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 2017/06/27 05:19:12 UTC
[01/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Repository: lucene-solr
Updated Branches:
refs/heads/feature/autoscaling 4c47a3295 -> e863d0f54
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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 8fbf839..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/solrconfig.xml
+++ /dev/null
@@ -1,1398 +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>
-
- <!-- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded. It is safe to increase or remove this setting,
- since it is purely an arbitrary limit to try and catch user errors where
- large boolean queries may not be the best implementation choice.
- -->
- <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/e4a7fc59/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/e4a7fc59/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
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/solr/solrj/src/java/org/apache/solr/common/cloud/ZkConfigManager.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/common/cloud/ZkConfigManager.java b/solr/solrj/src/java/org/apache/solr/common/cloud/ZkConfigManager.java
index 0b3608b..312cb90 100644
--- a/solr/solrj/src/java/org/apache/solr/common/cloud/ZkConfigManager.java
+++ b/solr/solrj/src/java/org/apache/solr/common/cloud/ZkConfigManager.java
@@ -186,7 +186,7 @@ public class ZkConfigManager {
// Order is important here since "confDir" may be
// 1> a full path to the parent of a solrconfig.xml or parent of /conf/solrconfig.xml
- // 2> one of the canned config sets only, e.g. basic_configs
+ // 2> one of the canned config sets only, e.g. _default
// and trying to assemble a path for configsetDir/confDir is A Bad Idea. if confDir is a full path.
public static Path getConfigsetPath(String confDir, String configSetDir) throws IOException {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/solr/solrj/src/test/org/apache/solr/client/solrj/SolrSchemalessExampleTest.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/client/solrj/SolrSchemalessExampleTest.java b/solr/solrj/src/test/org/apache/solr/client/solrj/SolrSchemalessExampleTest.java
index 3d553d8..a7b4619 100644
--- a/solr/solrj/src/test/org/apache/solr/client/solrj/SolrSchemalessExampleTest.java
+++ b/solr/solrj/src/test/org/apache/solr/client/solrj/SolrSchemalessExampleTest.java
@@ -51,7 +51,7 @@ public class SolrSchemalessExampleTest extends SolrExampleTestsBase {
FileUtils.copyFileToDirectory(new File(ExternalPaths.SERVER_HOME, "solr.xml"), tempSolrHome);
File collection1Dir = new File(tempSolrHome, "collection1");
FileUtils.forceMkdir(collection1Dir);
- FileUtils.copyDirectoryToDirectory(new File(ExternalPaths.SCHEMALESS_CONFIGSET), collection1Dir);
+ FileUtils.copyDirectoryToDirectory(new File(ExternalPaths.DEFAULT_CONFIGSET), collection1Dir);
Properties props = new Properties();
props.setProperty("name","collection1");
OutputStreamWriter writer = null;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/solr/test-framework/src/java/org/apache/solr/util/ExternalPaths.java
----------------------------------------------------------------------
diff --git a/solr/test-framework/src/java/org/apache/solr/util/ExternalPaths.java b/solr/test-framework/src/java/org/apache/solr/util/ExternalPaths.java
index 1ebb2e9..93bf92e 100644
--- a/solr/test-framework/src/java/org/apache/solr/util/ExternalPaths.java
+++ b/solr/test-framework/src/java/org/apache/solr/util/ExternalPaths.java
@@ -41,8 +41,8 @@ public class ExternalPaths {
/* @see #SOURCE_HOME */
public static String WEBAPP_HOME = new File(SOURCE_HOME, "webapp/web").getAbsolutePath();
/* @see #SOURCE_HOME */
- public static String SCHEMALESS_CONFIGSET =
- new File(SOURCE_HOME, "server/solr/configsets/data_driven_schema_configs/conf").getAbsolutePath();
+ public static String DEFAULT_CONFIGSET =
+ new File(SOURCE_HOME, "server/solr/configsets/_default/conf").getAbsolutePath();
public static String TECHPRODUCTS_CONFIGSET =
new File(SOURCE_HOME, "server/solr/configsets/sample_techproducts_configs/conf").getAbsolutePath();
[10/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Posted by sh...@apache.org.
SOLR-10574: Adding _default configset, replacing data_driven_schema_configs and basic_configs
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/e4a7fc59
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/e4a7fc59
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/e4a7fc59
Branch: refs/heads/feature/autoscaling
Commit: e4a7fc59ad1b3375e9a7572f694e16cd1aef0b28
Parents: e805730
Author: Ishan Chattopadhyaya <is...@lucidworks.com>
Authored: Mon Jun 26 04:58:02 2017 +0530
Committer: Ishan Chattopadhyaya <is...@lucidworks.com>
Committed: Mon Jun 26 04:58:02 2017 +0530
----------------------------------------------------------------------
solr/CHANGES.txt | 8 +
solr/bin/solr | 12 +-
solr/bin/solr.cmd | 14 +-
.../src/java/org/apache/solr/util/SolrCLI.java | 8 +-
.../apache/solr/cloud/SolrCloudExampleTest.java | 11 +-
.../apache/solr/util/TestSolrCLIRunExample.java | 2 +-
solr/server/README.txt | 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 | 1076 ++++++++++++++
.../solr/configsets/_default/conf/params.json | 20 +
.../solr/configsets/_default/conf/protwords.txt | 21 +
.../configsets/_default/conf/solrconfig.xml | 1394 +++++++++++++++++
.../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 | 1052 -------------
.../configsets/basic_configs/conf/params.json | 20 -
.../configsets/basic_configs/conf/protwords.txt | 21 -
.../basic_configs/conf/solrconfig.xml | 1401 ------------------
.../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 | 1076 --------------
.../data_driven_schema_configs/conf/params.json | 20 -
.../conf/protwords.txt | 21 -
.../conf/solrconfig.xml | 1398 -----------------
.../conf/stopwords.txt | 14 -
.../conf/synonyms.txt | 29 -
.../solr/common/cloud/ZkConfigManager.java | 2 +-
.../client/solrj/SolrSchemalessExampleTest.java | 2 +-
.../org/apache/solr/util/ExternalPaths.java | 4 +-
148 files changed, 8740 insertions(+), 17424 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 64095fa..800b645 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -111,6 +111,11 @@ Upgrading from Solr 6.x
* The unused 'valType' option has been removed from ExternalFileField, if you have this in your schema you
can safely remove it. see SOLR-10929 for more details.
+* 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)
@@ -165,6 +170,9 @@ 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.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/solr/bin/solr
----------------------------------------------------------------------
diff --git a/solr/bin/solr b/solr/bin/solr
index cd50828..fff11ed 100755
--- a/solr/bin/solr
+++ b/solr/bin/solr
@@ -419,12 +419,11 @@ 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"
@@ -441,12 +440,11 @@ 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 " 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_collection -c mycoll -d /tmp/myconfig"
@@ -935,7 +933,7 @@ 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/e4a7fc59/solr/bin/solr.cmd
----------------------------------------------------------------------
diff --git a/solr/bin/solr.cmd b/solr/bin/solr.cmd
index 8772200..0c05baa 100644
--- a/solr/bin/solr.cmd
+++ b/solr/bin/solr.cmd
@@ -404,12 +404,11 @@ echo -c name Name of core to create
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 c:/tmp/myconfig
@@ -428,12 +427,11 @@ echo -c name Name of collection to create
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 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_collection -c mycoll -d c:/tmp/myconfig
@@ -1404,7 +1402,7 @@ IF "!CREATE_NAME!"=="" (
set "SCRIPT_ERROR=Name (-c) is a required parameter for %SCRIPT_CMD%"
goto invalid_cmd_line
)
-IF "!CREATE_CONFDIR!"=="" set CREATE_CONFDIR=data_driven_schema_configs
+IF "!CREATE_CONFDIR!"=="" set CREATE_CONFDIR=_default
IF "!CREATE_NUM_SHARDS!"=="" set CREATE_NUM_SHARDS=1
IF "!CREATE_REPFACT!"=="" set CREATE_REPFACT=1
IF "!CREATE_CONFNAME!"=="" set CREATE_CONFNAME=!CREATE_NAME!
@@ -1861,4 +1859,4 @@ REM Safe echo which does not mess with () in strings
set "eout=%1"
set eout=%eout:"=%
echo !eout!
-GOTO :eof
\ No newline at end of file
+GOTO :eof
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/solr/core/src/java/org/apache/solr/util/SolrCLI.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/util/SolrCLI.java b/solr/core/src/java/org/apache/solr/util/SolrCLI.java
index c207dcf..668dd4f 100644
--- a/solr/core/src/java/org/apache/solr/util/SolrCLI.java
+++ b/solr/core/src/java/org/apache/solr/util/SolrCLI.java
@@ -993,7 +993,7 @@ public class SolrCLI {
}
} // end ApiTool class
- private static final String DEFAULT_CONFIG_SET = "data_driven_schema_configs";
+ private static final String DEFAULT_CONFIG_SET = "_default";
private static final long MS_IN_MIN = 60 * 1000L;
private static final long MS_IN_HOUR = MS_IN_MIN * 60L;
@@ -2681,7 +2681,7 @@ public class SolrCLI {
File exDir = setupExampleDir(serverDir, exampleDir, exampleName);
String collectionName = "schemaless".equals(exampleName) ? "gettingstarted" : exampleName;
String configSet =
- "techproducts".equals(exampleName) ? "sample_techproducts_configs" : "data_driven_schema_configs";
+ "techproducts".equals(exampleName) ? "sample_techproducts_configs" : "_default";
boolean isCloudMode = cli.hasOption('c');
String zkHost = cli.getOptionValue('z');
@@ -3054,7 +3054,7 @@ public class SolrCLI {
// yay! numNodes SolrCloud nodes running
int numShards = 2;
int replicationFactor = 2;
- String cloudConfig = "data_driven_schema_configs";
+ String cloudConfig = "_default";
String collectionName = "gettingstarted";
File configsetsDir = new File(serverDir, "solr/configsets");
@@ -3089,7 +3089,7 @@ public class SolrCLI {
"How many replicas per shard would you like to create? [2] ", "a replication factor", 2, 1, 4);
echo("Please choose a configuration for the "+collectionName+" collection, available options are:");
- String validConfigs = "basic_configs, data_driven_schema_configs, or sample_techproducts_configs ["+cloudConfig+"] ";
+ String validConfigs = "_default or sample_techproducts_configs ["+cloudConfig+"] ";
cloudConfig = prompt(readInput, validConfigs, cloudConfig);
// validate the cloudConfig name
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/solr/core/src/test/org/apache/solr/cloud/SolrCloudExampleTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/SolrCloudExampleTest.java b/solr/core/src/test/org/apache/solr/cloud/SolrCloudExampleTest.java
index 5e98f05..2b79408 100644
--- a/solr/core/src/test/org/apache/solr/cloud/SolrCloudExampleTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/SolrCloudExampleTest.java
@@ -55,7 +55,8 @@ import static org.apache.solr.common.util.Utils.getObjectByPath;
/**
* Emulates bin/solr -e cloud -noprompt; bin/post -c gettingstarted example/exampledocs/*.xml;
* this test is useful for catching regressions in indexing the example docs in collections that
- * use data-driven schema and managed schema features provided by configsets/data_driven_schema_configs.
+ * use data driven functionality and managed schema features of the default configset
+ * (configsets/_default).
*/
public class SolrCloudExampleTest extends AbstractFullDistribZkTestBase {
@@ -73,8 +74,8 @@ public class SolrCloudExampleTest extends AbstractFullDistribZkTestBase {
log.info("testLoadDocsIntoGettingStartedCollection initialized OK ... running test logic");
String testCollectionName = "gettingstarted";
- File data_driven_schema_configs = new File(ExternalPaths.SCHEMALESS_CONFIGSET);
- assertTrue(data_driven_schema_configs.getAbsolutePath()+" not found!", data_driven_schema_configs.isDirectory());
+ File defaultConfigs = new File(ExternalPaths.DEFAULT_CONFIGSET);
+ assertTrue(defaultConfigs.getAbsolutePath()+" not found!", defaultConfigs.isDirectory());
Set<String> liveNodes = cloudClient.getZkStateReader().getClusterState().getLiveNodes();
if (liveNodes.isEmpty())
@@ -88,8 +89,8 @@ public class SolrCloudExampleTest extends AbstractFullDistribZkTestBase {
"-shards", "2",
"-replicationFactor", "2",
"-confname", testCollectionName,
- "-confdir", "data_driven_schema_configs",
- "-configsetsDir", data_driven_schema_configs.getParentFile().getParentFile().getAbsolutePath(),
+ "-confdir", "_default",
+ "-configsetsDir", defaultConfigs.getParentFile().getParentFile().getAbsolutePath(),
"-solrUrl", solrUrl
};
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/solr/core/src/test/org/apache/solr/util/TestSolrCLIRunExample.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/util/TestSolrCLIRunExample.java b/solr/core/src/test/org/apache/solr/util/TestSolrCLIRunExample.java
index 86554b5..0c2421f 100644
--- a/solr/core/src/test/org/apache/solr/util/TestSolrCLIRunExample.java
+++ b/solr/core/src/test/org/apache/solr/util/TestSolrCLIRunExample.java
@@ -418,7 +418,7 @@ public class TestSolrCLIRunExample extends SolrTestCaseJ4 {
// sthis test only support launching one SolrCloud node due to how MiniSolrCloudCluster works
// and the need for setting the host and port system properties ...
- String userInput = "1\n"+bindPort+"\n"+collectionName+"\n2\n2\ndata_driven_schema_configs\n";
+ String userInput = "1\n"+bindPort+"\n"+collectionName+"\n2\n2\n_default\n";
// simulate user input from stdin
InputStream userInputSim = new ByteArrayInputStream(userInput.getBytes(StandardCharsets.UTF_8));
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/solr/server/README.txt
----------------------------------------------------------------------
diff --git a/solr/server/README.txt b/solr/server/README.txt
index 744f479..228f4d4 100644
--- a/solr/server/README.txt
+++ b/solr/server/README.txt
@@ -62,12 +62,11 @@ server/solr/configsets
Directories containing different configuration options for running Solr.
- basic_configs : Bare minimum configuration settings needed to run Solr.
-
- data_driven_schema_configs : Field-guessing and managed schema mode; use this configuration if you want
- to start indexing data in Solr without having to design a schema upfront.
- You can use the REST API to manage your schema as you refine your index
- requirements.
+ _default : Bare minimum configurations with field-guessing and managed schema turned
+ on by default, so as to start indexing data in Solr without having to design
+ a schema upfront. You can use the REST API to manage your schema as you refine your index
+ requirements. You can turn off the field (for a collection, say mycollection) guessing by:
+ curl http://host:8983/solr/mycollection/config -d '{"set-user-property": {"update.autoCreateFields":"false"}}'
sample_techproducts_configs : Comprehensive example configuration that demonstrates many of the powerful
features of Solr, based on the use case of building a search solution for
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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..532221a
--- /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 CurrencyFieldType 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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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
+
[26/27] lucene-solr:feature/autoscaling: SOLR-10406: Remove
workaround for SOLR-10768
Posted by sh...@apache.org.
SOLR-10406: Remove workaround for SOLR-10768
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/5d442437
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/5d442437
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/5d442437
Branch: refs/heads/feature/autoscaling
Commit: 5d442437b54961930ce503596ad8c3e0e926e5c5
Parents: c66a8d9
Author: Shalin Shekhar Mangar <sh...@apache.org>
Authored: Tue Jun 27 10:09:30 2017 +0530
Committer: Shalin Shekhar Mangar <sh...@apache.org>
Committed: Tue Jun 27 10:09:44 2017 +0530
----------------------------------------------------------------------
.../solr/cloud/autoscaling/AutoScalingHandlerTest.java | 12 ------------
1 file changed, 12 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/5d442437/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 ecc7afd..197801a 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
@@ -26,7 +26,6 @@ import java.util.Map;
import org.apache.solr.client.solrj.SolrClient;
import org.apache.solr.client.solrj.SolrRequest;
import org.apache.solr.client.solrj.SolrResponse;
-import org.apache.solr.client.solrj.SolrServerException;
import org.apache.solr.client.solrj.impl.CloudSolrClient;
import org.apache.solr.client.solrj.impl.HttpSolrClient;
import org.apache.solr.client.solrj.request.CollectionAdminRequest;
@@ -82,20 +81,9 @@ public class AutoScalingHandlerTest extends SolrCloudTestCase {
try {
solrClient.request(req);
fail("Adding a policy with 'cores' attribute should not have succeeded.");
- } catch (SolrServerException e) {
- // todo one of these catch blocks should not be needed after SOLR-10768
- if (e.getRootCause() instanceof HttpSolrClient.RemoteSolrException) {
- HttpSolrClient.RemoteSolrException rootCause = (HttpSolrClient.RemoteSolrException) e.getRootCause();
- // expected
- assertTrue(rootCause.getMessage().contains("cores is only allowed in 'cluster-policy'"));
- } else {
- throw e;
- }
} catch (HttpSolrClient.RemoteSolrException e) {
// expected
assertTrue(e.getMessage().contains("cores is only allowed in 'cluster-policy'"));
- } catch (Exception e) {
- throw e;
}
setPolicyCommand = "{'set-policy': {" +
[05/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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 c2db621..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/managed-schema
+++ /dev/null
@@ -1,1052 +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-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="*_s_ns" type="string" indexed="true" stored="false" />
- <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_l_ns" type="long" indexed="true" stored="false"/>
- <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:
- amountLongSuffix: Required. Refers to a dynamic field for the raw amount sub-field.
- The dynamic field must have a field type that extends LongValueFieldType.
- Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
- codeStrSuffix: Required. Refers to a dynamic field for the currency code sub-field.
- The dynamic field must have a field type that extends StrField.
- Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
- defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
- 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.CurrencyFieldType" amountLongSuffix="_l_ns" codeStrSuffix="_s_ns"
- 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/e4a7fc59/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/e4a7fc59/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
-
[21/27] lucene-solr:feature/autoscaling: SOLR-10892: Phase 2: large
pages with lots of tables + lots of heading cleanups & TOC placement changes
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/93c96b06/solr/solr-ref-guide/src/highlighting.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/highlighting.adoc b/solr/solr-ref-guide/src/highlighting.adoc
index 117ccbc..b0d094d 100644
--- a/solr/solr-ref-guide/src/highlighting.adoc
+++ b/solr/solr-ref-guide/src/highlighting.adoc
@@ -27,32 +27,68 @@ Highlighting is extremely configurable, perhaps more than any other part of Solr
[[Highlighting-Usage]]
== Usage
+=== Common Highlighter Parameters
You only need to set the `hl` and often `hl.fl` parameters to get results. The following table documents these and some other supported parameters. Note that many highlighting parameters support per-field overrides, such as: `f._title_txt_.hl.snippets`
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="20,15,65",options="header"]
-|===
-|Parameter |Default |Description
-|hl |false |Use this parameter to enable or disable highlighting.
-|hl.method |original |The highlighting implementation to use. Acceptable values are: `unified`, `original`, `fastVector`. See the <<Highlighting-ChoosingaHighlighter,Choosing a Highlighter>> section below for more details on the differences between the available highlighters.
-|hl.fl |_(df=)_ |Specifies a list of fields to highlight. Accepts a comma- or space-delimited list of fields for which Solr should generate highlighted snippets. A wildcard of `\*` (asterisk) can be used to match field globs, such as `text_*` or even `\*` to highlight on all fields where highlighting is possible. When using `\*`, consider adding `hl.requireFieldMatch=true`.
-|hl.q |_(q=)_ |A query to use for highlighting. This parameter allows you to highlight different terms than those being used to retrieve documents.
-|hl.qparser |_(defType=)_ |The query parser to use for the `hl.q` query.
-|hl.requireFieldMatch |false a|
-By default, *false*, all query terms will be highlighted for each field to be highlighted (`hl.fl`) no matter what fields the parsed query refer to. If set to *true*, only query terms aligning with the field being highlighted will in turn be highlighted.
-
-Note: if the query references fields different from the field being highlighted and they have different text analysis, the query may not highlight query terms it should have and vice versa. The analysis used is that of the field being highlighted (`hl.fl`), not the query fields.
-
-|hl.usePhraseHighlighter |true |If set to *true*, Solr will highlight phrase queries (and other advanced position-sensitive queries) accurately – as phrases. If *false*, the parts of the phrase will be highlighted everywhere instead of only when it forms the given phrase.
-|hl.highlightMultiTerm |true |If set to *true*, Solr will highlight wildcard queries (and other `MultiTermQuery` subclasses). If *false*, they won't be highlighted at all.
-|hl.snippets |1 |Specifies maximum number of highlighted snippets to generate per field. It is possible for any number of snippets from zero to this value to be generated.
-|hl.fragsize |100 |Specifies the approximate size, in characters, of fragments to consider for highlighting. *0* indicates that no fragmenting should be considered and the whole field value should be used.
-|hl.tag.pre |<em> |(`hl.simple.pre` for the Original Highlighter) Specifies the “tag” to use before a highlighted term. This can be any string, but is most often an HTML or XML tag.
-|hl.tag.post |</em> |(`hl.simple.post` for the Original Highlighter) Specifies the “tag” to use after a highlighted term. This can be any string, but is most often an HTML or XML tag.
-|hl.encoder |_(blank)_ |If blank, the default, then the stored text will be returned without any escaping/encoding performed by the highlighter. If set to *html* then special HMTL/XML characters will be encoded (e.g. `&` becomes `\&`). The pre/post snippet characters are never encoded.
-|hl.maxAnalyzedChars |51200 |The character limit to look for highlights, after which no highlighting will be done. This is mostly only a performance concern for an _analysis_ based offset source since it's the slowest. See <<Schema Options and Performance Considerations>>.
-|===
+`hl`::
+Use this parameter to enable or disable highlighting. The default is `false`. If you want to use highlighting, you must set this to `true`.
+
+`hl.method`::
+The highlighting implementation to use. Acceptable values are: `unified`, `original`, `fastVector`. The default is `original`.
++
+See the <<Highlighting-ChoosingaHighlighter,Choosing a Highlighter>> section below for more details on the differences between the available highlighters.
+
+`hl.fl`::
+Specifies a list of fields to highlight. Accepts a comma- or space-delimited list of fields for which Solr should generate highlighted snippets.
++
+A wildcard of `\*` (asterisk) can be used to match field globs, such as `text_*` or even `\*` to highlight on all fields where highlighting is possible. When using `*`, consider adding `hl.requireFieldMatch=true`.
++
+When not defined, the defaults defined for the `df` query parameter will be used.
+
+`hl.q`::
+A query to use for highlighting. This parameter allows you to highlight different terms than those being used to retrieve documents.
++
+When not defined, the query defined with the `q` parameter will the used.
+
+`hl.qparser`::
+The query parser to use for the `hl.q` query.
++
+When not defined, the query parser defined with the `defType` query parameter will be used.
+
+`hl.requireFieldMatch`::
+By default, `false`, all query terms will be highlighted for each field to be highlighted (`hl.fl`) no matter what fields the parsed query refer to. If set to `true`, only query terms aligning with the field being highlighted will in turn be highlighted.
++
+If the query references fields different from the field being highlighted and they have different text analysis, the query may not highlight query terms it should have and vice versa. The analysis used is that of the field being highlighted (`hl.fl`), not the query fields.
+
+`hl.usePhraseHighlighter`::
+If set to `true`, the default, Solr will highlight phrase queries (and other advanced position-sensitive queries) accurately – as phrases. If `false`, the parts of the phrase will be highlighted everywhere instead of only when it forms the given phrase.
+
+`hl.highlightMultiTerm`::
+If set to `true`, the default, Solr will highlight wildcard queries (and other `MultiTermQuery` subclasses). If `false`, they won't be highlighted at all.
+
+`hl.snippets`::
+Specifies maximum number of highlighted snippets to generate per field. It is possible for any number of snippets from zero to this value to be generated. The default is `1`.
+
+`hl.fragsize`::
+Specifies the approximate size, in characters, of fragments to consider for highlighting. The default is `100`. Using `0` indicates that no fragmenting should be considered and the whole field value should be used.
+
+`hl.tag.pre`::
+(`hl.simple.pre` for the Original Highlighter) Specifies the “tag” to use before a highlighted term. This can be any string, but is most often an HTML or XML tag.
++
+The default is `<em>`.
+
+`hl.tag.post`:: </em> |
+(`hl.simple.post` for the Original Highlighter) Specifies the “tag” to use after a highlighted term. This can be any string, but is most often an HTML or XML tag.
++
+The default is `</em>`.
+
+`hl.encoder`::
+If blank, the default, then the stored text will be returned without any escaping/encoding performed by the highlighter. If set to `html` then special HMTL/XML characters will be encoded (e.g. `&` becomes `\&`). The pre/post snippet characters are never encoded.
+
+`hl.maxAnalyzedChars`::
+The character limit to look for highlights, after which no highlighting will be done. This is mostly only a performance concern for an _analysis_ based offset source since it's the slowest. See <<Schema Options and Performance Considerations>>.
++
+The default is `51200` characters.
There are more parameters supported as well depending on the highlighter (via `hl.method`) chosen.
@@ -73,30 +109,26 @@ we get a response such as this (truncated slightly for space):
[source,json]
----
{
- "responseHeader": {
- "..."
- }
- },
- "response": {
- "numFound": 1,
- "start": 0,
- "docs": [{
- "id": "MA147LL/A",
- "name": "Apple 60 GB iPod with Video Playback Black",
- "manu": "Apple Computer Inc.",
- "cat": [
- "electronics",
- "music"
- ]
- }]
- },
- "highlighting": {
- "MA147LL/A": {
- "manu": [
- "<em>Apple</em> Computer Inc."
- ]
- }
+ "response": {
+ "numFound": 1,
+ "start": 0,
+ "docs": [{
+ "id": "MA147LL/A",
+ "name": "Apple 60 GB iPod with Video Playback Black",
+ "manu": "Apple Computer Inc.",
+ "cat": [
+ "electronics",
+ "music"
+ ]
+ }]
+ },
+ "highlighting": {
+ "MA147LL/A": {
+ "manu": [
+ "<em>Apple</em> Computer Inc."
+ ]
}
+ }
}
----
@@ -171,49 +203,114 @@ This adds substantial weight to the index – similar in size to the compressed
The Unified Highlighter supports these following additional parameters to the ones listed earlier:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="20,15,65",options="header"]
-|===
-|Parameter |Default |Description
-|hl.offsetSource |_(blank)_ |By default, the Unified Highlighter will usually pick the right offset source (see above). However it may be ambiguous such as during a migration from one offset source to another that hasn't completed. The offset source can be explicitly configured to one of: *ANALYSIS,* *POSTINGS*, *POSTINGS_WITH_TERM_VECTORS*, *TERM_VECTORS*
-|hl.tag.ellipsis |_(blank)_ |By default, each snippet is returned as a separate value (as is done with the other highlighters). Set this parameter to instead return one string with this text as the delimiter. _Note: this is likely to be removed in the future._
-|hl.defaultSummary |false |If *true*, use the leading portion of the text as a snippet if a proper highlighted snippet can't otherwise be generated.
-|hl.score.k1 |1.2 |Specifies BM25 term frequency normalization parameter 'k1'. For example, it can be set to "0" to rank passages solely based on the number of query terms that match.
-|hl.score.b |0.75 |Specifies BM25 length normalization parameter 'b'. For example, it can be set to "0" to ignore the length of passages entirely when ranking.
-|hl.score.pivot |87 |Specifies BM25 average passage length in characters.
-|hl.bs.language |_(blank)_ |Specifies the breakiterator language for dividing the document into passages.
-|hl.bs.country |_(blank)_ |Specifies the breakiterator country for dividing the document into passages.
-|hl.bs.variant |_(blank)_ |Specifies the breakiterator variant for dividing the document into passages.
-|hl.bs.type |SENTENCE |Specifies the breakiterator type for dividing the document into passages. Can be *SEPARATOR*, *SENTENCE*, *WORD*, *CHARACTER*, *LINE*, or *WHOLE*. SEPARATOR is special value that splits text on a user-provided character in `hl.bs.separator`.
-|hl.bs.separator |_(blank)_ |Indicates which character to break the text on. Requires `hl.bs.type=SEPARATOR`. This is useful when the text has already been manipulated in advance to have a special delineation character at desired highlight passage boundaries. This character will still appear in the text as the last character of a passage.
-|===
+`hl.offsetSource`:: _(blank)_ |
+By default, the Unified Highlighter will usually pick the right offset source (see above). However it may be ambiguous such as during a migration from one offset source to another that hasn't completed.
++
+The offset source can be explicitly configured to one of: `ANALYSIS`, `POSTINGS`, `POSTINGS_WITH_TERM_VECTORS`, or `TERM_VECTORS`.
+
+`hl.tag.ellipsis`::
+By default, each snippet is returned as a separate value (as is done with the other highlighters). Set this parameter to instead return one string with this text as the delimiter. _Note: this is likely to be removed in the future._
+
+`hl.defaultSummary`::
+If `true`, use the leading portion of the text as a snippet if a proper highlighted snippet can't otherwise be generated. The default is `false`.
+
+`hl.score.k1`::
+Specifies BM25 term frequency normalization parameter 'k1'. For example, it can be set to `0` to rank passages solely based on the number of query terms that match. The default is `1.2`.
+
+`hl.score.b`::
+Specifies BM25 length normalization parameter 'b'. For example, it can be set to "0" to ignore the length of passages entirely when ranking. The default is `0.75`.
+
+`hl.score.pivot`::
+Specifies BM25 average passage length in characters. The default is `87`.
+
+`hl.bs.language`::
+Specifies the breakiterator language for dividing the document into passages.
+
+`hl.bs.country`::
+Specifies the breakiterator country for dividing the document into passages.
+
+`hl.bs.variant`::
+Specifies the breakiterator variant for dividing the document into passages.
+
+`hl.bs.type`::
+Specifies the breakiterator type for dividing the document into passages. Can be `SEPARATOR`, `SENTENCE`, `WORD`*, `CHARACTER`, `LINE`, or `WHOLE`. `SEPARATOR` is special value that splits text on a user-provided character in `hl.bs.separator`.
++
+The default is `SENTENCE`.
+
+`hl.bs.separator`::
+Indicates which character to break the text on. Use only if you have defined `hl.bs.type=SEPARATOR`.
++
+This is useful when the text has already been manipulated in advance to have a special delineation character at desired highlight passage boundaries. This character will still appear in the text as the last character of a passage.
+
[[Highlighting-TheOriginalHighlighter]]
== The Original Highlighter
The Original Highlighter supports these following additional parameters to the ones listed earlier:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="25,15,60",options="header"]
-|===
-|Parameter |Default |Description
-|hl.mergeContiguous |false |Instructs Solr to collapse contiguous fragments into a single fragment. A value of *true* indicates contiguous fragments will be collapsed into single fragment. The default value, *false*, is also the backward-compatible setting.
-|hl.maxMultiValuedToExamine |`Integer.MAX_VALUE` |Specifies the maximum number of entries in a multi-valued field to examine before stopping. This can potentially return zero results if the limit is reached before any matches are found. If used with the `maxMultiValuedToMatch`, whichever limit is reached first will determine when to stop looking.
-|hl.maxMultiValuedToMatch |`Integer.MAX_VALUE` |Specifies the maximum number of matches in a multi-valued field that are found before stopping. If `hl.maxMultiValuedToExamine` is also defined, whichever limit is reached first will determine when to stop looking.
-|hl.alternateField |_(blank)_ |Specifies a field to be used as a backup default summary if Solr cannot generate a snippet (i.e., because no terms match).
-|hl.maxAlternateFieldLength |_(unlimited)_ |Specifies the maximum number of characters of the field to return. Any value less than or equal to 0 means the field's length is unlimited. This parameter is only used in conjunction with the `hl.alternateField` parameter.
-|hl.highlightAlternate |true |If set to *true*, and `hl.alternateFieldName` is active, Solr will show the entire alternate field, with highlighting of occurrences. If `hl.maxAlternateFieldLength=N` is used, Solr returns max `N` characters surrounding the best matching fragment. If set to *false*, or if there is no match in the alternate field either, the alternate field will be shown without highlighting.
-|hl.formatter |simple |Selects a formatter for the highlighted output. Currently the only legal value is *simple*, which surrounds a highlighted term with a customizable pre- and post-text snippet.
-|hl.simple.prehl.simple.post |<em> and </em> |Specifies the text that should appear before (`hl.simple.pre`) and after (`hl.simple.post`) a highlighted term, when using the simple formatter.
-|hl.fragmenter |gap |Specifies a text snippet generator for highlighted text. The standard fragmenter is *gap*, which creates fixed-sized fragments with gaps for multi-valued fields. Another option is *regex*, which tries to create fragments that resemble a specified regular expression.
-|hl.regex.slop |0.6 |When using the regex fragmenter (`hl.fragmenter=regex`), this parameter defines the factor by which the fragmenter can stray from the ideal fragment size (given by `hl.fragsize`) to accommodate a regular expression. For instance, a slop of 0.2 with `hl.fragsize=100` should yield fragments between 80 and 120 characters in length. It is usually good to provide a slightly smaller `hl.fragsize` value when using the regex fragmenter.
-|hl.regex.pattern |_(blank)_ |Specifies the regular expression for fragmenting. This could be used to extract sentences.
-|hl.regex.maxAnalyzedChars |10000 |Instructs Solr to analyze only this many characters from a field when using the regex fragmenter (after which, the fragmenter produces fixed-sized fragments). Applying a complicated regex to a huge field is computationally expensive.
-|hl.preserveMulti |false |If *true*, multi-valued fields will return all values in the order they were saved in the index. If *false*, only values that match the highlight request will be returned.
-|hl.payloads |_(automatic)_ |When `hl.usePhraseHighlighter` is true and the indexed field has payloads but not term vectors (generally quite rare), the index's payloads will be read into the highlighter's memory index along with the postings. If this may happen and you know you don't need them for highlighting (i.e. your queries don't filter by payload) then you can save a little memory by setting this to false.
-|===
+`hl.mergeContiguous`::
+Instructs Solr to collapse contiguous fragments into a single fragment. A value of `true` indicates contiguous fragments will be collapsed into single fragment. The default value, `false`, is also the backward-compatible setting.
+
+`hl.maxMultiValuedToExamine`::
+Specifies the maximum number of entries in a multi-valued field to examine before stopping. This can potentially return zero results if the limit is reached before any matches are found.
++
+If used with the `maxMultiValuedToMatch`, whichever limit is reached first will determine when to stop looking.
++
+The default is `Integer.MAX_VALUE`.
+
+`hl.maxMultiValuedToMatch`::
+Specifies the maximum number of matches in a multi-valued field that are found before stopping.
++
+If `hl.maxMultiValuedToExamine` is also defined, whichever limit is reached first will determine when to stop looking.
++
+The default is `Integer.MAX_VALUE`.
+
+`hl.alternateField`::
+Specifies a field to be used as a backup default summary if Solr cannot generate a snippet (i.e., because no terms match).
+
+`hl.maxAlternateFieldLength`::
+Specifies the maximum number of characters of the field to return. Any value less than or equal to `0` means the field's length is unlimited (the default behavior).
++
+This parameter is only used in conjunction with the `hl.alternateField` parameter.
+
+`hl.highlightAlternate`::
+If set to `true`, the default, and `hl.alternateFieldName` is active, Solr will show the entire alternate field, with highlighting of occurrences. If `hl.maxAlternateFieldLength=N` is used, Solr returns max `N` characters surrounding the best matching fragment.
++
+If set to `false`, or if there is no match in the alternate field either, the alternate field will be shown without highlighting.
+
+`hl.formatter`::
+Selects a formatter for the highlighted output. Currently the only legal value is `simple`, which surrounds a highlighted term with a customizable pre- and post-text snippet.
+
+`hl.simple.prehl.simple.post`::
+Specifies the text that should appear before (`hl.simple.pre`) and after (`hl.simple.post`) a highlighted term, when using the simple formatter. The default is `<em>` and `</em>`.
+
+`hl.fragmenter`::
+Specifies a text snippet generator for highlighted text. The standard (default) fragmenter is `gap`, which creates fixed-sized fragments with gaps for multi-valued fields.
++
+Another option is `regex`, which tries to create fragments that resemble a specified regular expression.
+
+`hl.regex.slop`:: 0.6 |
+When using the regex fragmenter (`hl.fragmenter=regex`), this parameter defines the factor by which the fragmenter can stray from the ideal fragment size (given by `hl.fragsize`) to accommodate a regular expression.
++
+For instance, a slop of `0.2` with `hl.fragsize=100` should yield fragments between 80 and 120 characters in length. It is usually good to provide a slightly smaller `hl.fragsize` value when using the regex fragmenter.
++
+The default is `0.6`.
+
+`hl.regex.pattern`::
+Specifies the regular expression for fragmenting. This could be used to extract sentences.
+
+`hl.regex.maxAnalyzedChars`:: 10000 |
+Instructs Solr to analyze only this many characters from a field when using the regex fragmenter (after which, the fragmenter produces fixed-sized fragments). The default is `10000`.
++
+Note, applying a complicated regex to a huge field is computationally expensive.
+
+`hl.preserveMulti`::
+If `true`, multi-valued fields will return all values in the order they were saved in the index. If `false`, the default, only values that match the highlight request will be returned.
+
+`hl.payloads`::
+When `hl.usePhraseHighlighter` is `true` and the indexed field has payloads but not term vectors (generally quite rare), the index's payloads will be read into the highlighter's memory index along with the postings.
++
+If this may happen and you know you don't need them for highlighting (i.e. your queries don't filter by payload) then you can save a little memory by setting this to false.
The Original Highlighter has a plugin architecture that enables new functionality to be registered in `solrconfig.xml`. The "```techproducts```" configset shows most of these settings explicitly. You can use it as a guide to provide your own components to include a `SolrFormatter`, `SolrEncoder`, and `SolrFragmenter.`
@@ -230,18 +327,28 @@ In addition to the initial listed parameters, the following parameters documente
And here are additional parameters supported by the FVH:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="20,15,65",options="header"]
-|===
-|Parameter |Default |Description
-|hl.fragListBuilder |weighted |The snippet fragmenting algorithm. The *weighted* fragListBuilder uses IDF-weights to order fragments. Other options are *single*, which returns the entire field contents as one snippet, or *simple*. You can select a fragListBuilder with this parameter, or modify an existing implementation in `solrconfig.xml` to be the default by adding "default=true".
-|hl.fragmentsBuilder |default |The fragments builder is responsible for formatting the fragments, which uses <em> and </em> markup (if `hl.tag.pre` and `hl.tag.post` are not defined). Another pre-configured choice is *colored*, which is an example of how to use the fragments builder to insert HTML into the snippets for colored highlights if you choose. You can also implement your own if you'd like. You can select a fragments builder with this parameter, or modify an existing implementation in `solrconfig.xml` to be the default by adding "default=true".
-|hl.boundaryScanner | |See <<Using Boundary Scanners with the FastVector Highlighter>> below.
-|hl.bs.* | |See <<Using Boundary Scanners with the FastVector Highlighter>> below.
-|hl.phraseLimit |5000 |The maximum number of phrases to analyze when searching for the highest-scoring phrase.
-|hl.multiValuedSeparatorChar |" " _(space)_ |Text to use to separate one value from the next for a multi-valued field.
-|===
+`hl.fragListBuilder`:: weighted |
+The snippet fragmenting algorithm. The `weighted` fragListBuilder uses IDF-weights to order fragments. This fragListBuilder is the default.
++
+Other options are `single`, which returns the entire field contents as one snippet, or `simple`. You can select a fragListBuilder with this parameter, or modify an existing implementation in `solrconfig.xml` to be the default by adding "default=true".
+
+`hl.fragmentsBuilder`::
+The fragments builder is responsible for formatting the fragments, which uses`<em>` and `</em>` markup by default (if `hl.tag.pre` and `hl.tag.post` are not defined).
++
+Another pre-configured choice is `colored`, which is an example of how to use the fragments builder to insert HTML into the snippets for colored highlights if you choose. You can also implement your own if you'd like. You can select a fragments builder with this parameter, or modify an existing implementation in `solrconfig.xml` to be the default by adding "default=true".
+
+`hl.boundaryScanner`::
+See <<Using Boundary Scanners with the FastVector Highlighter>> below.
+
+`hl.bs.*`::
+See <<Using Boundary Scanners with the FastVector Highlighter>> below.
+
+`hl.phraseLimit`::
+The maximum number of phrases to analyze when searching for the highest-scoring phrase. The default is `5000`.
+
+`hl.multiValuedSeparatorChar`::
+Text to use to separate one value from the next for a multi-valued field. The default is " " (a space).
+
[[Highlighting-UsingBoundaryScannerswiththeFastVectorHighlighter]]
=== Using Boundary Scanners with the FastVector Highlighter
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/93c96b06/solr/solr-ref-guide/src/other-parsers.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/other-parsers.adoc b/solr/solr-ref-guide/src/other-parsers.adoc
index 7032945..271c33b 100644
--- a/solr/solr-ref-guide/src/other-parsers.adoc
+++ b/solr/solr-ref-guide/src/other-parsers.adoc
@@ -178,16 +178,14 @@ The `ComplexPhraseQParser` provides support for wildcards, ORs, etc., inside phr
Under the covers, this query parser makes use of the Span group of queries, e.g., spanNear, spanOr, etc., and is subject to the same limitations as that family or parsers.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+*Parameters*
-[cols="30,70",options="header"]
-|===
-|Parameter |Description
-|`inOrder` |Set to true to force phrase queries to match terms in the order specified. Default: *true*
-|`df` |The default search field.
-|===
+`inOrder`::
+Set to true to force phrase queries to match terms in the order specified. The default is `true`.
+`df`::
+The default search field.
-*Examples:*
+*Examples*
[source,text]
----
@@ -284,20 +282,21 @@ Example:
The `FunctionRangeQParser` extends the `QParserPlugin` and creates a range query over a function. This is also referred to as `frange`, as seen in the examples below.
-Other parameters:
+*Parameters*
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`l`::
+The lower bound. This parameter is optional.
-[cols="30,70",options="header"]
-|===
-|Parameter |Description
-|l |The lower bound, optional
-|u |The upper bound, optional
-|incl |Include the lower bound: true/false, optional, default=true
-|incu |Include the upper bound: true/false, optional, default=true
-|===
+`u`::
+The upper bound. This parameter is optional.
-Examples:
+`incl`::
+Include the lower bound. This parameter is optional. The default is `true`.
+
+`incu`::
+Include the upper bound. This parameter is optional. The default is `true`.
+
+*Examples*
[source,text]
----
@@ -318,24 +317,30 @@ For more information about range queries over functions, see Yonik Seeley's intr
The `graph` query parser does a breadth first, cyclic aware, graph traversal of all documents that are "reachable" from a starting set of root documents identified by a wrapped query.
-The graph is built according to linkages between documents based on the terms found in "```from```" and "```to```" fields that you specify as part of the query
+The graph is built according to linkages between documents based on the terms found in `from` and `to` fields that you specify as part of the query.
[[OtherParsers-Parameters]]
=== Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`to`::
+The field name of matching documents to inspect to identify outgoing edges for graph traversal. Defaults to `edge_ids`.
-[cols="30,70",options="header"]
-|===
-|Parameter |Description
-|to |The field name of matching documents to inspect to identify outgoing edges for graph traversal. Defaults to `edge_ids` .
-|from |The field name to of candidate documents to inspect to identify incoming graph edges. Defaults to `node_id` .
-|traversalFilter |An optional query that can be supplied to limit the scope of documents that are traversed.
-|maxDepth |Integer specifying how deep the breadth first search of the graph should go beginning with the initial query. Defaults to -1 (unlimited)
-|returnRoot |Boolean to indicate if the documents that matched the original query (to define the starting points for graph) should be included in the final results. Defaults to true
-|returnOnlyLeaf |Boolean that indicates if the results of the query should be filtered so that only documents with no outgoing edges are returned. Defaults to false
-|useAutn |Boolean that indicates if an Automatons should be compiled for each iteration of the breadth first search, which may be faster for some graphs. Defaults to false.
-|===
+`from`::
+The field name to of candidate documents to inspect to identify incoming graph edges. Defaults to `node_id`.
+
+`traversalFilter`::
+An optional query that can be supplied to limit the scope of documents that are traversed.
+
+`maxDepth`::
+Integer specifying how deep the breadth first search of the graph should go beginning with the initial query. Defaults to `-1` (unlimited).
+
+`returnRoot`::
+Boolean to indicate if the documents that matched the original query (to define the starting points for graph) should be included in the final results. Defaults to `true`.
+
+`returnOnlyLeaf`::
+Boolean that indicates if the results of the query should be filtered so that only documents with no outgoing edges are returned. Defaults to `false`.
+
+`useAutn`:: Boolean that indicates if an Automatons should be compiled for each iteration of the breadth first search, which may be faster for some graphs. Defaults to `false`.
[[OtherParsers-Limitations.1]]
=== Limitations
@@ -590,23 +595,34 @@ Example:
This query parser takes the following parameters:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`qf`::
+Specifies the fields to use for similarity.
-[cols="30,70",options="header"]
-|===
-|Parameter |Description
-|qf |Specifies the fields to use for similarity.
-|mintf |Specifies the Minimum Term Frequency, the frequency below which terms will be ignored in the source document.
-|mindf |Specifies the Minimum Document Frequency, the frequency at which words will be ignored when they do not occur in at least this many documents.
-|maxdf |Specifies the Maximum Document Frequency, the frequency at which words will be ignored when they occur in more than this many documents.
-|minwl |Sets the minimum word length below which words will be ignored.
-|maxwl |Sets the maximum word length above which words will be ignored.
-|maxqt |Sets the maximum number of query terms that will be included in any generated query.
-|maxntp |Sets the maximum number of tokens to parse in each example document field that is not stored with TermVector support.
-|boost |Specifies if the query will be boosted by the interesting term relevance. It can be either "true" or "false".
-|===
+`mintf`::
+Specifies the Minimum Term Frequency, the frequency below which terms will be ignored in the source document.
-Examples:
+`mindf`::
+Specifies the Minimum Document Frequency, the frequency at which words will be ignored when they do not occur in at least this many documents.
+
+`maxdf`::
+Specifies the Maximum Document Frequency, the frequency at which words will be ignored when they occur in more than this many documents.
+
+`minwl`::
+Sets the minimum word length below which words will be ignored.
+
+`maxwl`::
+Sets the maximum word length above which words will be ignored.
+
+`maxqt`::
+Sets the maximum number of query terms that will be included in any generated query.
+
+`maxntp`::
+Sets the maximum number of tokens to parse in each example document field that is not stored with TermVector support.
+
+`boost`::
+Specifies if the query will be boosted by the interesting term relevance. It can be either "true" or "false".
+
+*Examples*
Find documents like the document with id=1 and using the `name` field for similarity.
@@ -663,17 +679,16 @@ The main query, for both of these parsers, is parsed straightforwardly from the
This parser accepts the following parameters:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`f`::
+The field to use (required).
-[cols="30,70",options="header"]
-|===
-|Parameter |Description
-|`f` |Field to use (required)
-|`func` |Payload function: min, max, average (required)
-|`includeSpanScore` |If true, multiples computed payload factor by the score of the original query. If false, the computed payload factor is the score. (default: false)
-|===
+`func`::
+Payload function: min, max, average (required).
-Example:
+`includeSpanScore`::
+If `true`, multiples computed payload factor by the score of the original query. If `false`, the default, the computed payload factor is the score.
+
+*Example*
[source,text]
----
@@ -687,20 +702,17 @@ Example:
This parser accepts the following parameters:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`f`::
+The field to use (required).
-[cols="30,70",options="header"]
-|===
-|Parameter |Description
-|`f` |Field to use (required)
-|payloads a|
+`payloads`::
A space-separated list of payloads that must match the query terms (required)
-
++
Each specified payload will be encoded using the encoder determined from the field type and encoded accordingly for matching.
-
++
`DelimitedPayloadTokenFilter` 'identity' encoded payloads also work here, as well as float and integer encoded ones.
-|===
+*Example*
[source,text]
----
@@ -761,7 +773,7 @@ q.operators::
Comma-separated list of names of parsing operators to enable. By default, all operations are enabled, and this parameter can be used to effectively disable specific operators as needed, by excluding them from the list. Passing an empty string with this parameter disables all operators.
+
// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
++
[cols="15,20,50,15",options="header"]
|===
|Name |Operator |Description |Example query
@@ -791,7 +803,8 @@ At the end of terms, specifies a fuzzy query.
q.op::
Defines the default operator to use if none is defined by the user. Allowed values are `AND` and `OR`. `OR` is used if none is specified.
-qf:: A list of query fields and boosts to use when building the query.
+qf::
+A list of query fields and boosts to use when building the query.
df::
Defines the default field if none is defined in the Schema, or overrides the default field if it is already defined.
@@ -901,23 +914,23 @@ If no analysis or transformation is desired for any type of field, see the <<Oth
[[OtherParsers-TermsQueryParser]]
== Terms Query Parser
-`TermsQParser`, functions similarly to the <<OtherParsers-TermQueryParser,Term Query Parser>> but takes in multiple values separated by commas and returns documents matching any of the specified values.
+`TermsQParser` functions similarly to the <<OtherParsers-TermQueryParser,Term Query Parser>> but takes in multiple values separated by commas and returns documents matching any of the specified values.
-This can be useful for generating filter queries from the external human readable terms returned by the faceting or terms components, and may be more efficient in some cases than using the <<the-standard-query-parser.adoc#the-standard-query-parser,Standard Query Parser>> to generate an boolean query since the default implementation "```method```" avoids scoring.
+This can be useful for generating filter queries from the external human readable terms returned by the faceting or terms components, and may be more efficient in some cases than using the <<the-standard-query-parser.adoc#the-standard-query-parser,Standard Query Parser>> to generate an boolean query since the default implementation `method` avoids scoring.
This query parser takes the following parameters:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`f`::
+The field on which to search. This parameter is required.
-[cols="30,70",options="header"]
-|===
-|Parameter |Description
-|f |The field on which to search. Required.
-|separator |Separator to use when parsing the input. If set to " " (a single blank space), will trim additional white space from the input terms. Defaults to "`,`".
-|method |The internal query-building implementation: `termsFilter`, `booleanQuery`, `automaton`, or `docValuesTermsFilter`. Defaults to "```termsFilter```".
-|===
+`separator`::
+Separator to use when parsing the input. If set to " " (a single blank space), will trim additional white space from the input terms. Defaults to a comma (`,`).
-Examples:
+`method`::
+The internal query-building implementation: `termsFilter`, `booleanQuery`, `automaton`, or `docValuesTermsFilter`. Defaults to `termsFilter`.
+
+
+*Examples*
[source,text]
----
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/93c96b06/solr/solr-ref-guide/src/query-re-ranking.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/query-re-ranking.adoc b/solr/solr-ref-guide/src/query-re-ranking.adoc
index 0bdc8bb..f05af72 100644
--- a/solr/solr-ref-guide/src/query-re-ranking.adoc
+++ b/solr/solr-ref-guide/src/query-re-ranking.adoc
@@ -43,15 +43,14 @@ Three rank queries are currently included in the Solr distribution. You can also
The `rerank` parser wraps a query specified by an local parameter, along with additional parameters indicating how many documents should be re-ranked, and how the final scores should be computed:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`reRankQuery`::
+The query string for your complex ranking query - in most cases <<local-parameters-in-queries.adoc#local-parameters-in-queries,a variable>> will be used to refer to another request parameter. This parameter is required.
-[cols="20,15,65",options="header"]
-|===
-|Parameter |Default |Description
-|`reRankQuery` |(Mandatory) |The query string for your complex ranking query - in most cases <<local-parameters-in-queries.adoc#local-parameters-in-queries,a variable>> will be used to refer to another request parameter.
-|`reRankDocs` |200 |The number of top N documents from the original query that should be re-ranked. This number will be treated as a minimum, and may be increased internally automatically in order to rank enough documents to satisfy the query (ie: start+rows)
-|`reRankWeight` |2.0 |A multiplicative factor that will be applied to the score from the reRankQuery for each of the top matching documents, before that score is added to the original score
-|===
+`reRankDocs`::
+The number of top N documents from the original query that should be re-ranked. This number will be treated as a minimum, and may be increased internally automatically in order to rank enough documents to satisfy the query (i.e., start+rows). The default is `200`.
+
+`reRankWeight`::
+A multiplicative factor that will be applied to the score from the reRankQuery for each of the top matching documents, before that score is added to the original score. The default is `2.0`.
In the example below, the top 1000 documents matching the query "greetings" will be re-ranked using the query "(hi hello hey hiya)". The resulting scores for each of those 1000 documents will be 3 times their score from the "(hi hello hey hiya)", plus the score from the original "greetings" query:
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/93c96b06/solr/solr-ref-guide/src/schema-api.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/schema-api.adoc b/solr/solr-ref-guide/src/schema-api.adoc
index e73da89..893936f 100644
--- a/solr/solr-ref-guide/src/schema-api.adoc
+++ b/solr/solr-ref-guide/src/schema-api.adoc
@@ -1,6 +1,7 @@
= Schema API
:page-shortname: schema-api
:page-permalink: schema-api.html
+:page-tocclass: right
// 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
@@ -51,20 +52,18 @@ The base address for the API is `\http://<host>:<port>/solr/<collection_name>`.
bin/solr -e cloud -noprompt
----
-[[SchemaAPI-APIEntryPoints]]
== API Entry Points
-* `/schema`: <<SchemaAPI-RetrievetheEntireSchema,retrieve>> the schema, or <<SchemaAPI-ModifytheSchema,modify>> the schema to add, remove, or replace fields, dynamic fields, copy fields, or field types
-* `/schema/fields`: <<SchemaAPI-ListFields,retrieve information>> about all defined fields or a specific named field
-* `/schema/dynamicfields`: <<SchemaAPI-ListDynamicFields,retrieve information>> about all dynamic field rules or a specific named dynamic rule
-* `/schema/fieldtypes`: <<SchemaAPI-ListFieldTypes,retrieve information>> about all field types or a specific field type
-* `/schema/copyfields`: <<SchemaAPI-ListCopyFields,retrieve information>> about copy fields
-* `/schema/name`: <<SchemaAPI-ShowSchemaName,retrieve>> the schema name
-* `/schema/version`: <<SchemaAPI-ShowtheSchemaVersion,retrieve>> the schema version
-* `/schema/uniquekey`: <<SchemaAPI-ListUniqueKey,retrieve>> the defined uniqueKey
-* `/schema/similarity`: <<SchemaAPI-ShowGlobalSimilarity,retrieve>> the global similarity definition
-
-[[SchemaAPI-ModifytheSchema]]
+* `/schema`: <<Retrieve the Entire Schema,retrieve>> the schema, or <<Modify the Schema,modify>> the schema to add, remove, or replace fields, dynamic fields, copy fields, or field types
+* `/schema/fields`: <<List Fields,retrieve information>> about all defined fields or a specific named field
+* `/schema/dynamicfields`: <<List Dynamic Fields,retrieve information>> about all dynamic field rules or a specific named dynamic rule
+* `/schema/fieldtypes`: <<List Field Types,retrieve information>> about all field types or a specific field type
+* `/schema/copyfields`: <<List Copy Fields,retrieve information>> about copy fields
+* `/schema/name`: <<Show Schema Name,retrieve>> the schema name
+* `/schema/version`: <<Show the Schema Version,retrieve>> the schema version
+* `/schema/uniquekey`: <<List UniqueKey,retrieve>> the defined uniqueKey
+* `/schema/similarity`: <<Show Global Similarity,retrieve>> the global similarity definition
+
== Modify the Schema
`POST /_collection_/schema`
@@ -89,7 +88,6 @@ In each case, the response will include the status and the time to process the r
When modifying the schema with the API, a core reload will automatically occur in order for the changes to be available immediately for documents indexed thereafter. Previously indexed documents will *not* be automatically handled - they *must* be re-indexed if they used schema elements that you changed.
-[[SchemaAPI-AddaNewField]]
=== Add a New Field
The `add-field` command adds a new field definition to your schema. If a field with the same name exists an error is thrown.
@@ -108,7 +106,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-DeleteaField]]
=== Delete a Field
The `delete-field` command removes a field definition from your schema. If the field does not exist in the schema, or if the field is the source or destination of a copy field rule, an error is thrown.
@@ -122,7 +119,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-ReplaceaField]]
=== Replace a Field
The `replace-field` command replaces a field's definition. Note that you must supply the full definition for a field - this command will *not* partially modify a field's definition. If the field does not exist in the schema an error is thrown.
@@ -141,7 +137,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-AddaDynamicFieldRule]]
=== Add a Dynamic Field Rule
The `add-dynamic-field` command adds a new dynamic field rule to your schema.
@@ -160,7 +155,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-DeleteaDynamicFieldRule]]
=== Delete a Dynamic Field Rule
The `delete-dynamic-field` command deletes a dynamic field rule from your schema. If the dynamic field rule does not exist in the schema, or if the schema contains a copy field rule with a target or destination that matches only this dynamic field rule, an error is thrown.
@@ -174,7 +168,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-ReplaceaDynamicFieldRule]]
=== Replace a Dynamic Field Rule
The `replace-dynamic-field` command replaces a dynamic field rule in your schema. Note that you must supply the full definition for a dynamic field rule - this command will *not* partially modify a dynamic field rule's definition. If the dynamic field rule does not exist in the schema an error is thrown.
@@ -193,7 +186,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-AddaNewFieldType]]
=== Add a New Field Type
The `add-field-type` command adds a new field type to your schema.
@@ -240,7 +232,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-DeleteaFieldType]]
=== Delete a Field Type
The `delete-field-type` command removes a field type from your schema. If the field type does not exist in the schema, or if any field or dynamic field rule in the schema uses the field type, an error is thrown.
@@ -254,7 +245,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-ReplaceaFieldType]]
=== Replace a Field Type
The `replace-field-type` command replaces a field type in your schema. Note that you must supply the full definition for a field type - this command will *not* partially modify a field type's definition. If the field type does not exist in the schema an error is thrown.
@@ -276,22 +266,21 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-AddaNewCopyFieldRule]]
=== Add a New Copy Field Rule
The `add-copy-field` command adds a new copy field rule to your schema.
The attributes supported by the command are the same as when creating copy field rules by manually editing the `schema.xml`, as below:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`source`::
+The source field. This parameter is required.
+
+`dest`::
+A field or an array of fields to which the source field will be copied. This parameter is required.
+
+`maxChars`::
+The upper limit for the number of characters to be copied. The section <<copying-fields.adoc#copying-fields,Copying Fields>> has more details.
-[cols="20,20,60",options="header"]
-|===
-|Name |Required |Description
-|source |Yes |The source field.
-|dest |Yes |A field or an array of fields to which the source field will be copied.
-|maxChars |No |The upper limit for the number of characters to be copied. The section <<copying-fields.adoc#copying-fields,Copying Fields>> has more details.
-|===
For example, to define a rule to copy the field "shelf" to the "location" and "catchall" fields, you would POST the following request:
@@ -304,7 +293,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-DeleteaCopyFieldRule]]
=== Delete a Copy Field Rule
The `delete-copy-field` command deletes a copy field rule from your schema. If the copy field rule does not exist in the schema an error is thrown.
@@ -320,7 +308,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-MultipleCommandsinaSinglePOST]]
=== Multiple Commands in a Single POST
It is possible to perform one or more add requests in a single command. The API is transactional and all commands in a single call either succeed or fail together.
@@ -387,7 +374,6 @@ curl -X POST -H 'Content-type:application/json' --data-binary '{
}' http://localhost:8983/solr/gettingstarted/schema
----
-[[SchemaAPI-SchemaChangesamongReplicas]]
=== Schema Changes among Replicas
When running in SolrCloud mode, changes made to the schema on one node will propagate to all replicas in the collection.
@@ -398,51 +384,39 @@ If agreement is not reached by all replicas in the specified time, then the requ
If you do not supply an `updateTimeoutSecs` parameter, the default behavior is for the receiving node to return immediately after persisting the updates to ZooKeeper. All other replicas will apply the updates asynchronously. Consequently, without supplying a timeout, your client application cannot be sure that all replicas have applied the changes.
-[[SchemaAPI-RetrieveSchemaInformation]]
== Retrieve Schema Information
The following endpoints allow you to read how your schema has been defined. You can GET the entire schema, or only portions of it as needed.
-To modify the schema, see the previous section <<SchemaAPI-ModifytheSchema,Modify the Schema>>.
+To modify the schema, see the previous section <<Modify the Schema>>.
-[[SchemaAPI-RetrievetheEntireSchema]]
=== Retrieve the Entire Schema
`GET /_collection_/schema`
-[[SchemaAPI-INPUT]]
-==== INPUT
+==== Retrieve Schema Parameters
*Path Parameters*
-
-[options="header",]
-|===
-|Key |Description
-|collection |The collection (or core) name.
-|===
+`collection`::
+The collection (or core) name.
*Query Parameters*
The query parameters should be added to the API request after '?'.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="10,20,10,10,50",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|wt |string |No |json |Defines the format of the response. The options are *json*, *xml* or *schema.xml*. If not specified, JSON will be returned by default.
-|===
+`wt`::
+Defines the format of the response. The options are *json*, *xml* or *schema.xml*. If not specified, JSON will be returned by default.
[[SchemaAPI-OUTPUT]]
-==== OUTPUT
+==== Retrieve Schema Response
*Output Content*
The output will include all fields, field types, dynamic rules and copy field rules, in the format requested (JSON or XML). The schema name and version are also included.
[[SchemaAPI-EXAMPLES]]
-==== EXAMPLES
+==== Retrieve Schema Examples
Get the entire schema in JSON.
@@ -589,52 +563,49 @@ curl http://localhost:8983/solr/gettingstarted/schema?wt=schema.xml
</schema>
----
-
-[[SchemaAPI-ListFields]]
=== List Fields
`GET /_collection_/schema/fields`
`GET /_collection_/schema/fields/_fieldname_`
-[[SchemaAPI-INPUT.1]]
-==== INPUT
+==== List Fields Parameters
*Path Parameters*
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`collection`::
+The collection (or core) name.
-[cols="30,70",options="header"]
-|===
-|Key |Description
-|collection |The collection (or core) name.
-|fieldname |The specific fieldname (if limiting request to a single field).
-|===
+`fieldname`::
+The specific fieldname (if limiting the request to a single field).
*Query Parameters*
The query parameters can be added to the API request after a '?'.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`wt`::
+Defines the format of the response. The options are `json` or `xml`. If not specified, JSON will be returned by default.
-[cols="20,15,10,15,40",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|wt |string |No |json |Defines the format of the response. The options are *json* or *xml*. If not specified, JSON will be returned by default.
-|fl |string |No |(all fields) |Comma- or space-separated list of one or more fields to return. If not specified, all fields will be returned by default.
-|includeDynamic |boolean |No |false |If *true*, and if the *fl* query parameter is specified or the *fieldname* path parameter is used, matching dynamic fields are included in the response and identified with the *dynamicBase* property. If neither the *fl* query parameter nor the *fieldname* path parameter is specified, the *includeDynamic* query parameter is ignored. If *false*, matching dynamic fields will not be returned.
-|showDefaults |boolean |No |false |If *true*, all default field properties from each field's field type will be included in the response (e.g. *tokenized* for `solr.TextField`). If *false*, only explicitly specified field properties will be included.
-|===
+`fl`::
+Comma- or space-separated list of one or more fields to return. If not specified, all fields will be returned by default.
-[[SchemaAPI-OUTPUT.1]]
-==== OUTPUT
+`includeDynamic`::
+If `true`, and if the `fl` query parameter is specified or the `fieldname` path parameter is used, matching dynamic fields are included in the response and identified with the `dynamicBase` property.
++
+If neither the `fl` query parameter nor the `fieldname` path parameter is specified, the `includeDynamic` query parameter is ignored.
++
+If `false`, the default, matching dynamic fields will not be returned.
-*Output Content*
+`showDefaults`::
+If `true`, all default field properties from each field's field type will be included in the response (e.g. `tokenized` for `solr.TextField`). If `false`, the default, only explicitly specified field properties will be included.
+
+==== List Fields Response
+
+The output will include each field and any defined configuration for each field. The defined configuration can vary for each field, but will minimally include the field `name`, the `type`, if it is `indexed` and if it is `stored`.
-The output will include each field and any defined configuration for each field. The defined configuration can vary for each field, but will minimally include the field `name`, the `type`, if it is `indexed` and if it is `stored`. If `multiValued` is defined as either true or false (most likely true), that will also be shown. See the section <<defining-fields.adoc#defining-fields,Defining Fields>> for more information about each parameter.
+If `multiValued` is defined as either true or false (most likely true), that will also be shown. See the section <<defining-fields.adoc#defining-fields,Defining Fields>> for more information about each parameter.
-[[SchemaAPI-EXAMPLES.1]]
-==== EXAMPLES
+==== List Fields Examples
Get a list of all fields.
@@ -677,48 +648,37 @@ The sample output below has been truncated to only show a few fields.
}
----
-
-[[SchemaAPI-ListDynamicFields]]
=== List Dynamic Fields
`GET /_collection_/schema/dynamicfields`
`GET /_collection_/schema/dynamicfields/_name_`
-[[SchemaAPI-INPUT.2]]
-==== INPUT
+==== List Dynamic Field Parameters
*Path Parameters*
-[options="header",]
-|===
-|Key |Description
-|collection |The collection (or core) name.
-|name |The name of the dynamic field rule (if limiting request to a single dynamic field rule).
-|===
+`collection`::
+The collection (or core) name.
+
+`name`::
+The name of the dynamic field rule (if limiting request to a single dynamic field rule).
*Query Parameters*
The query parameters can be added to the API request after a '?'.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`wt`::
+Defines the format of the response. The options are `json` or `xml`. If not specified, JSON will be returned by default.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|wt |string |No |json |Defines the format of the response. The options are *json,* *xml*. If not specified, JSON will be returned by default.
-|showDefaults |boolean |No |false |If *true*, all default field properties from each dynamic field's field type will be included in the response (e.g. *tokenized* for `solr.TextField`). If *false*, only explicitly specified field properties will be included.
-|===
+`showDefaults`::
+If `true`, all default field properties from each dynamic field's field type will be included in the response (e.g. `tokenized` for `solr.TextField`). If `false`, the default, only explicitly specified field properties will be included.
-[[SchemaAPI-OUTPUT.2]]
-==== OUTPUT
-
-*Output Content*
+==== List Dynamic Field Response
The output will include each dynamic field rule and the defined configuration for each rule. The defined configuration can vary for each rule, but will minimally include the dynamic field `name`, the `type`, if it is `indexed` and if it is `stored`. See the section <<dynamic-fields.adoc#dynamic-fields,Dynamic Fields>> for more information about each parameter.
-[[SchemaAPI-EXAMPLES.2]]
-==== EXAMPLES
+==== List Dynamic Field Examples
Get a list of all dynamic field declarations:
@@ -771,49 +731,37 @@ The sample output below has been truncated.
}
----
-[[SchemaAPI-ListFieldTypes]]
=== List Field Types
`GET /_collection_/schema/fieldtypes`
`GET /_collection_/schema/fieldtypes/_name_`
-[[SchemaAPI-INPUT.3]]
-==== INPUT
+==== List Field Type Parameters
*Path Parameters*
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`collection`::
+The collection (or core) name.
-[cols="30,70",options="header"]
-|===
-|Key |Description
-|collection |The collection (or core) name.
-|name |The name of the field type (if limiting request to a single field type).
-|===
+`name`::
+The name of the field type (if limiting request to a single field type).
*Query Parameters*
The query parameters can be added to the API request after a '?'.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`wt`::
+Defines the format of the response. The options are `json` or `xml`. If not specified, JSON will be returned by default.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|wt |string |No |json |Defines the format of the response. The options are *json* or *xml*. If not specified, JSON will be returned by default.
-|showDefaults |boolean |No |false |If *true*, all default field properties from each field type will be included in the response (e.g. *tokenized* for `solr.TextField`). If *false*, only explicitly specified field properties will be included.
-|===
+`showDefaults`::
+If `true`, all default field properties from each dynamic field's field type will be included in the response (e.g. `tokenized` for `solr.TextField`). If `false`, the default, only explicitly specified field properties will be included.
-[[SchemaAPI-OUTPUT.3]]
-==== OUTPUT
-
-*Output Content*
+==== List Field Type Response
The output will include each field type and any defined configuration for the type. The defined configuration can vary for each type, but will minimally include the field type `name` and the `class`. If query or index analyzers, tokenizers, or filters are defined, those will also be shown with other defined parameters. See the section <<solr-field-types.adoc#solr-field-types,Solr Field Types>> for more information about how to configure various types of fields.
-[[SchemaAPI-EXAMPLES.3]]
-==== EXAMPLES
+==== List Field Type Examples
Get a list of all field types.
@@ -873,49 +821,37 @@ The sample output below has been truncated to show a few different field types f
}
----
-[[SchemaAPI-ListCopyFields]]
=== List Copy Fields
`GET /_collection_/schema/copyfields`
-[[SchemaAPI-INPUT.4]]
-==== INPUT
+==== List Copy Field Parameters
*Path Parameters*
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="30,70",options="header"]
-|===
-|Key |Description
-|collection |The collection (or core) name.
-|===
+`collection`::
+The collection (or core) name.
*Query Parameters*
The query parameters can be added to the API request after a '?'.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`wt`::
+Defines the format of the response. The options are `json` or `xml`. If not specified, JSON will be returned by default.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|wt |string |No |json |Defines the format of the response. The options are *json* or *xml*. If not specified, JSON will be returned by default.
-|source.fl |string |No |(all source fields) |Comma- or space-separated list of one or more copyField source fields to include in the response - copyField directives with all other source fields will be excluded from the response. If not specified, all copyField-s will be included in the response.
-|dest.fl |string |No |(all dest fields) |Comma- or space-separated list of one or more copyField dest fields to include in the response - copyField directives with all other dest fields will be excluded. If not specified, all copyField-s will be included in the response.
-|===
+`source.fl`::
+Comma- or space-separated list of one or more copyField source fields to include in the response - copyField directives with all other source fields will be excluded from the response. If not specified, all copyField-s will be included in the response.
-[[SchemaAPI-OUTPUT.4]]
-==== OUTPUT
+`dest.fl`::
+Comma- or space-separated list of one or more copyField destination fields to include in the response. copyField directives with all other `dest` fields will be excluded. If not specified, all copyField-s will be included in the response.
-*Output Content*
+==== List Copy Field Response
-The output will include the `source` and `dest`ination of each copy field rule defined in `schema.xml`. For more information about copying fields, see the section <<copying-fields.adoc#copying-fields,Copying Fields>>.
+The output will include the `source` and `dest` (destination) of each copy field rule defined in `schema.xml`. For more information about copying fields, see the section <<copying-fields.adoc#copying-fields,Copying Fields>>.
-[[SchemaAPI-EXAMPLES.4]]
-==== EXAMPLES
+==== List Copy Field Examples
-Get a list of all copyfields.
+Get a list of all copyFields.
[source,bash]
----
@@ -952,44 +888,29 @@ The sample output below has been truncated to the first few copy definitions.
}
----
-
-[[SchemaAPI-ShowSchemaName]]
=== Show Schema Name
`GET /_collection_/schema/name`
-[[SchemaAPI-INPUT.5]]
-==== INPUT
+==== Show Schema Parameters
*Path Parameters*
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="30,70",options="header"]
-|===
-|Key |Description
-|collection |The collection (or core) name.
-|===
+`collection`::
+The collection (or core) name.
*Query Parameters*
The query parameters can be added to the API request after a '?'.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="15,10,10,10,55",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|wt |string |No |json |Defines the format of the response. The options are *json* or *xml*. If not specified, JSON will be returned by default.
-|===
+`wt`::
+Defines the format of the response. The options are `json` or `xml`. If not specified, JSON will be returned by default.
-[[SchemaAPI-OUTPUT.5]]
-==== OUTPUT
+==== Show Schema Response
-*Output Content* The output will be simply the name given to the schema.
+The output will be simply the name given to the schema.
-[[SchemaAPI-EXAMPLES.5]]
-==== EXAMPLES
+==== Show Schema Examples
Get the schema name.
@@ -1007,46 +928,29 @@ curl http://localhost:8983/solr/gettingstarted/schema/name?wt=json
"name":"example"}
----
-
-[[SchemaAPI-ShowtheSchemaVersion]]
=== Show the Schema Version
`GET /_collection_/schema/version`
-[[SchemaAPI-INPUT.6]]
-==== INPUT
+==== Show Schema Version Parameters
*Path Parameters*
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="30,70",options="header"]
-|===
-|Key |Description
-|collection |The collection (or core) name.
-|===
+collection::
+The collection (or core) name.
*Query Parameters*
The query parameters can be added to the API request after a '?'.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="15,10,10,10,55",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|wt |string |No |json |Defines the format of the response. The options are *json* or *xml*. If not specified, JSON will be returned by default.
-|===
+`wt`::
+Defines the format of the response. The options are `json` or `xml`. If not specified, JSON will be returned by default.
-[[SchemaAPI-OUTPUT.6]]
-==== OUTPUT
-
-*Output Content*
+==== Show Schema Version Response
The output will simply be the schema version in use.
-[[SchemaAPI-EXAMPLES.6]]
-==== EXAMPLES
+==== Show Schema Version Example
Get the schema version
@@ -1064,46 +968,30 @@ curl http://localhost:8983/solr/gettingstarted/schema/version?wt=json
"version":1.5}
----
-
-[[SchemaAPI-ListUniqueKey]]
=== List UniqueKey
`GET /_collection_/schema/uniquekey`
-[[SchemaAPI-INPUT.7]]
-==== INPUT
+==== List UniqueKey Parameters
*Path Parameters*
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+|`collection`::
+The collection (or core) name.
-[cols="30,70",options="header"]
-|===
-|Key |Description
-|collection |The collection (or core) name.
-|===
*Query Parameters*
The query parameters can be added to the API request after a '?'.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="15,10,10,10,55",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|wt |string |No |json |Defines the format of the response. The options are *json* or *xml*. If not specified, JSON will be returned by default.
-|===
+|`wt`::
+Defines the format of the response. The options are `json` or `xml`. If not specified, JSON will be returned by default.
-[[SchemaAPI-OUTPUT.7]]
-==== OUTPUT
-
-*Output Content*
+==== List UniqueKey Response
The output will include simply the field name that is defined as the uniqueKey for the index.
-[[SchemaAPI-EXAMPLES.7]]
-==== EXAMPLES
+==== List UniqueKey Example
List the uniqueKey.
@@ -1121,46 +1009,29 @@ curl http://localhost:8983/solr/gettingstarted/schema/uniquekey?wt=json
"uniqueKey":"id"}
----
-
-[[SchemaAPI-ShowGlobalSimilarity]]
=== Show Global Similarity
`GET /_collection_/schema/similarity`
-[[SchemaAPI-INPUT.8]]
-==== INPUT
+==== Show Global Similarity Parameters
*Path Parameters*
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="30,70",options="header"]
-|===
-|Key |Description
-|collection |The collection (or core) name.
-|===
+`collection`::
+The collection (or core) name.
*Query Parameters*
The query parameters can be added to the API request after a '?'.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`wt`::
+Defines the format of the response. The options are `json` or `xml`. If not specified, JSON will be returned by default.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|wt |string |No |json |Defines the format of the response. The options are *json* or *xml*. If not specified, JSON will be returned by default.
-|===
-
-[[SchemaAPI-OUTPUT.8]]
-==== OUTPUT
-
-*Output Content*
+==== Show Global Similary Response
The output will include the class name of the global similarity defined (if any).
-[[SchemaAPI-EXAMPLES.8]]
-==== EXAMPLES
+==== Show Global Similarity Example
Get the similarity implementation.
@@ -1179,8 +1050,6 @@ curl http://localhost:8983/solr/gettingstarted/schema/similarity?wt=json
"class":"org.apache.solr.search.similarities.DefaultSimilarityFactory"}}
----
-
-[[SchemaAPI-ManageResourceData]]
== Manage Resource Data
The <<managed-resources.adoc#managed-resources,Managed Resources>> REST API provides a mechanism for any Solr plugin to expose resources that should support CRUD (Create, Read, Update, Delete) operations. Depending on what Field Types and Analyzers are configured in your Schema, additional `/schema/` REST API paths may exist. See the <<managed-resources.adoc#managed-resources,Managed Resources>> section for more information and examples.
[16/27] lucene-solr:feature/autoscaling: Revert "SOLR-9981: Fixes
precommit error in test file"
Posted by sh...@apache.org.
Revert "SOLR-9981: Fixes precommit error in test file"
This reverts commit e8057309b90db0c79fc273e2284948b84c16ce4c.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/288ab09c
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/288ab09c
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/288ab09c
Branch: refs/heads/feature/autoscaling
Commit: 288ab09ceb913ce4784f8943a31f9bf1902c8bec
Parents: 945bf8f
Author: Dennis Gove <dp...@gmail.com>
Authored: Mon Jun 26 13:51:16 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Mon Jun 26 17:33:26 2017 -0400
----------------------------------------------------------------------
.../solr/analytics/facet/FacetSortingTest.java | 16 ----------------
1 file changed, 16 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/288ab09c/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FacetSortingTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FacetSortingTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FacetSortingTest.java
index d91aa18..0751b63 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FacetSortingTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FacetSortingTest.java
@@ -1,19 +1,3 @@
-/*
- * 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.analytics.facet;
import org.apache.lucene.util.LuceneTestCase.SuppressCodecs;
[20/27] lucene-solr:feature/autoscaling: SOLR-10892: Phase 2: large
pages with lots of tables + lots of heading cleanups & TOC placement changes
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/93c96b06/solr/solr-ref-guide/src/solr-control-script-reference.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/solr-control-script-reference.adoc b/solr/solr-ref-guide/src/solr-control-script-reference.adoc
index c3a0805..c933114 100644
--- a/solr/solr-ref-guide/src/solr-control-script-reference.adoc
+++ b/solr/solr-ref-guide/src/solr-control-script-reference.adoc
@@ -1,6 +1,7 @@
= Solr Control Script Reference
:page-shortname: solr-control-script-reference
:page-permalink: solr-control-script-reference.html
+:page-tocclass: right
// 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
@@ -26,10 +27,8 @@ You can find the script in the `bin/` directory of your Solr installation. The `
More examples of `bin/solr` in use are available throughout the Solr Reference Guide, but particularly in the sections <<running-solr.adoc#running-solr,Running Solr>> and <<getting-started-with-solrcloud.adoc#getting-started-with-solrcloud,Getting Started with SolrCloud>>.
-[[SolrControlScriptReference-StartingandStopping]]
== Starting and Stopping
-[[SolrControlScriptReference-StartandRestart]]
=== Start and Restart
The `start` command starts Solr. The `restart` command allows you to restart Solr while it is already running or if it has been stopped already.
@@ -46,62 +45,106 @@ The `start` and `restart` commands have several options to allow you to run in S
When using the `restart` command, you must pass all of the parameters you initially passed when you started Solr. Behind the scenes, a stop request is initiated, so Solr will be stopped before being started again. If no nodes are already running, restart will skip the step to stop and proceed to starting Solr.
-[[SolrControlScriptReference-AvailableParameters]]
-==== Available Parameters
+==== Start Parameters
-The`bin/solr` script provides many options to allow you to customize the server in common ways, such as changing the listening port. However, most of the defaults are adequate for most Solr installations, especially when just getting started.
+The `bin/solr` script provides many options to allow you to customize the server in common ways, such as changing the listening port. However, most of the defaults are adequate for most Solr installations, especially when just getting started.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`-a "<string>"`::
+Start Solr with additional JVM parameters, such as those starting with -X. If you are passing JVM parameters that begin with "-D", you can omit the -a option.
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-a "<string>" |Start Solr with additional JVM parameters, such as those starting with -X. If you are passing JVM parameters that begin with "-D", you can omit the -a option. |`bin/solr start -a "-Xdebug -Xrunjdwp:transport=dt_socket, server=y,suspend=n,address=1044"`
-|-cloud a|
-Start Solr in SolrCloud mode, which will also launch the embedded ZooKeeper instance included with Solr.
+*Example*:
-This option can be shortened to simply `-c`.
+[source,bash]
+bin/solr start -a "-Xdebug -Xrunjdwp:transport=dt_socket, server=y,suspend=n,address=1044"
+`-cloud`::
+Start Solr in SolrCloud mode, which will also launch the embedded ZooKeeper instance included with Solr.
++
+This option can be shortened to simply `-c`.
++
If you are already running a ZooKeeper ensemble that you want to use instead of the embedded (single-node) ZooKeeper, you should also pass the -z parameter.
++
+For more details, see the section <<SolrCloud Mode>> below.
++
+*Example*: `bin/solr start -c`
-For more details, see the section <<SolrControlScriptReference-SolrCloudMode,SolrCloud Mode>> below.
+`-d <dir>`::
+Define a server directory, defaults to `server` (as in, `$SOLR_HOME/server`). It is uncommon to override this option. When running multiple instances of Solr on the same host, it is more common to use the same server directory for each instance and use a unique Solr home directory using the -s option.
++
+*Example*: `bin/solr start -d newServerDir`
- |`bin/solr start -c`
-|-d <dir> |Define a server directory, defaults to `server` (as in, `$SOLR_HOME/server`). It is uncommon to override this option. When running multiple instances of Solr on the same host, it is more common to use the same server directory for each instance and use a unique Solr home directory using the -s option. |`bin/solr start -d newServerDir`
-|-e <name> a|
+`-e <name>`::
Start Solr with an example configuration. These examples are provided to help you get started faster with Solr generally, or just try a specific feature.
-
++
The available options are:
* cloud
* techproducts
* dih
* schemaless
-
++
See the section <<SolrControlScriptReference-RunningwithExampleConfigurations,Running with Example Configurations>> below for more details on the example configurations.
- |`bin/solr start -e schemaless`
-|-f |Start Solr in the foreground; you cannot use this option when running examples with the -e option. |`bin/solr start -f`
-|-h <hostname> |Start Solr with the defined hostname. If this is not specified, 'localhost' will be assumed. |`bin/solr start -h search.mysolr.com`
-|-m <memory> |Start Solr with the defined value as the min (-Xms) and max (-Xmx) heap size for the JVM. |`bin/solr start -m 1g`
-|-noprompt a|
-Start Solr and suppress any prompts that may be seen with another option. This would have the side effect of accepting all defaults implicitly.
++
+*Example*: `bin/solr start -e schemaless`
+`-f`::
+Start Solr in the foreground; you cannot use this option when running examples with the -e option.
++
+*Example*: `bin/solr start -f`
+
+`-h <hostname>`::
+Start Solr with the defined hostname. If this is not specified, 'localhost' will be assumed.
++
+*Example*: `bin/solr start -h search.mysolr.com`
+
+`-m <memory>`::
+Start Solr with the defined value as the min (-Xms) and max (-Xmx) heap size for the JVM.
++
+*Example*: `bin/solr start -m 1g`
+
+`-noprompt`::
+Start Solr and suppress any prompts that may be seen with another option. This would have the side effect of accepting all defaults implicitly.
++
For example, when using the "cloud" example, an interactive session guides you through several options for your SolrCloud cluster. If you want to accept all of the defaults, you can simply add the -noprompt option to your request.
++
+*Example*: `bin/solr start -e cloud -noprompt`
- |`bin/solr start -e cloud -noprompt`
-|-p <port> |Start Solr on the defined port. If this is not specified, '8983' will be used. |`bin/solr start -p 8655`
-|-s <dir> a|
-Sets the solr.solr.home system property; Solr will create core directories under this directory. This allows you to run multiple Solr instances on the same host while reusing the same server directory set using the -d parameter. If set, the specified directory should contain a solr.xml file, unless solr.xml exists in ZooKeeper. The default value is `server/solr`.
+`-p <port>`::
+Start Solr on the defined port. If this is not specified, '8983' will be used.
++
+*Example*: `bin/solr start -p 8655`
+`-s <dir>`::
+Sets the solr.solr.home system property; Solr will create core directories under this directory. This allows you to run multiple Solr instances on the same host while reusing the same server directory set using the -d parameter. If set, the specified directory should contain a solr.xml file, unless solr.xml exists in ZooKeeper. The default value is `server/solr`.
++
This parameter is ignored when running examples (-e), as the solr.solr.home depends on which example is run.
++
+*Example*: `bin/solr start -s newHome`
+
+`-v`::
+Be more verbose. This changes the logging level of log4j from `INFO` to `DEBUG`, having the same effect as if you edited `log4j.properties` accordingly.
++
+*Example*: `bin/solr start -f -v`
+
+`-q`::
+Be more quiet. This changes the logging level of log4j from `INFO` to `WARN`, having the same effect as if you edited `log4j.properties` accordingly. This can be useful in a production setting where you want to limit logging to warnings and errors.
++
+*Example*: `bin/solr start -f -q`
+
+`-V`::
+Start Solr with verbose messages from the start script.
++
+*Example*: `bin/solr start -V`
+
+`-z <zkHost>`::
+Start Solr with the defined ZooKeeper connection string. This option is only used with the -c option, to start Solr in SolrCloud mode. If this option is not provided, Solr will start the embedded ZooKeeper instance and use that instance for SolrCloud operations.
++
+*Example*: `bin/solr start -c -z server1:2181,server2:2181`
- |`bin/solr start -s newHome`
-|-v |Be more verbose. This changes the logging level of log4j from `INFO` to `DEBUG`, having the same effect as if you edited `log4j.properties` accordingly. |`bin/solr start -f -v`
-|-q |Be more quiet. This changes the logging level of log4j from `INFO` to `WARN`, having the same effect as if you edited `log4j.properties` accordingly. This can be useful in a production setting where you want to limit logging to warnings and errors. |`bin/solr start -f -q`
-|-V |Start Solr with verbose messages from the start script. |`bin/solr start -V`
-|-z <zkHost> |Start Solr with the defined ZooKeeper connection string. This option is only used with the -c option, to start Solr in SolrCloud mode. If this option is not provided, Solr will start the embedded ZooKeeper instance and use that instance for SolrCloud operations. |`bin/solr start -c -z server1:2181,server2:2181`
-|-force |If attempting to start Solr as the root user, the script will exit with a warning that running Solr as "root" can cause problems. It is possible to override this warning with the -force parameter. |`sudo bin/solr start -force`
-|===
+`-force`::
+If attempting to start Solr as the root user, the script will exit with a warning that running Solr as "root" can cause problems. It is possible to override this warning with the -force parameter.
++
+*Example*: `sudo bin/solr start -force`
To emphasize how the default settings work take a moment to understand that the following commands are equivalent:
@@ -111,7 +154,6 @@ To emphasize how the default settings work take a moment to understand that the
It is not necessary to define all of the options when starting if the defaults are fine for your needs.
-[[SolrControlScriptReference-SettingJavaSystemProperties]]
==== Setting Java System Properties
The `bin/solr` script will pass any additional parameters that begin with `-D` to the JVM, which allows you to set arbitrary Java system properties.
@@ -120,7 +162,6 @@ For example, to set the auto soft-commit frequency to 3 seconds, you can do:
`bin/solr start -Dsolr.autoSoftCommit.maxTime=3000`
-[[SolrControlScriptReference-SolrCloudMode]]
==== SolrCloud Mode
The `-c` and `-cloud` options are equivalent:
@@ -151,23 +192,34 @@ For more information about starting Solr in SolrCloud mode, see also the section
The example configurations allow you to get started quickly with a configuration that mirrors what you hope to accomplish with Solr.
-Each example launches Solr with a managed schema, which allows use of the <<schema-api.adoc#schema-api,Schema API>> to make schema edits, but does not allow manual editing of a Schema file If you would prefer to manually modify a `schema.xml` file directly, you can change this default as described in the section <<schema-factory-definition-in-solrconfig.adoc#schema-factory-definition-in-solrconfig,Schema Factory Definition in SolrConfig>>.
+Each example launches Solr with a managed schema, which allows use of the <<schema-api.adoc#schema-api,Schema API>> to make schema edits, but does not allow manual editing of a Schema file.
+
+If you would prefer to manually modify a `schema.xml` file directly, you can change this default as described in the section <<schema-factory-definition-in-solrconfig.adoc#schema-factory-definition-in-solrconfig,Schema Factory Definition in SolrConfig>>.
Unless otherwise noted in the descriptions below, the examples do not enable <<solrcloud.adoc#solrcloud,SolrCloud>> nor <<schemaless-mode.adoc#schemaless-mode,schemaless mode>>.
The following examples are provided:
-* *cloud*: This example starts a 1-4 node SolrCloud cluster on a single machine. When chosen, an interactive session will start to guide you through options to select the initial configset to use, the number of nodes for your example cluster, the ports to use, and name of the collection to be created. When using this example, you can choose from any of the available configsets found in `$SOLR_HOME/server/solr/configsets`.
-* *techproducts*: This example starts Solr in standalone mode with a schema designed for the sample documents included in the `$SOLR_HOME/example/exampledocs` directory. The configset used can be found in `$SOLR_HOME/server/solr/configsets/sample_techproducts_configs`.
-* *dih*: This example starts Solr in standalone mode with the DataImportHandler (DIH) enabled and several example `dataconfig.xml` files pre-configured for different types of data supported with DIH (such as, database contents, email, RSS feeds, etc.). The configset used is customized for DIH, and is found in `$SOLR_HOME/example/example-DIH/solr/conf`. For more information about DIH, see the section <<uploading-structured-data-store-data-with-the-data-import-handler.adoc#uploading-structured-data-store-data-with-the-data-import-handler,Uploading Structured Data Store Data with the Data Import Handler>>.
-* *schemaless*: This example starts Solr in standalone mode using a managed schema, as described in the section <<schema-factory-definition-in-solrconfig.adoc#schema-factory-definition-in-solrconfig,Schema Factory Definition in SolrConfig>>, and provides a very minimal pre-defined schema. Solr will run in <<schemaless-mode.adoc#schemaless-mode,Schemaless Mode>> with this configuration, where Solr will create fields in the schema on the fly and will guess field types used in incoming documents. The configset used can be found in `$SOLR_HOME/server/solr/configsets/data_driven_schema_configs`.
+* *cloud*: This example starts a 1-4 node SolrCloud cluster on a single machine. When chosen, an interactive session will start to guide you through options to select the initial configset to use, the number of nodes for your example cluster, the ports to use, and name of the collection to be created.
++
+When using this example, you can choose from any of the available configsets found in `$SOLR_HOME/server/solr/configsets`.
+* *techproducts*: This example starts Solr in standalone mode with a schema designed for the sample documents included in the `$SOLR_HOME/example/exampledocs` directory.
++
+The configset used can be found in `$SOLR_HOME/server/solr/configsets/sample_techproducts_configs`.
+* *dih*: This example starts Solr in standalone mode with the DataImportHandler (DIH) enabled and several example `dataconfig.xml` files pre-configured for different types of data supported with DIH (such as, database contents, email, RSS feeds, etc.).
++
+The configset used is customized for DIH, and is found in `$SOLR_HOME/example/example-DIH/solr/conf`.
++
+For more information about DIH, see the section <<uploading-structured-data-store-data-with-the-data-import-handler.adoc#uploading-structured-data-store-data-with-the-data-import-handler,Uploading Structured Data Store Data with the Data Import Handler>>.
+* *schemaless*: This example starts Solr in standalone mode using a managed schema, as described in the section <<schema-factory-definition-in-solrconfig.adoc#schema-factory-definition-in-solrconfig,Schema Factory Definition in SolrConfig>>, and provides a very minimal pre-defined schema. Solr will run in <<schemaless-mode.adoc#schemaless-mode,Schemaless Mode>> with this configuration, where Solr will create fields in the schema on the fly and will guess field types used in incoming documents.
++
+The configset used can be found in `$SOLR_HOME/server/solr/configsets/data_driven_schema_configs`.
[IMPORTANT]
====
The run in-foreground option (`-f`) is not compatible with the `-e` option since the script needs to perform additional tasks after starting the Solr server.
====
-[[SolrControlScriptReference-Stop]]
=== Stop
The `stop` command sends a STOP request to a running Solr node, which allows it to shutdown gracefully. The command will wait up to 5 seconds for Solr to stop gracefully and then will forcefully kill the process (kill -9).
@@ -176,23 +228,26 @@ The `stop` command sends a STOP request to a running Solr node, which allows it
`bin/solr stop -help`
-[[SolrControlScriptReference-AvailableParameters.1]]
-==== Available Parameters
+==== Stop Parameters
+
+`-p <port>`::
+Stop Solr running on the given port. If you are running more than one instance, or are running in SolrCloud mode, you either need to specify the ports in separate requests or use the -all option.
++
+*Example*: `bin/solr stop -p 8983`
+
+`-all`::
+Stop all running Solr instances that have a valid PID.
++
+*Example*: `bin/solr stop -all`
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`-k <key>`::
+Stop key used to protect from stopping Solr inadvertently; default is "solrrocks".
++
+*Example*: `bin/solr stop -k solrrocks`
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-p <port> |Stop Solr running on the given port. If you are running more than one instance, or are running in SolrCloud mode, you either need to specify the ports in separate requests or use the -all option. |`bin/solr stop -p 8983`
-|-all |Stop all running Solr instances that have a valid PID. |`bin/solr stop -all`
-|-k <key> |Stop key used to protect from stopping Solr inadvertently; default is "solrrocks". |`bin/solr stop -k solrrocks`
-|===
-[[SolrControlScriptReference-SystemInformation]]
== System Information
-[[SolrControlScriptReference-Version]]
=== Version
The `version` command simply returns the version of Solr currently installed and immediately exists.
@@ -203,7 +258,6 @@ $ bin/solr version
X.Y.0
----
-[[SolrControlScriptReference-Status]]
=== Status
The `status` command displays basic JSON-formatted information for any Solr nodes found running on the local system.
@@ -253,16 +307,17 @@ The `healthcheck` command generates a JSON-formatted health report for a collect
`bin/solr healthcheck -help`
[[SolrControlScriptReference-AvailableParameters.2]]
-==== Available Parameters
+==== Healthcheck Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`-c <collection>`::
+ Name of the collection to run a healthcheck against (required).
++
+*Example*: `bin/solr healthcheck -c gettingstarted`
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-c <collection> |Name of the collection to run a healthcheck against (required). |`bin/solr healthcheck -c gettingstarted`
-|-z <zkhost> |ZooKeeper connection string, defaults to localhost:9983. If you are running Solr on a port other than 8983, you will have to specify the ZooKeeper connection string. By default, this will be the Solr port + 1000. |`bin/solr healthcheck -z localhost:2181`
-|===
+`-z <zkhost>`::
+ZooKeeper connection string, defaults to `localhost:9983`. If you are running Solr on a port other than 8983, you will have to specify the ZooKeeper connection string. By default, this will be the Solr port + 1000.
++
+*Example*: `bin/solr healthcheck -z localhost:2181`
Below is an example healthcheck request and response using a non-standard ZooKeeper connect string, with 2 nodes running:
@@ -321,8 +376,7 @@ Below is an example healthcheck request and response using a non-standard ZooKee
The `bin/solr` script can also help you create new collections (in SolrCloud mode) or cores (in standalone mode), or delete collections.
-[[SolrControlScriptReference-Create]]
-=== Create
+=== Create a Core or Collection
The `create` command detects the mode that Solr is running in (standalone or SolrCloud) and then creates a core or collection depending on the mode.
@@ -330,65 +384,74 @@ The `create` command detects the mode that Solr is running in (standalone or Sol
`bin/solr create -help`
-[[SolrControlScriptReference-AvailableParameters.3]]
-==== Available Parameters
+==== Create Core or Collection Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`-c <name>`::
+Name of the core or collection to create (required).
++
+*Example*: `bin/solr create -c mycollection`
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-c <name> |Name of the core or collection to create (required). |`bin/solr create -c mycollection`
-|-d <confdir> a|
+`-d <confdir>`::
The configuration directory. This defaults to `data_driven_schema_configs`.
++
+See the section <<Configuration Directories and SolrCloud>> below for more details about this option when running in SolrCloud mode.
++
+*Example*: `bin/solr create -d basic_configs`
-See the section <<SolrControlScriptReference-ConfigurationDirectoriesandSolrCloud,Configuration Directories and SolrCloud>> below for more details about this option when running in SolrCloud mode.
+`-n <configName>`::
+The configuration name. This defaults to the same name as the core or collection.
++
+*Example*: `bin/solr create -n basic`
- |`bin/solr create -d basic_configs`
-|-n <configName> |The configuration name. This defaults to the same name as the core or collection. |`bin/solr create -n basic`
-|-p <port> a|
+`-p <port>`::
Port of a local Solr instance to send the create command to; by default the script tries to detect the port by looking for running Solr instances.
-
++
This option is useful if you are running multiple standalone Solr instances on the same host, thus requiring you to be specific about which instance to create the core in.
++
+*Example*: `bin/solr create -p 8983`
- |`bin/solr create -p 8983`
-a|
--s <shards>
-
--shards
-
- |Number of shards to split a collection into, default is 1; only applies when Solr is running in SolrCloud mode. |`bin/solr create -s 2`
-a|
--rf <replicas>
+`-s <shards>` or `-shards`::
+Number of shards to split a collection into, default is 1; only applies when Solr is running in SolrCloud mode.
++
+*Example*: `bin/solr create -s 2`
--replicationFactor
+`-rf <replicas>` or `-replicationFactor`::
+Number of copies of each document in the collection. The default is 1 (no replication).
++
+*Example*: `bin/solr create -rf 2`
- |Number of copies of each document in the collection. The default is 1 (no replication). |`bin/solr create -rf 2`
-|-force |If attempting to run create as "root" user, the script will exit with a warning that running Solr or actions against Solr as "root" can cause problems. It is possible to override this warning with the -force parameter. |`bin/solr create -c foo -force`
-|===
+`-force`::
+If attempting to run create as "root" user, the script will exit with a warning that running Solr or actions against Solr as "root" can cause problems. It is possible to override this warning with the -force parameter.
++
+*Example*: `bin/solr create -c foo -force`
-[[SolrControlScriptReference-ConfigurationDirectoriesandSolrCloud]]
==== Configuration Directories and SolrCloud
-Before creating a collection in SolrCloud, the configuration directory used by the collection must be uploaded to ZooKeeper. The create command supports several use cases for how collections and configuration directories work. The main decision you need to make is whether a configuration directory in ZooKeeper should be shared across multiple collections.
+Before creating a collection in SolrCloud, the configuration directory used by the collection must be uploaded to ZooKeeper. The `create` command supports several use cases for how collections and configuration directories work. The main decision you need to make is whether a configuration directory in ZooKeeper should be shared across multiple collections.
Let's work through a few examples to illustrate how configuration directories work in SolrCloud.
-First, if you don't provide the `-d` or `-n` options, then the default configuration (`$SOLR_HOME/server/solr/configsets/data_driven_schema_configs/conf`) is uploaded to ZooKeeper using the same name as the collection. For example, the following command will result in the *data_driven_schema_configs* configuration being uploaded to `/configs/contacts` in ZooKeeper: `bin/solr create -c contacts`. If you create another collection, by doing `bin/solr create -c contacts2`, then another copy of the `data_driven_schema_configs` directory will be uploaded to ZooKeeper under `/configs/contacts2`. Any changes you make to the configuration for the contacts collection will not affect the contacts2 collection. Put simply, the default behavior creates a unique copy of the configuration directory for each collection you create.
+First, if you don't provide the `-d` or `-n` options, then the default configuration (`$SOLR_HOME/server/solr/configsets/data_driven_schema_configs/conf`) is uploaded to ZooKeeper using the same name as the collection.
+
+For example, the following command will result in the `data_driven_schema_configs` configuration being uploaded to `/configs/contacts` in ZooKeeper: `bin/solr create -c contacts`.
+
+If you create another collection with `bin/solr create -c contacts2`, then another copy of the `data_driven_schema_configs` directory will be uploaded to ZooKeeper under `/configs/contacts2`.
+
+Any changes you make to the configuration for the contacts collection will not affect the `contacts2` collection. Put simply, the default behavior creates a unique copy of the configuration directory for each collection you create.
You can override the name given to the configuration directory in ZooKeeper by using the `-n` option. For instance, the command `bin/solr create -c logs -d basic_configs -n basic` will upload the `server/solr/configsets/basic_configs/conf` directory to ZooKeeper as `/configs/basic`.
-Notice that we used the `-d` option to specify a different configuration than the default. Solr provides several built-in configurations under `server/solr/configsets`. However you can also provide the path to your own configuration directory using the `-d` option. For instance, the command `bin/solr create -c mycoll -d /tmp/myconfigs`, will upload `/tmp/myconfigs` into ZooKeeper under `/configs/mycoll` . To reiterate, the configuration directory is named after the collection unless you override it using the `-n` option.
+Notice that we used the `-d` option to specify a different configuration than the default. Solr provides several built-in configurations under `server/solr/configsets`. However you can also provide the path to your own configuration directory using the `-d` option. For instance, the command `bin/solr create -c mycoll -d /tmp/myconfigs`, will upload `/tmp/myconfigs` into ZooKeeper under `/configs/mycoll` .
+
+To reiterate, the configuration directory is named after the collection unless you override it using the `-n` option.
Other collections can share the same configuration by specifying the name of the shared configuration using the `-n` option. For instance, the following command will create a new collection that shares the basic configuration created previously: `bin/solr create -c logs2 -n basic`.
-[[SolrControlScriptReference-Data-drivenSchemaandSharedConfigurations]]
==== Data-driven Schema and Shared Configurations
The `data_driven_schema_configs` schema can mutate as data is indexed. Consequently, we recommend that you do not share data-driven configurations between collections unless you are certain that all collections should inherit the changes made when indexing data into one of the collections.
-[[SolrControlScriptReference-Delete]]
-=== Delete
+=== Delete Core or Collection
The `delete` command detects the mode that Solr is running in (standalone or SolrCloud) and then deletes the specified core (standalone) or collection (SolrCloud) as appropriate.
@@ -396,33 +459,33 @@ The `delete` command detects the mode that Solr is running in (standalone or Sol
`bin/solr delete -help`
-If running in SolrCloud mode, the delete command checks if the configuration directory used by the collection you are deleting is being used by other collections. If not, then the configuration directory is also deleted from ZooKeeper. For example, if you created a collection by doing `bin/solr create -c contacts`, then the delete command `bin/solr delete -c contacts` will check to see if the `/configs/contacts` configuration directory is being used by any other collections. If not, then the `/configs/contacts` directory is removed from ZooKeeper.
+If running in SolrCloud mode, the delete command checks if the configuration directory used by the collection you are deleting is being used by other collections. If not, then the configuration directory is also deleted from ZooKeeper.
-[[SolrControlScriptReference-AvailableParameters.4]]
-==== Available Parameters
+For example, if you created a collection with `bin/solr create -c contacts`, then the delete command `bin/solr delete -c contacts` will check to see if the `/configs/contacts` configuration directory is being used by any other collections. If not, then the `/configs/contacts` directory is removed from ZooKeeper.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+==== Delete Core or Collection Parameters
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-c <name> |Name of the core / collection to delete (required). |`bin/solr delete -c mycoll`
-|-deleteConfig <true\|false> a|
-Delete the configuration directory from ZooKeeper. The default is true.
+`-c <name>`::
+Name of the core / collection to delete (required).
++
+*Example*: `bin/solr delete -c mycoll`
-If the configuration directory is being used by another collection, then it will not be deleted even if you pass `-deleteConfig` as true.
-|`bin/solr delete -deleteConfig false`
-|-p <port> a|
-The port of a local Solr instance to send the delete command to. By default the script tries to detect the port by looking for running Solr instances.
+`-deleteConfig`::
+Whether or not the configuration directory should also be deleted from ZooKeeper. The default is `true`.
++
+If the configuration directory is being used by another collection, then it will not be deleted even if you pass `-deleteConfig` as `true`.
++
+*Example*: `bin/solr delete -deleteConfig false`
+`-p <port>`::
+The port of a local Solr instance to send the delete command to. By default the script tries to detect the port by looking for running Solr instances.
++
This option is useful if you are running multiple standalone Solr instances on the same host, thus requiring you to be specific about which instance to delete the core from.
-|`bin/solr delete -p 8983`
-|===
++
+*Example*: `bin/solr delete -p 8983`
== Authentication
-// TODO 6.6 check this whole section for accuracy
-
The `bin/solr` script allows enabling or disabling Basic Authentication, allowing you to configure authentication from the command line.
Currently, this script only enables Basic Authentication, and is only available when using SolrCloud mode.
@@ -517,39 +580,38 @@ NOTE: Solr should have been started at least once before issuing these commands
Use the `zk upconfig` command to upload one of the pre-configured configuration set or a customized configuration set to ZooKeeper.
+==== ZK Upload Parameters
-[[SolrControlScriptReference-AvailableParameters_allparametersarerequired_]]
-==== Available Parameters (all parameters are required)
+All parameters below are required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-n <name> a|
+`-n <name>`::
Name of the configuration set in ZooKeeper. This command will upload the configuration set to the "configs" ZooKeeper node giving it the name specified.
-
++
You can see all uploaded configuration sets in the Admin UI via the Cloud screens. Choose Cloud \-> Tree \-> configs to see them.
-
++
If a pre-existing configuration set is specified, it will be overwritten in ZooKeeper.
++
+*Example*: `-n myconfig`
- |`-n myconfig`
-|-d <configset dir> a|
+`-d <configset dir>`::
The path of the configuration set to upload. It should have a "conf" directory immediately below it that in turn contains solrconfig.xml etc.
-
++
If just a name is supplied, `$SOLR_HOME/server/solr/configsets` will be checked for this name. An absolute path may be supplied instead.
++
+*Examples*:
- a|
-`-d directory_under_configsets`
-
-`-d /path/to/configset/source`
+* `-d directory_under_configsets`
+* `-d /path/to/configset/source`
-|-z <zkHost> |The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`. |`-z 123.321.23.43:2181`
-|===
+`-z <zkHost>`::
+The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`.
++
+*Example*: `-z 123.321.23.43:2181`
-An example of this command with these parameters is:
+An example of this command with all of the parameters is:
-`bin/solr zk upconfig -z 111.222.333.444:2181 -n mynewconfig -d /path/to/configset`
+[source,bash]
+bin/solr zk upconfig -z 111.222.333.444:2181 -n mynewconfig -d /path/to/configset
.Reload Collections When Changing Configurations
[WARNING]
@@ -562,57 +624,70 @@ This command does *not* automatically make changes effective! It simply uploads
Use the `zk downconfig` command to download a configuration set from ZooKeeper to the local filesystem.
+==== ZK Download Parameters
-[[SolrControlScriptReference-AvailableParameters_allparametersarerequired_.1]]
-==== Available Parameters (all parameters are required)
+All parameters listed below are required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`-n <name>`::
+Name of config set in ZooKeeper to download. The Admin UI Cloud \-> Tree \-> configs node lists all available configuration sets.
++
+*Example*: `-n myconfig`
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-n <name> |Name of config set in ZooKeeper to download. The Admin UI Cloud \-> Tree \-> configs node lists all available configuration sets. |`-n myconfig`
-|-d <configset dir> a|
+`-d <configset dir>`::
The path to write the downloaded configuration set into. If just a name is supplied, `$SOLR_HOME/server/solr/configsets` will be the parent. An absolute path may be supplied as well.
-
++
In either case, _pre-existing configurations at the destination will be overwritten!_
++
+*Examples*:
- a|
-`-d directory_under_configsets`
-
-`-d /path/to/configset/destination`
+* `-d directory_under_configsets`
+* `-d /path/to/configset/destination`
-|-z <zkHost> |The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`. |`-z 123.321.23.43:2181`
-|===
+`-z <zkHost>`::
+The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`.
++
+*Example*: `-z 123.321.23.43:2181`
-An example of this command with the parameters is:
+An example of this command with all parameters is:
-`bin/solr zk downconfig -z 111.222.333.444:2181 -n mynewconfig -d /path/to/configset`
+[source,bash]
+bin/solr zk downconfig -z 111.222.333.444:2181 -n mynewconfig -d /path/to/configset
A "best practice" is to keep your configuration sets in some form of version control as the system-of-record. In that scenario, `downconfig` should rarely be used.
-[[SolrControlScriptReference-CopybetweenLocalFilesandZooKeeperznodes]]
=== Copy between Local Files and ZooKeeper znodes
Use the `zk cp` command for transferring files and directories between ZooKeeper znodes and your local drive. This command will copy from the local drive to ZooKeeper, from ZooKeeper to the local drive or from ZooKeeper to ZooKeeper.
-[[SolrControlScriptReference-AvailableParameters.5]]
-==== Available Parameters
+==== ZK Copy Parameters
+
+`-r`::
+Optional. Do a recursive copy. The command will fail if the <src> has children unless '-r' is specified.
++
+*Example*: `-r`
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`<src>`::
+The file or path to copy from. If prefixed with `zk:` then the source is presumed to be ZooKeeper. If no prefix or the prefix is 'file:' this is the local drive. At least one of <src> or <dest> must be prefixed by `'zk:'` or the command will fail.
++
+*Examples*:
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-r |Optional. Do a recursive copy. The command will fail if the <src> has children unless '-r' is specified. |`-r`
-|<src> |The file or path to copy from. If prefixed with `zk:` then the source is presumed to be ZooKeeper. If no prefix or the prefix is 'file:' this is the local drive. At least one of <src> or <dest> must be prefixed by `'zk:'` or the command will fail. a|
-`zk:/configs/myconfigs/solrconfig.xml`
+* `zk:/configs/myconfigs/solrconfig.xml`
+* `file:/Users/apache/configs/src`
-`file:/Users/apache/configs/src`
+`<dest>`::
+The file or path to copy to. If prefixed with `zk:` then the source is presumed to be ZooKeeper. If no prefix or the prefix is `file:` this is the local drive.
++
+At least one of `<src>` or `<dest>` must be prefixed by `zk:` or the command will fail. If `<dest>` ends in a slash character it names a directory.
++
+*Examples*:
-|<dest> |The file or path to copy to. If prefixed with `zk:` then the source is presumed to be ZooKeeper. If no prefix or the prefix is 'file:' this is the local drive. At least one of <src> or <dest> must be prefixed by `zk:` or the command will fail. If <dest> ends in a slash character it names a directory. |`zk:/configs/myconfigs/solrconfig.xml` `file:/Users/apache/configs/src`
-|-z <zkHost> |The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`. |`-z 123.321.23.43:2181`
-|===
+* `zk:/configs/myconfigs/solrconfig.xml`
+* `file:/Users/apache/configs/src`
+
+`-z <zkHost>`::
+The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`.
++
+*Example*: `-z 123.321.23.43:2181`
An example of this command with the parameters is:
@@ -624,84 +699,88 @@ Copy a single file from ZooKeeper to local.
`bin/solr zk cp zk:/configs/myconf/managed_schema /configs/myconf/managed_schema -z 111.222.333.444:2181`
-[[SolrControlScriptReference-RemoveaznodefromZooKeeper]]
=== Remove a znode from ZooKeeper
Use the `zk rm` command to remove a znode (and optionally all child nodes) from ZooKeeper
-[[SolrControlScriptReference-AvailableParameters.6]]
-==== Available Parameters
+==== ZK Remove Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`-r`::
+Optional. Do a recursive removal. The command will fail if the <path> has children unless '-r' is specified.
++
+*Example*: `-r`
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-r |Optional. Do a recursive removal. The command will fail if the <path> has children unless '-r' is specified. |`-r`
-|<path> a|
+`<path>`::
The path to remove from ZooKeeper, either a parent or leaf node.
-
++
There are limited safety checks, you cannot remove '/' or '/zookeeper' nodes.
-
++
The path is assumed to be a ZooKeeper node, no `zk:` prefix is necessary.
++
+*Examples*:
- a|
-`/configs`
-
-`/configs/myconfigset`
-
-`/configs/myconfigset/solrconfig.xml`
+* `/configs`
+* `/configs/myconfigset`
+* `/configs/myconfigset/solrconfig.xml`
-|-z <zkHost> |The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`. |`-z 123.321.23.43:2181`
-|===
+`-z <zkHost>`::
+The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`.
++
+*Example*: `-z 123.321.23.43:2181`
-An example of this command with the parameters is:
+Examples of this command with the parameters are:
`bin/solr zk rm -r /configs`
`bin/solr zk rm /configs/myconfigset/schema.xml`
-[[SolrControlScriptReference-MoveOneZooKeeperznodetoAnother_Rename_]]
=== Move One ZooKeeper znode to Another (Rename)
Use the `zk mv` command to move (rename) a ZooKeeper znode
-[[SolrControlScriptReference-AvailableParameters.7]]
-==== Available Parameters
+==== ZK Move Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`<src>`::
+The znode to rename. The `zk:` prefix is assumed.
++
+*Example*: `/configs/oldconfigset`
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|<src> |The znode to rename. The `zk:` prefix is assumed. |`/configs/oldconfigset`
-|<dest> |The new name of the znode. The `zk:` prefix is assumed. |`/configs/newconfigset`
-|-z <zkHost> |The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`. |`-z 123.321.23.43:2181`
-|===
+`<dest>`::
+The new name of the znode. The `zk:` prefix is assumed.
++
+*Example*: `/configs/newconfigset`
+
+`-z <zkHost>`::
+The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`.
++
+*Example*: `-z 123.321.23.43:2181`
An example of this command is:
`bin/solr zk mv /configs/oldconfigset /configs/newconfigset`
-[[SolrControlScriptReference-ListaZooKeeperznode_sChildren]]
=== List a ZooKeeper znode's Children
Use the `zk ls` command to see the children of a znode.
-[[SolrControlScriptReference-AvailableParameters.8]]
-==== Available Parameters
+==== ZK List Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`-r`
+Optional. Recursively list all descendants of a znode.
++
+*Example*: `-r`
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|-r |Optional. Recursively list all descendants of a znode. |`-r`
-|<path> |The path on ZooKeeper to list. |`/collections/mycollection`
-|-z <zkHost> |The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`. |`-z 123.321.23.43:2181`
-|===
+`<path>`::
+The path on ZooKeeper to list.
++
+*Example*: `/collections/mycollection`
+
+`-z <zkHost>`::
+The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`.
++
+*Example*: `-z 123.321.23.43:2181`
An example of this command with the parameters is:
@@ -716,16 +795,17 @@ An example of this command with the parameters is:
Use the `zk mkroot` command to create a znode. The primary use-case for this command to support ZooKeeper's "chroot" concept. However, it can also be used to create arbitrary paths.
[[SolrControlScriptReference-AvailableParameters.9]]
-==== Available Parameters
+==== Create znode Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`<path>`::
+The path on ZooKeeper to create. Intermediate znodes will be created if necessary. A leading slash is assumed even if not specified.
++
+*Example*: `/solr`
-[cols="20,40,40",options="header"]
-|===
-|Parameter |Description |Example
-|<path> |The path on ZooKeeper to create. Intermediate znodes will be created if necessary. A leading slash is assumed even if not specified. |`/solr`
-|-z <zkHost> |The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`. |`-z 123.321.23.43:2181`
-|===
+`-z <zkHost>`::
+The ZooKeeper connection string. Unnecessary if ZK_HOST is defined in `solr.in.sh` or `solr.in.cmd`.
++
+*Example*: `-z 123.321.23.43:2181`
Examples of this command:
[14/27] lucene-solr:feature/autoscaling: SOLR-10907: add
@SuppressWarnings("resource") in ExpandComponent
Posted by sh...@apache.org.
SOLR-10907: add @SuppressWarnings("resource") in ExpandComponent
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/945bf8fa
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/945bf8fa
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/945bf8fa
Branch: refs/heads/feature/autoscaling
Commit: 945bf8fa82538d173d26a80a38e55141ffd0873f
Parents: 0dad305
Author: Christine Poerschke <cp...@apache.org>
Authored: Mon Jun 26 20:15:26 2017 +0100
Committer: Christine Poerschke <cp...@apache.org>
Committed: Mon Jun 26 20:33:02 2017 +0100
----------------------------------------------------------------------
.../java/org/apache/solr/handler/component/ExpandComponent.java | 2 ++
1 file changed, 2 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/945bf8fa/solr/core/src/java/org/apache/solr/handler/component/ExpandComponent.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/handler/component/ExpandComponent.java b/solr/core/src/java/org/apache/solr/handler/component/ExpandComponent.java
index 8b4fac1..10c5b13 100644
--- a/solr/core/src/java/org/apache/solr/handler/component/ExpandComponent.java
+++ b/solr/core/src/java/org/apache/solr/handler/component/ExpandComponent.java
@@ -216,6 +216,7 @@ public class ExpandComponent extends SearchComponent implements PluginInfoInitia
if(CollapsingQParserPlugin.HINT_TOP_FC.equals(hint)) {
Map<String, UninvertingReader.Type> mapping = new HashMap();
mapping.put(field, UninvertingReader.Type.SORTED);
+ @SuppressWarnings("resource")
UninvertingReader uninvertingReader = new UninvertingReader(new ReaderWrapper(searcher.getSlowAtomicReader(), field), mapping);
values = uninvertingReader.getSortedDocValues(field);
} else {
@@ -386,6 +387,7 @@ public class ExpandComponent extends SearchComponent implements PluginInfoInitia
if(CollapsingQParserPlugin.HINT_TOP_FC.equals(hint)) {
Map<String, UninvertingReader.Type> mapping = new HashMap();
mapping.put(field, UninvertingReader.Type.SORTED);
+ @SuppressWarnings("resource")
UninvertingReader uninvertingReader = new UninvertingReader(new ReaderWrapper(searcher.getSlowAtomicReader(), field), mapping);
values = uninvertingReader.getSortedDocValues(field);
} else {
[11/27] lucene-solr:feature/autoscaling: SOLR-10824: fixing stats
tests: ignore local scores from query result cache.
Posted by sh...@apache.org.
SOLR-10824: fixing stats tests: ignore local scores from query result cache.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/7c448623
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/7c448623
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/7c448623
Branch: refs/heads/feature/autoscaling
Commit: 7c448623ccb1d7284f72144bb69e2998051f75ab
Parents: e4a7fc5
Author: Mikhail Khludnev <mk...@apache.org>
Authored: Mon Jun 26 12:11:34 2017 +0300
Committer: Mikhail Khludnev <mk...@apache.org>
Committed: Mon Jun 26 12:11:51 2017 +0300
----------------------------------------------------------------------
.../test/org/apache/solr/search/stats/TestDefaultStatsCache.java | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/7c448623/solr/core/src/test/org/apache/solr/search/stats/TestDefaultStatsCache.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/search/stats/TestDefaultStatsCache.java b/solr/core/src/test/org/apache/solr/search/stats/TestDefaultStatsCache.java
index 88300ba..f577387 100644
--- a/solr/core/src/test/org/apache/solr/search/stats/TestDefaultStatsCache.java
+++ b/solr/core/src/test/org/apache/solr/search/stats/TestDefaultStatsCache.java
@@ -73,7 +73,7 @@ public class TestDefaultStatsCache extends BaseDistributedSearchTestCase {
commit();
if (aDocId != null) {
- dfQuery("q", "id:"+aDocId,"debugQuery", "true", "fl", "*,score");
+ dfQuery("q", "{!cache=false}id:"+aDocId,"debugQuery", "true", "fl", "*,score");
}
dfQuery("q", "a_t:one a_t:four", "debugQuery", "true", "fl", "*,score");
}
[13/27] lucene-solr:feature/autoscaling: SOLR-10823: correct
CHANGES.txt entry section (7.0.0 instead of 6.7.0)
Posted by sh...@apache.org.
SOLR-10823: correct CHANGES.txt entry section (7.0.0 instead of 6.7.0)
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/0dad3051
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/0dad3051
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/0dad3051
Branch: refs/heads/feature/autoscaling
Commit: 0dad3051936210c7aeb405520bfc3e7991a0f944
Parents: 44860bd
Author: Christine Poerschke <cp...@apache.org>
Authored: Mon Jun 26 20:12:22 2017 +0100
Committer: Christine Poerschke <cp...@apache.org>
Committed: Mon Jun 26 20:12:22 2017 +0100
----------------------------------------------------------------------
solr/CHANGES.txt | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/0dad3051/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 5b82f1e..d83b4ab 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -336,6 +336,8 @@ Other Changes
increase the visibility of builder elements to be protected so extending the builder, and the clients is possible.
(Jason Gerlowski, Anshum Gupta)
+* SOLR-10823: Add reporting period to SolrMetricReporter base class. (Christine Poerschke)
+
================== 6.7.0 ==================
Consult the LUCENE_CHANGES.txt file for additional, low level, changes in this release.
@@ -517,8 +519,6 @@ Other Changes
with point fields and provides control over dynamic fields used for the raw amount and currency
code sub-fields. (hossman, Steve Rowe)
-* SOLR-10823: Add reporting period to SolrMetricReporter base class. (Christine Poerschke)
-
================== 6.6.1 ==================
Bug Fixes
[02/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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 5604a93..0000000
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
+++ /dev/null
@@ -1,1076 +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="*_s_ns" type="string" indexed="true" stored="false" />
- <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_l_ns" type="long" indexed="true" stored="false"/>
- <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:
- amountLongSuffix: Required. Refers to a dynamic field for the raw amount sub-field.
- The dynamic field must have a field type that extends LongValueFieldType.
- Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
- codeStrSuffix: Required. Refers to a dynamic field for the currency code sub-field.
- The dynamic field must have a field type that extends StrField.
- Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
- defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
- 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.CurrencyFieldType" amountLongSuffix="_l_ns" codeStrSuffix="_s_ns"
- 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/e4a7fc59/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/e4a7fc59/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
-
[17/27] lucene-solr:feature/autoscaling: SOLR-10946: Randomize the
usage of Points based numerics in solrj test schemas
Posted by sh...@apache.org.
SOLR-10946: Randomize the usage of Points based numerics in solrj test schemas
This includes an @SuppressPointFields for SOLR-10960
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/14a0b4fa
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/14a0b4fa
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/14a0b4fa
Branch: refs/heads/feature/autoscaling
Commit: 14a0b4fa538dad949bdbdbf2e1f9115c7528e403
Parents: bee8d7c
Author: Chris Hostetter <ho...@apache.org>
Authored: Mon Jun 26 15:49:55 2017 -0700
Committer: Chris Hostetter <ho...@apache.org>
Committed: Mon Jun 26 15:49:55 2017 -0700
----------------------------------------------------------------------
solr/CHANGES.txt | 3 +++
.../collection1/conf/schema-replication1.xml | 2 +-
.../solrj/solr/collection1/conf/schema-sql.xml | 20 ++++++++---------
.../solrj/solr/collection1/conf/schema.xml | 20 ++++++++---------
.../solrj/solr/configsets/ml/conf/schema.xml | 20 ++++++++---------
.../solr/configsets/shared/conf/schema.xml | 2 +-
.../solr/configsets/streaming/conf/schema.xml | 20 ++++++++---------
.../solrj/solr/multicore/core0/conf/schema.xml | 2 +-
.../solrj/solr/multicore/core1/conf/schema.xml | 2 +-
.../client/solrj/io/stream/JDBCStreamTest.java | 2 ++
.../solr/client/solrj/request/SchemaTest.java | 23 +++++++++++---------
11 files changed, 62 insertions(+), 54 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index ff51bd7..8e9bd3d 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -332,6 +332,9 @@ Other Changes
* SOLR-10823: Add reporting period to SolrMetricReporter base class. (Christine Poerschke)
+* SOLR-10807: Randomize Points based numeric field types in (more) test schemas
+ - SOLR-10946: Randomize the usage of Points based numerics in solrj test schemas (hossman)
+
================== 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/14a0b4fa/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-replication1.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-replication1.xml b/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-replication1.xml
index eeb51bd..db9ecd6 100644
--- a/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-replication1.xml
+++ b/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-replication1.xml
@@ -27,7 +27,7 @@
<schema name="test" version="1.2">
- <fieldType name="integer" class="solr.TrieIntField" precisionStep="0"/>
+ <fieldType name="integer" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0"/>
<fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
<field name="id" type="string" indexed="true" stored="true" multiValued="false" required="false"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-sql.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-sql.xml b/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-sql.xml
index f3187ec..8cdc1f0 100644
--- a/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-sql.xml
+++ b/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-sql.xml
@@ -40,17 +40,17 @@
-->
- <fieldType name="int" docValues="true" class="solr.TrieIntField" precisionStep="0" omitNorms="true"
+ <fieldType name="int" docValues="true" class="${solr.tests.IntegerFieldType}" precisionStep="0" omitNorms="true"
positionIncrementGap="0"/>
- <fieldType name="float" docValues="true" class="solr.TrieFloatField" precisionStep="0" omitNorms="true"
+ <fieldType name="float" docValues="true" class="${solr.tests.FloatFieldType}" precisionStep="0" omitNorms="true"
positionIncrementGap="0"/>
- <fieldType name="long" docValues="true" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="long" docValues="true" class="${solr.tests.LongFieldType}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<!-- numeric field types that manipulate the value into
a string value that isn't human readable in it's internal form,
@@ -119,8 +119,8 @@
<!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
seconds part (.999) is optional.
-->
- <fieldtype name="date" class="solr.TrieDateField" precisionStep="0"/>
- <fieldtype name="tdate" class="solr.TrieDateField" precisionStep="6"/>
+ <fieldtype name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0"/>
+ <fieldtype name="tdate" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="6"/>
<!-- solr.TextField allows the specification of custom
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml b/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml
index 1886681..94fc2ed 100644
--- a/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml
+++ b/solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml
@@ -33,15 +33,15 @@
behavior of the fieldType.
-->
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<!-- Field type demonstrating an Analyzer failure -->
<fieldType name="failtype1" class="solr.TextField">
@@ -94,8 +94,8 @@
<!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
seconds part (.999) is optional.
-->
- <fieldType name="date" class="solr.TrieDateField" precisionStep="0"/>
- <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6"/>
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0"/>
+ <fieldType name="tdate" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="6"/>
<!-- solr.TextField allows the specification of custom
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/schema.xml b/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/schema.xml
index c70b9fd..0c9ee9c 100644
--- a/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/schema.xml
+++ b/solr/solrj/src/test-files/solrj/solr/configsets/ml/conf/schema.xml
@@ -27,15 +27,15 @@
<schema name="test" version="1.6">
- <fieldType name="int" docValues="true" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="float" docValues="true" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="int" docValues="true" class="${solr.tests.IntegerFieldType}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="float" docValues="true" class="${solr.tests.FloatFieldType}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
@@ -45,8 +45,8 @@
<!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
seconds part (.999) is optional.
-->
- <fieldtype name="date" class="solr.TrieDateField" precisionStep="0"/>
- <fieldtype name="tdate" class="solr.TrieDateField" precisionStep="6"/>
+ <fieldtype name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0"/>
+ <fieldtype name="tdate" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="6"/>
<field name="id" type="string" indexed="true" stored="true" multiValued="false" required="false"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/schema.xml b/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/schema.xml
index 15fc982..a3559b9 100644
--- a/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/schema.xml
+++ b/solr/solrj/src/test-files/solrj/solr/configsets/shared/conf/schema.xml
@@ -46,7 +46,7 @@
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
<!-- general -->
<field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml b/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml
index f17da41..1a3b96f 100644
--- a/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml
+++ b/solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml
@@ -40,15 +40,15 @@
-->
- <fieldType name="int" docValues="true" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="float" docValues="true" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="long" docValues="true" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="int" docValues="true" class="${solr.tests.IntegerFieldType}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="float" docValues="true" class="${solr.tests.FloatFieldType}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="long" docValues="true" class="${solr.tests.LongFieldType}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
@@ -115,8 +115,8 @@
<!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
seconds part (.999) is optional.
-->
- <fieldtype name="date" class="solr.TrieDateField" precisionStep="0" docValues="true"/>
- <fieldtype name="tdate" class="solr.TrieDateField" precisionStep="6" docValues="true"/>
+ <fieldtype name="date" class="${solr.tests.DateFieldType}" precisionStep="0" docValues="true"/>
+ <fieldtype name="tdate" class="${solr.tests.DateFieldType}" precisionStep="6" docValues="true"/>
<!-- solr.TextField allows the specification of custom
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/schema.xml b/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/schema.xml
index 4899eab..68c251b 100644
--- a/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/schema.xml
+++ b/solr/solrj/src/test-files/solrj/solr/multicore/core0/conf/schema.xml
@@ -19,7 +19,7 @@
<schema name="example core zero" version="1.1">
<fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
<!-- general -->
<field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/>
<field name="type" type="string" indexed="true" stored="true" multiValued="false" />
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/schema.xml b/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/schema.xml
index 260b106..9f4cde8 100644
--- a/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/schema.xml
+++ b/solr/solrj/src/test-files/solrj/solr/multicore/core1/conf/schema.xml
@@ -19,7 +19,7 @@
<schema name="example core one" version="1.1">
<fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
<!-- general -->
<field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/JDBCStreamTest.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/JDBCStreamTest.java b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/JDBCStreamTest.java
index 8813f24..501c6dd 100644
--- a/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/JDBCStreamTest.java
+++ b/solr/solrj/src/test/org/apache/solr/client/solrj/io/stream/JDBCStreamTest.java
@@ -41,6 +41,7 @@ import org.apache.solr.client.solrj.request.CollectionAdminRequest;
import org.apache.solr.client.solrj.request.UpdateRequest;
import org.apache.solr.cloud.AbstractDistribZkTestBase;
import org.apache.solr.cloud.SolrCloudTestCase;
+import org.apache.solr.SolrTestCaseJ4.SuppressPointFields;
import org.junit.AfterClass;
import org.junit.Before;
import org.junit.BeforeClass;
@@ -49,6 +50,7 @@ import org.junit.Test;
/**
*/
+@SuppressPointFields(bugUrl="https://issues.apache.org/jira/browse/SOLR-10960")
@LuceneTestCase.SuppressCodecs({"Lucene3x", "Lucene40","Lucene41","Lucene42","Lucene45"})
public class JDBCStreamTest extends SolrCloudTestCase {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/14a0b4fa/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java b/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java
index aded373..4f64009 100644
--- a/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java
+++ b/solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java
@@ -636,8 +636,7 @@ public class SchemaTest extends RestTestBase {
public void addFieldTypeShouldntBeCalledTwiceWithTheSameName() throws Exception {
Map<String, Object> fieldTypeAttributes = new LinkedHashMap<>();
fieldTypeAttributes.put("name", "failureInt");
- fieldTypeAttributes.put("class", "solr.TrieIntField");
- fieldTypeAttributes.put("precisionStep", 0);
+ fieldTypeAttributes.put("class", RANDOMIZED_NUMERIC_FIELDTYPES.get(Integer.class));
fieldTypeAttributes.put("omitNorms", true);
fieldTypeAttributes.put("positionIncrementGap", 0);
FieldTypeDefinition fieldTypeDefinition = new FieldTypeDefinition();
@@ -657,8 +656,7 @@ public class SchemaTest extends RestTestBase {
Map<String, Object> fieldTypeAttributes = new LinkedHashMap<>();
String fieldTypeName = "delInt";
fieldTypeAttributes.put("name", fieldTypeName);
- fieldTypeAttributes.put("class", "solr.TrieIntField");
- fieldTypeAttributes.put("precisionStep", 0);
+ fieldTypeAttributes.put("class", RANDOMIZED_NUMERIC_FIELDTYPES.get(Integer.class));
fieldTypeAttributes.put("omitNorms", true);
fieldTypeAttributes.put("positionIncrementGap", 0);
FieldTypeDefinition fieldTypeDefinition = new FieldTypeDefinition();
@@ -699,12 +697,15 @@ public class SchemaTest extends RestTestBase {
@Test
public void testReplaceFieldTypeAccuracy() throws Exception {
+ // a fixed value for comparison after update, be contraian from the randomized 'default'
+ final boolean useDv = Boolean.getBoolean(NUMERIC_DOCVALUES_SYSPROP);
+
// Given
Map<String, Object> fieldTypeAttributes = new LinkedHashMap<>();
String fieldTypeName = "replaceInt";
fieldTypeAttributes.put("name", fieldTypeName);
- fieldTypeAttributes.put("class", "solr.TrieIntField");
- fieldTypeAttributes.put("precisionStep", 0);
+ fieldTypeAttributes.put("class", RANDOMIZED_NUMERIC_FIELDTYPES.get(Integer.class));
+ fieldTypeAttributes.put("docValues", useDv);
fieldTypeAttributes.put("omitNorms", true);
fieldTypeAttributes.put("positionIncrementGap", 0);
FieldTypeDefinition fieldTypeDefinition = new FieldTypeDefinition();
@@ -715,7 +716,7 @@ public class SchemaTest extends RestTestBase {
assertValidSchemaResponse(addFieldTypeResponse);
// When : update the field definition
- fieldTypeAttributes.put("precisionStep", 1);
+ fieldTypeAttributes.put("positionIncrementGap", 42);
fieldTypeAttributes.put("omitNorms", false);
FieldTypeDefinition replaceFieldTypeDefinition = new FieldTypeDefinition();
replaceFieldTypeDefinition.setAttributes(fieldTypeAttributes);
@@ -731,10 +732,12 @@ public class SchemaTest extends RestTestBase {
FieldTypeRepresentation replacedFieldTypeRepresentation = newFieldTypeResponse.getFieldType();
Map<String, Object> replacedFieldTypeAttributes = replacedFieldTypeRepresentation.getAttributes();
assertThat(fieldTypeName, is(equalTo(replacedFieldTypeAttributes.get("name"))));
- assertThat("solr.TrieIntField", is(equalTo(replacedFieldTypeAttributes.get("class"))));
+ assertThat( RANDOMIZED_NUMERIC_FIELDTYPES.get(Integer.class),
+ is(equalTo(replacedFieldTypeAttributes.get("class"))));
assertThat(false, is(equalTo(replacedFieldTypeAttributes.get("omitNorms"))));
- assertThat("1", is(equalTo(replacedFieldTypeAttributes.get("precisionStep"))));
- assertThat("0", is(equalTo(replacedFieldTypeAttributes.get("positionIncrementGap"))));
+ assertThat("42", is(equalTo(replacedFieldTypeAttributes.get("positionIncrementGap"))));
+ // should be unchanged...
+ assertThat(useDv, is(equalTo(replacedFieldTypeAttributes.get("docValues"))));
}
@Test
[03/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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
[15/27] lucene-solr:feature/autoscaling: Revert "SOLR-9981:
Performance improvements and bug fixes for the Analytics component"
Posted by sh...@apache.org.
Revert "SOLR-9981: Performance improvements and bug fixes for the Analytics component"
This reverts commit a5dce163eb09dcc0eb7f7eb81d692bf3d19964a3.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/bee8d7cc
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/bee8d7cc
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/bee8d7cc
Branch: refs/heads/feature/autoscaling
Commit: bee8d7ccb32bc23bd808f729493631b60a64bffb
Parents: 288ab09
Author: Dennis Gove <dp...@gmail.com>
Authored: Mon Jun 26 13:51:28 2017 -0400
Committer: Dennis Gove <dp...@gmail.com>
Committed: Mon Jun 26 17:33:26 2017 -0400
----------------------------------------------------------------------
solr/CHANGES.txt | 6 ---
.../accumulator/FacetingAccumulator.java | 24 ++----------
.../solr/analytics/expression/Expression.java | 15 ++------
.../statistics/MinMaxStatsCollector.java | 23 +++--------
.../statistics/NumericStatsCollector.java | 8 ++--
.../StatsCollectorSupplierFactory.java | 14 ++-----
.../analytics/requestFiles/facetSorting.txt | 4 --
.../analytics/requestXMLFiles/facetSorting.xml | 14 -------
.../collection1/conf/solrconfig-analytics.xml | 40 --------------------
.../solr/collection1/conf/solrconfig-basic.xml | 40 ++++++++++++++++++++
.../org/apache/solr/analytics/NoFacetTest.java | 2 +-
.../analytics/expression/ExpressionTest.java | 2 +-
.../facet/AbstractAnalyticsFacetTest.java | 15 --------
.../solr/analytics/facet/FacetSortingTest.java | 40 --------------------
.../analytics/facet/FieldFacetExtrasTest.java | 2 +-
.../solr/analytics/facet/FieldFacetTest.java | 21 +++++-----
.../solr/analytics/facet/QueryFacetTest.java | 2 +-
.../solr/analytics/facet/RangeFacetTest.java | 2 +-
.../util/valuesource/FunctionTest.java | 2 +-
19 files changed, 73 insertions(+), 203 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index d83b4ab..ff51bd7 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -227,12 +227,6 @@ Optimizations
* SOLR-10727: Avoid polluting the filter cache for certain types of faceting (typically ranges) when
the base docset is empty. (David Smiley)
-* SOLR-9981: Performance improvements and bug fixes for the Analytics component. Performance fix that
- stops the reading of ALL lucene segments over and again for each stats collector. The AtomicReaderContext
- that refers to the "current " segment is reused. This fix shows an improvement of about 25% in query
- time for a dataset of ~10M (=9.8M) records. Given the nature of the fix, the improvement should get
- better as the dataset increases. Fix for the NPE during comparison (Houston Putman)
-
Other Changes
----------------------
* SOLR-10236: Removed FieldType.getNumericType(). Use getNumberType() instead. (Tomás Fernández Löbbe)
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/java/org/apache/solr/analytics/accumulator/FacetingAccumulator.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/java/org/apache/solr/analytics/accumulator/FacetingAccumulator.java b/solr/contrib/analytics/src/java/org/apache/solr/analytics/accumulator/FacetingAccumulator.java
index 92add72..d8828a6 100644
--- a/solr/contrib/analytics/src/java/org/apache/solr/analytics/accumulator/FacetingAccumulator.java
+++ b/solr/contrib/analytics/src/java/org/apache/solr/analytics/accumulator/FacetingAccumulator.java
@@ -28,7 +28,7 @@ import java.util.List;
import java.util.Map;
import java.util.Map.Entry;
import java.util.Set;
-import java.util.HashMap;
+import java.util.TreeMap;
import com.google.common.collect.Iterables;
import org.apache.lucene.index.LeafReaderContext;
@@ -98,7 +98,7 @@ public class FacetingAccumulator extends BasicAccumulator implements FacetValueA
List<RangeFacetRequest> rangeFreqs = request.getRangeFacets();
List<QueryFacetRequest> queryFreqs = request.getQueryFacets();
- this.fieldFacetExpressions = new HashMap<>();
+ this.fieldFacetExpressions = new TreeMap<>();
this.rangeFacetExpressions = new LinkedHashMap<>(rangeFreqs.size());
this.queryFacetExpressions = new LinkedHashMap<>(queryFreqs.size());
this.fieldFacetCollectors = new LinkedHashMap<>(fieldFreqs.size());
@@ -120,8 +120,8 @@ public class FacetingAccumulator extends BasicAccumulator implements FacetValueA
final SchemaField ff = fr.getField();
final FieldFacetAccumulator facc = FieldFacetAccumulator.create(searcher, this, ff);
facetAccumulators.add(facc);
- fieldFacetExpressions.put(freq.getName(), new HashMap<String, Expression[]>() );
- fieldFacetCollectors.put(freq.getName(), new HashMap<String,StatsCollector[]>());
+ fieldFacetExpressions.put(freq.getName(), new TreeMap<String, Expression[]>() );
+ fieldFacetCollectors.put(freq.getName(), new TreeMap<String,StatsCollector[]>());
}
/**
* For each range and query facet request add a bucket to the corresponding
@@ -299,22 +299,6 @@ public class FacetingAccumulator extends BasicAccumulator implements FacetValueA
@Override
public int compare(Entry<String,Expression[]> o1, Entry<String,Expression[]> o2) {
-
- // Handle nulls. Null is treated as an infinitely big number so that in case of ASCENDING sorts,
- // Nulls will appear last. In case of DESC sorts, Nulls will appear last.
- boolean firstIsNull = false;
- if (o1 == null || o1.getValue() == null || o1.getValue()[comparatorExpressionPlace] == null)
- firstIsNull = true;
- boolean secondIsNull = false;
- if (o2 == null || o2.getValue() == null || o2.getValue()[comparatorExpressionPlace] == null)
- secondIsNull = true;
- if (firstIsNull && secondIsNull)
- return 0;
- else if (firstIsNull)
- return 1;
- else if (secondIsNull)
- return -1;
-
return comp.compare(o1.getValue()[comparatorExpressionPlace], o2.getValue()[comparatorExpressionPlace]);
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/java/org/apache/solr/analytics/expression/Expression.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/java/org/apache/solr/analytics/expression/Expression.java b/solr/contrib/analytics/src/java/org/apache/solr/analytics/expression/Expression.java
index c0c3da3..ba26d9a 100644
--- a/solr/contrib/analytics/src/java/org/apache/solr/analytics/expression/Expression.java
+++ b/solr/contrib/analytics/src/java/org/apache/solr/analytics/expression/Expression.java
@@ -29,19 +29,10 @@ public abstract class Expression {
public Comparator<Expression> comparator(final FacetSortDirection direction) {
return (a, b) -> {
- boolean aIsNull = a.getValue() == null;
- boolean bIsNull = b.getValue() == null;
-
- if (aIsNull && bIsNull) return 0;
-
- if( direction == FacetSortDirection.ASCENDING ){ // nulls are last for ASC sort
- return aIsNull ? 1
- : bIsNull ? -1
- : a.getValue().compareTo(b.getValue());
+ if( direction == FacetSortDirection.ASCENDING ){
+ return a.getValue().compareTo(b.getValue());
} else {
- return aIsNull ? -1
- : bIsNull ? 1
- : b.getValue().compareTo(a.getValue());
+ return b.getValue().compareTo(a.getValue());
}
};
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/MinMaxStatsCollector.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/MinMaxStatsCollector.java b/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/MinMaxStatsCollector.java
index f41a032..c21b045 100644
--- a/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/MinMaxStatsCollector.java
+++ b/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/MinMaxStatsCollector.java
@@ -37,32 +37,19 @@ public class MinMaxStatsCollector implements StatsCollector{
protected MutableValue value;
protected final Set<String> statsList;
protected final ValueSource source;
+ protected FunctionValues function;
protected ValueFiller valueFiller;
- private CollectorState state;
- public MinMaxStatsCollector(ValueSource source, Set<String> statsList, CollectorState state) {
+ public MinMaxStatsCollector(ValueSource source, Set<String> statsList) {
this.source = source;
this.statsList = statsList;
- this.state = state;
}
public void setNextReader(LeafReaderContext context) throws IOException {
- state.setNextReader(source, context);
- valueFiller = state.function.getValueFiller();
+ function = source.getValues(null, context);
+ valueFiller = function.getValueFiller();
value = valueFiller.getValue();
}
-
- public static class CollectorState {
- FunctionValues function;
- LeafReaderContext context = null;
-
- public void setNextReader(ValueSource source, LeafReaderContext context) throws IOException {
- if (this.context != context) {
- this.context = context;
- this.function = source.getValues(null, context);
- }
- }
- }
public void collect(int doc) throws IOException {
valueFiller.fillValue(doc);
@@ -114,7 +101,7 @@ public class MinMaxStatsCollector implements StatsCollector{
@Override
public FunctionValues getFunction() {
- return state.function;
+ return function;
}
public String valueSourceString() {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/NumericStatsCollector.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/NumericStatsCollector.java b/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/NumericStatsCollector.java
index 4b1ca22..1f22baa 100644
--- a/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/NumericStatsCollector.java
+++ b/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/NumericStatsCollector.java
@@ -29,16 +29,14 @@ public class NumericStatsCollector extends MinMaxStatsCollector {
protected double sumOfSquares = 0;
protected double mean = 0;
protected double stddev = 0;
- protected CollectorState state;
- public NumericStatsCollector(ValueSource source, Set<String> statsList, CollectorState state) {
- super(source, statsList, state);
- this.state = state;
+ public NumericStatsCollector(ValueSource source, Set<String> statsList) {
+ super(source, statsList);
}
public void collect(int doc) throws IOException {
super.collect(doc);
- double value = state.function.doubleVal(doc);
+ double value = function.doubleVal(doc);
sum += value;
sumOfSquares += (value * value);
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/StatsCollectorSupplierFactory.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/StatsCollectorSupplierFactory.java b/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/StatsCollectorSupplierFactory.java
index c7c91d4..e22362d 100644
--- a/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/StatsCollectorSupplierFactory.java
+++ b/solr/contrib/analytics/src/java/org/apache/solr/analytics/statistics/StatsCollectorSupplierFactory.java
@@ -33,7 +33,6 @@ import org.apache.lucene.queries.function.valuesource.IntFieldSource;
import org.apache.lucene.queries.function.valuesource.LongFieldSource;
import org.apache.solr.analytics.expression.ExpressionFactory;
import org.apache.solr.analytics.request.ExpressionRequest;
-import org.apache.solr.analytics.statistics.MinMaxStatsCollector.CollectorState;
import org.apache.solr.analytics.util.AnalyticsParams;
import org.apache.solr.analytics.util.valuesource.AbsoluteValueDoubleFunction;
import org.apache.solr.analytics.util.valuesource.AddDoubleFunction;
@@ -214,32 +213,25 @@ public class StatsCollectorSupplierFactory {
}
}
}
-
- final CollectorState states[] = new CollectorState[statsArr.length];
- for (int count = 0; count < statsArr.length; count++) {
- states[count] = new CollectorState();
- }
// Making the Supplier
return new Supplier<StatsCollector[]>() {
- private final CollectorState collectorState[] = states;
-
public StatsCollector[] get() {
StatsCollector[] collectors = new StatsCollector[statsArr.length];
for (int count = 0; count < statsArr.length; count++) {
if(numericBools[count]){
- StatsCollector sc = new NumericStatsCollector(sourceArr[count], statsArr[count], collectorState[count]);
+ StatsCollector sc = new NumericStatsCollector(sourceArr[count], statsArr[count]);
if(uniqueBools[count]) sc = new UniqueStatsCollector(sc);
if(medianBools[count]) sc = new MedianStatsCollector(sc);
if(percsArr[count]!=null) sc = new PercentileStatsCollector(sc,percsArr[count],percsNames[count]);
collectors[count]=sc;
} else if (dateBools[count]) {
- StatsCollector sc = new MinMaxStatsCollector(sourceArr[count], statsArr[count], collectorState[count]);
+ StatsCollector sc = new MinMaxStatsCollector(sourceArr[count], statsArr[count]);
if(uniqueBools[count]) sc = new UniqueStatsCollector(sc);
if(medianBools[count]) sc = new DateMedianStatsCollector(sc);
if(percsArr[count]!=null) sc = new PercentileStatsCollector(sc,percsArr[count],percsNames[count]);
collectors[count]=sc;
} else {
- StatsCollector sc = new MinMaxStatsCollector(sourceArr[count], statsArr[count], collectorState[count]);
+ StatsCollector sc = new MinMaxStatsCollector(sourceArr[count], statsArr[count]);
if(uniqueBools[count]) sc = new UniqueStatsCollector(sc);
if(medianBools[count]) sc = new MedianStatsCollector(sc);
if(percsArr[count]!=null) sc = new PercentileStatsCollector(sc,percsArr[count],percsNames[count]);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test-files/analytics/requestFiles/facetSorting.txt
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test-files/analytics/requestFiles/facetSorting.txt b/solr/contrib/analytics/src/test-files/analytics/requestFiles/facetSorting.txt
deleted file mode 100644
index 4663217..0000000
--- a/solr/contrib/analytics/src/test-files/analytics/requestFiles/facetSorting.txt
+++ /dev/null
@@ -1,4 +0,0 @@
-o.ar.s.min=min(double_dd)
-o.ar.s.max=max(long_ld)
-o.ar.ff=string_sd
-o.ar.ff.string_sd.sortstatistic=min
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test-files/analytics/requestXMLFiles/facetSorting.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test-files/analytics/requestXMLFiles/facetSorting.xml b/solr/contrib/analytics/src/test-files/analytics/requestXMLFiles/facetSorting.xml
deleted file mode 100644
index 54e698a..0000000
--- a/solr/contrib/analytics/src/test-files/analytics/requestXMLFiles/facetSorting.xml
+++ /dev/null
@@ -1,14 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<analyticsRequestEnvelope stats="true" olap="true">
- <analyticsRequest>
- <name>MinMax Request</name>
- <statistic>
- <expression>min(double(double_dd))</expression>
- <name>min</name>
- </statistic>
- <statistic>
- <expression>max(long(long_ld))</expression>
- <name>max</name>
- </statistic>
- </analyticsRequest>
- </analyticsRequestEnvelope>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test-files/solr/collection1/conf/solrconfig-analytics.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test-files/solr/collection1/conf/solrconfig-analytics.xml b/solr/contrib/analytics/src/test-files/solr/collection1/conf/solrconfig-analytics.xml
deleted file mode 100644
index 604bb17..0000000
--- a/solr/contrib/analytics/src/test-files/solr/collection1/conf/solrconfig-analytics.xml
+++ /dev/null
@@ -1,40 +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.
--->
-
-<config>
- <luceneMatchVersion>${tests.luceneMatchVersion:LATEST}</luceneMatchVersion>
- <dataDir>${solr.data.dir:}</dataDir>
- <xi:include href="solrconfig.snippet.randomindexconfig.xml" xmlns:xi="http://www.w3.org/2001/XInclude"/>
- <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.RAMDirectoryFactory}"/>
- <schemaFactory class="ClassicIndexSchemaFactory"/>
-
- <requestHandler name="standard" class="solr.StandardRequestHandler">
- <arr name="components">
- <str>query</str>
- <str>facet</str>
- <str>analytics</str>
- <str>highlight</str>
- <str>debug</str>
- <str>expand</str>
- </arr>
- </requestHandler>
-
- <searchComponent name="analytics" class="org.apache.solr.handler.component.AnalyticsComponent" />
-
-</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test-files/solr/collection1/conf/solrconfig-basic.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test-files/solr/collection1/conf/solrconfig-basic.xml b/solr/contrib/analytics/src/test-files/solr/collection1/conf/solrconfig-basic.xml
new file mode 100644
index 0000000..604bb17
--- /dev/null
+++ b/solr/contrib/analytics/src/test-files/solr/collection1/conf/solrconfig-basic.xml
@@ -0,0 +1,40 @@
+<?xml version="1.0" ?>
+
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<config>
+ <luceneMatchVersion>${tests.luceneMatchVersion:LATEST}</luceneMatchVersion>
+ <dataDir>${solr.data.dir:}</dataDir>
+ <xi:include href="solrconfig.snippet.randomindexconfig.xml" xmlns:xi="http://www.w3.org/2001/XInclude"/>
+ <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.RAMDirectoryFactory}"/>
+ <schemaFactory class="ClassicIndexSchemaFactory"/>
+
+ <requestHandler name="standard" class="solr.StandardRequestHandler">
+ <arr name="components">
+ <str>query</str>
+ <str>facet</str>
+ <str>analytics</str>
+ <str>highlight</str>
+ <str>debug</str>
+ <str>expand</str>
+ </arr>
+ </requestHandler>
+
+ <searchComponent name="analytics" class="org.apache.solr.handler.component.AnalyticsComponent" />
+
+</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java
index 7b67d00..ae935fb 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java
@@ -60,7 +60,7 @@ public class NoFacetTest extends AbstractAnalyticsStatsTest {
@BeforeClass
public static void beforeClass() throws Exception {
- initCore("solrconfig-analytics.xml","schema-analytics.xml");
+ initCore("solrconfig-basic.xml","schema-analytics.xml");
h.update("<delete><query>*:*</query></delete>");
defaults.put("int_id", new Integer(0));
defaults.put("long_ld", new Long(0));
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test/org/apache/solr/analytics/expression/ExpressionTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/expression/ExpressionTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/expression/ExpressionTest.java
index 245ea1c..4a3276b 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/expression/ExpressionTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/expression/ExpressionTest.java
@@ -48,7 +48,7 @@ public class ExpressionTest extends AbstractAnalyticsStatsTest {
@BeforeClass
public static void beforeClass() throws Exception {
- initCore("solrconfig-analytics.xml", "schema-analytics.xml");
+ initCore("solrconfig-basic.xml", "schema-analytics.xml");
h.update("<delete><query>*:*</query></delete>");
for (int j = 0; j < NUM_LOOPS; ++j) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java
index dd331fd..dab68a3 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java
@@ -312,19 +312,4 @@ public class AbstractAnalyticsFacetTest extends SolrTestCaseJ4 {
IOUtils.closeWhileHandlingException(file, in);
}
}
-
- protected void removeNodes(String xPath, List<Double> string) throws XPathExpressionException {
- NodeList missingNodes = getNodes(xPath);
- List<Double> result = new ArrayList<Double>();
- for (int idx = 0; idx < missingNodes.getLength(); ++idx) {
- result.add(Double.parseDouble(missingNodes.item(idx).getTextContent()));
- }
- string.removeAll(result);
- }
-
- protected NodeList getNodes(String xPath) throws XPathExpressionException {
- StringBuilder sb = new StringBuilder(xPath);
- return (NodeList) xPathFact.newXPath().compile(sb.toString()).evaluate(doc, XPathConstants.NODESET);
- }
-
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FacetSortingTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FacetSortingTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FacetSortingTest.java
deleted file mode 100644
index 0751b63..0000000
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FacetSortingTest.java
+++ /dev/null
@@ -1,40 +0,0 @@
-package org.apache.solr.analytics.facet;
-
-import org.apache.lucene.util.LuceneTestCase.SuppressCodecs;
-import org.apache.solr.analytics.AbstractAnalyticsStatsTest;
-import org.apache.solr.analytics.expression.ExpressionTest;
-import org.junit.BeforeClass;
-import org.junit.Test;
-
-@SuppressCodecs({"Lucene3x","Lucene40","Lucene41","Lucene42","Appending","Asserting"})
-public class FacetSortingTest extends AbstractAnalyticsStatsTest {
- private static String fileName = "/analytics/requestFiles/facetSorting.txt";
-
- @BeforeClass
- public static void beforeClass() throws Exception {
- initCore("solrconfig-analytics.xml", "schema-analytics.xml");
- h.update("<delete><query>*:*</query></delete>");
-
- // The data set below is so generated that in bucket corresponding fieldFacet B, double_dd column has null values
- // and in bucket C corresponding to fieldFacet C has null values for column long_ld.
- // FieldFaceting occurs on string_sd field
- assertU(adoc("id", "1001", "string_sd", "A", "double_dd", "" + 3, "long_ld", "" + 1));
- assertU(adoc("id", "1002", "string_sd", "A", "double_dd", "" + 25, "long_ld", "" + 2));
- assertU(adoc("id", "1003", "string_sd", "B", "long_ld", "" + 3));
- assertU(adoc("id", "1004", "string_sd", "B", "long_ld", "" + 4));
- assertU(adoc("id", "1005", "string_sd", "C", "double_dd", "" + 17));
-
- assertU(commit());
- String response = h.query(request(fileToStringArr(ExpressionTest.class, fileName)));
- System.out.println("Response=" + response);
- setResponse(response);
- }
-
- @Test
- public void addTest() throws Exception {
- Double minResult = (Double) getStatResult("ar", "min", VAL_TYPE.DOUBLE);
- Long maxResult = (Long) getStatResult("ar", "max", VAL_TYPE.LONG);
- assertEquals(Double.valueOf(minResult), Double.valueOf(3.0));
- assertEquals(Long.valueOf(maxResult),Long.valueOf(4));
- }
-}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetExtrasTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetExtrasTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetExtrasTest.java
index afa0c3c..fc7df4b 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetExtrasTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetExtrasTest.java
@@ -44,7 +44,7 @@ public class FieldFacetExtrasTest extends AbstractAnalyticsFacetTest {
@BeforeClass
public static void beforeClass() throws Exception {
- initCore("solrconfig-analytics.xml","schema-analytics.xml");
+ initCore("solrconfig-basic.xml","schema-analytics.xml");
h.update("<delete><query>*:*</query></delete>");
//INT
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetTest.java
index 2230b02..bf67213 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/FieldFacetTest.java
@@ -24,7 +24,6 @@ import java.util.List;
import org.junit.Assert;
import org.junit.BeforeClass;
import org.junit.Test;
-import org.w3c.dom.Node;
public class FieldFacetTest extends AbstractAnalyticsFacetTest{
@@ -88,7 +87,7 @@ public class FieldFacetTest extends AbstractAnalyticsFacetTest{
@BeforeClass
public static void beforeClass() throws Exception {
- initCore("solrconfig-analytics.xml","schema-analytics.xml");
+ initCore("solrconfig-basic.xml","schema-analytics.xml");
h.update("<delete><query>*:*</query></delete>");
defaults.put("int", new Integer(0));
@@ -1038,33 +1037,31 @@ public class FieldFacetTest extends AbstractAnalyticsFacetTest{
public void missingFacetTest() throws Exception {
//int MultiDate
String xPath = "/response/lst[@name='stats']/lst[@name='missingf']/lst[@name='fieldFacets']/lst[@name='date_dtdm']/lst[@name='(MISSING)']";
- Node missingNodeXPath = getNode(xPath);
- assertNotNull(getRawResponse(), missingNodeXPath);
+ assertNotNull(getRawResponse(), getNode(xPath));
ArrayList<Double> string = getDoubleList("missingf", "fieldFacets", "date_dtdm", "double", "mean");
- super.removeNodes(xPath, string);
+ string.remove(0);
ArrayList<Double> stringTest = calculateNumberStat(multiDateTestStart, "mean");
assertEquals(getRawResponse(), string,stringTest);
-
+
//Int String
xPath = "/response/lst[@name='stats']/lst[@name='missingf']/lst[@name='fieldFacets']/lst[@name='string_sd']/lst[@name='(MISSING)']";
- missingNodeXPath = getNode(xPath);
- String missingNodeXPathStr = xPath;
- assertNotNull(getRawResponse(), missingNodeXPath);
+ assertNotNull(getRawResponse(), getNode(xPath));
xPath = "/response/lst[@name='stats']/lst[@name='missingf']/lst[@name='fieldFacets']/lst[@name='string_sd']/lst[@name='str0']";
assertNull(getRawResponse(), getNode(xPath));
-
List<Double> intString = getDoubleList("missingf", "fieldFacets", "string_sd", "double", "mean");
- removeNodes(missingNodeXPathStr, intString);
+ intString.remove(0);
ArrayList<Double> intStringTest = calculateNumberStat(intStringTestStart, "mean");
assertEquals(getRawResponse(), intString,intStringTest);
-
+
//Int Date
Collection<Double> intDate = getDoubleList("missingf", "fieldFacets", "date_dtd", "double", "mean");
ArrayList<ArrayList<Double>> intDateMissingTestStart = (ArrayList<ArrayList<Double>>) intDateTestStart.clone();
ArrayList<Double> intDateTest = calculateNumberStat(intDateMissingTestStart, "mean");
assertEquals(getRawResponse(),intDate,intDateTest);
+
+
}
private void checkStddevs(ArrayList<Double> list1, ArrayList<Double> list2) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/QueryFacetTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/QueryFacetTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/QueryFacetTest.java
index 99ce02d..f62a82b 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/QueryFacetTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/QueryFacetTest.java
@@ -35,7 +35,7 @@ public class QueryFacetTest extends AbstractAnalyticsFacetTest {
@BeforeClass
public static void beforeClass() throws Exception {
- initCore("solrconfig-analytics.xml","schema-analytics.xml");
+ initCore("solrconfig-basic.xml","schema-analytics.xml");
}
@SuppressWarnings("unchecked")
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/RangeFacetTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/RangeFacetTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/RangeFacetTest.java
index cf5e36b..cda8202 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/RangeFacetTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/RangeFacetTest.java
@@ -46,7 +46,7 @@ public class RangeFacetTest extends AbstractAnalyticsFacetTest {
@BeforeClass
public static void beforeClass() throws Exception {
- initCore("solrconfig-analytics.xml","schema-analytics.xml");
+ initCore("solrconfig-basic.xml","schema-analytics.xml");
h.update("<delete><query>*:*</query></delete>");
//INT
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/bee8d7cc/solr/contrib/analytics/src/test/org/apache/solr/analytics/util/valuesource/FunctionTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/util/valuesource/FunctionTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/util/valuesource/FunctionTest.java
index f9a9620..5981cc0 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/util/valuesource/FunctionTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/util/valuesource/FunctionTest.java
@@ -35,7 +35,7 @@ public class FunctionTest extends AbstractAnalyticsStatsTest {
@BeforeClass
public static void beforeClass() throws Exception {
- initCore("solrconfig-analytics.xml","schema-analytics.xml");
+ initCore("solrconfig-basic.xml","schema-analytics.xml");
h.update("<delete><query>*:*</query></delete>");
for (int j = 0; j < NUM_LOOPS; ++j) {
[06/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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
[24/27] lucene-solr:feature/autoscaling: SOLR-10272: Use _default
config set if config name is not specified with CREATE collection
Posted by sh...@apache.org.
SOLR-10272: Use _default config set if config name is not specified with CREATE collection
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/ee572b05
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/ee572b05
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/ee572b05
Branch: refs/heads/feature/autoscaling
Commit: ee572b052a9163d2884bad9e53cef52fc937bcbb
Parents: 93c96b0
Author: Ishan Chattopadhyaya <is...@apache.org>
Authored: Tue Jun 27 09:07:05 2017 +0530
Committer: Ishan Chattopadhyaya <is...@apache.org>
Committed: Tue Jun 27 09:07:05 2017 +0530
----------------------------------------------------------------------
solr/CHANGES.txt | 2 +
solr/bin/solr | 26 ++++----
solr/bin/solr.cmd | 12 ++--
.../apache/solr/cloud/CreateCollectionCmd.java | 65 ++++++++++++++++----
.../org/apache/solr/cloud/ZkController.java | 51 ++++++++++++++-
.../handler/admin/ConfigSetsHandlerApi.java | 2 +
.../apache/solr/servlet/SolrDispatchFilter.java | 6 +-
.../src/java/org/apache/solr/util/SolrCLI.java | 24 +++++---
.../solr/configsets/_default/conf/schema.xml | 37 +++++++++++
.../configsets/_default/conf/solrconfig.xml | 32 ++++++++++
.../solr/cloud/BaseCdcrDistributedZkTest.java | 4 +-
.../solr/cloud/BasicDistributedZk2Test.java | 2 +-
.../solr/cloud/BasicDistributedZkTest.java | 12 ++--
.../solr/cloud/ClusterStateUpdateTest.java | 2 +-
.../solr/cloud/CollectionsAPISolrJTest.java | 19 ++++++
.../org/apache/solr/cloud/ForceLeaderTest.java | 4 +-
.../apache/solr/cloud/HttpPartitionTest.java | 10 +--
.../cloud/LeaderFailoverAfterPartitionTest.java | 2 +-
.../LeaderInitiatedRecoveryOnCommitTest.java | 4 +-
...aderInitiatedRecoveryOnShardRestartTest.java | 2 +-
.../solr/cloud/ReplicationFactorTest.java | 6 +-
.../solr/cloud/ShardRoutingCustomTest.java | 2 +-
.../org/apache/solr/cloud/ShardSplitTest.java | 2 +-
.../apache/solr/cloud/TestConfigSetsAPI.java | 6 +-
.../cloud/TestOnReconnectListenerSupport.java | 2 +-
.../org/apache/solr/cloud/TestPullReplica.java | 8 +--
.../cloud/TestRandomRequestDistribution.java | 6 +-
.../cloud/TestSolrCloudWithKerberosAlt.java | 2 +-
.../org/apache/solr/cloud/TestTlogReplica.java | 8 +--
.../solr/cloud/UnloadDistributedZkTest.java | 4 +-
.../autoscaling/AutoScalingHandlerTest.java | 5 +-
.../solr/cloud/autoscaling/TestPolicyCloud.java | 6 +-
.../solr/cloud/hdfs/HdfsNNFailoverTest.java | 2 +-
.../HdfsWriteToMultipleCollectionsTest.java | 2 +-
.../apache/solr/cloud/hdfs/StressHdfsTest.java | 4 +-
.../handler/ThrowErrorOnInitRequestHandler.java | 4 ++
.../TestTrackingShardHandlerFactory.java | 2 +-
.../solr/cloud/autoscaling/package-info.java | 22 -------
.../cloud/AbstractFullDistribZkTestBase.java | 22 ++++---
39 files changed, 305 insertions(+), 128 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 76722fe..8d5c321 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -173,6 +173,8 @@ New Features
* 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)
+* SOLR-10272: Use _default config set if no collection.configName is specified with CREATE (Ishan Chattopadhyaya)
+
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/ee572b05/solr/bin/solr
----------------------------------------------------------------------
diff --git a/solr/bin/solr b/solr/bin/solr
index fff11ed..14f24eb 100755
--- a/solr/bin/solr
+++ b/solr/bin/solr
@@ -932,14 +932,12 @@ if [[ "$SCRIPT_CMD" == "create" || "$SCRIPT_CMD" == "create_core" || "$SCRIPT_CM
done
fi
- if [ -z "$CREATE_CONFDIR" ]; then
- CREATE_CONFDIR='_default'
- fi
-
- # validate the confdir arg
- if [[ ! -d "$SOLR_TIP/server/solr/configsets/$CREATE_CONFDIR" && ! -d "$CREATE_CONFDIR" ]]; then
- echo -e "\nSpecified configuration directory $CREATE_CONFDIR not found!\n"
- exit 1
+ # validate the confdir arg (if provided)
+ if ! [ -z "$CREATE_CONFDIR" ]; then
+ if [[ ! -d "$SOLR_TIP/server/solr/configsets/$CREATE_CONFDIR" && ! -d "$CREATE_CONFDIR" ]]; then
+ echo -e "\nSpecified configuration directory $CREATE_CONFDIR not found!\n"
+ exit 1
+ fi
fi
if [ -z "$CREATE_NAME" ]; then
@@ -948,11 +946,6 @@ if [[ "$SCRIPT_CMD" == "create" || "$SCRIPT_CMD" == "create_core" || "$SCRIPT_CM
exit 1
fi
- # If not defined, use the collection name for the name of the configuration in Zookeeper
- if [ -z "$CREATE_CONFNAME" ]; then
- CREATE_CONFNAME="$CREATE_NAME"
- fi
-
if [ -z "$CREATE_PORT" ]; then
for ID in `ps auxww | grep java | grep start\.jar | awk '{print $2}' | sort -r`
do
@@ -1661,6 +1654,11 @@ else
fi
fi
+# Set the default configset dir to be bootstrapped as _default
+if [ -z "$DEFAULT_CONFDIR" ]; then
+ DEFAULT_CONFDIR="$SOLR_SERVER_DIR/solr/configsets/_default/conf"
+fi
+
# This is quite hacky, but examples rely on a different log4j.properties
# so that we can write logs for examples to $SOLR_HOME/../logs
if [ -z "$SOLR_LOGS_DIR" ]; then
@@ -1911,7 +1909,7 @@ function launch_solr() {
"-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=$SOLR_HOME" "-Dsolr.data.home=$SOLR_DATA_HOME" "-Dsolr.install.dir=$SOLR_TIP" \
- "${LOG4J_CONFIG[@]}" "${SOLR_OPTS[@]}")
+ "-Dsolr.default.confdir=$DEFAULT_CONFDIR" "${LOG4J_CONFIG[@]}" "${SOLR_OPTS[@]}")
if [ "$SOLR_MODE" == "solrcloud" ]; then
IN_CLOUD_MODE=" in SolrCloud mode"
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/bin/solr.cmd
----------------------------------------------------------------------
diff --git a/solr/bin/solr.cmd b/solr/bin/solr.cmd
index 0c05baa..99bd815 100644
--- a/solr/bin/solr.cmd
+++ b/solr/bin/solr.cmd
@@ -1212,13 +1212,15 @@ IF "%JAVA_VENDOR%" == "IBM J9" (
set GCLOG_OPT="-Xloggc:!SOLR_LOGS_DIR!\solr_gc.log" -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=9 -XX:GCLogFileSize=20M
)
+IF "%DEFAULT_CONFDIR%"=="" set "DEFAULT_CONFDIR=%SOLR_SERVER_DIR%\solr\configsets\_default\conf"
+
IF "%FG%"=="1" (
REM run solr in the foreground
title "Solr-%SOLR_PORT%"
echo %SOLR_PORT%>"%SOLR_TIP%"\bin\solr-%SOLR_PORT%.port
"%JAVA%" %SERVEROPT% %SOLR_JAVA_MEM% %START_OPTS% %GCLOG_OPT% ^
-Dlog4j.configuration="%LOG4J_CONFIG%" -DSTOP.PORT=!STOP_PORT! -DSTOP.KEY=%STOP_KEY% ^
- -Dsolr.solr.home="%SOLR_HOME%" -Dsolr.install.dir="%SOLR_TIP%" ^
+ -Dsolr.solr.home="%SOLR_HOME%" -Dsolr.install.dir="%SOLR_TIP%" -Dsolr.default.confdir="%DEFAULT_CONFDIR%" ^
-Djetty.host=%SOLR_JETTY_HOST% -Djetty.port=%SOLR_PORT% -Djetty.home="%SOLR_SERVER_DIR%" ^
-Djava.io.tmpdir="%SOLR_SERVER_DIR%\tmp" -jar start.jar "%SOLR_JETTY_CONFIG%" "%SOLR_JETTY_ADDL_CONFIG%"
) ELSE (
@@ -1226,13 +1228,13 @@ IF "%FG%"=="1" (
"%JAVA%" %SERVEROPT% %SOLR_JAVA_MEM% %START_OPTS% %GCLOG_OPT% ^
-Dlog4j.configuration="%LOG4J_CONFIG%" -DSTOP.PORT=!STOP_PORT! -DSTOP.KEY=%STOP_KEY% ^
-Dsolr.log.muteconsole ^
- -Dsolr.solr.home="%SOLR_HOME%" -Dsolr.install.dir="%SOLR_TIP%" ^
+ -Dsolr.solr.home="%SOLR_HOME%" -Dsolr.install.dir="%SOLR_TIP%" -Dsolr.default.confdir="%DEFAULT_CONFDIR%" ^
-Djetty.host=%SOLR_JETTY_HOST% -Djetty.port=%SOLR_PORT% -Djetty.home="%SOLR_SERVER_DIR%" ^
-Djava.io.tmpdir="%SOLR_SERVER_DIR%\tmp" -jar start.jar "%SOLR_JETTY_CONFIG%" "%SOLR_JETTY_ADDL_CONFIG%" > "!SOLR_LOGS_DIR!\solr-%SOLR_PORT%-console.log"
echo %SOLR_PORT%>"%SOLR_TIP%"\bin\solr-%SOLR_PORT%.port
REM now wait to see Solr come online ...
- "%JAVA%" %SOLR_SSL_OPTS% %AUTHC_OPTS% %SOLR_ZK_CREDS_AND_ACLS% -Dsolr.install.dir="%SOLR_TIP%" ^
+ "%JAVA%" %SOLR_SSL_OPTS% %AUTHC_OPTS% %SOLR_ZK_CREDS_AND_ACLS% -Dsolr.install.dir="%SOLR_TIP%" -Dsolr.default.confdir="%DEFAULT_CONFDIR%"^
-Dlog4j.configuration="file:%DEFAULT_SERVER_DIR%\scripts\cloud-scripts\log4j.properties" ^
-classpath "%DEFAULT_SERVER_DIR%\solr-webapp\webapp\WEB-INF\lib\*;%DEFAULT_SERVER_DIR%\lib\ext\*" ^
org.apache.solr.util.SolrCLI status -maxWaitSecs 30 -solr !SOLR_URL_SCHEME!://%SOLR_TOOL_HOST%:%SOLR_PORT%/solr
@@ -1402,10 +1404,8 @@ IF "!CREATE_NAME!"=="" (
set "SCRIPT_ERROR=Name (-c) is a required parameter for %SCRIPT_CMD%"
goto invalid_cmd_line
)
-IF "!CREATE_CONFDIR!"=="" set CREATE_CONFDIR=_default
IF "!CREATE_NUM_SHARDS!"=="" set CREATE_NUM_SHARDS=1
IF "!CREATE_REPFACT!"=="" set CREATE_REPFACT=1
-IF "!CREATE_CONFNAME!"=="" set CREATE_CONFNAME=!CREATE_NAME!
REM Find a port that Solr is running on
if "!CREATE_PORT!"=="" (
@@ -1431,7 +1431,7 @@ if "%SCRIPT_CMD%"=="create_core" (
org.apache.solr.util.SolrCLI create_core -name !CREATE_NAME! -solrUrl !SOLR_URL_SCHEME!://%SOLR_TOOL_HOST%:!CREATE_PORT!/solr ^
-confdir !CREATE_CONFDIR! -configsetsDir "%SOLR_TIP%\server\solr\configsets"
) else (
- "%JAVA%" %SOLR_SSL_OPTS% %AUTHC_OPTS% %SOLR_ZK_CREDS_AND_ACLS% -Dsolr.install.dir="%SOLR_TIP%" ^
++ "%JAVA%" %SOLR_SSL_OPTS% %AUTHC_OPTS% %SOLR_ZK_CREDS_AND_ACLS% -Dsolr.install.dir="%SOLR_TIP%" -Dsolr.default.confdir="%DEFAULT_CONFDIR%"^
-Dlog4j.configuration="file:%DEFAULT_SERVER_DIR%\scripts\cloud-scripts\log4j.properties" ^
-classpath "%DEFAULT_SERVER_DIR%\solr-webapp\webapp\WEB-INF\lib\*;%DEFAULT_SERVER_DIR%\lib\ext\*" ^
org.apache.solr.util.SolrCLI create -name !CREATE_NAME! -shards !CREATE_NUM_SHARDS! -replicationFactor !CREATE_REPFACT! ^
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/java/org/apache/solr/cloud/CreateCollectionCmd.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/cloud/CreateCollectionCmd.java b/solr/core/src/java/org/apache/solr/cloud/CreateCollectionCmd.java
index d6a82a7..0c87658 100644
--- a/solr/core/src/java/org/apache/solr/cloud/CreateCollectionCmd.java
+++ b/solr/core/src/java/org/apache/solr/cloud/CreateCollectionCmd.java
@@ -22,6 +22,7 @@ import java.lang.invoke.MethodHandles;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
+import java.util.HashSet;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;
@@ -47,6 +48,7 @@ import org.apache.solr.common.params.ModifiableSolrParams;
import org.apache.solr.common.util.NamedList;
import org.apache.solr.common.util.SimpleOrderedMap;
import org.apache.solr.common.util.Utils;
+import org.apache.solr.handler.admin.ConfigSetsHandlerApi;
import org.apache.solr.handler.component.ShardHandler;
import org.apache.solr.handler.component.ShardRequest;
import org.apache.solr.util.TimeOut;
@@ -296,20 +298,49 @@ public class CreateCollectionCmd implements Cmd {
List<String> configNames = null;
try {
configNames = ocmh.zkStateReader.getZkClient().getChildren(ZkConfigManager.CONFIGS_ZKNODE, null, true);
- if (configNames != null && configNames.size() == 1) {
+ if (configNames.contains(ConfigSetsHandlerApi.DEFAULT_CONFIGSET_NAME)) {
+ if (!".system".equals(coll)) {
+ copyDefaultConfigSetTo(configNames, coll);
+ }
+ return coll;
+ } else if (configNames != null && configNames.size() == 1) {
configName = configNames.get(0);
// no config set named, but there is only 1 - use it
log.info("Only one config set found in zk - using it:" + configName);
- } else if (configNames.contains(coll)) {
- configName = coll;
}
} catch (KeeperException.NoNodeException e) {
}
}
- return configName;
+ return "".equals(configName)? null: configName;
}
+ /**
+ * Copies the _default configset to the specified configset name (overwrites if pre-existing)
+ */
+ private void copyDefaultConfigSetTo(List<String> configNames, String targetConfig) {
+ ZkConfigManager configManager = new ZkConfigManager(ocmh.zkStateReader.getZkClient());
+
+ // if a configset named coll exists, delete the configset so that _default can be copied over
+ if (configNames.contains(targetConfig)) {
+ log.info("There exists a configset by the same name as the collection we're trying to create: " + targetConfig +
+ ", deleting it so that we can copy the _default configs over and create the collection.");
+ try {
+ configManager.deleteConfigDir(targetConfig);
+ } catch (Exception e) {
+ throw new SolrException(ErrorCode.INVALID_STATE, "Error while deleting configset: " + targetConfig, e);
+ }
+ } else {
+ log.info("Only _default config set found, using it.");
+ }
+ // Copy _default into targetConfig
+ try {
+ configManager.copyConfigDir(ConfigSetsHandlerApi.DEFAULT_CONFIGSET_NAME, targetConfig, new HashSet<>());
+ } catch (Exception e) {
+ throw new SolrException(ErrorCode.INVALID_STATE, "Error while copying _default to " + targetConfig, e);
+ }
+ }
+
public static void createCollectionZkNode(SolrZkClient zkClient, String collection, Map<String,String> params) {
log.debug("Check for collection zkNode:" + collection);
String collectionPath = ZkStateReader.COLLECTIONS_ZKNODE + "/" + collection;
@@ -384,14 +415,14 @@ public class CreateCollectionCmd implements Cmd {
}
private static void getConfName(SolrZkClient zkClient, String collection, String collectionPath, Map<String,Object> collectionProps) throws KeeperException,
- InterruptedException {
+ InterruptedException {
// check for configName
log.debug("Looking for collection configName");
if (collectionProps.containsKey("configName")) {
log.info("configName was passed as a param {}", collectionProps.get("configName"));
return;
}
-
+
List<String> configNames = null;
int retry = 1;
int retryLimt = 6;
@@ -403,26 +434,34 @@ public class CreateCollectionCmd implements Cmd {
}
}
- // if there is only one conf, use that
try {
configNames = zkClient.getChildren(ZkConfigManager.CONFIGS_ZKNODE, null,
true);
} catch (NoNodeException e) {
// just keep trying
}
- if (configNames != null && configNames.size() == 1) {
- // no config set named, but there is only 1 - use it
- log.info("Only one config set found in zk - using it:" + configNames.get(0));
- collectionProps.put(ZkController.CONFIGNAME_PROP, configNames.get(0));
- break;
- }
+ // check if there's a config set with the same name as the collection
if (configNames != null && configNames.contains(collection)) {
log.info(
"Could not find explicit collection configName, but found config name matching collection name - using that set.");
collectionProps.put(ZkController.CONFIGNAME_PROP, collection);
break;
}
+ // if _default exists, use that
+ if (configNames != null && configNames.contains(ConfigSetsHandlerApi.DEFAULT_CONFIGSET_NAME)) {
+ log.info(
+ "Could not find explicit collection configName, but found _default config set - using that set.");
+ collectionProps.put(ZkController.CONFIGNAME_PROP, ConfigSetsHandlerApi.DEFAULT_CONFIGSET_NAME);
+ break;
+ }
+ // if there is only one conf, use that
+ if (configNames != null && configNames.size() == 1) {
+ // no config set named, but there is only 1 - use it
+ log.info("Only one config set found in zk - using it:" + configNames.get(0));
+ collectionProps.put(ZkController.CONFIGNAME_PROP, configNames.get(0));
+ break;
+ }
log.info("Could not find collection configName - pausing for 3 seconds and trying again - try: " + retry);
Thread.sleep(3000);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/java/org/apache/solr/cloud/ZkController.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/cloud/ZkController.java b/solr/core/src/java/org/apache/solr/cloud/ZkController.java
index b859599..391f29c 100644
--- a/solr/core/src/java/org/apache/solr/cloud/ZkController.java
+++ b/solr/core/src/java/org/apache/solr/cloud/ZkController.java
@@ -16,15 +16,19 @@
*/
package org.apache.solr.cloud;
+import java.io.File;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.lang.invoke.MethodHandles;
import java.net.InetAddress;
import java.net.NetworkInterface;
+import java.net.URISyntaxException;
+import java.net.URL;
import java.net.URLEncoder;
import java.net.UnknownHostException;
import java.nio.charset.StandardCharsets;
import java.nio.file.Path;
+import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Collections;
@@ -70,6 +74,7 @@ import org.apache.solr.common.cloud.ZkCmdExecutor;
import org.apache.solr.common.cloud.ZkConfigManager;
import org.apache.solr.common.cloud.ZkCoreNodeProps;
import org.apache.solr.common.cloud.ZkCredentialsProvider;
+import org.apache.solr.common.cloud.ZkMaintenanceUtils;
import org.apache.solr.common.cloud.ZkNodeProps;
import org.apache.solr.common.cloud.ZkStateReader;
import org.apache.solr.common.cloud.ZooKeeperException;
@@ -87,7 +92,9 @@ import org.apache.solr.core.CoreContainer;
import org.apache.solr.core.CoreDescriptor;
import org.apache.solr.core.SolrCore;
import org.apache.solr.core.SolrCoreInitializationException;
+import org.apache.solr.handler.admin.ConfigSetsHandlerApi;
import org.apache.solr.logging.MDCLoggingContext;
+import org.apache.solr.servlet.SolrDispatchFilter;
import org.apache.solr.update.UpdateLog;
import org.apache.zookeeper.CreateMode;
import org.apache.zookeeper.KeeperException;
@@ -660,7 +667,7 @@ public class ZkController {
* @throws KeeperException if there is a Zookeeper error
* @throws InterruptedException on interrupt
*/
- public static void createClusterZkNodes(SolrZkClient zkClient) throws KeeperException, InterruptedException {
+ public static void createClusterZkNodes(SolrZkClient zkClient) throws KeeperException, InterruptedException, IOException {
ZkCmdExecutor cmdExecutor = new ZkCmdExecutor(zkClient.getZkClientTimeout());
cmdExecutor.ensureExists(ZkStateReader.LIVE_NODES_ZKNODE, zkClient);
cmdExecutor.ensureExists(ZkStateReader.COLLECTIONS_ZKNODE, zkClient);
@@ -669,6 +676,48 @@ public class ZkController {
cmdExecutor.ensureExists(ZkStateReader.CLUSTER_STATE, emptyJson, CreateMode.PERSISTENT, zkClient);
cmdExecutor.ensureExists(ZkStateReader.SOLR_SECURITY_CONF_PATH, emptyJson, CreateMode.PERSISTENT, zkClient);
cmdExecutor.ensureExists(ZkStateReader.SOLR_AUTOSCALING_CONF_PATH, emptyJson, CreateMode.PERSISTENT, zkClient);
+ bootstrapDefaultConfigSet(zkClient);
+ }
+
+ private static void bootstrapDefaultConfigSet(SolrZkClient zkClient) throws KeeperException, InterruptedException, IOException {
+ if (zkClient.exists("/configs/_default", true) == false) {
+ String configDirPath = getDefaultConfigDirPath();
+ if (configDirPath == null) {
+ log.warn("The _default configset could not be uploaded. Please provide 'solr.default.confdir' parameter that points to a configset" +
+ " intended to be the default. Current 'solr.default.confdir' value: {}", System.getProperty(SolrDispatchFilter.SOLR_DEFAULT_CONFDIR_ATTRIBUTE));
+ } else {
+ ZkMaintenanceUtils.upConfig(zkClient, Paths.get(configDirPath), ConfigSetsHandlerApi.DEFAULT_CONFIGSET_NAME);
+ }
+ }
+ }
+
+ /**
+ * Gets the absolute filesystem path of the _default configset to bootstrap from.
+ * First tries the sysprop "solr.default.confdir". If not found, tries to find
+ * the _default dir relative to the sysprop "solr.install.dir".
+ * If that fails as well, tries to get the _default from the
+ * classpath. Returns null if not found anywhere.
+ */
+ private static String getDefaultConfigDirPath() {
+ String configDirPath = null;
+ String serverSubPath = "solr" + File.separator +
+ "configsets" + File.separator + "_default" +
+ File.separator + "conf";
+ String subPath = File.separator + "server" + File.separator + serverSubPath;
+ if (System.getProperty(SolrDispatchFilter.SOLR_DEFAULT_CONFDIR_ATTRIBUTE) != null && new File(System.getProperty(SolrDispatchFilter.SOLR_DEFAULT_CONFDIR_ATTRIBUTE)).exists()) {
+ configDirPath = new File(System.getProperty(SolrDispatchFilter.SOLR_DEFAULT_CONFDIR_ATTRIBUTE)).getAbsolutePath();
+ } else if (System.getProperty(SolrDispatchFilter.SOLR_INSTALL_DIR_ATTRIBUTE) != null &&
+ new File(System.getProperty(SolrDispatchFilter.SOLR_INSTALL_DIR_ATTRIBUTE) + subPath).exists()) {
+ configDirPath = new File(System.getProperty(SolrDispatchFilter.SOLR_INSTALL_DIR_ATTRIBUTE) + subPath).getAbsolutePath();
+ } else { // find "_default" in the classpath. This one is used for tests
+ URL classpathUrl = Thread.currentThread().getContextClassLoader().getResource(serverSubPath);
+ try {
+ if (classpathUrl != null && new File(classpathUrl.toURI()).exists()) {
+ configDirPath = new File(classpathUrl.toURI()).getAbsolutePath();
+ }
+ } catch (URISyntaxException ex) {}
+ }
+ return configDirPath;
}
private void init(CurrentCoreDescriptorProvider registerOnReconnect) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/java/org/apache/solr/handler/admin/ConfigSetsHandlerApi.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/handler/admin/ConfigSetsHandlerApi.java b/solr/core/src/java/org/apache/solr/handler/admin/ConfigSetsHandlerApi.java
index a4138a2..2028f67 100644
--- a/solr/core/src/java/org/apache/solr/handler/admin/ConfigSetsHandlerApi.java
+++ b/solr/core/src/java/org/apache/solr/handler/admin/ConfigSetsHandlerApi.java
@@ -31,6 +31,8 @@ import org.apache.solr.response.SolrQueryResponse;
public class ConfigSetsHandlerApi extends BaseHandlerApiSupport {
+ final public static String DEFAULT_CONFIGSET_NAME = "_default";
+
final ConfigSetsHandler configSetHandler;
static Collection<ApiCommand> apiCommands = createMapping();
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/java/org/apache/solr/servlet/SolrDispatchFilter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/servlet/SolrDispatchFilter.java b/solr/core/src/java/org/apache/solr/servlet/SolrDispatchFilter.java
index cdf3ce8..1b5c664 100644
--- a/solr/core/src/java/org/apache/solr/servlet/SolrDispatchFilter.java
+++ b/solr/core/src/java/org/apache/solr/servlet/SolrDispatchFilter.java
@@ -133,6 +133,10 @@ public class SolrDispatchFilter extends BaseSolrFilter {
public static final String SOLRHOME_ATTRIBUTE = "solr.solr.home";
+ public static final String SOLR_INSTALL_DIR_ATTRIBUTE = "solr.install.dir";
+
+ public static final String SOLR_DEFAULT_CONFDIR_ATTRIBUTE = "solr.default.confdir";
+
public static final String SOLR_LOG_MUTECONSOLE = "solr.log.muteconsole";
public static final String SOLR_LOG_LEVEL = "solr.log.level";
@@ -223,7 +227,7 @@ public class SolrDispatchFilter extends BaseSolrFilter {
private void logWelcomeBanner() {
log.info(" ___ _ Welcome to Apache Solr™ version {}", solrVersion());
log.info("/ __| ___| |_ _ Starting in {} mode on port {}", isCloudMode() ? "cloud" : "standalone", getSolrPort());
- log.info("\\__ \\/ _ \\ | '_| Install dir: {}", System.getProperty("solr.install.dir"));
+ log.info("\\__ \\/ _ \\ | '_| Install dir: {}, Default config dir: {}", System.getProperty(SOLR_INSTALL_DIR_ATTRIBUTE), System.getProperty(SOLR_DEFAULT_CONFDIR_ATTRIBUTE));
log.info("|___/\\___/_|_| Start time: {}", Instant.now().toString());
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/java/org/apache/solr/util/SolrCLI.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/util/SolrCLI.java b/solr/core/src/java/org/apache/solr/util/SolrCLI.java
index 668dd4f..30c5681 100644
--- a/solr/core/src/java/org/apache/solr/util/SolrCLI.java
+++ b/solr/core/src/java/org/apache/solr/util/SolrCLI.java
@@ -1503,17 +1503,23 @@ public class SolrCLI {
maxShardsPerNode = ((numShards*replicationFactor)+numNodes-1)/numNodes;
}
- String confname = cli.getOptionValue("confname", collectionName);
- boolean configExistsInZk =
+ String confname = cli.getOptionValue("confname");
+ String confdir = cli.getOptionValue("confdir");
+ String configsetsDir = cli.getOptionValue("configsetsDir");
+
+ boolean configExistsInZk = confname != null && !"".equals(confname.trim()) &&
cloudSolrClient.getZkStateReader().getZkClient().exists("/configs/" + confname, true);
if (".system".equals(collectionName)) {
//do nothing
} else if (configExistsInZk) {
echo("Re-using existing configuration directory "+confname);
- } else {
- Path confPath = ZkConfigManager.getConfigsetPath(cli.getOptionValue("confdir", DEFAULT_CONFIG_SET),
- cli.getOptionValue("configsetsDir"));
+ } else if (confdir != null && !"".equals(confdir.trim())){
+ if (confname == null || "".equals(confname.trim())) {
+ confname = collectionName;
+ }
+ Path confPath = ZkConfigManager.getConfigsetPath(confdir,
+ configsetsDir);
echo("Uploading " + confPath.toAbsolutePath().toString() +
" for config " + confname + " to ZooKeeper at " + cloudSolrClient.getZkHost());
@@ -1531,13 +1537,15 @@ public class SolrCLI {
// doesn't seem to exist ... try to create
String createCollectionUrl =
String.format(Locale.ROOT,
- "%s/admin/collections?action=CREATE&name=%s&numShards=%d&replicationFactor=%d&maxShardsPerNode=%d&collection.configName=%s",
+ "%s/admin/collections?action=CREATE&name=%s&numShards=%d&replicationFactor=%d&maxShardsPerNode=%d",
baseUrl,
collectionName,
numShards,
replicationFactor,
- maxShardsPerNode,
- confname);
+ maxShardsPerNode);
+ if (confname != null && !"".equals(confname.trim())) {
+ createCollectionUrl = createCollectionUrl + String.format(Locale.ROOT, "&collection.configName=%s", confname);
+ }
echo("\nCreating new collection '"+collectionName+"' using command:\n"+createCollectionUrl+"\n");
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test-files/solr/configsets/_default/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/configsets/_default/conf/schema.xml b/solr/core/src/test-files/solr/configsets/_default/conf/schema.xml
new file mode 100644
index 0000000..e94229e
--- /dev/null
+++ b/solr/core/src/test-files/solr/configsets/_default/conf/schema.xml
@@ -0,0 +1,37 @@
+<?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.
+-->
+
+<schema name="default-config" version="1.6">
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <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"/>
+
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+ <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test-files/solr/configsets/_default/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/core/src/test-files/solr/configsets/_default/conf/solrconfig.xml b/solr/core/src/test-files/solr/configsets/_default/conf/solrconfig.xml
new file mode 100644
index 0000000..acf95ba
--- /dev/null
+++ b/solr/core/src/test-files/solr/configsets/_default/conf/solrconfig.xml
@@ -0,0 +1,32 @@
+<?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.
+-->
+
+<config>
+
+ <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.RAMDirectoryFactory}"/>
+
+ <luceneMatchVersion>${tests.luceneMatchVersion:LATEST}</luceneMatchVersion>
+
+ <requestHandler name="my_error_handler" class="solr.ThrowErrorOnInitRequestHandler">
+ <str name="error">This is the _default configset, which is designed to throw error upon collection creation.</str>
+ </requestHandler>
+
+ <schemaFactory class="ClassicIndexSchemaFactory"/>
+
+</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/BaseCdcrDistributedZkTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/BaseCdcrDistributedZkTest.java b/solr/core/src/test/org/apache/solr/cloud/BaseCdcrDistributedZkTest.java
index ef2e224..8ce346b 100644
--- a/solr/core/src/test/org/apache/solr/cloud/BaseCdcrDistributedZkTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/BaseCdcrDistributedZkTest.java
@@ -432,7 +432,7 @@ public class BaseCdcrDistributedZkTest extends AbstractDistribZkTestBase {
REPLICATION_FACTOR, replicationFactor,
CREATE_NODE_SET, createNodeSetStr,
MAX_SHARDS_PER_NODE, maxShardsPerNode),
- client, null);
+ client, "conf1");
}
private CollectionAdminResponse createCollection(Map<String, List<Integer>> collectionInfos, String collectionName,
@@ -588,7 +588,7 @@ public class BaseCdcrDistributedZkTest extends AbstractDistribZkTestBase {
try (SolrClient client = createCloudClient(temporaryCollection)) {
assertEquals(0, CollectionAdminRequest
- .createCollection(temporaryCollection, shardCount, 1)
+ .createCollection(temporaryCollection, "conf1", shardCount, 1)
.setCreateNodeSet("")
.process(client).getStatus());
for (int i = 0; i < jettys.size(); i++) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZk2Test.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZk2Test.java b/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZk2Test.java
index 838ebb5..5bb938d 100644
--- a/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZk2Test.java
+++ b/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZk2Test.java
@@ -157,7 +157,7 @@ public class BasicDistributedZk2Test extends AbstractFullDistribZkTestBase {
private void testNodeWithoutCollectionForwarding() throws Exception {
assertEquals(0, CollectionAdminRequest
- .createCollection(ONE_NODE_COLLECTION, 1, 1)
+ .createCollection(ONE_NODE_COLLECTION, "conf1", 1, 1)
.setCreateNodeSet("")
.process(cloudClient).getStatus());
assertTrue(CollectionAdminRequest
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZkTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZkTest.java b/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZkTest.java
index a85165c..fcc51ac 100644
--- a/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZkTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/BasicDistributedZkTest.java
@@ -576,7 +576,7 @@ public class BasicDistributedZkTest extends AbstractFullDistribZkTestBase {
protected void createCores(final HttpSolrClient client,
ThreadPoolExecutor executor, final String collection, final int numShards, int cnt) {
try {
- assertEquals(0, CollectionAdminRequest.createCollection(collection, numShards, 1)
+ assertEquals(0, CollectionAdminRequest.createCollection(collection, "conf1", numShards, 1)
.setCreateNodeSet("")
.process(client).getStatus());
} catch (SolrServerException | IOException e) {
@@ -614,8 +614,9 @@ public class BasicDistributedZkTest extends AbstractFullDistribZkTestBase {
return url2;
}
+ @Override
protected CollectionAdminResponse createCollection(Map<String, List<Integer>> collectionInfos,
- String collectionName, int numShards, int numReplicas, int maxShardsPerNode, SolrClient client, String createNodeSetStr) throws SolrServerException, IOException {
+ String collectionName, String configSetName, int numShards, int numReplicas, int maxShardsPerNode, SolrClient client, String createNodeSetStr) throws SolrServerException, IOException {
// TODO: Use CollectionAdminRequest for this test
ModifiableSolrParams params = new ModifiableSolrParams();
params.set("action", CollectionAction.CREATE.toString());
@@ -633,6 +634,7 @@ public class BasicDistributedZkTest extends AbstractFullDistribZkTestBase {
collectionInfos.put(collectionName, list);
}
params.set("name", collectionName);
+ params.set("collection.configName", configSetName);
SolrRequest request = new QueryRequest(params);
request.setPath("/admin/collections");
@@ -795,7 +797,7 @@ public class BasicDistributedZkTest extends AbstractFullDistribZkTestBase {
private void testANewCollectionInOneInstanceWithManualShardAssignement() throws Exception {
log.info("### STARTING testANewCollectionInOneInstanceWithManualShardAssignement");
- assertEquals(0, CollectionAdminRequest.createCollection(oneInstanceCollection2, 2, 2)
+ assertEquals(0, CollectionAdminRequest.createCollection(oneInstanceCollection2, "conf1", 2, 2)
.setCreateNodeSet("")
.setMaxShardsPerNode(4)
.process(cloudClient).getStatus());
@@ -921,7 +923,7 @@ public class BasicDistributedZkTest extends AbstractFullDistribZkTestBase {
private void testANewCollectionInOneInstance() throws Exception {
log.info("### STARTING testANewCollectionInOneInstance");
- CollectionAdminResponse response = CollectionAdminRequest.createCollection(oneInstanceCollection, 2, 2)
+ CollectionAdminResponse response = CollectionAdminRequest.createCollection(oneInstanceCollection, "conf1", 2, 2)
.setCreateNodeSet(jettys.get(0).getNodeName())
.setMaxShardsPerNode(4)
.process(cloudClient);
@@ -1087,7 +1089,7 @@ public class BasicDistributedZkTest extends AbstractFullDistribZkTestBase {
private void createNewCollection(final String collection) throws InterruptedException {
try {
assertEquals(0, CollectionAdminRequest
- .createCollection(collection, 2, 1)
+ .createCollection(collection, "conf1", 2, 1)
.setCreateNodeSet("")
.process(cloudClient).getStatus());
} catch (Exception e) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/ClusterStateUpdateTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/ClusterStateUpdateTest.java b/solr/core/src/test/org/apache/solr/cloud/ClusterStateUpdateTest.java
index 763c3fc..0c331ae 100644
--- a/solr/core/src/test/org/apache/solr/cloud/ClusterStateUpdateTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/ClusterStateUpdateTest.java
@@ -61,7 +61,7 @@ public class ClusterStateUpdateTest extends SolrCloudTestCase {
public void testCoreRegistration() throws Exception {
System.setProperty("solrcloud.update.delay", "1");
- assertEquals(0, CollectionAdminRequest.createCollection("testcore", 1,1)
+ assertEquals(0, CollectionAdminRequest.createCollection("testcore", "conf", 1, 1)
.setCreateNodeSet(cluster.getJettySolrRunner(0).getNodeName())
.process(cluster.getSolrClient()).getStatus());
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/CollectionsAPISolrJTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/CollectionsAPISolrJTest.java b/solr/core/src/test/org/apache/solr/cloud/CollectionsAPISolrJTest.java
index d7a43c8..9c414cc 100644
--- a/solr/core/src/test/org/apache/solr/cloud/CollectionsAPISolrJTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/CollectionsAPISolrJTest.java
@@ -55,6 +55,25 @@ public class CollectionsAPISolrJTest extends SolrCloudTestCase {
.configure();
}
+ /**
+ * When a config name is not specified during collection creation, the _default should
+ * be used.
+ */
+ @Test
+ public void testCreateWithDefaultConfigSet() throws Exception {
+ String collectionName = "solrj_default_configset";
+ CollectionAdminResponse response = CollectionAdminRequest.createCollection(collectionName, 2, 2) // no configset specified
+ .process(cluster.getSolrClient());
+
+ // The _default configset (for the tests) is designed to error out upon collection creation,
+ // so we just ensure that the correct error message was obtained.
+ assertFalse(response.isSuccess());
+ System.out.println("Errors are: "+response.getErrorMessages());
+ assertTrue(response.getErrorMessages() != null && response.getErrorMessages().size() > 0);
+ assertTrue(response.getErrorMessages().getVal(0).contains("This is the _default configset, which is designed"
+ + " to throw error upon collection creation."));
+ }
+
@Test
public void testCreateAndDeleteCollection() throws Exception {
String collectionName = "solrj_test";
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/ForceLeaderTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/ForceLeaderTest.java b/solr/core/src/test/org/apache/solr/cloud/ForceLeaderTest.java
index b57dcb7..b60609f 100644
--- a/solr/core/src/test/org/apache/solr/cloud/ForceLeaderTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/ForceLeaderTest.java
@@ -80,7 +80,7 @@ public class ForceLeaderTest extends HttpPartitionTest {
handle.put("timestamp", SKIPVAL);
String testCollectionName = "forceleader_test_collection";
- createCollection(testCollectionName, 1, 3, 1);
+ createCollection(testCollectionName, "conf1", 1, 3, 1);
cloudClient.setDefaultCollection(testCollectionName);
try {
@@ -166,7 +166,7 @@ public class ForceLeaderTest extends HttpPartitionTest {
handle.put("timestamp", SKIPVAL);
String testCollectionName = "forceleader_last_published";
- createCollection(testCollectionName, 1, 3, 1);
+ createCollection(testCollectionName, "conf1", 1, 3, 1);
cloudClient.setDefaultCollection(testCollectionName);
log.info("Collection created: " + testCollectionName);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/HttpPartitionTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/HttpPartitionTest.java b/solr/core/src/test/org/apache/solr/cloud/HttpPartitionTest.java
index 2f2ccb4..ea989c0 100644
--- a/solr/core/src/test/org/apache/solr/cloud/HttpPartitionTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/HttpPartitionTest.java
@@ -152,7 +152,7 @@ public class HttpPartitionTest extends AbstractFullDistribZkTestBase {
protected void testLeaderInitiatedRecoveryCRUD() throws Exception {
String testCollectionName = "c8n_crud_1x2";
String shardId = "shard1";
- createCollectionRetry(testCollectionName, 1, 2, 1);
+ createCollectionRetry(testCollectionName, "conf1", 1, 2, 1);
cloudClient.setDefaultCollection(testCollectionName);
Replica leader = cloudClient.getZkStateReader().getLeaderRetry(testCollectionName, shardId);
@@ -204,7 +204,7 @@ public class HttpPartitionTest extends AbstractFullDistribZkTestBase {
protected void testMinRf() throws Exception {
// create a collection that has 1 shard and 3 replicas
String testCollectionName = "collMinRf_1x3";
- createCollection(testCollectionName, 1, 3, 1);
+ createCollection(testCollectionName, "conf1", 1, 3, 1);
cloudClient.setDefaultCollection(testCollectionName);
sendDoc(1, 2);
@@ -290,7 +290,7 @@ public class HttpPartitionTest extends AbstractFullDistribZkTestBase {
protected void testRf2() throws Exception {
// create a collection that has 1 shard but 2 replicas
String testCollectionName = "c8n_1x2";
- createCollectionRetry(testCollectionName, 1, 2, 1);
+ createCollectionRetry(testCollectionName, "conf1", 1, 2, 1);
cloudClient.setDefaultCollection(testCollectionName);
sendDoc(1);
@@ -386,7 +386,7 @@ public class HttpPartitionTest extends AbstractFullDistribZkTestBase {
protected void testRf3() throws Exception {
// create a collection that has 1 shard but 2 replicas
String testCollectionName = "c8n_1x3";
- createCollectionRetry(testCollectionName, 1, 3, 1);
+ createCollectionRetry(testCollectionName, "conf1", 1, 3, 1);
cloudClient.setDefaultCollection(testCollectionName);
@@ -437,7 +437,7 @@ public class HttpPartitionTest extends AbstractFullDistribZkTestBase {
protected void testLeaderZkSessionLoss() throws Exception {
String testCollectionName = "c8n_1x2_leader_session_loss";
- createCollectionRetry(testCollectionName, 1, 2, 1);
+ createCollectionRetry(testCollectionName, "conf1", 1, 2, 1);
cloudClient.setDefaultCollection(testCollectionName);
sendDoc(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/LeaderFailoverAfterPartitionTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/LeaderFailoverAfterPartitionTest.java b/solr/core/src/test/org/apache/solr/cloud/LeaderFailoverAfterPartitionTest.java
index 975459d..6a427c9 100644
--- a/solr/core/src/test/org/apache/solr/cloud/LeaderFailoverAfterPartitionTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/LeaderFailoverAfterPartitionTest.java
@@ -61,7 +61,7 @@ public class LeaderFailoverAfterPartitionTest extends HttpPartitionTest {
// kill the leader ... see what happens
// create a collection that has 1 shard but 3 replicas
String testCollectionName = "c8n_1x3_lf"; // _lf is leader fails
- createCollection(testCollectionName, 1, 3, 1);
+ createCollection(testCollectionName, "conf1", 1, 3, 1);
cloudClient.setDefaultCollection(testCollectionName);
sendDoc(1);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnCommitTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnCommitTest.java b/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnCommitTest.java
index f900d3a..b4e4860 100644
--- a/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnCommitTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnCommitTest.java
@@ -62,7 +62,7 @@ public class LeaderInitiatedRecoveryOnCommitTest extends BasicDistributedZkTest
// create a collection that has 2 shard and 2 replicas
String testCollectionName = "c8n_2x2_commits";
- createCollection(testCollectionName, 2, 2, 1);
+ createCollection(testCollectionName, "conf1", 2, 2, 1);
cloudClient.setDefaultCollection(testCollectionName);
List<Replica> notLeaders =
@@ -105,7 +105,7 @@ public class LeaderInitiatedRecoveryOnCommitTest extends BasicDistributedZkTest
// create a collection that has 1 shard and 3 replicas
String testCollectionName = "c8n_1x3_commits";
- createCollection(testCollectionName, 1, 3, 1);
+ createCollection(testCollectionName, "conf1", 1, 3, 1);
cloudClient.setDefaultCollection(testCollectionName);
List<Replica> notLeaders =
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnShardRestartTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnShardRestartTest.java b/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnShardRestartTest.java
index 003a843..8064513 100644
--- a/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnShardRestartTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/LeaderInitiatedRecoveryOnShardRestartTest.java
@@ -86,7 +86,7 @@ public class LeaderInitiatedRecoveryOnShardRestartTest extends AbstractFullDistr
String testCollectionName = "all_in_lir";
String shardId = "shard1";
- createCollection(testCollectionName, 1, 3, 1);
+ createCollection(testCollectionName, "conf1", 1, 3, 1);
waitForRecoveriesToFinish(testCollectionName, false);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/ReplicationFactorTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/ReplicationFactorTest.java b/solr/core/src/test/org/apache/solr/cloud/ReplicationFactorTest.java
index d0d4f78..8fa1607 100644
--- a/solr/core/src/test/org/apache/solr/cloud/ReplicationFactorTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/ReplicationFactorTest.java
@@ -98,12 +98,12 @@ public class ReplicationFactorTest extends AbstractFullDistribZkTestBase {
String shardId = "shard1";
int minRf = 2;
- CollectionAdminResponse resp = createCollection(testCollectionName, numShards, replicationFactor, maxShardsPerNode);
+ CollectionAdminResponse resp = createCollection(testCollectionName, "conf1", numShards, replicationFactor, maxShardsPerNode);
if (resp.getResponse().get("failure") != null) {
CollectionAdminRequest.deleteCollection(testCollectionName).process(cloudClient);
- resp = createCollection(testCollectionName, numShards, replicationFactor, maxShardsPerNode);
+ resp = createCollection(testCollectionName, "conf1", numShards, replicationFactor, maxShardsPerNode);
if (resp.getResponse().get("failure") != null) {
fail("Could not create " + testCollectionName);
@@ -184,7 +184,7 @@ public class ReplicationFactorTest extends AbstractFullDistribZkTestBase {
String shardId = "shard1";
int minRf = 2;
- createCollection(testCollectionName, numShards, replicationFactor, maxShardsPerNode);
+ createCollection(testCollectionName, "conf1", numShards, replicationFactor, maxShardsPerNode);
cloudClient.setDefaultCollection(testCollectionName);
List<Replica> replicas =
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/ShardRoutingCustomTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/ShardRoutingCustomTest.java b/solr/core/src/test/org/apache/solr/cloud/ShardRoutingCustomTest.java
index 78e4128..d7cd4a8 100644
--- a/solr/core/src/test/org/apache/solr/cloud/ShardRoutingCustomTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/ShardRoutingCustomTest.java
@@ -63,7 +63,7 @@ public class ShardRoutingCustomTest extends AbstractFullDistribZkTestBase {
setupJettySolrHome(jettyDir);
JettySolrRunner j = createJetty(jettyDir, createTempDir().toFile().getAbsolutePath(), "shardA", "solrconfig.xml", null);
assertEquals(0, CollectionAdminRequest
- .createCollection(DEFAULT_COLLECTION, 1, 1)
+ .createCollection(DEFAULT_COLLECTION, "conf1", 1, 1)
.setStateFormat(Integer.parseInt(getStateFormat()))
.setCreateNodeSet("")
.process(cloudClient).getStatus());
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/ShardSplitTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/ShardSplitTest.java b/solr/core/src/test/org/apache/solr/cloud/ShardSplitTest.java
index 35ac5c0..644221b 100644
--- a/solr/core/src/test/org/apache/solr/cloud/ShardSplitTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/ShardSplitTest.java
@@ -523,7 +523,7 @@ public class ShardSplitTest extends BasicDistributedZkTest {
log.info("Starting testSplitShardWithRule");
String collectionName = "shardSplitWithRule";
- CollectionAdminRequest.Create createRequest = CollectionAdminRequest.createCollection(collectionName,1,2)
+ CollectionAdminRequest.Create createRequest = CollectionAdminRequest.createCollection(collectionName, "conf1", 1, 2)
.setRule("shard:*,replica:<2,node:*");
CollectionAdminResponse response = createRequest.process(cloudClient);
assertEquals(0, response.getStatus());
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/TestConfigSetsAPI.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/TestConfigSetsAPI.java b/solr/core/src/test/org/apache/solr/cloud/TestConfigSetsAPI.java
index 875c0ef..27fcfc0 100644
--- a/solr/core/src/test/org/apache/solr/cloud/TestConfigSetsAPI.java
+++ b/solr/core/src/test/org/apache/solr/cloud/TestConfigSetsAPI.java
@@ -695,7 +695,7 @@ public class TestConfigSetsAPI extends SolrTestCaseJ4 {
ConfigSetAdminRequest.List list = new ConfigSetAdminRequest.List();
ConfigSetAdminResponse.List response = list.process(solrClient);
Collection<String> actualConfigSets = response.getConfigSets();
- assertEquals(0, actualConfigSets.size());
+ assertEquals(1, actualConfigSets.size()); // only the _default configset
// test multiple
Set<String> configSets = new HashSet<String>();
@@ -706,8 +706,8 @@ public class TestConfigSetsAPI extends SolrTestCaseJ4 {
}
response = list.process(solrClient);
actualConfigSets = response.getConfigSets();
- assertEquals(configSets.size(), actualConfigSets.size());
- assertTrue(configSets.containsAll(actualConfigSets));
+ assertEquals(configSets.size() + 1, actualConfigSets.size());
+ assertTrue(actualConfigSets.containsAll(configSets));
} finally {
zkClient.close();
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/TestOnReconnectListenerSupport.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/TestOnReconnectListenerSupport.java b/solr/core/src/test/org/apache/solr/cloud/TestOnReconnectListenerSupport.java
index 165b22a..36261e2 100644
--- a/solr/core/src/test/org/apache/solr/cloud/TestOnReconnectListenerSupport.java
+++ b/solr/core/src/test/org/apache/solr/cloud/TestOnReconnectListenerSupport.java
@@ -63,7 +63,7 @@ public class TestOnReconnectListenerSupport extends AbstractFullDistribZkTestBas
String testCollectionName = "c8n_onreconnect_1x1";
String shardId = "shard1";
- createCollectionRetry(testCollectionName, 1, 1, 1);
+ createCollectionRetry(testCollectionName, "conf1", 1, 1, 1);
cloudClient.setDefaultCollection(testCollectionName);
Replica leader = getShardLeader(testCollectionName, shardId, 30 /* timeout secs */);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/TestPullReplica.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/TestPullReplica.java b/solr/core/src/test/org/apache/solr/cloud/TestPullReplica.java
index 2156d3b..6c2298b 100644
--- a/solr/core/src/test/org/apache/solr/cloud/TestPullReplica.java
+++ b/solr/core/src/test/org/apache/solr/cloud/TestPullReplica.java
@@ -130,9 +130,9 @@ public class TestPullReplica extends SolrCloudTestCase {
break;
case 1:
// Sometimes use v1 API
- String url = String.format(Locale.ROOT, "%s/admin/collections?action=CREATE&name=%s&numShards=%s&pullReplicas=%s&maxShardsPerNode=%s",
+ String url = String.format(Locale.ROOT, "%s/admin/collections?action=CREATE&name=%s&collection.configName=%s&numShards=%s&pullReplicas=%s&maxShardsPerNode=%s",
cluster.getRandomJetty(random()).getBaseUrl(),
- collectionName,
+ collectionName, "conf",
2, // numShards
3, // pullReplicas
100); // maxShardsPerNode
@@ -143,8 +143,8 @@ public class TestPullReplica extends SolrCloudTestCase {
case 2:
// Sometimes use V2 API
url = cluster.getRandomJetty(random()).getBaseUrl().toString() + "/____v2/c";
- String requestBody = String.format(Locale.ROOT, "{create:{name:%s, numShards:%s, pullReplicas:%s, maxShardsPerNode:%s %s}}",
- collectionName,
+ String requestBody = String.format(Locale.ROOT, "{create:{name:%s, config:%s, numShards:%s, pullReplicas:%s, maxShardsPerNode:%s %s}}",
+ collectionName, "conf",
2, // numShards
3, // pullReplicas
100, // maxShardsPerNode
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/TestRandomRequestDistribution.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/TestRandomRequestDistribution.java b/solr/core/src/test/org/apache/solr/cloud/TestRandomRequestDistribution.java
index b486256..30898b9 100644
--- a/solr/core/src/test/org/apache/solr/cloud/TestRandomRequestDistribution.java
+++ b/solr/core/src/test/org/apache/solr/cloud/TestRandomRequestDistribution.java
@@ -73,11 +73,11 @@ public class TestRandomRequestDistribution extends AbstractFullDistribZkTestBase
*/
private void testRequestTracking() throws Exception {
- CollectionAdminRequest.createCollection("a1x2",1,2)
+ CollectionAdminRequest.createCollection("a1x2", "conf1", 1, 2)
.setCreateNodeSet(nodeNames.get(0) + ',' + nodeNames.get(1))
.process(cloudClient);
- CollectionAdminRequest.createCollection("b1x1",1,1)
+ CollectionAdminRequest.createCollection("b1x1", "conf1", 1, 1)
.setCreateNodeSet(nodeNames.get(2))
.process(cloudClient);
@@ -128,7 +128,7 @@ public class TestRandomRequestDistribution extends AbstractFullDistribZkTestBase
private void testQueryAgainstDownReplica() throws Exception {
log.info("Creating collection 'football' with 1 shard and 2 replicas");
- CollectionAdminRequest.createCollection("football",1,2)
+ CollectionAdminRequest.createCollection("football", "conf1", 1, 2)
.setCreateNodeSet(nodeNames.get(0) + ',' + nodeNames.get(1))
.process(cloudClient);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/TestSolrCloudWithKerberosAlt.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/TestSolrCloudWithKerberosAlt.java b/solr/core/src/test/org/apache/solr/cloud/TestSolrCloudWithKerberosAlt.java
index 16cee78..68af59f 100644
--- a/solr/core/src/test/org/apache/solr/cloud/TestSolrCloudWithKerberosAlt.java
+++ b/solr/core/src/test/org/apache/solr/cloud/TestSolrCloudWithKerberosAlt.java
@@ -174,7 +174,7 @@ public class TestSolrCloudWithKerberosAlt extends LuceneTestCase {
String configName = "solrCloudCollectionConfig";
miniCluster.uploadConfigSet(SolrTestCaseJ4.TEST_PATH().resolve("collection1/conf"), configName);
- CollectionAdminRequest.Create createRequest = CollectionAdminRequest.createCollection(collectionName,NUM_SHARDS,REPLICATION_FACTOR);
+ CollectionAdminRequest.Create createRequest = CollectionAdminRequest.createCollection(collectionName, configName, NUM_SHARDS,REPLICATION_FACTOR);
Properties properties = new Properties();
properties.put(CoreDescriptor.CORE_CONFIG, "solrconfig-tlog.xml");
properties.put("solr.tests.maxBufferedDocs", "100000");
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/TestTlogReplica.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/TestTlogReplica.java b/solr/core/src/test/org/apache/solr/cloud/TestTlogReplica.java
index 9990601..cc470d6 100644
--- a/solr/core/src/test/org/apache/solr/cloud/TestTlogReplica.java
+++ b/solr/core/src/test/org/apache/solr/cloud/TestTlogReplica.java
@@ -157,9 +157,9 @@ public class TestTlogReplica extends SolrCloudTestCase {
break;
case 1:
// Sometimes don't use SolrJ
- String url = String.format(Locale.ROOT, "%s/admin/collections?action=CREATE&name=%s&numShards=%s&tlogReplicas=%s&maxShardsPerNode=%s",
+ String url = String.format(Locale.ROOT, "%s/admin/collections?action=CREATE&name=%s&collection.configName=%s&numShards=%s&tlogReplicas=%s&maxShardsPerNode=%s",
cluster.getRandomJetty(random()).getBaseUrl(),
- collectionName,
+ collectionName, "conf",
2, // numShards
4, // tlogReplicas
100); // maxShardsPerNode
@@ -170,8 +170,8 @@ public class TestTlogReplica extends SolrCloudTestCase {
case 2:
// Sometimes use V2 API
url = cluster.getRandomJetty(random()).getBaseUrl().toString() + "/____v2/c";
- String requestBody = String.format(Locale.ROOT, "{create:{name:%s, numShards:%s, tlogReplicas:%s, maxShardsPerNode:%s}}",
- collectionName,
+ String requestBody = String.format(Locale.ROOT, "{create:{name:%s, config:%s, numShards:%s, tlogReplicas:%s, maxShardsPerNode:%s}}",
+ collectionName, "conf",
2, // numShards
4, // tlogReplicas
100); // maxShardsPerNode
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/UnloadDistributedZkTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/UnloadDistributedZkTest.java b/solr/core/src/test/org/apache/solr/cloud/UnloadDistributedZkTest.java
index 2591f2b..19dd998 100644
--- a/solr/core/src/test/org/apache/solr/cloud/UnloadDistributedZkTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/UnloadDistributedZkTest.java
@@ -109,7 +109,7 @@ public class UnloadDistributedZkTest extends BasicDistributedZkTest {
final String coreName1 = collection+"_1";
final String coreName2 = collection+"_2";
- assertEquals(0, CollectionAdminRequest.createCollection(collection, numShards, 1)
+ assertEquals(0, CollectionAdminRequest.createCollection(collection, "conf1", numShards, 1)
.setCreateNodeSet("")
.process(cloudClient).getStatus());
assertTrue(CollectionAdminRequest.addReplicaToShard(collection, "shard1")
@@ -168,7 +168,7 @@ public class UnloadDistributedZkTest extends BasicDistributedZkTest {
JettySolrRunner jetty1 = jettys.get(0);
assertEquals(0, CollectionAdminRequest
- .createCollection("unloadcollection", 1,1)
+ .createCollection("unloadcollection", "conf1", 1,1)
.setCreateNodeSet(jetty1.getNodeName())
.process(cloudClient).getStatus());
ZkStateReader zkStateReader = getCommonCloudSolrClient().getZkStateReader();
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/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 05cdb87..ecc7afd 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
@@ -49,10 +49,11 @@ import static org.apache.solr.common.cloud.ZkStateReader.SOLR_AUTOSCALING_CONF_P
* Test for AutoScalingHandler
*/
public class AutoScalingHandlerTest extends SolrCloudTestCase {
+ final static String CONFIGSET_NAME = "conf";
@BeforeClass
public static void setupCluster() throws Exception {
configureCluster(2)
- .addConfig("conf", configset("cloud-minimal"))
+ .addConfig(CONFIGSET_NAME, configset("cloud-minimal"))
.configure();
}
@@ -275,7 +276,7 @@ public class AutoScalingHandlerTest extends SolrCloudTestCase {
assertEquals(0, violations.size());
// lets create a collection which violates the rule replicas < 2
- CollectionAdminRequest.Create create = CollectionAdminRequest.Create.createCollection("readApiTestViolations", 1, 6);
+ CollectionAdminRequest.Create create = CollectionAdminRequest.Create.createCollection("readApiTestViolations", CONFIGSET_NAME, 1, 6);
create.setMaxShardsPerNode(10);
CollectionAdminResponse adminResponse = create.process(solrClient);
assertTrue(adminResponse.isSuccess());
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/autoscaling/TestPolicyCloud.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/autoscaling/TestPolicyCloud.java b/solr/core/src/test/org/apache/solr/cloud/autoscaling/TestPolicyCloud.java
index b584e49..cb519f2 100644
--- a/solr/core/src/test/org/apache/solr/cloud/autoscaling/TestPolicyCloud.java
+++ b/solr/core/src/test/org/apache/solr/cloud/autoscaling/TestPolicyCloud.java
@@ -73,7 +73,7 @@ public class TestPolicyCloud extends SolrCloudTestCase {
cluster.getSolrClient().request(AutoScalingHandlerTest.createAutoScalingRequest(SolrRequest.METHOD.POST, commands));
String collectionName = "testCreateCollectionAddReplica";
- CollectionAdminRequest.createCollection(collectionName, 1, 1)
+ CollectionAdminRequest.createCollection(collectionName, "conf", 1, 1)
.setPolicy("c1")
.process(cluster.getSolrClient());
@@ -102,7 +102,7 @@ public class TestPolicyCloud extends SolrCloudTestCase {
assertEquals("success", response.get("result"));
String collectionName = "testCreateCollectionSplitShard";
- CollectionAdminRequest.createCollection(collectionName, 1, 2)
+ CollectionAdminRequest.createCollection(collectionName, "conf", 1, 2)
.setPolicy("c1")
.setMaxShardsPerNode(10)
.process(cluster.getSolrClient());
@@ -140,7 +140,7 @@ public class TestPolicyCloud extends SolrCloudTestCase {
Map<String, Object> json = Utils.getJson(cluster.getZkClient(), ZkStateReader.SOLR_AUTOSCALING_CONF_PATH, true);
assertEquals("full json:"+ Utils.toJSONString(json) , "#EACH",
Utils.getObjectByPath(json, true, "/policies/c1[0]/shard"));
- CollectionAdminRequest.createCollectionWithImplicitRouter("policiesTest", null, "s1,s2", 1)
+ CollectionAdminRequest.createCollectionWithImplicitRouter("policiesTest", "conf", "s1,s2", 1)
.setPolicy("c1")
.process(cluster.getSolrClient());
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsNNFailoverTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsNNFailoverTest.java b/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsNNFailoverTest.java
index 349db11..7e1386d 100644
--- a/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsNNFailoverTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsNNFailoverTest.java
@@ -66,7 +66,7 @@ public class HdfsNNFailoverTest extends BasicDistributedZkTest {
@Test
public void test() throws Exception {
- createCollection(COLLECTION, 1, 1, 1);
+ createCollection(COLLECTION, "conf1", 1, 1, 1);
waitForRecoveriesToFinish(COLLECTION, false);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsWriteToMultipleCollectionsTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsWriteToMultipleCollectionsTest.java b/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsWriteToMultipleCollectionsTest.java
index ca85fe0..7e19c85 100644
--- a/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsWriteToMultipleCollectionsTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/hdfs/HdfsWriteToMultipleCollectionsTest.java
@@ -95,7 +95,7 @@ public class HdfsWriteToMultipleCollectionsTest extends BasicDistributedZkTest {
int docCount = random().nextInt(1313) + 1;
int cnt = random().nextInt(4) + 1;
for (int i = 0; i < cnt; i++) {
- createCollection(ACOLLECTION + i, 2, 2, 9);
+ createCollection(ACOLLECTION + i, "conf1", 2, 2, 9);
}
for (int i = 0; i < cnt; i++) {
waitForRecoveriesToFinish(ACOLLECTION + i, false);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/cloud/hdfs/StressHdfsTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/cloud/hdfs/StressHdfsTest.java b/solr/core/src/test/org/apache/solr/cloud/hdfs/StressHdfsTest.java
index 58ee708..0955493 100644
--- a/solr/core/src/test/org/apache/solr/cloud/hdfs/StressHdfsTest.java
+++ b/solr/core/src/test/org/apache/solr/cloud/hdfs/StressHdfsTest.java
@@ -107,7 +107,7 @@ public class StressHdfsTest extends BasicDistributedZkTest {
Timer timer = new Timer();
try {
- createCollection(DELETE_DATA_DIR_COLLECTION, 1, 1, 1);
+ createCollection(DELETE_DATA_DIR_COLLECTION, "conf1", 1, 1, 1);
waitForRecoveriesToFinish(DELETE_DATA_DIR_COLLECTION, false);
@@ -154,7 +154,7 @@ public class StressHdfsTest extends BasicDistributedZkTest {
if (nShards == 0) nShards = 1;
}
- createCollection(DELETE_DATA_DIR_COLLECTION, nShards, rep, maxReplicasPerNode);
+ createCollection(DELETE_DATA_DIR_COLLECTION, "conf1", nShards, rep, maxReplicasPerNode);
waitForRecoveriesToFinish(DELETE_DATA_DIR_COLLECTION, false);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/handler/ThrowErrorOnInitRequestHandler.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/handler/ThrowErrorOnInitRequestHandler.java b/solr/core/src/test/org/apache/solr/handler/ThrowErrorOnInitRequestHandler.java
index 594a3f1..6409e17 100644
--- a/solr/core/src/test/org/apache/solr/handler/ThrowErrorOnInitRequestHandler.java
+++ b/solr/core/src/test/org/apache/solr/handler/ThrowErrorOnInitRequestHandler.java
@@ -42,6 +42,10 @@ public class ThrowErrorOnInitRequestHandler extends RequestHandlerBase
@Override
public void init(NamedList args) {
+ String errorMessage = (String) args.get("error");
+ if (errorMessage != null) {
+ throw new Error(errorMessage);
+ }
throw new Error("Doing my job, throwing a java.lang.Error");
}
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/core/src/test/org/apache/solr/handler/component/TestTrackingShardHandlerFactory.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/handler/component/TestTrackingShardHandlerFactory.java b/solr/core/src/test/org/apache/solr/handler/component/TestTrackingShardHandlerFactory.java
index 5b95981..6a87bd7 100644
--- a/solr/core/src/test/org/apache/solr/handler/component/TestTrackingShardHandlerFactory.java
+++ b/solr/core/src/test/org/apache/solr/handler/component/TestTrackingShardHandlerFactory.java
@@ -65,7 +65,7 @@ public class TestTrackingShardHandlerFactory extends AbstractFullDistribZkTestBa
assertSame(trackingQueue, trackingShardHandlerFactory.getTrackingQueue());
}
- createCollection(collectionName, 2, 1, 1);
+ createCollection(collectionName, "conf1", 2, 1, 1);
waitForRecoveriesToFinish(collectionName, true);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/solrj/src/java/org/apache/solr/cloud/autoscaling/package-info.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/cloud/autoscaling/package-info.java b/solr/solrj/src/java/org/apache/solr/cloud/autoscaling/package-info.java
deleted file mode 100644
index a0167fa..0000000
--- a/solr/solrj/src/java/org/apache/solr/cloud/autoscaling/package-info.java
+++ /dev/null
@@ -1,22 +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.
- */
-
-/**
- * Common classes for autoscaling parsing filtering nodes and sorting
- */
-
-package org.apache.solr.cloud.autoscaling;
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ee572b05/solr/test-framework/src/java/org/apache/solr/cloud/AbstractFullDistribZkTestBase.java
----------------------------------------------------------------------
diff --git a/solr/test-framework/src/java/org/apache/solr/cloud/AbstractFullDistribZkTestBase.java b/solr/test-framework/src/java/org/apache/solr/cloud/AbstractFullDistribZkTestBase.java
index cd01a7f..6e1613f 100644
--- a/solr/test-framework/src/java/org/apache/solr/cloud/AbstractFullDistribZkTestBase.java
+++ b/solr/test-framework/src/java/org/apache/solr/cloud/AbstractFullDistribZkTestBase.java
@@ -312,7 +312,7 @@ public abstract class AbstractFullDistribZkTestBase extends AbstractDistribZkTes
+ "/control/data") : null);
try (SolrClient client = createCloudClient("control_collection")) {
assertEquals(0, CollectionAdminRequest
- .createCollection("control_collection", 1, 1)
+ .createCollection("control_collection", "conf1", 1, 1)
.setCreateNodeSet(controlJetty.getNodeName())
.process(client).getStatus());
}
@@ -380,7 +380,7 @@ public abstract class AbstractFullDistribZkTestBase extends AbstractDistribZkTes
StringBuilder sb = new StringBuilder();
assertEquals(0, CollectionAdminRequest
- .createCollection(DEFAULT_COLLECTION, sliceCount, 1)
+ .createCollection(DEFAULT_COLLECTION, "conf1", sliceCount, 1)
.setStateFormat(Integer.parseInt(getStateFormat()))
.setCreateNodeSet("")
.process(cloudClient).getStatus());
@@ -1600,12 +1600,12 @@ public abstract class AbstractFullDistribZkTestBase extends AbstractDistribZkTes
super.destroyServers();
}
- protected CollectionAdminResponse createCollection(String collectionName, int numShards, int replicationFactor, int maxShardsPerNode) throws SolrServerException, IOException {
- return createCollection(null, collectionName, numShards, replicationFactor, maxShardsPerNode, null, null);
+ protected CollectionAdminResponse createCollection(String collectionName, String configSetName, int numShards, int replicationFactor, int maxShardsPerNode) throws SolrServerException, IOException {
+ return createCollection(null, collectionName, configSetName, numShards, replicationFactor, maxShardsPerNode, null, null);
}
protected CollectionAdminResponse createCollection(Map<String,List<Integer>> collectionInfos, String collectionName, Map<String,Object> collectionProps, SolrClient client) throws SolrServerException, IOException{
- return createCollection(collectionInfos, collectionName, collectionProps, client, null);
+ return createCollection(collectionInfos, collectionName, collectionProps, client, "conf1");
}
// TODO: Use CollectionAdminRequest#createCollection() instead of a raw request
@@ -1640,6 +1640,8 @@ public abstract class AbstractFullDistribZkTestBase extends AbstractDistribZkTes
}
if (confSetName != null) {
params.set("collection.configName", confSetName);
+ } else {
+ params.set("collection.configName", "conf1");
}
int clientIndex = random().nextInt(2);
@@ -1671,7 +1673,7 @@ public abstract class AbstractFullDistribZkTestBase extends AbstractDistribZkTes
protected CollectionAdminResponse createCollection(Map<String,List<Integer>> collectionInfos,
- String collectionName, int numShards, int replicationFactor, int maxShardsPerNode, SolrClient client, String createNodeSetStr) throws SolrServerException, IOException {
+ String collectionName, String configSetName, int numShards, int replicationFactor, int maxShardsPerNode, SolrClient client, String createNodeSetStr) throws SolrServerException, IOException {
int numNrtReplicas = useTlogReplicas()?0:replicationFactor;
int numTlogReplicas = useTlogReplicas()?replicationFactor:0;
@@ -1683,7 +1685,7 @@ public abstract class AbstractFullDistribZkTestBase extends AbstractDistribZkTes
ZkStateReader.PULL_REPLICAS, getPullReplicaCount(),
CREATE_NODE_SET, createNodeSetStr,
ZkStateReader.MAX_SHARDS_PER_NODE, maxShardsPerNode),
- client);
+ client, configSetName);
}
protected CollectionAdminResponse createCollection(Map<String, List<Integer>> collectionInfos,
@@ -1893,14 +1895,14 @@ public abstract class AbstractFullDistribZkTestBase extends AbstractDistribZkTes
createCollection(collectionInfos, collName, props, client);
}
- protected void createCollectionRetry(String testCollectionName, int numShards, int replicationFactor, int maxShardsPerNode)
+ protected void createCollectionRetry(String testCollectionName, String configSetName, int numShards, int replicationFactor, int maxShardsPerNode)
throws SolrServerException, IOException {
- CollectionAdminResponse resp = createCollection(testCollectionName, numShards, replicationFactor, maxShardsPerNode);
+ CollectionAdminResponse resp = createCollection(testCollectionName, configSetName, numShards, replicationFactor, maxShardsPerNode);
if (resp.getResponse().get("failure") != null) {
CollectionAdminRequest.Delete req = CollectionAdminRequest.deleteCollection(testCollectionName);
req.process(cloudClient);
- resp = createCollection(testCollectionName, numShards, replicationFactor, maxShardsPerNode);
+ resp = createCollection(testCollectionName, configSetName, numShards, replicationFactor, maxShardsPerNode);
if (resp.getResponse().get("failure") != null) {
fail("Could not create " + testCollectionName);
[23/27] lucene-solr:feature/autoscaling: SOLR-10892: Phase 2: large
pages with lots of tables + lots of heading cleanups & TOC placement changes
Posted by sh...@apache.org.
SOLR-10892: Phase 2: large pages with lots of tables + lots of heading cleanups & TOC placement changes
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/93c96b06
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/93c96b06
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/93c96b06
Branch: refs/heads/feature/autoscaling
Commit: 93c96b06fb8ffa1f4a424356d699820d8e3c4d8f
Parents: 8da926e
Author: Cassandra Targett <ct...@apache.org>
Authored: Mon Jun 26 22:16:40 2017 -0500
Committer: Cassandra Targett <ct...@apache.org>
Committed: Mon Jun 26 22:17:59 2017 -0500
----------------------------------------------------------------------
solr/solr-ref-guide/src/collections-api.adoc | 1044 +++++++++---------
solr/solr-ref-guide/src/coreadmin-api.adoc | 276 +++--
solr/solr-ref-guide/src/format-of-solr-xml.adoc | 174 +--
solr/solr-ref-guide/src/function-queries.adoc | 410 +++++--
solr/solr-ref-guide/src/highlighting.adoc | 299 +++--
solr/solr-ref-guide/src/other-parsers.adoc | 169 +--
solr/solr-ref-guide/src/query-re-ranking.adoc | 15 +-
solr/solr-ref-guide/src/schema-api.adoc | 361 ++----
.../src/solr-control-script-reference.adoc | 520 +++++----
9 files changed, 1747 insertions(+), 1521 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/93c96b06/solr/solr-ref-guide/src/collections-api.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/collections-api.adoc b/solr/solr-ref-guide/src/collections-api.adoc
index 3b8541e..3a43d39 100644
--- a/solr/solr-ref-guide/src/collections-api.adoc
+++ b/solr/solr-ref-guide/src/collections-api.adoc
@@ -1,6 +1,8 @@
= Collections API
:page-shortname: collections-api
:page-permalink: collections-api.html
+:page-toclevels: 1
+:page-tocclass: right
// 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
@@ -18,59 +20,91 @@
// specific language governing permissions and limitations
// under the License.
-The Collections API is used to enable you to create, remove, or reload collections, but in the context of SolrCloud you can also use it to create collections with a specific number of shards and replicas.
+The Collections API is used to create, remove, or reload collections.
+
+In the context of SolrCloud you can use it to create collections with a specific number of shards and replicas, move replicas or shards, and create or delete collection aliases.
[[CollectionsAPI-create]]
== CREATE: Create a Collection
-`/admin/collections?action=CREATE&name=_name_&numShards=_number_&replicationFactor=_number_&maxShardsPerNode=_number_&createNodeSet=_nodelist_&collection.configName=_configname_`
+`/admin/collections?action=CREATE&name=_name_`
+
+=== CREATE Parameters
-[[CollectionsAPI-Input]]
-=== Input
+The CREATE action allows the following parameters:
-*Query Parameters*
+`name`::
+The name of the collection to be created. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`router.name`::
+The router name that will be used. The router defines how documents will be distributed among the shards. Possible values are `implicit` or `compositeId`, which is the default.
++
+The `implicit` router does not automatically route documents to different shards. Whichever shard you indicate on the indexing request (or within each document) will be used as the destination for those documents.
++
+The `compositeId` router hashes the value in the uniqueKey field and looks up that hash in the collection's clusterstate to determine which shard will receive the document, with the additional ability to manually direct the routing.
++
+When using the `implicit` router, the `shards` parameter is required. When using the `compositeId` router, the `numShards` parameter is required.
++
+For more information, see also the section <<shards-and-indexing-data-in-solrcloud.adoc#ShardsandIndexingDatainSolrCloud-DocumentRouting,Document Routing>>.
-[cols="25,10,10,15,40",options="header"]
-|===
-|Key |Type |Required |Default |Description
-|name |string |Yes | |The name of the collection to be created.
-|router.name |string |No |compositeId |The router name that will be used. The router defines how documents will be distributed among the shards. Possible values are *implicit* or *compositeId*.
+`numShards`::
+The number of shards to be created as part of the collection. This is a required parameter when the `router.name` is `compositeId`.
-The 'implicit' router does not automatically route documents to different shards. Whichever shard you indicate on the indexing request (or within each document) will be used as the destination for those documents.
+`shards`::
+A comma separated list of shard names, e.g., `shard-x,shard-y,shard-z`. This is a required parameter when the `router.name` is `implicit`.
-The 'compositeId' router hashes the value in the uniqueKey field and looks up that hash in the collection's clusterstate to determine which shard will receive the document, with the additional ability to manually direct the routing.
+`replicationFactor`::
+The number of replicas to be created for each shard. The default is `1`.
-When using the 'implicit' router, the `shards` parameter is required. When using the 'compositeId' router, the `numShards` parameter is required.
+`maxShardsPerNode`::
+When creating collections, the shards and/or replicas are spread across all available (i.e., live) nodes, and two replicas of the same shard will never be on the same node.
++
+If a node is not live when the CREATE action is called, it will not get any parts of the new collection, which could lead to too many replicas being created on a single live node. Defining `maxShardsPerNode` sets a limit on the number of replicas the CREATE action will spread to each node.
++
+If the entire collection can not be fit into the live nodes, no collection will be created at all. The default `maxShardsPerNode` value is `1`.
-For more information, see also the section <<shards-and-indexing-data-in-solrcloud.adoc#ShardsandIndexingDatainSolrCloud-DocumentRouting,Document Routing>>.
-|numShards |integer |No |empty |The number of shards to be created as part of the collection. This is a required parameter when using the 'compositeId' router.
-|shards |string |No |empty |A comma separated list of shard names, e.g., shard-x,shard-y,shard-z. This is a required parameter when using the 'implicit' router.
-|replicationFactor |integer |No |1 |The number of replicas to be created for each shard.
-|maxShardsPerNode |integer |No |1 |When creating collections, the shards and/or replicas are spread across all available (i.e., live) nodes, and two replicas of the same shard will never be on the same node. If a node is not live when the CREATE operation is called, it will not get any parts of the new collection, which could lead to too many replicas being created on a single live node. Defining `maxShardsPerNode` sets a limit on the number of replicas CREATE will spread to each node. If the entire collection can not be fit into the live nodes, no collection will be created at all.
-|createNodeSet |string |No | |Allows defining the nodes to spread the new collection across. If not provided, the CREATE operation will create shard-replica spread across all live Solr nodes. The format is a comma-separated list of node_names, such as `localhost:8983_solr,` `localhost:8984_solr,` `localhost:8985_solr`. Alternatively, use the special value of `EMPTY` to initially create no shard-replica within the new collection and then later use the <<CollectionsAPI-addreplica,ADDREPLICA>> operation to add shard-replica when and where required.
-|createNodeSet.shuffle |boolean |No |true a|
-Controls wether or not the shard-replicas created for this collection will be assigned to the nodes specified by the createNodeSet in a sequential manner, or if the list of nodes should be shuffled prior to creating individual replicas. A 'false' value makes the results of a collection creation predictible and gives more exact control over the location of the individual shard-replicas, but 'true' can be a better choice for ensuring replicas are distributed evenly across nodes.
-
-Ignored if createNodeSet is not also specified.
-
-|collection.configName |string |No |empty |Defines the name of the configurations (which must already be stored in ZooKeeper) to use for this collection. If not provided, Solr will default to the collection name as the configuration name.
-|router.field |string |No |empty |If this field is specified, the router will look at the value of the field in an input document to compute the hash and identify a shard instead of looking at the `uniqueKey` field. If the field specified is null in the document, the document will be rejected. Please note that <<realtime-get.adoc#realtime-get,RealTime Get>> or retrieval by id would also require the parameter `\_route_` (or `shard.keys`) to avoid a distributed search.
-|property._name_=_value_ |string |No | |Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
-|autoAddReplicas |boolean |No |false |When set to true, enables auto addition of replicas on shared file systems. See the section <<running-solr-on-hdfs.adoc#RunningSolronHDFS-AutomaticallyAddReplicasinSolrCloud,autoAddReplicas Settings>> for more details on settings and overrides.
-|async |string |No | |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|rule |string |No | |Replica placement rules. See the section <<rule-based-replica-placement.adoc#rule-based-replica-placement,Rule-based Replica Placement>> for details.
-|snitch |string |No | |Details of the snitch provider. See the section <<rule-based-replica-placement.adoc#rule-based-replica-placement,Rule-based Replica Placement>> for details.
-|===
-
-[[CollectionsAPI-Output]]
-=== Output
+`createNodeSet`::
+Allows defining the nodes to spread the new collection across. The format is a comma-separated list of node_names, such as `localhost:8983_solr,localhost:8984_solr,localhost:8985_solr`.
++
+If not provided, the CREATE operation will create shard-replicas spread across all live Solr nodes.
++
+Alternatively, use the special value of `EMPTY` to initially create no shard-replica within the new collection and then later use the <<CollectionsAPI-addreplica,ADDREPLICA>> operation to add shard-replicas when and where required.
+
+`createNodeSet.shuffle`::
+Controls wether or not the shard-replicas created for this collection will be assigned to the nodes specified by the `createNodeSet` in a sequential manner, or if the list of nodes should be shuffled prior to creating individual replicas.
++
+A `false` value makes the results of a collection creation predictable and gives more exact control over the location of the individual shard-replicas, but `true` can be a better choice for ensuring replicas are distributed evenly across nodes. The default is `true`.
++
+This parameter is ignored if `createNodeSet` is not also specified.
+
+`collection.configName`::
+Defines the name of the configurations (which *must already be stored in ZooKeeper*) to use for this collection. If not provided, Solr will default to the collection name as the configuration name.
+
+`router.field`::
+If this parameter is specified, the router will look at the value of the field in an input document to compute the hash and identify a shard instead of looking at the `uniqueKey` field. If the field specified is null in the document, the document will be rejected.
++
+Please note that <<realtime-get.adoc#realtime-get,RealTime Get>> or retrieval by document ID would also require the parameter `\_route_` (or `shard.keys`) to avoid a distributed search.
+
+`property._name_=_value_`::
+Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
+
+`autoAddReplicas`::
+When set to `true`, enables automatic addition of replicas on shared file systems (such as HDFS) only. See the section <<running-solr-on-hdfs.adoc#RunningSolronHDFS-AutomaticallyAddReplicasinSolrCloud,autoAddReplicas Settings>> for more details on settings and overrides. The default is `false`.
+
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
+
+`rule`::
+Replica placement rules. See the section <<rule-based-replica-placement.adoc#rule-based-replica-placement,Rule-based Replica Placement>> for details.
+
+`snitch`::
+Details of the snitch provider. See the section <<rule-based-replica-placement.adoc#rule-based-replica-placement,Rule-based Replica Placement>> for details.
+
+=== CREATE Response
The response will include the status of the request and the new core names. If the status is anything other than "success", an error message will explain why the request failed.
-[[CollectionsAPI-Examples]]
-=== Examples
+=== Examples using CREATE
*Input*
@@ -112,19 +146,16 @@ http://localhost:8983/solr/admin/collections?action=CREATE&name=newCollection&nu
`/admin/collections?action=MODIFYCOLLECTION&collection=_<collection-name>&<attribute-name>=<attribute-value>&<another-attribute-name>=<another-value>_`
-It's possible to edit multiple attributes at a time. Changing these values only updates the z-node on ZooKeeper, they do not change the topology of the collection. For instance, increasing replicationFactor will _not_ automatically add more replicas to the collection but _will_ allow more ADDREPLICA commands to succeed.
-
-*Query Parameters*
+It's possible to edit multiple attributes at a time. Changing these values only updates the z-node on ZooKeeper, they do not change the topology of the collection. For instance, increasing `replicationFactor` will _not_ automatically add more replicas to the collection but _will_ allow more ADDREPLICA commands to succeed.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+=== MODIFYCOLLECTION Parameters
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection to be modified.
-|<attribute-name> |string |Yes a|
-Key-value pairs of attribute names and attribute values.
+`collection`::
+The name of the collection to be modified. This parameter is required.
+`_attribute_=_value_`::
+Key-value pairs of attribute names and attribute values. At least one of these is required.
++
The attributes that can be modified are:
* maxShardsPerNode
@@ -133,10 +164,9 @@ The attributes that can be modified are:
* collection.configName
* rule
* snitch
++
+See the <<CollectionsAPI-create,CREATE action>> section above for details on these attributes.
-See the <<CollectionsAPI-create,CREATE>> section above for details on these attributes.
-
-|===
[[CollectionsAPI-reload]]
== RELOAD: Reload a Collection
@@ -145,28 +175,19 @@ See the <<CollectionsAPI-create,CREATE>> section above for details on these attr
The RELOAD action is used when you have changed a configuration in ZooKeeper.
-[[CollectionsAPI-Input.1]]
-=== Input
+=== RELOAD Parameters
-*Query Parameters*
+|`name`::
+The name of the collection to reload. This parameter is required.
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|name |string |Yes |The name of the collection to reload.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
-
-[[CollectionsAPI-Output.1]]
-=== Output
+=== RELOAD Response
The response will include the status of the request and the cores that were reloaded. If the status is anything other than "success", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.1]]
-=== Examples
+=== Examples using RELOAD
*Input*
@@ -208,41 +229,43 @@ http://localhost:8983/solr/admin/collections?action=RELOAD&name=newCollection
Splitting a shard will take an existing shard and break it into two pieces which are written to disk as two (new) shards. The original shard will continue to contain the same data as-is but it will start re-routing requests to the new shards. The new shards will have as many replicas as the original shard. A soft commit is automatically issued after splitting a shard so that documents are made visible on sub-shards. An explicit commit (hard or soft) is not necessary after a split operation because the index is automatically persisted to disk during the split operation.
-This command allows for seamless splitting and requires no downtime. A shard being split will continue to accept query and indexing requests and will automatically start routing them to the new shards once this operation is complete. This command can only be used for SolrCloud collections created with `numShards` parameter, meaning collections which rely on Solr's hash-based routing mechanism.
+This command allows for seamless splitting and requires no downtime. A shard being split will continue to accept query and indexing requests and will automatically start routing requests to the new shards once this operation is complete. This command can only be used for SolrCloud collections created with `numShards` parameter, meaning collections which rely on Solr's hash-based routing mechanism.
-The split is performed by dividing the original shard's hash range into two equal partitions and dividing up the documents in the original shard according to the new sub-ranges.
+The split is performed by dividing the original shard's hash range into two equal partitions and dividing up the documents in the original shard according to the new sub-ranges. Two parameters discussed below, `ranges` and `split.key` provide further control over how the split occurs.
-One can also specify an optional `ranges` parameter to divide the original shard's hash range into arbitrary hash range intervals specified in hexadecimal. For example, if the original hash range is 0-1500 then adding the parameter: ranges=0-1f4,1f5-3e8,3e9-5dc will divide the original shard into three shards with hash range 0-500, 501-1000 and 1001-1500 respectively.
+Shard splitting can be a long running process. In order to avoid timeouts, you should run this as an <<CollectionsAPI-async,asynchronous call>>.
-Another optional parameter `split.key` can be used to split a shard using a route key such that all documents of the specified route key end up in a single dedicated sub-shard. Providing the 'shard' parameter is not required in this case because the route key is enough to figure out the right shard. A route key which spans more than one shard is not supported. For example, suppose `split.key=A!` hashes to the range 12-15 and belongs to shard 'shard1' with range 0-20 then splitting by this route key would yield three sub-shards with ranges 0-11, 12-15 and 16-20. Note that the sub-shard with the hash range of the route key may also contain documents for other route keys whose hash ranges overlap.
+=== SPLITSHARD Parameters
-Shard splitting can be a long running process. In order to avoid timeouts, you should run this as an <<CollectionsAPI-async,asynchronous call>>.
+`collection`::
+The name of the collection that includes the shard to be split. This parameter is required.
-[[CollectionsAPI-Input.2]]
-=== Input
+`shard`::
+The name of the shard to be split. This parameter is required when `split.key` is not specified.
-*Query Parameters*
+`ranges`::
+A comma-separated list of hash ranges in hexadecimal, such as `ranges=0-1f4,1f5-3e8,3e9-5dc`.
++
+This parameter can be used to divide the original shard's hash range into arbitrary hash range intervals specified in hexadecimal. For example, if the original hash range is `0-1500` then adding the parameter: `ranges=0-1f4,1f5-3e8,3e9-5dc` will divide the original shard into three shards with hash range `0-500`, `501-1000`, and `1001-1500` respectively.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`split.key`::
+The key to use for splitting the index.
++
+This parameter can be used to split a shard using a route key such that all documents of the specified route key end up in a single dedicated sub-shard. Providing the `shard` parameter is not required in this case because the route key is enough to figure out the right shard. A route key which spans more than one shard is not supported.
++
+For example, suppose `split.key=A!` hashes to the range `12-15` and belongs to shard 'shard1' with range `0-20`. Splitting by this route key would yield three sub-shards with ranges `0-11`, `12-15` and `16-20`. Note that the sub-shard with the hash range of the route key may also contain documents for other route keys whose hash ranges overlap.
-[cols="25,15,10,50",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection that includes the shard to be split.
-|shard |string |Yes |The name of the shard to be split.
-|ranges |string |No |A comma-separated list of hash ranges in hexadecimal, such as `ranges=0-1f4,1f5-3e8,3e9-5dc`.
-|split.key |string |No |The key to use for splitting the index.
-|property._name_=_value_ |string |No |Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>
-|===
+`property._name_=_value_`::
+Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
-[[CollectionsAPI-Output.2]]
-=== Output
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>
+
+=== SPLITSHARD Response
The output will include the status of the request and the new shard names, which will use the original shard as their basis, adding an underscore and a number. For example, "shard1" will become "shard1_0" and "shard1_1". If the status is anything other than "success", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.2]]
-=== Examples
+=== Examples using SPLITSHARD
*Input*
@@ -318,34 +341,36 @@ http://localhost:8983/solr/admin/collections?action=SPLITSHARD&collection=anothe
[[CollectionsAPI-createshard]]
== CREATESHARD: Create a Shard
-Shards can only created with this API for collections that use the 'implicit' router. Use SPLITSHARD for collections using the 'compositeId' router. A new shard with a name can be created for an existing 'implicit' collection.
+Shards can only created with this API for collections that use the 'implicit' router (i.e., when the collection was created, `router.name=implicit`). A new shard with a name can be created for an existing 'implicit' collection.
+
+Use SPLITSHARD for collections created with the 'compositeId' router (`router.key=compositeId`).
`/admin/collections?action=CREATESHARD&shard=_shardName_&collection=_name_`
-[[CollectionsAPI-Input.3]]
-=== Input
+=== CREATESHARD Parameters
+
+`collection`::
+The name of the collection that includes the shard to be split. This parameter is required.
+
+`shard`::
+The name of the shard to be created. This parameter is required.
-*Query Parameters*
+`createNodeSet`::
+Allows defining the nodes to spread the new collection across. If not provided, the CREATESHARD operation will create shard-replica spread across all live Solr nodes.
++
+The format is a comma-separated list of node_names, such as `localhost:8983_solr,localhost:8984_solr,localhost:8985_solr`.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`property._name_=_value_`::
+Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
-[cols="25,15,10,50",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection that includes the shard that will be splitted.
-|shard |string |Yes |The name of the shard to be created.
-|createNodeSet |string |No |Allows defining the nodes to spread the new collection across. If not provided, the CREATE operation will create shard-replica spread across all live Solr nodes. The format is a comma-separated list of node_names, such as `localhost:8983_solr,` `localhost:8984_solr,` `localhost:8985_solr`.
-|property._name_=_value_ |string |No |Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-[[CollectionsAPI-Output.3]]
-=== Output
+=== CREATESHARD Response
The output will include the status of the request. If the status is anything other than "success", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.3]]
-=== Examples
+=== Examples using CREATESHARD
*Input*
@@ -375,29 +400,31 @@ Deleting a shard will unload all replicas of the shard, remove them from `cluste
`/admin/collections?action=DELETESHARD&shard=_shardID_&collection=_name_`
-[[CollectionsAPI-Input.4]]
-=== Input
+=== DELETESHARD Parameters
-*Query Parameters*
+`collection`::
+The name of the collection that includes the shard to be deleted. This parameter is required.
-[cols="25,15,10,50",options="header",]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection that includes the shard to be deleted.
-|shard |string |Yes |The name of the shard to be deleted.
-|deleteInstanceDir |boolean |No |By default Solr will delete the entire instanceDir of each replica that is deleted. Set this to `false` to prevent the instance directory from being deleted.
-|deleteDataDir |boolean |No |By default Solr will delete the dataDir of each replica that is deleted. Set this to `false` to prevent the data directory from being deleted.
-|deleteIndex |boolean |No |By default Solr will delete the index of each replica that is deleted. Set this to `false` to prevent the index directory from being deleted.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
+`shard`::
+The name of the shard to be deleted. This parameter is required.
-[[CollectionsAPI-Output.4]]
-=== Output
+`deleteInstanceDir`::
+By default Solr will delete the entire instanceDir of each replica that is deleted. Set this to `false` to prevent the instance directory from being deleted.
+
+`deleteDataDir`::
+By default Solr will delete the dataDir of each replica that is deleted. Set this to `false` to prevent the data directory from being deleted.
+
+`deleteIndex`::
+By default Solr will delete the index of each replica that is deleted. Set this to `false` to prevent the index directory from being deleted.
+
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
+
+=== DELETESHARD Response
The output will include the status of the request. If the status is anything other than "success", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.4]]
-=== Examples
+=== Examples using DELETESHARD
*Input*
@@ -435,28 +462,24 @@ The `CREATEALIAS` action will create a new alias pointing to one or more collect
`/admin/collections?action=CREATEALIAS&name=_name_&collections=_collectionlist_`
-[[CollectionsAPI-Input.5]]
-=== Input
+=== CREATEALIAS Parameters
-*Query Parameters*
+`name`::
+The alias name to be created. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`collections`::
+A comma-separated list of collections to be aliased. The collections must already exist in the cluster. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|name |string |Yes |The alias name to be created.
-|collections |string |Yes |The list of collections to be aliased, separated by commas. They must already exist in the cluster.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
[[CollectionsAPI-Output.5]]
-=== Output
+=== CREATEALIAS Response
The output will simply be a responseHeader with details of the time it took to process the request. To confirm the creation of the alias, you can look in the Solr Admin UI, under the Cloud section and find the `aliases.json` file.
[[CollectionsAPI-Examples.5]]
-=== Examples
+=== Examples using CREATEALIAS
*Input*
@@ -479,41 +502,53 @@ http://localhost:8983/solr/admin/collections?action=CREATEALIAS&name=testalias&c
</response>
----
-== LISTALIASES: List Collection Aliases
-
-Lists all aliases for each collection.
+[[CollectionsAPI-listaliases]]
+== LISTALIASES: List of all aliases in the cluster
`/admin/collections?action=LISTALIASES`
-// TODO 6.6 examples
+The LISTALIASES action does not take any parameters.
+=== LISTALIASES Response
+
+The output will contain a list of aliases with the corresponding collection names.
+
+=== Examples using LISTALIASES
+
+*Output*
+
+[source,xml]
+----
+<response>
+ <lst name="responseHeader">
+ <int name="status">0</int>
+ <int name="QTime">0</int>
+ </lst>
+ <lst name="aliases">
+ <str name="testalias1">collection1</str>
+ <str name="testalias2">collection2</str>
+ </lst>
+</response>
+----
[[CollectionsAPI-deletealias]]
== DELETEALIAS: Delete a Collection Alias
`/admin/collections?action=DELETEALIAS&name=_name_`
-[[CollectionsAPI-Input.6]]
-=== Input
+=== DELETEALIAS Parameters
-*Query Parameters*
+`name`::
+The name of the alias to delete. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|name |string |Yes |The name of the alias to delete.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
-
-[[CollectionsAPI-Output.6]]
-=== Output
+=== DELETEALIAS Response
The output will simply be a responseHeader with details of the time it took to process the request. To confirm the removal of the alias, you can look in the Solr Admin UI, under the Cloud section, and find the `aliases.json` file.
-[[CollectionsAPI-Examples.6]]
-=== Examples
+=== Examples using DELETEALIAS
*Input*
@@ -536,62 +571,24 @@ http://localhost:8983/solr/admin/collections?action=DELETEALIAS&name=testalias
</response>
----
-[[CollectionsAPI-listaliases]]
-== LISTALIASES: List of all aliases in the cluster
-
-`/admin/collections?action=LISTALIASES`
-
-[[CollectionsAPI-Output.27]]
-=== Output
-
-The output will contain a list of aliases with the corresponding collection names.
-
-[[CollectionsAPI-Examples.27]]
-=== Examples
-
-*Output*
-
-[source,xml]
-----
-<response>
- <lst name="responseHeader">
- <int name="status">0</int>
- <int name="QTime">0</int>
- </lst>
- <lst name="aliases">
- <str name="testalias1">collection1</str>
- <str name="testalias2">collection2</str>
- </lst>
-</response>
-----
-
-
[[CollectionsAPI-delete]]
== DELETE: Delete a Collection
`/admin/collections?action=DELETE&name=_collection_`
-[[CollectionsAPI-Input.7]]
-=== Input
-
-*Query Parameters*
+=== DELETE Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`name`::
+The name of the collection to delete. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|name |string |Yes |The name of the collection to delete.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-[[CollectionsAPI-Output.7]]
-=== Output
+=== DELETE Response
The response will include the status of the request and the cores that were deleted. If the status is anything other than "success", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.7]]
-=== Examples
+=== Examples using DELETE
*Input*
@@ -631,33 +628,46 @@ http://localhost:8983/solr/admin/collections?action=DELETE&name=newCollection
[[CollectionsAPI-deletereplica]]
== DELETEREPLICA: Delete a Replica
-Delete a named replica from the specified collection and shard. If the corresponding core is up and running the core is unloaded, the entry is removed from the clusterstate, and (by default) delete the instanceDir and dataDir. If the node/core is down, the entry is taken off the clusterstate and if the core comes up later it is automatically unregistered.
+Deletes a named replica from the specified collection and shard.
+
+If the corresponding core is up and running the core is unloaded, the entry is removed from the clusterstate, and (by default) delete the instanceDir and dataDir. If the node/core is down, the entry is taken off the clusterstate and if the core comes up later it is automatically unregistered.
`/admin/collections?action=DELETEREPLICA&collection=_collection_&shard=_shard_&replica=_replica_`
-[[CollectionsAPI-Input.8]]
-=== Input
+=== DELETEREPLICA Parameters
+
+`collection`::
+The name of the collection. This parameter is required.
+
+`shard`::
+The name of the shard that includes the replica to be removed. This parameter is required.
+
+`replica`::
+The name of the replica to remove.
++
+If `count` is used instead, this parameter is not required. Otherwise, this parameter must be supplied.
+
+`count`::
+The number of replicas to remove. If the requested number exceeds the number of replicas, no replicas will be deleted. If there is only one replica, it will not be removed.
++
+If `replica` is used instead, this parameter is not required. Otherwise, this parameter must be supplied.
+
+`deleteInstanceDir`::
+By default Solr will delete the entire instanceDir of the replica that is deleted. Set this to `false` to prevent the instance directory from being deleted.
-*Query Parameters*
+`deleteDataDir`::
+By default Solr will delete the dataDir of the replica that is deleted. Set this to `false` to prevent the data directory from being deleted.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`deleteIndex`::
+By default Solr will delete the index of the replica that is deleted. Set this to `false` to prevent the index directory from being deleted.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection.
-|shard |string |Yes |The name of the shard that includes the replica to be removed.
-|replica |string |No |The name of the replica to remove. Not required if `count` is used instead.
-|count |integer |No |The number of replicas to remove. If the requested number exceeds the number of replicas, no replicas will be deleted. If there is only one replica, it will not be removed. This parameter is not required if `replica` is used instead.
-|deleteInstanceDir |boolean |No |By default Solr will delete the entire instanceDir of the replica that is deleted. Set this to `false` to prevent the instance directory from being deleted.
-|deleteDataDir |boolean |No |By default Solr will delete the dataDir of the replica that is deleted. Set this to `false` to prevent the data directory from being deleted.
-|deleteIndex |boolean |No |By default Solr will delete the index of the replica that is deleted. Set this to `false` to prevent the index directory from being deleted.
-|onlyIfDown |boolean |No |When set to 'true' will not take any action if the replica is active. Default 'false'
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
+`onlyIfDown`::
+When set to `true`, no action will be taken if the replica is active. Default `false`.
-[[CollectionsAPI-Examples.8]]
-=== Examples
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
+
+=== Examples using DELETEREPLICA
*Input*
@@ -685,36 +695,36 @@ Add a replica to a shard in a collection. The node name can be specified if the
`/admin/collections?action=ADDREPLICA&collection=_collection_&shard=_shard_&node=_nodeName_`
-[[CollectionsAPI-Input.9]]
-=== Input
-
-*Query Parameters*
+=== ADDREPLICA Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`collection`::
+The name of the collection where the replica should be created. This parameter is required.
-[cols="25,15,10,50",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection.
-|shard |string |Yes* a|
+`shard`::
The name of the shard to which replica is to be added.
++
+If `shard` is not specified, then `\_route_` must be.
+
+`\_route_`::
+If the exact shard name is not known, users may pass the `\_route_` value and the system would identify the name of the shard.
++
+Ignored if the `shard` param is also specified.
+
+`node`::
+The name of the node where the replica should be created.
-If shard is not specified, then _route_ must be.
+`instanceDir`::
+The instanceDir for the core that will be created
-|_route_ |string |No* a|
-If the exact shard name is not known, users may pass the _route_ value and the system would identify the name of the shard.
+`dataDir`::
+The directory in which the core should be created
-Ignored if the shard param is also specified.
+`property._name_=_value_`::
+Set core property _name_ to _value_. See <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details about supported properties and values.
-|node |string |No |The name of the node where the replica should be created
-|instanceDir |string |No |The instanceDir for the core that will be created
-|dataDir |string |No |The directory in which the core should be created
-|property._name_=_value_ |string |No |Set core property _name_ to _value_. See <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>>.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>
-|===
+`async`:: string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>
-[[CollectionsAPI-Examples.9]]
-=== Examples
+=== Examples using ADDREPLICA
*Input*
@@ -751,27 +761,19 @@ Add, edit or delete a cluster-wide property.
`/admin/collections?action=CLUSTERPROP&name=_propertyName_&val=_propertyValue_`
-[[CollectionsAPI-Input.10]]
-=== Input
+=== CLUSTERPROP Parameters
-*Query Parameters*
+`name`::
+The name of the property. Supported properties names are `urlScheme` and `autoAddReplicas and location`. Other names are rejected with an error.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`val`::
+The value of the property. If the value is empty or null, the property is unset.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|name |string |Yes |The name of the property. The supported properties names are `urlScheme` and `autoAddReplicas and location`. Other names are rejected with an error.
-|val |string |Yes |The value of the property. If the value is empty or null, the property is unset.
-|===
-
-[[CollectionsAPI-Output.8]]
-=== Output
+=== CLUSTERPROP Response
The response will include the status of the request and the properties that were updated or removed. If the status is anything other than "0", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.10]]
-=== Examples
+=== Examples using CLUSTERPROP
*Input*
@@ -797,41 +799,41 @@ http://localhost:8983/solr/admin/collections?action=CLUSTERPROP&name=urlScheme&v
`/admin/collections?action=MIGRATE&collection=_name_&split.key=_key1!_&target.collection=_target_collection_&forward.timeout=60`
-The MIGRATE command is used to migrate all documents having the given routing key to another collection. The source collection will continue to have the same data as-is but it will start re-routing write requests to the target collection for the number of seconds specified by the forward.timeout parameter. It is the responsibility of the user to switch to the target collection for reads and writes after the ‘migrate’ command completes.
+The MIGRATE command is used to migrate all documents having a given routing key to another collection. The source collection will continue to have the same data as-is but it will start re-routing write requests to the target collection for the number of seconds specified by the `forward.timeout` parameter. It is the responsibility of the user to switch to the target collection for reads and writes after the MIGRATE action completes.
The routing key specified by the `split.key` parameter may span multiple shards on both the source and the target collections. The migration is performed shard-by-shard in a single thread. One or more temporary collections may be created by this command during the ‘migrate’ process but they are cleaned up at the end automatically.
-This is a long running operation and therefore using the `async` parameter is highly recommended. If the async parameter is not specified then the operation is synchronous by default and keeping a large read timeout on the invocation is advised. Even with a large read timeout, the request may still timeout due to inherent limitations of the Collection APIs but that doesn’t necessarily mean that the operation has failed. Users should check logs, cluster state, source and target collections before invoking the operation again.
+This is a long running operation and therefore using the `async` parameter is highly recommended. If the `async` parameter is not specified then the operation is synchronous by default and keeping a large read timeout on the invocation is advised. Even with a large read timeout, the request may still timeout but that doesn’t necessarily mean that the operation has failed. Users should check logs, cluster state, source and target collections before invoking the operation again.
+
+This command works only with collections using the compositeId router. The target collection must not receive any writes during the time the MIGRATE command is running otherwise some writes may be lost.
+
+Please note that the MIGRATE API does not perform any de-duplication on the documents so if the target collection contains documents with the same uniqueKey as the documents being migrated then the target collection will end up with duplicate documents.
-This command works only with collections having the compositeId router. The target collection must not receive any writes during the time the migrate command is running otherwise some writes may be lost.
+=== MIGRATE Parameters
-Please note that the migrate API does not perform any de-duplication on the documents so if the target collection contains documents with the same uniqueKey as the documents being migrated then the target collection will end up with duplicate documents.
+`collection`::
+The name of the source collection from which documents will be split. This parameter is required.
-[[CollectionsAPI-Input.11]]
-=== Input
+`target.collection`::
+The name of the target collection to which documents will be migrated. This parameter is required.
-*Query Parameters*
+`split.key`::
+The routing key prefix. For example, if the uniqueKey of a document is "a!123", then you would use `split.key=a!`. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`forward.timeout`::
+The timeout, in seconds, until which write requests made to the source collection for the given `split.key` will be forwarded to the target shard. The default is 60 seconds.
-[cols="25,15,10,50",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the source collection from which documents will be split.
-|target.collection |string |Yes |The name of the target collection to which documents will be migrated.
-|split.key |string |Yes |The routing key prefix. For example, if uniqueKey is a!123, then you would use `split.key=a!`.
-|forward.timeout |int |No |The timeout, in seconds, until which write requests made to the source collection for the given `split.key` will be forwarded to the target shard. The default is 60 seconds.
-|property._name_=_value_ |string |No |Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
+`property._name_=_value_`::
+Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
-[[CollectionsAPI-Output.9]]
-=== Output
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
+
+=== MIGRATE Response
The response will include the status of the request.
-[[CollectionsAPI-Examples.11]]
-=== Examples
+=== Examples using MIGRATE
*Input*
@@ -991,29 +993,23 @@ http://localhost:8983/solr/admin/collections?action=MIGRATE&collection=test1&spl
`/admin/collections?action=ADDROLE&role=_roleName_&node=_nodeName_`
-Assign a role to a given node in the cluster. The only supported role as of 4.7 is 'overseer'. Use this API to dedicate a particular node as Overseer. Invoke it multiple times to add more nodes. This is useful in large clusters where an Overseer is likely to get overloaded. If available, one among the list of nodes which are assigned the 'overseer' role would become the overseer. The system would assign the role to any other node if none of the designated nodes are up and running.
+Assigns a role to a given node in the cluster. The only supported role is `overseer`.
-[[CollectionsAPI-Input.12]]
-=== Input
+Use this command to dedicate a particular node as Overseer. Invoke it multiple times to add more nodes. This is useful in large clusters where an Overseer is likely to get overloaded. If available, one among the list of nodes which are assigned the 'overseer' role would become the overseer. The system would assign the role to any other node if none of the designated nodes are up and running.
-*Query Parameters*
+=== ADDROLE Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`role`::
+The name of the role. The only supported role as of now is `overseer`. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|role |string |Yes |The name of the role. The only supported role as of now is _overseer_.
-|node |string |Yes |The name of the node. It is possible to assign a role even before that node is started.
-|===
+`node`::
+|The name of the node that will be assigned the role. It is possible to assign a role even before that node is started. This parameter is started.
-[[CollectionsAPI-Output.10]]
-=== Output
+=== ADDROLE Response
The response will include the status of the request and the properties that were updated or removed. If the status is anything other than "0", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.12]]
-=== Examples
+=== Examples using ADDROLE
*Input*
@@ -1041,27 +1037,21 @@ Remove an assigned role. This API is used to undo the roles assigned using ADDRO
`/admin/collections?action=REMOVEROLE&role=_roleName_&node=_nodeName_`
-[[CollectionsAPI-Input.13]]
-=== Input
+=== REMOVEROLE Parameters
-*Query Parameters*
+`role`::
+The name of the role. The only supported role as of now is `overseer`. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`node`::
+The name of the node where the role should be removed.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|role |string |Yes |The name of the role. The only supported role as of now is _overseer_.
-|node |string |Yes |The name of the node.
-|===
[[CollectionsAPI-Output.11]]
-=== Output
+=== REMOVEROLE Response
The response will include the status of the request and the properties that were updated or removed. If the status is anything other than "0", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.13]]
-=== Examples
+=== Examples using REMOVEROLE
*Input*
@@ -1089,8 +1079,7 @@ Returns the current status of the overseer, performance statistics of various ov
`/admin/collections?action=OVERSEERSTATUS`
-[[CollectionsAPI-Examples.14]]
-=== Examples
+=== Examples using OVERSEERSTATUS
*Input:*
@@ -1164,28 +1153,23 @@ Fetch the cluster status including collections, shards, replicas, configuration
`/admin/collections?action=CLUSTERSTATUS`
-[[CollectionsAPI-Input.14]]
-=== Input
+=== CLUSTERSTATUS Parameters
-*Query Parameters*
+`collection`::
+The collection name for which information is requested. If omitted, information on all collections in the cluster will be returned.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`shard`::
+The shard(s) for which information is requested. Multiple shard names can be specified as a comma-separated list.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |No |The collection name for which information is requested. If omitted, information on all collections in the cluster will be returned.
-|shard |string |No |The shard(s) for which information is requested. Multiple shard names can be specified as a comma separated list.
-|_route_ |string |No |This can be used if you need the details of the shard where a particular document belongs to and you don't know which shard it falls under.
-|===
+`\_route_`::
+This can be used if you need the details of the shard where a particular document belongs to and you don't know which shard it falls under.
-[[CollectionsAPI-Output.12]]
-=== Output
+=== CLUSTERSTATUS Response
The response will include the status of the request and the status of the cluster.
[[CollectionsAPI-Examples.15]]
-=== Examples
+=== Examples using CLUSTERSTATUS
*Input*
@@ -1270,23 +1254,14 @@ Request the status and response of an already submitted <<CollectionsAPI-async,A
`/admin/collections?action=REQUESTSTATUS&requestid=_request-id_`
-[[CollectionsAPI-Input.15]]
-=== Input
-
-*Query Parameters*
+=== REQUESTSTATUS Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`requestid`::
+The user defined request ID for the request. This can be used to track the status of the submitted asynchronous task. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|requestid |string |Yes |The user defined request-id for the request. This can be used to track the status of the submitted asynchronous task.
-|===
+=== Examples using REQUESTSTATUS
-[[CollectionsAPI-Examples.16]]
-=== Examples
-
-*Input: Valid Request Status*
+*Input: Valid Request ID*
[source,text]
----
@@ -1309,7 +1284,7 @@ http://localhost:8983/solr/admin/collections?action=REQUESTSTATUS&requestid=1000
</response>
----
-*Input: Invalid RequestId*
+*Input: Invalid Request ID*
[source,text]
----
@@ -1335,28 +1310,21 @@ http://localhost:8983/solr/admin/collections?action=REQUESTSTATUS&requestid=1004
[[CollectionsAPI-deletestatus]]
== DELETESTATUS: Delete Status
-Delete the stored response of an already failed or completed <<CollectionsAPI-async,Asynchronous Collection API>> call.
+Deletes the stored response of an already failed or completed <<CollectionsAPI-async,Asynchronous Collection API>> call.
`/admin/collections?action=DELETESTATUS&requestid=_request-id_`
-[[CollectionsAPI-Input.16]]
-=== Input
-
-*Query Parameters*
+=== DELETESTATUS Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`requestid`::
+The request ID of the asynchronous call whose stored response should be cleared.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|requestid |string |No |The request-id of the async call we need to clear the stored response for.
-|flush |boolean |No |Set to true to clear all stored completed and failed async request responses.
-|===
+`flush`::
+Set to `true` to clear all stored completed and failed async request responses.
-[[CollectionsAPI-Examples.17]]
-=== Examples
+=== Examples using DELETESTATUS
-*Input: Valid Request Status*
+*Input: Valid Request ID*
[source,text]
----
@@ -1376,7 +1344,7 @@ http://localhost:8983/solr/admin/collections?action=DELETESTATUS&requestid=foo
</response>
----
-*Input: Invalid RequestId*
+*Input: Invalid Request ID*
[source,text]
----
@@ -1396,7 +1364,7 @@ http://localhost:8983/solr/admin/collections?action=DELETESTATUS&requestid=bar
</response>
----
-*Input: Clear all the stored statuses*
+*Input: Clear All Stored Statuses*
[source,text]
----
@@ -1423,8 +1391,7 @@ Fetch the names of the collections in the cluster.
`/admin/collections?action=LIST`
-[[CollectionsAPI-Example]]
-=== Example
+=== Examples using LIST
*Input*
@@ -1453,44 +1420,47 @@ Assign an arbitrary property to a particular replica and give it the value speci
`/admin/collections?action=ADDREPLICAPROP&collection=collectionName&shard=shardName&replica=replicaName&property=propertyName&property.value=value`
-[[CollectionsAPI-Input.17]]
-=== Input
+=== ADDREPLICAPROP Parameters
-*Query Parameters*
+`collection`::
+The name of the collection the replica belongs to. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`shard`::
+The name of the shard the replica belongs to. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection this replica belongs to.
-|shard |string |Yes |The name of the shard the replica belongs to.
-|replica |string |Yes |The replica, e.g. core_node1.
-|property |string |Yes a|
-The property to add. Note: this will have the literal 'property.' prepended to distinguish it from system-maintained properties. So these two forms are equivalent:
+`replica`::
+The replica, e.g., `core_node1`. This parameter is required.
+`property`::
+The name of the property to add. This property is required.
++
+This will have the literal `property.` prepended to distinguish it from system-maintained properties. So these two forms are equivalent:
++
`property=special`
-
++
and
-
++
`property=property.special`
-|property.value |string |Yes |The value to assign to the property.
-|shardUnique |Boolean |No |default: false. If true, then setting this property in one replica will remove the property from all other replicas in that shard.
-There is one pre-defined property `preferredLeader` for which `shardUnique` is forced to 'true' and an error returned if `shardUnique` is explicitly set to 'false'. `PreferredLeader` is a boolean property, any value assigned that is not equal (case insensitive) to 'true' will be interpreted as 'false' for `preferredLeader`.
-|===
+`property.value`::
+The value to assign to the property. This parameter is required.
-[[CollectionsAPI-Output.13]]
-=== Output
+`shardUnique`::
+If `true`, then setting this property in one replica will remove the property from all other replicas in that shard. The default is `false`.
++
+There is one pre-defined property `preferredLeader` for which `shardUnique` is forced to `true` and an error returned if `shardUnique` is explicitly set to `false`.
++
+`PreferredLeader` is a boolean property. Any value assigned that is not equal (case insensitive) to `true` will be interpreted as `false` for `preferredLeader`.
+
+=== ADDREPLICAPROP Response
The response will include the status of the request. If the status is anything other than "0", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.18]]
-=== Examples
+=== Examples using ADDREPLICAPROP
*Input*
-This command would set the preferredLeader (`property.preferredLeader`) to true on core_node1, and remove that property from any other replica in the shard.
+This command would set the "preferredLeader" property (`property.preferredLeader`) to "true" on "core_node1", and remove that property from any other replica in the shard.
[source,text]
----
@@ -1511,7 +1481,7 @@ http://localhost:8983/solr/admin/collections?action=ADDREPLICAPROP&shard=shard1&
*Input*
-This pair of commands will set the "testprop" (`property.testprop`) to 'value1' and 'value2' respectively for two nodes in the same shard.
+This pair of commands will set the "testprop" property (`property.testprop`) to 'value1' and 'value2' respectively for two nodes in the same shard.
[source,text]
----
@@ -1522,7 +1492,7 @@ http://localhost:8983/solr/admin/collections?action=ADDREPLICAPROP&shard=shard1&
*Input*
-This pair of commands would result in core_node_3 having the testprop (`property.testprop`) value set because the second command specifies `shardUnique=true`, which would cause the property to be removed from core_node_1.
+This pair of commands would result in "core_node_3" having the "testprop" property (`property.testprop`) value set because the second command specifies `shardUnique=true`, which would cause the property to be removed from "core_node_1".
[source,text]
----
@@ -1538,36 +1508,31 @@ Deletes an arbitrary property from a particular replica.
`/admin/collections?action=DELETEREPLICAPROP&collection=collectionName&shard=_shardName_&replica=_replicaName_&property=_propertyName_`
-[[CollectionsAPI-Input.18]]
-=== Input
+=== DELETEREPLICAPROP Parameters
-*Query Parameters*
+`collection`::
+The name of the collection the replica belongs to. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`shard`::
+The name of the shard the replica belongs to. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection this replica belongs to
-|shard |string |Yes |The name of the shard the replica belongs to.
-|replica |string |Yes |The replica, e.g. core_node1.
-|property |string |Yes a|
-The property to add. Note: this will have the literal 'property.' prepended to distinguish it from system-maintained properties. So these two forms are equivalent:
+`replica`::
+The replica, e.g. `core_node1`. This parameter is required.
+`property`::
+The property to add. This will have the literal `property.` prepended to distinguish it from system-maintained properties. So these two forms are equivalent:
++
`property=special`
-
++
and
-
++
`property=property.special`
-|===
-[[CollectionsAPI-Output.14]]
-=== Output
+=== DELETEREPLICAPROP Response
The response will include the status of the request. If the status is anything other than "0", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.19]]
-=== Examples
+=== Examples using DELETEREPLICAPROP
*Input*
@@ -1597,29 +1562,25 @@ http://localhost:8983/solr/admin/collections?action=DELETEREPLICAPROP&shard=shar
Insures that a particular property is distributed evenly amongst the physical nodes that make up a collection. If the property already exists on a replica, every effort is made to leave it there. If the property is *not* on any replica on a shard, one is chosen and the property is added.
-[[CollectionsAPI-Input.19]]
-=== Input
+=== BALANCESHARDUNIQUE Parameters
+
+`collection`::
+The name of the collection to balance the property in. This parameter is required.
-*Query Parameters*
+`property`::
+The property to balance. The literal `property.` is prepended to this property if not specified explicitly. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`onlyactivenodes`::
+Defaults to `true`. Normally, the property is instantiated on active nodes only. If this parameter is specified as `false`, then inactive nodes are also included for distribution.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection to balance the property in.
-|property |string |Yes |The property to balance. The literal "property." is prepended to this property if not specified explicitly.
-|onlyactivenodes |boolean |No |Defaults to true. Normally, the property is instantiated on active nodes only. If this parameter is specified as "false", then inactive nodes are also included for distribution.
-|shardUnique |boolean |No |Something of a safety valve. There is one pre-defined property (preferredLeader) that defaults this value to "true". For all other properties that are balanced, this must be set to "true" or an error message is returned.
-|===
+`shardUnique`::
+Something of a safety valve. There is one pre-defined property (`preferredLeader`) that defaults this value to `true`. For all other properties that are balanced, this must be set to `true` or an error message will be returned.
-[[CollectionsAPI-Output.15]]
-=== Output
+=== BALANCESHARDUNIQUE Response
The response will include the status of the request. If the status is anything other than "0", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.20]]
-=== Examples
+=== Examples using BALANCESHARDUNIQUE
*Input*
@@ -1649,38 +1610,38 @@ Examining the clusterstate after issuing this call should show exactly one repli
[[CollectionsAPI-rebalanceleaders]]
== REBALANCELEADERS: Rebalance Leaders
-Reassign leaders in a collection according to the preferredLeader property across active nodes.
+Reassigns leaders in a collection according to the preferredLeader property across active nodes.
`/admin/collections?action=REBALANCELEADERS&collection=collectionName`
-Assigns leaders in a collection according to the preferredLeader property on active nodes. This command should be run after the preferredLeader property has been assigned via the BALANCESHARDUNIQUE or ADDREPLICAPROP commands. NOTE: it is not _required_ that all shards in a collection have a preferredLeader property. Rebalancing will only attempt to reassign leadership to those replicas that have the preferredLeader property set to "true" _and_ are not currently the shard leader _and_ are currently active.
+Leaders are assigned in a collection according to the `preferredLeader` property on active nodes. This command should be run after the preferredLeader property has been assigned via the BALANCESHARDUNIQUE or ADDREPLICAPROP commands.
-[[CollectionsAPI-Input.20]]
-=== Input
+NOTE: It is not _required_ that all shards in a collection have a `preferredLeader` property. Rebalancing will only attempt to reassign leadership to those replicas that have the `preferredLeader` property set to `true` _and_ are not currently the shard leader _and_ are currently active.
-*Query Parameters*
+=== REBALANCELEADERS Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`collection`::
+The name of the collection to rebalance `preferredLeaders` on. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection to rebalance preferredLeaders on.
-|maxAtOnce |string |No |The maximum number of reassignments to have queue up at once. Values \<=0 are use the default value Integer.MAX_VALUE. When this number is reached, the process waits for one or more leaders to be successfully assigned before adding more to the queue.
-|maxWaitSeconds |string |No |Defaults to 60. This is the timeout value when waiting for leaders to be reassigned. NOTE: if maxAtOnce is less than the number of reassignments that will take place, this is the maximum interval that any _single_ wait for at least one reassignment. For example, if 10 reassignments are to take place and maxAtOnce is 1 and maxWaitSeconds is 60, the upper bound on the time that the command may wait is 10 minutes.
-|===
+`maxAtOnce`::
+The maximum number of reassignments to have queue up at once. Values \<=0 are use the default value Integer.MAX_VALUE.
++
+When this number is reached, the process waits for one or more leaders to be successfully assigned before adding more to the queue.
-[[CollectionsAPI-Output.16]]
-=== Output
+`maxWaitSeconds`::
+Defaults to `60`. This is the timeout value when waiting for leaders to be reassigned. If `maxAtOnce` is less than the number of reassignments that will take place, this is the maximum interval that any _single_ wait for at least one reassignment.
++
+For example, if 10 reassignments are to take place and `maxAtOnce` is `1` and `maxWaitSeconds` is `60`, the upper bound on the time that the command may wait is 10 minutes.
+
+=== REBALANCELEADERS Response
The response will include the status of the request. If the status is anything other than "0", an error message will explain why the request failed.
-[[CollectionsAPI-Examples.21]]
-=== Examples
+=== Examples using REBALANCELEADERS
*Input*
-Either of these commands would cause all the active replicas that had the "preferredLeader" property set and were _not_ already the preferred leader to become leaders.
+Either of these commands would cause all the active replicas that had the `preferredLeader` property set and were _not_ already the preferred leader to become leaders.
[source,text]
----
@@ -1690,7 +1651,9 @@ http://localhost:8983/solr/admin/collections?action=REBALANCELEADERS&collection=
*Output*
-In this example, two replicas in the "alreadyLeaders" section already had the leader assigned to the same node as the preferredLeader property so no action was taken. The replica in the "inactivePreferreds" section had the preferredLeader property set but the node was down and no action was taken. The three nodes in the "successes" section were made leaders because they had the preferredLeader property set but were not leaders and they were active.
+In this example, two replicas in the "alreadyLeaders" section already had the leader assigned to the same node as the `preferredLeader` property so no action was taken.
+
+The replica in the "inactivePreferreds" section had the `preferredLeader` property set but the node was down and no action was taken. The three nodes in the "successes" section were made leaders because they had the `preferredLeader` property set but were not leaders and they were active.
[source,xml]
----
@@ -1744,7 +1707,7 @@ In this example, two replicas in the "alreadyLeaders" section already had the le
</response>
----
-Examining the clusterstate after issuing this call should show that every live node that has the "preferredLeader" property should also have the "leader" property set to _true_.
+Examining the clusterstate after issuing this call should show that every live node that has the `preferredLeader` property should also have the "leader" property set to _true_.
[[CollectionsAPI-FORCELEADER_ForceShardLeader]]
@@ -1752,28 +1715,19 @@ Examining the clusterstate after issuing this call should show that every live n
[[CollectionsAPI-forceleader]]
== FORCELEADER: Force Shard Leader
-In the unlikely event of a shard losing its leader, this command can be invoked to force the election of a new leader
+In the unlikely event of a shard losing its leader, this command can be invoked to force the election of a new leader.
`/admin/collections?action=FORCELEADER&collection=<collectionName>&shard=<shardName>`
-[[CollectionsAPI-Input.21]]
-=== Input
+=== FORCELEADER Parameters
-*Query Parameters*
+`collection`::
+The name of the collection. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`shard`::
+The name of the shard where leader election should occur. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection
-|shard |string |Yes |The name of the shard
-|===
-
-[IMPORTANT]
-====
-This is an expert level command, and should be invoked only when regular leader election is not working. This may potentially lead to loss of data in the event that the new leader doesn't have certain updates, possibly recent ones, which were acknowledged by the old leader before going down.
-====
+WARNING: This is an expert level command, and should be invoked only when regular leader election is not working. This may potentially lead to loss of data in the event that the new leader doesn't have certain updates, possibly recent ones, which were acknowledged by the old leader before going down.
[[CollectionsAPI-migratestateformat]]
== MIGRATESTATEFORMAT: Migrate Cluster State
@@ -1782,41 +1736,38 @@ A expert level utility API to move a collection from shared `clusterstate.json`
`/admin/collections?action=MIGRATESTATEFORMAT&collection=<collection_name>`
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+=== MIGRATESTATEFORMAT Parameters
+
+`collection`::
+The name of the collection to be migrated from `clusterstate.json` to its own `state.json` ZooKeeper node. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection to be migrated from `clusterstate.json` to its own `state.json` zookeeper node
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
This API is useful in migrating any collections created prior to Solr 5.0 to the more scalable cluster state format now used by default. If a collection was created in any Solr 5.x version or higher, then executing this command is not necessary.
[[CollectionsAPI-backup]]
== BACKUP: Backup Collection
-Backup Solr collections and it's associated configurations to a shared filesystem - for example a Network File System
+Backs up Solr collections and associated configurations to a shared filesystem - for example a Network File System.
`/admin/collections?action=BACKUP&name=myBackupName&collection=myCollectionName&location=/path/to/my/shared/drive`
-The backup command will backup Solr indexes and configurations for a specified collection. The backup command takes one copy from each shard for the indexes. For configurations it backs up the configSet that was associated with the collection and metadata.
+The BACKUP command will backup Solr indexes and configurations for a specified collection. The BACKUP command takes one copy from each shard for the indexes. For configurations, it backs up the configSet that was associated with the collection and metadata.
-[[CollectionsAPI-Input.22]]
-=== Input
+=== BACKUP Parameters
-*Query Parameters*
+`collection`::
+The name of the collection to be backed up. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`location`::
+The location on a shared drive for the backup command to write to. Alternately it can be set as a <<CollectionsAPI-clusterprop,cluster property>>.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection that needs to be backed up
-|location |string |No |The location on the shared drive for the backup command to write to. Alternately it can be set as a <<CollectionsAPI-clusterprop,cluster property>>
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>
-|repository |string |No |The name of the repository to be used for the backup. If no repository is specified then the local filesystem repository will be used automatically.
-|===
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
+
+`repository`::
+The name of a repository to be used for the backup. If no repository is specified then the local filesystem repository will be used automatically.
[[CollectionsAPI-restore]]
== RESTORE: Restore Collection
@@ -1825,43 +1776,48 @@ Restores Solr indexes and associated configurations.
`/admin/collections?action=RESTORE&name=myBackupName&location=/path/to/my/shared/drive&collection=myRestoredCollectionName`
-The restore operation will create a collection with the specified name in the collection parameter. You cannot restore into the same collection the backup was taken from and the target collection should not be present at the time the API is called as Solr will create it for you.
+The RESTORE operation will create a collection with the specified name in the collection parameter. You cannot restore into the same collection the backup was taken from. Also the target collection should not be present at the time the API is called as Solr will create it for you.
+
+The collection created will be have the same number of shards and replicas as the original collection, preserving routing information, etc. Optionally, you can override some parameters documented below.
-The collection created will be of the same number of shards and replicas as the original collection, preserving routing information, etc. Optionally, you can override some parameters documented below. While restoring, if a configSet with the same name exists in ZooKeeper then Solr will reuse that, or else it will upload the backed up configSet in ZooKeeper and use that.
+While restoring, if a configSet with the same name exists in ZooKeeper then Solr will reuse that, or else it will upload the backed up configSet in ZooKeeper and use that.
-You can use the collection <<CollectionsAPI-createalias,alias>> API to make sure client's don't need to change the endpoint to query or index against the newly restored collection.
+You can use the collection <<CollectionsAPI-createalias,CREATEALIAS>> command to make sure clients don't need to change the endpoint to query or index against the newly restored collection.
-[[CollectionsAPI-Input.23]]
-=== Input
+=== RESTORE Parameters
-*Query Parameters*
+`collection`::
+The collection where the indexes will be restored into. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`location`::
+The location on a shared drive for the RESTORE command to read from. Alternately it can be set as a <<CollectionsAPI-clusterprop,cluster property>>.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The collection where the indexes will be restored into.
-|location |string |No |The location on the shared drive for the restore command to read from. Alternately it can be set as a <<CollectionsAPI-clusterprop,cluster property>>.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|repository |string |No |The name of the repository to be used for the backup. If no repository is specified then the local filesystem repository will be used automatically.
-|===
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-Additionally, there are several parameters that can be overridden:
+`repository`::
+The name of a repository to be used for the backup. If no repository is specified then the local filesystem repository will be used automatically.
*Override Parameters*
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+Additionally, there are several parameters that may have been set on the original collection that can be overridden when restoring the backup:
+
+`collection.configName`::
+Defines the name of the configurations to use for this collection. These must already be stored in ZooKeeper. If not provided, Solr will default to the collection name as the configuration name.
+
+`replicationFactor`::
+The number of replicas to be created for each shard.
+
+`maxShardsPerNode`::
+When creating collections, the shards and/or replicas are spread across all available (i.e., live) nodes, and two replicas of the same shard will never be on the same node.
++
+If a node is not live when the CREATE operation is called, it will not get any parts of the new collection, which could lead to too many replicas being created on a single live node. Defining `maxShardsPerNode` sets a limit on the number of replicas CREATE will spread to each node. If the entire collection can not be fit into the live nodes, no collection will be created at all.
+
+`autoAddReplicas`::
+When set to `true`, enables auto addition of replicas on shared file systems. See the section <<running-solr-on-hdfs.adoc#RunningSolronHDFS-AutomaticallyAddReplicasinSolrCloud,Automatically Add Replicas in SolrCloud>> for more details on settings and overrides.
-[cols="25,15,10,50",options="header"]
-|===
-|Key |Type |Required |Description
-|collection.configName |String |No |Defines the name of the configurations to use for this collection. These must already be stored in ZooKeeper. If not provided, Solr will default to the collection name as the configuration name.
-|replicationFactor |Integer |No |The number of replicas to be created for each shard.
-|maxShardsPerNode |Integer |No |When creating collections, the shards and/or replicas are spread across all available (i.e., live) nodes, and two replicas of the same shard will never be on the same node. If a node is not live when the CREATE operation is called, it will not get any parts of the new collection, which could lead to too many replicas being created on a single live node. Defining `maxShardsPerNode` sets a limit on the number of replicas CREATE will spread to each node. If the entire collection can not be fit into the live nodes, no collection will be created at all.
-|autoAddReplicas |Boolean |No |When set to true, enables auto addition of replicas on shared file systems. See the section <<running-solr-on-hdfs.adoc#RunningSolronHDFS-AutomaticallyAddReplicasinSolrCloud,Automatically Add Replicas in SolrCloud>> for more details on settings and overrides.
-|property._name_=_value_ |String |No |Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
-|===
+`property._name_=_value_`::
+Set core property _name_ to _value_. See the section <<defining-core-properties.adoc#defining-core-properties,Defining core.properties>> for details on supported properties and values.
[[CollectionsAPI-deletenode]]
== DELETENODE: Delete Replicas in a Node
@@ -1870,43 +1826,38 @@ Deletes all replicas of all collections in that node. Please note that the node
`/admin/collections?action=DELETENODE&node=nodeName`
-[[CollectionsAPI-Input.24]]
-=== Input
+=== DELETENODE Parameters
-*Query Parameters*
+`node`:: string |Yes |The node to be removed. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|node |string |Yes |The node to be cleaned up
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
[[CollectionsAPI-replacenode]]
== REPLACENODE: Move All Replicas in a Node to Another
-This command recreates replicas in the source node to the target node. After each replica is copied, the replicas in the source node are deleted. For source replicas that are also shard leaders the operation will wait for "timeout" seconds to make sure there's an active replica that can become a leader (either an existing replica becoming a leader or the new replica completing the recovery and becoming a leader).
+This command recreates replicas in one node (the source) to another node (the target). After each replica is copied, the replicas in the source node are deleted.
+
+For source replicas that are also shard leaders the operation will wait for the number of seconds set with the `timeout` parameter to make sure there's an active replica that can become a leader (either an existing replica becoming a leader or the new replica completing recovery and becoming a leader).
`/admin/collections?action=REPLACENODE&source=_source-node_&target=_target-node_`
-[[CollectionsAPI-Input.25]]
-=== Input
+=== REPLACENODE Parameters
+
+`source`::
+The source node from which the replicas need to be copied from. This parameter is required.
+
+`target`::
+The target node where replicas will be copied. This parameter is required.
-*Query Parameters*
+`parallel`::
+If this flag is set to `true`, all replicas are created in separate threads. Keep in mind that this can lead to very high network and disk I/O if the replicas have very large indices. The default is `false`.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|source |string |Yes |The source node from which the replicas need to be copied from
-|target |string |Yes |The target node
-|parallel |boolean |No |default=false. if this flag is set to true, all replicas are created inseparatee threads. Keep in mind that this can lead to very high network and disk I/O if the replicas have very large indices.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|timeout |int |No |default is 300. Timeout in seconds to wait until new replicas are created, and until leader replicas are fully recovered.
-|===
+`timeout`::
+Time in seconds to wait until new replicas are created, and until leader replicas are fully recovered. The default is `300`, or 5 minutes.
[IMPORTANT]
====
@@ -1914,39 +1865,40 @@ This operation does not hold necessary locks on the replicas that belong to on t
====
[[CollectionsAPI-movereplica]]
-== MOVEREPLICA: Move a Replica to a New node
+== MOVEREPLICA: Move a Replica to a New Node
-This command move a replica from a node to a new node, in case of shared-file systems the `dataDir` will be reused.
+This command moves a replica from one node to a new node. In case of shared filesystems the `dataDir` will be reused.
`/admin/collections?action=MOVEREPLICA&collection=collection&shard=shard&replica=replica&node=nodeName&toNode=nodeName`
-[[CollectionsAPI-Input.26]]
-=== Input
+=== MOVEREPLICA Parameters
+
+`collection`::
+The name of the collection. This parameter is required.
+
+`shard`::
+The name of the shard that the replica belongs to. This parameter is required.
+
+`replica`::
+The name of the replica. This parameter is required.
-*Query Parameters*
+`node`::
+The name of the node that contains the replica. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`toNode`::
+The name of the destination node. This parameter is required.
-[cols="20,15,10,55",options="header"]
-|===
-|Key |Type |Required |Description
-|collection |string |Yes |The name of the collection.
-|shard |string |Yes |The name of shard that replica belong to.
-|replica |string |Yes |The name of the replica.
-|node |string |Yes |The name of the node that contains the replica.
-|toNode |string |Yes |The name of the destination node.
-|async |string |No |Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
-|===
+`async`::
+Request ID to track this action which will be <<CollectionsAPI-async,processed asynchronously>>.
[[CollectionsAPI-async]]
== Asynchronous Calls
-Since some collection API calls can be long running tasks e.g. Shard Split, you can optionally have the calls run asynchronously. Specifying `async=<request-id>` enables you to make an asynchronous call, the status of which can be requested using the <<CollectionsAPI-requeststatus,REQUESTSTATUS>> call at any time.
+Since some collection API calls can be long running tasks (such as SPLITSHARD), you can optionally have the calls run asynchronously. Specifying `async=<request-id>` enables you to make an asynchronous call, the status of which can be requested using the <<CollectionsAPI-requeststatus,REQUESTSTATUS>> call at any time.
As of now, REQUESTSTATUS does not automatically clean up the tracking data structures, meaning the status of completed or failed tasks stays stored in ZooKeeper unless cleared manually. DELETESTATUS can be used to clear the stored statuses. However, there is a limit of 10,000 on the number of async call responses stored in a cluster.
-[[CollectionsAPI-Example.1]]
-=== Example
+=== Examples of Async Requests
*Input*
[19/27] lucene-solr:feature/autoscaling: Ref Guide: fix bad JSON in
examples
Posted by sh...@apache.org.
Ref Guide: fix bad JSON in examples
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/8da926e7
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/8da926e7
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/8da926e7
Branch: refs/heads/feature/autoscaling
Commit: 8da926e7cb08b39a100448e385b8c068f94eedec
Parents: 9f56698
Author: Cassandra Targett <ct...@apache.org>
Authored: Mon Jun 26 20:24:48 2017 -0500
Committer: Cassandra Targett <ct...@apache.org>
Committed: Mon Jun 26 22:17:59 2017 -0500
----------------------------------------------------------------------
.../src/rule-based-authorization-plugin.adoc | 23 +++++++-------------
1 file changed, 8 insertions(+), 15 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/8da926e7/solr/solr-ref-guide/src/rule-based-authorization-plugin.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/rule-based-authorization-plugin.adoc b/solr/solr-ref-guide/src/rule-based-authorization-plugin.adoc
index 5b548f2..ee2fd88 100644
--- a/solr/solr-ref-guide/src/rule-based-authorization-plugin.adoc
+++ b/solr/solr-ref-guide/src/rule-based-authorization-plugin.adoc
@@ -152,8 +152,9 @@ For example, this property could be used to limit the actions a role is allowed
+
[source,json]
----
-"params": {
+{"params": {
"action": ["LIST", "CLUSTERSTATUS"]
+ }
}
----
+
@@ -163,8 +164,9 @@ If the commands LIST and CLUSTERSTATUS are case insensitive, the above example s
+
[source,json]
----
-"params": {
+{"params": {
"action": ["REGEX:(?i)LIST", "REGEX:(?i)CLUSTERSTATUS"]
+ }
}
----
@@ -177,25 +179,21 @@ The name of the role(s) to give this permission. This name will be used to map u
The following creates a new permission named "collection-mgr" that is allowed to create and list collections. The permission will be placed before the "read" permission. Note also that we have defined "collection as `null`, this is because requests to the Collections API are never collection-specific.
[source,bash]
-----
curl --user solr:SolrRocks -H 'Content-type:application/json' -d '{
"set-permission": {"collection": null,
"path":"/admin/collections",
- "params":{"action":[LIST, CREATE]},
+ "params":{"action":["LIST", "CREATE"]},
"before": 3,
"role": "admin"}
}' http://localhost:8983/solr/admin/authorization
-----
Apply an update permission on all collections to a role called `dev` and read permissions to a role called `guest`:
[source,bash]
-----
curl --user solr:SolrRocks -H 'Content-type:application/json' -d '{
- "set-permission": {"name": "update, "role":"dev"},
- "set-permission": {"name": "read, "role":"guest"},
+ "set-permission": {"name": "update", "role":"dev"},
+ "set-permission": {"name": "read", "role":"guest"}
}' http://localhost:8983/solr/admin/authorization
-----
[[Rule-BasedAuthorizationPlugin-UpdateorDeletePermissions]]
=== Update or Delete Permissions
@@ -205,21 +203,18 @@ Permissions can be accessed using their index in the list. Use the `/admin/autho
The following example updates the `'role'` attribute of permission at index `3`:
[source,bash]
-----
curl --user solr:SolrRocks -H 'Content-type:application/json' -d '{
"update-permission": {"index": 3,
"role": ["admin", "dev"]}
}' http://localhost:8983/solr/admin/authorization
-----
The following example deletes permission at index `3`:
[source,bash]
-----
curl --user solr:SolrRocks -H 'Content-type:application/json' -d '{
"delete-permission": 3
}' http://localhost:8983/solr/admin/authorization
-----
+
[[Rule-BasedAuthorizationPlugin-MapRolestoUsers]]
=== Map Roles to Users
@@ -235,9 +230,7 @@ The values supplied to the command are simply a user ID and one or more roles th
For example, the following would grant a user "solr" the "admin" and "dev" roles, and remove all roles from the user ID "harry":
[source,bash]
-----
curl -u solr:SolrRocks -H 'Content-type:application/json' -d '{
"set-user-role" : {"solr": ["admin","dev"],
"harry": null}
}' http://localhost:8983/solr/admin/authorization
-----
[08/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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..a88300a
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/managed-schema
@@ -0,0 +1,1076 @@
+<?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="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 _default 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"/>
+
+ <!-- This can be enabled, in case the client does not know what fields may be searched. It isn't enabled by default
+ 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="*_s_ns" type="string" indexed="true" stored="false" />
+ <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_l_ns" type="long" indexed="true" stored="false"/>
+ <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:
+ amountLongSuffix: Required. Refers to a dynamic field for the raw amount sub-field.
+ The dynamic field must have a field type that extends LongValueFieldType.
+ Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
+ codeStrSuffix: Required. Refers to a dynamic field for the currency code sub-field.
+ The dynamic field must have a field type that extends StrField.
+ Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
+ defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
+ 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.CurrencyFieldType" amountLongSuffix="_l_ns" codeStrSuffix="_s_ns"
+ 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/e4a7fc59/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/e4a7fc59/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
+
[04/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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 15d7ab4..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
+++ /dev/null
@@ -1,1401 +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>
-
- <!-- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded. It is safe to increase or remove this setting,
- since it is purely an arbitrary limit to try and catch user errors where
- large boolean queries may not be the best implementation choice.
- -->
- <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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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 532221a..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 CurrencyFieldType 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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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
[22/27] lucene-solr:feature/autoscaling: SOLR-10892: Phase 2: large
pages with lots of tables + lots of heading cleanups & TOC placement changes
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/93c96b06/solr/solr-ref-guide/src/coreadmin-api.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/coreadmin-api.adoc b/solr/solr-ref-guide/src/coreadmin-api.adoc
index fef4929..a4a8ea9 100644
--- a/solr/solr-ref-guide/src/coreadmin-api.adoc
+++ b/solr/solr-ref-guide/src/coreadmin-api.adoc
@@ -1,6 +1,7 @@
= CoreAdmin API
:page-shortname: coreadmin-api
:page-permalink: coreadmin-api.html
+:page-toclevels: 1
// 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
@@ -35,19 +36,13 @@ The `STATUS` action returns the status of all running Solr cores, or status for
`admin/cores?action=STATUS&core=_core-name_`
-[[CoreAdminAPI-Input]]
-=== *Input*
+=== STATUS Parameters
-*Query Parameters*
+`core`::
+The name of a core, as listed in the "name" attribute of a `<core>` element in `solr.xml`.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|core |string |No | |The name of a core, as listed in the "name" attribute of a `<core>` element in `solr.xml`.
-|indexInfo |boolean |No |true |If **false**, information about the index will not be returned with a core STATUS request. In Solr implementations with a large number of cores (i.e., more than hundreds), retrieving the index information for each core can take a lot of time and isn't always required.
-|===
+`indexInfo`::
+If `false`, information about the index will not be returned with a core STATUS request. In Solr implementations with a large number of cores (i.e., more than hundreds), retrieving the index information for each core can take a lot of time and isn't always required. The default is `true`.
[[CoreAdminAPI-CREATE]]
== CREATE
@@ -65,52 +60,60 @@ Note that this command is the only one of the Core Admin API commands that *does
====
Your CREATE call must be able to find a configuration, or it will not succeed.
-When you are running SolrCloud and create a new core for a collection, the configuration will be inherited from the collection. Each collection is linked to a configName, which is stored in the ZooKeeper database. This satisfies the config requirement. There is something to note, though – if you're running SolrCloud, you should *NOT* be using the CoreAdmin API at all. Use the Collections API.
+When you are running SolrCloud and create a new core for a collection, the configuration will be inherited from the collection. Each collection is linked to a configName, which is stored in ZooKeeper. This satisfies the config requirement. There is something to note, though – if you're running SolrCloud, you should *NOT* be using the CoreAdmin API at all. Use the <<collections-api.adoc#collections-api,Collections API>>.
-When you are not running SolrCloud, if you have <<config-sets.adoc#config-sets,Config Sets>> defined, you can use the configSet parameter as documented below. If there are no config sets, then the instanceDir specified in the CREATE call must already exist, and it must contain a `conf` directory which in turn must contain `solrconfig.xml`, your schema, which is usually named either `managed-schema` or `schema.xml`, and any files referenced by those configs.
+When you are not running SolrCloud, if you have <<config-sets.adoc#config-sets,Config Sets>> defined, you can use the configSet parameter as documented below. If there are no config sets, then the `instanceDir` specified in the CREATE call must already exist, and it must contain a `conf` directory which in turn must contain `solrconfig.xml`, your schema (usually named either `managed-schema` or `schema.xml`), and any files referenced by those configs.
-The config and schema filenames can be specified with the config and schema parameters, but these are expert options. One thing you could do to avoid creating the conf directory is use config and schema parameters that point at absolute paths, but this can lead to confusing configurations unless you fully understand what you are doing.
+The config and schema filenames can be specified with the `config` and `schema` parameters, but these are expert options. One thing you could do to avoid creating the `conf` directory is use `config` and `schema` parameters that point at absolute paths, but this can lead to confusing configurations unless you fully understand what you are doing.
====
-.CREATE and the core.properties file
+.CREATE and the `core.properties` file
[IMPORTANT]
====
-The core.properties file is built as part of the CREATE command. If you create a core.properties file yourself in a core directory and then try to use CREATE to add that core to Solr, you will get an error telling you that another core is already defined there. The core.properties file must NOT exist before calling the CoreAdmin API with the CREATE command.
+The `core.properties` file is built as part of the CREATE command. If you create a `core.properties` file yourself in a core directory and then try to use CREATE to add that core to Solr, you will get an error telling you that another core is already defined there. The `core.properties` file must NOT exist before calling the CoreAdmin API with the CREATE command.
====
-[[CoreAdminAPI-Input.1]]
-=== *Input*
+=== CREATE Core Parameters
-*Query Parameters*
+`name`::
+The name of the new core. Same as `name` on the `<core>` element. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`instanceDir`::
+The directory where files for this core should be stored. Same as `instanceDir` on the `<core>` element. The default is the value specified for the `name` parameter if not supplied.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|name |string |Yes |N/A |The name of the new core. Same as "name" on the `<core>` element.
-|instanceDir |string |No |The value specified for "name" parameter |The directory where files for this SolrCore should be stored. Same as `instanceDir` on the `<core>` element.
-|config |string |No | |Name of the config file (i.e., `solrconfig.xml`) relative to `instanceDir`.
-|schema |string |No | |Name of the schema file to use for the core. Please note that if you are using a "managed schema" (the default behavior) then any value for this property which does not match the effective `managedSchemaResourceName` will be read once, backed up, and converted for managed schema use. See <<schema-factory-definition-in-solrconfig.adoc#schema-factory-definition-in-solrconfig,Schema Factory Definition in SolrConfig>> for details.
-|dataDir |string |No | |Name of the data directory relative to `instanceDir`.
-|configSet |string |No | |Name of the configset to use for this core. For more information, see the section <<config-sets.adoc#config-sets,Config Sets>>.
-|collection |string |No | |The name of the collection to which this core belongs. The default is the name of the core. `collection.<param>=<value>` causes a property of `<param>=<value>` to be set if a new collection is being created. Use `collection.configName=<configname>` to point to the configuration for a new collection.
-|shard |string |No | |The shard id this core represents. Normally you want to be auto-assigned a shard id.
-|property.__name__=__value__ |string |No | |Sets the core property _name_ to __value__. See the section on defining <<defining-core-properties.adoc#Definingcore.properties-core.properties_files,core.properties file contents>>.
-|async |string |No | |Request ID to track this action which will be processed asynchronously
-|===
+`config`::
+Name of the config file (i.e., `solrconfig.xml`) relative to `instanceDir`.
-Use `collection.configName=<configname>` to point to the config for a new collection.
+`schema`::
+Name of the schema file to use for the core. Please note that if you are using a "managed schema" (the default behavior) then any value for this property which does not match the effective `managedSchemaResourceName` will be read once, backed up, and converted for managed schema use. See <<schema-factory-definition-in-solrconfig.adoc#schema-factory-definition-in-solrconfig,Schema Factory Definition in SolrConfig>> for details.
-[[CoreAdminAPI-Example]]
-=== Example
+`dataDir`::
+Name of the data directory relative to `instanceDir`.
-`\http://localhost:8983/solr/admin/cores?action=CREATE&name=my_core&collection=my_collection&shard=shard2`
+`configSet`::
+Name of the configset to use for this core. For more information, see the section <<config-sets.adoc#config-sets,Config Sets>>.
+
+`collection`::
+The name of the collection to which this core belongs. The default is the name of the core. `collection._param_=_value_` causes a property of `_param_=_value_` to be set if a new collection is being created. Use `collection.configName=_config-name_` to point to the configuration for a new collection.
++
+WARNING: While it's possible to create a core for a non-existent collection, this approach is not supported and not recommended. Always create a collection using the <<collections-api.adoc#collections-api,Collections API>> before creating a core directly for it.
+
+`shard`::
+The shard id this core represents. Normally you want to be auto-assigned a shard id.
+
+`property._name_=_value_`::
+Sets the core property _name_ to _value_. See the section on defining <<defining-core-properties.adoc#Definingcore.properties-core.properties_files,core.properties file contents>>.
+
+`async`::
+Request ID to track this action which will be processed asynchronously.
+
+Use `collection.configName=_configname_` to point to the config for a new collection.
+
+=== CREATE Example
+
+[source,bash]
+http://localhost:8983/solr/admin/cores?action=CREATE&name=my_core&collection=my_collection&shard=shard2
-[WARNING]
-====
-While it's possible to create a core for a non-existent collection, this approach is not supported and not recommended. Always create a collection using the <<collections-api.adoc#collections-api,Collections API>> before creating a core directly for it.
-====
[[CoreAdminAPI-RELOAD]]
== RELOAD
@@ -126,18 +129,10 @@ This is useful when you've made changes to a Solr core's configuration on disk,
RELOAD performs "live" reloads of SolrCore, reusing some existing objects. Some configuration options, such as the `dataDir` location and `IndexWriter`-related settings in `solrconfig.xml` can not be changed and made active with a simple RELOAD action.
====
-[[CoreAdminAPI-Input.2]]
-=== Input
-
-*Query Parameters*
+=== RELOAD Core Parameters
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|core |string |Yes |N/A |The name of the core, as listed in the "name" attribute of a `<core>` element in `solr.xml`.
-|===
+`core`::
+The name of the core, as listed in the "name" attribute of a `<core>` element in `solr.xml`. This parameter is required.
[[CoreAdminAPI-RENAME]]
== RENAME
@@ -146,20 +141,17 @@ The `RENAME` action changes the name of a Solr core.
`admin/cores?action=RENAME&core=_core-name_&other=_other-core-name_`
-[[CoreAdminAPI-Input.3]]
-=== Input
+=== RENAME Parameters
+
+`core`::
+The name of the Solr core to be renamed. This parameter is required.
-**Query Parameters**
+`other`::
+The new name for the Solr core. If the persistent attribute of `<solr>` is `true`, the new name will be written to `solr.xml` as the `name` attribute of the `<core>` attribute. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`async`::
+Request ID to track this action which will be processed asynchronously.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|core |string |Yes | |The name of the Solr core to be renamed.
-|other |string |Yes | |The new name for the Solr core. If the persistent attribute of `<solr>` is `true`, the new name will be written to `solr.xml` as the `name` attribute of the `<core>` attribute.
-|async |string |No | |Request ID to track this action which will be processed asynchronously
-|===
[[CoreAdminAPI-SWAP]]
== SWAP
@@ -175,20 +167,17 @@ Do not use `SWAP` with a SolrCloud node. It is not supported and can result in t
====
-[[CoreAdminAPI-Input.4]]
-=== Input
+=== SWAP Parameters
+
+`core`::
+The name of one of the cores to be swapped. This parameter is required.
-*Query Parameters*
+`other`::
+The name of one of the cores to be swapped. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`async`::
+Request ID to track this action which will be processed asynchronously.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|core |string |Yes | |The name of one of the cores to be swapped.
-|other |string |Yes | |The name of one of the cores to be swapped.
-|async |string |No | |Request ID to track this action which will be processed asynchronously
-|===
[[CoreAdminAPI-UNLOAD]]
== UNLOAD
@@ -204,22 +193,23 @@ The `UNLOAD` action requires a parameter (`core`) identifying the core to be rem
Unloading all cores in a SolrCloud collection causes the removal of that collection's metadata from ZooKeeper.
====
-[[CoreAdminAPI-Input.5]]
-=== Input
+=== UNLOAD Parameters
-*Query Parameters*
+`core`::
+The name of a core to be removed. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`deleteIndex`::
+If `true`, will remove the index when unloading the core. The default is `false`.
+
+`deleteDataDir`::
+If `true`, removes the `data` directory and all sub-directories. The default is `false`.
+
+`deleteInstanceDir`::
+If `true`, removes everything related to the core, including the index directory, configuration files and other related files. The default is `false`.
+
+`async`::
+Request ID to track this action which will be processed asynchronously.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|core |string |Yes | |The name of one of the cores to be removed.
-|deleteIndex |boolean |No |false |If true, will remove the index when unloading the core.
-|deleteDataDir |boolean |No |false |If true, removes the `data` directory and all sub-directories.
-|deleteInstanceDir |boolean |No |false |If true, removes everything related to the core, including the index directory, configuration files and other related files.
-|async |string |No | |Request ID to track this action which will be processed asynchronously
-|===
[[CoreAdminAPI-MERGEINDEXES]]
== MERGEINDEXES
@@ -238,21 +228,20 @@ This approach allows us to define cores that may not have an index path that is
We can make this call run asynchronously by specifying the `async` parameter and passing a request-id. This id can then be used to check the status of the already submitted task using the REQUESTSTATUS API.
-[[CoreAdminAPI-Input.6]]
-=== Input
+=== MERGEINDEXES Parameters
+
+`core`::
+The name of the target core/index. This parameter is required.
-*Query Parameters*
+`indexDir`::
+Multi-valued, directories that would be merged.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`srcCore`::
+Multi-valued, source cores that would be merged.
+
+`async`::
+Request ID to track this action which will be processed asynchronously
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|core |string |Yes | |The name of the target core/index.
-|indexDir |string | | |Multi-valued, directories that would be merged.
-|srcCore |string | | |Multi-valued, source cores that would be merged.
-|async |string | | |Request ID to track this action which will be processed asynchronously
-|===
[[CoreAdminAPI-SPLIT]]
== SPLIT
@@ -261,55 +250,56 @@ The `SPLIT` action splits an index into two or more indexes. The index being spl
The `SPLIT` action supports five parameters, which are described in the table below.
-[[CoreAdminAPI-Input.7]]
-=== Input
+=== SPLIT Parameters
-*Query Parameters*
+`core`::
+The name of the core to be split. This parameter is required.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`path`::
+Multi-valued, the directory path in which a piece of the index will be written. Either this parameter or `targetCore` must be specified. If this is specified, the `targetCore` parameter may not be used.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|core |string |Yes | |The name of the core to be split.
-|path |string | | |Multi-valued, the directory path in which a piece of the index will be written.
-|targetCore |string | | |Multi-valued, the target Solr core to which a piece of the index will be merged
-|ranges |string |No | |A comma-separated list of hash ranges in hexadecimal format
-|split.key |string |No | |The key to be used for splitting the index
-|async |string |No | |Request ID to track this action which will be processed asynchronously
-|===
+`targetCore`::
+Multi-valued, the target Solr core to which a piece of the index will be merged. Either this parameter or `path` must be specified. If this is specified, the `path` parameter may not be used.
+
+`ranges`::
+A comma-separated list of hash ranges in hexadecimal format. If this parameter is used, `split.key` should not be. See the <<SPLIT Examples>> below for an example of how this parameter can be used.
+
+`split.key`::
+The key to be used for splitting the index. If this parameter is used, `ranges` should not be. See the <<SPLIT Examples>> below for an example of how this parameter can be used.
+
+`async`::
+Request ID to track this action which will be processed asynchronously.
-[IMPORTANT]
-====
-Either `path` or `targetCore` parameter must be specified but not both. The ranges and split.key parameters are optional and only one of the two should be specified, if at all required.
-====
-[[CoreAdminAPI-Examples]]
-=== Examples
+=== SPLIT Examples
The `core` index will be split into as many pieces as the number of `path` or `targetCore` parameters.
==== Usage with two targetCore parameters:
-`\http://localhost:8983/solr/admin/cores?action=SPLIT&core=core0&targetCore=core1&targetCore=core2`
+[source,bash]
+http://localhost:8983/solr/admin/cores?action=SPLIT&core=core0&targetCore=core1&targetCore=core2
Here the `core` index will be split into two pieces and merged into the two `targetCore` indexes.
==== Usage with two path parameters:
-`\http://localhost:8983/solr/admin/cores?action=SPLIT&core=core0&path=/path/to/index/1&path=/path/to/index/2`
+[source,bash]
+http://localhost:8983/solr/admin/cores?action=SPLIT&core=core0&path=/path/to/index/1&path=/path/to/index/2
The `core` index will be split into two pieces and written into the two directory paths specified.
==== Usage with the split.key parameter:
-`\http://localhost:8983/solr/admin/cores?action=SPLIT&core=core0&targetCore=core1&split.key=A!`
+[source,bash]
+http://localhost:8983/solr/admin/cores?action=SPLIT&core=core0&targetCore=core1&split.key=A!
Here all documents having the same route key as the `split.key` i.e. 'A!' will be split from the `core` index and written to the `targetCore`.
==== Usage with ranges parameter:
-`\http://localhost:8983/solr/admin/cores?action=SPLIT&core=core0&targetCore=core1&targetCore=core2&targetCore=core3&ranges=0-1f4,1f5-3e8,3e9-5dc`
+[source,bash]
+http://localhost:8983/solr/admin/cores?action=SPLIT&core=core0&targetCore=core1&targetCore=core2&targetCore=core3&ranges=0-1f4,1f5-3e8,3e9-5dc
This example uses the `ranges` parameter with hash ranges 0-500, 501-1000 and 1001-1500 specified in hexadecimal. Here the index will be split into three pieces with each targetCore receiving documents matching the hash ranges specified i.e. core1 will get documents with hash range 0-500, core2 will receive documents with hash range 501-1000 and finally, core3 will receive documents with hash range 1001-1500. At least one hash range must be specified. Please note that using a single hash range equal to a route key's hash range is NOT equivalent to using the `split.key` parameter because multiple route keys can hash to the same range.
@@ -324,22 +314,17 @@ Request the status of an already submitted asynchronous CoreAdmin API call.
`admin/cores?action=REQUESTSTATUS&requestid=_id_`
-[[CoreAdminAPI-Input.8]]
-=== Input
+=== Core REQUESTSTATUS Parameters
-*Query Parameters*
+The REQUESTSTATUS command has only one parameter.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`requestid`::
+The user defined request-id for the asynchronous request. This parameter is required.
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|requestid |string |Yes | |The user defined request-id for the Asynchronous request.
-|===
+The call below will return the status of an already submitted asynchronous CoreAdmin call.
-The call below will return the status of an already submitted Asynchronous CoreAdmin call.
-
-`\http://localhost:8983/solr/admin/cores?action=REQUESTSTATUS&requestid=1`
+[source,bash]
+http://localhost:8983/solr/admin/cores?action=REQUESTSTATUS&requestid=1
[[CoreAdminAPI-REQUESTRECOVERY]]
== REQUESTRECOVERY
@@ -348,22 +333,15 @@ The `REQUESTRECOVERY` action manually asks a core to recover by synching with th
`admin/cores?action=REQUESTRECOVERY&core=_core-name_`
-[[CoreAdminAPI-Input.9]]
-=== Input
-
-*Query Parameters*
-
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+=== REQUESTRECOVERY Parameters
-[cols="15,10,10,10,55",options="header"]
-|===
-|Parameter |Type |Required |Default |Description
-|core |string |Yes | |The name of the core to re-sync.
-|===
+`core`::
+The name of the core to re-sync. This parameter is required.
[[CoreAdminAPI-Examples.1]]
-=== Examples
+=== REQUESTRECOVERY Examples
-`\http://localhost:8981/solr/admin/cores?action=REQUESTRECOVERY&core=gettingstarted_shard1_replica1`
+[source,bash]
+http://localhost:8981/solr/admin/cores?action=REQUESTRECOVERY&core=gettingstarted_shard1_replica1
The core to specify can be found by expanding the appropriate ZooKeeper node via the admin UI.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/93c96b06/solr/solr-ref-guide/src/format-of-solr-xml.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/format-of-solr-xml.adoc b/solr/solr-ref-guide/src/format-of-solr-xml.adoc
index 28dc3c4..98f21d1 100644
--- a/solr/solr-ref-guide/src/format-of-solr-xml.adoc
+++ b/solr/solr-ref-guide/src/format-of-solr-xml.adoc
@@ -55,66 +55,98 @@ As you can see, the discovery Solr configuration is "SolrCloud friendly". Howeve
There are no attributes that you can specify in the `<solr>` tag, which is the root element of `solr.xml`. The tables below list the child nodes of each XML element in `solr.xml`.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="30,70",options="header"]
-|===
-|Node |Description
-|`adminHandler` |If used, this attribute should be set to the FQN (Fully qualified name) of a class that inherits from CoreAdminHandler. For example, `<str name="adminHandler">com.myorg.MyAdminHandler</str>` would configure the custom admin handler (MyAdminHandler) to handle admin requests. If this attribute isn't set, Solr uses the default admin handler, `org.apache.solr.handler.admin.CoreAdminHandler`. For more information on this parameter, see the Solr Wiki at http://wiki.apache.org/solr/CoreAdmin#cores.
-|`collectionsHandler` |As above, for custom CollectionsHandler implementations.
-| `infoHandler` |As above, for custom InfoHandler implementations.
-|`coreLoadThreads` |Specifies the number of threads that will be assigned to load cores in parallel.
-|`coreRootDirectory` |The root of the core discovery tree, defaults to `$SOLR_HOME`.
-|`managementPath` |Currently non-operational.
-|`sharedLib` |Specifies the path to a common library directory that will be shared across all cores. Any JAR files in this directory will be added to the search path for Solr plugins. This path is relative to `$SOLR_HOME`. Custom handlers may be placed in this directory.
-|`shareSchema` |This attribute, when set to true, ensures that the multiple cores pointing to the same Schema resource file will be referring to the same IndexSchema Object. Sharing the IndexSchema Object makes loading the core faster. If you use this feature, make sure that no core-specific property is used in your Schema file.
-|`transientCacheSize` |Defines how many cores with transient=true that can be loaded before swapping the least recently used core for a new core.
-|`configSetBaseDir` |The directory under which configsets for Solr cores can be found. Defaults to `$SOLR_HOME/configsets`.
-|===
+`adminHandler`::
+This attribute does not need to be set.
++
+If used, this attribute should be set to the FQN (Fully qualified name) of a class that inherits from CoreAdminHandler. For example, `<str name="adminHandler">com.myorg.MyAdminHandler</str>` would configure the custom admin handler (MyAdminHandler) to handle admin requests.
++
+If this attribute isn't set, Solr uses the default admin handler, `org.apache.solr.handler.admin.CoreAdminHandler`.
+
+`collectionsHandler`::
+As above, for custom CollectionsHandler implementations.
+
+`infoHandler`::
+As above, for custom InfoHandler implementations.
+
+`coreLoadThreads`::
+Specifies the number of threads that will be assigned to load cores in parallel.
+
+`coreRootDirectory`::
+The root of the core discovery tree, defaults to `$SOLR_HOME` (by default, `server/solr`).
+
+`managementPath`::
+Currently non-operational.
+
+`sharedLib`::
+Specifies the path to a common library directory that will be shared across all cores. Any JAR files in this directory will be added to the search path for Solr plugins. This path is relative to `$SOLR_HOME`. Custom handlers may be placed in this directory.
+
+`shareSchema`::
+This attribute, when set to `true`, ensures that the multiple cores pointing to the same Schema resource file will be referring to the same IndexSchema Object. Sharing the IndexSchema Object makes loading the core faster. If you use this feature, make sure that no core-specific property is used in your Schema file.
+
+`transientCacheSize`::
+Defines how many cores with `transient=true` that can be loaded before swapping the least recently used core for a new core.
+
+`configSetBaseDir`::
+The directory under which configSets for Solr cores can be found. Defaults to `$SOLR_HOME/configsets`.
+
=== The <solrcloud> Element
This element defines several parameters that relate so SolrCloud. This section is ignored unless theSolr instance is started with either `-DzkRun` or `-DzkHost`
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="30,70",options="header"]
-|===
-|Node |Description
-|`distribUpdateConnTimeout` |Used to set the underlying "connTimeout" for intra-cluster updates.
-|`distribUpdateSoTimeout` |Used to set the underlying "socketTimeout" for intra-cluster updates.
-|`host` |The hostname Solr uses to access cores.
-|`hostContext` |The url context path.
-|`hostPort` |The port Solr uses to access cores. In the default `solr.xml` file, this is set to `${jetty.port:8983`}, which will use the Solr port defined in Jetty, and otherwise fall back to 8983.
-|`leaderVoteWait` |When SolrCloud is starting up, how long each Solr node will wait for all known replicas for that shard to be found before assuming that any nodes that haven't reported are down.
-|`leaderConflictResolveWait` |When trying to elect a leader for a shard, this property sets the maximum time a replica will wait to see conflicting state information to be resolved; temporary conflicts in state information can occur when doing rolling restarts, especially when the node hosting the Overseer is restarted. Typically, the default value of 180000 (ms) is sufficient for conflicts to be resolved; you may need to increase this value if you have hundreds or thousands of small collections in SolrCloud.
-|`zkClientTimeout` |A timeout for connection to a ZooKeeper server. It is used with SolrCloud.
-|`zkHost` |In SolrCloud mode, the URL of the ZooKeeper host that Solr should use for cluster state information.
-|`genericCoreNodeNames` |If `TRUE`, node names are not based on the address of the node, but on a generic name that identifies the core. When a different machine takes over serving that core things will be much easier to understand.
-|`zkCredentialsProvider` & ` zkACLProvider` |Optional parameters that can be specified if you are using <<zookeeper-access-control.adoc#zookeeper-access-control,ZooKeeper Access Control>>.
-|===
+`distribUpdateConnTimeout`::
+Used to set the underlying `connTimeout` for intra-cluster updates.
+
+`distribUpdateSoTimeout`::
+Used to set the underlying `socketTimeout` for intra-cluster updates.
+
+`host`::
+The hostname Solr uses to access cores.
+
+`hostContext`::
+The url context path.
+
+`hostPort`::
+The port Solr uses to access cores.
++
+In the default `solr.xml` file, this is set to `${jetty.port:8983}`, which will use the Solr port defined in Jetty, and otherwise fall back to 8983.
+
+`leaderVoteWait`::
+When SolrCloud is starting up, how long each Solr node will wait for all known replicas for that shard to be found before assuming that any nodes that haven't reported are down.
+
+`leaderConflictResolveWait`::
+When trying to elect a leader for a shard, this property sets the maximum time a replica will wait to see conflicting state information to be resolved; temporary conflicts in state information can occur when doing rolling restarts, especially when the node hosting the Overseer is restarted.
++
+Typically, the default value of `180000` (ms) is sufficient for conflicts to be resolved; you may need to increase this value if you have hundreds or thousands of small collections in SolrCloud.
+
+`zkClientTimeout`::
+A timeout for connection to a ZooKeeper server. It is used with SolrCloud.
+
+`zkHost`::
+In SolrCloud mode, the URL of the ZooKeeper host that Solr should use for cluster state information.
+
+`genericCoreNodeNames`::
+If `TRUE`, node names are not based on the address of the node, but on a generic name that identifies the core. When a different machine takes over serving that core things will be much easier to understand.
+
+`zkCredentialsProvider` & `zkACLProvider`::
+Optional parameters that can be specified if you are using <<zookeeper-access-control.adoc#zookeeper-access-control,ZooKeeper Access Control>>.
+
=== The <logging> Element
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`class`::
+The class to use for logging. The corresponding JAR file must be available to Solr, perhaps through a `<lib>` directive in `solrconfig.xml`.
-[cols="30,70",options="header"]
-|===
-|Node |Description
-|`class` |The class to use for logging. The corresponding JAR file must be available to Solr, perhaps through a `<lib>` directive in `solrconfig.xml`.
-|`enabled` |true/false - whether to enable logging or not.
-|===
+`enabled`::
+true/false - whether to enable logging or not.
==== The <logging><watcher> Element
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+`size`::
+The number of log events that are buffered.
-[cols="30,70",options="header"]
-|===
-|Node |Description
-|`size` |The number of log events that are buffered.
-|`threshold` |The logging level above which your particular logging implementation will record. For example when using log4j one might specify DEBUG, WARN, INFO, etc.
-|===
+`threshold`::
+The logging level above which your particular logging implementation will record. For example when using log4j one might specify DEBUG, WARN, INFO, etc.
=== The <shardHandlerFactory> Element
@@ -127,26 +159,40 @@ Custom shard handlers can be defined in `solr.xml` if you wish to create a custo
Since this is a custom shard handler, sub-elements are specific to the implementation. The default and only shard handler provided by Solr is the HttpShardHandlerFactory in which case, the following sub-elements can be specified:
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
-
-[cols="30,70",options="header"]
-|===
-|Node |Description
-|`socketTimeout` |The read timeout for intra-cluster query and administrative requests. The default is the same as the `distribUpdateSoTimeout` specified in the `<solrcloud>` section.
-|`connTimeout` |The connection timeout for intra-cluster query and administrative requests. Defaults to the `distribUpdateConnTimeout` specified in the `<solrcloud>` section
-|`urlScheme` |URL scheme to be used in distributed search
-|`maxConnectionsPerHost` |Maximum connections allowed per host. Defaults to 20
-|`maxConnections` |Maximum total connections allowed. Defaults to 10000
-|`corePoolSize` |The initial core size of the threadpool servicing requests. Default is 0.
-|`maximumPoolSize` |The maximum size of the threadpool servicing requests. Default is unlimited.
-|`maxThreadIdleTime` |The amount of time in seconds that idle threads persist for in the queue, before being killed. Default is 5 seconds.
-|`sizeOfQueue` |If the threadpool uses a backing queue, what is its maximum size to use direct handoff. Default is to use a SynchronousQueue.
-|`fairnessPolicy` |A boolean to configure if the threadpool favours fairness over throughput. Default is false to favor throughput.
-|===
+`socketTimeout`::
+The read timeout for intra-cluster query and administrative requests. The default is the same as the `distribUpdateSoTimeout` specified in the `<solrcloud>` section.
+
+`connTimeout`::
+The connection timeout for intra-cluster query and administrative requests. Defaults to the `distribUpdateConnTimeout` specified in the `<solrcloud>` section.
+
+`urlScheme`::
+The URL scheme to be used in distributed search.
+
+`maxConnectionsPerHost`::
+Maximum connections allowed per host. Defaults to `20`.
+
+`maxConnections`::
+Maximum total connections allowed. Defaults to `10000`.
+
+`corePoolSize`::
+The initial core size of the threadpool servicing requests. Default is `0`.
+
+`maximumPoolSize`::
+The maximum size of the threadpool servicing requests. Default is unlimited.
+
+`maxThreadIdleTime`::
+The amount of time in seconds that idle threads persist for in the queue, before being killed. Default is `5` seconds.
+
+`sizeOfQueue`::
+If the threadpool uses a backing queue, what is its maximum size to use direct handoff. Default is to use a SynchronousQueue.
+
+`fairnessPolicy`::
+A boolean to configure if the threadpool favors fairness over throughput. Default is false to favor throughput.
+
=== The <metrics> Element
-The `<metrics>` element in `solr.xml` allows you to customize the metrics reported by Solr. You can define system properties that should not be returned, or define custom suppliers and reporters.
+The `<metrics>` element in `solr.xml` allows you to customize the metrics reported by Solr. You can define system properties that should not be returned, or define custom suppliers and reporters.
In a default `solr.xml` you will not see any `<metrics>` configuration. If you would like to customize the metrics for your installation, see the section <<metrics-reporting.adoc#metrics-configuration,Metrics Configuration>>.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/93c96b06/solr/solr-ref-guide/src/function-queries.adoc
----------------------------------------------------------------------
diff --git a/solr/solr-ref-guide/src/function-queries.adoc b/solr/solr-ref-guide/src/function-queries.adoc
index 86a7d02..29cca9c 100644
--- a/solr/solr-ref-guide/src/function-queries.adoc
+++ b/solr/solr-ref-guide/src/function-queries.adoc
@@ -1,6 +1,7 @@
= Function Queries
:page-shortname: function-queries
:page-permalink: function-queries.html
+:page-tocclass: right
// 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
@@ -80,57 +81,90 @@ Only functions with fast random access are recommended.
The table below summarizes the functions available for function queries.
-// TODO: Change column width to %autowidth.spread when https://github.com/asciidoctor/asciidoctor-pdf/issues/599 is fixed
+=== abs Function
+Returns the absolute value of the specified value or function.
-[cols="20,40,40",options="header"]
-|===
-|Function |Description |Syntax Examples
-|abs |Returns the absolute value of the specified value or function. |`abs(x)` `abs(-5)`
+*Syntax Example*
-|childfield(field) |Returns the value of the given field for one of the matched child docs when searching by <<other-parsers.adoc#OtherParsers-BlockJoinParentQueryParser,{!parent}>>. It can be used only in `sort` parameter. a|
-* `sort=childfield(name) asc` implies `$q` as a second argument and therefor it assumes `q={!parent ..}..`;
+* `abs(x)` `abs(-5)`
+
+=== childfield(field) Function
+Returns the value of the given field for one of the matched child docs when searching by <<other-parsers.adoc#OtherParsers-BlockJoinParentQueryParser,{!parent}>>. It can be used only in `sort` parameter.
+
+*Syntax Examples*
+
+* `sort=childfield(name) asc` implies `$q` as a second argument and therefore it assumes `q={!parent ..}..`;
* `sort=childfield(field,$bjq) asc` refers to a separate parameter `bjq={!parent ..}..`;
* `sort=childfield(field,{!parent of=...}...) desc` allows to inline block join parent query
-|concat(v,f..)|concatenates the given string fields, literals and other functions |`concat(name," ",$param,def(opt,"-"))`
+=== concat Function
+Concatenates the given string fields, literals and other functions.
+
+*Syntax Example*
+
+* `concat(name," ",$param,def(opt,"-"))`
+
+=== "constant" Function
+
+Specifies a floating point constant.
+
+*Syntax Example*
+
+* `1.5`
-|"constant" |Specifies a floating point constant. |`1.5`
+=== def Function
+`def` is short for default. Returns the value of field "field", or if the field does not exist, returns the default value specified. Yields the first value where `exists()==true`.
-|def |`def` is short for default. Returns the value of field "field", or if the field does not exist, returns the default value specified. and yields the first value where `exists()==true`.) |`def(rating,5):` This `def()` function returns the rating, or if no rating specified in the doc, returns 5 `def(myfield, 1.0):` equivalent to `if(exists(myfield),myfield,1.0)`
+*Syntax Example*
-|div |Divides one value or function by another. div(x,y) divides x by y. a|`div(1,y)`
+* `def(rating,5)`: This `def()` function returns the rating, or if no rating specified in the doc, returns 5 `def(myfield, 1.0):` equivalent to `if(exists(myfield),myfield,1.0)`
-`div(sum(x,100),max(y,1))`
+=== div Function
+Divides one value or function by another. `div(x,y)` divides `x` by `y`.
-|dist |Return the distance between two vectors (points) in an n-dimensional space. Takes in the power, plus two or more ValueSource instances and calculates the distances between the two vectors. Each ValueSource must be a number. There must be an even number of ValueSource instances passed in and the method assumes that the first half represent the first vector and the second half represent the second vector. a|`dist(2, x, y, 0, 0):` calculates the Euclidean distance between (0,0) and (x,y) for each document.
+*Syntax Examples*
-`dist(1, x, y, 0, 0)`: calculates the Manhattan (taxicab) distance between (0,0) and (x,y) for each document.
+* `div(1,y)`
+* `div(sum(x,100),max(y,1))`
-`dist(2, x,y,z,0,0,0):` Euclidean distance between (0,0,0) and (x,y,z) for each document.
+=== dist Function
+Returns the distance between two vectors (points) in an n-dimensional space. Takes in the power, plus two or more ValueSource instances and calculates the distances between the two vectors. Each ValueSource must be a number.
-`dist(1,x,y,z,e,f,g)`: Manhattan distance between (x,y,z) and (e,f,g) where each letter is a field name.
+There must be an even number of ValueSource instances passed in and the method assumes that the first half represent the first vector and the second half represent the second vector.
-|docfreq(field,val) |Returns the number of documents that contain the term in the field. This is a constant (the same value for all documents in the index).
+*Syntax Examples*
-You can quote the term if it's more complex, or do parameter substitution for the term value. a|`docfreq(text,'solr')`
+* `dist(2, x, y, 0, 0)`: calculates the Euclidean distance between (0,0) and (x,y) for each document.
+* `dist(1, x, y, 0, 0)`: calculates the Manhattan (taxicab) distance between (0,0) and (x,y) for each document.
+* `dist(2, x,y,z,0,0,0):` Euclidean distance between (0,0,0) and (x,y,z) for each document.
+* `dist(1,x,y,z,e,f,g)`: Manhattan distance between (x,y,z) and (e,f,g) where each letter is a field name.
-`...&defType=func` `&q=docfreq(text,$myterm)&myterm=solr`
+=== docfreq(field,val) Function
+Returns the number of documents that contain the term in the field. This is a constant (the same value for all documents in the index).
-|field[[FunctionQueries-field]] a|
+You can quote the term if it's more complex, or do parameter substitution for the term value.
+
+*Syntax Examples*
+
+* `docfreq(text,'solr')`
+* `...&defType=func` `&q=docfreq(text,$myterm)&myterm=solr`
+
+[[FunctionQueries-field]]
+=== field Function
Returns the numeric docValues or indexed value of the field with the specified name. In its simplest (single argument) form, this function can only be used on single valued fields, and can be called using the name of the field as a string, or for most conventional field names simply use the field name by itself with out using the `field(...)` syntax.
-When using docValues, an optional 2nd argument can be specified to select the "`min"` or "```max```" value of multivalued fields.
+When using docValues, an optional 2nd argument can be specified to select the `min` or `max` value of multivalued fields.
0 is returned for documents without a value in the field.
- a|
+*Syntax Examples*
These 3 examples are all equivalent:
* `myFloatFieldName`
* `field(myFloatFieldName)`
* `field("myFloatFieldName")`
-The last form is convinient when your field name is atypical:
+The last form is convenient when your field name is atypical:
* `field("my complex float fieldName")`
@@ -139,11 +173,21 @@ For multivalued docValues fields:
* `field(myMultiValuedFloatField,min)`
* `field(myMultiValuedFloatField,max)`
-|hsin |The Haversine distance calculates the distance between two points on a sphere when traveling along the sphere. The values must be in radians. `hsin` also take a Boolean argument to specify whether the function should convert its output to radians. |`hsin(2, true, x, y, 0, 0)`
+=== hsin Function
+The Haversine distance calculates the distance between two points on a sphere when traveling along the sphere. The values must be in radians. `hsin` also take a Boolean argument to specify whether the function should convert its output to radians.
+
+*Syntax Example*
-|idf |Inverse document frequency; a measure of whether the term is common or rare across all documents. Obtained by dividing the total number of documents by the number of documents containing the term, and then taking the logarithm of that quotient. See also `tf`. |`idf(fieldName,'solr')`: measures the inverse of the frequency of the occurrence of the term `'solr'` in `fieldName`.
+* `hsin(2, true, x, y, 0, 0)`
-|if a|
+=== idf Function
+Inverse document frequency; a measure of whether the term is common or rare across all documents. Obtained by dividing the total number of documents by the number of documents containing the term, and then taking the logarithm of that quotient. See also `tf`.
+
+*Syntax Example*
+
+* `idf(fieldName,'solr')`: measures the inverse of the frequency of the occurrence of the term `'solr'` in `fieldName`.
+
+=== if Function
Enables conditional function queries. In `if(test,value1,value2)`:
* `test` is or refers to a logical value or expression that returns a logical value (TRUE or FALSE).
@@ -152,174 +196,312 @@ Enables conditional function queries. In `if(test,value1,value2)`:
An expression can be any function which outputs boolean values, or even functions returning numeric values, in which case value 0 will be interpreted as false, or strings, in which case empty string is interpreted as false.
- a|`if(termfreq` `(cat,'electronics'),` `popularity,42)`: This function checks each document for the to see if it contains the term "```electronics```" in the `cat` field. If it does, then the value of the `popularity` field is returned, otherwise the value of `42` is returned.
+*Syntax Example*
+
+* `if(termfreq (cat,'electronics'),popularity,42)`: This function checks each document for to see if it contains the term "electronics" in the `cat` field. If it does, then the value of the `popularity` field is returned, otherwise the value of `42` is returned.
-|linear |Implements `m*x+c` where `m` and `c` are constants and `x` is an arbitrary function. This is equivalent to `sum(product(m,x),c)`, but slightly more efficient as it is implemented as a single function. a|`linear(x,m,c)`
+=== linear Function
+Implements `m*x+c` where `m` and `c` are constants and `x` is an arbitrary function. This is equivalent to `sum(product(m,x),c)`, but slightly more efficient as it is implemented as a single function.
-`linear(x,2,4)` returns `2*x+4`
+*Syntax Examples*
-|log |Returns the log base 10 of the specified function. a|
-`log(x)`
+* `linear(x,m,c)`
+* `linear(x,2,4)`: returns `2*x+4`
-`log(sum(x,100))`
+=== log Function
+Returns the log base 10 of the specified function.
-|map |Maps any values of an input function x that fall within min and max inclusive to the specified target. The arguments min and max must be constants. The arguments `target` and `default` can be constants or functions. If the value of x does not fall between min and max, then either the value of x is returned, or a default value is returned if specified as a 5th argument. a|
-`map(x,min,max,target)` `map(x,0,0,1)` - changes any values of 0 to 1. This can be useful in handling default 0 values.
+*Syntax Examples*
-`map(x,min,max,target,default)` `map(x,0,100,1,-1)` - changes any values between `0` and `100` to `1`, and all other values to` -1`.
+* `log(x)`
+* `log(sum(x,100))`
-`map(x,0,100,` `sum(x,599),` `docfreq(text,solr))` - changes any values between `0` and `100` to x+599, and all other values to frequency of the term 'solr' in the field text.
+=== map Function
+Maps any values of an input function `x` that fall within `min` and `max` inclusive to the specified `target`. The arguments `min` and `max` must be constants. The arguments `target` and `default` can be constants or functions.
-|max a|
-Returns the maximum numeric value of multiple nested functions or constants, which are specified as arguments: `max(x,y,...)`. The max function can also be useful for "bottoming out" another function or field at some specified constant.
+If the value of `x` does not fall between `min` and `max`, then either the value of `x` is returned, or a default value is returned if specified as a 5th argument.
-(Use the `field(myfield,max)` syntax for <<FunctionQueries-field,selecting the maximum value of a single multivalued field>>)
+*Syntax Examples*
- |`max(myfield,myotherfield,0)`
+* `map(x,min,max,target)`
+** `map(x,0,0,1)`: Changes any values of 0 to 1. This can be useful in handling default 0 values.
+* `map(x,min,max,target,default)`
+** `map(x,0,100,1,-1)`: Changes any values between `0` and `100` to `1`, and all other values to` -1`.
+* `map(x,0,100,sum(x,599),docfreq(text,solr))`: Changes any values between `0` and `100` to x+599, and all other values to frequency of the term 'solr' in the field text.
-|maxdoc |Returns the number of documents in the index, including those that are marked as deleted but have not yet been purged. This is a constant (the same value for all documents in the index). |`maxdoc()`
+=== max Function
+Returns the maximum numeric value of multiple nested functions or constants, which are specified as arguments: `max(x,y,...)`. The `max` function can also be useful for "bottoming out" another function or field at some specified constant.
-|min a|
-Returns the minimum numeric value of multiple nested functions of constants, which are specified as arguments: `min(x,y,...)`. The min function can also be useful for providing an "upper bound" on a function using a constant.
+Use the `field(myfield,max)` syntax for <<FunctionQueries-field,selecting the maximum value of a single multivalued field>>.
-(Use the `field(myfield,min)` <<FunctionQueries-field,syntax for selecting the minimum value of a single multivalued field>>)
+*Syntax Example*
- |`min(myfield,myotherfield,0)`
+* `max(myfield,myotherfield,0)`
-|ms a|
-Returns milliseconds of difference between its arguments. Dates are relative to the Unix or POSIX time epoch, midnight, January 1, 1970 UTC. Arguments may be the name of an indexed `TrieDateField`, or date math based on a <<working-with-dates.adoc#working-with-dates,constant date or `NOW`>>.
+=== maxdoc Function
+Returns the number of documents in the index, including those that are marked as deleted but have not yet been purged. This is a constant (the same value for all documents in the index).
+
+*Syntax Example*
+
+* `maxdoc()`
+
+=== min Function
+Returns the minimum numeric value of multiple nested functions of constants, which are specified as arguments: `min(x,y,...)`. The `min` function can also be useful for providing an "upper bound" on a function using a constant.
+
+Use the `field(myfield,min)` <<FunctionQueries-field,syntax for selecting the minimum value of a single multivalued field>>.
+
+*Syntax Example*
+
+* `min(myfield,myotherfield,0)`
+
+=== ms Function
+Returns milliseconds of difference between its arguments. Dates are relative to the Unix or POSIX time epoch, midnight, January 1, 1970 UTC.
+
+Arguments may be the name of an indexed `TrieDateField`, or date math based on a <<working-with-dates.adoc#working-with-dates,constant date or `NOW`>>.
* `ms()`: Equivalent to `ms(NOW)`, number of milliseconds since the epoch.
* `ms(a):` Returns the number of milliseconds since the epoch that the argument represents.
-* `ms(a,b)` : Returns the number of milliseconds that b occurs before a (that is, a - b) a|`ms(NOW/DAY)`
+* `ms(a,b)` : Returns the number of milliseconds that b occurs before a (that is, a - b)
-`ms(2000-01-01T00:00:00Z)`
+*Syntax Examples*
-`ms(mydatefield)`
+* `ms(NOW/DAY)`
+* `ms(2000-01-01T00:00:00Z)`
+* `ms(mydatefield)`
+* `ms(NOW,mydatefield)`
+* `ms(mydatefield, 2000-01-01T00:00:00Z)`
+* `ms(datefield1, datefield2)`
-`ms(NOW,mydatefield)`
+=== norm(_field_) Function
+Returns the "norm" stored in the index for the specified field. This is the product of the index time boost and the length normalization factor, according to the {lucene-javadocs}/core/org/apache/lucene/search/similarities/Similarity.html[Similarity] for the field.
-`ms(mydatefield, 2000-01-01T00:00:00Z)`
+*Syntax Example*
-`ms(datefield1, datefield2)`
+* `norm(fieldName)`
-|norm(_field_) |Returns the "norm" stored in the index for the specified field. This is the product of the index time boost and the length normalization factor, according to the {lucene-javadocs}/core/org/apache/lucene/search/similarities/Similarity.html[Similarity] for the field. |`norm(fieldName)`
+=== numdocs Function
+Returns the number of documents in the index, not including those that are marked as deleted but have not yet been purged. This is a constant (the same value for all documents in the index).
-|numdocs |Returns the number of documents in the index, not including those that are marked as deleted but have not yet been purged. This is a constant (the same value for all documents in the index). |`numdocs()`
+*Syntax Example*
-|ord a|
-Returns the ordinal of the indexed field value within the indexed list of terms for that field in Lucene index order (lexicographically ordered by unicode value), starting at 1. In other words, for a given field, all values are ordered lexicographically; this function then returns the offset of a particular value in that ordering. The field must have a maximum of one value per document (not multi-valued). 0 is returned for documents without a value in the field.
+* `numdocs()`
-[IMPORTANT]
-====
-`ord()` depends on the position in an index and can change when other documents are inserted or deleted.
-====
+=== ord Function
+Returns the ordinal of the indexed field value within the indexed list of terms for that field in Lucene index order (lexicographically ordered by unicode value), starting at 1.
+
+In other words, for a given field, all values are ordered lexicographically; this function then returns the offset of a particular value in that ordering. The field must have a maximum of one value per document (not multi-valued). `0` is returned for documents without a value in the field.
+
+IMPORTANT: `ord()` depends on the position in an index and can change when other documents are inserted or deleted.
See also `rord` below.
- a|`ord(myIndexedField)`
+*Syntax Example*
+
+* `ord(myIndexedField)`
+
+* If there were only three values ("apple","banana","pear") for a particular field X, then `ord(X)` would be `1` for documents containing "apple", `2` for documents containing "banana", etc.
-Example: If there were only three values ("apple","banana","pear") for a particular field X, then `ord(X)` would be `1` for documents containing "apple", `2` for documents containing "banana", etc.
+=== payload Function
+Returns the float value computed from the decoded payloads of the term specified.
-|payload a|
-Returns the float value computed from the decoded payloads of the term specified. The return value is computed using the `min`, `max`, or `average` of the decoded payloads. A special `first` function can be used instead of the others, to short-circuit term enumeration and return only the decoded payload of the first term. The field specified must have float or integer payload encoding capability (via `DelimitedPayloadTokenFilter` or `NumericPayloadTokenFilter`). If no payload is found for the term, the default value is returned.
+The return value is computed using the `min`, `max`, or `average` of the decoded payloads. A special `first` function can be used instead of the others, to short-circuit term enumeration and return only the decoded payload of the first term.
+
+The field specified must have float or integer payload encoding capability (via `DelimitedPayloadTokenFilter` or `NumericPayloadTokenFilter`). If no payload is found for the term, the default value is returned.
* `payload(field_name,term)`: default value is 0.0, `average` function is used.
* `payload(field_name,term,default_value)`: default value can be a constant, field name, or another float returning function. `average` function used.
-* `payload(field_name,term,default_value,function)`: function values can be `min`, `max`, `average`, or `first`. |`payload(payloaded_field_dpf,term,0.0,first)`
+* `payload(field_name,term,default_value,function)`: function values can be `min`, `max`, `average`, or `first`.
+
+*Syntax Example*
+
+* `payload(payloaded_field_dpf,term,0.0,first)`
+
+=== pow Function
-|pow |Raises the specified base to the specified power. `pow(x,y)` raises x to the power of y. a|`pow(x,y)`
+Raises the specified base to the specified power. `pow(x,y)` raises `x` to the power of `y`.
-`pow(x,log(y))`
+*Syntax Examples*
-`pow(x,0.5):` the same as `sqrt`
+* `pow(x,y)`
+* `pow(x,log(y))`
+* `pow(x,0.5):` the same as `sqrt`
-|product |Returns the product of multiple values or functions, which are specified in a comma-separated list. `mul(...)` may also be used as an alias for this function. |`product(x,y,...)` `product(x,2)` `product(x,y)mul(x,y)`
+=== product Function
+Returns the product of multiple values or functions, which are specified in a comma-separated list. `mul(...)` may also be used as an alias for this function.
-|query |Returns the score for the given subquery, or the default value for documents not matching the query. Any type of subquery is supported through either parameter de-referencing `$otherparam` or direct specification of the query string in the <<local-parameters-in-queries.adoc#local-parameters-in-queries,Local Parameters>> through the `v` key. a|`query(subquery, default)`
+*Syntax Examples*
-`q=product` `(popularity,` `query({!dismax v='solr rocks'})`: returns the product of the popularity and the score of the DisMax query.
+* `product(x,y,...)`
+* `product(x,2)`
+* `product(x,y)mul(x,y)`
-`q=product` `(popularity,` `query($qq))&qq={!dismax}solr rocks`: equivalent to the previous query, using parameter de-referencing.
+=== query Function
+Returns the score for the given subquery, or the default value for documents not matching the query. Any type of subquery is supported through either parameter de-referencing `$otherparam` or direct specification of the query string in the <<local-parameters-in-queries.adoc#local-parameters-in-queries,Local Parameters>> through the `v` key.
-`q=product` `(popularity,` `query($qq,0.1))` `&qq={!dismax}` `solr rocks`: specifies a default score of 0.1 for documents that don't match the DisMax query.
-|recip a|
+*Syntax Examples*
+
+* `query(subquery, default)`
+* `q=product (popularity,query({!dismax v='solr rocks'})`: returns the product of the popularity and the score of the DisMax query.
+* `q=product (popularity,query($qq))&qq={!dismax}solr rocks`: equivalent to the previous query, using parameter de-referencing.
+* `q=product (popularity,query($qq,0.1))&qq={!dismax}solr rocks`: specifies a default score of 0.1 for documents that don't match the DisMax query.
+
+=== recip Function
Performs a reciprocal function with `recip(x,m,a,b)` implementing `a/(m*x+b)` where `m,a,b` are constants, and `x` is any arbitrarily complex function.
-When a and b are equal, and x>=0, this function has a maximum value of 1 that drops as x increases. Increasing the value of a and b together results in a movement of the entire function to a flatter part of the curve. These properties can make this an ideal function for boosting more recent documents when x is `rord(datefield)`.
+When `a` and `b` are equal, and `x>=0`, this function has a maximum value of `1` that drops as `x` increases. Increasing the value of `a` and `b` together results in a movement of the entire function to a flatter part of the curve. These properties can make this an ideal function for boosting more recent documents when x is `rord(datefield)`.
+
+*Syntax Examples*
+
+* `recip(myfield,m,a,b)`
+* `recip(rord` `(creationDate), 1,1000,1000)`
+
+=== rord Function
+Returns the reverse ordering of that returned by `ord`.
+
+*Syntax Example*
+
+* `rord(myDateField)`
+
+=== scale Function
+Scales values of the function `x` such that they fall between the specified `minTarget` and `maxTarget` inclusive. The current implementation traverses all of the function values to obtain the min and max, so it can pick the correct scale.
+
+The current implementation cannot distinguish when documents have been deleted or documents that have no value. It uses `0.0` values for these cases. This means that if values are normally all greater than `0.0`, one can still end up with `0.0` as the `min` value to map from. In these cases, an appropriate `map()` function could be used as a workaround to change `0.0` to a value in the real range, as shown here: `scale(map(x,0,0,5),1,2)`
-a|`recip(myfield,m,a,b)`
+*Syntax Examples*
-`recip(rord` `(creationDate), 1,1000,1000)`
+* `scale(x, minTarget, maxTarget)`
+* `scale(x,1,2)`: scales the values of x such that all values will be between 1 and 2 inclusive.
-|rord |Returns the reverse ordering of that returned by `ord`. |`rord(myDateField)`
+=== sqedist Function
+The Square Euclidean distance calculates the 2-norm (Euclidean distance) but does not take the square root, thus saving a fairly expensive operation. It is often the case that applications that care about Euclidean distance do not need the actual distance, but instead can use the square of the distance. There must be an even number of ValueSource instances passed in and the method assumes that the first half represent the first vector and the second half represent the second vector.
-|scale a|
-Scales values of the function x such that they fall between the specified `minTarget` and `maxTarget` inclusive. The current implementation traverses all of the function values to obtain the min and max, so it can pick the correct scale.
+*Syntax Example*
-The current implementation cannot distinguish when documents have been deleted or documents that have no value. It uses 0.0 values for these cases. This means that if values are normally all greater than 0.0, one can still end up with 0.0 as the min value to map from. In these cases, an appropriate map() function could be used as a workaround to change 0.0 to a value in the real range, as shown here: `scale(map(x,0,0,5),1,2)` a|`scale(x, minTarget, maxTarget)`
+* `sqedist(x_td, y_td, 0, 0)`
-`scale(x,1,2)`: scales the values of x such that all values will be between 1 and 2 inclusive.
+=== sqrt Function
+Returns the square root of the specified value or function.
-|sqedist |The Square Euclidean distance calculates the 2-norm (Euclidean distance) but does not take the square root, thus saving a fairly expensive operation. It is often the case that applications that care about Euclidean distance do not need the actual distance, but instead can use the square of the distance. There must be an even number of ValueSource instances passed in and the method assumes that the first half represent the first vector and the second half represent the second vector. |`sqedist(x_td, y_td, 0, 0)`
+*Syntax Example*
-|sqrt |Returns the square root of the specified value or function. |`sqrt(x)sqrt(100)sqrt(sum(x,100))`
+* `sqrt(x)sqrt(100)sqrt(sum(x,100))`
-|strdist a|Calculate the distance between two strings. Uses the Lucene spell checker `StringDistance` interface and supports all of the implementations available in that package, plus allows applications to plug in their own via Solr's resource loading capabilities. `strdist` takes (string1, string2, distance measure).
+=== strdist Function
+Calculate the distance between two strings. Uses the Lucene spell checker `StringDistance` interface and supports all of the implementations available in that package, plus allows applications to plug in their own via Solr's resource loading capabilities. `strdist` takes (string1, string2, distance measure).
Possible values for distance measure are:
* jw: Jaro-Winkler
* edit: Levenstein or Edit distance
* ngram: The NGramDistance, if specified, can optionally pass in the ngram size too. Default is 2.
-* FQN: Fully Qualified class Name for an implementation of the StringDistance interface. Must have a no-arg constructor. |`strdist("SOLR",id,edit)`
+* FQN: Fully Qualified class Name for an implementation of the StringDistance interface. Must have a no-arg constructor.
-|sub |Returns `x-y` from `sub(x,y)`. a|`sub(myfield,myfield2)`
+*Syntax Example*
-`sub(100, sqrt(myfield))`
+* `strdist("SOLR",id,edit)`
-|sum |Returns the sum of multiple values or functions, which are specified in a comma-separated list. `add(...)` may be used as an alias for this function a|`sum(x,y,...) sum(x,1)`
+=== sub Function
+Returns `x-y` from `sub(x,y)`.
-`sum(x,y)`
+*Syntax Examples*
-`sum(sqrt(x),log(y),z,0.5)`
+* `sub(myfield,myfield2)`
+* `sub(100, sqrt(myfield))`
-`add(x,y)`
+=== sum Function
+Returns the sum of multiple values or functions, which are specified in a comma-separated list. `add(...)` may be used as an alias for this function.
-|sumtotaltermfreq |Returns the sum of `totaltermfreq` values for all terms in the field in the entire index (i.e., the number of indexed tokens for that field). (Aliases `sumtotaltermfreq` to `sttf`.) a|If doc1:(fieldX:A B C) and doc2:(fieldX:A A A A):
+*Syntax Examples*
-`docFreq(fieldX:A)` = 2 (A appears in 2 docs)
+* `sum(x,y,...) sum(x,1)`
+* `sum(x,y)`
+* `sum(sqrt(x),log(y),z,0.5)`
+* `add(x,y)`
-`freq(doc1, fieldX:A)` = 4 (A appears 4 times in doc 2)
+=== sumtotaltermfreq Function
+Returns the sum of `totaltermfreq` values for all terms in the field in the entire index (i.e., the number of indexed tokens for that field). (Aliases `sumtotaltermfreq` to `sttf`.)
-`totalTermFreq(fieldX:A)` = 5 (A appears 5 times across all docs)
+*Syntax Example*
+If doc1:(fieldX:A B C) and doc2:(fieldX:A A A A):
-`sumTotalTermFreq(fieldX)` = 7 in `fieldX`, there are 5 As, 1 B, 1 C
+* `docFreq(fieldX:A)` = 2 (A appears in 2 docs)
+* `freq(doc1, fieldX:A)` = 4 (A appears 4 times in doc 2)
+* `totalTermFreq(fieldX:A)` = 5 (A appears 5 times across all docs)
+* `sumTotalTermFreq(fieldX)` = 7 in `fieldX`, there are 5 As, 1 B, 1 C
-|termfreq |Returns the number of times the term appears in the field for that document. |`termfreq(text,'memory')`
+=== termfreq Function
+Returns the number of times the term appears in the field for that document.
-|tf |Term frequency; returns the term frequency factor for the given term, using the {lucene-javadocs}/core/org/apache/lucene/search/similarities/Similarity.html[Similarity] for the field. The `tf-idf` value increases proportionally to the number of times a word appears in the document, but is offset by the frequency of the word in the document, which helps to control for the fact that some words are generally more common than others. See also `idf`. |`tf(text,'solr')`
+*Syntax Example*
-|top a|
+* `termfreq(text,'memory')`
+
+=== tf Function
+Term frequency; returns the term frequency factor for the given term, using the {lucene-javadocs}/core/org/apache/lucene/search/similarities/Similarity.html[Similarity] for the field. The `tf-idf` value increases proportionally to the number of times a word appears in the document, but is offset by the frequency of the word in the document, which helps to control for the fact that some words are generally more common than others. See also `idf`.
+
+*Syntax Examples*
+
+* `tf(text,'solr')`
+
+=== top Function
Causes the function query argument to derive its values from the top-level IndexReader containing all parts of an index. For example, the ordinal of a value in a single segment will be different from the ordinal of that same value in the complete index.
-The `ord()` and `rord()` functions implicitly use `top()`, and hence `ord(foo)` is equivalent to `top(ord(foo))`. |
+The `ord()` and `rord()` functions implicitly use `top()`, and hence `ord(foo)` is equivalent to `top(ord(foo))`.
-|totaltermfreq |Returns the number of times the term appears in the field in the entire index. (Aliases `totaltermfreq` to `ttf`.) |`ttf(text,'memory')`
-|===
+=== totaltermfreq Function
+Returns the number of times the term appears in the field in the entire index. (Aliases `totaltermfreq` to `ttf`.)
+*Syntax Example*
+
+* `ttf(text,'memory')`
+
+== Boolean Functions
The following functions are boolean – they return true or false. They are mostly useful as the first argument of the `if` function, and some of these can be combined. If used somewhere else, it will yield a '1' or '0'.
-[width="100%",options="header",]
-|===
-|Function |Description |Syntax Examples
-|and |Returns a value of true if and only if all of its operands evaluate to true. |`and(not` `(exists` `(popularity)),` `exists` `(price)):` returns `true` for any document which has a value in the `price` field, but does not have a value in the `popularity` field
-|or |A logical disjunction. |`or(value1,value2):` TRUE if either `value1` or `value2` is true.
-|xor |Logical exclusive disjunction, or one or the other but not both. |`xor(field1,field2)` returns TRUE if either `field1` or `field2` is true; FALSE if both are true.
-|not |The logically negated value of the wrapped function. |`not(exists(author))`: TRUE only when `exists(author)` is false.
-|exists |Returns TRUE if any member of the field exists. |`exists(author)` returns TRUE for any document has a value in the "author" field. `exists(query(price:5.00))` returns TRUE if "price" matches "5.00".
-|gt, gte, lt, lte, eq |5 comparison functions: Greater Than, Greater Than or Equal, Less Than, Less Than or Equal, Equal |`if(lt(ms(mydatefield),315569259747),0.8,1)` translates to this pseudocode: `if mydatefield < 315569259747 then 0.8 else 1`
-|===
+=== and Function
+Returns a value of true if and only if all of its operands evaluate to true.
+
+*Syntax Example*
+
+* `and(not(exists(popularity)),exists(price))`: returns `true` for any document which has a value in the `price` field, but does not have a value in the `popularity` field.
+
+=== or Function
+A logical disjunction.
+
+*Syntax Example*
+
+* `or(value1,value2):` `true` if either `value1` or `value2` is true.
+
+=== xor Function
+Logical exclusive disjunction, or one or the other but not both.
+
+*Syntax Example*
+
+* `xor(field1,field2)` returns `true` if either `field1` or `field2` is true; FALSE if both are true.
+
+=== not Function
+The logically negated value of the wrapped function.
+
+*Syntax Example*
+
+* `not(exists(author))`: `true` only when `exists(author)` is false.
+
+=== exists Function
+Returns `true` if any member of the field exists.
+
+*Syntax Example*
+
+* `exists(author)`: returns `true` for any document has a value in the "author" field.
+* `exists(query(price:5.00))`: returns `true` if "price" matches "5.00".
+
+=== Comparison Functions
+`gt`, `gte`, `lt`, `lte`, `eq`
+
+5 comparison functions: Greater Than, Greater Than or Equal, Less Than, Less Than or Equal, Equal
+
+*Syntax Example*
+* `if(lt(ms(mydatefield),315569259747),0.8,1)` translates to this pseudocode: `if mydatefield < 315569259747 then 0.8 else 1`
+
[[FunctionQueries-ExampleFunctionQueries]]
== Example Function Queries
[25/27] lucene-solr:feature/autoscaling: SOLR-10272: Reverting a
mistakenly deleted file
Posted by sh...@apache.org.
SOLR-10272: Reverting a mistakenly deleted file
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/c66a8d9f
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/c66a8d9f
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/c66a8d9f
Branch: refs/heads/feature/autoscaling
Commit: c66a8d9fda97f24216e561df410f3eb351b5c934
Parents: ee572b0
Author: Ishan Chattopadhyaya <is...@apache.org>
Authored: Tue Jun 27 09:14:00 2017 +0530
Committer: Ishan Chattopadhyaya <is...@apache.org>
Committed: Tue Jun 27 09:14:00 2017 +0530
----------------------------------------------------------------------
.../solr/cloud/autoscaling/package-info.java | 23 ++++++++++++++++++++
1 file changed, 23 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/c66a8d9f/solr/solrj/src/java/org/apache/solr/cloud/autoscaling/package-info.java
----------------------------------------------------------------------
diff --git a/solr/solrj/src/java/org/apache/solr/cloud/autoscaling/package-info.java b/solr/solrj/src/java/org/apache/solr/cloud/autoscaling/package-info.java
new file mode 100644
index 0000000..472b1ac
--- /dev/null
+++ b/solr/solrj/src/java/org/apache/solr/cloud/autoscaling/package-info.java
@@ -0,0 +1,23 @@
+/*
+ * 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.
+ */
+
+/**
+ * Common classes for autoscaling parsing filtering nodes and sorting
+ */
+
+package org.apache.solr.cloud.autoscaling;
+
[12/27] lucene-solr:feature/autoscaling: SOLR-10823: Add reporting
period to SolrMetricReporter base class.
Posted by sh...@apache.org.
SOLR-10823: Add reporting period to SolrMetricReporter base class.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/44860bd4
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/44860bd4
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/44860bd4
Branch: refs/heads/feature/autoscaling
Commit: 44860bd48a31c76e11808d914be016df7196596a
Parents: 7c44862
Author: Christine Poerschke <cp...@apache.org>
Authored: Mon Jun 26 16:26:37 2017 +0100
Committer: Christine Poerschke <cp...@apache.org>
Committed: Mon Jun 26 16:26:37 2017 +0100
----------------------------------------------------------------------
solr/CHANGES.txt | 2 ++
.../org/apache/solr/metrics/SolrMetricReporter.java | 15 +++++++++++++++
.../solr/metrics/reporters/SolrGangliaReporter.java | 5 -----
.../solr/metrics/reporters/SolrGraphiteReporter.java | 5 -----
.../solr/metrics/reporters/SolrJmxReporter.java | 5 ++++-
.../solr/metrics/reporters/SolrSlf4jReporter.java | 5 -----
.../metrics/reporters/solr/SolrClusterReporter.java | 12 +-----------
.../metrics/reporters/solr/SolrShardReporter.java | 12 +-----------
.../apache/solr/metrics/SolrMetricManagerTest.java | 5 +++++
.../solr/metrics/reporters/MockMetricReporter.java | 3 +++
10 files changed, 31 insertions(+), 38 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 800b645..5b82f1e 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -517,6 +517,8 @@ Other Changes
with point fields and provides control over dynamic fields used for the raw amount and currency
code sub-fields. (hossman, Steve Rowe)
+* SOLR-10823: Add reporting period to SolrMetricReporter base class. (Christine Poerschke)
+
================== 6.6.1 ==================
Bug Fixes
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/core/src/java/org/apache/solr/metrics/SolrMetricReporter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/metrics/SolrMetricReporter.java b/solr/core/src/java/org/apache/solr/metrics/SolrMetricReporter.java
index 222377b..3f7f73c 100644
--- a/solr/core/src/java/org/apache/solr/metrics/SolrMetricReporter.java
+++ b/solr/core/src/java/org/apache/solr/metrics/SolrMetricReporter.java
@@ -36,6 +36,7 @@ public abstract class SolrMetricReporter implements Closeable, PluginInfoInitial
protected final SolrMetricManager metricManager;
protected PluginInfo pluginInfo;
protected boolean enabled = true;
+ protected int period = SolrMetricManager.DEFAULT_CLOUD_REPORTER_PERIOD;
/**
* Create a reporter for metrics managed in a named registry.
@@ -86,6 +87,20 @@ public abstract class SolrMetricReporter implements Closeable, PluginInfoInitial
}
/**
+ * @param period - in seconds
+ */
+ public void setPeriod(int period) {
+ this.period = period;
+ }
+
+ /**
+ * @return period, in seconds
+ */
+ public int getPeriod() {
+ return period;
+ }
+
+ /**
* Get the effective {@link PluginInfo} instance that was used for
* initialization of this plugin.
* @return plugin info, or null if not yet initialized.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGangliaReporter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGangliaReporter.java b/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGangliaReporter.java
index 8d87940..bf95ef4 100644
--- a/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGangliaReporter.java
+++ b/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGangliaReporter.java
@@ -35,7 +35,6 @@ public class SolrGangliaReporter extends SolrMetricReporter {
private String host = null;
private int port = -1;
private boolean multicast;
- private int period = 60;
private String instancePrefix = null;
private List<String> filters = new ArrayList<>();
private boolean testing;
@@ -88,10 +87,6 @@ public class SolrGangliaReporter extends SolrMetricReporter {
}
}
- public void setPeriod(int period) {
- this.period = period;
- }
-
public void setMulticast(boolean multicast) {
this.multicast = multicast;
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGraphiteReporter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGraphiteReporter.java b/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGraphiteReporter.java
index e74bb35..c097718 100644
--- a/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGraphiteReporter.java
+++ b/solr/core/src/java/org/apache/solr/metrics/reporters/SolrGraphiteReporter.java
@@ -36,7 +36,6 @@ public class SolrGraphiteReporter extends SolrMetricReporter {
private String host = null;
private int port = -1;
- private int period = 60;
private boolean pickled = false;
private String instancePrefix = null;
private List<String> filters = new ArrayList<>();
@@ -90,10 +89,6 @@ public class SolrGraphiteReporter extends SolrMetricReporter {
this.pickled = pickled;
}
- public void setPeriod(int period) {
- this.period = period;
- }
-
@Override
protected void doInit() {
if (reporter != null) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/core/src/java/org/apache/solr/metrics/reporters/SolrJmxReporter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/metrics/reporters/SolrJmxReporter.java b/solr/core/src/java/org/apache/solr/metrics/reporters/SolrJmxReporter.java
index 68a94ef..170dd33 100644
--- a/solr/core/src/java/org/apache/solr/metrics/reporters/SolrJmxReporter.java
+++ b/solr/core/src/java/org/apache/solr/metrics/reporters/SolrJmxReporter.java
@@ -70,6 +70,7 @@ public class SolrJmxReporter extends SolrMetricReporter {
*/
public SolrJmxReporter(SolrMetricManager metricManager, String registryName) {
super(metricManager, registryName);
+ period = 0; // setting to zero to indicate not applicable
setDomain(registryName);
}
@@ -151,7 +152,9 @@ public class SolrJmxReporter extends SolrMetricReporter {
*/
@Override
protected void validate() throws IllegalStateException {
- // Nothing to validate
+ if (period != 0) {
+ throw new IllegalStateException("Init argument 'period' is not supported for "+getClass().getCanonicalName());
+ }
}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/core/src/java/org/apache/solr/metrics/reporters/SolrSlf4jReporter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/metrics/reporters/SolrSlf4jReporter.java b/solr/core/src/java/org/apache/solr/metrics/reporters/SolrSlf4jReporter.java
index e301885..e2c6015 100644
--- a/solr/core/src/java/org/apache/solr/metrics/reporters/SolrSlf4jReporter.java
+++ b/solr/core/src/java/org/apache/solr/metrics/reporters/SolrSlf4jReporter.java
@@ -47,7 +47,6 @@ public class SolrSlf4jReporter extends SolrMetricReporter {
@SuppressWarnings("unused") // we need this to pass validate-source-patterns
private static final Logger log = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass());
- private int period = 60;
private String instancePrefix = null;
private String logger = null;
private List<String> filters = new ArrayList<>();
@@ -91,10 +90,6 @@ public class SolrSlf4jReporter extends SolrMetricReporter {
this.logger = logger;
}
- public void setPeriod(int period) {
- this.period = period;
- }
-
@Override
protected void doInit() {
if (instancePrefix == null) {
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrClusterReporter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrClusterReporter.java b/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrClusterReporter.java
index 1e64b8a..d8714d4 100644
--- a/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrClusterReporter.java
+++ b/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrClusterReporter.java
@@ -124,7 +124,6 @@ public class SolrClusterReporter extends SolrMetricReporter {
}};
private String handler = MetricsCollectorHandler.HANDLER_PATH;
- private int period = SolrMetricManager.DEFAULT_CLOUD_REPORTER_PERIOD;
private List<SolrReporter.Report> reports = new ArrayList<>();
private SolrReporter reporter;
@@ -143,10 +142,6 @@ public class SolrClusterReporter extends SolrMetricReporter {
this.handler = handler;
}
- public void setPeriod(int period) {
- this.period = period;
- }
-
public void setReport(List<Map> reportConfig) {
if (reportConfig == null || reportConfig.isEmpty()) {
return;
@@ -169,11 +164,6 @@ public class SolrClusterReporter extends SolrMetricReporter {
}
}
- // for unit tests
- int getPeriod() {
- return period;
- }
-
List<SolrReporter.Report> getReports() {
return reports;
}
@@ -187,7 +177,7 @@ public class SolrClusterReporter extends SolrMetricReporter {
@Override
protected void validate() throws IllegalStateException {
- // Nothing to validate
+ // (period < 1) means "don't start reporter" and so no (period > 0) validation needed
}
@Override
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrShardReporter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrShardReporter.java b/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrShardReporter.java
index b3b055d..e9710b8 100644
--- a/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrShardReporter.java
+++ b/solr/core/src/java/org/apache/solr/metrics/reporters/solr/SolrShardReporter.java
@@ -70,7 +70,6 @@ public class SolrShardReporter extends SolrMetricReporter {
}};
private String handler = MetricsCollectorHandler.HANDLER_PATH;
- private int period = SolrMetricManager.DEFAULT_CLOUD_REPORTER_PERIOD;
private List<String> filters = new ArrayList<>();
private SolrReporter reporter;
@@ -90,10 +89,6 @@ public class SolrShardReporter extends SolrMetricReporter {
this.handler = handler;
}
- public void setPeriod(int period) {
- this.period = period;
- }
-
public void setFilter(List<String> filterConfig) {
if (filterConfig == null || filterConfig.isEmpty()) {
return;
@@ -107,11 +102,6 @@ public class SolrShardReporter extends SolrMetricReporter {
}
}
- // for unit tests
- int getPeriod() {
- return period;
- }
-
@Override
protected void doInit() {
if (filters.isEmpty()) {
@@ -122,7 +112,7 @@ public class SolrShardReporter extends SolrMetricReporter {
@Override
protected void validate() throws IllegalStateException {
- // Nothing to validate
+ // (period < 1) means "don't start reporter" and so no (period > 0) validation needed
}
@Override
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/core/src/test/org/apache/solr/metrics/SolrMetricManagerTest.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/metrics/SolrMetricManagerTest.java b/solr/core/src/test/org/apache/solr/metrics/SolrMetricManagerTest.java
index d306119..5739e53 100644
--- a/solr/core/src/test/org/apache/solr/metrics/SolrMetricManagerTest.java
+++ b/solr/core/src/test/org/apache/solr/metrics/SolrMetricManagerTest.java
@@ -249,6 +249,11 @@ public class SolrMetricManagerTest extends SolrTestCaseJ4 {
}
+ @Test
+ public void testDefaultCloudReporterPeriodUnchanged() throws Exception {
+ assertEquals(60, SolrMetricManager.DEFAULT_CLOUD_REPORTER_PERIOD);
+ }
+
private PluginInfo createPluginInfo(String name, String group, String registry) {
Map<String,String> attrs = new HashMap<>();
attrs.put("name", name);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/44860bd4/solr/core/src/test/org/apache/solr/metrics/reporters/MockMetricReporter.java
----------------------------------------------------------------------
diff --git a/solr/core/src/test/org/apache/solr/metrics/reporters/MockMetricReporter.java b/solr/core/src/test/org/apache/solr/metrics/reporters/MockMetricReporter.java
index e6110ba..f815c7c 100644
--- a/solr/core/src/test/org/apache/solr/metrics/reporters/MockMetricReporter.java
+++ b/solr/core/src/test/org/apache/solr/metrics/reporters/MockMetricReporter.java
@@ -53,6 +53,9 @@ public class MockMetricReporter extends SolrMetricReporter {
if (configurable == null) {
throw new IllegalStateException("MockMetricReporter::configurable not defined.");
}
+ if (period < 1) {
+ throw new IllegalStateException("Init argument 'period' is in time unit 'seconds' and must be at least 1.");
+ }
}
public void setConfigurable(String configurable) {
[18/27] lucene-solr:feature/autoscaling: SOLR-10948: Fix extraction
component to treat DatePointField the same as TrieDateField
Posted by sh...@apache.org.
SOLR-10948: Fix extraction component to treat DatePointField the same as TrieDateField
SOLR-10947: Randomize the usage of Points based numerics in contrib test schemas
This commit also adds @SuppressPointFields needed for SOLR-10949
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/9f56698d
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/9f56698d
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/9f56698d
Branch: refs/heads/feature/autoscaling
Commit: 9f56698d33d1db9fab6a0d6f63b360b334f71583
Parents: 14a0b4f
Author: Chris Hostetter <ho...@apache.org>
Authored: Mon Jun 26 17:03:00 2017 -0700
Committer: Chris Hostetter <ho...@apache.org>
Committed: Mon Jun 26 17:03:00 2017 -0700
----------------------------------------------------------------------
solr/CHANGES.txt | 3 +++
.../solr/collection1/conf/schema-analytics.xml | 10 +++++-----
.../analytics/AbstractAnalyticsStatsTest.java | 1 +
.../org/apache/solr/analytics/NoFacetTest.java | 1 -
.../facet/AbstractAnalyticsFacetTest.java | 1 +
.../clustering/solr/collection1/conf/schema.xml | 18 +++++++++---------
.../conf/dataimport-schema-no-unique-key.xml | 18 +++++++++---------
.../solr/collection1/conf/dataimport-schema.xml | 10 +++++-----
.../conf/dataimport-solr_id-schema.xml | 18 +++++++++---------
.../handler/extraction/SolrContentHandler.java | 4 ++--
.../extraction/solr/collection1/conf/schema.xml | 18 +++++++++---------
.../test-files/solr/collection1/conf/schema.xml | 10 +++++-----
.../uima/solr/collection1/conf/schema.xml | 20 ++++++++++----------
.../test-files/uima/uima-tokenizers-schema.xml | 20 ++++++++++----------
14 files changed, 78 insertions(+), 74 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 8e9bd3d..76722fe 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -207,6 +207,8 @@ Bug Fixes
thus disabling the global check, and replaces it with specific checks where desired via
QueryUtils.build(). (yonik)
+* SOLR-10948: Fix extraction component to treat DatePointField the same as TrieDateField (hossman)
+
Optimizations
----------------------
@@ -334,6 +336,7 @@ Other Changes
* SOLR-10807: Randomize Points based numeric field types in (more) test schemas
- SOLR-10946: Randomize the usage of Points based numerics in solrj test schemas (hossman)
+ - SOLR-10947: Randomize the usage of Points based numerics in contrib test schemas (hossman)
================== 6.7.0 ==================
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/analytics/src/test-files/solr/collection1/conf/schema-analytics.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test-files/solr/collection1/conf/schema-analytics.xml b/solr/contrib/analytics/src/test-files/solr/collection1/conf/schema-analytics.xml
index 2d90359..04b22b1 100644
--- a/solr/contrib/analytics/src/test-files/solr/collection1/conf/schema-analytics.xml
+++ b/solr/contrib/analytics/src/test-files/solr/collection1/conf/schema-analytics.xml
@@ -39,14 +39,14 @@
These are provided more for backward compatability, allowing one
to create a schema that matches an existing lucene index.
-->
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
seconds part (.999) is optional.
-->
- <fieldType name="date" class="solr.TrieDateField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="boolean" class="solr.BoolField"/>
<fieldType name="string" class="solr.StrField"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/analytics/src/test/org/apache/solr/analytics/AbstractAnalyticsStatsTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/AbstractAnalyticsStatsTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/AbstractAnalyticsStatsTest.java
index 881822c..c3d2f28 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/AbstractAnalyticsStatsTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/AbstractAnalyticsStatsTest.java
@@ -48,6 +48,7 @@ import org.xml.sax.SAXException;
import com.google.common.collect.ObjectArrays;
+@SolrTestCaseJ4.SuppressPointFields(bugUrl="https://issues.apache.org/jira/browse/SOLR-10949")
public class AbstractAnalyticsStatsTest extends SolrTestCaseJ4 {
protected static final String[] BASEPARMS = new String[]{ "q", "*:*", "indent", "true", "olap", "true", "rows", "0" };
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java
index ae935fb..f4d6275 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/NoFacetTest.java
@@ -16,7 +16,6 @@
*/
package org.apache.solr.analytics;
-
import java.util.ArrayList;
import java.util.List;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java
----------------------------------------------------------------------
diff --git a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java
index dab68a3..3660208 100644
--- a/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java
+++ b/solr/contrib/analytics/src/test/org/apache/solr/analytics/facet/AbstractAnalyticsFacetTest.java
@@ -52,6 +52,7 @@ import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpressionException;
import javax.xml.xpath.XPathFactory;
+@SolrTestCaseJ4.SuppressPointFields(bugUrl="https://issues.apache.org/jira/browse/SOLR-10949")
public class AbstractAnalyticsFacetTest extends SolrTestCaseJ4 {
protected static final HashMap<String,Object> defaults = new HashMap<>();
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml b/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml
index 66a6223..e14c607 100644
--- a/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml
+++ b/solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml
@@ -72,10 +72,10 @@
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-->
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
<!--
Numeric field types that index each value at various levels of precision
@@ -87,10 +87,10 @@
indexed per value, slightly larger index size, and faster range queries.
A precisionStep of 0 disables indexing at different precision levels.
-->
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
@@ -113,7 +113,7 @@
Consult the TrieDateField javadocs for more information.
-->
- <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" sortMissingLast="true" omitNorms="true"/>
<!-- The "RandomSortField" is not used to store or search any
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml b/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml
index ad01778..793482a 100644
--- a/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml
+++ b/solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml
@@ -73,10 +73,10 @@
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-->
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="latLon" class="solr.LatLonType" subFieldType="double"/>
@@ -90,10 +90,10 @@
indexed per value, slightly larger index size, and faster range queries.
A precisionStep of 0 disables indexing at different precision levels.
-->
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
@@ -116,7 +116,7 @@
Consult the TrieDateField javadocs for more information.
-->
- <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" sortMissingLast="true" omitNorms="true"/>
<!-- The "RandomSortField" is not used to store or search any
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
index 7f34e00..7187138 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml
@@ -2,11 +2,11 @@
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" sortMissingLast="true" omitNorms="true"/>
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.MockTokenizerFactory"/>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
index fabe7e2..e8deee4 100644
--- a/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
+++ b/solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml
@@ -73,10 +73,10 @@
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-->
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
<!--
Numeric field types that index each value at various levels of precision
@@ -88,10 +88,10 @@
indexed per value, slightly larger index size, and faster range queries.
A precisionStep of 0 disables indexing at different precision levels.
-->
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
@@ -114,7 +114,7 @@
Consult the TrieDateField javadocs for more information.
-->
- <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" sortMissingLast="true" omitNorms="true"/>
<!-- The "RandomSortField" is not used to store or search any
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/extraction/src/java/org/apache/solr/handler/extraction/SolrContentHandler.java
----------------------------------------------------------------------
diff --git a/solr/contrib/extraction/src/java/org/apache/solr/handler/extraction/SolrContentHandler.java b/solr/contrib/extraction/src/java/org/apache/solr/handler/extraction/SolrContentHandler.java
index 9268f1c..8c012e5 100644
--- a/solr/contrib/extraction/src/java/org/apache/solr/handler/extraction/SolrContentHandler.java
+++ b/solr/contrib/extraction/src/java/org/apache/solr/handler/extraction/SolrContentHandler.java
@@ -32,7 +32,7 @@ import org.apache.solr.common.SolrInputDocument;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.schema.IndexSchema;
import org.apache.solr.schema.SchemaField;
-import org.apache.solr.schema.TrieDateField;
+import org.apache.solr.schema.NumberType;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.metadata.TikaMetadataKeys;
import org.slf4j.Logger;
@@ -321,7 +321,7 @@ public class SolrContentHandler extends DefaultHandler implements ExtractingPara
*/
protected String transformValue(String val, SchemaField schFld) {
String result = val;
- if (schFld != null && schFld.getType() instanceof TrieDateField) {
+ if (schFld != null && NumberType.DATE.equals(schFld.getType().getNumberType())) {
//try to transform the date
try {
Date date = ExtractionDateUtil.parseDate(val, dateFormats); // may throw
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml b/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
index 2865653..3dbd6aa 100644
--- a/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
+++ b/solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml
@@ -31,10 +31,10 @@
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-->
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
<!--
Numeric field types that index each value at various levels of precision
@@ -46,10 +46,10 @@
indexed per value, slightly larger index size, and faster range queries.
A precisionStep of 0 disables indexing at different precision levels.
-->
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="8" positionIncrementGap="0"/>
<!-- Field type demonstrating an Analyzer failure -->
<fieldType name="failtype1" class="solr.TextField">
@@ -105,7 +105,7 @@
<!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
seconds part (.999) is optional.
-->
- <fieldType name="date" class="solr.TrieDateField" sortMissingLast="true" omitNorms="true"/>
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" sortMissingLast="true" omitNorms="true"/>
<!-- solr.TextField allows the specification of custom
text analyzers specified as a tokenizer and a list
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/ltr/src/test-files/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/ltr/src/test-files/solr/collection1/conf/schema.xml b/solr/contrib/ltr/src/test-files/solr/collection1/conf/schema.xml
index f27f092..4699b0f 100644
--- a/solr/contrib/ltr/src/test-files/solr/collection1/conf/schema.xml
+++ b/solr/contrib/ltr/src/test-files/solr/collection1/conf/schema.xml
@@ -41,11 +41,11 @@
<types>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" />
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}" precisionStep="0" positionIncrementGap="0"/>
<fieldtype name="binary" class="solr.BinaryField"/>
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml
index 35d3131..8020fbd 100644
--- a/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml
+++ b/solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml
@@ -94,13 +94,13 @@
Default numeric field types. For faster range queries, consider
the tint/tfloat/tlong/tdouble types.
-->
- <fieldType name="int" class="solr.TrieIntField"
+ <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="0" omitNorms="true" positionIncrementGap="0" />
- <fieldType name="float" class="solr.TrieFloatField"
+ <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="0" omitNorms="true" positionIncrementGap="0" />
- <fieldType name="long" class="solr.TrieLongField"
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="0" omitNorms="true" positionIncrementGap="0" />
- <fieldType name="double" class="solr.TrieDoubleField"
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="0" omitNorms="true" positionIncrementGap="0" />
<!--
@@ -113,13 +113,13 @@
queries. A precisionStep of 0 disables indexing at different
precision levels.
-->
- <fieldType name="tint" class="solr.TrieIntField"
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="8" omitNorms="true" positionIncrementGap="0" />
- <fieldType name="tfloat" class="solr.TrieFloatField"
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="8" omitNorms="true" positionIncrementGap="0" />
- <fieldType name="tlong" class="solr.TrieLongField"
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="8" omitNorms="true" positionIncrementGap="0" />
- <fieldType name="tdouble" class="solr.TrieDoubleField"
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="8" omitNorms="true" positionIncrementGap="0" />
<!--
@@ -137,14 +137,14 @@
the TrieDateField javadocs for more information. Note: For faster
range queries, consider the tdate type
-->
- <fieldType name="date" class="solr.TrieDateField"
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}"
omitNorms="true" precisionStep="0" positionIncrementGap="0" />
<!--
A Trie based date field for faster date range queries and date
faceting.
-->
- <fieldType name="tdate" class="solr.TrieDateField"
+ <fieldType name="tdate" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}"
omitNorms="true" precisionStep="6" positionIncrementGap="0" />
<!--
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/9f56698d/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
----------------------------------------------------------------------
diff --git a/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml b/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
index bf4c72d..d5d3987 100644
--- a/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
+++ b/solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml
@@ -94,13 +94,13 @@
Default numeric field types. For faster range queries, consider
the tint/tfloat/tlong/tdouble types.
-->
- <fieldType name="int" class="solr.TrieIntField"
+ <fieldType name="int" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField"
+ <fieldType name="float" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField"
+ <fieldType name="long" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField"
+ <fieldType name="double" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<!--
@@ -113,13 +113,13 @@
queries. A precisionStep of 0 disables indexing at different
precision levels.
-->
- <fieldType name="tint" class="solr.TrieIntField"
+ <fieldType name="tint" class="${solr.tests.IntegerFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField"
+ <fieldType name="tfloat" class="${solr.tests.FloatFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField"
+ <fieldType name="tlong" class="${solr.tests.LongFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField"
+ <fieldType name="tdouble" class="${solr.tests.DoubleFieldType}" docValues="${solr.tests.numeric.dv}"
precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<!--
@@ -137,14 +137,14 @@
the TrieDateField javadocs for more information. Note: For faster
range queries, consider the tdate type
-->
- <fieldType name="date" class="solr.TrieDateField"
+ <fieldType name="date" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}"
omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
<!--
A Trie based date field for faster date range queries and date
faceting.
-->
- <fieldType name="tdate" class="solr.TrieDateField"
+ <fieldType name="tdate" class="${solr.tests.DateFieldType}" docValues="${solr.tests.numeric.dv}"
omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
<!--
[07/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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..e524dbf
--- /dev/null
+++ b/solr/server/solr/configsets/_default/conf/solrconfig.xml
@@ -0,0 +1,1394 @@
+<?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>
+
+ <!-- Maximum number of clauses in each BooleanQuery, an exception
+ is thrown if exceeded. It is safe to increase or remove this setting,
+ since it is purely an arbitrary limit to try and catch user errors where
+ large boolean queries may not be the best implementation choice.
+ -->
+ <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>
+
+ <!-- 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">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>
+ </updateProcessor>
+
+ <!-- The update.autoCreateFields property can be turned to false to disable schemaless mode -->
+ <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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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
[09/27] lucene-solr:feature/autoscaling: SOLR-10574: Adding _default
configset, replacing data_driven_schema_configs and basic_configs
Posted by sh...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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/e4a7fc59/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
[27/27] 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
# solr/core/src/java/org/apache/solr/cloud/ZkController.java
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/e863d0f5
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/e863d0f5
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/e863d0f5
Branch: refs/heads/feature/autoscaling
Commit: e863d0f548ea3fe76e5fdc369ef990ed37377dbb
Parents: 4c47a32 5d44243
Author: Shalin Shekhar Mangar <sh...@apache.org>
Authored: Tue Jun 27 10:48:05 2017 +0530
Committer: Shalin Shekhar Mangar <sh...@apache.org>
Committed: Tue Jun 27 10:48:05 2017 +0530
----------------------------------------------------------------------
solr/CHANGES.txt | 24 +-
solr/bin/solr | 36 +-
solr/bin/solr.cmd | 24 +-
.../accumulator/FacetingAccumulator.java | 24 +-
.../solr/analytics/expression/Expression.java | 15 +-
.../statistics/MinMaxStatsCollector.java | 23 +-
.../statistics/NumericStatsCollector.java | 8 +-
.../StatsCollectorSupplierFactory.java | 14 +-
.../analytics/requestFiles/facetSorting.txt | 4 -
.../analytics/requestXMLFiles/facetSorting.xml | 14 -
.../solr/collection1/conf/schema-analytics.xml | 10 +-
.../collection1/conf/solrconfig-analytics.xml | 40 -
.../solr/collection1/conf/solrconfig-basic.xml | 40 +
.../analytics/AbstractAnalyticsStatsTest.java | 1 +
.../org/apache/solr/analytics/NoFacetTest.java | 3 +-
.../analytics/expression/ExpressionTest.java | 2 +-
.../facet/AbstractAnalyticsFacetTest.java | 16 +-
.../solr/analytics/facet/FacetSortingTest.java | 56 -
.../analytics/facet/FieldFacetExtrasTest.java | 2 +-
.../solr/analytics/facet/FieldFacetTest.java | 21 +-
.../solr/analytics/facet/QueryFacetTest.java | 2 +-
.../solr/analytics/facet/RangeFacetTest.java | 2 +-
.../util/valuesource/FunctionTest.java | 2 +-
.../clustering/solr/collection1/conf/schema.xml | 18 +-
.../conf/dataimport-schema-no-unique-key.xml | 18 +-
.../solr/collection1/conf/dataimport-schema.xml | 10 +-
.../conf/dataimport-solr_id-schema.xml | 18 +-
.../handler/extraction/SolrContentHandler.java | 4 +-
.../extraction/solr/collection1/conf/schema.xml | 18 +-
.../test-files/solr/collection1/conf/schema.xml | 10 +-
.../uima/solr/collection1/conf/schema.xml | 20 +-
.../test-files/uima/uima-tokenizers-schema.xml | 20 +-
.../apache/solr/cloud/CreateCollectionCmd.java | 65 +-
.../org/apache/solr/cloud/ZkController.java | 67 +-
.../handler/admin/ConfigSetsHandlerApi.java | 2 +
.../solr/handler/component/ExpandComponent.java | 2 +
.../apache/solr/metrics/SolrMetricReporter.java | 15 +
.../metrics/reporters/SolrGangliaReporter.java | 5 -
.../metrics/reporters/SolrGraphiteReporter.java | 5 -
.../solr/metrics/reporters/SolrJmxReporter.java | 5 +-
.../metrics/reporters/SolrSlf4jReporter.java | 5 -
.../reporters/solr/SolrClusterReporter.java | 12 +-
.../reporters/solr/SolrShardReporter.java | 12 +-
.../apache/solr/servlet/SolrDispatchFilter.java | 6 +-
.../src/java/org/apache/solr/util/SolrCLI.java | 32 +-
.../solr/configsets/_default/conf/schema.xml | 37 +
.../configsets/_default/conf/solrconfig.xml | 32 +
.../solr/cloud/BaseCdcrDistributedZkTest.java | 4 +-
.../solr/cloud/BasicDistributedZk2Test.java | 2 +-
.../solr/cloud/BasicDistributedZkTest.java | 12 +-
.../solr/cloud/ClusterStateUpdateTest.java | 2 +-
.../solr/cloud/CollectionsAPISolrJTest.java | 19 +
.../org/apache/solr/cloud/ForceLeaderTest.java | 4 +-
.../apache/solr/cloud/HttpPartitionTest.java | 10 +-
.../cloud/LeaderFailoverAfterPartitionTest.java | 2 +-
.../LeaderInitiatedRecoveryOnCommitTest.java | 4 +-
...aderInitiatedRecoveryOnShardRestartTest.java | 2 +-
.../solr/cloud/ReplicationFactorTest.java | 6 +-
.../solr/cloud/ShardRoutingCustomTest.java | 2 +-
.../org/apache/solr/cloud/ShardSplitTest.java | 2 +-
.../apache/solr/cloud/SolrCloudExampleTest.java | 11 +-
.../apache/solr/cloud/TestConfigSetsAPI.java | 6 +-
.../cloud/TestOnReconnectListenerSupport.java | 2 +-
.../org/apache/solr/cloud/TestPullReplica.java | 8 +-
.../cloud/TestRandomRequestDistribution.java | 6 +-
.../cloud/TestSolrCloudWithKerberosAlt.java | 2 +-
.../org/apache/solr/cloud/TestTlogReplica.java | 8 +-
.../solr/cloud/UnloadDistributedZkTest.java | 4 +-
.../autoscaling/AutoScalingHandlerTest.java | 17 +-
.../solr/cloud/autoscaling/TestPolicyCloud.java | 6 +-
.../solr/cloud/hdfs/HdfsNNFailoverTest.java | 2 +-
.../HdfsWriteToMultipleCollectionsTest.java | 2 +-
.../apache/solr/cloud/hdfs/StressHdfsTest.java | 4 +-
.../handler/ThrowErrorOnInitRequestHandler.java | 4 +
.../TestTrackingShardHandlerFactory.java | 2 +-
.../solr/metrics/SolrMetricManagerTest.java | 5 +
.../metrics/reporters/MockMetricReporter.java | 3 +
.../search/stats/TestDefaultStatsCache.java | 2 +-
.../apache/solr/util/TestSolrCLIRunExample.java | 2 +-
solr/server/README.txt | 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 | 1076 ++++++++++++++
.../solr/configsets/_default/conf/params.json | 20 +
.../solr/configsets/_default/conf/protwords.txt | 21 +
.../configsets/_default/conf/solrconfig.xml | 1394 +++++++++++++++++
.../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 | 1052 -------------
.../configsets/basic_configs/conf/params.json | 20 -
.../configsets/basic_configs/conf/protwords.txt | 21 -
.../basic_configs/conf/solrconfig.xml | 1401 ------------------
.../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 | 1076 --------------
.../data_driven_schema_configs/conf/params.json | 20 -
.../conf/protwords.txt | 21 -
.../conf/solrconfig.xml | 1398 -----------------
.../conf/stopwords.txt | 14 -
.../conf/synonyms.txt | 29 -
solr/solr-ref-guide/src/collections-api.adoc | 1044 +++++++------
solr/solr-ref-guide/src/coreadmin-api.adoc | 276 ++--
solr/solr-ref-guide/src/format-of-solr-xml.adoc | 174 ++-
solr/solr-ref-guide/src/function-queries.adoc | 410 +++--
solr/solr-ref-guide/src/highlighting.adoc | 299 ++--
solr/solr-ref-guide/src/other-parsers.adoc | 169 ++-
solr/solr-ref-guide/src/query-re-ranking.adoc | 15 +-
.../src/rule-based-authorization-plugin.adoc | 23 +-
solr/solr-ref-guide/src/schema-api.adoc | 361 ++---
.../src/solr-control-script-reference.adoc | 520 ++++---
.../solr/cloud/autoscaling/package-info.java | 3 +-
.../solr/common/cloud/ZkConfigManager.java | 2 +-
.../collection1/conf/schema-replication1.xml | 2 +-
.../solrj/solr/collection1/conf/schema-sql.xml | 20 +-
.../solrj/solr/collection1/conf/schema.xml | 20 +-
.../solrj/solr/configsets/ml/conf/schema.xml | 20 +-
.../solr/configsets/shared/conf/schema.xml | 2 +-
.../solr/configsets/streaming/conf/schema.xml | 20 +-
.../solrj/solr/multicore/core0/conf/schema.xml | 2 +-
.../solrj/solr/multicore/core1/conf/schema.xml | 2 +-
.../client/solrj/SolrSchemalessExampleTest.java | 2 +-
.../client/solrj/io/stream/JDBCStreamTest.java | 2 +
.../solr/client/solrj/request/SchemaTest.java | 23 +-
.../cloud/AbstractFullDistribZkTestBase.java | 22 +-
.../org/apache/solr/util/ExternalPaths.java | 4 +-
243 files changed, 11060 insertions(+), 19466 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e863d0f5/solr/CHANGES.txt
----------------------------------------------------------------------
diff --cc solr/CHANGES.txt
index a700f71,8d5c321..d614519
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@@ -175,9 -170,11 +180,14 @@@ New Feature
* 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)
++ (Ishan Chattopadhyaya, noble, shalin, hossman, David Smiley, Jan Hoydahl, Alexandre Rafalovich)
+
+ * SOLR-10272: Use _default config set if no collection.configName is specified with CREATE (Ishan Chattopadhyaya)
+
+* SOLR-10496: New ComputePlanAction for autoscaling which uses the policy framework to compute cluster
+ operations upon a trigger fire. (Noble Paul, shalin)
+
Bug Fixes
----------------------
* SOLR-9262: Connection and read timeouts are being ignored by UpdateShardHandler after SOLR-4509.
@@@ -212,13 -209,8 +222,15 @@@
thus disabling the global check, and replaces it with specific checks where desired via
QueryUtils.build(). (yonik)
+ * SOLR-10948: Fix extraction component to treat DatePointField the same as TrieDateField (hossman)
+
+* 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
----------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e863d0f5/solr/core/src/java/org/apache/solr/cloud/CreateCollectionCmd.java
----------------------------------------------------------------------
diff --cc solr/core/src/java/org/apache/solr/cloud/CreateCollectionCmd.java
index 3d89fd2,0c87658..ee5cc47
--- a/solr/core/src/java/org/apache/solr/cloud/CreateCollectionCmd.java
+++ b/solr/core/src/java/org/apache/solr/cloud/CreateCollectionCmd.java
@@@ -51,10 -48,9 +52,11 @@@ import org.apache.solr.common.util.Cont
import org.apache.solr.common.util.NamedList;
import org.apache.solr.common.util.SimpleOrderedMap;
import org.apache.solr.common.util.Utils;
+ import org.apache.solr.handler.admin.ConfigSetsHandlerApi;
import org.apache.solr.handler.component.ShardHandler;
import org.apache.solr.handler.component.ShardRequest;
+import org.apache.solr.request.LocalSolrQueryRequest;
+import org.apache.solr.response.SolrQueryResponse;
import org.apache.solr.util.TimeOut;
import org.apache.zookeeper.CreateMode;
import org.apache.zookeeper.KeeperException;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e863d0f5/solr/core/src/java/org/apache/solr/cloud/ZkController.java
----------------------------------------------------------------------
diff --cc solr/core/src/java/org/apache/solr/cloud/ZkController.java
index c3878e1,391f29c..9c552be
--- a/solr/core/src/java/org/apache/solr/cloud/ZkController.java
+++ b/solr/core/src/java/org/apache/solr/cloud/ZkController.java
@@@ -55,8 -57,27 +59,19 @@@ import org.apache.solr.cloud.overseer.O
import org.apache.solr.cloud.overseer.SliceMutator;
import org.apache.solr.common.SolrException;
import org.apache.solr.common.SolrException.ErrorCode;
-import org.apache.solr.common.cloud.BeforeReconnect;
-import org.apache.solr.common.cloud.ClusterState;
-import org.apache.solr.common.cloud.ClusterStateUtil;
-import org.apache.solr.common.cloud.DefaultConnectionStrategy;
-import org.apache.solr.common.cloud.DefaultZkACLProvider;
-import org.apache.solr.common.cloud.DefaultZkCredentialsProvider;
-import org.apache.solr.common.cloud.DocCollection;
-import org.apache.solr.common.cloud.OnReconnect;
-import org.apache.solr.common.cloud.Replica;
+import org.apache.solr.common.cloud.*;
import org.apache.solr.common.cloud.Replica.Type;
+ import org.apache.solr.common.cloud.Slice;
+ import org.apache.solr.common.cloud.SolrZkClient;
+ import org.apache.solr.common.cloud.ZkACLProvider;
+ import org.apache.solr.common.cloud.ZkCmdExecutor;
+ import org.apache.solr.common.cloud.ZkConfigManager;
+ import org.apache.solr.common.cloud.ZkCoreNodeProps;
+ import org.apache.solr.common.cloud.ZkCredentialsProvider;
+ import org.apache.solr.common.cloud.ZkMaintenanceUtils;
+ import org.apache.solr.common.cloud.ZkNodeProps;
+ import org.apache.solr.common.cloud.ZkStateReader;
+ import org.apache.solr.common.cloud.ZooKeeperException;
import org.apache.solr.common.params.CollectionParams;
import org.apache.solr.common.params.CommonParams;
import org.apache.solr.common.params.SolrParams;
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e863d0f5/solr/core/src/test/org/apache/solr/cloud/ShardSplitTest.java
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e863d0f5/solr/core/src/test/org/apache/solr/cloud/autoscaling/AutoScalingHandlerTest.java
----------------------------------------------------------------------