You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by ar...@apache.org on 2017/04/01 17:54:20 UTC
[1/6] [lucene-solr] Git Push Summary
Repository: lucene-solr
Updated Branches:
refs/heads/master 35aac1d46 -> 580f6e98f
[2/6] lucene-solr:master: SOLR-7383: Replace DIH 'rss' example with
'atom' rss example was broken for multiple reasons. atom example showcases
the same - and more - features and uses the smallest config file needed to
make it work.
Posted by ar...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/solrconfig.xml b/solr/example/example-DIH/solr/rss/conf/solrconfig.xml
deleted file mode 100644
index eae60a7..0000000
--- a/solr/example/example-DIH/solr/rss/conf/solrconfig.xml
+++ /dev/null
@@ -1,1396 +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="${solr.install.dir:../../../..}/dist/" regex="solr-dataimporthandler-.*\.jar" />
-
- <lib dir="${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/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, not
- persistent, and doesn't work with replication.
- -->
- <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.
- -->
- <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.
- The default is 100 MB. -->
- <!-- <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="solr.TieredMergePolicyFactory">
- <int name="maxMergeAtOnce">10</int>
- <int name="segmentsPerTier">10</int>
- </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 info stream to solr's log. By default,
- this is enabled here, and controlled through log4j.properties.
- -->
- <infoStream>true</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. -->
- <updateLog>
- <str name="dir">${solr.ulog.dir:}</str>
- </updateLog>
-
- <!-- AutoCommit
-
- Perform a hard commit automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time in ms that is allowed to pass
- since a document was added before automatically
- triggering a new commit.
- openSearcher - if false, the commit causes recent index changes
- to be flushed to stable storage, but does not cause a new
- searcher to be opened to make those changes visible.
-
- If the updateLog is enabled, then it's highly recommended to
- have some sort of hard autoCommit to limit the log size.
- -->
- <autoCommit>
- <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
-
- <!-- softAutoCommit is like autoCommit except it causes a
- 'soft' commit which only ensures that changes are visible
- but does not ensure that data is synced to disk. This is
- faster and more near-realtime friendly than a hard commit.
- -->
-
- <autoSoftCommit>
- <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
- </autoSoftCommit>
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- The RunExecutableListener executes an external command from a
- hook such as postCommit or postOptimize.
-
- exe - the name of the executable to run
- dir - dir to use as the current working directory. (default=".")
- wait - the calling thread waits until the executable returns.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
-
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Query section - these settings control query time things like caches
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded.
-
- ** WARNING **
-
- This option actually modifies a global Lucene property that
- will affect all SolrCores. If multiple solrconfig.xml files
- disagree on this property, the value at any given moment will
- be based on the last SolrCore to be initialized.
-
- -->
- <maxBooleanClauses>1024</maxBooleanClauses>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (see java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- -->
- <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.
- -->
- <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 ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
-
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
- 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.
-
- -->
-
- <requestHandler name="/dataimport" class="solr.DataImportHandler">
- <lst name="defaults">
- <str name="config">rss-data-config.xml</str>
- </lst>
- </requestHandler>
-
- <!-- 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>
- <str name="df">text</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">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
-
- <!-- VelocityResponseWriter settings -->
- <str name="wt">velocity</str>
- <str name="v.template">browse</str>
- <str name="v.layout">layout</str>
-
- <!-- Query settings -->
- <str name="defType">edismax</str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
-
- <!-- Faceting defaults -->
- <str name="facet">on</str>
- <str name="facet.mincount">1</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="uprefix">ignored_</str>
-
- <!-- capture link hrefs but ignore div attributes -->
- <str name="captureAttr">true</str>
- <str name="fmap.a">links</str>
- <str name="fmap.div">ignored_</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>
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="comparatorClass">freq</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <lst name="spellchecker">
- <str name="classname">solr.FileBasedSpellChecker</str>
- <str name="name">file</str>
- <str name="sourceLocation">spellings.txt</str>
- <str name="characterEncoding">UTF-8</str>
- <str name="spellcheckIndexDir">spellcheckerFile</str>
- </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">
- <str name="df">text</str>
- <!-- 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.dictionary">wordbreak</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>
-
- <searchComponent name="suggest" class="solr.SuggestComponent">
- <lst name="suggester">
- <str name="name">mySuggester</str>
- <str name="lookupImpl">FuzzyLookupFactory</str> <!-- org.apache.solr.spelling.suggest.fst -->
- <str name="dictionaryImpl">DocumentDictionaryFactory</str> <!-- org.apache.solr.spelling.suggest.HighFrequencyDictionaryFactory -->
- <str name="field">cat</str>
- <str name="weightField">price</str>
- <str name="suggestAnalyzerFieldType">string</str>
- </lst>
- </searchComponent>
-
- <requestHandler name="/suggest" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="suggest">true</str>
- <str name="suggest.count">10</str>
- </lst>
- <arr name="components">
- <str>suggest</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">
- <str name="df">text</str>
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- 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>
- <str name="df">text</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
-
- -->
- <!-- 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>
- </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/580f6e98/solr/example/example-DIH/solr/rss/conf/spellings.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/spellings.txt b/solr/example/example-DIH/solr/rss/conf/spellings.txt
deleted file mode 100644
index d7ede6f..0000000
--- a/solr/example/example-DIH/solr/rss/conf/spellings.txt
+++ /dev/null
@@ -1,2 +0,0 @@
-pizza
-history
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/stopwords.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/stopwords.txt b/solr/example/example-DIH/solr/rss/conf/stopwords.txt
deleted file mode 100644
index ae1e83e..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/synonyms.txt b/solr/example/example-DIH/solr/rss/conf/synonyms.txt
deleted file mode 100644
index eab4ee8..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/update-script.js
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/update-script.js b/solr/example/example-DIH/solr/rss/conf/update-script.js
deleted file mode 100644
index 49b07f9..0000000
--- a/solr/example/example-DIH/solr/rss/conf/update-script.js
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- This is a basic skeleton JavaScript update processor.
-
- In order for this to be executed, it must be properly wired into solrconfig.xml; by default it is commented out in
- the example solrconfig.xml and must be uncommented to be enabled.
-
- See http://wiki.apache.org/solr/ScriptUpdateProcessor for more details.
-*/
-
-function processAdd(cmd) {
-
- doc = cmd.solrDoc; // org.apache.solr.common.SolrInputDocument
- id = doc.getFieldValue("id");
- logger.info("update-script#processAdd: id=" + id);
-
-// Set a field value:
-// doc.setField("foo_s", "whatever");
-
-// Get a configuration parameter:
-// config_param = params.get('config_param'); // "params" only exists if processor configured with <lst name="params">
-
-// Get a request parameter:
-// some_param = req.getParams().get("some_param")
-
-// Add a field of field names that match a pattern:
-// - Potentially useful to determine the fields/attributes represented in a result set, via faceting on field_name_ss
-// field_names = doc.getFieldNames().toArray();
-// for(i=0; i < field_names.length; i++) {
-// field_name = field_names[i];
-// if (/attr_.*/.test(field_name)) { doc.addField("attribute_ss", field_names[i]); }
-// }
-
-}
-
-function processDelete(cmd) {
- // no-op
-}
-
-function processMergeIndexes(cmd) {
- // no-op
-}
-
-function processCommit(cmd) {
- // no-op
-}
-
-function processRollback(cmd) {
- // no-op
-}
-
-function finish() {
- // no-op
-}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/xslt/example.xsl
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/xslt/example.xsl b/solr/example/example-DIH/solr/rss/conf/xslt/example.xsl
deleted file mode 100644
index b899270..0000000
--- a/solr/example/example-DIH/solr/rss/conf/xslt/example.xsl
+++ /dev/null
@@ -1,132 +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.
- -->
-
-<!--
- Simple transform of Solr query results to HTML
- -->
-<xsl:stylesheet version='1.0'
- xmlns:xsl='http://www.w3.org/1999/XSL/Transform'
->
-
- <xsl:output media-type="text/html" encoding="UTF-8"/>
-
- <xsl:variable name="title" select="concat('Solr search results (',response/result/@numFound,' documents)')"/>
-
- <xsl:template match='/'>
- <html>
- <head>
- <title><xsl:value-of select="$title"/></title>
- <xsl:call-template name="css"/>
- </head>
- <body>
- <h1><xsl:value-of select="$title"/></h1>
- <div class="note">
- This has been formatted by the sample "example.xsl" transform -
- use your own XSLT to get a nicer page
- </div>
- <xsl:apply-templates select="response/result/doc"/>
- </body>
- </html>
- </xsl:template>
-
- <xsl:template match="doc">
- <xsl:variable name="pos" select="position()"/>
- <div class="doc">
- <table width="100%">
- <xsl:apply-templates>
- <xsl:with-param name="pos"><xsl:value-of select="$pos"/></xsl:with-param>
- </xsl:apply-templates>
- </table>
- </div>
- </xsl:template>
-
- <xsl:template match="doc/*[@name='score']" priority="100">
- <xsl:param name="pos"></xsl:param>
- <tr>
- <td class="name">
- <xsl:value-of select="@name"/>
- </td>
- <td class="value">
- <xsl:value-of select="."/>
-
- <xsl:if test="boolean(//lst[@name='explain'])">
- <xsl:element name="a">
- <!-- can't allow whitespace here -->
- <xsl:attribute name="href">javascript:toggle("<xsl:value-of select="concat('exp-',$pos)" />");</xsl:attribute>?</xsl:element>
- <br/>
- <xsl:element name="div">
- <xsl:attribute name="class">exp</xsl:attribute>
- <xsl:attribute name="id">
- <xsl:value-of select="concat('exp-',$pos)" />
- </xsl:attribute>
- <xsl:value-of select="//lst[@name='explain']/str[position()=$pos]"/>
- </xsl:element>
- </xsl:if>
- </td>
- </tr>
- </xsl:template>
-
- <xsl:template match="doc/arr" priority="100">
- <tr>
- <td class="name">
- <xsl:value-of select="@name"/>
- </td>
- <td class="value">
- <ul>
- <xsl:for-each select="*">
- <li><xsl:value-of select="."/></li>
- </xsl:for-each>
- </ul>
- </td>
- </tr>
- </xsl:template>
-
-
- <xsl:template match="doc/*">
- <tr>
- <td class="name">
- <xsl:value-of select="@name"/>
- </td>
- <td class="value">
- <xsl:value-of select="."/>
- </td>
- </tr>
- </xsl:template>
-
- <xsl:template match="*"/>
-
- <xsl:template name="css">
- <script>
- function toggle(id) {
- var obj = document.getElementById(id);
- obj.style.display = (obj.style.display != 'block') ? 'block' : 'none';
- }
- </script>
- <style type="text/css">
- body { font-family: "Lucida Grande", sans-serif }
- td.name { font-style: italic; font-size:80%; }
- td { vertical-align: top; }
- ul { margin: 0px; margin-left: 1em; padding: 0px; }
- .note { font-size:80%; }
- .doc { margin-top: 1em; border-top: solid grey 1px; }
- .exp { display: none; font-family: monospace; white-space: pre; }
- </style>
- </xsl:template>
-
-</xsl:stylesheet>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/xslt/example_atom.xsl
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/xslt/example_atom.xsl b/solr/example/example-DIH/solr/rss/conf/xslt/example_atom.xsl
deleted file mode 100644
index b6c2315..0000000
--- a/solr/example/example-DIH/solr/rss/conf/xslt/example_atom.xsl
+++ /dev/null
@@ -1,67 +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.
- -->
-
-<!--
- Simple transform of Solr query results to Atom
- -->
-
-<xsl:stylesheet version='1.0'
- xmlns:xsl='http://www.w3.org/1999/XSL/Transform'>
-
- <xsl:output
- method="xml"
- encoding="utf-8"
- media-type="application/xml"
- />
-
- <xsl:template match='/'>
- <xsl:variable name="query" select="response/lst[@name='responseHeader']/lst[@name='params']/str[@name='q']"/>
- <feed xmlns="http://www.w3.org/2005/Atom">
- <title>Example Solr Atom 1.0 Feed</title>
- <subtitle>
- This has been formatted by the sample "example_atom.xsl" transform -
- use your own XSLT to get a nicer Atom feed.
- </subtitle>
- <author>
- <name>Apache Solr</name>
- <email>solr-user@lucene.apache.org</email>
- </author>
- <link rel="self" type="application/atom+xml"
- href="http://localhost:8983/solr/q={$query}&wt=xslt&tr=atom.xsl"/>
- <updated>
- <xsl:value-of select="response/result/doc[position()=1]/date[@name='timestamp']"/>
- </updated>
- <id>tag:localhost,2007:example</id>
- <xsl:apply-templates select="response/result/doc"/>
- </feed>
- </xsl:template>
-
- <!-- search results xslt -->
- <xsl:template match="doc">
- <xsl:variable name="id" select="str[@name='id']"/>
- <entry>
- <title><xsl:value-of select="str[@name='name']"/></title>
- <link href="http://localhost:8983/solr/select?q={$id}"/>
- <id>tag:localhost,2007:<xsl:value-of select="$id"/></id>
- <summary><xsl:value-of select="arr[@name='features']"/></summary>
- <updated><xsl:value-of select="date[@name='timestamp']"/></updated>
- </entry>
- </xsl:template>
-
-</xsl:stylesheet>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/xslt/example_rss.xsl
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/xslt/example_rss.xsl b/solr/example/example-DIH/solr/rss/conf/xslt/example_rss.xsl
deleted file mode 100644
index c8ab5bf..0000000
--- a/solr/example/example-DIH/solr/rss/conf/xslt/example_rss.xsl
+++ /dev/null
@@ -1,66 +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.
- -->
-
-<!--
- Simple transform of Solr query results to RSS
- -->
-
-<xsl:stylesheet version='1.0'
- xmlns:xsl='http://www.w3.org/1999/XSL/Transform'>
-
- <xsl:output
- method="xml"
- encoding="utf-8"
- media-type="application/xml"
- />
- <xsl:template match='/'>
- <rss version="2.0">
- <channel>
- <title>Example Solr RSS 2.0 Feed</title>
- <link>http://localhost:8983/solr</link>
- <description>
- This has been formatted by the sample "example_rss.xsl" transform -
- use your own XSLT to get a nicer RSS feed.
- </description>
- <language>en-us</language>
- <docs>http://localhost:8983/solr</docs>
- <xsl:apply-templates select="response/result/doc"/>
- </channel>
- </rss>
- </xsl:template>
-
- <!-- search results xslt -->
- <xsl:template match="doc">
- <xsl:variable name="id" select="str[@name='id']"/>
- <xsl:variable name="timestamp" select="date[@name='timestamp']"/>
- <item>
- <title><xsl:value-of select="str[@name='name']"/></title>
- <link>
- http://localhost:8983/solr/select?q=id:<xsl:value-of select="$id"/>
- </link>
- <description>
- <xsl:value-of select="arr[@name='features']"/>
- </description>
- <pubDate><xsl:value-of select="$timestamp"/></pubDate>
- <guid>
- http://localhost:8983/solr/select?q=id:<xsl:value-of select="$id"/>
- </guid>
- </item>
- </xsl:template>
-</xsl:stylesheet>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/xslt/luke.xsl
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/xslt/luke.xsl b/solr/example/example-DIH/solr/rss/conf/xslt/luke.xsl
deleted file mode 100644
index 05fb5bf..0000000
--- a/solr/example/example-DIH/solr/rss/conf/xslt/luke.xsl
+++ /dev/null
@@ -1,337 +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.
--->
-
-
-<!--
- Display the luke request handler with graphs
- -->
-<xsl:stylesheet
- xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
- xmlns="http://www.w3.org/1999/xhtml"
- version="1.0"
- >
- <xsl:output
- method="html"
- encoding="UTF-8"
- media-type="text/html"
- doctype-public="-//W3C//DTD XHTML 1.0 Strict//EN"
- doctype-system="http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"
- />
-
- <xsl:variable name="title">Solr Luke Request Handler Response</xsl:variable>
-
- <xsl:template match="/">
- <html xmlns="http://www.w3.org/1999/xhtml">
- <head>
- <link rel="stylesheet" type="text/css" href="solr-admin.css"/>
- <link rel="icon" href="favicon.ico" type="image/x-icon"/>
- <link rel="shortcut icon" href="favicon.ico" type="image/x-icon"/>
- <title>
- <xsl:value-of select="$title"/>
- </title>
- <xsl:call-template name="css"/>
-
- </head>
- <body>
- <h1>
- <xsl:value-of select="$title"/>
- </h1>
- <div class="doc">
- <ul>
- <xsl:if test="response/lst[@name='index']">
- <li>
- <a href="#index">Index Statistics</a>
- </li>
- </xsl:if>
- <xsl:if test="response/lst[@name='fields']">
- <li>
- <a href="#fields">Field Statistics</a>
- <ul>
- <xsl:for-each select="response/lst[@name='fields']/lst">
- <li>
- <a href="#{@name}">
- <xsl:value-of select="@name"/>
- </a>
- </li>
- </xsl:for-each>
- </ul>
- </li>
- </xsl:if>
- <xsl:if test="response/lst[@name='doc']">
- <li>
- <a href="#doc">Document statistics</a>
- </li>
- </xsl:if>
- </ul>
- </div>
- <xsl:if test="response/lst[@name='index']">
- <h2><a name="index"/>Index Statistics</h2>
- <xsl:apply-templates select="response/lst[@name='index']"/>
- </xsl:if>
- <xsl:if test="response/lst[@name='fields']">
- <h2><a name="fields"/>Field Statistics</h2>
- <xsl:apply-templates select="response/lst[@name='fields']"/>
- </xsl:if>
- <xsl:if test="response/lst[@name='doc']">
- <h2><a name="doc"/>Document statistics</h2>
- <xsl:apply-templates select="response/lst[@name='doc']"/>
- </xsl:if>
- </body>
- </html>
- </xsl:template>
-
- <xsl:template match="lst">
- <xsl:if test="parent::lst">
- <tr>
- <td colspan="2">
- <div class="doc">
- <xsl:call-template name="list"/>
- </div>
- </td>
- </tr>
- </xsl:if>
- <xsl:if test="not(parent::lst)">
- <div class="doc">
- <xsl:call-template name="list"/>
- </div>
- </xsl:if>
- </xsl:template>
-
- <xsl:template name="list">
- <xsl:if test="count(child::*)>0">
- <table>
- <thead>
- <tr>
- <th colspan="2">
- <p>
- <a name="{@name}"/>
- </p>
- <xsl:value-of select="@name"/>
- </th>
- </tr>
- </thead>
- <tbody>
- <xsl:choose>
- <xsl:when
- test="@name='histogram'">
- <tr>
- <td colspan="2">
- <xsl:call-template name="histogram"/>
- </td>
- </tr>
- </xsl:when>
- <xsl:otherwise>
- <xsl:apply-templates/>
- </xsl:otherwise>
- </xsl:choose>
- </tbody>
- </table>
- </xsl:if>
- </xsl:template>
-
- <xsl:template name="histogram">
- <div class="doc">
- <xsl:call-template name="barchart">
- <xsl:with-param name="max_bar_width">50</xsl:with-param>
- <xsl:with-param name="iwidth">800</xsl:with-param>
- <xsl:with-param name="iheight">160</xsl:with-param>
- <xsl:with-param name="fill">blue</xsl:with-param>
- </xsl:call-template>
- </div>
- </xsl:template>
-
- <xsl:template name="barchart">
- <xsl:param name="max_bar_width"/>
- <xsl:param name="iwidth"/>
- <xsl:param name="iheight"/>
- <xsl:param name="fill"/>
- <xsl:variable name="max">
- <xsl:for-each select="int">
- <xsl:sort data-type="number" order="descending"/>
- <xsl:if test="position()=1">
- <xsl:value-of select="."/>
- </xsl:if>
- </xsl:for-each>
- </xsl:variable>
- <xsl:variable name="bars">
- <xsl:value-of select="count(int)"/>
- </xsl:variable>
- <xsl:variable name="bar_width">
- <xsl:choose>
- <xsl:when test="$max_bar_width < ($iwidth div $bars)">
- <xsl:value-of select="$max_bar_width"/>
- </xsl:when>
- <xsl:otherwise>
- <xsl:value-of select="$iwidth div $bars"/>
- </xsl:otherwise>
- </xsl:choose>
- </xsl:variable>
- <table class="histogram">
- <tbody>
- <tr>
- <xsl:for-each select="int">
- <td>
- <xsl:value-of select="."/>
- <div class="histogram">
- <xsl:attribute name="style">background-color: <xsl:value-of select="$fill"/>; width: <xsl:value-of select="$bar_width"/>px; height: <xsl:value-of select="($iheight*number(.)) div $max"/>px;</xsl:attribute>
- </div>
- </td>
- </xsl:for-each>
- </tr>
- <tr>
- <xsl:for-each select="int">
- <td>
- <xsl:value-of select="@name"/>
- </td>
- </xsl:for-each>
- </tr>
- </tbody>
- </table>
- </xsl:template>
-
- <xsl:template name="keyvalue">
- <xsl:choose>
- <xsl:when test="@name">
- <tr>
- <td class="name">
- <xsl:value-of select="@name"/>
- </td>
- <td class="value">
- <xsl:value-of select="."/>
- </td>
- </tr>
- </xsl:when>
- <xsl:otherwise>
- <xsl:value-of select="."/>
- </xsl:otherwise>
- </xsl:choose>
- </xsl:template>
-
- <xsl:template match="int|bool|long|float|double|uuid|date">
- <xsl:call-template name="keyvalue"/>
- </xsl:template>
-
- <xsl:template match="arr">
- <tr>
- <td class="name">
- <xsl:value-of select="@name"/>
- </td>
- <td class="value">
- <ul>
- <xsl:for-each select="child::*">
- <li>
- <xsl:apply-templates/>
- </li>
- </xsl:for-each>
- </ul>
- </td>
- </tr>
- </xsl:template>
-
- <xsl:template match="str">
- <xsl:choose>
- <xsl:when test="@name='schema' or @name='index' or @name='flags'">
- <xsl:call-template name="schema"/>
- </xsl:when>
- <xsl:otherwise>
- <xsl:call-template name="keyvalue"/>
- </xsl:otherwise>
- </xsl:choose>
- </xsl:template>
-
- <xsl:template name="schema">
- <tr>
- <td class="name">
- <xsl:value-of select="@name"/>
- </td>
- <td class="value">
- <xsl:if test="contains(.,'unstored')">
- <xsl:value-of select="."/>
- </xsl:if>
- <xsl:if test="not(contains(.,'unstored'))">
- <xsl:call-template name="infochar2string">
- <xsl:with-param name="charList">
- <xsl:value-of select="."/>
- </xsl:with-param>
- </xsl:call-template>
- </xsl:if>
- </td>
- </tr>
- </xsl:template>
-
- <xsl:template name="infochar2string">
- <xsl:param name="i">1</xsl:param>
- <xsl:param name="charList"/>
-
- <xsl:variable name="char">
- <xsl:value-of select="substring($charList,$i,1)"/>
- </xsl:variable>
- <xsl:choose>
- <xsl:when test="$char='I'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='I']"/> - </xsl:when>
- <xsl:when test="$char='T'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='T']"/> - </xsl:when>
- <xsl:when test="$char='S'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='S']"/> - </xsl:when>
- <xsl:when test="$char='M'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='M']"/> - </xsl:when>
- <xsl:when test="$char='V'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='V']"/> - </xsl:when>
- <xsl:when test="$char='o'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='o']"/> - </xsl:when>
- <xsl:when test="$char='p'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='p']"/> - </xsl:when>
- <xsl:when test="$char='O'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='O']"/> - </xsl:when>
- <xsl:when test="$char='L'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='L']"/> - </xsl:when>
- <xsl:when test="$char='B'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='B']"/> - </xsl:when>
- <xsl:when test="$char='C'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='C']"/> - </xsl:when>
- <xsl:when test="$char='f'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='f']"/> - </xsl:when>
- <xsl:when test="$char='l'">
- <xsl:value-of select="/response/lst[@name='info']/lst/str[@name='l']"/> -
- </xsl:when>
- </xsl:choose>
-
- <xsl:if test="not($i>=string-length($charList))">
- <xsl:call-template name="infochar2string">
- <xsl:with-param name="i">
- <xsl:value-of select="$i+1"/>
- </xsl:with-param>
- <xsl:with-param name="charList">
- <xsl:value-of select="$charList"/>
- </xsl:with-param>
- </xsl:call-template>
- </xsl:if>
- </xsl:template>
- <xsl:template name="css">
- <style type="text/css">
- <![CDATA[
- td.name {font-style: italic; font-size:80%; }
- .doc { margin: 0.5em; border: solid grey 1px; }
- .exp { display: none; font-family: monospace; white-space: pre; }
- div.histogram { background: none repeat scroll 0%; -moz-background-clip: -moz-initial; -moz-background-origin: -moz-initial; -moz-background-inline-policy: -moz-initial;}
- table.histogram { width: auto; vertical-align: bottom; }
- table.histogram td, table.histogram th { text-align: center; vertical-align: bottom; border-bottom: 1px solid #ff9933; width: auto; }
- ]]>
- </style>
- </xsl:template>
-</xsl:stylesheet>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/xslt/updateXml.xsl
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/xslt/updateXml.xsl b/solr/example/example-DIH/solr/rss/conf/xslt/updateXml.xsl
deleted file mode 100644
index a96e1d0..0000000
--- a/solr/example/example-DIH/solr/rss/conf/xslt/updateXml.xsl
+++ /dev/null
@@ -1,70 +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.
- -->
-
-<!--
- Simple transform of Solr query response into Solr Update XML compliant XML.
- When used in the xslt response writer you will get UpdaateXML as output.
- But you can also store a query response XML to disk and feed this XML to
- the XSLTUpdateRequestHandler to index the content. Provided as example only.
- See http://wiki.apache.org/solr/XsltUpdateRequestHandler for more info
- -->
-<xsl:stylesheet version='1.0' xmlns:xsl='http://www.w3.org/1999/XSL/Transform'>
- <xsl:output media-type="text/xml" method="xml" indent="yes"/>
-
- <xsl:template match='/'>
- <add>
- <xsl:apply-templates select="response/result/doc"/>
- </add>
- </xsl:template>
-
- <!-- Ignore score (makes no sense to index) -->
- <xsl:template match="doc/*[@name='score']" priority="100">
- </xsl:template>
-
- <xsl:template match="doc">
- <xsl:variable name="pos" select="position()"/>
- <doc>
- <xsl:apply-templates>
- <xsl:with-param name="pos"><xsl:value-of select="$pos"/></xsl:with-param>
- </xsl:apply-templates>
- </doc>
- </xsl:template>
-
- <!-- Flatten arrays to duplicate field lines -->
- <xsl:template match="doc/arr" priority="100">
- <xsl:variable name="fn" select="@name"/>
-
- <xsl:for-each select="*">
- <xsl:element name="field">
- <xsl:attribute name="name"><xsl:value-of select="$fn"/></xsl:attribute>
- <xsl:value-of select="."/>
- </xsl:element>
- </xsl:for-each>
- </xsl:template>
-
-
- <xsl:template match="doc/*">
- <xsl:variable name="fn" select="@name"/>
-
- <xsl:element name="field">
- <xsl:attribute name="name"><xsl:value-of select="$fn"/></xsl:attribute>
- <xsl:value-of select="."/>
- </xsl:element>
- </xsl:template>
-
- <xsl:template match="*"/>
-</xsl:stylesheet>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/core.properties
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/core.properties b/solr/example/example-DIH/solr/rss/core.properties
deleted file mode 100644
index e69de29..0000000
[6/6] lucene-solr:master: SOLR-7383: Replace DIH 'rss' example with
'atom' rss example was broken for multiple reasons. atom example showcases
the same - and more - features and uses the smallest config file needed to
make it work.
Posted by ar...@apache.org.
SOLR-7383: Replace DIH 'rss' example with 'atom'
rss example was broken for multiple reasons.
atom example showcases the same - and more - features
and uses the smallest config file needed to make it work.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/580f6e98
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/580f6e98
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/580f6e98
Branch: refs/heads/master
Commit: 580f6e98fb033dbbb8e0921fc3175021714ce956
Parents: 35aac1d
Author: Alexandre Rafalovitch <ar...@apache.org>
Authored: Sat Apr 1 13:42:23 2017 -0400
Committer: Alexandre Rafalovitch <ar...@apache.org>
Committed: Sat Apr 1 13:42:23 2017 -0400
----------------------------------------------------------------------
solr/CHANGES.txt | 2 +
solr/README.txt | 2 +-
solr/example/README.txt | 2 +-
solr/example/example-DIH/README.txt | 11 +-
.../solr/atom/conf/atom-data-config.xml | 35 +
.../solr/atom/conf/lang/stopwords_en.txt | 54 +
.../example-DIH/solr/atom/conf/managed-schema | 106 +
.../example-DIH/solr/atom/conf/protwords.txt | 17 +
.../example-DIH/solr/atom/conf/solrconfig.xml | 61 +
.../example-DIH/solr/atom/conf/synonyms.txt | 29 +
.../example-DIH/solr/atom/conf/url_types.txt | 1 +
.../example-DIH/solr/atom/core.properties | 0
.../example-DIH/solr/rss/conf/admin-extra.html | 24 -
.../solr/rss/conf/admin-extra.menu-bottom.html | 25 -
.../solr/rss/conf/admin-extra.menu-top.html | 25 -
.../clustering/carrot2/kmeans-attributes.xml | 19 -
.../clustering/carrot2/lingo-attributes.xml | 24 -
.../conf/clustering/carrot2/stc-attributes.xml | 19 -
.../example-DIH/solr/rss/conf/currency.xml | 67 -
.../example-DIH/solr/rss/conf/elevate.xml | 42 -
.../solr/rss/conf/lang/contractions_ca.txt | 8 -
.../solr/rss/conf/lang/contractions_fr.txt | 15 -
.../solr/rss/conf/lang/contractions_ga.txt | 5 -
.../solr/rss/conf/lang/contractions_it.txt | 23 -
.../solr/rss/conf/lang/hyphenations_ga.txt | 5 -
.../solr/rss/conf/lang/stemdict_nl.txt | 6 -
.../solr/rss/conf/lang/stoptags_ja.txt | 420 --
.../solr/rss/conf/lang/stopwords_ar.txt | 125 -
.../solr/rss/conf/lang/stopwords_bg.txt | 193 -
.../solr/rss/conf/lang/stopwords_ca.txt | 220 -
.../solr/rss/conf/lang/stopwords_ckb.txt | 136 -
.../solr/rss/conf/lang/stopwords_cz.txt | 172 -
.../solr/rss/conf/lang/stopwords_da.txt | 110 -
.../solr/rss/conf/lang/stopwords_de.txt | 294 --
.../solr/rss/conf/lang/stopwords_el.txt | 78 -
.../solr/rss/conf/lang/stopwords_en.txt | 54 -
.../solr/rss/conf/lang/stopwords_es.txt | 356 --
.../solr/rss/conf/lang/stopwords_eu.txt | 99 -
.../solr/rss/conf/lang/stopwords_fa.txt | 313 --
.../solr/rss/conf/lang/stopwords_fi.txt | 97 -
.../solr/rss/conf/lang/stopwords_fr.txt | 186 -
.../solr/rss/conf/lang/stopwords_ga.txt | 110 -
.../solr/rss/conf/lang/stopwords_gl.txt | 161 -
.../solr/rss/conf/lang/stopwords_hi.txt | 235 --
.../solr/rss/conf/lang/stopwords_hu.txt | 211 -
.../solr/rss/conf/lang/stopwords_hy.txt | 46 -
.../solr/rss/conf/lang/stopwords_id.txt | 359 --
.../solr/rss/conf/lang/stopwords_it.txt | 303 --
.../solr/rss/conf/lang/stopwords_ja.txt | 127 -
.../solr/rss/conf/lang/stopwords_lv.txt | 172 -
.../solr/rss/conf/lang/stopwords_nl.txt | 119 -
.../solr/rss/conf/lang/stopwords_no.txt | 194 -
.../solr/rss/conf/lang/stopwords_pt.txt | 253 --
.../solr/rss/conf/lang/stopwords_ro.txt | 233 --
.../solr/rss/conf/lang/stopwords_ru.txt | 243 --
.../solr/rss/conf/lang/stopwords_sv.txt | 133 -
.../solr/rss/conf/lang/stopwords_th.txt | 119 -
.../solr/rss/conf/lang/stopwords_tr.txt | 212 -
.../solr/rss/conf/lang/userdict_ja.txt | 29 -
.../example-DIH/solr/rss/conf/managed-schema | 1096 -----
.../solr/rss/conf/mapping-FoldToASCII.txt | 3813 ------------------
.../solr/rss/conf/mapping-ISOLatin1Accent.txt | 246 --
.../example-DIH/solr/rss/conf/protwords.txt | 21 -
.../solr/rss/conf/rss-data-config.xml | 26 -
.../example-DIH/solr/rss/conf/solrconfig.xml | 1396 -------
.../example-DIH/solr/rss/conf/spellings.txt | 2 -
.../example-DIH/solr/rss/conf/stopwords.txt | 14 -
.../example-DIH/solr/rss/conf/synonyms.txt | 29 -
.../example-DIH/solr/rss/conf/update-script.js | 53 -
.../example-DIH/solr/rss/conf/xslt/example.xsl | 132 -
.../solr/rss/conf/xslt/example_atom.xsl | 67 -
.../solr/rss/conf/xslt/example_rss.xsl | 66 -
.../example-DIH/solr/rss/conf/xslt/luke.xsl | 337 --
.../solr/rss/conf/xslt/updateXml.xsl | 70 -
.../example-DIH/solr/rss/core.properties | 0
75 files changed, 312 insertions(+), 13795 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 1efefd0..3187dc3 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -180,6 +180,8 @@ Other Changes
* SOLR-10399: Generalize some internal facet logic to simplify points/non-points field handling (Adrien Grand, hossman)
+* SOLR-7383: New DataImportHandler 'atom' example, replacing broken 'rss' example (Alexandre Rafalovitch)
+
================== 6.5.0 ==================
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/580f6e98/solr/README.txt
----------------------------------------------------------------------
diff --git a/solr/README.txt b/solr/README.txt
index 4ef5eac..6af0cc6 100644
--- a/solr/README.txt
+++ b/solr/README.txt
@@ -67,7 +67,7 @@ Solr includes a few examples to help you get started. To run a specific example,
bin/solr -e <EXAMPLE> where <EXAMPLE> is one of:
cloud : SolrCloud example
- dih : Data Import Handler (rdbms, mail, rss, tika)
+ dih : Data Import Handler (rdbms, mail, atom, tika)
schemaless : Schema-less example (schema is inferred from data during indexing)
techproducts : Kitchen sink example providing comprehensive examples of Solr features
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/README.txt
----------------------------------------------------------------------
diff --git a/solr/example/README.txt b/solr/example/README.txt
index d8402eb..4c8cca1 100644
--- a/solr/example/README.txt
+++ b/solr/example/README.txt
@@ -22,7 +22,7 @@ separate directory. To run a specific example, do:
bin/solr -e <EXAMPLE> where <EXAMPLE> is one of:
cloud : SolrCloud example
- dih : Data Import Handler (rdbms, mail, rss, tika)
+ dih : Data Import Handler (rdbms, mail, atom, tika)
schemaless : Schema-less example (schema is inferred from data during indexing)
techproducts : Kitchen sink example providing comprehensive examples of Solr features
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/README.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/README.txt b/solr/example/example-DIH/README.txt
index 0926bb6..ea8d28f 100644
--- a/solr/example/example-DIH/README.txt
+++ b/solr/example/example-DIH/README.txt
@@ -16,7 +16,7 @@
Solr DataImportHandler example configuration
--------------------------------------------
-To run this example, use the "-e" option of the bin/solr script:
+To run this multi-core example, use the "-e" option of the bin/solr script:
> bin/solr -e dih
@@ -28,9 +28,9 @@ When Solr is started connect to:
http://localhost:8983/solr/db/dataimport?command=full-import
-* To import data from an RSS feed, connect to:
+* To import data from an ATOM feed, connect to:
- http://localhost:8983/solr/rss/dataimport?command=full-import
+ http://localhost:8983/solr/atom/dataimport?command=full-import
* To import data from your IMAP server:
@@ -45,6 +45,5 @@ When Solr is started connect to:
http://localhost:8983/solr/tika/dataimport?command=full-import
-See also README.txt in the solr subdirectory, and check
-http://wiki.apache.org/solr/DataImportHandler for detailed
-usage guide and tutorial.
+Check also the Solr Reference Guide for detailed usage guide:
+https://cwiki.apache.org/confluence/display/solr/Uploading+Structured+Data+Store+Data+with+the+Data+Import+Handler
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/atom/conf/atom-data-config.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/atom/conf/atom-data-config.xml b/solr/example/example-DIH/solr/atom/conf/atom-data-config.xml
new file mode 100644
index 0000000..53b5060
--- /dev/null
+++ b/solr/example/example-DIH/solr/atom/conf/atom-data-config.xml
@@ -0,0 +1,35 @@
+<dataConfig>
+ <dataSource type="URLDataSource"/>
+ <document>
+
+ <entity name="stackoverflow"
+ url="http://stackoverflow.com/feeds/tag/solr"
+ processor="XPathEntityProcessor"
+ forEach="/feed|/feed/entry"
+ transformer="HTMLStripTransformer,RegexTransformer">
+
+ <!-- Pick this value up from the feed level and apply to all documents -->
+ <field column="lastchecked_dt" xpath="/feed/updated" commonField="true"/>
+
+ <!-- Keep only the final numeric part of the URL -->
+ <field column="id" xpath="/feed/entry/id" regex=".*/" replaceWith=""/>
+
+ <field column="title" xpath="/feed/entry/title"/>
+ <field column="author" xpath="/feed/entry/author/name"/>
+ <field column="category" xpath="/feed/entry/category/@term"/>
+ <field column="link" xpath="/feed/entry/link[@rel='alternate']/@href"/>
+
+ <!-- Use transformers to convert HTML into plain text.
+ There is also an UpdateRequestProcess to trim remaining spaces.
+ -->
+ <field column="summary" xpath="/feed/entry/summary" stripHTML="true" regex="( |\n)+" replaceWith=" "/>
+
+ <!-- Ignore namespaces when matching XPath -->
+ <field column="rank" xpath="/feed/entry/rank"/>
+
+ <field column="published_dt" xpath="/feed/entry/published"/>
+ <field column="updated_dt" xpath="/feed/entry/updated"/>
+ </entity>
+
+ </document>
+</dataConfig>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/atom/conf/lang/stopwords_en.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/atom/conf/lang/stopwords_en.txt b/solr/example/example-DIH/solr/atom/conf/lang/stopwords_en.txt
new file mode 100644
index 0000000..2c164c0
--- /dev/null
+++ b/solr/example/example-DIH/solr/atom/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/580f6e98/solr/example/example-DIH/solr/atom/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/atom/conf/managed-schema b/solr/example/example-DIH/solr/atom/conf/managed-schema
new file mode 100644
index 0000000..5875152
--- /dev/null
+++ b/solr/example/example-DIH/solr/atom/conf/managed-schema
@@ -0,0 +1,106 @@
+<?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="example-DIH-atom" version="1.6">
+ <uniqueKey>id</uniqueKey>
+
+ <field name="id" type="string" indexed="true" stored="true" required="true"/>
+ <field name="title" type="text_en_splitting" indexed="true" stored="true"/>
+ <field name="author" type="string" indexed="true" stored="true"/>
+ <field name="category" type="string" indexed="true" stored="true" multiValued="true"/>
+ <field name="link" type="string" indexed="true" stored="true"/>
+ <field name="summary" type="text_en_splitting" indexed="true" stored="true"/>
+ <field name="rank" type="pint" indexed="true" stored="true"/>
+
+ <dynamicField name="*_dt" type="pdate" indexed="true" stored="true"/>
+
+ <!-- Catch-all field, aggregating all "useful to search as text" fields via the copyField instructions -->
+ <field name="text" type="text_en_splitting" indexed="true" stored="false" multiValued="true"/>
+
+ <field name="urls" type="url_only" indexed="true" stored="false"/>
+
+
+ <copyField source="id" dest="text"/>
+ <copyField source="title" dest="text"/>
+ <copyField source="author" dest="text"/>
+ <copyField source="category" dest="text"/>
+ <copyField source="summary" dest="text"/>
+
+ <!-- extract URLs from summary for faceting -->
+ <copyField source="summary" dest="urls"/>
+
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true"/>
+ <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+ <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
+
+
+ <!-- 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
+ WordDelimiterFilter 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".
+ -->
+ <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>
+
+ <!-- Field type that extracts URLs from the text.
+ As the stored representation is not changed, it is only useful for faceting.
+ It is not terribly useful for searching URLs either, as there are too many special symbols.
+ -->
+ <fieldType name="url_only" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.UAX29URLEmailTokenizerFactory" maxTokenLength="255"/>
+ <filter class="solr.TypeTokenFilterFactory" types="url_types.txt" useWhitelist="true"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+
+</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/atom/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/atom/conf/protwords.txt b/solr/example/example-DIH/solr/atom/conf/protwords.txt
new file mode 100644
index 0000000..1303e42
--- /dev/null
+++ b/solr/example/example-DIH/solr/atom/conf/protwords.txt
@@ -0,0 +1,17 @@
+# 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.
+
+lucene
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/atom/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/atom/conf/solrconfig.xml b/solr/example/example-DIH/solr/atom/conf/solrconfig.xml
new file mode 100644
index 0000000..22005dd
--- /dev/null
+++ b/solr/example/example-DIH/solr/atom/conf/solrconfig.xml
@@ -0,0 +1,61 @@
+<?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 a DEMO configuration, highlighting elements
+ specifically needed to get this example running
+ such as libraries and request handler specifics.
+
+ It uses defaults or does not define most of production-level settings
+ such as various caches or auto-commit policies.
+
+ See Solr Reference Guide and other examples for
+ more details on a well configured solrconfig.xml
+ https://cwiki.apache.org/confluence/display/solr/The+Well-Configured+Solr+Instance
+-->
+<config>
+
+ <!-- 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 dir="${solr.install.dir:../../../..}/dist/" regex="solr-dataimporthandler-.*\.jar"/>
+
+ <requestHandler name="/select" class="solr.SearchHandler">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="df">text</str>
+ </lst>
+ </requestHandler>
+
+ <requestHandler name="/dataimport" class="solr.DataImportHandler">
+ <lst name="defaults">
+ <str name="config">atom-data-config.xml</str>
+ <str name="processor">trim_text</str>
+ </lst>
+ </requestHandler>
+
+ <updateProcessor class="solr.processor.TrimFieldUpdateProcessorFactory" name="trim_text">
+ <str name="typeName">text_en_splitting</str>
+ </updateProcessor>
+
+</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/atom/conf/synonyms.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/atom/conf/synonyms.txt b/solr/example/example-DIH/solr/atom/conf/synonyms.txt
new file mode 100644
index 0000000..eab4ee8
--- /dev/null
+++ b/solr/example/example-DIH/solr/atom/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/580f6e98/solr/example/example-DIH/solr/atom/conf/url_types.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/atom/conf/url_types.txt b/solr/example/example-DIH/solr/atom/conf/url_types.txt
new file mode 100644
index 0000000..808f313
--- /dev/null
+++ b/solr/example/example-DIH/solr/atom/conf/url_types.txt
@@ -0,0 +1 @@
+<URL>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/atom/core.properties
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/atom/core.properties b/solr/example/example-DIH/solr/atom/core.properties
new file mode 100644
index 0000000..e69de29
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/admin-extra.html
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/admin-extra.html b/solr/example/example-DIH/solr/rss/conf/admin-extra.html
deleted file mode 100644
index fecab20..0000000
--- a/solr/example/example-DIH/solr/rss/conf/admin-extra.html
+++ /dev/null
@@ -1,24 +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.
--->
-
-<!-- The content of this page will be statically included into the top-
-right box of the cores overview page. Uncomment this as an example to
-see there the content will show up.
-
-<img src="img/ico/construction.png"> This line will appear at the top-
-right box on collection1's Overview
--->
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/admin-extra.menu-bottom.html
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/admin-extra.menu-bottom.html b/solr/example/example-DIH/solr/rss/conf/admin-extra.menu-bottom.html
deleted file mode 100644
index 3359a46..0000000
--- a/solr/example/example-DIH/solr/rss/conf/admin-extra.menu-bottom.html
+++ /dev/null
@@ -1,25 +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.
--->
-
-<!-- admin-extra.menu-bottom.html -->
-<!--
-<li>
- <a href="#" style="background-image: url(img/ico/construction.png);">
- LAST ITEM
- </a>
-</li>
--->
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/admin-extra.menu-top.html
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/admin-extra.menu-top.html b/solr/example/example-DIH/solr/rss/conf/admin-extra.menu-top.html
deleted file mode 100644
index 0886cee..0000000
--- a/solr/example/example-DIH/solr/rss/conf/admin-extra.menu-top.html
+++ /dev/null
@@ -1,25 +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.
--->
-
-<!-- admin-extra.menu-top.html -->
-<!--
-<li>
- <a href="#" style="background-image: url(img/ico/construction.png);">
- FIRST ITEM
- </a>
-</li>
--->
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/kmeans-attributes.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/kmeans-attributes.xml b/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/kmeans-attributes.xml
deleted file mode 100644
index d802465..0000000
--- a/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/kmeans-attributes.xml
+++ /dev/null
@@ -1,19 +0,0 @@
-<!--
- Default configuration for the bisecting k-means clustering algorithm.
-
- This file can be loaded (and saved) by Carrot2 Workbench.
- http://project.carrot2.org/download.html
--->
-<attribute-sets default="attributes">
- <attribute-set id="attributes">
- <value-set>
- <label>attributes</label>
- <attribute key="MultilingualClustering.defaultLanguage">
- <value type="org.carrot2.core.LanguageCode" value="ENGLISH"/>
- </attribute>
- <attribute key="MultilingualClustering.languageAggregationStrategy">
- <value type="org.carrot2.text.clustering.MultilingualClustering$LanguageAggregationStrategy" value="FLATTEN_MAJOR_LANGUAGE"/>
- </attribute>
- </value-set>
- </attribute-set>
-</attribute-sets>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/lingo-attributes.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/lingo-attributes.xml b/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/lingo-attributes.xml
deleted file mode 100644
index 4bf1360..0000000
--- a/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/lingo-attributes.xml
+++ /dev/null
@@ -1,24 +0,0 @@
-<!--
- Default configuration for the Lingo clustering algorithm.
-
- This file can be loaded (and saved) by Carrot2 Workbench.
- http://project.carrot2.org/download.html
--->
-<attribute-sets default="attributes">
- <attribute-set id="attributes">
- <value-set>
- <label>attributes</label>
- <!--
- The language to assume for clustered documents.
- For a list of allowed values, see:
- http://download.carrot2.org/stable/manual/#section.attribute.lingo.MultilingualClustering.defaultLanguage
- -->
- <attribute key="MultilingualClustering.defaultLanguage">
- <value type="org.carrot2.core.LanguageCode" value="ENGLISH"/>
- </attribute>
- <attribute key="LingoClusteringAlgorithm.desiredClusterCountBase">
- <value type="java.lang.Integer" value="20"/>
- </attribute>
- </value-set>
- </attribute-set>
-</attribute-sets>
\ No newline at end of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/stc-attributes.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/stc-attributes.xml b/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/stc-attributes.xml
deleted file mode 100644
index c1bf110..0000000
--- a/solr/example/example-DIH/solr/rss/conf/clustering/carrot2/stc-attributes.xml
+++ /dev/null
@@ -1,19 +0,0 @@
-<!--
- Default configuration for the STC clustering algorithm.
-
- This file can be loaded (and saved) by Carrot2 Workbench.
- http://project.carrot2.org/download.html
--->
-<attribute-sets default="attributes">
- <attribute-set id="attributes">
- <value-set>
- <label>attributes</label>
- <attribute key="MultilingualClustering.defaultLanguage">
- <value type="org.carrot2.core.LanguageCode" value="ENGLISH"/>
- </attribute>
- <attribute key="MultilingualClustering.languageAggregationStrategy">
- <value type="org.carrot2.text.clustering.MultilingualClustering$LanguageAggregationStrategy" value="FLATTEN_MAJOR_LANGUAGE"/>
- </attribute>
- </value-set>
- </attribute-set>
-</attribute-sets>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/currency.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/currency.xml b/solr/example/example-DIH/solr/rss/conf/currency.xml
deleted file mode 100644
index 3a9c58a..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/elevate.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/elevate.xml b/solr/example/example-DIH/solr/rss/conf/elevate.xml
deleted file mode 100644
index 2c09ebe..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/contractions_ca.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/contractions_ca.txt b/solr/example/example-DIH/solr/rss/conf/lang/contractions_ca.txt
deleted file mode 100644
index 307a85f..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/contractions_fr.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/contractions_fr.txt b/solr/example/example-DIH/solr/rss/conf/lang/contractions_fr.txt
deleted file mode 100644
index f1bba51..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/contractions_ga.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/contractions_ga.txt b/solr/example/example-DIH/solr/rss/conf/lang/contractions_ga.txt
deleted file mode 100644
index 9ebe7fa..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/contractions_it.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/contractions_it.txt b/solr/example/example-DIH/solr/rss/conf/lang/contractions_it.txt
deleted file mode 100644
index cac0409..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/hyphenations_ga.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/hyphenations_ga.txt b/solr/example/example-DIH/solr/rss/conf/lang/hyphenations_ga.txt
deleted file mode 100644
index 4d2642c..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stemdict_nl.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stemdict_nl.txt b/solr/example/example-DIH/solr/rss/conf/lang/stemdict_nl.txt
deleted file mode 100644
index 4410729..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stoptags_ja.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stoptags_ja.txt b/solr/example/example-DIH/solr/rss/conf/lang/stoptags_ja.txt
deleted file mode 100644
index 71b7508..0000000
--- a/solr/example/example-DIH/solr/rss/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
-#\u540d\u8a5e
-#
-# noun-common: Common nouns or nouns where the sub-classification is undefined
-#\u540d\u8a5e-\u4e00\u822c
-#
-# noun-proper: Proper nouns where the sub-classification is undefined
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e
-#
-# noun-proper-misc: miscellaneous proper nouns
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e-\u4e00\u822c
-#
-# noun-proper-person: Personal names where the sub-classification is undefined
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e-\u4eba\u540d
-#
-# 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. \u304a\u5e02\u306e\u65b9
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e-\u4eba\u540d-\u4e00\u822c
-#
-# noun-proper-person-surname: Mainly Japanese surnames.
-# e.g. \u5c71\u7530
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e-\u4eba\u540d-\u59d3
-#
-# noun-proper-person-given_name: Mainly Japanese given names.
-# e.g. \u592a\u90ce
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e-\u4eba\u540d-\u540d
-#
-# noun-proper-organization: Names representing organizations.
-# e.g. \u901a\u7523\u7701, NHK
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e-\u7d44\u7e54
-#
-# noun-proper-place: Place names where the sub-classification is undefined
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e-\u5730\u57df
-#
-# noun-proper-place-misc: Place names excluding countries.
-# e.g. \u30a2\u30b8\u30a2, \u30d0\u30eb\u30bb\u30ed\u30ca, \u4eac\u90fd
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e-\u5730\u57df-\u4e00\u822c
-#
-# noun-proper-place-country: Country names.
-# e.g. \u65e5\u672c, \u30aa\u30fc\u30b9\u30c8\u30e9\u30ea\u30a2
-#\u540d\u8a5e-\u56fa\u6709\u540d\u8a5e-\u5730\u57df-\u56fd
-#
-# noun-pronoun: Pronouns where the sub-classification is undefined
-#\u540d\u8a5e-\u4ee3\u540d\u8a5e
-#
-# noun-pronoun-misc: miscellaneous pronouns:
-# e.g. \u305d\u308c, \u3053\u3053, \u3042\u3044\u3064, \u3042\u306a\u305f, \u3042\u3061\u3053\u3061, \u3044\u304f\u3064, \u3069\u3053\u304b, \u306a\u306b, \u307f\u306a\u3055\u3093, \u307f\u3093\u306a, \u308f\u305f\u304f\u3057, \u308f\u308c\u308f\u308c
-#\u540d\u8a5e-\u4ee3\u540d\u8a5e-\u4e00\u822c
-#
-# noun-pronoun-contraction: Spoken language contraction made by combining a
-# pronoun and the particle 'wa'.
-# e.g. \u3042\u308a\u3083, \u3053\u308a\u3083, \u3053\u308a\u3083\u3042, \u305d\u308a\u3083, \u305d\u308a\u3083\u3042
-#\u540d\u8a5e-\u4ee3\u540d\u8a5e-\u7e2e\u7d04
-#
-# 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. \u91d1\u66dc, \u4e00\u6708, \u5348\u5f8c, \u5c11\u91cf
-#\u540d\u8a5e-\u526f\u8a5e\u53ef\u80fd
-#
-# noun-verbal: Nouns that take arguments with case and can appear followed by
-# 'suru' and related verbs (\u3059\u308b, \u3067\u304d\u308b, \u306a\u3055\u308b, \u304f\u3060\u3055\u308b)
-# e.g. \u30a4\u30f3\u30d7\u30c3\u30c8, \u611b\u7740, \u60aa\u5316, \u60aa\u6226\u82e6\u95d8, \u4e00\u5b89\u5fc3, \u4e0b\u53d6\u308a
-#\u540d\u8a5e-\u30b5\u5909\u63a5\u7d9a
-#
-# noun-adjective-base: The base form of adjectives, words that appear before \u306a ("na")
-# e.g. \u5065\u5eb7, \u5b89\u6613, \u99c4\u76ee, \u3060\u3081
-#\u540d\u8a5e-\u5f62\u5bb9\u52d5\u8a5e\u8a9e\u5e79
-#
-# noun-numeric: Arabic numbers, Chinese numerals, and counters like \u4f55 (\u56de), \u6570.
-# e.g. 0, 1, 2, \u4f55, \u6570, \u5e7e
-#\u540d\u8a5e-\u6570
-#
-# noun-affix: noun affixes where the sub-classification is undefined
-#\u540d\u8a5e-\u975e\u81ea\u7acb
-#
-# noun-affix-misc: Of adnominalizers, the case-marker \u306e ("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. \u3042\u304b\u3064\u304d, \u6681, \u304b\u3044, \u7532\u6590, \u6c17, \u304d\u3089\u3044, \u5acc\u3044, \u304f\u305b, \u7656, \u3053\u3068, \u4e8b, \u3054\u3068, \u6bce, \u3057\u3060\u3044, \u6b21\u7b2c,
-# \u9806, \u305b\u3044, \u6240\u70ba, \u3064\u3044\u3067, \u5e8f\u3067, \u3064\u3082\u308a, \u7a4d\u3082\u308a, \u70b9, \u3069\u3053\u308d, \u306e, \u306f\u305a, \u7b48, \u306f\u305a\u307f, \u5f3e\u307f,
-# \u62cd\u5b50, \u3075\u3046, \u3075\u308a, \u632f\u308a, \u307b\u3046, \u65b9, \u65e8, \u3082\u306e, \u7269, \u8005, \u3086\u3048, \u6545, \u3086\u3048\u3093, \u6240\u4ee5, \u308f\u3051, \u8a33,
-# \u308f\u308a, \u5272\u308a, \u5272, \u3093-\u53e3\u8a9e/, \u3082\u3093-\u53e3\u8a9e/
-#\u540d\u8a5e-\u975e\u81ea\u7acb-\u4e00\u822c
-#
-# noun-affix-adverbial: noun affixes that that can behave as adverbs.
-# e.g. \u3042\u3044\u3060, \u9593, \u3042\u3052\u304f, \u6319\u3052\u53e5, \u3042\u3068, \u5f8c, \u4f59\u308a, \u4ee5\u5916, \u4ee5\u964d, \u4ee5\u5f8c, \u4ee5\u4e0a, \u4ee5\u524d, \u4e00\u65b9, \u3046\u3048,
-# \u4e0a, \u3046\u3061, \u5185, \u304a\u308a, \u6298\u308a, \u304b\u304e\u308a, \u9650\u308a, \u304d\u308a, \u3063\u304d\u308a, \u7d50\u679c, \u3053\u308d, \u9803, \u3055\u3044, \u969b, \u6700\u4e2d, \u3055\u306a\u304b,
-# \u6700\u4e2d, \u3058\u305f\u3044, \u81ea\u4f53, \u305f\u3073, \u5ea6, \u305f\u3081, \u70ba, \u3064\u3069, \u90fd\u5ea6, \u3068\u304a\u308a, \u901a\u308a, \u3068\u304d, \u6642, \u3068\u3053\u308d, \u6240,
-# \u3068\u305f\u3093, \u9014\u7aef, \u306a\u304b, \u4e2d, \u306e\u3061, \u5f8c, \u3070\u3042\u3044, \u5834\u5408, \u65e5, \u3076\u3093, \u5206, \u307b\u304b, \u4ed6, \u307e\u3048, \u524d, \u307e\u307e,
-# \u5118, \u4fad, \u307f\u304e\u308a, \u77e2\u5148
-#\u540d\u8a5e-\u975e\u81ea\u7acb-\u526f\u8a5e\u53ef\u80fd
-#
-# noun-affix-aux: noun affixes treated as \u52a9\u52d5\u8a5e ("auxiliary verb") in school grammars
-# with the stem \u3088\u3046(\u3060) ("you(da)").
-# e.g. \u3088\u3046, \u3084\u3046, \u69d8 (\u3088\u3046)
-#\u540d\u8a5e-\u975e\u81ea\u7acb-\u52a9\u52d5\u8a5e\u8a9e\u5e79
-#
-# noun-affix-adjective-base: noun affixes that can connect to the indeclinable
-# connection form \u306a (aux "da").
-# e.g. \u307f\u305f\u3044, \u3075\u3046
-#\u540d\u8a5e-\u975e\u81ea\u7acb-\u5f62\u5bb9\u52d5\u8a5e\u8a9e\u5e79
-#
-# noun-special: special nouns where the sub-classification is undefined.
-#\u540d\u8a5e-\u7279\u6b8a
-#
-# noun-special-aux: The \u305d\u3046\u3060 ("souda") stem form that is used for reporting news, is
-# treated as \u52a9\u52d5\u8a5e ("auxiliary verb") in school grammars, and attach to the base
-# form of inflectional words.
-# e.g. \u305d\u3046
-#\u540d\u8a5e-\u7279\u6b8a-\u52a9\u52d5\u8a5e\u8a9e\u5e79
-#
-# noun-suffix: noun suffixes where the sub-classification is undefined.
-#\u540d\u8a5e-\u63a5\u5c3e
-#
-# noun-suffix-misc: Of the nouns or stem forms of other parts of speech that connect
-# to \u30ac\u30eb or \u30bf\u30a4 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
-# \u63a5\u5c3e\u8a9e ("suffix") and is usually the last element in a compound noun.
-# e.g. \u304a\u304d, \u304b\u305f, \u65b9, \u7532\u6590 (\u304c\u3044), \u304c\u304b\u308a, \u304e\u307f, \u6c17\u5473, \u3050\u308b\u307f, (\uff5e\u3057\u305f) \u3055, \u6b21\u7b2c, \u6e08 (\u305a) \u307f,
-# \u3088\u3046, (\u3067\u304d)\u3063\u3053, \u611f, \u89b3, \u6027, \u5b66, \u985e, \u9762, \u7528
-#\u540d\u8a5e-\u63a5\u5c3e-\u4e00\u822c
-#
-# noun-suffix-person: Suffixes that form nouns and attach to person names more often
-# than other nouns.
-# e.g. \u541b, \u69d8, \u8457
-#\u540d\u8a5e-\u63a5\u5c3e-\u4eba\u540d
-#
-# noun-suffix-place: Suffixes that form nouns and attach to place names more often
-# than other nouns.
-# e.g. \u753a, \u5e02, \u770c
-#\u540d\u8a5e-\u63a5\u5c3e-\u5730\u57df
-#
-# noun-suffix-verbal: Of the suffixes that attach to nouns and form nouns, those that
-# can appear before \u30b9\u30eb ("suru").
-# e.g. \u5316, \u8996, \u5206\u3051, \u5165\u308a, \u843d\u3061, \u8cb7\u3044
-#\u540d\u8a5e-\u63a5\u5c3e-\u30b5\u5909\u63a5\u7d9a
-#
-# noun-suffix-aux: The stem form of \u305d\u3046\u3060 (\u69d8\u614b) that is used to indicate conditions,
-# is treated as \u52a9\u52d5\u8a5e ("auxiliary verb") in school grammars, and attach to the
-# conjunctive form of inflectional words.
-# e.g. \u305d\u3046
-#\u540d\u8a5e-\u63a5\u5c3e-\u52a9\u52d5\u8a5e\u8a9e\u5e79
-#
-# noun-suffix-adjective-base: Suffixes that attach to other nouns or the conjunctive
-# form of inflectional words and appear before the copula \u3060 ("da").
-# e.g. \u7684, \u3052, \u304c\u3061
-#\u540d\u8a5e-\u63a5\u5c3e-\u5f62\u5bb9\u52d5\u8a5e\u8a9e\u5e79
-#
-# noun-suffix-adverbial: Suffixes that attach to other nouns and can behave as adverbs.
-# e.g. \u5f8c (\u3054), \u4ee5\u5f8c, \u4ee5\u964d, \u4ee5\u524d, \u524d\u5f8c, \u4e2d, \u672b, \u4e0a, \u6642 (\u3058)
-#\u540d\u8a5e-\u63a5\u5c3e-\u526f\u8a5e\u53ef\u80fd
-#
-# noun-suffix-classifier: Suffixes that attach to numbers and form nouns. This category
-# is more inclusive than \u52a9\u6570\u8a5e ("classifier") and includes common nouns that attach
-# to numbers.
-# e.g. \u500b, \u3064, \u672c, \u518a, \u30d1\u30fc\u30bb\u30f3\u30c8, cm, kg, \u30ab\u6708, \u304b\u56fd, \u533a\u753b, \u6642\u9593, \u6642\u534a
-#\u540d\u8a5e-\u63a5\u5c3e-\u52a9\u6570\u8a5e
-#
-# noun-suffix-special: Special suffixes that mainly attach to inflecting words.
-# e.g. (\u697d\u3057) \u3055, (\u8003\u3048) \u65b9
-#\u540d\u8a5e-\u63a5\u5c3e-\u7279\u6b8a
-#
-# noun-suffix-conjunctive: Nouns that behave like conjunctions and join two words
-# together.
-# e.g. (\u65e5\u672c) \u5bfe (\u30a2\u30e1\u30ea\u30ab), \u5bfe (\u30a2\u30e1\u30ea\u30ab), (3) \u5bfe (5), (\u5973\u512a) \u517c (\u4e3b\u5a66)
-#\u540d\u8a5e-\u63a5\u7d9a\u8a5e\u7684
-#
-# noun-verbal_aux: Nouns that attach to the conjunctive particle \u3066 ("te") and are
-# semantically verb-like.
-# e.g. \u3054\u3089\u3093, \u3054\u89a7, \u5fa1\u89a7, \u9802\u6234
-#\u540d\u8a5e-\u52d5\u8a5e\u975e\u81ea\u7acb\u7684
-#
-# noun-quotation: text that cannot be segmented into words, proverbs, Chinese poetry,
-# dialects, English, etc. Currently, the only entry for \u540d\u8a5e \u5f15\u7528\u6587\u5b57\u5217 ("noun quotation")
-# is \u3044\u308f\u304f ("iwaku").
-#\u540d\u8a5e-\u5f15\u7528\u6587\u5b57\u5217
-#
-# noun-nai_adjective: Words that appear before the auxiliary verb \u306a\u3044 ("nai") and
-# behave like an adjective.
-# e.g. \u7533\u3057\u8a33, \u4ed5\u65b9, \u3068\u3093\u3067\u3082, \u9055\u3044
-#\u540d\u8a5e-\u30ca\u30a4\u5f62\u5bb9\u8a5e\u8a9e\u5e79
-#
-#####
-# prefix: unclassified prefixes
-#\u63a5\u982d\u8a5e
-#
-# prefix-nominal: Prefixes that attach to nouns (including adjective stem forms)
-# excluding numerical expressions.
-# e.g. \u304a (\u6c34), \u67d0 (\u6c0f), \u540c (\u793e), \u6545 (\uff5e\u6c0f), \u9ad8 (\u54c1\u8cea), \u304a (\u898b\u4e8b), \u3054 (\u7acb\u6d3e)
-#\u63a5\u982d\u8a5e-\u540d\u8a5e\u63a5\u7d9a
-#
-# prefix-verbal: Prefixes that attach to the imperative form of a verb or a verb
-# in conjunctive form followed by \u306a\u308b/\u306a\u3055\u308b/\u304f\u3060\u3055\u308b.
-# e.g. \u304a (\u8aad\u307f\u306a\u3055\u3044), \u304a (\u5ea7\u308a)
-#\u63a5\u982d\u8a5e-\u52d5\u8a5e\u63a5\u7d9a
-#
-# prefix-adjectival: Prefixes that attach to adjectives.
-# e.g. \u304a (\u5bd2\u3044\u3067\u3059\u306d\u3048), \u30d0\u30ab (\u3067\u304b\u3044)
-#\u63a5\u982d\u8a5e-\u5f62\u5bb9\u8a5e\u63a5\u7d9a
-#
-# prefix-numerical: Prefixes that attach to numerical expressions.
-# e.g. \u7d04, \u304a\u3088\u305d, \u6bce\u6642
-#\u63a5\u982d\u8a5e-\u6570\u63a5\u7d9a
-#
-#####
-# verb: unclassified verbs
-#\u52d5\u8a5e
-#
-# verb-main:
-#\u52d5\u8a5e-\u81ea\u7acb
-#
-# verb-auxiliary:
-#\u52d5\u8a5e-\u975e\u81ea\u7acb
-#
-# verb-suffix:
-#\u52d5\u8a5e-\u63a5\u5c3e
-#
-#####
-# adjective: unclassified adjectives
-#\u5f62\u5bb9\u8a5e
-#
-# adjective-main:
-#\u5f62\u5bb9\u8a5e-\u81ea\u7acb
-#
-# adjective-auxiliary:
-#\u5f62\u5bb9\u8a5e-\u975e\u81ea\u7acb
-#
-# adjective-suffix:
-#\u5f62\u5bb9\u8a5e-\u63a5\u5c3e
-#
-#####
-# adverb: unclassified adverbs
-#\u526f\u8a5e
-#
-# adverb-misc: Words that can be segmented into one unit and where adnominal
-# modification is not possible.
-# e.g. \u3042\u3044\u304b\u308f\u3089\u305a, \u591a\u5206
-#\u526f\u8a5e-\u4e00\u822c
-#
-# adverb-particle_conjunction: Adverbs that can be followed by \u306e, \u306f, \u306b,
-# \u306a, \u3059\u308b, \u3060, etc.
-# e.g. \u3053\u3093\u306a\u306b, \u305d\u3093\u306a\u306b, \u3042\u3093\u306a\u306b, \u306a\u306b\u304b, \u306a\u3093\u3067\u3082
-#\u526f\u8a5e-\u52a9\u8a5e\u985e\u63a5\u7d9a
-#
-#####
-# adnominal: Words that only have noun-modifying forms.
-# e.g. \u3053\u306e, \u305d\u306e, \u3042\u306e, \u3069\u306e, \u3044\u308f\u3086\u308b, \u306a\u3093\u3089\u304b\u306e, \u4f55\u3089\u304b\u306e, \u3044\u308d\u3093\u306a, \u3053\u3046\u3044\u3046, \u305d\u3046\u3044\u3046, \u3042\u3042\u3044\u3046,
-# \u3069\u3046\u3044\u3046, \u3053\u3093\u306a, \u305d\u3093\u306a, \u3042\u3093\u306a, \u3069\u3093\u306a, \u5927\u304d\u306a, \u5c0f\u3055\u306a, \u304a\u304b\u3057\u306a, \u307b\u3093\u306e, \u305f\u3044\u3057\u305f,
-# \u300c(, \u3082) \u3055\u308b (\u3053\u3068\u306a\u304c\u3089)\u300d, \u5fae\u3005\u305f\u308b, \u5802\u3005\u305f\u308b, \u5358\u306a\u308b, \u3044\u304b\u306a\u308b, \u6211\u304c\u300d\u300c\u540c\u3058, \u4ea1\u304d
-#\u9023\u4f53\u8a5e
-#
-#####
-# conjunction: Conjunctions that can occur independently.
-# e.g. \u304c, \u3051\u308c\u3069\u3082, \u305d\u3057\u3066, \u3058\u3083\u3042, \u305d\u308c\u3069\u3053\u308d\u304b
-\u63a5\u7d9a\u8a5e
-#
-#####
-# particle: unclassified particles.
-\u52a9\u8a5e
-#
-# particle-case: case particles where the subclassification is undefined.
-\u52a9\u8a5e-\u683c\u52a9\u8a5e
-#
-# particle-case-misc: Case particles.
-# e.g. \u304b\u3089, \u304c, \u3067, \u3068, \u306b, \u3078, \u3088\u308a, \u3092, \u306e, \u306b\u3066
-\u52a9\u8a5e-\u683c\u52a9\u8a5e-\u4e00\u822c
-#
-# particle-case-quote: the "to" that appears after nouns, a person\u2019s speech,
-# quotation marks, expressions of decisions from a meeting, reasons, judgements,
-# conjectures, etc.
-# e.g. ( \u3060) \u3068 (\u8ff0\u3079\u305f.), ( \u3067\u3042\u308b) \u3068 (\u3057\u3066\u57f7\u884c\u7336\u4e88...)
-\u52a9\u8a5e-\u683c\u52a9\u8a5e-\u5f15\u7528
-#
-# particle-case-compound: Compounds of particles and verbs that mainly behave
-# like case particles.
-# e.g. \u3068\u3044\u3046, \u3068\u3044\u3063\u305f, \u3068\u304b\u3044\u3046, \u3068\u3057\u3066, \u3068\u3068\u3082\u306b, \u3068\u5171\u306b, \u3067\u3082\u3063\u3066, \u306b\u3042\u305f\u3063\u3066, \u306b\u5f53\u305f\u3063\u3066, \u306b\u5f53\u3063\u3066,
-# \u306b\u3042\u305f\u308a, \u306b\u5f53\u305f\u308a, \u306b\u5f53\u308a, \u306b\u5f53\u305f\u308b, \u306b\u3042\u305f\u308b, \u306b\u304a\u3044\u3066, \u306b\u65bc\u3044\u3066,\u306b\u65bc\u3066, \u306b\u304a\u3051\u308b, \u306b\u65bc\u3051\u308b,
-# \u306b\u304b\u3051, \u306b\u304b\u3051\u3066, \u306b\u304b\u3093\u3057, \u306b\u95a2\u3057, \u306b\u304b\u3093\u3057\u3066, \u306b\u95a2\u3057\u3066, \u306b\u304b\u3093\u3059\u308b, \u306b\u95a2\u3059\u308b, \u306b\u969b\u3057,
-# \u306b\u969b\u3057\u3066, \u306b\u3057\u305f\u304c\u3044, \u306b\u5f93\u3044, \u306b\u5f93\u3046, \u306b\u3057\u305f\u304c\u3063\u3066, \u306b\u5f93\u3063\u3066, \u306b\u305f\u3044\u3057, \u306b\u5bfe\u3057, \u306b\u305f\u3044\u3057\u3066,
-# \u306b\u5bfe\u3057\u3066, \u306b\u305f\u3044\u3059\u308b, \u306b\u5bfe\u3059\u308b, \u306b\u3064\u3044\u3066, \u306b\u3064\u304d, \u306b\u3064\u3051, \u306b\u3064\u3051\u3066, \u306b\u3064\u308c, \u306b\u3064\u308c\u3066, \u306b\u3068\u3063\u3066,
-# \u306b\u3068\u308a, \u306b\u307e\u3064\u308f\u308b, \u306b\u3088\u3063\u3066, \u306b\u4f9d\u3063\u3066, \u306b\u56e0\u3063\u3066, \u306b\u3088\u308a, \u306b\u4f9d\u308a, \u306b\u56e0\u308a, \u306b\u3088\u308b, \u306b\u4f9d\u308b, \u306b\u56e0\u308b,
-# \u306b\u308f\u305f\u3063\u3066, \u306b\u308f\u305f\u308b, \u3092\u3082\u3063\u3066, \u3092\u4ee5\u3063\u3066, \u3092\u901a\u3058, \u3092\u901a\u3058\u3066, \u3092\u901a\u3057\u3066, \u3092\u3081\u3050\u3063\u3066, \u3092\u3081\u3050\u308a, \u3092\u3081\u3050\u308b,
-# \u3063\u3066-\u53e3\u8a9e/, \u3061\u3085\u3046-\u95a2\u897f\u5f01\u300c\u3068\u3044\u3046\u300d/, (\u4f55) \u3066\u3044\u3046 (\u4eba)-\u53e3\u8a9e/, \u3063\u3066\u3044\u3046-\u53e3\u8a9e/, \u3068\u3044\u3075, \u3068\u304b\u3044\u3075
-\u52a9\u8a5e-\u683c\u52a9\u8a5e-\u9023\u8a9e
-#
-# particle-conjunctive:
-# e.g. \u304b\u3089, \u304b\u3089\u306b\u306f, \u304c, \u3051\u308c\u3069, \u3051\u308c\u3069\u3082, \u3051\u3069, \u3057, \u3064\u3064, \u3066, \u3067, \u3068, \u3068\u3053\u308d\u304c, \u3069\u3053\u308d\u304b, \u3068\u3082, \u3069\u3082,
-# \u306a\u304c\u3089, \u306a\u308a, \u306e\u3067, \u306e\u306b, \u3070, \u3082\u306e\u306e, \u3084 ( \u3057\u305f), \u3084\u3044\u306a\u3084, (\u3053\u308d\u3093) \u3058\u3083(\u3044\u3051\u306a\u3044)-\u53e3\u8a9e/,
-# (\u884c\u3063) \u3061\u3083(\u3044\u3051\u306a\u3044)-\u53e3\u8a9e/, (\u8a00\u3063) \u305f\u3063\u3066 (\u3057\u304b\u305f\u304c\u306a\u3044)-\u53e3\u8a9e/, (\u305d\u308c\u304c\u306a\u304f)\u3063\u305f\u3063\u3066 (\u5e73\u6c17)-\u53e3\u8a9e/
-\u52a9\u8a5e-\u63a5\u7d9a\u52a9\u8a5e
-#
-# particle-dependency:
-# e.g. \u3053\u305d, \u3055\u3048, \u3057\u304b, \u3059\u3089, \u306f, \u3082, \u305e
-\u52a9\u8a5e-\u4fc2\u52a9\u8a5e
-#
-# particle-adverbial:
-# e.g. \u304c\u3066\u3089, \u304b\u3082, \u304f\u3089\u3044, \u4f4d, \u3050\u3089\u3044, \u3057\u3082, (\u5b66\u6821) \u3058\u3083(\u3053\u308c\u304c\u6d41\u884c\u3063\u3066\u3044\u308b)-\u53e3\u8a9e/,
-# (\u305d\u308c)\u3058\u3083\u3042 (\u3088\u304f\u306a\u3044)-\u53e3\u8a9e/, \u305a\u3064, (\u79c1) \u306a\u305e, \u306a\u3069, (\u79c1) \u306a\u308a (\u306b), (\u5148\u751f) \u306a\u3093\u304b (\u5927\u5acc\u3044)-\u53e3\u8a9e/,
-# (\u79c1) \u306a\u3093\u305e, (\u5148\u751f) \u306a\u3093\u3066 (\u5927\u5acc\u3044)-\u53e3\u8a9e/, \u306e\u307f, \u3060\u3051, (\u79c1) \u3060\u3063\u3066-\u53e3\u8a9e/, \u3060\u306b,
-# (\u5f7c)\u3063\u305f\u3089-\u53e3\u8a9e/, (\u304a\u8336) \u3067\u3082 (\u3044\u304b\u304c), \u7b49 (\u3068\u3046), (\u4eca\u5f8c) \u3068\u3082, \u3070\u304b\u308a, \u3070\u3063\u304b-\u53e3\u8a9e/, \u3070\u3063\u304b\u308a-\u53e3\u8a9e/,
-# \u307b\u3069, \u7a0b, \u307e\u3067, \u8fc4, (\u8ab0) \u3082 (\u304c)([\u52a9\u8a5e-\u683c\u52a9\u8a5e] \u304a\u3088\u3073 [\u52a9\u8a5e-\u4fc2\u52a9\u8a5e] \u306e\u524d\u306b\u4f4d\u7f6e\u3059\u308b\u300c\u3082\u300d)
-\u52a9\u8a5e-\u526f\u52a9\u8a5e
-#
-# particle-interjective: particles with interjective grammatical roles.
-# e.g. (\u677e\u5cf6) \u3084
-\u52a9\u8a5e-\u9593\u6295\u52a9\u8a5e
-#
-# particle-coordinate:
-# e.g. \u3068, \u305f\u308a, \u3060\u306e, \u3060\u308a, \u3068\u304b, \u306a\u308a, \u3084, \u3084\u3089
-\u52a9\u8a5e-\u4e26\u7acb\u52a9\u8a5e
-#
-# particle-final:
-# e.g. \u304b\u3044, \u304b\u3057\u3089, \u3055, \u305c, (\u3060)\u3063\u3051-\u53e3\u8a9e/, (\u3068\u307e\u3063\u3066\u308b) \u3067-\u65b9\u8a00/, \u306a, \u30ca, \u306a\u3042-\u53e3\u8a9e/, \u305e, \u306d, \u30cd,
-# \u306d\u3047-\u53e3\u8a9e/, \u306d\u3048-\u53e3\u8a9e/, \u306d\u3093-\u65b9\u8a00/, \u306e, \u306e\u3046-\u53e3\u8a9e/, \u3084, \u3088, \u30e8, \u3088\u3049-\u53e3\u8a9e/, \u308f, \u308f\u3044-\u53e3\u8a9e/
-\u52a9\u8a5e-\u7d42\u52a9\u8a5e
-#
-# particle-adverbial/conjunctive/final: The particle "ka" when unknown whether it is
-# adverbial, conjunctive, or sentence final. For example:
-# (a) \u300cA \u304b B \u304b\u300d. Ex:\u300c(\u56fd\u5185\u3067\u904b\u7528\u3059\u308b) \u304b,(\u6d77\u5916\u3067\u904b\u7528\u3059\u308b) \u304b (.)\u300d
-# (b) Inside an adverb phrase. Ex:\u300c(\u5e78\u3044\u3068\u3044\u3046) \u304b (, \u6b7b\u8005\u306f\u3044\u306a\u304b\u3063\u305f.)\u300d
-# \u300c(\u7948\u308a\u304c\u5c4a\u3044\u305f\u305b\u3044) \u304b (, \u8a66\u9a13\u306b\u5408\u683c\u3057\u305f.)\u300d
-# (c) \u300c\u304b\u306e\u3088\u3046\u306b\u300d. Ex:\u300c(\u4f55\u3082\u306a\u304b\u3063\u305f) \u304b (\u306e\u3088\u3046\u306b\u632f\u308b\u821e\u3063\u305f.)\u300d
-# e.g. \u304b
-\u52a9\u8a5e-\u526f\u52a9\u8a5e\uff0f\u4e26\u7acb\u52a9\u8a5e\uff0f\u7d42\u52a9\u8a5e
-#
-# particle-adnominalizer: The "no" that attaches to nouns and modifies
-# non-inflectional words.
-\u52a9\u8a5e-\u9023\u4f53\u5316
-#
-# particle-adnominalizer: The "ni" and "to" that appear following nouns and adverbs
-# that are giongo, giseigo, or gitaigo.
-# e.g. \u306b, \u3068
-\u52a9\u8a5e-\u526f\u8a5e\u5316
-#
-# 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. \u304b\u306a, \u3051\u3080, ( \u3057\u305f\u3060\u308d\u3046) \u306b, (\u3042\u3093\u305f) \u306b\u3083(\u308f\u304b\u3089\u3093), (\u4ffa) \u3093 (\u5bb6)
-\u52a9\u8a5e-\u7279\u6b8a
-#
-#####
-# auxiliary-verb:
-\u52a9\u52d5\u8a5e
-#
-#####
-# interjection: Greetings and other exclamations.
-# e.g. \u304a\u306f\u3088\u3046, \u304a\u306f\u3088\u3046\u3054\u3056\u3044\u307e\u3059, \u3053\u3093\u306b\u3061\u306f, \u3053\u3093\u3070\u3093\u306f, \u3042\u308a\u304c\u3068\u3046, \u3069\u3046\u3082\u3042\u308a\u304c\u3068\u3046, \u3042\u308a\u304c\u3068\u3046\u3054\u3056\u3044\u307e\u3059,
-# \u3044\u305f\u3060\u304d\u307e\u3059, \u3054\u3061\u305d\u3046\u3055\u307e, \u3055\u3088\u306a\u3089, \u3055\u3088\u3046\u306a\u3089, \u306f\u3044, \u3044\u3044\u3048, \u3054\u3081\u3093, \u3054\u3081\u3093\u306a\u3055\u3044
-#\u611f\u52d5\u8a5e
-#
-#####
-# symbol: unclassified Symbols.
-\u8a18\u53f7
-#
-# symbol-misc: A general symbol not in one of the categories below.
-# e.g. [\u25cb\u25ce@$\u3012\u2192+]
-\u8a18\u53f7-\u4e00\u822c
-#
-# symbol-comma: Commas
-# e.g. [,\u3001]
-\u8a18\u53f7-\u8aad\u70b9
-#
-# symbol-period: Periods and full stops.
-# e.g. [.\uff0e\u3002]
-\u8a18\u53f7-\u53e5\u70b9
-#
-# symbol-space: Full-width whitespace.
-\u8a18\u53f7-\u7a7a\u767d
-#
-# symbol-open_bracket:
-# e.g. [({\u2018\u201c\u300e\u3010]
-\u8a18\u53f7-\u62ec\u5f27\u958b
-#
-# symbol-close_bracket:
-# e.g. [)}\u2019\u201d\u300f\u300d\u3011]
-\u8a18\u53f7-\u62ec\u5f27\u9589
-#
-# symbol-alphabetic:
-#\u8a18\u53f7-\u30a2\u30eb\u30d5\u30a1\u30d9\u30c3\u30c8
-#
-#####
-# other: unclassified other
-#\u305d\u306e\u4ed6
-#
-# other-interjection: Words that are hard to classify as noun-suffixes or
-# sentence-final particles.
-# e.g. (\u3060)\u30a1
-\u305d\u306e\u4ed6-\u9593\u6295
-#
-#####
-# filler: Aizuchi that occurs during a conversation or sounds inserted as filler.
-# e.g. \u3042\u306e, \u3046\u3093\u3068, \u3048\u3068
-\u30d5\u30a3\u30e9\u30fc
-#
-#####
-# non-verbal: non-verbal sound.
-\u975e\u8a00\u8a9e\u97f3
-#
-#####
-# fragment:
-#\u8a9e\u65ad\u7247
-#
-#####
-# unknown: unknown part of speech.
-#\u672a\u77e5\u8a9e
-#
-##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ar.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ar.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ar.txt
deleted file mode 100644
index 046829d..0000000
--- a/solr/example/example-DIH/solr/rss/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 \u0623 and \u0627
-\u0645\u0646
-\u0648\u0645\u0646
-\u0645\u0646\u0647\u0627
-\u0645\u0646\u0647
-\u0641\u064a
-\u0648\u0641\u064a
-\u0641\u064a\u0647\u0627
-\u0641\u064a\u0647
-\u0648
-\u0641
-\u062b\u0645
-\u0627\u0648
-\u0623\u0648
-\u0628
-\u0628\u0647\u0627
-\u0628\u0647
-\u0627
-\u0623
-\u0627\u0649
-\u0627\u064a
-\u0623\u064a
-\u0623\u0649
-\u0644\u0627
-\u0648\u0644\u0627
-\u0627\u0644\u0627
-\u0623\u0644\u0627
-\u0625\u0644\u0627
-\u0644\u0643\u0646
-\u0645\u0627
-\u0648\u0645\u0627
-\u0643\u0645\u0627
-\u0641\u0645\u0627
-\u0639\u0646
-\u0645\u0639
-\u0627\u0630\u0627
-\u0625\u0630\u0627
-\u0627\u0646
-\u0623\u0646
-\u0625\u0646
-\u0627\u0646\u0647\u0627
-\u0623\u0646\u0647\u0627
-\u0625\u0646\u0647\u0627
-\u0627\u0646\u0647
-\u0623\u0646\u0647
-\u0625\u0646\u0647
-\u0628\u0627\u0646
-\u0628\u0623\u0646
-\u0641\u0627\u0646
-\u0641\u0623\u0646
-\u0648\u0627\u0646
-\u0648\u0623\u0646
-\u0648\u0625\u0646
-\u0627\u0644\u062a\u0649
-\u0627\u0644\u062a\u064a
-\u0627\u0644\u0630\u0649
-\u0627\u0644\u0630\u064a
-\u0627\u0644\u0630\u064a\u0646
-\u0627\u0644\u0649
-\u0627\u0644\u064a
-\u0625\u0644\u0649
-\u0625\u0644\u064a
-\u0639\u0644\u0649
-\u0639\u0644\u064a\u0647\u0627
-\u0639\u0644\u064a\u0647
-\u0627\u0645\u0627
-\u0623\u0645\u0627
-\u0625\u0645\u0627
-\u0627\u064a\u0636\u0627
-\u0623\u064a\u0636\u0627
-\u0643\u0644
-\u0648\u0643\u0644
-\u0644\u0645
-\u0648\u0644\u0645
-\u0644\u0646
-\u0648\u0644\u0646
-\u0647\u0649
-\u0647\u064a
-\u0647\u0648
-\u0648\u0647\u0649
-\u0648\u0647\u064a
-\u0648\u0647\u0648
-\u0641\u0647\u0649
-\u0641\u0647\u064a
-\u0641\u0647\u0648
-\u0627\u0646\u062a
-\u0623\u0646\u062a
-\u0644\u0643
-\u0644\u0647\u0627
-\u0644\u0647
-\u0647\u0630\u0647
-\u0647\u0630\u0627
-\u062a\u0644\u0643
-\u0630\u0644\u0643
-\u0647\u0646\u0627\u0643
-\u0643\u0627\u0646\u062a
-\u0643\u0627\u0646
-\u064a\u0643\u0648\u0646
-\u062a\u0643\u0648\u0646
-\u0648\u0643\u0627\u0646\u062a
-\u0648\u0643\u0627\u0646
-\u063a\u064a\u0631
-\u0628\u0639\u0636
-\u0642\u062f
-\u0646\u062d\u0648
-\u0628\u064a\u0646
-\u0628\u064a\u0646\u0645\u0627
-\u0645\u0646\u0630
-\u0636\u0645\u0646
-\u062d\u064a\u062b
-\u0627\u0644\u0627\u0646
-\u0627\u0644\u0622\u0646
-\u062e\u0644\u0627\u0644
-\u0628\u0639\u062f
-\u0642\u0628\u0644
-\u062d\u062a\u0649
-\u0639\u0646\u062f
-\u0639\u0646\u062f\u0645\u0627
-\u0644\u062f\u0649
-\u062c\u0645\u064a\u0639
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_bg.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_bg.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_bg.txt
deleted file mode 100644
index 1ae4ba2..0000000
--- a/solr/example/example-DIH/solr/rss/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
-\u0430
-\u0430\u0437
-\u0430\u043a\u043e
-\u0430\u043b\u0430
-\u0431\u0435
-\u0431\u0435\u0437
-\u0431\u0435\u0448\u0435
-\u0431\u0438
-\u0431\u0438\u043b
-\u0431\u0438\u043b\u0430
-\u0431\u0438\u043b\u0438
-\u0431\u0438\u043b\u043e
-\u0431\u043b\u0438\u0437\u043e
-\u0431\u044a\u0434\u0430\u0442
-\u0431\u044a\u0434\u0435
-\u0431\u044f\u0445\u0430
-\u0432
-\u0432\u0430\u0441
-\u0432\u0430\u0448
-\u0432\u0430\u0448\u0430
-\u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e
-\u0432\u0435\u0447\u0435
-\u0432\u0437\u0435\u043c\u0430
-\u0432\u0438
-\u0432\u0438\u0435
-\u0432\u0438\u043d\u0430\u0433\u0438
-\u0432\u0441\u0435
-\u0432\u0441\u0435\u043a\u0438
-\u0432\u0441\u0438\u0447\u043a\u0438
-\u0432\u0441\u0438\u0447\u043a\u043e
-\u0432\u0441\u044f\u043a\u0430
-\u0432\u044a\u0432
-\u0432\u044a\u043f\u0440\u0435\u043a\u0438
-\u0432\u044a\u0440\u0445\u0443
-\u0433
-\u0433\u0438
-\u0433\u043b\u0430\u0432\u043d\u043e
-\u0433\u043e
-\u0434
-\u0434\u0430
-\u0434\u0430\u043b\u0438
-\u0434\u043e
-\u0434\u043e\u043a\u0430\u0442\u043e
-\u0434\u043e\u043a\u043e\u0433\u0430
-\u0434\u043e\u0440\u0438
-\u0434\u043e\u0441\u0435\u0433\u0430
-\u0434\u043e\u0441\u0442\u0430
-\u0435
-\u0435\u0434\u0432\u0430
-\u0435\u0434\u0438\u043d
-\u0435\u0442\u043e
-\u0437\u0430
-\u0437\u0430\u0434
-\u0437\u0430\u0435\u0434\u043d\u043e
-\u0437\u0430\u0440\u0430\u0434\u0438
-\u0437\u0430\u0441\u0435\u0433\u0430
-\u0437\u0430\u0442\u043e\u0432\u0430
-\u0437\u0430\u0449\u043e
-\u0437\u0430\u0449\u043e\u0442\u043e
-\u0438
-\u0438\u0437
-\u0438\u043b\u0438
-\u0438\u043c
-\u0438\u043c\u0430
-\u0438\u043c\u0430\u0442
-\u0438\u0441\u043a\u0430
-\u0439
-\u043a\u0430\u0437\u0430
-\u043a\u0430\u043a
-\u043a\u0430\u043a\u0432\u0430
-\u043a\u0430\u043a\u0432\u043e
-\u043a\u0430\u043a\u0442\u043e
-\u043a\u0430\u043a\u044a\u0432
-\u043a\u0430\u0442\u043e
-\u043a\u043e\u0433\u0430
-\u043a\u043e\u0433\u0430\u0442\u043e
-\u043a\u043e\u0435\u0442\u043e
-\u043a\u043e\u0438\u0442\u043e
-\u043a\u043e\u0439
-\u043a\u043e\u0439\u0442\u043e
-\u043a\u043e\u043b\u043a\u043e
-\u043a\u043e\u044f\u0442\u043e
-\u043a\u044a\u0434\u0435
-\u043a\u044a\u0434\u0435\u0442\u043e
-\u043a\u044a\u043c
-\u043b\u0438
-\u043c
-\u043c\u0435
-\u043c\u0435\u0436\u0434\u0443
-\u043c\u0435\u043d
-\u043c\u0438
-\u043c\u043d\u043e\u0437\u0438\u043d\u0430
-\u043c\u043e\u0433\u0430
-\u043c\u043e\u0433\u0430\u0442
-\u043c\u043e\u0436\u0435
-\u043c\u043e\u043b\u044f
-\u043c\u043e\u043c\u0435\u043d\u0442\u0430
-\u043c\u0443
-\u043d
-\u043d\u0430
-\u043d\u0430\u0434
-\u043d\u0430\u0437\u0430\u0434
-\u043d\u0430\u0439
-\u043d\u0430\u043f\u0440\u0430\u0432\u0438
-\u043d\u0430\u043f\u0440\u0435\u0434
-\u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440
-\u043d\u0430\u0441
-\u043d\u0435
-\u043d\u0435\u0433\u043e
-\u043d\u0435\u044f
-\u043d\u0438
-\u043d\u0438\u0435
-\u043d\u0438\u043a\u043e\u0439
-\u043d\u0438\u0442\u043e
-\u043d\u043e
-\u043d\u044f\u043a\u043e\u0438
-\u043d\u044f\u043a\u043e\u0439
-\u043d\u044f\u043c\u0430
-\u043e\u0431\u0430\u0447\u0435
-\u043e\u043a\u043e\u043b\u043e
-\u043e\u0441\u0432\u0435\u043d
-\u043e\u0441\u043e\u0431\u0435\u043d\u043e
-\u043e\u0442
-\u043e\u0442\u0433\u043e\u0440\u0435
-\u043e\u0442\u043d\u043e\u0432\u043e
-\u043e\u0449\u0435
-\u043f\u0430\u043a
-\u043f\u043e
-\u043f\u043e\u0432\u0435\u0447\u0435
-\u043f\u043e\u0432\u0435\u0447\u0435\u0442\u043e
-\u043f\u043e\u0434
-\u043f\u043e\u043d\u0435
-\u043f\u043e\u0440\u0430\u0434\u0438
-\u043f\u043e\u0441\u043b\u0435
-\u043f\u043e\u0447\u0442\u0438
-\u043f\u0440\u0430\u0432\u0438
-\u043f\u0440\u0435\u0434
-\u043f\u0440\u0435\u0434\u0438
-\u043f\u0440\u0435\u0437
-\u043f\u0440\u0438
-\u043f\u044a\u043a
-\u043f\u044a\u0440\u0432\u043e
-\u0441
-\u0441\u0430
-\u0441\u0430\u043c\u043e
-\u0441\u0435
-\u0441\u0435\u0433\u0430
-\u0441\u0438
-\u0441\u043a\u043e\u0440\u043e
-\u0441\u043b\u0435\u0434
-\u0441\u043c\u0435
-\u0441\u043f\u043e\u0440\u0435\u0434
-\u0441\u0440\u0435\u0434
-\u0441\u0440\u0435\u0449\u0443
-\u0441\u0442\u0435
-\u0441\u044a\u043c
-\u0441\u044a\u0441
-\u0441\u044a\u0449\u043e
-\u0442
-\u0442\u0430\u0437\u0438
-\u0442\u0430\u043a\u0430
-\u0442\u0430\u043a\u0438\u0432\u0430
-\u0442\u0430\u043a\u044a\u0432
-\u0442\u0430\u043c
-\u0442\u0432\u043e\u0439
-\u0442\u0435
-\u0442\u0435\u0437\u0438
-\u0442\u0438
-\u0442\u043d
-\u0442\u043e
-\u0442\u043e\u0432\u0430
-\u0442\u043e\u0433\u0430\u0432\u0430
-\u0442\u043e\u0437\u0438
-\u0442\u043e\u0439
-\u0442\u043e\u043b\u043a\u043e\u0432\u0430
-\u0442\u043e\u0447\u043d\u043e
-\u0442\u0440\u044f\u0431\u0432\u0430
-\u0442\u0443\u043a
-\u0442\u044a\u0439
-\u0442\u044f
-\u0442\u044f\u0445
-\u0443
-\u0445\u0430\u0440\u0435\u0441\u0432\u0430
-\u0447
-\u0447\u0435
-\u0447\u0435\u0441\u0442\u043e
-\u0447\u0440\u0435\u0437
-\u0449\u0435
-\u0449\u043e\u043c
-\u044f
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ca.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ca.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ca.txt
deleted file mode 100644
index 3da65de..0000000
--- a/solr/example/example-DIH/solr/rss/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
-ac�
-ah
-aix�
-aix�
-al
-als
-aleshores
-algun
-alguna
-algunes
-alguns
-alhora
-all�
-all�
-all�
-altra
-altre
-altres
-amb
-ambd�s
-ambdues
-apa
-aquell
-aquella
-aquelles
-aquells
-aquest
-aquesta
-aquestes
-aquests
-aqu�
-baix
-cada
-cadasc�
-cadascuna
-cadascunes
-cadascuns
-com
-contra
-d'un
-d'una
-d'unes
-d'uns
-dalt
-de
-del
-dels
-des
-despr�s
-dins
-dintre
-donat
-doncs
-durant
-e
-eh
-el
-els
-em
-en
-encara
-ens
-entre
-�rem
-eren
-�reu
-es
-�s
-esta
-est�
-est�vem
-estaven
-est�veu
-esteu
-et
-etc
-ets
-fins
-fora
-gaireb�
-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
-m�s
-meu
-meus
-meva
-meves
-molt
-molta
-moltes
-molts
-mon
-mons
-n'he
-n'hi
-ne
-ni
-no
-nogensmenys
-nom�s
-nosaltres
-nostra
-nostre
-nostres
-o
-oh
-oi
-on
-pas
-pel
-pels
-per
-per�
-perqu�
-poc
-poca
-pocs
-poques
-potser
-propi
-qual
-quals
-quan
-quant
-que
-qu�
-quelcom
-qui
-quin
-quina
-quines
-quins
-s'ha
-s'han
-sa
-semblant
-semblants
-ses
-seu
-seus
-seva
-seva
-seves
-si
-sobre
-sobretot
-s�c
-solament
-sols
-son
-s�n
-sons
-sota
-sou
-t'ha
-t'han
-t'he
-ta
-tal
-tamb�
-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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ckb.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ckb.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ckb.txt
deleted file mode 100644
index 87abf11..0000000
--- a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ckb.txt
+++ /dev/null
@@ -1,136 +0,0 @@
-# set of kurdish stopwords
-# note these have been normalized with our scheme (e represented with U+06D5, etc)
-# constructed from:
-# * Fig 5 of "Building A Test Collection For Sorani Kurdish" (Esmaili et al)
-# * "Sorani Kurdish: A Reference Grammar with selected readings" (Thackston)
-# * Corpus-based analysis of 77M word Sorani collection: wikipedia, news, blogs, etc
-
-# and
-\u0648
-# which
-\u06a9\u06d5
-# of
-\u06cc
-# made/did
-\u06a9\u0631\u062f
-# that/which
-\u0626\u06d5\u0648\u06d5\u06cc
-# on/head
-\u0633\u06d5\u0631
-# two
-\u062f\u0648\u0648
-# also
-\u0647\u06d5\u0631\u0648\u06d5\u0647\u0627
-# from/that
-\u0644\u06d5\u0648
-# makes/does
-\u062f\u06d5\u06a9\u0627\u062a
-# some
-\u0686\u06d5\u0646\u062f
-# every
-\u0647\u06d5\u0631
-
-# demonstratives
-# that
-\u0626\u06d5\u0648
-# this
-\u0626\u06d5\u0645
-
-# personal pronouns
-# I
-\u0645\u0646
-# we
-\u0626\u06ce\u0645\u06d5
-# you
-\u062a\u06c6
-# you
-\u0626\u06ce\u0648\u06d5
-# he/she/it
-\u0626\u06d5\u0648
-# they
-\u0626\u06d5\u0648\u0627\u0646
-
-# prepositions
-# to/with/by
-\u0628\u06d5
-\u067e\u06ce
-# without
-\u0628\u06d5\u0628\u06ce
-# along with/while/during
-\u0628\u06d5\u062f\u06d5\u0645
-# in the opinion of
-\u0628\u06d5\u0644\u0627\u06cc
-# according to
-\u0628\u06d5\u067e\u06ce\u06cc
-# before
-\u0628\u06d5\u0631\u0644\u06d5
-# in the direction of
-\u0628\u06d5\u0631\u06d5\u0648\u06cc
-# in front of/toward
-\u0628\u06d5\u0631\u06d5\u0648\u06d5
-# before/in the face of
-\u0628\u06d5\u0631\u062f\u06d5\u0645
-# without
-\u0628\u06ce
-# except for
-\u0628\u06ce\u062c\u06af\u06d5
-# for
-\u0628\u06c6
-# on/in
-\u062f\u06d5
-\u062a\u06ce
-# with
-\u062f\u06d5\u06af\u06d5\u06b5
-# after
-\u062f\u0648\u0627\u06cc
-# except for/aside from
-\u062c\u06af\u06d5
-# in/from
-\u0644\u06d5
-\u0644\u06ce
-# in front of/before/because of
-\u0644\u06d5\u0628\u06d5\u0631
-# between/among
-\u0644\u06d5\u0628\u06d5\u06cc\u0646\u06cc
-# concerning/about
-\u0644\u06d5\u0628\u0627\u0628\u06d5\u062a
-# concerning
-\u0644\u06d5\u0628\u0627\u0631\u06d5\u06cc
-# instead of
-\u0644\u06d5\u0628\u0627\u062a\u06cc
-# beside
-\u0644\u06d5\u0628\u0646
-# instead of
-\u0644\u06d5\u0628\u0631\u06ce\u062a\u06cc
-# behind
-\u0644\u06d5\u062f\u06d5\u0645
-# with/together with
-\u0644\u06d5\u06af\u06d5\u06b5
-# by
-\u0644\u06d5\u0644\u0627\u06cc\u06d5\u0646
-# within
-\u0644\u06d5\u0646\u0627\u0648
-# between/among
-\u0644\u06d5\u0646\u06ce\u0648
-# for the sake of
-\u0644\u06d5\u067e\u06ce\u0646\u0627\u0648\u06cc
-# with respect to
-\u0644\u06d5\u0631\u06d5\u0648\u06cc
-# by means of/for
-\u0644\u06d5\u0631\u06ce
-# for the sake of
-\u0644\u06d5\u0631\u06ce\u06af\u0627
-# on/on top of/according to
-\u0644\u06d5\u0633\u06d5\u0631
-# under
-\u0644\u06d5\u0698\u06ce\u0631
-# between/among
-\u0646\u0627\u0648
-# between/among
-\u0646\u06ce\u0648\u0627\u0646
-# after
-\u067e\u0627\u0634
-# before
-\u067e\u06ce\u0634
-# like
-\u0648\u06d5\u06a9
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_cz.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_cz.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_cz.txt
deleted file mode 100644
index 53c6097..0000000
--- a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_cz.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-a
-s
-k
-o
-i
-u
-v
-z
-dnes
-cz
-t�mto
-bude\u0161
-budem
-byli
-jse\u0161
-m\u016fj
-sv�m
-ta
-tomto
-tohle
-tuto
-tyto
-jej
-zda
-pro\u010d
-m�te
-tato
-kam
-tohoto
-kdo
-kte\u0159�
-mi
-n�m
-tom
-tomuto
-m�t
-nic
-proto
-kterou
-byla
-toho
-proto\u017ee
-asi
-ho
-na\u0161i
-napi\u0161te
-re
-co\u017e
-t�m
-tak\u017ee
-sv�ch
-jej�
-sv�mi
-jste
-aj
-tu
-tedy
-teto
-bylo
-kde
-ke
-prav�
-ji
-nad
-nejsou
-\u010di
-pod
-t�ma
-mezi
-p\u0159es
-ty
-pak
-v�m
-ani
-kdy\u017e
-v\u0161ak
-neg
-jsem
-tento
-\u010dl�nku
-\u010dl�nky
-aby
-jsme
-p\u0159ed
-pta
-jejich
-byl
-je\u0161t\u011b
-a\u017e
-bez
-tak�
-pouze
-prvn�
-va\u0161e
-kter�
-n�s
-nov�
-tipy
-pokud
-m\u016f\u017ee
-strana
-jeho
-sv�
-jin�
-zpr�vy
-nov�
-nen�
-v�s
-jen
-podle
-zde
-u\u017e
-b�t
-v�ce
-bude
-ji\u017e
-ne\u017e
-kter�
-by
-kter�
-co
-nebo
-ten
-tak
-m�
-p\u0159i
-od
-po
-jsou
-jak
-dal\u0161�
-ale
-si
-se
-ve
-to
-jako
-za
-zp\u011bt
-ze
-do
-pro
-je
-na
-atd
-atp
-jakmile
-p\u0159i\u010dem\u017e
-j�
-on
-ona
-ono
-oni
-ony
-my
-vy
-j�
-ji
-m\u011b
-mne
-jemu
-tomu
-t\u011bm
-t\u011bmu
-n\u011bmu
-n\u011bmu\u017e
-jeho\u017e
-j�\u017e
-jeliko\u017e
-je\u017e
-jako\u017e
-na\u010de\u017e
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_da.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_da.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_da.txt
deleted file mode 100644
index 42e6145..0000000
--- a/solr/example/example-DIH/solr/rss/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
-p� | 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
-n�r | when
-v�re | 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
-ogs� | 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
-v�ret | be
-thi | for (conj)
-jer | you
-s�dan | such, like this/like that
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_de.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_de.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_de.txt
deleted file mode 100644
index 86525e7..0000000
--- a/solr/example/example-DIH/solr/rss/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
-
-da� | 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
-
-f�r | 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
-
-k�nnen | can
-k�nnte | 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
-�ber | over
-um | about, around
-und | and
-
-uns | us
-unse
-unsem
-unsen
-unser
-unses
-
-unter | under
-viel | much
-vom | von + dem
-von | from
-vor | before
-w�hrend | 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
-w�rde | would
-w�rden | would
-zu | to
-zum | zu + dem
-zur | zu + der
-zwar | indeed
-zwischen | between
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_el.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_el.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_el.txt
deleted file mode 100644
index 232681f..0000000
--- a/solr/example/example-DIH/solr/rss/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 '\u03c3' instead of '\u03c2'
-\u03bf
-\u03b7
-\u03c4\u03bf
-\u03bf\u03b9
-\u03c4\u03b1
-\u03c4\u03bf\u03c5
-\u03c4\u03b7\u03c3
-\u03c4\u03c9\u03bd
-\u03c4\u03bf\u03bd
-\u03c4\u03b7\u03bd
-\u03ba\u03b1\u03b9
-\u03ba\u03b9
-\u03ba
-\u03b5\u03b9\u03bc\u03b1\u03b9
-\u03b5\u03b9\u03c3\u03b1\u03b9
-\u03b5\u03b9\u03bd\u03b1\u03b9
-\u03b5\u03b9\u03bc\u03b1\u03c3\u03c4\u03b5
-\u03b5\u03b9\u03c3\u03c4\u03b5
-\u03c3\u03c4\u03bf
-\u03c3\u03c4\u03bf\u03bd
-\u03c3\u03c4\u03b7
-\u03c3\u03c4\u03b7\u03bd
-\u03bc\u03b1
-\u03b1\u03bb\u03bb\u03b1
-\u03b1\u03c0\u03bf
-\u03b3\u03b9\u03b1
-\u03c0\u03c1\u03bf\u03c3
-\u03bc\u03b5
-\u03c3\u03b5
-\u03c9\u03c3
-\u03c0\u03b1\u03c1\u03b1
-\u03b1\u03bd\u03c4\u03b9
-\u03ba\u03b1\u03c4\u03b1
-\u03bc\u03b5\u03c4\u03b1
-\u03b8\u03b1
-\u03bd\u03b1
-\u03b4\u03b5
-\u03b4\u03b5\u03bd
-\u03bc\u03b7
-\u03bc\u03b7\u03bd
-\u03b5\u03c0\u03b9
-\u03b5\u03bd\u03c9
-\u03b5\u03b1\u03bd
-\u03b1\u03bd
-\u03c4\u03bf\u03c4\u03b5
-\u03c0\u03bf\u03c5
-\u03c0\u03c9\u03c3
-\u03c0\u03bf\u03b9\u03bf\u03c3
-\u03c0\u03bf\u03b9\u03b1
-\u03c0\u03bf\u03b9\u03bf
-\u03c0\u03bf\u03b9\u03bf\u03b9
-\u03c0\u03bf\u03b9\u03b5\u03c3
-\u03c0\u03bf\u03b9\u03c9\u03bd
-\u03c0\u03bf\u03b9\u03bf\u03c5\u03c3
-\u03b1\u03c5\u03c4\u03bf\u03c3
-\u03b1\u03c5\u03c4\u03b7
-\u03b1\u03c5\u03c4\u03bf
-\u03b1\u03c5\u03c4\u03bf\u03b9
-\u03b1\u03c5\u03c4\u03c9\u03bd
-\u03b1\u03c5\u03c4\u03bf\u03c5\u03c3
-\u03b1\u03c5\u03c4\u03b5\u03c3
-\u03b1\u03c5\u03c4\u03b1
-\u03b5\u03ba\u03b5\u03b9\u03bd\u03bf\u03c3
-\u03b5\u03ba\u03b5\u03b9\u03bd\u03b7
-\u03b5\u03ba\u03b5\u03b9\u03bd\u03bf
-\u03b5\u03ba\u03b5\u03b9\u03bd\u03bf\u03b9
-\u03b5\u03ba\u03b5\u03b9\u03bd\u03b5\u03c3
-\u03b5\u03ba\u03b5\u03b9\u03bd\u03b1
-\u03b5\u03ba\u03b5\u03b9\u03bd\u03c9\u03bd
-\u03b5\u03ba\u03b5\u03b9\u03bd\u03bf\u03c5\u03c3
-\u03bf\u03c0\u03c9\u03c3
-\u03bf\u03bc\u03c9\u03c3
-\u03b9\u03c3\u03c9\u03c3
-\u03bf\u03c3\u03bf
-\u03bf\u03c4\u03b9
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_en.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_en.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_en.txt
deleted file mode 100644
index 2c164c0..0000000
--- a/solr/example/example-DIH/solr/rss/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
[3/6] lucene-solr:master: SOLR-7383: Replace DIH 'rss' example with
'atom' rss example was broken for multiple reasons. atom example showcases
the same - and more - features and uses the smallest config file needed to
make it work.
Posted by ar...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/mapping-FoldToASCII.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/mapping-FoldToASCII.txt b/solr/example/example-DIH/solr/rss/conf/mapping-FoldToASCII.txt
deleted file mode 100644
index 9a84b6e..0000000
--- a/solr/example/example-DIH/solr/rss/conf/mapping-FoldToASCII.txt
+++ /dev/null
@@ -1,3813 +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.
-
-
-# This map converts alphabetic, numeric, and symbolic Unicode characters
-# which are not in the first 127 ASCII characters (the "Basic Latin" Unicode
-# block) into their ASCII equivalents, if one exists.
-#
-# Characters from the following Unicode blocks are converted; however, only
-# those characters with reasonable ASCII alternatives are converted:
-#
-# - C1 Controls and Latin-1 Supplement: http://www.unicode.org/charts/PDF/U0080.pdf
-# - Latin Extended-A: http://www.unicode.org/charts/PDF/U0100.pdf
-# - Latin Extended-B: http://www.unicode.org/charts/PDF/U0180.pdf
-# - Latin Extended Additional: http://www.unicode.org/charts/PDF/U1E00.pdf
-# - Latin Extended-C: http://www.unicode.org/charts/PDF/U2C60.pdf
-# - Latin Extended-D: http://www.unicode.org/charts/PDF/UA720.pdf
-# - IPA Extensions: http://www.unicode.org/charts/PDF/U0250.pdf
-# - Phonetic Extensions: http://www.unicode.org/charts/PDF/U1D00.pdf
-# - Phonetic Extensions Supplement: http://www.unicode.org/charts/PDF/U1D80.pdf
-# - General Punctuation: http://www.unicode.org/charts/PDF/U2000.pdf
-# - Superscripts and Subscripts: http://www.unicode.org/charts/PDF/U2070.pdf
-# - Enclosed Alphanumerics: http://www.unicode.org/charts/PDF/U2460.pdf
-# - Dingbats: http://www.unicode.org/charts/PDF/U2700.pdf
-# - Supplemental Punctuation: http://www.unicode.org/charts/PDF/U2E00.pdf
-# - Alphabetic Presentation Forms: http://www.unicode.org/charts/PDF/UFB00.pdf
-# - Halfwidth and Fullwidth Forms: http://www.unicode.org/charts/PDF/UFF00.pdf
-#
-# See: http://en.wikipedia.org/wiki/Latin_characters_in_Unicode
-#
-# The set of character conversions supported by this map is a superset of
-# those supported by the map represented by mapping-ISOLatin1Accent.txt.
-#
-# See the bottom of this file for the Perl script used to generate the contents
-# of this file (without this header) from ASCIIFoldingFilter.java.
-
-
-# Syntax:
-# "source" => "target"
-# "source".length() > 0 (source cannot be empty.)
-# "target".length() >= 0 (target can be empty.)
-
-
-# � [LATIN CAPITAL LETTER A WITH GRAVE]
-"\u00C0" => "A"
-
-# � [LATIN CAPITAL LETTER A WITH ACUTE]
-"\u00C1" => "A"
-
-# � [LATIN CAPITAL LETTER A WITH CIRCUMFLEX]
-"\u00C2" => "A"
-
-# � [LATIN CAPITAL LETTER A WITH TILDE]
-"\u00C3" => "A"
-
-# � [LATIN CAPITAL LETTER A WITH DIAERESIS]
-"\u00C4" => "A"
-
-# � [LATIN CAPITAL LETTER A WITH RING ABOVE]
-"\u00C5" => "A"
-
-# \u0100 [LATIN CAPITAL LETTER A WITH MACRON]
-"\u0100" => "A"
-
-# \u0102 [LATIN CAPITAL LETTER A WITH BREVE]
-"\u0102" => "A"
-
-# \u0104 [LATIN CAPITAL LETTER A WITH OGONEK]
-"\u0104" => "A"
-
-# \u018f http://en.wikipedia.org/wiki/Schwa [LATIN CAPITAL LETTER SCHWA]
-"\u018F" => "A"
-
-# \u01cd [LATIN CAPITAL LETTER A WITH CARON]
-"\u01CD" => "A"
-
-# \u01de [LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON]
-"\u01DE" => "A"
-
-# \u01e0 [LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON]
-"\u01E0" => "A"
-
-# \u01fa [LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE]
-"\u01FA" => "A"
-
-# \u0200 [LATIN CAPITAL LETTER A WITH DOUBLE GRAVE]
-"\u0200" => "A"
-
-# \u0202 [LATIN CAPITAL LETTER A WITH INVERTED BREVE]
-"\u0202" => "A"
-
-# \u0226 [LATIN CAPITAL LETTER A WITH DOT ABOVE]
-"\u0226" => "A"
-
-# \u023a [LATIN CAPITAL LETTER A WITH STROKE]
-"\u023A" => "A"
-
-# \u1d00 [LATIN LETTER SMALL CAPITAL A]
-"\u1D00" => "A"
-
-# \u1e00 [LATIN CAPITAL LETTER A WITH RING BELOW]
-"\u1E00" => "A"
-
-# \u1ea0 [LATIN CAPITAL LETTER A WITH DOT BELOW]
-"\u1EA0" => "A"
-
-# \u1ea2 [LATIN CAPITAL LETTER A WITH HOOK ABOVE]
-"\u1EA2" => "A"
-
-# \u1ea4 [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE]
-"\u1EA4" => "A"
-
-# \u1ea6 [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE]
-"\u1EA6" => "A"
-
-# \u1ea8 [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
-"\u1EA8" => "A"
-
-# \u1eaa [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE]
-"\u1EAA" => "A"
-
-# \u1eac [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
-"\u1EAC" => "A"
-
-# \u1eae [LATIN CAPITAL LETTER A WITH BREVE AND ACUTE]
-"\u1EAE" => "A"
-
-# \u1eb0 [LATIN CAPITAL LETTER A WITH BREVE AND GRAVE]
-"\u1EB0" => "A"
-
-# \u1eb2 [LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE]
-"\u1EB2" => "A"
-
-# \u1eb4 [LATIN CAPITAL LETTER A WITH BREVE AND TILDE]
-"\u1EB4" => "A"
-
-# \u1eb6 [LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW]
-"\u1EB6" => "A"
-
-# \u24b6 [CIRCLED LATIN CAPITAL LETTER A]
-"\u24B6" => "A"
-
-# \uff21 [FULLWIDTH LATIN CAPITAL LETTER A]
-"\uFF21" => "A"
-
-# � [LATIN SMALL LETTER A WITH GRAVE]
-"\u00E0" => "a"
-
-# � [LATIN SMALL LETTER A WITH ACUTE]
-"\u00E1" => "a"
-
-# � [LATIN SMALL LETTER A WITH CIRCUMFLEX]
-"\u00E2" => "a"
-
-# � [LATIN SMALL LETTER A WITH TILDE]
-"\u00E3" => "a"
-
-# � [LATIN SMALL LETTER A WITH DIAERESIS]
-"\u00E4" => "a"
-
-# � [LATIN SMALL LETTER A WITH RING ABOVE]
-"\u00E5" => "a"
-
-# \u0101 [LATIN SMALL LETTER A WITH MACRON]
-"\u0101" => "a"
-
-# \u0103 [LATIN SMALL LETTER A WITH BREVE]
-"\u0103" => "a"
-
-# \u0105 [LATIN SMALL LETTER A WITH OGONEK]
-"\u0105" => "a"
-
-# \u01ce [LATIN SMALL LETTER A WITH CARON]
-"\u01CE" => "a"
-
-# \u01df [LATIN SMALL LETTER A WITH DIAERESIS AND MACRON]
-"\u01DF" => "a"
-
-# \u01e1 [LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON]
-"\u01E1" => "a"
-
-# \u01fb [LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE]
-"\u01FB" => "a"
-
-# \u0201 [LATIN SMALL LETTER A WITH DOUBLE GRAVE]
-"\u0201" => "a"
-
-# \u0203 [LATIN SMALL LETTER A WITH INVERTED BREVE]
-"\u0203" => "a"
-
-# \u0227 [LATIN SMALL LETTER A WITH DOT ABOVE]
-"\u0227" => "a"
-
-# \u0250 [LATIN SMALL LETTER TURNED A]
-"\u0250" => "a"
-
-# \u0259 [LATIN SMALL LETTER SCHWA]
-"\u0259" => "a"
-
-# \u025a [LATIN SMALL LETTER SCHWA WITH HOOK]
-"\u025A" => "a"
-
-# \u1d8f [LATIN SMALL LETTER A WITH RETROFLEX HOOK]
-"\u1D8F" => "a"
-
-# \u1d95 [LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK]
-"\u1D95" => "a"
-
-# \u1ea1 [LATIN SMALL LETTER A WITH RING BELOW]
-"\u1E01" => "a"
-
-# \u1ea3 [LATIN SMALL LETTER A WITH RIGHT HALF RING]
-"\u1E9A" => "a"
-
-# \u1ea1 [LATIN SMALL LETTER A WITH DOT BELOW]
-"\u1EA1" => "a"
-
-# \u1ea3 [LATIN SMALL LETTER A WITH HOOK ABOVE]
-"\u1EA3" => "a"
-
-# \u1ea5 [LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE]
-"\u1EA5" => "a"
-
-# \u1ea7 [LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE]
-"\u1EA7" => "a"
-
-# \u1ea9 [LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
-"\u1EA9" => "a"
-
-# \u1eab [LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE]
-"\u1EAB" => "a"
-
-# \u1ead [LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
-"\u1EAD" => "a"
-
-# \u1eaf [LATIN SMALL LETTER A WITH BREVE AND ACUTE]
-"\u1EAF" => "a"
-
-# \u1eb1 [LATIN SMALL LETTER A WITH BREVE AND GRAVE]
-"\u1EB1" => "a"
-
-# \u1eb3 [LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE]
-"\u1EB3" => "a"
-
-# \u1eb5 [LATIN SMALL LETTER A WITH BREVE AND TILDE]
-"\u1EB5" => "a"
-
-# \u1eb7 [LATIN SMALL LETTER A WITH BREVE AND DOT BELOW]
-"\u1EB7" => "a"
-
-# \u2090 [LATIN SUBSCRIPT SMALL LETTER A]
-"\u2090" => "a"
-
-# \u2094 [LATIN SUBSCRIPT SMALL LETTER SCHWA]
-"\u2094" => "a"
-
-# \u24d0 [CIRCLED LATIN SMALL LETTER A]
-"\u24D0" => "a"
-
-# \u2c65 [LATIN SMALL LETTER A WITH STROKE]
-"\u2C65" => "a"
-
-# \u2c6f [LATIN CAPITAL LETTER TURNED A]
-"\u2C6F" => "a"
-
-# \uff41 [FULLWIDTH LATIN SMALL LETTER A]
-"\uFF41" => "a"
-
-# \ua732 [LATIN CAPITAL LETTER AA]
-"\uA732" => "AA"
-
-# � [LATIN CAPITAL LETTER AE]
-"\u00C6" => "AE"
-
-# \u01e2 [LATIN CAPITAL LETTER AE WITH MACRON]
-"\u01E2" => "AE"
-
-# \u01fc [LATIN CAPITAL LETTER AE WITH ACUTE]
-"\u01FC" => "AE"
-
-# \u1d01 [LATIN LETTER SMALL CAPITAL AE]
-"\u1D01" => "AE"
-
-# \ua734 [LATIN CAPITAL LETTER AO]
-"\uA734" => "AO"
-
-# \ua736 [LATIN CAPITAL LETTER AU]
-"\uA736" => "AU"
-
-# \ua738 [LATIN CAPITAL LETTER AV]
-"\uA738" => "AV"
-
-# \ua73a [LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR]
-"\uA73A" => "AV"
-
-# \ua73c [LATIN CAPITAL LETTER AY]
-"\uA73C" => "AY"
-
-# \u249c [PARENTHESIZED LATIN SMALL LETTER A]
-"\u249C" => "(a)"
-
-# \ua733 [LATIN SMALL LETTER AA]
-"\uA733" => "aa"
-
-# � [LATIN SMALL LETTER AE]
-"\u00E6" => "ae"
-
-# \u01e3 [LATIN SMALL LETTER AE WITH MACRON]
-"\u01E3" => "ae"
-
-# \u01fd [LATIN SMALL LETTER AE WITH ACUTE]
-"\u01FD" => "ae"
-
-# \u1d02 [LATIN SMALL LETTER TURNED AE]
-"\u1D02" => "ae"
-
-# \ua735 [LATIN SMALL LETTER AO]
-"\uA735" => "ao"
-
-# \ua737 [LATIN SMALL LETTER AU]
-"\uA737" => "au"
-
-# \ua739 [LATIN SMALL LETTER AV]
-"\uA739" => "av"
-
-# \ua73b [LATIN SMALL LETTER AV WITH HORIZONTAL BAR]
-"\uA73B" => "av"
-
-# \ua73d [LATIN SMALL LETTER AY]
-"\uA73D" => "ay"
-
-# \u0181 [LATIN CAPITAL LETTER B WITH HOOK]
-"\u0181" => "B"
-
-# \u0182 [LATIN CAPITAL LETTER B WITH TOPBAR]
-"\u0182" => "B"
-
-# \u0243 [LATIN CAPITAL LETTER B WITH STROKE]
-"\u0243" => "B"
-
-# \u0299 [LATIN LETTER SMALL CAPITAL B]
-"\u0299" => "B"
-
-# \u1d03 [LATIN LETTER SMALL CAPITAL BARRED B]
-"\u1D03" => "B"
-
-# \u1e02 [LATIN CAPITAL LETTER B WITH DOT ABOVE]
-"\u1E02" => "B"
-
-# \u1e04 [LATIN CAPITAL LETTER B WITH DOT BELOW]
-"\u1E04" => "B"
-
-# \u1e06 [LATIN CAPITAL LETTER B WITH LINE BELOW]
-"\u1E06" => "B"
-
-# \u24b7 [CIRCLED LATIN CAPITAL LETTER B]
-"\u24B7" => "B"
-
-# \uff22 [FULLWIDTH LATIN CAPITAL LETTER B]
-"\uFF22" => "B"
-
-# \u0180 [LATIN SMALL LETTER B WITH STROKE]
-"\u0180" => "b"
-
-# \u0183 [LATIN SMALL LETTER B WITH TOPBAR]
-"\u0183" => "b"
-
-# \u0253 [LATIN SMALL LETTER B WITH HOOK]
-"\u0253" => "b"
-
-# \u1d6c [LATIN SMALL LETTER B WITH MIDDLE TILDE]
-"\u1D6C" => "b"
-
-# \u1d80 [LATIN SMALL LETTER B WITH PALATAL HOOK]
-"\u1D80" => "b"
-
-# \u1e03 [LATIN SMALL LETTER B WITH DOT ABOVE]
-"\u1E03" => "b"
-
-# \u1e05 [LATIN SMALL LETTER B WITH DOT BELOW]
-"\u1E05" => "b"
-
-# \u1e07 [LATIN SMALL LETTER B WITH LINE BELOW]
-"\u1E07" => "b"
-
-# \u24d1 [CIRCLED LATIN SMALL LETTER B]
-"\u24D1" => "b"
-
-# \uff42 [FULLWIDTH LATIN SMALL LETTER B]
-"\uFF42" => "b"
-
-# \u249d [PARENTHESIZED LATIN SMALL LETTER B]
-"\u249D" => "(b)"
-
-# � [LATIN CAPITAL LETTER C WITH CEDILLA]
-"\u00C7" => "C"
-
-# \u0106 [LATIN CAPITAL LETTER C WITH ACUTE]
-"\u0106" => "C"
-
-# \u0108 [LATIN CAPITAL LETTER C WITH CIRCUMFLEX]
-"\u0108" => "C"
-
-# \u010a [LATIN CAPITAL LETTER C WITH DOT ABOVE]
-"\u010A" => "C"
-
-# \u010c [LATIN CAPITAL LETTER C WITH CARON]
-"\u010C" => "C"
-
-# \u0187 [LATIN CAPITAL LETTER C WITH HOOK]
-"\u0187" => "C"
-
-# \u023b [LATIN CAPITAL LETTER C WITH STROKE]
-"\u023B" => "C"
-
-# \u0297 [LATIN LETTER STRETCHED C]
-"\u0297" => "C"
-
-# \u1d04 [LATIN LETTER SMALL CAPITAL C]
-"\u1D04" => "C"
-
-# \u1e08 [LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE]
-"\u1E08" => "C"
-
-# \u24b8 [CIRCLED LATIN CAPITAL LETTER C]
-"\u24B8" => "C"
-
-# \uff23 [FULLWIDTH LATIN CAPITAL LETTER C]
-"\uFF23" => "C"
-
-# � [LATIN SMALL LETTER C WITH CEDILLA]
-"\u00E7" => "c"
-
-# \u0107 [LATIN SMALL LETTER C WITH ACUTE]
-"\u0107" => "c"
-
-# \u0109 [LATIN SMALL LETTER C WITH CIRCUMFLEX]
-"\u0109" => "c"
-
-# \u010b [LATIN SMALL LETTER C WITH DOT ABOVE]
-"\u010B" => "c"
-
-# \u010d [LATIN SMALL LETTER C WITH CARON]
-"\u010D" => "c"
-
-# \u0188 [LATIN SMALL LETTER C WITH HOOK]
-"\u0188" => "c"
-
-# \u023c [LATIN SMALL LETTER C WITH STROKE]
-"\u023C" => "c"
-
-# \u0255 [LATIN SMALL LETTER C WITH CURL]
-"\u0255" => "c"
-
-# \u1e09 [LATIN SMALL LETTER C WITH CEDILLA AND ACUTE]
-"\u1E09" => "c"
-
-# \u2184 [LATIN SMALL LETTER REVERSED C]
-"\u2184" => "c"
-
-# \u24d2 [CIRCLED LATIN SMALL LETTER C]
-"\u24D2" => "c"
-
-# \ua73e [LATIN CAPITAL LETTER REVERSED C WITH DOT]
-"\uA73E" => "c"
-
-# \ua73f [LATIN SMALL LETTER REVERSED C WITH DOT]
-"\uA73F" => "c"
-
-# \uff43 [FULLWIDTH LATIN SMALL LETTER C]
-"\uFF43" => "c"
-
-# \u249e [PARENTHESIZED LATIN SMALL LETTER C]
-"\u249E" => "(c)"
-
-# � [LATIN CAPITAL LETTER ETH]
-"\u00D0" => "D"
-
-# \u010e [LATIN CAPITAL LETTER D WITH CARON]
-"\u010E" => "D"
-
-# \u0110 [LATIN CAPITAL LETTER D WITH STROKE]
-"\u0110" => "D"
-
-# \u0189 [LATIN CAPITAL LETTER AFRICAN D]
-"\u0189" => "D"
-
-# \u018a [LATIN CAPITAL LETTER D WITH HOOK]
-"\u018A" => "D"
-
-# \u018b [LATIN CAPITAL LETTER D WITH TOPBAR]
-"\u018B" => "D"
-
-# \u1d05 [LATIN LETTER SMALL CAPITAL D]
-"\u1D05" => "D"
-
-# \u1d06 [LATIN LETTER SMALL CAPITAL ETH]
-"\u1D06" => "D"
-
-# \u1e0a [LATIN CAPITAL LETTER D WITH DOT ABOVE]
-"\u1E0A" => "D"
-
-# \u1e0c [LATIN CAPITAL LETTER D WITH DOT BELOW]
-"\u1E0C" => "D"
-
-# \u1e0e [LATIN CAPITAL LETTER D WITH LINE BELOW]
-"\u1E0E" => "D"
-
-# \u1e10 [LATIN CAPITAL LETTER D WITH CEDILLA]
-"\u1E10" => "D"
-
-# \u1e12 [LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW]
-"\u1E12" => "D"
-
-# \u24b9 [CIRCLED LATIN CAPITAL LETTER D]
-"\u24B9" => "D"
-
-# \ua779 [LATIN CAPITAL LETTER INSULAR D]
-"\uA779" => "D"
-
-# \uff24 [FULLWIDTH LATIN CAPITAL LETTER D]
-"\uFF24" => "D"
-
-# � [LATIN SMALL LETTER ETH]
-"\u00F0" => "d"
-
-# \u010f [LATIN SMALL LETTER D WITH CARON]
-"\u010F" => "d"
-
-# \u0111 [LATIN SMALL LETTER D WITH STROKE]
-"\u0111" => "d"
-
-# \u018c [LATIN SMALL LETTER D WITH TOPBAR]
-"\u018C" => "d"
-
-# \u0221 [LATIN SMALL LETTER D WITH CURL]
-"\u0221" => "d"
-
-# \u0256 [LATIN SMALL LETTER D WITH TAIL]
-"\u0256" => "d"
-
-# \u0257 [LATIN SMALL LETTER D WITH HOOK]
-"\u0257" => "d"
-
-# \u1d6d [LATIN SMALL LETTER D WITH MIDDLE TILDE]
-"\u1D6D" => "d"
-
-# \u1d81 [LATIN SMALL LETTER D WITH PALATAL HOOK]
-"\u1D81" => "d"
-
-# \u1d91 [LATIN SMALL LETTER D WITH HOOK AND TAIL]
-"\u1D91" => "d"
-
-# \u1e0b [LATIN SMALL LETTER D WITH DOT ABOVE]
-"\u1E0B" => "d"
-
-# \u1e0d [LATIN SMALL LETTER D WITH DOT BELOW]
-"\u1E0D" => "d"
-
-# \u1e0f [LATIN SMALL LETTER D WITH LINE BELOW]
-"\u1E0F" => "d"
-
-# \u1e11 [LATIN SMALL LETTER D WITH CEDILLA]
-"\u1E11" => "d"
-
-# \u1e13 [LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW]
-"\u1E13" => "d"
-
-# \u24d3 [CIRCLED LATIN SMALL LETTER D]
-"\u24D3" => "d"
-
-# \ua77a [LATIN SMALL LETTER INSULAR D]
-"\uA77A" => "d"
-
-# \uff44 [FULLWIDTH LATIN SMALL LETTER D]
-"\uFF44" => "d"
-
-# \u01c4 [LATIN CAPITAL LETTER DZ WITH CARON]
-"\u01C4" => "DZ"
-
-# \u01f1 [LATIN CAPITAL LETTER DZ]
-"\u01F1" => "DZ"
-
-# \u01c5 [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON]
-"\u01C5" => "Dz"
-
-# \u01f2 [LATIN CAPITAL LETTER D WITH SMALL LETTER Z]
-"\u01F2" => "Dz"
-
-# \u249f [PARENTHESIZED LATIN SMALL LETTER D]
-"\u249F" => "(d)"
-
-# \u0238 [LATIN SMALL LETTER DB DIGRAPH]
-"\u0238" => "db"
-
-# \u01c6 [LATIN SMALL LETTER DZ WITH CARON]
-"\u01C6" => "dz"
-
-# \u01f3 [LATIN SMALL LETTER DZ]
-"\u01F3" => "dz"
-
-# \u02a3 [LATIN SMALL LETTER DZ DIGRAPH]
-"\u02A3" => "dz"
-
-# \u02a5 [LATIN SMALL LETTER DZ DIGRAPH WITH CURL]
-"\u02A5" => "dz"
-
-# � [LATIN CAPITAL LETTER E WITH GRAVE]
-"\u00C8" => "E"
-
-# � [LATIN CAPITAL LETTER E WITH ACUTE]
-"\u00C9" => "E"
-
-# � [LATIN CAPITAL LETTER E WITH CIRCUMFLEX]
-"\u00CA" => "E"
-
-# � [LATIN CAPITAL LETTER E WITH DIAERESIS]
-"\u00CB" => "E"
-
-# \u0112 [LATIN CAPITAL LETTER E WITH MACRON]
-"\u0112" => "E"
-
-# \u0114 [LATIN CAPITAL LETTER E WITH BREVE]
-"\u0114" => "E"
-
-# \u0116 [LATIN CAPITAL LETTER E WITH DOT ABOVE]
-"\u0116" => "E"
-
-# \u0118 [LATIN CAPITAL LETTER E WITH OGONEK]
-"\u0118" => "E"
-
-# \u011a [LATIN CAPITAL LETTER E WITH CARON]
-"\u011A" => "E"
-
-# \u018e [LATIN CAPITAL LETTER REVERSED E]
-"\u018E" => "E"
-
-# \u0190 [LATIN CAPITAL LETTER OPEN E]
-"\u0190" => "E"
-
-# \u0204 [LATIN CAPITAL LETTER E WITH DOUBLE GRAVE]
-"\u0204" => "E"
-
-# \u0206 [LATIN CAPITAL LETTER E WITH INVERTED BREVE]
-"\u0206" => "E"
-
-# \u0228 [LATIN CAPITAL LETTER E WITH CEDILLA]
-"\u0228" => "E"
-
-# \u0246 [LATIN CAPITAL LETTER E WITH STROKE]
-"\u0246" => "E"
-
-# \u1d07 [LATIN LETTER SMALL CAPITAL E]
-"\u1D07" => "E"
-
-# \u1e14 [LATIN CAPITAL LETTER E WITH MACRON AND GRAVE]
-"\u1E14" => "E"
-
-# \u1e16 [LATIN CAPITAL LETTER E WITH MACRON AND ACUTE]
-"\u1E16" => "E"
-
-# \u1e18 [LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW]
-"\u1E18" => "E"
-
-# \u1e1a [LATIN CAPITAL LETTER E WITH TILDE BELOW]
-"\u1E1A" => "E"
-
-# \u1e1c [LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE]
-"\u1E1C" => "E"
-
-# \u1eb8 [LATIN CAPITAL LETTER E WITH DOT BELOW]
-"\u1EB8" => "E"
-
-# \u1eba [LATIN CAPITAL LETTER E WITH HOOK ABOVE]
-"\u1EBA" => "E"
-
-# \u1ebc [LATIN CAPITAL LETTER E WITH TILDE]
-"\u1EBC" => "E"
-
-# \u1ebe [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE]
-"\u1EBE" => "E"
-
-# \u1ec0 [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE]
-"\u1EC0" => "E"
-
-# \u1ec2 [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
-"\u1EC2" => "E"
-
-# \u1ec4 [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE]
-"\u1EC4" => "E"
-
-# \u1ec6 [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
-"\u1EC6" => "E"
-
-# \u24ba [CIRCLED LATIN CAPITAL LETTER E]
-"\u24BA" => "E"
-
-# \u2c7b [LATIN LETTER SMALL CAPITAL TURNED E]
-"\u2C7B" => "E"
-
-# \uff25 [FULLWIDTH LATIN CAPITAL LETTER E]
-"\uFF25" => "E"
-
-# � [LATIN SMALL LETTER E WITH GRAVE]
-"\u00E8" => "e"
-
-# � [LATIN SMALL LETTER E WITH ACUTE]
-"\u00E9" => "e"
-
-# � [LATIN SMALL LETTER E WITH CIRCUMFLEX]
-"\u00EA" => "e"
-
-# � [LATIN SMALL LETTER E WITH DIAERESIS]
-"\u00EB" => "e"
-
-# \u0113 [LATIN SMALL LETTER E WITH MACRON]
-"\u0113" => "e"
-
-# \u0115 [LATIN SMALL LETTER E WITH BREVE]
-"\u0115" => "e"
-
-# \u0117 [LATIN SMALL LETTER E WITH DOT ABOVE]
-"\u0117" => "e"
-
-# \u0119 [LATIN SMALL LETTER E WITH OGONEK]
-"\u0119" => "e"
-
-# \u011b [LATIN SMALL LETTER E WITH CARON]
-"\u011B" => "e"
-
-# \u01dd [LATIN SMALL LETTER TURNED E]
-"\u01DD" => "e"
-
-# \u0205 [LATIN SMALL LETTER E WITH DOUBLE GRAVE]
-"\u0205" => "e"
-
-# \u0207 [LATIN SMALL LETTER E WITH INVERTED BREVE]
-"\u0207" => "e"
-
-# \u0229 [LATIN SMALL LETTER E WITH CEDILLA]
-"\u0229" => "e"
-
-# \u0247 [LATIN SMALL LETTER E WITH STROKE]
-"\u0247" => "e"
-
-# \u0258 [LATIN SMALL LETTER REVERSED E]
-"\u0258" => "e"
-
-# \u025b [LATIN SMALL LETTER OPEN E]
-"\u025B" => "e"
-
-# \u025c [LATIN SMALL LETTER REVERSED OPEN E]
-"\u025C" => "e"
-
-# \u025d [LATIN SMALL LETTER REVERSED OPEN E WITH HOOK]
-"\u025D" => "e"
-
-# \u025e [LATIN SMALL LETTER CLOSED REVERSED OPEN E]
-"\u025E" => "e"
-
-# \u029a [LATIN SMALL LETTER CLOSED OPEN E]
-"\u029A" => "e"
-
-# \u1d08 [LATIN SMALL LETTER TURNED OPEN E]
-"\u1D08" => "e"
-
-# \u1d92 [LATIN SMALL LETTER E WITH RETROFLEX HOOK]
-"\u1D92" => "e"
-
-# \u1d93 [LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK]
-"\u1D93" => "e"
-
-# \u1d94 [LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK]
-"\u1D94" => "e"
-
-# \u1e15 [LATIN SMALL LETTER E WITH MACRON AND GRAVE]
-"\u1E15" => "e"
-
-# \u1e17 [LATIN SMALL LETTER E WITH MACRON AND ACUTE]
-"\u1E17" => "e"
-
-# \u1e19 [LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW]
-"\u1E19" => "e"
-
-# \u1e1b [LATIN SMALL LETTER E WITH TILDE BELOW]
-"\u1E1B" => "e"
-
-# \u1e1d [LATIN SMALL LETTER E WITH CEDILLA AND BREVE]
-"\u1E1D" => "e"
-
-# \u1eb9 [LATIN SMALL LETTER E WITH DOT BELOW]
-"\u1EB9" => "e"
-
-# \u1ebb [LATIN SMALL LETTER E WITH HOOK ABOVE]
-"\u1EBB" => "e"
-
-# \u1ebd [LATIN SMALL LETTER E WITH TILDE]
-"\u1EBD" => "e"
-
-# \u1ebf [LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE]
-"\u1EBF" => "e"
-
-# \u1ec1 [LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE]
-"\u1EC1" => "e"
-
-# \u1ec3 [LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
-"\u1EC3" => "e"
-
-# \u1ec5 [LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE]
-"\u1EC5" => "e"
-
-# \u1ec7 [LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
-"\u1EC7" => "e"
-
-# \u2091 [LATIN SUBSCRIPT SMALL LETTER E]
-"\u2091" => "e"
-
-# \u24d4 [CIRCLED LATIN SMALL LETTER E]
-"\u24D4" => "e"
-
-# \u2c78 [LATIN SMALL LETTER E WITH NOTCH]
-"\u2C78" => "e"
-
-# \uff45 [FULLWIDTH LATIN SMALL LETTER E]
-"\uFF45" => "e"
-
-# \u24a0 [PARENTHESIZED LATIN SMALL LETTER E]
-"\u24A0" => "(e)"
-
-# \u0191 [LATIN CAPITAL LETTER F WITH HOOK]
-"\u0191" => "F"
-
-# \u1e1e [LATIN CAPITAL LETTER F WITH DOT ABOVE]
-"\u1E1E" => "F"
-
-# \u24bb [CIRCLED LATIN CAPITAL LETTER F]
-"\u24BB" => "F"
-
-# \ua730 [LATIN LETTER SMALL CAPITAL F]
-"\uA730" => "F"
-
-# \ua77b [LATIN CAPITAL LETTER INSULAR F]
-"\uA77B" => "F"
-
-# \ua7fb [LATIN EPIGRAPHIC LETTER REVERSED F]
-"\uA7FB" => "F"
-
-# \uff26 [FULLWIDTH LATIN CAPITAL LETTER F]
-"\uFF26" => "F"
-
-# \u0192 [LATIN SMALL LETTER F WITH HOOK]
-"\u0192" => "f"
-
-# \u1d6e [LATIN SMALL LETTER F WITH MIDDLE TILDE]
-"\u1D6E" => "f"
-
-# \u1d82 [LATIN SMALL LETTER F WITH PALATAL HOOK]
-"\u1D82" => "f"
-
-# \u1e1f [LATIN SMALL LETTER F WITH DOT ABOVE]
-"\u1E1F" => "f"
-
-# \u1e9b [LATIN SMALL LETTER LONG S WITH DOT ABOVE]
-"\u1E9B" => "f"
-
-# \u24d5 [CIRCLED LATIN SMALL LETTER F]
-"\u24D5" => "f"
-
-# \ua77c [LATIN SMALL LETTER INSULAR F]
-"\uA77C" => "f"
-
-# \uff46 [FULLWIDTH LATIN SMALL LETTER F]
-"\uFF46" => "f"
-
-# \u24a1 [PARENTHESIZED LATIN SMALL LETTER F]
-"\u24A1" => "(f)"
-
-# \ufb00 [LATIN SMALL LIGATURE FF]
-"\uFB00" => "ff"
-
-# \ufb03 [LATIN SMALL LIGATURE FFI]
-"\uFB03" => "ffi"
-
-# \ufb04 [LATIN SMALL LIGATURE FFL]
-"\uFB04" => "ffl"
-
-# \ufb01 [LATIN SMALL LIGATURE FI]
-"\uFB01" => "fi"
-
-# \ufb02 [LATIN SMALL LIGATURE FL]
-"\uFB02" => "fl"
-
-# \u011c [LATIN CAPITAL LETTER G WITH CIRCUMFLEX]
-"\u011C" => "G"
-
-# \u011e [LATIN CAPITAL LETTER G WITH BREVE]
-"\u011E" => "G"
-
-# \u0120 [LATIN CAPITAL LETTER G WITH DOT ABOVE]
-"\u0120" => "G"
-
-# \u0122 [LATIN CAPITAL LETTER G WITH CEDILLA]
-"\u0122" => "G"
-
-# \u0193 [LATIN CAPITAL LETTER G WITH HOOK]
-"\u0193" => "G"
-
-# \u01e4 [LATIN CAPITAL LETTER G WITH STROKE]
-"\u01E4" => "G"
-
-# \u01e5 [LATIN SMALL LETTER G WITH STROKE]
-"\u01E5" => "G"
-
-# \u01e6 [LATIN CAPITAL LETTER G WITH CARON]
-"\u01E6" => "G"
-
-# \u01e7 [LATIN SMALL LETTER G WITH CARON]
-"\u01E7" => "G"
-
-# \u01f4 [LATIN CAPITAL LETTER G WITH ACUTE]
-"\u01F4" => "G"
-
-# \u0262 [LATIN LETTER SMALL CAPITAL G]
-"\u0262" => "G"
-
-# \u029b [LATIN LETTER SMALL CAPITAL G WITH HOOK]
-"\u029B" => "G"
-
-# \u1e20 [LATIN CAPITAL LETTER G WITH MACRON]
-"\u1E20" => "G"
-
-# \u24bc [CIRCLED LATIN CAPITAL LETTER G]
-"\u24BC" => "G"
-
-# \ua77d [LATIN CAPITAL LETTER INSULAR G]
-"\uA77D" => "G"
-
-# \ua77e [LATIN CAPITAL LETTER TURNED INSULAR G]
-"\uA77E" => "G"
-
-# \uff27 [FULLWIDTH LATIN CAPITAL LETTER G]
-"\uFF27" => "G"
-
-# \u011d [LATIN SMALL LETTER G WITH CIRCUMFLEX]
-"\u011D" => "g"
-
-# \u011f [LATIN SMALL LETTER G WITH BREVE]
-"\u011F" => "g"
-
-# \u0121 [LATIN SMALL LETTER G WITH DOT ABOVE]
-"\u0121" => "g"
-
-# \u0123 [LATIN SMALL LETTER G WITH CEDILLA]
-"\u0123" => "g"
-
-# \u01f5 [LATIN SMALL LETTER G WITH ACUTE]
-"\u01F5" => "g"
-
-# \u0260 [LATIN SMALL LETTER G WITH HOOK]
-"\u0260" => "g"
-
-# \u0261 [LATIN SMALL LETTER SCRIPT G]
-"\u0261" => "g"
-
-# \u1d77 [LATIN SMALL LETTER TURNED G]
-"\u1D77" => "g"
-
-# \u1d79 [LATIN SMALL LETTER INSULAR G]
-"\u1D79" => "g"
-
-# \u1d83 [LATIN SMALL LETTER G WITH PALATAL HOOK]
-"\u1D83" => "g"
-
-# \u1e21 [LATIN SMALL LETTER G WITH MACRON]
-"\u1E21" => "g"
-
-# \u24d6 [CIRCLED LATIN SMALL LETTER G]
-"\u24D6" => "g"
-
-# \ua77f [LATIN SMALL LETTER TURNED INSULAR G]
-"\uA77F" => "g"
-
-# \uff47 [FULLWIDTH LATIN SMALL LETTER G]
-"\uFF47" => "g"
-
-# \u24a2 [PARENTHESIZED LATIN SMALL LETTER G]
-"\u24A2" => "(g)"
-
-# \u0124 [LATIN CAPITAL LETTER H WITH CIRCUMFLEX]
-"\u0124" => "H"
-
-# \u0126 [LATIN CAPITAL LETTER H WITH STROKE]
-"\u0126" => "H"
-
-# \u021e [LATIN CAPITAL LETTER H WITH CARON]
-"\u021E" => "H"
-
-# \u029c [LATIN LETTER SMALL CAPITAL H]
-"\u029C" => "H"
-
-# \u1e22 [LATIN CAPITAL LETTER H WITH DOT ABOVE]
-"\u1E22" => "H"
-
-# \u1e24 [LATIN CAPITAL LETTER H WITH DOT BELOW]
-"\u1E24" => "H"
-
-# \u1e26 [LATIN CAPITAL LETTER H WITH DIAERESIS]
-"\u1E26" => "H"
-
-# \u1e28 [LATIN CAPITAL LETTER H WITH CEDILLA]
-"\u1E28" => "H"
-
-# \u1e2a [LATIN CAPITAL LETTER H WITH BREVE BELOW]
-"\u1E2A" => "H"
-
-# \u24bd [CIRCLED LATIN CAPITAL LETTER H]
-"\u24BD" => "H"
-
-# \u2c67 [LATIN CAPITAL LETTER H WITH DESCENDER]
-"\u2C67" => "H"
-
-# \u2c75 [LATIN CAPITAL LETTER HALF H]
-"\u2C75" => "H"
-
-# \uff28 [FULLWIDTH LATIN CAPITAL LETTER H]
-"\uFF28" => "H"
-
-# \u0125 [LATIN SMALL LETTER H WITH CIRCUMFLEX]
-"\u0125" => "h"
-
-# \u0127 [LATIN SMALL LETTER H WITH STROKE]
-"\u0127" => "h"
-
-# \u021f [LATIN SMALL LETTER H WITH CARON]
-"\u021F" => "h"
-
-# \u0265 [LATIN SMALL LETTER TURNED H]
-"\u0265" => "h"
-
-# \u0266 [LATIN SMALL LETTER H WITH HOOK]
-"\u0266" => "h"
-
-# \u02ae [LATIN SMALL LETTER TURNED H WITH FISHHOOK]
-"\u02AE" => "h"
-
-# \u02af [LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL]
-"\u02AF" => "h"
-
-# \u1e23 [LATIN SMALL LETTER H WITH DOT ABOVE]
-"\u1E23" => "h"
-
-# \u1e25 [LATIN SMALL LETTER H WITH DOT BELOW]
-"\u1E25" => "h"
-
-# \u1e27 [LATIN SMALL LETTER H WITH DIAERESIS]
-"\u1E27" => "h"
-
-# \u1e29 [LATIN SMALL LETTER H WITH CEDILLA]
-"\u1E29" => "h"
-
-# \u1e2b [LATIN SMALL LETTER H WITH BREVE BELOW]
-"\u1E2B" => "h"
-
-# \u1e96 [LATIN SMALL LETTER H WITH LINE BELOW]
-"\u1E96" => "h"
-
-# \u24d7 [CIRCLED LATIN SMALL LETTER H]
-"\u24D7" => "h"
-
-# \u2c68 [LATIN SMALL LETTER H WITH DESCENDER]
-"\u2C68" => "h"
-
-# \u2c76 [LATIN SMALL LETTER HALF H]
-"\u2C76" => "h"
-
-# \uff48 [FULLWIDTH LATIN SMALL LETTER H]
-"\uFF48" => "h"
-
-# \u01f6 http://en.wikipedia.org/wiki/Hwair [LATIN CAPITAL LETTER HWAIR]
-"\u01F6" => "HV"
-
-# \u24a3 [PARENTHESIZED LATIN SMALL LETTER H]
-"\u24A3" => "(h)"
-
-# \u0195 [LATIN SMALL LETTER HV]
-"\u0195" => "hv"
-
-# � [LATIN CAPITAL LETTER I WITH GRAVE]
-"\u00CC" => "I"
-
-# � [LATIN CAPITAL LETTER I WITH ACUTE]
-"\u00CD" => "I"
-
-# � [LATIN CAPITAL LETTER I WITH CIRCUMFLEX]
-"\u00CE" => "I"
-
-# � [LATIN CAPITAL LETTER I WITH DIAERESIS]
-"\u00CF" => "I"
-
-# \u0128 [LATIN CAPITAL LETTER I WITH TILDE]
-"\u0128" => "I"
-
-# \u012a [LATIN CAPITAL LETTER I WITH MACRON]
-"\u012A" => "I"
-
-# \u012c [LATIN CAPITAL LETTER I WITH BREVE]
-"\u012C" => "I"
-
-# \u012e [LATIN CAPITAL LETTER I WITH OGONEK]
-"\u012E" => "I"
-
-# \u0130 [LATIN CAPITAL LETTER I WITH DOT ABOVE]
-"\u0130" => "I"
-
-# \u0196 [LATIN CAPITAL LETTER IOTA]
-"\u0196" => "I"
-
-# \u0197 [LATIN CAPITAL LETTER I WITH STROKE]
-"\u0197" => "I"
-
-# \u01cf [LATIN CAPITAL LETTER I WITH CARON]
-"\u01CF" => "I"
-
-# \u0208 [LATIN CAPITAL LETTER I WITH DOUBLE GRAVE]
-"\u0208" => "I"
-
-# \u020a [LATIN CAPITAL LETTER I WITH INVERTED BREVE]
-"\u020A" => "I"
-
-# \u026a [LATIN LETTER SMALL CAPITAL I]
-"\u026A" => "I"
-
-# \u1d7b [LATIN SMALL CAPITAL LETTER I WITH STROKE]
-"\u1D7B" => "I"
-
-# \u1e2c [LATIN CAPITAL LETTER I WITH TILDE BELOW]
-"\u1E2C" => "I"
-
-# \u1e2e [LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE]
-"\u1E2E" => "I"
-
-# \u1ec8 [LATIN CAPITAL LETTER I WITH HOOK ABOVE]
-"\u1EC8" => "I"
-
-# \u1eca [LATIN CAPITAL LETTER I WITH DOT BELOW]
-"\u1ECA" => "I"
-
-# \u24be [CIRCLED LATIN CAPITAL LETTER I]
-"\u24BE" => "I"
-
-# \ua7fe [LATIN EPIGRAPHIC LETTER I LONGA]
-"\uA7FE" => "I"
-
-# \uff29 [FULLWIDTH LATIN CAPITAL LETTER I]
-"\uFF29" => "I"
-
-# � [LATIN SMALL LETTER I WITH GRAVE]
-"\u00EC" => "i"
-
-# � [LATIN SMALL LETTER I WITH ACUTE]
-"\u00ED" => "i"
-
-# � [LATIN SMALL LETTER I WITH CIRCUMFLEX]
-"\u00EE" => "i"
-
-# � [LATIN SMALL LETTER I WITH DIAERESIS]
-"\u00EF" => "i"
-
-# \u0129 [LATIN SMALL LETTER I WITH TILDE]
-"\u0129" => "i"
-
-# \u012b [LATIN SMALL LETTER I WITH MACRON]
-"\u012B" => "i"
-
-# \u012d [LATIN SMALL LETTER I WITH BREVE]
-"\u012D" => "i"
-
-# \u012f [LATIN SMALL LETTER I WITH OGONEK]
-"\u012F" => "i"
-
-# \u0131 [LATIN SMALL LETTER DOTLESS I]
-"\u0131" => "i"
-
-# \u01d0 [LATIN SMALL LETTER I WITH CARON]
-"\u01D0" => "i"
-
-# \u0209 [LATIN SMALL LETTER I WITH DOUBLE GRAVE]
-"\u0209" => "i"
-
-# \u020b [LATIN SMALL LETTER I WITH INVERTED BREVE]
-"\u020B" => "i"
-
-# \u0268 [LATIN SMALL LETTER I WITH STROKE]
-"\u0268" => "i"
-
-# \u1d09 [LATIN SMALL LETTER TURNED I]
-"\u1D09" => "i"
-
-# \u1d62 [LATIN SUBSCRIPT SMALL LETTER I]
-"\u1D62" => "i"
-
-# \u1d7c [LATIN SMALL LETTER IOTA WITH STROKE]
-"\u1D7C" => "i"
-
-# \u1d96 [LATIN SMALL LETTER I WITH RETROFLEX HOOK]
-"\u1D96" => "i"
-
-# \u1e2d [LATIN SMALL LETTER I WITH TILDE BELOW]
-"\u1E2D" => "i"
-
-# \u1e2f [LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE]
-"\u1E2F" => "i"
-
-# \u1ec9 [LATIN SMALL LETTER I WITH HOOK ABOVE]
-"\u1EC9" => "i"
-
-# \u1ecb [LATIN SMALL LETTER I WITH DOT BELOW]
-"\u1ECB" => "i"
-
-# \u2071 [SUPERSCRIPT LATIN SMALL LETTER I]
-"\u2071" => "i"
-
-# \u24d8 [CIRCLED LATIN SMALL LETTER I]
-"\u24D8" => "i"
-
-# \uff49 [FULLWIDTH LATIN SMALL LETTER I]
-"\uFF49" => "i"
-
-# \u0132 [LATIN CAPITAL LIGATURE IJ]
-"\u0132" => "IJ"
-
-# \u24a4 [PARENTHESIZED LATIN SMALL LETTER I]
-"\u24A4" => "(i)"
-
-# \u0133 [LATIN SMALL LIGATURE IJ]
-"\u0133" => "ij"
-
-# \u0134 [LATIN CAPITAL LETTER J WITH CIRCUMFLEX]
-"\u0134" => "J"
-
-# \u0248 [LATIN CAPITAL LETTER J WITH STROKE]
-"\u0248" => "J"
-
-# \u1d0a [LATIN LETTER SMALL CAPITAL J]
-"\u1D0A" => "J"
-
-# \u24bf [CIRCLED LATIN CAPITAL LETTER J]
-"\u24BF" => "J"
-
-# \uff2a [FULLWIDTH LATIN CAPITAL LETTER J]
-"\uFF2A" => "J"
-
-# \u0135 [LATIN SMALL LETTER J WITH CIRCUMFLEX]
-"\u0135" => "j"
-
-# \u01f0 [LATIN SMALL LETTER J WITH CARON]
-"\u01F0" => "j"
-
-# \u0237 [LATIN SMALL LETTER DOTLESS J]
-"\u0237" => "j"
-
-# \u0249 [LATIN SMALL LETTER J WITH STROKE]
-"\u0249" => "j"
-
-# \u025f [LATIN SMALL LETTER DOTLESS J WITH STROKE]
-"\u025F" => "j"
-
-# \u0284 [LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK]
-"\u0284" => "j"
-
-# \u029d [LATIN SMALL LETTER J WITH CROSSED-TAIL]
-"\u029D" => "j"
-
-# \u24d9 [CIRCLED LATIN SMALL LETTER J]
-"\u24D9" => "j"
-
-# \u2c7c [LATIN SUBSCRIPT SMALL LETTER J]
-"\u2C7C" => "j"
-
-# \uff4a [FULLWIDTH LATIN SMALL LETTER J]
-"\uFF4A" => "j"
-
-# \u24a5 [PARENTHESIZED LATIN SMALL LETTER J]
-"\u24A5" => "(j)"
-
-# \u0136 [LATIN CAPITAL LETTER K WITH CEDILLA]
-"\u0136" => "K"
-
-# \u0198 [LATIN CAPITAL LETTER K WITH HOOK]
-"\u0198" => "K"
-
-# \u01e8 [LATIN CAPITAL LETTER K WITH CARON]
-"\u01E8" => "K"
-
-# \u1d0b [LATIN LETTER SMALL CAPITAL K]
-"\u1D0B" => "K"
-
-# \u1e30 [LATIN CAPITAL LETTER K WITH ACUTE]
-"\u1E30" => "K"
-
-# \u1e32 [LATIN CAPITAL LETTER K WITH DOT BELOW]
-"\u1E32" => "K"
-
-# \u1e34 [LATIN CAPITAL LETTER K WITH LINE BELOW]
-"\u1E34" => "K"
-
-# \u24c0 [CIRCLED LATIN CAPITAL LETTER K]
-"\u24C0" => "K"
-
-# \u2c69 [LATIN CAPITAL LETTER K WITH DESCENDER]
-"\u2C69" => "K"
-
-# \ua740 [LATIN CAPITAL LETTER K WITH STROKE]
-"\uA740" => "K"
-
-# \ua742 [LATIN CAPITAL LETTER K WITH DIAGONAL STROKE]
-"\uA742" => "K"
-
-# \ua744 [LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE]
-"\uA744" => "K"
-
-# \uff2b [FULLWIDTH LATIN CAPITAL LETTER K]
-"\uFF2B" => "K"
-
-# \u0137 [LATIN SMALL LETTER K WITH CEDILLA]
-"\u0137" => "k"
-
-# \u0199 [LATIN SMALL LETTER K WITH HOOK]
-"\u0199" => "k"
-
-# \u01e9 [LATIN SMALL LETTER K WITH CARON]
-"\u01E9" => "k"
-
-# \u029e [LATIN SMALL LETTER TURNED K]
-"\u029E" => "k"
-
-# \u1d84 [LATIN SMALL LETTER K WITH PALATAL HOOK]
-"\u1D84" => "k"
-
-# \u1e31 [LATIN SMALL LETTER K WITH ACUTE]
-"\u1E31" => "k"
-
-# \u1e33 [LATIN SMALL LETTER K WITH DOT BELOW]
-"\u1E33" => "k"
-
-# \u1e35 [LATIN SMALL LETTER K WITH LINE BELOW]
-"\u1E35" => "k"
-
-# \u24da [CIRCLED LATIN SMALL LETTER K]
-"\u24DA" => "k"
-
-# \u2c6a [LATIN SMALL LETTER K WITH DESCENDER]
-"\u2C6A" => "k"
-
-# \ua741 [LATIN SMALL LETTER K WITH STROKE]
-"\uA741" => "k"
-
-# \ua743 [LATIN SMALL LETTER K WITH DIAGONAL STROKE]
-"\uA743" => "k"
-
-# \ua745 [LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE]
-"\uA745" => "k"
-
-# \uff4b [FULLWIDTH LATIN SMALL LETTER K]
-"\uFF4B" => "k"
-
-# \u24a6 [PARENTHESIZED LATIN SMALL LETTER K]
-"\u24A6" => "(k)"
-
-# \u0139 [LATIN CAPITAL LETTER L WITH ACUTE]
-"\u0139" => "L"
-
-# \u013b [LATIN CAPITAL LETTER L WITH CEDILLA]
-"\u013B" => "L"
-
-# \u013d [LATIN CAPITAL LETTER L WITH CARON]
-"\u013D" => "L"
-
-# \u013f [LATIN CAPITAL LETTER L WITH MIDDLE DOT]
-"\u013F" => "L"
-
-# \u0141 [LATIN CAPITAL LETTER L WITH STROKE]
-"\u0141" => "L"
-
-# \u023d [LATIN CAPITAL LETTER L WITH BAR]
-"\u023D" => "L"
-
-# \u029f [LATIN LETTER SMALL CAPITAL L]
-"\u029F" => "L"
-
-# \u1d0c [LATIN LETTER SMALL CAPITAL L WITH STROKE]
-"\u1D0C" => "L"
-
-# \u1e36 [LATIN CAPITAL LETTER L WITH DOT BELOW]
-"\u1E36" => "L"
-
-# \u1e38 [LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON]
-"\u1E38" => "L"
-
-# \u1e3a [LATIN CAPITAL LETTER L WITH LINE BELOW]
-"\u1E3A" => "L"
-
-# \u1e3c [LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW]
-"\u1E3C" => "L"
-
-# \u24c1 [CIRCLED LATIN CAPITAL LETTER L]
-"\u24C1" => "L"
-
-# \u2c60 [LATIN CAPITAL LETTER L WITH DOUBLE BAR]
-"\u2C60" => "L"
-
-# \u2c62 [LATIN CAPITAL LETTER L WITH MIDDLE TILDE]
-"\u2C62" => "L"
-
-# \ua746 [LATIN CAPITAL LETTER BROKEN L]
-"\uA746" => "L"
-
-# \ua748 [LATIN CAPITAL LETTER L WITH HIGH STROKE]
-"\uA748" => "L"
-
-# \ua780 [LATIN CAPITAL LETTER TURNED L]
-"\uA780" => "L"
-
-# \uff2c [FULLWIDTH LATIN CAPITAL LETTER L]
-"\uFF2C" => "L"
-
-# \u013a [LATIN SMALL LETTER L WITH ACUTE]
-"\u013A" => "l"
-
-# \u013c [LATIN SMALL LETTER L WITH CEDILLA]
-"\u013C" => "l"
-
-# \u013e [LATIN SMALL LETTER L WITH CARON]
-"\u013E" => "l"
-
-# \u0140 [LATIN SMALL LETTER L WITH MIDDLE DOT]
-"\u0140" => "l"
-
-# \u0142 [LATIN SMALL LETTER L WITH STROKE]
-"\u0142" => "l"
-
-# \u019a [LATIN SMALL LETTER L WITH BAR]
-"\u019A" => "l"
-
-# \u0234 [LATIN SMALL LETTER L WITH CURL]
-"\u0234" => "l"
-
-# \u026b [LATIN SMALL LETTER L WITH MIDDLE TILDE]
-"\u026B" => "l"
-
-# \u026c [LATIN SMALL LETTER L WITH BELT]
-"\u026C" => "l"
-
-# \u026d [LATIN SMALL LETTER L WITH RETROFLEX HOOK]
-"\u026D" => "l"
-
-# \u1d85 [LATIN SMALL LETTER L WITH PALATAL HOOK]
-"\u1D85" => "l"
-
-# \u1e37 [LATIN SMALL LETTER L WITH DOT BELOW]
-"\u1E37" => "l"
-
-# \u1e39 [LATIN SMALL LETTER L WITH DOT BELOW AND MACRON]
-"\u1E39" => "l"
-
-# \u1e3b [LATIN SMALL LETTER L WITH LINE BELOW]
-"\u1E3B" => "l"
-
-# \u1e3d [LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW]
-"\u1E3D" => "l"
-
-# \u24db [CIRCLED LATIN SMALL LETTER L]
-"\u24DB" => "l"
-
-# \u2c61 [LATIN SMALL LETTER L WITH DOUBLE BAR]
-"\u2C61" => "l"
-
-# \ua747 [LATIN SMALL LETTER BROKEN L]
-"\uA747" => "l"
-
-# \ua749 [LATIN SMALL LETTER L WITH HIGH STROKE]
-"\uA749" => "l"
-
-# \ua781 [LATIN SMALL LETTER TURNED L]
-"\uA781" => "l"
-
-# \uff4c [FULLWIDTH LATIN SMALL LETTER L]
-"\uFF4C" => "l"
-
-# \u01c7 [LATIN CAPITAL LETTER LJ]
-"\u01C7" => "LJ"
-
-# \u1efa [LATIN CAPITAL LETTER MIDDLE-WELSH LL]
-"\u1EFA" => "LL"
-
-# \u01c8 [LATIN CAPITAL LETTER L WITH SMALL LETTER J]
-"\u01C8" => "Lj"
-
-# \u24a7 [PARENTHESIZED LATIN SMALL LETTER L]
-"\u24A7" => "(l)"
-
-# \u01c9 [LATIN SMALL LETTER LJ]
-"\u01C9" => "lj"
-
-# \u1efb [LATIN SMALL LETTER MIDDLE-WELSH LL]
-"\u1EFB" => "ll"
-
-# \u02aa [LATIN SMALL LETTER LS DIGRAPH]
-"\u02AA" => "ls"
-
-# \u02ab [LATIN SMALL LETTER LZ DIGRAPH]
-"\u02AB" => "lz"
-
-# \u019c [LATIN CAPITAL LETTER TURNED M]
-"\u019C" => "M"
-
-# \u1d0d [LATIN LETTER SMALL CAPITAL M]
-"\u1D0D" => "M"
-
-# \u1e3e [LATIN CAPITAL LETTER M WITH ACUTE]
-"\u1E3E" => "M"
-
-# \u1e40 [LATIN CAPITAL LETTER M WITH DOT ABOVE]
-"\u1E40" => "M"
-
-# \u1e42 [LATIN CAPITAL LETTER M WITH DOT BELOW]
-"\u1E42" => "M"
-
-# \u24c2 [CIRCLED LATIN CAPITAL LETTER M]
-"\u24C2" => "M"
-
-# \u2c6e [LATIN CAPITAL LETTER M WITH HOOK]
-"\u2C6E" => "M"
-
-# \ua7fd [LATIN EPIGRAPHIC LETTER INVERTED M]
-"\uA7FD" => "M"
-
-# \ua7ff [LATIN EPIGRAPHIC LETTER ARCHAIC M]
-"\uA7FF" => "M"
-
-# \uff2d [FULLWIDTH LATIN CAPITAL LETTER M]
-"\uFF2D" => "M"
-
-# \u026f [LATIN SMALL LETTER TURNED M]
-"\u026F" => "m"
-
-# \u0270 [LATIN SMALL LETTER TURNED M WITH LONG LEG]
-"\u0270" => "m"
-
-# \u0271 [LATIN SMALL LETTER M WITH HOOK]
-"\u0271" => "m"
-
-# \u1d6f [LATIN SMALL LETTER M WITH MIDDLE TILDE]
-"\u1D6F" => "m"
-
-# \u1d86 [LATIN SMALL LETTER M WITH PALATAL HOOK]
-"\u1D86" => "m"
-
-# \u1e3f [LATIN SMALL LETTER M WITH ACUTE]
-"\u1E3F" => "m"
-
-# \u1e41 [LATIN SMALL LETTER M WITH DOT ABOVE]
-"\u1E41" => "m"
-
-# \u1e43 [LATIN SMALL LETTER M WITH DOT BELOW]
-"\u1E43" => "m"
-
-# \u24dc [CIRCLED LATIN SMALL LETTER M]
-"\u24DC" => "m"
-
-# \uff4d [FULLWIDTH LATIN SMALL LETTER M]
-"\uFF4D" => "m"
-
-# \u24a8 [PARENTHESIZED LATIN SMALL LETTER M]
-"\u24A8" => "(m)"
-
-# � [LATIN CAPITAL LETTER N WITH TILDE]
-"\u00D1" => "N"
-
-# \u0143 [LATIN CAPITAL LETTER N WITH ACUTE]
-"\u0143" => "N"
-
-# \u0145 [LATIN CAPITAL LETTER N WITH CEDILLA]
-"\u0145" => "N"
-
-# \u0147 [LATIN CAPITAL LETTER N WITH CARON]
-"\u0147" => "N"
-
-# \u014a http://en.wikipedia.org/wiki/Eng_(letter) [LATIN CAPITAL LETTER ENG]
-"\u014A" => "N"
-
-# \u019d [LATIN CAPITAL LETTER N WITH LEFT HOOK]
-"\u019D" => "N"
-
-# \u01f8 [LATIN CAPITAL LETTER N WITH GRAVE]
-"\u01F8" => "N"
-
-# \u0220 [LATIN CAPITAL LETTER N WITH LONG RIGHT LEG]
-"\u0220" => "N"
-
-# \u0274 [LATIN LETTER SMALL CAPITAL N]
-"\u0274" => "N"
-
-# \u1d0e [LATIN LETTER SMALL CAPITAL REVERSED N]
-"\u1D0E" => "N"
-
-# \u1e44 [LATIN CAPITAL LETTER N WITH DOT ABOVE]
-"\u1E44" => "N"
-
-# \u1e46 [LATIN CAPITAL LETTER N WITH DOT BELOW]
-"\u1E46" => "N"
-
-# \u1e48 [LATIN CAPITAL LETTER N WITH LINE BELOW]
-"\u1E48" => "N"
-
-# \u1e4a [LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW]
-"\u1E4A" => "N"
-
-# \u24c3 [CIRCLED LATIN CAPITAL LETTER N]
-"\u24C3" => "N"
-
-# \uff2e [FULLWIDTH LATIN CAPITAL LETTER N]
-"\uFF2E" => "N"
-
-# � [LATIN SMALL LETTER N WITH TILDE]
-"\u00F1" => "n"
-
-# \u0144 [LATIN SMALL LETTER N WITH ACUTE]
-"\u0144" => "n"
-
-# \u0146 [LATIN SMALL LETTER N WITH CEDILLA]
-"\u0146" => "n"
-
-# \u0148 [LATIN SMALL LETTER N WITH CARON]
-"\u0148" => "n"
-
-# \u0149 [LATIN SMALL LETTER N PRECEDED BY APOSTROPHE]
-"\u0149" => "n"
-
-# \u014b http://en.wikipedia.org/wiki/Eng_(letter) [LATIN SMALL LETTER ENG]
-"\u014B" => "n"
-
-# \u019e [LATIN SMALL LETTER N WITH LONG RIGHT LEG]
-"\u019E" => "n"
-
-# \u01f9 [LATIN SMALL LETTER N WITH GRAVE]
-"\u01F9" => "n"
-
-# \u0235 [LATIN SMALL LETTER N WITH CURL]
-"\u0235" => "n"
-
-# \u0272 [LATIN SMALL LETTER N WITH LEFT HOOK]
-"\u0272" => "n"
-
-# \u0273 [LATIN SMALL LETTER N WITH RETROFLEX HOOK]
-"\u0273" => "n"
-
-# \u1d70 [LATIN SMALL LETTER N WITH MIDDLE TILDE]
-"\u1D70" => "n"
-
-# \u1d87 [LATIN SMALL LETTER N WITH PALATAL HOOK]
-"\u1D87" => "n"
-
-# \u1e45 [LATIN SMALL LETTER N WITH DOT ABOVE]
-"\u1E45" => "n"
-
-# \u1e47 [LATIN SMALL LETTER N WITH DOT BELOW]
-"\u1E47" => "n"
-
-# \u1e49 [LATIN SMALL LETTER N WITH LINE BELOW]
-"\u1E49" => "n"
-
-# \u1e4b [LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW]
-"\u1E4B" => "n"
-
-# \u207f [SUPERSCRIPT LATIN SMALL LETTER N]
-"\u207F" => "n"
-
-# \u24dd [CIRCLED LATIN SMALL LETTER N]
-"\u24DD" => "n"
-
-# \uff4e [FULLWIDTH LATIN SMALL LETTER N]
-"\uFF4E" => "n"
-
-# \u01ca [LATIN CAPITAL LETTER NJ]
-"\u01CA" => "NJ"
-
-# \u01cb [LATIN CAPITAL LETTER N WITH SMALL LETTER J]
-"\u01CB" => "Nj"
-
-# \u24a9 [PARENTHESIZED LATIN SMALL LETTER N]
-"\u24A9" => "(n)"
-
-# \u01cc [LATIN SMALL LETTER NJ]
-"\u01CC" => "nj"
-
-# � [LATIN CAPITAL LETTER O WITH GRAVE]
-"\u00D2" => "O"
-
-# � [LATIN CAPITAL LETTER O WITH ACUTE]
-"\u00D3" => "O"
-
-# � [LATIN CAPITAL LETTER O WITH CIRCUMFLEX]
-"\u00D4" => "O"
-
-# � [LATIN CAPITAL LETTER O WITH TILDE]
-"\u00D5" => "O"
-
-# � [LATIN CAPITAL LETTER O WITH DIAERESIS]
-"\u00D6" => "O"
-
-# � [LATIN CAPITAL LETTER O WITH STROKE]
-"\u00D8" => "O"
-
-# \u014c [LATIN CAPITAL LETTER O WITH MACRON]
-"\u014C" => "O"
-
-# \u014e [LATIN CAPITAL LETTER O WITH BREVE]
-"\u014E" => "O"
-
-# \u0150 [LATIN CAPITAL LETTER O WITH DOUBLE ACUTE]
-"\u0150" => "O"
-
-# \u0186 [LATIN CAPITAL LETTER OPEN O]
-"\u0186" => "O"
-
-# \u019f [LATIN CAPITAL LETTER O WITH MIDDLE TILDE]
-"\u019F" => "O"
-
-# \u01a0 [LATIN CAPITAL LETTER O WITH HORN]
-"\u01A0" => "O"
-
-# \u01d1 [LATIN CAPITAL LETTER O WITH CARON]
-"\u01D1" => "O"
-
-# \u01ea [LATIN CAPITAL LETTER O WITH OGONEK]
-"\u01EA" => "O"
-
-# \u01ec [LATIN CAPITAL LETTER O WITH OGONEK AND MACRON]
-"\u01EC" => "O"
-
-# \u01fe [LATIN CAPITAL LETTER O WITH STROKE AND ACUTE]
-"\u01FE" => "O"
-
-# \u020c [LATIN CAPITAL LETTER O WITH DOUBLE GRAVE]
-"\u020C" => "O"
-
-# \u020e [LATIN CAPITAL LETTER O WITH INVERTED BREVE]
-"\u020E" => "O"
-
-# \u022a [LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON]
-"\u022A" => "O"
-
-# \u022c [LATIN CAPITAL LETTER O WITH TILDE AND MACRON]
-"\u022C" => "O"
-
-# \u022e [LATIN CAPITAL LETTER O WITH DOT ABOVE]
-"\u022E" => "O"
-
-# \u0230 [LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON]
-"\u0230" => "O"
-
-# \u1d0f [LATIN LETTER SMALL CAPITAL O]
-"\u1D0F" => "O"
-
-# \u1d10 [LATIN LETTER SMALL CAPITAL OPEN O]
-"\u1D10" => "O"
-
-# \u1e4c [LATIN CAPITAL LETTER O WITH TILDE AND ACUTE]
-"\u1E4C" => "O"
-
-# \u1e4e [LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS]
-"\u1E4E" => "O"
-
-# \u1e50 [LATIN CAPITAL LETTER O WITH MACRON AND GRAVE]
-"\u1E50" => "O"
-
-# \u1e52 [LATIN CAPITAL LETTER O WITH MACRON AND ACUTE]
-"\u1E52" => "O"
-
-# \u1ecc [LATIN CAPITAL LETTER O WITH DOT BELOW]
-"\u1ECC" => "O"
-
-# \u1ece [LATIN CAPITAL LETTER O WITH HOOK ABOVE]
-"\u1ECE" => "O"
-
-# \u1ed0 [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE]
-"\u1ED0" => "O"
-
-# \u1ed2 [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE]
-"\u1ED2" => "O"
-
-# \u1ed4 [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
-"\u1ED4" => "O"
-
-# \u1ed6 [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE]
-"\u1ED6" => "O"
-
-# \u1ed8 [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
-"\u1ED8" => "O"
-
-# \u1eda [LATIN CAPITAL LETTER O WITH HORN AND ACUTE]
-"\u1EDA" => "O"
-
-# \u1edc [LATIN CAPITAL LETTER O WITH HORN AND GRAVE]
-"\u1EDC" => "O"
-
-# \u1ede [LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE]
-"\u1EDE" => "O"
-
-# \u1ee0 [LATIN CAPITAL LETTER O WITH HORN AND TILDE]
-"\u1EE0" => "O"
-
-# \u1ee2 [LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW]
-"\u1EE2" => "O"
-
-# \u24c4 [CIRCLED LATIN CAPITAL LETTER O]
-"\u24C4" => "O"
-
-# \ua74a [LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY]
-"\uA74A" => "O"
-
-# \ua74c [LATIN CAPITAL LETTER O WITH LOOP]
-"\uA74C" => "O"
-
-# \uff2f [FULLWIDTH LATIN CAPITAL LETTER O]
-"\uFF2F" => "O"
-
-# � [LATIN SMALL LETTER O WITH GRAVE]
-"\u00F2" => "o"
-
-# � [LATIN SMALL LETTER O WITH ACUTE]
-"\u00F3" => "o"
-
-# � [LATIN SMALL LETTER O WITH CIRCUMFLEX]
-"\u00F4" => "o"
-
-# � [LATIN SMALL LETTER O WITH TILDE]
-"\u00F5" => "o"
-
-# � [LATIN SMALL LETTER O WITH DIAERESIS]
-"\u00F6" => "o"
-
-# � [LATIN SMALL LETTER O WITH STROKE]
-"\u00F8" => "o"
-
-# \u014d [LATIN SMALL LETTER O WITH MACRON]
-"\u014D" => "o"
-
-# \u014f [LATIN SMALL LETTER O WITH BREVE]
-"\u014F" => "o"
-
-# \u0151 [LATIN SMALL LETTER O WITH DOUBLE ACUTE]
-"\u0151" => "o"
-
-# \u01a1 [LATIN SMALL LETTER O WITH HORN]
-"\u01A1" => "o"
-
-# \u01d2 [LATIN SMALL LETTER O WITH CARON]
-"\u01D2" => "o"
-
-# \u01eb [LATIN SMALL LETTER O WITH OGONEK]
-"\u01EB" => "o"
-
-# \u01ed [LATIN SMALL LETTER O WITH OGONEK AND MACRON]
-"\u01ED" => "o"
-
-# \u01ff [LATIN SMALL LETTER O WITH STROKE AND ACUTE]
-"\u01FF" => "o"
-
-# \u020d [LATIN SMALL LETTER O WITH DOUBLE GRAVE]
-"\u020D" => "o"
-
-# \u020f [LATIN SMALL LETTER O WITH INVERTED BREVE]
-"\u020F" => "o"
-
-# \u022b [LATIN SMALL LETTER O WITH DIAERESIS AND MACRON]
-"\u022B" => "o"
-
-# \u022d [LATIN SMALL LETTER O WITH TILDE AND MACRON]
-"\u022D" => "o"
-
-# \u022f [LATIN SMALL LETTER O WITH DOT ABOVE]
-"\u022F" => "o"
-
-# \u0231 [LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON]
-"\u0231" => "o"
-
-# \u0254 [LATIN SMALL LETTER OPEN O]
-"\u0254" => "o"
-
-# \u0275 [LATIN SMALL LETTER BARRED O]
-"\u0275" => "o"
-
-# \u1d16 [LATIN SMALL LETTER TOP HALF O]
-"\u1D16" => "o"
-
-# \u1d17 [LATIN SMALL LETTER BOTTOM HALF O]
-"\u1D17" => "o"
-
-# \u1d97 [LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK]
-"\u1D97" => "o"
-
-# \u1e4d [LATIN SMALL LETTER O WITH TILDE AND ACUTE]
-"\u1E4D" => "o"
-
-# \u1e4f [LATIN SMALL LETTER O WITH TILDE AND DIAERESIS]
-"\u1E4F" => "o"
-
-# \u1e51 [LATIN SMALL LETTER O WITH MACRON AND GRAVE]
-"\u1E51" => "o"
-
-# \u1e53 [LATIN SMALL LETTER O WITH MACRON AND ACUTE]
-"\u1E53" => "o"
-
-# \u1ecd [LATIN SMALL LETTER O WITH DOT BELOW]
-"\u1ECD" => "o"
-
-# \u1ecf [LATIN SMALL LETTER O WITH HOOK ABOVE]
-"\u1ECF" => "o"
-
-# \u1ed1 [LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE]
-"\u1ED1" => "o"
-
-# \u1ed3 [LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE]
-"\u1ED3" => "o"
-
-# \u1ed5 [LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
-"\u1ED5" => "o"
-
-# \u1ed7 [LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE]
-"\u1ED7" => "o"
-
-# \u1ed9 [LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
-"\u1ED9" => "o"
-
-# \u1edb [LATIN SMALL LETTER O WITH HORN AND ACUTE]
-"\u1EDB" => "o"
-
-# \u1edd [LATIN SMALL LETTER O WITH HORN AND GRAVE]
-"\u1EDD" => "o"
-
-# \u1edf [LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE]
-"\u1EDF" => "o"
-
-# \u1ee1 [LATIN SMALL LETTER O WITH HORN AND TILDE]
-"\u1EE1" => "o"
-
-# \u1ee3 [LATIN SMALL LETTER O WITH HORN AND DOT BELOW]
-"\u1EE3" => "o"
-
-# \u2092 [LATIN SUBSCRIPT SMALL LETTER O]
-"\u2092" => "o"
-
-# \u24de [CIRCLED LATIN SMALL LETTER O]
-"\u24DE" => "o"
-
-# \u2c7a [LATIN SMALL LETTER O WITH LOW RING INSIDE]
-"\u2C7A" => "o"
-
-# \ua74b [LATIN SMALL LETTER O WITH LONG STROKE OVERLAY]
-"\uA74B" => "o"
-
-# \ua74d [LATIN SMALL LETTER O WITH LOOP]
-"\uA74D" => "o"
-
-# \uff4f [FULLWIDTH LATIN SMALL LETTER O]
-"\uFF4F" => "o"
-
-# \u0152 [LATIN CAPITAL LIGATURE OE]
-"\u0152" => "OE"
-
-# \u0276 [LATIN LETTER SMALL CAPITAL OE]
-"\u0276" => "OE"
-
-# \ua74e [LATIN CAPITAL LETTER OO]
-"\uA74E" => "OO"
-
-# \u0222 http://en.wikipedia.org/wiki/OU [LATIN CAPITAL LETTER OU]
-"\u0222" => "OU"
-
-# \u1d15 [LATIN LETTER SMALL CAPITAL OU]
-"\u1D15" => "OU"
-
-# \u24aa [PARENTHESIZED LATIN SMALL LETTER O]
-"\u24AA" => "(o)"
-
-# \u0153 [LATIN SMALL LIGATURE OE]
-"\u0153" => "oe"
-
-# \u1d14 [LATIN SMALL LETTER TURNED OE]
-"\u1D14" => "oe"
-
-# \ua74f [LATIN SMALL LETTER OO]
-"\uA74F" => "oo"
-
-# \u0223 http://en.wikipedia.org/wiki/OU [LATIN SMALL LETTER OU]
-"\u0223" => "ou"
-
-# \u01a4 [LATIN CAPITAL LETTER P WITH HOOK]
-"\u01A4" => "P"
-
-# \u1d18 [LATIN LETTER SMALL CAPITAL P]
-"\u1D18" => "P"
-
-# \u1e54 [LATIN CAPITAL LETTER P WITH ACUTE]
-"\u1E54" => "P"
-
-# \u1e56 [LATIN CAPITAL LETTER P WITH DOT ABOVE]
-"\u1E56" => "P"
-
-# \u24c5 [CIRCLED LATIN CAPITAL LETTER P]
-"\u24C5" => "P"
-
-# \u2c63 [LATIN CAPITAL LETTER P WITH STROKE]
-"\u2C63" => "P"
-
-# \ua750 [LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER]
-"\uA750" => "P"
-
-# \ua752 [LATIN CAPITAL LETTER P WITH FLOURISH]
-"\uA752" => "P"
-
-# \ua754 [LATIN CAPITAL LETTER P WITH SQUIRREL TAIL]
-"\uA754" => "P"
-
-# \uff30 [FULLWIDTH LATIN CAPITAL LETTER P]
-"\uFF30" => "P"
-
-# \u01a5 [LATIN SMALL LETTER P WITH HOOK]
-"\u01A5" => "p"
-
-# \u1d71 [LATIN SMALL LETTER P WITH MIDDLE TILDE]
-"\u1D71" => "p"
-
-# \u1d7d [LATIN SMALL LETTER P WITH STROKE]
-"\u1D7D" => "p"
-
-# \u1d88 [LATIN SMALL LETTER P WITH PALATAL HOOK]
-"\u1D88" => "p"
-
-# \u1e55 [LATIN SMALL LETTER P WITH ACUTE]
-"\u1E55" => "p"
-
-# \u1e57 [LATIN SMALL LETTER P WITH DOT ABOVE]
-"\u1E57" => "p"
-
-# \u24df [CIRCLED LATIN SMALL LETTER P]
-"\u24DF" => "p"
-
-# \ua751 [LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER]
-"\uA751" => "p"
-
-# \ua753 [LATIN SMALL LETTER P WITH FLOURISH]
-"\uA753" => "p"
-
-# \ua755 [LATIN SMALL LETTER P WITH SQUIRREL TAIL]
-"\uA755" => "p"
-
-# \ua7fc [LATIN EPIGRAPHIC LETTER REVERSED P]
-"\uA7FC" => "p"
-
-# \uff50 [FULLWIDTH LATIN SMALL LETTER P]
-"\uFF50" => "p"
-
-# \u24ab [PARENTHESIZED LATIN SMALL LETTER P]
-"\u24AB" => "(p)"
-
-# \u024a [LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL]
-"\u024A" => "Q"
-
-# \u24c6 [CIRCLED LATIN CAPITAL LETTER Q]
-"\u24C6" => "Q"
-
-# \ua756 [LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER]
-"\uA756" => "Q"
-
-# \ua758 [LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE]
-"\uA758" => "Q"
-
-# \uff31 [FULLWIDTH LATIN CAPITAL LETTER Q]
-"\uFF31" => "Q"
-
-# \u0138 http://en.wikipedia.org/wiki/Kra_(letter) [LATIN SMALL LETTER KRA]
-"\u0138" => "q"
-
-# \u024b [LATIN SMALL LETTER Q WITH HOOK TAIL]
-"\u024B" => "q"
-
-# \u02a0 [LATIN SMALL LETTER Q WITH HOOK]
-"\u02A0" => "q"
-
-# \u24e0 [CIRCLED LATIN SMALL LETTER Q]
-"\u24E0" => "q"
-
-# \ua757 [LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER]
-"\uA757" => "q"
-
-# \ua759 [LATIN SMALL LETTER Q WITH DIAGONAL STROKE]
-"\uA759" => "q"
-
-# \uff51 [FULLWIDTH LATIN SMALL LETTER Q]
-"\uFF51" => "q"
-
-# \u24ac [PARENTHESIZED LATIN SMALL LETTER Q]
-"\u24AC" => "(q)"
-
-# \u0239 [LATIN SMALL LETTER QP DIGRAPH]
-"\u0239" => "qp"
-
-# \u0154 [LATIN CAPITAL LETTER R WITH ACUTE]
-"\u0154" => "R"
-
-# \u0156 [LATIN CAPITAL LETTER R WITH CEDILLA]
-"\u0156" => "R"
-
-# \u0158 [LATIN CAPITAL LETTER R WITH CARON]
-"\u0158" => "R"
-
-# \u0212 [LATIN CAPITAL LETTER R WITH DOUBLE GRAVE]
-"\u0210" => "R"
-
-# \u0212 [LATIN CAPITAL LETTER R WITH INVERTED BREVE]
-"\u0212" => "R"
-
-# \u024c [LATIN CAPITAL LETTER R WITH STROKE]
-"\u024C" => "R"
-
-# \u0280 [LATIN LETTER SMALL CAPITAL R]
-"\u0280" => "R"
-
-# \u0281 [LATIN LETTER SMALL CAPITAL INVERTED R]
-"\u0281" => "R"
-
-# \u1d19 [LATIN LETTER SMALL CAPITAL REVERSED R]
-"\u1D19" => "R"
-
-# \u1d1a [LATIN LETTER SMALL CAPITAL TURNED R]
-"\u1D1A" => "R"
-
-# \u1e58 [LATIN CAPITAL LETTER R WITH DOT ABOVE]
-"\u1E58" => "R"
-
-# \u1e5a [LATIN CAPITAL LETTER R WITH DOT BELOW]
-"\u1E5A" => "R"
-
-# \u1e5c [LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON]
-"\u1E5C" => "R"
-
-# \u1e5e [LATIN CAPITAL LETTER R WITH LINE BELOW]
-"\u1E5E" => "R"
-
-# \u24c7 [CIRCLED LATIN CAPITAL LETTER R]
-"\u24C7" => "R"
-
-# \u2c64 [LATIN CAPITAL LETTER R WITH TAIL]
-"\u2C64" => "R"
-
-# \ua75a [LATIN CAPITAL LETTER R ROTUNDA]
-"\uA75A" => "R"
-
-# \ua782 [LATIN CAPITAL LETTER INSULAR R]
-"\uA782" => "R"
-
-# \uff32 [FULLWIDTH LATIN CAPITAL LETTER R]
-"\uFF32" => "R"
-
-# \u0155 [LATIN SMALL LETTER R WITH ACUTE]
-"\u0155" => "r"
-
-# \u0157 [LATIN SMALL LETTER R WITH CEDILLA]
-"\u0157" => "r"
-
-# \u0159 [LATIN SMALL LETTER R WITH CARON]
-"\u0159" => "r"
-
-# \u0211 [LATIN SMALL LETTER R WITH DOUBLE GRAVE]
-"\u0211" => "r"
-
-# \u0213 [LATIN SMALL LETTER R WITH INVERTED BREVE]
-"\u0213" => "r"
-
-# \u024d [LATIN SMALL LETTER R WITH STROKE]
-"\u024D" => "r"
-
-# \u027c [LATIN SMALL LETTER R WITH LONG LEG]
-"\u027C" => "r"
-
-# \u027d [LATIN SMALL LETTER R WITH TAIL]
-"\u027D" => "r"
-
-# \u027e [LATIN SMALL LETTER R WITH FISHHOOK]
-"\u027E" => "r"
-
-# \u027f [LATIN SMALL LETTER REVERSED R WITH FISHHOOK]
-"\u027F" => "r"
-
-# \u1d63 [LATIN SUBSCRIPT SMALL LETTER R]
-"\u1D63" => "r"
-
-# \u1d72 [LATIN SMALL LETTER R WITH MIDDLE TILDE]
-"\u1D72" => "r"
-
-# \u1d73 [LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE]
-"\u1D73" => "r"
-
-# \u1d89 [LATIN SMALL LETTER R WITH PALATAL HOOK]
-"\u1D89" => "r"
-
-# \u1e59 [LATIN SMALL LETTER R WITH DOT ABOVE]
-"\u1E59" => "r"
-
-# \u1e5b [LATIN SMALL LETTER R WITH DOT BELOW]
-"\u1E5B" => "r"
-
-# \u1e5d [LATIN SMALL LETTER R WITH DOT BELOW AND MACRON]
-"\u1E5D" => "r"
-
-# \u1e5f [LATIN SMALL LETTER R WITH LINE BELOW]
-"\u1E5F" => "r"
-
-# \u24e1 [CIRCLED LATIN SMALL LETTER R]
-"\u24E1" => "r"
-
-# \ua75b [LATIN SMALL LETTER R ROTUNDA]
-"\uA75B" => "r"
-
-# \ua783 [LATIN SMALL LETTER INSULAR R]
-"\uA783" => "r"
-
-# \uff52 [FULLWIDTH LATIN SMALL LETTER R]
-"\uFF52" => "r"
-
-# \u24ad [PARENTHESIZED LATIN SMALL LETTER R]
-"\u24AD" => "(r)"
-
-# \u015a [LATIN CAPITAL LETTER S WITH ACUTE]
-"\u015A" => "S"
-
-# \u015c [LATIN CAPITAL LETTER S WITH CIRCUMFLEX]
-"\u015C" => "S"
-
-# \u015e [LATIN CAPITAL LETTER S WITH CEDILLA]
-"\u015E" => "S"
-
-# \u0160 [LATIN CAPITAL LETTER S WITH CARON]
-"\u0160" => "S"
-
-# \u0218 [LATIN CAPITAL LETTER S WITH COMMA BELOW]
-"\u0218" => "S"
-
-# \u1e60 [LATIN CAPITAL LETTER S WITH DOT ABOVE]
-"\u1E60" => "S"
-
-# \u1e62 [LATIN CAPITAL LETTER S WITH DOT BELOW]
-"\u1E62" => "S"
-
-# \u1e64 [LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE]
-"\u1E64" => "S"
-
-# \u1e66 [LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE]
-"\u1E66" => "S"
-
-# \u1e68 [LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE]
-"\u1E68" => "S"
-
-# \u24c8 [CIRCLED LATIN CAPITAL LETTER S]
-"\u24C8" => "S"
-
-# \ua731 [LATIN LETTER SMALL CAPITAL S]
-"\uA731" => "S"
-
-# \ua785 [LATIN SMALL LETTER INSULAR S]
-"\uA785" => "S"
-
-# \uff33 [FULLWIDTH LATIN CAPITAL LETTER S]
-"\uFF33" => "S"
-
-# \u015b [LATIN SMALL LETTER S WITH ACUTE]
-"\u015B" => "s"
-
-# \u015d [LATIN SMALL LETTER S WITH CIRCUMFLEX]
-"\u015D" => "s"
-
-# \u015f [LATIN SMALL LETTER S WITH CEDILLA]
-"\u015F" => "s"
-
-# \u0161 [LATIN SMALL LETTER S WITH CARON]
-"\u0161" => "s"
-
-# \u017f http://en.wikipedia.org/wiki/Long_S [LATIN SMALL LETTER LONG S]
-"\u017F" => "s"
-
-# \u0219 [LATIN SMALL LETTER S WITH COMMA BELOW]
-"\u0219" => "s"
-
-# \u023f [LATIN SMALL LETTER S WITH SWASH TAIL]
-"\u023F" => "s"
-
-# \u0282 [LATIN SMALL LETTER S WITH HOOK]
-"\u0282" => "s"
-
-# \u1d74 [LATIN SMALL LETTER S WITH MIDDLE TILDE]
-"\u1D74" => "s"
-
-# \u1d8a [LATIN SMALL LETTER S WITH PALATAL HOOK]
-"\u1D8A" => "s"
-
-# \u1e61 [LATIN SMALL LETTER S WITH DOT ABOVE]
-"\u1E61" => "s"
-
-# \u1e63 [LATIN SMALL LETTER S WITH DOT BELOW]
-"\u1E63" => "s"
-
-# \u1e65 [LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE]
-"\u1E65" => "s"
-
-# \u1e67 [LATIN SMALL LETTER S WITH CARON AND DOT ABOVE]
-"\u1E67" => "s"
-
-# \u1e69 [LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE]
-"\u1E69" => "s"
-
-# \u1e9c [LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE]
-"\u1E9C" => "s"
-
-# \u1e9d [LATIN SMALL LETTER LONG S WITH HIGH STROKE]
-"\u1E9D" => "s"
-
-# \u24e2 [CIRCLED LATIN SMALL LETTER S]
-"\u24E2" => "s"
-
-# \ua784 [LATIN CAPITAL LETTER INSULAR S]
-"\uA784" => "s"
-
-# \uff53 [FULLWIDTH LATIN SMALL LETTER S]
-"\uFF53" => "s"
-
-# \u1e9e [LATIN CAPITAL LETTER SHARP S]
-"\u1E9E" => "SS"
-
-# \u24ae [PARENTHESIZED LATIN SMALL LETTER S]
-"\u24AE" => "(s)"
-
-# � [LATIN SMALL LETTER SHARP S]
-"\u00DF" => "ss"
-
-# \ufb06 [LATIN SMALL LIGATURE ST]
-"\uFB06" => "st"
-
-# \u0162 [LATIN CAPITAL LETTER T WITH CEDILLA]
-"\u0162" => "T"
-
-# \u0164 [LATIN CAPITAL LETTER T WITH CARON]
-"\u0164" => "T"
-
-# \u0166 [LATIN CAPITAL LETTER T WITH STROKE]
-"\u0166" => "T"
-
-# \u01ac [LATIN CAPITAL LETTER T WITH HOOK]
-"\u01AC" => "T"
-
-# \u01ae [LATIN CAPITAL LETTER T WITH RETROFLEX HOOK]
-"\u01AE" => "T"
-
-# \u021a [LATIN CAPITAL LETTER T WITH COMMA BELOW]
-"\u021A" => "T"
-
-# \u023e [LATIN CAPITAL LETTER T WITH DIAGONAL STROKE]
-"\u023E" => "T"
-
-# \u1d1b [LATIN LETTER SMALL CAPITAL T]
-"\u1D1B" => "T"
-
-# \u1e6a [LATIN CAPITAL LETTER T WITH DOT ABOVE]
-"\u1E6A" => "T"
-
-# \u1e6c [LATIN CAPITAL LETTER T WITH DOT BELOW]
-"\u1E6C" => "T"
-
-# \u1e6e [LATIN CAPITAL LETTER T WITH LINE BELOW]
-"\u1E6E" => "T"
-
-# \u1e70 [LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW]
-"\u1E70" => "T"
-
-# \u24c9 [CIRCLED LATIN CAPITAL LETTER T]
-"\u24C9" => "T"
-
-# \ua786 [LATIN CAPITAL LETTER INSULAR T]
-"\uA786" => "T"
-
-# \uff34 [FULLWIDTH LATIN CAPITAL LETTER T]
-"\uFF34" => "T"
-
-# \u0163 [LATIN SMALL LETTER T WITH CEDILLA]
-"\u0163" => "t"
-
-# \u0165 [LATIN SMALL LETTER T WITH CARON]
-"\u0165" => "t"
-
-# \u0167 [LATIN SMALL LETTER T WITH STROKE]
-"\u0167" => "t"
-
-# \u01ab [LATIN SMALL LETTER T WITH PALATAL HOOK]
-"\u01AB" => "t"
-
-# \u01ad [LATIN SMALL LETTER T WITH HOOK]
-"\u01AD" => "t"
-
-# \u021b [LATIN SMALL LETTER T WITH COMMA BELOW]
-"\u021B" => "t"
-
-# \u0236 [LATIN SMALL LETTER T WITH CURL]
-"\u0236" => "t"
-
-# \u0287 [LATIN SMALL LETTER TURNED T]
-"\u0287" => "t"
-
-# \u0288 [LATIN SMALL LETTER T WITH RETROFLEX HOOK]
-"\u0288" => "t"
-
-# \u1d75 [LATIN SMALL LETTER T WITH MIDDLE TILDE]
-"\u1D75" => "t"
-
-# \u1e6b [LATIN SMALL LETTER T WITH DOT ABOVE]
-"\u1E6B" => "t"
-
-# \u1e6d [LATIN SMALL LETTER T WITH DOT BELOW]
-"\u1E6D" => "t"
-
-# \u1e6f [LATIN SMALL LETTER T WITH LINE BELOW]
-"\u1E6F" => "t"
-
-# \u1e71 [LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW]
-"\u1E71" => "t"
-
-# \u1e97 [LATIN SMALL LETTER T WITH DIAERESIS]
-"\u1E97" => "t"
-
-# \u24e3 [CIRCLED LATIN SMALL LETTER T]
-"\u24E3" => "t"
-
-# \u2c66 [LATIN SMALL LETTER T WITH DIAGONAL STROKE]
-"\u2C66" => "t"
-
-# \uff54 [FULLWIDTH LATIN SMALL LETTER T]
-"\uFF54" => "t"
-
-# � [LATIN CAPITAL LETTER THORN]
-"\u00DE" => "TH"
-
-# \ua766 [LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER]
-"\uA766" => "TH"
-
-# \ua728 [LATIN CAPITAL LETTER TZ]
-"\uA728" => "TZ"
-
-# \u24af [PARENTHESIZED LATIN SMALL LETTER T]
-"\u24AF" => "(t)"
-
-# \u02a8 [LATIN SMALL LETTER TC DIGRAPH WITH CURL]
-"\u02A8" => "tc"
-
-# � [LATIN SMALL LETTER THORN]
-"\u00FE" => "th"
-
-# \u1d7a [LATIN SMALL LETTER TH WITH STRIKETHROUGH]
-"\u1D7A" => "th"
-
-# \ua767 [LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER]
-"\uA767" => "th"
-
-# \u02a6 [LATIN SMALL LETTER TS DIGRAPH]
-"\u02A6" => "ts"
-
-# \ua729 [LATIN SMALL LETTER TZ]
-"\uA729" => "tz"
-
-# � [LATIN CAPITAL LETTER U WITH GRAVE]
-"\u00D9" => "U"
-
-# � [LATIN CAPITAL LETTER U WITH ACUTE]
-"\u00DA" => "U"
-
-# � [LATIN CAPITAL LETTER U WITH CIRCUMFLEX]
-"\u00DB" => "U"
-
-# � [LATIN CAPITAL LETTER U WITH DIAERESIS]
-"\u00DC" => "U"
-
-# \u0168 [LATIN CAPITAL LETTER U WITH TILDE]
-"\u0168" => "U"
-
-# \u016a [LATIN CAPITAL LETTER U WITH MACRON]
-"\u016A" => "U"
-
-# \u016c [LATIN CAPITAL LETTER U WITH BREVE]
-"\u016C" => "U"
-
-# \u016e [LATIN CAPITAL LETTER U WITH RING ABOVE]
-"\u016E" => "U"
-
-# \u0170 [LATIN CAPITAL LETTER U WITH DOUBLE ACUTE]
-"\u0170" => "U"
-
-# \u0172 [LATIN CAPITAL LETTER U WITH OGONEK]
-"\u0172" => "U"
-
-# \u01af [LATIN CAPITAL LETTER U WITH HORN]
-"\u01AF" => "U"
-
-# \u01d3 [LATIN CAPITAL LETTER U WITH CARON]
-"\u01D3" => "U"
-
-# \u01d5 [LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON]
-"\u01D5" => "U"
-
-# \u01d7 [LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE]
-"\u01D7" => "U"
-
-# \u01d9 [LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON]
-"\u01D9" => "U"
-
-# \u01db [LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE]
-"\u01DB" => "U"
-
-# \u0214 [LATIN CAPITAL LETTER U WITH DOUBLE GRAVE]
-"\u0214" => "U"
-
-# \u0216 [LATIN CAPITAL LETTER U WITH INVERTED BREVE]
-"\u0216" => "U"
-
-# \u0244 [LATIN CAPITAL LETTER U BAR]
-"\u0244" => "U"
-
-# \u1d1c [LATIN LETTER SMALL CAPITAL U]
-"\u1D1C" => "U"
-
-# \u1d7e [LATIN SMALL CAPITAL LETTER U WITH STROKE]
-"\u1D7E" => "U"
-
-# \u1e72 [LATIN CAPITAL LETTER U WITH DIAERESIS BELOW]
-"\u1E72" => "U"
-
-# \u1e74 [LATIN CAPITAL LETTER U WITH TILDE BELOW]
-"\u1E74" => "U"
-
-# \u1e76 [LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW]
-"\u1E76" => "U"
-
-# \u1e78 [LATIN CAPITAL LETTER U WITH TILDE AND ACUTE]
-"\u1E78" => "U"
-
-# \u1e7a [LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS]
-"\u1E7A" => "U"
-
-# \u1ee4 [LATIN CAPITAL LETTER U WITH DOT BELOW]
-"\u1EE4" => "U"
-
-# \u1ee6 [LATIN CAPITAL LETTER U WITH HOOK ABOVE]
-"\u1EE6" => "U"
-
-# \u1ee8 [LATIN CAPITAL LETTER U WITH HORN AND ACUTE]
-"\u1EE8" => "U"
-
-# \u1eea [LATIN CAPITAL LETTER U WITH HORN AND GRAVE]
-"\u1EEA" => "U"
-
-# \u1eec [LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE]
-"\u1EEC" => "U"
-
-# \u1eee [LATIN CAPITAL LETTER U WITH HORN AND TILDE]
-"\u1EEE" => "U"
-
-# \u1ef0 [LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW]
-"\u1EF0" => "U"
-
-# \u24ca [CIRCLED LATIN CAPITAL LETTER U]
-"\u24CA" => "U"
-
-# \uff35 [FULLWIDTH LATIN CAPITAL LETTER U]
-"\uFF35" => "U"
-
-# � [LATIN SMALL LETTER U WITH GRAVE]
-"\u00F9" => "u"
-
-# � [LATIN SMALL LETTER U WITH ACUTE]
-"\u00FA" => "u"
-
-# � [LATIN SMALL LETTER U WITH CIRCUMFLEX]
-"\u00FB" => "u"
-
-# � [LATIN SMALL LETTER U WITH DIAERESIS]
-"\u00FC" => "u"
-
-# \u0169 [LATIN SMALL LETTER U WITH TILDE]
-"\u0169" => "u"
-
-# \u016b [LATIN SMALL LETTER U WITH MACRON]
-"\u016B" => "u"
-
-# \u016d [LATIN SMALL LETTER U WITH BREVE]
-"\u016D" => "u"
-
-# \u016f [LATIN SMALL LETTER U WITH RING ABOVE]
-"\u016F" => "u"
-
-# \u0171 [LATIN SMALL LETTER U WITH DOUBLE ACUTE]
-"\u0171" => "u"
-
-# \u0173 [LATIN SMALL LETTER U WITH OGONEK]
-"\u0173" => "u"
-
-# \u01b0 [LATIN SMALL LETTER U WITH HORN]
-"\u01B0" => "u"
-
-# \u01d4 [LATIN SMALL LETTER U WITH CARON]
-"\u01D4" => "u"
-
-# \u01d6 [LATIN SMALL LETTER U WITH DIAERESIS AND MACRON]
-"\u01D6" => "u"
-
-# \u01d8 [LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE]
-"\u01D8" => "u"
-
-# \u01da [LATIN SMALL LETTER U WITH DIAERESIS AND CARON]
-"\u01DA" => "u"
-
-# \u01dc [LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE]
-"\u01DC" => "u"
-
-# \u0215 [LATIN SMALL LETTER U WITH DOUBLE GRAVE]
-"\u0215" => "u"
-
-# \u0217 [LATIN SMALL LETTER U WITH INVERTED BREVE]
-"\u0217" => "u"
-
-# \u0289 [LATIN SMALL LETTER U BAR]
-"\u0289" => "u"
-
-# \u1d64 [LATIN SUBSCRIPT SMALL LETTER U]
-"\u1D64" => "u"
-
-# \u1d99 [LATIN SMALL LETTER U WITH RETROFLEX HOOK]
-"\u1D99" => "u"
-
-# \u1e73 [LATIN SMALL LETTER U WITH DIAERESIS BELOW]
-"\u1E73" => "u"
-
-# \u1e75 [LATIN SMALL LETTER U WITH TILDE BELOW]
-"\u1E75" => "u"
-
-# \u1e77 [LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW]
-"\u1E77" => "u"
-
-# \u1e79 [LATIN SMALL LETTER U WITH TILDE AND ACUTE]
-"\u1E79" => "u"
-
-# \u1e7b [LATIN SMALL LETTER U WITH MACRON AND DIAERESIS]
-"\u1E7B" => "u"
-
-# \u1ee5 [LATIN SMALL LETTER U WITH DOT BELOW]
-"\u1EE5" => "u"
-
-# \u1ee7 [LATIN SMALL LETTER U WITH HOOK ABOVE]
-"\u1EE7" => "u"
-
-# \u1ee9 [LATIN SMALL LETTER U WITH HORN AND ACUTE]
-"\u1EE9" => "u"
-
-# \u1eeb [LATIN SMALL LETTER U WITH HORN AND GRAVE]
-"\u1EEB" => "u"
-
-# \u1eed [LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE]
-"\u1EED" => "u"
-
-# \u1eef [LATIN SMALL LETTER U WITH HORN AND TILDE]
-"\u1EEF" => "u"
-
-# \u1ef1 [LATIN SMALL LETTER U WITH HORN AND DOT BELOW]
-"\u1EF1" => "u"
-
-# \u24e4 [CIRCLED LATIN SMALL LETTER U]
-"\u24E4" => "u"
-
-# \uff55 [FULLWIDTH LATIN SMALL LETTER U]
-"\uFF55" => "u"
-
-# \u24b0 [PARENTHESIZED LATIN SMALL LETTER U]
-"\u24B0" => "(u)"
-
-# \u1d6b [LATIN SMALL LETTER UE]
-"\u1D6B" => "ue"
-
-# \u01b2 [LATIN CAPITAL LETTER V WITH HOOK]
-"\u01B2" => "V"
-
-# \u0245 [LATIN CAPITAL LETTER TURNED V]
-"\u0245" => "V"
-
-# \u1d20 [LATIN LETTER SMALL CAPITAL V]
-"\u1D20" => "V"
-
-# \u1e7c [LATIN CAPITAL LETTER V WITH TILDE]
-"\u1E7C" => "V"
-
-# \u1e7e [LATIN CAPITAL LETTER V WITH DOT BELOW]
-"\u1E7E" => "V"
-
-# \u1efc [LATIN CAPITAL LETTER MIDDLE-WELSH V]
-"\u1EFC" => "V"
-
-# \u24cb [CIRCLED LATIN CAPITAL LETTER V]
-"\u24CB" => "V"
-
-# \ua75e [LATIN CAPITAL LETTER V WITH DIAGONAL STROKE]
-"\uA75E" => "V"
-
-# \ua768 [LATIN CAPITAL LETTER VEND]
-"\uA768" => "V"
-
-# \uff36 [FULLWIDTH LATIN CAPITAL LETTER V]
-"\uFF36" => "V"
-
-# \u028b [LATIN SMALL LETTER V WITH HOOK]
-"\u028B" => "v"
-
-# \u028c [LATIN SMALL LETTER TURNED V]
-"\u028C" => "v"
-
-# \u1d65 [LATIN SUBSCRIPT SMALL LETTER V]
-"\u1D65" => "v"
-
-# \u1d8c [LATIN SMALL LETTER V WITH PALATAL HOOK]
-"\u1D8C" => "v"
-
-# \u1e7d [LATIN SMALL LETTER V WITH TILDE]
-"\u1E7D" => "v"
-
-# \u1e7f [LATIN SMALL LETTER V WITH DOT BELOW]
-"\u1E7F" => "v"
-
-# \u24e5 [CIRCLED LATIN SMALL LETTER V]
-"\u24E5" => "v"
-
-# \u2c71 [LATIN SMALL LETTER V WITH RIGHT HOOK]
-"\u2C71" => "v"
-
-# \u2c74 [LATIN SMALL LETTER V WITH CURL]
-"\u2C74" => "v"
-
-# \ua75f [LATIN SMALL LETTER V WITH DIAGONAL STROKE]
-"\uA75F" => "v"
-
-# \uff56 [FULLWIDTH LATIN SMALL LETTER V]
-"\uFF56" => "v"
-
-# \ua760 [LATIN CAPITAL LETTER VY]
-"\uA760" => "VY"
-
-# \u24b1 [PARENTHESIZED LATIN SMALL LETTER V]
-"\u24B1" => "(v)"
-
-# \ua761 [LATIN SMALL LETTER VY]
-"\uA761" => "vy"
-
-# \u0174 [LATIN CAPITAL LETTER W WITH CIRCUMFLEX]
-"\u0174" => "W"
-
-# \u01f7 http://en.wikipedia.org/wiki/Wynn [LATIN CAPITAL LETTER WYNN]
-"\u01F7" => "W"
-
-# \u1d21 [LATIN LETTER SMALL CAPITAL W]
-"\u1D21" => "W"
-
-# \u1e80 [LATIN CAPITAL LETTER W WITH GRAVE]
-"\u1E80" => "W"
-
-# \u1e82 [LATIN CAPITAL LETTER W WITH ACUTE]
-"\u1E82" => "W"
-
-# \u1e84 [LATIN CAPITAL LETTER W WITH DIAERESIS]
-"\u1E84" => "W"
-
-# \u1e86 [LATIN CAPITAL LETTER W WITH DOT ABOVE]
-"\u1E86" => "W"
-
-# \u1e88 [LATIN CAPITAL LETTER W WITH DOT BELOW]
-"\u1E88" => "W"
-
-# \u24cc [CIRCLED LATIN CAPITAL LETTER W]
-"\u24CC" => "W"
-
-# \u2c72 [LATIN CAPITAL LETTER W WITH HOOK]
-"\u2C72" => "W"
-
-# \uff37 [FULLWIDTH LATIN CAPITAL LETTER W]
-"\uFF37" => "W"
-
-# \u0175 [LATIN SMALL LETTER W WITH CIRCUMFLEX]
-"\u0175" => "w"
-
-# \u01bf http://en.wikipedia.org/wiki/Wynn [LATIN LETTER WYNN]
-"\u01BF" => "w"
-
-# \u028d [LATIN SMALL LETTER TURNED W]
-"\u028D" => "w"
-
-# \u1e81 [LATIN SMALL LETTER W WITH GRAVE]
-"\u1E81" => "w"
-
-# \u1e83 [LATIN SMALL LETTER W WITH ACUTE]
-"\u1E83" => "w"
-
-# \u1e85 [LATIN SMALL LETTER W WITH DIAERESIS]
-"\u1E85" => "w"
-
-# \u1e87 [LATIN SMALL LETTER W WITH DOT ABOVE]
-"\u1E87" => "w"
-
-# \u1e89 [LATIN SMALL LETTER W WITH DOT BELOW]
-"\u1E89" => "w"
-
-# \u1e98 [LATIN SMALL LETTER W WITH RING ABOVE]
-"\u1E98" => "w"
-
-# \u24e6 [CIRCLED LATIN SMALL LETTER W]
-"\u24E6" => "w"
-
-# \u2c73 [LATIN SMALL LETTER W WITH HOOK]
-"\u2C73" => "w"
-
-# \uff57 [FULLWIDTH LATIN SMALL LETTER W]
-"\uFF57" => "w"
-
-# \u24b2 [PARENTHESIZED LATIN SMALL LETTER W]
-"\u24B2" => "(w)"
-
-# \u1e8a [LATIN CAPITAL LETTER X WITH DOT ABOVE]
-"\u1E8A" => "X"
-
-# \u1e8c [LATIN CAPITAL LETTER X WITH DIAERESIS]
-"\u1E8C" => "X"
-
-# \u24cd [CIRCLED LATIN CAPITAL LETTER X]
-"\u24CD" => "X"
-
-# \uff38 [FULLWIDTH LATIN CAPITAL LETTER X]
-"\uFF38" => "X"
-
-# \u1d8d [LATIN SMALL LETTER X WITH PALATAL HOOK]
-"\u1D8D" => "x"
-
-# \u1e8b [LATIN SMALL LETTER X WITH DOT ABOVE]
-"\u1E8B" => "x"
-
-# \u1e8d [LATIN SMALL LETTER X WITH DIAERESIS]
-"\u1E8D" => "x"
-
-# \u2093 [LATIN SUBSCRIPT SMALL LETTER X]
-"\u2093" => "x"
-
-# \u24e7 [CIRCLED LATIN SMALL LETTER X]
-"\u24E7" => "x"
-
-# \uff58 [FULLWIDTH LATIN SMALL LETTER X]
-"\uFF58" => "x"
-
-# \u24b3 [PARENTHESIZED LATIN SMALL LETTER X]
-"\u24B3" => "(x)"
-
-# � [LATIN CAPITAL LETTER Y WITH ACUTE]
-"\u00DD" => "Y"
-
-# \u0176 [LATIN CAPITAL LETTER Y WITH CIRCUMFLEX]
-"\u0176" => "Y"
-
-# \u0178 [LATIN CAPITAL LETTER Y WITH DIAERESIS]
-"\u0178" => "Y"
-
-# \u01b3 [LATIN CAPITAL LETTER Y WITH HOOK]
-"\u01B3" => "Y"
-
-# \u0232 [LATIN CAPITAL LETTER Y WITH MACRON]
-"\u0232" => "Y"
-
-# \u024e [LATIN CAPITAL LETTER Y WITH STROKE]
-"\u024E" => "Y"
-
-# \u028f [LATIN LETTER SMALL CAPITAL Y]
-"\u028F" => "Y"
-
-# \u1e8e [LATIN CAPITAL LETTER Y WITH DOT ABOVE]
-"\u1E8E" => "Y"
-
-# \u1ef2 [LATIN CAPITAL LETTER Y WITH GRAVE]
-"\u1EF2" => "Y"
-
-# \u1ef4 [LATIN CAPITAL LETTER Y WITH DOT BELOW]
-"\u1EF4" => "Y"
-
-# \u1ef6 [LATIN CAPITAL LETTER Y WITH HOOK ABOVE]
-"\u1EF6" => "Y"
-
-# \u1ef8 [LATIN CAPITAL LETTER Y WITH TILDE]
-"\u1EF8" => "Y"
-
-# \u1efe [LATIN CAPITAL LETTER Y WITH LOOP]
-"\u1EFE" => "Y"
-
-# \u24ce [CIRCLED LATIN CAPITAL LETTER Y]
-"\u24CE" => "Y"
-
-# \uff39 [FULLWIDTH LATIN CAPITAL LETTER Y]
-"\uFF39" => "Y"
-
-# � [LATIN SMALL LETTER Y WITH ACUTE]
-"\u00FD" => "y"
-
-# � [LATIN SMALL LETTER Y WITH DIAERESIS]
-"\u00FF" => "y"
-
-# \u0177 [LATIN SMALL LETTER Y WITH CIRCUMFLEX]
-"\u0177" => "y"
-
-# \u01b4 [LATIN SMALL LETTER Y WITH HOOK]
-"\u01B4" => "y"
-
-# \u0233 [LATIN SMALL LETTER Y WITH MACRON]
-"\u0233" => "y"
-
-# \u024f [LATIN SMALL LETTER Y WITH STROKE]
-"\u024F" => "y"
-
-# \u028e [LATIN SMALL LETTER TURNED Y]
-"\u028E" => "y"
-
-# \u1e8f [LATIN SMALL LETTER Y WITH DOT ABOVE]
-"\u1E8F" => "y"
-
-# \u1e99 [LATIN SMALL LETTER Y WITH RING ABOVE]
-"\u1E99" => "y"
-
-# \u1ef3 [LATIN SMALL LETTER Y WITH GRAVE]
-"\u1EF3" => "y"
-
-# \u1ef5 [LATIN SMALL LETTER Y WITH DOT BELOW]
-"\u1EF5" => "y"
-
-# \u1ef7 [LATIN SMALL LETTER Y WITH HOOK ABOVE]
-"\u1EF7" => "y"
-
-# \u1ef9 [LATIN SMALL LETTER Y WITH TILDE]
-"\u1EF9" => "y"
-
-# \u1eff [LATIN SMALL LETTER Y WITH LOOP]
-"\u1EFF" => "y"
-
-# \u24e8 [CIRCLED LATIN SMALL LETTER Y]
-"\u24E8" => "y"
-
-# \uff59 [FULLWIDTH LATIN SMALL LETTER Y]
-"\uFF59" => "y"
-
-# \u24b4 [PARENTHESIZED LATIN SMALL LETTER Y]
-"\u24B4" => "(y)"
-
-# \u0179 [LATIN CAPITAL LETTER Z WITH ACUTE]
-"\u0179" => "Z"
-
-# \u017b [LATIN CAPITAL LETTER Z WITH DOT ABOVE]
-"\u017B" => "Z"
-
-# \u017d [LATIN CAPITAL LETTER Z WITH CARON]
-"\u017D" => "Z"
-
-# \u01b5 [LATIN CAPITAL LETTER Z WITH STROKE]
-"\u01B5" => "Z"
-
-# \u021c http://en.wikipedia.org/wiki/Yogh [LATIN CAPITAL LETTER YOGH]
-"\u021C" => "Z"
-
-# \u0224 [LATIN CAPITAL LETTER Z WITH HOOK]
-"\u0224" => "Z"
-
-# \u1d22 [LATIN LETTER SMALL CAPITAL Z]
-"\u1D22" => "Z"
-
-# \u1e90 [LATIN CAPITAL LETTER Z WITH CIRCUMFLEX]
-"\u1E90" => "Z"
-
-# \u1e92 [LATIN CAPITAL LETTER Z WITH DOT BELOW]
-"\u1E92" => "Z"
-
-# \u1e94 [LATIN CAPITAL LETTER Z WITH LINE BELOW]
-"\u1E94" => "Z"
-
-# \u24cf [CIRCLED LATIN CAPITAL LETTER Z]
-"\u24CF" => "Z"
-
-# \u2c6b [LATIN CAPITAL LETTER Z WITH DESCENDER]
-"\u2C6B" => "Z"
-
-# \ua762 [LATIN CAPITAL LETTER VISIGOTHIC Z]
-"\uA762" => "Z"
-
-# \uff3a [FULLWIDTH LATIN CAPITAL LETTER Z]
-"\uFF3A" => "Z"
-
-# \u017a [LATIN SMALL LETTER Z WITH ACUTE]
-"\u017A" => "z"
-
-# \u017c [LATIN SMALL LETTER Z WITH DOT ABOVE]
-"\u017C" => "z"
-
-# \u017e [LATIN SMALL LETTER Z WITH CARON]
-"\u017E" => "z"
-
-# \u01b6 [LATIN SMALL LETTER Z WITH STROKE]
-"\u01B6" => "z"
-
-# \u021d http://en.wikipedia.org/wiki/Yogh [LATIN SMALL LETTER YOGH]
-"\u021D" => "z"
-
-# \u0225 [LATIN SMALL LETTER Z WITH HOOK]
-"\u0225" => "z"
-
-# \u0240 [LATIN SMALL LETTER Z WITH SWASH TAIL]
-"\u0240" => "z"
-
-# \u0290 [LATIN SMALL LETTER Z WITH RETROFLEX HOOK]
-"\u0290" => "z"
-
-# \u0291 [LATIN SMALL LETTER Z WITH CURL]
-"\u0291" => "z"
-
-# \u1d76 [LATIN SMALL LETTER Z WITH MIDDLE TILDE]
-"\u1D76" => "z"
-
-# \u1d8e [LATIN SMALL LETTER Z WITH PALATAL HOOK]
-"\u1D8E" => "z"
-
-# \u1e91 [LATIN SMALL LETTER Z WITH CIRCUMFLEX]
-"\u1E91" => "z"
-
-# \u1e93 [LATIN SMALL LETTER Z WITH DOT BELOW]
-"\u1E93" => "z"
-
-# \u1e95 [LATIN SMALL LETTER Z WITH LINE BELOW]
-"\u1E95" => "z"
-
-# \u24e9 [CIRCLED LATIN SMALL LETTER Z]
-"\u24E9" => "z"
-
-# \u2c6c [LATIN SMALL LETTER Z WITH DESCENDER]
-"\u2C6C" => "z"
-
-# \ua763 [LATIN SMALL LETTER VISIGOTHIC Z]
-"\uA763" => "z"
-
-# \uff5a [FULLWIDTH LATIN SMALL LETTER Z]
-"\uFF5A" => "z"
-
-# \u24b5 [PARENTHESIZED LATIN SMALL LETTER Z]
-"\u24B5" => "(z)"
-
-# \u2070 [SUPERSCRIPT ZERO]
-"\u2070" => "0"
-
-# \u2080 [SUBSCRIPT ZERO]
-"\u2080" => "0"
-
-# \u24ea [CIRCLED DIGIT ZERO]
-"\u24EA" => "0"
-
-# \u24ff [NEGATIVE CIRCLED DIGIT ZERO]
-"\u24FF" => "0"
-
-# \uff10 [FULLWIDTH DIGIT ZERO]
-"\uFF10" => "0"
-
-# � [SUPERSCRIPT ONE]
-"\u00B9" => "1"
-
-# \u2081 [SUBSCRIPT ONE]
-"\u2081" => "1"
-
-# \u2460 [CIRCLED DIGIT ONE]
-"\u2460" => "1"
-
-# \u24f5 [DOUBLE CIRCLED DIGIT ONE]
-"\u24F5" => "1"
-
-# \u2776 [DINGBAT NEGATIVE CIRCLED DIGIT ONE]
-"\u2776" => "1"
-
-# \u2780 [DINGBAT CIRCLED SANS-SERIF DIGIT ONE]
-"\u2780" => "1"
-
-# \u278a [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE]
-"\u278A" => "1"
-
-# \uff11 [FULLWIDTH DIGIT ONE]
-"\uFF11" => "1"
-
-# \u2488 [DIGIT ONE FULL STOP]
-"\u2488" => "1."
-
-# \u2474 [PARENTHESIZED DIGIT ONE]
-"\u2474" => "(1)"
-
-# � [SUPERSCRIPT TWO]
-"\u00B2" => "2"
-
-# \u2082 [SUBSCRIPT TWO]
-"\u2082" => "2"
-
-# \u2461 [CIRCLED DIGIT TWO]
-"\u2461" => "2"
-
-# \u24f6 [DOUBLE CIRCLED DIGIT TWO]
-"\u24F6" => "2"
-
-# \u2777 [DINGBAT NEGATIVE CIRCLED DIGIT TWO]
-"\u2777" => "2"
-
-# \u2781 [DINGBAT CIRCLED SANS-SERIF DIGIT TWO]
-"\u2781" => "2"
-
-# \u278b [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO]
-"\u278B" => "2"
-
-# \uff12 [FULLWIDTH DIGIT TWO]
-"\uFF12" => "2"
-
-# \u2489 [DIGIT TWO FULL STOP]
-"\u2489" => "2."
-
-# \u2475 [PARENTHESIZED DIGIT TWO]
-"\u2475" => "(2)"
-
-# � [SUPERSCRIPT THREE]
-"\u00B3" => "3"
-
-# \u2083 [SUBSCRIPT THREE]
-"\u2083" => "3"
-
-# \u2462 [CIRCLED DIGIT THREE]
-"\u2462" => "3"
-
-# \u24f7 [DOUBLE CIRCLED DIGIT THREE]
-"\u24F7" => "3"
-
-# \u2778 [DINGBAT NEGATIVE CIRCLED DIGIT THREE]
-"\u2778" => "3"
-
-# \u2782 [DINGBAT CIRCLED SANS-SERIF DIGIT THREE]
-"\u2782" => "3"
-
-# \u278c [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE]
-"\u278C" => "3"
-
-# \uff13 [FULLWIDTH DIGIT THREE]
-"\uFF13" => "3"
-
-# \u248a [DIGIT THREE FULL STOP]
-"\u248A" => "3."
-
-# \u2476 [PARENTHESIZED DIGIT THREE]
-"\u2476" => "(3)"
-
-# \u2074 [SUPERSCRIPT FOUR]
-"\u2074" => "4"
-
-# \u2084 [SUBSCRIPT FOUR]
-"\u2084" => "4"
-
-# \u2463 [CIRCLED DIGIT FOUR]
-"\u2463" => "4"
-
-# \u24f8 [DOUBLE CIRCLED DIGIT FOUR]
-"\u24F8" => "4"
-
-# \u2779 [DINGBAT NEGATIVE CIRCLED DIGIT FOUR]
-"\u2779" => "4"
-
-# \u2783 [DINGBAT CIRCLED SANS-SERIF DIGIT FOUR]
-"\u2783" => "4"
-
-# \u278d [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR]
-"\u278D" => "4"
-
-# \uff14 [FULLWIDTH DIGIT FOUR]
-"\uFF14" => "4"
-
-# \u248b [DIGIT FOUR FULL STOP]
-"\u248B" => "4."
-
-# \u2477 [PARENTHESIZED DIGIT FOUR]
-"\u2477" => "(4)"
-
-# \u2075 [SUPERSCRIPT FIVE]
-"\u2075" => "5"
-
-# \u2085 [SUBSCRIPT FIVE]
-"\u2085" => "5"
-
-# \u2464 [CIRCLED DIGIT FIVE]
-"\u2464" => "5"
-
-# \u24f9 [DOUBLE CIRCLED DIGIT FIVE]
-"\u24F9" => "5"
-
-# \u277a [DINGBAT NEGATIVE CIRCLED DIGIT FIVE]
-"\u277A" => "5"
-
-# \u2784 [DINGBAT CIRCLED SANS-SERIF DIGIT FIVE]
-"\u2784" => "5"
-
-# \u278e [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE]
-"\u278E" => "5"
-
-# \uff15 [FULLWIDTH DIGIT FIVE]
-"\uFF15" => "5"
-
-# \u248c [DIGIT FIVE FULL STOP]
-"\u248C" => "5."
-
-# \u2478 [PARENTHESIZED DIGIT FIVE]
-"\u2478" => "(5)"
-
-# \u2076 [SUPERSCRIPT SIX]
-"\u2076" => "6"
-
-# \u2086 [SUBSCRIPT SIX]
-"\u2086" => "6"
-
-# \u2465 [CIRCLED DIGIT SIX]
-"\u2465" => "6"
-
-# \u24fa [DOUBLE CIRCLED DIGIT SIX]
-"\u24FA" => "6"
-
-# \u277b [DINGBAT NEGATIVE CIRCLED DIGIT SIX]
-"\u277B" => "6"
-
-# \u2785 [DINGBAT CIRCLED SANS-SERIF DIGIT SIX]
-"\u2785" => "6"
-
-# \u278f [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX]
-"\u278F" => "6"
-
-# \uff16 [FULLWIDTH DIGIT SIX]
-"\uFF16" => "6"
-
-# \u248d [DIGIT SIX FULL STOP]
-"\u248D" => "6."
-
-# \u2479 [PARENTHESIZED DIGIT SIX]
-"\u2479" => "(6)"
-
-# \u2077 [SUPERSCRIPT SEVEN]
-"\u2077" => "7"
-
-# \u2087 [SUBSCRIPT SEVEN]
-"\u2087" => "7"
-
-# \u2466 [CIRCLED DIGIT SEVEN]
-"\u2466" => "7"
-
-# \u24fb [DOUBLE CIRCLED DIGIT SEVEN]
-"\u24FB" => "7"
-
-# \u277c [DINGBAT NEGATIVE CIRCLED DIGIT SEVEN]
-"\u277C" => "7"
-
-# \u2786 [DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN]
-"\u2786" => "7"
-
-# \u2790 [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN]
-"\u2790" => "7"
-
-# \uff17 [FULLWIDTH DIGIT SEVEN]
-"\uFF17" => "7"
-
-# \u248e [DIGIT SEVEN FULL STOP]
-"\u248E" => "7."
-
-# \u247a [PARENTHESIZED DIGIT SEVEN]
-"\u247A" => "(7)"
-
-# \u2078 [SUPERSCRIPT EIGHT]
-"\u2078" => "8"
-
-# \u2088 [SUBSCRIPT EIGHT]
-"\u2088" => "8"
-
-# \u2467 [CIRCLED DIGIT EIGHT]
-"\u2467" => "8"
-
-# \u24fc [DOUBLE CIRCLED DIGIT EIGHT]
-"\u24FC" => "8"
-
-# \u277d [DINGBAT NEGATIVE CIRCLED DIGIT EIGHT]
-"\u277D" => "8"
-
-# \u2787 [DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT]
-"\u2787" => "8"
-
-# \u2791 [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT]
-"\u2791" => "8"
-
-# \uff18 [FULLWIDTH DIGIT EIGHT]
-"\uFF18" => "8"
-
-# \u248f [DIGIT EIGHT FULL STOP]
-"\u248F" => "8."
-
-# \u247b [PARENTHESIZED DIGIT EIGHT]
-"\u247B" => "(8)"
-
-# \u2079 [SUPERSCRIPT NINE]
-"\u2079" => "9"
-
-# \u2089 [SUBSCRIPT NINE]
-"\u2089" => "9"
-
-# \u2468 [CIRCLED DIGIT NINE]
-"\u2468" => "9"
-
-# \u24fd [DOUBLE CIRCLED DIGIT NINE]
-"\u24FD" => "9"
-
-# \u277e [DINGBAT NEGATIVE CIRCLED DIGIT NINE]
-"\u277E" => "9"
-
-# \u2788 [DINGBAT CIRCLED SANS-SERIF DIGIT NINE]
-"\u2788" => "9"
-
-# \u2792 [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE]
-"\u2792" => "9"
-
-# \uff19 [FULLWIDTH DIGIT NINE]
-"\uFF19" => "9"
-
-# \u2490 [DIGIT NINE FULL STOP]
-"\u2490" => "9."
-
-# \u247c [PARENTHESIZED DIGIT NINE]
-"\u247C" => "(9)"
-
-# \u2469 [CIRCLED NUMBER TEN]
-"\u2469" => "10"
-
-# \u24fe [DOUBLE CIRCLED NUMBER TEN]
-"\u24FE" => "10"
-
-# \u277f [DINGBAT NEGATIVE CIRCLED NUMBER TEN]
-"\u277F" => "10"
-
-# \u2789 [DINGBAT CIRCLED SANS-SERIF NUMBER TEN]
-"\u2789" => "10"
-
-# \u2793 [DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN]
-"\u2793" => "10"
-
-# \u2491 [NUMBER TEN FULL STOP]
-"\u2491" => "10."
-
-# \u247d [PARENTHESIZED NUMBER TEN]
-"\u247D" => "(10)"
-
-# \u246a [CIRCLED NUMBER ELEVEN]
-"\u246A" => "11"
-
-# \u24eb [NEGATIVE CIRCLED NUMBER ELEVEN]
-"\u24EB" => "11"
-
-# \u2492 [NUMBER ELEVEN FULL STOP]
-"\u2492" => "11."
-
-# \u247e [PARENTHESIZED NUMBER ELEVEN]
-"\u247E" => "(11)"
-
-# \u246b [CIRCLED NUMBER TWELVE]
-"\u246B" => "12"
-
-# \u24ec [NEGATIVE CIRCLED NUMBER TWELVE]
-"\u24EC" => "12"
-
-# \u2493 [NUMBER TWELVE FULL STOP]
-"\u2493" => "12."
-
-# \u247f [PARENTHESIZED NUMBER TWELVE]
-"\u247F" => "(12)"
-
-# \u246c [CIRCLED NUMBER THIRTEEN]
-"\u246C" => "13"
-
-# \u24ed [NEGATIVE CIRCLED NUMBER THIRTEEN]
-"\u24ED" => "13"
-
-# \u2494 [NUMBER THIRTEEN FULL STOP]
-"\u2494" => "13."
-
-# \u2480 [PARENTHESIZED NUMBER THIRTEEN]
-"\u2480" => "(13)"
-
-# \u246d [CIRCLED NUMBER FOURTEEN]
-"\u246D" => "14"
-
-# \u24ee [NEGATIVE CIRCLED NUMBER FOURTEEN]
-"\u24EE" => "14"
-
-# \u2495 [NUMBER FOURTEEN FULL STOP]
-"\u2495" => "14."
-
-# \u2481 [PARENTHESIZED NUMBER FOURTEEN]
-"\u2481" => "(14)"
-
-# \u246e [CIRCLED NUMBER FIFTEEN]
-"\u246E" => "15"
-
-# \u24ef [NEGATIVE CIRCLED NUMBER FIFTEEN]
-"\u24EF" => "15"
-
-# \u2496 [NUMBER FIFTEEN FULL STOP]
-"\u2496" => "15."
-
-# \u2482 [PARENTHESIZED NUMBER FIFTEEN]
-"\u2482" => "(15)"
-
-# \u246f [CIRCLED NUMBER SIXTEEN]
-"\u246F" => "16"
-
-# \u24f0 [NEGATIVE CIRCLED NUMBER SIXTEEN]
-"\u24F0" => "16"
-
-# \u2497 [NUMBER SIXTEEN FULL STOP]
-"\u2497" => "16."
-
-# \u2483 [PARENTHESIZED NUMBER SIXTEEN]
-"\u2483" => "(16)"
-
-# \u2470 [CIRCLED NUMBER SEVENTEEN]
-"\u2470" => "17"
-
-# \u24f1 [NEGATIVE CIRCLED NUMBER SEVENTEEN]
-"\u24F1" => "17"
-
-# \u2498 [NUMBER SEVENTEEN FULL STOP]
-"\u2498" => "17."
-
-# \u2484 [PARENTHESIZED NUMBER SEVENTEEN]
-"\u2484" => "(17)"
-
-# \u2471 [CIRCLED NUMBER EIGHTEEN]
-"\u2471" => "18"
-
-# \u24f2 [NEGATIVE CIRCLED NUMBER EIGHTEEN]
-"\u24F2" => "18"
-
-# \u2499 [NUMBER EIGHTEEN FULL STOP]
-"\u2499" => "18."
-
-# \u2485 [PARENTHESIZED NUMBER EIGHTEEN]
-"\u2485" => "(18)"
-
-# \u2472 [CIRCLED NUMBER NINETEEN]
-"\u2472" => "19"
-
-# \u24f3 [NEGATIVE CIRCLED NUMBER NINETEEN]
-"\u24F3" => "19"
-
-# \u249a [NUMBER NINETEEN FULL STOP]
-"\u249A" => "19."
-
-# \u2486 [PARENTHESIZED NUMBER NINETEEN]
-"\u2486" => "(19)"
-
-# \u2473 [CIRCLED NUMBER TWENTY]
-"\u2473" => "20"
-
-# \u24f4 [NEGATIVE CIRCLED NUMBER TWENTY]
-"\u24F4" => "20"
-
-# \u249b [NUMBER TWENTY FULL STOP]
-"\u249B" => "20."
-
-# \u2487 [PARENTHESIZED NUMBER TWENTY]
-"\u2487" => "(20)"
-
-# � [LEFT-POINTING DOUBLE ANGLE QUOTATION MARK]
-"\u00AB" => "\""
-
-# � [RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK]
-"\u00BB" => "\""
-
-# \u201c [LEFT DOUBLE QUOTATION MARK]
-"\u201C" => "\""
-
-# \u201d [RIGHT DOUBLE QUOTATION MARK]
-"\u201D" => "\""
-
-# \u201e [DOUBLE LOW-9 QUOTATION MARK]
-"\u201E" => "\""
-
-# \u2033 [DOUBLE PRIME]
-"\u2033" => "\""
-
-# \u2036 [REVERSED DOUBLE PRIME]
-"\u2036" => "\""
-
-# \u275d [HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT]
-"\u275D" => "\""
-
-# \u275e [HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT]
-"\u275E" => "\""
-
-# \u276e [HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT]
-"\u276E" => "\""
-
-# \u276f [HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT]
-"\u276F" => "\""
-
-# \uff02 [FULLWIDTH QUOTATION MARK]
-"\uFF02" => "\""
-
-# \u2018 [LEFT SINGLE QUOTATION MARK]
-"\u2018" => "\'"
-
-# \u2019 [RIGHT SINGLE QUOTATION MARK]
-"\u2019" => "\'"
-
-# \u201a [SINGLE LOW-9 QUOTATION MARK]
-"\u201A" => "\'"
-
-# \u201b [SINGLE HIGH-REVERSED-9 QUOTATION MARK]
-"\u201B" => "\'"
-
-# \u2032 [PRIME]
-"\u2032" => "\'"
-
-# \u2035 [REVERSED PRIME]
-"\u2035" => "\'"
-
-# \u2039 [SINGLE LEFT-POINTING ANGLE QUOTATION MARK]
-"\u2039" => "\'"
-
-# \u203a [SINGLE RIGHT-POINTING ANGLE QUOTATION MARK]
-"\u203A" => "\'"
-
-# \u275b [HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT]
-"\u275B" => "\'"
-
-# \u275c [HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT]
-"\u275C" => "\'"
-
-# \uff07 [FULLWIDTH APOSTROPHE]
-"\uFF07" => "\'"
-
-# \u2010 [HYPHEN]
-"\u2010" => "-"
-
-# \u2011 [NON-BREAKING HYPHEN]
-"\u2011" => "-"
-
-# \u2012 [FIGURE DASH]
-"\u2012" => "-"
-
-# \u2013 [EN DASH]
-"\u2013" => "-"
-
-# \u2014 [EM DASH]
-"\u2014" => "-"
-
-# \u207b [SUPERSCRIPT MINUS]
-"\u207B" => "-"
-
-# \u208b [SUBSCRIPT MINUS]
-"\u208B" => "-"
-
-# \uff0d [FULLWIDTH HYPHEN-MINUS]
-"\uFF0D" => "-"
-
-# \u2045 [LEFT SQUARE BRACKET WITH QUILL]
-"\u2045" => "["
-
-# \u2772 [LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT]
-"\u2772" => "["
-
-# \uff3b [FULLWIDTH LEFT SQUARE BRACKET]
-"\uFF3B" => "["
-
-# \u2046 [RIGHT SQUARE BRACKET WITH QUILL]
-"\u2046" => "]"
-
-# \u2773 [LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT]
-"\u2773" => "]"
-
-# \uff3d [FULLWIDTH RIGHT SQUARE BRACKET]
-"\uFF3D" => "]"
-
-# \u207d [SUPERSCRIPT LEFT PARENTHESIS]
-"\u207D" => "("
-
-# \u208d [SUBSCRIPT LEFT PARENTHESIS]
-"\u208D" => "("
-
-# \u2768 [MEDIUM LEFT PARENTHESIS ORNAMENT]
-"\u2768" => "("
-
-# \u276a [MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT]
-"\u276A" => "("
-
-# \uff08 [FULLWIDTH LEFT PARENTHESIS]
-"\uFF08" => "("
-
-# \u2e28 [LEFT DOUBLE PARENTHESIS]
-"\u2E28" => "(("
-
-# \u207e [SUPERSCRIPT RIGHT PARENTHESIS]
-"\u207E" => ")"
-
-# \u208e [SUBSCRIPT RIGHT PARENTHESIS]
-"\u208E" => ")"
-
-# \u2769 [MEDIUM RIGHT PARENTHESIS ORNAMENT]
-"\u2769" => ")"
-
-# \u276b [MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT]
-"\u276B" => ")"
-
-# \uff09 [FULLWIDTH RIGHT PARENTHESIS]
-"\uFF09" => ")"
-
-# \u2e29 [RIGHT DOUBLE PARENTHESIS]
-"\u2E29" => "))"
-
-# \u276c [MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT]
-"\u276C" => "<"
-
-# \u2770 [HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT]
-"\u2770" => "<"
-
-# \uff1c [FULLWIDTH LESS-THAN SIGN]
-"\uFF1C" => "<"
-
-# \u276d [MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT]
-"\u276D" => ">"
-
-# \u2771 [HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT]
-"\u2771" => ">"
-
-# \uff1e [FULLWIDTH GREATER-THAN SIGN]
-"\uFF1E" => ">"
-
-# \u2774 [MEDIUM LEFT CURLY BRACKET ORNAMENT]
-"\u2774" => "{"
-
-# \uff5b [FULLWIDTH LEFT CURLY BRACKET]
-"\uFF5B" => "{"
-
-# \u2775 [MEDIUM RIGHT CURLY BRACKET ORNAMENT]
-"\u2775" => "}"
-
-# \uff5d [FULLWIDTH RIGHT CURLY BRACKET]
-"\uFF5D" => "}"
-
-# \u207a [SUPERSCRIPT PLUS SIGN]
-"\u207A" => "+"
-
-# \u208a [SUBSCRIPT PLUS SIGN]
-"\u208A" => "+"
-
-# \uff0b [FULLWIDTH PLUS SIGN]
-"\uFF0B" => "+"
-
-# \u207c [SUPERSCRIPT EQUALS SIGN]
-"\u207C" => "="
-
-# \u208c [SUBSCRIPT EQUALS SIGN]
-"\u208C" => "="
-
-# \uff1d [FULLWIDTH EQUALS SIGN]
-"\uFF1D" => "="
-
-# \uff01 [FULLWIDTH EXCLAMATION MARK]
-"\uFF01" => "!"
-
-# \u203c [DOUBLE EXCLAMATION MARK]
-"\u203C" => "!!"
-
-# \u2049 [EXCLAMATION QUESTION MARK]
-"\u2049" => "!?"
-
-# \uff03 [FULLWIDTH NUMBER SIGN]
-"\uFF03" => "#"
-
-# \uff04 [FULLWIDTH DOLLAR SIGN]
-"\uFF04" => "$"
-
-# \u2052 [COMMERCIAL MINUS SIGN]
-"\u2052" => "%"
-
-# \uff05 [FULLWIDTH PERCENT SIGN]
-"\uFF05" => "%"
-
-# \uff06 [FULLWIDTH AMPERSAND]
-"\uFF06" => "&"
-
-# \u204e [LOW ASTERISK]
-"\u204E" => "*"
-
-# \uff0a [FULLWIDTH ASTERISK]
-"\uFF0A" => "*"
-
-# \uff0c [FULLWIDTH COMMA]
-"\uFF0C" => ","
-
-# \uff0e [FULLWIDTH FULL STOP]
-"\uFF0E" => "."
-
-# \u2044 [FRACTION SLASH]
-"\u2044" => "/"
-
-# \uff0f [FULLWIDTH SOLIDUS]
-"\uFF0F" => "/"
-
-# \uff1a [FULLWIDTH COLON]
-"\uFF1A" => ":"
-
-# \u204f [REVERSED SEMICOLON]
-"\u204F" => ";"
-
-# \uff1b [FULLWIDTH SEMICOLON]
-"\uFF1B" => ";"
-
-# \uff1f [FULLWIDTH QUESTION MARK]
-"\uFF1F" => "?"
-
-# \u2047 [DOUBLE QUESTION MARK]
-"\u2047" => "??"
-
-# \u2048 [QUESTION EXCLAMATION MARK]
-"\u2048" => "?!"
-
-# \uff20 [FULLWIDTH COMMERCIAL AT]
-"\uFF20" => "@"
-
-# \uff3c [FULLWIDTH REVERSE SOLIDUS]
-"\uFF3C" => "\\"
-
-# \u2038 [CARET]
-"\u2038" => "^"
-
-# \uff3e [FULLWIDTH CIRCUMFLEX ACCENT]
-"\uFF3E" => "^"
-
-# \uff3f [FULLWIDTH LOW LINE]
-"\uFF3F" => "_"
-
-# \u2053 [SWUNG DASH]
-"\u2053" => "~"
-
-# \uff5e [FULLWIDTH TILDE]
-"\uFF5E" => "~"
-
-################################################################
-# Below is the Perl script used to generate the above mappings #
-# from ASCIIFoldingFilter.java: #
-################################################################
-#
-# #!/usr/bin/perl
-#
-# use warnings;
-# use strict;
-#
-# my @source_chars = ();
-# my @source_char_descriptions = ();
-# my $target = '';
-#
-# while (<>) {
-# if (/case\s+'(\\u[A-F0-9]+)':\s*\/\/\s*(.*)/i) {
-# push @source_chars, $1;
-# push @source_char_descriptions, $2;
-# next;
-# }
-# if (/output\[[^\]]+\]\s*=\s*'(\\'|\\\\|.)'/) {
-# $target .= $1;
-# next;
-# }
-# if (/break;/) {
-# $target = "\\\"" if ($target eq '"');
-# for my $source_char_num (0..$#source_chars) {
-# print "# $source_char_descriptions[$source_char_num]\n";
-# print "\"$source_chars[$source_char_num]\" => \"$target\"\n\n";
-# }
-# @source_chars = ();
-# @source_char_descriptions = ();
-# $target = '';
-# }
-# }
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/mapping-ISOLatin1Accent.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/mapping-ISOLatin1Accent.txt b/solr/example/example-DIH/solr/rss/conf/mapping-ISOLatin1Accent.txt
deleted file mode 100644
index ede7742..0000000
--- a/solr/example/example-DIH/solr/rss/conf/mapping-ISOLatin1Accent.txt
+++ /dev/null
@@ -1,246 +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.
-
-# Syntax:
-# "source" => "target"
-# "source".length() > 0 (source cannot be empty.)
-# "target".length() >= 0 (target can be empty.)
-
-# example:
-# "�" => "A"
-# "\u00C0" => "A"
-# "\u00C0" => "\u0041"
-# "�" => "ss"
-# "\t" => " "
-# "\n" => ""
-
-# � => A
-"\u00C0" => "A"
-
-# � => A
-"\u00C1" => "A"
-
-# � => A
-"\u00C2" => "A"
-
-# � => A
-"\u00C3" => "A"
-
-# � => A
-"\u00C4" => "A"
-
-# � => A
-"\u00C5" => "A"
-
-# � => AE
-"\u00C6" => "AE"
-
-# � => C
-"\u00C7" => "C"
-
-# � => E
-"\u00C8" => "E"
-
-# � => E
-"\u00C9" => "E"
-
-# � => E
-"\u00CA" => "E"
-
-# � => E
-"\u00CB" => "E"
-
-# � => I
-"\u00CC" => "I"
-
-# � => I
-"\u00CD" => "I"
-
-# � => I
-"\u00CE" => "I"
-
-# � => I
-"\u00CF" => "I"
-
-# \u0132 => IJ
-"\u0132" => "IJ"
-
-# � => D
-"\u00D0" => "D"
-
-# � => N
-"\u00D1" => "N"
-
-# � => O
-"\u00D2" => "O"
-
-# � => O
-"\u00D3" => "O"
-
-# � => O
-"\u00D4" => "O"
-
-# � => O
-"\u00D5" => "O"
-
-# � => O
-"\u00D6" => "O"
-
-# � => O
-"\u00D8" => "O"
-
-# \u0152 => OE
-"\u0152" => "OE"
-
-# �
-"\u00DE" => "TH"
-
-# � => U
-"\u00D9" => "U"
-
-# � => U
-"\u00DA" => "U"
-
-# � => U
-"\u00DB" => "U"
-
-# � => U
-"\u00DC" => "U"
-
-# � => Y
-"\u00DD" => "Y"
-
-# \u0178 => Y
-"\u0178" => "Y"
-
-# � => a
-"\u00E0" => "a"
-
-# � => a
-"\u00E1" => "a"
-
-# � => a
-"\u00E2" => "a"
-
-# � => a
-"\u00E3" => "a"
-
-# � => a
-"\u00E4" => "a"
-
-# � => a
-"\u00E5" => "a"
-
-# � => ae
-"\u00E6" => "ae"
-
-# � => c
-"\u00E7" => "c"
-
-# � => e
-"\u00E8" => "e"
-
-# � => e
-"\u00E9" => "e"
-
-# � => e
-"\u00EA" => "e"
-
-# � => e
-"\u00EB" => "e"
-
-# � => i
-"\u00EC" => "i"
-
-# � => i
-"\u00ED" => "i"
-
-# � => i
-"\u00EE" => "i"
-
-# � => i
-"\u00EF" => "i"
-
-# \u0133 => ij
-"\u0133" => "ij"
-
-# � => d
-"\u00F0" => "d"
-
-# � => n
-"\u00F1" => "n"
-
-# � => o
-"\u00F2" => "o"
-
-# � => o
-"\u00F3" => "o"
-
-# � => o
-"\u00F4" => "o"
-
-# � => o
-"\u00F5" => "o"
-
-# � => o
-"\u00F6" => "o"
-
-# � => o
-"\u00F8" => "o"
-
-# \u0153 => oe
-"\u0153" => "oe"
-
-# � => ss
-"\u00DF" => "ss"
-
-# � => th
-"\u00FE" => "th"
-
-# � => u
-"\u00F9" => "u"
-
-# � => u
-"\u00FA" => "u"
-
-# � => u
-"\u00FB" => "u"
-
-# � => u
-"\u00FC" => "u"
-
-# � => y
-"\u00FD" => "y"
-
-# � => y
-"\u00FF" => "y"
-
-# \ufb00 => ff
-"\uFB00" => "ff"
-
-# \ufb01 => fi
-"\uFB01" => "fi"
-
-# \ufb02 => fl
-"\uFB02" => "fl"
-
-# \ufb03 => ffi
-"\uFB03" => "ffi"
-
-# \ufb04 => ffl
-"\uFB04" => "ffl"
-
-# \ufb05 => ft
-"\uFB05" => "ft"
-
-# \ufb06 => st
-"\uFB06" => "st"
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/protwords.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/protwords.txt b/solr/example/example-DIH/solr/rss/conf/protwords.txt
deleted file mode 100644
index 1dfc0ab..0000000
--- a/solr/example/example-DIH/solr/rss/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
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/rss-data-config.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/rss-data-config.xml b/solr/example/example-DIH/solr/rss/conf/rss-data-config.xml
deleted file mode 100644
index 704325b..0000000
--- a/solr/example/example-DIH/solr/rss/conf/rss-data-config.xml
+++ /dev/null
@@ -1,26 +0,0 @@
-<dataConfig>
- <dataSource type="URLDataSource" />
- <document>
- <entity name="slashdot"
- pk="link"
- url="http://rss.slashdot.org/Slashdot/slashdot"
- processor="XPathEntityProcessor"
- forEach="/rss/channel/item"
- transformer="DateFormatTransformer">
-
- <field column="source" xpath="/rss/channel/title" commonField="true" />
- <field column="source-link" xpath="/rss/channel/link" commonField="true" />
- <field column="subject" xpath="/rss/channel/subject" commonField="true" />
-
- <field column="title" xpath="/rss/channel/item/title" />
- <field column="link" xpath="/rss/channel/item/link" />
- <field column="description" xpath="/rss/channel/item/description" />
- <field column="creator" xpath="/rss/channel/item/creator" />
- <field column="item-subject" xpath="/rss/channel/item/subject" />
- <field column="date" xpath="/rss/channel/item/date" dateTimeFormat="yyyy-MM-dd'T'HH:mm:ss" />
- <field column="slash-department" xpath="/rss/channel/item/department" />
- <field column="slash-section" xpath="/rss/channel/item/section" />
- <field column="slash-comments" xpath="/rss/channel/item/comments" />
- </entity>
- </document>
-</dataConfig>
[5/6] lucene-solr:master: SOLR-7383: Replace DIH 'rss' example with
'atom' rss example was broken for multiple reasons. atom example showcases
the same - and more - features and uses the smallest config file needed to
make it work.
Posted by ar...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_es.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_es.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_es.txt
deleted file mode 100644
index 487d78c..0000000
--- a/solr/example/example-DIH/solr/rss/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
-m�s | more
-pero | pero
-sus | su plural
-le | to him, her
-ya | already
-o | or
- | fue from SER
-este | this
- | ha from HABER
-s� | himself etc
-porque | because
-esta | this
- | son from SER
-entre | between
- | est� from ESTAR
-cuando | when
-muy | very
-sin | without
-sobre | on
- | ser from SER
- | tiene from TENER
-tambi�n | also
-me | me
-hasta | until
-hay | there is/are
-donde | where
- | han from HABER
-quien | whom, that
- | est�n 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
- | hab�a from HABER
-ante | before
-ellos | they
-e | and (variant of y)
-esto | this
-m� | me
-antes | before
-algunos | some
-qu� | what?
-unos | a
-yo | I
-otro | other
-otras | other
-otra | other
-�l | 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
-t� | thou
-te | thee
-ti | thee
-tu | thy
-tus | tu plural
-ellas | they
-nosotras | we
-vosotros | you
-vosotras | you
-os | you
-m�o | mine
-m�a |
-m�os |
-m�as |
-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
-est�s
-est�
-estamos
-est�is
-est�n
-est�
-est�s
-estemos
-est�is
-est�n
-estar�
-estar�s
-estar�
-estaremos
-estar�is
-estar�n
-estar�a
-estar�as
-estar�amos
-estar�ais
-estar�an
-estaba
-estabas
-est�bamos
-estabais
-estaban
-estuve
-estuviste
-estuvo
-estuvimos
-estuvisteis
-estuvieron
-estuviera
-estuvieras
-estuvi�ramos
-estuvierais
-estuvieran
-estuviese
-estuvieses
-estuvi�semos
-estuvieseis
-estuviesen
-estando
-estado
-estada
-estados
-estadas
-estad
-
- | forms of haber, to have (not including the infinitive):
-he
-has
-ha
-hemos
-hab�is
-han
-haya
-hayas
-hayamos
-hay�is
-hayan
-habr�
-habr�s
-habr�
-habremos
-habr�is
-habr�n
-habr�a
-habr�as
-habr�amos
-habr�ais
-habr�an
-hab�a
-hab�as
-hab�amos
-hab�ais
-hab�an
-hube
-hubiste
-hubo
-hubimos
-hubisteis
-hubieron
-hubiera
-hubieras
-hubi�ramos
-hubierais
-hubieran
-hubiese
-hubieses
-hubi�semos
-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
-se�is
-sean
-ser�
-ser�s
-ser�
-seremos
-ser�is
-ser�n
-ser�a
-ser�as
-ser�amos
-ser�ais
-ser�an
-era
-eras
-�ramos
-erais
-eran
-fui
-fuiste
-fue
-fuimos
-fuisteis
-fueron
-fuera
-fueras
-fu�ramos
-fuerais
-fueran
-fuese
-fueses
-fu�semos
-fueseis
-fuesen
-siendo
-sido
- | sed also means 'thirst'
-
- | forms of tener, to have (not including the infinitive):
-tengo
-tienes
-tiene
-tenemos
-ten�is
-tienen
-tenga
-tengas
-tengamos
-teng�is
-tengan
-tendr�
-tendr�s
-tendr�
-tendremos
-tendr�is
-tendr�n
-tendr�a
-tendr�as
-tendr�amos
-tendr�ais
-tendr�an
-ten�a
-ten�as
-ten�amos
-ten�ais
-ten�an
-tuve
-tuviste
-tuvo
-tuvimos
-tuvisteis
-tuvieron
-tuviera
-tuvieras
-tuvi�ramos
-tuvierais
-tuvieran
-tuviese
-tuvieses
-tuvi�semos
-tuvieseis
-tuviesen
-teniendo
-tenido
-tenida
-tenidos
-tenidas
-tened
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_eu.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_eu.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_eu.txt
deleted file mode 100644
index 25f1db9..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_fa.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_fa.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_fa.txt
deleted file mode 100644
index 723641c..0000000
--- a/solr/example/example-DIH/solr/rss/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 '\u064a' instead of '\u06cc'
-\u0627\u0646\u0627\u0646
-\u0646\u062f\u0627\u0634\u062a\u0647
-\u0633\u0631\u0627\u0633\u0631
-\u062e\u064a\u0627\u0647
-\u0627\u064a\u0634\u0627\u0646
-\u0648\u064a
-\u062a\u0627\u0643\u0646\u0648\u0646
-\u0628\u064a\u0634\u062a\u0631\u064a
-\u062f\u0648\u0645
-\u067e\u0633
-\u0646\u0627\u0634\u064a
-\u0648\u06af\u0648
-\u064a\u0627
-\u062f\u0627\u0634\u062a\u0646\u062f
-\u0633\u067e\u0633
-\u0647\u0646\u06af\u0627\u0645
-\u0647\u0631\u06af\u0632
-\u067e\u0646\u062c
-\u0646\u0634\u0627\u0646
-\u0627\u0645\u0633\u0627\u0644
-\u062f\u064a\u06af\u0631
-\u06af\u0631\u0648\u0647\u064a
-\u0634\u062f\u0646\u062f
-\u0686\u0637\u0648\u0631
-\u062f\u0647
-\u0648
-\u062f\u0648
-\u0646\u062e\u0633\u062a\u064a\u0646
-\u0648\u0644\u064a
-\u0686\u0631\u0627
-\u0686\u0647
-\u0648\u0633\u0637
-\u0647
-\u0643\u062f\u0627\u0645
-\u0642\u0627\u0628\u0644
-\u064a\u0643
-\u0631\u0641\u062a
-\u0647\u0641\u062a
-\u0647\u0645\u0686\u0646\u064a\u0646
-\u062f\u0631
-\u0647\u0632\u0627\u0631
-\u0628\u0644\u0647
-\u0628\u0644\u064a
-\u0634\u0627\u064a\u062f
-\u0627\u0645\u0627
-\u0634\u0646\u0627\u0633\u064a
-\u06af\u0631\u0641\u062a\u0647
-\u062f\u0647\u062f
-\u062f\u0627\u0634\u062a\u0647
-\u062f\u0627\u0646\u0633\u062a
-\u062f\u0627\u0634\u062a\u0646
-\u062e\u0648\u0627\u0647\u064a\u0645
-\u0645\u064a\u0644\u064a\u0627\u0631\u062f
-\u0648\u0642\u062a\u064a\u0643\u0647
-\u0627\u0645\u062f
-\u062e\u0648\u0627\u0647\u062f
-\u062c\u0632
-\u0627\u0648\u0631\u062f\u0647
-\u0634\u062f\u0647
-\u0628\u0644\u0643\u0647
-\u062e\u062f\u0645\u0627\u062a
-\u0634\u062f\u0646
-\u0628\u0631\u062e\u064a
-\u0646\u0628\u0648\u062f
-\u0628\u0633\u064a\u0627\u0631\u064a
-\u062c\u0644\u0648\u06af\u064a\u0631\u064a
-\u062d\u0642
-\u0643\u0631\u062f\u0646\u062f
-\u0646\u0648\u0639\u064a
-\u0628\u0639\u0631\u064a
-\u0646\u0643\u0631\u062f\u0647
-\u0646\u0638\u064a\u0631
-\u0646\u0628\u0627\u064a\u062f
-\u0628\u0648\u062f\u0647
-\u0628\u0648\u062f\u0646
-\u062f\u0627\u062f
-\u0627\u0648\u0631\u062f
-\u0647\u0633\u062a
-\u062c\u0627\u064a\u064a
-\u0634\u0648\u062f
-\u062f\u0646\u0628\u0627\u0644
-\u062f\u0627\u062f\u0647
-\u0628\u0627\u064a\u062f
-\u0633\u0627\u0628\u0642
-\u0647\u064a\u0686
-\u0647\u0645\u0627\u0646
-\u0627\u0646\u062c\u0627
-\u0643\u0645\u062a\u0631
-\u0643\u062c\u0627\u0633\u062a
-\u06af\u0631\u062f\u062f
-\u0643\u0633\u064a
-\u062a\u0631
-\u0645\u0631\u062f\u0645
-\u062a\u0627\u0646
-\u062f\u0627\u062f\u0646
-\u0628\u0648\u062f\u0646\u062f
-\u0633\u0631\u064a
-\u062c\u062f\u0627
-\u0646\u062f\u0627\u0631\u0646\u062f
-\u0645\u06af\u0631
-\u064a\u0643\u062f\u064a\u06af\u0631
-\u062f\u0627\u0631\u062f
-\u062f\u0647\u0646\u062f
-\u0628\u0646\u0627\u0628\u0631\u0627\u064a\u0646
-\u0647\u0646\u06af\u0627\u0645\u064a
-\u0633\u0645\u062a
-\u062c\u0627
-\u0627\u0646\u0686\u0647
-\u062e\u0648\u062f
-\u062f\u0627\u062f\u0646\u062f
-\u0632\u064a\u0627\u062f
-\u062f\u0627\u0631\u0646\u062f
-\u0627\u062b\u0631
-\u0628\u062f\u0648\u0646
-\u0628\u0647\u062a\u0631\u064a\u0646
-\u0628\u064a\u0634\u062a\u0631
-\u0627\u0644\u0628\u062a\u0647
-\u0628\u0647
-\u0628\u0631\u0627\u0633\u0627\u0633
-\u0628\u064a\u0631\u0648\u0646
-\u0643\u0631\u062f
-\u0628\u0639\u0636\u064a
-\u06af\u0631\u0641\u062a
-\u062a\u0648\u064a
-\u0627\u064a
-\u0645\u064a\u0644\u064a\u0648\u0646
-\u0627\u0648
-\u062c\u0631\u064a\u0627\u0646
-\u062a\u0648\u0644
-\u0628\u0631
-\u0645\u0627\u0646\u0646\u062f
-\u0628\u0631\u0627\u0628\u0631
-\u0628\u0627\u0634\u064a\u0645
-\u0645\u062f\u062a\u064a
-\u06af\u0648\u064a\u0646\u062f
-\u0627\u0643\u0646\u0648\u0646
-\u062a\u0627
-\u062a\u0646\u0647\u0627
-\u062c\u062f\u064a\u062f
-\u0686\u0646\u062f
-\u0628\u064a
-\u0646\u0634\u062f\u0647
-\u0643\u0631\u062f\u0646
-\u0643\u0631\u062f\u0645
-\u06af\u0648\u064a\u062f
-\u0643\u0631\u062f\u0647
-\u0643\u0646\u064a\u0645
-\u0646\u0645\u064a
-\u0646\u0632\u062f
-\u0631\u0648\u064a
-\u0642\u0635\u062f
-\u0641\u0642\u0637
-\u0628\u0627\u0644\u0627\u064a
-\u062f\u064a\u06af\u0631\u0627\u0646
-\u0627\u064a\u0646
-\u062f\u064a\u0631\u0648\u0632
-\u062a\u0648\u0633\u0637
-\u0633\u0648\u0645
-\u0627\u064a\u0645
-\u062f\u0627\u0646\u0646\u062f
-\u0633\u0648\u064a
-\u0627\u0633\u062a\u0641\u0627\u062f\u0647
-\u0634\u0645\u0627
-\u0643\u0646\u0627\u0631
-\u062f\u0627\u0631\u064a\u0645
-\u0633\u0627\u062e\u062a\u0647
-\u0637\u0648\u0631
-\u0627\u0645\u062f\u0647
-\u0631\u0641\u062a\u0647
-\u0646\u062e\u0633\u062a
-\u0628\u064a\u0633\u062a
-\u0646\u0632\u062f\u064a\u0643
-\u0637\u064a
-\u0643\u0646\u064a\u062f
-\u0627\u0632
-\u0627\u0646\u0647\u0627
-\u062a\u0645\u0627\u0645\u064a
-\u062f\u0627\u0634\u062a
-\u064a\u0643\u064a
-\u0637\u0631\u064a\u0642
-\u0627\u0634
-\u0686\u064a\u0633\u062a
-\u0631\u0648\u0628
-\u0646\u0645\u0627\u064a\u062f
-\u06af\u0641\u062a
-\u0686\u0646\u062f\u064a\u0646
-\u0686\u064a\u0632\u064a
-\u062a\u0648\u0627\u0646\u062f
-\u0627\u0645
-\u0627\u064a\u0627
-\u0628\u0627
-\u0627\u0646
-\u0627\u064a\u062f
-\u062a\u0631\u064a\u0646
-\u0627\u064a\u0646\u0643\u0647
-\u062f\u064a\u06af\u0631\u064a
-\u0631\u0627\u0647
-\u0647\u0627\u064a\u064a
-\u0628\u0631\u0648\u0632
-\u0647\u0645\u0686\u0646\u0627\u0646
-\u067e\u0627\u0639\u064a\u0646
-\u0643\u0633
-\u062d\u062f\u0648\u062f
-\u0645\u062e\u062a\u0644\u0641
-\u0645\u0642\u0627\u0628\u0644
-\u0686\u064a\u0632
-\u06af\u064a\u0631\u062f
-\u0646\u062f\u0627\u0631\u062f
-\u0636\u062f
-\u0647\u0645\u0686\u0648\u0646
-\u0633\u0627\u0632\u064a
-\u0634\u0627\u0646
-\u0645\u0648\u0631\u062f
-\u0628\u0627\u0631\u0647
-\u0645\u0631\u0633\u064a
-\u062e\u0648\u064a\u0634
-\u0628\u0631\u062e\u0648\u0631\u062f\u0627\u0631
-\u0686\u0648\u0646
-\u062e\u0627\u0631\u062c
-\u0634\u0634
-\u0647\u0646\u0648\u0632
-\u062a\u062d\u062a
-\u0636\u0645\u0646
-\u0647\u0633\u062a\u064a\u0645
-\u06af\u0641\u062a\u0647
-\u0641\u0643\u0631
-\u0628\u0633\u064a\u0627\u0631
-\u067e\u064a\u0634
-\u0628\u0631\u0627\u064a
-\u0631\u0648\u0632\u0647\u0627\u064a
-\u0627\u0646\u0643\u0647
-\u0646\u062e\u0648\u0627\u0647\u062f
-\u0628\u0627\u0644\u0627
-\u0643\u0644
-\u0648\u0642\u062a\u064a
-\u0643\u064a
-\u0686\u0646\u064a\u0646
-\u0643\u0647
-\u06af\u064a\u0631\u064a
-\u0646\u064a\u0633\u062a
-\u0627\u0633\u062a
-\u0643\u062c\u0627
-\u0643\u0646\u062f
-\u0646\u064a\u0632
-\u064a\u0627\u0628\u062f
-\u0628\u0646\u062f\u064a
-\u062d\u062a\u064a
-\u062a\u0648\u0627\u0646\u0646\u062f
-\u0639\u0642\u0628
-\u062e\u0648\u0627\u0633\u062a
-\u0643\u0646\u0646\u062f
-\u0628\u064a\u0646
-\u062a\u0645\u0627\u0645
-\u0647\u0645\u0647
-\u0645\u0627
-\u0628\u0627\u0634\u0646\u062f
-\u0645\u062b\u0644
-\u0634\u062f
-\u0627\u0631\u064a
-\u0628\u0627\u0634\u062f
-\u0627\u0631\u0647
-\u0637\u0628\u0642
-\u0628\u0639\u062f
-\u0627\u06af\u0631
-\u0635\u0648\u0631\u062a
-\u063a\u064a\u0631
-\u062c\u0627\u064a
-\u0628\u064a\u0634
-\u0631\u064a\u0632\u064a
-\u0627\u0646\u062f
-\u0632\u064a\u0631\u0627
-\u0686\u06af\u0648\u0646\u0647
-\u0628\u0627\u0631
-\u0644\u0637\u0641\u0627
-\u0645\u064a
-\u062f\u0631\u0628\u0627\u0631\u0647
-\u0645\u0646
-\u062f\u064a\u062f\u0647
-\u0647\u0645\u064a\u0646
-\u06af\u0630\u0627\u0631\u064a
-\u0628\u0631\u062f\u0627\u0631\u064a
-\u0639\u0644\u062a
-\u06af\u0630\u0627\u0634\u062a\u0647
-\u0647\u0645
-\u0641\u0648\u0642
-\u0646\u0647
-\u0647\u0627
-\u0634\u0648\u0646\u062f
-\u0627\u0628\u0627\u062f
-\u0647\u0645\u0648\u0627\u0631\u0647
-\u0647\u0631
-\u0627\u0648\u0644
-\u062e\u0648\u0627\u0647\u0646\u062f
-\u0686\u0647\u0627\u0631
-\u0646\u0627\u0645
-\u0627\u0645\u0631\u0648\u0632
-\u0645\u0627\u0646
-\u0647\u0627\u064a
-\u0642\u0628\u0644
-\u0643\u0646\u0645
-\u0633\u0639\u064a
-\u062a\u0627\u0632\u0647
-\u0631\u0627
-\u0647\u0633\u062a\u0646\u062f
-\u0632\u064a\u0631
-\u062c\u0644\u0648\u064a
-\u0639\u0646\u0648\u0627\u0646
-\u0628\u0648\u062f
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_fi.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_fi.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_fi.txt
deleted file mode 100644
index 4372c9a..0000000
--- a/solr/example/example-DIH/solr/rss/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
-eiv�t
-
-|Nom Gen Acc Part Iness Elat Illat Adess Ablat Allat Ess Trans
-min� minun minut minua minussa minusta minuun minulla minulta minulle | I
-sin� sinun sinut sinua sinussa sinusta sinuun sinulla sinulta sinulle | you
-h�n h�nen h�net h�nt� h�ness� h�nest� h�neen h�nell� h�nelt� h�nelle | he she
-me meid�n meid�t meit� meiss� meist� meihin meill� meilt� meille | we
-te teid�n teid�t teit� teiss� teist� teihin teill� teilt� teille | you
-he heid�n heid�t heit� heiss� heist� heihin heill� heilt� heille | they
-
-t�m� t�m�n t�t� t�ss� t�st� t�h�n tall� t�lt� t�lle t�n� t�ksi | this
-tuo tuon tuot� tuossa tuosta tuohon tuolla tuolta tuolle tuona tuoksi | that
-se sen sit� siin� siit� siihen sill� silt� sille sin� siksi | it
-n�m� n�iden n�it� n�iss� n�ist� n�ihin n�ill� n�ilt� n�ille n�in� n�iksi | these
-nuo noiden noita noissa noista noihin noilla noilta noille noina noiksi | those
-ne niiden niit� niiss� niist� niihin niill� niilt� niille niin� niiksi | they
-
-kuka kenen kenet ket� keness� kenest� keneen kenell� kenelt� kenelle kenen� keneksi| who
-ketk� keiden ketk� keit� keiss� keist� keihin keill� keilt� keille kein� keiksi | (pl)
-mik� mink� mink� mit� miss� mist� mihin mill� milt� mille min� miksi | which what
-mitk� | (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
-
-ett� | that
-ja | and
-jos | if
-koska | because
-kuin | than
-mutta | but
-niin | so
-sek� | and
-sill� | 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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_fr.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_fr.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_fr.txt
deleted file mode 100644
index 749abae..0000000
--- a/solr/example/example-DIH/solr/rss/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
-m�me | same; as in moi-m�me (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'
-� | to, at
-m | m'
-n | n'
-s | s'
-t | t'
-y | there
-
- | forms of �tre (not including the infinitive):
-�t�
-�t�e
-�t�es
-�t�s
-�tant
-suis
-es
-est
-sommes
-�tes
-sont
-serai
-seras
-sera
-serons
-serez
-seront
-serais
-serait
-serions
-seriez
-seraient
-�tais
-�tait
-�tions
-�tiez
-�taient
-fus
-fut
-f�mes
-f�tes
-furent
-sois
-soit
-soyons
-soyez
-soient
-fusse
-fusses
-f�t
-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
-e�mes
-e�tes
-eurent
-aie
-aies
-ait
-ayons
-ayez
-aient
-eusse
-eusses
-e�t
-eussions
-eussiez
-eussent
-
- | Later additions (from Jean-Christophe Deschamps)
-ceci | this
-cela | that
-cel� | 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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ga.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ga.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ga.txt
deleted file mode 100644
index 9ff88d7..0000000
--- a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ga.txt
+++ /dev/null
@@ -1,110 +0,0 @@
-
-a
-ach
-ag
-agus
-an
-aon
-ar
-arna
-as
-b'
-ba
-beirt
-bh�r
-caoga
-ceathair
-ceathrar
-chomh
-cht�
-chuig
-chun
-cois
-c�ad
-c�ig
-c�igear
-d'
-daichead
-dar
-de
-deich
-deichni�r
-den
-dh�
-do
-don
-dt�
-d�
-d�r
-d�
-faoi
-faoin
-faoina
-faoin�r
-fara
-fiche
-gach
-gan
-go
-gur
-haon
-hocht
-i
-iad
-idir
-in
-ina
-ins
-in�r
-is
-le
-leis
-lena
-len�r
-m'
-mar
-mo
-m�
-na
-nach
-naoi
-naon�r
-n�
-n�
-n�or
-n�
-n�cha
-ocht
-ochtar
-os
-roimh
-sa
-seacht
-seachtar
-seacht�
-seasca
-seisear
-siad
-sibh
-sinn
-sna
-s�
-s�
-tar
-thar
-th�
-tri�r
-tr�
-tr�na
-tr�n�r
-tr�ocha
-t�
-um
-�r
-�
-�is
-�
-�
-�n
-�na
-�n�r
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_gl.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_gl.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_gl.txt
deleted file mode 100644
index d8760b1..0000000
--- a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_gl.txt
+++ /dev/null
@@ -1,161 +0,0 @@
-# galican stopwords
-a
-a�nda
-al�
-aquel
-aquela
-aquelas
-aqueles
-aquilo
-aqu�
-ao
-aos
-as
-as�
-�
-ben
-cando
-che
-co
-coa
-comigo
-con
-connosco
-contigo
-convosco
-coas
-cos
-cun
-cuns
-cunha
-cunhas
-da
-dalgunha
-dalgunhas
-dalg�n
-dalg�ns
-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
-est�
-est�n
-este
-estes
-estiven
-estou
-eu
-�
-facer
-foi
-foron
-fun
-hab�a
-hai
-iso
-isto
-la
-las
-lle
-lles
-lo
-los
-mais
-me
-meu
-meus
-min
-mi�a
-mi�as
-moi
-na
-nas
-neste
-nin
-no
-non
-nos
-nosa
-nosas
-noso
-nosos
-n�s
-nun
-nunha
-nuns
-nunhas
-o
-os
-ou
-�
-�s
-para
-pero
-pode
-pois
-pola
-polas
-polo
-polos
-por
-que
-se
-sen�n
-ser
-seu
-seus
-sexa
-sido
-sobre
-s�a
-s�as
-tam�n
-tan
-te
-ten
-te�en
-te�o
-ter
-teu
-teus
-ti
-tido
-ti�a
-tiven
-t�a
-t�as
-un
-unha
-unhas
-uns
-vos
-vosa
-vosas
-voso
-vosos
-v�s
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hi.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hi.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hi.txt
deleted file mode 100644
index 86286bb..0000000
--- a/solr/example/example-DIH/solr/rss/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.
-\u0905\u0902\u0926\u0930
-\u0905\u0924
-\u0905\u092a\u0928\u093e
-\u0905\u092a\u0928\u0940
-\u0905\u092a\u0928\u0947
-\u0905\u092d\u0940
-\u0906\u0926\u093f
-\u0906\u092a
-\u0907\u0924\u094d\u092f\u093e\u0926\u093f
-\u0907\u0928
-\u0907\u0928\u0915\u093e
-\u0907\u0928\u094d\u0939\u0940\u0902
-\u0907\u0928\u094d\u0939\u0947\u0902
-\u0907\u0928\u094d\u0939\u094b\u0902
-\u0907\u0938
-\u0907\u0938\u0915\u093e
-\u0907\u0938\u0915\u0940
-\u0907\u0938\u0915\u0947
-\u0907\u0938\u092e\u0947\u0902
-\u0907\u0938\u0940
-\u0907\u0938\u0947
-\u0909\u0928
-\u0909\u0928\u0915\u093e
-\u0909\u0928\u0915\u0940
-\u0909\u0928\u0915\u0947
-\u0909\u0928\u0915\u094b
-\u0909\u0928\u094d\u0939\u0940\u0902
-\u0909\u0928\u094d\u0939\u0947\u0902
-\u0909\u0928\u094d\u0939\u094b\u0902
-\u0909\u0938
-\u0909\u0938\u0915\u0947
-\u0909\u0938\u0940
-\u0909\u0938\u0947
-\u090f\u0915
-\u090f\u0935\u0902
-\u090f\u0938
-\u0910\u0938\u0947
-\u0914\u0930
-\u0915\u0908
-\u0915\u0930
-\u0915\u0930\u0924\u093e
-\u0915\u0930\u0924\u0947
-\u0915\u0930\u0928\u093e
-\u0915\u0930\u0928\u0947
-\u0915\u0930\u0947\u0902
-\u0915\u0939\u0924\u0947
-\u0915\u0939\u093e
-\u0915\u093e
-\u0915\u093e\u095e\u0940
-\u0915\u093f
-\u0915\u093f\u0924\u0928\u093e
-\u0915\u093f\u0928\u094d\u0939\u0947\u0902
-\u0915\u093f\u0928\u094d\u0939\u094b\u0902
-\u0915\u093f\u092f\u093e
-\u0915\u093f\u0930
-\u0915\u093f\u0938
-\u0915\u093f\u0938\u0940
-\u0915\u093f\u0938\u0947
-\u0915\u0940
-\u0915\u0941\u091b
-\u0915\u0941\u0932
-\u0915\u0947
-\u0915\u094b
-\u0915\u094b\u0908
-\u0915\u094c\u0928
-\u0915\u094c\u0928\u0938\u093e
-\u0917\u092f\u093e
-\u0918\u0930
-\u091c\u092c
-\u091c\u0939\u093e\u0901
-\u091c\u093e
-\u091c\u093f\u0924\u0928\u093e
-\u091c\u093f\u0928
-\u091c\u093f\u0928\u094d\u0939\u0947\u0902
-\u091c\u093f\u0928\u094d\u0939\u094b\u0902
-\u091c\u093f\u0938
-\u091c\u093f\u0938\u0947
-\u091c\u0940\u0927\u0930
-\u091c\u0948\u0938\u093e
-\u091c\u0948\u0938\u0947
-\u091c\u094b
-\u0924\u0915
-\u0924\u092c
-\u0924\u0930\u0939
-\u0924\u093f\u0928
-\u0924\u093f\u0928\u094d\u0939\u0947\u0902
-\u0924\u093f\u0928\u094d\u0939\u094b\u0902
-\u0924\u093f\u0938
-\u0924\u093f\u0938\u0947
-\u0924\u094b
-\u0925\u093e
-\u0925\u0940
-\u0925\u0947
-\u0926\u092c\u093e\u0930\u093e
-\u0926\u093f\u092f\u093e
-\u0926\u0941\u0938\u0930\u093e
-\u0926\u0942\u0938\u0930\u0947
-\u0926\u094b
-\u0926\u094d\u0935\u093e\u0930\u093e
-\u0928
-\u0928\u0939\u0940\u0902
-\u0928\u093e
-\u0928\u093f\u0939\u093e\u092f\u0924
-\u0928\u0940\u091a\u0947
-\u0928\u0947
-\u092a\u0930
-\u092a\u0930
-\u092a\u0939\u0932\u0947
-\u092a\u0942\u0930\u093e
-\u092a\u0947
-\u092b\u093f\u0930
-\u092c\u0928\u0940
-\u092c\u0939\u0940
-\u092c\u0939\u0941\u0924
-\u092c\u093e\u0926
-\u092c\u093e\u0932\u093e
-\u092c\u093f\u0932\u0915\u0941\u0932
-\u092d\u0940
-\u092d\u0940\u0924\u0930
-\u092e\u0917\u0930
-\u092e\u093e\u0928\u094b
-\u092e\u0947
-\u092e\u0947\u0902
-\u092f\u0926\u093f
-\u092f\u0939
-\u092f\u0939\u093e\u0901
-\u092f\u0939\u0940
-\u092f\u093e
-\u092f\u093f\u0939
-\u092f\u0947
-\u0930\u0916\u0947\u0902
-\u0930\u0939\u093e
-\u0930\u0939\u0947
-\u0931\u094d\u0935\u093e\u0938\u093e
-\u0932\u093f\u090f
-\u0932\u093f\u092f\u0947
-\u0932\u0947\u0915\u093f\u0928
-\u0935
-\u0935\u0930\u094d\u0917
-\u0935\u0939
-\u0935\u0939
-\u0935\u0939\u093e\u0901
-\u0935\u0939\u0940\u0902
-\u0935\u093e\u0932\u0947
-\u0935\u0941\u0939
-\u0935\u0947
-\u0935\u095a\u0948\u0930\u0939
-\u0938\u0902\u0917
-\u0938\u0915\u0924\u093e
-\u0938\u0915\u0924\u0947
-\u0938\u092c\u0938\u0947
-\u0938\u092d\u0940
-\u0938\u093e\u0925
-\u0938\u093e\u092c\u0941\u0924
-\u0938\u093e\u092d
-\u0938\u093e\u0930\u093e
-\u0938\u0947
-\u0938\u094b
-\u0939\u0940
-\u0939\u0941\u0906
-\u0939\u0941\u0908
-\u0939\u0941\u090f
-\u0939\u0948
-\u0939\u0948\u0902
-\u0939\u094b
-\u0939\u094b\u0924\u093e
-\u0939\u094b\u0924\u0940
-\u0939\u094b\u0924\u0947
-\u0939\u094b\u0928\u093e
-\u0939\u094b\u0928\u0947
-# additional normalized forms of the above
-\u0905\u092a\u0928\u093f
-\u091c\u0947\u0938\u0947
-\u0939\u094b\u0924\u093f
-\u0938\u092d\u093f
-\u0924\u093f\u0902\u0939\u094b\u0902
-\u0907\u0902\u0939\u094b\u0902
-\u0926\u0935\u093e\u0930\u093e
-\u0907\u0938\u093f
-\u0915\u093f\u0902\u0939\u0947\u0902
-\u0925\u093f
-\u0909\u0902\u0939\u094b\u0902
-\u0913\u0930
-\u091c\u093f\u0902\u0939\u0947\u0902
-\u0935\u0939\u093f\u0902
-\u0905\u092d\u093f
-\u092c\u0928\u093f
-\u0939\u093f
-\u0909\u0902\u0939\u093f\u0902
-\u0909\u0902\u0939\u0947\u0902
-\u0939\u0947\u0902
-\u0935\u0917\u0947\u0930\u0939
-\u090f\u0938\u0947
-\u0930\u0935\u093e\u0938\u093e
-\u0915\u094b\u0928
-\u0928\u093f\u091a\u0947
-\u0915\u093e\u092b\u093f
-\u0909\u0938\u093f
-\u092a\u0941\u0930\u093e
-\u092d\u093f\u0924\u0930
-\u0939\u0947
-\u092c\u0939\u093f
-\u0935\u0939\u093e\u0902
-\u0915\u094b\u0907
-\u092f\u0939\u093e\u0902
-\u091c\u093f\u0902\u0939\u094b\u0902
-\u0924\u093f\u0902\u0939\u0947\u0902
-\u0915\u093f\u0938\u093f
-\u0915\u0907
-\u092f\u0939\u093f
-\u0907\u0902\u0939\u093f\u0902
-\u091c\u093f\u0927\u0930
-\u0907\u0902\u0939\u0947\u0902
-\u0905\u0926\u093f
-\u0907\u0924\u092f\u093e\u0926\u093f
-\u0939\u0941\u0907
-\u0915\u094b\u0928\u0938\u093e
-\u0907\u0938\u0915\u093f
-\u0926\u0941\u0938\u0930\u0947
-\u091c\u0939\u093e\u0902
-\u0905\u092a
-\u0915\u093f\u0902\u0939\u094b\u0902
-\u0909\u0928\u0915\u093f
-\u092d\u093f
-\u0935\u0930\u0917
-\u0939\u0941\u0905
-\u091c\u0947\u0938\u093e
-\u0928\u0939\u093f\u0902
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hu.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hu.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hu.txt
deleted file mode 100644
index 37526da..0000000
--- a/solr/example/example-DIH/solr/rss/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
-�ltal
-�ltal�ban
-amely
-amelyek
-amelyekben
-amelyeket
-amelyet
-amelynek
-ami
-amit
-amolyan
-am�g
-amikor
-�t
-abban
-ahhoz
-annak
-arra
-arr�l
-az
-azok
-azon
-azt
-azzal
-az�rt
-azt�n
-azut�n
-azonban
-b�r
-be
-bel�l
-benne
-cikk
-cikkek
-cikkeket
-csak
-de
-e
-eddig
-eg�sz
-egy
-egyes
-egyetlen
-egy�b
-egyik
-egyre
-ekkor
-el
-el�g
-ellen
-el\u0151
-el\u0151sz�r
-el\u0151tt
-els\u0151
-�n
-�ppen
-ebben
-ehhez
-emilyen
-ennek
-erre
-ez
-ezt
-ezek
-ezen
-ezzel
-ez�rt
-�s
-fel
-fel�
-hanem
-hiszen
-hogy
-hogyan
-igen
-�gy
-illetve
-ill.
-ill
-ilyen
-ilyenkor
-ison
-ism�t
-itt
-j�
-j�l
-jobban
-kell
-kellett
-kereszt�l
-keress�nk
-ki
-k�v�l
-k�z�tt
-k�z�l
-legal�bb
-lehet
-lehetett
-legyen
-lenne
-lenni
-lesz
-lett
-maga
-mag�t
-majd
-majd
-m�r
-m�s
-m�sik
-meg
-m�g
-mellett
-mert
-mely
-melyek
-mi
-mit
-m�g
-mi�rt
-milyen
-mikor
-minden
-mindent
-mindenki
-mindig
-mint
-mintha
-mivel
-most
-nagy
-nagyobb
-nagyon
-ne
-n�ha
-nekem
-neki
-nem
-n�h�ny
-n�lk�l
-nincs
-olyan
-ott
-�ssze
-\u0151
-\u0151k
-\u0151ket
-pedig
-persze
-r�
-s
-saj�t
-sem
-semmi
-sok
-sokat
-sokkal
-sz�m�ra
-szemben
-szerint
-szinte
-tal�n
-teh�t
-teljes
-tov�bb
-tov�bb�
-t�bb
-�gy
-ugyanis
-�j
-�jabb
-�jra
-ut�n
-ut�na
-utols�
-vagy
-vagyis
-valaki
-valami
-valamint
-val�
-vagyok
-van
-vannak
-volt
-voltam
-voltak
-voltunk
-vissza
-vele
-viszont
-volna
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hy.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hy.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hy.txt
deleted file mode 100644
index 60c1c50..0000000
--- a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_hy.txt
+++ /dev/null
@@ -1,46 +0,0 @@
-# example set of Armenian stopwords.
-\u0561\u0575\u0564
-\u0561\u0575\u056c
-\u0561\u0575\u0576
-\u0561\u0575\u057d
-\u0564\u0578\u0582
-\u0564\u0578\u0582\u0584
-\u0565\u0574
-\u0565\u0576
-\u0565\u0576\u0584
-\u0565\u057d
-\u0565\u0584
-\u0567
-\u0567\u056b
-\u0567\u056b\u0576
-\u0567\u056b\u0576\u0584
-\u0567\u056b\u0580
-\u0567\u056b\u0584
-\u0567\u0580
-\u0568\u057d\u057f
-\u0569
-\u056b
-\u056b\u0576
-\u056b\u057d\u056f
-\u056b\u0580
-\u056f\u0561\u0574
-\u0570\u0561\u0574\u0561\u0580
-\u0570\u0565\u057f
-\u0570\u0565\u057f\u0578
-\u0574\u0565\u0576\u0584
-\u0574\u0565\u057b
-\u0574\u056b
-\u0576
-\u0576\u0561
-\u0576\u0561\u0587
-\u0576\u0580\u0561
-\u0576\u0580\u0561\u0576\u0584
-\u0578\u0580
-\u0578\u0580\u0568
-\u0578\u0580\u0578\u0576\u0584
-\u0578\u0580\u057a\u0565\u057d
-\u0578\u0582
-\u0578\u0582\u0574
-\u057a\u056b\u057f\u056b
-\u057e\u0580\u0561
-\u0587
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_id.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_id.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_id.txt
deleted file mode 100644
index 4617f83..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_it.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_it.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_it.txt
deleted file mode 100644
index 1219cc7..0000000
--- a/solr/example/example-DIH/solr/rss/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
-perch� | why, because
-anche | also
-come | how
-dov | where (as dov')
-dove | where
-che | who, that
-chi | who
-cui | whom
-non | not
-pi� | 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
-avr�
-avrai
-avr�
-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
-�
-siamo
-siete
-sia
-siate
-siano
-sar�
-sarai
-sar�
-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
-far�
-farai
-far�
-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
-star�
-starai
-star�
-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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ja.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ja.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ja.txt
deleted file mode 100644
index d4321be..0000000
--- a/solr/example/example-DIH/solr/rss/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.
-#
-\u306e
-\u306b
-\u306f
-\u3092
-\u305f
-\u304c
-\u3067
-\u3066
-\u3068
-\u3057
-\u308c
-\u3055
-\u3042\u308b
-\u3044\u308b
-\u3082
-\u3059\u308b
-\u304b\u3089
-\u306a
-\u3053\u3068
-\u3068\u3057\u3066
-\u3044
-\u3084
-\u308c\u308b
-\u306a\u3069
-\u306a\u3063
-\u306a\u3044
-\u3053\u306e
-\u305f\u3081
-\u305d\u306e
-\u3042\u3063
-\u3088\u3046
-\u307e\u305f
-\u3082\u306e
-\u3068\u3044\u3046
-\u3042\u308a
-\u307e\u3067
-\u3089\u308c
-\u306a\u308b
-\u3078
-\u304b
-\u3060
-\u3053\u308c
-\u306b\u3088\u3063\u3066
-\u306b\u3088\u308a
-\u304a\u308a
-\u3088\u308a
-\u306b\u3088\u308b
-\u305a
-\u306a\u308a
-\u3089\u308c\u308b
-\u306b\u304a\u3044\u3066
-\u3070
-\u306a\u304b\u3063
-\u306a\u304f
-\u3057\u304b\u3057
-\u306b\u3064\u3044\u3066
-\u305b
-\u3060\u3063
-\u305d\u306e\u5f8c
-\u3067\u304d\u308b
-\u305d\u308c
-\u3046
-\u306e\u3067
-\u306a\u304a
-\u306e\u307f
-\u3067\u304d
-\u304d
-\u3064
-\u306b\u304a\u3051\u308b
-\u304a\u3088\u3073
-\u3044\u3046
-\u3055\u3089\u306b
-\u3067\u3082
-\u3089
-\u305f\u308a
-\u305d\u306e\u4ed6
-\u306b\u95a2\u3059\u308b
-\u305f\u3061
-\u307e\u3059
-\u3093
-\u306a\u3089
-\u306b\u5bfe\u3057\u3066
-\u7279\u306b
-\u305b\u308b
-\u53ca\u3073
-\u3053\u308c\u3089
-\u3068\u304d
-\u3067\u306f
-\u306b\u3066
-\u307b\u304b
-\u306a\u304c\u3089
-\u3046\u3061
-\u305d\u3057\u3066
-\u3068\u3068\u3082\u306b
-\u305f\u3060\u3057
-\u304b\u3064\u3066
-\u305d\u308c\u305e\u308c
-\u307e\u305f\u306f
-\u304a
-\u307b\u3069
-\u3082\u306e\u306e
-\u306b\u5bfe\u3059\u308b
-\u307b\u3068\u3093\u3069
-\u3068\u5171\u306b
-\u3068\u3044\u3063\u305f
-\u3067\u3059
-\u3068\u3082
-\u3068\u3053\u308d
-\u3053\u3053
-##### End of file
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_lv.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_lv.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_lv.txt
deleted file mode 100644
index e21a23c..0000000
--- a/solr/example/example-DIH/solr/rss/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
-apak\u0161
-\u0101rpus
-aug\u0161pus
-bez
-caur
-d\u0113\u013c
-gar
-iek\u0161
-iz
-kop\u0161
-labad
-lejpus
-l\u012bdz
-no
-otrpus
-pa
-par
-p\u0101r
-p\u0113c
-pie
-pirms
-pret
-priek\u0161
-starp
-\u0161aipus
-uz
-vi\u0146pus
-virs
-virspus
-zem
-apak\u0161pus
-# Conjunctions
-un
-bet
-jo
-ja
-ka
-lai
-tom\u0113r
-tikko
-turpret\u012b
-ar\u012b
-kaut
-gan
-t\u0101d\u0113\u013c
-t\u0101
-ne
-tikvien
-vien
-k\u0101
-ir
-te
-vai
-kam\u0113r
-# Particles
-ar
-diezin
-dro\u0161i
-diem\u017e\u0113l
-neb\u016bt
-ik
-it
-ta\u010du
-nu
-pat
-tiklab
-iek\u0161pus
-nedz
-tik
-nevis
-turpretim
-jeb
-iekam
-iek\u0101m
-iek\u0101ms
-kol\u012bdz
-l\u012bdzko
-tikl\u012bdz
-jeb\u0161u
-t\u0101lab
-t\u0101p\u0113c
-nek\u0101
-itin
-j\u0101
-jau
-jel
-n\u0113
-nezin
-tad
-tikai
-vis
-tak
-iekams
-vien
-# modal verbs
-b\u016bt
-biju
-biji
-bija
-bij\u0101m
-bij\u0101t
-esmu
-esi
-esam
-esat
-b\u016b\u0161u
-b\u016bsi
-b\u016bs
-b\u016bsim
-b\u016bsiet
-tikt
-tiku
-tiki
-tika
-tik\u0101m
-tik\u0101t
-tieku
-tiec
-tiek
-tiekam
-tiekat
-tik\u0161u
-tiks
-tiksim
-tiksiet
-tapt
-tapi
-tap\u0101t
-topat
-tap\u0161u
-tapsi
-taps
-tapsim
-tapsiet
-k\u013c\u016bt
-k\u013cuvu
-k\u013cuvi
-k\u013cuva
-k\u013cuv\u0101m
-k\u013cuv\u0101t
-k\u013c\u016bstu
-k\u013c\u016bsti
-k\u013c\u016bst
-k\u013c\u016bstam
-k\u013c\u016bstat
-k\u013c\u016b\u0161u
-k\u013c\u016bsi
-k\u013c\u016bs
-k\u013c\u016bsim
-k\u013c\u016bsiet
-# verbs
-var\u0113t
-var\u0113ju
-var\u0113j\u0101m
-var\u0113\u0161u
-var\u0113sim
-var
-var\u0113ji
-var\u0113j\u0101t
-var\u0113si
-var\u0113siet
-varat
-var\u0113ja
-var\u0113s
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_nl.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_nl.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_nl.txt
deleted file mode 100644
index 47a2aea..0000000
--- a/solr/example/example-DIH/solr/rss/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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_no.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_no.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_no.txt
deleted file mode 100644
index a7a2c28..0000000
--- a/solr/example/example-DIH/solr/rss/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 bokm�l 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
-p� | on
-de | they / you(formal)
-med | with
-han | he
-av | of
-ikke | not
-ikkje | not *
-der | there
-s� | 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
-n� | 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)
-sj�l | self (reflective)
-her | here
-alle | all
-vil | will
-bli | become
-ble | became
-blei | became *
-blitt | have become
-kunne | could
-inn | in
-n�r | when
-v�re | 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
-� | 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)
-s�nn | such a
-inni | inside/within
-mellom | between
-v�r | our
-hver | each
-hvem | who
-vors | us/ours
-hvis | whose
-b�de | both
-bare | only/just
-enn | than
-fordi | as/because
-f�r | before
-mange | many
-ogs� | also
-slik | just
-v�rt | been
-v�re | to be
-b�e | both *
-begge | both
-siden | since
-dykk | your *
-dykkar | yours *
-dei | they *
-deira | them *
-deires | theirs *
-deim | them *
-di | your (fem.) *
-d� | as/when *
-eg | I *
-ein | a/an *
-eit | a/an *
-eitt | a/an *
-elles | or *
-honom | he *
-hj� | 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/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_pt.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_pt.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_pt.txt
deleted file mode 100644
index acfeb01..0000000
--- a/solr/example/example-DIH/solr/rss/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
- | � from SER
-com | with
-n�o | 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
-� | a + a
-seu | his
-sua | her
-ou | or
- | ser from SER
-quando | when
-muito | much
- | h� from HAV
-nos | em + os; us
-j� | already, now
- | est� from EST
-eu | I
-tamb�m | also
-s� | only, just
-pelo | per + o
-pela | per + a
-at� | 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
- | est�o from EST
-voc� | you
- | tinha from TER
- | foram from SER
-essa | that
-num | em + um
-nem | nor
-suas | her
-meu | my
-�s | a + as
-minha | my
- | t�m from TER
-numa | em + uma
-pelos | per + os
-elas | they
- | havia from HAV
- | seja from SER
-qual | which
- | ser� from SER
-n�s | 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
-voc�s | 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
-est�
-estamos
-est�o
-estive
-esteve
-estivemos
-estiveram
-estava
-est�vamos
-estavam
-estivera
-estiv�ramos
-esteja
-estejamos
-estejam
-estivesse
-estiv�ssemos
-estivessem
-estiver
-estivermos
-estiverem
-
- | forms of haver, to have (not including the infinitive):
-hei
-h�
-havemos
-h�o
-houve
-houvemos
-houveram
-houvera
-houv�ramos
-haja
-hajamos
-hajam
-houvesse
-houv�ssemos
-houvessem
-houver
-houvermos
-houverem
-houverei
-houver�
-houveremos
-houver�o
-houveria
-houver�amos
-houveriam
-
- | forms of ser, to be (not including the infinitive):
-sou
-somos
-s�o
-era
-�ramos
-eram
-fui
-foi
-fomos
-foram
-fora
-f�ramos
-seja
-sejamos
-sejam
-fosse
-f�ssemos
-fossem
-for
-formos
-forem
-serei
-ser�
-seremos
-ser�o
-seria
-ser�amos
-seriam
-
- | forms of ter, to have (not including the infinitive):
-tenho
-tem
-temos
-t�m
-tinha
-t�nhamos
-tinham
-tive
-teve
-tivemos
-tiveram
-tivera
-tiv�ramos
-tenha
-tenhamos
-tenham
-tivesse
-tiv�ssemos
-tivessem
-tiver
-tivermos
-tiverem
-terei
-ter�
-teremos
-ter�o
-teria
-ter�amos
-teriam
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ro.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ro.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ro.txt
deleted file mode 100644
index 4fdee90..0000000
--- a/solr/example/example-DIH/solr/rss/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
-aceast\u0103
-aceea
-acei
-aceia
-acel
-acela
-acele
-acelea
-acest
-acesta
-aceste
-acestea
-ace\u015fti
-ace\u015ftia
-acolo
-acum
-ai
-aia
-aib\u0103
-aici
-al
-\u0103la
-ale
-alea
-\u0103lea
-altceva
-altcineva
-am
-ar
-are
-a\u015f
-a\u015fadar
-asemenea
-asta
-\u0103sta
-ast\u0103zi
-astea
-\u0103stea
-\u0103\u015ftia
-asupra
-a\u0163i
-au
-avea
-avem
-ave\u0163i
-azi
-bine
-bucur
-bun\u0103
-ca
-c\u0103
-c\u0103ci
-c�nd
-care
-c\u0103rei
-c\u0103ror
-c\u0103rui
-c�t
-c�te
-c�\u0163i
-c\u0103tre
-c�tva
-ce
-cel
-ceva
-chiar
-c�nd
-cine
-cineva
-c�t
-c�te
-c�\u0163i
-c�tva
-contra
-cu
-cum
-cumva
-cur�nd
-cur�nd
-da
-d\u0103
-dac\u0103
-dar
-datorit\u0103
-de
-deci
-deja
-deoarece
-departe
-de\u015fi
-din
-dinaintea
-dintr
-dintre
-drept
-dup\u0103
-ea
-ei
-el
-ele
-eram
-este
-e\u015fti
-eu
-face
-f\u0103r\u0103
-fi
-fie
-fiecare
-fii
-fim
-fi\u0163i
-iar
-ieri
-�i
-�l
-�mi
-�mpotriva
-�n
-�nainte
-�naintea
-�nc�t
-�nc�t
-�ncotro
-�ntre
-�ntruc�t
-�ntruc�t
-�\u0163i
-la
-l�ng\u0103
-le
-li
-l�ng\u0103
-lor
-lui
-m\u0103
-m�ine
-mea
-mei
-mele
-mereu
-meu
-mi
-mine
-mult
-mult\u0103
-mul\u0163i
-ne
-nic\u0103ieri
-nici
-nimeni
-ni\u015fte
-noastr\u0103
-noastre
-noi
-no\u015ftri
-nostru
-nu
-ori
-oric�nd
-oricare
-oric�t
-orice
-oric�nd
-oricine
-oric�t
-oricum
-oriunde
-p�n\u0103
-pe
-pentru
-peste
-p�n\u0103
-poate
-pot
-prea
-prima
-primul
-prin
-printr
-sa
-s\u0103
-s\u0103i
-sale
-sau
-s\u0103u
-se
-\u015fi
-s�nt
-s�ntem
-s�nte\u0163i
-spre
-sub
-sunt
-suntem
-sunte\u0163i
-ta
-t\u0103i
-tale
-t\u0103u
-te
-\u0163i
-\u0163ie
-tine
-toat\u0103
-toate
-tot
-to\u0163i
-totu\u015fi
-tu
-un
-una
-unde
-undeva
-unei
-unele
-uneori
-unor
-v\u0103
-vi
-voastr\u0103
-voastre
-voi
-vo\u015ftri
-vostru
-vou\u0103
-vreo
-vreun
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ru.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ru.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_ru.txt
deleted file mode 100644
index 5527140..0000000
--- a/solr/example/example-DIH/solr/rss/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 `\u0451' is translated to `\u0435'.
-
-\u0438 | and
-\u0432 | in/into
-\u0432\u043e | alternative form
-\u043d\u0435 | not
-\u0447\u0442\u043e | what/that
-\u043e\u043d | he
-\u043d\u0430 | on/onto
-\u044f | i
-\u0441 | from
-\u0441\u043e | alternative form
-\u043a\u0430\u043a | how
-\u0430 | milder form of `no' (but)
-\u0442\u043e | conjunction and form of `that'
-\u0432\u0441\u0435 | all
-\u043e\u043d\u0430 | she
-\u0442\u0430\u043a | so, thus
-\u0435\u0433\u043e | him
-\u043d\u043e | but
-\u0434\u0430 | yes/and
-\u0442\u044b | thou
-\u043a | towards, by
-\u0443 | around, chez
-\u0436\u0435 | intensifier particle
-\u0432\u044b | you
-\u0437\u0430 | beyond, behind
-\u0431\u044b | conditional/subj. particle
-\u043f\u043e | up to, along
-\u0442\u043e\u043b\u044c\u043a\u043e | only
-\u0435\u0435 | her
-\u043c\u043d\u0435 | to me
-\u0431\u044b\u043b\u043e | it was
-\u0432\u043e\u0442 | here is/are, particle
-\u043e\u0442 | away from
-\u043c\u0435\u043d\u044f | me
-\u0435\u0449\u0435 | still, yet, more
-\u043d\u0435\u0442 | no, there isnt/arent
-\u043e | about
-\u0438\u0437 | out of
-\u0435\u043c\u0443 | to him
-\u0442\u0435\u043f\u0435\u0440\u044c | now
-\u043a\u043e\u0433\u0434\u0430 | when
-\u0434\u0430\u0436\u0435 | even
-\u043d\u0443 | so, well
-\u0432\u0434\u0440\u0443\u0433 | suddenly
-\u043b\u0438 | interrogative particle
-\u0435\u0441\u043b\u0438 | if
-\u0443\u0436\u0435 | already, but homonym of `narrower'
-\u0438\u043b\u0438 | or
-\u043d\u0438 | neither
-\u0431\u044b\u0442\u044c | to be
-\u0431\u044b\u043b | he was
-\u043d\u0435\u0433\u043e | prepositional form of \u0435\u0433\u043e
-\u0434\u043e | up to
-\u0432\u0430\u0441 | you accusative
-\u043d\u0438\u0431\u0443\u0434\u044c | indef. suffix preceded by hyphen
-\u043e\u043f\u044f\u0442\u044c | again
-\u0443\u0436 | already, but homonym of `adder'
-\u0432\u0430\u043c | to you
-\u0441\u043a\u0430\u0437\u0430\u043b | he said
-\u0432\u0435\u0434\u044c | particle `after all'
-\u0442\u0430\u043c | there
-\u043f\u043e\u0442\u043e\u043c | then
-\u0441\u0435\u0431\u044f | oneself
-\u043d\u0438\u0447\u0435\u0433\u043e | nothing
-\u0435\u0439 | to her
-\u043c\u043e\u0436\u0435\u0442 | usually with `\u0431\u044b\u0442\u044c' as `maybe'
-\u043e\u043d\u0438 | they
-\u0442\u0443\u0442 | here
-\u0433\u0434\u0435 | where
-\u0435\u0441\u0442\u044c | there is/are
-\u043d\u0430\u0434\u043e | got to, must
-\u043d\u0435\u0439 | prepositional form of \u0435\u0439
-\u0434\u043b\u044f | for
-\u043c\u044b | we
-\u0442\u0435\u0431\u044f | thee
-\u0438\u0445 | them, their
-\u0447\u0435\u043c | than
-\u0431\u044b\u043b\u0430 | she was
-\u0441\u0430\u043c | self
-\u0447\u0442\u043e\u0431 | in order to
-\u0431\u0435\u0437 | without
-\u0431\u0443\u0434\u0442\u043e | as if
-\u0447\u0435\u043b\u043e\u0432\u0435\u043a | man, person, one
-\u0447\u0435\u0433\u043e | genitive form of `what'
-\u0440\u0430\u0437 | once
-\u0442\u043e\u0436\u0435 | also
-\u0441\u0435\u0431\u0435 | to oneself
-\u043f\u043e\u0434 | beneath
-\u0436\u0438\u0437\u043d\u044c | life
-\u0431\u0443\u0434\u0435\u0442 | will be
-\u0436 | short form of intensifer particle `\u0436\u0435'
-\u0442\u043e\u0433\u0434\u0430 | then
-\u043a\u0442\u043e | who
-\u044d\u0442\u043e\u0442 | this
-\u0433\u043e\u0432\u043e\u0440\u0438\u043b | was saying
-\u0442\u043e\u0433\u043e | genitive form of `that'
-\u043f\u043e\u0442\u043e\u043c\u0443 | for that reason
-\u044d\u0442\u043e\u0433\u043e | genitive form of `this'
-\u043a\u0430\u043a\u043e\u0439 | which
-\u0441\u043e\u0432\u0441\u0435\u043c | altogether
-\u043d\u0438\u043c | prepositional form of `\u0435\u0433\u043e', `\u043e\u043d\u0438'
-\u0437\u0434\u0435\u0441\u044c | here
-\u044d\u0442\u043e\u043c | prepositional form of `\u044d\u0442\u043e\u0442'
-\u043e\u0434\u0438\u043d | one
-\u043f\u043e\u0447\u0442\u0438 | almost
-\u043c\u043e\u0439 | my
-\u0442\u0435\u043c | instrumental/dative plural of `\u0442\u043e\u0442', `\u0442\u043e'
-\u0447\u0442\u043e\u0431\u044b | full form of `in order that'
-\u043d\u0435\u0435 | her (acc.)
-\u043a\u0430\u0436\u0435\u0442\u0441\u044f | it seems
-\u0441\u0435\u0439\u0447\u0430\u0441 | now
-\u0431\u044b\u043b\u0438 | they were
-\u043a\u0443\u0434\u0430 | where to
-\u0437\u0430\u0447\u0435\u043c | why
-\u0441\u043a\u0430\u0437\u0430\u0442\u044c | to say
-\u0432\u0441\u0435\u0445 | all (acc., gen. preposn. plural)
-\u043d\u0438\u043a\u043e\u0433\u0434\u0430 | never
-\u0441\u0435\u0433\u043e\u0434\u043d\u044f | today
-\u043c\u043e\u0436\u043d\u043e | possible, one can
-\u043f\u0440\u0438 | by
-\u043d\u0430\u043a\u043e\u043d\u0435\u0446 | finally
-\u0434\u0432\u0430 | two
-\u043e\u0431 | alternative form of `\u043e', about
-\u0434\u0440\u0443\u0433\u043e\u0439 | another
-\u0445\u043e\u0442\u044c | even
-\u043f\u043e\u0441\u043b\u0435 | after
-\u043d\u0430\u0434 | above
-\u0431\u043e\u043b\u044c\u0448\u0435 | more
-\u0442\u043e\u0442 | that one (masc.)
-\u0447\u0435\u0440\u0435\u0437 | across, in
-\u044d\u0442\u0438 | these
-\u043d\u0430\u0441 | us
-\u043f\u0440\u043e | about
-\u0432\u0441\u0435\u0433\u043e | in all, only, of all
-\u043d\u0438\u0445 | prepositional form of `\u043e\u043d\u0438' (they)
-\u043a\u0430\u043a\u0430\u044f | which, feminine
-\u043c\u043d\u043e\u0433\u043e | lots
-\u0440\u0430\u0437\u0432\u0435 | interrogative particle
-\u0441\u043a\u0430\u0437\u0430\u043b\u0430 | she said
-\u0442\u0440\u0438 | three
-\u044d\u0442\u0443 | this, acc. fem. sing.
-\u043c\u043e\u044f | my, feminine
-\u0432\u043f\u0440\u043e\u0447\u0435\u043c | moreover, besides
-\u0445\u043e\u0440\u043e\u0448\u043e | good
-\u0441\u0432\u043e\u044e | ones own, acc. fem. sing.
-\u044d\u0442\u043e\u0439 | oblique form of `\u044d\u0442\u0430', fem. `this'
-\u043f\u0435\u0440\u0435\u0434 | in front of
-\u0438\u043d\u043e\u0433\u0434\u0430 | sometimes
-\u043b\u0443\u0447\u0448\u0435 | better
-\u0447\u0443\u0442\u044c | a little
-\u0442\u043e\u043c | preposn. form of `that one'
-\u043d\u0435\u043b\u044c\u0437\u044f | one must not
-\u0442\u0430\u043a\u043e\u0439 | such a one
-\u0438\u043c | to them
-\u0431\u043e\u043b\u0435\u0435 | more
-\u0432\u0441\u0435\u0433\u0434\u0430 | always
-\u043a\u043e\u043d\u0435\u0447\u043d\u043e | of course
-\u0432\u0441\u044e | acc. fem. sing of `all'
-\u043c\u0435\u0436\u0434\u0443 | between
-
-
- | b: some paradigms
- |
- | personal pronouns
- |
- | \u044f \u043c\u0435\u043d\u044f \u043c\u043d\u0435 \u043c\u043d\u043e\u0439 [\u043c\u043d\u043e\u044e]
- | \u0442\u044b \u0442\u0435\u0431\u044f \u0442\u0435\u0431\u0435 \u0442\u043e\u0431\u043e\u0439 [\u0442\u043e\u0431\u043e\u044e]
- | \u043e\u043d \u0435\u0433\u043e \u0435\u043c\u0443 \u0438\u043c [\u043d\u0435\u0433\u043e, \u043d\u0435\u043c\u0443, \u043d\u0438\u043c]
- | \u043e\u043d\u0430 \u0435\u0435 \u044d\u0438 \u0435\u044e [\u043d\u0435\u0435, \u043d\u044d\u0438, \u043d\u0435\u044e]
- | \u043e\u043d\u043e \u0435\u0433\u043e \u0435\u043c\u0443 \u0438\u043c [\u043d\u0435\u0433\u043e, \u043d\u0435\u043c\u0443, \u043d\u0438\u043c]
- |
- | \u043c\u044b \u043d\u0430\u0441 \u043d\u0430\u043c \u043d\u0430\u043c\u0438
- | \u0432\u044b \u0432\u0430\u0441 \u0432\u0430\u043c \u0432\u0430\u043c\u0438
- | \u043e\u043d\u0438 \u0438\u0445 \u0438\u043c \u0438\u043c\u0438 [\u043d\u0438\u0445, \u043d\u0438\u043c, \u043d\u0438\u043c\u0438]
- |
- | \u0441\u0435\u0431\u044f \u0441\u0435\u0431\u0435 \u0441\u043e\u0431\u043e\u0439 [\u0441\u043e\u0431\u043e\u044e]
- |
- | demonstrative pronouns: \u044d\u0442\u043e\u0442 (this), \u0442\u043e\u0442 (that)
- |
- | \u044d\u0442\u043e\u0442 \u044d\u0442\u0430 \u044d\u0442\u043e \u044d\u0442\u0438
- | \u044d\u0442\u043e\u0433\u043e \u044d\u0442\u044b \u044d\u0442\u043e \u044d\u0442\u0438
- | \u044d\u0442\u043e\u0433\u043e \u044d\u0442\u043e\u0439 \u044d\u0442\u043e\u0433\u043e \u044d\u0442\u0438\u0445
- | \u044d\u0442\u043e\u043c\u0443 \u044d\u0442\u043e\u0439 \u044d\u0442\u043e\u043c\u0443 \u044d\u0442\u0438\u043c
- | \u044d\u0442\u0438\u043c \u044d\u0442\u043e\u0439 \u044d\u0442\u0438\u043c [\u044d\u0442\u043e\u044e] \u044d\u0442\u0438\u043c\u0438
- | \u044d\u0442\u043e\u043c \u044d\u0442\u043e\u0439 \u044d\u0442\u043e\u043c \u044d\u0442\u0438\u0445
- |
- | \u0442\u043e\u0442 \u0442\u0430 \u0442\u043e \u0442\u0435
- | \u0442\u043e\u0433\u043e \u0442\u0443 \u0442\u043e \u0442\u0435
- | \u0442\u043e\u0433\u043e \u0442\u043e\u0439 \u0442\u043e\u0433\u043e \u0442\u0435\u0445
- | \u0442\u043e\u043c\u0443 \u0442\u043e\u0439 \u0442\u043e\u043c\u0443 \u0442\u0435\u043c
- | \u0442\u0435\u043c \u0442\u043e\u0439 \u0442\u0435\u043c [\u0442\u043e\u044e] \u0442\u0435\u043c\u0438
- | \u0442\u043e\u043c \u0442\u043e\u0439 \u0442\u043e\u043c \u0442\u0435\u0445
- |
- | determinative pronouns
- |
- | (a) \u0432\u0435\u0441\u044c (all)
- |
- | \u0432\u0435\u0441\u044c \u0432\u0441\u044f \u0432\u0441\u0435 \u0432\u0441\u0435
- | \u0432\u0441\u0435\u0433\u043e \u0432\u0441\u044e \u0432\u0441\u0435 \u0432\u0441\u0435
- | \u0432\u0441\u0435\u0433\u043e \u0432\u0441\u0435\u0439 \u0432\u0441\u0435\u0433\u043e \u0432\u0441\u0435\u0445
- | \u0432\u0441\u0435\u043c\u0443 \u0432\u0441\u0435\u0439 \u0432\u0441\u0435\u043c\u0443 \u0432\u0441\u0435\u043c
- | \u0432\u0441\u0435\u043c \u0432\u0441\u0435\u0439 \u0432\u0441\u0435\u043c [\u0432\u0441\u0435\u044e] \u0432\u0441\u0435\u043c\u0438
- | \u0432\u0441\u0435\u043c \u0432\u0441\u0435\u0439 \u0432\u0441\u0435\u043c \u0432\u0441\u0435\u0445
- |
- | (b) \u0441\u0430\u043c (himself etc)
- |
- | \u0441\u0430\u043c \u0441\u0430\u043c\u0430 \u0441\u0430\u043c\u043e \u0441\u0430\u043c\u0438
- | \u0441\u0430\u043c\u043e\u0433\u043e \u0441\u0430\u043c\u0443 \u0441\u0430\u043c\u043e \u0441\u0430\u043c\u0438\u0445
- | \u0441\u0430\u043c\u043e\u0433\u043e \u0441\u0430\u043c\u043e\u0439 \u0441\u0430\u043c\u043e\u0433\u043e \u0441\u0430\u043c\u0438\u0445
- | \u0441\u0430\u043c\u043e\u043c\u0443 \u0441\u0430\u043c\u043e\u0439 \u0441\u0430\u043c\u043e\u043c\u0443 \u0441\u0430\u043c\u0438\u043c
- | \u0441\u0430\u043c\u0438\u043c \u0441\u0430\u043c\u043e\u0439 \u0441\u0430\u043c\u0438\u043c [\u0441\u0430\u043c\u043e\u044e] \u0441\u0430\u043c\u0438\u043c\u0438
- | \u0441\u0430\u043c\u043e\u043c \u0441\u0430\u043c\u043e\u0439 \u0441\u0430\u043c\u043e\u043c \u0441\u0430\u043c\u0438\u0445
- |
- | stems of verbs `to be', `to have', `to do' and modal
- |
- | \u0431\u044b\u0442\u044c \u0431\u044b \u0431\u0443\u0434 \u0431\u044b\u0432 \u0435\u0441\u0442\u044c \u0441\u0443\u0442\u044c
- | \u0438\u043c\u0435
- | \u0434\u0435\u043b
- | \u043c\u043e\u0433 \u043c\u043e\u0436 \u043c\u043e\u0447\u044c
- | \u0443\u043c\u0435
- | \u0445\u043e\u0447 \u0445\u043e\u0442
- | \u0434\u043e\u043b\u0436
- | \u043c\u043e\u0436\u043d
- | \u043d\u0443\u0436\u043d
- | \u043d\u0435\u043b\u044c\u0437\u044f
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_sv.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_sv.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_sv.txt
deleted file mode 100644
index 096f87f..0000000
--- a/solr/example/example-DIH/solr/rss/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
- | s� = 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
-p� | on
-den | it, this/that
-med | with
-var | where, each
-sig | him(self) etc
-f�r | for
-s� | so (also: seed)
-till | to
-�r | 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
-d� | then, when
-sin | his
-nu | now
-har | have
-inte | inte n�gon = no one
-hans | his
-honom | him
-skulle | 'sake'
-hennes | her
-d�r | there
-min | my
-man | one (pronoun)
-ej | nor
-vid | at, by, on (also: vast)
-kunde | could
-n�got | some etc
-fr�n | from, off
-ut | out
-n�r | when
-efter | after, behind
-upp | up
-vi | we
-dem | them
-vara | be
-vad | what
-�ver | over
-�n | than
-dig | you
-kan | can
-sina | his
-h�r | here
-ha | have
-mot | towards
-alla | all
-under | under (also: wonder)
-n�gon | some etc
-eller | or (else)
-allt | all
-mycket | much
-sedan | since
-ju | why
-denna | this/that
-sj�lv | myself, yourself etc
-detta | this/that
-�t | 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
-n�gra | some etc
-deras | their
-blir | from bli
-mina | my
-samma | (the) same
-vilken | who, that
-er | you, your
-s�dan | such a
-v�r | our
-blivit | from bli
-dess | its
-inom | within
-mellan | between
-s�dant | such a
-varf�r | why
-varje | each
-vilka | who, that
-ditt | thy
-vem | who
-vilket | who, that
-sitta | his
-s�dana | such a
-vart | each
-dina | thy
-vars | whose
-v�rt | our
-v�ra | our
-ert | your
-era | your
-vilkas | whose
-
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_th.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_th.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_th.txt
deleted file mode 100644
index 07f0fab..0000000
--- a/solr/example/example-DIH/solr/rss/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
-\u0e44\u0e27\u0e49
-\u0e44\u0e21\u0e48
-\u0e44\u0e1b
-\u0e44\u0e14\u0e49
-\u0e43\u0e2b\u0e49
-\u0e43\u0e19
-\u0e42\u0e14\u0e22
-\u0e41\u0e2b\u0e48\u0e07
-\u0e41\u0e25\u0e49\u0e27
-\u0e41\u0e25\u0e30
-\u0e41\u0e23\u0e01
-\u0e41\u0e1a\u0e1a
-\u0e41\u0e15\u0e48
-\u0e40\u0e2d\u0e07
-\u0e40\u0e2b\u0e47\u0e19
-\u0e40\u0e25\u0e22
-\u0e40\u0e23\u0e34\u0e48\u0e21
-\u0e40\u0e23\u0e32
-\u0e40\u0e21\u0e37\u0e48\u0e2d
-\u0e40\u0e1e\u0e37\u0e48\u0e2d
-\u0e40\u0e1e\u0e23\u0e32\u0e30
-\u0e40\u0e1b\u0e47\u0e19\u0e01\u0e32\u0e23
-\u0e40\u0e1b\u0e47\u0e19
-\u0e40\u0e1b\u0e34\u0e14\u0e40\u0e1c\u0e22
-\u0e40\u0e1b\u0e34\u0e14
-\u0e40\u0e19\u0e37\u0e48\u0e2d\u0e07\u0e08\u0e32\u0e01
-\u0e40\u0e14\u0e35\u0e22\u0e27\u0e01\u0e31\u0e19
-\u0e40\u0e14\u0e35\u0e22\u0e27
-\u0e40\u0e0a\u0e48\u0e19
-\u0e40\u0e09\u0e1e\u0e32\u0e30
-\u0e40\u0e04\u0e22
-\u0e40\u0e02\u0e49\u0e32
-\u0e40\u0e02\u0e32
-\u0e2d\u0e35\u0e01
-\u0e2d\u0e32\u0e08
-\u0e2d\u0e30\u0e44\u0e23
-\u0e2d\u0e2d\u0e01
-\u0e2d\u0e22\u0e48\u0e32\u0e07
-\u0e2d\u0e22\u0e39\u0e48
-\u0e2d\u0e22\u0e32\u0e01
-\u0e2b\u0e32\u0e01
-\u0e2b\u0e25\u0e32\u0e22
-\u0e2b\u0e25\u0e31\u0e07\u0e08\u0e32\u0e01
-\u0e2b\u0e25\u0e31\u0e07
-\u0e2b\u0e23\u0e37\u0e2d
-\u0e2b\u0e19\u0e36\u0e48\u0e07
-\u0e2a\u0e48\u0e27\u0e19
-\u0e2a\u0e48\u0e07
-\u0e2a\u0e38\u0e14
-\u0e2a\u0e4d\u0e32\u0e2b\u0e23\u0e31\u0e1a
-\u0e27\u0e48\u0e32
-\u0e27\u0e31\u0e19
-\u0e25\u0e07
-\u0e23\u0e48\u0e27\u0e21
-\u0e23\u0e32\u0e22
-\u0e23\u0e31\u0e1a
-\u0e23\u0e30\u0e2b\u0e27\u0e48\u0e32\u0e07
-\u0e23\u0e27\u0e21
-\u0e22\u0e31\u0e07
-\u0e21\u0e35
-\u0e21\u0e32\u0e01
-\u0e21\u0e32
-\u0e1e\u0e23\u0e49\u0e2d\u0e21
-\u0e1e\u0e1a
-\u0e1c\u0e48\u0e32\u0e19
-\u0e1c\u0e25
-\u0e1a\u0e32\u0e07
-\u0e19\u0e48\u0e32
-\u0e19\u0e35\u0e49
-\u0e19\u0e4d\u0e32
-\u0e19\u0e31\u0e49\u0e19
-\u0e19\u0e31\u0e01
-\u0e19\u0e2d\u0e01\u0e08\u0e32\u0e01
-\u0e17\u0e38\u0e01
-\u0e17\u0e35\u0e48\u0e2a\u0e38\u0e14
-\u0e17\u0e35\u0e48
-\u0e17\u0e4d\u0e32\u0e43\u0e2b\u0e49
-\u0e17\u0e4d\u0e32
-\u0e17\u0e32\u0e07
-\u0e17\u0e31\u0e49\u0e07\u0e19\u0e35\u0e49
-\u0e17\u0e31\u0e49\u0e07
-\u0e16\u0e49\u0e32
-\u0e16\u0e39\u0e01
-\u0e16\u0e36\u0e07
-\u0e15\u0e49\u0e2d\u0e07
-\u0e15\u0e48\u0e32\u0e07\u0e46
-\u0e15\u0e48\u0e32\u0e07
-\u0e15\u0e48\u0e2d
-\u0e15\u0e32\u0e21
-\u0e15\u0e31\u0e49\u0e07\u0e41\u0e15\u0e48
-\u0e15\u0e31\u0e49\u0e07
-\u0e14\u0e49\u0e32\u0e19
-\u0e14\u0e49\u0e27\u0e22
-\u0e14\u0e31\u0e07
-\u0e0b\u0e36\u0e48\u0e07
-\u0e0a\u0e48\u0e27\u0e07
-\u0e08\u0e36\u0e07
-\u0e08\u0e32\u0e01
-\u0e08\u0e31\u0e14
-\u0e08\u0e30
-\u0e04\u0e37\u0e2d
-\u0e04\u0e27\u0e32\u0e21
-\u0e04\u0e23\u0e31\u0e49\u0e07
-\u0e04\u0e07
-\u0e02\u0e36\u0e49\u0e19
-\u0e02\u0e2d\u0e07
-\u0e02\u0e2d
-\u0e02\u0e13\u0e30
-\u0e01\u0e48\u0e2d\u0e19
-\u0e01\u0e47
-\u0e01\u0e32\u0e23
-\u0e01\u0e31\u0e1a
-\u0e01\u0e31\u0e19
-\u0e01\u0e27\u0e48\u0e32
-\u0e01\u0e25\u0e48\u0e32\u0e27
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/stopwords_tr.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/stopwords_tr.txt b/solr/example/example-DIH/solr/rss/conf/lang/stopwords_tr.txt
deleted file mode 100644
index 84d9408..0000000
--- a/solr/example/example-DIH/solr/rss/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
-altm\u0131\u015f
-alt\u0131
-ama
-ancak
-arada
-asl\u0131nda
-ayr\u0131ca
-bana
-baz\u0131
-belki
-ben
-benden
-beni
-benim
-beri
-be\u015f
-bile
-bin
-bir
-bir�ok
-biri
-birka�
-birkez
-bir\u015fey
-bir\u015feyi
-biz
-bize
-bizden
-bizi
-bizim
-b�yle
-b�ylece
-bu
-buna
-bunda
-bundan
-bunlar
-bunlar\u0131
-bunlar\u0131n
-bunu
-bunun
-burada
-�ok
-��nk�
-da
-daha
-dahi
-de
-defa
-de\u011fil
-di\u011fer
-diye
-doksan
-dokuz
-dolay\u0131
-dolay\u0131s\u0131yla
-d�rt
-edecek
-eden
-ederek
-edilecek
-ediliyor
-edilmesi
-ediyor
-e\u011fer
-elli
-en
-etmesi
-etti
-etti\u011fi
-etti\u011fini
-gibi
-g�re
-halen
-hangi
-hatta
-hem
-hen�z
-hep
-hepsi
-her
-herhangi
-herkesin
-hi�
-hi�bir
-i�in
-iki
-ile
-ilgili
-ise
-i\u015fte
-itibaren
-itibariyle
-kadar
-kar\u015f\u0131n
-katrilyon
-kendi
-kendilerine
-kendini
-kendisi
-kendisine
-kendisini
-kez
-ki
-kim
-kimden
-kime
-kimi
-kimse
-k\u0131rk
-milyar
-milyon
-mu
-m�
-m\u0131
-nas\u0131l
-ne
-neden
-nedenle
-nerde
-nerede
-nereye
-niye
-ni�in
-o
-olan
-olarak
-oldu
-oldu\u011fu
-oldu\u011funu
-olduklar\u0131n\u0131
-olmad\u0131
-olmad\u0131\u011f\u0131
-olmak
-olmas\u0131
-olmayan
-olmaz
-olsa
-olsun
-olup
-olur
-olursa
-oluyor
-on
-ona
-ondan
-onlar
-onlardan
-onlar\u0131
-onlar\u0131n
-onu
-onun
-otuz
-oysa
-�yle
-pek
-ra\u011fmen
-sadece
-sanki
-sekiz
-seksen
-sen
-senden
-seni
-senin
-siz
-sizden
-sizi
-sizin
-\u015fey
-\u015feyden
-\u015feyi
-\u015feyler
-\u015f�yle
-\u015fu
-\u015funa
-\u015funda
-\u015fundan
-\u015funlar\u0131
-\u015funu
-taraf\u0131ndan
-trilyon
-t�m
-��
-�zere
-var
-vard\u0131
-ve
-veya
-ya
-yani
-yapacak
-yap\u0131lan
-yap\u0131lmas\u0131
-yap\u0131yor
-yapmak
-yapt\u0131
-yapt\u0131\u011f\u0131
-yapt\u0131\u011f\u0131n\u0131
-yapt\u0131klar\u0131
-yedi
-yerine
-yetmi\u015f
-yine
-yirmi
-yoksa
-y�z
-zaten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/lang/userdict_ja.txt
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/lang/userdict_ja.txt b/solr/example/example-DIH/solr/rss/conf/lang/userdict_ja.txt
deleted file mode 100644
index 6f0368e..0000000
--- a/solr/example/example-DIH/solr/rss/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
-\u65e5\u672c\u7d4c\u6e08\u65b0\u805e,\u65e5\u672c \u7d4c\u6e08 \u65b0\u805e,\u30cb\u30db\u30f3 \u30b1\u30a4\u30b6\u30a4 \u30b7\u30f3\u30d6\u30f3,\u30ab\u30b9\u30bf\u30e0\u540d\u8a5e
-\u95a2\u897f\u56fd\u969b\u7a7a\u6e2f,\u95a2\u897f \u56fd\u969b \u7a7a\u6e2f,\u30ab\u30f3\u30b5\u30a4 \u30b3\u30af\u30b5\u30a4 \u30af\u30a6\u30b3\u30a6,\u30ab\u30b9\u30bf\u30e0\u540d\u8a5e
-
-# Custom segmentation for compound katakana
-\u30c8\u30fc\u30c8\u30d0\u30c3\u30b0,\u30c8\u30fc\u30c8 \u30d0\u30c3\u30b0,\u30c8\u30fc\u30c8 \u30d0\u30c3\u30b0,\u304b\u305a\u30ab\u30ca\u540d\u8a5e
-\u30b7\u30e7\u30eb\u30c0\u30fc\u30d0\u30c3\u30b0,\u30b7\u30e7\u30eb\u30c0\u30fc \u30d0\u30c3\u30b0,\u30b7\u30e7\u30eb\u30c0\u30fc \u30d0\u30c3\u30b0,\u304b\u305a\u30ab\u30ca\u540d\u8a5e
-
-# Custom reading for former sumo wrestler
-\u671d\u9752\u9f8d,\u671d\u9752\u9f8d,\u30a2\u30b5\u30b7\u30e7\u30a6\u30ea\u30e5\u30a6,\u30ab\u30b9\u30bf\u30e0\u4eba\u540d
[4/6] lucene-solr:master: SOLR-7383: Replace DIH 'rss' example with
'atom' rss example was broken for multiple reasons. atom example showcases
the same - and more - features and uses the smallest config file needed to
make it work.
Posted by ar...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/580f6e98/solr/example/example-DIH/solr/rss/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/rss/conf/managed-schema b/solr/example/example-DIH/solr/rss/conf/managed-schema
deleted file mode 100644
index 9417902..0000000
--- a/solr/example/example-DIH/solr/rss/conf/managed-schema
+++ /dev/null
@@ -1,1096 +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-DIH-rss" 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
- 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 for faceting, grouping, sorting and function queries. Although not
- required, 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
- and all Trie*Fields, 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.
- -->
-
- <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml
- or Solr won't start. _version_ and update log are required for SolrCloud
- -->
- <field name="_version_" type="long" indexed="true" stored="true"/>
-
- <field name="subject" type="text_general" indexed="true" stored="true"/>
-
- <!-- catchall field, containing all other searchable text fields (implemented
- via copyField further on in this schema -->
- <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
-
- <field name="source" type="text_general" indexed="true" stored="true" />
- <field name="source-link" type="string" indexed="false" stored="true" />
-
- <field name="title" type="text_general" indexed="true" stored="true" />
- <field name="description" type="html" indexed="true" stored="true" />
-
- <field name="link" type="string" indexed="true" stored="true" required="true" multiValued="false" />
- <field name="creator" type="string" indexed="false" stored="true" />
- <field name="item-subject" type="string" indexed="true" stored="false" />
- <field name="date" type="date" indexed="true" stored="false" />
- <field name="slash-department" type="string" indexed="true" stored="false" />
- <field name="slash-section" type="string" indexed="true" stored="false" />
- <field name="slash-comments" type="int" indexed="true" stored="true" />
-
- <!-- 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="int" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true" />
- <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
-
- <!-- Type used to index the lat and lon components for the "location" FieldType -->
- <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
-
- <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"/>
-
- <!-- some trie-coded dynamic fields for faster range queries -->
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_tdt" type="tdate" 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 -->
- <!--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>link</uniqueKey>
-
- <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
- parsing a query string that isn't explicit about the field. Machine (non-user)
- generated queries are best made explicit, or they can use the "df" request parameter
- which takes precedence over this.
- Note: Un-commenting defaultSearchField will be insufficient if your request handler
- in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
- <defaultSearchField>text</defaultSearchField> -->
-
- <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
- when parsing a query string to determine if a clause of the query should be marked as
- required or optional, assuming the clause isn't already marked by some operator.
- The default is OR, which is generally assumed so it is not a good idea to change it
- globally here. The "q.op" request parameter takes precedence over this.
- <solrQueryParser defaultOperator="OR"/> -->
-
- <!-- 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="source" dest="text"/>
- <copyField source="subject" dest="text"/>
- <copyField source="title" dest="text"/>
- <copyField source="description" dest="text"/>
- <copyField source="creator" dest="text"/>
- <copyField source="item-subject" dest="text"/>
-
- <!-- Above, multiple source fields are copied to the [text] field.
- Another way to map multiple source fields to the same
- destination field is to use the dynamic field syntax.
- copyField also supports a maxChars to copy setting. -->
-
- <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
-
- <!-- copy name to alphaNameSort, a field designed for sorting by name -->
- <!-- <copyField source="name" dest="alphaNameSort"/> -->
-
-
- <!-- 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
- -->
-
- <fieldType name="html" stored="true" indexed="true" class="solr.TextField">
- <analyzer type="index">
- <charFilter class="solr.HTMLStripCharFilterFactory"/>
- <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.StopFilterFactory" ignoreCase="true" words="stopwords.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.RemoveDuplicatesTokenFilterFactory"/>
- <filter class="solr.FlattenGraphFilterFactory" />
- </analyzer>
- <analyzer type="query">
- <charFilter class="solr.HTMLStripCharFilterFactory"/>
- <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.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"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- 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" />
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="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", and, as of 3.5 (and 4.x),
- int, float, long, date, double, including the "Trie" 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.
- -->
-
- <!--
- Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-
- These fields support doc values, but they require the field to be
- single-valued and either be required or have a default value.
- -->
- <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"/>
-
- <!--
- 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.
- -->
- <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"/>
-
- <!-- 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.
-
- Note: For faster range queries, consider the tdate type
- -->
- <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
-
- <!-- A Trie based date field for faster date range queries and date faceting. -->
- <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
-
-
- <!--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 -->
- <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">
- <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. -->
- <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".
- -->
- <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. -->
- <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. -->
- <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>
-
- <!-- charFilter + WhitespaceTokenizer -->
- <!--
- <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
- -->
-
- <!-- This is an example of using the KeywordTokenizer along
- With various TokenFilterFactories to produce a sortable field
- that does not include some properties of the source text
- -->
- <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
- <analyzer>
- <!-- KeywordTokenizer does no actual tokenizing, so the entire
- input string is preserved as a single token
- -->
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <!-- The LowerCase TokenFilter does what you expect, which can be
- when you want your sorting to be case insensitive
- -->
- <filter class="solr.LowerCaseFilterFactory" />
- <!-- The TrimFilter removes any leading or trailing whitespace -->
- <filter class="solr.TrimFilterFactory" />
- <!-- The PatternReplaceFilter gives you the flexibility to use
- Java Regular expression to replace any sequence of characters
- matching a pattern with an arbitrary replacement string,
- which may include back references to portions of the original
- string matched by the pattern.
-
- See the Java Regular Expression documentation for more
- information on pattern and replacement string syntax.
-
- http://docs.oracle.com/javase/8/docs/api/java/util/regex/package-summary.html
- -->
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-z])" replacement="" replace="all"
- />
- </analyzer>
- </fieldType>
-
- <fieldType name="phonetic" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
- </analyzer>
- </fieldType>
-
- <fieldType name="payloads" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!--
- The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
- a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
- Attributes of the DelimitedPayloadTokenFilterFactory :
- "delimiter" - a one character delimiter. Default is | (pipe)
- "encoder" - how to encode the following value into a playload
- float -> org.apache.lucene.analysis.payloads.FloatEncoder,
- integer -> o.a.l.a.p.IntegerEncoder
- identity -> o.a.l.a.p.IdentityEncoder
- Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
- -->
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </analyzer>
- </fieldType>
-
- <!-- lowercases the entire field value, keeping it as a single token. -->
- <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
- -->
- <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
- -->
- <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" 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.
- -->
- <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
-
- <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
- <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
-
- <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
- For more information about this and other Spatial fields new to Solr 4, see:
- http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
- -->
- <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
- geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
-
- <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
- Parameters:
- defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
- precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
- providerClass: Lets you plug in other exchange provider backend:
- solr.FileExchangeRateProvider is the default and takes one parameter:
- currencyConfig: name of an xml file holding exchange rates
- solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
- ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
- refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
- -->
- <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
-
-
-
- <!-- some examples for different languages (generally ordered by ISO code) -->
-
- <!-- Arabic -->
- <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 \ufeef to \ufef1, etc -->
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.ArabicStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Bulgarian -->
- <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 -->
- <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) -->
- <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>
-
- <!-- Kurdish -->
- <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SoraniNormalizationFilterFactory"/>
- <!-- for any latin text -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
- <filter class="solr.SoraniStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Czech -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 query
- parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
- OR if you would like to optimize for recall (default).
- -->
- <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 (\u8f9e\u66f8\u5f62) -->
- <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 -->
- <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 -->
- <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 -->
- <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" variant="nb"/> -->
- <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
- <!-- The "light" and "minimal" stemmers support variants: nb=Bokm�l, nn=Nynorsk, no=Both -->
- </analyzer>
- </fieldType>
-
- <!-- Portuguese -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <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 -->
- <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.ApostropheFilterFactory"/>
- <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>