be
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ja.txt
@@ -0,0 +1,127 @@
+#
+# This file defines a stopword set for Japanese.
+#
+# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
+# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
+# for frequency lists, etc. that can be useful for making your own set (if desired)
+#
+# Note that there is an overlap between these stopwords and the terms stopped when used
+# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
+# that comments are not allowed on the same line as stopwords.
+#
+# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
+# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
+# using the same character width as the entries in this file. Since this StopFilter is
+# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
+# entries to be in half-width and your kana entries to be in full-width.
+#
+の
+に
+は
+を
+た
+が
+で
+て
+と
+し
+れ
+さ
+ある
+いる
+も
+する
+から
+な
+こと
+として
+い
+や
+れる
+など
+なっ
+ない
+この
+ため
+その
+あっ
+よう
+また
+もの
+という
+あり
+まで
+られ
+なる
+へ
+か
+だ
+これ
+によって
+により
+おり
+より
+による
+ず
+なり
+られる
+において
+ば
+なかっ
+なく
+しかし
+について
+せ
+だっ
+その後
+できる
+それ
+う
+ので
+なお
+のみ
+でき
+き
+つ
+における
+および
+いう
+さらに
+でも
+ら
+たり
+その他
+に関する
+たち
+ます
+ん
+なら
+に対して
+特に
+せる
+及び
+これら
+とき
+では
+にて
+ほか
+ながら
+うち
+そして
+とともに
+ただし
+かつて
+それぞれ
+または
+お
+ほど
+ものの
+に対する
+ほとんど
+と共に
+といった
+です
+とも
+ところ
+ここ
+##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_lv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_lv.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_lv.txt
new file mode 100644
index 0000000..e21a23c
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_lv.txt
@@ -0,0 +1,172 @@
+# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
+# the original list of over 800 forms was refined:
+# pronouns, adverbs, interjections were removed
+#
+# prepositions
+aiz
+ap
+ar
+apakš
+ārpus
+augšpus
+bez
+caur
+dēļ
+gar
+iekš
+iz
+kopš
+labad
+lejpus
+līdz
+no
+otrpus
+pa
+par
+pār
+pēc
+pie
+pirms
+pret
+priekš
+starp
+šaipus
+uz
+viņpus
+virs
+virspus
+zem
+apakšpus
+# Conjunctions
+un
+bet
+jo
+ja
+ka
+lai
+tomēr
+tikko
+turpretī
+arī
+kaut
+gan
+tādēļ
+tā
+ne
+tikvien
+vien
+kā
+ir
+te
+vai
+kamēr
+# Particles
+ar
+diezin
+droši
+diemžēl
+nebūt
+ik
+it
+taču
+nu
+pat
+tiklab
+iekšpus
+nedz
+tik
+nevis
+turpretim
+jeb
+iekam
+iekām
+iekāms
+kolīdz
+līdzko
+tiklīdz
+jebšu
+tālab
+tāpēc
+nekā
+itin
+jā
+jau
+jel
+nē
+nezin
+tad
+tikai
+vis
+tak
+iekams
+vien
+# modal verbs
+būt
+biju
+biji
+bija
+bijām
+bijāt
+esmu
+esi
+esam
+esat
+būšu
+būsi
+būs
+būsim
+būsiet
+tikt
+tiku
+tiki
+tika
+tikām
+tikāt
+tieku
+tiec
+tiek
+tiekam
+tiekat
+tikšu
+tiks
+tiksim
+tiksiet
+tapt
+tapi
+tapāt
+topat
+tapšu
+tapsi
+taps
+tapsim
+tapsiet
+kļūt
+kļuvu
+kļuvi
+kļuva
+kļuvām
+kļuvāt
+kļūstu
+kļūsti
+kļūst
+kļūstam
+kļūstat
+kļūšu
+kļūsi
+kļūs
+kļūsim
+kļūsiet
+# verbs
+varēt
+varēju
+varējām
+varēšu
+varēsim
+var
+varēji
+varējāt
+varēsi
+varēsiet
+varat
+varēja
+varēs
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_nl.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_nl.txt
new file mode 100644
index 0000000..47a2aea
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_nl.txt
@@ -0,0 +1,119 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Dutch stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large sample of Dutch text.
+
+ | Dutch stop words frequently exhibit homonym clashes. These are indicated
+ | clearly below.
+
+de | the
+en | and
+van | of, from
+ik | I, the ego
+te | (1) chez, at etc, (2) to, (3) too
+dat | that, which
+die | that, those, who, which
+in | in, inside
+een | a, an, one
+hij | he
+het | the, it
+niet | not, nothing, naught
+zijn | (1) to be, being, (2) his, one's, its
+is | is
+was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
+op | on, upon, at, in, up, used up
+aan | on, upon, to (as dative)
+met | with, by
+als | like, such as, when
+voor | (1) before, in front of, (2) furrow
+had | had, past tense all persons sing. of 'hebben' (have)
+er | there
+maar | but, only
+om | round, about, for etc
+hem | him
+dan | then
+zou | should/would, past tense all persons sing. of 'zullen'
+of | or, whether, if
+wat | what, something, anything
+mijn | possessive and noun 'mine'
+men | people, 'one'
+dit | this
+zo | so, thus, in this way
+door | through by
+over | over, across
+ze | she, her, they, them
+zich | oneself
+bij | (1) a bee, (2) by, near, at
+ook | also, too
+tot | till, until
+je | you
+mij | me
+uit | out of, from
+der | Old Dutch form of 'van der' still found in surnames
+daar | (1) there, (2) because
+haar | (1) her, their, them, (2) hair
+naar | (1) unpleasant, unwell etc, (2) towards, (3) as
+heb | present first person sing. of 'to have'
+hoe | how, why
+heeft | present third person sing. of 'to have'
+hebben | 'to have' and various parts thereof
+deze | this
+u | you
+want | (1) for, (2) mitten, (3) rigging
+nog | yet, still
+zal | 'shall', first and third person sing. of verb 'zullen' (will)
+me | me
+zij | she, they
+nu | now
+ge | 'thou', still used in Belgium and south Netherlands
+geen | none
+omdat | because
+iets | something, somewhat
+worden | to become, grow, get
+toch | yet, still
+al | all, every, each
+waren | (1) 'were' (2) to wander, (3) wares, (3)
+veel | much, many
+meer | (1) more, (2) lake
+doen | to do, to make
+toen | then, when
+moet | noun 'spot/mote' and present form of 'to must'
+ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
+zonder | without
+kan | noun 'can' and present form of 'to be able'
+hun | their, them
+dus | so, consequently
+alles | all, everything, anything
+onder | under, beneath
+ja | yes, of course
+eens | once, one day
+hier | here
+wie | who
+werd | imperfect third person sing. of 'become'
+altijd | always
+doch | yet, but etc
+wordt | present third person sing. of 'become'
+wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
+kunnen | to be able
+ons | us/our
+zelf | self
+tegen | against, towards, at
+na | after, near
+reeds | already
+wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
+kon | could; past tense of 'to be able'
+niets | nothing
+uw | your
+iemand | somebody
+geweest | been; past participle of 'be'
+andere | other
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_no.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_no.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_no.txt
new file mode 100644
index 0000000..a7a2c28
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_no.txt
@@ -0,0 +1,194 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Norwegian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This stop word list is for the dominant bokmål dialect. Words unique
+ | to nynorsk are marked *.
+
+ | Revised by Jan Bruusgaard <Ja...@ssb.no>, Jan 2005
+
+og | and
+i | in
+jeg | I
+det | it/this/that
+at | to (w. inf.)
+en | a/an
+et | a/an
+den | it/this/that
+til | to
+er | is/am/are
+som | who/that
+på | on
+de | they / you(formal)
+med | with
+han | he
+av | of
+ikke | not
+ikkje | not *
+der | there
+så | so
+var | was/were
+meg | me
+seg | you
+men | but
+ett | one
+har | have
+om | about
+vi | we
+min | my
+mitt | my
+ha | have
+hadde | had
+hun | she
+nå | now
+over | over
+da | when/as
+ved | by/know
+fra | from
+du | you
+ut | out
+sin | your
+dem | them
+oss | us
+opp | up
+man | you/one
+kan | can
+hans | his
+hvor | where
+eller | or
+hva | what
+skal | shall/must
+selv | self (reflective)
+sjøl | self (reflective)
+her | here
+alle | all
+vil | will
+bli | become
+ble | became
+blei | became *
+blitt | have become
+kunne | could
+inn | in
+når | when
+være | be
+kom | come
+noen | some
+noe | some
+ville | would
+dere | you
+som | who/which/that
+deres | their/theirs
+kun | only/just
+ja | yes
+etter | after
+ned | down
+skulle | should
+denne | this
+for | for/because
+deg | you
+si | hers/his
+sine | hers/his
+sitt | hers/his
+mot | against
+å | to
+meget | much
+hvorfor | why
+dette | this
+disse | these/those
+uten | without
+hvordan | how
+ingen | none
+din | your
+ditt | your
+blir | become
+samme | same
+hvilken | which
+hvilke | which (plural)
+sånn | such a
+inni | inside/within
+mellom | between
+vår | our
+hver | each
+hvem | who
+vors | us/ours
+hvis | whose
+både | both
+bare | only/just
+enn | than
+fordi | as/because
+før | before
+mange | many
+også | also
+slik | just
+vært | been
+være | to be
+båe | both *
+begge | both
+siden | since
+dykk | your *
+dykkar | yours *
+dei | they *
+deira | them *
+deires | theirs *
+deim | them *
+di | your (fem.) *
+då | as/when *
+eg | I *
+ein | a/an *
+eit | a/an *
+eitt | a/an *
+elles | or *
+honom | he *
+hjå | at *
+ho | she *
+hoe | she *
+henne | her
+hennar | her/hers
+hennes | hers
+hoss | how *
+hossen | how *
+ikkje | not *
+ingi | noone *
+inkje | noone *
+korleis | how *
+korso | how *
+kva | what/which *
+kvar | where *
+kvarhelst | where *
+kven | who/whom *
+kvi | why *
+kvifor | why *
+me | we *
+medan | while *
+mi | my *
+mine | my *
+mykje | much *
+no | now *
+nokon | some (masc./neut.) *
+noka | some (fem.) *
+nokor | some *
+noko | some *
+nokre | some *
+si | his/hers *
+sia | since *
+sidan | since *
+so | so *
+somt | some *
+somme | some *
+um | about*
+upp | up *
+vere | be *
+vore | was *
+verte | become *
+vort | become *
+varte | became *
+vart | became *
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_pt.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_pt.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_pt.txt
new file mode 100644
index 0000000..acfeb01
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_pt.txt
@@ -0,0 +1,253 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Portuguese stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | of, from
+a | the; to, at; her
+o | the; him
+que | who, that
+e | and
+do | de + o
+da | de + a
+em | in
+um | a
+para | for
+ | é from SER
+com | with
+não | not, no
+uma | a
+os | the; them
+no | em + o
+se | himself etc
+na | em + a
+por | for
+mais | more
+as | the; them
+dos | de + os
+como | as, like
+mas | but
+ | foi from SER
+ao | a + o
+ele | he
+das | de + as
+ | tem from TER
+à | a + a
+seu | his
+sua | her
+ou | or
+ | ser from SER
+quando | when
+muito | much
+ | há from HAV
+nos | em + os; us
+já | already, now
+ | está from EST
+eu | I
+também | also
+só | only, just
+pelo | per + o
+pela | per + a
+até | up to
+isso | that
+ela | he
+entre | between
+ | era from SER
+depois | after
+sem | without
+mesmo | same
+aos | a + os
+ | ter from TER
+seus | his
+quem | whom
+nas | em + as
+me | me
+esse | that
+eles | they
+ | estão from EST
+você | you
+ | tinha from TER
+ | foram from SER
+essa | that
+num | em + um
+nem | nor
+suas | her
+meu | my
+às | a + as
+minha | my
+ | têm from TER
+numa | em + uma
+pelos | per + os
+elas | they
+ | havia from HAV
+ | seja from SER
+qual | which
+ | será from SER
+nós | we
+ | tenho from TER
+lhe | to him, her
+deles | of them
+essas | those
+esses | those
+pelas | per + as
+este | this
+ | fosse from SER
+dele | of him
+
+ | other words. There are many contractions such as naquele = em+aquele,
+ | mo = me+o, but they are rare.
+ | Indefinite article plural forms are also rare.
+
+tu | thou
+te | thee
+vocês | you (plural)
+vos | you
+lhes | to them
+meus | my
+minhas
+teu | thy
+tua
+teus
+tuas
+nosso | our
+nossa
+nossos
+nossas
+
+dela | of her
+delas | of them
+
+esta | this
+estes | these
+estas | these
+aquele | that
+aquela | that
+aqueles | those
+aquelas | those
+isto | this
+aquilo | that
+
+ | forms of estar, to be (not including the infinitive):
+estou
+está
+estamos
+estão
+estive
+esteve
+estivemos
+estiveram
+estava
+estávamos
+estavam
+estivera
+estivéramos
+esteja
+estejamos
+estejam
+estivesse
+estivéssemos
+estivessem
+estiver
+estivermos
+estiverem
+
+ | forms of haver, to have (not including the infinitive):
+hei
+há
+havemos
+hão
+houve
+houvemos
+houveram
+houvera
+houvéramos
+haja
+hajamos
+hajam
+houvesse
+houvéssemos
+houvessem
+houver
+houvermos
+houverem
+houverei
+houverá
+houveremos
+houverão
+houveria
+houveríamos
+houveriam
+
+ | forms of ser, to be (not including the infinitive):
+sou
+somos
+são
+era
+éramos
+eram
+fui
+foi
+fomos
+foram
+fora
+fôramos
+seja
+sejamos
+sejam
+fosse
+fôssemos
+fossem
+for
+formos
+forem
+serei
+será
+seremos
+serão
+seria
+seríamos
+seriam
+
+ | forms of ter, to have (not including the infinitive):
+tenho
+tem
+temos
+tém
+tinha
+tínhamos
+tinham
+tive
+teve
+tivemos
+tiveram
+tivera
+tivéramos
+tenha
+tenhamos
+tenham
+tivesse
+tivéssemos
+tivessem
+tiver
+tivermos
+tiverem
+terei
+terá
+teremos
+terão
+teria
+teríamos
+teriam
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ro.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ro.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ro.txt
new file mode 100644
index 0000000..4fdee90
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stopwords_ro.txt
@@ -0,0 +1,233 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+acea
+aceasta
+această
+aceea
+acei
+aceia
+acel
+acela
+acele
+acelea
+acest
+acesta
+aceste
+acestea
+aceşti
+aceştia
+acolo
+acum
+ai
+aia
+aibă
+aici
+al
+ăla
+ale
+alea
+ălea
+altceva
+altcineva
+am
+ar
+are
+aş
+aşadar
+asemenea
+asta
+ăsta
+astăzi
+astea
+ăstea
+ăştia
+asupra
+aţi
+au
+avea
+avem
+aveţi
+azi
+bine
+bucur
+bună
+ca
+că
+căci
+când
+care
+cărei
+căror
+cărui
+cât
+câte
+câţi
+către
+câtva
+ce
+cel
+ceva
+chiar
+cînd
+cine
+cineva
+cît
+cîte
+cîţi
+cîtva
+contra
+cu
+cum
+cumva
+curând
+curînd
+da
+dă
+dacă
+dar
+datorită
+de
+deci
+deja
+deoarece
+departe
+deşi
+din
+dinaintea
+dintr
+dintre
+drept
+după
+ea
+ei
+el
+ele
+eram
+este
+eşti
+eu
+face
+fără
+fi
+fie
+fiecare
+fii
+fim
+fiţi
+iar
+ieri
+îi
+îl
+îmi
+împotriva
+în
+înainte
+înaintea
+încât
+încît
+încotro
+între
+întrucât
+întrucît
+îţi
+la
+lângă
+le
+li
+lîngă
+lor
+lui
+mă
+mâine
+mea
+mei
+mele
+mereu
+meu
+mi
+mine
+mult
+multă
+mulţi
+ne
+nicăieri
+nici
+nimeni
+nişte
+noastră
+noastre
+noi
+noştri
+nostru
+nu
+ori
+oricând
+oricare
+oricât
+orice
+oricînd
+oricine
+oricît
+oricum
+oriunde
+până
+pe
+pentru
+peste
+pînă
+poate
+pot
+prea
+prima
+primul
+prin
+printr
+sa
+să
+săi
+sale
+sau
+său
+se
+şi
+sînt
+sîntem
+sînteţi
+spre
+sub
+sunt
+suntem
+sunteţi
+ta
+tăi
+tale
+tău
+te
+ţi
+ţie
+tine
+toată
+toate
+tot
+toţi
+totuşi
+tu
+un
+una
+unde
+undeva
+unei
+unele
+uneori
+unor
+vă
+vi
+voastră
+voastre
+voi
+voştri
+vostru
+vouă
+vreo
+vreun
[43/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt
new file mode 100644
index 0000000..5527140
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt
@@ -0,0 +1,243 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | a russian stop word list. comments begin with vertical bar. each stop
+ | word is at the start of a line.
+
+ | this is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | letter `ё' is translated to `е'.
+
+и | and
+в | in/into
+во | alternative form
+не | not
+что | what/that
+он | he
+на | on/onto
+я | i
+с | from
+со | alternative form
+как | how
+а | milder form of `no' (but)
+то | conjunction and form of `that'
+все | all
+она | she
+так | so, thus
+его | him
+но | but
+да | yes/and
+ты | thou
+к | towards, by
+у | around, chez
+же | intensifier particle
+вы | you
+за | beyond, behind
+бы | conditional/subj. particle
+по | up to, along
+только | only
+ее | her
+мне | to me
+было | it was
+вот | here is/are, particle
+от | away from
+меня | me
+еще | still, yet, more
+нет | no, there isnt/arent
+о | about
+из | out of
+ему | to him
+теперь | now
+когда | when
+даже | even
+ну | so, well
+вдруг | suddenly
+ли | interrogative particle
+если | if
+уже | already, but homonym of `narrower'
+или | or
+ни | neither
+быть | to be
+был | he was
+него | prepositional form of его
+до | up to
+вас | you accusative
+нибудь | indef. suffix preceded by hyphen
+опять | again
+уж | already, but homonym of `adder'
+вам | to you
+сказал | he said
+ведь | particle `after all'
+там | there
+потом | then
+себя | oneself
+ничего | nothing
+ей | to her
+может | usually with `быть' as `maybe'
+они | they
+тут | here
+где | where
+есть | there is/are
+надо | got to, must
+ней | prepositional form of ей
+для | for
+мы | we
+тебя | thee
+их | them, their
+чем | than
+была | she was
+сам | self
+чтоб | in order to
+без | without
+будто | as if
+человек | man, person, one
+чего | genitive form of `what'
+раз | once
+тоже | also
+себе | to oneself
+под | beneath
+жизнь | life
+будет | will be
+ж | short form of intensifer particle `же'
+тогда | then
+кто | who
+этот | this
+говорил | was saying
+того | genitive form of `that'
+потому | for that reason
+этого | genitive form of `this'
+какой | which
+совсем | altogether
+ним | prepositional form of `его', `они'
+здесь | here
+этом | prepositional form of `этот'
+один | one
+почти | almost
+мой | my
+тем | instrumental/dative plural of `тот', `то'
+чтобы | full form of `in order that'
+нее | her (acc.)
+кажется | it seems
+сейчас | now
+были | they were
+куда | where to
+зачем | why
+сказать | to say
+всех | all (acc., gen. preposn. plural)
+никогда | never
+сегодня | today
+можно | possible, one can
+при | by
+наконец | finally
+два | two
+об | alternative form of `о', about
+другой | another
+хоть | even
+после | after
+над | above
+больше | more
+тот | that one (masc.)
+через | across, in
+эти | these
+нас | us
+про | about
+всего | in all, only, of all
+них | prepositional form of `они' (they)
+какая | which, feminine
+много | lots
+разве | interrogative particle
+сказала | she said
+три | three
+эту | this, acc. fem. sing.
+моя | my, feminine
+впрочем | moreover, besides
+хорошо | good
+свою | ones own, acc. fem. sing.
+этой | oblique form of `эта', fem. `this'
+перед | in front of
+иногда | sometimes
+лучше | better
+чуть | a little
+том | preposn. form of `that one'
+нельзя | one must not
+такой | such a one
+им | to them
+более | more
+всегда | always
+конечно | of course
+всю | acc. fem. sing of `all'
+между | between
+
+
+ | b: some paradigms
+ |
+ | personal pronouns
+ |
+ | я меня мне мной [мною]
+ | ты тебя тебе тобой [тобою]
+ | он его ему им [него, нему, ним]
+ | она ее эи ею [нее, нэи, нею]
+ | оно его ему им [него, нему, ним]
+ |
+ | мы нас нам нами
+ | вы вас вам вами
+ | они их им ими [них, ним, ними]
+ |
+ | себя себе собой [собою]
+ |
+ | demonstrative pronouns: этот (this), тот (that)
+ |
+ | этот эта это эти
+ | этого эты это эти
+ | этого этой этого этих
+ | этому этой этому этим
+ | этим этой этим [этою] этими
+ | этом этой этом этих
+ |
+ | тот та то те
+ | того ту то те
+ | того той того тех
+ | тому той тому тем
+ | тем той тем [тою] теми
+ | том той том тех
+ |
+ | determinative pronouns
+ |
+ | (a) весь (all)
+ |
+ | весь вся все все
+ | всего всю все все
+ | всего всей всего всех
+ | всему всей всему всем
+ | всем всей всем [всею] всеми
+ | всем всей всем всех
+ |
+ | (b) сам (himself etc)
+ |
+ | сам сама само сами
+ | самого саму само самих
+ | самого самой самого самих
+ | самому самой самому самим
+ | самим самой самим [самою] самими
+ | самом самой самом самих
+ |
+ | stems of verbs `to be', `to have', `to do' and modal
+ |
+ | быть бы буд быв есть суть
+ | име
+ | дел
+ | мог мож мочь
+ | уме
+ | хоч хот
+ | долж
+ | можн
+ | нужн
+ | нельзя
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt
new file mode 100644
index 0000000..096f87f
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt
@@ -0,0 +1,133 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Swedish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | Swedish stop words occasionally exhibit homonym clashes. For example
+ | så = so, but also seed. These are indicated clearly below.
+
+och | and
+det | it, this/that
+att | to (with infinitive)
+i | in, at
+en | a
+jag | I
+hon | she
+som | who, that
+han | he
+på | on
+den | it, this/that
+med | with
+var | where, each
+sig | him(self) etc
+för | for
+så | so (also: seed)
+till | to
+är | is
+men | but
+ett | a
+om | if; around, about
+hade | had
+de | they, these/those
+av | of
+icke | not, no
+mig | me
+du | you
+henne | her
+då | then, when
+sin | his
+nu | now
+har | have
+inte | inte någon = no one
+hans | his
+honom | him
+skulle | 'sake'
+hennes | her
+där | there
+min | my
+man | one (pronoun)
+ej | nor
+vid | at, by, on (also: vast)
+kunde | could
+något | some etc
+från | from, off
+ut | out
+när | when
+efter | after, behind
+upp | up
+vi | we
+dem | them
+vara | be
+vad | what
+över | over
+än | than
+dig | you
+kan | can
+sina | his
+här | here
+ha | have
+mot | towards
+alla | all
+under | under (also: wonder)
+någon | some etc
+eller | or (else)
+allt | all
+mycket | much
+sedan | since
+ju | why
+denna | this/that
+själv | myself, yourself etc
+detta | this/that
+åt | to
+utan | without
+varit | was
+hur | how
+ingen | no
+mitt | my
+ni | you
+bli | to be, become
+blev | from bli
+oss | us
+din | thy
+dessa | these/those
+några | some etc
+deras | their
+blir | from bli
+mina | my
+samma | (the) same
+vilken | who, that
+er | you, your
+sådan | such a
+vår | our
+blivit | from bli
+dess | its
+inom | within
+mellan | between
+sådant | such a
+varför | why
+varje | each
+vilka | who, that
+ditt | thy
+vem | who
+vilket | who, that
+sitta | his
+sådana | such a
+vart | each
+dina | thy
+vars | whose
+vårt | our
+våra | our
+ert | your
+era | your
+vilkas | whose
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt
new file mode 100644
index 0000000..07f0fab
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt
@@ -0,0 +1,119 @@
+# Thai stopwords from:
+# "Opinion Detection in Thai Political News Columns
+# Based on Subjectivity Analysis"
+# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
+ไว้
+ไม่
+ไป
+ได้
+ให้
+ใน
+โดย
+แห่ง
+แล้ว
+และ
+แรก
+แบบ
+แต่
+เอง
+เห็น
+เลย
+เริ่ม
+เรา
+เมื่อ
+เพื่อ
+เพราะ
+เป็นการ
+เป็น
+เปิดเผย
+เปิด
+เนื่องจาก
+เดียวกัน
+เดียว
+เช่น
+เฉพาะ
+เคย
+เข้า
+เขา
+อีก
+อาจ
+อะไร
+ออก
+อย่าง
+อยู่
+อยาก
+หาก
+หลาย
+หลังจาก
+หลัง
+หรือ
+หนึ่ง
+ส่วน
+ส่ง
+สุด
+สําหรับ
+ว่า
+วัน
+ลง
+ร่วม
+ราย
+รับ
+ระหว่าง
+รวม
+ยัง
+มี
+มาก
+มา
+พร้อม
+พบ
+ผ่าน
+ผล
+บาง
+น่า
+นี้
+นํา
+นั้น
+นัก
+นอกจาก
+ทุก
+ที่สุด
+ที่
+ทําให้
+ทํา
+ทาง
+ทั้งนี้
+ทั้ง
+ถ้า
+ถูก
+ถึง
+ต้อง
+ต่างๆ
+ต่าง
+ต่อ
+ตาม
+ตั้งแต่
+ตั้ง
+ด้าน
+ด้วย
+ดัง
+ซึ่ง
+ช่วง
+จึง
+จาก
+จัด
+จะ
+คือ
+ความ
+ครั้ง
+คง
+ขึ้น
+ของ
+ขอ
+ขณะ
+ก่อน
+ก็
+การ
+กับ
+กัน
+กว่า
+กล่าว
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt
new file mode 100644
index 0000000..84d9408
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+altmış
+altı
+ama
+ancak
+arada
+aslında
+ayrıca
+bana
+bazı
+belki
+ben
+benden
+beni
+benim
+beri
+beş
+bile
+bin
+bir
+birçok
+biri
+birkaç
+birkez
+birşey
+birşeyi
+biz
+bize
+bizden
+bizi
+bizim
+böyle
+böylece
+bu
+buna
+bunda
+bundan
+bunlar
+bunları
+bunların
+bunu
+bunun
+burada
+çok
+çünkü
+da
+daha
+dahi
+de
+defa
+değil
+diğer
+diye
+doksan
+dokuz
+dolayı
+dolayısıyla
+dört
+edecek
+eden
+ederek
+edilecek
+ediliyor
+edilmesi
+ediyor
+eğer
+elli
+en
+etmesi
+etti
+ettiği
+ettiğini
+gibi
+göre
+halen
+hangi
+hatta
+hem
+henüz
+hep
+hepsi
+her
+herhangi
+herkesin
+hiç
+hiçbir
+için
+iki
+ile
+ilgili
+ise
+işte
+itibaren
+itibariyle
+kadar
+karşın
+katrilyon
+kendi
+kendilerine
+kendini
+kendisi
+kendisine
+kendisini
+kez
+ki
+kim
+kimden
+kime
+kimi
+kimse
+kırk
+milyar
+milyon
+mu
+mü
+mı
+nasıl
+ne
+neden
+nedenle
+nerde
+nerede
+nereye
+niye
+niçin
+o
+olan
+olarak
+oldu
+olduğu
+olduğunu
+olduklarını
+olmadı
+olmadığı
+olmak
+olması
+olmayan
+olmaz
+olsa
+olsun
+olup
+olur
+olursa
+oluyor
+on
+ona
+ondan
+onlar
+onlardan
+onları
+onların
+onu
+onun
+otuz
+oysa
+öyle
+pek
+rağmen
+sadece
+sanki
+sekiz
+seksen
+sen
+senden
+seni
+senin
+siz
+sizden
+sizi
+sizin
+şey
+şeyden
+şeyi
+şeyler
+şöyle
+şu
+şuna
+şunda
+şundan
+şunları
+şunu
+tarafından
+trilyon
+tüm
+üç
+üzere
+var
+vardı
+ve
+veya
+ya
+yani
+yapacak
+yapılan
+yapılması
+yapıyor
+yapmak
+yaptı
+yaptığı
+yaptığını
+yaptıkları
+yedi
+yerine
+yetmiş
+yine
+yirmi
+yoksa
+yüz
+zaten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt b/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt
new file mode 100644
index 0000000..6f0368e
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt
@@ -0,0 +1,29 @@
+#
+# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
+#
+# Add entries to this file in order to override the statistical model in terms
+# of segmentation, readings and part-of-speech tags. Notice that entries do
+# not have weights since they are always used when found. This is by-design
+# in order to maximize ease-of-use.
+#
+# Entries are defined using the following CSV format:
+# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
+#
+# Notice that a single half-width space separates tokens and readings, and
+# that the number tokens and readings must match exactly.
+#
+# Also notice that multiple entries with the same <text> is undefined.
+#
+# Whitespace only lines are ignored. Comments are not allowed on entry lines.
+#
+
+# Custom segmentation for kanji compounds
+日本経済新聞,日本 経済 新聞,ニホン ケイザイ シンブン,カスタム名詞
+関西国際空港,関西 国際 空港,カンサイ コクサイ クウコウ,カスタム名詞
+
+# Custom segmentation for compound katakana
+トートバッグ,トート バッグ,トート バッグ,かずカナ名詞
+ショルダーバッグ,ショルダー バッグ,ショルダー バッグ,かずカナ名詞
+
+# Custom reading for former sumo wrestler
+朝青龍,朝青龍,アサショウリュウ,カスタム人名
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/managed-schema b/solr/server/solr/configsets/basic_configs/conf/managed-schema
new file mode 100644
index 0000000..599b0cc
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/managed-schema
@@ -0,0 +1,1045 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking. To improve performance one could
+ - set stored="false" for all fields possible (esp large fields) when you
+ only need to search on the field but don't need to return the original
+ value.
+ - set indexed="false" if you don't need to search on the field, but only
+ return the field as a result of searching on other indexed fields.
+ - remove all unneeded copyField statements
+ - for best index size and searching performance, set "index" to false
+ for all general text fields, use copyField to copy them to the
+ catchall "text" field, and use that for searching.
+ - For maximum indexing performance, use the ConcurrentUpdateSolrServer
+ java client.
+ - Remember to run the JVM in server mode, and use a higher logging level
+ that avoids logging every request
+-->
+
+<schema name="example-basic" version="1.6">
+ <!-- attribute "name" is the name of this schema and is only used for display purposes.
+ version="x.y" is Solr's version number for the schema syntax and
+ semantics. It should not normally be changed by applications.
+
+ 1.0: multiValued attribute did not exist, all fields are multiValued
+ by nature
+ 1.1: multiValued attribute introduced, false by default
+ 1.2: omitTermFreqAndPositions attribute introduced, true by default
+ except for text fields.
+ 1.3: removed optional field compress feature
+ 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+ behavior when a single string produces multiple tokens. Defaults
+ to off for version >= 1.4
+ 1.5: omitNorms defaults to true for primitive field types
+ (int, float, boolean, string...)
+ 1.6: useDocValuesAsStored defaults to true.
+ -->
+
+ <!-- Valid attributes for fields:
+ name: mandatory - the name for the field
+ type: mandatory - the name of a field type from the
+ fieldTypes section
+ indexed: true if this field should be indexed (searchable or sortable)
+ stored: true if this field should be retrievable
+ docValues: true if this field should have doc values. Doc values are
+ useful (required, if you are using *Point fields) for faceting,
+ grouping, sorting and function queries. Doc values will make the index
+ faster to load, more NRT-friendly and more memory-efficient.
+ They however come with some limitations: they are currently only
+ supported by StrField, UUIDField, all Trie*Fields and *PointFields,
+ and depending on the field type, they might require the field to be
+ single-valued, be required or have a default value (check the
+ documentation of the field type you're interested in for more information)
+ multiValued: true if this field may contain multiple values per document
+ omitNorms: (expert) set to true to omit the norms associated with
+ this field (this disables length normalization and index-time
+ boosting for the field, and saves some memory). Only full-text
+ fields or fields that need an index-time boost need norms.
+ Norms are omitted for primitive (non-analyzed) types by default.
+ termVectors: [false] set to true to store the term vector for a
+ given field.
+ When using MoreLikeThis, fields used for similarity should be
+ stored for best performance.
+ termPositions: Store position information with the term vector.
+ This will increase storage costs.
+ termOffsets: Store offset information with the term vector. This
+ will increase storage costs.
+ required: The field is required. It will throw an error if the
+ value does not exist
+ default: a value that should be used if no value is specified
+ when adding a document.
+ -->
+
+ <!-- field names should consist of alphanumeric or underscore characters only and
+ not start with a digit. This is not currently strictly enforced,
+ but other field names will not have first class support from all components
+ and back compatibility is not guaranteed. Names with both leading and
+ trailing underscores (e.g. _version_) are reserved.
+ -->
+
+ <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
+ id, _version_, and _text_. All other fields will be type guessed and added via the
+ "add-unknown-fields-to-the-schema" update request processor chain declared
+ in solrconfig.xml.
+
+ Note that many dynamic fields are also defined - you can use them to specify a
+ field's type via field naming conventions - see below.
+
+ WARNING: The _text_ catch-all field will significantly increase your index size.
+ If you don't need it, consider removing it and the corresponding copyField directive.
+ -->
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <!-- doc values are enabled by default for primitive types such as long so we don't index the version field -->
+ <field name="_version_" type="long" indexed="false" stored="false"/>
+ <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+ <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+ <!-- Only enabled in the "schemaless" data-driven example (assuming the client
+ does not know what fields may be searched) because it's very expensive to index everything twice. -->
+ <!-- <copyField source="*" dest="_text_"/> -->
+
+ <!-- Dynamic field definitions allow using convention over configuration
+ for fields via the specification of patterns to match field names.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end. -->
+
+ <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+ <dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true" />
+ <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
+
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+ <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
+ <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
+ <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
+
+ <!-- KD-tree (point) numerics -->
+ <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
+ <dynamicField name="*_pis" type="pints" indexed="true" stored="true"/>
+ <dynamicField name="*_pl" type="plong" indexed="true" stored="true"/>
+ <dynamicField name="*_pls" type="plongs" indexed="true" stored="true"/>
+ <dynamicField name="*_pf" type="pfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_pfs" type="pfloats" indexed="true" stored="true"/>
+ <dynamicField name="*_pd" type="pdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_pds" type="pdoubles" indexed="true" stored="true"/>
+ <dynamicField name="*_pdt" type="pdate" indexed="true" stored="true"/>
+ <dynamicField name="*_pdts" type="pdates" indexed="true" stored="true"/>
+
+ <!-- some trie-coded dynamic fields -->
+ <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
+ <dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
+ <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
+ <dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
+ <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
+ <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
+ <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
+ <dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
+
+ <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
+
+ <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+ <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+ <dynamicField name="random_*" type="random" />
+
+ <!-- uncomment the following to ignore any fields that don't already match an existing
+ field name or dynamic field, rather than reporting them as an error.
+ alternately, change the type="ignored" to some other type e.g. "text" if you want
+ unknown fields indexed and/or stored by default
+
+ NB: use of "*" dynamic fields will disable field type guessing and adding
+ unknown fields to the schema. -->
+ <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+ <!-- Field to use to determine and enforce document uniqueness.
+ Unless this field is marked with required="false", it will be a required field
+ -->
+ <uniqueKey>id</uniqueKey>
+
+ <!-- copyField commands copy one field to another at the time a document
+ is added to the index. It's used either to index the same field differently,
+ or to add multiple fields to the same field for easier/faster searching.
+
+ <copyField source="sourceFieldName" dest="destinationFieldName"/>
+ -->
+
+ <!-- field type definitions. The "name" attribute is
+ just a label to be used by field definitions. The "class"
+ attribute and any other attributes determine the real
+ behavior of the fieldType.
+ Class names starting with "solr" refer to java classes in a
+ standard package such as org.apache.solr.analysis
+ -->
+
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+ It supports doc values but in that case the field needs to be
+ single-valued and either required or have a default value.
+ -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+ <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+ <!-- boolean type: "true" or "false" -->
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+ <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
+ <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
+ currently supported on types that are sorted internally as strings
+ and on numeric types.
+ This includes "string","boolean", "int", "float", "long", "date", "double",
+ including the "Trie" and "Point" variants.
+ - If sortMissingLast="true", then a sort on this field will cause documents
+ without the field to come after documents with the field,
+ regardless of the requested sort order (asc or desc).
+ - If sortMissingFirst="true", then a sort on this field will cause documents
+ without the field to come before documents with the field,
+ regardless of the requested sort order.
+ - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+ then default lucene sorting will be used which places docs without the
+ field first in an ascending sort and last in a descending sort.
+ -->
+
+ <!--
+ Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
+ search time and at index time, but some features are still not supported.
+ Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
+ -->
+ <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+ <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+ <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+ <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
+
+ <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
+ <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
+ <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
+ <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+
+ <!--
+ Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
+ tint/tfloat/tlong/tdouble types.
+ -->
+ <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+
+ <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
+ <!--
+ Numeric field types that index each value at various levels of precision
+ to accelerate range queries when the number of values between the range
+ endpoints is large. See the javadoc for NumericRangeQuery for internal
+ implementation details.
+
+ Smaller precisionStep values (specified in bits) will lead to more tokens
+ indexed per value, slightly larger index size, and faster range queries.
+ A precisionStep of 0 disables indexing at different precision levels.
+
+ Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
+ -->
+ <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+
+ <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
+ is a more restricted form of the canonical representation of dateTime
+ http://www.w3.org/TR/xmlschema-2/#dateTime
+ The trailing "Z" designates UTC time and is mandatory.
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+ All other components are mandatory.
+
+ Expressions can also be used to denote calculations that should be
+ performed relative to "NOW" to determine the value, ie...
+
+ NOW/HOUR
+ ... Round to the start of the current hour
+ NOW-1DAY
+ ... Exactly 1 day prior to now
+ NOW/DAY+6MONTHS+3DAYS
+ ... 6 months and 3 days in the future from the start of
+ the current day
+
+ Consult the TrieDateField javadocs for more information.
+ -->
+ <!-- KD-tree versions of date fields -->
+ <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+ <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
+
+ <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
+ <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
+ <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
+
+
+ <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+ <fieldType name="binary" class="solr.BinaryField"/>
+
+ <!-- The "RandomSortField" is not used to store or search any
+ data. You can declare fields of this type it in your schema
+ to generate pseudo-random orderings of your docs for sorting
+ or function purposes. The ordering is generated based on the field
+ name and the version of the index. As long as the index version
+ remains unchanged, and the same field name is reused,
+ the ordering of the docs will be consistent.
+ If you want different psuedo-random orderings of documents,
+ for the same version of the index, use a dynamicField and
+ change the field name in the request.
+ -->
+ <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+
+ <!-- solr.TextField allows the specification of custom text analyzers
+ specified as a tokenizer and a list of token filters. Different
+ analyzers may be specified for indexing and querying.
+
+ The optional positionIncrementGap puts space between multiple fields of
+ this type on the same document, with the purpose of preventing false phrase
+ matching across fields.
+
+ For more info on customizing your analyzer chain, please see
+ http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+ -->
+
+ <!-- One can also specify an existing Analyzer class that has a
+ default constructor via the class attribute on the analyzer element.
+ Example:
+ <fieldType name="text_greek" class="solr.TextField">
+ <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+ </fieldType>
+ -->
+
+ <!-- A text field that only splits on whitespace for exact matching of words -->
+ <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
+ <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A general text field that has reasonable, generic
+ cross-language defaults: it tokenizes with StandardTokenizer,
+ removes stop words from case-insensitive "stopwords.txt"
+ (empty by default), and down cases. At query time only, it
+ also applies synonyms.
+ -->
+ <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English: it
+ tokenizes with StandardTokenizer, removes English stop words
+ (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+ finally applies Porter's stemming. The query time analyzer
+ also applies synonyms from synonyms.txt. -->
+ <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
+ <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.FlattenGraphFilterFactory"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English, plus
+ aggressive word-splitting and autophrase features enabled.
+ This field is just like text_en, except it adds
+ WordDelimiterGraphFilter to enable splitting and matching of
+ words on case-change, alpha numeric boundaries, and
+ non-alphanumeric chars. This means certain compound word
+ cases will work, for example query "wi fi" will match
+ document "WiFi" or "wi-fi".
+ -->
+ <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
+ <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
+ but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
+ <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
+ <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+ possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ <filter class="solr.FlattenGraphFilterFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+ possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Just like text_general except it reverses the characters of
+ each token, to enable more efficient leading wildcard queries.
+ -->
+ <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
+ <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+ maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
+ <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- lowercases the entire field value, keeping it as a single token. -->
+ <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
+ <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at index time, so
+ queries for paths match documents at that path, or in descendent paths
+ -->
+ <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
+ <fieldType name="descendent_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at query time, so
+ queries for paths match documents at that path, or in ancestor paths
+ -->
+ <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
+ <fieldType name="ancestor_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ </fieldType>
+
+ <!-- since fields of this type are by default not stored or indexed,
+ any data added to them will be ignored outright. -->
+ <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
+
+ <!-- This point type indexes the coordinates as separate fields (subFields)
+ If subFieldType is defined, it references a type, and a dynamic field
+ definition is created matching *___<typename>. Alternately, if
+ subFieldSuffix is defined, that is used to create the subFields.
+ Example: if subFieldType="double", then the coordinates would be
+ indexed in fields myloc_0___double,myloc_1___double.
+ Example: if subFieldSuffix="_d" then the coordinates would be indexed
+ in fields myloc_0_d,myloc_1_d
+ The subFields are an implementation detail of the fieldType, and end
+ users normally should not need to know about them.
+ -->
+ <dynamicField name="*_point" type="point" indexed="true" stored="true"/>
+ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+ <!-- A specialized field for geospatial search filters and distance sorting. -->
+ <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
+
+ <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
+ For more information about this and other Spatial fields new to Solr 4, see:
+ http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+ -->
+ <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+ geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
+
+ <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
+ Parameters:
+ defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
+ precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
+ providerClass: Lets you plug in other exchange provider backend:
+ solr.FileExchangeRateProvider is the default and takes one parameter:
+ currencyConfig: name of an xml file holding exchange rates
+ solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
+ ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
+ refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
+ -->
+ <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
+
+
+
+ <!-- some examples for different languages (generally ordered by ISO code) -->
+
+ <!-- Arabic -->
+ <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
+ <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- for any non-arabic -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+ <!-- normalizes ﻯ to ﻱ, etc -->
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.ArabicStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Bulgarian -->
+ <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
+ <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+ <filter class="solr.BulgarianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Catalan -->
+ <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
+ <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+ <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
+ <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- for any non-CJK -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.CJKBigramFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Czech -->
+ <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
+ <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+ <filter class="solr.CzechStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Danish -->
+ <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
+ <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- German -->
+ <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
+ <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+ <filter class="solr.GermanNormalizationFilterFactory"/>
+ <filter class="solr.GermanLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Greek -->
+ <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
+ <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- greek specific lowercase for sigma -->
+ <filter class="solr.GreekLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+ <filter class="solr.GreekStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Spanish -->
+ <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
+ <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+ <filter class="solr.SpanishLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Basque -->
+ <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
+ <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Persian -->
+ <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
+ <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <!-- for ZWNJ -->
+ <charFilter class="solr.PersianCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.PersianNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Finnish -->
+ <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
+ <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+ <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- French -->
+ <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
+ <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+ <filter class="solr.FrenchLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Irish -->
+ <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
+ <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes d', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+ <!-- removes n-, etc. position increments is intentionally false! -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+ <filter class="solr.IrishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Galician -->
+ <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
+ <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+ <filter class="solr.GalicianStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Hindi -->
+ <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
+ <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- normalizes unicode representation -->
+ <filter class="solr.IndicNormalizationFilterFactory"/>
+ <!-- normalizes variation in spelling -->
+ <filter class="solr.HindiNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+ <filter class="solr.HindiStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Hungarian -->
+ <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
+ <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Armenian -->
+ <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
+ <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Indonesian -->
+ <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
+ <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+ <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+ <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Italian -->
+ <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
+ <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+ <filter class="solr.ItalianLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+ NOTE: If you want to optimize search for precision, use default operator AND in your request
+ handler config (q.op) Use OR if you would like to optimize for recall (default).
+ -->
+ <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
+ <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+ <analyzer>
+ <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+ Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
+ is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+ Valid values for attribute mode are:
+ normal: regular segmentation
+ search: segmentation useful for search with synonyms compounds (default)
+ extended: same as search mode, but unigrams unknown words (experimental)
+
+ For some applications it might be good to use search mode for indexing and normal mode for
+ queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+ Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+ Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+ model with your own entries for segmentation, part-of-speech tags and readings without a need
+ to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+ User dictionary attributes are:
+ userDictionary: user dictionary filename
+ userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+ See lang/userdict_ja.txt for a sample user dictionary file.
+
+ Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
+
+ See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+ -->
+ <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+ <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+ <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
+ <filter class="solr.JapaneseBaseFormFilterFactory"/>
+ <!-- Removes tokens with certain part-of-speech tags -->
+ <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
+ <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
+ <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
+ <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
+ <!-- Lower-cases romaji characters -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Latvian -->
+ <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
+ <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+ <filter class="solr.LatvianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Dutch -->
+ <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
+ <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+ <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Norwegian -->
+ <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
+ <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+ <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+ <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Portuguese -->
+ <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
+ <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+ <filter class="solr.PortugueseLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+ <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Romanian -->
+ <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
+ <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Russian -->
+ <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
+ <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+ <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Swedish -->
+ <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
+ <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+ <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Thai -->
+ <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
+ <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.ThaiTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Turkish -->
+ <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
+ <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.TurkishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Similarity is the scoring routine for each document vs. a query.
+ A custom Similarity or SimilarityFactory may be specified here, but
+ the default is fine for most applications.
+ For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+ -->
+ <!--
+ <similarity class="com.example.solr.CustomSimilarityFactory">
+ <str name="paramkey">param value</str>
+ </similarity>
+ -->
+
+</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/params.json
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/params.json b/solr/server/solr/configsets/basic_configs/conf/params.json
new file mode 100644
index 0000000..06114ef
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/params.json
@@ -0,0 +1,20 @@
+{"params":{
+ "query":{
+ "defType":"edismax",
+ "q.alt":"*:*",
+ "rows":"10",
+ "fl":"*,score",
+ "":{"v":0}
+ },
+ "facets":{
+ "facet":"on",
+ "facet.mincount": "1",
+ "":{"v":0}
+ },
+ "velocity":{
+ "wt": "velocity",
+ "v.template":"browse",
+ "v.layout": "layout",
+ "":{"v":0}
+ }
+}}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/protwords.txt b/solr/server/solr/configsets/basic_configs/conf/protwords.txt
new file mode 100644
index 0000000..1dfc0ab
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/protwords.txt
@@ -0,0 +1,21 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+# Use a protected word file to protect against the stemmer reducing two
+# unrelated words to the same base word.
+
+# Some non-words that normally won't be encountered,
+# just to test that they won't be stemmed.
+dontstems
+zwhacky
+
[34/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-6671: Possible
to set solr.data.home property as root dir for all data
Posted by sh...@apache.org.
SOLR-6671: Possible to set solr.data.home property as root dir for all data
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/39dfb780
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/39dfb780
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/39dfb780
Branch: refs/heads/feature/autoscaling
Commit: 39dfb7808ac11c369985549dff06441f0cf5b93c
Parents: 0ec9d64
Author: Jan Høydahl <ja...@apache.org>
Authored: Tue Jun 20 13:20:44 2017 +0200
Committer: Jan Høydahl <ja...@apache.org>
Committed: Tue Jun 20 13:21:14 2017 +0200
----------------------------------------------------------------------
solr/CHANGES.txt | 1 +
solr/bin/solr | 18 +++++-
solr/bin/solr.cmd | 32 +++++++++-
solr/bin/solr.in.cmd | 4 ++
solr/bin/solr.in.sh | 4 ++
.../solr/core/CachingDirectoryFactory.java | 10 ++++
.../org/apache/solr/core/DirectoryFactory.java | 24 +++++++-
.../apache/solr/core/DirectoryFactoryTest.java | 61 ++++++++++++++++++++
...adir-and-directoryfactory-in-solrconfig.adoc | 2 +
9 files changed, 150 insertions(+), 6 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/39dfb780/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 5c865a1..9267039 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -909,6 +909,7 @@ New Features
parsers' behavior remains the same: queries will be split on whitespace before sending individual terms to analysis.
(Steve Rowe)
+* SOLR-6671: Possible to set solr.data.home property as root dir for all data (janhoy, Shawn Heisey, Mark Miller)
Bug Fixes
----------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/39dfb780/solr/bin/solr
----------------------------------------------------------------------
diff --git a/solr/bin/solr b/solr/bin/solr
index d21167e1..a22ef93 100755
--- a/solr/bin/solr
+++ b/solr/bin/solr
@@ -299,7 +299,7 @@ function print_usage() {
echo ""
elif [[ "$CMD" == "start" || "$CMD" == "restart" ]]; then
echo ""
- echo "Usage: solr $CMD [-f] [-c] [-h hostname] [-p port] [-d directory] [-z zkHost] [-m memory] [-e example] [-s solr.solr.home] [-a \"additional-options\"] [-V]"
+ echo "Usage: solr $CMD [-f] [-c] [-h hostname] [-p port] [-d directory] [-z zkHost] [-m memory] [-e example] [-s solr.solr.home] [-t solr.data.home] [-a \"additional-options\"] [-V]"
echo ""
echo " -f Start Solr in foreground; default starts Solr in the background"
echo " and sends stdout / stderr to solr-PORT-console.log"
@@ -329,6 +329,9 @@ function print_usage() {
echo " This parameter is ignored when running examples (-e), as the solr.solr.home depends"
echo " on which example is run. The default value is server/solr."
echo ""
+ echo " -t <dir> Sets the solr.data.home system property, where Solr will store data (index)."
+ echo " If not set, Solr uses solr.solr.home for config and data."
+ echo ""
echo " -e <example> Name of the example to run; available examples:"
echo " cloud: SolrCloud example"
echo " techproducts: Comprehensive example illustrating many of Solr's core capabilities"
@@ -1387,6 +1390,10 @@ if [ $# -gt 0 ]; then
SOLR_HOME="$2"
shift 2
;;
+ -t|-data.home)
+ SOLR_DATA_HOME="$2"
+ shift 2
+ ;;
-e|-example)
if [[ -z "$2" || "${2:0:1}" == "-" ]]; then
print_usage "$SCRIPT_CMD" "Example name is required when using the $1 option!"
@@ -1682,6 +1689,10 @@ if [ ! -e "$SOLR_HOME" ]; then
echo -e "\nSolr home directory $SOLR_HOME not found!\n"
exit 1
fi
+if [[ $SOLR_DATA_HOME ]] && [ ! -e "$SOLR_DATA_HOME" ]; then
+ echo -e "\nSolr data home directory $SOLR_DATA_HOME not found!\n"
+ exit 1
+fi
if $verbose ; then
q=""
else
@@ -1882,6 +1893,9 @@ function launch_solr() {
echo -e " SOLR_LOG_LEVEL = $SOLR_LOG_LEVEL"
fi
+ if [ "$SOLR_DATA_HOME" != "" ]; then
+ echo -e " SOLR_DATA_HOME = $SOLR_DATA_HOME"
+ fi
echo -e "\n"
fi
@@ -1897,7 +1911,7 @@ function launch_solr() {
"${REMOTE_JMX_OPTS[@]}" "${CLOUD_MODE_OPTS[@]}" $SOLR_LOG_LEVEL_OPT -Dsolr.log.dir="$SOLR_LOGS_DIR" \
"-Djetty.port=$SOLR_PORT" "-DSTOP.PORT=$stop_port" "-DSTOP.KEY=$STOP_KEY" \
"${SOLR_HOST_ARG[@]}" "-Duser.timezone=$SOLR_TIMEZONE" \
- "-Djetty.home=$SOLR_SERVER_DIR" "-Dsolr.solr.home=$SOLR_HOME" "-Dsolr.install.dir=$SOLR_TIP" \
+ "-Djetty.home=$SOLR_SERVER_DIR" "-Dsolr.solr.home=$SOLR_HOME" "-Dsolr.data.home=$SOLR_DATA_HOME" "-Dsolr.install.dir=$SOLR_TIP" \
"${LOG4J_CONFIG[@]}" "${SOLR_OPTS[@]}")
if [ "$SOLR_MODE" == "solrcloud" ]; then
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/39dfb780/solr/bin/solr.cmd
----------------------------------------------------------------------
diff --git a/solr/bin/solr.cmd b/solr/bin/solr.cmd
index 0afea02..8772200 100644
--- a/solr/bin/solr.cmd
+++ b/solr/bin/solr.cmd
@@ -285,7 +285,7 @@ goto done
:start_usage
@echo.
-@echo Usage: solr %SCRIPT_CMD% [-f] [-c] [-h hostname] [-p port] [-d directory] [-z zkHost] [-m memory] [-e example] [-s solr.solr.home] [-a "additional-options"] [-V]
+@echo Usage: solr %SCRIPT_CMD% [-f] [-c] [-h hostname] [-p port] [-d directory] [-z zkHost] [-m memory] [-e example] [-s solr.solr.home] [-t solr.data.home] [-a "additional-options"] [-V]
@echo.
@echo -f Start Solr in foreground; default starts Solr in the background
@echo and sends stdout / stderr to solr-PORT-console.log
@@ -312,6 +312,9 @@ goto done
@echo This parameter is ignored when running examples (-e), as the solr.solr.home depends
@echo on which example is run. The default value is server/solr.
@echo.
+@echo -t dir Sets the solr.data.home system property, used as root for ^<instance_dir^>/data directories.
+@echo If not set, Solr uses solr.solr.home for both config and data.
+@echo.
@echo -e example Name of the example to run; available examples:
@echo cloud: SolrCloud example
@echo techproducts: Comprehensive example illustrating many of Solr's core capabilities
@@ -602,6 +605,7 @@ IF "%1"=="-cloud" goto set_cloud_mode
IF "%1"=="-d" goto set_server_dir
IF "%1"=="-dir" goto set_server_dir
IF "%1"=="-s" goto set_solr_home_dir
+IF "%1"=="-t" goto set_solr_data_dir
IF "%1"=="-solr.home" goto set_solr_home_dir
IF "%1"=="-e" goto set_example
IF "%1"=="-example" goto set_example
@@ -697,6 +701,24 @@ SHIFT
SHIFT
goto parse_args
+:set_solr_data_dir
+
+set "arg=%~2"
+IF "%arg%"=="" (
+ set SCRIPT_ERROR=Directory name is required!
+ goto invalid_cmd_line
+)
+
+set firstChar=%arg:~0,1%
+IF "%firstChar%"=="-" (
+ set SCRIPT_ERROR=Expected directory but found %2 instead!
+ goto invalid_cmd_line
+)
+set "SOLR_DATA_HOME=%~2"
+SHIFT
+SHIFT
+goto parse_args
+
:set_example
set "arg=%~2"
@@ -897,6 +919,7 @@ IF [%SOLR_LOGS_DIR%] == [] (
set SOLR_LOGS_DIR=%SOLR_LOGS_DIR:"=%
)
set SOLR_LOGS_DIR_QUOTED="%SOLR_LOGS_DIR%"
+set SOLR_DATA_HOME_QUOTED="%SOLR_DATA_HOME%"
set "EXAMPLE_DIR=%SOLR_TIP%\example"
set TMP=!SOLR_HOME:%EXAMPLE_DIR%=!
@@ -1139,6 +1162,10 @@ IF "%verbose%"=="1" (
@echo SOLR_LOG_LEVEL = !SOLR_LOG_LEVEL!
)
+ IF NOT "%SOLR_DATA_HOME%"=="" (
+ @echo SOLR_DATA_HOME = !SOLR_DATA_HOME!
+ )
+
@echo.
)
@@ -1155,6 +1182,7 @@ IF "%SOLR_SSL_ENABLED%"=="true" (
)
IF NOT "%SOLR_LOG_LEVEL%"=="" set "START_OPTS=%START_OPTS% -Dsolr.log.level=%SOLR_LOG_LEVEL%"
set "START_OPTS=%START_OPTS% -Dsolr.log.dir=%SOLR_LOGS_DIR_QUOTED%"
+IF NOT "%SOLR_DATA_HOME%"=="" set "START_OPTS=%START_OPTS% -Dsolr.data.home=%SOLR_DATA_HOME_QUOTED%"
IF NOT DEFINED LOG4J_CONFIG set "LOG4J_CONFIG=file:%SOLR_SERVER_DIR%\resources\log4j.properties"
cd /d "%SOLR_SERVER_DIR%"
@@ -1833,4 +1861,4 @@ REM Safe echo which does not mess with () in strings
set "eout=%1"
set eout=%eout:"=%
echo !eout!
-GOTO :eof
+GOTO :eof
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/39dfb780/solr/bin/solr.in.cmd
----------------------------------------------------------------------
diff --git a/solr/bin/solr.in.cmd b/solr/bin/solr.in.cmd
index 077b68d..6071263 100644
--- a/solr/bin/solr.in.cmd
+++ b/solr/bin/solr.in.cmd
@@ -68,6 +68,10 @@ REM Path to a directory for Solr to store cores and their data. By default, Solr
REM If solr.xml is not stored in ZooKeeper, this directory needs to contain solr.xml
REM set SOLR_HOME=
+REM Path to a directory that Solr will use as root for data folders for each core.
+REM If not set, defaults to <instance_dir>/data. Overridable per core through 'dataDir' core property
+REM set SOLR_DATA_HOME=
+
REM Changes the logging level. Valid values: ALL, TRACE, DEBUG, INFO, WARN, ERROR, FATAL, OFF. Default is INFO
REM This is an alternative to changing the rootLogger in log4j.properties
REM set SOLR_LOG_LEVEL=INFO
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/39dfb780/solr/bin/solr.in.sh
----------------------------------------------------------------------
diff --git a/solr/bin/solr.in.sh b/solr/bin/solr.in.sh
index 6c6c229..060ece9 100644
--- a/solr/bin/solr.in.sh
+++ b/solr/bin/solr.in.sh
@@ -86,6 +86,10 @@
# If solr.xml is not stored in ZooKeeper, this directory needs to contain solr.xml
#SOLR_HOME=
+# Path to a directory that Solr will use as root for data folders for each core.
+# If not set, defaults to <instance_dir>/data. Overridable per core through 'dataDir' core property
+#SOLR_DATA_HOME=
+
# Solr provides a default Log4J configuration properties file in server/resources
# however, you may want to customize the log settings and file appender location
# so you can point the script to use a different log4j.properties file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/39dfb780/solr/core/src/java/org/apache/solr/core/CachingDirectoryFactory.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/core/CachingDirectoryFactory.java b/solr/core/src/java/org/apache/solr/core/CachingDirectoryFactory.java
index e710063..5301370 100644
--- a/solr/core/src/java/org/apache/solr/core/CachingDirectoryFactory.java
+++ b/solr/core/src/java/org/apache/solr/core/CachingDirectoryFactory.java
@@ -19,6 +19,7 @@ package org.apache.solr.core;
import java.io.File;
import java.io.IOException;
import java.lang.invoke.MethodHandles;
+import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.Collection;
import java.util.HashMap;
@@ -395,6 +396,15 @@ public abstract class CachingDirectoryFactory extends DirectoryFactory {
maxWriteMBPerSecMerge = (Double) args.get("maxWriteMBPerSecMerge");
maxWriteMBPerSecRead = (Double) args.get("maxWriteMBPerSecRead");
maxWriteMBPerSecDefault = (Double) args.get("maxWriteMBPerSecDefault");
+
+ dataHomePath = args.get(DATA_HOME) == null ? null : Paths.get((String) args.get(DATA_HOME));
+ if (dataHomePath == null && System.getProperty(DATA_HOME) != null && System.getProperty(DATA_HOME).length() > 0) {
+ // If solr.data.home is not specified explicitly in solrconfig.xml, fall back to global System Property with same name
+ dataHomePath = Paths.get(System.getProperty(DATA_HOME));
+ }
+ if (dataHomePath != null) {
+ log.info(DATA_HOME + "=" + dataHomePath);
+ }
}
/*
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/39dfb780/solr/core/src/java/org/apache/solr/core/DirectoryFactory.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/core/DirectoryFactory.java b/solr/core/src/java/org/apache/solr/core/DirectoryFactory.java
index 20824ab..f60958d 100644
--- a/solr/core/src/java/org/apache/solr/core/DirectoryFactory.java
+++ b/solr/core/src/java/org/apache/solr/core/DirectoryFactory.java
@@ -24,6 +24,8 @@ import java.io.IOException;
import java.lang.invoke.MethodHandles;
import java.nio.file.NoSuchFileException;
import java.util.Arrays;
+import java.nio.file.Path;
+import java.nio.file.Paths;
import java.util.Collections;
import java.util.List;
@@ -53,6 +55,11 @@ public abstract class DirectoryFactory implements NamedListInitializedPlugin,
protected static final String INDEX_W_TIMESTAMP_REGEX = "index\\.[0-9]{17}"; // see SnapShooter.DATE_FMT
+ public static final String DATA_HOME = "solr.data.home";
+
+ // May be set by sub classes as data root, in which case getDataHome will use it as base
+ protected Path dataHomePath;
+
// hint about what the directory contains - default is index directory
public enum DirContext {DEFAULT, META_DATA}
@@ -315,9 +322,22 @@ public abstract class DirectoryFactory implements NamedListInitializedPlugin,
return false;
}
+ /**
+ * Get the data home folder. If solr.data.home is set, that is used, else base on instanceDir
+ * @param cd core descriptor instance
+ * @return a String with absolute path to data direcotry
+ */
public String getDataHome(CoreDescriptor cd) throws IOException {
- // by default, we go off the instance directory
- return cd.getInstanceDir().resolve(cd.getDataDir()).toAbsolutePath().toString();
+ String dataDir;
+ if (dataHomePath != null) {
+ String instanceDirLastPath = cd.getInstanceDir().getName(cd.getInstanceDir().getNameCount()-1).toString();
+ dataDir = Paths.get(coreContainer.getSolrHome()).resolve(dataHomePath)
+ .resolve(instanceDirLastPath).resolve(cd.getDataDir()).toAbsolutePath().toString();
+ } else {
+ // by default, we go off the instance directory
+ dataDir = cd.getInstanceDir().resolve(cd.getDataDir()).toAbsolutePath().toString();
+ }
+ return dataDir;
}
public void cleanupOldIndexDirectories(final String dataDirPath, final String currentIndexDirPath, boolean afterCoreReload) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/39dfb780/solr/core/src/test/org/apache/solr/core/DirectoryFactoryTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/core/DirectoryFactoryTest.java b/solr/core/src/test/org/apache/solr/core/DirectoryFactoryTest.java
index 59868b5..35198b7 100755
--- a/solr/core/src/test/org/apache/solr/core/DirectoryFactoryTest.java
+++ b/solr/core/src/test/org/apache/solr/core/DirectoryFactoryTest.java
@@ -16,7 +16,17 @@
*/
package org.apache.solr.core;
+import java.io.IOException;
+import java.nio.file.Paths;
+import java.util.Properties;
+
import org.apache.lucene.util.LuceneTestCase;
+import org.apache.solr.common.util.NamedList;
+import org.apache.solr.handler.admin.CoreAdminHandler;
+import org.apache.solr.handler.component.HttpShardHandlerFactory;
+import org.junit.After;
+import org.junit.Before;
+import org.junit.Test;
public class DirectoryFactoryTest extends LuceneTestCase {
@@ -28,4 +38,55 @@ public class DirectoryFactoryTest extends LuceneTestCase {
assertEquals("hdfs", DirectoryFactory.LOCK_TYPE_HDFS);
}
+ @After
+ @Before
+ public void clean() {
+ System.clearProperty("solr.data.home");
+ System.clearProperty("solr.solr.home");
+ }
+
+ @Test
+ public void testGetDataHome() throws Exception {
+ MockCoreContainer cc = new MockCoreContainer("/solr/home");
+ Properties cp = cc.getContainerProperties();
+ boolean zkAware = cc.isZooKeeperAware();
+ RAMDirectoryFactory rdf = new RAMDirectoryFactory();
+ rdf.initCoreContainer(cc);
+ rdf.init(new NamedList());
+
+ // No solr.data.home property set. Absolute instanceDir
+ assertEquals("/tmp/inst1/data", rdf.getDataHome(new CoreDescriptor("core_name", Paths.get("/tmp/inst1"), cp, zkAware)));
+
+ // Simulate solr.data.home set in solrconfig.xml <directoryFactory> tag
+ NamedList args = new NamedList();
+ args.add("solr.data.home", "/solrdata/");
+ rdf.init(args);
+ assertEquals("/solrdata/inst_dir/data", rdf.getDataHome(new CoreDescriptor("core_name", Paths.get("inst_dir"), cp, zkAware)));
+
+ // solr.data.home set with System property, and relative path
+ System.setProperty("solr.data.home", "solrdata");
+ rdf.init(new NamedList());
+ assertEquals("/solr/home/solrdata/inst_dir/data", rdf.getDataHome(new CoreDescriptor("core_name", Paths.get("inst_dir"), cp, zkAware)));
+ // Test parsing last component of instanceDir, and using custom dataDir
+ assertEquals("/solr/home/solrdata/myinst/mydata", rdf.getDataHome(new CoreDescriptor("core_name", Paths.get("/path/to/myinst"), cp, zkAware, "dataDir", "mydata")));
+ }
+
+
+ private static class MockCoreContainer extends CoreContainer {
+
+ private final String mockSolrHome;
+
+ public MockCoreContainer(String solrHome) throws IOException {
+ super(new Object());
+ mockSolrHome = solrHome;
+ this.shardHandlerFactory = new HttpShardHandlerFactory();
+ this.coreAdminHandler = new CoreAdminHandler();
+ }
+
+ @Override
+ public String getSolrHome() {
+ return mockSolrHome;
+ }
+ }
+
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/39dfb780/solr/solr-ref-guide/src/datadir-and-directoryfactory-in-solrconfig.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/datadir-and-directoryfactory-in-solrconfig.adoc b/solr/solr-ref-guide/src/datadir-and-directoryfactory-in-solrconfig.adoc
index 8ee43be..c68a3ad 100644
--- a/solr/solr-ref-guide/src/datadir-and-directoryfactory-in-solrconfig.adoc
+++ b/solr/solr-ref-guide/src/datadir-and-directoryfactory-in-solrconfig.adoc
@@ -33,6 +33,8 @@ The `${solr.core.name}` substitution will cause the name of the current core to
If you are using replication to replicate the Solr index (as described in <<legacy-scaling-and-distribution.adoc#legacy-scaling-and-distribution,Legacy Scaling and Distribution>>), then the `<dataDir>` directory should correspond to the index directory used in the replication configuration.
+NOTE: If the environment variable `SOLR_DATA_HOME` if defined, or if `solr.data.home` is configured for your DirectoryFactory, the location of data directory will be `<SOLR_DATA_HOME>/<instance_name>/data`.
+
[[DataDirandDirectoryFactoryinSolrConfig-SpecifyingtheDirectoryFactoryForYourIndex]]
== Specifying the DirectoryFactory For Your Index
[10/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10882:
LengthEvaluator now supports collections of any type
Posted by sh...@apache.org.
SOLR-10882: LengthEvaluator now supports collections of any type
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/f1695104
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/f1695104
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/f1695104
Branch: refs/heads/feature/autoscaling
Commit: f1695104fa8df6d9b484ef94d13eac16bcb3cf36
Parents: fffbe67
Author: Dennis Gove <dp...@gmail.com>
Authored: Tue Jun 13 09:06:00 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Sun Jun 18 11:50:57 2017 -0400
----------------------------------------------------------------------
.../client/solrj/io/eval/LengthEvaluator.java | 23 +++-
.../io/stream/eval/LengthEvaluatorTest.java | 119 +++++++++++++++++++
2 files changed, 138 insertions(+), 4 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/f1695104/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/LengthEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/LengthEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/LengthEvaluator.java
index da55ee4..b070fe8 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/LengthEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/LengthEvaluator.java
@@ -17,7 +17,8 @@
package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
-import java.util.List;
+import java.util.Collection;
+import java.util.Locale;
import org.apache.solr.client.solrj.io.Tuple;
import org.apache.solr.client.solrj.io.stream.expr.Explanation;
@@ -33,12 +34,26 @@ public class LengthEvaluator extends ComplexEvaluator implements Expressible {
public LengthEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
+
+ if(1 != subEvaluators.size()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - expecting one value but found %d",expression,subEvaluators.size()));
+ }
}
public Number evaluate(Tuple tuple) throws IOException {
- StreamEvaluator colEval1 = subEvaluators.get(0);
- List<Number> numbers = (List<Number>)colEval1.evaluate(tuple);
- return numbers.size();
+
+ Object result = subEvaluators.get(0).evaluate(tuple);
+
+ if(null == result){
+ throw new IOException(String.format(Locale.ROOT, "Unable to find %s(...) because the value is null", constructingFactory.getFunctionName(getClass())));
+ }
+
+ if(result instanceof Collection<?>){
+ // Cause other evaluators expect Long instead of Integer
+ return new Long(((Collection<?>)result).size());
+ }
+
+ throw new IOException(String.format(Locale.ROOT, "Unable to find %s(...) because the value is not a collection, instead a %s was found", constructingFactory.getFunctionName(getClass()), result.getClass().getSimpleName()));
}
@Override
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/f1695104/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/eval/LengthEvaluatorTest.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/eval/LengthEvaluatorTest.java b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/eval/LengthEvaluatorTest.java
new file mode 100644
index 0000000..4b137b5
--- /dev/null
+++ b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/eval/LengthEvaluatorTest.java
@@ -0,0 +1,119 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.solr.client.solrj.io.stream.eval;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.Map;
+
+import org.apache.lucene.util.LuceneTestCase;
+import org.apache.solr.client.solrj.io.Tuple;
+import org.apache.solr.client.solrj.io.eval.LengthEvaluator;
+import org.apache.solr.client.solrj.io.eval.SequenceEvaluator;
+import org.apache.solr.client.solrj.io.eval.StreamEvaluator;
+import org.apache.solr.client.solrj.io.stream.expr.StreamFactory;
+import org.junit.Test;
+
+import junit.framework.Assert;
+
+public class LengthEvaluatorTest extends LuceneTestCase {
+
+ StreamFactory factory;
+ Map<String, Object> values;
+
+ public LengthEvaluatorTest() {
+ super();
+
+ factory = new StreamFactory()
+ .withFunctionName("length", LengthEvaluator.class)
+ .withFunctionName("sequence", SequenceEvaluator.class);
+ values = new HashMap<String,Object>();
+ }
+
+ @Test
+ public void lengthField() throws Exception{
+ StreamEvaluator evaluator = factory.constructEvaluator("length(a)");
+ Object result;
+
+ values.clear();
+ values.put("a", new ArrayList<Integer>(){{ add(1); add(2); add(4); }});
+ result = evaluator.evaluate(new Tuple(values));
+ Assert.assertTrue(result instanceof Long);
+ Assert.assertEquals(3L, result);
+
+ values.clear();
+ values.put("a", new ArrayList<String>(){{ add("a"); add("b"); }});
+ result = evaluator.evaluate(new Tuple(values));
+ Assert.assertTrue(result instanceof Long);
+ Assert.assertEquals(2L, result);
+
+ values.clear();
+ values.put("a", new ArrayList<String>(){{ }});
+ result = evaluator.evaluate(new Tuple(values));
+ Assert.assertTrue(result instanceof Long);
+ Assert.assertEquals(0L, result);
+ }
+
+ @Test
+ public void lengthEvaluator() throws Exception{
+ StreamEvaluator evaluator = factory.constructEvaluator("length(sequence(3,4,10))");
+ Object result;
+
+ values.clear();
+ result = evaluator.evaluate(new Tuple(values));
+ Assert.assertTrue(result instanceof Long);
+ Assert.assertEquals(3L, result);
+ }
+
+ @Test(expected = IOException.class)
+ public void lengthValueNotCollection() throws Exception{
+ StreamEvaluator evaluator = factory.constructEvaluator("length(a)");
+
+ values.clear();
+ values.put("a", "foo");
+ evaluator.evaluate(new Tuple(values));
+ }
+
+ @Test(expected = IOException.class)
+ public void lengthNoField() throws Exception{
+ factory.constructEvaluator("length()");
+ }
+
+ @Test(expected = IOException.class)
+ public void lengthTwoFields() throws Exception{
+ factory.constructEvaluator("length(a,b)");
+ }
+
+ @Test(expected = IOException.class)
+ public void lengthNoValue() throws Exception{
+ StreamEvaluator evaluator = factory.constructEvaluator("length(a)");
+
+ values.clear();
+ Object result = evaluator.evaluate(new Tuple(values));
+ assertNull(result);
+ }
+ @Test(expected = IOException.class)
+ public void lengthNullValue() throws Exception{
+ StreamEvaluator evaluator = factory.constructEvaluator("length(a)");
+
+ values.clear();
+ values.put("a", null);
+ Object result = evaluator.evaluate(new Tuple(values));
+ assertNull(result);
+ }
+}
[44/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt
new file mode 100644
index 0000000..046829d
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt
@@ -0,0 +1,125 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Cleaned on October 11, 2009 (not normalized, so use before normalization)
+# This means that when modifying this list, you might need to add some
+# redundant entries, for example containing forms with both أ and ا
+من
+ومن
+منها
+منه
+في
+وفي
+فيها
+فيه
+و
+ف
+ثم
+او
+أو
+ب
+بها
+به
+ا
+أ
+اى
+اي
+أي
+أى
+لا
+ولا
+الا
+ألا
+إلا
+لكن
+ما
+وما
+كما
+فما
+عن
+مع
+اذا
+إذا
+ان
+أن
+إن
+انها
+أنها
+إنها
+انه
+أنه
+إنه
+بان
+بأن
+فان
+فأن
+وان
+وأن
+وإن
+التى
+التي
+الذى
+الذي
+الذين
+الى
+الي
+إلى
+إلي
+على
+عليها
+عليه
+اما
+أما
+إما
+ايضا
+أيضا
+كل
+وكل
+لم
+ولم
+لن
+ولن
+هى
+هي
+هو
+وهى
+وهي
+وهو
+فهى
+فهي
+فهو
+انت
+أنت
+لك
+لها
+له
+هذه
+هذا
+تلك
+ذلك
+هناك
+كانت
+كان
+يكون
+تكون
+وكانت
+وكان
+غير
+بعض
+قد
+نحو
+بين
+بينما
+منذ
+ضمن
+حيث
+الان
+الآن
+خلال
+بعد
+قبل
+حتى
+عند
+عندما
+لدى
+جميع
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt
new file mode 100644
index 0000000..1ae4ba2
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt
@@ -0,0 +1,193 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+а
+аз
+ако
+ала
+бе
+без
+беше
+би
+бил
+била
+били
+било
+близо
+бъдат
+бъде
+бяха
+в
+вас
+ваш
+ваша
+вероятно
+вече
+взема
+ви
+вие
+винаги
+все
+всеки
+всички
+всичко
+всяка
+във
+въпреки
+върху
+г
+ги
+главно
+го
+д
+да
+дали
+до
+докато
+докога
+дори
+досега
+доста
+е
+едва
+един
+ето
+за
+зад
+заедно
+заради
+засега
+затова
+защо
+защото
+и
+из
+или
+им
+има
+имат
+иска
+й
+каза
+как
+каква
+какво
+както
+какъв
+като
+кога
+когато
+което
+които
+кой
+който
+колко
+която
+къде
+където
+към
+ли
+м
+ме
+между
+мен
+ми
+мнозина
+мога
+могат
+може
+моля
+момента
+му
+н
+на
+над
+назад
+най
+направи
+напред
+например
+нас
+не
+него
+нея
+ни
+ние
+никой
+нито
+но
+някои
+някой
+няма
+обаче
+около
+освен
+особено
+от
+отгоре
+отново
+още
+пак
+по
+повече
+повечето
+под
+поне
+поради
+после
+почти
+прави
+пред
+преди
+през
+при
+пък
+първо
+с
+са
+само
+се
+сега
+си
+скоро
+след
+сме
+според
+сред
+срещу
+сте
+съм
+със
+също
+т
+тази
+така
+такива
+такъв
+там
+твой
+те
+тези
+ти
+тн
+то
+това
+тогава
+този
+той
+толкова
+точно
+трябва
+тук
+тъй
+тя
+тях
+у
+харесва
+ч
+че
+често
+чрез
+ще
+щом
+я
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt
new file mode 100644
index 0000000..3da65de
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt
@@ -0,0 +1,220 @@
+# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
+a
+abans
+ací
+ah
+així
+això
+al
+als
+aleshores
+algun
+alguna
+algunes
+alguns
+alhora
+allà
+allí
+allò
+altra
+altre
+altres
+amb
+ambdós
+ambdues
+apa
+aquell
+aquella
+aquelles
+aquells
+aquest
+aquesta
+aquestes
+aquests
+aquí
+baix
+cada
+cadascú
+cadascuna
+cadascunes
+cadascuns
+com
+contra
+d'un
+d'una
+d'unes
+d'uns
+dalt
+de
+del
+dels
+des
+després
+dins
+dintre
+donat
+doncs
+durant
+e
+eh
+el
+els
+em
+en
+encara
+ens
+entre
+érem
+eren
+éreu
+es
+és
+esta
+està
+estàvem
+estaven
+estàveu
+esteu
+et
+etc
+ets
+fins
+fora
+gairebé
+ha
+han
+has
+havia
+he
+hem
+heu
+hi
+ho
+i
+igual
+iguals
+ja
+l'hi
+la
+les
+li
+li'n
+llavors
+m'he
+ma
+mal
+malgrat
+mateix
+mateixa
+mateixes
+mateixos
+me
+mentre
+més
+meu
+meus
+meva
+meves
+molt
+molta
+moltes
+molts
+mon
+mons
+n'he
+n'hi
+ne
+ni
+no
+nogensmenys
+només
+nosaltres
+nostra
+nostre
+nostres
+o
+oh
+oi
+on
+pas
+pel
+pels
+per
+però
+perquè
+poc
+poca
+pocs
+poques
+potser
+propi
+qual
+quals
+quan
+quant
+que
+què
+quelcom
+qui
+quin
+quina
+quines
+quins
+s'ha
+s'han
+sa
+semblant
+semblants
+ses
+seu
+seus
+seva
+seva
+seves
+si
+sobre
+sobretot
+sóc
+solament
+sols
+son
+són
+sons
+sota
+sou
+t'ha
+t'han
+t'he
+ta
+tal
+també
+tampoc
+tan
+tant
+tanta
+tantes
+teu
+teus
+teva
+teves
+ton
+tons
+tot
+tota
+totes
+tots
+un
+una
+unes
+uns
+us
+va
+vaig
+vam
+van
+vas
+veu
+vosaltres
+vostra
+vostre
+vostres
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt
new file mode 100644
index 0000000..53c6097
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt
@@ -0,0 +1,172 @@
+a
+s
+k
+o
+i
+u
+v
+z
+dnes
+cz
+tímto
+budeš
+budem
+byli
+jseš
+můj
+svým
+ta
+tomto
+tohle
+tuto
+tyto
+jej
+zda
+proč
+máte
+tato
+kam
+tohoto
+kdo
+kteří
+mi
+nám
+tom
+tomuto
+mít
+nic
+proto
+kterou
+byla
+toho
+protože
+asi
+ho
+naši
+napište
+re
+což
+tím
+takže
+svých
+její
+svými
+jste
+aj
+tu
+tedy
+teto
+bylo
+kde
+ke
+pravé
+ji
+nad
+nejsou
+či
+pod
+téma
+mezi
+přes
+ty
+pak
+vám
+ani
+když
+však
+neg
+jsem
+tento
+článku
+články
+aby
+jsme
+před
+pta
+jejich
+byl
+ještě
+až
+bez
+také
+pouze
+první
+vaše
+která
+nás
+nový
+tipy
+pokud
+může
+strana
+jeho
+své
+jiné
+zprávy
+nové
+není
+vás
+jen
+podle
+zde
+už
+být
+více
+bude
+již
+než
+který
+by
+které
+co
+nebo
+ten
+tak
+má
+při
+od
+po
+jsou
+jak
+další
+ale
+si
+se
+ve
+to
+jako
+za
+zpět
+ze
+do
+pro
+je
+na
+atd
+atp
+jakmile
+přičemž
+já
+on
+ona
+ono
+oni
+ony
+my
+vy
+jí
+ji
+mě
+mne
+jemu
+tomu
+těm
+těmu
+němu
+němuž
+jehož
+jíž
+jelikož
+jež
+jakož
+načež
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt
new file mode 100644
index 0000000..42e6145
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt
@@ -0,0 +1,110 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Danish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+
+og | and
+i | in
+jeg | I
+det | that (dem. pronoun)/it (pers. pronoun)
+at | that (in front of a sentence)/to (with infinitive)
+en | a/an
+den | it (pers. pronoun)/that (dem. pronoun)
+til | to/at/for/until/against/by/of/into, more
+er | present tense of "to be"
+som | who, as
+på | on/upon/in/on/at/to/after/of/with/for, on
+de | they
+med | with/by/in, along
+han | he
+af | of/by/from/off/for/in/with/on, off
+for | at/for/to/from/by/of/ago, in front/before, because
+ikke | not
+der | who/which, there/those
+var | past tense of "to be"
+mig | me/myself
+sig | oneself/himself/herself/itself/themselves
+men | but
+et | a/an/one, one (number), someone/somebody/one
+har | present tense of "to have"
+om | round/about/for/in/a, about/around/down, if
+vi | we
+min | my
+havde | past tense of "to have"
+ham | him
+hun | she
+nu | now
+over | over/above/across/by/beyond/past/on/about, over/past
+da | then, when/as/since
+fra | from/off/since, off, since
+du | you
+ud | out
+sin | his/her/its/one's
+dem | them
+os | us/ourselves
+op | up
+man | you/one
+hans | his
+hvor | where
+eller | or
+hvad | what
+skal | must/shall etc.
+selv | myself/youself/herself/ourselves etc., even
+her | here
+alle | all/everyone/everybody etc.
+vil | will (verb)
+blev | past tense of "to stay/to remain/to get/to become"
+kunne | could
+ind | in
+når | when
+være | present tense of "to be"
+dog | however/yet/after all
+noget | something
+ville | would
+jo | you know/you see (adv), yes
+deres | their/theirs
+efter | after/behind/according to/for/by/from, later/afterwards
+ned | down
+skulle | should
+denne | this
+end | than
+dette | this
+mit | my/mine
+også | also
+under | under/beneath/below/during, below/underneath
+have | have
+dig | you
+anden | other
+hende | her
+mine | my
+alt | everything
+meget | much/very, plenty of
+sit | his, her, its, one's
+sine | his, her, its, one's
+vor | our
+mod | against
+disse | these
+hvis | if
+din | your/yours
+nogle | some
+hos | by/at
+blive | be/become
+mange | many
+ad | by/through
+bliver | present tense of "to be/to become"
+hendes | her/hers
+været | be
+thi | for (conj)
+jer | you
+sådan | such, like this/like that
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt
new file mode 100644
index 0000000..86525e7
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt
@@ -0,0 +1,294 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A German stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | The number of forms in this list is reduced significantly by passing it
+ | through the German stemmer.
+
+
+aber | but
+
+alle | all
+allem
+allen
+aller
+alles
+
+als | than, as
+also | so
+am | an + dem
+an | at
+
+ander | other
+andere
+anderem
+anderen
+anderer
+anderes
+anderm
+andern
+anderr
+anders
+
+auch | also
+auf | on
+aus | out of
+bei | by
+bin | am
+bis | until
+bist | art
+da | there
+damit | with it
+dann | then
+
+der | the
+den
+des
+dem
+die
+das
+
+daß | that
+
+derselbe | the same
+derselben
+denselben
+desselben
+demselben
+dieselbe
+dieselben
+dasselbe
+
+dazu | to that
+
+dein | thy
+deine
+deinem
+deinen
+deiner
+deines
+
+denn | because
+
+derer | of those
+dessen | of him
+
+dich | thee
+dir | to thee
+du | thou
+
+dies | this
+diese
+diesem
+diesen
+dieser
+dieses
+
+
+doch | (several meanings)
+dort | (over) there
+
+
+durch | through
+
+ein | a
+eine
+einem
+einen
+einer
+eines
+
+einig | some
+einige
+einigem
+einigen
+einiger
+einiges
+
+einmal | once
+
+er | he
+ihn | him
+ihm | to him
+
+es | it
+etwas | something
+
+euer | your
+eure
+eurem
+euren
+eurer
+eures
+
+für | for
+gegen | towards
+gewesen | p.p. of sein
+hab | have
+habe | have
+haben | have
+hat | has
+hatte | had
+hatten | had
+hier | here
+hin | there
+hinter | behind
+
+ich | I
+mich | me
+mir | to me
+
+
+ihr | you, to her
+ihre
+ihrem
+ihren
+ihrer
+ihres
+euch | to you
+
+im | in + dem
+in | in
+indem | while
+ins | in + das
+ist | is
+
+jede | each, every
+jedem
+jeden
+jeder
+jedes
+
+jene | that
+jenem
+jenen
+jener
+jenes
+
+jetzt | now
+kann | can
+
+kein | no
+keine
+keinem
+keinen
+keiner
+keines
+
+können | can
+könnte | could
+machen | do
+man | one
+
+manche | some, many a
+manchem
+manchen
+mancher
+manches
+
+mein | my
+meine
+meinem
+meinen
+meiner
+meines
+
+mit | with
+muss | must
+musste | had to
+nach | to(wards)
+nicht | not
+nichts | nothing
+noch | still, yet
+nun | now
+nur | only
+ob | whether
+oder | or
+ohne | without
+sehr | very
+
+sein | his
+seine
+seinem
+seinen
+seiner
+seines
+
+selbst | self
+sich | herself
+
+sie | they, she
+ihnen | to them
+
+sind | are
+so | so
+
+solche | such
+solchem
+solchen
+solcher
+solches
+
+soll | shall
+sollte | should
+sondern | but
+sonst | else
+über | over
+um | about, around
+und | and
+
+uns | us
+unse
+unsem
+unsen
+unser
+unses
+
+unter | under
+viel | much
+vom | von + dem
+von | from
+vor | before
+während | while
+war | was
+waren | were
+warst | wast
+was | what
+weg | away, off
+weil | because
+weiter | further
+
+welche | which
+welchem
+welchen
+welcher
+welches
+
+wenn | when
+werde | will
+werden | will
+wie | how
+wieder | again
+will | want
+wir | we
+wird | will
+wirst | willst
+wo | where
+wollen | want
+wollte | wanted
+würde | would
+würden | would
+zu | to
+zum | zu + dem
+zur | zu + der
+zwar | indeed
+zwischen | between
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt
new file mode 100644
index 0000000..232681f
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt
@@ -0,0 +1,78 @@
+# Lucene Greek Stopwords list
+# Note: by default this file is used after GreekLowerCaseFilter,
+# so when modifying this file use 'σ' instead of 'ς'
+ο
+η
+το
+οι
+τα
+του
+τησ
+των
+τον
+την
+και
+κι
+κ
+ειμαι
+εισαι
+ειναι
+ειμαστε
+ειστε
+στο
+στον
+στη
+στην
+μα
+αλλα
+απο
+για
+προσ
+με
+σε
+ωσ
+παρα
+αντι
+κατα
+μετα
+θα
+να
+δε
+δεν
+μη
+μην
+επι
+ενω
+εαν
+αν
+τοτε
+που
+πωσ
+ποιοσ
+ποια
+ποιο
+ποιοι
+ποιεσ
+ποιων
+ποιουσ
+αυτοσ
+αυτη
+αυτο
+αυτοι
+αυτων
+αυτουσ
+αυτεσ
+αυτα
+εκεινοσ
+εκεινη
+εκεινο
+εκεινοι
+εκεινεσ
+εκεινα
+εκεινων
+εκεινουσ
+οπωσ
+ομωσ
+ισωσ
+οσο
+οτι
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_en.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_en.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_en.txt
new file mode 100644
index 0000000..2c164c0
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_en.txt
@@ -0,0 +1,54 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+# Standard english stop words taken from Lucene's StopAnalyzer
+a
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+of
+on
+or
+such
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt
new file mode 100644
index 0000000..487d78c
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt
@@ -0,0 +1,356 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Spanish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | from, of
+la | the, her
+que | who, that
+el | the
+en | in
+y | and
+a | to
+los | the, them
+del | de + el
+se | himself, from him etc
+las | the, them
+por | for, by, etc
+un | a
+para | for
+con | with
+no | no
+una | a
+su | his, her
+al | a + el
+ | es from SER
+lo | him
+como | how
+más | more
+pero | pero
+sus | su plural
+le | to him, her
+ya | already
+o | or
+ | fue from SER
+este | this
+ | ha from HABER
+sí | himself etc
+porque | because
+esta | this
+ | son from SER
+entre | between
+ | está from ESTAR
+cuando | when
+muy | very
+sin | without
+sobre | on
+ | ser from SER
+ | tiene from TENER
+también | also
+me | me
+hasta | until
+hay | there is/are
+donde | where
+ | han from HABER
+quien | whom, that
+ | están from ESTAR
+ | estado from ESTAR
+desde | from
+todo | all
+nos | us
+durante | during
+ | estados from ESTAR
+todos | all
+uno | a
+les | to them
+ni | nor
+contra | against
+otros | other
+ | fueron from SER
+ese | that
+eso | that
+ | había from HABER
+ante | before
+ellos | they
+e | and (variant of y)
+esto | this
+mí | me
+antes | before
+algunos | some
+qué | what?
+unos | a
+yo | I
+otro | other
+otras | other
+otra | other
+él | he
+tanto | so much, many
+esa | that
+estos | these
+mucho | much, many
+quienes | who
+nada | nothing
+muchos | many
+cual | who
+ | sea from SER
+poco | few
+ella | she
+estar | to be
+ | haber from HABER
+estas | these
+ | estaba from ESTAR
+ | estamos from ESTAR
+algunas | some
+algo | something
+nosotros | we
+
+ | other forms
+
+mi | me
+mis | mi plural
+tú | thou
+te | thee
+ti | thee
+tu | thy
+tus | tu plural
+ellas | they
+nosotras | we
+vosotros | you
+vosotras | you
+os | you
+mío | mine
+mía |
+míos |
+mías |
+tuyo | thine
+tuya |
+tuyos |
+tuyas |
+suyo | his, hers, theirs
+suya |
+suyos |
+suyas |
+nuestro | ours
+nuestra |
+nuestros |
+nuestras |
+vuestro | yours
+vuestra |
+vuestros |
+vuestras |
+esos | those
+esas | those
+
+ | forms of estar, to be (not including the infinitive):
+estoy
+estás
+está
+estamos
+estáis
+están
+esté
+estés
+estemos
+estéis
+estén
+estaré
+estarás
+estará
+estaremos
+estaréis
+estarán
+estaría
+estarías
+estaríamos
+estaríais
+estarían
+estaba
+estabas
+estábamos
+estabais
+estaban
+estuve
+estuviste
+estuvo
+estuvimos
+estuvisteis
+estuvieron
+estuviera
+estuvieras
+estuviéramos
+estuvierais
+estuvieran
+estuviese
+estuvieses
+estuviésemos
+estuvieseis
+estuviesen
+estando
+estado
+estada
+estados
+estadas
+estad
+
+ | forms of haber, to have (not including the infinitive):
+he
+has
+ha
+hemos
+habéis
+han
+haya
+hayas
+hayamos
+hayáis
+hayan
+habré
+habrás
+habrá
+habremos
+habréis
+habrán
+habría
+habrías
+habríamos
+habríais
+habrían
+había
+habías
+habíamos
+habíais
+habían
+hube
+hubiste
+hubo
+hubimos
+hubisteis
+hubieron
+hubiera
+hubieras
+hubiéramos
+hubierais
+hubieran
+hubiese
+hubieses
+hubiésemos
+hubieseis
+hubiesen
+habiendo
+habido
+habida
+habidos
+habidas
+
+ | forms of ser, to be (not including the infinitive):
+soy
+eres
+es
+somos
+sois
+son
+sea
+seas
+seamos
+seáis
+sean
+seré
+serás
+será
+seremos
+seréis
+serán
+sería
+serías
+seríamos
+seríais
+serían
+era
+eras
+éramos
+erais
+eran
+fui
+fuiste
+fue
+fuimos
+fuisteis
+fueron
+fuera
+fueras
+fuéramos
+fuerais
+fueran
+fuese
+fueses
+fuésemos
+fueseis
+fuesen
+siendo
+sido
+ | sed also means 'thirst'
+
+ | forms of tener, to have (not including the infinitive):
+tengo
+tienes
+tiene
+tenemos
+tenéis
+tienen
+tenga
+tengas
+tengamos
+tengáis
+tengan
+tendré
+tendrás
+tendrá
+tendremos
+tendréis
+tendrán
+tendría
+tendrías
+tendríamos
+tendríais
+tendrían
+tenía
+tenías
+teníamos
+teníais
+tenían
+tuve
+tuviste
+tuvo
+tuvimos
+tuvisteis
+tuvieron
+tuviera
+tuvieras
+tuviéramos
+tuvierais
+tuvieran
+tuviese
+tuvieses
+tuviésemos
+tuvieseis
+tuviesen
+teniendo
+tenido
+tenida
+tenidos
+tenidas
+tened
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt
new file mode 100644
index 0000000..25f1db9
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt
@@ -0,0 +1,99 @@
+# example set of basque stopwords
+al
+anitz
+arabera
+asko
+baina
+bat
+batean
+batek
+bati
+batzuei
+batzuek
+batzuetan
+batzuk
+bera
+beraiek
+berau
+berauek
+bere
+berori
+beroriek
+beste
+bezala
+da
+dago
+dira
+ditu
+du
+dute
+edo
+egin
+ere
+eta
+eurak
+ez
+gainera
+gu
+gutxi
+guzti
+haiei
+haiek
+haietan
+hainbeste
+hala
+han
+handik
+hango
+hara
+hari
+hark
+hartan
+hau
+hauei
+hauek
+hauetan
+hemen
+hemendik
+hemengo
+hi
+hona
+honek
+honela
+honetan
+honi
+hor
+hori
+horiei
+horiek
+horietan
+horko
+horra
+horrek
+horrela
+horretan
+horri
+hortik
+hura
+izan
+ni
+noiz
+nola
+non
+nondik
+nongo
+nor
+nora
+ze
+zein
+zen
+zenbait
+zenbat
+zer
+zergatik
+ziren
+zituen
+zu
+zuek
+zuen
+zuten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt
new file mode 100644
index 0000000..723641c
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt
@@ -0,0 +1,313 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Note: by default this file is used after normalization, so when adding entries
+# to this file, use the arabic 'ي' instead of 'ی'
+انان
+نداشته
+سراسر
+خياه
+ايشان
+وي
+تاكنون
+بيشتري
+دوم
+پس
+ناشي
+وگو
+يا
+داشتند
+سپس
+هنگام
+هرگز
+پنج
+نشان
+امسال
+ديگر
+گروهي
+شدند
+چطور
+ده
+و
+دو
+نخستين
+ولي
+چرا
+چه
+وسط
+ه
+كدام
+قابل
+يك
+رفت
+هفت
+همچنين
+در
+هزار
+بله
+بلي
+شايد
+اما
+شناسي
+گرفته
+دهد
+داشته
+دانست
+داشتن
+خواهيم
+ميليارد
+وقتيكه
+امد
+خواهد
+جز
+اورده
+شده
+بلكه
+خدمات
+شدن
+برخي
+نبود
+بسياري
+جلوگيري
+حق
+كردند
+نوعي
+بعري
+نكرده
+نظير
+نبايد
+بوده
+بودن
+داد
+اورد
+هست
+جايي
+شود
+دنبال
+داده
+بايد
+سابق
+هيچ
+همان
+انجا
+كمتر
+كجاست
+گردد
+كسي
+تر
+مردم
+تان
+دادن
+بودند
+سري
+جدا
+ندارند
+مگر
+يكديگر
+دارد
+دهند
+بنابراين
+هنگامي
+سمت
+جا
+انچه
+خود
+دادند
+زياد
+دارند
+اثر
+بدون
+بهترين
+بيشتر
+البته
+به
+براساس
+بيرون
+كرد
+بعضي
+گرفت
+توي
+اي
+ميليون
+او
+جريان
+تول
+بر
+مانند
+برابر
+باشيم
+مدتي
+گويند
+اكنون
+تا
+تنها
+جديد
+چند
+بي
+نشده
+كردن
+كردم
+گويد
+كرده
+كنيم
+نمي
+نزد
+روي
+قصد
+فقط
+بالاي
+ديگران
+اين
+ديروز
+توسط
+سوم
+ايم
+دانند
+سوي
+استفاده
+شما
+كنار
+داريم
+ساخته
+طور
+امده
+رفته
+نخست
+بيست
+نزديك
+طي
+كنيد
+از
+انها
+تمامي
+داشت
+يكي
+طريق
+اش
+چيست
+روب
+نمايد
+گفت
+چندين
+چيزي
+تواند
+ام
+ايا
+با
+ان
+ايد
+ترين
+اينكه
+ديگري
+راه
+هايي
+بروز
+همچنان
+پاعين
+كس
+حدود
+مختلف
+مقابل
+چيز
+گيرد
+ندارد
+ضد
+همچون
+سازي
+شان
+مورد
+باره
+مرسي
+خويش
+برخوردار
+چون
+خارج
+شش
+هنوز
+تحت
+ضمن
+هستيم
+گفته
+فكر
+بسيار
+پيش
+براي
+روزهاي
+انكه
+نخواهد
+بالا
+كل
+وقتي
+كي
+چنين
+كه
+گيري
+نيست
+است
+كجا
+كند
+نيز
+يابد
+بندي
+حتي
+توانند
+عقب
+خواست
+كنند
+بين
+تمام
+همه
+ما
+باشند
+مثل
+شد
+اري
+باشد
+اره
+طبق
+بعد
+اگر
+صورت
+غير
+جاي
+بيش
+ريزي
+اند
+زيرا
+چگونه
+بار
+لطفا
+مي
+درباره
+من
+ديده
+همين
+گذاري
+برداري
+علت
+گذاشته
+هم
+فوق
+نه
+ها
+شوند
+اباد
+همواره
+هر
+اول
+خواهند
+چهار
+نام
+امروز
+مان
+هاي
+قبل
+كنم
+سعي
+تازه
+را
+هستند
+زير
+جلوي
+عنوان
+بود
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt
new file mode 100644
index 0000000..4372c9a
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt
@@ -0,0 +1,97 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+| forms of BE
+
+olla
+olen
+olet
+on
+olemme
+olette
+ovat
+ole | negative form
+
+oli
+olisi
+olisit
+olisin
+olisimme
+olisitte
+olisivat
+olit
+olin
+olimme
+olitte
+olivat
+ollut
+olleet
+
+en | negation
+et
+ei
+emme
+ette
+eivät
+
+|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
+minä minun minut minua minussa minusta minuun minulla minulta minulle | I
+sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
+hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she
+me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we
+te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you
+he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they
+
+tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this
+tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
+se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it
+nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these
+nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
+ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they
+
+kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
+ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl)
+mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what
+mitkä | (pl)
+
+joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which
+jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl)
+
+| conjunctions
+
+että | that
+ja | and
+jos | if
+koska | because
+kuin | than
+mutta | but
+niin | so
+sekä | and
+sillä | for
+tai | or
+vaan | but
+vai | or
+vaikka | although
+
+
+| prepositions
+
+kanssa | with
+mukaan | according to
+noin | about
+poikki | across
+yli | over, across
+
+| other
+
+kun | when
+niin | so
+nyt | now
+itse | self
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt
new file mode 100644
index 0000000..749abae
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt
@@ -0,0 +1,186 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A French stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+au | a + le
+aux | a + les
+avec | with
+ce | this
+ces | these
+dans | with
+de | of
+des | de + les
+du | de + le
+elle | she
+en | `of them' etc
+et | and
+eux | them
+il | he
+je | I
+la | the
+le | the
+leur | their
+lui | him
+ma | my (fem)
+mais | but
+me | me
+même | same; as in moi-même (myself) etc
+mes | me (pl)
+moi | me
+mon | my (masc)
+ne | not
+nos | our (pl)
+notre | our
+nous | we
+on | one
+ou | where
+par | by
+pas | not
+pour | for
+qu | que before vowel
+que | that
+qui | who
+sa | his, her (fem)
+se | oneself
+ses | his (pl)
+son | his, her (masc)
+sur | on
+ta | thy (fem)
+te | thee
+tes | thy (pl)
+toi | thee
+ton | thy (masc)
+tu | thou
+un | a
+une | a
+vos | your (pl)
+votre | your
+vous | you
+
+ | single letter forms
+
+c | c'
+d | d'
+j | j'
+l | l'
+à | to, at
+m | m'
+n | n'
+s | s'
+t | t'
+y | there
+
+ | forms of être (not including the infinitive):
+été
+étée
+étées
+étés
+étant
+suis
+es
+est
+sommes
+êtes
+sont
+serai
+seras
+sera
+serons
+serez
+seront
+serais
+serait
+serions
+seriez
+seraient
+étais
+était
+étions
+étiez
+étaient
+fus
+fut
+fûmes
+fûtes
+furent
+sois
+soit
+soyons
+soyez
+soient
+fusse
+fusses
+fût
+fussions
+fussiez
+fussent
+
+ | forms of avoir (not including the infinitive):
+ayant
+eu
+eue
+eues
+eus
+ai
+as
+avons
+avez
+ont
+aurai
+auras
+aura
+aurons
+aurez
+auront
+aurais
+aurait
+aurions
+auriez
+auraient
+avais
+avait
+avions
+aviez
+avaient
+eut
+eûmes
+eûtes
+eurent
+aie
+aies
+ait
+ayons
+ayez
+aient
+eusse
+eusses
+eût
+eussions
+eussiez
+eussent
+
+ | Later additions (from Jean-Christophe Deschamps)
+ceci | this
+cela | that
+celà | that
+cet | this
+cette | this
+ici | here
+ils | they
+les | the (pl)
+leurs | their (pl)
+quel | which
+quels | which
+quelle | which
+quelles | which
+sans | without
+soi | oneself
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt
new file mode 100644
index 0000000..9ff88d7
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt
@@ -0,0 +1,110 @@
+
+a
+ach
+ag
+agus
+an
+aon
+ar
+arna
+as
+b'
+ba
+beirt
+bhúr
+caoga
+ceathair
+ceathrar
+chomh
+chtó
+chuig
+chun
+cois
+céad
+cúig
+cúigear
+d'
+daichead
+dar
+de
+deich
+deichniúr
+den
+dhá
+do
+don
+dtí
+dá
+dár
+dó
+faoi
+faoin
+faoina
+faoinár
+fara
+fiche
+gach
+gan
+go
+gur
+haon
+hocht
+i
+iad
+idir
+in
+ina
+ins
+inár
+is
+le
+leis
+lena
+lenár
+m'
+mar
+mo
+mé
+na
+nach
+naoi
+naonúr
+ná
+ní
+níor
+nó
+nócha
+ocht
+ochtar
+os
+roimh
+sa
+seacht
+seachtar
+seachtó
+seasca
+seisear
+siad
+sibh
+sinn
+sna
+sé
+sí
+tar
+thar
+thú
+triúr
+trí
+trína
+trínár
+tríocha
+tú
+um
+ár
+é
+éis
+í
+ó
+ón
+óna
+ónár
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt
new file mode 100644
index 0000000..d8760b1
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt
@@ -0,0 +1,161 @@
+# galican stopwords
+a
+aínda
+alí
+aquel
+aquela
+aquelas
+aqueles
+aquilo
+aquí
+ao
+aos
+as
+así
+á
+ben
+cando
+che
+co
+coa
+comigo
+con
+connosco
+contigo
+convosco
+coas
+cos
+cun
+cuns
+cunha
+cunhas
+da
+dalgunha
+dalgunhas
+dalgún
+dalgúns
+das
+de
+del
+dela
+delas
+deles
+desde
+deste
+do
+dos
+dun
+duns
+dunha
+dunhas
+e
+el
+ela
+elas
+eles
+en
+era
+eran
+esa
+esas
+ese
+eses
+esta
+estar
+estaba
+está
+están
+este
+estes
+estiven
+estou
+eu
+é
+facer
+foi
+foron
+fun
+había
+hai
+iso
+isto
+la
+las
+lle
+lles
+lo
+los
+mais
+me
+meu
+meus
+min
+miña
+miñas
+moi
+na
+nas
+neste
+nin
+no
+non
+nos
+nosa
+nosas
+noso
+nosos
+nós
+nun
+nunha
+nuns
+nunhas
+o
+os
+ou
+ó
+ós
+para
+pero
+pode
+pois
+pola
+polas
+polo
+polos
+por
+que
+se
+senón
+ser
+seu
+seus
+sexa
+sido
+sobre
+súa
+súas
+tamén
+tan
+te
+ten
+teñen
+teño
+ter
+teu
+teus
+ti
+tido
+tiña
+tiven
+túa
+túas
+un
+unha
+unhas
+uns
+vos
+vosa
+vosas
+voso
+vosos
+vós
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt
new file mode 100644
index 0000000..86286bb
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt
@@ -0,0 +1,235 @@
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# Note: by default this file also contains forms normalized by HindiNormalizer
+# for spelling variation (see section below), such that it can be used whether or
+# not you enable that feature. When adding additional entries to this list,
+# please add the normalized form as well.
+अंदर
+अत
+अपना
+अपनी
+अपने
+अभी
+आदि
+आप
+इत्यादि
+इन
+इनका
+इन्हीं
+इन्हें
+इन्हों
+इस
+इसका
+इसकी
+इसके
+इसमें
+इसी
+इसे
+उन
+उनका
+उनकी
+उनके
+उनको
+उन्हीं
+उन्हें
+उन्हों
+उस
+उसके
+उसी
+उसे
+एक
+एवं
+एस
+ऐसे
+और
+कई
+कर
+करता
+करते
+करना
+करने
+करें
+कहते
+कहा
+का
+काफ़ी
+कि
+कितना
+किन्हें
+किन्हों
+किया
+किर
+किस
+किसी
+किसे
+की
+कुछ
+कुल
+के
+को
+कोई
+कौन
+कौनसा
+गया
+घर
+जब
+जहाँ
+जा
+जितना
+जिन
+जिन्हें
+जिन्हों
+जिस
+जिसे
+जीधर
+जैसा
+जैसे
+जो
+तक
+तब
+तरह
+तिन
+तिन्हें
+तिन्हों
+तिस
+तिसे
+तो
+था
+थी
+थे
+दबारा
+दिया
+दुसरा
+दूसरे
+दो
+द्वारा
+न
+नहीं
+ना
+निहायत
+नीचे
+ने
+पर
+पर
+पहले
+पूरा
+पे
+फिर
+बनी
+बही
+बहुत
+बाद
+बाला
+बिलकुल
+भी
+भीतर
+मगर
+मानो
+मे
+में
+यदि
+यह
+यहाँ
+यही
+या
+यिह
+ये
+रखें
+रहा
+रहे
+ऱ्वासा
+लिए
+लिये
+लेकिन
+व
+वर्ग
+वह
+वह
+वहाँ
+वहीं
+वाले
+वुह
+वे
+वग़ैरह
+संग
+सकता
+सकते
+सबसे
+सभी
+साथ
+साबुत
+साभ
+सारा
+से
+सो
+ही
+हुआ
+हुई
+हुए
+है
+हैं
+हो
+होता
+होती
+होते
+होना
+होने
+# additional normalized forms of the above
+अपनि
+जेसे
+होति
+सभि
+तिंहों
+इंहों
+दवारा
+इसि
+किंहें
+थि
+उंहों
+ओर
+जिंहें
+वहिं
+अभि
+बनि
+हि
+उंहिं
+उंहें
+हें
+वगेरह
+एसे
+रवासा
+कोन
+निचे
+काफि
+उसि
+पुरा
+भितर
+हे
+बहि
+वहां
+कोइ
+यहां
+जिंहों
+तिंहें
+किसि
+कइ
+यहि
+इंहिं
+जिधर
+इंहें
+अदि
+इतयादि
+हुइ
+कोनसा
+इसकि
+दुसरे
+जहां
+अप
+किंहों
+उनकि
+भि
+वरग
+हुअ
+जेसा
+नहिं
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt
new file mode 100644
index 0000000..37526da
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt
@@ -0,0 +1,211 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+| Hungarian stop word list
+| prepared by Anna Tordai
+
+a
+ahogy
+ahol
+aki
+akik
+akkor
+alatt
+által
+általában
+amely
+amelyek
+amelyekben
+amelyeket
+amelyet
+amelynek
+ami
+amit
+amolyan
+amíg
+amikor
+át
+abban
+ahhoz
+annak
+arra
+arról
+az
+azok
+azon
+azt
+azzal
+azért
+aztán
+azután
+azonban
+bár
+be
+belül
+benne
+cikk
+cikkek
+cikkeket
+csak
+de
+e
+eddig
+egész
+egy
+egyes
+egyetlen
+egyéb
+egyik
+egyre
+ekkor
+el
+elég
+ellen
+elő
+először
+előtt
+első
+én
+éppen
+ebben
+ehhez
+emilyen
+ennek
+erre
+ez
+ezt
+ezek
+ezen
+ezzel
+ezért
+és
+fel
+felé
+hanem
+hiszen
+hogy
+hogyan
+igen
+így
+illetve
+ill.
+ill
+ilyen
+ilyenkor
+ison
+ismét
+itt
+jó
+jól
+jobban
+kell
+kellett
+keresztül
+keressünk
+ki
+kívül
+között
+közül
+legalább
+lehet
+lehetett
+legyen
+lenne
+lenni
+lesz
+lett
+maga
+magát
+majd
+majd
+már
+más
+másik
+meg
+még
+mellett
+mert
+mely
+melyek
+mi
+mit
+míg
+miért
+milyen
+mikor
+minden
+mindent
+mindenki
+mindig
+mint
+mintha
+mivel
+most
+nagy
+nagyobb
+nagyon
+ne
+néha
+nekem
+neki
+nem
+néhány
+nélkül
+nincs
+olyan
+ott
+össze
+ő
+ők
+őket
+pedig
+persze
+rá
+s
+saját
+sem
+semmi
+sok
+sokat
+sokkal
+számára
+szemben
+szerint
+szinte
+talán
+tehát
+teljes
+tovább
+továbbá
+több
+úgy
+ugyanis
+új
+újabb
+újra
+után
+utána
+utolsó
+vagy
+vagyis
+valaki
+valami
+valamint
+való
+vagyok
+van
+vannak
+volt
+voltam
+voltak
+voltunk
+vissza
+vele
+viszont
+volna
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt
new file mode 100644
index 0000000..60c1c50
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt
@@ -0,0 +1,46 @@
+# example set of Armenian stopwords.
+այդ
+այլ
+այն
+այս
+դու
+դուք
+եմ
+են
+ենք
+ես
+եք
+է
+էի
+էին
+էինք
+էիր
+էիք
+էր
+ըստ
+թ
+ի
+ին
+իսկ
+իր
+կամ
+համար
+հետ
+հետո
+մենք
+մեջ
+մի
+ն
+նա
+նաև
+նրա
+նրանք
+որ
+որը
+որոնք
+որպես
+ու
+ում
+պիտի
+վրա
+և
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt
new file mode 100644
index 0000000..4617f83
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt
@@ -0,0 +1,359 @@
+# from appendix D of: A Study of Stemming Effects on Information
+# Retrieval in Bahasa Indonesia
+ada
+adanya
+adalah
+adapun
+agak
+agaknya
+agar
+akan
+akankah
+akhirnya
+aku
+akulah
+amat
+amatlah
+anda
+andalah
+antar
+diantaranya
+antara
+antaranya
+diantara
+apa
+apaan
+mengapa
+apabila
+apakah
+apalagi
+apatah
+atau
+ataukah
+ataupun
+bagai
+bagaikan
+sebagai
+sebagainya
+bagaimana
+bagaimanapun
+sebagaimana
+bagaimanakah
+bagi
+bahkan
+bahwa
+bahwasanya
+sebaliknya
+banyak
+sebanyak
+beberapa
+seberapa
+begini
+beginian
+beginikah
+beginilah
+sebegini
+begitu
+begitukah
+begitulah
+begitupun
+sebegitu
+belum
+belumlah
+sebelum
+sebelumnya
+sebenarnya
+berapa
+berapakah
+berapalah
+berapapun
+betulkah
+sebetulnya
+biasa
+biasanya
+bila
+bilakah
+bisa
+bisakah
+sebisanya
+boleh
+bolehkah
+bolehlah
+buat
+bukan
+bukankah
+bukanlah
+bukannya
+cuma
+percuma
+dahulu
+dalam
+dan
+dapat
+dari
+daripada
+dekat
+demi
+demikian
+demikianlah
+sedemikian
+dengan
+depan
+di
+dia
+dialah
+dini
+diri
+dirinya
+terdiri
+dong
+dulu
+enggak
+enggaknya
+entah
+entahlah
+terhadap
+terhadapnya
+hal
+hampir
+hanya
+hanyalah
+harus
+haruslah
+harusnya
+seharusnya
+hendak
+hendaklah
+hendaknya
+hingga
+sehingga
+ia
+ialah
+ibarat
+ingin
+inginkah
+inginkan
+ini
+inikah
+inilah
+itu
+itukah
+itulah
+jangan
+jangankan
+janganlah
+jika
+jikalau
+juga
+justru
+kala
+kalau
+kalaulah
+kalaupun
+kalian
+kami
+kamilah
+kamu
+kamulah
+kan
+kapan
+kapankah
+kapanpun
+dikarenakan
+karena
+karenanya
+ke
+kecil
+kemudian
+kenapa
+kepada
+kepadanya
+ketika
+seketika
+khususnya
+kini
+kinilah
+kiranya
+sekiranya
+kita
+kitalah
+kok
+lagi
+lagian
+selagi
+lah
+lain
+lainnya
+melainkan
+selaku
+lalu
+melalui
+terlalu
+lama
+lamanya
+selama
+selama
+selamanya
+lebih
+terlebih
+bermacam
+macam
+semacam
+maka
+makanya
+makin
+malah
+malahan
+mampu
+mampukah
+mana
+manakala
+manalagi
+masih
+masihkah
+semasih
+masing
+mau
+maupun
+semaunya
+memang
+mereka
+merekalah
+meski
+meskipun
+semula
+mungkin
+mungkinkah
+nah
+namun
+nanti
+nantinya
+nyaris
+oleh
+olehnya
+seorang
+seseorang
+pada
+padanya
+padahal
+paling
+sepanjang
+pantas
+sepantasnya
+sepantasnyalah
+para
+pasti
+pastilah
+per
+pernah
+pula
+pun
+merupakan
+rupanya
+serupa
+saat
+saatnya
+sesaat
+saja
+sajalah
+saling
+bersama
+sama
+sesama
+sambil
+sampai
+sana
+sangat
+sangatlah
+saya
+sayalah
+se
+sebab
+sebabnya
+sebuah
+tersebut
+tersebutlah
+sedang
+sedangkan
+sedikit
+sedikitnya
+segala
+segalanya
+segera
+sesegera
+sejak
+sejenak
+sekali
+sekalian
+sekalipun
+sesekali
+sekaligus
+sekarang
+sekarang
+sekitar
+sekitarnya
+sela
+selain
+selalu
+seluruh
+seluruhnya
+semakin
+sementara
+sempat
+semua
+semuanya
+sendiri
+sendirinya
+seolah
+seperti
+sepertinya
+sering
+seringnya
+serta
+siapa
+siapakah
+siapapun
+disini
+disinilah
+sini
+sinilah
+sesuatu
+sesuatunya
+suatu
+sesudah
+sesudahnya
+sudah
+sudahkah
+sudahlah
+supaya
+tadi
+tadinya
+tak
+tanpa
+setelah
+telah
+tentang
+tentu
+tentulah
+tentunya
+tertentu
+seterusnya
+tapi
+tetapi
+setiap
+tiap
+setidaknya
+tidak
+tidakkah
+tidaklah
+toh
+waduh
+wah
+wahai
+sewaktu
+walau
+walaupun
+wong
+yaitu
+yakni
+yang
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt
new file mode 100644
index 0000000..1219cc7
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt
@@ -0,0 +1,303 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | An Italian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ad | a (to) before vowel
+al | a + il
+allo | a + lo
+ai | a + i
+agli | a + gli
+all | a + l'
+agl | a + gl'
+alla | a + la
+alle | a + le
+con | with
+col | con + il
+coi | con + i (forms collo, cogli etc are now very rare)
+da | from
+dal | da + il
+dallo | da + lo
+dai | da + i
+dagli | da + gli
+dall | da + l'
+dagl | da + gll'
+dalla | da + la
+dalle | da + le
+di | of
+del | di + il
+dello | di + lo
+dei | di + i
+degli | di + gli
+dell | di + l'
+degl | di + gl'
+della | di + la
+delle | di + le
+in | in
+nel | in + el
+nello | in + lo
+nei | in + i
+negli | in + gli
+nell | in + l'
+negl | in + gl'
+nella | in + la
+nelle | in + le
+su | on
+sul | su + il
+sullo | su + lo
+sui | su + i
+sugli | su + gli
+sull | su + l'
+sugl | su + gl'
+sulla | su + la
+sulle | su + le
+per | through, by
+tra | among
+contro | against
+io | I
+tu | thou
+lui | he
+lei | she
+noi | we
+voi | you
+loro | they
+mio | my
+mia |
+miei |
+mie |
+tuo |
+tua |
+tuoi | thy
+tue |
+suo |
+sua |
+suoi | his, her
+sue |
+nostro | our
+nostra |
+nostri |
+nostre |
+vostro | your
+vostra |
+vostri |
+vostre |
+mi | me
+ti | thee
+ci | us, there
+vi | you, there
+lo | him, the
+la | her, the
+li | them
+le | them, the
+gli | to him, the
+ne | from there etc
+il | the
+un | a
+uno | a
+una | a
+ma | but
+ed | and
+se | if
+perché | why, because
+anche | also
+come | how
+dov | where (as dov')
+dove | where
+che | who, that
+chi | who
+cui | whom
+non | not
+più | more
+quale | who, that
+quanto | how much
+quanti |
+quanta |
+quante |
+quello | that
+quelli |
+quella |
+quelle |
+questo | this
+questi |
+questa |
+queste |
+si | yes
+tutto | all
+tutti | all
+
+ | single letter forms:
+
+a | at
+c | as c' for ce or ci
+e | and
+i | the
+l | as l'
+o | or
+
+ | forms of avere, to have (not including the infinitive):
+
+ho
+hai
+ha
+abbiamo
+avete
+hanno
+abbia
+abbiate
+abbiano
+avrò
+avrai
+avrà
+avremo
+avrete
+avranno
+avrei
+avresti
+avrebbe
+avremmo
+avreste
+avrebbero
+avevo
+avevi
+aveva
+avevamo
+avevate
+avevano
+ebbi
+avesti
+ebbe
+avemmo
+aveste
+ebbero
+avessi
+avesse
+avessimo
+avessero
+avendo
+avuto
+avuta
+avuti
+avute
+
+ | forms of essere, to be (not including the infinitive):
+sono
+sei
+è
+siamo
+siete
+sia
+siate
+siano
+sarò
+sarai
+sarà
+saremo
+sarete
+saranno
+sarei
+saresti
+sarebbe
+saremmo
+sareste
+sarebbero
+ero
+eri
+era
+eravamo
+eravate
+erano
+fui
+fosti
+fu
+fummo
+foste
+furono
+fossi
+fosse
+fossimo
+fossero
+essendo
+
+ | forms of fare, to do (not including the infinitive, fa, fat-):
+faccio
+fai
+facciamo
+fanno
+faccia
+facciate
+facciano
+farò
+farai
+farà
+faremo
+farete
+faranno
+farei
+faresti
+farebbe
+faremmo
+fareste
+farebbero
+facevo
+facevi
+faceva
+facevamo
+facevate
+facevano
+feci
+facesti
+fece
+facemmo
+faceste
+fecero
+facessi
+facesse
+facessimo
+facessero
+facendo
+
+ | forms of stare, to be (not including the infinitive):
+sto
+stai
+sta
+stiamo
+stanno
+stia
+stiate
+stiano
+starò
+starai
+starà
+staremo
+starete
+staranno
+starei
+staresti
+starebbe
+staremmo
+stareste
+starebbero
+stavo
+stavi
+stava
+stavamo
+stavate
+stavano
+stetti
+stesti
+stette
+stemmo
+steste
+stettero
+stessi
+stesse
+stessimo
+stessero
+stando
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt
new file mode 100644
index 0000000..d4321be
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt
@@ -0,0 +1,127 @@
+#
+# This file defines a stopword set for Japanese.
+#
+# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
+# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
+# for frequency lists, etc. that can be useful for making your own set (if desired)
+#
+# Note that there is an overlap between these stopwords and the terms stopped when used
+# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
+# that comments are not allowed on the same line as stopwords.
+#
+# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
+# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
+# using the same character width as the entries in this file. Since this StopFilter is
+# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
+# entries to be in half-width and your kana entries to be in full-width.
+#
+の
+に
+は
+を
+た
+が
+で
+て
+と
+し
+れ
+さ
+ある
+いる
+も
+する
+から
+な
+こと
+として
+い
+や
+れる
+など
+なっ
+ない
+この
+ため
+その
+あっ
+よう
+また
+もの
+という
+あり
+まで
+られ
+なる
+へ
+か
+だ
+これ
+によって
+により
+おり
+より
+による
+ず
+なり
+られる
+において
+ば
+なかっ
+なく
+しかし
+について
+せ
+だっ
+その後
+できる
+それ
+う
+ので
+なお
+のみ
+でき
+き
+つ
+における
+および
+いう
+さらに
+でも
+ら
+たり
+その他
+に関する
+たち
+ます
+ん
+なら
+に対して
+特に
+せる
+及び
+これら
+とき
+では
+にて
+ほか
+ながら
+うち
+そして
+とともに
+ただし
+かつて
+それぞれ
+または
+お
+ほど
+ものの
+に対する
+ほとんど
+と共に
+といった
+です
+とも
+ところ
+ここ
+##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt
new file mode 100644
index 0000000..e21a23c
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt
@@ -0,0 +1,172 @@
+# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
+# the original list of over 800 forms was refined:
+# pronouns, adverbs, interjections were removed
+#
+# prepositions
+aiz
+ap
+ar
+apakš
+ārpus
+augšpus
+bez
+caur
+dēļ
+gar
+iekš
+iz
+kopš
+labad
+lejpus
+līdz
+no
+otrpus
+pa
+par
+pār
+pēc
+pie
+pirms
+pret
+priekš
+starp
+šaipus
+uz
+viņpus
+virs
+virspus
+zem
+apakšpus
+# Conjunctions
+un
+bet
+jo
+ja
+ka
+lai
+tomēr
+tikko
+turpretī
+arī
+kaut
+gan
+tādēļ
+tā
+ne
+tikvien
+vien
+kā
+ir
+te
+vai
+kamēr
+# Particles
+ar
+diezin
+droši
+diemžēl
+nebūt
+ik
+it
+taču
+nu
+pat
+tiklab
+iekšpus
+nedz
+tik
+nevis
+turpretim
+jeb
+iekam
+iekām
+iekāms
+kolīdz
+līdzko
+tiklīdz
+jebšu
+tālab
+tāpēc
+nekā
+itin
+jā
+jau
+jel
+nē
+nezin
+tad
+tikai
+vis
+tak
+iekams
+vien
+# modal verbs
+būt
+biju
+biji
+bija
+bijām
+bijāt
+esmu
+esi
+esam
+esat
+būšu
+būsi
+būs
+būsim
+būsiet
+tikt
+tiku
+tiki
+tika
+tikām
+tikāt
+tieku
+tiec
+tiek
+tiekam
+tiekat
+tikšu
+tiks
+tiksim
+tiksiet
+tapt
+tapi
+tapāt
+topat
+tapšu
+tapsi
+taps
+tapsim
+tapsiet
+kļūt
+kļuvu
+kļuvi
+kļuva
+kļuvām
+kļuvāt
+kļūstu
+kļūsti
+kļūst
+kļūstam
+kļūstat
+kļūšu
+kļūsi
+kļūs
+kļūsim
+kļūsiet
+# verbs
+varēt
+varēju
+varējām
+varēšu
+varēsim
+var
+varēji
+varējāt
+varēsi
+varēsiet
+varat
+varēja
+varēs
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt
new file mode 100644
index 0000000..47a2aea
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt
@@ -0,0 +1,119 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Dutch stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large sample of Dutch text.
+
+ | Dutch stop words frequently exhibit homonym clashes. These are indicated
+ | clearly below.
+
+de | the
+en | and
+van | of, from
+ik | I, the ego
+te | (1) chez, at etc, (2) to, (3) too
+dat | that, which
+die | that, those, who, which
+in | in, inside
+een | a, an, one
+hij | he
+het | the, it
+niet | not, nothing, naught
+zijn | (1) to be, being, (2) his, one's, its
+is | is
+was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
+op | on, upon, at, in, up, used up
+aan | on, upon, to (as dative)
+met | with, by
+als | like, such as, when
+voor | (1) before, in front of, (2) furrow
+had | had, past tense all persons sing. of 'hebben' (have)
+er | there
+maar | but, only
+om | round, about, for etc
+hem | him
+dan | then
+zou | should/would, past tense all persons sing. of 'zullen'
+of | or, whether, if
+wat | what, something, anything
+mijn | possessive and noun 'mine'
+men | people, 'one'
+dit | this
+zo | so, thus, in this way
+door | through by
+over | over, across
+ze | she, her, they, them
+zich | oneself
+bij | (1) a bee, (2) by, near, at
+ook | also, too
+tot | till, until
+je | you
+mij | me
+uit | out of, from
+der | Old Dutch form of 'van der' still found in surnames
+daar | (1) there, (2) because
+haar | (1) her, their, them, (2) hair
+naar | (1) unpleasant, unwell etc, (2) towards, (3) as
+heb | present first person sing. of 'to have'
+hoe | how, why
+heeft | present third person sing. of 'to have'
+hebben | 'to have' and various parts thereof
+deze | this
+u | you
+want | (1) for, (2) mitten, (3) rigging
+nog | yet, still
+zal | 'shall', first and third person sing. of verb 'zullen' (will)
+me | me
+zij | she, they
+nu | now
+ge | 'thou', still used in Belgium and south Netherlands
+geen | none
+omdat | because
+iets | something, somewhat
+worden | to become, grow, get
+toch | yet, still
+al | all, every, each
+waren | (1) 'were' (2) to wander, (3) wares, (3)
+veel | much, many
+meer | (1) more, (2) lake
+doen | to do, to make
+toen | then, when
+moet | noun 'spot/mote' and present form of 'to must'
+ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
+zonder | without
+kan | noun 'can' and present form of 'to be able'
+hun | their, them
+dus | so, consequently
+alles | all, everything, anything
+onder | under, beneath
+ja | yes, of course
+eens | once, one day
+hier | here
+wie | who
+werd | imperfect third person sing. of 'become'
+altijd | always
+doch | yet, but etc
+wordt | present third person sing. of 'become'
+wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
+kunnen | to be able
+ons | us/our
+zelf | self
+tegen | against, towards, at
+na | after, near
+reeds | already
+wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
+kon | could; past tense of 'to be able'
+niets | nothing
+uw | your
+iemand | somebody
+geweest | been; past participle of 'be'
+andere | other
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt
new file mode 100644
index 0000000..a7a2c28
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt
@@ -0,0 +1,194 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Norwegian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This stop word list is for the dominant bokmål dialect. Words unique
+ | to nynorsk are marked *.
+
+ | Revised by Jan Bruusgaard <Ja...@ssb.no>, Jan 2005
+
+og | and
+i | in
+jeg | I
+det | it/this/that
+at | to (w. inf.)
+en | a/an
+et | a/an
+den | it/this/that
+til | to
+er | is/am/are
+som | who/that
+på | on
+de | they / you(formal)
+med | with
+han | he
+av | of
+ikke | not
+ikkje | not *
+der | there
+så | so
+var | was/were
+meg | me
+seg | you
+men | but
+ett | one
+har | have
+om | about
+vi | we
+min | my
+mitt | my
+ha | have
+hadde | had
+hun | she
+nå | now
+over | over
+da | when/as
+ved | by/know
+fra | from
+du | you
+ut | out
+sin | your
+dem | them
+oss | us
+opp | up
+man | you/one
+kan | can
+hans | his
+hvor | where
+eller | or
+hva | what
+skal | shall/must
+selv | self (reflective)
+sjøl | self (reflective)
+her | here
+alle | all
+vil | will
+bli | become
+ble | became
+blei | became *
+blitt | have become
+kunne | could
+inn | in
+når | when
+være | be
+kom | come
+noen | some
+noe | some
+ville | would
+dere | you
+som | who/which/that
+deres | their/theirs
+kun | only/just
+ja | yes
+etter | after
+ned | down
+skulle | should
+denne | this
+for | for/because
+deg | you
+si | hers/his
+sine | hers/his
+sitt | hers/his
+mot | against
+å | to
+meget | much
+hvorfor | why
+dette | this
+disse | these/those
+uten | without
+hvordan | how
+ingen | none
+din | your
+ditt | your
+blir | become
+samme | same
+hvilken | which
+hvilke | which (plural)
+sånn | such a
+inni | inside/within
+mellom | between
+vår | our
+hver | each
+hvem | who
+vors | us/ours
+hvis | whose
+både | both
+bare | only/just
+enn | than
+fordi | as/because
+før | before
+mange | many
+også | also
+slik | just
+vært | been
+være | to be
+båe | both *
+begge | both
+siden | since
+dykk | your *
+dykkar | yours *
+dei | they *
+deira | them *
+deires | theirs *
+deim | them *
+di | your (fem.) *
+då | as/when *
+eg | I *
+ein | a/an *
+eit | a/an *
+eitt | a/an *
+elles | or *
+honom | he *
+hjå | at *
+ho | she *
+hoe | she *
+henne | her
+hennar | her/hers
+hennes | hers
+hoss | how *
+hossen | how *
+ikkje | not *
+ingi | noone *
+inkje | noone *
+korleis | how *
+korso | how *
+kva | what/which *
+kvar | where *
+kvarhelst | where *
+kven | who/whom *
+kvi | why *
+kvifor | why *
+me | we *
+medan | while *
+mi | my *
+mine | my *
+mykje | much *
+no | now *
+nokon | some (masc./neut.) *
+noka | some (fem.) *
+nokor | some *
+noko | some *
+nokre | some *
+si | his/hers *
+sia | since *
+sidan | since *
+so | so *
+somt | some *
+somme | some *
+um | about*
+upp | up *
+vere | be *
+vore | was *
+verte | become *
+vort | become *
+varte | became *
+vart | became *
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt
new file mode 100644
index 0000000..acfeb01
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt
@@ -0,0 +1,253 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Portuguese stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | of, from
+a | the; to, at; her
+o | the; him
+que | who, that
+e | and
+do | de + o
+da | de + a
+em | in
+um | a
+para | for
+ | é from SER
+com | with
+não | not, no
+uma | a
+os | the; them
+no | em + o
+se | himself etc
+na | em + a
+por | for
+mais | more
+as | the; them
+dos | de + os
+como | as, like
+mas | but
+ | foi from SER
+ao | a + o
+ele | he
+das | de + as
+ | tem from TER
+à | a + a
+seu | his
+sua | her
+ou | or
+ | ser from SER
+quando | when
+muito | much
+ | há from HAV
+nos | em + os; us
+já | already, now
+ | está from EST
+eu | I
+também | also
+só | only, just
+pelo | per + o
+pela | per + a
+até | up to
+isso | that
+ela | he
+entre | between
+ | era from SER
+depois | after
+sem | without
+mesmo | same
+aos | a + os
+ | ter from TER
+seus | his
+quem | whom
+nas | em + as
+me | me
+esse | that
+eles | they
+ | estão from EST
+você | you
+ | tinha from TER
+ | foram from SER
+essa | that
+num | em + um
+nem | nor
+suas | her
+meu | my
+às | a + as
+minha | my
+ | têm from TER
+numa | em + uma
+pelos | per + os
+elas | they
+ | havia from HAV
+ | seja from SER
+qual | which
+ | será from SER
+nós | we
+ | tenho from TER
+lhe | to him, her
+deles | of them
+essas | those
+esses | those
+pelas | per + as
+este | this
+ | fosse from SER
+dele | of him
+
+ | other words. There are many contractions such as naquele = em+aquele,
+ | mo = me+o, but they are rare.
+ | Indefinite article plural forms are also rare.
+
+tu | thou
+te | thee
+vocês | you (plural)
+vos | you
+lhes | to them
+meus | my
+minhas
+teu | thy
+tua
+teus
+tuas
+nosso | our
+nossa
+nossos
+nossas
+
+dela | of her
+delas | of them
+
+esta | this
+estes | these
+estas | these
+aquele | that
+aquela | that
+aqueles | those
+aquelas | those
+isto | this
+aquilo | that
+
+ | forms of estar, to be (not including the infinitive):
+estou
+está
+estamos
+estão
+estive
+esteve
+estivemos
+estiveram
+estava
+estávamos
+estavam
+estivera
+estivéramos
+esteja
+estejamos
+estejam
+estivesse
+estivéssemos
+estivessem
+estiver
+estivermos
+estiverem
+
+ | forms of haver, to have (not including the infinitive):
+hei
+há
+havemos
+hão
+houve
+houvemos
+houveram
+houvera
+houvéramos
+haja
+hajamos
+hajam
+houvesse
+houvéssemos
+houvessem
+houver
+houvermos
+houverem
+houverei
+houverá
+houveremos
+houverão
+houveria
+houveríamos
+houveriam
+
+ | forms of ser, to be (not including the infinitive):
+sou
+somos
+são
+era
+éramos
+eram
+fui
+foi
+fomos
+foram
+fora
+fôramos
+seja
+sejamos
+sejam
+fosse
+fôssemos
+fossem
+for
+formos
+forem
+serei
+será
+seremos
+serão
+seria
+seríamos
+seriam
+
+ | forms of ter, to have (not including the infinitive):
+tenho
+tem
+temos
+tém
+tinha
+tínhamos
+tinham
+tive
+teve
+tivemos
+tiveram
+tivera
+tivéramos
+tenha
+tenhamos
+tenham
+tivesse
+tivéssemos
+tivessem
+tiver
+tivermos
+tiverem
+terei
+terá
+teremos
+terão
+teria
+teríamos
+teriam
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt
new file mode 100644
index 0000000..4fdee90
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt
@@ -0,0 +1,233 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+acea
+aceasta
+această
+aceea
+acei
+aceia
+acel
+acela
+acele
+acelea
+acest
+acesta
+aceste
+acestea
+aceşti
+aceştia
+acolo
+acum
+ai
+aia
+aibă
+aici
+al
+ăla
+ale
+alea
+ălea
+altceva
+altcineva
+am
+ar
+are
+aş
+aşadar
+asemenea
+asta
+ăsta
+astăzi
+astea
+ăstea
+ăştia
+asupra
+aţi
+au
+avea
+avem
+aveţi
+azi
+bine
+bucur
+bună
+ca
+că
+căci
+când
+care
+cărei
+căror
+cărui
+cât
+câte
+câţi
+către
+câtva
+ce
+cel
+ceva
+chiar
+cînd
+cine
+cineva
+cît
+cîte
+cîţi
+cîtva
+contra
+cu
+cum
+cumva
+curând
+curînd
+da
+dă
+dacă
+dar
+datorită
+de
+deci
+deja
+deoarece
+departe
+deşi
+din
+dinaintea
+dintr
+dintre
+drept
+după
+ea
+ei
+el
+ele
+eram
+este
+eşti
+eu
+face
+fără
+fi
+fie
+fiecare
+fii
+fim
+fiţi
+iar
+ieri
+îi
+îl
+îmi
+împotriva
+în
+înainte
+înaintea
+încât
+încît
+încotro
+între
+întrucât
+întrucît
+îţi
+la
+lângă
+le
+li
+lîngă
+lor
+lui
+mă
+mâine
+mea
+mei
+mele
+mereu
+meu
+mi
+mine
+mult
+multă
+mulţi
+ne
+nicăieri
+nici
+nimeni
+nişte
+noastră
+noastre
+noi
+noştri
+nostru
+nu
+ori
+oricând
+oricare
+oricât
+orice
+oricînd
+oricine
+oricît
+oricum
+oriunde
+până
+pe
+pentru
+peste
+pînă
+poate
+pot
+prea
+prima
+primul
+prin
+printr
+sa
+să
+săi
+sale
+sau
+său
+se
+şi
+sînt
+sîntem
+sînteţi
+spre
+sub
+sunt
+suntem
+sunteţi
+ta
+tăi
+tale
+tău
+te
+ţi
+ţie
+tine
+toată
+toate
+tot
+toţi
+totuşi
+tu
+un
+una
+unde
+undeva
+unei
+unele
+uneori
+unor
+vă
+vi
+voastră
+voastre
+voi
+voştri
+vostru
+vouă
+vreo
+vreun
[26/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml b/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
deleted file mode 100644
index 1b55374..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
+++ /dev/null
@@ -1,1408 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
-
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
-
- <!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
- -->
- <luceneMatchVersion>7.0.0</luceneMatchVersion>
-
- <!-- <lib/> directives can be used to instruct Solr to load any Jars
- identified and use them to resolve any "plugins" specified in
- your solrconfig.xml or schema.xml (ie: Analyzers, Request
- Handlers, etc...).
-
- All directories and paths are resolved relative to the
- instanceDir.
-
- Please note that <lib/> directives are processed in the order
- that they appear in your solrconfig.xml file, and are "stacked"
- on top of each other when building a ClassLoader - so if you have
- plugin jars with dependencies on other jars, the "lower level"
- dependency jars should be loaded first.
-
- If a "./lib" directory exists in your instanceDir, all files
- found in it are included as if you had used the following
- syntax...
-
- <lib dir="./lib" />
- -->
-
- <!-- A 'dir' option by itself adds any files found in the directory
- to the classpath, this is useful for including all jars in a
- directory.
-
- When a 'regex' is specified in addition to a 'dir', only the
- files in that directory which completely match the regex
- (anchored on both ends) will be included.
-
- If a 'dir' option (with or without a regex) is used and nothing
- is found that matches, a warning will be logged.
-
- The examples below can be used to load some solr-contribs along
- with their external dependencies.
- -->
- <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
- <!-- an exact 'path' can be used instead of a 'dir' to specify a
- specific jar file. This will cause a serious error to be logged
- if it can't be loaded.
- -->
- <!--
- <lib path="../a-jar-that-does-not-exist.jar" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:}</dataDir>
-
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory is filesystem
- based and tries to pick the best implementation for the current
- JVM and platform. solr.NRTCachingDirectoryFactory, the default,
- wraps solr.StandardDirectoryFactory and caches small files in memory
- for better NRT performance.
-
- One can force a particular implementation via solr.MMapDirectoryFactory,
- solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
-
- solr.RAMDirectoryFactory is memory based and not persistent.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
-
- <!-- The CodecFactory for defining the format of the inverted index.
- The default implementation is SchemaCodecFactory, which is the official Lucene
- index format, but hooks into the schema to provide per-field customization of
- the postings lists and per-document values in the fieldType element
- (postingsFormat/docValuesFormat). Note that most of the alternative implementations
- are experimental, so if you choose to customize the index format, it's a good
- idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
- before upgrading to a newer version to avoid unnecessary reindexing.
- A "compressionMode" string element can be added to <codecFactory> to choose
- between the existing compression modes in the default codec: "BEST_SPEED" (default)
- or "BEST_COMPRESSION".
- -->
- <codecFactory class="solr.SchemaCodecFactory"/>
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Index Config - These settings control low-level behavior of indexing
- Most example settings here show the default value, but are commented
- out, to more easily see where customizations have been made.
-
- Note: This replaces <indexDefaults> and <mainIndex> from older versions
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <indexConfig>
- <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
- LimitTokenCountFilterFactory in your fieldType definition. E.g.
- <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
- -->
- <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
- <!-- <writeLockTimeout>1000</writeLockTimeout> -->
-
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
- Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
- <!-- <useCompoundFile>false</useCompoundFile> -->
-
- <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
- indexing for buffering added documents and deletions before they are
- flushed to the Directory.
- maxBufferedDocs sets a limit on the number of documents buffered
- before flushing.
- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first. -->
- <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <!-- Expert: Merge Policy
- The Merge Policy in Lucene controls how merging of segments is done.
- The default since Solr/Lucene 3.3 is TieredMergePolicy.
- The default since Lucene 2.3 was the LogByteSizeMergePolicy,
- Even older versions of Lucene used LogDocMergePolicy.
- -->
- <!--
- <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
- <int name="maxMergeAtOnce">10</int>
- <int name="segmentsPerTier">10</int>
- <double name="noCFSRatio">0.1</double>
- </mergePolicyFactory>
- -->
-
- <!-- Expert: Merge Scheduler
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- can perform merges in the background using separate threads.
- The SerialMergeScheduler (Lucene 2.2 default) does not.
- -->
- <!--
- <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
- -->
-
- <!-- LockFactory
-
- This option specifies which Lucene LockFactory implementation
- to use.
-
- single = SingleInstanceLockFactory - suggested for a
- read-only index or when there is no possibility of
- another process trying to modify the index.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- Defaults: 'native' is default for Solr3.6 and later, otherwise
- 'simple' is the default
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>${solr.lock.type:native}</lockType>
-
- <!-- Commit Deletion Policy
- Custom deletion policies can be specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- The default Solr IndexDeletionPolicy implementation supports
- deleting index commit points on number of commits, age of
- commit point and optimized status.
-
- The latest commit point should always be preserved regardless
- of the criteria.
- -->
- <!--
- <deletionPolicy class="solr.SolrDeletionPolicy">
- -->
- <!-- The number of commit points to be kept -->
- <!-- <str name="maxCommitsToKeep">1</str> -->
- <!-- The number of optimized commit points to be kept -->
- <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <str name="maxCommitAge">30MINUTES</str>
- <str name="maxCommitAge">1DAY</str>
- -->
- <!--
- </deletionPolicy>
- -->
-
- <!-- Lucene Infostream
-
- To aid in advanced debugging, Lucene provides an "InfoStream"
- of detailed information when indexing.
-
- Setting The value to true will instruct the underlying Lucene
- IndexWriter to write its debugging info the specified file
- -->
- <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
- </indexConfig>
-
-
- <!-- JMX
-
- This example enables JMX if and only if an existing MBeanServer
- is found, use this if you want to configure JMX through JVM
- parameters. Remove this to disable exposing Solr configuration
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- Enables a transaction log, used for real-time get, durability, and
- and solr cloud replica recovery. The log can grow as big as
- uncommitted changes to the index, so use of a hard autoCommit
- is recommended (see below).
- "dir" - the target directory for transaction logs, defaults to the
- solr data directory.
- "numVersionBuckets" - sets the number of buckets used to keep
- track of max version values when checking for re-ordered
- updates; increase this value to reduce the cost of
- synchronizing access to version buckets during high-volume
- indexing, this requires 8 bytes (long) * numVersionBuckets
- of heap space per Solr core.
- -->
- <updateLog>
- <str name="dir">${solr.ulog.dir:}</str>
- <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
- </updateLog>
-
- <!-- AutoCommit
-
- Perform a hard commit automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time in ms that is allowed to pass
- since a document was added before automatically
- triggering a new commit.
- openSearcher - if false, the commit causes recent index changes
- to be flushed to stable storage, but does not cause a new
- searcher to be opened to make those changes visible.
-
- If the updateLog is enabled, then it's highly recommended to
- have some sort of hard autoCommit to limit the log size.
- -->
- <autoCommit>
- <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
-
- <!-- softAutoCommit is like autoCommit except it causes a
- 'soft' commit which only ensures that changes are visible
- but does not ensure that data is synced to disk. This is
- faster and more near-realtime friendly than a hard commit.
- -->
-
- <autoSoftCommit>
- <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
- </autoSoftCommit>
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- The RunExecutableListener executes an external command from a
- hook such as postCommit or postOptimize.
-
- exe - the name of the executable to run
- dir - dir to use as the current working directory. (default=".")
- wait - the calling thread waits until the executable returns.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
-
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Query section - these settings control query time things like caches
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded.
-
- ** WARNING **
-
- This option actually modifies a global Lucene property that
- will affect all SolrCores. If multiple solrconfig.xml files
- disagree on this property, the value at any given moment will
- be based on the last SolrCore to be initialized.
-
- -->
- <maxBooleanClauses>1024</maxBooleanClauses>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (see java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
- to occupy. Note that when this option is specified, the size
- and initialSize parameters are ignored.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Query Result Cache
-
- Caches results of searches - ordered lists of document ids
- (DocList) based on a query, a sort, and the range of documents requested.
- Additional supported parameter by LRUCache:
- maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
- to occupy
- -->
- <queryResultCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Document Cache
-
- Caches Lucene Document objects (the stored fields for each
- document). Since Lucene internal document ids are transient,
- this cache will not be autowarmed.
- -->
- <documentCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- custom cache currently used by block join -->
- <cache name="perSegFilter"
- class="solr.search.LRUCache"
- size="10"
- initialSize="0"
- autowarmCount="10"
- regenerator="solr.NoOpRegenerator" />
-
- <!-- Field Value Cache
-
- Cache used to hold field values that are quickly accessible
- by document id. The fieldValueCache is created by default
- even if not configured here.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- name through SolrIndexSearcher.getCache(),cacheLookup(), and
- cacheInsert(). The purpose is to enable easy caching of
- user/application level data. The regenerator argument should
- be specified as an implementation of solr.CacheRegenerator
- if autowarming is desired.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- are collected. For example, if a search for a particular query
- requests matching documents 10 through 19, and queryWindowSize is 50,
- then documents 0 through 49 will be collected and cached. Any further
- requests in that range can be satisfied via the cache.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- prepared but there is no current registered searcher to handle
- requests or to gain autowarming data from.
-
-
- -->
- <!-- QuerySenderListener takes an array of NamedList and executes a
- local query request for each NamedList in sequence.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- -->
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <useColdSearcher>false</useColdSearcher>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect is a legacy option that affects the behavior of requests
- such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and dispatch the query to a handler specified by the
- "qt" param, assuming "/select" isn't already registered.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests, resulting in a 404 unless a handler
- is explicitly registered with the name "/select"
-
- handleSelect="true" is not recommended for new users, but is the default
- for backwards compatibility
- -->
- <requestDispatcher handleSelect="false" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- multipartUploadLimitInKB - specifies the max size (in KiB) of
- Multipart File Uploads that Solr will allow in a Request.
-
- formdataUploadLimitInKB - specifies the max size (in KiB) of
- form data (application/x-www-form-urlencoded) sent via
- POST. You can use POST to pass request parameters not
- fitting into the URL.
-
- addHttpRequestToContext - if set to true, it will instruct
- the requestParsers to include the original HttpServletRequest
- object in the context map of the SolrQueryRequest under the
- key "httpRequest". It will not be used by any of the existing
- Solr components, but may be useful when developing custom
- plugins.
-
- *** WARNING ***
- Before enabling remote streaming, you should make sure your
- system has authentication enabled.
-
- <requestParsers enableRemoteStreaming="false"
- multipartUploadLimitInKB="-1"
- formdataUploadLimitInKB="-1"
- addHttpRequestToContext="false"/>
- -->
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- If you include a <cacheControl> directive, it will be used to
- generate a Cache-Control header (as well as an Expires header
- if the value contains "max-age=")
-
- By default, no Cache-Control header is generated.
-
- You can use the <cacheControl> option even if you have set
- never304="true"
- -->
- <!--
- <httpCaching never304="true" >
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- <!-- To enable Solr to respond with automatically generated HTTP
- Caching headers, and to response to Cache Validation requests
- correctly, set the value of never304="false"
-
- This will cause Solr to generate Last-Modified and ETag
- headers based on the properties of the Index.
-
- The following options can also be specified to affect the
- values of these headers...
-
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- Incoming queries will be dispatched to a specific handler by name
- based on the path specified in the request.
-
- Legacy behavior: If the request path uses "/select" but no Request
- Handler has that name, and if handleSelect="true" has been specified in
- the requestDispatcher, then the Request Handler is dispatched based on
- the qt parameter. Handlers without a leading '/' are accessed this way
- like so: http://host/app/[core/]select?qt=name If no qt is
- given, then the requestHandler that declares default="true" will be
- used or the one named "standard".
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
- <requestHandler name="/select" class="solr.SearchHandler">
- <!-- default values for query parameters can be specified, these
- will be overridden by parameters in the request
- -->
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <int name="rows">10</int>
- <!-- <str name="df">text</str> -->
- </lst>
- <!-- In addition to defaults, "appends" params can be specified
- to identify values which should be appended to the list of
- multi-val params from the query (or the existing "defaults").
- -->
- <!-- In this example, the param "fq=instock:true" would be appended to
- any query time fq params the user may specify, as a mechanism for
- partitioning the index, independent of any user selected filtering
- that may also be desired (perhaps as a result of faceted searching).
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "appends" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="appends">
- <str name="fq">inStock:true</str>
- </lst>
- -->
- <!-- "invariants" are a way of letting the Solr maintainer lock down
- the options available to Solr clients. Any params values
- specified here are used regardless of what values may be specified
- in either the query, the "defaults", or the "appends" params.
-
- In this example, the facet.field and facet.query params would
- be fixed, limiting the facets clients can use. Faceting is
- not turned on by default - but if the client does specify
- facet=true in the request, these are the only facets they
- will be able to see counts for; regardless of what other
- facet.field or facet.query params they may specify.
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "invariants" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="invariants">
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">price:[* TO 500]</str>
- <str name="facet.query">price:[500 TO *]</str>
- </lst>
- -->
- <!-- If the default list of SearchComponents is not desired, that
- list can either be overridden completely, or components can be
- prepended or appended to the default list. (see below)
- -->
- <!--
- <arr name="components">
- <str>nameOfCustomComponent1</str>
- <str>nameOfCustomComponent2</str>
- </arr>
- -->
- </requestHandler>
-
- <!-- A request handler that returns indented JSON by default -->
- <requestHandler name="/query" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- </lst>
- </requestHandler>
-
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- </requestHandler>
-
- <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
- <lst name="defaults">
- <str name="df">_text_</str>
- </lst>
- </initParams>
-
- <!-- This enabled schemaless mode
- <initParams path="/update/**">
- <lst name="defaults">
- <str name="update.chain">add-unknown-fields-to-the-schema</str>
- </lst>
- </initParams>
- -->
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <str name="lowernames">true</str>
- <str name="fmap.meta">ignored_</str>
- <str name="fmap.content">_text_</str>
- </lst>
- </requestHandler>
- <!-- Search Components
-
- Search components are registered to SolrCore and used by
- instances of SearchHandler (which can access them by name)
-
- By default, the following components are available:
-
- <searchComponent name="query" class="solr.QueryComponent" />
- <searchComponent name="facet" class="solr.FacetComponent" />
- <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
- <searchComponent name="highlight" class="solr.HighlightComponent" />
- <searchComponent name="stats" class="solr.StatsComponent" />
- <searchComponent name="debug" class="solr.DebugComponent" />
-
- Default configuration in a requestHandler would look like:
-
- <arr name="components">
- <str>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- If you register a searchComponent to one of the standard names,
- that will be used instead of the default.
-
- To insert components before or after the 'standard' components, use:
-
- <arr name="first-components">
- <str>myFirstComponentName</str>
- </arr>
-
- <arr name="last-components">
- <str>myLastComponentName</str>
- </arr>
-
- NOTE: The component registered with the name "debug" will
- always be executed after the "last-components"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text_general</str>
-
- <!-- Multiple "Spell Checkers" can be declared and used by this
- component
- -->
-
- <!-- a spellchecker built from a field of the main index -->
- <lst name="spellchecker">
- <str name="name">default</str>
- <str name="field">_text_</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
- <str name="distanceMeasure">internal</str>
- <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
- <float name="accuracy">0.5</float>
- <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
- <int name="maxEdits">2</int>
- <!-- the minimum shared prefix when enumerating terms -->
- <int name="minPrefix">1</int>
- <!-- maximum number of inspections per result. -->
- <int name="maxInspections">5</int>
- <!-- minimum length of a query term to be considered for correction -->
- <int name="minQueryLength">4</int>
- <!-- maximum threshold of documents a query term can appear to be considered for correction -->
- <float name="maxQueryFrequency">0.01</float>
- <!-- uncomment this to require suggestions to occur in 1% of the documents
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
- <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
- <!--
- <lst name="spellchecker">
- <str name="name">wordbreak</str>
- <str name="classname">solr.WordBreakSolrSpellChecker</str>
- <str name="field">name</str>
- <str name="combineWords">true</str>
- <str name="breakWords">true</str>
- <int name="maxChanges">10</int>
- </lst>
- -->
- </searchComponent>
-
- <!-- A request handler for demonstrating the spellcheck component.
-
- NOTE: This is purely as an example. The whole purpose of the
- SpellCheckComponent is to hook it into the request handler that
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
- NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
-
- See http://wiki.apache.org/solr/SpellCheckComponent for details
- on the request parameters.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <!-- Solr will use suggestions from both the 'default' spellchecker
- and from the 'wordbreak' spellchecker and combine them.
- collations (re-written queries) can include a combination of
- corrections from both spellcheckers -->
- <str name="spellcheck.dictionary">default</str>
- <str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">true</str>
- <str name="spellcheck.count">10</str>
- <str name="spellcheck.alternativeTermCount">5</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
- <str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
- <str name="spellcheck.maxCollationTries">10</str>
- <str name="spellcheck.maxCollations">5</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component. (Omitted here. See the default Solr example for a typical configuration.) -->
-
- <!-- Terms Component
-
- http://wiki.apache.org/solr/TermsComponent
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- <bool name="distrib">false</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- Configure the weighted fragListBuilder -->
- <fragListBuilder name="weighted"
- default="true"
- class="solr.highlight.WeightedFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <fragmentsBuilder name="default"
- default="true"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <!--
- <lst name="defaults">
- <str name="hl.multiValuedSeparatorChar">/</str>
- </lst>
- -->
- </fragmentsBuilder>
-
- <!-- multi-colored tag FragmentsBuilder -->
- <fragmentsBuilder name="colored"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
-
- <boundaryScanner name="default"
- default="true"
- class="solr.highlight.SimpleBoundaryScanner">
- <lst name="defaults">
- <str name="hl.bs.maxScan">10</str>
- <str name="hl.bs.chars">.,!? 	 </str>
- </lst>
- </boundaryScanner>
-
- <boundaryScanner name="breakIterator"
- class="solr.highlight.BreakIteratorBoundaryScanner">
- <lst name="defaults">
- <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
- <str name="hl.bs.type">WORD</str>
- <!-- language and country are used when constructing Locale object. -->
- <!-- And the Locale object will be used when getting instance of BreakIterator -->
- <str name="hl.bs.language">en</str>
- <str name="hl.bs.country">US</str>
- </lst>
- </boundaryScanner>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- http://wiki.apache.org/solr/UpdateRequestProcessor
-
- -->
-
- <!-- Add unknown fields to the schema
-
- Field type guessing update processors that will
- attempt to parse string-typed field values as Booleans, Longs,
- Doubles, or Dates, and then add schema fields with the guessed
- field types.
-
- These require that the schema is both managed and mutable, by
- declaring schemaFactory as ManagedIndexSchemaFactory, with
- mutable specified as true.
-
- See http://wiki.apache.org/solr/GuessingFieldTypes
- -->
- <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
- <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
- <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
- <str name="pattern">[^\w-\.]</str>
- <str name="replacement">_</str>
- </updateProcessor>
- <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
- <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
- <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
- <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
- <arr name="format">
- <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss</str>
- <str>yyyy-MM-dd'T'HH:mmZ</str>
- <str>yyyy-MM-dd'T'HH:mm</str>
- <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd HH:mm:ssZ</str>
- <str>yyyy-MM-dd HH:mm:ss</str>
- <str>yyyy-MM-dd HH:mmZ</str>
- <str>yyyy-MM-dd HH:mm</str>
- <str>yyyy-MM-dd</str>
- </arr>
- </updateProcessor>
- <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
- <str name="defaultFieldType">strings</str>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Boolean</str>
- <str name="fieldType">booleans</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.util.Date</str>
- <str name="fieldType">tdates</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Long</str>
- <str name="valueClass">java.lang.Integer</str>
- <str name="fieldType">tlongs</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Number</str>
- <str name="fieldType">tdoubles</str>
- </lst>
- </updateProcessor>
-
- <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:true}"
- processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
- <processor class="solr.LogUpdateProcessorFactory"/>
- <processor class="solr.DistributedUpdateProcessorFactory"/>
- <processor class="solr.RunUpdateProcessorFactory"/>
- </updateRequestProcessorChain>
-
- <!-- Deduplication
-
- An example dedup update processor that creates the "id" field
- on the fly based on the hash code of some other fields. This
- example has overwriteDupes set to false since we are using the
- id field as the signatureField and Solr will maintain
- uniqueness based on that anyway.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Language identification
-
- This example update chain identifies the language of the incoming
- documents using the langid contrib. The detected language is
- written to field language_s. No field name mapping is done.
- The fields used for detection are text, title, subject and description,
- making this example suitable for detecting languages form full-text
- rich documents injected via ExtractingRequestHandler.
- See more about langId at http://wiki.apache.org/solr/LanguageDetection
- -->
- <!--
- <updateRequestProcessorChain name="langid">
- <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
- <str name="langid.fl">text,title,subject,description</str>
- <str name="langid.langField">language_s</str>
- <str name="langid.fallback">en</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Script update processor
-
- This example hooks in an update processor implemented using JavaScript.
-
- See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
- -->
- <!--
- <updateRequestProcessorChain name="script">
- <processor class="solr.StatelessScriptUpdateProcessorFactory">
- <str name="script">update-script.js</str>
- <lst name="params">
- <str name="config_param">example config parameter</str>
- </lst>
- </processor>
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
- -->
-
- <queryResponseWriter name="json" class="solr.JSONResponseWriter">
- <!-- For the purposes of the tutorial, JSON responses are written as
- plain text so that they are easy to read in *any* browser.
- If you expect a MIME type of "application/json" just remove this override.
- -->
- <str name="content-type">text/plain; charset=UTF-8</str>
- </queryResponseWriter>
-
- <!--
- Custom response writers can be declared as needed...
- -->
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
- <str name="template.base.dir">${velocity.template.base.dir:}</str>
- <str name="solr.resource.loader.enabled">${velocity.solr.resource.loader.enabled:true}</str>
- <str name="params.resource.loader.enabled">${velocity.params.resource.loader.enabled:false}</str>
- </queryResponseWriter>
-
- <!-- XSLT response writer transforms the XML output by any xslt file found
- in Solr's conf/xslt directory. Changes to xslt files are checked for
- every xsltCacheLifetimeSeconds.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- https://cwiki.apache.org/confluence/display/solr/Query+Syntax+and+Parsing
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
-
- <!-- Document Transformers
- http://wiki.apache.org/solr/DocTransformers
- -->
- <!--
- Could be something like:
- <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
- <int name="connection">jdbc://....</int>
- </transformer>
-
- To add a constant value to all docs, use:
- <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <int name="value">5</int>
- </transformer>
-
- If you want the user to still be able to change it with _value:something_ use this:
- <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <double name="defaultValue">5</double>
- </transformer>
-
- If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
- EditorialMarkerFactory will do exactly that:
- <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
- -->
-</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/stopwords.txt b/solr/server/solr/configsets/basic_configs/conf/stopwords.txt
deleted file mode 100644
index ae1e83e..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/stopwords.txt
+++ /dev/null
@@ -1,14 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/synonyms.txt b/solr/server/solr/configsets/basic_configs/conf/synonyms.txt
deleted file mode 100644
index eab4ee8..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/synonyms.txt
+++ /dev/null
@@ -1,29 +0,0 @@
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-#-----------------------------------------------------------------------
-#some test synonym mappings unlikely to appear in real input text
-aaafoo => aaabar
-bbbfoo => bbbfoo bbbbar
-cccfoo => cccbar cccbaz
-fooaaa,baraaa,bazaaa
-
-# Some synonym groups specific to this example
-GB,gib,gigabyte,gigabytes
-MB,mib,megabyte,megabytes
-Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
-#after us won't split it into two words.
-
-# Synonym mappings can be used for spelling correction too
-pixima => pixma
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/currency.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/currency.xml b/solr/server/solr/configsets/data_driven_schema_configs/conf/currency.xml
deleted file mode 100644
index 3a9c58a..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/currency.xml
+++ /dev/null
@@ -1,67 +0,0 @@
-<?xml version="1.0" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- Example exchange rates file for CurrencyField type named "currency" in example schema -->
-
-<currencyConfig version="1.0">
- <rates>
- <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 -->
- <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" />
- <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" />
- <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" />
- <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" />
- <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" />
- <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" />
- <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" />
- <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" />
- <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" />
- <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" />
- <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" />
- <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" />
- <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" />
- <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" />
- <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" />
- <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" />
- <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" />
- <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" />
- <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" />
- <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" />
- <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" />
- <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" />
- <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" />
- <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" />
- <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" />
- <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" />
- <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" />
- <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" />
- <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" />
- <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" />
- <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" />
- <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" />
- <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" />
- <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" />
- <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" />
- <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" />
- <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" />
-
- <!-- Cross-rates for some common currencies -->
- <rate from="EUR" to="GBP" rate="0.869914" />
- <rate from="EUR" to="NOK" rate="7.800095" />
- <rate from="GBP" to="NOK" rate="8.966508" />
- </rates>
-</currencyConfig>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml b/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml
deleted file mode 100644
index 2c09ebe..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml
+++ /dev/null
@@ -1,42 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- If this file is found in the config directory, it will only be
- loaded once at startup. If it is found in Solr's data
- directory, it will be re-loaded every commit.
-
- See http://wiki.apache.org/solr/QueryElevationComponent for more info
-
--->
-<elevate>
- <!-- Query elevation examples
- <query text="foo bar">
- <doc id="1" />
- <doc id="2" />
- <doc id="3" />
- </query>
-
-for use with techproducts example
-
- <query text="ipod">
- <doc id="MA147LL/A" /> put the actual ipod at the top
- <doc id="IW-02" exclude="true" /> exclude this cable
- </query>
--->
-
-</elevate>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ca.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ca.txt
deleted file mode 100644
index 307a85f..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ca.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-# Set of Catalan contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-l
-m
-n
-s
-t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_fr.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_fr.txt
deleted file mode 100644
index f1bba51..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_fr.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-# Set of French contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-l
-m
-t
-qu
-n
-s
-j
-d
-c
-jusqu
-quoiqu
-lorsqu
-puisqu
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ga.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ga.txt
deleted file mode 100644
index 9ebe7fa..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ga.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-# Set of Irish contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-d
-m
-b
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_it.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_it.txt
deleted file mode 100644
index cac0409..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_it.txt
+++ /dev/null
@@ -1,23 +0,0 @@
-# Set of Italian contractions for ElisionFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-c
-l
-all
-dall
-dell
-nell
-sull
-coll
-pell
-gl
-agl
-dagl
-degl
-negl
-sugl
-un
-m
-t
-s
-v
-d
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/hyphenations_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/hyphenations_ga.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/hyphenations_ga.txt
deleted file mode 100644
index 4d2642c..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/hyphenations_ga.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-# Set of Irish hyphenations for StopFilter
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-h
-n
-t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stemdict_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stemdict_nl.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stemdict_nl.txt
deleted file mode 100644
index 4410729..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stemdict_nl.txt
+++ /dev/null
@@ -1,6 +0,0 @@
-# Set of overrides for the dutch stemmer
-# TODO: load this as a resource from the analyzer and sync it in build.xml
-fiets fiets
-bromfiets bromfiets
-ei eier
-kind kinder
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stoptags_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stoptags_ja.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stoptags_ja.txt
deleted file mode 100644
index 71b7508..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stoptags_ja.txt
+++ /dev/null
@@ -1,420 +0,0 @@
-#
-# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
-#
-# Any token with a part-of-speech tag that exactly matches those defined in this
-# file are removed from the token stream.
-#
-# Set your own stoptags by uncommenting the lines below. Note that comments are
-# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
-# etc. that can be useful for building you own stoptag set.
-#
-# The entire possible tagset is provided below for convenience.
-#
-#####
-# noun: unclassified nouns
-#名詞
-#
-# noun-common: Common nouns or nouns where the sub-classification is undefined
-#名詞-一般
-#
-# noun-proper: Proper nouns where the sub-classification is undefined
-#名詞-固有名詞
-#
-# noun-proper-misc: miscellaneous proper nouns
-#名詞-固有名詞-一般
-#
-# noun-proper-person: Personal names where the sub-classification is undefined
-#名詞-固有名詞-人名
-#
-# noun-proper-person-misc: names that cannot be divided into surname and
-# given name; foreign names; names where the surname or given name is unknown.
-# e.g. お市の方
-#名詞-固有名詞-人名-一般
-#
-# noun-proper-person-surname: Mainly Japanese surnames.
-# e.g. 山田
-#名詞-固有名詞-人名-姓
-#
-# noun-proper-person-given_name: Mainly Japanese given names.
-# e.g. 太郎
-#名詞-固有名詞-人名-名
-#
-# noun-proper-organization: Names representing organizations.
-# e.g. 通産省, NHK
-#名詞-固有名詞-組織
-#
-# noun-proper-place: Place names where the sub-classification is undefined
-#名詞-固有名詞-地域
-#
-# noun-proper-place-misc: Place names excluding countries.
-# e.g. アジア, バルセロナ, 京都
-#名詞-固有名詞-地域-一般
-#
-# noun-proper-place-country: Country names.
-# e.g. 日本, オーストラリア
-#名詞-固有名詞-地域-国
-#
-# noun-pronoun: Pronouns where the sub-classification is undefined
-#名詞-代名詞
-#
-# noun-pronoun-misc: miscellaneous pronouns:
-# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
-#名詞-代名詞-一般
-#
-# noun-pronoun-contraction: Spoken language contraction made by combining a
-# pronoun and the particle 'wa'.
-# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
-#名詞-代名詞-縮約
-#
-# noun-adverbial: Temporal nouns such as names of days or months that behave
-# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
-# e.g. 金曜, 一月, 午後, 少量
-#名詞-副詞可能
-#
-# noun-verbal: Nouns that take arguments with case and can appear followed by
-# 'suru' and related verbs (する, できる, なさる, くださる)
-# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
-#名詞-サ変接続
-#
-# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
-# e.g. 健康, 安易, 駄目, だめ
-#名詞-形容動詞語幹
-#
-# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
-# e.g. 0, 1, 2, 何, 数, 幾
-#名詞-数
-#
-# noun-affix: noun affixes where the sub-classification is undefined
-#名詞-非自立
-#
-# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
-# attach to the base form of inflectional words, words that cannot be classified
-# into any of the other categories below. This category includes indefinite nouns.
-# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
-# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
-# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
-# わり, 割り, 割, ん-口語/, もん-口語/
-#名詞-非自立-一般
-#
-# noun-affix-adverbial: noun affixes that that can behave as adverbs.
-# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
-# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
-# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
-# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
-# 儘, 侭, みぎり, 矢先
-#名詞-非自立-副詞可能
-#
-# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
-# with the stem よう(だ) ("you(da)").
-# e.g. よう, やう, 様 (よう)
-#名詞-非自立-助動詞語幹
-#
-# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
-# connection form な (aux "da").
-# e.g. みたい, ふう
-#名詞-非自立-形容動詞語幹
-#
-# noun-special: special nouns where the sub-classification is undefined.
-#名詞-特殊
-#
-# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
-# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
-# form of inflectional words.
-# e.g. そう
-#名詞-特殊-助動詞語幹
-#
-# noun-suffix: noun suffixes where the sub-classification is undefined.
-#名詞-接尾
-#
-# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
-# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
-# any of the other categories below. In general, this category is more inclusive than
-# 接尾語 ("suffix") and is usually the last element in a compound noun.
-# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
-# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
-#名詞-接尾-一般
-#
-# noun-suffix-person: Suffixes that form nouns and attach to person names more often
-# than other nouns.
-# e.g. 君, 様, 著
-#名詞-接尾-人名
-#
-# noun-suffix-place: Suffixes that form nouns and attach to place names more often
-# than other nouns.
-# e.g. 町, 市, 県
-#名詞-接尾-地域
-#
-# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
-# can appear before スル ("suru").
-# e.g. 化, 視, 分け, 入り, 落ち, 買い
-#名詞-接尾-サ変接続
-#
-# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
-# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
-# conjunctive form of inflectional words.
-# e.g. そう
-#名詞-接尾-助動詞語幹
-#
-# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
-# form of inflectional words and appear before the copula だ ("da").
-# e.g. 的, げ, がち
-#名詞-接尾-形容動詞語幹
-#
-# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
-# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
-#名詞-接尾-副詞可能
-#
-# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
-# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
-# to numbers.
-# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
-#名詞-接尾-助数詞
-#
-# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
-# e.g. (楽し) さ, (考え) 方
-#名詞-接尾-特殊
-#
-# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
-# together.
-# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
-#名詞-接続詞的
-#
-# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
-# semantically verb-like.
-# e.g. ごらん, ご覧, 御覧, 頂戴
-#名詞-動詞非自立的
-#
-# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
-# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
-# is いわく ("iwaku").
-#名詞-引用文字列
-#
-# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
-# behave like an adjective.
-# e.g. 申し訳, 仕方, とんでも, 違い
-#名詞-ナイ形容詞語幹
-#
-#####
-# prefix: unclassified prefixes
-#接頭詞
-#
-# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
-# excluding numerical expressions.
-# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
-#接頭詞-名詞接続
-#
-# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
-# in conjunctive form followed by なる/なさる/くださる.
-# e.g. お (読みなさい), お (座り)
-#接頭詞-動詞接続
-#
-# prefix-adjectival: Prefixes that attach to adjectives.
-# e.g. お (寒いですねえ), バカ (でかい)
-#接頭詞-形容詞接続
-#
-# prefix-numerical: Prefixes that attach to numerical expressions.
-# e.g. 約, およそ, 毎時
-#接頭詞-数接続
-#
-#####
-# verb: unclassified verbs
-#動詞
-#
-# verb-main:
-#動詞-自立
-#
-# verb-auxiliary:
-#動詞-非自立
-#
-# verb-suffix:
-#動詞-接尾
-#
-#####
-# adjective: unclassified adjectives
-#形容詞
-#
-# adjective-main:
-#形容詞-自立
-#
-# adjective-auxiliary:
-#形容詞-非自立
-#
-# adjective-suffix:
-#形容詞-接尾
-#
-#####
-# adverb: unclassified adverbs
-#副詞
-#
-# adverb-misc: Words that can be segmented into one unit and where adnominal
-# modification is not possible.
-# e.g. あいかわらず, 多分
-#副詞-一般
-#
-# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
-# な, する, だ, etc.
-# e.g. こんなに, そんなに, あんなに, なにか, なんでも
-#副詞-助詞類接続
-#
-#####
-# adnominal: Words that only have noun-modifying forms.
-# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
-# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
-# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
-#連体詞
-#
-#####
-# conjunction: Conjunctions that can occur independently.
-# e.g. が, けれども, そして, じゃあ, それどころか
-接続詞
-#
-#####
-# particle: unclassified particles.
-助詞
-#
-# particle-case: case particles where the subclassification is undefined.
-助詞-格助詞
-#
-# particle-case-misc: Case particles.
-# e.g. から, が, で, と, に, へ, より, を, の, にて
-助詞-格助詞-一般
-#
-# particle-case-quote: the "to" that appears after nouns, a person’s speech,
-# quotation marks, expressions of decisions from a meeting, reasons, judgements,
-# conjectures, etc.
-# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
-助詞-格助詞-引用
-#
-# particle-case-compound: Compounds of particles and verbs that mainly behave
-# like case particles.
-# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
-# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
-# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
-# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
-# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
-# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
-# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
-# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
-助詞-格助詞-連語
-#
-# particle-conjunctive:
-# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
-# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
-# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
-助詞-接続助詞
-#
-# particle-dependency:
-# e.g. こそ, さえ, しか, すら, は, も, ぞ
-助詞-係助詞
-#
-# particle-adverbial:
-# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
-# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
-# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
-# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
-# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
-助詞-副助詞
-#
-# particle-interjective: particles with interjective grammatical roles.
-# e.g. (松島) や
-助詞-間投助詞
-#
-# particle-coordinate:
-# e.g. と, たり, だの, だり, とか, なり, や, やら
-助詞-並立助詞
-#
-# particle-final:
-# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
-# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
-助詞-終助詞
-#
-# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
-# adverbial, conjunctive, or sentence final. For example:
-# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
-# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
-# 「(祈りが届いたせい) か (, 試験に合格した.)」
-# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
-# e.g. か
-助詞-副助詞／並立助詞／終助詞
-#
-# particle-adnominalizer: The "no" that attaches to nouns and modifies
-# non-inflectional words.
-助詞-連体化
-#
-# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
-# that are giongo, giseigo, or gitaigo.
-# e.g. に, と
-助詞-副詞化
-#
-# particle-special: A particle that does not fit into one of the above classifications.
-# This includes particles that are used in Tanka, Haiku, and other poetry.
-# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
-助詞-特殊
-#
-#####
-# auxiliary-verb:
-助動詞
-#
-#####
-# interjection: Greetings and other exclamations.
-# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
-# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
-#感動詞
-#
-#####
-# symbol: unclassified Symbols.
-記号
-#
-# symbol-misc: A general symbol not in one of the categories below.
-# e.g. [○◎@$〒→+]
-記号-一般
-#
-# symbol-comma: Commas
-# e.g. [,、]
-記号-読点
-#
-# symbol-period: Periods and full stops.
-# e.g. [.．。]
-記号-句点
-#
-# symbol-space: Full-width whitespace.
-記号-空白
-#
-# symbol-open_bracket:
-# e.g. [({‘“『【]
-記号-括弧開
-#
-# symbol-close_bracket:
-# e.g. [)}’”』」】]
-記号-括弧閉
-#
-# symbol-alphabetic:
-#記号-アルファベット
-#
-#####
-# other: unclassified other
-#その他
-#
-# other-interjection: Words that are hard to classify as noun-suffixes or
-# sentence-final particles.
-# e.g. (だ)ァ
-その他-間投
-#
-#####
-# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
-# e.g. あの, うんと, えと
-フィラー
-#
-#####
-# non-verbal: non-verbal sound.
-非言語音
-#
-#####
-# fragment:
-#語断片
-#
-#####
-# unknown: unknown part of speech.
-#未知語
-#
-##### End of file
[21/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-9623: Disable
remote streaming in example configs by default. Adjust Upload Limit defaults
Posted by sh...@apache.org.
SOLR-9623: Disable remote streaming in example configs by default. Adjust Upload Limit defaults
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/4746ff0e
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/4746ff0e
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/4746ff0e
Branch: refs/heads/feature/autoscaling
Commit: 4746ff0ec8a008d42a44c6e6dd3e94cbb2886410
Parents: b1b566f
Author: Jan Høydahl <ja...@apache.org>
Authored: Tue Jun 20 11:00:08 2017 +0200
Committer: Jan Høydahl <ja...@apache.org>
Committed: Tue Jun 20 11:00:08 2017 +0200
----------------------------------------------------------------------
solr/CHANGES.txt | 2 ++
.../solr/collection1/conf/solrconfig.xml | 7 ++---
.../collection1/conf/dataimport-solrconfig.xml | 5 ++--
.../conf/contentstream-solrconfig.xml | 7 ++---
.../conf/dataimport-nodatasource-solrconfig.xml | 5 ++--
.../collection1/conf/dataimport-solrconfig.xml | 5 ++--
.../solr/collection1/conf/solrconfig.xml | 3 +--
.../conf/solrconfig-languageidentifier.xml | 3 +--
.../uima/solr/collection1/conf/solrconfig.xml | 4 +--
.../uima/uima-tokenizers-solrconfig.xml | 4 +--
.../java/org/apache/solr/core/SolrConfig.java | 6 +++--
.../conf/solrconfig-analytics-query.xml | 3 +--
.../conf/solrconfig-collapseqparser.xml | 3 +--
.../conf/solrconfig-components-name.xml | 3 +--
.../conf/solrconfig-delaying-component.xml | 2 +-
.../conf/solrconfig-doctransformers.xml | 2 +-
.../collection1/conf/solrconfig-elevate.xml | 3 +--
.../solr/collection1/conf/solrconfig-hash.xml | 2 +-
.../conf/solrconfig-master-throttled.xml | 3 +--
.../solr/collection1/conf/solrconfig-master.xml | 3 +--
.../conf/solrconfig-master1-keepOneBackup.xml | 3 +--
.../collection1/conf/solrconfig-master1.xml | 3 +--
.../collection1/conf/solrconfig-master2.xml | 3 +--
.../collection1/conf/solrconfig-master3.xml | 3 +--
.../collection1/conf/solrconfig-nocache.xml | 2 +-
.../conf/solrconfig-plugcollector.xml | 3 +--
.../collection1/conf/solrconfig-repeater.xml | 3 +--
.../solr/collection1/conf/solrconfig-slave.xml | 3 +--
.../solr/collection1/conf/solrconfig-slave1.xml | 3 +--
.../solr/collection1/conf/solrconfig-sql.xml | 2 +-
.../solr/collection1/conf/solrconfig.xml | 3 +--
.../solr/collection1/conf/solrconfig_perf.xml | 2 +-
.../example-DIH/solr/db/conf/solrconfig.xml | 15 +++++------
.../example-DIH/solr/mail/conf/solrconfig.xml | 15 +++++------
.../example-DIH/solr/solr/conf/solrconfig.xml | 15 +++++------
solr/example/files/conf/solrconfig.xml | 13 +++++----
.../basic_configs/conf/solrconfig.xml | 13 +++++----
.../conf/solrconfig.xml | 13 +++++----
.../conf/solrconfig.xml | 15 +++++------
solr/solr-ref-guide/src/content-streams.adoc | 28 +++++++++++++-------
.../src/requestdispatcher-in-solrconfig.adoc | 12 ++++-----
...g-data-with-solr-cell-using-apache-tika.adoc | 9 -------
.../solr/collection1/conf/solrconfig-slave1.xml | 3 +--
.../solr/collection1/conf/solrconfig-sql.xml | 2 +-
.../solrj/solr/collection1/conf/solrconfig.xml | 2 +-
.../solr/configsets/ml/conf/solrconfig.xml | 2 +-
.../solr/configsets/shared/conf/solrconfig.xml | 2 +-
.../configsets/streaming/conf/solrconfig.xml | 2 +-
.../solr/multicore/core0/conf/solrconfig.xml | 2 +-
.../solr/multicore/core1/conf/solrconfig.xml | 2 +-
50 files changed, 129 insertions(+), 144 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index b163a7f..cc67391 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -283,6 +283,8 @@ Other Changes
* SOLR-10779: JavaBinCodec should use close consistently rather than having marshal() and close() call finish()
(which closes the underlying stream). (Erick Erickson)
+* SOLR-9623: Disable remote streaming in example configs by default. Adjust Upload Limit defaults (janhoy, yonik)
+
================== 6.7.0 ==================
Consult the LUCENE_CHANGES.txt file for additional, low level, changes in this release.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/solrconfig.xml b/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/solrconfig.xml
index 6482286..74d903e 100644
--- a/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/solrconfig.xml
+++ b/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/solrconfig.xml
@@ -220,9 +220,10 @@
handleSelect=false will use solr1.1 style error formatting
-->
<requestDispatcher handleSelect="true" >
- <!--Make sure your system has some authentication before enabling remote streaming! -->
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
-
+ <!--Make sure your system has some authentication before enabling remote streaming!
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
+ -->
+
<!-- Set HTTP caching related parameters (for proxy caches and clients).
To get the behaviour of Solr 1.2 (ie: no caching related headers)
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-solrconfig.xml b/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-solrconfig.xml
index 611a250..7672cab 100644
--- a/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-solrconfig.xml
+++ b/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-solrconfig.xml
@@ -179,8 +179,9 @@
handleSelect=false will use solr1.1 style error formatting
-->
<requestDispatcher handleSelect="true" >
- <!--Make sure your system has some authentication before enabling remote streaming! -->
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <!--Make sure your system has some authentication before enabling remote streaming!
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
+ -->
<!-- Set HTTP caching related parameters (for proxy caches and clients).
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/contentstream-solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/contentstream-solrconfig.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/contentstream-solrconfig.xml
index e75bf0f..235b15c 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/contentstream-solrconfig.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/contentstream-solrconfig.xml
@@ -179,9 +179,10 @@
handleSelect=false will use solr1.1 style error formatting
-->
<requestDispatcher handleSelect="true" >
- <!--Make sure your system has some authentication before enabling remote streaming! -->
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
-
+ <!--Make sure your system has some authentication before enabling remote streaming!
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
+ -->
+
<!-- Set HTTP caching related parameters (for proxy caches and clients).
To get the behaviour of Solr 1.2 (ie: no caching related headers)
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-nodatasource-solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-nodatasource-solrconfig.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-nodatasource-solrconfig.xml
index d445278..7f20677 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-nodatasource-solrconfig.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-nodatasource-solrconfig.xml
@@ -181,8 +181,9 @@
handleSelect=false will use solr1.1 style error formatting
-->
<requestDispatcher handleSelect="true" >
- <!--Make sure your system has some authentication before enabling remote streaming! -->
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <!--Make sure your system has some authentication before enabling remote streaming!
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
+ -->
<!-- Set HTTP caching related parameters (for proxy caches and clients).
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solrconfig.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solrconfig.xml
index 1029373..2eacf8a 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solrconfig.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solrconfig.xml
@@ -179,8 +179,9 @@
handleSelect=false will use solr1.1 style error formatting
-->
<requestDispatcher handleSelect="true" >
- <!--Make sure your system has some authentication before enabling remote streaming! -->
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <!--Make sure your system has some authentication before enabling remote streaming!
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
+ -->
<!-- Set HTTP caching related parameters (for proxy caches and clients).
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/solrconfig.xml b/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/solrconfig.xml
index ed33c6b..261263e 100644
--- a/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/solrconfig.xml
+++ b/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/solrconfig.xml
@@ -227,9 +227,8 @@
</highlighting>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/solrconfig-languageidentifier.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/solrconfig-languageidentifier.xml b/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/solrconfig-languageidentifier.xml
index 520d772..04b75f2 100644
--- a/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/solrconfig-languageidentifier.xml
+++ b/solr/contrib/langid/src/test-files/langid/solr/collection1/conf/solrconfig-languageidentifier.xml
@@ -48,9 +48,8 @@
<bool name="httpCaching">true</bool>
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/solrconfig.xml b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/solrconfig.xml
index d527bf2..a79db3f 100644
--- a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/solrconfig.xml
+++ b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/solrconfig.xml
@@ -325,8 +325,8 @@
Make sure your system has some authentication before enabling
remote streaming!
-->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000" />
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1" />
<!--
Set HTTP caching related parameters (for proxy caches and
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/contrib/uima/src/test-files/uima/uima-tokenizers-solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/uima-tokenizers-solrconfig.xml b/solr/contrib/uima/src/test-files/uima/uima-tokenizers-solrconfig.xml
index e33def7..1a0f58b 100644
--- a/solr/contrib/uima/src/test-files/uima/uima-tokenizers-solrconfig.xml
+++ b/solr/contrib/uima/src/test-files/uima/uima-tokenizers-solrconfig.xml
@@ -324,8 +324,8 @@
Make sure your system has some authentication before enabling
remote streaming!
-->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000" />
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1" />
<!--
Set HTTP caching related parameters (for proxy caches and
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/java/org/apache/solr/core/SolrConfig.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/core/SolrConfig.java b/solr/core/src/java/org/apache/solr/core/SolrConfig.java
index 4e7ab48..12fd6ef 100644
--- a/solr/core/src/java/org/apache/solr/core/SolrConfig.java
+++ b/solr/core/src/java/org/apache/solr/core/SolrConfig.java
@@ -298,10 +298,12 @@ public class SolrConfig extends Config implements MapSerializable {
updateHandlerInfo = loadUpdatehandlerInfo();
multipartUploadLimitKB = getInt(
- "requestDispatcher/requestParsers/@multipartUploadLimitInKB", 2048);
+ "requestDispatcher/requestParsers/@multipartUploadLimitInKB", Integer.MAX_VALUE);
+ if (multipartUploadLimitKB == -1) multipartUploadLimitKB = Integer.MAX_VALUE;
formUploadLimitKB = getInt(
- "requestDispatcher/requestParsers/@formdataUploadLimitInKB", 2048);
+ "requestDispatcher/requestParsers/@formdataUploadLimitInKB", Integer.MAX_VALUE);
+ if (formUploadLimitKB == -1) formUploadLimitKB = Integer.MAX_VALUE;
enableRemoteStreams = getBool(
"requestDispatcher/requestParsers/@enableRemoteStreaming", false);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-analytics-query.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-analytics-query.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-analytics-query.xml
index b5959cc..f729afa 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-analytics-query.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-analytics-query.xml
@@ -461,9 +461,8 @@ based HashBitset. -->
</highlighting>
</searchComponent>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-collapseqparser.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-collapseqparser.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-collapseqparser.xml
index 77b456c..8267451 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-collapseqparser.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-collapseqparser.xml
@@ -355,9 +355,8 @@ based HashBitset. -->
</highlighting>
</searchComponent>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-components-name.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-components-name.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-components-name.xml
index cda92d1..fe0e55c 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-components-name.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-components-name.xml
@@ -52,9 +52,8 @@
</arr>
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-delaying-component.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-delaying-component.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-delaying-component.xml
index 033a73e..91f1068 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-delaying-component.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-delaying-component.xml
@@ -35,7 +35,7 @@
</requestHandler>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching never304="true" />
</requestDispatcher>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-doctransformers.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-doctransformers.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-doctransformers.xml
index 5b269af..b242f11 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-doctransformers.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-doctransformers.xml
@@ -40,7 +40,7 @@
<requestHandler name="/select" class="solr.StandardRequestHandler"/>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
</requestDispatcher>
<!-- config for the admin interface -->
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-elevate.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-elevate.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-elevate.xml
index e190d68..03efed6 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-elevate.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-elevate.xml
@@ -150,9 +150,8 @@
</arr>
</requestHandler>-->
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-hash.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-hash.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-hash.xml
index 911fbb2..94cceb61 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-hash.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-hash.xml
@@ -47,7 +47,7 @@
</requestHandler>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
</requestDispatcher>
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-master-throttled.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master-throttled.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master-throttled.xml
index 5bc5ac7..516d504 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master-throttled.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master-throttled.xml
@@ -56,9 +56,8 @@
</lst>
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-master.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master.xml
index 75bbfe9..b1345ac 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master.xml
@@ -60,9 +60,8 @@
</lst>
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1-keepOneBackup.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1-keepOneBackup.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1-keepOneBackup.xml
index 034b19c..69f7659 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1-keepOneBackup.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1-keepOneBackup.xml
@@ -39,9 +39,8 @@
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1.xml
index fedb32a..db39b1f 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master1.xml
@@ -58,9 +58,8 @@
</lst>
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-master2.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master2.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master2.xml
index 778cfb7..91923c9 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master2.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master2.xml
@@ -56,9 +56,8 @@
</lst>
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-master3.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master3.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master3.xml
index 33d47fc..b03aef4 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-master3.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-master3.xml
@@ -57,9 +57,8 @@
</lst>
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-nocache.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-nocache.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-nocache.xml
index c6d33b2..15e58af 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-nocache.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-nocache.xml
@@ -35,7 +35,7 @@
<requestHandler name="standard" class="solr.StandardRequestHandler"/>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching never304="true" />
</requestDispatcher>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-plugcollector.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-plugcollector.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-plugcollector.xml
index 75f7ced..09f0974 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-plugcollector.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-plugcollector.xml
@@ -458,9 +458,8 @@ based HashBitset. -->
</highlighting>
</searchComponent>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-repeater.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-repeater.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-repeater.xml
index 511a13b..76c379c 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-repeater.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-repeater.xml
@@ -51,9 +51,8 @@
</lst>
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave.xml
index fc3926d..5ca7184 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave.xml
@@ -49,9 +49,8 @@
</lst>
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave1.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave1.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave1.xml
index 0e94c6c..aa2f8a4 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave1.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-slave1.xml
@@ -42,9 +42,8 @@
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig-sql.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig-sql.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig-sql.xml
index 10feac9..6a0c5b5 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig-sql.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig-sql.xml
@@ -45,7 +45,7 @@
</requestHandler>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
</requestDispatcher>
<requestHandler name="/replication" class="solr.ReplicationHandler" startup="lazy" />
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml
index 27f2e42..afbef84 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig.xml
@@ -460,9 +460,8 @@
</highlighting>
</searchComponent>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/core/src/test-files/solr/collection1/conf/solrconfig_perf.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/collection1/conf/solrconfig_perf.xml b/solr/core/src/test-files/solr/collection1/conf/solrconfig_perf.xml
index c0b297f..cc6f97b 100644
--- a/solr/core/src/test-files/solr/collection1/conf/solrconfig_perf.xml
+++ b/solr/core/src/test-files/solr/collection1/conf/solrconfig_perf.xml
@@ -62,7 +62,7 @@
<requestDispatcher handleSelect="true" >
<!--Make sure your system has some authentication before enabling remote streaming! -->
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048000" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
<httpCaching lastModifiedFrom="openTime"
etagSeed="Solr">
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/example/example-DIH/solr/db/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/db/conf/solrconfig.xml b/solr/example/example-DIH/solr/db/conf/solrconfig.xml
index 8513aa0..46e7b87 100644
--- a/solr/example/example-DIH/solr/db/conf/solrconfig.xml
+++ b/solr/example/example-DIH/solr/db/conf/solrconfig.xml
@@ -628,15 +628,14 @@
plugins.
*** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
-
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
+
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
addHttpRequestToContext="false"/>
+ -->
<!-- HTTP Caching
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/example/example-DIH/solr/mail/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/mail/conf/solrconfig.xml b/solr/example/example-DIH/solr/mail/conf/solrconfig.xml
index 7120e43..950a891 100644
--- a/solr/example/example-DIH/solr/mail/conf/solrconfig.xml
+++ b/solr/example/example-DIH/solr/mail/conf/solrconfig.xml
@@ -631,15 +631,14 @@
plugins.
*** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
-
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
+
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
addHttpRequestToContext="false"/>
+ -->
<!-- HTTP Caching
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/example/example-DIH/solr/solr/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/solr/conf/solrconfig.xml b/solr/example/example-DIH/solr/solr/conf/solrconfig.xml
index 5fc9711..0fd689f 100644
--- a/solr/example/example-DIH/solr/solr/conf/solrconfig.xml
+++ b/solr/example/example-DIH/solr/solr/conf/solrconfig.xml
@@ -628,15 +628,14 @@
plugins.
*** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
-
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
+
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
addHttpRequestToContext="false"/>
+ -->
<!-- HTTP Caching
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/example/files/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/example/files/conf/solrconfig.xml b/solr/example/files/conf/solrconfig.xml
index 35ec28e..d16ddb1 100644
--- a/solr/example/files/conf/solrconfig.xml
+++ b/solr/example/files/conf/solrconfig.xml
@@ -626,15 +626,14 @@
plugins.
*** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
addHttpRequestToContext="false"/>
+ -->
<!-- HTTP Caching
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml b/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
index 770ac60..64d59fc 100644
--- a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
+++ b/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
@@ -646,15 +646,14 @@
plugins.
*** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
addHttpRequestToContext="false"/>
+ -->
<!-- HTTP Caching
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml b/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
index 33ef773..1cb477b 100644
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
@@ -646,15 +646,14 @@
plugins.
*** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
addHttpRequestToContext="false"/>
+ -->
<!-- HTTP Caching
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml b/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml
index 698213d..b1ad3a5 100644
--- a/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml
+++ b/solr/server/solr/configsets/sample_techproducts_configs/conf/solrconfig.xml
@@ -678,15 +678,14 @@
plugins.
*** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
-
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
+
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
addHttpRequestToContext="false"/>
+ -->
<!-- HTTP Caching
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solr-ref-guide/src/content-streams.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/content-streams.adoc b/solr/solr-ref-guide/src/content-streams.adoc
index 438fa77..2dc6404 100644
--- a/solr/solr-ref-guide/src/content-streams.adoc
+++ b/solr/solr-ref-guide/src/content-streams.adoc
@@ -39,23 +39,33 @@ By default, curl sends a `contentType="application/x-www-form-urlencoded"` heade
Remote streaming lets you send the contents of a URL as a stream to a given SolrRequestHandler. You could use remote streaming to send a remote or local file to an update plugin.
-For convenience, remote streaming is enabled in most of the example `solrconfig.xml` files included with Solr, however it is not recommended in a production situation without additional security between you and untrusted remote clients.
+Remote streaming is disabled by default. Enabling it is not recommended in a production situation without additional security between you and untrusted remote clients.
[source,xml]
----
- <!-- *** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
- -->
- <requestParsers enableRemoteStreaming="true" />
+ *** WARNING ***
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
+
+ <requestParsers enableRemoteStreaming="false"...>
----
-The default behavior, when `enableRemoteStreaming` is not specified in `solrconfig.xml` is to _not_ allow remote streaming (i.e., `enableRemoteStreaming="false"`).
+When `enableRemoteStreaming` is not specified in `solrconfig.xml`, the default behavior is to _not_ allow remote streaming (i.e., `enableRemoteStreaming="false"`).
+
+Remote streaming can also be enabled through the <<config-api.adoc,Config API>> as follows:
+
+[source]
+----
+curl -d '
+{
+ "set-property" : {"requestDispatcher.requestParsers.enableRemoteStreaming":true}
+}
+' http://localhost:8983/solr/techproducts/config -H 'Content-type:application/json'
+----
[IMPORTANT]
====
-If you `enableRemoteStreaming="true"` is used, be aware that this allows _anyone_ to send a request to any URL or local file. If <<ContentStreams-DebuggingRequests,DumpRequestHandler>> is enabled, it will allow anyone to view any file on your system.
+If `enableRemoteStreaming="true"` is used, be aware that this allows _anyone_ to send a request to any URL or local file. If <<ContentStreams-DebuggingRequests,DumpRequestHandler>> is enabled, it will allow anyone to view any file on your system.
====
[[ContentStreams-DebuggingRequests]]
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solr-ref-guide/src/requestdispatcher-in-solrconfig.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/requestdispatcher-in-solrconfig.adoc b/solr/solr-ref-guide/src/requestdispatcher-in-solrconfig.adoc
index 430b404..659dd41 100644
--- a/solr/solr-ref-guide/src/requestdispatcher-in-solrconfig.adoc
+++ b/solr/solr-ref-guide/src/requestdispatcher-in-solrconfig.adoc
@@ -46,20 +46,20 @@ In recent versions of Solr, a `/select` requestHandler is defined by default, so
The `<requestParsers>` sub-element controls values related to parsing requests. This is an empty XML element that doesn't have any content, only attributes.
-The attribute `enableRemoteStreaming` controls whether remote streaming of content is allowed. If set to `false`, streaming will not be allowed. Setting it to `true` (the default) lets you specify the location of content to be streamed using `stream.file` or `stream.url` parameters.
+The attribute `enableRemoteStreaming` controls whether remote streaming of content is allowed. If omitted or set to `false` (the default), streaming will not be allowed. Setting it to `true` lets you specify the location of content to be streamed using `stream.file` or `stream.url` parameters.
-If you enable remote streaming, be sure that you have authentication enabled. Otherwise, someone could potentially gain access to your content by accessing arbitrary URLs. It's also a good idea to place Solr behind a firewall to prevent it being accessed from untrusted clients.
+If you enable remote streaming, be sure that you have authentication enabled. Otherwise, someone could potentially gain access to your content by accessing arbitrary URLs. It's also a good idea to place Solr behind a firewall to prevent it from being accessed from untrusted clients.
-The attribute `multipartUploadLimitInKB` sets an upper limit in kilobytes on the size of a document that may be submitted in a multi-part HTTP POST request. The value specified is multiplied by 1024 to determine the size in bytes.
+The attribute `multipartUploadLimitInKB` sets an upper limit in kilobytes on the size of a document that may be submitted in a multi-part HTTP POST request. The value specified is multiplied by 1024 to determine the size in bytes. A value of `-1` means MAX_INT, which is also the system default if omitted.
-The attribute `formdataUploadLimitInKB` sets a limit in kilobytes on the size of form data (application/x-www-form-urlencoded) submitted in a HTTP POST request, which can be used to pass request parameters that will not fit in a URL.
+The attribute `formdataUploadLimitInKB` sets a limit in kilobytes on the size of form data (application/x-www-form-urlencoded) submitted in a HTTP POST request, which can be used to pass request parameters that will not fit in a URL. A value of `-1` means MAX_INT, which is also the system default if omitted.
The attribute `addHttpRequestToContext` can be used to indicate that the original `HttpServletRequest` object should be included in the context map of the `SolrQueryRequest` using the key `httpRequest`. This `HttpServletRequest` is not used by any Solr component, but may be useful when developing custom plugins.
[source,xml]
----
-<requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
+<requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="2048"
formdataUploadLimitInKB="2048"
addHttpRequestToContext="false" />
----
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solr-ref-guide/src/uploading-data-with-solr-cell-using-apache-tika.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/uploading-data-with-solr-cell-using-apache-tika.adoc b/solr/solr-ref-guide/src/uploading-data-with-solr-cell-using-apache-tika.adoc
index 8096e8c..894e949 100644
--- a/solr/solr-ref-guide/src/uploading-data-with-solr-cell-using-apache-tika.adoc
+++ b/solr/solr-ref-guide/src/uploading-data-with-solr-cell-using-apache-tika.adoc
@@ -216,15 +216,6 @@ The `tika.config` entry points to a file containing a Tika configuration. The `d
* `EEEE, dd-MMM-yy HH:mm:ss zzz`
* `EEE MMM d HH:mm:ss yyyy`
-You may also need to adjust the `multipartUploadLimitInKB` attribute as follows if you are submitting very large documents.
-
-[source,xml]
-----
-<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="20480" />
- ...
-----
-
[[UploadingDatawithSolrCellusingApacheTika-Parserspecificproperties]]
=== Parser-Specific Properties
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-slave1.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-slave1.xml b/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-slave1.xml
index c527d7b..9114cfd 100644
--- a/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-slave1.xml
+++ b/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-slave1.xml
@@ -47,9 +47,8 @@
</requestHandler>
- <!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true">
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048"/>
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1"/>
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-sql.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-sql.xml b/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-sql.xml
index 10feac9..6a0c5b5 100644
--- a/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-sql.xml
+++ b/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig-sql.xml
@@ -45,7 +45,7 @@
</requestHandler>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
</requestDispatcher>
<requestHandler name="/replication" class="solr.ReplicationHandler" startup="lazy" />
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig.xml b/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig.xml
index 3368b69..a2db090 100644
--- a/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig.xml
+++ b/solr/solrj/src/test-files/solrj/solr/collection1/conf/solrconfig.xml
@@ -36,7 +36,7 @@
</updateHandler>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
</requestDispatcher>
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/solrconfig.xml b/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/solrconfig.xml
index 6b10869..b404e87 100644
--- a/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/solrconfig.xml
+++ b/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/solrconfig.xml
@@ -37,7 +37,7 @@
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
</requestDispatcher>
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/solrconfig.xml b/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/solrconfig.xml
index 0b34685..6beb0b7 100644
--- a/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/solrconfig.xml
+++ b/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/solrconfig.xml
@@ -36,7 +36,7 @@
</updateHandler>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
</requestDispatcher>
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/solrconfig.xml b/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/solrconfig.xml
index bb98650..c7985d2 100644
--- a/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/solrconfig.xml
+++ b/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/solrconfig.xml
@@ -37,7 +37,7 @@
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" />
</requestDispatcher>
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/solrconfig.xml b/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/solrconfig.xml
index e49a3b7..58a7892 100644
--- a/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/solrconfig.xml
+++ b/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/solrconfig.xml
@@ -58,7 +58,7 @@
</updateHandler>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" formdataUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" formdataUploadLimitInKB="-1" />
</requestDispatcher>
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/4746ff0e/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/solrconfig.xml b/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/solrconfig.xml
index 825070a..81ee32a 100644
--- a/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/solrconfig.xml
+++ b/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/solrconfig.xml
@@ -58,7 +58,7 @@
</updateHandler>
<requestDispatcher handleSelect="true" >
- <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" formdataUploadLimitInKB="2048" />
+ <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="-1" formdataUploadLimitInKB="-1" />
</requestDispatcher>
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />
[36/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-4646: Add the
word "optionally" to refGuide: * optionally treats "and" and "or" as "AND"
and "OR" in Lucene syntax mode.
Posted by sh...@apache.org.
SOLR-4646: Add the word "optionally" to refGuide:
* optionally treats "and" and "or" as "AND" and "OR" in Lucene syntax mode.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/3bb8939a
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/3bb8939a
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/3bb8939a
Branch: refs/heads/feature/autoscaling
Commit: 3bb8939afec6b6e26689de580ddc5311bd5f0680
Parents: 8648b00
Author: Jan Høydahl <ja...@apache.org>
Authored: Tue Jun 20 13:41:31 2017 +0200
Committer: Jan Høydahl <ja...@apache.org>
Committed: Tue Jun 20 13:41:31 2017 +0200
----------------------------------------------------------------------
solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/3bb8939a/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc b/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc
index e949a61..c4e0fde 100644
--- a/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc
+++ b/solr/solr-ref-guide/src/the-extended-dismax-query-parser.adoc
@@ -24,7 +24,7 @@ In addition to supporting all the DisMax query parser parameters, Extended Disma
* supports the <<the-standard-query-parser.adoc#the-standard-query-parser,full Lucene query parser syntax>>.
* supports queries such as AND, OR, NOT, -, and +.
-* treats "and" and "or" as "AND" and "OR" in Lucene syntax mode.
+* optionally treats "and" and "or" as "AND" and "OR" in Lucene syntax mode.
* respects the 'magic field' names `\_val_` and `\_query_`. These are not a real fields in the Schema, but if used it helps do special things (like a function query in the case of `\_val_` or a nested query in the case of `\_query_`). If `\_val_` is used in a term or phrase query, the value is parsed as a function.
* includes improved smart partial escaping in the case of syntax errors; fielded queries, +/-, and phrase queries are still supported in this mode.
* improves proximity boosting by using word shingles; you do not need the query to match all words in the document before proximity boosting is applied.
[49/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10923:
AutoScalingHandlerTest.testPolicyAndPreferences() failure: Adding a policy
with 'cores' attribute should not have succeeded
Posted by sh...@apache.org.
SOLR-10923: AutoScalingHandlerTest.testPolicyAndPreferences() failure: Adding a policy with 'cores' attribute should not have succeeded
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/2d26d7e8
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/2d26d7e8
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/2d26d7e8
Branch: refs/heads/feature/autoscaling
Commit: 2d26d7e8718960842125ba42e078612744ddaf90
Parents: 1a58412
Author: Cao Manh Dat <da...@apache.org>
Authored: Wed Jun 21 09:53:23 2017 +0700
Committer: Cao Manh Dat <da...@apache.org>
Committed: Wed Jun 21 09:53:23 2017 +0700
----------------------------------------------------------------------
.../org/apache/solr/cloud/autoscaling/AutoScalingHandlerTest.java | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/2d26d7e8/solr/core/src/test/org/apache/solr/cloud/autoscaling/AutoScalingHandlerTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/autoscaling/AutoScalingHandlerTest.java b/solr/core/src/test/org/apache/solr/cloud/autoscaling/AutoScalingHandlerTest.java
index 830bef2..d9f0388 100644
--- a/solr/core/src/test/org/apache/solr/cloud/autoscaling/AutoScalingHandlerTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/autoscaling/AutoScalingHandlerTest.java
@@ -80,7 +80,8 @@ public class AutoScalingHandlerTest extends SolrCloudTestCase {
NamedList<Object> response = null;
try {
response = solrClient.request(req);
- fail("Adding a policy with 'cores' attribute should not have succeeded.");
+ String errorMsg = (String) ((NamedList)response.get("error")).get("msg");
+ assertTrue(errorMsg.contains("cores is only allowed in 'cluster-policy'"));
} catch (SolrServerException e) {
// todo one of these catch blocks should not be needed after SOLR-10768
if (e.getRootCause() instanceof HttpSolrClient.RemoteSolrException) {
[42/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574:
Reverting previous commits to tackle test failues
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml b/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
new file mode 100644
index 0000000..64d59fc
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
@@ -0,0 +1,1408 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!--
+ For more details about configurations options that may appear in
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+ <!-- In all configuration below, a prefix of "solr." for class names
+ is an alias that causes solr to search appropriate packages,
+ including org.apache.solr.(search|update|request|core|analysis)
+
+ You may also specify a fully qualified Java classname if you
+ have your own custom plugins.
+ -->
+
+ <!-- Controls what version of Lucene various components of Solr
+ adhere to. Generally, you want to use the latest version to
+ get all bug fixes and improvements. It is highly recommended
+ that you fully re-index after changing this setting as it can
+ affect both how text is indexed and queried.
+ -->
+ <luceneMatchVersion>7.0.0</luceneMatchVersion>
+
+ <!-- <lib/> directives can be used to instruct Solr to load any Jars
+ identified and use them to resolve any "plugins" specified in
+ your solrconfig.xml or schema.xml (ie: Analyzers, Request
+ Handlers, etc...).
+
+ All directories and paths are resolved relative to the
+ instanceDir.
+
+ Please note that <lib/> directives are processed in the order
+ that they appear in your solrconfig.xml file, and are "stacked"
+ on top of each other when building a ClassLoader - so if you have
+ plugin jars with dependencies on other jars, the "lower level"
+ dependency jars should be loaded first.
+
+ If a "./lib" directory exists in your instanceDir, all files
+ found in it are included as if you had used the following
+ syntax...
+
+ <lib dir="./lib" />
+ -->
+
+ <!-- A 'dir' option by itself adds any files found in the directory
+ to the classpath, this is useful for including all jars in a
+ directory.
+
+ When a 'regex' is specified in addition to a 'dir', only the
+ files in that directory which completely match the regex
+ (anchored on both ends) will be included.
+
+ If a 'dir' option (with or without a regex) is used and nothing
+ is found that matches, a warning will be logged.
+
+ The examples below can be used to load some solr-contribs along
+ with their external dependencies.
+ -->
+ <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
+ <!-- an exact 'path' can be used instead of a 'dir' to specify a
+ specific jar file. This will cause a serious error to be logged
+ if it can't be loaded.
+ -->
+ <!--
+ <lib path="../a-jar-that-does-not-exist.jar" />
+ -->
+
+ <!-- Data Directory
+
+ Used to specify an alternate directory to hold all index data
+ other than the default ./data under the Solr home. If
+ replication is in use, this should match the replication
+ configuration.
+ -->
+ <dataDir>${solr.data.dir:}</dataDir>
+
+
+ <!-- The DirectoryFactory to use for indexes.
+
+ solr.StandardDirectoryFactory is filesystem
+ based and tries to pick the best implementation for the current
+ JVM and platform. solr.NRTCachingDirectoryFactory, the default,
+ wraps solr.StandardDirectoryFactory and caches small files in memory
+ for better NRT performance.
+
+ One can force a particular implementation via solr.MMapDirectoryFactory,
+ solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+ solr.RAMDirectoryFactory is memory based and not persistent.
+ -->
+ <directoryFactory name="DirectoryFactory"
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
+
+ <!-- The CodecFactory for defining the format of the inverted index.
+ The default implementation is SchemaCodecFactory, which is the official Lucene
+ index format, but hooks into the schema to provide per-field customization of
+ the postings lists and per-document values in the fieldType element
+ (postingsFormat/docValuesFormat). Note that most of the alternative implementations
+ are experimental, so if you choose to customize the index format, it's a good
+ idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
+ before upgrading to a newer version to avoid unnecessary reindexing.
+ A "compressionMode" string element can be added to <codecFactory> to choose
+ between the existing compression modes in the default codec: "BEST_SPEED" (default)
+ or "BEST_COMPRESSION".
+ -->
+ <codecFactory class="solr.SchemaCodecFactory"/>
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Index Config - These settings control low-level behavior of indexing
+ Most example settings here show the default value, but are commented
+ out, to more easily see where customizations have been made.
+
+ Note: This replaces <indexDefaults> and <mainIndex> from older versions
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+ <indexConfig>
+ <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+ LimitTokenCountFilterFactory in your fieldType definition. E.g.
+ <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+ -->
+ <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+ <!-- <writeLockTimeout>1000</writeLockTimeout> -->
+
+ <!-- Expert: Enabling compound file will use less files for the index,
+ using fewer file descriptors on the expense of performance decrease.
+ Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+ <!-- <useCompoundFile>false</useCompoundFile> -->
+
+ <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+ indexing for buffering added documents and deletions before they are
+ flushed to the Directory.
+ maxBufferedDocs sets a limit on the number of documents buffered
+ before flushing.
+ If both ramBufferSizeMB and maxBufferedDocs is set, then
+ Lucene will flush based on whichever limit is hit first. -->
+ <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
+ <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+ <!-- Expert: Merge Policy
+ The Merge Policy in Lucene controls how merging of segments is done.
+ The default since Solr/Lucene 3.3 is TieredMergePolicy.
+ The default since Lucene 2.3 was the LogByteSizeMergePolicy,
+ Even older versions of Lucene used LogDocMergePolicy.
+ -->
+ <!--
+ <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
+ <int name="maxMergeAtOnce">10</int>
+ <int name="segmentsPerTier">10</int>
+ <double name="noCFSRatio">0.1</double>
+ </mergePolicyFactory>
+ -->
+
+ <!-- Expert: Merge Scheduler
+ The Merge Scheduler in Lucene controls how merges are
+ performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
+ can perform merges in the background using separate threads.
+ The SerialMergeScheduler (Lucene 2.2 default) does not.
+ -->
+ <!--
+ <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+ -->
+
+ <!-- LockFactory
+
+ This option specifies which Lucene LockFactory implementation
+ to use.
+
+ single = SingleInstanceLockFactory - suggested for a
+ read-only index or when there is no possibility of
+ another process trying to modify the index.
+ native = NativeFSLockFactory - uses OS native file locking.
+ Do not use when multiple solr webapps in the same
+ JVM are attempting to share a single index.
+ simple = SimpleFSLockFactory - uses a plain file for locking
+
+ Defaults: 'native' is default for Solr3.6 and later, otherwise
+ 'simple' is the default
+
+ More details on the nuances of each LockFactory...
+ http://wiki.apache.org/lucene-java/AvailableLockFactories
+ -->
+ <lockType>${solr.lock.type:native}</lockType>
+
+ <!-- Commit Deletion Policy
+ Custom deletion policies can be specified here. The class must
+ implement org.apache.lucene.index.IndexDeletionPolicy.
+
+ The default Solr IndexDeletionPolicy implementation supports
+ deleting index commit points on number of commits, age of
+ commit point and optimized status.
+
+ The latest commit point should always be preserved regardless
+ of the criteria.
+ -->
+ <!--
+ <deletionPolicy class="solr.SolrDeletionPolicy">
+ -->
+ <!-- The number of commit points to be kept -->
+ <!-- <str name="maxCommitsToKeep">1</str> -->
+ <!-- The number of optimized commit points to be kept -->
+ <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+ <!--
+ Delete all commit points once they have reached the given age.
+ Supports DateMathParser syntax e.g.
+ -->
+ <!--
+ <str name="maxCommitAge">30MINUTES</str>
+ <str name="maxCommitAge">1DAY</str>
+ -->
+ <!--
+ </deletionPolicy>
+ -->
+
+ <!-- Lucene Infostream
+
+ To aid in advanced debugging, Lucene provides an "InfoStream"
+ of detailed information when indexing.
+
+ Setting The value to true will instruct the underlying Lucene
+ IndexWriter to write its debugging info the specified file
+ -->
+ <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
+ </indexConfig>
+
+
+ <!-- JMX
+
+ This example enables JMX if and only if an existing MBeanServer
+ is found, use this if you want to configure JMX through JVM
+ parameters. Remove this to disable exposing Solr configuration
+ and statistics to JMX.
+
+ For more details see http://wiki.apache.org/solr/SolrJmx
+ -->
+ <jmx />
+ <!-- If you want to connect to a particular server, specify the
+ agentId
+ -->
+ <!-- <jmx agentId="myAgent" /> -->
+ <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+ <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+ -->
+
+ <!-- The default high-performance update handler -->
+ <updateHandler class="solr.DirectUpdateHandler2">
+
+ <!-- Enables a transaction log, used for real-time get, durability, and
+ and solr cloud replica recovery. The log can grow as big as
+ uncommitted changes to the index, so use of a hard autoCommit
+ is recommended (see below).
+ "dir" - the target directory for transaction logs, defaults to the
+ solr data directory.
+ "numVersionBuckets" - sets the number of buckets used to keep
+ track of max version values when checking for re-ordered
+ updates; increase this value to reduce the cost of
+ synchronizing access to version buckets during high-volume
+ indexing, this requires 8 bytes (long) * numVersionBuckets
+ of heap space per Solr core.
+ -->
+ <updateLog>
+ <str name="dir">${solr.ulog.dir:}</str>
+ <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
+ </updateLog>
+
+ <!-- AutoCommit
+
+ Perform a hard commit automatically under certain conditions.
+ Instead of enabling autoCommit, consider using "commitWithin"
+ when adding documents.
+
+ http://wiki.apache.org/solr/UpdateXmlMessages
+
+ maxDocs - Maximum number of documents to add since the last
+ commit before automatically triggering a new commit.
+
+ maxTime - Maximum amount of time in ms that is allowed to pass
+ since a document was added before automatically
+ triggering a new commit.
+ openSearcher - if false, the commit causes recent index changes
+ to be flushed to stable storage, but does not cause a new
+ searcher to be opened to make those changes visible.
+
+ If the updateLog is enabled, then it's highly recommended to
+ have some sort of hard autoCommit to limit the log size.
+ -->
+ <autoCommit>
+ <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+ <openSearcher>false</openSearcher>
+ </autoCommit>
+
+ <!-- softAutoCommit is like autoCommit except it causes a
+ 'soft' commit which only ensures that changes are visible
+ but does not ensure that data is synced to disk. This is
+ faster and more near-realtime friendly than a hard commit.
+ -->
+
+ <autoSoftCommit>
+ <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+ </autoSoftCommit>
+
+ <!-- Update Related Event Listeners
+
+ Various IndexWriter related events can trigger Listeners to
+ take actions.
+
+ postCommit - fired after every commit or optimize command
+ postOptimize - fired after every optimize command
+ -->
+ <!-- The RunExecutableListener executes an external command from a
+ hook such as postCommit or postOptimize.
+
+ exe - the name of the executable to run
+ dir - dir to use as the current working directory. (default=".")
+ wait - the calling thread waits until the executable returns.
+ (default="true")
+ args - the arguments to pass to the program. (default is none)
+ env - environment variables to set. (default is none)
+ -->
+ <!-- This example shows how RunExecutableListener could be used
+ with the script based replication...
+ http://wiki.apache.org/solr/CollectionDistribution
+ -->
+ <!--
+ <listener event="postCommit" class="solr.RunExecutableListener">
+ <str name="exe">solr/bin/snapshooter</str>
+ <str name="dir">.</str>
+ <bool name="wait">true</bool>
+ <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
+ <arr name="env"> <str>MYVAR=val1</str> </arr>
+ </listener>
+ -->
+
+ </updateHandler>
+
+ <!-- IndexReaderFactory
+
+ Use the following format to specify a custom IndexReaderFactory,
+ which allows for alternate IndexReader implementations.
+
+ ** Experimental Feature **
+
+ Please note - Using a custom IndexReaderFactory may prevent
+ certain other features from working. The API to
+ IndexReaderFactory may change without warning or may even be
+ removed from future releases if the problems cannot be
+ resolved.
+
+
+ ** Features that may not work with custom IndexReaderFactory **
+
+ The ReplicationHandler assumes a disk-resident index. Using a
+ custom IndexReader implementation may cause incompatibility
+ with ReplicationHandler and may cause replication to not work
+ correctly. See SOLR-1366 for details.
+
+ -->
+ <!--
+ <indexReaderFactory name="IndexReaderFactory" class="package.class">
+ <str name="someArg">Some Value</str>
+ </indexReaderFactory >
+ -->
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Query section - these settings control query time things like caches
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
+ <query>
+ <!-- Max Boolean Clauses
+
+ Maximum number of clauses in each BooleanQuery, an exception
+ is thrown if exceeded.
+
+ ** WARNING **
+
+ This option actually modifies a global Lucene property that
+ will affect all SolrCores. If multiple solrconfig.xml files
+ disagree on this property, the value at any given moment will
+ be based on the last SolrCore to be initialized.
+
+ -->
+ <maxBooleanClauses>1024</maxBooleanClauses>
+
+
+ <!-- Solr Internal Query Caches
+
+ There are two implementations of cache available for Solr,
+ LRUCache, based on a synchronized LinkedHashMap, and
+ FastLRUCache, based on a ConcurrentHashMap.
+
+ FastLRUCache has faster gets and slower puts in single
+ threaded operation and thus is generally faster than LRUCache
+ when the hit ratio of the cache is high (> 75%), and may be
+ faster under other scenarios on multi-cpu systems.
+ -->
+
+ <!-- Filter Cache
+
+ Cache used by SolrIndexSearcher for filters (DocSets),
+ unordered sets of *all* documents that match a query. When a
+ new searcher is opened, its caches may be prepopulated or
+ "autowarmed" using data from caches in the old searcher.
+ autowarmCount is the number of items to prepopulate. For
+ LRUCache, the autowarmed items will be the most recently
+ accessed items.
+
+ Parameters:
+ class - the SolrCache implementation LRUCache or
+ (LRUCache or FastLRUCache)
+ size - the maximum number of entries in the cache
+ initialSize - the initial capacity (number of entries) of
+ the cache. (see java.util.HashMap)
+ autowarmCount - the number of entries to prepopulate from
+ and old cache.
+ maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+ to occupy. Note that when this option is specified, the size
+ and initialSize parameters are ignored.
+ -->
+ <filterCache class="solr.FastLRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- Query Result Cache
+
+ Caches results of searches - ordered lists of document ids
+ (DocList) based on a query, a sort, and the range of documents requested.
+ Additional supported parameter by LRUCache:
+ maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+ to occupy
+ -->
+ <queryResultCache class="solr.LRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- Document Cache
+
+ Caches Lucene Document objects (the stored fields for each
+ document). Since Lucene internal document ids are transient,
+ this cache will not be autowarmed.
+ -->
+ <documentCache class="solr.LRUCache"
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+
+ <!-- custom cache currently used by block join -->
+ <cache name="perSegFilter"
+ class="solr.search.LRUCache"
+ size="10"
+ initialSize="0"
+ autowarmCount="10"
+ regenerator="solr.NoOpRegenerator" />
+
+ <!-- Field Value Cache
+
+ Cache used to hold field values that are quickly accessible
+ by document id. The fieldValueCache is created by default
+ even if not configured here.
+ -->
+ <!--
+ <fieldValueCache class="solr.FastLRUCache"
+ size="512"
+ autowarmCount="128"
+ showItems="32" />
+ -->
+
+ <!-- Custom Cache
+
+ Example of a generic cache. These caches may be accessed by
+ name through SolrIndexSearcher.getCache(),cacheLookup(), and
+ cacheInsert(). The purpose is to enable easy caching of
+ user/application level data. The regenerator argument should
+ be specified as an implementation of solr.CacheRegenerator
+ if autowarming is desired.
+ -->
+ <!--
+ <cache name="myUserCache"
+ class="solr.LRUCache"
+ size="4096"
+ initialSize="1024"
+ autowarmCount="1024"
+ regenerator="com.mycompany.MyRegenerator"
+ />
+ -->
+
+
+ <!-- Lazy Field Loading
+
+ If true, stored fields that are not requested will be loaded
+ lazily. This can result in a significant speed improvement
+ if the usual case is to not load all stored fields,
+ especially if the skipped fields are large compressed text
+ fields.
+ -->
+ <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+ <!-- Use Filter For Sorted Query
+
+ A possible optimization that attempts to use a filter to
+ satisfy a search. If the requested sort does not include
+ score, then the filterCache will be checked for a filter
+ matching the query. If found, the filter will be used as the
+ source of document ids, and then the sort will be applied to
+ that.
+
+ For most situations, this will not be useful unless you
+ frequently get the same search repeatedly with different sort
+ options, and none of them ever use "score"
+ -->
+ <!--
+ <useFilterForSortedQuery>true</useFilterForSortedQuery>
+ -->
+
+ <!-- Result Window Size
+
+ An optimization for use with the queryResultCache. When a search
+ is requested, a superset of the requested number of document ids
+ are collected. For example, if a search for a particular query
+ requests matching documents 10 through 19, and queryWindowSize is 50,
+ then documents 0 through 49 will be collected and cached. Any further
+ requests in that range can be satisfied via the cache.
+ -->
+ <queryResultWindowSize>20</queryResultWindowSize>
+
+ <!-- Maximum number of documents to cache for any entry in the
+ queryResultCache.
+ -->
+ <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+ <!-- Query Related Event Listeners
+
+ Various IndexSearcher related events can trigger Listeners to
+ take actions.
+
+ newSearcher - fired whenever a new searcher is being prepared
+ and there is a current searcher handling requests (aka
+ registered). It can be used to prime certain caches to
+ prevent long request times for certain requests.
+
+ firstSearcher - fired whenever a new searcher is being
+ prepared but there is no current registered searcher to handle
+ requests or to gain autowarming data from.
+
+
+ -->
+ <!-- QuerySenderListener takes an array of NamedList and executes a
+ local query request for each NamedList in sequence.
+ -->
+ <listener event="newSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <!--
+ <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
+ <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
+ -->
+ </arr>
+ </listener>
+ <listener event="firstSearcher" class="solr.QuerySenderListener">
+ <arr name="queries">
+ <!--
+ <lst>
+ <str name="q">static firstSearcher warming in solrconfig.xml</str>
+ </lst>
+ -->
+ </arr>
+ </listener>
+
+ <!-- Use Cold Searcher
+
+ If a search request comes in and there is no current
+ registered searcher, then immediately register the still
+ warming searcher and use it. If "false" then all requests
+ will block until the first searcher is done warming.
+ -->
+ <useColdSearcher>false</useColdSearcher>
+
+ </query>
+
+
+ <!-- Request Dispatcher
+
+ This section contains instructions for how the SolrDispatchFilter
+ should behave when processing requests for this SolrCore.
+
+ handleSelect is a legacy option that affects the behavior of requests
+ such as /select?qt=XXX
+
+ handleSelect="true" will cause the SolrDispatchFilter to process
+ the request and dispatch the query to a handler specified by the
+ "qt" param, assuming "/select" isn't already registered.
+
+ handleSelect="false" will cause the SolrDispatchFilter to
+ ignore "/select" requests, resulting in a 404 unless a handler
+ is explicitly registered with the name "/select"
+
+ handleSelect="true" is not recommended for new users, but is the default
+ for backwards compatibility
+ -->
+ <requestDispatcher handleSelect="false" >
+ <!-- Request Parsing
+
+ These settings indicate how Solr Requests may be parsed, and
+ what restrictions may be placed on the ContentStreams from
+ those requests
+
+ enableRemoteStreaming - enables use of the stream.file
+ and stream.url parameters for specifying remote streams.
+
+ multipartUploadLimitInKB - specifies the max size (in KiB) of
+ Multipart File Uploads that Solr will allow in a Request.
+
+ formdataUploadLimitInKB - specifies the max size (in KiB) of
+ form data (application/x-www-form-urlencoded) sent via
+ POST. You can use POST to pass request parameters not
+ fitting into the URL.
+
+ addHttpRequestToContext - if set to true, it will instruct
+ the requestParsers to include the original HttpServletRequest
+ object in the context map of the SolrQueryRequest under the
+ key "httpRequest". It will not be used by any of the existing
+ Solr components, but may be useful when developing custom
+ plugins.
+
+ *** WARNING ***
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
+
+ <requestParsers enableRemoteStreaming="false"
+ multipartUploadLimitInKB="-1"
+ formdataUploadLimitInKB="-1"
+ addHttpRequestToContext="false"/>
+ -->
+
+ <!-- HTTP Caching
+
+ Set HTTP caching related parameters (for proxy caches and clients).
+
+ The options below instruct Solr not to output any HTTP Caching
+ related headers
+ -->
+ <httpCaching never304="true" />
+ <!-- If you include a <cacheControl> directive, it will be used to
+ generate a Cache-Control header (as well as an Expires header
+ if the value contains "max-age=")
+
+ By default, no Cache-Control header is generated.
+
+ You can use the <cacheControl> option even if you have set
+ never304="true"
+ -->
+ <!--
+ <httpCaching never304="true" >
+ <cacheControl>max-age=30, public</cacheControl>
+ </httpCaching>
+ -->
+ <!-- To enable Solr to respond with automatically generated HTTP
+ Caching headers, and to response to Cache Validation requests
+ correctly, set the value of never304="false"
+
+ This will cause Solr to generate Last-Modified and ETag
+ headers based on the properties of the Index.
+
+ The following options can also be specified to affect the
+ values of these headers...
+
+ lastModFrom - the default value is "openTime" which means the
+ Last-Modified value (and validation against If-Modified-Since
+ requests) will all be relative to when the current Searcher
+ was opened. You can change it to lastModFrom="dirLastMod" if
+ you want the value to exactly correspond to when the physical
+ index was last modified.
+
+ etagSeed="..." is an option you can change to force the ETag
+ header (and validation against If-None-Match requests) to be
+ different even if the index has not changed (ie: when making
+ significant changes to your config file)
+
+ (lastModifiedFrom and etagSeed are both ignored if you use
+ the never304="true" option)
+ -->
+ <!--
+ <httpCaching lastModifiedFrom="openTime"
+ etagSeed="Solr">
+ <cacheControl>max-age=30, public</cacheControl>
+ </httpCaching>
+ -->
+ </requestDispatcher>
+
+ <!-- Request Handlers
+
+ http://wiki.apache.org/solr/SolrRequestHandler
+
+ Incoming queries will be dispatched to a specific handler by name
+ based on the path specified in the request.
+
+ Legacy behavior: If the request path uses "/select" but no Request
+ Handler has that name, and if handleSelect="true" has been specified in
+ the requestDispatcher, then the Request Handler is dispatched based on
+ the qt parameter. Handlers without a leading '/' are accessed this way
+ like so: http://host/app/[core/]select?qt=name If no qt is
+ given, then the requestHandler that declares default="true" will be
+ used or the one named "standard".
+
+ If a Request Handler is declared with startup="lazy", then it will
+ not be initialized until the first request that uses it.
+
+ -->
+ <!-- SearchHandler
+
+ http://wiki.apache.org/solr/SearchHandler
+
+ For processing Search Queries, the primary Request Handler
+ provided with Solr is "SearchHandler" It delegates to a sequent
+ of SearchComponents (see below) and supports distributed
+ queries across multiple shards
+ -->
+ <requestHandler name="/select" class="solr.SearchHandler">
+ <!-- default values for query parameters can be specified, these
+ will be overridden by parameters in the request
+ -->
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <int name="rows">10</int>
+ <!-- <str name="df">text</str> -->
+ </lst>
+ <!-- In addition to defaults, "appends" params can be specified
+ to identify values which should be appended to the list of
+ multi-val params from the query (or the existing "defaults").
+ -->
+ <!-- In this example, the param "fq=instock:true" would be appended to
+ any query time fq params the user may specify, as a mechanism for
+ partitioning the index, independent of any user selected filtering
+ that may also be desired (perhaps as a result of faceted searching).
+
+ NOTE: there is *absolutely* nothing a client can do to prevent these
+ "appends" values from being used, so don't use this mechanism
+ unless you are sure you always want it.
+ -->
+ <!--
+ <lst name="appends">
+ <str name="fq">inStock:true</str>
+ </lst>
+ -->
+ <!-- "invariants" are a way of letting the Solr maintainer lock down
+ the options available to Solr clients. Any params values
+ specified here are used regardless of what values may be specified
+ in either the query, the "defaults", or the "appends" params.
+
+ In this example, the facet.field and facet.query params would
+ be fixed, limiting the facets clients can use. Faceting is
+ not turned on by default - but if the client does specify
+ facet=true in the request, these are the only facets they
+ will be able to see counts for; regardless of what other
+ facet.field or facet.query params they may specify.
+
+ NOTE: there is *absolutely* nothing a client can do to prevent these
+ "invariants" values from being used, so don't use this mechanism
+ unless you are sure you always want it.
+ -->
+ <!--
+ <lst name="invariants">
+ <str name="facet.field">cat</str>
+ <str name="facet.field">manu_exact</str>
+ <str name="facet.query">price:[* TO 500]</str>
+ <str name="facet.query">price:[500 TO *]</str>
+ </lst>
+ -->
+ <!-- If the default list of SearchComponents is not desired, that
+ list can either be overridden completely, or components can be
+ prepended or appended to the default list. (see below)
+ -->
+ <!--
+ <arr name="components">
+ <str>nameOfCustomComponent1</str>
+ <str>nameOfCustomComponent2</str>
+ </arr>
+ -->
+ </requestHandler>
+
+ <!-- A request handler that returns indented JSON by default -->
+ <requestHandler name="/query" class="solr.SearchHandler">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="wt">json</str>
+ <str name="indent">true</str>
+ </lst>
+ </requestHandler>
+
+
+ <!-- A Robust Example
+
+ This example SearchHandler declaration shows off usage of the
+ SearchHandler with many defaults declared
+
+ Note that multiple instances of the same Request Handler
+ (SearchHandler) can be registered multiple times with different
+ names (and different init parameters)
+ -->
+ <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
+ </requestHandler>
+
+ <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
+ <lst name="defaults">
+ <str name="df">_text_</str>
+ </lst>
+ </initParams>
+
+ <!-- This enabled schemaless mode
+ <initParams path="/update/**">
+ <lst name="defaults">
+ <str name="update.chain">add-unknown-fields-to-the-schema</str>
+ </lst>
+ </initParams>
+ -->
+
+ <!-- Solr Cell Update Request Handler
+
+ http://wiki.apache.org/solr/ExtractingRequestHandler
+
+ -->
+ <requestHandler name="/update/extract"
+ startup="lazy"
+ class="solr.extraction.ExtractingRequestHandler" >
+ <lst name="defaults">
+ <str name="lowernames">true</str>
+ <str name="fmap.meta">ignored_</str>
+ <str name="fmap.content">_text_</str>
+ </lst>
+ </requestHandler>
+ <!-- Search Components
+
+ Search components are registered to SolrCore and used by
+ instances of SearchHandler (which can access them by name)
+
+ By default, the following components are available:
+
+ <searchComponent name="query" class="solr.QueryComponent" />
+ <searchComponent name="facet" class="solr.FacetComponent" />
+ <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
+ <searchComponent name="highlight" class="solr.HighlightComponent" />
+ <searchComponent name="stats" class="solr.StatsComponent" />
+ <searchComponent name="debug" class="solr.DebugComponent" />
+
+ Default configuration in a requestHandler would look like:
+
+ <arr name="components">
+ <str>query</str>
+ <str>facet</str>
+ <str>mlt</str>
+ <str>highlight</str>
+ <str>stats</str>
+ <str>debug</str>
+ </arr>
+
+ If you register a searchComponent to one of the standard names,
+ that will be used instead of the default.
+
+ To insert components before or after the 'standard' components, use:
+
+ <arr name="first-components">
+ <str>myFirstComponentName</str>
+ </arr>
+
+ <arr name="last-components">
+ <str>myLastComponentName</str>
+ </arr>
+
+ NOTE: The component registered with the name "debug" will
+ always be executed after the "last-components"
+
+ -->
+
+ <!-- Spell Check
+
+ The spell check component can return a list of alternative spelling
+ suggestions.
+
+ http://wiki.apache.org/solr/SpellCheckComponent
+ -->
+ <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+ <str name="queryAnalyzerFieldType">text_general</str>
+
+ <!-- Multiple "Spell Checkers" can be declared and used by this
+ component
+ -->
+
+ <!-- a spellchecker built from a field of the main index -->
+ <lst name="spellchecker">
+ <str name="name">default</str>
+ <str name="field">_text_</str>
+ <str name="classname">solr.DirectSolrSpellChecker</str>
+ <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+ <str name="distanceMeasure">internal</str>
+ <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+ <float name="accuracy">0.5</float>
+ <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+ <int name="maxEdits">2</int>
+ <!-- the minimum shared prefix when enumerating terms -->
+ <int name="minPrefix">1</int>
+ <!-- maximum number of inspections per result. -->
+ <int name="maxInspections">5</int>
+ <!-- minimum length of a query term to be considered for correction -->
+ <int name="minQueryLength">4</int>
+ <!-- maximum threshold of documents a query term can appear to be considered for correction -->
+ <float name="maxQueryFrequency">0.01</float>
+ <!-- uncomment this to require suggestions to occur in 1% of the documents
+ <float name="thresholdTokenFrequency">.01</float>
+ -->
+ </lst>
+
+ <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
+ <!--
+ <lst name="spellchecker">
+ <str name="name">wordbreak</str>
+ <str name="classname">solr.WordBreakSolrSpellChecker</str>
+ <str name="field">name</str>
+ <str name="combineWords">true</str>
+ <str name="breakWords">true</str>
+ <int name="maxChanges">10</int>
+ </lst>
+ -->
+ </searchComponent>
+
+ <!-- A request handler for demonstrating the spellcheck component.
+
+ NOTE: This is purely as an example. The whole purpose of the
+ SpellCheckComponent is to hook it into the request handler that
+ handles your normal user queries so that a separate request is
+ not needed to get suggestions.
+
+ IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+ NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+ See http://wiki.apache.org/solr/SpellCheckComponent for details
+ on the request parameters.
+ -->
+ <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <!-- Solr will use suggestions from both the 'default' spellchecker
+ and from the 'wordbreak' spellchecker and combine them.
+ collations (re-written queries) can include a combination of
+ corrections from both spellcheckers -->
+ <str name="spellcheck.dictionary">default</str>
+ <str name="spellcheck">on</str>
+ <str name="spellcheck.extendedResults">true</str>
+ <str name="spellcheck.count">10</str>
+ <str name="spellcheck.alternativeTermCount">5</str>
+ <str name="spellcheck.maxResultsForSuggest">5</str>
+ <str name="spellcheck.collate">true</str>
+ <str name="spellcheck.collateExtendedResults">true</str>
+ <str name="spellcheck.maxCollationTries">10</str>
+ <str name="spellcheck.maxCollations">5</str>
+ </lst>
+ <arr name="last-components">
+ <str>spellcheck</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Term Vector Component
+
+ http://wiki.apache.org/solr/TermVectorComponent
+ -->
+ <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
+
+ <!-- A request handler for demonstrating the term vector component
+
+ This is purely as an example.
+
+ In reality you will likely want to add the component to your
+ already specified request handlers.
+ -->
+ <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <bool name="tv">true</bool>
+ </lst>
+ <arr name="last-components">
+ <str>tvComponent</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Clustering Component. (Omitted here. See the default Solr example for a typical configuration.) -->
+
+ <!-- Terms Component
+
+ http://wiki.apache.org/solr/TermsComponent
+
+ A component to return terms and document frequency of those
+ terms
+ -->
+ <searchComponent name="terms" class="solr.TermsComponent"/>
+
+ <!-- A request handler for demonstrating the terms component -->
+ <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <bool name="terms">true</bool>
+ <bool name="distrib">false</bool>
+ </lst>
+ <arr name="components">
+ <str>terms</str>
+ </arr>
+ </requestHandler>
+
+
+ <!-- Query Elevation Component
+
+ http://wiki.apache.org/solr/QueryElevationComponent
+
+ a search component that enables you to configure the top
+ results for a given query regardless of the normal lucene
+ scoring.
+ -->
+ <searchComponent name="elevator" class="solr.QueryElevationComponent" >
+ <!-- pick a fieldType to analyze queries -->
+ <str name="queryFieldType">string</str>
+ <str name="config-file">elevate.xml</str>
+ </searchComponent>
+
+ <!-- A request handler for demonstrating the elevator component -->
+ <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
+ <arr name="last-components">
+ <str>elevator</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Highlighting Component
+
+ http://wiki.apache.org/solr/HighlightingParameters
+ -->
+ <searchComponent class="solr.HighlightComponent" name="highlight">
+ <highlighting>
+ <!-- Configure the standard fragmenter -->
+ <!-- This could most likely be commented out in the "default" case -->
+ <fragmenter name="gap"
+ default="true"
+ class="solr.highlight.GapFragmenter">
+ <lst name="defaults">
+ <int name="hl.fragsize">100</int>
+ </lst>
+ </fragmenter>
+
+ <!-- A regular-expression-based fragmenter
+ (for sentence extraction)
+ -->
+ <fragmenter name="regex"
+ class="solr.highlight.RegexFragmenter">
+ <lst name="defaults">
+ <!-- slightly smaller fragsizes work better because of slop -->
+ <int name="hl.fragsize">70</int>
+ <!-- allow 50% slop on fragment sizes -->
+ <float name="hl.regex.slop">0.5</float>
+ <!-- a basic sentence pattern -->
+ <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
+ </lst>
+ </fragmenter>
+
+ <!-- Configure the standard formatter -->
+ <formatter name="html"
+ default="true"
+ class="solr.highlight.HtmlFormatter">
+ <lst name="defaults">
+ <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+ <str name="hl.simple.post"><![CDATA[</em>]]></str>
+ </lst>
+ </formatter>
+
+ <!-- Configure the standard encoder -->
+ <encoder name="html"
+ class="solr.highlight.HtmlEncoder" />
+
+ <!-- Configure the standard fragListBuilder -->
+ <fragListBuilder name="simple"
+ class="solr.highlight.SimpleFragListBuilder"/>
+
+ <!-- Configure the single fragListBuilder -->
+ <fragListBuilder name="single"
+ class="solr.highlight.SingleFragListBuilder"/>
+
+ <!-- Configure the weighted fragListBuilder -->
+ <fragListBuilder name="weighted"
+ default="true"
+ class="solr.highlight.WeightedFragListBuilder"/>
+
+ <!-- default tag FragmentsBuilder -->
+ <fragmentsBuilder name="default"
+ default="true"
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
+ <!--
+ <lst name="defaults">
+ <str name="hl.multiValuedSeparatorChar">/</str>
+ </lst>
+ -->
+ </fragmentsBuilder>
+
+ <!-- multi-colored tag FragmentsBuilder -->
+ <fragmentsBuilder name="colored"
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
+ <lst name="defaults">
+ <str name="hl.tag.pre"><![CDATA[
+ <b style="background:yellow">,<b style="background:lawgreen">,
+ <b style="background:aquamarine">,<b style="background:magenta">,
+ <b style="background:palegreen">,<b style="background:coral">,
+ <b style="background:wheat">,<b style="background:khaki">,
+ <b style="background:lime">,<b style="background:deepskyblue">]]></str>
+ <str name="hl.tag.post"><![CDATA[</b>]]></str>
+ </lst>
+ </fragmentsBuilder>
+
+ <boundaryScanner name="default"
+ default="true"
+ class="solr.highlight.SimpleBoundaryScanner">
+ <lst name="defaults">
+ <str name="hl.bs.maxScan">10</str>
+ <str name="hl.bs.chars">.,!? 	 </str>
+ </lst>
+ </boundaryScanner>
+
+ <boundaryScanner name="breakIterator"
+ class="solr.highlight.BreakIteratorBoundaryScanner">
+ <lst name="defaults">
+ <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
+ <str name="hl.bs.type">WORD</str>
+ <!-- language and country are used when constructing Locale object. -->
+ <!-- And the Locale object will be used when getting instance of BreakIterator -->
+ <str name="hl.bs.language">en</str>
+ <str name="hl.bs.country">US</str>
+ </lst>
+ </boundaryScanner>
+ </highlighting>
+ </searchComponent>
+
+ <!-- Update Processors
+
+ Chains of Update Processor Factories for dealing with Update
+ Requests can be declared, and then used by name in Update
+ Request Processors
+
+ http://wiki.apache.org/solr/UpdateRequestProcessor
+
+ -->
+
+ <!-- Add unknown fields to the schema
+
+ An example field type guessing update processor that will
+ attempt to parse string-typed field values as Booleans, Longs,
+ Doubles, or Dates, and then add schema fields with the guessed
+ field types.
+
+ This requires that the schema is both managed and mutable, by
+ declaring schemaFactory as ManagedIndexSchemaFactory, with
+ mutable specified as true.
+
+ See http://wiki.apache.org/solr/GuessingFieldTypes
+ -->
+ <updateRequestProcessorChain name="add-unknown-fields-to-the-schema">
+ <!-- UUIDUpdateProcessorFactory will generate an id if none is present in the incoming document -->
+ <processor class="solr.UUIDUpdateProcessorFactory" />
+ <processor class="solr.RemoveBlankFieldUpdateProcessorFactory"/>
+ <processor class="solr.FieldNameMutatingUpdateProcessorFactory">
+ <str name="pattern">[^\w-\.]</str>
+ <str name="replacement">_</str>
+ </processor>
+ <processor class="solr.ParseBooleanFieldUpdateProcessorFactory"/>
+ <processor class="solr.ParseLongFieldUpdateProcessorFactory"/>
+ <processor class="solr.ParseDoubleFieldUpdateProcessorFactory"/>
+ <processor class="solr.ParseDateFieldUpdateProcessorFactory">
+ <arr name="format">
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss</str>
+ <str>yyyy-MM-dd'T'HH:mmZ</str>
+ <str>yyyy-MM-dd'T'HH:mm</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd HH:mm:ssZ</str>
+ <str>yyyy-MM-dd HH:mm:ss</str>
+ <str>yyyy-MM-dd HH:mmZ</str>
+ <str>yyyy-MM-dd HH:mm</str>
+ <str>yyyy-MM-dd</str>
+ </arr>
+ </processor>
+ <processor class="solr.AddSchemaFieldsUpdateProcessorFactory">
+ <str name="defaultFieldType">strings</str>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Boolean</str>
+ <str name="fieldType">booleans</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.util.Date</str>
+ <str name="fieldType">pdates</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Long</str>
+ <str name="valueClass">java.lang.Integer</str>
+ <str name="fieldType">plongs</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Number</str>
+ <str name="fieldType">pdoubles</str>
+ </lst>
+ </processor>
+
+ <processor class="solr.LogUpdateProcessorFactory"/>
+ <processor class="solr.DistributedUpdateProcessorFactory"/>
+ <processor class="solr.RunUpdateProcessorFactory"/>
+ </updateRequestProcessorChain>
+
+ <!-- Deduplication
+
+ An example dedup update processor that creates the "id" field
+ on the fly based on the hash code of some other fields. This
+ example has overwriteDupes set to false since we are using the
+ id field as the signatureField and Solr will maintain
+ uniqueness based on that anyway.
+
+ -->
+ <!--
+ <updateRequestProcessorChain name="dedupe">
+ <processor class="solr.processor.SignatureUpdateProcessorFactory">
+ <bool name="enabled">true</bool>
+ <str name="signatureField">id</str>
+ <bool name="overwriteDupes">false</bool>
+ <str name="fields">name,features,cat</str>
+ <str name="signatureClass">solr.processor.Lookup3Signature</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Language identification
+
+ This example update chain identifies the language of the incoming
+ documents using the langid contrib. The detected language is
+ written to field language_s. No field name mapping is done.
+ The fields used for detection are text, title, subject and description,
+ making this example suitable for detecting languages form full-text
+ rich documents injected via ExtractingRequestHandler.
+ See more about langId at http://wiki.apache.org/solr/LanguageDetection
+ -->
+ <!--
+ <updateRequestProcessorChain name="langid">
+ <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
+ <str name="langid.fl">text,title,subject,description</str>
+ <str name="langid.langField">language_s</str>
+ <str name="langid.fallback">en</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Script update processor
+
+ This example hooks in an update processor implemented using JavaScript.
+
+ See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
+ -->
+ <!--
+ <updateRequestProcessorChain name="script">
+ <processor class="solr.StatelessScriptUpdateProcessorFactory">
+ <str name="script">update-script.js</str>
+ <lst name="params">
+ <str name="config_param">example config parameter</str>
+ </lst>
+ </processor>
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Response Writers
+
+ http://wiki.apache.org/solr/QueryResponseWriter
+
+ Request responses will be written using the writer specified by
+ the 'wt' request parameter matching the name of a registered
+ writer.
+
+ The "default" writer is the default and will be used if 'wt' is
+ not specified in the request.
+ -->
+ <!-- The following response writers are implicitly configured unless
+ overridden...
+ -->
+ <!--
+ <queryResponseWriter name="xml"
+ default="true"
+ class="solr.XMLResponseWriter" />
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+ <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+ <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+ <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+ <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+ <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+ <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+ -->
+
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+ <!-- For the purposes of the tutorial, JSON responses are written as
+ plain text so that they are easy to read in *any* browser.
+ If you expect a MIME type of "application/json" just remove this override.
+ -->
+ <str name="content-type">text/plain; charset=UTF-8</str>
+ </queryResponseWriter>
+
+ <!--
+ Custom response writers can be declared as needed...
+ -->
+ <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
+ <str name="template.base.dir">${velocity.template.base.dir:}</str>
+ <str name="solr.resource.loader.enabled">${velocity.solr.resource.loader.enabled:true}</str>
+ <str name="params.resource.loader.enabled">${velocity.params.resource.loader.enabled:false}</str>
+ </queryResponseWriter>
+
+ <!-- XSLT response writer transforms the XML output by any xslt file found
+ in Solr's conf/xslt directory. Changes to xslt files are checked for
+ every xsltCacheLifetimeSeconds.
+ -->
+ <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
+ <int name="xsltCacheLifetimeSeconds">5</int>
+ </queryResponseWriter>
+
+ <!-- Query Parsers
+
+ https://cwiki.apache.org/confluence/display/solr/Query+Syntax+and+Parsing
+
+ Multiple QParserPlugins can be registered by name, and then
+ used in either the "defType" param for the QueryComponent (used
+ by SearchHandler) or in LocalParams
+ -->
+ <!-- example of registering a query parser -->
+ <!--
+ <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+ -->
+
+ <!-- Function Parsers
+
+ http://wiki.apache.org/solr/FunctionQuery
+
+ Multiple ValueSourceParsers can be registered by name, and then
+ used as function names when using the "func" QParser.
+ -->
+ <!-- example of registering a custom function parser -->
+ <!--
+ <valueSourceParser name="myfunc"
+ class="com.mycompany.MyValueSourceParser" />
+ -->
+
+
+ <!-- Document Transformers
+ http://wiki.apache.org/solr/DocTransformers
+ -->
+ <!--
+ Could be something like:
+ <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+ <int name="connection">jdbc://....</int>
+ </transformer>
+
+ To add a constant value to all docs, use:
+ <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <int name="value">5</int>
+ </transformer>
+
+ If you want the user to still be able to change it with _value:something_ use this:
+ <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <double name="defaultValue">5</double>
+ </transformer>
+
+ If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
+ EditorialMarkerFactory will do exactly that:
+ <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+ -->
+</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/stopwords.txt b/solr/server/solr/configsets/basic_configs/conf/stopwords.txt
new file mode 100644
index 0000000..ae1e83e
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/stopwords.txt
@@ -0,0 +1,14 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/basic_configs/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/synonyms.txt b/solr/server/solr/configsets/basic_configs/conf/synonyms.txt
new file mode 100644
index 0000000..eab4ee8
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/synonyms.txt
@@ -0,0 +1,29 @@
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#-----------------------------------------------------------------------
+#some test synonym mappings unlikely to appear in real input text
+aaafoo => aaabar
+bbbfoo => bbbfoo bbbbar
+cccfoo => cccbar cccbaz
+fooaaa,baraaa,bazaaa
+
+# Some synonym groups specific to this example
+GB,gib,gigabyte,gigabytes
+MB,mib,megabyte,megabytes
+Television, Televisions, TV, TVs
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
+#after us won't split it into two words.
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/currency.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/currency.xml b/solr/server/solr/configsets/data_driven_schema_configs/conf/currency.xml
new file mode 100644
index 0000000..3a9c58a
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/currency.xml
@@ -0,0 +1,67 @@
+<?xml version="1.0" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!-- Example exchange rates file for CurrencyField type named "currency" in example schema -->
+
+<currencyConfig version="1.0">
+ <rates>
+ <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 -->
+ <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" />
+ <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" />
+ <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" />
+ <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" />
+ <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" />
+ <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" />
+ <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" />
+ <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" />
+ <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" />
+ <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" />
+ <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" />
+ <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" />
+ <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" />
+ <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" />
+ <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" />
+ <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" />
+ <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" />
+ <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" />
+ <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" />
+ <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" />
+ <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" />
+ <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" />
+ <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" />
+ <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" />
+ <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" />
+ <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" />
+ <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" />
+ <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" />
+ <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" />
+ <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" />
+ <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" />
+ <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" />
+ <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" />
+ <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" />
+ <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" />
+ <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" />
+ <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" />
+
+ <!-- Cross-rates for some common currencies -->
+ <rate from="EUR" to="GBP" rate="0.869914" />
+ <rate from="EUR" to="NOK" rate="7.800095" />
+ <rate from="GBP" to="NOK" rate="8.966508" />
+ </rates>
+</currencyConfig>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml b/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml
new file mode 100644
index 0000000..2c09ebe
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml
@@ -0,0 +1,42 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!-- If this file is found in the config directory, it will only be
+ loaded once at startup. If it is found in Solr's data
+ directory, it will be re-loaded every commit.
+
+ See http://wiki.apache.org/solr/QueryElevationComponent for more info
+
+-->
+<elevate>
+ <!-- Query elevation examples
+ <query text="foo bar">
+ <doc id="1" />
+ <doc id="2" />
+ <doc id="3" />
+ </query>
+
+for use with techproducts example
+
+ <query text="ipod">
+ <doc id="MA147LL/A" /> put the actual ipod at the top
+ <doc id="IW-02" exclude="true" /> exclude this cable
+ </query>
+-->
+
+</elevate>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ca.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ca.txt
new file mode 100644
index 0000000..307a85f
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ca.txt
@@ -0,0 +1,8 @@
+# Set of Catalan contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+l
+m
+n
+s
+t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_fr.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_fr.txt
new file mode 100644
index 0000000..f1bba51
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_fr.txt
@@ -0,0 +1,15 @@
+# Set of French contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+l
+m
+t
+qu
+n
+s
+j
+d
+c
+jusqu
+quoiqu
+lorsqu
+puisqu
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ga.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ga.txt
new file mode 100644
index 0000000..9ebe7fa
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+m
+b
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_it.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_it.txt
new file mode 100644
index 0000000..cac0409
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/contractions_it.txt
@@ -0,0 +1,23 @@
+# Set of Italian contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+c
+l
+all
+dall
+dell
+nell
+sull
+coll
+pell
+gl
+agl
+dagl
+degl
+negl
+sugl
+un
+m
+t
+s
+v
+d
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/hyphenations_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/hyphenations_ga.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/hyphenations_ga.txt
new file mode 100644
index 0000000..4d2642c
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/hyphenations_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish hyphenations for StopFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+h
+n
+t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stemdict_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stemdict_nl.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stemdict_nl.txt
new file mode 100644
index 0000000..4410729
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stemdict_nl.txt
@@ -0,0 +1,6 @@
+# Set of overrides for the dutch stemmer
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+fiets fiets
+bromfiets bromfiets
+ei eier
+kind kinder
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a58412e/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stoptags_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stoptags_ja.txt b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stoptags_ja.txt
new file mode 100644
index 0000000..71b7508
--- /dev/null
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/lang/stoptags_ja.txt
@@ -0,0 +1,420 @@
+#
+# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
+#
+# Any token with a part-of-speech tag that exactly matches those defined in this
+# file are removed from the token stream.
+#
+# Set your own stoptags by uncommenting the lines below. Note that comments are
+# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
+# etc. that can be useful for building you own stoptag set.
+#
+# The entire possible tagset is provided below for convenience.
+#
+#####
+# noun: unclassified nouns
+#名詞
+#
+# noun-common: Common nouns or nouns where the sub-classification is undefined
+#名詞-一般
+#
+# noun-proper: Proper nouns where the sub-classification is undefined
+#名詞-固有名詞
+#
+# noun-proper-misc: miscellaneous proper nouns
+#名詞-固有名詞-一般
+#
+# noun-proper-person: Personal names where the sub-classification is undefined
+#名詞-固有名詞-人名
+#
+# noun-proper-person-misc: names that cannot be divided into surname and
+# given name; foreign names; names where the surname or given name is unknown.
+# e.g. お市の方
+#名詞-固有名詞-人名-一般
+#
+# noun-proper-person-surname: Mainly Japanese surnames.
+# e.g. 山田
+#名詞-固有名詞-人名-姓
+#
+# noun-proper-person-given_name: Mainly Japanese given names.
+# e.g. 太郎
+#名詞-固有名詞-人名-名
+#
+# noun-proper-organization: Names representing organizations.
+# e.g. 通産省, NHK
+#名詞-固有名詞-組織
+#
+# noun-proper-place: Place names where the sub-classification is undefined
+#名詞-固有名詞-地域
+#
+# noun-proper-place-misc: Place names excluding countries.
+# e.g. アジア, バルセロナ, 京都
+#名詞-固有名詞-地域-一般
+#
+# noun-proper-place-country: Country names.
+# e.g. 日本, オーストラリア
+#名詞-固有名詞-地域-国
+#
+# noun-pronoun: Pronouns where the sub-classification is undefined
+#名詞-代名詞
+#
+# noun-pronoun-misc: miscellaneous pronouns:
+# e.g. それ, ここ, あいつ, あなた, あちこち, いくつ, どこか, なに, みなさん, みんな, わたくし, われわれ
+#名詞-代名詞-一般
+#
+# noun-pronoun-contraction: Spoken language contraction made by combining a
+# pronoun and the particle 'wa'.
+# e.g. ありゃ, こりゃ, こりゃあ, そりゃ, そりゃあ
+#名詞-代名詞-縮約
+#
+# noun-adverbial: Temporal nouns such as names of days or months that behave
+# like adverbs. Nouns that represent amount or ratios and can be used adverbially,
+# e.g. 金曜, 一月, 午後, 少量
+#名詞-副詞可能
+#
+# noun-verbal: Nouns that take arguments with case and can appear followed by
+# 'suru' and related verbs (する, できる, なさる, くださる)
+# e.g. インプット, 愛着, 悪化, 悪戦苦闘, 一安心, 下取り
+#名詞-サ変接続
+#
+# noun-adjective-base: The base form of adjectives, words that appear before な ("na")
+# e.g. 健康, 安易, 駄目, だめ
+#名詞-形容動詞語幹
+#
+# noun-numeric: Arabic numbers, Chinese numerals, and counters like 何 (回), 数.
+# e.g. 0, 1, 2, 何, 数, 幾
+#名詞-数
+#
+# noun-affix: noun affixes where the sub-classification is undefined
+#名詞-非自立
+#
+# noun-affix-misc: Of adnominalizers, the case-marker の ("no"), and words that
+# attach to the base form of inflectional words, words that cannot be classified
+# into any of the other categories below. This category includes indefinite nouns.
+# e.g. あかつき, 暁, かい, 甲斐, 気, きらい, 嫌い, くせ, 癖, こと, 事, ごと, 毎, しだい, 次第,
+# 順, せい, 所為, ついで, 序で, つもり, 積もり, 点, どころ, の, はず, 筈, はずみ, 弾み,
+# 拍子, ふう, ふり, 振り, ほう, 方, 旨, もの, 物, 者, ゆえ, 故, ゆえん, 所以, わけ, 訳,
+# わり, 割り, 割, ん-口語/, もん-口語/
+#名詞-非自立-一般
+#
+# noun-affix-adverbial: noun affixes that that can behave as adverbs.
+# e.g. あいだ, 間, あげく, 挙げ句, あと, 後, 余り, 以外, 以降, 以後, 以上, 以前, 一方, うえ,
+# 上, うち, 内, おり, 折り, かぎり, 限り, きり, っきり, 結果, ころ, 頃, さい, 際, 最中, さなか,
+# 最中, じたい, 自体, たび, 度, ため, 為, つど, 都度, とおり, 通り, とき, 時, ところ, 所,
+# とたん, 途端, なか, 中, のち, 後, ばあい, 場合, 日, ぶん, 分, ほか, 他, まえ, 前, まま,
+# 儘, 侭, みぎり, 矢先
+#名詞-非自立-副詞可能
+#
+# noun-affix-aux: noun affixes treated as 助動詞 ("auxiliary verb") in school grammars
+# with the stem よう(だ) ("you(da)").
+# e.g. よう, やう, 様 (よう)
+#名詞-非自立-助動詞語幹
+#
+# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
+# connection form な (aux "da").
+# e.g. みたい, ふう
+#名詞-非自立-形容動詞語幹
+#
+# noun-special: special nouns where the sub-classification is undefined.
+#名詞-特殊
+#
+# noun-special-aux: The そうだ ("souda") stem form that is used for reporting news, is
+# treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the base
+# form of inflectional words.
+# e.g. そう
+#名詞-特殊-助動詞語幹
+#
+# noun-suffix: noun suffixes where the sub-classification is undefined.
+#名詞-接尾
+#
+# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
+# to ガル or タイ and can combine into compound nouns, words that cannot be classified into
+# any of the other categories below. In general, this category is more inclusive than
+# 接尾語 ("suffix") and is usually the last element in a compound noun.
+# e.g. おき, かた, 方, 甲斐 (がい), がかり, ぎみ, 気味, ぐるみ, (～した) さ, 次第, 済 (ず) み,
+# よう, (でき)っこ, 感, 観, 性, 学, 類, 面, 用
+#名詞-接尾-一般
+#
+# noun-suffix-person: Suffixes that form nouns and attach to person names more often
+# than other nouns.
+# e.g. 君, 様, 著
+#名詞-接尾-人名
+#
+# noun-suffix-place: Suffixes that form nouns and attach to place names more often
+# than other nouns.
+# e.g. 町, 市, 県
+#名詞-接尾-地域
+#
+# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
+# can appear before スル ("suru").
+# e.g. 化, 視, 分け, 入り, 落ち, 買い
+#名詞-接尾-サ変接続
+#
+# noun-suffix-aux: The stem form of そうだ (様態) that is used to indicate conditions,
+# is treated as 助動詞 ("auxiliary verb") in school grammars, and attach to the
+# conjunctive form of inflectional words.
+# e.g. そう
+#名詞-接尾-助動詞語幹
+#
+# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
+# form of inflectional words and appear before the copula だ ("da").
+# e.g. 的, げ, がち
+#名詞-接尾-形容動詞語幹
+#
+# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
+# e.g. 後 (ご), 以後, 以降, 以前, 前後, 中, 末, 上, 時 (じ)
+#名詞-接尾-副詞可能
+#
+# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
+# is more inclusive than 助数詞 ("classifier") and includes common nouns that attach
+# to numbers.
+# e.g. 個, つ, 本, 冊, パーセント, cm, kg, カ月, か国, 区画, 時間, 時半
+#名詞-接尾-助数詞
+#
+# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
+# e.g. (楽し) さ, (考え) 方
+#名詞-接尾-特殊
+#
+# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
+# together.
+# e.g. (日本) 対 (アメリカ), 対 (アメリカ), (3) 対 (5), (女優) 兼 (主婦)
+#名詞-接続詞的
+#
+# noun-verbal_aux: Nouns that attach to the conjunctive particle て ("te") and are
+# semantically verb-like.
+# e.g. ごらん, ご覧, 御覧, 頂戴
+#名詞-動詞非自立的
+#
+# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
+# dialects, English, etc. Currently, the only entry for 名詞 引用文字列 ("noun quotation")
+# is いわく ("iwaku").
+#名詞-引用文字列
+#
+# noun-nai_adjective: Words that appear before the auxiliary verb ない ("nai") and
+# behave like an adjective.
+# e.g. 申し訳, 仕方, とんでも, 違い
+#名詞-ナイ形容詞語幹
+#
+#####
+# prefix: unclassified prefixes
+#接頭詞
+#
+# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
+# excluding numerical expressions.
+# e.g. お (水), 某 (氏), 同 (社), 故 (～氏), 高 (品質), お (見事), ご (立派)
+#接頭詞-名詞接続
+#
+# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
+# in conjunctive form followed by なる/なさる/くださる.
+# e.g. お (読みなさい), お (座り)
+#接頭詞-動詞接続
+#
+# prefix-adjectival: Prefixes that attach to adjectives.
+# e.g. お (寒いですねえ), バカ (でかい)
+#接頭詞-形容詞接続
+#
+# prefix-numerical: Prefixes that attach to numerical expressions.
+# e.g. 約, およそ, 毎時
+#接頭詞-数接続
+#
+#####
+# verb: unclassified verbs
+#動詞
+#
+# verb-main:
+#動詞-自立
+#
+# verb-auxiliary:
+#動詞-非自立
+#
+# verb-suffix:
+#動詞-接尾
+#
+#####
+# adjective: unclassified adjectives
+#形容詞
+#
+# adjective-main:
+#形容詞-自立
+#
+# adjective-auxiliary:
+#形容詞-非自立
+#
+# adjective-suffix:
+#形容詞-接尾
+#
+#####
+# adverb: unclassified adverbs
+#副詞
+#
+# adverb-misc: Words that can be segmented into one unit and where adnominal
+# modification is not possible.
+# e.g. あいかわらず, 多分
+#副詞-一般
+#
+# adverb-particle_conjunction: Adverbs that can be followed by の, は, に,
+# な, する, だ, etc.
+# e.g. こんなに, そんなに, あんなに, なにか, なんでも
+#副詞-助詞類接続
+#
+#####
+# adnominal: Words that only have noun-modifying forms.
+# e.g. この, その, あの, どの, いわゆる, なんらかの, 何らかの, いろんな, こういう, そういう, ああいう,
+# どういう, こんな, そんな, あんな, どんな, 大きな, 小さな, おかしな, ほんの, たいした,
+# 「(, も) さる (ことながら)」, 微々たる, 堂々たる, 単なる, いかなる, 我が」「同じ, 亡き
+#連体詞
+#
+#####
+# conjunction: Conjunctions that can occur independently.
+# e.g. が, けれども, そして, じゃあ, それどころか
+接続詞
+#
+#####
+# particle: unclassified particles.
+助詞
+#
+# particle-case: case particles where the subclassification is undefined.
+助詞-格助詞
+#
+# particle-case-misc: Case particles.
+# e.g. から, が, で, と, に, へ, より, を, の, にて
+助詞-格助詞-一般
+#
+# particle-case-quote: the "to" that appears after nouns, a person’s speech,
+# quotation marks, expressions of decisions from a meeting, reasons, judgements,
+# conjectures, etc.
+# e.g. ( だ) と (述べた.), ( である) と (して執行猶予...)
+助詞-格助詞-引用
+#
+# particle-case-compound: Compounds of particles and verbs that mainly behave
+# like case particles.
+# e.g. という, といった, とかいう, として, とともに, と共に, でもって, にあたって, に当たって, に当って,
+# にあたり, に当たり, に当り, に当たる, にあたる, において, に於いて,に於て, における, に於ける,
+# にかけ, にかけて, にかんし, に関し, にかんして, に関して, にかんする, に関する, に際し,
+# に際して, にしたがい, に従い, に従う, にしたがって, に従って, にたいし, に対し, にたいして,
+# に対して, にたいする, に対する, について, につき, につけ, につけて, につれ, につれて, にとって,
+# にとり, にまつわる, によって, に依って, に因って, により, に依り, に因り, による, に依る, に因る,
+# にわたって, にわたる, をもって, を以って, を通じ, を通じて, を通して, をめぐって, をめぐり, をめぐる,
+# って-口語/, ちゅう-関西弁「という」/, (何) ていう (人)-口語/, っていう-口語/, といふ, とかいふ
+助詞-格助詞-連語
+#
+# particle-conjunctive:
+# e.g. から, からには, が, けれど, けれども, けど, し, つつ, て, で, と, ところが, どころか, とも, ども,
+# ながら, なり, ので, のに, ば, ものの, や ( した), やいなや, (ころん) じゃ(いけない)-口語/,
+# (行っ) ちゃ(いけない)-口語/, (言っ) たって (しかたがない)-口語/, (それがなく)ったって (平気)-口語/
+助詞-接続助詞
+#
+# particle-dependency:
+# e.g. こそ, さえ, しか, すら, は, も, ぞ
+助詞-係助詞
+#
+# particle-adverbial:
+# e.g. がてら, かも, くらい, 位, ぐらい, しも, (学校) じゃ(これが流行っている)-口語/,
+# (それ)じゃあ (よくない)-口語/, ずつ, (私) なぞ, など, (私) なり (に), (先生) なんか (大嫌い)-口語/,
+# (私) なんぞ, (先生) なんて (大嫌い)-口語/, のみ, だけ, (私) だって-口語/, だに,
+# (彼)ったら-口語/, (お茶) でも (いかが), 等 (とう), (今後) とも, ばかり, ばっか-口語/, ばっかり-口語/,
+# ほど, 程, まで, 迄, (誰) も (が)([助詞-格助詞] および [助詞-係助詞] の前に位置する「も」)
+助詞-副助詞
+#
+# particle-interjective: particles with interjective grammatical roles.
+# e.g. (松島) や
+助詞-間投助詞
+#
+# particle-coordinate:
+# e.g. と, たり, だの, だり, とか, なり, や, やら
+助詞-並立助詞
+#
+# particle-final:
+# e.g. かい, かしら, さ, ぜ, (だ)っけ-口語/, (とまってる) で-方言/, な, ナ, なあ-口語/, ぞ, ね, ネ,
+# ねぇ-口語/, ねえ-口語/, ねん-方言/, の, のう-口語/, や, よ, ヨ, よぉ-口語/, わ, わい-口語/
+助詞-終助詞
+#
+# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
+# adverbial, conjunctive, or sentence final. For example:
+# (a) 「A か B か」. Ex:「(国内で運用する) か,(海外で運用する) か (.)」
+# (b) Inside an adverb phrase. Ex:「(幸いという) か (, 死者はいなかった.)」
+# 「(祈りが届いたせい) か (, 試験に合格した.)」
+# (c) 「かのように」. Ex:「(何もなかった) か (のように振る舞った.)」
+# e.g. か
+助詞-副助詞／並立助詞／終助詞
+#
+# particle-adnominalizer: The "no" that attaches to nouns and modifies
+# non-inflectional words.
+助詞-連体化
+#
+# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
+# that are giongo, giseigo, or gitaigo.
+# e.g. に, と
+助詞-副詞化
+#
+# particle-special: A particle that does not fit into one of the above classifications.
+# This includes particles that are used in Tanka, Haiku, and other poetry.
+# e.g. かな, けむ, ( しただろう) に, (あんた) にゃ(わからん), (俺) ん (家)
+助詞-特殊
+#
+#####
+# auxiliary-verb:
+助動詞
+#
+#####
+# interjection: Greetings and other exclamations.
+# e.g. おはよう, おはようございます, こんにちは, こんばんは, ありがとう, どうもありがとう, ありがとうございます,
+# いただきます, ごちそうさま, さよなら, さようなら, はい, いいえ, ごめん, ごめんなさい
+#感動詞
+#
+#####
+# symbol: unclassified Symbols.
+記号
+#
+# symbol-misc: A general symbol not in one of the categories below.
+# e.g. [○◎@$〒→+]
+記号-一般
+#
+# symbol-comma: Commas
+# e.g. [,、]
+記号-読点
+#
+# symbol-period: Periods and full stops.
+# e.g. [.．。]
+記号-句点
+#
+# symbol-space: Full-width whitespace.
+記号-空白
+#
+# symbol-open_bracket:
+# e.g. [({‘“『【]
+記号-括弧開
+#
+# symbol-close_bracket:
+# e.g. [)}’”』」】]
+記号-括弧閉
+#
+# symbol-alphabetic:
+#記号-アルファベット
+#
+#####
+# other: unclassified other
+#その他
+#
+# other-interjection: Words that are hard to classify as noun-suffixes or
+# sentence-final particles.
+# e.g. (だ)ァ
+その他-間投
+#
+#####
+# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
+# e.g. あの, うんと, えと
+フィラー
+#
+#####
+# non-verbal: non-verbal sound.
+非言語音
+#
+#####
+# fragment:
+#語断片
+#
+#####
+# unknown: unknown part of speech.
+#未知語
+#
+##### End of file
[15/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10882:
ArrayEvaluator now works with all types and allows sorts (deleted
ArraySortEvaluator)
Posted by sh...@apache.org.
SOLR-10882: ArrayEvaluator now works with all types and allows sorts (deleted ArraySortEvaluator)
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/113459a8
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/113459a8
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/113459a8
Branch: refs/heads/feature/autoscaling
Commit: 113459a840e8ca3482ebd36a76dda551fac885ec
Parents: 5fca6a4
Author: Dennis Gove <dp...@gmail.com>
Authored: Thu Jun 15 22:10:37 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Sun Jun 18 11:50:58 2017 -0400
----------------------------------------------------------------------
.../org/apache/solr/handler/StreamHandler.java | 479 +++++++++----------
.../client/solrj/io/eval/ArrayEvaluator.java | 48 +-
.../solrj/io/eval/ArraySortEvaluator.java | 77 ---
.../client/solrj/io/eval/ComplexEvaluator.java | 18 +-
.../io/stream/eval/ArrayEvaluatorTest.java | 155 ++++++
5 files changed, 452 insertions(+), 325 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/113459a8/solr/core/src/java/org/apache/solr/handler/StreamHandler.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/handler/StreamHandler.java b/solr/core/src/java/org/apache/solr/handler/StreamHandler.java
index 7889bf7..4616204 100644
--- a/solr/core/src/java/org/apache/solr/handler/StreamHandler.java
+++ b/solr/core/src/java/org/apache/solr/handler/StreamHandler.java
@@ -77,7 +77,7 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
private StreamFactory streamFactory = new StreamFactory();
private static final Logger logger = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());
private String coreName;
- private Map<String, DaemonStream> daemons = Collections.synchronizedMap(new HashMap());
+ private Map<String,DaemonStream> daemons = Collections.synchronizedMap(new HashMap());
@Override
public PermissionNameProvider.Name getPermissionName(AuthorizationContext request) {
@@ -89,202 +89,202 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
}
public void inform(SolrCore core) {
-
- /* The stream factory will always contain the zkUrl for the given collection
- * Adds default streams with their corresponding function names. These
- * defaults can be overridden or added to in the solrConfig in the stream
- * RequestHandler def. Example config override
- * <lst name="streamFunctions">
- * <str name="group">org.apache.solr.client.solrj.io.stream.ReducerStream</str>
- * <str name="count">org.apache.solr.client.solrj.io.stream.RecordCountStream</str>
- * </lst>
- * */
+
+ /*
+ * The stream factory will always contain the zkUrl for the given collection Adds default streams with their
+ * corresponding function names. These defaults can be overridden or added to in the solrConfig in the stream
+ * RequestHandler def. Example config override
+ * <lst name="streamFunctions">
+ * <str name="group">org.apache.solr.client.solrj.io.stream.ReducerStream</str>
+ * <str name="count">org.apache.solr.client.solrj.io.stream.RecordCountStream</str>
+ * </lst>
+ */
String defaultCollection;
String defaultZkhost;
CoreContainer coreContainer = core.getCoreContainer();
this.coreName = core.getName();
- if(coreContainer.isZooKeeperAware()) {
+ if (coreContainer.isZooKeeperAware()) {
defaultCollection = core.getCoreDescriptor().getCollectionName();
defaultZkhost = core.getCoreContainer().getZkController().getZkServerAddress();
streamFactory.withCollectionZkHost(defaultCollection, defaultZkhost);
streamFactory.withDefaultZkHost(defaultZkhost);
modelCache = new ModelCache(250,
- defaultZkhost,
- clientCache);
- }
-
- streamFactory
- // source streams
- .withFunctionName("search", CloudSolrStream.class)
- .withFunctionName("facet", FacetStream.class)
- .withFunctionName("update", UpdateStream.class)
- .withFunctionName("jdbc", JDBCStream.class)
- .withFunctionName("topic", TopicStream.class)
- .withFunctionName("commit", CommitStream.class)
- .withFunctionName("random", RandomStream.class)
- .withFunctionName("knn", KnnStream.class)
-
- // decorator streams
- .withFunctionName("merge", MergeStream.class)
- .withFunctionName("unique", UniqueStream.class)
- .withFunctionName("top", RankStream.class)
- .withFunctionName("group", GroupOperation.class)
- .withFunctionName("reduce", ReducerStream.class)
- .withFunctionName("parallel", ParallelStream.class)
- .withFunctionName("rollup", RollupStream.class)
- .withFunctionName("stats", StatsStream.class)
- .withFunctionName("innerJoin", InnerJoinStream.class)
- .withFunctionName("leftOuterJoin", LeftOuterJoinStream.class)
- .withFunctionName("hashJoin", HashJoinStream.class)
- .withFunctionName("outerHashJoin", OuterHashJoinStream.class)
- .withFunctionName("intersect", IntersectStream.class)
- .withFunctionName("complement", ComplementStream.class)
- .withFunctionName(SORT, SortStream.class)
- .withFunctionName("train", TextLogitStream.class)
- .withFunctionName("features", FeaturesSelectionStream.class)
- .withFunctionName("daemon", DaemonStream.class)
- .withFunctionName("shortestPath", ShortestPathStream.class)
- .withFunctionName("gatherNodes", GatherNodesStream.class)
- .withFunctionName("nodes", GatherNodesStream.class)
- .withFunctionName("select", SelectStream.class)
- .withFunctionName("shortestPath", ShortestPathStream.class)
- .withFunctionName("gatherNodes", GatherNodesStream.class)
- .withFunctionName("nodes", GatherNodesStream.class)
- .withFunctionName("scoreNodes", ScoreNodesStream.class)
- .withFunctionName("model", ModelStream.class)
- .withFunctionName("classify", ClassifyStream.class)
- .withFunctionName("fetch", FetchStream.class)
- .withFunctionName("executor", ExecutorStream.class)
- .withFunctionName("null", NullStream.class)
- .withFunctionName("priority", PriorityStream.class)
- .withFunctionName("significantTerms", SignificantTermsStream.class)
- .withFunctionName("cartesianProduct", CartesianProductStream.class)
- .withFunctionName("shuffle", ShuffleStream.class)
- .withFunctionName("calc", CalculatorStream.class)
- .withFunctionName("eval",EvalStream.class)
- .withFunctionName("echo", EchoStream.class)
- .withFunctionName("cell", CellStream.class)
- .withFunctionName("list", ListStream.class)
- .withFunctionName("let", LetStream.class)
- .withFunctionName("get", GetStream.class)
- .withFunctionName("timeseries", TimeSeriesStream.class)
- .withFunctionName("tuple", TupStream.class)
- .withFunctionName("sql", SqlStream.class)
- .withFunctionName("col", ColumnEvaluator.class)
- .withFunctionName("predict", PredictEvaluator.class)
- .withFunctionName("regress", RegressionEvaluator.class)
- .withFunctionName("cov", CovarianceEvaluator.class)
- .withFunctionName("conv", ConvolutionEvaluator.class)
- .withFunctionName("normalize", NormalizeEvaluator.class)
- .withFunctionName("rev", ReverseEvaluator.class)
- .withFunctionName("length", LengthEvaluator.class)
- .withFunctionName("rank", RankEvaluator.class)
- .withFunctionName("scale", ScaleEvaluator.class)
- .withFunctionName("distance", DistanceEvaluator.class)
- .withFunctionName("copyOf", CopyOfEvaluator.class)
- .withFunctionName("copyOfRange", CopyOfRangeEvaluator.class)
- .withFunctionName("percentile", PercentileEvaluator.class)
- .withFunctionName("empiricalDistribution", EmpiricalDistributionEvaluator.class)
- .withFunctionName("cumulativeProbability", CumulativeProbabilityEvaluator.class)
- .withFunctionName("describe", DescribeEvaluator.class)
- .withFunctionName("finddelay", FindDelayEvaluator.class)
- .withFunctionName("sequence", SequenceEvaluator.class)
- .withFunctionName("array", ArrayEvaluator.class)
- .withFunctionName("hist", HistogramEvaluator.class)
- .withFunctionName("anova", AnovaEvaluator.class)
- .withFunctionName("movingAvg", MovingAverageEvaluator.class)
- .withFunctionName("arraySort", ArraySortEvaluator.class)
-
- // metrics
- .withFunctionName("min", MinMetric.class)
- .withFunctionName("max", MaxMetric.class)
- .withFunctionName("avg", MeanMetric.class)
- .withFunctionName("sum", SumMetric.class)
- .withFunctionName("count", CountMetric.class)
-
- // tuple manipulation operations
- .withFunctionName("replace", ReplaceOperation.class)
- .withFunctionName("concat", ConcatOperation.class)
-
- // stream reduction operations
- .withFunctionName("group", GroupOperation.class)
- .withFunctionName("distinct", DistinctOperation.class)
- .withFunctionName("having", HavingStream.class)
-
- // Stream Evaluators
- .withFunctionName("val", RawValueEvaluator.class)
-
- // Boolean Stream Evaluators
- .withFunctionName("and", AndEvaluator.class)
- .withFunctionName("eor", ExclusiveOrEvaluator.class)
- .withFunctionName("eq", EqualsEvaluator.class)
- .withFunctionName("gt", GreaterThanEvaluator.class)
- .withFunctionName("gteq", GreaterThanEqualToEvaluator.class)
- .withFunctionName("lt", LessThanEvaluator.class)
- .withFunctionName("lteq", LessThanEqualToEvaluator.class)
- .withFunctionName("not", NotEvaluator.class)
- .withFunctionName("or", OrEvaluator.class)
-
- // Date Time Evaluators
- .withFunctionName(TemporalEvaluatorYear.FUNCTION_NAME, TemporalEvaluatorYear.class)
- .withFunctionName(TemporalEvaluatorMonth.FUNCTION_NAME, TemporalEvaluatorMonth.class)
- .withFunctionName(TemporalEvaluatorDay.FUNCTION_NAME, TemporalEvaluatorDay.class)
- .withFunctionName(TemporalEvaluatorDayOfYear.FUNCTION_NAME, TemporalEvaluatorDayOfYear.class)
- .withFunctionName(TemporalEvaluatorHour.FUNCTION_NAME, TemporalEvaluatorHour.class)
- .withFunctionName(TemporalEvaluatorMinute.FUNCTION_NAME, TemporalEvaluatorMinute.class)
- .withFunctionName(TemporalEvaluatorSecond.FUNCTION_NAME, TemporalEvaluatorSecond.class)
- .withFunctionName(TemporalEvaluatorEpoch.FUNCTION_NAME, TemporalEvaluatorEpoch.class)
- .withFunctionName(TemporalEvaluatorWeek.FUNCTION_NAME, TemporalEvaluatorWeek.class)
- .withFunctionName(TemporalEvaluatorQuarter.FUNCTION_NAME, TemporalEvaluatorQuarter.class)
- .withFunctionName(TemporalEvaluatorDayOfQuarter.FUNCTION_NAME, TemporalEvaluatorDayOfQuarter.class)
-
- // Number Stream Evaluators
- .withFunctionName("abs", AbsoluteValueEvaluator.class)
- .withFunctionName("add", AddEvaluator.class)
- .withFunctionName("div", DivideEvaluator.class)
- .withFunctionName("mult", MultiplyEvaluator.class)
- .withFunctionName("sub", SubtractEvaluator.class)
- .withFunctionName("log", NaturalLogEvaluator.class)
- .withFunctionName("pow", PowerEvaluator.class)
- .withFunctionName("mod", ModuloEvaluator.class)
- .withFunctionName("ceil", CeilingEvaluator.class)
- .withFunctionName("floor", FloorEvaluator.class)
- .withFunctionName("sin", SineEvaluator.class)
- .withFunctionName("asin", ArcSineEvaluator.class)
- .withFunctionName("sinh", HyperbolicSineEvaluator.class)
- .withFunctionName("cos", CosineEvaluator.class)
- .withFunctionName("acos", ArcCosineEvaluator.class)
- .withFunctionName("cosh", HyperbolicCosineEvaluator.class)
- .withFunctionName("tan", TangentEvaluator.class)
- .withFunctionName("atan", ArcTangentEvaluator.class)
- .withFunctionName("tanh", HyperbolicTangentEvaluator.class)
- .withFunctionName("round", RoundEvaluator.class)
- .withFunctionName("sqrt", SquareRootEvaluator.class)
- .withFunctionName("cbrt", CubedRootEvaluator.class)
- .withFunctionName("coalesce", CoalesceEvaluator.class)
- .withFunctionName("uuid", UuidEvaluator.class)
- .withFunctionName("corr", CorrelationEvaluator.class)
-
-
- // Conditional Stream Evaluators
- .withFunctionName("if", IfThenElseEvaluator.class)
- .withFunctionName("analyze", AnalyzeEvaluator.class)
- .withFunctionName("convert", ConversionEvaluator.class)
- ;
-
- // This pulls all the overrides and additions from the config
- List<PluginInfo> pluginInfos = core.getSolrConfig().getPluginInfos(Expressible.class.getName());
- for (PluginInfo pluginInfo : pluginInfos) {
- Class<? extends Expressible> clazz = core.getMemClassLoader().findClass(pluginInfo.className, Expressible.class);
- streamFactory.withFunctionName(pluginInfo.name, clazz);
- }
+ defaultZkhost,
+ clientCache);
+ }
+
+ streamFactory
+ // source streams
+ .withFunctionName("search", CloudSolrStream.class)
+ .withFunctionName("facet", FacetStream.class)
+ .withFunctionName("update", UpdateStream.class)
+ .withFunctionName("jdbc", JDBCStream.class)
+ .withFunctionName("topic", TopicStream.class)
+ .withFunctionName("commit", CommitStream.class)
+ .withFunctionName("random", RandomStream.class)
+ .withFunctionName("knn", KnnStream.class)
+
+ // decorator streams
+ .withFunctionName("merge", MergeStream.class)
+ .withFunctionName("unique", UniqueStream.class)
+ .withFunctionName("top", RankStream.class)
+ .withFunctionName("group", GroupOperation.class)
+ .withFunctionName("reduce", ReducerStream.class)
+ .withFunctionName("parallel", ParallelStream.class)
+ .withFunctionName("rollup", RollupStream.class)
+ .withFunctionName("stats", StatsStream.class)
+ .withFunctionName("innerJoin", InnerJoinStream.class)
+ .withFunctionName("leftOuterJoin", LeftOuterJoinStream.class)
+ .withFunctionName("hashJoin", HashJoinStream.class)
+ .withFunctionName("outerHashJoin", OuterHashJoinStream.class)
+ .withFunctionName("intersect", IntersectStream.class)
+ .withFunctionName("complement", ComplementStream.class)
+ .withFunctionName(SORT, SortStream.class)
+ .withFunctionName("train", TextLogitStream.class)
+ .withFunctionName("features", FeaturesSelectionStream.class)
+ .withFunctionName("daemon", DaemonStream.class)
+ .withFunctionName("shortestPath", ShortestPathStream.class)
+ .withFunctionName("gatherNodes", GatherNodesStream.class)
+ .withFunctionName("nodes", GatherNodesStream.class)
+ .withFunctionName("select", SelectStream.class)
+ .withFunctionName("shortestPath", ShortestPathStream.class)
+ .withFunctionName("gatherNodes", GatherNodesStream.class)
+ .withFunctionName("nodes", GatherNodesStream.class)
+ .withFunctionName("scoreNodes", ScoreNodesStream.class)
+ .withFunctionName("model", ModelStream.class)
+ .withFunctionName("classify", ClassifyStream.class)
+ .withFunctionName("fetch", FetchStream.class)
+ .withFunctionName("executor", ExecutorStream.class)
+ .withFunctionName("null", NullStream.class)
+ .withFunctionName("priority", PriorityStream.class)
+ .withFunctionName("significantTerms", SignificantTermsStream.class)
+ .withFunctionName("cartesianProduct", CartesianProductStream.class)
+ .withFunctionName("shuffle", ShuffleStream.class)
+ .withFunctionName("calc", CalculatorStream.class)
+ .withFunctionName("eval", EvalStream.class)
+ .withFunctionName("echo", EchoStream.class)
+ .withFunctionName("cell", CellStream.class)
+ .withFunctionName("list", ListStream.class)
+ .withFunctionName("let", LetStream.class)
+ .withFunctionName("get", GetStream.class)
+ .withFunctionName("timeseries", TimeSeriesStream.class)
+ .withFunctionName("tuple", TupStream.class)
+ .withFunctionName("sql", SqlStream.class)
+
+ // metrics
+ .withFunctionName("min", MinMetric.class)
+ .withFunctionName("max", MaxMetric.class)
+ .withFunctionName("avg", MeanMetric.class)
+ .withFunctionName("sum", SumMetric.class)
+ .withFunctionName("count", CountMetric.class)
+
+ // tuple manipulation operations
+ .withFunctionName("replace", ReplaceOperation.class)
+ .withFunctionName("concat", ConcatOperation.class)
+
+ // stream reduction operations
+ .withFunctionName("group", GroupOperation.class)
+ .withFunctionName("distinct", DistinctOperation.class)
+ .withFunctionName("having", HavingStream.class)
+
+ // Stream Evaluators
+ .withFunctionName("val", RawValueEvaluator.class)
+
+ // New Evaluators
+ .withFunctionName("anova", AnovaEvaluator.class)
+ .withFunctionName("array", ArrayEvaluator.class)
+ .withFunctionName("col", ColumnEvaluator.class)
+ .withFunctionName("conv", ConvolutionEvaluator.class)
+ .withFunctionName("copyOf", CopyOfEvaluator.class)
+ .withFunctionName("copyOfRange", CopyOfRangeEvaluator.class)
+ .withFunctionName("cov", CovarianceEvaluator.class)
+ .withFunctionName("cumulativeProbability", CumulativeProbabilityEvaluator.class)
+ .withFunctionName("describe", DescribeEvaluator.class)
+ .withFunctionName("distance", DistanceEvaluator.class)
+ .withFunctionName("empiricalDistribution", EmpiricalDistributionEvaluator.class)
+ .withFunctionName("finddelay", FindDelayEvaluator.class)
+ .withFunctionName("hist", HistogramEvaluator.class)
+ .withFunctionName("length", LengthEvaluator.class)
+ .withFunctionName("movingAvg", MovingAverageEvaluator.class)
+ .withFunctionName("normalize", NormalizeEvaluator.class)
+ .withFunctionName("percentile", PercentileEvaluator.class)
+ .withFunctionName("predict", PredictEvaluator.class)
+ .withFunctionName("rank", RankEvaluator.class)
+ .withFunctionName("regress", RegressionEvaluator.class)
+ .withFunctionName("rev", ReverseEvaluator.class)
+ .withFunctionName("scale", ScaleEvaluator.class)
+ .withFunctionName("sequence", SequenceEvaluator.class)
+
+ // Boolean Stream Evaluators
+ .withFunctionName("and", AndEvaluator.class)
+ .withFunctionName("eor", ExclusiveOrEvaluator.class)
+ .withFunctionName("eq", EqualsEvaluator.class)
+ .withFunctionName("gt", GreaterThanEvaluator.class)
+ .withFunctionName("gteq", GreaterThanEqualToEvaluator.class)
+ .withFunctionName("lt", LessThanEvaluator.class)
+ .withFunctionName("lteq", LessThanEqualToEvaluator.class)
+ .withFunctionName("not", NotEvaluator.class)
+ .withFunctionName("or", OrEvaluator.class)
+
+ // Date Time Evaluators
+ .withFunctionName(TemporalEvaluatorYear.FUNCTION_NAME, TemporalEvaluatorYear.class)
+ .withFunctionName(TemporalEvaluatorMonth.FUNCTION_NAME, TemporalEvaluatorMonth.class)
+ .withFunctionName(TemporalEvaluatorDay.FUNCTION_NAME, TemporalEvaluatorDay.class)
+ .withFunctionName(TemporalEvaluatorDayOfYear.FUNCTION_NAME, TemporalEvaluatorDayOfYear.class)
+ .withFunctionName(TemporalEvaluatorHour.FUNCTION_NAME, TemporalEvaluatorHour.class)
+ .withFunctionName(TemporalEvaluatorMinute.FUNCTION_NAME, TemporalEvaluatorMinute.class)
+ .withFunctionName(TemporalEvaluatorSecond.FUNCTION_NAME, TemporalEvaluatorSecond.class)
+ .withFunctionName(TemporalEvaluatorEpoch.FUNCTION_NAME, TemporalEvaluatorEpoch.class)
+ .withFunctionName(TemporalEvaluatorWeek.FUNCTION_NAME, TemporalEvaluatorWeek.class)
+ .withFunctionName(TemporalEvaluatorQuarter.FUNCTION_NAME, TemporalEvaluatorQuarter.class)
+ .withFunctionName(TemporalEvaluatorDayOfQuarter.FUNCTION_NAME, TemporalEvaluatorDayOfQuarter.class)
+
+ // Number Stream Evaluators
+ .withFunctionName("abs", AbsoluteValueEvaluator.class)
+ .withFunctionName("add", AddEvaluator.class)
+ .withFunctionName("div", DivideEvaluator.class)
+ .withFunctionName("mult", MultiplyEvaluator.class)
+ .withFunctionName("sub", SubtractEvaluator.class)
+ .withFunctionName("log", NaturalLogEvaluator.class)
+ .withFunctionName("pow", PowerEvaluator.class)
+ .withFunctionName("mod", ModuloEvaluator.class)
+ .withFunctionName("ceil", CeilingEvaluator.class)
+ .withFunctionName("floor", FloorEvaluator.class)
+ .withFunctionName("sin", SineEvaluator.class)
+ .withFunctionName("asin", ArcSineEvaluator.class)
+ .withFunctionName("sinh", HyperbolicSineEvaluator.class)
+ .withFunctionName("cos", CosineEvaluator.class)
+ .withFunctionName("acos", ArcCosineEvaluator.class)
+ .withFunctionName("cosh", HyperbolicCosineEvaluator.class)
+ .withFunctionName("tan", TangentEvaluator.class)
+ .withFunctionName("atan", ArcTangentEvaluator.class)
+ .withFunctionName("tanh", HyperbolicTangentEvaluator.class)
+ .withFunctionName("round", RoundEvaluator.class)
+ .withFunctionName("sqrt", SquareRootEvaluator.class)
+ .withFunctionName("cbrt", CubedRootEvaluator.class)
+ .withFunctionName("coalesce", CoalesceEvaluator.class)
+ .withFunctionName("uuid", UuidEvaluator.class)
+ .withFunctionName("corr", CorrelationEvaluator.class)
+
+ // Conditional Stream Evaluators
+ .withFunctionName("if", IfThenElseEvaluator.class)
+ .withFunctionName("analyze", AnalyzeEvaluator.class)
+ .withFunctionName("convert", ConversionEvaluator.class);
+
+ // This pulls all the overrides and additions from the config
+ List<PluginInfo> pluginInfos = core.getSolrConfig().getPluginInfos(Expressible.class.getName());
+ for (PluginInfo pluginInfo : pluginInfos) {
+ Class<? extends Expressible> clazz = core.getMemClassLoader().findClass(pluginInfo.className, Expressible.class);
+ streamFactory.withFunctionName(pluginInfo.name, clazz);
+ }
+
core.addCloseHook(new CloseHook() {
@Override
public void preClose(SolrCore core) {
- //To change body of implemented methods use File | Settings | File Templates.
+ // To change body of implemented methods use File | Settings | File Templates.
}
@Override
@@ -299,7 +299,7 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
params = adjustParams(params);
req.setParams(params);
- if(params.get("action") != null) {
+ if (params.get("action") != null) {
handleAdmin(req, rsp, params);
return;
}
@@ -308,7 +308,7 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
try {
StreamExpression streamExpression = StreamExpressionParser.parse(params.get("expr"));
- if(this.streamFactory.isEvaluator(streamExpression)) {
+ if (this.streamFactory.isEvaluator(streamExpression)) {
StreamExpression tupleExpression = new StreamExpression("tuple");
tupleExpression.addParameter(new StreamExpressionNamedParameter("return-value", streamExpression));
tupleStream = this.streamFactory.constructStream(tupleExpression);
@@ -316,7 +316,8 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
tupleStream = this.streamFactory.constructStream(streamExpression);
}
} catch (Exception e) {
- //Catch exceptions that occur while the stream is being created. This will include streaming expression parse rules.
+ // Catch exceptions that occur while the stream is being created. This will include streaming expression parse
+ // rules.
SolrException.log(logger, e);
rsp.add("result-set", new DummyErrorStream(e));
@@ -334,21 +335,21 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
context.put("core", this.coreName);
context.put("solr-core", req.getCore());
tupleStream.setStreamContext(context);
-
+
// if asking for explanation then go get it
- if(params.getBool("explain", false)){
+ if (params.getBool("explain", false)) {
rsp.add("explanation", tupleStream.toExplanation(this.streamFactory));
}
-
- if(tupleStream instanceof DaemonStream) {
- DaemonStream daemonStream = (DaemonStream)tupleStream;
- if(daemons.containsKey(daemonStream.getId())) {
+
+ if (tupleStream instanceof DaemonStream) {
+ DaemonStream daemonStream = (DaemonStream) tupleStream;
+ if (daemons.containsKey(daemonStream.getId())) {
daemons.remove(daemonStream.getId()).close();
}
daemonStream.setDaemons(daemons);
- daemonStream.open(); //This will start the deamonStream
+ daemonStream.open(); // This will start the deamonStream
daemons.put(daemonStream.getId(), daemonStream);
- rsp.add("result-set", new DaemonResponseStream("Deamon:"+daemonStream.getId()+" started on "+coreName));
+ rsp.add("result-set", new DaemonResponseStream("Deamon:" + daemonStream.getId() + " started on " + coreName));
} else {
rsp.add("result-set", new TimerStream(new ExceptionStream(tupleStream)));
}
@@ -356,10 +357,10 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
private void handleAdmin(SolrQueryRequest req, SolrQueryResponse rsp, SolrParams params) {
String action = params.get("action");
- if("stop".equalsIgnoreCase(action)) {
+ if ("stop".equalsIgnoreCase(action)) {
String id = params.get(ID);
DaemonStream d = daemons.get(id);
- if(d != null) {
+ if (d != null) {
d.close();
rsp.add("result-set", new DaemonResponseStream("Deamon:" + id + " stopped on " + coreName));
} else {
@@ -400,50 +401,46 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
return null;
}
-
public static class DummyErrorStream extends TupleStream {
private Exception e;
public DummyErrorStream(Exception e) {
this.e = e;
}
+
public StreamComparator getStreamSort() {
return null;
}
- public void close() {
- }
+ public void close() {}
- public void open() {
- }
+ public void open() {}
- public void setStreamContext(StreamContext context) {
- }
+ public void setStreamContext(StreamContext context) {}
public List<TupleStream> children() {
return null;
}
-
+
@Override
public Explanation toExplanation(StreamFactory factory) throws IOException {
return new StreamExplanation(getStreamNodeId().toString())
- .withFunctionName("error")
- .withImplementingClass(this.getClass().getName())
- .withExpressionType(ExpressionType.STREAM_DECORATOR)
- .withExpression("--non-expressible--");
+ .withFunctionName("error")
+ .withImplementingClass(this.getClass().getName())
+ .withExpressionType(ExpressionType.STREAM_DECORATOR)
+ .withExpression("--non-expressible--");
}
public Tuple read() {
String msg = e.getMessage();
Throwable t = e.getCause();
- while(t != null) {
+ while (t != null) {
msg = t.getMessage();
t = t.getCause();
}
-
Map m = new HashMap();
m.put("EOF", true);
m.put("EXCEPTION", msg);
@@ -457,18 +454,16 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
public DaemonCollectionStream(Collection<DaemonStream> col) {
this.it = col.iterator();
}
+
public StreamComparator getStreamSort() {
return null;
}
- public void close() {
- }
+ public void close() {}
- public void open() {
- }
+ public void open() {}
- public void setStreamContext(StreamContext context) {
- }
+ public void setStreamContext(StreamContext context) {}
public List<TupleStream> children() {
return null;
@@ -478,14 +473,14 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
public Explanation toExplanation(StreamFactory factory) throws IOException {
return new StreamExplanation(getStreamNodeId().toString())
- .withFunctionName("daemon-collection")
- .withImplementingClass(this.getClass().getName())
- .withExpressionType(ExpressionType.STREAM_DECORATOR)
- .withExpression("--non-expressible--");
+ .withFunctionName("daemon-collection")
+ .withImplementingClass(this.getClass().getName())
+ .withExpressionType(ExpressionType.STREAM_DECORATOR)
+ .withExpression("--non-expressible--");
}
-
+
public Tuple read() {
- if(it.hasNext()) {
+ if (it.hasNext()) {
return it.next().getInfo();
} else {
Map m = new HashMap();
@@ -502,18 +497,16 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
public DaemonResponseStream(String message) {
this.message = message;
}
+
public StreamComparator getStreamSort() {
return null;
}
- public void close() {
- }
+ public void close() {}
- public void open() {
- }
+ public void open() {}
- public void setStreamContext(StreamContext context) {
- }
+ public void setStreamContext(StreamContext context) {}
public List<TupleStream> children() {
return null;
@@ -523,10 +516,10 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
public Explanation toExplanation(StreamFactory factory) throws IOException {
return new StreamExplanation(getStreamNodeId().toString())
- .withFunctionName("daemon-response")
- .withImplementingClass(this.getClass().getName())
- .withExpressionType(ExpressionType.STREAM_DECORATOR)
- .withExpression("--non-expressible--");
+ .withFunctionName("daemon-response")
+ .withImplementingClass(this.getClass().getName())
+ .withExpressionType(ExpressionType.STREAM_DECORATOR)
+ .withExpression("--non-expressible--");
}
public Tuple read() {
@@ -537,7 +530,7 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
} else {
sendEOF = true;
Map m = new HashMap();
- m.put("DaemonOp",message);
+ m.put("DaemonOp", message);
return new Tuple(m);
}
}
@@ -577,15 +570,15 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
public Explanation toExplanation(StreamFactory factory) throws IOException {
return new StreamExplanation(getStreamNodeId().toString())
- .withFunctionName("timer")
- .withImplementingClass(this.getClass().getName())
- .withExpressionType(ExpressionType.STREAM_DECORATOR)
- .withExpression("--non-expressible--");
+ .withFunctionName("timer")
+ .withImplementingClass(this.getClass().getName())
+ .withExpressionType(ExpressionType.STREAM_DECORATOR)
+ .withExpression("--non-expressible--");
}
public Tuple read() throws IOException {
Tuple tuple = this.tupleStream.read();
- if(tuple.EOF) {
+ if (tuple.EOF) {
long totalTime = (System.nanoTime() - begin) / 1000000;
tuple.fields.put("RESPONSE_TIME", totalTime);
}
@@ -593,25 +586,25 @@ public class StreamHandler extends RequestHandlerBase implements SolrCoreAware,
}
}
- private Map<String, List<String>> getCollectionShards(SolrParams params) {
+ private Map<String,List<String>> getCollectionShards(SolrParams params) {
- Map<String, List<String>> collectionShards = new HashMap();
+ Map<String,List<String>> collectionShards = new HashMap();
Iterator<String> paramsIt = params.getParameterNamesIterator();
- while(paramsIt.hasNext()) {
+ while (paramsIt.hasNext()) {
String param = paramsIt.next();
- if(param.indexOf(".shards") > -1) {
+ if (param.indexOf(".shards") > -1) {
String collection = param.split("\\.")[0];
String shardString = params.get(param);
String[] shards = shardString.split(",");
List<String> shardList = new ArrayList();
- for(String shard : shards) {
+ for (String shard : shards) {
shardList.add(shard);
}
collectionShards.put(collection, shardList);
}
}
- if(collectionShards.size() > 0) {
+ if (collectionShards.size() > 0) {
return collectionShards;
} else {
return null;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/113459a8/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
index ed45ee9..065335b 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArrayEvaluator.java
@@ -18,30 +18,72 @@ package org.apache.solr.client.solrj.io.eval;
import java.io.IOException;
import java.util.ArrayList;
+import java.util.Comparator;
import java.util.List;
+import java.util.Locale;
+import java.util.stream.Collectors;
import org.apache.solr.client.solrj.io.Tuple;
import org.apache.solr.client.solrj.io.stream.expr.Explanation;
import org.apache.solr.client.solrj.io.stream.expr.Explanation.ExpressionType;
import org.apache.solr.client.solrj.io.stream.expr.Expressible;
import org.apache.solr.client.solrj.io.stream.expr.StreamExpression;
+import org.apache.solr.client.solrj.io.stream.expr.StreamExpressionNamedParameter;
import org.apache.solr.client.solrj.io.stream.expr.StreamExpressionParameter;
+import org.apache.solr.client.solrj.io.stream.expr.StreamExpressionValue;
import org.apache.solr.client.solrj.io.stream.expr.StreamFactory;
+import com.google.common.collect.Lists;
+
public class ArrayEvaluator extends ComplexEvaluator implements Expressible {
private static final long serialVersionUID = 1;
-
+ private String sortOrder;
+
public ArrayEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
- super(expression, factory);
+ super(expression, factory, Lists.newArrayList("sort"));
+
+ sortOrder = extractSortOrder(expression, factory);
+ }
+
+ private String extractSortOrder(StreamExpression expression, StreamFactory factory) throws IOException{
+ StreamExpressionNamedParameter sortParam = factory.getNamedOperand(expression, "sort");
+ if(null == sortParam){
+ return null; // this is ok
+ }
+
+ if(sortParam.getParameter() instanceof StreamExpressionValue){
+ String sortOrder = ((StreamExpressionValue)sortParam.getParameter()).getValue().trim().toLowerCase(Locale.ROOT);
+ if("asc".equals(sortOrder) || "desc".equals(sortOrder)){
+ return sortOrder;
+ }
+ }
+
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - invalid 'sort' parameter - expecting either 'asc' or 'desc'", expression));
}
public List<Object> evaluate(Tuple tuple) throws IOException {
List<Object> list = new ArrayList<>();
for(StreamEvaluator subEvaluator : subEvaluators) {
- Object value = (Number)subEvaluator.evaluate(tuple);
+ Object value = subEvaluator.evaluate(tuple);
+
+ // if we want sorting but the evaluated value is not comparable then we have an error
+ if(null != sortOrder && !(value instanceof Comparable<?>)){
+ String message = String.format(Locale.ROOT,"Failed to evaluate to a comparable object - evaluator '%s' resulted in type '%s' and value '%s'",
+ subEvaluator.toExpression(constructingFactory),
+ value.getClass().getName(),
+ value.toString());
+ throw new IOException(message);
+ }
+
list.add(value);
}
+
+ if(null != sortOrder){
+ // Because of the type checking above we know that the value is at least Comparable
+ Comparator<Comparable> comparator = "asc".equals(sortOrder) ? (left,right) -> left.compareTo(right) : (left,right) -> right.compareTo(left);
+ list = list.stream().map(value -> (Comparable<Object>)value).sorted(comparator).collect(Collectors.toList());
+ }
return list;
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/113459a8/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArraySortEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArraySortEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArraySortEvaluator.java
deleted file mode 100644
index dabc615..0000000
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ArraySortEvaluator.java
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one or more
- * contributor license agreements. See the NOTICE file distributed with
- * this work for additional information regarding copyright ownership.
- * The ASF licenses this file to You under the Apache License, Version 2.0
- * (the "License"); you may not use this file except in compliance with
- * the License. You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-package org.apache.solr.client.solrj.io.eval;
-
-import java.io.IOException;
-import java.util.ArrayList;
-import java.util.Collections;
-import java.util.Comparator;
-import java.util.List;
-
-import org.apache.solr.client.solrj.io.Tuple;
-import org.apache.solr.client.solrj.io.stream.expr.Explanation;
-import org.apache.solr.client.solrj.io.stream.expr.Explanation.ExpressionType;
-import org.apache.solr.client.solrj.io.stream.expr.Expressible;
-import org.apache.solr.client.solrj.io.stream.expr.StreamExpression;
-import org.apache.solr.client.solrj.io.stream.expr.StreamExpressionParameter;
-import org.apache.solr.client.solrj.io.stream.expr.StreamFactory;
-
-public class ArraySortEvaluator extends ComplexEvaluator implements Expressible {
-
- private static final long serialVersionUID = 1;
-
- public ArraySortEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
- super(expression, factory);
- }
-
- public List<Number> evaluate(Tuple tuple) throws IOException {
-
- if(subEvaluators.size() != 1) {
- throw new IOException("Array sort evaluator expects 1 parameters found: "+subEvaluators.size());
- }
-
- StreamEvaluator colEval1 = subEvaluators.get(0);
-
- List<Number> numbers1 = (List<Number>)colEval1.evaluate(tuple);
- List<Number> numbers2 = new ArrayList();
- numbers2.addAll(numbers1);
- Collections.sort(numbers2, new Comparator<Number>() {
- @Override
- public int compare(Number o1, Number o2) {
- Double d1 = o1.doubleValue();
- Double d2 = o2.doubleValue();
- return d1.compareTo(d2);
- }
- });
- return numbers2;
- }
-
- @Override
- public StreamExpressionParameter toExpression(StreamFactory factory) throws IOException {
- StreamExpression expression = new StreamExpression(factory.getFunctionName(getClass()));
- return expression;
- }
-
- @Override
- public Explanation toExplanation(StreamFactory factory) throws IOException {
- return new Explanation(nodeId.toString())
- .withExpressionType(ExpressionType.EVALUATOR)
- .withFunctionName(factory.getFunctionName(getClass()))
- .withImplementingClass(getClass().getName())
- .withExpression(toExpression(factory).toString());
- }
-}
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/113459a8/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ComplexEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ComplexEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ComplexEvaluator.java
index ea4c88c..ca1f0de 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ComplexEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/ComplexEvaluator.java
@@ -20,7 +20,9 @@ import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Locale;
+import java.util.Set;
import java.util.UUID;
+import java.util.stream.Collectors;
import org.apache.solr.client.solrj.io.stream.StreamContext;
import org.apache.solr.client.solrj.io.stream.expr.Explanation;
@@ -40,6 +42,10 @@ public abstract class ComplexEvaluator implements StreamEvaluator {
protected List<StreamEvaluator> subEvaluators = new ArrayList<StreamEvaluator>();
public ComplexEvaluator(StreamExpression expression, StreamFactory factory) throws IOException{
+ this(expression, factory, new ArrayList<>());
+ }
+
+ public ComplexEvaluator(StreamExpression expression, StreamFactory factory, List<String> ignoredNamedParameters) throws IOException{
constructingFactory = factory;
// We have to do this because order of the parameters matter
@@ -75,8 +81,16 @@ public abstract class ComplexEvaluator implements StreamEvaluator {
}
}
- if(expression.getParameters().size() != subEvaluators.size()){
- throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - unknown operands found - expecting only StreamEvaluators or field names", expression));
+ Set<String> namedParameters = factory.getNamedOperands(expression).stream().map(param -> param.getName()).collect(Collectors.toSet());
+ long ignorableCount = ignoredNamedParameters.stream().filter(name -> namedParameters.contains(name)).count();
+
+ if(0 != expression.getParameters().size() - subEvaluators.size() - ignorableCount){
+ if(namedParameters.isEmpty()){
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - unknown operands found - expecting only StreamEvaluators or field names", expression));
+ }
+ else{
+ throw new IOException(String.format(Locale.ROOT,"Invalid expression %s - unknown operands found - expecting only StreamEvaluators, field names, or named parameters [%s]", expression, namedParameters.stream().collect(Collectors.joining(","))));
+ }
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/113459a8/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/eval/ArrayEvaluatorTest.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/eval/ArrayEvaluatorTest.java b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/eval/ArrayEvaluatorTest.java
new file mode 100644
index 0000000..36e5e78
--- /dev/null
+++ b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/eval/ArrayEvaluatorTest.java
@@ -0,0 +1,155 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.solr.client.solrj.io.stream.eval;
+
+import java.io.IOException;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+import org.apache.lucene.util.LuceneTestCase;
+import org.apache.solr.client.solrj.io.Tuple;
+import org.apache.solr.client.solrj.io.eval.ArrayEvaluator;
+import org.apache.solr.client.solrj.io.eval.StreamEvaluator;
+import org.apache.solr.client.solrj.io.stream.StreamContext;
+import org.apache.solr.client.solrj.io.stream.expr.StreamFactory;
+import org.junit.Test;
+
+import junit.framework.Assert;
+
+public class ArrayEvaluatorTest extends LuceneTestCase {
+
+ StreamFactory factory;
+ Map<String, Object> values;
+
+ public ArrayEvaluatorTest() {
+ super();
+
+ factory = new StreamFactory()
+ .withFunctionName("array", ArrayEvaluator.class);
+ values = new HashMap<String,Object>();
+ }
+
+ @Test
+ public void arrayLongSortAscTest() throws IOException{
+ StreamEvaluator evaluator = factory.constructEvaluator("array(a,b,c, sort=asc)");
+ StreamContext context = new StreamContext();
+ evaluator.setStreamContext(context);
+ Object result;
+
+ values.put("a", 1L);
+ values.put("b", 3L);
+ values.put("c", 2L);
+
+ result = evaluator.evaluate(new Tuple(values));
+
+ Assert.assertTrue(result instanceof List<?>);
+
+ Assert.assertEquals(3, ((List<?>)result).size());
+ Assert.assertEquals(1L, ((List<?>)result).get(0));
+ Assert.assertEquals(2L, ((List<?>)result).get(1));
+ Assert.assertEquals(3L, ((List<?>)result).get(2));
+ }
+
+ @Test
+ public void arrayLongSortDescTest() throws IOException{
+ StreamEvaluator evaluator = factory.constructEvaluator("array(a,b,c, sort=desc)");
+ StreamContext context = new StreamContext();
+ evaluator.setStreamContext(context);
+ Object result;
+
+ values.put("a", 1L);
+ values.put("b", 3L);
+ values.put("c", 2L);
+
+ result = evaluator.evaluate(new Tuple(values));
+
+ Assert.assertTrue(result instanceof List<?>);
+
+ Assert.assertEquals(3, ((List<?>)result).size());
+ Assert.assertEquals(3L, ((List<?>)result).get(0));
+ Assert.assertEquals(2L, ((List<?>)result).get(1));
+ Assert.assertEquals(1L, ((List<?>)result).get(2));
+ }
+
+ @Test
+ public void arrayStringSortAscTest() throws IOException{
+ StreamEvaluator evaluator = factory.constructEvaluator("array(a,b,c, sort=asc)");
+ StreamContext context = new StreamContext();
+ evaluator.setStreamContext(context);
+ Object result;
+
+ values.put("a", "a");
+ values.put("b", "c");
+ values.put("c", "b");
+
+ result = evaluator.evaluate(new Tuple(values));
+
+ Assert.assertTrue(result instanceof List<?>);
+
+ Assert.assertEquals(3, ((List<?>)result).size());
+ Assert.assertEquals("a", ((List<?>)result).get(0));
+ Assert.assertEquals("b", ((List<?>)result).get(1));
+ Assert.assertEquals("c", ((List<?>)result).get(2));
+ }
+
+ @Test
+ public void arrayStringSortDescTest() throws IOException{
+ StreamEvaluator evaluator = factory.constructEvaluator("array(a,b,c, sort=desc)");
+ StreamContext context = new StreamContext();
+ evaluator.setStreamContext(context);
+ Object result;
+
+ values.put("a", "a");
+ values.put("b", "c");
+ values.put("c", "b");
+
+ result = evaluator.evaluate(new Tuple(values));
+
+ Assert.assertTrue(result instanceof List<?>);
+
+ Assert.assertEquals(3, ((List<?>)result).size());
+ Assert.assertEquals("c", ((List<?>)result).get(0));
+ Assert.assertEquals("b", ((List<?>)result).get(1));
+ Assert.assertEquals("a", ((List<?>)result).get(2));
+ }
+
+ @Test
+ public void arrayStringUnsortedTest() throws IOException{
+ StreamEvaluator evaluator = factory.constructEvaluator("array(a,b,c)");
+ StreamContext context = new StreamContext();
+ evaluator.setStreamContext(context);
+ Object result;
+
+ values.put("a", "a");
+ values.put("b", "c");
+ values.put("c", "b");
+
+ result = evaluator.evaluate(new Tuple(values));
+
+ Assert.assertTrue(result instanceof List<?>);
+
+ Assert.assertEquals(3, ((List<?>)result).size());
+ Assert.assertEquals("a", ((List<?>)result).get(0));
+ Assert.assertEquals("c", ((List<?>)result).get(1));
+ Assert.assertEquals("b", ((List<?>)result).get(2));
+ }
+
+
+
+
+}
[11/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10882: Moves
parameter checking of anova evaluator
Posted by sh...@apache.org.
SOLR-10882: Moves parameter checking of anova evaluator
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/89888626
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/89888626
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/89888626
Branch: refs/heads/feature/autoscaling
Commit: 8988862698d95d2fc1239ffdf4f9c0e47eebbd99
Parents: f169510
Author: Dennis Gove <dp...@gmail.com>
Authored: Tue Jun 13 09:14:02 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Sun Jun 18 11:50:57 2017 -0400
----------------------------------------------------------------------
.../org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/89888626/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java
index d80e693..45c3c3f 100644
--- a/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java
+++ b/solr/solrj/src/java/org/apache/solr/client/solrj/io/eval/AnovaEvaluator.java
@@ -37,13 +37,13 @@ public class AnovaEvaluator extends ComplexEvaluator implements Expressible {
public AnovaEvaluator(StreamExpression expression, StreamFactory factory) throws IOException {
super(expression, factory);
- }
-
- public Tuple evaluate(Tuple tuple) throws IOException {
-
+
if(subEvaluators.size() < 2) {
throw new IOException("ANOVA evaluator expects atleast 2 parameters found: "+subEvaluators.size());
}
+ }
+
+ public Tuple evaluate(Tuple tuple) throws IOException {
List<double[]> list = new ArrayList();
for(StreamEvaluator subEvaluator : subEvaluators) {
[28/50] [abbrv] lucene-solr:feature/autoscaling: SOLR-10574: Adding
unified _default config set
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt
deleted file mode 100644
index 046829d..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt
+++ /dev/null
@@ -1,125 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Cleaned on October 11, 2009 (not normalized, so use before normalization)
-# This means that when modifying this list, you might need to add some
-# redundant entries, for example containing forms with both أ and ا
-من
-ومن
-منها
-منه
-في
-وفي
-فيها
-فيه
-و
-ف
-ثم
-او
-أو
-ب
-بها
-به
-ا
-أ
-اى
-اي
-أي
-أى
-لا
-ولا
-الا
-ألا
-إلا
-لكن
-ما
-وما
-كما
-فما
-عن
-مع
-اذا
-إذا
-ان
-أن
-إن
-انها
-أنها
-إنها
-انه
-أنه
-إنه
-بان
-بأن
-فان
-فأن
-وان
-وأن
-وإن
-التى
-التي
-الذى
-الذي
-الذين
-الى
-الي
-إلى
-إلي
-على
-عليها
-عليه
-اما
-أما
-إما
-ايضا
-أيضا
-كل
-وكل
-لم
-ولم
-لن
-ولن
-هى
-هي
-هو
-وهى
-وهي
-وهو
-فهى
-فهي
-فهو
-انت
-أنت
-لك
-لها
-له
-هذه
-هذا
-تلك
-ذلك
-هناك
-كانت
-كان
-يكون
-تكون
-وكانت
-وكان
-غير
-بعض
-قد
-نحو
-بين
-بينما
-منذ
-ضمن
-حيث
-الان
-الآن
-خلال
-بعد
-قبل
-حتى
-عند
-عندما
-لدى
-جميع
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt
deleted file mode 100644
index 1ae4ba2..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt
+++ /dev/null
@@ -1,193 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-а
-аз
-ако
-ала
-бе
-без
-беше
-би
-бил
-била
-били
-било
-близо
-бъдат
-бъде
-бяха
-в
-вас
-ваш
-ваша
-вероятно
-вече
-взема
-ви
-вие
-винаги
-все
-всеки
-всички
-всичко
-всяка
-във
-въпреки
-върху
-г
-ги
-главно
-го
-д
-да
-дали
-до
-докато
-докога
-дори
-досега
-доста
-е
-едва
-един
-ето
-за
-зад
-заедно
-заради
-засега
-затова
-защо
-защото
-и
-из
-или
-им
-има
-имат
-иска
-й
-каза
-как
-каква
-какво
-както
-какъв
-като
-кога
-когато
-което
-които
-кой
-който
-колко
-която
-къде
-където
-към
-ли
-м
-ме
-между
-мен
-ми
-мнозина
-мога
-могат
-може
-моля
-момента
-му
-н
-на
-над
-назад
-най
-направи
-напред
-например
-нас
-не
-него
-нея
-ни
-ние
-никой
-нито
-но
-някои
-някой
-няма
-обаче
-около
-освен
-особено
-от
-отгоре
-отново
-още
-пак
-по
-повече
-повечето
-под
-поне
-поради
-после
-почти
-прави
-пред
-преди
-през
-при
-пък
-първо
-с
-са
-само
-се
-сега
-си
-скоро
-след
-сме
-според
-сред
-срещу
-сте
-съм
-със
-също
-т
-тази
-така
-такива
-такъв
-там
-твой
-те
-тези
-ти
-тн
-то
-това
-тогава
-този
-той
-толкова
-точно
-трябва
-тук
-тъй
-тя
-тях
-у
-харесва
-ч
-че
-често
-чрез
-ще
-щом
-я
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt
deleted file mode 100644
index 3da65de..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt
+++ /dev/null
@@ -1,220 +0,0 @@
-# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
-a
-abans
-ací
-ah
-així
-això
-al
-als
-aleshores
-algun
-alguna
-algunes
-alguns
-alhora
-allà
-allí
-allò
-altra
-altre
-altres
-amb
-ambdós
-ambdues
-apa
-aquell
-aquella
-aquelles
-aquells
-aquest
-aquesta
-aquestes
-aquests
-aquí
-baix
-cada
-cadascú
-cadascuna
-cadascunes
-cadascuns
-com
-contra
-d'un
-d'una
-d'unes
-d'uns
-dalt
-de
-del
-dels
-des
-després
-dins
-dintre
-donat
-doncs
-durant
-e
-eh
-el
-els
-em
-en
-encara
-ens
-entre
-érem
-eren
-éreu
-es
-és
-esta
-està
-estàvem
-estaven
-estàveu
-esteu
-et
-etc
-ets
-fins
-fora
-gairebé
-ha
-han
-has
-havia
-he
-hem
-heu
-hi
-ho
-i
-igual
-iguals
-ja
-l'hi
-la
-les
-li
-li'n
-llavors
-m'he
-ma
-mal
-malgrat
-mateix
-mateixa
-mateixes
-mateixos
-me
-mentre
-més
-meu
-meus
-meva
-meves
-molt
-molta
-moltes
-molts
-mon
-mons
-n'he
-n'hi
-ne
-ni
-no
-nogensmenys
-només
-nosaltres
-nostra
-nostre
-nostres
-o
-oh
-oi
-on
-pas
-pel
-pels
-per
-però
-perquè
-poc
-poca
-pocs
-poques
-potser
-propi
-qual
-quals
-quan
-quant
-que
-què
-quelcom
-qui
-quin
-quina
-quines
-quins
-s'ha
-s'han
-sa
-semblant
-semblants
-ses
-seu
-seus
-seva
-seva
-seves
-si
-sobre
-sobretot
-sóc
-solament
-sols
-son
-són
-sons
-sota
-sou
-t'ha
-t'han
-t'he
-ta
-tal
-també
-tampoc
-tan
-tant
-tanta
-tantes
-teu
-teus
-teva
-teves
-ton
-tons
-tot
-tota
-totes
-tots
-un
-una
-unes
-uns
-us
-va
-vaig
-vam
-van
-vas
-veu
-vosaltres
-vostra
-vostre
-vostres
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt
deleted file mode 100644
index 53c6097..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-a
-s
-k
-o
-i
-u
-v
-z
-dnes
-cz
-tímto
-budeš
-budem
-byli
-jseš
-můj
-svým
-ta
-tomto
-tohle
-tuto
-tyto
-jej
-zda
-proč
-máte
-tato
-kam
-tohoto
-kdo
-kteří
-mi
-nám
-tom
-tomuto
-mít
-nic
-proto
-kterou
-byla
-toho
-protože
-asi
-ho
-naši
-napište
-re
-což
-tím
-takže
-svých
-její
-svými
-jste
-aj
-tu
-tedy
-teto
-bylo
-kde
-ke
-pravé
-ji
-nad
-nejsou
-či
-pod
-téma
-mezi
-přes
-ty
-pak
-vám
-ani
-když
-však
-neg
-jsem
-tento
-článku
-články
-aby
-jsme
-před
-pta
-jejich
-byl
-ještě
-až
-bez
-také
-pouze
-první
-vaše
-která
-nás
-nový
-tipy
-pokud
-může
-strana
-jeho
-své
-jiné
-zprávy
-nové
-není
-vás
-jen
-podle
-zde
-už
-být
-více
-bude
-již
-než
-který
-by
-které
-co
-nebo
-ten
-tak
-má
-při
-od
-po
-jsou
-jak
-další
-ale
-si
-se
-ve
-to
-jako
-za
-zpět
-ze
-do
-pro
-je
-na
-atd
-atp
-jakmile
-přičemž
-já
-on
-ona
-ono
-oni
-ony
-my
-vy
-jí
-ji
-mě
-mne
-jemu
-tomu
-těm
-těmu
-němu
-němuž
-jehož
-jíž
-jelikož
-jež
-jakož
-načež
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt
deleted file mode 100644
index 42e6145..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt
+++ /dev/null
@@ -1,110 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Danish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large text sample.
-
-
-og | and
-i | in
-jeg | I
-det | that (dem. pronoun)/it (pers. pronoun)
-at | that (in front of a sentence)/to (with infinitive)
-en | a/an
-den | it (pers. pronoun)/that (dem. pronoun)
-til | to/at/for/until/against/by/of/into, more
-er | present tense of "to be"
-som | who, as
-på | on/upon/in/on/at/to/after/of/with/for, on
-de | they
-med | with/by/in, along
-han | he
-af | of/by/from/off/for/in/with/on, off
-for | at/for/to/from/by/of/ago, in front/before, because
-ikke | not
-der | who/which, there/those
-var | past tense of "to be"
-mig | me/myself
-sig | oneself/himself/herself/itself/themselves
-men | but
-et | a/an/one, one (number), someone/somebody/one
-har | present tense of "to have"
-om | round/about/for/in/a, about/around/down, if
-vi | we
-min | my
-havde | past tense of "to have"
-ham | him
-hun | she
-nu | now
-over | over/above/across/by/beyond/past/on/about, over/past
-da | then, when/as/since
-fra | from/off/since, off, since
-du | you
-ud | out
-sin | his/her/its/one's
-dem | them
-os | us/ourselves
-op | up
-man | you/one
-hans | his
-hvor | where
-eller | or
-hvad | what
-skal | must/shall etc.
-selv | myself/youself/herself/ourselves etc., even
-her | here
-alle | all/everyone/everybody etc.
-vil | will (verb)
-blev | past tense of "to stay/to remain/to get/to become"
-kunne | could
-ind | in
-når | when
-være | present tense of "to be"
-dog | however/yet/after all
-noget | something
-ville | would
-jo | you know/you see (adv), yes
-deres | their/theirs
-efter | after/behind/according to/for/by/from, later/afterwards
-ned | down
-skulle | should
-denne | this
-end | than
-dette | this
-mit | my/mine
-også | also
-under | under/beneath/below/during, below/underneath
-have | have
-dig | you
-anden | other
-hende | her
-mine | my
-alt | everything
-meget | much/very, plenty of
-sit | his, her, its, one's
-sine | his, her, its, one's
-vor | our
-mod | against
-disse | these
-hvis | if
-din | your/yours
-nogle | some
-hos | by/at
-blive | be/become
-mange | many
-ad | by/through
-bliver | present tense of "to be/to become"
-hendes | her/hers
-været | be
-thi | for (conj)
-jer | you
-sådan | such, like this/like that
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt
deleted file mode 100644
index 86525e7..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt
+++ /dev/null
@@ -1,294 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A German stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | The number of forms in this list is reduced significantly by passing it
- | through the German stemmer.
-
-
-aber | but
-
-alle | all
-allem
-allen
-aller
-alles
-
-als | than, as
-also | so
-am | an + dem
-an | at
-
-ander | other
-andere
-anderem
-anderen
-anderer
-anderes
-anderm
-andern
-anderr
-anders
-
-auch | also
-auf | on
-aus | out of
-bei | by
-bin | am
-bis | until
-bist | art
-da | there
-damit | with it
-dann | then
-
-der | the
-den
-des
-dem
-die
-das
-
-daß | that
-
-derselbe | the same
-derselben
-denselben
-desselben
-demselben
-dieselbe
-dieselben
-dasselbe
-
-dazu | to that
-
-dein | thy
-deine
-deinem
-deinen
-deiner
-deines
-
-denn | because
-
-derer | of those
-dessen | of him
-
-dich | thee
-dir | to thee
-du | thou
-
-dies | this
-diese
-diesem
-diesen
-dieser
-dieses
-
-
-doch | (several meanings)
-dort | (over) there
-
-
-durch | through
-
-ein | a
-eine
-einem
-einen
-einer
-eines
-
-einig | some
-einige
-einigem
-einigen
-einiger
-einiges
-
-einmal | once
-
-er | he
-ihn | him
-ihm | to him
-
-es | it
-etwas | something
-
-euer | your
-eure
-eurem
-euren
-eurer
-eures
-
-für | for
-gegen | towards
-gewesen | p.p. of sein
-hab | have
-habe | have
-haben | have
-hat | has
-hatte | had
-hatten | had
-hier | here
-hin | there
-hinter | behind
-
-ich | I
-mich | me
-mir | to me
-
-
-ihr | you, to her
-ihre
-ihrem
-ihren
-ihrer
-ihres
-euch | to you
-
-im | in + dem
-in | in
-indem | while
-ins | in + das
-ist | is
-
-jede | each, every
-jedem
-jeden
-jeder
-jedes
-
-jene | that
-jenem
-jenen
-jener
-jenes
-
-jetzt | now
-kann | can
-
-kein | no
-keine
-keinem
-keinen
-keiner
-keines
-
-können | can
-könnte | could
-machen | do
-man | one
-
-manche | some, many a
-manchem
-manchen
-mancher
-manches
-
-mein | my
-meine
-meinem
-meinen
-meiner
-meines
-
-mit | with
-muss | must
-musste | had to
-nach | to(wards)
-nicht | not
-nichts | nothing
-noch | still, yet
-nun | now
-nur | only
-ob | whether
-oder | or
-ohne | without
-sehr | very
-
-sein | his
-seine
-seinem
-seinen
-seiner
-seines
-
-selbst | self
-sich | herself
-
-sie | they, she
-ihnen | to them
-
-sind | are
-so | so
-
-solche | such
-solchem
-solchen
-solcher
-solches
-
-soll | shall
-sollte | should
-sondern | but
-sonst | else
-über | over
-um | about, around
-und | and
-
-uns | us
-unse
-unsem
-unsen
-unser
-unses
-
-unter | under
-viel | much
-vom | von + dem
-von | from
-vor | before
-während | while
-war | was
-waren | were
-warst | wast
-was | what
-weg | away, off
-weil | because
-weiter | further
-
-welche | which
-welchem
-welchen
-welcher
-welches
-
-wenn | when
-werde | will
-werden | will
-wie | how
-wieder | again
-will | want
-wir | we
-wird | will
-wirst | willst
-wo | where
-wollen | want
-wollte | wanted
-würde | would
-würden | would
-zu | to
-zum | zu + dem
-zur | zu + der
-zwar | indeed
-zwischen | between
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt
deleted file mode 100644
index 232681f..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt
+++ /dev/null
@@ -1,78 +0,0 @@
-# Lucene Greek Stopwords list
-# Note: by default this file is used after GreekLowerCaseFilter,
-# so when modifying this file use 'σ' instead of 'ς'
-ο
-η
-το
-οι
-τα
-του
-τησ
-των
-τον
-την
-και
-κι
-κ
-ειμαι
-εισαι
-ειναι
-ειμαστε
-ειστε
-στο
-στον
-στη
-στην
-μα
-αλλα
-απο
-για
-προσ
-με
-σε
-ωσ
-παρα
-αντι
-κατα
-μετα
-θα
-να
-δε
-δεν
-μη
-μην
-επι
-ενω
-εαν
-αν
-τοτε
-που
-πωσ
-ποιοσ
-ποια
-ποιο
-ποιοι
-ποιεσ
-ποιων
-ποιουσ
-αυτοσ
-αυτη
-αυτο
-αυτοι
-αυτων
-αυτουσ
-αυτεσ
-αυτα
-εκεινοσ
-εκεινη
-εκεινο
-εκεινοι
-εκεινεσ
-εκεινα
-εκεινων
-εκεινουσ
-οπωσ
-ομωσ
-ισωσ
-οσο
-οτι
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_en.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_en.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_en.txt
deleted file mode 100644
index 2c164c0..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_en.txt
+++ /dev/null
@@ -1,54 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one or more
-# contributor license agreements. See the NOTICE file distributed with
-# this work for additional information regarding copyright ownership.
-# The ASF licenses this file to You under the Apache License, Version 2.0
-# (the "License"); you may not use this file except in compliance with
-# the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-# a couple of test stopwords to test that the words are really being
-# configured from this file:
-stopworda
-stopwordb
-
-# Standard english stop words taken from Lucene's StopAnalyzer
-a
-an
-and
-are
-as
-at
-be
-but
-by
-for
-if
-in
-into
-is
-it
-no
-not
-of
-on
-or
-such
-that
-the
-their
-then
-there
-these
-they
-this
-to
-was
-will
-with
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt
deleted file mode 100644
index 487d78c..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt
+++ /dev/null
@@ -1,356 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Spanish stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-
- | The following is a ranked list (commonest to rarest) of stopwords
- | deriving from a large sample of text.
-
- | Extra words have been added at the end.
-
-de | from, of
-la | the, her
-que | who, that
-el | the
-en | in
-y | and
-a | to
-los | the, them
-del | de + el
-se | himself, from him etc
-las | the, them
-por | for, by, etc
-un | a
-para | for
-con | with
-no | no
-una | a
-su | his, her
-al | a + el
- | es from SER
-lo | him
-como | how
-más | more
-pero | pero
-sus | su plural
-le | to him, her
-ya | already
-o | or
- | fue from SER
-este | this
- | ha from HABER
-sí | himself etc
-porque | because
-esta | this
- | son from SER
-entre | between
- | está from ESTAR
-cuando | when
-muy | very
-sin | without
-sobre | on
- | ser from SER
- | tiene from TENER
-también | also
-me | me
-hasta | until
-hay | there is/are
-donde | where
- | han from HABER
-quien | whom, that
- | están from ESTAR
- | estado from ESTAR
-desde | from
-todo | all
-nos | us
-durante | during
- | estados from ESTAR
-todos | all
-uno | a
-les | to them
-ni | nor
-contra | against
-otros | other
- | fueron from SER
-ese | that
-eso | that
- | había from HABER
-ante | before
-ellos | they
-e | and (variant of y)
-esto | this
-mí | me
-antes | before
-algunos | some
-qué | what?
-unos | a
-yo | I
-otro | other
-otras | other
-otra | other
-él | he
-tanto | so much, many
-esa | that
-estos | these
-mucho | much, many
-quienes | who
-nada | nothing
-muchos | many
-cual | who
- | sea from SER
-poco | few
-ella | she
-estar | to be
- | haber from HABER
-estas | these
- | estaba from ESTAR
- | estamos from ESTAR
-algunas | some
-algo | something
-nosotros | we
-
- | other forms
-
-mi | me
-mis | mi plural
-tú | thou
-te | thee
-ti | thee
-tu | thy
-tus | tu plural
-ellas | they
-nosotras | we
-vosotros | you
-vosotras | you
-os | you
-mío | mine
-mía |
-míos |
-mías |
-tuyo | thine
-tuya |
-tuyos |
-tuyas |
-suyo | his, hers, theirs
-suya |
-suyos |
-suyas |
-nuestro | ours
-nuestra |
-nuestros |
-nuestras |
-vuestro | yours
-vuestra |
-vuestros |
-vuestras |
-esos | those
-esas | those
-
- | forms of estar, to be (not including the infinitive):
-estoy
-estás
-está
-estamos
-estáis
-están
-esté
-estés
-estemos
-estéis
-estén
-estaré
-estarás
-estará
-estaremos
-estaréis
-estarán
-estaría
-estarías
-estaríamos
-estaríais
-estarían
-estaba
-estabas
-estábamos
-estabais
-estaban
-estuve
-estuviste
-estuvo
-estuvimos
-estuvisteis
-estuvieron
-estuviera
-estuvieras
-estuviéramos
-estuvierais
-estuvieran
-estuviese
-estuvieses
-estuviésemos
-estuvieseis
-estuviesen
-estando
-estado
-estada
-estados
-estadas
-estad
-
- | forms of haber, to have (not including the infinitive):
-he
-has
-ha
-hemos
-habéis
-han
-haya
-hayas
-hayamos
-hayáis
-hayan
-habré
-habrás
-habrá
-habremos
-habréis
-habrán
-habría
-habrías
-habríamos
-habríais
-habrían
-había
-habías
-habíamos
-habíais
-habían
-hube
-hubiste
-hubo
-hubimos
-hubisteis
-hubieron
-hubiera
-hubieras
-hubiéramos
-hubierais
-hubieran
-hubiese
-hubieses
-hubiésemos
-hubieseis
-hubiesen
-habiendo
-habido
-habida
-habidos
-habidas
-
- | forms of ser, to be (not including the infinitive):
-soy
-eres
-es
-somos
-sois
-son
-sea
-seas
-seamos
-seáis
-sean
-seré
-serás
-será
-seremos
-seréis
-serán
-sería
-serías
-seríamos
-seríais
-serían
-era
-eras
-éramos
-erais
-eran
-fui
-fuiste
-fue
-fuimos
-fuisteis
-fueron
-fuera
-fueras
-fuéramos
-fuerais
-fueran
-fuese
-fueses
-fuésemos
-fueseis
-fuesen
-siendo
-sido
- | sed also means 'thirst'
-
- | forms of tener, to have (not including the infinitive):
-tengo
-tienes
-tiene
-tenemos
-tenéis
-tienen
-tenga
-tengas
-tengamos
-tengáis
-tengan
-tendré
-tendrás
-tendrá
-tendremos
-tendréis
-tendrán
-tendría
-tendrías
-tendríamos
-tendríais
-tendrían
-tenía
-tenías
-teníamos
-teníais
-tenían
-tuve
-tuviste
-tuvo
-tuvimos
-tuvisteis
-tuvieron
-tuviera
-tuvieras
-tuviéramos
-tuvierais
-tuvieran
-tuviese
-tuvieses
-tuviésemos
-tuvieseis
-tuviesen
-teniendo
-tenido
-tenida
-tenidos
-tenidas
-tened
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt
deleted file mode 100644
index 25f1db9..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt
+++ /dev/null
@@ -1,99 +0,0 @@
-# example set of basque stopwords
-al
-anitz
-arabera
-asko
-baina
-bat
-batean
-batek
-bati
-batzuei
-batzuek
-batzuetan
-batzuk
-bera
-beraiek
-berau
-berauek
-bere
-berori
-beroriek
-beste
-bezala
-da
-dago
-dira
-ditu
-du
-dute
-edo
-egin
-ere
-eta
-eurak
-ez
-gainera
-gu
-gutxi
-guzti
-haiei
-haiek
-haietan
-hainbeste
-hala
-han
-handik
-hango
-hara
-hari
-hark
-hartan
-hau
-hauei
-hauek
-hauetan
-hemen
-hemendik
-hemengo
-hi
-hona
-honek
-honela
-honetan
-honi
-hor
-hori
-horiei
-horiek
-horietan
-horko
-horra
-horrek
-horrela
-horretan
-horri
-hortik
-hura
-izan
-ni
-noiz
-nola
-non
-nondik
-nongo
-nor
-nora
-ze
-zein
-zen
-zenbait
-zenbat
-zer
-zergatik
-ziren
-zituen
-zu
-zuek
-zuen
-zuten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt
deleted file mode 100644
index 723641c..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt
+++ /dev/null
@@ -1,313 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# Note: by default this file is used after normalization, so when adding entries
-# to this file, use the arabic 'ي' instead of 'ی'
-انان
-نداشته
-سراسر
-خياه
-ايشان
-وي
-تاكنون
-بيشتري
-دوم
-پس
-ناشي
-وگو
-يا
-داشتند
-سپس
-هنگام
-هرگز
-پنج
-نشان
-امسال
-ديگر
-گروهي
-شدند
-چطور
-ده
-و
-دو
-نخستين
-ولي
-چرا
-چه
-وسط
-ه
-كدام
-قابل
-يك
-رفت
-هفت
-همچنين
-در
-هزار
-بله
-بلي
-شايد
-اما
-شناسي
-گرفته
-دهد
-داشته
-دانست
-داشتن
-خواهيم
-ميليارد
-وقتيكه
-امد
-خواهد
-جز
-اورده
-شده
-بلكه
-خدمات
-شدن
-برخي
-نبود
-بسياري
-جلوگيري
-حق
-كردند
-نوعي
-بعري
-نكرده
-نظير
-نبايد
-بوده
-بودن
-داد
-اورد
-هست
-جايي
-شود
-دنبال
-داده
-بايد
-سابق
-هيچ
-همان
-انجا
-كمتر
-كجاست
-گردد
-كسي
-تر
-مردم
-تان
-دادن
-بودند
-سري
-جدا
-ندارند
-مگر
-يكديگر
-دارد
-دهند
-بنابراين
-هنگامي
-سمت
-جا
-انچه
-خود
-دادند
-زياد
-دارند
-اثر
-بدون
-بهترين
-بيشتر
-البته
-به
-براساس
-بيرون
-كرد
-بعضي
-گرفت
-توي
-اي
-ميليون
-او
-جريان
-تول
-بر
-مانند
-برابر
-باشيم
-مدتي
-گويند
-اكنون
-تا
-تنها
-جديد
-چند
-بي
-نشده
-كردن
-كردم
-گويد
-كرده
-كنيم
-نمي
-نزد
-روي
-قصد
-فقط
-بالاي
-ديگران
-اين
-ديروز
-توسط
-سوم
-ايم
-دانند
-سوي
-استفاده
-شما
-كنار
-داريم
-ساخته
-طور
-امده
-رفته
-نخست
-بيست
-نزديك
-طي
-كنيد
-از
-انها
-تمامي
-داشت
-يكي
-طريق
-اش
-چيست
-روب
-نمايد
-گفت
-چندين
-چيزي
-تواند
-ام
-ايا
-با
-ان
-ايد
-ترين
-اينكه
-ديگري
-راه
-هايي
-بروز
-همچنان
-پاعين
-كس
-حدود
-مختلف
-مقابل
-چيز
-گيرد
-ندارد
-ضد
-همچون
-سازي
-شان
-مورد
-باره
-مرسي
-خويش
-برخوردار
-چون
-خارج
-شش
-هنوز
-تحت
-ضمن
-هستيم
-گفته
-فكر
-بسيار
-پيش
-براي
-روزهاي
-انكه
-نخواهد
-بالا
-كل
-وقتي
-كي
-چنين
-كه
-گيري
-نيست
-است
-كجا
-كند
-نيز
-يابد
-بندي
-حتي
-توانند
-عقب
-خواست
-كنند
-بين
-تمام
-همه
-ما
-باشند
-مثل
-شد
-اري
-باشد
-اره
-طبق
-بعد
-اگر
-صورت
-غير
-جاي
-بيش
-ريزي
-اند
-زيرا
-چگونه
-بار
-لطفا
-مي
-درباره
-من
-ديده
-همين
-گذاري
-برداري
-علت
-گذاشته
-هم
-فوق
-نه
-ها
-شوند
-اباد
-همواره
-هر
-اول
-خواهند
-چهار
-نام
-امروز
-مان
-هاي
-قبل
-كنم
-سعي
-تازه
-را
-هستند
-زير
-جلوي
-عنوان
-بود
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt
deleted file mode 100644
index 4372c9a..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt
+++ /dev/null
@@ -1,97 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
-| forms of BE
-
-olla
-olen
-olet
-on
-olemme
-olette
-ovat
-ole | negative form
-
-oli
-olisi
-olisit
-olisin
-olisimme
-olisitte
-olisivat
-olit
-olin
-olimme
-olitte
-olivat
-ollut
-olleet
-
-en | negation
-et
-ei
-emme
-ette
-eivät
-
-|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
-minä minun minut minua minussa minusta minuun minulla minulta minulle | I
-sinä sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
-hän hänen hänet häntä hänessä hänestä häneen hänellä häneltä hänelle | he she
-me meidän meidät meitä meissä meistä meihin meillä meiltä meille | we
-te teidän teidät teitä teissä teistä teihin teillä teiltä teille | you
-he heidän heidät heitä heissä heistä heihin heillä heiltä heille | they
-
-tämä tämän tätä tässä tästä tähän tallä tältä tälle tänä täksi | this
-tuo tuon tuotä tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
-se sen sitä siinä siitä siihen sillä siltä sille sinä siksi | it
-nämä näiden näitä näissä näistä näihin näillä näiltä näille näinä näiksi | these
-nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
-ne niiden niitä niissä niistä niihin niillä niiltä niille niinä niiksi | they
-
-kuka kenen kenet ketä kenessä kenestä keneen kenellä keneltä kenelle kenenä keneksi| who
-ketkä keiden ketkä keitä keissä keistä keihin keillä keiltä keille keinä keiksi | (pl)
-mikä minkä minkä mitä missä mistä mihin millä miltä mille minä miksi | which what
-mitkä | (pl)
-
-joka jonka jota jossa josta johon jolla jolta jolle jona joksi | who which
-jotka joiden joita joissa joista joihin joilla joilta joille joina joiksi | (pl)
-
-| conjunctions
-
-että | that
-ja | and
-jos | if
-koska | because
-kuin | than
-mutta | but
-niin | so
-sekä | and
-sillä | for
-tai | or
-vaan | but
-vai | or
-vaikka | although
-
-
-| prepositions
-
-kanssa | with
-mukaan | according to
-noin | about
-poikki | across
-yli | over, across
-
-| other
-
-kun | when
-niin | so
-nyt | now
-itse | self
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt
deleted file mode 100644
index 749abae..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt
+++ /dev/null
@@ -1,186 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A French stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-au | a + le
-aux | a + les
-avec | with
-ce | this
-ces | these
-dans | with
-de | of
-des | de + les
-du | de + le
-elle | she
-en | `of them' etc
-et | and
-eux | them
-il | he
-je | I
-la | the
-le | the
-leur | their
-lui | him
-ma | my (fem)
-mais | but
-me | me
-même | same; as in moi-même (myself) etc
-mes | me (pl)
-moi | me
-mon | my (masc)
-ne | not
-nos | our (pl)
-notre | our
-nous | we
-on | one
-ou | where
-par | by
-pas | not
-pour | for
-qu | que before vowel
-que | that
-qui | who
-sa | his, her (fem)
-se | oneself
-ses | his (pl)
-son | his, her (masc)
-sur | on
-ta | thy (fem)
-te | thee
-tes | thy (pl)
-toi | thee
-ton | thy (masc)
-tu | thou
-un | a
-une | a
-vos | your (pl)
-votre | your
-vous | you
-
- | single letter forms
-
-c | c'
-d | d'
-j | j'
-l | l'
-à | to, at
-m | m'
-n | n'
-s | s'
-t | t'
-y | there
-
- | forms of être (not including the infinitive):
-été
-étée
-étées
-étés
-étant
-suis
-es
-est
-sommes
-êtes
-sont
-serai
-seras
-sera
-serons
-serez
-seront
-serais
-serait
-serions
-seriez
-seraient
-étais
-était
-étions
-étiez
-étaient
-fus
-fut
-fûmes
-fûtes
-furent
-sois
-soit
-soyons
-soyez
-soient
-fusse
-fusses
-fût
-fussions
-fussiez
-fussent
-
- | forms of avoir (not including the infinitive):
-ayant
-eu
-eue
-eues
-eus
-ai
-as
-avons
-avez
-ont
-aurai
-auras
-aura
-aurons
-aurez
-auront
-aurais
-aurait
-aurions
-auriez
-auraient
-avais
-avait
-avions
-aviez
-avaient
-eut
-eûmes
-eûtes
-eurent
-aie
-aies
-ait
-ayons
-ayez
-aient
-eusse
-eusses
-eût
-eussions
-eussiez
-eussent
-
- | Later additions (from Jean-Christophe Deschamps)
-ceci | this
-cela | that
-celà | that
-cet | this
-cette | this
-ici | here
-ils | they
-les | the (pl)
-leurs | their (pl)
-quel | which
-quels | which
-quelle | which
-quelles | which
-sans | without
-soi | oneself
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt
deleted file mode 100644
index 9ff88d7..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt
+++ /dev/null
@@ -1,110 +0,0 @@
-
-a
-ach
-ag
-agus
-an
-aon
-ar
-arna
-as
-b'
-ba
-beirt
-bhúr
-caoga
-ceathair
-ceathrar
-chomh
-chtó
-chuig
-chun
-cois
-céad
-cúig
-cúigear
-d'
-daichead
-dar
-de
-deich
-deichniúr
-den
-dhá
-do
-don
-dtí
-dá
-dár
-dó
-faoi
-faoin
-faoina
-faoinár
-fara
-fiche
-gach
-gan
-go
-gur
-haon
-hocht
-i
-iad
-idir
-in
-ina
-ins
-inár
-is
-le
-leis
-lena
-lenár
-m'
-mar
-mo
-mé
-na
-nach
-naoi
-naonúr
-ná
-ní
-níor
-nó
-nócha
-ocht
-ochtar
-os
-roimh
-sa
-seacht
-seachtar
-seachtó
-seasca
-seisear
-siad
-sibh
-sinn
-sna
-sé
-sí
-tar
-thar
-thú
-triúr
-trí
-trína
-trínár
-tríocha
-tú
-um
-ár
-é
-éis
-í
-ó
-ón
-óna
-ónár
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt
deleted file mode 100644
index d8760b1..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt
+++ /dev/null
@@ -1,161 +0,0 @@
-# galican stopwords
-a
-aínda
-alí
-aquel
-aquela
-aquelas
-aqueles
-aquilo
-aquí
-ao
-aos
-as
-así
-á
-ben
-cando
-che
-co
-coa
-comigo
-con
-connosco
-contigo
-convosco
-coas
-cos
-cun
-cuns
-cunha
-cunhas
-da
-dalgunha
-dalgunhas
-dalgún
-dalgúns
-das
-de
-del
-dela
-delas
-deles
-desde
-deste
-do
-dos
-dun
-duns
-dunha
-dunhas
-e
-el
-ela
-elas
-eles
-en
-era
-eran
-esa
-esas
-ese
-eses
-esta
-estar
-estaba
-está
-están
-este
-estes
-estiven
-estou
-eu
-é
-facer
-foi
-foron
-fun
-había
-hai
-iso
-isto
-la
-las
-lle
-lles
-lo
-los
-mais
-me
-meu
-meus
-min
-miña
-miñas
-moi
-na
-nas
-neste
-nin
-no
-non
-nos
-nosa
-nosas
-noso
-nosos
-nós
-nun
-nunha
-nuns
-nunhas
-o
-os
-ou
-ó
-ós
-para
-pero
-pode
-pois
-pola
-polas
-polo
-polos
-por
-que
-se
-senón
-ser
-seu
-seus
-sexa
-sido
-sobre
-súa
-súas
-tamén
-tan
-te
-ten
-teñen
-teño
-ter
-teu
-teus
-ti
-tido
-tiña
-tiven
-túa
-túas
-un
-unha
-unhas
-uns
-vos
-vosa
-vosas
-voso
-vosos
-vós
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt
deleted file mode 100644
index 86286bb..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt
+++ /dev/null
@@ -1,235 +0,0 @@
-# Also see http://www.opensource.org/licenses/bsd-license.html
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# Note: by default this file also contains forms normalized by HindiNormalizer
-# for spelling variation (see section below), such that it can be used whether or
-# not you enable that feature. When adding additional entries to this list,
-# please add the normalized form as well.
-अंदर
-अत
-अपना
-अपनी
-अपने
-अभी
-आदि
-आप
-इत्यादि
-इन
-इनका
-इन्हीं
-इन्हें
-इन्हों
-इस
-इसका
-इसकी
-इसके
-इसमें
-इसी
-इसे
-उन
-उनका
-उनकी
-उनके
-उनको
-उन्हीं
-उन्हें
-उन्हों
-उस
-उसके
-उसी
-उसे
-एक
-एवं
-एस
-ऐसे
-और
-कई
-कर
-करता
-करते
-करना
-करने
-करें
-कहते
-कहा
-का
-काफ़ी
-कि
-कितना
-किन्हें
-किन्हों
-किया
-किर
-किस
-किसी
-किसे
-की
-कुछ
-कुल
-के
-को
-कोई
-कौन
-कौनसा
-गया
-घर
-जब
-जहाँ
-जा
-जितना
-जिन
-जिन्हें
-जिन्हों
-जिस
-जिसे
-जीधर
-जैसा
-जैसे
-जो
-तक
-तब
-तरह
-तिन
-तिन्हें
-तिन्हों
-तिस
-तिसे
-तो
-था
-थी
-थे
-दबारा
-दिया
-दुसरा
-दूसरे
-दो
-द्वारा
-न
-नहीं
-ना
-निहायत
-नीचे
-ने
-पर
-पर
-पहले
-पूरा
-पे
-फिर
-बनी
-बही
-बहुत
-बाद
-बाला
-बिलकुल
-भी
-भीतर
-मगर
-मानो
-मे
-में
-यदि
-यह
-यहाँ
-यही
-या
-यिह
-ये
-रखें
-रहा
-रहे
-ऱ्वासा
-लिए
-लिये
-लेकिन
-व
-वर्ग
-वह
-वह
-वहाँ
-वहीं
-वाले
-वुह
-वे
-वग़ैरह
-संग
-सकता
-सकते
-सबसे
-सभी
-साथ
-साबुत
-साभ
-सारा
-से
-सो
-ही
-हुआ
-हुई
-हुए
-है
-हैं
-हो
-होता
-होती
-होते
-होना
-होने
-# additional normalized forms of the above
-अपनि
-जेसे
-होति
-सभि
-तिंहों
-इंहों
-दवारा
-इसि
-किंहें
-थि
-उंहों
-ओर
-जिंहें
-वहिं
-अभि
-बनि
-हि
-उंहिं
-उंहें
-हें
-वगेरह
-एसे
-रवासा
-कोन
-निचे
-काफि
-उसि
-पुरा
-भितर
-हे
-बहि
-वहां
-कोइ
-यहां
-जिंहों
-तिंहें
-किसि
-कइ
-यहि
-इंहिं
-जिधर
-इंहें
-अदि
-इतयादि
-हुइ
-कोनसा
-इसकि
-दुसरे
-जहां
-अप
-किंहों
-उनकि
-भि
-वरग
-हुअ
-जेसा
-नहिं
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt
deleted file mode 100644
index 37526da..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt
+++ /dev/null
@@ -1,211 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
-| Hungarian stop word list
-| prepared by Anna Tordai
-
-a
-ahogy
-ahol
-aki
-akik
-akkor
-alatt
-által
-általában
-amely
-amelyek
-amelyekben
-amelyeket
-amelyet
-amelynek
-ami
-amit
-amolyan
-amíg
-amikor
-át
-abban
-ahhoz
-annak
-arra
-arról
-az
-azok
-azon
-azt
-azzal
-azért
-aztán
-azután
-azonban
-bár
-be
-belül
-benne
-cikk
-cikkek
-cikkeket
-csak
-de
-e
-eddig
-egész
-egy
-egyes
-egyetlen
-egyéb
-egyik
-egyre
-ekkor
-el
-elég
-ellen
-elő
-először
-előtt
-első
-én
-éppen
-ebben
-ehhez
-emilyen
-ennek
-erre
-ez
-ezt
-ezek
-ezen
-ezzel
-ezért
-és
-fel
-felé
-hanem
-hiszen
-hogy
-hogyan
-igen
-így
-illetve
-ill.
-ill
-ilyen
-ilyenkor
-ison
-ismét
-itt
-jó
-jól
-jobban
-kell
-kellett
-keresztül
-keressünk
-ki
-kívül
-között
-közül
-legalább
-lehet
-lehetett
-legyen
-lenne
-lenni
-lesz
-lett
-maga
-magát
-majd
-majd
-már
-más
-másik
-meg
-még
-mellett
-mert
-mely
-melyek
-mi
-mit
-míg
-miért
-milyen
-mikor
-minden
-mindent
-mindenki
-mindig
-mint
-mintha
-mivel
-most
-nagy
-nagyobb
-nagyon
-ne
-néha
-nekem
-neki
-nem
-néhány
-nélkül
-nincs
-olyan
-ott
-össze
-ő
-ők
-őket
-pedig
-persze
-rá
-s
-saját
-sem
-semmi
-sok
-sokat
-sokkal
-számára
-szemben
-szerint
-szinte
-talán
-tehát
-teljes
-tovább
-továbbá
-több
-úgy
-ugyanis
-új
-újabb
-újra
-után
-utána
-utolsó
-vagy
-vagyis
-valaki
-valami
-valamint
-való
-vagyok
-van
-vannak
-volt
-voltam
-voltak
-voltunk
-vissza
-vele
-viszont
-volna
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt
deleted file mode 100644
index 60c1c50..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt
+++ /dev/null
@@ -1,46 +0,0 @@
-# example set of Armenian stopwords.
-այդ
-այլ
-այն
-այս
-դու
-դուք
-եմ
-են
-ենք
-ես
-եք
-է
-էի
-էին
-էինք
-էիր
-էիք
-էր
-ըստ
-թ
-ի
-ին
-իսկ
-իր
-կամ
-համար
-հետ
-հետո
-մենք
-մեջ
-մի
-ն
-նա
-նաև
-նրա
-նրանք
-որ
-որը
-որոնք
-որպես
-ու
-ում
-պիտի
-վրա
-և
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt
deleted file mode 100644
index 4617f83..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt
+++ /dev/null
@@ -1,359 +0,0 @@
-# from appendix D of: A Study of Stemming Effects on Information
-# Retrieval in Bahasa Indonesia
-ada
-adanya
-adalah
-adapun
-agak
-agaknya
-agar
-akan
-akankah
-akhirnya
-aku
-akulah
-amat
-amatlah
-anda
-andalah
-antar
-diantaranya
-antara
-antaranya
-diantara
-apa
-apaan
-mengapa
-apabila
-apakah
-apalagi
-apatah
-atau
-ataukah
-ataupun
-bagai
-bagaikan
-sebagai
-sebagainya
-bagaimana
-bagaimanapun
-sebagaimana
-bagaimanakah
-bagi
-bahkan
-bahwa
-bahwasanya
-sebaliknya
-banyak
-sebanyak
-beberapa
-seberapa
-begini
-beginian
-beginikah
-beginilah
-sebegini
-begitu
-begitukah
-begitulah
-begitupun
-sebegitu
-belum
-belumlah
-sebelum
-sebelumnya
-sebenarnya
-berapa
-berapakah
-berapalah
-berapapun
-betulkah
-sebetulnya
-biasa
-biasanya
-bila
-bilakah
-bisa
-bisakah
-sebisanya
-boleh
-bolehkah
-bolehlah
-buat
-bukan
-bukankah
-bukanlah
-bukannya
-cuma
-percuma
-dahulu
-dalam
-dan
-dapat
-dari
-daripada
-dekat
-demi
-demikian
-demikianlah
-sedemikian
-dengan
-depan
-di
-dia
-dialah
-dini
-diri
-dirinya
-terdiri
-dong
-dulu
-enggak
-enggaknya
-entah
-entahlah
-terhadap
-terhadapnya
-hal
-hampir
-hanya
-hanyalah
-harus
-haruslah
-harusnya
-seharusnya
-hendak
-hendaklah
-hendaknya
-hingga
-sehingga
-ia
-ialah
-ibarat
-ingin
-inginkah
-inginkan
-ini
-inikah
-inilah
-itu
-itukah
-itulah
-jangan
-jangankan
-janganlah
-jika
-jikalau
-juga
-justru
-kala
-kalau
-kalaulah
-kalaupun
-kalian
-kami
-kamilah
-kamu
-kamulah
-kan
-kapan
-kapankah
-kapanpun
-dikarenakan
-karena
-karenanya
-ke
-kecil
-kemudian
-kenapa
-kepada
-kepadanya
-ketika
-seketika
-khususnya
-kini
-kinilah
-kiranya
-sekiranya
-kita
-kitalah
-kok
-lagi
-lagian
-selagi
-lah
-lain
-lainnya
-melainkan
-selaku
-lalu
-melalui
-terlalu
-lama
-lamanya
-selama
-selama
-selamanya
-lebih
-terlebih
-bermacam
-macam
-semacam
-maka
-makanya
-makin
-malah
-malahan
-mampu
-mampukah
-mana
-manakala
-manalagi
-masih
-masihkah
-semasih
-masing
-mau
-maupun
-semaunya
-memang
-mereka
-merekalah
-meski
-meskipun
-semula
-mungkin
-mungkinkah
-nah
-namun
-nanti
-nantinya
-nyaris
-oleh
-olehnya
-seorang
-seseorang
-pada
-padanya
-padahal
-paling
-sepanjang
-pantas
-sepantasnya
-sepantasnyalah
-para
-pasti
-pastilah
-per
-pernah
-pula
-pun
-merupakan
-rupanya
-serupa
-saat
-saatnya
-sesaat
-saja
-sajalah
-saling
-bersama
-sama
-sesama
-sambil
-sampai
-sana
-sangat
-sangatlah
-saya
-sayalah
-se
-sebab
-sebabnya
-sebuah
-tersebut
-tersebutlah
-sedang
-sedangkan
-sedikit
-sedikitnya
-segala
-segalanya
-segera
-sesegera
-sejak
-sejenak
-sekali
-sekalian
-sekalipun
-sesekali
-sekaligus
-sekarang
-sekarang
-sekitar
-sekitarnya
-sela
-selain
-selalu
-seluruh
-seluruhnya
-semakin
-sementara
-sempat
-semua
-semuanya
-sendiri
-sendirinya
-seolah
-seperti
-sepertinya
-sering
-seringnya
-serta
-siapa
-siapakah
-siapapun
-disini
-disinilah
-sini
-sinilah
-sesuatu
-sesuatunya
-suatu
-sesudah
-sesudahnya
-sudah
-sudahkah
-sudahlah
-supaya
-tadi
-tadinya
-tak
-tanpa
-setelah
-telah
-tentang
-tentu
-tentulah
-tentunya
-tertentu
-seterusnya
-tapi
-tetapi
-setiap
-tiap
-setidaknya
-tidak
-tidakkah
-tidaklah
-toh
-waduh
-wah
-wahai
-sewaktu
-walau
-walaupun
-wong
-yaitu
-yakni
-yang
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt
deleted file mode 100644
index 1219cc7..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt
+++ /dev/null
@@ -1,303 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | An Italian stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-ad | a (to) before vowel
-al | a + il
-allo | a + lo
-ai | a + i
-agli | a + gli
-all | a + l'
-agl | a + gl'
-alla | a + la
-alle | a + le
-con | with
-col | con + il
-coi | con + i (forms collo, cogli etc are now very rare)
-da | from
-dal | da + il
-dallo | da + lo
-dai | da + i
-dagli | da + gli
-dall | da + l'
-dagl | da + gll'
-dalla | da + la
-dalle | da + le
-di | of
-del | di + il
-dello | di + lo
-dei | di + i
-degli | di + gli
-dell | di + l'
-degl | di + gl'
-della | di + la
-delle | di + le
-in | in
-nel | in + el
-nello | in + lo
-nei | in + i
-negli | in + gli
-nell | in + l'
-negl | in + gl'
-nella | in + la
-nelle | in + le
-su | on
-sul | su + il
-sullo | su + lo
-sui | su + i
-sugli | su + gli
-sull | su + l'
-sugl | su + gl'
-sulla | su + la
-sulle | su + le
-per | through, by
-tra | among
-contro | against
-io | I
-tu | thou
-lui | he
-lei | she
-noi | we
-voi | you
-loro | they
-mio | my
-mia |
-miei |
-mie |
-tuo |
-tua |
-tuoi | thy
-tue |
-suo |
-sua |
-suoi | his, her
-sue |
-nostro | our
-nostra |
-nostri |
-nostre |
-vostro | your
-vostra |
-vostri |
-vostre |
-mi | me
-ti | thee
-ci | us, there
-vi | you, there
-lo | him, the
-la | her, the
-li | them
-le | them, the
-gli | to him, the
-ne | from there etc
-il | the
-un | a
-uno | a
-una | a
-ma | but
-ed | and
-se | if
-perché | why, because
-anche | also
-come | how
-dov | where (as dov')
-dove | where
-che | who, that
-chi | who
-cui | whom
-non | not
-più | more
-quale | who, that
-quanto | how much
-quanti |
-quanta |
-quante |
-quello | that
-quelli |
-quella |
-quelle |
-questo | this
-questi |
-questa |
-queste |
-si | yes
-tutto | all
-tutti | all
-
- | single letter forms:
-
-a | at
-c | as c' for ce or ci
-e | and
-i | the
-l | as l'
-o | or
-
- | forms of avere, to have (not including the infinitive):
-
-ho
-hai
-ha
-abbiamo
-avete
-hanno
-abbia
-abbiate
-abbiano
-avrò
-avrai
-avrà
-avremo
-avrete
-avranno
-avrei
-avresti
-avrebbe
-avremmo
-avreste
-avrebbero
-avevo
-avevi
-aveva
-avevamo
-avevate
-avevano
-ebbi
-avesti
-ebbe
-avemmo
-aveste
-ebbero
-avessi
-avesse
-avessimo
-avessero
-avendo
-avuto
-avuta
-avuti
-avute
-
- | forms of essere, to be (not including the infinitive):
-sono
-sei
-è
-siamo
-siete
-sia
-siate
-siano
-sarò
-sarai
-sarà
-saremo
-sarete
-saranno
-sarei
-saresti
-sarebbe
-saremmo
-sareste
-sarebbero
-ero
-eri
-era
-eravamo
-eravate
-erano
-fui
-fosti
-fu
-fummo
-foste
-furono
-fossi
-fosse
-fossimo
-fossero
-essendo
-
- | forms of fare, to do (not including the infinitive, fa, fat-):
-faccio
-fai
-facciamo
-fanno
-faccia
-facciate
-facciano
-farò
-farai
-farà
-faremo
-farete
-faranno
-farei
-faresti
-farebbe
-faremmo
-fareste
-farebbero
-facevo
-facevi
-faceva
-facevamo
-facevate
-facevano
-feci
-facesti
-fece
-facemmo
-faceste
-fecero
-facessi
-facesse
-facessimo
-facessero
-facendo
-
- | forms of stare, to be (not including the infinitive):
-sto
-stai
-sta
-stiamo
-stanno
-stia
-stiate
-stiano
-starò
-starai
-starà
-staremo
-starete
-staranno
-starei
-staresti
-starebbe
-staremmo
-stareste
-starebbero
-stavo
-stavi
-stava
-stavamo
-stavate
-stavano
-stetti
-stesti
-stette
-stemmo
-steste
-stettero
-stessi
-stesse
-stessimo
-stessero
-stando
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt
deleted file mode 100644
index d4321be..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt
+++ /dev/null
@@ -1,127 +0,0 @@
-#
-# This file defines a stopword set for Japanese.
-#
-# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
-# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
-# for frequency lists, etc. that can be useful for making your own set (if desired)
-#
-# Note that there is an overlap between these stopwords and the terms stopped when used
-# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
-# that comments are not allowed on the same line as stopwords.
-#
-# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
-# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
-# using the same character width as the entries in this file. Since this StopFilter is
-# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
-# entries to be in half-width and your kana entries to be in full-width.
-#
-の
-に
-は
-を
-た
-が
-で
-て
-と
-し
-れ
-さ
-ある
-いる
-も
-する
-から
-な
-こと
-として
-い
-や
-れる
-など
-なっ
-ない
-この
-ため
-その
-あっ
-よう
-また
-もの
-という
-あり
-まで
-られ
-なる
-へ
-か
-だ
-これ
-によって
-により
-おり
-より
-による
-ず
-なり
-られる
-において
-ば
-なかっ
-なく
-しかし
-について
-せ
-だっ
-その後
-できる
-それ
-う
-ので
-なお
-のみ
-でき
-き
-つ
-における
-および
-いう
-さらに
-でも
-ら
-たり
-その他
-に関する
-たち
-ます
-ん
-なら
-に対して
-特に
-せる
-及び
-これら
-とき
-では
-にて
-ほか
-ながら
-うち
-そして
-とともに
-ただし
-かつて
-それぞれ
-または
-お
-ほど
-ものの
-に対する
-ほとんど
-と共に
-といった
-です
-とも
-ところ
-ここ
-##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt
deleted file mode 100644
index e21a23c..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
-# the original list of over 800 forms was refined:
-# pronouns, adverbs, interjections were removed
-#
-# prepositions
-aiz
-ap
-ar
-apakš
-ārpus
-augšpus
-bez
-caur
-dēļ
-gar
-iekš
-iz
-kopš
-labad
-lejpus
-līdz
-no
-otrpus
-pa
-par
-pār
-pēc
-pie
-pirms
-pret
-priekš
-starp
-šaipus
-uz
-viņpus
-virs
-virspus
-zem
-apakšpus
-# Conjunctions
-un
-bet
-jo
-ja
-ka
-lai
-tomēr
-tikko
-turpretī
-arī
-kaut
-gan
-tādēļ
-tā
-ne
-tikvien
-vien
-kā
-ir
-te
-vai
-kamēr
-# Particles
-ar
-diezin
-droši
-diemžēl
-nebūt
-ik
-it
-taču
-nu
-pat
-tiklab
-iekšpus
-nedz
-tik
-nevis
-turpretim
-jeb
-iekam
-iekām
-iekāms
-kolīdz
-līdzko
-tiklīdz
-jebšu
-tālab
-tāpēc
-nekā
-itin
-jā
-jau
-jel
-nē
-nezin
-tad
-tikai
-vis
-tak
-iekams
-vien
-# modal verbs
-būt
-biju
-biji
-bija
-bijām
-bijāt
-esmu
-esi
-esam
-esat
-būšu
-būsi
-būs
-būsim
-būsiet
-tikt
-tiku
-tiki
-tika
-tikām
-tikāt
-tieku
-tiec
-tiek
-tiekam
-tiekat
-tikšu
-tiks
-tiksim
-tiksiet
-tapt
-tapi
-tapāt
-topat
-tapšu
-tapsi
-taps
-tapsim
-tapsiet
-kļūt
-kļuvu
-kļuvi
-kļuva
-kļuvām
-kļuvāt
-kļūstu
-kļūsti
-kļūst
-kļūstam
-kļūstat
-kļūšu
-kļūsi
-kļūs
-kļūsim
-kļūsiet
-# verbs
-varēt
-varēju
-varējām
-varēšu
-varēsim
-var
-varēji
-varējāt
-varēsi
-varēsiet
-varat
-varēja
-varēs
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt
deleted file mode 100644
index 47a2aea..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt
+++ /dev/null
@@ -1,119 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Dutch stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This is a ranked list (commonest to rarest) of stopwords derived from
- | a large sample of Dutch text.
-
- | Dutch stop words frequently exhibit homonym clashes. These are indicated
- | clearly below.
-
-de | the
-en | and
-van | of, from
-ik | I, the ego
-te | (1) chez, at etc, (2) to, (3) too
-dat | that, which
-die | that, those, who, which
-in | in, inside
-een | a, an, one
-hij | he
-het | the, it
-niet | not, nothing, naught
-zijn | (1) to be, being, (2) his, one's, its
-is | is
-was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
-op | on, upon, at, in, up, used up
-aan | on, upon, to (as dative)
-met | with, by
-als | like, such as, when
-voor | (1) before, in front of, (2) furrow
-had | had, past tense all persons sing. of 'hebben' (have)
-er | there
-maar | but, only
-om | round, about, for etc
-hem | him
-dan | then
-zou | should/would, past tense all persons sing. of 'zullen'
-of | or, whether, if
-wat | what, something, anything
-mijn | possessive and noun 'mine'
-men | people, 'one'
-dit | this
-zo | so, thus, in this way
-door | through by
-over | over, across
-ze | she, her, they, them
-zich | oneself
-bij | (1) a bee, (2) by, near, at
-ook | also, too
-tot | till, until
-je | you
-mij | me
-uit | out of, from
-der | Old Dutch form of 'van der' still found in surnames
-daar | (1) there, (2) because
-haar | (1) her, their, them, (2) hair
-naar | (1) unpleasant, unwell etc, (2) towards, (3) as
-heb | present first person sing. of 'to have'
-hoe | how, why
-heeft | present third person sing. of 'to have'
-hebben | 'to have' and various parts thereof
-deze | this
-u | you
-want | (1) for, (2) mitten, (3) rigging
-nog | yet, still
-zal | 'shall', first and third person sing. of verb 'zullen' (will)
-me | me
-zij | she, they
-nu | now
-ge | 'thou', still used in Belgium and south Netherlands
-geen | none
-omdat | because
-iets | something, somewhat
-worden | to become, grow, get
-toch | yet, still
-al | all, every, each
-waren | (1) 'were' (2) to wander, (3) wares, (3)
-veel | much, many
-meer | (1) more, (2) lake
-doen | to do, to make
-toen | then, when
-moet | noun 'spot/mote' and present form of 'to must'
-ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
-zonder | without
-kan | noun 'can' and present form of 'to be able'
-hun | their, them
-dus | so, consequently
-alles | all, everything, anything
-onder | under, beneath
-ja | yes, of course
-eens | once, one day
-hier | here
-wie | who
-werd | imperfect third person sing. of 'become'
-altijd | always
-doch | yet, but etc
-wordt | present third person sing. of 'become'
-wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
-kunnen | to be able
-ons | us/our
-zelf | self
-tegen | against, towards, at
-na | after, near
-reeds | already
-wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
-kon | could; past tense of 'to be able'
-niets | nothing
-uw | your
-iemand | somebody
-geweest | been; past participle of 'be'
-andere | other
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt
deleted file mode 100644
index a7a2c28..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt
+++ /dev/null
@@ -1,194 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Norwegian stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
- | This stop word list is for the dominant bokmål dialect. Words unique
- | to nynorsk are marked *.
-
- | Revised by Jan Bruusgaard <Ja...@ssb.no>, Jan 2005
-
-og | and
-i | in
-jeg | I
-det | it/this/that
-at | to (w. inf.)
-en | a/an
-et | a/an
-den | it/this/that
-til | to
-er | is/am/are
-som | who/that
-på | on
-de | they / you(formal)
-med | with
-han | he
-av | of
-ikke | not
-ikkje | not *
-der | there
-så | so
-var | was/were
-meg | me
-seg | you
-men | but
-ett | one
-har | have
-om | about
-vi | we
-min | my
-mitt | my
-ha | have
-hadde | had
-hun | she
-nå | now
-over | over
-da | when/as
-ved | by/know
-fra | from
-du | you
-ut | out
-sin | your
-dem | them
-oss | us
-opp | up
-man | you/one
-kan | can
-hans | his
-hvor | where
-eller | or
-hva | what
-skal | shall/must
-selv | self (reflective)
-sjøl | self (reflective)
-her | here
-alle | all
-vil | will
-bli | become
-ble | became
-blei | became *
-blitt | have become
-kunne | could
-inn | in
-når | when
-være | be
-kom | come
-noen | some
-noe | some
-ville | would
-dere | you
-som | who/which/that
-deres | their/theirs
-kun | only/just
-ja | yes
-etter | after
-ned | down
-skulle | should
-denne | this
-for | for/because
-deg | you
-si | hers/his
-sine | hers/his
-sitt | hers/his
-mot | against
-å | to
-meget | much
-hvorfor | why
-dette | this
-disse | these/those
-uten | without
-hvordan | how
-ingen | none
-din | your
-ditt | your
-blir | become
-samme | same
-hvilken | which
-hvilke | which (plural)
-sånn | such a
-inni | inside/within
-mellom | between
-vår | our
-hver | each
-hvem | who
-vors | us/ours
-hvis | whose
-både | both
-bare | only/just
-enn | than
-fordi | as/because
-før | before
-mange | many
-også | also
-slik | just
-vært | been
-være | to be
-båe | both *
-begge | both
-siden | since
-dykk | your *
-dykkar | yours *
-dei | they *
-deira | them *
-deires | theirs *
-deim | them *
-di | your (fem.) *
-då | as/when *
-eg | I *
-ein | a/an *
-eit | a/an *
-eitt | a/an *
-elles | or *
-honom | he *
-hjå | at *
-ho | she *
-hoe | she *
-henne | her
-hennar | her/hers
-hennes | hers
-hoss | how *
-hossen | how *
-ikkje | not *
-ingi | noone *
-inkje | noone *
-korleis | how *
-korso | how *
-kva | what/which *
-kvar | where *
-kvarhelst | where *
-kven | who/whom *
-kvi | why *
-kvifor | why *
-me | we *
-medan | while *
-mi | my *
-mine | my *
-mykje | much *
-no | now *
-nokon | some (masc./neut.) *
-noka | some (fem.) *
-nokor | some *
-noko | some *
-nokre | some *
-si | his/hers *
-sia | since *
-sidan | since *
-so | so *
-somt | some *
-somme | some *
-um | about*
-upp | up *
-vere | be *
-vore | was *
-verte | become *
-vort | become *
-varte | became *
-vart | became *
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt
deleted file mode 100644
index acfeb01..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt
+++ /dev/null
@@ -1,253 +0,0 @@
- | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
- | This file is distributed under the BSD License.
- | See http://snowball.tartarus.org/license.php
- | Also see http://www.opensource.org/licenses/bsd-license.html
- | - Encoding was converted to UTF-8.
- | - This notice was added.
- |
- | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
-
- | A Portuguese stop word list. Comments begin with vertical bar. Each stop
- | word is at the start of a line.
-
-
- | The following is a ranked list (commonest to rarest) of stopwords
- | deriving from a large sample of text.
-
- | Extra words have been added at the end.
-
-de | of, from
-a | the; to, at; her
-o | the; him
-que | who, that
-e | and
-do | de + o
-da | de + a
-em | in
-um | a
-para | for
- | é from SER
-com | with
-não | not, no
-uma | a
-os | the; them
-no | em + o
-se | himself etc
-na | em + a
-por | for
-mais | more
-as | the; them
-dos | de + os
-como | as, like
-mas | but
- | foi from SER
-ao | a + o
-ele | he
-das | de + as
- | tem from TER
-à | a + a
-seu | his
-sua | her
-ou | or
- | ser from SER
-quando | when
-muito | much
- | há from HAV
-nos | em + os; us
-já | already, now
- | está from EST
-eu | I
-também | also
-só | only, just
-pelo | per + o
-pela | per + a
-até | up to
-isso | that
-ela | he
-entre | between
- | era from SER
-depois | after
-sem | without
-mesmo | same
-aos | a + os
- | ter from TER
-seus | his
-quem | whom
-nas | em + as
-me | me
-esse | that
-eles | they
- | estão from EST
-você | you
- | tinha from TER
- | foram from SER
-essa | that
-num | em + um
-nem | nor
-suas | her
-meu | my
-às | a + as
-minha | my
- | têm from TER
-numa | em + uma
-pelos | per + os
-elas | they
- | havia from HAV
- | seja from SER
-qual | which
- | será from SER
-nós | we
- | tenho from TER
-lhe | to him, her
-deles | of them
-essas | those
-esses | those
-pelas | per + as
-este | this
- | fosse from SER
-dele | of him
-
- | other words. There are many contractions such as naquele = em+aquele,
- | mo = me+o, but they are rare.
- | Indefinite article plural forms are also rare.
-
-tu | thou
-te | thee
-vocês | you (plural)
-vos | you
-lhes | to them
-meus | my
-minhas
-teu | thy
-tua
-teus
-tuas
-nosso | our
-nossa
-nossos
-nossas
-
-dela | of her
-delas | of them
-
-esta | this
-estes | these
-estas | these
-aquele | that
-aquela | that
-aqueles | those
-aquelas | those
-isto | this
-aquilo | that
-
- | forms of estar, to be (not including the infinitive):
-estou
-está
-estamos
-estão
-estive
-esteve
-estivemos
-estiveram
-estava
-estávamos
-estavam
-estivera
-estivéramos
-esteja
-estejamos
-estejam
-estivesse
-estivéssemos
-estivessem
-estiver
-estivermos
-estiverem
-
- | forms of haver, to have (not including the infinitive):
-hei
-há
-havemos
-hão
-houve
-houvemos
-houveram
-houvera
-houvéramos
-haja
-hajamos
-hajam
-houvesse
-houvéssemos
-houvessem
-houver
-houvermos
-houverem
-houverei
-houverá
-houveremos
-houverão
-houveria
-houveríamos
-houveriam
-
- | forms of ser, to be (not including the infinitive):
-sou
-somos
-são
-era
-éramos
-eram
-fui
-foi
-fomos
-foram
-fora
-fôramos
-seja
-sejamos
-sejam
-fosse
-fôssemos
-fossem
-for
-formos
-forem
-serei
-será
-seremos
-serão
-seria
-seríamos
-seriam
-
- | forms of ter, to have (not including the infinitive):
-tenho
-tem
-temos
-tém
-tinha
-tínhamos
-tinham
-tive
-teve
-tivemos
-tiveram
-tivera
-tivéramos
-tenha
-tenhamos
-tenham
-tivesse
-tivéssemos
-tivessem
-tiver
-tivermos
-tiverem
-terei
-terá
-teremos
-terão
-teria
-teríamos
-teriam
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/d1c807dd/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt
deleted file mode 100644
index 4fdee90..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt
+++ /dev/null
@@ -1,233 +0,0 @@
-# This file was created by Jacques Savoy and is distributed under the BSD license.
-# See http://members.unine.ch/jacques.savoy/clef/index.html.
-# Also see http://www.opensource.org/licenses/bsd-license.html
-acea
-aceasta
-această
-aceea
-acei
-aceia
-acel
-acela
-acele
-acelea
-acest
-acesta
-aceste
-acestea
-aceşti
-aceştia
-acolo
-acum
-ai
-aia
-aibă
-aici
-al
-ăla
-ale
-alea
-ălea
-altceva
-altcineva
-am
-ar
-are
-aş
-aşadar
-asemenea
-asta
-ăsta
-astăzi
-astea
-ăstea
-ăştia
-asupra
-aţi
-au
-avea
-avem
-aveţi
-azi
-bine
-bucur
-bună
-ca
-că
-căci
-când
-care
-cărei
-căror
-cărui
-cât
-câte
-câţi
-către
-câtva
-ce
-cel
-ceva
-chiar
-cînd
-cine
-cineva
-cît
-cîte
-cîţi
-cîtva
-contra
-cu
-cum
-cumva
-curând
-curînd
-da
-dă
-dacă
-dar
-datorită
-de
-deci
-deja
-deoarece
-departe
-deşi
-din
-dinaintea
-dintr
-dintre
-drept
-după
-ea
-ei
-el
-ele
-eram
-este
-eşti
-eu
-face
-fără
-fi
-fie
-fiecare
-fii
-fim
-fiţi
-iar
-ieri
-îi
-îl
-îmi
-împotriva
-în
-înainte
-înaintea
-încât
-încît
-încotro
-între
-întrucât
-întrucît
-îţi
-la
-lângă
-le
-li
-lîngă
-lor
-lui
-mă
-mâine
-mea
-mei
-mele
-mereu
-meu
-mi
-mine
-mult
-multă
-mulţi
-ne
-nicăieri
-nici
-nimeni
-nişte
-noastră
-noastre
-noi
-noştri
-nostru
-nu
-ori
-oricând
-oricare
-oricât
-orice
-oricînd
-oricine
-oricît
-oricum
-oriunde
-până
-pe
-pentru
-peste
-pînă
-poate
-pot
-prea
-prima
-primul
-prin
-printr
-sa
-să
-săi
-sale
-sau
-său
-se
-şi
-sînt
-sîntem
-sînteţi
-spre
-sub
-sunt
-suntem
-sunteţi
-ta
-tăi
-tale
-tău
-te
-ţi
-ţie
-tine
-toată
-toate
-tot
-toţi
-totuşi
-tu
-un
-una
-unde
-undeva
-unei
-unele
-uneori
-unor
-vă
-vi
-voastră
-voastre
-voi
-voştri
-vostru
-vouă
-vreo
-vreun