solr5.3.1 集成IK中文分词器

1.下载IK分词器包。

链接:http://pan.baidu.com/s/1i4D0fZJ 密码:bcen

2.解压并把IKAnalyzer5.3.1.jar 、IK-Analyzer-extra-5.3.1.jar拷贝到tomcat/webapps/solr/WEB-INF/lib下。

 

3.修改schema.xml配置文件,如下:

修改后的配置文件

 1 <?xml version="1.0" encoding="UTF-8" ?>
 2 <schema name="example" version="1.5">
 3    <field name="_version_" type="long" indexed="true" stored="true"/>
 4    <field name="_root_" type="string" indexed="true" stored="false"/>
 5    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
 6    <field name="title" type="text_ik" indexed="true" stored="true" multiValued="true"/>
 7    <field name="subject" type="text_ik" indexed="true" stored="true"/>
 8    <field name="description" type="text_ik" indexed="true" stored="true"/>
 9    <field name="text" type="text_ik" indexed="true" stored="false" multiValued="true"/>
10   
11    <uniqueKey>id</uniqueKey>
12   
13    <copyField source="title" dest="text"/>
14    <copyField source="subject" dest="text"/>
15    <copyField source="description" dest="text"/>
16   
17    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
18    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
19    <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
20     
21    <fieldType name="text_ik" class="solr.TextField">
22     <analyzer type="index" useSmart="false" class="org.wltea.analyzer.lucene.IKAnalyzer"/>   
23     <analyzer type="query" useSmart="true" class="org.wltea.analyzer.lucene.IKAnalyzer"/>   
24    </fieldType>
25    
26    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
27       <analyzer type="index">
28         <tokenizer class="solr.StandardTokenizerFactory"/>
29         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
30         <filter class="solr.LowerCaseFilterFactory"/>
31       </analyzer>
32       <analyzer type="query">
33         <tokenizer class="solr.StandardTokenizerFactory"/>
34         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
35         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
36         <filter class="solr.LowerCaseFilterFactory"/>
37       </analyzer>
38    </fieldType>
39 </schema>

 

 修改完成之后保存并重启solr服务器。

posted @ 2016-08-22 19:52  s百世经纶  阅读(2758)  评论(0编辑  收藏  举报