solr4.7.2开发实践 ——拼音检索【需要用到的包pinyin4j-2.5.0.jar和pinyinAnalyzer.jar；只需要配置schema.xml文件、solrj的java代码测试】

文章来源：http://my.oschina.net/MrMichael/blog/261231

  拼音检索的大致思路是这样的：

            ①将需要使用拼音检索的字段汇集到一个拼音分词字段里（我的拼音分词字段使用pinyin4j+NGram做的）；

                加入两个jar包：pinyin4j-2.5.0.jar、pinyinAnalyzer.jar；

                schema.xml文件设置：

< field  name = "pinyin"  type ="text_pinyin" indexed ="true" stored ="false" multiValued ="true"/>
< copyField  source = "name"  dest = "pinyin" />
 < copyField  source = "author"  dest = "pinyin" />
 < copyField  source = "region"  dest = "pinyin" />
 < copyField  source = "theme"  dest = "pinyin" />
<!-- by michael: pinyin  -->
  < fieldType  name = "text_pinyin"  class = "solr.TextField"  positionIncrementGap = "0" >
     < analyzer  type = "index" >
     < tokenizer  class = "org.apache.lucene.analysis.cn.smart.SmartChineseSentenceTokenizerFactory" />
     < filter  class = "org.apache.lucene.analysis.cn.smart.SmartChineseWordTokenFilterFactory" />
     < filter  class = "com.shentong.search.analyzers.PinyinTransformTokenFilterFactory"  minTermLenght = "2"  />
     < filter  class = "com.shentong.search.analyzers.PinyinNGramTokenFilterFactory"  minGram = "6"  maxGram = "20"  />
     </ analyzer >
     < analyzer  type = "query" >
     < tokenizer  class = "org.apache.lucene.analysis.cn.smart.SmartChineseSentenceTokenizerFactory" />
     < filter  class = "org.apache.lucene.analysis.cn.smart.SmartChineseWordTokenFilterFactory" />
     < filter  class = "com.shentong.search.analyzers.PinyinTransformTokenFilterFactory"  minTermLenght = "2"  />
     < filter  class = "com.shentong.search.analyzers.PinyinNGramTokenFilterFactory"  minGram = "6"  maxGram = "20"  />
     </ analyzer >
  </ fieldType >

        ②使用solrj进行拼音检索：

/**
 * @method: testPhoneticize
 * @Description: 拼音检索
 *    ??? 也会把不符合条件的检索出来
 *    (解决方法：把汉子和相应的拼音建立同义词)
 * @return void
 *
 * @author: ChenYW
 * @date 2014-4-16 下午01:44:57
 */
    public  List<Map<String, String>> phoneticize(String pinyin){
  try  {
   List<Map<String, String>> list =  new  ArrayList<Map<String, String>>();

   SolrQuery query =  new  SolrQuery();
   query.set( "q" ,  "pinyin:" +pinyin); //高亮查询字段

         QueryResponse qr=server.query(query); //执行查询
         SolrDocumentList dlist=qr.getResults();

         System.out.println( "总数：" +dlist.getNumFound());
         Map<String, String> mapRe =  null ;
         for (SolrDocument sd:dlist){
             mapRe =  new  HashMap<String, String>();
             mapRe.put( "name" , sd.getFieldValue( "name" ).toString());
             mapRe.put( "content" , sd.getFieldValue( "content" ).toString().substring( 0 , 200 ));
             list.add(mapRe);
         }

         return  list;
  }  catch  (SolrServerException e) {
   e.printStackTrace();
  }
  return  null ;
 }