elasticsearch中英文查询

插件安装

• 安装IK Analysis插件 下载

  mkdir /plugins/ik
  #解压
  elasticsearch-analysis-ik.zip
  

• pinyin插件 下载

  mkdir /plugins/pinyin
  #解压
  elasticsearch-analysis-pinyin-6.8.1.zip
  

ik使用

• 建索引

  PUT /index
  #设置分析方式
  POST /index/fulltext/_mapping
  {
    "properties": {
      "content":{
        "type": "text",
        "analyzer": "ik_max_word",
        "search_analyzer": "ik_max_word"
      }
    }
  }
  

• 插入数据

  POST /index/fulltext/1
  {"content":"美国留给伊拉克的是个烂摊子吗"}
  
  POST /index/fulltext/2
  {"content":"公安部：各地校车将享最高路权"}
  
  POST /index/fulltext/3
  {"content":"中韩渔警冲突调查：韩警平均每天扣1艘中国渔船"}
  
  POST /index/fulltext/4
  {"content":"中国驻洛杉矶领事馆遭亚裔男子枪击 嫌犯已自首"}
  

• 查询

  POST /index/fulltext/_search
  {
    "query": {
      "match": {
        "content": "中国"
      }
    },
    "highlight": {
      "pre_tags": ["<tag1>","<tag2>"],
      "post_tags": ["</tag1>","</tag2>"],
      "fields": {
        "content": {}
      }
    }
  }
  

pinyin使用

• 自定义拼音分析器创建索引

  PUT /medcl/ 
  {
      "index" : {
          "analysis" : {
              "analyzer" : {
                  "pinyin_analyzer" : {
                      "tokenizer" : "my_pinyin"
                      }
              },
              "tokenizer" : {
                  "my_pinyin" : {
                      "type" : "pinyin",
                      "keep_separate_first_letter" : false,
                      "keep_full_pinyin" : true,
                      "keep_original" : true,
                      "limit_first_letter_length" : 16,
                      "lowercase" : true,
                      "remove_duplicated_term" : true
                  }
              }
          }
      }
  }
  # 分析
  GET /medcl/_analyze
  {
    "text": ["刘德华"],
    "analyzer": "pinyin_analyzer"
  }
  

• 创建映射mapping

  POST /medcl/folks/_mapping 
  {
      "folks": {
          "properties": {
              "name": {
                  "type": "keyword",
                  "fields": {
                      "pinyin": {
                          "type": "text",
                          "store": false,
                          "term_vector": "with_offsets",
                          "analyzer": "pinyin_analyzer",
                          "boost": 10
                      }
                  }
              }
          }
      }
  }
  

• 插入数据并查询

  POST /medcl/folks/andy 
  {"name":"刘德华"}
  
  #查询
  GET /medcl/_search
  {
    "query": {
      "match": {
        "name.pinyin": "刘dehua"
      }
    }
  }