solrsan 0.0.20

data/config/solr/conf/solrconfig.xml

@@ -0,0 +1,430 @@
+<?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.
+
+     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
+-->
+<config>
+  <abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
+
+  <!-- lib directives can be used to instruct Solr to load an Jars identified
+       and use them to resolve any "plugins" specified in your solrconfig.xml or
+       schema.xml (ie: Analyzers, Request Handlers, etc...).
+
+       All directories and paths are resolved relative the instanceDir.
+
+       If a "./lib" directory exists in your instanceDir, all files found in it
+       are included as if you had used the following syntax...
+       
+              <lib dir="./lib" />
+    -->
+  <!-- A dir option by itself adds any files found in the directory to the
+       classpath, this is useful for including all jars in a directory.
+    -->
+  <lib dir="../../contrib/extraction/lib" />
+  <!-- When a regex is specified in addition to a directory, only the files in that
+       directory which completely match the regex (anchored on both ends)
+       will be included.
+    -->
+  <lib dir="../../dist/" regex="apache-solr-cell-\d.*\.jar" />
+  <lib dir="../../dist/" regex="apache-solr-clustering-\d.*\.jar" />
+  <!-- If a dir option (with or without a regex) is used and nothing is found
+       that matches, it will be ignored
+    -->
+  <lib dir="../../contrib/clustering/lib/downloads/" />
+  <lib dir="../../contrib/clustering/lib/" />
+  <lib dir="/total/crap/dir/ignored" /> 
+
+  <!-- Used to specify an alternate directory to hold all index data
+       other than the default ./data under the Solr home.
+       If replication is in use, this should match the replication configuration. -->
+  <dataDir>${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>
+    <ramBufferSizeMB>32</ramBufferSizeMB>
+    <!-- <maxMergeDocs>2147483647</maxMergeDocs> -->
+    <maxFieldLength>10000</maxFieldLength>
+    <writeLockTimeout>1000</writeLockTimeout>
+    <commitLockTimeout>10000</commitLockTimeout>
+    <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>
+    <unlockOnStartup>false</unlockOnStartup>
+    
+    <reopenReaders>true</reopenReaders>
+    <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>
+    </deletionPolicy>
+
+     <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.
+
+		If you want to connect to a particular server, specify the agentId
+		e.g. <jmx agentId="myAgent" />
+
+		If you want to start a new MBeanServer, specify the serviceUrl
+		e.g <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+
+		For more details see http://wiki.apache.org/solr/SolrJmx
+  -->
+  <jmx />
+
+  <!-- the default high-performance update handler -->
+  <updateHandler class="solr.DirectUpdateHandler2">
+  </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>
+
+   <!-- 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>
+
+    <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>
+    <useColdSearcher>false</useColdSearcher>
+    <maxWarmingSearchers>2</maxWarmingSearchers>
+  </query>
+
+  <requestDispatcher handleSelect="true" >
+    <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048000" />
+    <httpCaching lastModifiedFrom="openTime"
+                 etagSeed="Solr">
+    </httpCaching>
+  </requestDispatcher>
+    
+  <!-- <requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">
+    <lst name="defaults">
+      <str name="config">xml-data-config.xml</str>
+    </lst>
+  </requestHandler> -->
+  
+  <requestHandler name="standard" class="solr.SearchHandler" default="true">
+     <lst name="defaults">
+       <str name="echoParams">explicit</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
+     </str>
+      <str name="mm">3</str>
+     <int name="ps">100</int>
+     <str name="q.alt">*:*</str>
+     <str name="f.name.hl.alternateField">name</str>
+     <str name="f.text.hl.fragmenter">regex</str> <!-- defined below -->
+    </lst>
+  </requestHandler>
+
+   <!-- 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>
+  </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.
+
+  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>
+    <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>
+  </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>
+  </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">
+     <lst name="defaults">
+      <bool name="terms">true</bool>
+    </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">
+    <lst name="defaults">
+      <str name="echoParams">explicit</str>
+    </lst>
+    <arr name="last-components">
+      <str>elevator</str>
+    </arr>
+  </requestHandler>
+
+  <requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
+  <requestHandler name="/update/javabin" class="solr.BinaryUpdateRequestHandler" />
+  <requestHandler name="/analysis/document" class="solr.DocumentAnalysisRequestHandler" />
+  <requestHandler name="/analysis/field" class="solr.FieldAnalysisRequestHandler" />
+  <!-- CSV update handler, loaded on demand -->
+  <requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy" />
+  <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>
+    </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>
+
+
+  <queryResponseWriter name="xslt" class="org.apache.solr.request.XSLTResponseWriter">
+    <int name="xsltCacheLifetimeSeconds">5</int>
+  </queryResponseWriter>
+
+  <admin>
+    <defaultQuery>solr</defaultQuery>
+
+  </admin>
+
+</config>
+

data/config/solr/conf/spellings.txt

@@ -0,0 +1,2 @@
+pizza
+history

data/config/solr/conf/stopwords.txt

@@ -0,0 +1,56 @@
+# 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.
+
+#-----------------------------------------------------------------------
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+#Standard english stop words taken from Lucene's StopAnalyzer
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+on
+or
+s
+such
+t
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
+

data/config/solr/conf/synonyms.txt

@@ -0,0 +1,24 @@
+# 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.
+
+#-----------------------------------------------------------------------
+
+# Some synonym groups specific to this example
+med,medical
+cs,computer science
+eng, engineering
+sci, science
+uci, university of california irvine
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+

data/config/solr/conf/xslt/example.xsl

@@ -0,0 +1,132 @@
+<?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.
+ -->
+
+<!-- 
+  Simple transform of Solr query results to HTML
+ -->
+<xsl:stylesheet version='1.0'
+    xmlns:xsl='http://www.w3.org/1999/XSL/Transform'
+>
+
+  <xsl:output media-type="text/html; charset=UTF-8" encoding="UTF-8"/> 
+  
+  <xsl:variable name="title" select="concat('Solr search results (',response/result/@numFound,' documents)')"/>
+  
+  <xsl:template match='/'>
+    <html>
+      <head>
+        <title><xsl:value-of select="$title"/></title>
+        <xsl:call-template name="css"/>
+      </head>
+      <body>
+        <h1><xsl:value-of select="$title"/></h1>
+        <div class="note">
+          This has been formatted by the sample "example.xsl" transform -
+          use your own XSLT to get a nicer page
+        </div>
+        <xsl:apply-templates select="response/result/doc"/>
+      </body>
+    </html>
+  </xsl:template>
+  
+  <xsl:template match="doc">
+    <xsl:variable name="pos" select="position()"/>
+    <div class="doc">
+      <table width="100%">
+        <xsl:apply-templates>
+          <xsl:with-param name="pos"><xsl:value-of select="$pos"/></xsl:with-param>
+        </xsl:apply-templates>
+      </table>
+    </div>
+  </xsl:template>
+
+  <xsl:template match="doc/*[@name='score']" priority="100">
+    <xsl:param name="pos"></xsl:param>
+    <tr>
+      <td class="name">
+        <xsl:value-of select="@name"/>
+      </td>
+      <td class="value">
+        <xsl:value-of select="."/>
+
+        <xsl:if test="boolean(//lst[@name='explain'])">
+          <xsl:element name="a">
+            <!-- can't allow whitespace here -->
+            <xsl:attribute name="href">javascript:toggle("<xsl:value-of select="concat('exp-',$pos)" />");</xsl:attribute>?</xsl:element>
+          <br/>
+          <xsl:element name="div">
+            <xsl:attribute name="class">exp</xsl:attribute>
+            <xsl:attribute name="id">
+              <xsl:value-of select="concat('exp-',$pos)" />
+            </xsl:attribute>
+            <xsl:value-of select="//lst[@name='explain']/str[position()=$pos]"/>
+          </xsl:element>
+        </xsl:if>
+      </td>
+    </tr>
+  </xsl:template>
+
+  <xsl:template match="doc/arr" priority="100">
+    <tr>
+      <td class="name">
+        <xsl:value-of select="@name"/>
+      </td>
+      <td class="value">
+        <ul>
+        <xsl:for-each select="*">
+          <li><xsl:value-of select="."/></li>
+        </xsl:for-each>
+        </ul>
+      </td>
+    </tr>
+  </xsl:template>
+
+
+  <xsl:template match="doc/*">
+    <tr>
+      <td class="name">
+        <xsl:value-of select="@name"/>
+      </td>
+      <td class="value">
+        <xsl:value-of select="."/>
+      </td>
+    </tr>
+  </xsl:template>
+
+  <xsl:template match="*"/>
+  
+  <xsl:template name="css">
+    <script>
+      function toggle(id) {
+        var obj = document.getElementById(id);
+        obj.style.display = (obj.style.display != 'block') ? 'block' : 'none';
+      }
+    </script>
+    <style type="text/css">
+      body { font-family: "Lucida Grande", sans-serif }
+      td.name { font-style: italic; font-size:80%; }
+      td { vertical-align: top; }
+      ul { margin: 0px; margin-left: 1em; padding: 0px; }
+      .note { font-size:80%; }
+      .doc { margin-top: 1em; border-top: solid grey 1px; }
+      .exp { display: none; font-family: monospace; white-space: pre; }
+    </style>
+  </xsl:template>
+
+</xsl:stylesheet>