spec/dummy/solr/conf/solrconfig.xml in enju_oai-0.1.0.pre11 vs spec/dummy/solr/conf/solrconfig.xml in enju_oai-0.1.0.pre12
- old
+ new
@@ -1,6 +1,6 @@
-<?xml version="1.0" encoding="UTF-8"?>
+<?xml version="1.0" encoding="UTF-8" ?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
@@ -13,922 +13,655 @@
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
-<!--
- For more details about configurations options that may appear in this
- file, see http://wiki.apache.org/solr/SolrConfigXml.
- Specifically, the Solr Config can support XInclude, which may make it easier to manage
- the configuration. See https://issues.apache.org/jira/browse/SOLR-1167
+<!--
+ For more details about configurations options that may appear in
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
-->
<config>
- <!-- Set this to 'false' if you want solr to continue working after it has
- encountered an severe configuration error. In a production environment,
- you may want solr to keep working even if one handler is mis-configured.
+ <!-- In all configuration below, a prefix of "solr." for class names
+ is an alias that causes solr to search appropriate packages,
+ including org.apache.solr.(search|update|request|core|analysis)
- You may also set this to false using by setting the system property:
- -Dsolr.abortOnConfigurationError=false
- -->
- <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
- <!-- lib directives can be used to instruct Solr to load an Jars identified
- and use them to resolve any "plugins" specified in your solrconfig.xml or
- schema.xml (ie: Analyzers, Request Handlers, etc...).
+ You may also specify a fully qualified Java classname if you
+ have your own custom plugins.
+ -->
- All directories and paths are resolved relative the instanceDir.
+ <!-- Controls what version of Lucene various components of Solr
+ adhere to. Generally, you want to use the latest version to
+ get all bug fixes and improvements. It is highly recommended
+ that you fully re-index after changing this setting as it can
+ affect both how text is indexed and queried.
+ -->
+ <luceneMatchVersion>LUCENE_41</luceneMatchVersion>
- If a "./lib" directory exists in your instanceDir, all files found in it
- are included as if you had used the following syntax...
+ <!-- <lib/> directives can be used to instruct Solr to load an 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.
- -->
- <lib dir="../../contrib/extraction/lib"/>
- <!-- When a regex is specified in addition to a directory, only the files in that
- directory which completely match the regex (anchored on both ends)
- will be included.
- -->
- <lib dir="../../dist/" regex="apache-solr-cell-\d.*\.jar"/>
- <lib dir="../../dist/" regex="apache-solr-clustering-\d.*\.jar"/>
- <!-- If a dir option (with or without a regex) is used and nothing is found
- that matches, it will be ignored
- -->
- <lib dir="../../contrib/clustering/lib/downloads/"/>
- <lib dir="../../contrib/clustering/lib/"/>
- <lib dir="/total/crap/dir/ignored"/>
- <!-- an exact path can be used to specify a specific 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" />
- -->
- <!-- 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:./solr/data}</dataDir>
- <!-- WARNING: this <indexDefaults> section only provides defaults for index writers
- in general. See also the <mainIndex> section after that when changing parameters
- for Solr's main Lucene index. -->
- <indexDefaults>
- <!-- Values here affect all index writers and act as a default unless overridden. -->
- <useCompoundFile>false</useCompoundFile>
- <mergeFactor>10</mergeFactor>
- <!-- If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush
- based on whichever limit is hit first. -->
- <!--<maxBufferedDocs>1000</maxBufferedDocs>-->
- <!-- 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. -->
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <!-- <maxMergeDocs>2147483647</maxMergeDocs> -->
- <maxFieldLength>10000</maxFieldLength>
- <writeLockTimeout>1000</writeLockTimeout>
- <commitLockTimeout>10000</commitLockTimeout>
- <!--
- Expert: Turn on Lucene's auto commit capability. This causes intermediate
- segment flushes to write a new lucene index descriptor, enabling it to be
- opened by an external IndexReader. This can greatly slow down indexing
- speed. NOTE: Despite the name, this value does not have any relation to
- Solr's autoCommit functionality
- -->
- <!--<luceneAutoCommit>false</luceneAutoCommit>-->
- <!--
- Expert: The Merge Policy in Lucene controls how merging is handled by
- Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
- versions used LogDocMergePolicy.
+ <dataDir>${solr.data.dir:}</dataDir>
- LogByteSizeMergePolicy chooses segments to merge based on their size. The
- Lucene 2.2 default, LogDocMergePolicy chose when to merge based on number
- of documents
- Other implementations of MergePolicy must have a no-argument constructor
- -->
- <!--<mergePolicy class="org.apache.lucene.index.LogByteSizeMergePolicy"/>-->
- <!--
- Expert:
- 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"/>-->
- <!--
- 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
- simple = SimpleFSLockFactory - uses a plain file for locking
+ <!-- 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.
- (For backwards compatibility with Solr 1.2, 'simple' is the default
- if not specified.)
+ 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.
-->
- <lockType>native</lockType>
- <!--
- Expert:
- Controls how often Lucene loads terms into memory -->
- <!--<termIndexInterval>256</termIndexInterval>-->
- </indexDefaults>
- <mainIndex>
- <!-- options specific to the main on-disk lucene index -->
- <useCompoundFile>false</useCompoundFile>
- <ramBufferSizeMB>32</ramBufferSizeMB>
- <mergeFactor>10</mergeFactor>
- <!-- Deprecated -->
- <!--<maxBufferedDocs>1000</maxBufferedDocs>-->
- <!--<maxMergeDocs>2147483647</maxMergeDocs>-->
- <!-- inherit from indexDefaults <maxFieldLength>10000</maxFieldLength> -->
- <!-- If true, unlock any held write or commit locks on startup.
- This defeats the locking mechanism that allows multiple
- processes to safely access a lucene index, and should be
- used with care.
- This is not needed if lock type is 'none' or 'single'
- -->
- <unlockOnStartup>false</unlockOnStartup>
- <!-- If true, IndexReaders will be reopened (often more efficient) instead
- of closed and then opened. -->
- <reopenReaders>true</reopenReaders>
- <!--
- Expert:
- Controls how often Lucene loads terms into memory. Default is 128 and is likely good for most everyone. -->
- <!--<termIndexInterval>256</termIndexInterval>-->
- <!--
- Custom deletion policies can specified here. The class must
- implement org.apache.lucene.index.IndexDeletionPolicy.
+ <directoryFactory name="DirectoryFactory"
+ class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
- http://lucene.apache.org/java/2_3_2/api/org/apache/lucene/index/IndexDeletionPolicy.html
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ 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> -->
- The standard Solr IndexDeletionPolicy implementation supports deleting
- index commit points on number of commits, age of commit point and
- optimized status.
+ <!-- The maximum number of simultaneous threads that may be
+ indexing documents at once in IndexWriter; if more than this
+ many threads arrive they will wait for others to finish.
+ Default in Solr/Lucene is 8. -->
+ <maxIndexingThreads>2</maxIndexingThreads>
- 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>
- <!-- To aid in advanced debugging, you may turn on IndexWriter debug logging.
- Setting to true will set the file that the underlying Lucene IndexWriter
- will write its debug infostream to. -->
- <infoStream file="INFOSTREAM.txt">false</infoStream>
- </mainIndex>
- <!-- 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.
+ <useCompoundFile>true</useCompoundFile>
- If you want to connect to a particular server, specify the agentId
- e.g. <jmx agentId="myAgent" />
+ <!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
+ indexing for buffering added documents and deletions before they are
+ flushed to the Directory.
+ maxBufferedDocs sets a limit on the number of documents buffered
+ before flushing.
+ If both ramBufferSizeMB and maxBufferedDocs is set, then
+ Lucene will flush based on whichever limit is hit first. -->
+ <ramBufferSizeMB>20</ramBufferSizeMB> -->
+ <maxBufferedDocs>10000</maxBufferedDocs>
- If you want to start a new MBeanServer, specify the serviceUrl
- e.g <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+ <!-- 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.
+ -->
+ <mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
+ <int name="maxMergeAtOnce">4</int>
+ <int name="segmentsPerTier">4</int>
+ </mergePolicy>
+
+ <unlockOnStartup>true</unlockOnStartup>
+
+ </indexConfig>
- For more details see http://wiki.apache.org/solr/SolrJmx
- -->
- <jmx/>
- <!-- the default high-performance update handler -->
<updateHandler class="solr.DirectUpdateHandler2">
- <!-- 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)
- -->
- <!-- Perform a <commit/> automatically under certain conditions:
- maxDocs - number of updates since last commit is greater than this
- maxTime - oldest uncommited update (in ms) is this long ago
- Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents. http://wiki.apache.org/solr/UpdateXmlMessages
- <autoCommit>
- <maxDocs>10000</maxDocs>
- <maxTime>1000</maxTime>
- </autoCommit>
- -->
- <!-- 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=nothing
- env - environment variables to set. default=nothing
- -->
- <!-- A postCommit event is fired after every commit or optimize command
- <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>
- -->
- <!-- A postOptimize event is fired only after every optimize command
- <listener event="postOptimize" class="solr.RunExecutableListener">
- <str name="exe">snapshooter</str>
- <str name="dir">solr/bin</str>
- <bool name="wait">true</bool>
- </listener>
- -->
- </updateHandler>
- <!-- Use the following format to specify a custom IndexReaderFactory - 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.
+ <!-- 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>
- ** 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.
+ <autoCommit>
+ <maxTime>15000</maxTime>
+ <openSearcher>false</openSearcher>
+ </autoCommit>
- <indexReaderFactory name="IndexReaderFactory" class="package.class">
- Parameters as required by the implementation
- </indexReaderFactory >
- -->
- <!-- To set the termInfosIndexDivisor, do this: -->
- <!--<indexReaderFactory name="IndexReaderFactory" class="org.apache.solr.core.StandardIndexReaderFactory">
- <int name="termInfosIndexDivisor">12</int>
- </indexReaderFactory >-->
+ <autoSoftCommit>
+ <maxTime>5000</maxTime>
+ </autoSoftCommit>
+ </updateHandler>
+
<query>
- <!-- Maximum number of clauses in a boolean query... in the past, this affected
- range or prefix queries that expanded to big boolean queries - built in Solr
- query parsers no longer create queries with this limitation.
- An exception is thrown if exceeded. -->
<maxBooleanClauses>1024</maxBooleanClauses>
- <!-- There are two implementations of cache available for Solr,
+
+
+ <!-- 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. -->
- <!-- 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 FastLRUCache
- size - the maximum number of entries in the cache
- initialSize - the initial capacity (number of entries) of
- the cache. (seel java.util.HashMap)
- autowarmCount - the number of entries to prepopulate from
- and old cache.
- -->
- <filterCache class="solr.FastLRUCache" size="512" initialSize="512" autowarmCount="0"/>
- <!-- 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"
- />
+ 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.
-->
- <!-- queryResultCache 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"/>
- <!-- documentCache 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"/>
- <!-- 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.
+
+ <!-- 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"/>
+
+ <!-- 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>
- <!-- 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.search.CacheRegenerator if autowarming is desired. -->
- <!--
- <cache name="myUserCache"
- class="solr.LRUCache"
- size="4096"
- initialSize="1024"
- autowarmCount="1024"
- regenerator="org.mycompany.mypackage.MyRegenerator"
- />
- -->
- <!-- An 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.
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
- <!-- An optimization for use with the queryResultCache. When a search
- is requested, a superset of the requested number of document ids
- are collected. For example, if a search for a particular query
- requests matching documents 10 through 19, and queryWindowSize is 50,
- then documents 0 through 49 will be collected and cached. Any further
- requests in that range can be satisfied via the cache. -->
- <queryResultWindowSize>20</queryResultWindowSize>
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache. -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
- <!-- a newSearcher event is 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.
- -->
- <!-- 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="start">0</str> <str name="rows">10</str> </lst>
- <lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
- <lst><str name="q">static newSearcher warming query from solrconfig.xml</str></lst>
- -->
- </arr>
- </listener>
- <!-- a firstSearcher event is fired whenever a new searcher is being
- prepared but there is no current registered searcher to handle
- requests or to gain autowarming data from. -->
- <listener event="firstSearcher" class="solr.QuerySenderListener">
- <arr name="queries">
- <lst>
- <str name="q">solr rocks</str>
- <str name="start">0</str>
- <str name="rows">10</str>
- </lst>
- <lst>
- <str name="q">static firstSearcher warming query from solrconfig.xml</str>
- </lst>
- </arr>
- </listener>
- <!-- 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. -->
+
+ <!-- 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.
+
+
+ -->
+
+ <!-- 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>
- <!-- Maximum number of searchers that may be warming in the background
- concurrently. An error is returned if this limit is exceeded. Recommend
- 1-2 for read-only slaves, higher for masters w/o cache warming. -->
- <maxWarmingSearchers>2</maxWarmingSearchers>
+
+ <!-- Max Warming Searchers
+
+ Maximum number of searchers that may be warming in the
+ background concurrently. An error is returned if this limit
+ is exceeded.
+
+ Recommend values of 1-2 for read-only slaves, higher for
+ masters w/o cache warming.
+ -->
+ <maxWarmingSearchers>5</maxWarmingSearchers>
+
</query>
- <!--
- Let the dispatch filter handler /select?qt=XXX
- handleSelect=true will use consistent error handling for /select and /update
- handleSelect=false will use solr1.1 style error formatting
- -->
- <requestDispatcher handleSelect="true">
- <!--Make sure your system has some authentication before enabling remote streaming! -->
- <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048000"/>
- <!-- Set HTTP caching related parameters (for proxy caches and clients).
-
- To get the behaviour of Solr 1.2 (ie: no caching related headers)
- use the never304="true" option and do not specify a value for
- <cacheControl>
- -->
- <!-- <httpCaching never304="true"> -->
- <httpCaching lastModifiedFrom="openTime" etagSeed="Solr">
- <!-- lastModFrom="openTime" is the default, 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 corrispond 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
- differnet 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.
- -->
- <!-- 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="
+ <!-- Request Dispatcher
- By default, no Cache-Control header is generated.
+ This section contains instructions for how the SolrDispatchFilter
+ should behave when processing requests for this SolrCore.
- You can use the <cacheControl> option even if you have set
- never304="true"
- -->
- <!-- <cacheControl>max-age=30, public</cacheControl> -->
- </httpCaching>
- </requestDispatcher>
- <!-- requestHandler plugins... incoming queries will be dispatched to the
- correct handler based on the path or the qt (query type) param.
- Names starting with a '/' are accessed with the a path equal to the
- registered name. Names without a leading '/' are accessed with:
- http://host/app/select?qt=name
- If no qt is defined, the requestHandler that declares default="true"
- will be used.
- -->
- <requestHandler name="standard" class="solr.SearchHandler" default="true">
- <!-- default values for query parameters -->
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <!--
- <int name="rows">10</int>
- <str name="fl">*</str>
- <str name="version">2.1</str>
- -->
- </lst>
- </requestHandler>
- <!-- Please refer to http://wiki.apache.org/solr/SolrReplication for details on configuring replication -->
- <!-- remove the <lst name="master"> section if this is just a slave -->
- <!-- remove the <lst name="slave"> section if this is just a master -->
- <!--
-<requestHandler name="/replication" class="solr.ReplicationHandler" >
- <lst name="master">
- <str name="replicateAfter">commit</str>
- <str name="replicateAfter">startup</str>
- <str name="confFiles">schema.xml,stopwords.txt</str>
- </lst>
- <lst name="slave">
- <str name="masterUrl">http://localhost:8983/solr/replication</str>
- <str name="pollInterval">00:00:60</str>
- </lst>
-</requestHandler>-->
- <!-- DisMaxRequestHandler allows easy searching across multiple fields
- for simple user-entered phrases. It's implementation is now
- just the standard SearchHandler with a default query type
- of "dismax".
- see http://wiki.apache.org/solr/DisMaxRequestHandler
- -->
- <requestHandler name="dismax" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="defType">dismax</str>
- <str name="echoParams">explicit</str>
- <float name="tie">0.01</float>
- <str name="qf">
- text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
- </str>
- <str name="pf">
- text^0.2 features^1.1 name^1.5 manu^1.4 manu_exact^1.9
- </str>
- <str name="bf">
- popularity^0.5 recip(price,1,1000,1000)^0.3
- </str>
- <str name="fl">
- id,name,price,score
- </str>
- <str name="mm">
- 2<-1 5<-2 6<90%
- </str>
- <int name="ps">100</int>
- <str name="q.alt">*:*</str>
- <!-- example highlighter config, enable per-query with hl=true -->
- <str name="hl.fl">text features name</str>
- <!-- for this field, we want no fragmenting, just highlighting -->
- <str name="f.name.hl.fragsize">0</str>
- <!-- instructs Solr to return the field itself if no query terms are
- found -->
- <str name="f.name.hl.alternateField">name</str>
- <str name="f.text.hl.fragmenter">regex</str>
- <!-- defined below -->
- </lst>
- </requestHandler>
- <!-- Note how you can register the same handler multiple times with
- different names (and different init parameters)
+ 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
-->
- <requestHandler name="partitioned" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="defType">dismax</str>
- <str name="echoParams">explicit</str>
- <str name="qf">text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0</str>
- <str name="mm">2<-1 5<-2 6<90%</str>
- <!-- This is an example of using Date Math to specify a constantly
- moving date range in a config...
- -->
- <str name="bq">incubationdate_dt:[* TO NOW/DAY-1MONTH]^2.2</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").
+ <requestDispatcher handleSelect="false" >
+ <!-- Request Parsing
- In this example, the param "fq=instock:true" will 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).
+ These settings indicate how Solr Requests may be parsed, and
+ what restrictions may be placed on the ContentStreams from
+ those requests
- 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.
+ 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.
+
+ *** WARNING ***
+ The settings below authorize Solr to fetch remote files, You
+ should make sure your system has some authentication before
+ using enableRemoteStreaming="true"
+
+ -->
+
+ <!-- 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
-->
- <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.
+ <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.
- In this example, the facet.field and facet.query params are 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.
+ The following options can also be specified to affect the
+ values of these headers...
- 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.
+ 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)
-->
- <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>
- </requestHandler>
- <!--
- Search components are registered to SolrCore and used by Search Handlers
-
- By default, the following components are avaliable:
-
- <searchComponent name="query" class="org.apache.solr.handler.component.QueryComponent" />
- <searchComponent name="facet" class="org.apache.solr.handler.component.FacetComponent" />
- <searchComponent name="mlt" class="org.apache.solr.handler.component.MoreLikeThisComponent" />
- <searchComponent name="highlight" class="org.apache.solr.handler.component.HighlightComponent" />
- <searchComponent name="stats" class="org.apache.solr.handler.component.StatsComponent" />
- <searchComponent name="debug" class="org.apache.solr.handler.component.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>
+ <!--
+ <httpCaching lastModifiedFrom="openTime"
+ etagSeed="Solr">
+ <cacheControl>max-age=30, public</cacheControl>
+ </httpCaching>
+ -->
+ </requestDispatcher>
- If you register a searchComponent to one of the standard names, that will be used instead.
- 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>
- -->
- <!-- The spell check component can return a list of alternative spelling
- suggestions. -->
- <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
- <str name="queryAnalyzerFieldType">textSpell</str>
- <lst name="spellchecker">
- <str name="name">default</str>
- <str name="field">name</str>
- <str name="spellcheckIndexDir">./spellchecker</str>
- </lst>
- <!-- a spellchecker that uses a different distance measure
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
- <str name="spellcheckIndexDir">./spellchecker2</str>
- </lst>
- -->
- <!-- a file based spell checker
- <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>
+ <!-- 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.
+
-->
- </searchComponent>
- <!-- A request handler utilizing 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 (i.e.
- the standard or dismax SearchHandler) queries such that a separate request is
- not needed to get suggestions.
+ <!-- SearchHandler
- IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS NOT WHAT YOU
- WANT FOR YOUR PRODUCTION SYSTEM!
- #############################################################################
- -->
- <requestHandler name="/spell" class="solr.SearchHandler" lazy="true">
- <lst name="defaults">
- <!-- omp = Only More Popular -->
- <str name="spellcheck.onlyMorePopular">false</str>
- <!-- exr = Extended Results -->
- <str name="spellcheck.extendedResults">false</str>
- <!-- The number of suggestions to return -->
- <str name="spellcheck.count">1</str>
- </lst>
+ 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">
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
- <searchComponent name="tvComponent" class="org.apache.solr.handler.component.TermVectorComponent"/>
- <!-- A Req Handler for working with the tvComponent. This is purely as an example.
- You will likely want to add the component to your already specified request handlers. -->
- <requestHandler name="tvrh" class="org.apache.solr.handler.component.SearchHandler">
- <lst name="defaults">
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
+
+ <!-- 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>
+ <arr name="last-components">
+ <str>spellcheck</str>
+ </arr>
</requestHandler>
- <!-- Clustering Component
- http://wiki.apache.org/solr/ClusteringComponent
- This relies on third party jars which are not included in the release.
- To use this component (and the "/clustering" handler)
- Those jars will need to be downloaded, and you'll need to set the
- solr.cluster.enabled system property when running solr...
- java -Dsolr.clustering.enabled=true -jar start.jar
- -->
- <searchComponent name="clusteringComponent" enable="${solr.clustering.enabled:false}" class="org.apache.solr.handler.clustering.ClusteringComponent">
- <!-- Declare an engine -->
- <lst name="engine">
- <!-- The name, only one can be named "default" -->
- <str name="name">default</str>
- <!--
- Class name of Carrot2 clustering algorithm. Currently available algorithms are:
-
- * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
- * org.carrot2.clustering.stc.STCClusteringAlgorithm
-
- See http://project.carrot2.org/algorithms.html for the algorithm's characteristics.
- -->
- <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
- <!--
- Overriding values for Carrot2 default algorithm attributes. For a description
- of all available attributes, see: http://download.carrot2.org/stable/manual/#chapter.components.
- Use attribute key as name attribute of str elements below. These can be further
- overridden for individual requests by specifying attribute key as request
- parameter name and attribute value as parameter value.
- -->
- <str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str>
- </lst>
- <lst name="engine">
- <str name="name">stc</str>
- <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
- </lst>
- </searchComponent>
- <requestHandler name="/clustering" enable="${solr.clustering.enabled:false}" class="solr.SearchHandler">
- <lst name="defaults">
- <bool name="clustering">true</bool>
- <str name="clustering.engine">default</str>
- <bool name="clustering.results">true</bool>
- <!-- The title field -->
- <str name="carrot.title">name</str>
- <str name="carrot.url">id</str>
- <!-- The field to cluster on -->
- <str name="carrot.snippet">features</str>
- <!-- produce summaries -->
- <bool name="carrot.produceSummary">true</bool>
- <!-- the maximum number of labels per cluster -->
- <!--<int name="carrot.numDescriptions">5</int>-->
- <!-- produce sub clusters -->
- <bool name="carrot.outputSubClusters">false</bool>
- </lst>
- <arr name="last-components">
- <str>clusteringComponent</str>
- </arr>
+
+
+ <!-- realtime get handler, guaranteed to return the latest stored fields of
+ any document, without the need to commit or open a new searcher. The
+ current implementation relies on the updateLog feature being enabled. -->
+ <requestHandler name="/get" class="solr.RealTimeGetHandler">
+ <lst name="defaults">
+ <str name="omitHeader">true</str>
+ <str name="wt">json</str>
+ <str name="indent">true</str>
+ </lst>
</requestHandler>
- <!-- Solr Cell: http://wiki.apache.org/solr/ExtractingRequestHandler -->
- <requestHandler name="/update/extract" class="org.apache.solr.handler.extraction.ExtractingRequestHandler" startup="lazy">
+
+ <requestHandler name="/update" class="solr.UpdateRequestHandler">
+ </requestHandler>
+
+ <requestHandler name="/update/json" class="solr.JsonUpdateRequestHandler">
+ <lst name="defaults">
+ <str name="stream.contentType">application/json</str>
+ </lst>
+ </requestHandler>
+
+ <requestHandler name="/update/csv" class="solr.CSVRequestHandler">
+ <lst name="defaults">
+ <str name="stream.contentType">application/csv</str>
+ </lst>
+ </requestHandler>
+
+ <requestHandler name="/update/extract"
+ startup="lazy"
+ class="solr.extraction.ExtractingRequestHandler" >
<lst name="defaults">
- <!-- All the main content goes into "text"... if you need to return
- the extracted text or do highlighting, use a stored field. -->
- <str name="fmap.content">text</str>
<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>
- <!-- A component to return terms and document frequency of those terms.
- This component does not yet support distributed search. -->
- <searchComponent name="termsComponent" class="org.apache.solr.handler.component.TermsComponent"/>
- <requestHandler name="/terms" class="org.apache.solr.handler.component.SearchHandler">
+
+ <requestHandler name="/analysis/field"
+ startup="lazy"
+ class="solr.FieldAnalysisRequestHandler" />
+
+ <requestHandler name="/analysis/document"
+ class="solr.DocumentAnalysisRequestHandler"
+ startup="lazy" />
+
+ <!-- ping/healthcheck -->
+ <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
+ <lst name="invariants">
+ <str name="q">solrpingquery</str>
+ </lst>
<lst name="defaults">
- <bool name="terms">true</bool>
+ <str name="echoParams">all</str>
</lst>
- <arr name="components">
- <str>termsComponent</str>
- </arr>
</requestHandler>
- <!-- a search component that enables you to configure the top results for
- a given query regardless of the normal lucene scoring.-->
- <searchComponent name="elevator" class="solr.QueryElevationComponent">
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
- <!-- a request handler utilizing the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
+
+ <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
<lst name="defaults">
- <str name="echoParams">explicit</str>
+ <str name="echoParams">explicit</str>
+ <str name="echoHandler">true</str>
</lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
</requestHandler>
- <!-- Update request handler.
- Note: Since solr1.1 requestHandlers requires a valid content type header if posted in
- the body. For example, curl now requires: -H 'Content-type:text/xml; charset=utf-8'
- The response format differs from solr1.1 formatting and returns a standard error code.
- To enable solr1.1 behavior, remove the /update handler or change its path
- -->
- <requestHandler name="/update" class="solr.XmlUpdateRequestHandler"/>
- <requestHandler name="/update/javabin" class="solr.BinaryUpdateRequestHandler"/>
- <!--
- Analysis request handler. Since Solr 1.3. Use to return how a document is analyzed. Useful
- for debugging and as a token server for other types of applications.
+ <requestHandler name="/replication" class="solr.ReplicationHandler" >
+ </requestHandler>
- This is deprecated in favor of the improved DocumentAnalysisRequestHandler and FieldAnalysisRequestHandler
+ <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
- <requestHandler name="/analysis" class="solr.AnalysisRequestHandler" />
- -->
- <!--
- An analysis handler that provides a breakdown of the analysis process of provided docuemnts. This handler expects a
- (single) content stream with the following format:
+ <str name="queryAnalyzerFieldType">textSpell</str>
- <docs>
- <doc>
- <field name="id">1</field>
- <field name="name">The Name</field>
- <field name="text">The Text Value</field>
- <doc>
- <doc>...</doc>
- <doc>...</doc>
- ...
- </docs>
+ <!-- Multiple "Spell Checkers" can be declared and used by this
+ component
+ -->
- Note: Each document must contain a field which serves as the unique key. This key is used in the returned
- response to assoicate an analysis breakdown to the analyzed document.
-
- Like the FieldAnalysisRequestHandler, this handler also supports query analysis by
- sending either an "analysis.query" or "q" request paraemter that holds the query text to be analyized. It also
- supports the "analysis.showmatch" parameter which when set to true, all field tokens that match the query
- tokens will be marked as a "match".
- -->
- <requestHandler name="/analysis/document" class="solr.DocumentAnalysisRequestHandler"/>
- <!--
- RequestHandler that provides much the same functionality as analysis.jsp. Provides the ability
- to specify multiple field types and field names in the same request and outputs index-time and
- query-time analysis for each of them.
-
- Request parameters are:
- analysis.fieldname - The field name whose analyzers are to be used
- analysis.fieldtype - The field type whose analyzers are to be used
- analysis.fieldvalue - The text for index-time analysis
- q (or analysis.q) - The text for query time analysis
- analysis.showmatch (true|false) - When set to true and when query analysis is performed, the produced
- tokens of the field value analysis will be marked as "matched" for every
- token that is produces by the query analysis
- -->
- <requestHandler name="/analysis/field" class="solr.FieldAnalysisRequestHandler"/>
- <!-- CSV update handler, loaded on demand -->
- <requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy"/>
- <!--
- Admin Handlers - This will register all the standard admin RequestHandlers. Adding
- this single handler is equivalent to registering:
-
- <requestHandler name="/admin/luke" class="org.apache.solr.handler.admin.LukeRequestHandler" />
- <requestHandler name="/admin/system" class="org.apache.solr.handler.admin.SystemInfoHandler" />
- <requestHandler name="/admin/plugins" class="org.apache.solr.handler.admin.PluginInfoHandler" />
- <requestHandler name="/admin/threads" class="org.apache.solr.handler.admin.ThreadDumpHandler" />
- <requestHandler name="/admin/properties" class="org.apache.solr.handler.admin.PropertiesRequestHandler" />
- <requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
-
- If you wish to hide files under ${solr.home}/conf, explicitly register the ShowFileRequestHandler using:
- <requestHandler name="/admin/file" class="org.apache.solr.handler.admin.ShowFileRequestHandler" >
- <lst name="invariants">
- <str name="hidden">synonyms.txt</str>
- <str name="hidden">anotherfile.txt</str>
+ <!-- a spellchecker built from a field of the main index -->
+ <lst name="spellchecker">
+ <str name="name">default</str>
+ <str name="field">name</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>
- </requestHandler>
- -->
- <requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers"/>
- <!-- ping/healthcheck -->
- <requestHandler name="/admin/ping" class="PingRequestHandler">
- <lst name="defaults">
- <str name="qt">standard</str>
- <str name="q">solrpingquery</str>
- <str name="echoParams">all</str>
+
+ <!-- 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>
- </requestHandler>
- <!-- Echo the request contents back to the client -->
- <requestHandler name="/debug/dump" class="solr.DumpRequestHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <!-- for all params (including the default etc) use: 'all' -->
- <str name="echoHandler">true</str>
- </lst>
- </requestHandler>
- <highlighting>
- <!-- Configure the standard fragmenter -->
- <!-- This could most likely be commented out in the "default" case -->
- <fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
- <lst name="defaults">
- <int name="hl.fragsize">100</int>
- </lst>
- </fragmenter>
- <!-- A regular-expression-based fragmenter (f.i., for sentence extraction) -->
- <fragmenter name="regex" class="org.apache.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" class="org.apache.solr.highlight.HtmlFormatter" default="true">
- <lst name="defaults">
- <str name="hl.simple.pre"><![CDATA[<em>]]></str>
- <str name="hl.simple.post"><![CDATA[</em>]]></str>
- </lst>
- </formatter>
- </highlighting>
- <!-- 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.
-
- You have to link the chain to an update handler above to use it ie:
- <requestHandler name="/update "class="solr.XmlUpdateRequestHandler">
- <lst name="defaults">
- <str name="update.processor">dedupe</str>
- </lst>
- </requestHandler>
- -->
- <!--
- <updateRequestProcessorChain name="dedupe">
- <processor class="org.apache.solr.update.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">org.apache.solr.update.processor.Lookup3Signature</str>
- </processor>
- <processor class="solr.LogUpdateProcessorFactory" />
- <processor class="solr.RunUpdateProcessorFactory" />
- </updateRequestProcessorChain>
- -->
- <!-- queryResponseWriter plugins... query 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. XMLResponseWriter will be used if nothing is specified here.
- The json, python, and ruby writers are also available by default.
+ </searchComponent>
- <queryResponseWriter name="xml" class="org.apache.solr.request.XMLResponseWriter" default="true"/>
- <queryResponseWriter name="json" class="org.apache.solr.request.JSONResponseWriter"/>
- <queryResponseWriter name="python" class="org.apache.solr.request.PythonResponseWriter"/>
- <queryResponseWriter name="ruby" class="org.apache.solr.request.RubyResponseWriter"/>
- <queryResponseWriter name="php" class="org.apache.solr.request.PHPResponseWriter"/>
- <queryResponseWriter name="phps" class="org.apache.solr.request.PHPSerializedResponseWriter"/>
+ <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
- <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
- -->
- <!-- 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="org.apache.solr.request.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
- </queryResponseWriter>
- <!-- example of registering a query parser
- <queryParser name="lucene" class="org.apache.solr.search.LuceneQParserPlugin"/>
- -->
- <!-- example of registering a custom function parser
- <valueSourceParser name="myfunc" class="com.mycompany.MyValueSourceParser" />
- -->
- <!-- config for the admin interface -->
- <admin>
- <defaultQuery>solr</defaultQuery>
- <!-- configure a healthcheck file for servers behind a loadbalancer
- <healthcheck type="file">server-enabled</healthcheck>
- -->
- </admin>
+ <searchComponent name="terms" class="solr.TermsComponent"/>
+
+ <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>
+
<requestHandler class="solr.MoreLikeThisHandler" name="/mlt">
<lst name="defaults">
<str name="mlt.mintf">1</str>
<str name="mlt.mindf">2</str>
</lst>
</requestHandler>
+
+ <!-- Admin Handlers - This will register all the standard admin RequestHandlers. -->
+ <requestHandler name="/admin/" class="solr.admin.AdminHandlers" />
</config>