solr 引入中文分词器

1 在solr的webapp下创建一个classes文件夹：

IKAnalyzer.cfg.xml:

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">  
<properties>  
	<comment>IK Analyzer 扩展配置</comment>
	<!--用户可以在这里配置自己的扩展字典 -->
	<entry key="ext_dict">ext.dic</entry> 
	
	<!--用户可以在这里配置自己的扩展停止词字典-->
	<entry key="ext_stopwords">my_ext_stopword.dic</entry>
</properties>

 ext.dic:存放同义词：

厉害了我的国
相同,相似,相近
电脑,笔记本电脑=>计算机

 my_ext_stopword.dic：存放停用词：

的
地
了
你
我
他
它
不
嗯
 

需要引入的jar:

配置solrconfig.xml：

<!--增量导入--> 

<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-dataimporthandler-.*\.jar" />

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

db-data-config.xmf增量导入配置文件：

<dataConfig>
    <dataSource 
	driver="com.mysql.jdbc.Driver" 
	url="jdbc:mysql://*****:3306/yjcq_prod?useUnicode=true&amp;characterEncoding=utf-8&amp;serverTimezone=GMT" 
	user="**"  
	password="**"/>
    <document>
        <entity name="video" pk="id"
			query="select * from db_video_copy "
			deltaQuery="select id from db_video_copy where last_modify_time > '${dataimporter.last_index_time}'" 
			deltaImportQuery ="select * from db_video_copy where id = ${dih.delta.id}"
			>
			
			<!--对应统计表-->
			<entity name="statistics" pk="video_id"
			query="select play_num from db_user_video_statistics_copy where video_id = '${video.id}'"
			deltaQuery="select video_id from db_user_video_statistics_copy where last_modify_time > '${dataimporter.last_index_time}'" 
			parentDeltaQuery ="select id from db_video_copy where id = ${statistics.video_id}"
			>
			<field column="play_num" name="play_num"/>
			</entity>
        </entity>
    </document>
</dataConfig>

 managed-schema配置文件添加字段与中文分词器 ：

 <!-- 定义中文分词器字段类型-->
  <fieldType name="my_zh_text" class="solr.TextField" indexed="true" stored="true" >
	<analyzer type="index">
	  <tokenizer class="com.dongnao.lucene.demo.analizer.ik.IkTokenizer4Lucene7Factory" useSmart="true" /> 
	  <filter class="solr.LowerCaseFilterFactory"/>
	  <filter class="solr.StopFilterFactory" words="my_ext_stopword.dic"/>
	  <filter class="solr.SynonymGraphFilterFactory" synonyms="ext.dic"/>
	</analyzer>
	<analyzer type="query">
	  <tokenizer class="com.dongnao.lucene.demo.analizer.ik.IkTokenizer4Lucene7Factory" useSmart="true" />
	</analyzer>
  </fieldType>
  <!-- 自定义的字段类型-->
  <fieldType name="my_str" class="solr.StrField" />
  <fieldType name="my_strs" class="solr.StrField" positionIncrementGap="100" multiValued="true"/>
  <fieldType name="my_bool" class="solr.BoolField"  />
  <fieldType name="my_bools" class="solr.BoolField"  multiValued="true"/>
  <fieldType name="my_int" class="solr.IntPointField"  />
  <fieldType name="my_long" class="solr.LongPointField"  />
  <fieldType name="my_float" class="solr.FloatPointField"  />
  <fieldType name="my_double" class="solr.DoublePointField"  />
  <fieldType name="my_date" class="solr.DatePointField"  />
  <fieldType name="my_ints" class="solr.IntPointField"  multiValued="true" />
  <fieldType name="my_longs" class="solr.LongPointField"  multiValued="true"/>
  <fieldType name="my_floats" class="solr.FloatPointField"  multiValued="true"/>
  <fieldType name="my_doubles" class="solr.DoublePointField"  multiValued="true"/>
  <fieldType name="my_dates" class="solr.DatePointField"  multiValued="true"/>
  <fieldType name="my_str_only_stored" class="solr.StrField" indexed="false" />
  
   <!--video表-->
  <field name="video_name" type="my_zh_text" indexed="true" stored="true" />
  <field name="title_second" type="my_zh_text" />
  <field name="publish_time" type="my_str" />
  <field name="create_time" type="my_date" />
  <field name="module_id" type="my_long" />
  <field name="module_name" type="my_zh_text" />
  <field name="category_one_id" type="my_long" />
  <field name="category_one_name" type="my_zh_text" />
  <field name="category_two_id" type="my_long" />
  <field name="category_two_name" type="my_zh_text" />
  <field name="category_three_id" type="my_long" />
  <field name="category_three_name" type="my_zh_text" />
  <field name="hot" type="my_int" />
  <field name="remark" type="my_zh_text" />
  <field name="pay_type" type="my_int" />
  <field name="free_audio_url" type="my_str" />
  <field name="charge_audio_url" type="my_str"/>
  <field name="free_video_url" type="my_str"  />
  <field name="charge_video_url" type="my_str" />
  <field name="video_type" type="my_int"  />
  <field name="audio_img" type="my_str" />
  <field name="video_img" type="my_str" />
  <field name="image_url" type="my_str" />
  <field name="charge" type="my_str" />
  <field name="sort" type="my_long" />
  <field name="video_time" type="my_long" />
  <field name="spreak_man" type="my_zh_text" />
  <field name="putaway" type="my_int"  />
  <field name="graphic_img_url" type="my_str" />
  <field name="wx_img_url" type="my_str" />
  <field name="label" type="my_zh_text" />
  <field name="search" type="my_zh_text" />
  <field name="titles_time" type="my_long" />
  
  <field name="play_num" type="my_int" />

结果：