docker构建solr及ik和拼音分词

• solr 8.2 docker部署

docker run --name solr  -d -p 8999:8983 -t solr:8.2.0

ik-analyzer-8.2.0https://search.maven.org/artifact/com.github.magese/ik-analyzer/8.2.0/jar

拼音分词下载https://files-cdn.cnblogs.com/files/wander1129/pinyin.zip

• 将jar包拷贝至docker中

docker cp *.jar solr:solr:/opt/solr-8.2.0/server/solr-webapp/webapp/WEB-INF/lib
# *.jar为ik-analyzer-8.2.0.jar、lucene-analyzers-smartcn-8.2.0.jar、pinyin4j-2.5.0.jar、pinyinAnalyzer4.3.1.jar几个文件

• 构建镜像

docker commit solr solr-ik-pinyin:8.2.0

• 构建数据集

docker exec -it --user=solr solr bin/solr create_core -c demo_core

• 修改demo_core的managed-schema，添加如下配置：

    <dynamicField name="*_text_ik" type="text_ik"  indexed="true"  stored="true"/>
    <fieldType name="text_ik" class="solr.TextField">
      <analyzer type="index">
        <tokenizer class="org.wltea.analyzer.lucene.IKTokenizerFactory" useSmart="true"/>
        <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
        <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="org.wltea.analyzer.lucene.IKTokenizerFactory" useSmart="true"/>
        <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
        <filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
      </analyzer>
    </fieldType>

    <dynamicField name="*_text_pinyin" type="text_ik"  indexed="true"  stored="true"/>
    <fieldType name="text_pinyin" class="solr.TextField" positionIncrementGap="0">
      <analyzer type="index">
        <tokenizer class="org.wltea.analyzer.lucene.IKTokenizerFactory" useSmart="true"/>
        <filter class="com.shentong.search.analyzers.PinyinTransformTokenFilterFactory" minTermLenght="2"/>
        <filter class="com.shentong.search.analyzers.PinyinNGramTokenFilterFactory" maxGram="20" minGram="1"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="org.wltea.analyzer.lucene.IKTokenizerFactory" useSmart="true"/>
        <filter class="com.shentong.search.analyzers.PinyinTransformTokenFilterFactory" minTermLenght="2"/>
        <filter class="com.shentong.search.analyzers.PinyinNGramTokenFilterFactory" maxGram="20" minGram="1"/>
      </analyzer>
    </fieldType>

• 重启docker测试即可