solrconfig

<?xml version="1.0" encoding="UTF-8" ?>
<!--
 Licensed to the Apache Software Foundation (ASF) under one or more
 contributor license agreements.  See the NOTICE file distributed with
 this work for additional information regarding copyright ownership.
 The ASF licenses this file to You under the Apache License, Version 2.0
 (the "License"); you may not use this file except in compliance with
 the License.  You may obtain a copy of the License at

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

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

<!--
     For more details about configurations options that may appear in
     this file, see http://wiki.apache.org/solr/SolrConfigXml.
-->
<config>
  <luceneMatchVersion>LUCENE_44</luceneMatchVersion>
  <dataDir>${solr.data.dir:}\${solr.core.name}</dataDir>

  <directoryFactory name="DirectoryFactory"
                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>

  <indexConfig>
  </indexConfig>

  <!--jmx /-->

  <updateHandler class="solr.DirectUpdateHandler2">

     <autoCommit>
       <maxTime>15000</maxTime>
       <openSearcher>false</openSearcher>
     </autoCommit>

    <!-- softAutoCommit is like autoCommit except it causes a
         'soft' commit which only ensures that changes are visible
         but does not ensure that data is synced to disk.  This is
         faster and more near-realtime friendly than a hard commit.
      -->
     <!--
       <autoSoftCommit>
         <maxTime>1000</maxTime>
       </autoSoftCommit>
      -->
    <updateLog>
      <str name="dir">${solr.data.dir:}\${solr.core.name}</str>
    </updateLog>

  </updateHandler>

  <query>
    <maxBooleanClauses>1024</maxBooleanClauses>

    <filterCache class="solr.FastLRUCache"
                 size="512"
                 initialSize="512"
                 autowarmCount="0"/>

    <queryResultCache class="solr.LRUCache"
                     size="512"
                     initialSize="512"
                     autowarmCount="0"/>

    <documentCache class="solr.LRUCache"
                   size="512"
                   initialSize="512"
                   autowarmCount="0"/>

    <enableLazyFieldLoading>true</enableLazyFieldLoading>

   <queryResultWindowSize>20</queryResultWindowSize>

   <queryResultMaxDocsCached>200</queryResultMaxDocsCached>

    <listener event="newSearcher" class="solr.QuerySenderListener">
      <arr name="queries">
        <!--
           <lst><str name="q">solr</str><str name="sort">price asc</str></lst>
           <lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
          -->
      </arr>
    </listener>
    <listener event="firstSearcher" class="solr.QuerySenderListener">
      <arr name="queries">
        <lst>
          <str name="q">static firstSearcher warming in solrconfig.xml</str>
        </lst>
      </arr>
    </listener>

    <useColdSearcher>false</useColdSearcher>

    <maxWarmingSearchers>2</maxWarmingSearchers>

  </query>

  <requestDispatcher handleSelect="false" >

    <requestParsers enableRemoteStreaming="true"
                    multipartUploadLimitInKB="2048000" />

    <httpCaching never304="true" />

  </requestDispatcher>

  <requestHandler name="/select" class="solr.SearchHandler">
     <lst name="defaults">
       <str name="echoParams">explicit</str>
       <int name="rows">10</int>
       <str name="df">full_text_stx</str>
       <str name="q.op">AND</str>
     </lst>
    </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">full_text_stx</str>
       <str name="q.op">AND</str>
     </lst>
  </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>
     </lst>
  </requestHandler>

  <requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">
    <lst name="defaults">
      <str name="config">${dataimport.config}</str>
    </lst>
    <lst name="invariants">
      <!--str name="datasource.driver">${dataimport.datasource.driver}</str-->
      <str name="url">${dataimport.datasource.url}</str>
      <str name="user">${dataimport.datasource.user}</str>
      <str name="password">${dataimport.datasource.password}</str>
    </lst>
  </requestHandler>

  <requestHandler name="/update" class="solr.UpdateRequestHandler">
    <!--
       <lst name="defaults">
         <str name="update.chain">dedupe</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>


  <requestHandler name="/analysis/field"
                  startup="lazy"
                  class="solr.FieldAnalysisRequestHandler" />


  <requestHandler name="/analysis/document"
                  class="solr.DocumentAnalysisRequestHandler"
                  startup="lazy" />

  <requestHandler name="/admin/"
                  class="solr.admin.AdminHandlers" />

  <!-- 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>

  <!-- Echo the request contents back to the client -->
  <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
    <lst name="defaults">
     <str name="echoParams">explicit</str>
     <str name="echoHandler">true</str>
    </lst>
  </requestHandler>



   <!-- Spell Check

        The spell check component can return a list of alternative spelling
        suggestions.

        http://wiki.apache.org/solr/SpellCheckComponent
     -->
  <searchComponent name="spellcheck" class="solr.SpellCheckComponent">

    <str name="queryAnalyzerFieldType">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>

  <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
    <lst name="defaults">
      <str name="df">full_text_stx</str>
      <str name="q.op">AND</str>
      <!-- Solr will use suggestions from both the 'default' spellchecker
           and from the 'wordbreak' spellchecker and combine them.
           collations (re-written queries) can include a combination of
           corrections from both spellcheckers -->
      <str name="spellcheck.dictionary">default</str>
      <str name="spellcheck.dictionary">wordbreak</str>
      <str name="spellcheck">on</str>
      <str name="spellcheck.extendedResults">true</str>
      <str name="spellcheck.count">10</str>
      <str name="spellcheck.alternativeTermCount">5</str>
      <str name="spellcheck.maxResultsForSuggest">5</str>
      <str name="spellcheck.collate">true</str>
      <str name="spellcheck.collateExtendedResults">true</str>
      <str name="spellcheck.maxCollationTries">10</str>
      <str name="spellcheck.maxCollations">5</str>
    </lst>
    <arr name="last-components">
      <str>spellcheck</str>
    </arr>
  </requestHandler>

  <searchComponent name="terms" class="solr.TermsComponent"/>

  <!-- A request handler for demonstrating the terms component -->
  <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
     <lst name="defaults">
      <bool name="terms">true</bool>
    </lst>
    <arr name="components">
      <str>terms</str>
    </arr>
  </requestHandler>

  <!-- Highlighting Component

       http://wiki.apache.org/solr/HighlightingParameters
    -->
  <searchComponent class="solr.HighlightComponent" name="highlight"> <!-- nmg -->
    <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\&quot;&apos;]{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">.,!? &#9;&#10;&#13;</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>

  <queryResponseWriter name="json" class="solr.JSONResponseWriter">
     <!-- For the purposes of the tutorial, JSON responses are written as
      plain text so that they are easy to read in *any* browser.
      If you expect a MIME type of "application/json" just remove this override.
     -->
    <str name="content-type">text/plain; charset=UTF-8</str>
  </queryResponseWriter>

  <!--
     Custom response writers can be declared as needed...
    -->
    <queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy"/>


  <!-- XSLT response writer transforms the XML output by any xslt file found
       in Solr's conf/xslt directory.  Changes to xslt files are checked for
       every xsltCacheLifetimeSeconds.
    -->
  <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
    <int name="xsltCacheLifetimeSeconds">5</int>
  </queryResponseWriter>

  <!-- Legacy config for the admin interface -->
  <admin>
    <defaultQuery>*:*</defaultQuery>
  </admin>

</config>