7步从零开始搭建一个SOLR支持中文分词【solr3.3】

下载如下三个软件【请注意版本】

1：Solr的下载地址 http://labs.renren.com/apache-mirror//lucene/solr/3.3.0/apache-solr-3.3.0.zip 【使用 D:\solr\apache-solr-3.3.0\example\solr文件夹里的内容】
2：Tomcat的下载地址 http://apache.etoak.com/tomcat/tomcat-6/v6.0.33/bin/apache-tomcat-6.0.33.tar.gz 【使用其运行JAVA WEB】
3：IKAnalyzer下载地址 http://ik-analyzer.googlecode.com/files/IKAnalyzer3.2.8%20bin.zip 【只使用其IKAnalyzer3.2.5Stable.jar】

提前是安装好JDK1.6+，并将每个软件解压到 /sinykk 里

1、将TOMCAT解压到 /usr/local/apache-tomcat-6.0.33/

2、将 /solr/apache-solr-3.3.0/example/solr 文件拷贝到 /usr/local/apache-tomcat-6.0.33/

3、然后修改TOMCAT的/usr/local/apache-tomcat-6.0.33/conf/server.xml【增加中文支持】

Xml代码




<Connector port="8983" protocol="HTTP/1.1"

connectionTimeout="20000"

redirectPort="8443" URIEncoding="UTF-8"/>

4、添加文件 /usr/local/apache-tomcat-6.0.33/conf/Catalina/localhost/solr.xml 内容如下

Xml代码




<?xml version="1.0" encoding="UTF-8"?>

<Context docBase="/usr/local/apache-tomcat-6.0.33/webapps/solr" debug="0" crossContext="true" >

<Environment name="solr/home" type="java.lang.String" value="/usr/local/apache-tomcat-6.0.33/solr" override="true" />

</Context>

5、将/sinykk/solr/apache-solr-3.3.0/example/webapps/solr.war文件放到/usr/local/apache-tomcat-6.0.33/webapps文件夹下，并启动TOMCAT

6、将/sinykk/solr/IKAnalyzer3.2.8.jar 文件放到/usr/local/apache-tomcat-6.0.33/webapps/solr/WEB-INF/lib 目录下

7、修改/usr/local/apache-tomcat-6.0.33/solr/conf/schema.xml文件为

Xml代码




<?xml version="1.0" encoding="UTF-8" ?>

<schema name="example" version="1.4">

<types>

<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>

<!--

<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">

<analyzer type="index">

<tokenizer class="solr.StandardTokenizerFactory"/>

<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />

<filter class="solr.LowerCaseFilterFactory"/>

</analyzer>

<analyzer type="query">

<tokenizer class="solr.StandardTokenizerFactory"/>

<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />

<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>

<filter class="solr.LowerCaseFilterFactory"/>

</analyzer>

</fieldType>

-->

<fieldType name="textik" class="solr.TextField" >

<analyzer class="org.wltea.analyzer.lucene.IKAnalyzer"/>

<analyzer type="index">

<tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory" isMaxWordLength="false"/>

<filter class="solr.StopFilterFactory"

ignoreCase="true" words="stopwords.txt"/>

<filter class="solr.WordDelimiterFilterFactory"

generateWordParts="1"

generateNumberParts="1"

catenateWords="1"

catenateNumbers="1"

catenateAll="0"

splitOnCaseChange="1"/>

<filter class="solr.LowerCaseFilterFactory"/>

<filter class="solr.EnglishPorterFilterFactory"

protected="protwords.txt"/>

<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>

</analyzer>

<analyzer type="query">

<tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory" isMaxWordLength="false"/>

<filter class="solr.StopFilterFactory"

ignoreCase="true" words="stopwords.txt"/>

<filter class="solr.WordDelimiterFilterFactory"

generateWordParts="1"

generateNumberParts="1"

catenateWords="1"

catenateNumbers="1"

catenateAll="0"

splitOnCaseChange="1"/>

<filter class="solr.LowerCaseFilterFactory"/>

<filter class="solr.EnglishPorterFilterFactory"

protected="protwords.txt"/>

<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>

</analyzer>

</fieldType>

</types>

<fields>

<field name="id" type="string" indexed="true" stored="true" required="true" />

</fields>

<uniqueKey>id</uniqueKey>

</schema>

最后运行http://192.168.171.129:8983/solr/admin/analysis.jsp
效果图如下