solrconfig.xml

<!--

 Licensed to the Apache Software Foundation (ASF) under one or more
 contributor license agreements.  See the NOTICE file distributed with
 this work for additional information regarding copyright ownership.
 The ASF licenses this file to You under the Apache License, Version 2.0
 (the "License"); you may not use this file except in compliance with
 the License.  You may obtain a copy of the License at

     http://www.apache.org/licenses/LICENSE-2.0

 Unless required by applicable law or agreed to in writing, software
 distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
-->
<!--

     For more details about configurations options that may appear in
     this file, see http://wiki.apache.org/solr/SolrConfigXml.
-->
<config>
<!--
 In all configuration below, a prefix of "solr." for class names
       is an alias that causes solr to search appropriate packages,
       including org.apache.solr.(search|update|request|core|analysis)

       You may also specify a fully qualified Java classname if you
       have your own custom plugins.

-->
<!--
 Controls what version of Lucene various components of Solr
       adhere to.  Generally, you want to use the latest version to
       get all bug fixes and improvements. It is highly recommended
       that you fully re-index after changing this setting as it can
       affect both how text is indexed and queried.

-->
<luceneMatchVersion>LUCENE_41</luceneMatchVersion>
<!--
 <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" />

-->
<dataDir>${solr.data.dir:}</dataDir>
<!--
 The DirectoryFactory to use for indexes.

       solr.StandardDirectoryFactory is filesystem
       based and tries to pick the best implementation for the current
       JVM and platform.  solr.NRTCachingDirectoryFactory, the default,
       wraps solr.StandardDirectoryFactory and caches small files in memory
       for better NRT performance.

       One can force a particular implementation via solr.MMapDirectoryFactory,
       solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.

       solr.RAMDirectoryFactory is memory based, not
       persistent, and doesn't work with replication.

-->
<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
<!--
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
       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 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>
<useCompoundFile>true</useCompoundFile>
<!--
 ramBufferSizeMB sets the amount of RAM that may be used by Lucene
         indexing for buffering added documents and deletions before they are
         flushed to the Directory.
         maxBufferedDocs sets a limit on the number of documents buffered
         before flushing.
         If both ramBufferSizeMB and maxBufferedDocs is set, then
         Lucene will flush based on whichever limit is hit first.
-->
<ramBufferSizeMB>20</ramBufferSizeMB>
-->
<maxBufferedDocs>10000</maxBufferedDocs>
<!--
 Expert: Merge Policy
         The Merge Policy in Lucene controls how merging of segments is done.
         The default since Solr/Lucene 3.3 is TieredMergePolicy.
         The default since Lucene 2.3 was the LogByteSizeMergePolicy,
         Even older versions of Lucene used LogDocMergePolicy.

-->
<mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
<int name="maxMergeAtOnce">4</int>
<int name="segmentsPerTier">4</int>
</mergePolicy>
<unlockOnStartup>true</unlockOnStartup>
</indexConfig>
<updateHandler class="solr.DirectUpdateHandler2">
<!--
 Enables a transaction log, used for real-time get, durability, and
         and solr cloud replica recovery.  The log can grow as big as
         uncommitted changes to the index, so use of a hard autoCommit
         is recommended (see below).
         "dir" - the target directory for transaction logs, defaults to the
                solr data directory.
-->
<updateLog>
<str name="dir">${solr.ulog.dir:}</str>
</updateLog>
<autoCommit>
<maxTime>15000</maxTime>
<openSearcher>false</openSearcher>
</autoCommit>
<autoSoftCommit>
<maxTime>5000</maxTime>
</autoSoftCommit>
</updateHandler>
<query>
<maxBooleanClauses>1024</maxBooleanClauses>
<!--
 Solr Internal Query Caches

         There are two implementations of cache available for Solr,
         LRUCache, based on a synchronized LinkedHashMap, and
         FastLRUCache, based on a ConcurrentHashMap.

         FastLRUCache has faster gets and slower puts in single
         threaded operation and thus is generally faster than LRUCache
         when the hit ratio of the cache is high (> 75%), and may be
         faster under other scenarios on multi-cpu systems.

-->
<!--
 Filter Cache

         Cache used by SolrIndexSearcher for filters (DocSets),
         unordered sets of *all* documents that match a query.  When a
         new searcher is opened, its caches may be prepopulated or
         "autowarmed" using data from caches in the old searcher.
         autowarmCount is the number of items to prepopulate.  For
         LRUCache, the autowarmed items will be the most recently
         accessed items.

         Parameters:
           class - the SolrCache implementation LRUCache or
               (LRUCache or FastLRUCache)
           size - the maximum number of entries in the cache
           initialSize - the initial capacity (number of entries) of
               the cache.  (see java.util.HashMap)
           autowarmCount - the number of entries to prepopulate from
               and old cache.

-->
<filterCache class="solr.FastLRUCache" size="512" initialSize="512" autowarmCount="0"/>
<!--
 Query Result Cache

         Caches results of searches - ordered lists of document ids
         (DocList) based on a query, a sort, and the range of documents requested.

-->
<queryResultCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0"/>
<!--
 Document Cache

         Caches Lucene Document objects (the stored fields for each
         document).  Since Lucene internal document ids are transient,
         this cache will not be autowarmed.

-->
<documentCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0"/>
<!--
 Lazy Field Loading

         If true, stored fields that are not requested will be loaded
         lazily.  This can result in a significant speed improvement
         if the usual case is to not load all stored fields,
         especially if the skipped fields are large compressed text
         fields.

-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<!--
 Use Filter For Sorted Query

        A possible optimization that attempts to use a filter to
        satisfy a search.  If the requested sort does not include
        score, then the filterCache will be checked for a filter
        matching the query. If found, the filter will be used as the
        source of document ids, and then the sort will be applied to
        that.

        For most situations, this will not be useful unless you
        frequently get the same search repeatedly with different sort
        options, and none of them ever use "score"

-->
<!--

      <useFilterForSortedQuery>true</useFilterForSortedQuery>

-->
<!--
 Result Window Size

        An optimization for use with the queryResultCache.  When a search
        is requested, a superset of the requested number of document ids
        are collected.  For example, if a search for a particular query
        requests matching documents 10 through 19, and queryWindowSize is 50,
        then documents 0 through 49 will be collected and cached.  Any further
        requests in that range can be satisfied via the cache.

-->
<queryResultWindowSize>20</queryResultWindowSize>
<!--
 Maximum number of documents to cache for any entry in the
        queryResultCache.

-->
<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
<!--
 Query Related Event Listeners

        Various IndexSearcher related events can trigger Listeners to
        take actions.

        newSearcher - fired whenever a new searcher is being prepared
        and there is a current searcher handling requests (aka
        registered).  It can be used to prime certain caches to
        prevent long request times for certain requests.

        firstSearcher - fired whenever a new searcher is being
        prepared but there is no current registered searcher to handle
        requests or to gain autowarming data from.



-->
<!--
 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>
<!--
 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>
<!--
 Request Dispatcher

       This section contains instructions for how the SolrDispatchFilter
       should behave when processing requests for this SolrCore.

       handleSelect is a legacy option that affects the behavior of requests
       such as /select?qt=XXX

       handleSelect="true" will cause the SolrDispatchFilter to process
       the request and dispatch the query to a handler specified by the
       "qt" param, assuming "/select" isn't already registered.

       handleSelect="false" will cause the SolrDispatchFilter to
       ignore "/select" requests, resulting in a 404 unless a handler
       is explicitly registered with the name "/select"

       handleSelect="true" is not recommended for new users, but is the default
       for backwards compatibility

-->
<requestDispatcher handleSelect="false">
<!--
 Request Parsing

         These settings indicate how Solr Requests may be parsed, and
         what restrictions may be placed on the ContentStreams from
         those requests

         enableRemoteStreaming - enables use of the stream.file
         and stream.url parameters for specifying remote streams.

         multipartUploadLimitInKB - specifies the max size (in KiB) of
         Multipart File Uploads that Solr will allow in a Request.

         formdataUploadLimitInKB - specifies the max size (in KiB) of
         form data (application/x-www-form-urlencoded) sent via
         POST. You can use POST to pass request parameters not
         fitting into the URL.

         *** 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

-->
<httpCaching never304="true"/>
<!--
 If you include a <cacheControl> directive, it will be used to
         generate a Cache-Control header (as well as an Expires header
         if the value contains "max-age=")

         By default, no Cache-Control header is generated.

         You can use the <cacheControl> option even if you have set
         never304="true"

-->
<!--

       <httpCaching never304="true" >
         <cacheControl>max-age=30, public</cacheControl>
       </httpCaching>

-->
<!--
 To enable Solr to respond with automatically generated HTTP
         Caching headers, and to response to Cache Validation requests
         correctly, set the value of never304="false"

         This will cause Solr to generate Last-Modified and ETag
         headers based on the properties of the Index.

         The following options can also be specified to affect the
         values of these headers...

         lastModFrom - the default value is "openTime" which means the
         Last-Modified value (and validation against If-Modified-Since
         requests) will all be relative to when the current Searcher
         was opened.  You can change it to lastModFrom="dirLastMod" if
         you want the value to exactly correspond to when the physical
         index was last modified.

         etagSeed="..." is an option you can change to force the ETag
         header (and validation against If-None-Match requests) to be
         different even if the index has not changed (ie: when making
         significant changes to your config file)

         (lastModifiedFrom and etagSeed are both ignored if you use
         the never304="true" option)

-->
<!--

       <httpCaching lastModifiedFrom="openTime"
                    etagSeed="Solr">
         <cacheControl>max-age=30, public</cacheControl>
       </httpCaching>

-->
</requestDispatcher>
<!--
 Request Handlers

       http://wiki.apache.org/solr/SolrRequestHandler

       Incoming queries will be dispatched to a specific handler by name
       based on the path specified in the request.

       Legacy behavior: If the request path uses "/select" but no Request
       Handler has that name, and if handleSelect="true" has been specified in
       the requestDispatcher, then the Request Handler is dispatched based on
       the qt parameter.  Handlers without a leading '/' are accessed this way
       like so: http://host/app/[core/]select?qt=name  If no qt is
       given, then the requestHandler that declares default="true" will be
       used or the one named "standard".

       If a Request Handler is declared with startup="lazy", then it will
       not be initialized until the first request that uses it.


-->
<!--
 SearchHandler

       http://wiki.apache.org/solr/SearchHandler

       For processing Search Queries, the primary Request Handler
       provided with Solr is "SearchHandler" It delegates to a sequent
       of SearchComponents (see below) and supports distributed
       queries across multiple shards

-->
<requestHandler name="search" class="solr.SearchHandler" default="true">
<!--
 default values for query parameters can be specified, these
         will be overridden by parameters in the request

-->
<lst name="defaults">
<str name="defType">dismax</str>
<str name="echoParams">explicit</str>
<int name="rows">10</int>
<str name="q.alt">*:*</str>
<str name="mm">2<-1 5<-2 6<90%</str>
<str name="fl">
id, score, author_display, author_vern_display, format, isbn_t, language_facet, lc_callnum_display, material_type_display, published_display, published_vern_display, pub_date, title_display, title_vern_display, subject_topic_facet, subject_geo_facet, subject_era_facet, subtitle_display, subtitle_vern_display, url_fulltext_display, url_suppl_display, material,
</str>
<str name="material_qf">
material_unstem_search^200 material_addl_unstem_search^50 material_t^20 material_addl_t
</str>
<str name="material_pf">
material_unstem_search^2000 material_addl_unstem_search^500 material_t^200 material_addl_t^10
</str>
<str name="facet">true</str>
<str name="facet.mincount">1</str>
<str name="facet.limit">10</str>
<str name="facet.field">format</str>
<str name="facet.field">pub_date</str>
<str name="facet.field">material</str>
</lst>
</requestHandler>
<requestHandler name="/select" class="solr.SearchHandler">
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<!--
 A request handler that returns indented JSON by default
-->
<requestHandler name="/query" class="solr.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
<str name="wt">json</str>
<str name="indent">true</str>
<str name="df">text</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<!--
 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>
<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">
<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>
<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">
<str name="echoParams">all</str>
</lst>
</requestHandler>
<requestHandler name="/debug/dump" class="solr.DumpRequestHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
<str name="echoHandler">true</str>
</lst>
</requestHandler>
<requestHandler name="/replication" class="solr.ReplicationHandler"></requestHandler>
<searchComponent name="spellcheck" class="solr.SpellCheckComponent">
<str name="queryAnalyzerFieldType">textSpell</str>
<!--
 Multiple "Spell Checkers" can be declared and used by this
         component

-->
<!--
 a spellchecker built from a field of the main index
-->
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">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>
<!--
 a spellchecker that can break or combine words.  See "/spell" handler below for usage
-->
<lst name="spellchecker">
<str name="name">wordbreak</str>
<str name="classname">solr.WordBreakSolrSpellChecker</str>
<str name="field">name</str>
<str name="combineWords">true</str>
<str name="breakWords">true</str>
<int name="maxChanges">10</int>
</lst>
</searchComponent>
<searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
<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>