hankcs/hanlp-lucene-plugin

    <dependency>
      <groupId>com.hankcs.nlp</groupId>
      <artifactId>hanlp-lucene-plugin</artifactId>
      <version>1.1.7</version>
    </dependency>

  <fieldType name="text_cn" class="solr.TextField">
      <analyzer type="index">
          <tokenizer class="com.hankcs.lucene.HanLPTokenizerFactory" enableIndexMode="true"/>
      </analyzer>
      <analyzer type="query">
          <!-- 切记不要在query中开启index模式 -->
          <tokenizer class="com.hankcs.lucene.HanLPTokenizerFactory" enableIndexMode="false"/>
      </analyzer>
  </fieldType>
  <!-- 业务系统中需要分词的字段都需要指定type为text_cn -->
  <field name="my_field1" type="text_cn" indexed="true" stored="true"/>
  <field name="my_field2" type="text_cn" indexed="true" stored="true"/>

    <!-- text_cn字段类型: 指定使用HanLP分词器，同时开启索引模式。通过solr自带的停用词过滤器，使用"stopwords.txt"（默认空白）过滤。
	 在搜索的时候，还支持solr自带的同义词词典。-->
    <fieldType name="text_cn" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="com.hankcs.lucene.HanLPTokenizerFactory" enableIndexMode="true"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <!-- 取消注释可以启用索引期间的同义词词典
        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
        -->
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="com.hankcs.lucene.HanLPTokenizerFactory" enableIndexMode="false"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>
    <!-- 业务系统中需要分词的字段都需要指定type为text_cn -->
    <field name="my_field1" type="text_cn" indexed="true" stored="true"/>
    <field name="my_field2" type="text_cn" indexed="true" stored="true"/>

String text = "中华人民共和国很辽阔";
for (int i = 0; i < text.length(); ++i)
{
    System.out.print(text.charAt(i) + "" + i + " ");
}
System.out.println();
Analyzer analyzer = new HanLPAnalyzer();
TokenStream tokenStream = analyzer.tokenStream("field", text);
tokenStream.reset();
while (tokenStream.incrementToken())
{
    CharTermAttribute attribute = tokenStream.getAttribute(CharTermAttribute.class);
    // 偏移量
    OffsetAttribute offsetAtt = tokenStream.getAttribute(OffsetAttribute.class);
    // 距离
    PositionIncrementAttribute positionAttr = tokenStream.getAttribute(PositionIncrementAttribute.class);
    // 词性
    TypeAttribute typeAttr = tokenStream.getAttribute(TypeAttribute.class);
    System.out.printf("[%d:%d %d] %s/%s\n", offsetAtt.startOffset(), offsetAtt.endOffset(), positionAttr.getPositionIncrement(), attribute, typeAttr.type());
}

tokenizer = new HanLPTokenizer(HanLP.newSegment()
                                    .enableJapaneseNameRecognize(true)
                                    .enableIndexMode(true), null, false);
tokenizer.setReader(new StringReader("林志玲亮相网友:确定不是波多野结衣？"));