solr的搭建与配置

<env-entry>
       <env-entry-name>solr/home</env-entry-name>
       <env-entry-value>/usr/local/jetty/webapps/solr/WEB-INF/solr</env-entry-value>
       <env-entry-type>java.lang.String</env-entry-type>
    </env-entry>

<schema name="example" version="1.2">    
  <types>    
    <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>    
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>    
    <fieldtype name="binary" class="solr.BinaryField"/>    
    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true"     
                                                                positionIncrementGap="0"/>    
    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true"     
                                                                positionIncrementGap="0"/>    
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true"     
                                                                positionIncrementGap="0"/>    
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true"     
                                                                positionIncrementGap="0"/>  
    <fieldType name="name_n_gram" class="solr.TextField">
        <analyzer type="index">
            <tokenizer class="solr.WhitespaceTokenizerFactory" />
            <filter class="solr.LowerCaseFilterFactory" />
            <filter class="com.kingdee.lucene.analysis.ScriptTokenFilterFactory" />
            <filter class="com.kingdee.lucene.analysis.NGramExtensionTokenFilterFactory"
minGramSize="1" maxGramSize="40" />
        <filter
class="com.kingdee.lucene.analysis.MultipleSpellingTokenFilterFactory" />
        </analyzer>
        <analyzer type="query">
            <tokenizer class="solr.KeywordTokenizerFactory" />
            <filter class="solr.LowerCaseFilterFactory" />
        </analyzer>
    </fieldType>
  ...    
  </types>    
  ...    
</schema>

<?xml version="1.0" encoding="UTF-8" ?>
<config>
	<luceneMatchVersion>LUCENE_42</luceneMatchVersion>
	<dataDir>${solr.data.dir:}</dataDir>
	<directoryFactory name="DirectoryFactory"
		class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}" />
    <codecFactory class="solr.SchemaCodecFactory"/>

	<indexConfig>
		<filter class="solr.LimitTokenCountFilterFactory"
			maxTokenCount="10000" />
		<writeLockTimeout>1000</writeLockTimeout>
		<maxIndexingThreads>8</maxIndexingThreads>
		<useCompoundFile>false</useCompoundFile>
		<ramBufferSizeMB>32</ramBufferSizeMB>
		<maxBufferedDocs>1000</maxBufferedDocs>
		<mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
			<int name="maxMergeAtOnce">10</int>
			<int name="segmentsPerTier">10</int>
		</mergePolicy>
		<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler" />
		<lockType>native</lockType>
		<unlockOnStartup>false</unlockOnStartup>
		<termIndexInterval>128</termIndexInterval>
		<reopenReaders>true</reopenReaders>
		<deletionPolicy class="solr.SolrDeletionPolicy">
			<str name="maxCommitsToKeep">1</str>
			<str name="maxOptimizedCommitsToKeep">0</str>
			<str name="maxCommitAge">30MINUTES</str>
			<str name="maxCommitAge">1DAY</str>
		</deletionPolicy>
		<infoStream file="INFOSTREAM.txt">false</infoStream>
	</indexConfig>

	<updateHandler class="solr.DirectUpdateHandler2">
		<autoCommit>
			<maxTime>15000</maxTime>
			<openSearcher>false</openSearcher>
		</autoCommit>
		<autoSoftCommit>
			<maxTime>1000</maxTime>
		</autoSoftCommit>
		<updateLog>
			<str name="dir">${solr.data.dir:}</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" />
		<fieldValueCache class="solr.FastLRUCache" size="512"
			autowarmCount="128" showItems="32" />
		<enableLazyFieldLoading>true</enableLazyFieldLoading>
		<queryResultWindowSize>60</queryResultWindowSize>
		<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
		<listener event="newSearcher" class="solr.QuerySenderListener">
			<arr name="queries">
			</arr>
		</listener>
		<listener event="firstSearcher" class="solr.QuerySenderListener">
			<arr name="queries">
			</arr>
		</listener>
		<useColdSearcher>false</useColdSearcher>
		<maxWarmingSearchers>4</maxWarmingSearchers>
	</query>

	<requestDispatcher handleSelect="false">
		<requestParsers enableRemoteStreaming="false"
			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>
		</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">text</str>
		</lst>
	</requestHandler>

	<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>

	<!-- Solr Cell Update Request Handler http://wiki.apache.org/solr/ExtractingRequestHandler -->
	<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" />

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

	<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>
		</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">text</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>

	<!-- Term Vector Component http://wiki.apache.org/solr/TermVectorComponent -->
	<searchComponent name="tvComponent" class="solr.TermVectorComponent" />
	<!-- A request handler for demonstrating the term vector component This 
		is purely as an example. In reality you will likely want to add the component 
		to your already specified request handlers. -->
	<requestHandler name="/tvrh" class="solr.SearchHandler"
		startup="lazy">
		<lst name="defaults">
			<str name="df">text</str>
			<bool name="tv">true</bool>
		</lst>
		<arr name="last-components">
			<str>tvComponent</str>
		</arr>
	</requestHandler>

	<requestHandler name="/dataimport"
		class="org.apache.solr.handler.dataimport.DataImportHandler">
		<lst name="defaults">
			<str name="config">data-config.xml</str>
		</lst>
	</requestHandler>

	<searchComponent name="clustering"
		enable="${solr.clustering.enabled:false}" class="solr.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 
				* org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm 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>

			<!-- Location of Carrot2 lexical resources. A directory from which to 
				load Carrot2-specific stop words and stop labels. Absolute or relative to 
				Solr config directory. If a specific resource (e.g. stopwords.en) is present 
				in the specified dir, it will completely override the corresponding default 
				one that ships with Carrot2. For an overview of Carrot2 lexical resources, 
				see: http://download.carrot2.org/head/manual/#chapter.lexical-resources -->
			<str name="carrot.lexicalResourcesDir">clustering/carrot2</str>

			<!-- The language to assume for the documents. For a list of allowed values, 
				see: http://download.carrot2.org/stable/manual/#section.attribute.lingo.MultilingualClustering.defaultLanguage -->
			<str name="MultilingualClustering.defaultLanguage">ENGLISH</str>
		</lst>
		<lst name="engine">
			<str name="name">stc</str>
			<str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
		</lst>
	</searchComponent>

	<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 class="highlight">]]></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="com.kingdee.solr.highlight.ScoreOrderFragmentsBuilder">
				<!-- <lst name="defaults"> <str name="hl.multiValuedSeparatorChar">/</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>

	<queryResponseWriter name="xml" default="true"
		class="solr.XMLResponseWriter" />
	<queryResponseWriter name="json" class="solr.JSONResponseWriter" />
	<queryResponseWriter name="python"
		class="solr.PythonResponseWriter" />
	<queryResponseWriter name="ruby" class="solr.RubyResponseWriter" />
	<queryResponseWriter name="php" class="solr.PHPResponseWriter" />
	<queryResponseWriter name="phps"
		class="solr.PHPSerializedResponseWriter" />
	<queryResponseWriter name="csv" class="solr.CSVResponseWriter" />
	<queryResponseWriter name="velocity"
		class="solr.VelocityResponseWriter" startup="lazy" />
	<queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
		<int name="xsltCacheLifetimeSeconds">5</int>
	</queryResponseWriter>

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