solr1.4.1添加Analyzer3.1.6GA中文分词器

 

mmseg4j-1.8.3版本支持solr1.4.1，当前最高版本版本mmseg1.8.5版本过高不支持solr1.4.1

在$SOLR_HOME目录下新建lib,dic两个文件夹

下载IKAnalyzer3.1.6GA_AllInOne.rar到D:/solrworkspace/IKAnalyzer3.1.6GA_AllInOne.rar

解压D:/solrworkspace/IKAnalyzer3.1.6GA_AllInOne.rar为D:/solrworkspace/IKAnalyzer3.1.6GA_AllInOne($IKANALYZER_HOME)

新建目录 $SOLR_HOME/dic目录，并添加自定义词库

复制$IKANALYZER_HOME/IKAnalyzer3.1.6GA.jar到目录$SOLR_HOME/lib目录下

修改$SOLR_HOME/config/schema.xml

 <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <!-- in this example, we will only use synonyms at query time
        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
        -->
        <!-- Case insensitive stop word removal.
          add enablePositionIncrements=true in both the index and query
          analyzers to leave a 'gap' for more accurate phrase queries.
        -->
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="stopwords.txt"
                enablePositionIncrements="true"
                />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="stopwords.txt"
                enablePositionIncrements="true"
                />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
      </analyzer>
    </fieldType>

 <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory14" isMaxWordLength="false"/>
       <!--tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="max-word" dicPath="dic"/--> 
        <!--tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="simple" dicPath="my_dic"/--> 
        <!--tokenizer class="solr.WhitespaceTokenizerFactory"/-->
        <!-- in this example, we will only use synonyms at query time
        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
        -->
        <!-- Case insensitive stop word removal.
          add enablePositionIncrements=true in both the index and query
          analyzers to leave a 'gap' for more accurate phrase queries.
        -->
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="stopwords.txt"
                enablePositionIncrements="true"
                />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="org.wltea.analyzer.solr.IKTokenizerFactory14" isMaxWordLength="false"/>
  <!--tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="max-word" dicPath="dic"/--> 
        <!--tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="simple" dicPath="my_dic"/--> 
        <!--tokenizer class="solr.WhitespaceTokenizerFactory"/-->
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="stopwords.txt"
                enablePositionIncrements="true"
                />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
      </analyzer>
    </fieldType>

 

添加field字段   <field name="textIKAnalyzer" type="text" indexed="true" stored="false"/>

访问http://localhost:8080/solr/admin/analysis.jsp

Filed 选择框选择 name    后面的输入框填写textIKAnalyzer

Field value (Index) 被索引的分词词组，Field value (Query) 被查询的分词词组

后面的输入框输入你想要被分词的语句或词组  

点击Analyze可以看到分词后被索引，和查询的结果