1 <?xml version="1.0" encoding="UTF-8" ?>
3 Licensed to the Apache Software Foundation (ASF) under one or more
4 contributor license agreements. See the NOTICE file distributed with
5 this work for additional information regarding copyright ownership.
6 The ASF licenses this file to You under the Apache License, Version 2.0
7 (the "License"); you may not use this file except in compliance with
8 the License. You may obtain a copy of the License at
10 http://www.apache.org/licenses/LICENSE-2.0
12 Unless required by applicable law or agreed to in writing, software
13 distributed under the License is distributed on an "AS IS" BASIS,
14 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15 See the License for the specific language governing permissions and
16 limitations under the License.
20 For more details about configurations options that may appear in
21 this file, see http://wiki.apache.org/solr/SolrConfigXml.
24 <!-- In all configuration below, a prefix of "solr." for class names
25 is an alias that causes solr to search appropriate packages,
26 including org.apache.solr.(search|update|request|core|analysis)
28 You may also specify a fully qualified Java classname if you
29 have your own custom plugins.
32 <!-- Set this to 'false' if you want solr to continue working after
33 it has encountered an severe configuration error. In a
34 production environment, you may want solr to keep working even
35 if one handler is mis-configured.
37 You may also set this to false using by setting the system
40 -Dsolr.abortOnConfigurationError=false
42 <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
44 <!-- Controls what version of Lucene various components of Solr
45 adhere to. Generally, you want to use the latest version to
46 get all bug fixes and improvements. It is highly recommended
47 that you fully re-index after changing this setting as it can
48 affect both how text is indexed and queried.
50 <luceneMatchVersion>LUCENE_43</luceneMatchVersion>
52 <!-- lib directives can be used to instruct Solr to load an Jars
53 identified and use them to resolve any "plugins" specified in
54 your solrconfig.xml or schema.xml (ie: Analyzers, Request
57 All directories and paths are resolved relative to the
60 If a "./lib" directory exists in your instanceDir, all files
61 found in it are included as if you had used the following
66 <!-- A dir option by itself adds any files found in the directory to
67 the classpath, this is useful for including all jars in a
70 <lib dir="../../contrib/extraction/lib" />
71 <!-- When a regex is specified in addition to a directory, only the
72 files in that directory which completely match the regex
73 (anchored on both ends) will be included.
75 <lib dir="../../dist/" regex="apache-solr-cell-\d.*\.jar" />
76 <lib dir="../../dist/" regex="apache-solr-clustering-\d.*\.jar" />
77 <lib dir="../../dist/" regex="apache-solr-dataimporthandler-\d.*\.jar" />
79 <!-- If a dir option (with or without a regex) is used and nothing
80 is found that matches, it will be ignored
82 <lib dir="../../contrib/clustering/lib/" />
83 <lib dir="/total/crap/dir/ignored" />
84 <!-- an exact path can be used to specify a specific file. This
85 will cause a serious error to be logged if it can't be loaded.
88 <lib path="../a-jar-that-does-not-exist.jar" />
93 Used to specify an alternate directory to hold all index data
94 other than the default ./data under the Solr home. If
95 replication is in use, this should match the replication
98 <dataDir>${solr.data.dir:/home/dennis/proj/lui-solr/data}</dataDir>
100 <!-- The DirectoryFactory to use for indexes.
102 solr.StandardDirectoryFactory, the default, is filesystem
103 based. solr.RAMDirectoryFactory is memory based, not
104 persistent, and doesn't work with replication.
106 <directoryFactory name="DirectoryFactory"
107 class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
112 Values here affect all index writers and act as a default
115 WARNING: See also the <mainIndex> section below for parameters
116 that overfor Solr's main Lucene index.
120 <useCompoundFile>false</useCompoundFile>
122 <mergeFactor>10</mergeFactor>
123 <!-- Sets the amount of RAM that may be used by Lucene indexing
124 for buffering added documents and deletions before they are
125 flushed to the Directory. -->
126 <ramBufferSizeMB>32</ramBufferSizeMB>
127 <!-- If both ramBufferSizeMB and maxBufferedDocs is set, then
128 Lucene will flush based on whichever limit is hit first.
130 <!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
132 <maxFieldLength>10000</maxFieldLength>
133 <writeLockTimeout>1000</writeLockTimeout>
134 <commitLockTimeout>10000</commitLockTimeout>
136 <!-- Expert: Merge Policy
138 The Merge Policy in Lucene controls how merging is handled by
139 Lucene. The default in Solr 3.3 is TieredMergePolicy.
141 The default in 2.3 was the LogByteSizeMergePolicy,
142 previous versions used LogDocMergePolicy.
144 LogByteSizeMergePolicy chooses segments to merge based on
145 their size. The Lucene 2.2 default, LogDocMergePolicy chose
146 when to merge based on number of documents
148 Other implementations of MergePolicy must have a no-argument
152 <mergePolicy class="org.apache.lucene.index.TieredMergePolicy"/>
155 <!-- Expert: Merge Scheduler
157 The Merge Scheduler in Lucene controls how merges are
158 performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
159 can perform merges in the background using separate threads.
160 The SerialMergeScheduler (Lucene 2.2 default) does not.
163 <mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
168 This option specifies which Lucene LockFactory implementation
171 single = SingleInstanceLockFactory - suggested for a
172 read-only index or when there is no possibility of
173 another process trying to modify the index.
174 native = NativeFSLockFactory - uses OS native file locking.
175 Do not use when multiple solr webapps in the same
176 JVM are attempting to share a single index.
177 simple = SimpleFSLockFactory - uses a plain file for locking
179 (For backwards compatibility with Solr 1.2, 'simple' is the
180 default if not specified.)
182 More details on the nuances of each LockFactory...
183 http://wiki.apache.org/lucene-java/AvailableLockFactories
185 <lockType>native</lockType>
187 <!-- Expert: Controls how often Lucene loads terms into memory
188 Default is 128 and is likely good for most everyone.
190 <!-- <termIndexInterval>256</termIndexInterval> -->
195 Values here override the values in the <indexDefaults> section
196 for the main on disk index.
200 <useCompoundFile>false</useCompoundFile>
201 <ramBufferSizeMB>32</ramBufferSizeMB>
202 <mergeFactor>10</mergeFactor>
204 <!-- Unlock On Startup
206 If true, unlock any held write or commit locks on startup.
207 This defeats the locking mechanism that allows multiple
208 processes to safely access a lucene index, and should be used
211 This is not needed if lock type is 'none' or 'single'
213 <unlockOnStartup>false</unlockOnStartup>
215 <!-- If true, IndexReaders will be reopened (often more efficient)
216 instead of closed and then opened.
218 <reopenReaders>true</reopenReaders>
220 <!-- Commit Deletion Policy
222 Custom deletion policies can specified here. The class must
223 implement org.apache.lucene.index.IndexDeletionPolicy.
225 http://lucene.apache.org/java/2_9_1/api/all/org/apache/lucene/index/IndexDeletionPolicy.html
227 The standard Solr IndexDeletionPolicy implementation supports
228 deleting index commit points on number of commits, age of
229 commit point and optimized status.
231 The latest commit point should always be preserved regardless
234 <deletionPolicy class="solr.SolrDeletionPolicy">
235 <!-- The number of commit points to be kept -->
236 <str name="maxCommitsToKeep">1</str>
237 <!-- The number of optimized commit points to be kept -->
238 <str name="maxOptimizedCommitsToKeep">0</str>
240 Delete all commit points once they have reached the given age.
241 Supports DateMathParser syntax e.g.
244 <str name="maxCommitAge">30MINUTES</str>
245 <str name="maxCommitAge">1DAY</str>
249 <!-- Lucene Infostream
251 To aid in advanced debugging, Lucene provides an "InfoStream"
252 of detailed information when indexing.
254 Setting The value to true will instruct the underlying Lucene
255 IndexWriter to write its debugging info the specified file
257 <infoStream file="INFOSTREAM.txt">false</infoStream>
263 This example enables JMX if and only if an existing MBeanServer
264 is found, use this if you want to configure JMX through JVM
265 parameters. Remove this to disable exposing Solr configuration
266 and statistics to JMX.
268 For more details see http://wiki.apache.org/solr/SolrJmx
271 <!-- If you want to connect to a particular server, specify the
274 <!-- <jmx agentId="myAgent" /> -->
275 <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
276 <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
279 <!-- The default high-performance update handler -->
280 <updateHandler class="solr.DirectUpdateHandler2">
284 Perform a <commit/> automatically under certain conditions.
285 Instead of enabling autoCommit, consider using "commitWithin"
286 when adding documents.
288 http://wiki.apache.org/solr/UpdateXmlMessages
290 maxDocs - Maximum number of documents to add since the last
291 commit before automatically triggering a new commit.
293 maxTime - Maximum amount of time that is allowed to pass
294 since a document was added before automaticly
295 triggering a new commit.
299 <maxDocs>10000</maxDocs>
300 <maxTime>1000</maxTime>
304 <!-- Update Related Event Listeners
306 Various IndexWriter related events can trigger Listeners to
309 postCommit - fired after every commit or optimize command
310 postOptimize - fired after every optimize command
312 <!-- The RunExecutableListener executes an external command from a
313 hook such as postCommit or postOptimize.
315 exe - the name of the executable to run
316 dir - dir to use as the current working directory. (default=".")
317 wait - the calling thread waits until the executable returns.
319 args - the arguments to pass to the program. (default is none)
320 env - environment variables to set. (default is none)
322 <!-- This example shows how RunExecutableListener could be used
323 with the script based replication...
324 http://wiki.apache.org/solr/CollectionDistribution
327 <listener event="postCommit" class="solr.RunExecutableListener">
328 <str name="exe">solr/bin/snapshooter</str>
329 <str name="dir">.</str>
330 <bool name="wait">true</bool>
331 <arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
332 <arr name="env"> <str>MYVAR=val1</str> </arr>
337 <!-- IndexReaderFactory
339 Use the following format to specify a custom IndexReaderFactory,
340 which allows for alternate IndexReader implementations.
342 ** Experimental Feature **
344 Please note - Using a custom IndexReaderFactory may prevent
345 certain other features from working. The API to
346 IndexReaderFactory may change without warning or may even be
347 removed from future releases if the problems cannot be
351 ** Features that may not work with custom IndexReaderFactory **
353 The ReplicationHandler assumes a disk-resident index. Using a
354 custom IndexReader implementation may cause incompatibility
355 with ReplicationHandler and may cause replication to not work
356 correctly. See SOLR-1366 for details.
360 <indexReaderFactory name="IndexReaderFactory" class="package.class">
361 <str name="someArg">Some Value</str>
362 </indexReaderFactory >
364 <!-- By explicitly declaring the Factory, the termIndexDivisor can
368 <indexReaderFactory name="IndexReaderFactory"
369 class="solr.StandardIndexReaderFactory">
370 <int name="setTermIndexDivisor">12</int>
371 </indexReaderFactory >
376 <!-- Max Boolean Clauses
378 Maximum number of clauses in each BooleanQuery, an exception
379 is thrown if exceeded.
383 This option actually modifies a global Lucene property that
384 will affect all SolrCores. If multiple solrconfig.xml files
385 disagree on this property, the value at any given moment will
386 be based on the last SolrCore to be initialized.
389 <maxBooleanClauses>1024</maxBooleanClauses>
392 <!-- Solr Internal Query Caches
394 There are two implementations of cache available for Solr,
395 LRUCache, based on a synchronized LinkedHashMap, and
396 FastLRUCache, based on a ConcurrentHashMap.
398 FastLRUCache has faster gets and slower puts in single
399 threaded operation and thus is generally faster than LRUCache
400 when the hit ratio of the cache is high (> 75%), and may be
401 faster under other scenarios on multi-cpu systems.
406 Cache used by SolrIndexSearcher for filters (DocSets),
407 unordered sets of *all* documents that match a query. When a
408 new searcher is opened, its caches may be prepopulated or
409 "autowarmed" using data from caches in the old searcher.
410 autowarmCount is the number of items to prepopulate. For
411 LRUCache, the autowarmed items will be the most recently
415 class - the SolrCache implementation LRUCache or
416 (LRUCache or FastLRUCache)
417 size - the maximum number of entries in the cache
418 initialSize - the initial capacity (number of entries) of
419 the cache. (see java.util.HashMap)
420 autowarmCount - the number of entries to prepopulate from
423 <filterCache class="solr.FastLRUCache"
428 <!-- Query Result Cache
430 Caches results of searches - ordered lists of document ids
431 (DocList) based on a query, a sort, and the range of documents requested.
433 <queryResultCache class="solr.LRUCache"
440 Caches Lucene Document objects (the stored fields for each
441 document). Since Lucene internal document ids are transient,
442 this cache will not be autowarmed.
444 <documentCache class="solr.LRUCache"
449 <!-- Field Value Cache
451 Cache used to hold field values that are quickly accessible
452 by document id. The fieldValueCache is created by default
453 even if not configured here.
456 <fieldValueCache class="solr.FastLRUCache"
464 Example of a generic cache. These caches may be accessed by
465 name through SolrIndexSearcher.getCache(),cacheLookup(), and
466 cacheInsert(). The purpose is to enable easy caching of
467 user/application level data. The regenerator argument should
468 be specified as an implementation of solr.CacheRegenerator
469 if autowarming is desired.
472 <cache name="myUserCache"
473 class="solr.LRUCache"
477 regenerator="com.mycompany.MyRegenerator"
482 <!-- Lazy Field Loading
484 If true, stored fields that are not requested will be loaded
485 lazily. This can result in a significant speed improvement
486 if the usual case is to not load all stored fields,
487 especially if the skipped fields are large compressed text
490 <enableLazyFieldLoading>true</enableLazyFieldLoading>
492 <!-- Use Filter For Sorted Query
494 A possible optimization that attempts to use a filter to
495 satisfy a search. If the requested sort does not include
496 score, then the filterCache will be checked for a filter
497 matching the query. If found, the filter will be used as the
498 source of document ids, and then the sort will be applied to
501 For most situations, this will not be useful unless you
502 frequently get the same search repeatedly with different sort
503 options, and none of them ever use "score"
506 <useFilterForSortedQuery>true</useFilterForSortedQuery>
509 <!-- Result Window Size
511 An optimization for use with the queryResultCache. When a search
512 is requested, a superset of the requested number of document ids
513 are collected. For example, if a search for a particular query
514 requests matching documents 10 through 19, and queryWindowSize is 50,
515 then documents 0 through 49 will be collected and cached. Any further
516 requests in that range can be satisfied via the cache.
518 <queryResultWindowSize>20</queryResultWindowSize>
520 <!-- Maximum number of documents to cache for any entry in the
523 <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
525 <!-- Query Related Event Listeners
527 Various IndexSearcher related events can trigger Listeners to
530 newSearcher - fired whenever a new searcher is being prepared
531 and there is a current searcher handling requests (aka
532 registered). It can be used to prime certain caches to
533 prevent long request times for certain requests.
535 firstSearcher - fired whenever a new searcher is being
536 prepared but there is no current registered searcher to handle
537 requests or to gain autowarming data from.
541 <!-- QuerySenderListener takes an array of NamedList and executes a
542 local query request for each NamedList in sequence.
544 <listener event="newSearcher" class="solr.QuerySenderListener">
547 <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
548 <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
552 <listener event="firstSearcher" class="solr.QuerySenderListener">
555 <str name="q">static firstSearcher warming in solrconfig.xml</str>
560 <!-- Use Cold Searcher
562 If a search request comes in and there is no current
563 registered searcher, then immediately register the still
564 warming searcher and use it. If "false" then all requests
565 will block until the first searcher is done warming.
567 <useColdSearcher>false</useColdSearcher>
569 <!-- Max Warming Searchers
571 Maximum number of searchers that may be warming in the
572 background concurrently. An error is returned if this limit
575 Recommend values of 1-2 for read-only slaves, higher for
576 masters w/o cache warming.
578 <maxWarmingSearchers>10</maxWarmingSearchers>
583 <!-- Request Dispatcher
585 This section contains instructions for how the SolrDispatchFilter
586 should behave when processing requests for this SolrCore.
588 handleSelect affects the behavior of requests such as /select?qt=XXX
590 handleSelect="true" will cause the SolrDispatchFilter to process
591 the request and will result in consistent error handling and
592 formatting for all types of requests.
594 handleSelect="false" will cause the SolrDispatchFilter to
595 ignore "/select" requests and fallback to using the legacy
596 SolrServlet and it's Solr 1.1 style error formatting
598 <requestDispatcher handleSelect="true" >
601 These settings indicate how Solr Requests may be parsed, and
602 what restrictions may be placed on the ContentStreams from
605 enableRemoteStreaming - enables use of the stream.file
606 and stream.url parameters for specifying remote streams.
608 multipartUploadLimitInKB - specifies the max size of
609 Multipart File Uploads that Solr will allow in a Request.
612 The settings below authorize Solr to fetch remote files, You
613 should make sure your system has some authentication before
614 using enableRemoteStreaming="true"
617 <requestParsers enableRemoteStreaming="true"
618 multipartUploadLimitInKB="2048000" />
622 Set HTTP caching related parameters (for proxy caches and clients).
624 The options below instruct Solr not to output any HTTP Caching
627 <httpCaching never304="true" />
628 <!-- If you include a <cacheControl> directive, it will be used to
629 generate a Cache-Control header (as well as an Expires header
630 if the value contains "max-age=")
632 By default, no Cache-Control header is generated.
634 You can use the <cacheControl> option even if you have set
638 <httpCaching never304="true" >
639 <cacheControl>max-age=30, public</cacheControl>
642 <!-- To enable Solr to respond with automatically generated HTTP
643 Caching headers, and to response to Cache Validation requests
644 correctly, set the value of never304="false"
646 This will cause Solr to generate Last-Modified and ETag
647 headers based on the properties of the Index.
649 The following options can also be specified to affect the
650 values of these headers...
652 lastModFrom - the default value is "openTime" which means the
653 Last-Modified value (and validation against If-Modified-Since
654 requests) will all be relative to when the current Searcher
655 was opened. You can change it to lastModFrom="dirLastMod" if
656 you want the value to exactly correspond to when the physical
657 index was last modified.
659 etagSeed="..." is an option you can change to force the ETag
660 header (and validation against If-None-Match requests) to be
661 different even if the index has not changed (ie: when making
662 significant changes to your config file)
664 (lastModifiedFrom and etagSeed are both ignored if you use
665 the never304="true" option)
668 <httpCaching lastModifiedFrom="openTime"
670 <cacheControl>max-age=30, public</cacheControl>
675 <!-- Request Handlers
677 http://wiki.apache.org/solr/SolrRequestHandler
679 incoming queries will be dispatched to the correct handler
680 based on the path or the qt (query type) param.
682 Names starting with a '/' are accessed with the a path equal to
683 the registered name. Names without a leading '/' are accessed
684 with: http://host/app/[core/]select?qt=name
686 If a /select request is processed with out a qt param
687 specified, the requestHandler that declares default="true" will
690 If a Request Handler is declared with startup="lazy", then it will
691 not be initialized until the first request that uses it.
696 http://wiki.apache.org/solr/SearchHandler
698 For processing Search Queries, the primary Request Handler
699 provided with Solr is "SearchHandler" It delegates to a sequent
700 of SearchComponents (see below) and supports distributed
701 queries across multiple shards
703 <requestHandler name="search" class="solr.SearchHandler" default="true">
704 <lst name="defaults">
705 <str name="echoParams">explicit</str>
706 <str name="spellcheck.dictionary">text</str>
707 <!-- omp = Only More Popular -->
708 <str name="spellcheck.onlyMorePopular">false</str>
709 <!-- exr = Extended Results -->
710 <str name="spellcheck.extendedResults">true</str>
711 <!-- The number of suggestions to return -->
712 <str name="spellcheck.count">5</str>
713 <str name="spellcheck">true</str>
715 <arr name="last-components">
716 <str>spellcheck</str>
720 <!-- A Robust Example
722 This example SearchHandler declaration shows off usage of the
723 SearchHandler with many defaults declared
725 Note that multiple instances of the same Request Handler
726 (SearchHandler) can be registered multiple times with different
727 names (and different init parameters)
729 <requestHandler name="/browse" class="solr.SearchHandler">
730 <lst name="defaults">
731 <str name="echoParams">explicit</str>
733 <!-- VelocityResponseWriter settings -->
734 <str name="wt">velocity</str>
736 <str name="v.template">browse</str>
737 <str name="v.layout">layout</str>
738 <str name="title">Solritas</str>
740 <str name="defType">edismax</str>
741 <str name="q.alt">*:*</str>
742 <str name="rows">10</str>
743 <str name="fl">*,score</str>
745 text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
747 <str name="mlt.fl">text,features,name,sku,id,manu,cat</str>
748 <int name="mlt.count">3</int>
751 text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
754 <str name="facet">on</str>
755 <str name="facet.field">cat</str>
756 <str name="facet.field">manu_exact</str>
757 <str name="facet.query">ipod</str>
758 <str name="facet.query">GB</str>
759 <str name="facet.mincount">1</str>
760 <str name="facet.pivot">cat,inStock</str>
761 <str name="facet.range">price</str>
762 <int name="f.price.facet.range.start">0</int>
763 <int name="f.price.facet.range.end">600</int>
764 <int name="f.price.facet.range.gap">50</int>
765 <str name="f.price.facet.range.other">after</str>
766 <str name="facet.range">manufacturedate_dt</str>
767 <str name="f.manufacturedate_dt.facet.range.start">NOW/YEAR-10YEARS</str>
768 <str name="f.manufacturedate_dt.facet.range.end">NOW</str>
769 <str name="f.manufacturedate_dt.facet.range.gap">+1YEAR</str>
770 <str name="f.manufacturedate_dt.facet.range.other">before</str>
771 <str name="f.manufacturedate_dt.facet.range.other">after</str>
774 <!-- Highlighting defaults -->
775 <str name="hl">on</str>
776 <str name="hl.fl">text features name</str>
777 <str name="f.name.hl.fragsize">0</str>
778 <str name="f.name.hl.alternateField">name</str>
780 <arr name="last-components">
781 <str>spellcheck</str>
784 <str name="url-scheme">httpx</str>
788 <!-- XML Update Request Handler.
790 http://wiki.apache.org/solr/UpdateXmlMessages
792 The canonical Request Handler for Modifying the Index through
793 commands specified using XML.
795 Note: Since solr1.1 requestHandlers requires a valid content
796 type header if posted in the body. For example, curl now
797 requires: -H 'Content-type:text/xml; charset=utf-8'
799 <requestHandler name="/update"
800 class="solr.XmlUpdateRequestHandler">
801 <!-- See below for information on defining
802 updateRequestProcessorChains that can be used by name
803 on each Update Request
806 <lst name="defaults">
807 <str name="update.chain">dedupe</str>
811 <!-- Binary Update Request Handler
812 http://wiki.apache.org/solr/javabin
814 <requestHandler name="/update/javabin"
815 class="solr.BinaryUpdateRequestHandler" />
817 <!-- CSV Update Request Handler
818 http://wiki.apache.org/solr/UpdateCSV
820 <requestHandler name="/update/csv"
821 class="solr.CSVRequestHandler"
824 <!-- JSON Update Request Handler
825 http://wiki.apache.org/solr/UpdateJSON
827 <requestHandler name="/update/json"
828 class="solr.JsonUpdateRequestHandler"
831 <!-- Solr Cell Update Request Handler
833 http://wiki.apache.org/solr/ExtractingRequestHandler
836 <requestHandler name="/update/extract"
838 class="solr.extraction.ExtractingRequestHandler" >
839 <lst name="defaults">
840 <!-- All the main content goes into "text"... if you need to return
841 the extracted text or do highlighting, use a stored field. -->
842 <str name="fmap.content">text</str>
843 <str name="lowernames">true</str>
844 <str name="uprefix">ignored_</str>
846 <!-- capture link hrefs but ignore div attributes -->
847 <str name="captureAttr">true</str>
848 <str name="fmap.a">links</str>
849 <str name="fmap.div">ignored_</str>
853 <!-- Field Analysis Request Handler
855 RequestHandler that provides much the same functionality as
856 analysis.jsp. Provides the ability to specify multiple field
857 types and field names in the same request and outputs
858 index-time and query-time analysis for each of them.
860 Request parameters are:
861 analysis.fieldname - field name whose analyzers are to be used
863 analysis.fieldtype - field type whose analyzers are to be used
864 analysis.fieldvalue - text for index-time analysis
865 q (or analysis.q) - text for query time analysis
866 analysis.showmatch (true|false) - When set to true and when
867 query analysis is performed, the produced tokens of the
868 field value analysis will be marked as "matched" for every
869 token that is produces by the query analysis
871 <requestHandler name="/analysis/field"
873 class="solr.FieldAnalysisRequestHandler" />
876 <!-- Document Analysis Handler
878 http://wiki.apache.org/solr/AnalysisRequestHandler
880 An analysis handler that provides a breakdown of the analysis
881 process of provided docuemnts. This handler expects a (single)
882 content stream with the following format:
886 <field name="id">1</field>
887 <field name="name">The Name</field>
888 <field name="text">The Text Value</field>
895 Note: Each document must contain a field which serves as the
896 unique key. This key is used in the returned response to associate
897 an analysis breakdown to the analyzed document.
899 Like the FieldAnalysisRequestHandler, this handler also supports
900 query analysis by sending either an "analysis.query" or "q"
901 request parameter that holds the query text to be analyzed. It
902 also supports the "analysis.showmatch" parameter which when set to
903 true, all field tokens that match the query tokens will be marked
906 <requestHandler name="/analysis/document"
907 class="solr.DocumentAnalysisRequestHandler"
912 Admin Handlers - This will register all the standard admin
915 <requestHandler name="/admin/"
916 class="solr.admin.AdminHandlers" />
917 <!-- This single handler is equivalent to the following... -->
919 <requestHandler name="/admin/luke" class="solr.admin.LukeRequestHandler" />
920 <requestHandler name="/admin/system" class="solr.admin.SystemInfoHandler" />
921 <requestHandler name="/admin/plugins" class="solr.admin.PluginInfoHandler" />
922 <requestHandler name="/admin/threads" class="solr.admin.ThreadDumpHandler" />
923 <requestHandler name="/admin/properties" class="solr.admin.PropertiesRequestHandler" />
924 <requestHandler name="/admin/file" class="solr.admin.ShowFileRequestHandler" >
926 <!-- If you wish to hide files under ${solr.home}/conf, explicitly
927 register the ShowFileRequestHandler using:
930 <requestHandler name="/admin/file"
931 class="solr.admin.ShowFileRequestHandler" >
932 <lst name="invariants">
933 <str name="hidden">synonyms.txt</str>
934 <str name="hidden">anotherfile.txt</str>
939 <!-- ping/healthcheck -->
940 <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
941 <lst name="defaults">
942 <str name="qt">search</str>
943 <str name="q">solrpingquery</str>
944 <str name="echoParams">all</str>
948 <!-- Echo the request contents back to the client -->
949 <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
950 <lst name="defaults">
951 <str name="echoParams">explicit</str>
952 <str name="echoHandler">true</str>
956 <!-- Solr Replication
958 The SolrReplicationHandler supports replicating indexes from a
959 "master" used for indexing and "salves" used for queries.
961 http://wiki.apache.org/solr/SolrReplication
963 In the example below, remove the <lst name="master"> section if
964 this is just a slave and remove the <lst name="slave"> section
965 if this is just a master.
968 <requestHandler name="/replication" class="solr.ReplicationHandler" >
970 <str name="replicateAfter">commit</str>
971 <str name="replicateAfter">startup</str>
972 <str name="confFiles">schema.xml,stopwords.txt</str>
975 <str name="masterUrl">http://localhost:8983/solr/replication</str>
976 <str name="pollInterval">00:00:60</str>
981 <!-- Search Components
983 Search components are registered to SolrCore and used by
984 instances of SearchHandler (which can access them by name)
986 By default, the following components are available:
988 <searchComponent name="query" class="solr.QueryComponent" />
989 <searchComponent name="facet" class="solr.FacetComponent" />
990 <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
991 <searchComponent name="highlight" class="solr.HighlightComponent" />
992 <searchComponent name="stats" class="solr.StatsComponent" />
993 <searchComponent name="debug" class="solr.DebugComponent" />
995 Default configuration in a requestHandler would look like:
997 <arr name="components">
1001 <str>highlight</str>
1006 If you register a searchComponent to one of the standard names,
1007 that will be used instead of the default.
1009 To insert components before or after the 'standard' components, use:
1011 <arr name="first-components">
1012 <str>myFirstComponentName</str>
1015 <arr name="last-components">
1016 <str>myLastComponentName</str>
1019 NOTE: The component registered with the name "debug" will
1020 always be executed after the "last-components"
1026 The spell check component can return a list of alternative spelling
1029 http://wiki.apache.org/solr/SpellCheckComponent
1031 <searchComponent name="spellcheck" class="solr.SpellCheckComponent">
1033 <str name="queryAnalyzerFieldType">text</str>
1035 <lst name="spellchecker">
1036 <str name="classname">solr.IndexBasedSpellChecker</str>
1037 <str name="name">text</str>
1038 <str name="field">text</str>
1039 <str name="buildOnOptimize">true</str>
1040 <str name="spellcheckIndexDir">./spellchecker</str>
1041 <!-- uncomment this to require terms to occur in 1% of the documents in order to be included in the dictionary
1042 <float name="thresholdTokenFrequency">.01</float>
1047 <!-- a spellchecker that uses a different distance measure -->
1049 <lst name="spellchecker">
1050 <str name="name">jarowinkler</str>
1051 <str name="field">spell</str>
1052 <str name="distanceMeasure">
1053 org.apache.lucene.search.spell.JaroWinklerDistance
1055 <str name="spellcheckIndexDir">spellcheckerJaro</str>
1059 <!-- a spellchecker that use an alternate comparator
1061 comparatorClass be one of:
1063 2. freq (Frequency first, then score)
1064 3. A fully qualified class name
1067 <lst name="spellchecker">
1068 <str name="name">freq</str>
1069 <str name="field">lowerfilt</str>
1070 <str name="spellcheckIndexDir">spellcheckerFreq</str>
1071 <str name="comparatorClass">freq</str>
1072 <str name="buildOnCommit">true</str>
1075 <!-- A spellchecker that reads the list of words from a file -->
1077 <lst name="spellchecker">
1078 <str name="classname">solr.FileBasedSpellChecker</str>
1079 <str name="name">file</str>
1080 <str name="sourceLocation">spellings.txt</str>
1081 <str name="characterEncoding">UTF-8</str>
1082 <str name="spellcheckIndexDir">spellcheckerFile</str>
1087 <!-- A request handler for demonstrating the spellcheck component.
1089 NOTE: This is purely as an example. The whole purpose of the
1090 SpellCheckComponent is to hook it into the request handler that
1091 handles your normal user queries so that a separate request is
1092 not needed to get suggestions.
1094 IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
1095 NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
1097 See http://wiki.apache.org/solr/SpellCheckComponent for details
1098 on the request parameters.
1100 <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
1101 <lst name="defaults">
1102 <str name="spellcheck.onlyMorePopular">false</str>
1103 <str name="spellcheck.extendedResults">false</str>
1104 <str name="spellcheck.count">1</str>
1106 <arr name="last-components">
1107 <str>spellcheck</str>
1111 <!-- Term Vector Component
1113 http://wiki.apache.org/solr/TermVectorComponent
1115 <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
1117 <!-- A request handler for demonstrating the term vector component
1119 This is purely as an example.
1121 In reality you will likely want to add the component to your
1122 already specified request handlers.
1124 <requestHandler name="tvrh" class="solr.SearchHandler" startup="lazy">
1125 <lst name="defaults">
1126 <bool name="tv">true</bool>
1128 <arr name="last-components">
1129 <str>tvComponent</str>
1133 <!-- Clustering Component
1135 http://wiki.apache.org/solr/ClusteringComponent
1137 This relies on third party jars which are notincluded in the
1138 release. To use this component (and the "/clustering" handler)
1139 Those jars will need to be downloaded, and you'll need to set
1140 the solr.cluster.enabled system property when running solr...
1142 java -Dsolr.clustering.enabled=true -jar start.jar
1144 <searchComponent name="clustering"
1145 enable="${solr.clustering.enabled:false}"
1146 class="solr.clustering.ClusteringComponent" >
1147 <!-- Declare an engine -->
1149 <!-- The name, only one can be named "default" -->
1150 <str name="name">default</str>
1152 <!-- Class name of Carrot2 clustering algorithm.
1154 Currently available algorithms are:
1156 * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
1157 * org.carrot2.clustering.stc.STCClusteringAlgorithm
1158 * org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm
1160 See http://project.carrot2.org/algorithms.html for the
1161 algorithm's characteristics.
1163 <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
1165 <!-- Overriding values for Carrot2 default algorithm attributes.
1167 For a description of all available attributes, see:
1168 http://download.carrot2.org/stable/manual/#chapter.components.
1169 Use attribute key as name attribute of str elements
1170 below. These can be further overridden for individual
1171 requests by specifying attribute key as request parameter
1172 name and attribute value as parameter value.
1174 <str name="LingoClusteringAlgorithm.desiredClusterCountBase">20</str>
1176 <!-- Location of Carrot2 lexical resources.
1178 A directory from which to load Carrot2-specific stop words
1179 and stop labels. Absolute or relative to Solr config directory.
1180 If a specific resource (e.g. stopwords.en) is present in the
1181 specified dir, it will completely override the corresponding
1182 default one that ships with Carrot2.
1184 For an overview of Carrot2 lexical resources, see:
1185 http://download.carrot2.org/head/manual/#chapter.lexical-resources
1187 <str name="carrot.lexicalResourcesDir">clustering/carrot2</str>
1189 <!-- The language to assume for the documents.
1191 For a list of allowed values, see:
1192 http://download.carrot2.org/stable/manual/#section.attribute.lingo.MultilingualClustering.defaultLanguage
1194 <str name="MultilingualClustering.defaultLanguage">ENGLISH</str>
1197 <str name="name">stc</str>
1198 <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
1202 <!-- A request handler for demonstrating the clustering component
1204 This is purely as an example.
1206 In reality you will likely want to add the component to your
1207 already specified request handlers.
1209 <requestHandler name="/clustering"
1211 enable="${solr.clustering.enabled:false}"
1212 class="solr.SearchHandler">
1213 <lst name="defaults">
1214 <bool name="clustering">true</bool>
1215 <str name="clustering.engine">default</str>
1216 <bool name="clustering.results">true</bool>
1217 <!-- The title field -->
1218 <str name="carrot.title">name</str>
1219 <str name="carrot.url">id</str>
1220 <!-- The field to cluster on -->
1221 <str name="carrot.snippet">features</str>
1222 <!-- produce summaries -->
1223 <bool name="carrot.produceSummary">true</bool>
1224 <!-- the maximum number of labels per cluster -->
1225 <!--<int name="carrot.numDescriptions">5</int>-->
1226 <!-- produce sub clusters -->
1227 <bool name="carrot.outputSubClusters">false</bool>
1229 <str name="defType">edismax</str>
1231 text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
1233 <str name="q.alt">*:*</str>
1234 <str name="rows">10</str>
1235 <str name="fl">*,score</str>
1237 <arr name="last-components">
1238 <str>clustering</str>
1242 <!-- Terms Component
1244 http://wiki.apache.org/solr/TermsComponent
1246 A component to return terms and document frequency of those
1249 <searchComponent name="terms" class="solr.TermsComponent"/>
1251 <!-- A request handler for demonstrating the terms component -->
1252 <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
1253 <lst name="defaults">
1254 <bool name="terms">true</bool>
1256 <arr name="components">
1262 <!-- Query Elevation Component
1264 http://wiki.apache.org/solr/QueryElevationComponent
1266 a search component that enables you to configure the top
1267 results for a given query regardless of the normal lucene
1270 <searchComponent name="elevator" class="solr.QueryElevationComponent" >
1271 <!-- pick a fieldType to analyze queries -->
1272 <str name="queryFieldType">string</str>
1273 <str name="config-file">elevate.xml</str>
1276 <!-- A request handler for demonstrating the elevator component -->
1277 <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
1278 <lst name="defaults">
1279 <str name="echoParams">explicit</str>
1281 <arr name="last-components">
1286 <!-- Highlighting Component
1288 http://wiki.apache.org/solr/HighlightingParameters
1290 <searchComponent class="solr.HighlightComponent" name="highlight">
1292 <!-- Configure the standard fragmenter -->
1293 <!-- This could most likely be commented out in the "default" case -->
1294 <fragmenter name="gap"
1296 class="solr.highlight.GapFragmenter">
1297 <lst name="defaults">
1298 <int name="hl.fragsize">100</int>
1302 <!-- A regular-expression-based fragmenter
1303 (for sentence extraction)
1305 <fragmenter name="regex"
1306 class="solr.highlight.RegexFragmenter">
1307 <lst name="defaults">
1308 <!-- slightly smaller fragsizes work better because of slop -->
1309 <int name="hl.fragsize">70</int>
1310 <!-- allow 50% slop on fragment sizes -->
1311 <float name="hl.regex.slop">0.5</float>
1312 <!-- a basic sentence pattern -->
1313 <str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
1317 <!-- Configure the standard formatter -->
1318 <formatter name="html"
1320 class="solr.highlight.HtmlFormatter">
1321 <lst name="defaults">
1322 <str name="hl.simple.pre"><![CDATA[<em>]]></str>
1323 <str name="hl.simple.post"><![CDATA[</em>]]></str>
1327 <!-- Configure the standard encoder -->
1328 <encoder name="html"
1329 class="solr.highlight.HtmlEncoder" />
1331 <!-- Configure the standard fragListBuilder -->
1332 <fragListBuilder name="simple"
1334 class="solr.highlight.SimpleFragListBuilder"/>
1336 <!-- Configure the single fragListBuilder -->
1337 <fragListBuilder name="single"
1338 class="solr.highlight.SingleFragListBuilder"/>
1340 <!-- default tag FragmentsBuilder -->
1341 <fragmentsBuilder name="default"
1343 class="solr.highlight.ScoreOrderFragmentsBuilder">
1345 <lst name="defaults">
1346 <str name="hl.multiValuedSeparatorChar">/</str>
1351 <!-- multi-colored tag FragmentsBuilder -->
1352 <fragmentsBuilder name="colored"
1353 class="solr.highlight.ScoreOrderFragmentsBuilder">
1354 <lst name="defaults">
1355 <str name="hl.tag.pre"><![CDATA[
1356 <b style="background:yellow">,<b style="background:lawgreen">,
1357 <b style="background:aquamarine">,<b style="background:magenta">,
1358 <b style="background:palegreen">,<b style="background:coral">,
1359 <b style="background:wheat">,<b style="background:khaki">,
1360 <b style="background:lime">,<b style="background:deepskyblue">]]></str>
1361 <str name="hl.tag.post"><![CDATA[</b>]]></str>
1367 <!-- Update Processors
1369 Chains of Update Processor Factories for dealing with Update
1370 Requests can be declared, and then used by name in Update
1373 http://wiki.apache.org/solr/UpdateRequestProcessor
1378 An example dedup update processor that creates the "id" field
1379 on the fly based on the hash code of some other fields. This
1380 example has overwriteDupes set to false since we are using the
1381 id field as the signatureField and Solr will maintain
1382 uniqueness based on that anyway.
1386 <updateRequestProcessorChain name="dedupe">
1387 <processor class="solr.processor.SignatureUpdateProcessorFactory">
1388 <bool name="enabled">true</bool>
1389 <str name="signatureField">id</str>
1390 <bool name="overwriteDupes">false</bool>
1391 <str name="fields">name,features,cat</str>
1392 <str name="signatureClass">solr.processor.Lookup3Signature</str>
1394 <processor class="solr.LogUpdateProcessorFactory" />
1395 <processor class="solr.RunUpdateProcessorFactory" />
1396 </updateRequestProcessorChain>
1399 <!-- Response Writers
1401 http://wiki.apache.org/solr/QueryResponseWriter
1403 Request responses will be written using the writer specified by
1404 the 'wt' request parameter matching the name of a registered
1407 The "default" writer is the default and will be used if 'wt' is
1408 not specified in the request.
1410 <!-- The following response writers are implicitly configured unless
1414 <queryResponseWriter name="xml"
1416 class="solr.XMLResponseWriter" />
1417 <queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
1418 <queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
1419 <queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
1420 <queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
1421 <queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
1422 <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter"/>
1423 <queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
1426 Custom response writers can be declared as needed...
1429 <queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
1432 <!-- XSLT response writer transforms the XML output by any xslt file found
1433 in Solr's conf/xslt directory. Changes to xslt files are checked for
1434 every xsltCacheLifetimeSeconds.
1436 <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
1437 <int name="xsltCacheLifetimeSeconds">5</int>
1438 </queryResponseWriter>
1442 http://wiki.apache.org/solr/SolrQuerySyntax
1444 Multiple QParserPlugins can be registered by name, and then
1445 used in either the "defType" param for the QueryComponent (used
1446 by SearchHandler) or in LocalParams
1448 <!-- example of registering a query parser -->
1450 <queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
1453 <!-- Function Parsers
1455 http://wiki.apache.org/solr/FunctionQuery
1457 Multiple ValueSourceParsers can be registered by name, and then
1458 used as function names when using the "func" QParser.
1460 <!-- example of registering a custom function parser -->
1462 <valueSourceParser name="myfunc"
1463 class="com.mycompany.MyValueSourceParser" />
1466 <!-- Legacy config for the admin interface -->
1468 <defaultQuery>*:*</defaultQuery>
1470 <!-- configure a healthcheck file for servers behind a
1474 <healthcheck type="file">server-enabled</healthcheck>