solrStudy-中文分词器

这里选择 IKAnalyzer2012_u5.zip 下载，下载后解压，将解压出来的 IKAnalyzer2012.jar 复制出来。在 D:\apache-solr-3.5.0\example\solr 下新建 lib 目录，将 IKAnalyzer2012.jar 放入 lib 下。打开 “D:\apache-solr-3.5.0\example\solr\conf\schema.xml” ，在 types 节点下 添加

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

      <analyzer type="index">

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

      </analyzer>

      <analyzer type="query">

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

      </analyzer>

    </fieldType>

然后在 fields 节点下引用 text_zh 这一字段类型，如下所示：

1	<field name="title" type="text_zh" indexed="true" stored="true"/>

这样标题字段就支持中文分词了。

 

<schema name="example" version="1.4">
<types>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
<fieldType name="text_zh" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory" useSmart="false"/>
</analyzer>
<analyzer type="query">
<tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory" useSmart="false"/>
</analyzer>
</fieldType>
<fieldType name="url" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1"/>
</analyzer>
</fieldType>
</types>
<fields>
<field name="id" type="string" indexed="true" stored="true" required="true"/>
<field name="title" type="text_zh" indexed="true" stored="true"/>
<field name="description" type="text_zh" indexed="true" stored="true"/>
<field name="pubDate" type="tdate" indexed="true" stored="true"/>
<field name="link" type="url" indexed="true" stored="true"/>
</fields>
<uniqueKey>id</uniqueKey>
<defaultSearchField>title</defaultSearchField>
<solrQueryParser defaultOperator="OR"/>
</schema>