中文拼音混合检索案例

1.准备工作

从ik和拼音官方github地址下载并安装ik和拼音插件

ik:
https://github.com/medcl/elasticsearch-analysis-ik

pinyin:
https://github.com/medcl/elasticsearch-analysis-pinyin

2.定义拼音和ik分词机制的索引mapping

创建定义mapping 结构的dsl配置文件

创建xml文件-esmapper/estrace/pinyin.xml，定义名称为createDemoIndice的dsl配置：

  1. <property name="createDemoIndice">
  2.     <![CDATA[{
  3.         "settings": {
  4.             "number_of_shards": 6,
  5.             "index.refresh_interval": "5s",
  6.             "analysis" : {
  7.                 "analyzer" : {
  8.                     "pinyin_analyzer" : {
  9.                         "tokenizer" : "my_pinyin"
  10.                         }
  11.                 },
  12.                 "tokenizer" : {
  13.                     "my_pinyin" : {
  14.                         "type" : "pinyin",
  15.                         "keep_separate_first_letter" : false,
  16.                         "keep_full_pinyin" : true,
  17.                         "keep_original" : true,
  18.                         "limit_first_letter_length" : 16,
  19.                         "lowercase" : true,
  20.                         "remove_duplicated_term" : true
  21.                     }
  22.                 }
  23.             }
  24.         },
  25.         "mappings": {
  26.             "demo": {
  27.                 "properties": {
  28.                     "contentbody": {
  29.                         "type": "text",
  30.                         "term_vector": "with_positions_offsets",
  31.                         "analyzer": "ik_max_word",
  32.                         "search_analyzer": "ik_max_word",
  33.                         "fields": {
  34.                             "keyword": {
  35.                                 "type": "keyword"
  37.                             }
  38.                         }
  39.                     },
  40.                     "agentStarttime": {
  41.                         "type": "date",
  42.                         "format":"yyyy-MM-dd HH:mm:ss.SSS||yyyy-MM-dd'T'HH:mm:ss.SSS||yyyy-MM-dd HH:mm:ss||epoch_millis"
  43.                     },
  44.                     "applicationName": {
  45.                         "type": "text",
  46.                         "fields": {
  47.                             "keyword": {
  48.                                 "type": "keyword"
  49.                             }
  50.                         }
  51.                     },
  52.                     "name": {
  53.                         "type": "text",
  54.                         "fields": {
  55.                             "pinyin": { ## 定义内置pinyin字段，采用拼音分词器
  56.                                 "type": "text",
  57.                                 "store": false,
  58.                                 "term_vector": "with_offsets",
  59.                                 "analyzer": "pinyin_analyzer",
  60.                                 "boost": 10
  61.                             }
  62.                         }
  63.                     }
  64.                 }
  65.             }
  66.         }
  67.     }]]>
  68. </property>

加载配置文件并创建demo索引结构

  1. public void testCreateDemoMapping(){
  3.       ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil("esmapper/estrace/pinyin.xml");
  4.       try {
  5.          //可以先删除索引mapping，重新初始化数据
  6.          clientUtil.dropIndice("demo");
  7.       } catch (ElasticSearchException e) {
  8.          // TODO Auto-generated catch block
  9.          e.printStackTrace();
  10.       }
  13. //
  14.       //创建索引表结构
  15.       String response = clientUtil.createIndiceMapping("demo","createDemoIndice");
  16. //       获取并打印创建的索引表结构
  17.       System.out.println(clientUtil.getIndice("demo"));
  19.    }

3.添加测试数据

  1. ClientInterface clientUtil = ElasticSearchHelper.getRestClientUtil();
  2. List<Demo> demos = new ArrayList<>();
  3. Demo demo = new Demo();
  4. demo.setDemoId(2l);
  5. demo.setAgentStarttime(new Date());
  6. demo.setApplicationName("blackcatdemo2");
  7. demo.setContentbody("this is content body2");
  8. demo.setName("刘德华");
  9. demos.add(demo);
  11. demo = new Demo();
  12. demo.setDemoId(3l);
  13. demo.setAgentStarttime(new Date());
  14. demo.setApplicationName("blackcatdemo3");
  15. demo.setContentbody("四大天王，这种文化很好，中华人民共和国");
  16. demo.setName("张学友");
  17. demos.add(demo);
  19. //创建模板
  20. String response = clientUtil.addDocuments("demo",//索引表
  21.       "demo",//索引类型
  22.       demos);
  24. System.out.println("addDocuments-------------------------");
  25. System.out.println(response);
  27. //验证创建的两条索引记录
  28. response = clientUtil.getDocument("demo",//索引表
  29.       "demo",//索引类型
  30.       "2");
  31. System.out.println("getDocument-------------------------");
  32. System.out.println(response);
  34. demo = clientUtil.getDocument("demo",//索引表
  35.       "demo",//索引类型
  36.       "3",//文档id
  37.       Demo.class);

4.拼音检索

定义拼音检索dsl

在之前定义的pinyin.xml文件中新增dsl配置-searchPinyinDemo

  1. <property name="searchPinyinDemo"><![CDATA[{
  2.     "size": 100,
  3.     "query": {
  4.         "bool": {
  5.             "must": [
  6.                 {
  7.                       "match_phrase_prefix" : {
  8.                             "name" : {
  9.                                 "query" : #[name],
  10.                                 "max_expansions" : 10
  11.                             }
  12.                         }
  14.                 }
  15.             ]
  16.         }
  17.     }
  18. }]]></property>

执行拼音检索操作

  1. @Test
  2. public void searchPinyinDemo(){
  3.    ClientInterface clientUtil = ElasticSearchHelper.getConfigRestClientUtil("esmapper/estrace/pinyin.xml");
  4.    Map<String,String> params = new HashMap<String,String>();
  5.    params.put("name","zhang学友");//设置中文拼音混合检索条件
  6.       ESDatas<Map> esDatas = clientUtil.searchList("demo/_search","searchPinyinDemo",params,Map.class);
  7.       List<Map> datas = esDatas.getDatas();
  8.       long totalSize = esDatas.getTotalSize();
  9. }