You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by yo...@apache.org on 2016/07/08 19:45:57 UTC
[1/4] lucene-solr:branch_6x: SOLR-9163: sync basic_configs w/
data_driven_schema_configs
Repository: lucene-solr
Updated Branches:
refs/heads/branch_6x df2207c5d -> 1a53346c0
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml b/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
index 069a4ee..c7e41e8 100644
--- a/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
+++ b/solr/server/solr/configsets/basic_configs/conf/solrconfig.xml
@@ -37,6 +37,60 @@
-->
<luceneMatchVersion>6.2.0</luceneMatchVersion>
+ <!-- <lib/> directives can be used to instruct Solr to load any Jars
+ identified and use them to resolve any "plugins" specified in
+ your solrconfig.xml or schema.xml (ie: Analyzers, Request
+ Handlers, etc...).
+
+ All directories and paths are resolved relative to the
+ instanceDir.
+
+ Please note that <lib/> directives are processed in the order
+ that they appear in your solrconfig.xml file, and are "stacked"
+ on top of each other when building a ClassLoader - so if you have
+ plugin jars with dependencies on other jars, the "lower level"
+ dependency jars should be loaded first.
+
+ If a "./lib" directory exists in your instanceDir, all files
+ found in it are included as if you had used the following
+ syntax...
+
+ <lib dir="./lib" />
+ -->
+
+ <!-- A 'dir' option by itself adds any files found in the directory
+ to the classpath, this is useful for including all jars in a
+ directory.
+
+ When a 'regex' is specified in addition to a 'dir', only the
+ files in that directory which completely match the regex
+ (anchored on both ends) will be included.
+
+ If a 'dir' option (with or without a regex) is used and nothing
+ is found that matches, a warning will be logged.
+
+ The examples below can be used to load some solr-contribs along
+ with their external dependencies.
+ -->
+ <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
+
+ <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
+ <!-- an exact 'path' can be used instead of a 'dir' to specify a
+ specific jar file. This will cause a serious error to be logged
+ if it can't be loaded.
+ -->
+ <!--
+ <lib path="../a-jar-that-does-not-exist.jar" />
+ -->
+
<!-- Data Directory
Used to specify an alternate directory to hold all index data
@@ -61,9 +115,8 @@
solr.RAMDirectoryFactory is memory based, not
persistent, and doesn't work with replication.
-->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
- </directoryFactory>
+ <directoryFactory name="DirectoryFactory"
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
<!-- The CodecFactory for defining the format of the inverted index.
The default implementation is SchemaCodecFactory, which is the official Lucene
@@ -87,6 +140,51 @@
Note: This replaces <indexDefaults> and <mainIndex> from older versions
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
<indexConfig>
+ <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
+ LimitTokenCountFilterFactory in your fieldType definition. E.g.
+ <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
+ -->
+ <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
+ <!-- <writeLockTimeout>1000</writeLockTimeout> -->
+
+ <!-- Expert: Enabling compound file will use less files for the index,
+ using fewer file descriptors on the expense of performance decrease.
+ Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
+ <!-- <useCompoundFile>false</useCompoundFile> -->
+
+ <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+ indexing for buffering added documents and deletions before they are
+ flushed to the Directory.
+ maxBufferedDocs sets a limit on the number of documents buffered
+ before flushing.
+ If both ramBufferSizeMB and maxBufferedDocs is set, then
+ Lucene will flush based on whichever limit is hit first. -->
+ <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
+ <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
+
+ <!-- Expert: Merge Policy
+ The Merge Policy in Lucene controls how merging of segments is done.
+ The default since Solr/Lucene 3.3 is TieredMergePolicy.
+ The default since Lucene 2.3 was the LogByteSizeMergePolicy,
+ Even older versions of Lucene used LogDocMergePolicy.
+ -->
+ <!--
+ <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
+ <int name="maxMergeAtOnce">10</int>
+ <int name="segmentsPerTier">10</int>
+ <double name="noCFSRatio">0.1</double>
+ </mergePolicyFactory>
+ -->
+
+ <!-- Expert: Merge Scheduler
+ The Merge Scheduler in Lucene controls how merges are
+ performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
+ can perform merges in the background using separate threads.
+ The SerialMergeScheduler (Lucene 2.2 default) does not.
+ -->
+ <!--
+ <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
+ -->
<!-- LockFactory
@@ -109,16 +207,45 @@
-->
<lockType>${solr.lock.type:native}</lockType>
+ <!-- Commit Deletion Policy
+ Custom deletion policies can be specified here. The class must
+ implement org.apache.lucene.index.IndexDeletionPolicy.
+
+ The default Solr IndexDeletionPolicy implementation supports
+ deleting index commit points on number of commits, age of
+ commit point and optimized status.
+
+ The latest commit point should always be preserved regardless
+ of the criteria.
+ -->
+ <!--
+ <deletionPolicy class="solr.SolrDeletionPolicy">
+ -->
+ <!-- The number of commit points to be kept -->
+ <!-- <str name="maxCommitsToKeep">1</str> -->
+ <!-- The number of optimized commit points to be kept -->
+ <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
+ <!--
+ Delete all commit points once they have reached the given age.
+ Supports DateMathParser syntax e.g.
+ -->
+ <!--
+ <str name="maxCommitAge">30MINUTES</str>
+ <str name="maxCommitAge">1DAY</str>
+ -->
+ <!--
+ </deletionPolicy>
+ -->
+
<!-- Lucene Infostream
To aid in advanced debugging, Lucene provides an "InfoStream"
of detailed information when indexing.
- Setting the value to true will instruct the underlying Lucene
- IndexWriter to write its info stream to solr's log. By default,
- this is enabled here, and controlled through log4j.properties.
+ Setting The value to true will instruct the underlying Lucene
+ IndexWriter to write its debugging info the specified file
-->
- <infoStream>true</infoStream>
+ <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
</indexConfig>
@@ -160,7 +287,7 @@
<str name="dir">${solr.ulog.dir:}</str>
<int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
</updateLog>
-
+
<!-- AutoCommit
Perform a hard commit automatically under certain conditions.
@@ -182,22 +309,83 @@
If the updateLog is enabled, then it's highly recommended to
have some sort of hard autoCommit to limit the log size.
-->
- <autoCommit>
- <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
+ <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>
+
+ <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
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
@@ -247,7 +435,7 @@
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.
+ and old cache.
-->
<filterCache class="solr.FastLRUCache"
size="512"
@@ -255,36 +443,69 @@
autowarmCount="0"/>
<!-- Query Result Cache
-
- Caches results of searches - ordered lists of document ids
- (DocList) based on a query, a sort, and the range of documents requested.
- Additional supported parameter by LRUCache:
- maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
- to occupy
- -->
+
+ Caches results of searches - ordered lists of document ids
+ (DocList) based on a query, a sort, and the range of documents requested.
+ Additional supported parameter by LRUCache:
+ maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+ to occupy
+ -->
<queryResultCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
+ 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.
+ this cache will not be autowarmed.
-->
<documentCache class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
-
- <!-- custom cache currently used by block join -->
+
+ <!-- custom cache currently used by block join -->
<cache name="perSegFilter"
- class="solr.search.LRUCache"
- size="10"
- initialSize="0"
- autowarmCount="10"
- regenerator="solr.NoOpRegenerator" />
+ 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
@@ -296,21 +517,75 @@
-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
- <!-- Result Window Size
+ <!-- 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>
+ -->
- 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>
+ <!-- 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>
+ <!-- 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
@@ -384,8 +659,8 @@
should make sure your system has some authentication before
using enableRemoteStreaming="true"
- -->
- <requestParsers enableRemoteStreaming="true"
+ -->
+ <requestParsers enableRemoteStreaming="true"
multipartUploadLimitInKB="2048000"
formdataUploadLimitInKB="2048"
addHttpRequestToContext="false"/>
@@ -398,7 +673,51 @@
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
@@ -433,29 +752,119 @@
<!-- 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>
- </lst>
-
- </requestHandler>
+ <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>
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="wt">json</str>
+ <str name="indent">true</str>
+ </lst>
+ </requestHandler>
+
+
+ <!-- A Robust Example
+
+ This example SearchHandler declaration shows off usage of the
+ SearchHandler with many defaults declared
+
+ Note that multiple instances of the same Request Handler
+ (SearchHandler) can be registered multiple times with different
+ names (and different init parameters)
+ -->
+ <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
</requestHandler>
- <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell">
+ <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
<lst name="defaults">
- <str name="df">text</str>
+ <str name="df">_text_</str>
</lst>
</initParams>
+ <!-- This enabled schemaless mode
+ <initParams path="/update/**">
+ <lst name="defaults">
+ <str name="update.chain">add-unknown-fields-to-the-schema</str>
+ </lst>
+ </initParams>
+ -->
+
+ <!-- Solr Cell Update Request Handler
+
+ http://wiki.apache.org/solr/ExtractingRequestHandler
+
+ -->
+ <requestHandler name="/update/extract"
+ startup="lazy"
+ class="solr.extraction.ExtractingRequestHandler" >
+ <lst name="defaults">
+ <str name="lowernames">true</str>
+ <str name="fmap.meta">ignored_</str>
+ <str name="fmap.content">_text_</str>
+ </lst>
+ </requestHandler>
+
<!-- Field Analysis Request Handler
RequestHandler that provides much the same functionality as
@@ -474,7 +883,7 @@
field value analysis will be marked as "matched" for every
token that is produces by the query analysis
-->
- <requestHandler name="/analysis/field"
+ <requestHandler name="/analysis/field"
startup="lazy"
class="solr.FieldAnalysisRequestHandler" />
@@ -509,19 +918,17 @@
true, all field tokens that match the query tokens will be marked
as a "match".
-->
- <requestHandler name="/analysis/document"
- class="solr.DocumentAnalysisRequestHandler"
+ <requestHandler name="/analysis/document"
+ class="solr.DocumentAnalysisRequestHandler"
startup="lazy" />
<!-- Echo the request contents back to the client -->
<requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
<lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="echoHandler">true</str>
+ <str name="echoParams">explicit</str>
+ <str name="echoHandler">true</str>
</lst>
</requestHandler>
-
-
<!-- Search Components
@@ -536,9 +943,147 @@
<searchComponent name="highlight" class="solr.HighlightComponent" />
<searchComponent name="stats" class="solr.StatsComponent" />
<searchComponent name="debug" class="solr.DebugComponent" />
+
+ Default configuration in a requestHandler would look like:
+
+ <arr name="components">
+ <str>query</str>
+ <str>facet</str>
+ <str>mlt</str>
+ <str>highlight</str>
+ <str>stats</str>
+ <str>debug</str>
+ </arr>
+
+ If you register a searchComponent to one of the standard names,
+ that will be used instead of the default.
+
+ To insert components before or after the 'standard' components, use:
+
+ <arr name="first-components">
+ <str>myFirstComponentName</str>
+ </arr>
+
+ <arr name="last-components">
+ <str>myLastComponentName</str>
+ </arr>
+
+ NOTE: The component registered with the name "debug" will
+ always be executed after the "last-components"
-->
+ <!-- Spell Check
+
+ The spell check component can return a list of alternative spelling
+ suggestions.
+
+ http://wiki.apache.org/solr/SpellCheckComponent
+ -->
+ <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
+
+ <str name="queryAnalyzerFieldType">text_general</str>
+
+ <!-- Multiple "Spell Checkers" can be declared and used by this
+ component
+ -->
+
+ <!-- a spellchecker built from a field of the main index -->
+ <lst name="spellchecker">
+ <str name="name">default</str>
+ <str name="field">_text_</str>
+ <str name="classname">solr.DirectSolrSpellChecker</str>
+ <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
+ <str name="distanceMeasure">internal</str>
+ <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
+ <float name="accuracy">0.5</float>
+ <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
+ <int name="maxEdits">2</int>
+ <!-- the minimum shared prefix when enumerating terms -->
+ <int name="minPrefix">1</int>
+ <!-- maximum number of inspections per result. -->
+ <int name="maxInspections">5</int>
+ <!-- minimum length of a query term to be considered for correction -->
+ <int name="minQueryLength">4</int>
+ <!-- maximum threshold of documents a query term can appear to be considered for correction -->
+ <float name="maxQueryFrequency">0.01</float>
+ <!-- uncomment this to require suggestions to occur in 1% of the documents
+ <float name="thresholdTokenFrequency">.01</float>
+ -->
+ </lst>
+
+ <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
+ <!--
+ <lst name="spellchecker">
+ <str name="name">wordbreak</str>
+ <str name="classname">solr.WordBreakSolrSpellChecker</str>
+ <str name="field">name</str>
+ <str name="combineWords">true</str>
+ <str name="breakWords">true</str>
+ <int name="maxChanges">10</int>
+ </lst>
+ -->
+ </searchComponent>
+
+ <!-- A request handler for demonstrating the spellcheck component.
+
+ NOTE: This is purely as an example. The whole purpose of the
+ SpellCheckComponent is to hook it into the request handler that
+ handles your normal user queries so that a separate request is
+ not needed to get suggestions.
+
+ IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
+ NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
+
+ See http://wiki.apache.org/solr/SpellCheckComponent for details
+ on the request parameters.
+ -->
+ <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <!-- Solr will use suggestions from both the 'default' spellchecker
+ and from the 'wordbreak' spellchecker and combine them.
+ collations (re-written queries) can include a combination of
+ corrections from both spellcheckers -->
+ <str name="spellcheck.dictionary">default</str>
+ <str name="spellcheck">on</str>
+ <str name="spellcheck.extendedResults">true</str>
+ <str name="spellcheck.count">10</str>
+ <str name="spellcheck.alternativeTermCount">5</str>
+ <str name="spellcheck.maxResultsForSuggest">5</str>
+ <str name="spellcheck.collate">true</str>
+ <str name="spellcheck.collateExtendedResults">true</str>
+ <str name="spellcheck.maxCollationTries">10</str>
+ <str name="spellcheck.maxCollations">5</str>
+ </lst>
+ <arr name="last-components">
+ <str>spellcheck</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Term Vector Component
+
+ http://wiki.apache.org/solr/TermVectorComponent
+ -->
+ <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
+
+ <!-- A request handler for demonstrating the term vector component
+
+ This is purely as an example.
+
+ In reality you will likely want to add the component to your
+ already specified request handlers.
+ -->
+ <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <bool name="tv">true</bool>
+ </lst>
+ <arr name="last-components">
+ <str>tvComponent</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Clustering Component. (Omitted here. See the default Solr example for a typical configuration.) -->
+
<!-- Terms Component
http://wiki.apache.org/solr/TermsComponent
@@ -550,13 +1095,390 @@
<!-- A request handler for demonstrating the terms component -->
<requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
+ <lst name="defaults">
<bool name="terms">true</bool>
<bool name="distrib">false</bool>
- </lst>
+ </lst>
<arr name="components">
<str>terms</str>
</arr>
</requestHandler>
+
+ <!-- Query Elevation Component
+
+ http://wiki.apache.org/solr/QueryElevationComponent
+
+ a search component that enables you to configure the top
+ results for a given query regardless of the normal lucene
+ scoring.
+ -->
+ <searchComponent name="elevator" class="solr.QueryElevationComponent" >
+ <!-- pick a fieldType to analyze queries -->
+ <str name="queryFieldType">string</str>
+ <str name="config-file">elevate.xml</str>
+ </searchComponent>
+
+ <!-- A request handler for demonstrating the elevator component -->
+ <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ </lst>
+ <arr name="last-components">
+ <str>elevator</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Highlighting Component
+
+ http://wiki.apache.org/solr/HighlightingParameters
+ -->
+ <searchComponent class="solr.HighlightComponent" name="highlight">
+ <highlighting>
+ <!-- Configure the standard fragmenter -->
+ <!-- This could most likely be commented out in the "default" case -->
+ <fragmenter name="gap"
+ default="true"
+ class="solr.highlight.GapFragmenter">
+ <lst name="defaults">
+ <int name="hl.fragsize">100</int>
+ </lst>
+ </fragmenter>
+
+ <!-- A regular-expression-based fragmenter
+ (for sentence extraction)
+ -->
+ <fragmenter name="regex"
+ class="solr.highlight.RegexFragmenter">
+ <lst name="defaults">
+ <!-- slightly smaller fragsizes work better because of slop -->
+ <int name="hl.fragsize">70</int>
+ <!-- allow 50% slop on fragment sizes -->
+ <float name="hl.regex.slop">0.5</float>
+ <!-- a basic sentence pattern -->
+ <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
+ </lst>
+ </fragmenter>
+
+ <!-- Configure the standard formatter -->
+ <formatter name="html"
+ default="true"
+ class="solr.highlight.HtmlFormatter">
+ <lst name="defaults">
+ <str name="hl.simple.pre"><![CDATA[<em>]]></str>
+ <str name="hl.simple.post"><![CDATA[</em>]]></str>
+ </lst>
+ </formatter>
+
+ <!-- Configure the standard encoder -->
+ <encoder name="html"
+ class="solr.highlight.HtmlEncoder" />
+
+ <!-- Configure the standard fragListBuilder -->
+ <fragListBuilder name="simple"
+ class="solr.highlight.SimpleFragListBuilder"/>
+
+ <!-- Configure the single fragListBuilder -->
+ <fragListBuilder name="single"
+ class="solr.highlight.SingleFragListBuilder"/>
+
+ <!-- Configure the weighted fragListBuilder -->
+ <fragListBuilder name="weighted"
+ default="true"
+ class="solr.highlight.WeightedFragListBuilder"/>
+
+ <!-- default tag FragmentsBuilder -->
+ <fragmentsBuilder name="default"
+ default="true"
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
+ <!--
+ <lst name="defaults">
+ <str name="hl.multiValuedSeparatorChar">/</str>
+ </lst>
+ -->
+ </fragmentsBuilder>
+
+ <!-- multi-colored tag FragmentsBuilder -->
+ <fragmentsBuilder name="colored"
+ class="solr.highlight.ScoreOrderFragmentsBuilder">
+ <lst name="defaults">
+ <str name="hl.tag.pre"><![CDATA[
+ <b style="background:yellow">,<b style="background:lawgreen">,
+ <b style="background:aquamarine">,<b style="background:magenta">,
+ <b style="background:palegreen">,<b style="background:coral">,
+ <b style="background:wheat">,<b style="background:khaki">,
+ <b style="background:lime">,<b style="background:deepskyblue">]]></str>
+ <str name="hl.tag.post"><![CDATA[</b>]]></str>
+ </lst>
+ </fragmentsBuilder>
+
+ <boundaryScanner name="default"
+ default="true"
+ class="solr.highlight.SimpleBoundaryScanner">
+ <lst name="defaults">
+ <str name="hl.bs.maxScan">10</str>
+ <str name="hl.bs.chars">.,!? 	 </str>
+ </lst>
+ </boundaryScanner>
+
+ <boundaryScanner name="breakIterator"
+ class="solr.highlight.BreakIteratorBoundaryScanner">
+ <lst name="defaults">
+ <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
+ <str name="hl.bs.type">WORD</str>
+ <!-- language and country are used when constructing Locale object. -->
+ <!-- And the Locale object will be used when getting instance of BreakIterator -->
+ <str name="hl.bs.language">en</str>
+ <str name="hl.bs.country">US</str>
+ </lst>
+ </boundaryScanner>
+ </highlighting>
+ </searchComponent>
+
+ <!-- Update Processors
+
+ Chains of Update Processor Factories for dealing with Update
+ Requests can be declared, and then used by name in Update
+ Request Processors
+
+ http://wiki.apache.org/solr/UpdateRequestProcessor
+
+ -->
+
+ <!-- Add unknown fields to the schema
+
+ An example field type guessing update processor that will
+ attempt to parse string-typed field values as Booleans, Longs,
+ Doubles, or Dates, and then add schema fields with the guessed
+ field types.
+
+ This requires that the schema is both managed and mutable, by
+ declaring schemaFactory as ManagedIndexSchemaFactory, with
+ mutable specified as true.
+
+ See http://wiki.apache.org/solr/GuessingFieldTypes
+ -->
+ <updateRequestProcessorChain name="add-unknown-fields-to-the-schema">
+ <!-- UUIDUpdateProcessorFactory will generate an id if none is present in the incoming document -->
+ <processor class="solr.UUIDUpdateProcessorFactory" />
+
+ <processor class="solr.LogUpdateProcessorFactory"/>
+ <processor class="solr.DistributedUpdateProcessorFactory"/>
+ <processor class="solr.RemoveBlankFieldUpdateProcessorFactory"/>
+ <processor class="solr.FieldNameMutatingUpdateProcessorFactory">
+ <str name="pattern">[^\w-\.]</str>
+ <str name="replacement">_</str>
+ </processor>
+ <processor class="solr.ParseBooleanFieldUpdateProcessorFactory"/>
+ <processor class="solr.ParseLongFieldUpdateProcessorFactory"/>
+ <processor class="solr.ParseDoubleFieldUpdateProcessorFactory"/>
+ <processor class="solr.ParseDateFieldUpdateProcessorFactory">
+ <arr name="format">
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
+ <str>yyyy-MM-dd'T'HH:mm:ss</str>
+ <str>yyyy-MM-dd'T'HH:mmZ</str>
+ <str>yyyy-MM-dd'T'HH:mm</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
+ <str>yyyy-MM-dd HH:mm:ss.SSS</str>
+ <str>yyyy-MM-dd HH:mm:ss,SSS</str>
+ <str>yyyy-MM-dd HH:mm:ssZ</str>
+ <str>yyyy-MM-dd HH:mm:ss</str>
+ <str>yyyy-MM-dd HH:mmZ</str>
+ <str>yyyy-MM-dd HH:mm</str>
+ <str>yyyy-MM-dd</str>
+ </arr>
+ </processor>
+ <processor class="solr.AddSchemaFieldsUpdateProcessorFactory">
+ <str name="defaultFieldType">strings</str>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Boolean</str>
+ <str name="fieldType">booleans</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.util.Date</str>
+ <str name="fieldType">tdates</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Long</str>
+ <str name="valueClass">java.lang.Integer</str>
+ <str name="fieldType">tlongs</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Number</str>
+ <str name="fieldType">tdoubles</str>
+ </lst>
+ </processor>
+ <processor class="solr.RunUpdateProcessorFactory"/>
+ </updateRequestProcessorChain>
+
+ <!-- Deduplication
+
+ An example dedup update processor that creates the "id" field
+ on the fly based on the hash code of some other fields. This
+ example has overwriteDupes set to false since we are using the
+ id field as the signatureField and Solr will maintain
+ uniqueness based on that anyway.
+
+ -->
+ <!--
+ <updateRequestProcessorChain name="dedupe">
+ <processor class="solr.processor.SignatureUpdateProcessorFactory">
+ <bool name="enabled">true</bool>
+ <str name="signatureField">id</str>
+ <bool name="overwriteDupes">false</bool>
+ <str name="fields">name,features,cat</str>
+ <str name="signatureClass">solr.processor.Lookup3Signature</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Language identification
+
+ This example update chain identifies the language of the incoming
+ documents using the langid contrib. The detected language is
+ written to field language_s. No field name mapping is done.
+ The fields used for detection are text, title, subject and description,
+ making this example suitable for detecting languages form full-text
+ rich documents injected via ExtractingRequestHandler.
+ See more about langId at http://wiki.apache.org/solr/LanguageDetection
+ -->
+ <!--
+ <updateRequestProcessorChain name="langid">
+ <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
+ <str name="langid.fl">text,title,subject,description</str>
+ <str name="langid.langField">language_s</str>
+ <str name="langid.fallback">en</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory" />
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Script update processor
+
+ This example hooks in an update processor implemented using JavaScript.
+
+ See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
+ -->
+ <!--
+ <updateRequestProcessorChain name="script">
+ <processor class="solr.StatelessScriptUpdateProcessorFactory">
+ <str name="script">update-script.js</str>
+ <lst name="params">
+ <str name="config_param">example config parameter</str>
+ </lst>
+ </processor>
+ <processor class="solr.RunUpdateProcessorFactory" />
+ </updateRequestProcessorChain>
+ -->
+
+ <!-- Response Writers
+
+ http://wiki.apache.org/solr/QueryResponseWriter
+
+ Request responses will be written using the writer specified by
+ the 'wt' request parameter matching the name of a registered
+ writer.
+
+ The "default" writer is the default and will be used if 'wt' is
+ not specified in the request.
+ -->
+ <!-- The following response writers are implicitly configured unless
+ overridden...
+ -->
+ <!--
+ <queryResponseWriter name="xml"
+ default="true"
+ class="solr.XMLResponseWriter" />
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
+ <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
+ <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
+ <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
+ <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
+ <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
+ <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
+ -->
+
+ <queryResponseWriter name="json" class="solr.JSONResponseWriter">
+ <!-- For the purposes of the tutorial, JSON responses are written as
+ plain text so that they are easy to read in *any* browser.
+ If you expect a MIME type of "application/json" just remove this override.
+ -->
+ <str name="content-type">text/plain; charset=UTF-8</str>
+ </queryResponseWriter>
+
+ <!--
+ Custom response writers can be declared as needed...
+ -->
+ <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
+ <str name="template.base.dir">${velocity.template.base.dir:}</str>
+ <str name="solr.resource.loader.enabled">${velocity.solr.resource.loader.enabled:true}</str>
+ <str name="params.resource.loader.enabled">${velocity.params.resource.loader.enabled:false}</str>
+ </queryResponseWriter>
+
+ <!-- XSLT response writer transforms the XML output by any xslt file found
+ in Solr's conf/xslt directory. Changes to xslt files are checked for
+ every xsltCacheLifetimeSeconds.
+ -->
+ <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
+ <int name="xsltCacheLifetimeSeconds">5</int>
+ </queryResponseWriter>
+
+ <!-- Query Parsers
+
+ https://cwiki.apache.org/confluence/display/solr/Query+Syntax+and+Parsing
+
+ Multiple QParserPlugins can be registered by name, and then
+ used in either the "defType" param for the QueryComponent (used
+ by SearchHandler) or in LocalParams
+ -->
+ <!-- example of registering a query parser -->
+ <!--
+ <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
+ -->
+
+ <!-- Function Parsers
+
+ http://wiki.apache.org/solr/FunctionQuery
+
+ Multiple ValueSourceParsers can be registered by name, and then
+ used as function names when using the "func" QParser.
+ -->
+ <!-- example of registering a custom function parser -->
+ <!--
+ <valueSourceParser name="myfunc"
+ class="com.mycompany.MyValueSourceParser" />
+ -->
+
+
+ <!-- Document Transformers
+ http://wiki.apache.org/solr/DocTransformers
+ -->
+ <!--
+ Could be something like:
+ <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
+ <int name="connection">jdbc://....</int>
+ </transformer>
+
+ To add a constant value to all docs, use:
+ <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <int name="value">5</int>
+ </transformer>
+
+ If you want the user to still be able to change it with _value:something_ use this:
+ <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
+ <double name="defaultValue">5</double>
+ </transformer>
+
+ If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
+ EditorialMarkerFactory will do exactly that:
+ <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
+ -->
</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema b/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
index cf2b873..5b969dd 100644
--- a/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
+++ b/solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema
@@ -121,8 +121,10 @@
<field name="_version_" type="long" indexed="true" stored="false"/>
<field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
<field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
- <copyField source="*" dest="_text_"/>
+ <!-- Only enabled in the "schemaless" data-driven example (assuming the client
+ does not know what fields may be searched) because it's very expensive to index everything twice. -->
+ <copyField source="*" dest="_text_"/>
<!-- Dynamic field definitions allow using convention over configuration
for fields via the specification of patterns to match field names.
[2/4] lucene-solr:branch_6x: SOLR-9163: sync basic_configs w/
data_driven_schema_configs
Posted by yo...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/managed-schema b/solr/server/solr/configsets/basic_configs/conf/managed-schema
index ba24bf1..95a9027 100644
--- a/solr/server/solr/configsets/basic_configs/conf/managed-schema
+++ b/solr/server/solr/configsets/basic_configs/conf/managed-schema
@@ -27,10 +27,26 @@
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" version="1.6">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
+<schema name="example-basic" version="1.6">
+ <!-- attribute "name" is the name of this schema and is only used for display purposes.
version="x.y" is Solr's version number for the schema syntax and
semantics. It should not normally be changed by applications.
@@ -46,13 +62,12 @@
1.5: omitNorms defaults to true for primitive field types
(int, float, boolean, string...)
1.6: useDocValuesAsStored defaults to true.
- -->
-
+ -->
- <!-- Valid attributes for fields:
+ <!-- Valid attributes for fields:
name: mandatory - the name for the field
type: mandatory - the name of a field type from the
- fieldTypes
+ fieldTypes section
indexed: true if this field should be indexed (searchable or sortable)
stored: true if this field should be retrievable
docValues: true if this field should have doc values. Doc values are
@@ -82,99 +97,104 @@
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
+ <!-- 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="false" />
-
- <!-- points to the root document of a block of nested documents. Required for nested
- document support, may be removed otherwise
- -->
- <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
-
- <!-- Only remove the "id" field if you have a very good reason to. While not strictly
- required, it is highly recommended. A <uniqueKey> is present in almost all Solr
- installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id".
- Do NOT change the type and apply index-time analysis to the <uniqueKey> as it will likely
- make routing in SolrCloud and document replacement in general fail. Limited _query_ time
- analysis is possible as long as the indexing process is guaranteed to index the term
- in a compatible way. Any analysis applied to the <uniqueKey> should _not_ produce multiple
- tokens
- -->
- <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
-
- <!-- Dynamic field definitions allow using convention over configuration
+ <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
+ id, _version_, and _text_. All other fields will be type guessed and added via the
+ "add-unknown-fields-to-the-schema" update request processor chain declared
+ in solrconfig.xml.
+
+ Note that many dynamic fields are also defined - you can use them to specify a
+ field's type via field naming conventions - see below.
+
+ WARNING: The _text_ catch-all field will significantly increase your index size.
+ If you don't need it, consider removing it and the corresponding copyField directive.
+ -->
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <field name="_version_" type="long" indexed="true" stored="false"/>
+ <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+ <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
+
+ <!-- Only enabled in the "schemaless" data-driven example (assuming the client
+ does not know what fields may be searched) because it's very expensive to index everything twice. -->
+ <!-- <copyField source="*" dest="_text_"/> -->
+
+ <!-- Dynamic field definitions allow using convention over configuration
for fields via the specification of patterns to match field names.
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
RESTRICTION: the glob-like pattern in the name attribute must have
a "*" only at the start or the end. -->
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_is" type="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" useDocValuesAsStored="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
+ <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+ <dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true" />
+ <dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
+ <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
+
+ <!-- Type used to index the lat and lon components for the "location" FieldType -->
+ <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" useDocValuesAsStored="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"/>
+ <dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
+
+ <!-- some trie-coded dynamic fields for faster range queries -->
+ <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
+ <dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
+ <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
+ <dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
+ <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
+ <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
+ <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
+ <dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
+
+ <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
+
+ <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+ <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
+
+ <dynamicField name="random_*" type="random" />
+
+ <!-- uncomment the following to ignore any fields that don't already match an existing
field name or dynamic field, rather than reporting them as an error.
alternately, change the type="ignored" to some other type e.g. "text" if you want
- unknown fields indexed and/or stored by default -->
- <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+ unknown fields indexed and/or stored by default
+
+ NB: use of "*" dynamic fields will disable field type guessing and adding
+ unknown fields to the schema. -->
+ <!--dynamicField name="*" type="ignored" multiValued="true" /-->
- <!-- Field to use to determine and enforce document uniqueness.
+ <!-- Field to use to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
- -->
- <uniqueKey>id</uniqueKey>
+ -->
+ <uniqueKey>id</uniqueKey>
- <!-- copyField commands copy one field to another at the time a document
- is added to the index. It's used either to index the same field differently,
- or to add multiple fields to the same field for easier/faster searching. -->
+ <!-- copyField commands copy one field to another at the time a document
+ is added to the index. It's used either to index the same field differently,
+ or to add multiple fields to the same field for easier/faster searching.
+
+ <copyField source="sourceFieldName" dest="destinationFieldName"/>
+ -->
- <!--
- <copyField source="title" dest="text"/>
- <copyField source="body" dest="text"/>
- -->
-
<!-- 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
@@ -188,15 +208,18 @@
single-valued and either required or have a default value.
-->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+ <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+ <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
<!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
currently supported on types that are sorted internally as strings
and on numeric types.
- This includes "string","boolean", and, as of 3.5 (and 4.x),
- int, float, long, date, double, including the "Trie" variants.
+ 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).
@@ -219,6 +242,11 @@
<fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
+
<!--
Numeric field types that index each value at various levels of precision
to accelerate range queries when the number of values between the range
@@ -233,6 +261,11 @@
<fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
+
+ <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+ <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
@@ -257,10 +290,13 @@
Note: For faster range queries, consider the tdate type
-->
<fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
+ <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
<!-- A Trie based date field for faster date range queries and date faceting. -->
<fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
+ <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
+
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldType name="binary" class="solr.BinaryField"/>
@@ -299,6 +335,7 @@
-->
<!-- A text field that only splits on whitespace for exact matching of words -->
+ <dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -307,10 +344,11 @@
<!-- 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">
+ removes stop words from case-insensitive "stopwords.txt"
+ (empty by default), and down cases. At query time only, it
+ also applies synonyms.
+ -->
+ <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
@@ -332,6 +370,7 @@
(lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
finally applies Porter's stemming. The query time analyzer
also applies synonyms from synonyms.txt. -->
+ <dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
@@ -343,13 +382,13 @@
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
- />
+ />
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <!-- 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">
@@ -358,26 +397,27 @@
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
- />
+ />
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <!-- 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
- 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".
- -->
+ 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".
+ -->
+ <dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -389,7 +429,7 @@
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
- />
+ />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -401,7 +441,7 @@
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
- />
+ />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -411,6 +451,7 @@
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
+ <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -427,14 +468,16 @@
</fieldType>
<!-- Just like text_general except it reverses the characters of
- each token, to enable more efficient leading wildcard queries. -->
+ each token, to enable more efficient leading wildcard queries.
+ -->
+ <dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+ maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
@@ -444,40 +487,16 @@
</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">
+ <dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
+ <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
<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/7/docs/api/java/util/regex/package-summary.html
- -->
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-z])" replacement="" replace="all"
- />
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldType>
<!-- lowercases the entire field value, keeping it as a single token. -->
+ <dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
@@ -485,6 +504,34 @@
</analyzer>
</fieldType>
+ <!--
+ Example of using PathHierarchyTokenizerFactory at index time, so
+ queries for paths match documents at that path, or in descendent paths
+ -->
+ <dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
+ <fieldType name="descendent_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!--
+ Example of using PathHierarchyTokenizerFactory at query time, so
+ queries for paths match documents at that path, or in ancestor paths
+ -->
+ <dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
+ <fieldType name="ancestor_path" class="solr.TextField">
+ <analyzer type="index">
+ <tokenizer class="solr.KeywordTokenizerFactory" />
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+ </analyzer>
+ </fieldType>
+
<!-- since fields of this type are by default not stored or indexed,
any data added to them will be ignored outright. -->
<fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
@@ -500,6 +547,7 @@
The subFields are an implementation detail of the fieldType, and end
users normally should not need to know about them.
-->
+ <dynamicField name="*_point" type="point" indexed="true" stored="true"/>
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
@@ -510,16 +558,9 @@
http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
-->
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
- geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
-
- <!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has
- special relevancy modes: score=overlapRatio|area|area2D (local-param to the query). DocValues is recommended for
- relevancy. -->
- <fieldType name="bbox" class="solr.BBoxField"
- geo="true" distanceUnits="kilometers" numberType="_bbox_coord" />
- <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" useDocValuesAsStored="false" stored="false"/>
+ geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
- <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
+ <!-- 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
@@ -529,7 +570,436 @@
solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
- -->
+ -->
<fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
+
+
+
+ <!-- some examples for different languages (generally ordered by ISO code) -->
+
+ <!-- Arabic -->
+ <dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
+ <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- for any non-arabic -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
+ <!-- normalizes \ufeef to \ufef1, etc -->
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.ArabicStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Bulgarian -->
+ <dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
+ <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
+ <filter class="solr.BulgarianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Catalan -->
+ <dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
+ <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+ <dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
+ <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- for any non-CJK -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.CJKBigramFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Czech -->
+ <dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
+ <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
+ <filter class="solr.CzechStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Danish -->
+ <dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
+ <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- German -->
+ <dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
+ <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
+ <filter class="solr.GermanNormalizationFilterFactory"/>
+ <filter class="solr.GermanLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Greek -->
+ <dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
+ <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- greek specific lowercase for sigma -->
+ <filter class="solr.GreekLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
+ <filter class="solr.GreekStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Spanish -->
+ <dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
+ <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
+ <filter class="solr.SpanishLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Basque -->
+ <dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
+ <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Persian -->
+ <dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
+ <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <!-- for ZWNJ -->
+ <charFilter class="solr.PersianCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.PersianNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Finnish -->
+ <dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
+ <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+ <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- French -->
+ <dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
+ <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
+ <filter class="solr.FrenchLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Irish -->
+ <dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
+ <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes d', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+ <!-- removes n-, etc. position increments is intentionally false! -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+ <filter class="solr.IrishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Galician -->
+ <dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
+ <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
+ <filter class="solr.GalicianStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Hindi -->
+ <dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
+ <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- normalizes unicode representation -->
+ <filter class="solr.IndicNormalizationFilterFactory"/>
+ <!-- normalizes variation in spelling -->
+ <filter class="solr.HindiNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
+ <filter class="solr.HindiStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Hungarian -->
+ <dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
+ <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Armenian -->
+ <dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
+ <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Indonesian -->
+ <dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
+ <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
+ <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+ <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Italian -->
+ <dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
+ <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
+ <filter class="solr.ItalianLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
+
+ NOTE: If you want to optimize search for precision, use default operator AND in your query
+ parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
+ OR if you would like to optimize for recall (default).
+ -->
+ <dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
+ <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
+ <analyzer>
+ <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
+
+ Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
+ is used to segment compounds into its parts and the compound itself is kept as synonym.
+
+ Valid values for attribute mode are:
+ normal: regular segmentation
+ search: segmentation useful for search with synonyms compounds (default)
+ extended: same as search mode, but unigrams unknown words (experimental)
+
+ For some applications it might be good to use search mode for indexing and normal mode for
+ queries to reduce recall and prevent parts of compounds from being matched and highlighted.
+ Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
+
+ Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
+ model with your own entries for segmentation, part-of-speech tags and readings without a need
+ to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+ User dictionary attributes are:
+ userDictionary: user dictionary filename
+ userDictionaryEncoding: user dictionary encoding (default is UTF-8)
+
+ See lang/userdict_ja.txt for a sample user dictionary file.
+
+ Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
+
+ See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
+ -->
+ <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
+ <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
+ <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (\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 -->
+ <dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
+ <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
+ <filter class="solr.LatvianStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Dutch -->
+ <dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
+ <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
+ <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Norwegian -->
+ <dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
+ <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+ <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+ <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Portuguese -->
+ <dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
+ <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
+ <filter class="solr.PortugueseLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+ <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Romanian -->
+ <dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
+ <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Russian -->
+ <dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
+ <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+ <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Swedish -->
+ <dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
+ <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+ <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Thai -->
+ <dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
+ <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.ThaiTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
+ </analyzer>
+ </fieldType>
+
+ <!-- Turkish -->
+ <dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
+ <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.TurkishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
+ <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Similarity is the scoring routine for each document vs. a query.
+ A custom Similarity or SimilarityFactory may be specified here, but
+ the default is fine for most applications.
+ For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+ -->
+ <!--
+ <similarity class="com.example.solr.CustomSimilarityFactory">
+ <str name="paramkey">param value</str>
+ </similarity>
+ -->
</schema>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/params.json
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/params.json b/solr/server/solr/configsets/basic_configs/conf/params.json
new file mode 100644
index 0000000..06114ef
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/params.json
@@ -0,0 +1,20 @@
+{"params":{
+ "query":{
+ "defType":"edismax",
+ "q.alt":"*:*",
+ "rows":"10",
+ "fl":"*,score",
+ "":{"v":0}
+ },
+ "facets":{
+ "facet":"on",
+ "facet.mincount": "1",
+ "":{"v":0}
+ },
+ "velocity":{
+ "wt": "velocity",
+ "v.template":"browse",
+ "v.layout": "layout",
+ "":{"v":0}
+ }
+}}
\ No newline at end of file
[3/4] lucene-solr:branch_6x: SOLR-9163: sync basic_configs w/
data_driven_schema_configs
Posted by yo...@apache.org.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt
new file mode 100644
index 0000000..e21a23c
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_lv.txt
@@ -0,0 +1,172 @@
+# Set of Latvian stopwords from A Stemming Algorithm for Latvian, Karlis Kreslins
+# the original list of over 800 forms was refined:
+# pronouns, adverbs, interjections were removed
+#
+# prepositions
+aiz
+ap
+ar
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt
new file mode 100644
index 0000000..47a2aea
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_nl.txt
@@ -0,0 +1,119 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/dutch/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Dutch stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large sample of Dutch text.
+
+ | Dutch stop words frequently exhibit homonym clashes. These are indicated
+ | clearly below.
+
+de | the
+en | and
+van | of, from
+ik | I, the ego
+te | (1) chez, at etc, (2) to, (3) too
+dat | that, which
+die | that, those, who, which
+in | in, inside
+een | a, an, one
+hij | he
+het | the, it
+niet | not, nothing, naught
+zijn | (1) to be, being, (2) his, one's, its
+is | is
+was | (1) was, past tense of all persons sing. of 'zijn' (to be) (2) wax, (3) the washing, (4) rise of river
+op | on, upon, at, in, up, used up
+aan | on, upon, to (as dative)
+met | with, by
+als | like, such as, when
+voor | (1) before, in front of, (2) furrow
+had | had, past tense all persons sing. of 'hebben' (have)
+er | there
+maar | but, only
+om | round, about, for etc
+hem | him
+dan | then
+zou | should/would, past tense all persons sing. of 'zullen'
+of | or, whether, if
+wat | what, something, anything
+mijn | possessive and noun 'mine'
+men | people, 'one'
+dit | this
+zo | so, thus, in this way
+door | through by
+over | over, across
+ze | she, her, they, them
+zich | oneself
+bij | (1) a bee, (2) by, near, at
+ook | also, too
+tot | till, until
+je | you
+mij | me
+uit | out of, from
+der | Old Dutch form of 'van der' still found in surnames
+daar | (1) there, (2) because
+haar | (1) her, their, them, (2) hair
+naar | (1) unpleasant, unwell etc, (2) towards, (3) as
+heb | present first person sing. of 'to have'
+hoe | how, why
+heeft | present third person sing. of 'to have'
+hebben | 'to have' and various parts thereof
+deze | this
+u | you
+want | (1) for, (2) mitten, (3) rigging
+nog | yet, still
+zal | 'shall', first and third person sing. of verb 'zullen' (will)
+me | me
+zij | she, they
+nu | now
+ge | 'thou', still used in Belgium and south Netherlands
+geen | none
+omdat | because
+iets | something, somewhat
+worden | to become, grow, get
+toch | yet, still
+al | all, every, each
+waren | (1) 'were' (2) to wander, (3) wares, (3)
+veel | much, many
+meer | (1) more, (2) lake
+doen | to do, to make
+toen | then, when
+moet | noun 'spot/mote' and present form of 'to must'
+ben | (1) am, (2) 'are' in interrogative second person singular of 'to be'
+zonder | without
+kan | noun 'can' and present form of 'to be able'
+hun | their, them
+dus | so, consequently
+alles | all, everything, anything
+onder | under, beneath
+ja | yes, of course
+eens | once, one day
+hier | here
+wie | who
+werd | imperfect third person sing. of 'become'
+altijd | always
+doch | yet, but etc
+wordt | present third person sing. of 'become'
+wezen | (1) to be, (2) 'been' as in 'been fishing', (3) orphans
+kunnen | to be able
+ons | us/our
+zelf | self
+tegen | against, towards, at
+na | after, near
+reeds | already
+wil | (1) present tense of 'want', (2) 'will', noun, (3) fender
+kon | could; past tense of 'to be able'
+niets | nothing
+uw | your
+iemand | somebody
+geweest | been; past participle of 'be'
+andere | other
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt
new file mode 100644
index 0000000..a7a2c28
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_no.txt
@@ -0,0 +1,194 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/norwegian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Norwegian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This stop word list is for the dominant 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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt
new file mode 100644
index 0000000..acfeb01
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_pt.txt
@@ -0,0 +1,253 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/portuguese/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Portuguese stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | of, from
+a | the; to, at; her
+o | the; him
+que | who, that
+e | and
+do | de + o
+da | de + a
+em | in
+um | a
+para | for
+ | � 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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt
new file mode 100644
index 0000000..4fdee90
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ro.txt
@@ -0,0 +1,233 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+acea
+aceasta
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt
new file mode 100644
index 0000000..5527140
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ru.txt
@@ -0,0 +1,243 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/russian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | a russian stop word list. comments begin with vertical bar. each stop
+ | word is at the start of a line.
+
+ | this is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | letter `\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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt
new file mode 100644
index 0000000..096f87f
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_sv.txt
@@ -0,0 +1,133 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/swedish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Swedish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+ | Swedish stop words occasionally exhibit homonym clashes. For example
+ | 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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt
new file mode 100644
index 0000000..07f0fab
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_th.txt
@@ -0,0 +1,119 @@
+# Thai stopwords from:
+# "Opinion Detection in Thai Political News Columns
+# Based on Subjectivity Analysis"
+# Khampol Sukhum, Supot Nitsuwat, and Choochart Haruechaiyasak
+\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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt
new file mode 100644
index 0000000..84d9408
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_tr.txt
@@ -0,0 +1,212 @@
+# Turkish stopwords from LUCENE-559
+# merged with the list from "Information Retrieval on Turkish Texts"
+# (http://www.users.muohio.edu/canf/papers/JASIST2008offPrint.pdf)
+acaba
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt b/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt
new file mode 100644
index 0000000..6f0368e
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/userdict_ja.txt
@@ -0,0 +1,29 @@
+#
+# This is a sample user dictionary for Kuromoji (JapaneseTokenizer)
+#
+# Add entries to this file in order to override the statistical model in terms
+# of segmentation, readings and part-of-speech tags. Notice that entries do
+# not have weights since they are always used when found. This is by-design
+# in order to maximize ease-of-use.
+#
+# Entries are defined using the following CSV format:
+# <text>,<token 1> ... <token n>,<reading 1> ... <reading n>,<part-of-speech tag>
+#
+# Notice that a single half-width space separates tokens and readings, and
+# that the number tokens and readings must match exactly.
+#
+# Also notice that multiple entries with the same <text> is undefined.
+#
+# Whitespace only lines are ignored. Comments are not allowed on entry lines.
+#
+
+# Custom segmentation for kanji compounds
+\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
[4/4] lucene-solr:branch_6x: SOLR-9163: sync basic_configs w/
data_driven_schema_configs
Posted by yo...@apache.org.
SOLR-9163: sync basic_configs w/ data_driven_schema_configs
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/1a53346c
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/1a53346c
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/1a53346c
Branch: refs/heads/branch_6x
Commit: 1a53346c0e33956d0b568a78e8a3753bc58789c5
Parents: df2207c
Author: yonik <yo...@apache.org>
Authored: Fri Jul 8 15:43:30 2016 -0400
Committer: yonik <yo...@apache.org>
Committed: Fri Jul 8 15:45:30 2016 -0400
----------------------------------------------------------------------
solr/CHANGES.txt | 3 +
.../basic_configs/conf/_rest_managed.json | 1 -
.../configsets/basic_configs/conf/elevate.xml | 42 +
.../basic_configs/conf/lang/contractions_ca.txt | 8 +
.../basic_configs/conf/lang/contractions_fr.txt | 15 +
.../basic_configs/conf/lang/contractions_ga.txt | 5 +
.../basic_configs/conf/lang/contractions_it.txt | 23 +
.../basic_configs/conf/lang/hyphenations_ga.txt | 5 +
.../basic_configs/conf/lang/stemdict_nl.txt | 6 +
.../basic_configs/conf/lang/stoptags_ja.txt | 420 +++++++
.../basic_configs/conf/lang/stopwords_ar.txt | 125 ++
.../basic_configs/conf/lang/stopwords_bg.txt | 193 ++++
.../basic_configs/conf/lang/stopwords_ca.txt | 220 ++++
.../basic_configs/conf/lang/stopwords_cz.txt | 172 +++
.../basic_configs/conf/lang/stopwords_da.txt | 110 ++
.../basic_configs/conf/lang/stopwords_de.txt | 294 +++++
.../basic_configs/conf/lang/stopwords_el.txt | 78 ++
.../basic_configs/conf/lang/stopwords_es.txt | 356 ++++++
.../basic_configs/conf/lang/stopwords_eu.txt | 99 ++
.../basic_configs/conf/lang/stopwords_fa.txt | 313 +++++
.../basic_configs/conf/lang/stopwords_fi.txt | 97 ++
.../basic_configs/conf/lang/stopwords_fr.txt | 186 +++
.../basic_configs/conf/lang/stopwords_ga.txt | 110 ++
.../basic_configs/conf/lang/stopwords_gl.txt | 161 +++
.../basic_configs/conf/lang/stopwords_hi.txt | 235 ++++
.../basic_configs/conf/lang/stopwords_hu.txt | 211 ++++
.../basic_configs/conf/lang/stopwords_hy.txt | 46 +
.../basic_configs/conf/lang/stopwords_id.txt | 359 ++++++
.../basic_configs/conf/lang/stopwords_it.txt | 303 +++++
.../basic_configs/conf/lang/stopwords_ja.txt | 127 +++
.../basic_configs/conf/lang/stopwords_lv.txt | 172 +++
.../basic_configs/conf/lang/stopwords_nl.txt | 119 ++
.../basic_configs/conf/lang/stopwords_no.txt | 194 ++++
.../basic_configs/conf/lang/stopwords_pt.txt | 253 +++++
.../basic_configs/conf/lang/stopwords_ro.txt | 233 ++++
.../basic_configs/conf/lang/stopwords_ru.txt | 243 ++++
.../basic_configs/conf/lang/stopwords_sv.txt | 133 +++
.../basic_configs/conf/lang/stopwords_th.txt | 119 ++
.../basic_configs/conf/lang/stopwords_tr.txt | 212 ++++
.../basic_configs/conf/lang/userdict_ja.txt | 29 +
.../basic_configs/conf/managed-schema | 764 ++++++++++---
.../configsets/basic_configs/conf/params.json | 20 +
.../basic_configs/conf/solrconfig.xml | 1072 ++++++++++++++++--
.../conf/managed-schema | 4 +-
44 files changed, 7666 insertions(+), 224 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 00f5230..ce380a4 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -128,6 +128,9 @@ Other Changes
* SOLR-9277: Clean up some more remnants of supporting old and new style solr.xml in tests (Erick Erickson)
+* SOLR-9163: Sync up basic_configs and data_driven_schema_configs, removing almost all differences
+ except what is required for schemaless. (yonik)
+
================== 6.1.0 ==================
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/1a53346c/solr/server/solr/configsets/basic_configs/conf/_rest_managed.json
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/_rest_managed.json b/solr/server/solr/configsets/basic_configs/conf/_rest_managed.json
deleted file mode 100644
index 6a4aec3..0000000
--- a/solr/server/solr/configsets/basic_configs/conf/_rest_managed.json
+++ /dev/null
@@ -1 +0,0 @@
-{"initArgs":{},"managedList":[]}
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/elevate.xml
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/elevate.xml b/solr/server/solr/configsets/basic_configs/conf/elevate.xml
new file mode 100644
index 0000000..2c09ebe
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/elevate.xml
@@ -0,0 +1,42 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Licensed to the Apache Software Foundation (ASF) under one or more
+ contributor license agreements. See the NOTICE file distributed with
+ this work for additional information regarding copyright ownership.
+ The ASF licenses this file to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+-->
+
+<!-- If this file is found in the config directory, it will only be
+ loaded once at startup. If it is found in Solr's data
+ directory, it will be re-loaded every commit.
+
+ See http://wiki.apache.org/solr/QueryElevationComponent for more info
+
+-->
+<elevate>
+ <!-- Query elevation examples
+ <query text="foo bar">
+ <doc id="1" />
+ <doc id="2" />
+ <doc id="3" />
+ </query>
+
+for use with techproducts example
+
+ <query text="ipod">
+ <doc id="MA147LL/A" /> put the actual ipod at the top
+ <doc id="IW-02" exclude="true" /> exclude this cable
+ </query>
+-->
+
+</elevate>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt
new file mode 100644
index 0000000..307a85f
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ca.txt
@@ -0,0 +1,8 @@
+# Set of Catalan contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+l
+m
+n
+s
+t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt
new file mode 100644
index 0000000..f1bba51
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_fr.txt
@@ -0,0 +1,15 @@
+# Set of French contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+l
+m
+t
+qu
+n
+s
+j
+d
+c
+jusqu
+quoiqu
+lorsqu
+puisqu
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt
new file mode 100644
index 0000000..9ebe7fa
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+d
+m
+b
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt
new file mode 100644
index 0000000..cac0409
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/contractions_it.txt
@@ -0,0 +1,23 @@
+# Set of Italian contractions for ElisionFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+c
+l
+all
+dall
+dell
+nell
+sull
+coll
+pell
+gl
+agl
+dagl
+degl
+negl
+sugl
+un
+m
+t
+s
+v
+d
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt b/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt
new file mode 100644
index 0000000..4d2642c
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/hyphenations_ga.txt
@@ -0,0 +1,5 @@
+# Set of Irish hyphenations for StopFilter
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+h
+n
+t
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt
new file mode 100644
index 0000000..4410729
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stemdict_nl.txt
@@ -0,0 +1,6 @@
+# Set of overrides for the dutch stemmer
+# TODO: load this as a resource from the analyzer and sync it in build.xml
+fiets fiets
+bromfiets bromfiets
+ei eier
+kind kinder
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt
new file mode 100644
index 0000000..71b7508
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stoptags_ja.txt
@@ -0,0 +1,420 @@
+#
+# This file defines a Japanese stoptag set for JapanesePartOfSpeechStopFilter.
+#
+# Any token with a part-of-speech tag that exactly matches those defined in this
+# file are removed from the token stream.
+#
+# Set your own stoptags by uncommenting the lines below. Note that comments are
+# not allowed on the same line as a stoptag. See LUCENE-3745 for frequency lists,
+# etc. that can be useful for building you own stoptag set.
+#
+# The entire possible tagset is provided below for convenience.
+#
+#####
+# noun: unclassified nouns
+#\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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt
new file mode 100644
index 0000000..046829d
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ar.txt
@@ -0,0 +1,125 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Cleaned on October 11, 2009 (not normalized, so use before normalization)
+# This means that when modifying this list, you might need to add some
+# redundant entries, for example containing forms with both \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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt
new file mode 100644
index 0000000..1ae4ba2
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_bg.txt
@@ -0,0 +1,193 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+\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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt
new file mode 100644
index 0000000..3da65de
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ca.txt
@@ -0,0 +1,220 @@
+# Catalan stopwords from http://github.com/vcl/cue.language (Apache 2 Licensed)
+a
+abans
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt
new file mode 100644
index 0000000..53c6097
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_cz.txt
@@ -0,0 +1,172 @@
+a
+s
+k
+o
+i
+u
+v
+z
+dnes
+cz
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt
new file mode 100644
index 0000000..42e6145
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_da.txt
@@ -0,0 +1,110 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/danish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Danish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | This is a ranked list (commonest to rarest) of stopwords derived from
+ | a large text sample.
+
+
+og | and
+i | in
+jeg | I
+det | that (dem. pronoun)/it (pers. pronoun)
+at | that (in front of a sentence)/to (with infinitive)
+en | a/an
+den | it (pers. pronoun)/that (dem. pronoun)
+til | to/at/for/until/against/by/of/into, more
+er | present tense of "to be"
+som | who, as
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt
new file mode 100644
index 0000000..86525e7
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_de.txt
@@ -0,0 +1,294 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/german/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A German stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ | The number of forms in this list is reduced significantly by passing it
+ | through the German stemmer.
+
+
+aber | but
+
+alle | all
+allem
+allen
+aller
+alles
+
+als | than, as
+also | so
+am | an + dem
+an | at
+
+ander | other
+andere
+anderem
+anderen
+anderer
+anderes
+anderm
+andern
+anderr
+anders
+
+auch | also
+auf | on
+aus | out of
+bei | by
+bin | am
+bis | until
+bist | art
+da | there
+damit | with it
+dann | then
+
+der | the
+den
+des
+dem
+die
+das
+
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt
new file mode 100644
index 0000000..232681f
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_el.txt
@@ -0,0 +1,78 @@
+# Lucene Greek Stopwords list
+# Note: by default this file is used after GreekLowerCaseFilter,
+# so when modifying this file use '\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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt
new file mode 100644
index 0000000..487d78c
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_es.txt
@@ -0,0 +1,356 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/spanish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A Spanish stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+
+ | The following is a ranked list (commonest to rarest) of stopwords
+ | deriving from a large sample of text.
+
+ | Extra words have been added at the end.
+
+de | from, of
+la | the, her
+que | who, that
+el | the
+en | in
+y | and
+a | to
+los | the, them
+del | de + el
+se | himself, from him etc
+las | the, them
+por | for, by, etc
+un | a
+para | for
+con | with
+no | no
+una | a
+su | his, her
+al | a + el
+ | es from SER
+lo | him
+como | how
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt
new file mode 100644
index 0000000..25f1db9
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_eu.txt
@@ -0,0 +1,99 @@
+# example set of basque stopwords
+al
+anitz
+arabera
+asko
+baina
+bat
+batean
+batek
+bati
+batzuei
+batzuek
+batzuetan
+batzuk
+bera
+beraiek
+berau
+berauek
+bere
+berori
+beroriek
+beste
+bezala
+da
+dago
+dira
+ditu
+du
+dute
+edo
+egin
+ere
+eta
+eurak
+ez
+gainera
+gu
+gutxi
+guzti
+haiei
+haiek
+haietan
+hainbeste
+hala
+han
+handik
+hango
+hara
+hari
+hark
+hartan
+hau
+hauei
+hauek
+hauetan
+hemen
+hemendik
+hemengo
+hi
+hona
+honek
+honela
+honetan
+honi
+hor
+hori
+horiei
+horiek
+horietan
+horko
+horra
+horrek
+horrela
+horretan
+horri
+hortik
+hura
+izan
+ni
+noiz
+nola
+non
+nondik
+nongo
+nor
+nora
+ze
+zein
+zen
+zenbait
+zenbat
+zer
+zergatik
+ziren
+zituen
+zu
+zuek
+zuen
+zuten
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt
new file mode 100644
index 0000000..723641c
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fa.txt
@@ -0,0 +1,313 @@
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# Note: by default this file is used after normalization, so when adding entries
+# to this file, use the arabic '\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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt
new file mode 100644
index 0000000..4372c9a
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fi.txt
@@ -0,0 +1,97 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/finnish/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+| forms of BE
+
+olla
+olen
+olet
+on
+olemme
+olette
+ovat
+ole | negative form
+
+oli
+olisi
+olisit
+olisin
+olisimme
+olisitte
+olisivat
+olit
+olin
+olimme
+olitte
+olivat
+ollut
+olleet
+
+en | negation
+et
+ei
+emme
+ette
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt
new file mode 100644
index 0000000..749abae
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_fr.txt
@@ -0,0 +1,186 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/french/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | A French stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+au | a + le
+aux | a + les
+avec | with
+ce | this
+ces | these
+dans | with
+de | of
+des | de + les
+du | de + le
+elle | she
+en | `of them' etc
+et | and
+eux | them
+il | he
+je | I
+la | the
+le | the
+leur | their
+lui | him
+ma | my (fem)
+mais | but
+me | me
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt
new file mode 100644
index 0000000..9ff88d7
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ga.txt
@@ -0,0 +1,110 @@
+
+a
+ach
+ag
+agus
+an
+aon
+ar
+arna
+as
+b'
+ba
+beirt
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt
new file mode 100644
index 0000000..d8760b1
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_gl.txt
@@ -0,0 +1,161 @@
+# galican stopwords
+a
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt
new file mode 100644
index 0000000..86286bb
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hi.txt
@@ -0,0 +1,235 @@
+# Also see http://www.opensource.org/licenses/bsd-license.html
+# See http://members.unine.ch/jacques.savoy/clef/index.html.
+# This file was created by Jacques Savoy and is distributed under the BSD license.
+# Note: by default this file also contains forms normalized by HindiNormalizer
+# for spelling variation (see section below), such that it can be used whether or
+# not you enable that feature. When adding additional entries to this list,
+# please add the normalized form as well.
+\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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt
new file mode 100644
index 0000000..37526da
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hu.txt
@@ -0,0 +1,211 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/hungarian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+| Hungarian stop word list
+| prepared by Anna Tordai
+
+a
+ahogy
+ahol
+aki
+akik
+akkor
+alatt
+�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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt
new file mode 100644
index 0000000..60c1c50
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_hy.txt
@@ -0,0 +1,46 @@
+# example set of Armenian stopwords.
+\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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt
new file mode 100644
index 0000000..4617f83
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_id.txt
@@ -0,0 +1,359 @@
+# from appendix D of: A Study of Stemming Effects on Information
+# Retrieval in Bahasa Indonesia
+ada
+adanya
+adalah
+adapun
+agak
+agaknya
+agar
+akan
+akankah
+akhirnya
+aku
+akulah
+amat
+amatlah
+anda
+andalah
+antar
+diantaranya
+antara
+antaranya
+diantara
+apa
+apaan
+mengapa
+apabila
+apakah
+apalagi
+apatah
+atau
+ataukah
+ataupun
+bagai
+bagaikan
+sebagai
+sebagainya
+bagaimana
+bagaimanapun
+sebagaimana
+bagaimanakah
+bagi
+bahkan
+bahwa
+bahwasanya
+sebaliknya
+banyak
+sebanyak
+beberapa
+seberapa
+begini
+beginian
+beginikah
+beginilah
+sebegini
+begitu
+begitukah
+begitulah
+begitupun
+sebegitu
+belum
+belumlah
+sebelum
+sebelumnya
+sebenarnya
+berapa
+berapakah
+berapalah
+berapapun
+betulkah
+sebetulnya
+biasa
+biasanya
+bila
+bilakah
+bisa
+bisakah
+sebisanya
+boleh
+bolehkah
+bolehlah
+buat
+bukan
+bukankah
+bukanlah
+bukannya
+cuma
+percuma
+dahulu
+dalam
+dan
+dapat
+dari
+daripada
+dekat
+demi
+demikian
+demikianlah
+sedemikian
+dengan
+depan
+di
+dia
+dialah
+dini
+diri
+dirinya
+terdiri
+dong
+dulu
+enggak
+enggaknya
+entah
+entahlah
+terhadap
+terhadapnya
+hal
+hampir
+hanya
+hanyalah
+harus
+haruslah
+harusnya
+seharusnya
+hendak
+hendaklah
+hendaknya
+hingga
+sehingga
+ia
+ialah
+ibarat
+ingin
+inginkah
+inginkan
+ini
+inikah
+inilah
+itu
+itukah
+itulah
+jangan
+jangankan
+janganlah
+jika
+jikalau
+juga
+justru
+kala
+kalau
+kalaulah
+kalaupun
+kalian
+kami
+kamilah
+kamu
+kamulah
+kan
+kapan
+kapankah
+kapanpun
+dikarenakan
+karena
+karenanya
+ke
+kecil
+kemudian
+kenapa
+kepada
+kepadanya
+ketika
+seketika
+khususnya
+kini
+kinilah
+kiranya
+sekiranya
+kita
+kitalah
+kok
+lagi
+lagian
+selagi
+lah
+lain
+lainnya
+melainkan
+selaku
+lalu
+melalui
+terlalu
+lama
+lamanya
+selama
+selama
+selamanya
+lebih
+terlebih
+bermacam
+macam
+semacam
+maka
+makanya
+makin
+malah
+malahan
+mampu
+mampukah
+mana
+manakala
+manalagi
+masih
+masihkah
+semasih
+masing
+mau
+maupun
+semaunya
+memang
+mereka
+merekalah
+meski
+meskipun
+semula
+mungkin
+mungkinkah
+nah
+namun
+nanti
+nantinya
+nyaris
+oleh
+olehnya
+seorang
+seseorang
+pada
+padanya
+padahal
+paling
+sepanjang
+pantas
+sepantasnya
+sepantasnyalah
+para
+pasti
+pastilah
+per
+pernah
+pula
+pun
+merupakan
+rupanya
+serupa
+saat
+saatnya
+sesaat
+saja
+sajalah
+saling
+bersama
+sama
+sesama
+sambil
+sampai
+sana
+sangat
+sangatlah
+saya
+sayalah
+se
+sebab
+sebabnya
+sebuah
+tersebut
+tersebutlah
+sedang
+sedangkan
+sedikit
+sedikitnya
+segala
+segalanya
+segera
+sesegera
+sejak
+sejenak
+sekali
+sekalian
+sekalipun
+sesekali
+sekaligus
+sekarang
+sekarang
+sekitar
+sekitarnya
+sela
+selain
+selalu
+seluruh
+seluruhnya
+semakin
+sementara
+sempat
+semua
+semuanya
+sendiri
+sendirinya
+seolah
+seperti
+sepertinya
+sering
+seringnya
+serta
+siapa
+siapakah
+siapapun
+disini
+disinilah
+sini
+sinilah
+sesuatu
+sesuatunya
+suatu
+sesudah
+sesudahnya
+sudah
+sudahkah
+sudahlah
+supaya
+tadi
+tadinya
+tak
+tanpa
+setelah
+telah
+tentang
+tentu
+tentulah
+tentunya
+tertentu
+seterusnya
+tapi
+tetapi
+setiap
+tiap
+setidaknya
+tidak
+tidakkah
+tidaklah
+toh
+waduh
+wah
+wahai
+sewaktu
+walau
+walaupun
+wong
+yaitu
+yakni
+yang
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt
new file mode 100644
index 0000000..1219cc7
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_it.txt
@@ -0,0 +1,303 @@
+ | From svn.tartarus.org/snowball/trunk/website/algorithms/italian/stop.txt
+ | This file is distributed under the BSD License.
+ | See http://snowball.tartarus.org/license.php
+ | Also see http://www.opensource.org/licenses/bsd-license.html
+ | - Encoding was converted to UTF-8.
+ | - This notice was added.
+ |
+ | NOTE: To use this file with StopFilterFactory, you must specify format="snowball"
+
+ | An Italian stop word list. Comments begin with vertical bar. Each stop
+ | word is at the start of a line.
+
+ad | a (to) before vowel
+al | a + il
+allo | a + lo
+ai | a + i
+agli | a + gli
+all | a + l'
+agl | a + gl'
+alla | a + la
+alle | a + le
+con | with
+col | con + il
+coi | con + i (forms collo, cogli etc are now very rare)
+da | from
+dal | da + il
+dallo | da + lo
+dai | da + i
+dagli | da + gli
+dall | da + l'
+dagl | da + gll'
+dalla | da + la
+dalle | da + le
+di | of
+del | di + il
+dello | di + lo
+dei | di + i
+degli | di + gli
+dell | di + l'
+degl | di + gl'
+della | di + la
+delle | di + le
+in | in
+nel | in + el
+nello | in + lo
+nei | in + i
+negli | in + gli
+nell | in + l'
+negl | in + gl'
+nella | in + la
+nelle | in + le
+su | on
+sul | su + il
+sullo | su + lo
+sui | su + i
+sugli | su + gli
+sull | su + l'
+sugl | su + gl'
+sulla | su + la
+sulle | su + le
+per | through, by
+tra | among
+contro | against
+io | I
+tu | thou
+lui | he
+lei | she
+noi | we
+voi | you
+loro | they
+mio | my
+mia |
+miei |
+mie |
+tuo |
+tua |
+tuoi | thy
+tue |
+suo |
+sua |
+suoi | his, her
+sue |
+nostro | our
+nostra |
+nostri |
+nostre |
+vostro | your
+vostra |
+vostri |
+vostre |
+mi | me
+ti | thee
+ci | us, there
+vi | you, there
+lo | him, the
+la | her, the
+li | them
+le | them, the
+gli | to him, the
+ne | from there etc
+il | the
+un | a
+uno | a
+una | a
+ma | but
+ed | and
+se | if
+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/1a53346c/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt
----------------------------------------------------------------------
diff --git a/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt
new file mode 100644
index 0000000..d4321be
--- /dev/null
+++ b/solr/server/solr/configsets/basic_configs/conf/lang/stopwords_ja.txt
@@ -0,0 +1,127 @@
+#
+# This file defines a stopword set for Japanese.
+#
+# This set is made up of hand-picked frequent terms from segmented Japanese Wikipedia.
+# Punctuation characters and frequent kanji have mostly been left out. See LUCENE-3745
+# for frequency lists, etc. that can be useful for making your own set (if desired)
+#
+# Note that there is an overlap between these stopwords and the terms stopped when used
+# in combination with the JapanesePartOfSpeechStopFilter. When editing this file, note
+# that comments are not allowed on the same line as stopwords.
+#
+# Also note that stopping is done in a case-insensitive manner. Change your StopFilter
+# configuration if you need case-sensitive stopping. Lastly, note that stopping is done
+# using the same character width as the entries in this file. Since this StopFilter is
+# normally done after a CJKWidthFilter in your chain, you would usually want your romaji
+# entries to be in half-width and your kana entries to be in full-width.
+#
+\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