You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by ar...@apache.org on 2017/04/01 23:13:37 UTC
[1/2] lucene-solr:branch_6x: SOLR-9601: DIH Tika example is now
minimal. Only keep definitions and files required to show Tika-extraction in
DIH
Repository: lucene-solr
Updated Branches:
refs/heads/branch_6x e987654aa -> 812b0eebf
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/812b0eeb/solr/example/example-DIH/solr/tika/conf/solrconfig.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/tika/conf/solrconfig.xml b/solr/example/example-DIH/solr/tika/conf/solrconfig.xml
index 8d3c8ef..09226e9 100644
--- a/solr/example/example-DIH/solr/tika/conf/solrconfig.xml
+++ b/solr/example/example-DIH/solr/tika/conf/solrconfig.xml
@@ -17,1356 +17,42 @@
-->
<!--
- For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
--->
-<config>
- <!-- In all configuration below, a prefix of "solr." for class names
- is an alias that causes solr to search appropriate packages,
- including org.apache.solr.(search|update|request|core|analysis)
+ This is a DEMO configuration highlighting elements
+ specifically needed to get this example running
+ such as libraries and request handler specifics.
- You may also specify a fully qualified Java classname if you
- have your own custom plugins.
- -->
+ It uses defaults or does not define most of production-level settings
+ such as various caches or auto-commit policies.
+
+ See Solr Reference Guide and other examples for
+ more details on a well configured solrconfig.xml
+ https://cwiki.apache.org/confluence/display/solr/The+Well-Configured+Solr+Instance
+-->
+<config>
<!-- Controls what version of Lucene various components of Solr
- adhere to. Generally, you want to use the latest version to
- get all bug fixes and improvements. It is highly recommended
- that you fully re-index after changing this setting as it can
- affect both how text is indexed and queried.
+ adhere to. Generally, you want to use the latest version to
+ get all bug fixes and improvements. It is highly recommended
+ that you fully re-index after changing this setting as it can
+ affect both how text is indexed and queried.
-->
<luceneMatchVersion>6.6.0</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="${solr.install.dir:../../../..}/contrib/dataimporthandler/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-dataimporthandler-.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
-
- <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
-
- <!-- an exact 'path' can be used instead of a 'dir' to specify a
- specific jar file. This will cause a serious error to be logged
- if it can't be loaded.
- -->
- <!--
- <lib path="../a-jar-that-does-not-exist.jar" />
- -->
-
- <!-- Data Directory
-
- Used to specify an alternate directory to hold all index data
- other than the default ./data under the Solr home. If
- replication is in use, this should match the replication
- configuration.
- -->
- <dataDir>${solr.data.dir:}</dataDir>
-
-
- <!-- The DirectoryFactory to use for indexes.
-
- solr.StandardDirectoryFactory is filesystem
- based and tries to pick the best implementation for the current
- JVM and platform. solr.NRTCachingDirectoryFactory, the default,
- wraps solr.StandardDirectoryFactory and caches small files in memory
- for better NRT performance.
-
- One can force a particular implementation via solr.MMapDirectoryFactory,
- solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
-
- solr.RAMDirectoryFactory is memory based, not
- persistent, and doesn't work with replication.
- -->
- <directoryFactory name="DirectoryFactory"
- class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
-
- <!-- The CodecFactory for defining the format of the inverted index.
- The default implementation is SchemaCodecFactory, which is the official Lucene
- index format, but hooks into the schema to provide per-field customization of
- the postings lists and per-document values in the fieldType element
- (postingsFormat/docValuesFormat). Note that most of the alternative implementations
- are experimental, so if you choose to customize the index format, it's a good
- idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
- before upgrading to a newer version to avoid unnecessary reindexing.
- -->
- <codecFactory class="solr.SchemaCodecFactory"/>
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Index Config - These settings control low-level behavior of indexing
- Most example settings here show the default value, but are commented
- out, to more easily see where customizations have been made.
-
- Note: This replaces <indexDefaults> and <mainIndex> from older versions
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <indexConfig>
- <!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
- LimitTokenCountFilterFactory in your fieldType definition. E.g.
- <filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
- -->
- <!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
- <!-- <writeLockTimeout>1000</writeLockTimeout> -->
-
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
- Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
- <!-- <useCompoundFile>false</useCompoundFile> -->
-
- <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
- indexing for buffering added documents and deletions before they are
- flushed to the Directory.
- maxBufferedDocs sets a limit on the number of documents buffered
- before flushing.
- If both ramBufferSizeMB and maxBufferedDocs is set, then
- Lucene will flush based on whichever limit is hit first.
- The default is 100 MB. -->
- <!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
- <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
-
- <!-- Expert: Merge Policy
- The Merge Policy in Lucene controls how merging of segments is done.
- The default since Solr/Lucene 3.3 is TieredMergePolicy.
- The default since Lucene 2.3 was the LogByteSizeMergePolicy,
- Even older versions of Lucene used LogDocMergePolicy.
- -->
- <!--
- <mergePolicyFactory class="solr.TieredMergePolicyFactory">
- <int name="maxMergeAtOnce">10</int>
- <int name="segmentsPerTier">10</int>
- </mergePolicyFactory>
- -->
-
- <!-- Expert: Merge Scheduler
- The Merge Scheduler in Lucene controls how merges are
- performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
- can perform merges in the background using separate threads.
- The SerialMergeScheduler (Lucene 2.2 default) does not.
- -->
- <!--
- <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
- -->
-
- <!-- LockFactory
-
- This option specifies which Lucene LockFactory implementation
- to use.
-
- single = SingleInstanceLockFactory - suggested for a
- read-only index or when there is no possibility of
- another process trying to modify the index.
- native = NativeFSLockFactory - uses OS native file locking.
- Do not use when multiple solr webapps in the same
- JVM are attempting to share a single index.
- simple = SimpleFSLockFactory - uses a plain file for locking
-
- Defaults: 'native' is default for Solr3.6 and later, otherwise
- 'simple' is the default
-
- More details on the nuances of each LockFactory...
- http://wiki.apache.org/lucene-java/AvailableLockFactories
- -->
- <lockType>${solr.lock.type:native}</lockType>
-
- <!-- Commit Deletion Policy
- Custom deletion policies can be specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
-
- The default Solr IndexDeletionPolicy implementation supports
- deleting index commit points on number of commits, age of
- commit point and optimized status.
-
- The latest commit point should always be preserved regardless
- of the criteria.
- -->
- <!--
- <deletionPolicy class="solr.SolrDeletionPolicy">
- -->
- <!-- The number of commit points to be kept -->
- <!-- <str name="maxCommitsToKeep">1</str> -->
- <!-- The number of optimized commit points to be kept -->
- <!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
- <!--
- Delete all commit points once they have reached the given age.
- Supports DateMathParser syntax e.g.
- -->
- <!--
- <str name="maxCommitAge">30MINUTES</str>
- <str name="maxCommitAge">1DAY</str>
- -->
- <!--
- </deletionPolicy>
- -->
-
- <!-- Lucene Infostream
-
- To aid in advanced debugging, Lucene provides an "InfoStream"
- of detailed information when indexing.
-
- Setting the value to true will instruct the underlying Lucene
- IndexWriter to write its info stream to solr's log. By default,
- this is enabled here, and controlled through log4j.properties.
- -->
- <infoStream>true</infoStream>
- </indexConfig>
-
-
- <!-- JMX
-
- This example enables JMX if and only if an existing MBeanServer
- is found, use this if you want to configure JMX through JVM
- parameters. Remove this to disable exposing Solr configuration
- and statistics to JMX.
-
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx />
- <!-- If you want to connect to a particular server, specify the
- agentId
- -->
- <!-- <jmx agentId="myAgent" /> -->
- <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
- <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
- -->
-
- <!-- The default high-performance update handler -->
- <updateHandler class="solr.DirectUpdateHandler2">
-
- <!-- Enables a transaction log, used for real-time get, durability, and
- and solr cloud replica recovery. The log can grow as big as
- uncommitted changes to the index, so use of a hard autoCommit
- is recommended (see below).
- "dir" - the target directory for transaction logs, defaults to the
- solr data directory. -->
- <!--
- <updateLog>
- <str name="dir">${solr.ulog.dir:}</str>
- </updateLog>
- -->
-
- <!-- AutoCommit
-
- Perform a hard commit automatically under certain conditions.
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- maxDocs - Maximum number of documents to add since the last
- commit before automatically triggering a new commit.
-
- maxTime - Maximum amount of time in ms that is allowed to pass
- since a document was added before automatically
- triggering a new commit.
- openSearcher - if false, the commit causes recent index changes
- to be flushed to stable storage, but does not cause a new
- searcher to be opened to make those changes visible.
-
- If the updateLog is enabled, then it's highly recommended to
- have some sort of hard autoCommit to limit the log size.
- -->
- <autoCommit>
- <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
-
- <!-- softAutoCommit is like autoCommit except it causes a
- 'soft' commit which only ensures that changes are visible
- but does not ensure that data is synced to disk. This is
- faster and more near-realtime friendly than a hard commit.
- -->
-
- <autoSoftCommit>
- <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
- </autoSoftCommit>
-
- <!-- Update Related Event Listeners
-
- Various IndexWriter related events can trigger Listeners to
- take actions.
-
- postCommit - fired after every commit or optimize command
- postOptimize - fired after every optimize command
- -->
- <!-- The RunExecutableListener executes an external command from a
- hook such as postCommit or postOptimize.
-
- exe - the name of the executable to run
- dir - dir to use as the current working directory. (default=".")
- wait - the calling thread waits until the executable returns.
- (default="true")
- args - the arguments to pass to the program. (default is none)
- env - environment variables to set. (default is none)
- -->
- <!-- This example shows how RunExecutableListener could be used
- with the script based replication...
- http://wiki.apache.org/solr/CollectionDistribution
- -->
- <!--
- <listener event="postCommit" class="solr.RunExecutableListener">
- <str name="exe">solr/bin/snapshooter</str>
- <str name="dir">.</str>
- <bool name="wait">true</bool>
- <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
- <arr name="env"> <str>MYVAR=val1</str> </arr>
- </listener>
- -->
-
- </updateHandler>
-
- <!-- IndexReaderFactory
-
- Use the following format to specify a custom IndexReaderFactory,
- which allows for alternate IndexReader implementations.
-
- ** Experimental Feature **
-
- Please note - Using a custom IndexReaderFactory may prevent
- certain other features from working. The API to
- IndexReaderFactory may change without warning or may even be
- removed from future releases if the problems cannot be
- resolved.
-
-
- ** Features that may not work with custom IndexReaderFactory **
-
- The ReplicationHandler assumes a disk-resident index. Using a
- custom IndexReader implementation may cause incompatibility
- with ReplicationHandler and may cause replication to not work
- correctly. See SOLR-1366 for details.
-
- -->
- <!--
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- <str name="someArg">Some Value</str>
- </indexReaderFactory >
- -->
-
- <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Query section - these settings control query time things like caches
- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
- <query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded.
-
- ** WARNING **
-
- This option actually modifies a global Lucene property that
- will affect all SolrCores. If multiple solrconfig.xml files
- disagree on this property, the value at any given moment will
- be based on the last SolrCore to be initialized.
-
- -->
- <maxBooleanClauses>1024</maxBooleanClauses>
-
-
- <!-- Solr Internal Query Caches
-
- There are two implementations of cache available for Solr,
- LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
- FastLRUCache has faster gets and slower puts in single
- threaded operation and thus is generally faster than LRUCache
- when the hit ratio of the cache is high (> 75%), and may be
- faster under other scenarios on multi-cpu systems.
- -->
-
- <!-- Filter Cache
-
- Cache used by SolrIndexSearcher for filters (DocSets),
- unordered sets of *all* documents that match a query. When a
- new searcher is opened, its caches may be prepopulated or
- "autowarmed" using data from caches in the old searcher.
- autowarmCount is the number of items to prepopulate. For
- LRUCache, the autowarmed items will be the most recently
- accessed items.
-
- Parameters:
- class - the SolrCache implementation LRUCache or
- (LRUCache or FastLRUCache)
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (see java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- -->
- <filterCache class="solr.FastLRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Query Result Cache
-
- Caches results of searches - ordered lists of document ids
- (DocList) based on a query, a sort, and the range of documents requested.
- -->
- <queryResultCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Document Cache
-
- Caches Lucene Document objects (the stored fields for each
- document). Since Lucene internal document ids are transient,
- this cache will not be autowarmed.
- -->
- <documentCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- custom cache currently used by block join -->
- <cache name="perSegFilter"
- class="solr.search.LRUCache"
- size="10"
- initialSize="0"
- autowarmCount="10"
- regenerator="solr.NoOpRegenerator" />
-
- <!-- Field Value Cache
-
- Cache used to hold field values that are quickly accessible
- by document id. The fieldValueCache is created by default
- even if not configured here.
- -->
- <!--
- <fieldValueCache class="solr.FastLRUCache"
- size="512"
- autowarmCount="128"
- showItems="32" />
- -->
-
- <!-- Custom Cache
-
- Example of a generic cache. These caches may be accessed by
- name through SolrIndexSearcher.getCache(),cacheLookup(), and
- cacheInsert(). The purpose is to enable easy caching of
- user/application level data. The regenerator argument should
- be specified as an implementation of solr.CacheRegenerator
- if autowarming is desired.
- -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="com.mycompany.MyRegenerator"
- />
- -->
-
-
- <!-- Lazy Field Loading
-
- If true, stored fields that are not requested will be loaded
- lazily. This can result in a significant speed improvement
- if the usual case is to not load all stored fields,
- especially if the skipped fields are large compressed text
- fields.
- -->
- <enableLazyFieldLoading>true</enableLazyFieldLoading>
-
- <!-- Use Filter For Sorted Query
-
- A possible optimization that attempts to use a filter to
- satisfy a search. If the requested sort does not include
- score, then the filterCache will be checked for a filter
- matching the query. If found, the filter will be used as the
- source of document ids, and then the sort will be applied to
- that.
-
- For most situations, this will not be useful unless you
- frequently get the same search repeatedly with different sort
- options, and none of them ever use "score"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- Result Window Size
-
- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- are collected. For example, if a search for a particular query
- requests matching documents 10 through 19, and queryWindowSize is 50,
- then documents 0 through 49 will be collected and cached. Any further
- requests in that range can be satisfied via the cache.
- -->
- <queryResultWindowSize>20</queryResultWindowSize>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
-
- newSearcher - fired whenever a new searcher is being prepared
- and there is a current searcher handling requests (aka
- registered). It can be used to prime certain caches to
- prevent long request times for certain requests.
-
- firstSearcher - fired whenever a new searcher is being
- prepared but there is no current registered searcher to handle
- requests or to gain autowarming data from.
-
-
- -->
- <!-- QuerySenderListener takes an array of NamedList and executes a
- local query request for each NamedList in sequence.
- -->
- <listener event="newSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <!--
- <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
- <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
- -->
- </arr>
- </listener>
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <lst>
- <str name="q">static firstSearcher warming in solrconfig.xml</str>
- </lst>
- </arr>
- </listener>
-
- <!-- Use Cold Searcher
-
- If a search request comes in and there is no current
- registered searcher, then immediately register the still
- warming searcher and use it. If "false" then all requests
- will block until the first searcher is done warming.
- -->
- <useColdSearcher>false</useColdSearcher>
-
- </query>
-
-
- <!-- Request Dispatcher
-
- This section contains instructions for how the SolrDispatchFilter
- should behave when processing requests for this SolrCore.
-
- handleSelect is a legacy option that affects the behavior of requests
- such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and dispatch the query to a handler specified by the
- "qt" param, assuming "/select" isn't already registered.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests, resulting in a 404 unless a handler
- is explicitly registered with the name "/select"
-
- handleSelect="true" is not recommended for new users, but is the default
- for backwards compatibility
- -->
- <requestDispatcher handleSelect="false" >
- <!-- Request Parsing
-
- These settings indicate how Solr Requests may be parsed, and
- what restrictions may be placed on the ContentStreams from
- those requests
-
- enableRemoteStreaming - enables use of the stream.file
- and stream.url parameters for specifying remote streams.
-
- multipartUploadLimitInKB - specifies the max size (in KiB) of
- Multipart File Uploads that Solr will allow in a Request.
-
- formdataUploadLimitInKB - specifies the max size (in KiB) of
- form data (application/x-www-form-urlencoded) sent via
- POST. You can use POST to pass request parameters not
- fitting into the URL.
-
- addHttpRequestToContext - if set to true, it will instruct
- the requestParsers to include the original HttpServletRequest
- object in the context map of the SolrQueryRequest under the
- key "httpRequest". It will not be used by any of the existing
- Solr components, but may be useful when developing custom
- plugins.
-
- *** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
-
- -->
- <requestParsers enableRemoteStreaming="true"
- multipartUploadLimitInKB="2048000"
- formdataUploadLimitInKB="2048"
- addHttpRequestToContext="false"/>
-
- <!-- HTTP Caching
-
- Set HTTP caching related parameters (for proxy caches and clients).
-
- The options below instruct Solr not to output any HTTP Caching
- related headers
- -->
- <httpCaching never304="true" />
- <!-- If you include a <cacheControl> directive, it will be used to
- generate a Cache-Control header (as well as an Expires header
- if the value contains "max-age=")
-
- By default, no Cache-Control header is generated.
-
- You can use the <cacheControl> option even if you have set
- never304="true"
- -->
- <!--
- <httpCaching never304="true" >
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- <!-- To enable Solr to respond with automatically generated HTTP
- Caching headers, and to response to Cache Validation requests
- correctly, set the value of never304="false"
-
- This will cause Solr to generate Last-Modified and ETag
- headers based on the properties of the Index.
-
- The following options can also be specified to affect the
- values of these headers...
+ <!-- Load Data Import Handler and Apache Tika (extraction) libraries -->
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-dataimporthandler-.*\.jar"/>
+ <lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar"/>
- lastModFrom - the default value is "openTime" which means the
- Last-Modified value (and validation against If-Modified-Since
- requests) will all be relative to when the current Searcher
- was opened. You can change it to lastModFrom="dirLastMod" if
- you want the value to exactly correspond to when the physical
- index was last modified.
-
- etagSeed="..." is an option you can change to force the ETag
- header (and validation against If-None-Match requests) to be
- different even if the index has not changed (ie: when making
- significant changes to your config file)
-
- (lastModifiedFrom and etagSeed are both ignored if you use
- the never304="true" option)
- -->
- <!--
- <httpCaching lastModifiedFrom="openTime"
- etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
- </httpCaching>
- -->
- </requestDispatcher>
-
- <!-- Request Handlers
-
- http://wiki.apache.org/solr/SolrRequestHandler
-
- Incoming queries will be dispatched to a specific handler by name
- based on the path specified in the request.
-
- Legacy behavior: If the request path uses "/select" but no Request
- Handler has that name, and if handleSelect="true" has been specified in
- the requestDispatcher, then the Request Handler is dispatched based on
- the qt parameter. Handlers without a leading '/' are accessed this way
- like so: http://host/app/[core/]select?qt=name If no qt is
- given, then the requestHandler that declares default="true" will be
- used or the one named "standard".
-
- If a Request Handler is declared with startup="lazy", then it will
- not be initialized until the first request that uses it.
-
- -->
-
- <requestHandler name="/dataimport" class="solr.DataImportHandler">
- <lst name="defaults">
- <str name="config">tika-data-config.xml</str>
- </lst>
- </requestHandler>
-
- <!-- SearchHandler
-
- http://wiki.apache.org/solr/SearchHandler
-
- For processing Search Queries, the primary Request Handler
- provided with Solr is "SearchHandler" It delegates to a sequent
- of SearchComponents (see below) and supports distributed
- queries across multiple shards
- -->
<requestHandler name="/select" class="solr.SearchHandler">
- <!-- default values for query parameters can be specified, these
- will be overridden by parameters in the request
- -->
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <int name="rows">10</int>
- <str name="df">text</str>
- </lst>
- <!-- In addition to defaults, "appends" params can be specified
- to identify values which should be appended to the list of
- multi-val params from the query (or the existing "defaults").
- -->
- <!-- In this example, the param "fq=instock:true" would be appended to
- any query time fq params the user may specify, as a mechanism for
- partitioning the index, independent of any user selected filtering
- that may also be desired (perhaps as a result of faceted searching).
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "appends" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="appends">
- <str name="fq">inStock:true</str>
- </lst>
- -->
- <!-- "invariants" are a way of letting the Solr maintainer lock down
- the options available to Solr clients. Any params values
- specified here are used regardless of what values may be specified
- in either the query, the "defaults", or the "appends" params.
-
- In this example, the facet.field and facet.query params would
- be fixed, limiting the facets clients can use. Faceting is
- not turned on by default - but if the client does specify
- facet=true in the request, these are the only facets they
- will be able to see counts for; regardless of what other
- facet.field or facet.query params they may specify.
-
- NOTE: there is *absolutely* nothing a client can do to prevent these
- "invariants" values from being used, so don't use this mechanism
- unless you are sure you always want it.
- -->
- <!--
- <lst name="invariants">
- <str name="facet.field">cat</str>
- <str name="facet.field">manu_exact</str>
- <str name="facet.query">price:[* TO 500]</str>
- <str name="facet.query">price:[500 TO *]</str>
- </lst>
- -->
- <!-- If the default list of SearchComponents is not desired, that
- list can either be overridden completely, or components can be
- prepended or appended to the default list. (see below)
- -->
- <!--
- <arr name="components">
- <str>nameOfCustomComponent1</str>
- <str>nameOfCustomComponent2</str>
- </arr>
- -->
- </requestHandler>
-
- <!-- A request handler that returns indented JSON by default -->
- <requestHandler name="/query" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- <str name="df">text</str>
- </lst>
- </requestHandler>
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
-
- <!-- VelocityResponseWriter settings -->
- <str name="wt">velocity</str>
- <str name="v.template">browse</str>
- <str name="v.layout">layout</str>
-
- <!-- Query settings -->
- <str name="defType">edismax</str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
-
- <!-- Faceting defaults -->
- <str name="facet">on</str>
- <str name="facet.mincount">1</str>
- </lst>
- </requestHandler>
-
- <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
- <lst name="defaults">
- <str name="df">text</str>
- </lst>
- </initParams>
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <str name="lowernames">true</str>
- <str name="uprefix">ignored_</str>
-
- <!-- capture link hrefs but ignore div attributes -->
- <str name="captureAttr">true</str>
- <str name="fmap.a">links</str>
- <str name="fmap.div">ignored_</str>
- </lst>
- </requestHandler>
- <!-- Search Components
-
- Search components are registered to SolrCore and used by
- instances of SearchHandler (which can access them by name)
-
- By default, the following components are available:
-
- <searchComponent name="query" class="solr.QueryComponent" />
- <searchComponent name="facet" class="solr.FacetComponent" />
- <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
- <searchComponent name="highlight" class="solr.HighlightComponent" />
- <searchComponent name="stats" class="solr.StatsComponent" />
- <searchComponent name="debug" class="solr.DebugComponent" />
-
- Default configuration in a requestHandler would look like:
-
- <arr name="components">
- <str>query</str>
- <str>facet</str>
- <str>mlt</str>
- <str>highlight</str>
- <str>stats</str>
- <str>debug</str>
- </arr>
-
- If you register a searchComponent to one of the standard names,
- that will be used instead of the default.
-
- To insert components before or after the 'standard' components, use:
-
- <arr name="first-components">
- <str>myFirstComponentName</str>
- </arr>
-
- <arr name="last-components">
- <str>myLastComponentName</str>
- </arr>
-
- NOTE: The component registered with the name "debug" will
- always be executed after the "last-components"
-
- -->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
-
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-
- <str name="queryAnalyzerFieldType">text_general</str>
-
- <!-- Multiple "Spell Checkers" can be declared and used by this
- component
- -->
-
- <!-- a spellchecker built from a field of the main index -->
- <lst name="spellchecker">
- <str name="name">default</str>
- <str name="field">text</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <!-- the spellcheck distance measure used, the default is the internal levenshtein -->
- <str name="distanceMeasure">internal</str>
- <!-- minimum accuracy needed to be considered a valid spellcheck suggestion -->
- <float name="accuracy">0.5</float>
- <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 -->
- <int name="maxEdits">2</int>
- <!-- the minimum shared prefix when enumerating terms -->
- <int name="minPrefix">1</int>
- <!-- maximum number of inspections per result. -->
- <int name="maxInspections">5</int>
- <!-- minimum length of a query term to be considered for correction -->
- <int name="minQueryLength">4</int>
- <!-- maximum threshold of documents a query term can appear to be considered for correction -->
- <float name="maxQueryFrequency">0.01</float>
- <!-- uncomment this to require suggestions to occur in 1% of the documents
- <float name="thresholdTokenFrequency">.01</float>
- -->
- </lst>
-
- <!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
- <lst name="spellchecker">
- <str name="name">wordbreak</str>
- <str name="classname">solr.WordBreakSolrSpellChecker</str>
- <str name="field">name</str>
- <str name="combineWords">true</str>
- <str name="breakWords">true</str>
- <int name="maxChanges">10</int>
- </lst>
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="comparatorClass">freq</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <lst name="spellchecker">
- <str name="classname">solr.FileBasedSpellChecker</str>
- <str name="name">file</str>
- <str name="sourceLocation">spellings.txt</str>
- <str name="characterEncoding">UTF-8</str>
- <str name="spellcheckIndexDir">spellcheckerFile</str>
- </lst>
- -->
- </searchComponent>
-
- <!-- A request handler for demonstrating the spellcheck component.
-
- NOTE: This is purely as an example. The whole purpose of the
- SpellCheckComponent is to hook it into the request handler that
- handles your normal user queries so that a separate request is
- not needed to get suggestions.
-
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
- NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
-
- See http://wiki.apache.org/solr/SpellCheckComponent for details
- on the request parameters.
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
<str name="df">text</str>
- <!-- Solr will use suggestions from both the 'default' spellchecker
- and from the 'wordbreak' spellchecker and combine them.
- collations (re-written queries) can include a combination of
- corrections from both spellcheckers -->
- <str name="spellcheck.dictionary">default</str>
- <str name="spellcheck.dictionary">wordbreak</str>
- <str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">true</str>
- <str name="spellcheck.count">10</str>
- <str name="spellcheck.alternativeTermCount">5</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
- <str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
- <str name="spellcheck.maxCollationTries">10</str>
- <str name="spellcheck.maxCollations">5</str>
- </lst>
- <arr name="last-components">
- <str>spellcheck</str>
- </arr>
- </requestHandler>
-
- <searchComponent name="suggest" class="solr.SuggestComponent">
- <lst name="suggester">
- <str name="name">mySuggester</str>
- <str name="lookupImpl">FuzzyLookupFactory</str> <!-- org.apache.solr.spelling.suggest.fst -->
- <str name="dictionaryImpl">DocumentDictionaryFactory</str> <!-- org.apache.solr.spelling.suggest.HighFrequencyDictionaryFactory -->
- <str name="field">cat</str>
- <str name="weightField">price</str>
- <str name="suggestAnalyzerFieldType">string</str>
</lst>
- </searchComponent>
-
- <requestHandler name="/suggest" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="suggest">true</str>
- <str name="suggest.count">10</str>
- </lst>
- <arr name="components">
- <str>suggest</str>
- </arr>
</requestHandler>
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector component
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
+ <requestHandler name="/dataimport" class="solr.DataImportHandler">
<lst name="defaults">
- <str name="df">text</str>
- <bool name="tv">true</bool>
+ <str name="config">tika-data-config.xml</str>
</lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
</requestHandler>
- <!-- Terms Component
-
- http://wiki.apache.org/solr/TermsComponent
-
- A component to return terms and document frequency of those
- terms
- -->
- <searchComponent name="terms" class="solr.TermsComponent"/>
-
- <!-- A request handler for demonstrating the terms component -->
- <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <bool name="terms">true</bool>
- <bool name="distrib">false</bool>
- </lst>
- <arr name="components">
- <str>terms</str>
- </arr>
- </requestHandler>
-
-
- <!-- Highlighting Component
-
- http://wiki.apache.org/solr/HighlightingParameters
- -->
- <searchComponent class="solr.HighlightComponent" name="highlight">
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap"
- default="true"
- class="solr.highlight.GapFragmenter">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
-
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
- -->
- <fragmenter name="regex"
- class="solr.highlight.RegexFragmenter">
- <lst name="defaults">
- <!-- slightly smaller fragsizes work better because of slop -->
- <int name="hl.fragsize">70</int>
- <!-- allow 50% slop on fragment sizes -->
- <float name="hl.regex.slop">0.5</float>
- <!-- a basic sentence pattern -->
- <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
- </lst>
- </fragmenter>
-
- <!-- Configure the standard formatter -->
- <formatter name="html"
- default="true"
- class="solr.highlight.HtmlFormatter">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
-
- <!-- Configure the standard encoder -->
- <encoder name="html"
- class="solr.highlight.HtmlEncoder" />
-
- <!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
- class="solr.highlight.SimpleFragListBuilder"/>
-
- <!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
- class="solr.highlight.SingleFragListBuilder"/>
-
- <!-- Configure the weighted fragListBuilder -->
- <fragListBuilder name="weighted"
- default="true"
- class="solr.highlight.WeightedFragListBuilder"/>
-
- <!-- default tag FragmentsBuilder -->
- <fragmentsBuilder name="default"
- default="true"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <!--
- <lst name="defaults">
- <str name="hl.multiValuedSeparatorChar">/</str>
- </lst>
- -->
- </fragmentsBuilder>
-
- <!-- multi-colored tag FragmentsBuilder -->
- <fragmentsBuilder name="colored"
- class="solr.highlight.ScoreOrderFragmentsBuilder">
- <lst name="defaults">
- <str name="hl.tag.pre"><![CDATA[
- <b style="background:yellow">,<b style="background:lawgreen">,
- <b style="background:aquamarine">,<b style="background:magenta">,
- <b style="background:palegreen">,<b style="background:coral">,
- <b style="background:wheat">,<b style="background:khaki">,
- <b style="background:lime">,<b style="background:deepskyblue">]]></str>
- <str name="hl.tag.post"><![CDATA[</b>]]></str>
- </lst>
- </fragmentsBuilder>
-
- <boundaryScanner name="default"
- default="true"
- class="solr.highlight.SimpleBoundaryScanner">
- <lst name="defaults">
- <str name="hl.bs.maxScan">10</str>
- <str name="hl.bs.chars">.,!? 	 </str>
- </lst>
- </boundaryScanner>
-
- <boundaryScanner name="breakIterator"
- class="solr.highlight.BreakIteratorBoundaryScanner">
- <lst name="defaults">
- <!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
- <str name="hl.bs.type">WORD</str>
- <!-- language and country are used when constructing Locale object. -->
- <!-- And the Locale object will be used when getting instance of BreakIterator -->
- <str name="hl.bs.language">en</str>
- <str name="hl.bs.country">US</str>
- </lst>
- </boundaryScanner>
- </highlighting>
- </searchComponent>
-
- <!-- Update Processors
-
- Chains of Update Processor Factories for dealing with Update
- Requests can be declared, and then used by name in Update
- Request Processors
-
- http://wiki.apache.org/solr/UpdateRequestProcessor
-
- -->
- <!-- Deduplication
-
- An example dedup update processor that creates the "id" field
- on the fly based on the hash code of some other fields. This
- example has overwriteDupes set to false since we are using the
- id field as the signatureField and Solr will maintain
- uniqueness based on that anyway.
-
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="solr.processor.SignatureUpdateProcessorFactory">
- <bool name="enabled">true</bool>
- <str name="signatureField">id</str>
- <bool name="overwriteDupes">false</bool>
- <str name="fields">name,features,cat</str>
- <str name="signatureClass">solr.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Language identification
-
- This example update chain identifies the language of the incoming
- documents using the langid contrib. The detected language is
- written to field language_s. No field name mapping is done.
- The fields used for detection are text, title, subject and description,
- making this example suitable for detecting languages form full-text
- rich documents injected via ExtractingRequestHandler.
- See more about langId at http://wiki.apache.org/solr/LanguageDetection
- -->
- <!--
- <updateRequestProcessorChain name="langid">
- <processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
- <str name="langid.fl">text,title,subject,description</str>
- <str name="langid.langField">language_s</str>
- <str name="langid.fallback">en</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Script update processor
-
- This example hooks in an update processor implemented using JavaScript.
-
- See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
- -->
- <!--
- <updateRequestProcessorChain name="script">
- <processor class="solr.StatelessScriptUpdateProcessorFactory">
- <str name="script">update-script.js</str>
- <lst name="params">
- <str name="config_param">example config parameter</str>
- </lst>
- </processor>
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
-
- <!-- Response Writers
-
- http://wiki.apache.org/solr/QueryResponseWriter
-
- Request responses will be written using the writer specified by
- the 'wt' request parameter matching the name of a registered
- writer.
-
- The "default" writer is the default and will be used if 'wt' is
- not specified in the request.
- -->
- <!-- The following response writers are implicitly configured unless
- overridden...
- -->
- <!--
- <queryResponseWriter name="xml"
- default="true"
- class="solr.XMLResponseWriter" />
- <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
- <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
- <queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
- -->
-
- <queryResponseWriter name="json" class="solr.JSONResponseWriter">
- <!-- For the purposes of the tutorial, JSON responses are written as
- plain text so that they are easy to read in *any* browser.
- If you expect a MIME type of "application/json" just remove this override.
- -->
- <str name="content-type">text/plain; charset=UTF-8</str>
- </queryResponseWriter>
-
- <!--
- Custom response writers can be declared as needed...
- -->
- <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
- <str name="template.base.dir">${velocity.template.base.dir:}</str>
- </queryResponseWriter>
-
- <!-- XSLT response writer transforms the XML output by any xslt file found
- in Solr's conf/xslt directory. Changes to xslt files are checked for
- every xsltCacheLifetimeSeconds.
- -->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
-
- <!-- Query Parsers
-
- https://cwiki.apache.org/confluence/display/solr/Query+Syntax+and+Parsing
-
- Multiple QParserPlugins can be registered by name, and then
- used in either the "defType" param for the QueryComponent (used
- by SearchHandler) or in LocalParams
- -->
- <!-- example of registering a query parser -->
- <!--
- <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
- -->
-
- <!-- Function Parsers
-
- http://wiki.apache.org/solr/FunctionQuery
-
- Multiple ValueSourceParsers can be registered by name, and then
- used as function names when using the "func" QParser.
- -->
- <!-- example of registering a custom function parser -->
- <!--
- <valueSourceParser name="myfunc"
- class="com.mycompany.MyValueSourceParser" />
- -->
-
-
- <!-- Document Transformers
- http://wiki.apache.org/solr/DocTransformers
- -->
- <!--
- Could be something like:
- <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
- <int name="connection">jdbc://....</int>
- </transformer>
-
- To add a constant value to all docs, use:
- <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <int name="value">5</int>
- </transformer>
-
- If you want the user to still be able to change it with _value:something_ use this:
- <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
- <double name="defaultValue">5</double>
- </transformer>
-
- If you are using the QueryElevationComponent, you may wish to mark documents that get boosted. The
- EditorialMarkerFactory will do exactly that:
- <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
- -->
</config>
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/812b0eeb/solr/example/example-DIH/solr/tika/conf/tika-data-config.xml
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/tika/conf/tika-data-config.xml b/solr/example/example-DIH/solr/tika/conf/tika-data-config.xml
index 0d9e768..5286fc4 100644
--- a/solr/example/example-DIH/solr/tika/conf/tika-data-config.xml
+++ b/solr/example/example-DIH/solr/tika/conf/tika-data-config.xml
@@ -1,11 +1,26 @@
<dataConfig>
- <dataSource type="BinFileDataSource" />
- <document>
- <entity name="tika-test" processor="TikaEntityProcessor"
- url="${solr.install.dir}/example/exampledocs/solr-word.pdf" format="text">
- <field column="Author" name="author" meta="true"/>
- <field column="title" name="title" meta="true"/>
- <field column="text" name="text"/>
- </entity>
- </document>
+ <dataSource type="BinFileDataSource"/>
+ <document>
+ <entity name="file" processor="FileListEntityProcessor" dataSource="null"
+ baseDir="${solr.install.dir}/example/exampledocs" fileName=".*pdf"
+ rootEntity="false">
+
+ <field column="file" name="id"/>
+
+ <entity name="pdf" processor="TikaEntityProcessor"
+ url="${file.fileAbsolutePath}" format="text">
+
+ <field column="Author" name="author" meta="true"/>
+ <!-- in the original PDF, the Author meta-field name is upper-cased,
+ but in Solr schema it is lower-cased
+ -->
+
+ <field column="title" name="title" meta="true"/>
+ <field column="dc:format" name="format" meta="true"/>
+
+ <field column="text" name="text"/>
+
+ </entity>
+ </entity>
+ </document>
</dataConfig>
[2/2] lucene-solr:branch_6x: SOLR-9601: DIH Tika example is now
minimal. Only keep definitions and files required to show Tika-extraction in
DIH
Posted by ar...@apache.org.
SOLR-9601: DIH Tika example is now minimal.
Only keep definitions and files required to show Tika-extraction in DIH
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/812b0eeb
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/812b0eeb
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/812b0eeb
Branch: refs/heads/branch_6x
Commit: 812b0eebf3d50a141b952af27bbf7c225df5072d
Parents: e987654
Author: Alexandre Rafalovitch <ar...@apache.org>
Authored: Sat Apr 1 19:13:07 2017 -0400
Committer: Alexandre Rafalovitch <ar...@apache.org>
Committed: Sat Apr 1 19:13:07 2017 -0400
----------------------------------------------------------------------
solr/CHANGES.txt | 2 +
.../example-DIH/solr/tika/conf/admin-extra.html | 24 -
.../solr/tika/conf/admin-extra.menu-bottom.html | 25 -
.../solr/tika/conf/admin-extra.menu-top.html | 25 -
.../example-DIH/solr/tika/conf/managed-schema | 910 +-----------
.../example-DIH/solr/tika/conf/solrconfig.xml | 1354 +-----------------
.../solr/tika/conf/tika-data-config.xml | 33 +-
7 files changed, 72 insertions(+), 2301 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/812b0eeb/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 184af31..953c016 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -107,6 +107,8 @@ Other Changes
* SOLR-7383: New DataImportHandler 'atom' example, replacing broken 'rss' example (Alexandre Rafalovitch)
+* SOLR-9601: Redone DataImportHandler 'tika' example, removing all unused and irrelevant definitions (Alexandre Rafalovitch)
+
================== 6.5.0 ==================
Consult the LUCENE_CHANGES.txt file for additional, low level, changes in this release.
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/812b0eeb/solr/example/example-DIH/solr/tika/conf/admin-extra.html
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/tika/conf/admin-extra.html b/solr/example/example-DIH/solr/tika/conf/admin-extra.html
deleted file mode 100644
index fecab20..0000000
--- a/solr/example/example-DIH/solr/tika/conf/admin-extra.html
+++ /dev/null
@@ -1,24 +0,0 @@
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- The content of this page will be statically included into the top-
-right box of the cores overview page. Uncomment this as an example to
-see there the content will show up.
-
-<img src="img/ico/construction.png"> This line will appear at the top-
-right box on collection1's Overview
--->
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/812b0eeb/solr/example/example-DIH/solr/tika/conf/admin-extra.menu-bottom.html
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/tika/conf/admin-extra.menu-bottom.html b/solr/example/example-DIH/solr/tika/conf/admin-extra.menu-bottom.html
deleted file mode 100644
index 3359a46..0000000
--- a/solr/example/example-DIH/solr/tika/conf/admin-extra.menu-bottom.html
+++ /dev/null
@@ -1,25 +0,0 @@
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- admin-extra.menu-bottom.html -->
-<!--
-<li>
- <a href="#" style="background-image: url(img/ico/construction.png);">
- LAST ITEM
- </a>
-</li>
--->
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/812b0eeb/solr/example/example-DIH/solr/tika/conf/admin-extra.menu-top.html
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/tika/conf/admin-extra.menu-top.html b/solr/example/example-DIH/solr/tika/conf/admin-extra.menu-top.html
deleted file mode 100644
index 0886cee..0000000
--- a/solr/example/example-DIH/solr/tika/conf/admin-extra.menu-top.html
+++ /dev/null
@@ -1,25 +0,0 @@
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements. See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License. You may obtain a copy of the License at
-
- http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- admin-extra.menu-top.html -->
-<!--
-<li>
- <a href="#" style="background-image: url(img/ico/construction.png);">
- FIRST ITEM
- </a>
-</li>
--->
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/812b0eeb/solr/example/example-DIH/solr/tika/conf/managed-schema
----------------------------------------------------------------------
diff --git a/solr/example/example-DIH/solr/tika/conf/managed-schema b/solr/example/example-DIH/solr/tika/conf/managed-schema
index 58b2a80..6d506f7 100644
--- a/solr/example/example-DIH/solr/tika/conf/managed-schema
+++ b/solr/example/example-DIH/solr/tika/conf/managed-schema
@@ -16,897 +16,39 @@
limitations under the License.
-->
-<!--
- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default)
- or located where the classloader for the Solr webapp can find it.
-
- This example schema is the recommended starting point for users.
- It should be kept correct and concise, usable out-of-the-box.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
-
- PERFORMANCE NOTE: this schema includes many optional features and should not
- be used for benchmarking. To improve performance one could
- - set stored="false" for all fields possible (esp large fields) when you
- only need to search on the field but don't need to return the original
- value.
- - set indexed="false" if you don't need to search on the field, but only
- return the field as a result of searching on other indexed fields.
- - remove all unneeded copyField statements
- - for best index size and searching performance, set "index" to false
- for all general text fields, use copyField to copy them to the
- catchall "text" field, and use that for searching.
- - For maximum indexing performance, use the ConcurrentUpdateSolrServer
- java client.
- - Remember to run the JVM in server mode, and use a higher logging level
- that avoids logging every request
--->
-
<schema name="example-DIH-tika" version="1.6">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
- version="x.y" is Solr's version number for the schema syntax and
- semantics. It should not normally be changed by applications.
-
- 1.0: multiValued attribute did not exist, all fields are multiValued
- by nature
- 1.1: multiValued attribute introduced, false by default
- 1.2: omitTermFreqAndPositions attribute introduced, true by default
- except for text fields.
- 1.3: removed optional field compress feature
- 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
- behavior when a single string produces multiple tokens. Defaults
- to off for version >= 1.4
- 1.5: omitNorms defaults to true for primitive field types
- (int, float, boolean, string...)
- 1.6: useDocValuesAsStored defaults to true.
- -->
-
-
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a field type from the
- fieldTypes
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- docValues: true if this field should have doc values. Doc values are
- useful for faceting, grouping, sorting and function queries. Although not
- required, doc values will make the index faster to load, more
- NRT-friendly and more memory-efficient. They however come with some
- limitations: they are currently only supported by StrField, UUIDField
- and all Trie*Fields, and depending on the field type, they might
- require the field to be single-valued, be required or have a default
- value (check the documentation of the field type you're interested in
- for more information)
- multiValued: true if this field may contain multiple values per document
- omitNorms: (expert) set to true to omit the norms associated with
- this field (this disables length normalization and index-time
- boosting for the field, and saves some memory). Only full-text
- fields or fields that need an index-time boost need norms.
- Norms are omitted for primitive (non-analyzed) types by default.
- termVectors: [false] set to true to store the term vector for a
- given field.
- When using MoreLikeThis, fields used for similarity should be
- stored for best performance.
- termPositions: Store position information with the term vector.
- This will increase storage costs.
- termOffsets: Store offset information with the term vector. This
- will increase storage costs.
- required: The field is required. It will throw an error if the
- value does not exist
- default: a value that should be used if no value is specified
- when adding a document.
- -->
-
- <!-- field names should consist of alphanumeric or underscore characters only and
- not start with a digit. This is not currently strictly enforced,
- but other field names will not have first class support from all components
- and back compatibility is not guaranteed. Names with both leading and
- trailing underscores (e.g. _version_) are reserved.
- -->
-
- <field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
- <field name="author" type="text_general" indexed="true" stored="true"/>
- <field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
-
-
- <!-- Dynamic field definitions allow using convention over configuration
- for fields via the specification of patterns to match field names.
- EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
- RESTRICTION: the glob-like pattern in the name attribute must have
- a "*" only at the start or the end. -->
-
- <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
- <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_s" type="string" indexed="true" stored="true" />
- <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
- <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/>
-
- <!-- Type used to index the lat and lon components for the "location" FieldType -->
- <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
-
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
- <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
-
- <!-- some trie-coded dynamic fields for faster range queries -->
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
-
- <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
- <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
-
- <dynamicField name="random_*" type="random" />
-
- <!-- uncomment the following to ignore any fields that don't already match an existing
- field name or dynamic field, rather than reporting them as an error.
- alternately, change the type="ignored" to some other type e.g. "text" if you want
- unknown fields indexed and/or stored by default -->
- <!--dynamicField name="*" type="ignored" multiValued="true" /-->
-
-
-
-
- <!-- Field to use to determine and enforce document uniqueness.
- Unless this field is marked with required="false", it will be a required field
- -->
- <!-- <uniqueKey>id</uniqueKey> -->
-
- <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
- parsing a query string that isn't explicit about the field. Machine (non-user)
- generated queries are best made explicit, or they can use the "df" request parameter
- which takes precedence over this.
- Note: Un-commenting defaultSearchField will be insufficient if your request handler
- in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
- <defaultSearchField>text</defaultSearchField> -->
-
- <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
- when parsing a query string to determine if a clause of the query should be marked as
- required or optional, assuming the clause isn't already marked by some operator.
- The default is OR, which is generally assumed so it is not a good idea to change it
- globally here. The "q.op" request parameter takes precedence over this.
- <solrQueryParser defaultOperator="OR"/> -->
-
- <!-- field type definitions. The "name" attribute is
- just a label to be used by field definitions. The "class"
- attribute and any other attributes determine the real
- behavior of the fieldType.
- Class names starting with "solr" refer to java classes in a
- standard package such as org.apache.solr.analysis
- -->
-
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- It supports doc values but in that case the field needs to be
- single-valued and either required or have a default value.
- -->
- <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
-
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
-
- <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
- currently supported on types that are sorted internally as strings
- and on numeric types.
- This includes "string","boolean", and, as of 3.5 (and 4.x),
- int, float, long, date, double, including the "Trie" variants.
- - If sortMissingLast="true", then a sort on this field will cause documents
- without the field to come after documents with the field,
- regardless of the requested sort order (asc or desc).
- - If sortMissingFirst="true", then a sort on this field will cause documents
- without the field to come before documents with the field,
- regardless of the requested sort order.
- - If sortMissingLast="false" and sortMissingFirst="false" (the default),
- then default lucene sorting will be used which places docs without the
- field first in an ascending sort and last in a descending sort.
- -->
-
- <!--
- Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-
- These fields support doc values, but they require the field to be
- single-valued and either be required or have a default value.
- -->
- <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
-
- <!--
- Numeric field types that index each value at various levels of precision
- to accelerate range queries when the number of values between the range
- endpoints is large. See the javadoc for NumericRangeQuery for internal
- implementation details.
-
- Smaller precisionStep values (specified in bits) will lead to more tokens
- indexed per value, slightly larger index size, and faster range queries.
- A precisionStep of 0 disables indexing at different precision levels.
- -->
- <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
-
- <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
- is a more restricted form of the canonical representation of dateTime
- http://www.w3.org/TR/xmlschema-2/#dateTime
- The trailing "Z" designates UTC time and is mandatory.
- Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
- All other components are mandatory.
-
- Expressions can also be used to denote calculations that should be
- performed relative to "NOW" to determine the value, ie...
-
- NOW/HOUR
- ... Round to the start of the current hour
- NOW-1DAY
- ... Exactly 1 day prior to now
- NOW/DAY+6MONTHS+3DAYS
- ... 6 months and 3 days in the future from the start of
- the current day
-
- Consult the TrieDateField javadocs for more information.
-
- Note: For faster range queries, consider the tdate type
- -->
- <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
- <!-- A Trie based date field for faster date range queries and date faceting. -->
- <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
+ <uniqueKey>id</uniqueKey>
+ <field name="id" type="string" indexed="true" stored="true"/>
+ <field name="author" type="text_simple" indexed="true" stored="true"/>
+ <field name="title" type="text_simple" indexed="true" stored="true" multiValued="true"/>
+ <field name="format" type="string" indexed="true" stored="true"/>
- <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
- <fieldType name="binary" class="solr.BinaryField"/>
+ <!-- field "text" is searchable (it is the default search field) but it is not stored to save space -->
+ <field name="text" type="text_simple" indexed="true" stored="false" multiValued="true"/>
- <!-- The "RandomSortField" is not used to store or search any
- data. You can declare fields of this type it in your schema
- to generate pseudo-random orderings of your docs for sorting
- or function purposes. The ordering is generated based on the field
- name and the version of the index. As long as the index version
- remains unchanged, and the same field name is reused,
- the ordering of the docs will be consistent.
- If you want different psuedo-random orderings of documents,
- for the same version of the index, use a dynamicField and
- change the field name in the request.
- -->
- <fieldType name="random" class="solr.RandomSortField" indexed="true" />
- <!-- solr.TextField allows the specification of custom text analyzers
- specified as a tokenizer and a list of token filters. Different
- analyzers may be specified for indexing and querying.
-
- The optional positionIncrementGap puts space between multiple fields of
- this type on the same document, with the purpose of preventing false phrase
- matching across fields.
-
- For more info on customizing your analyzer chain, please see
- http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
- -->
-
- <!-- One can also specify an existing Analyzer class that has a
- default constructor via the class attribute on the analyzer element.
- Example:
- <fieldType name="text_greek" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
- </fieldType>
- -->
-
- <!-- A text field that only splits on whitespace for exact matching of words -->
- <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A general text field that has reasonable, generic
- cross-language defaults: it tokenizes with StandardTokenizer,
- and down cases. -->
- <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English: it
- tokenizes with StandardTokenizer, down cases, and
- finally applies Porter's stemming. -->
- <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- -->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- Uncomment the dynamicField definition to catch any other fields
+ that may have been declared in the DIH configuration.
+ This allows to speed up prototyping.
-->
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- A text field with defaults appropriate for English, plus
- aggressive word-splitting and autophrase features enabled.
- This field is just like text_en, except it adds
- WordDelimiterGraphFilter to enable splitting and matching of
- words on case-change, alpha numeric boundaries, and
- non-alphanumeric chars. This means certain compound word
- cases will work, for example query "wi fi" will match
- document "WiFi" or "wi-fi".
- -->
- <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
- <filter class="solr.FlattenGraphFilterFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Less flexible matching, but less false matches. Probably not ideal for product names,
- but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
- <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- <filter class="solr.FlattenGraphFilterFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
- possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Just like text_general except it reverses the characters of
- each token, to enable more efficient leading wildcard queries. -->
- <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
- maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- charFilter + WhitespaceTokenizer -->
- <!--
- <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
- <analyzer>
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- </analyzer>
- </fieldType>
- -->
-
- <!-- This is an example of using the KeywordTokenizer along
- With various TokenFilterFactories to produce a sortable field
- that does not include some properties of the source text
- -->
- <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
- <analyzer>
- <!-- KeywordTokenizer does no actual tokenizing, so the entire
- input string is preserved as a single token
- -->
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <!-- The LowerCase TokenFilter does what you expect, which can be
- when you want your sorting to be case insensitive
- -->
- <filter class="solr.LowerCaseFilterFactory" />
- <!-- The TrimFilter removes any leading or trailing whitespace -->
- <filter class="solr.TrimFilterFactory" />
- <!-- The PatternReplaceFilter gives you the flexibility to use
- Java Regular expression to replace any sequence of characters
- matching a pattern with an arbitrary replacement string,
- which may include back references to portions of the original
- string matched by the pattern.
-
- See the Java Regular Expression documentation for more
- information on pattern and replacement string syntax.
-
- http://docs.oracle.com/javase/7/docs/api/java/util/regex/package-summary.html
- -->
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-z])" replacement="" replace="all"
- />
- </analyzer>
- </fieldType>
-
- <fieldType name="phonetic" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
- </analyzer>
- </fieldType>
-
- <fieldType name="payloads" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!--
- The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
- a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
- Attributes of the DelimitedPayloadTokenFilterFactory :
- "delimiter" - a one character delimiter. Default is | (pipe)
- "encoder" - how to encode the following value into a playload
- float -> org.apache.lucene.analysis.payloads.FloatEncoder,
- integer -> o.a.l.a.p.IntegerEncoder
- identity -> o.a.l.a.p.IdentityEncoder
- Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
- -->
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </analyzer>
- </fieldType>
-
- <!-- lowercases the entire field value, keeping it as a single token. -->
- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory" />
- </analyzer>
- </fieldType>
-
- <!--
- Example of using PathHierarchyTokenizerFactory at index time, so
- queries for paths match documents at that path, or in descendent paths
- -->
- <fieldType name="descendent_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- </fieldType>
- <!--
- Example of using PathHierarchyTokenizerFactory at query time, so
- queries for paths match documents at that path, or in ancestor paths
- -->
- <fieldType name="ancestor_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- </fieldType>
-
- <!-- since fields of this type are by default not stored or indexed,
- any data added to them will be ignored outright. -->
- <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
-
- <!-- This point type indexes the coordinates as separate fields (subFields)
- If subFieldType is defined, it references a type, and a dynamic field
- definition is created matching *___<typename>. Alternately, if
- subFieldSuffix is defined, that is used to create the subFields.
- Example: if subFieldType="double", then the coordinates would be
- indexed in fields myloc_0___double,myloc_1___double.
- Example: if subFieldSuffix="_d" then the coordinates would be indexed
- in fields myloc_0_d,myloc_1_d
- The subFields are an implementation detail of the fieldType, and end
- users normally should not need to know about them.
- -->
- <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+ <!-- <dynamicField name="*" type="string" indexed="true" stored="true" multiValued="true"/> -->
- <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
- <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
+ <!-- The StrField type is not analyzed, but is indexed/stored verbatim. -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
- <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
- For more information about this and other Spatial fields new to Solr 4, see:
- http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
- -->
- <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
- geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
-
-
-
- <!-- some examples for different languages (generally ordered by ISO code) -->
-
- <!-- Arabic -->
- <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- for any non-arabic -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <!-- normalizes \ufeef to \ufef1, etc -->
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.ArabicStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Bulgarian -->
- <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.BulgarianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Catalan -->
- <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
- </analyzer>
- </fieldType>
-
- <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
- <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- for any non-CJK -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.CJKBigramFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Kurdish -->
- <fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SoraniNormalizationFilterFactory"/>
- <!-- for any latin text -->
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SoraniStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Czech -->
- <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.CzechStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Danish -->
- <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
- </analyzer>
- </fieldType>
-
- <!-- German -->
- <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.GermanNormalizationFilterFactory"/>
- <filter class="solr.GermanLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Greek -->
- <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <!-- greek specific lowercase for sigma -->
- <filter class="solr.GreekLowerCaseFilterFactory"/>
- <filter class="solr.GreekStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Spanish -->
- <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SpanishLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Basque -->
- <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
- </analyzer>
- </fieldType>
-
- <!-- Persian -->
- <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <!-- for ZWNJ -->
- <charFilter class="solr.PersianCharFilterFactory"/>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ArabicNormalizationFilterFactory"/>
- <filter class="solr.PersianNormalizationFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Finnish -->
- <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
- <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- French -->
- <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.FrenchLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Irish -->
- <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.IrishLowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
- </analyzer>
- </fieldType>
-
- <!-- Galician -->
- <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.GalicianStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Hindi -->
- <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <!-- normalizes unicode representation -->
- <filter class="solr.IndicNormalizationFilterFactory"/>
- <!-- normalizes variation in spelling -->
- <filter class="solr.HindiNormalizationFilterFactory"/>
- <filter class="solr.HindiStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Hungarian -->
- <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
- <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Armenian -->
- <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
- </analyzer>
- </fieldType>
-
- <!-- Indonesian -->
- <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
- <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
- </analyzer>
- </fieldType>
-
- <!-- Italian -->
- <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ItalianLightStemFilterFactory"/>
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
-
- NOTE: If you want to optimize search for precision, use default operator AND in your query
- parser config with <solrQueryParser defaultOperator="AND"/> further down in this file. Use
- OR if you would like to optimize for recall (default).
- -->
- <fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
- <analyzer>
- <!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
-
- Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
- is used to segment compounds into its parts and the compound itself is kept as synonym.
-
- Valid values for attribute mode are:
- normal: regular segmentation
- search: segmentation useful for search with synonyms compounds (default)
- extended: same as search mode, but unigrams unknown words (experimental)
-
- For some applications it might be good to use search mode for indexing and normal mode for
- queries to reduce recall and prevent parts of compounds from being matched and highlighted.
- Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
-
- Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
- model with your own entries for segmentation, part-of-speech tags and readings without a need
- to specify weights. Notice that user dictionaries have not been subject to extensive testing.
-
- User dictionary attributes are:
- userDictionary: user dictionary filename
- userDictionaryEncoding: user dictionary encoding (default is UTF-8)
-
- 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"/>
- <!-- Reduces inflected verbs and adjectives to their base/dictionary forms (\u8f9e\u66f8\u5f62) -->
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
- <!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
- <filter class="solr.CJKWidthFilterFactory"/>
- <!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
- <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
- <!-- Lower-cases romaji characters -->
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Latvian -->
- <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.LatvianStemFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Dutch -->
- <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
- </analyzer>
- </fieldType>
-
- <!-- Norwegian -->
- <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
- <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/> -->
- <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
- <!-- The "light" and "minimal" stemmers support variants: nb=Bokm�l, nn=Nynorsk, no=Both -->
- </analyzer>
- </fieldType>
-
- <!-- Portuguese -->
- <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.PortugueseLightStemFilterFactory"/>
- <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
- <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
- <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Romanian -->
- <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
- </analyzer>
- </fieldType>
-
- <!-- Russian -->
- <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
- <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Swedish -->
- <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
- <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
- </analyzer>
- </fieldType>
-
- <!-- Thai -->
- <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.ThaiTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
-
- <!-- Turkish -->
- <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.ApostropheFilterFactory"/>
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
- <filter class="solr.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>
+ <!-- A basic text field that has reasonable, generic
+ cross-language defaults: it tokenizes with StandardTokenizer,
+ and down cases. It does not deal with stopwords or other issues.
+ See other examples for alternative definitions.
+ -->
+ <fieldType name="text_simple" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+</schema>
\ No newline at end of file