環(huán)境

• Ubuntu18.04
• ES 6.6.1

分詞插件

1. 中文： https://github.com/medcl/elasticsearch-analysis-ik/releases/
2. 拼音： https://github.com/medcl/elasticsearch-analysis-pinyin/releases/
3. 簡(jiǎn)體/繁體轉(zhuǎn)換：https://github.com/medcl/elasticsearch-analysis-stconvert/releases/

安裝插件

1. 下載es對(duì)應(yīng)版本的插件，解壓，copy to ES_HOME/plugins
2. restart es

ik 分詞器使用

GET /_analyze
{
  "text":"中華人民共和國(guó)國(guó)徽",
  "analyzer":"ik_smart"
}

GET /_analyze
{
  "text":"中華人民共和國(guó)國(guó)徽",
  "analyzer":"ik_max_word"
}

pinyin分詞器使用

GET /_analyze
{
  "text": "劉德華",
  "analyzer": "pinyin"
}

簡(jiǎn)體/繁體轉(zhuǎn)換 分詞

PUT /stconvert/
{
    "settings" : {
        "analysis" : {
            "analyzer" : {
                "tsconvert" : {
                    "tokenizer" : "tsconvert"
                    }
            },
            "tokenizer" : {
                "tsconvert" : {
                    "type" : "stconvert",
                    "delimiter" : "#",
                    "keep_both" : false,
                    "convert_type" : "t2s"
                }
            },   
             "filter": {
               "tsconvert" : {
                     "type" : "stconvert",
                     "delimiter" : "#",
                     "keep_both" : false,
                     "convert_type" : "t2s"
                 }
             },
            "char_filter" : {
                "tsconvert" : {
                    "type" : "stconvert",
                    "convert_type" : "t2s"
                }
            }
        }
    }
}

GET stconvert/_analyze
{
  "tokenizer" : "keyword",
  "filter" : ["lowercase"],
  "char_filter" : ["tsconvert"],
  "text" : "國(guó)際國(guó)際"
}

ik分詞 和 pinyin分詞 組合使用

PUT /my_index
{
  "settings": {
        "analysis": {
            "analyzer": {
                "ik_smart_pinyin": {
                    "type": "custom",
                    "tokenizer": "ik_smart",
                    "filter": ["my_pinyin", "word_delimiter"]
                },
                "ik_max_word_pinyin": {
                    "type": "custom",
                    "tokenizer": "ik_max_word",
                    "filter": ["my_pinyin", "word_delimiter"]
                }
            },
            "filter": {
                "my_pinyin": {
                    "type" : "pinyin",
                    "keep_separate_first_letter" : true,
                    "keep_full_pinyin" : true,
                    "keep_original" : true,
                    "limit_first_letter_length" : 16,
                    "lowercase" : true,
                    "remove_duplicated_term" : true 
                }
            }
        }
  }
}

PUT /my_index/my_type/_mapping
{
    "my_type":{
      "properties": {
        "id":{
          "type": "integer"
        },
        "name":{
          "type": "text",
          "analyzer": "ik_smart_pinyin"
        }
      }
    }
}

POST /my_index/my_type/_bulk
{ "index": { "_id":1}}
{ "name": "張三"}
{ "index": { "_id": 2}}
{ "name": "張四"}
{ "index": { "_id": 3}}
{ "name": "李四"}

GET /my_index/my_type/_search
{
  "query": {
    "match": {
      "name": "zhang"
    }
  }
}

GET /my_index/my_type/_search
{
  "query": {
    "match_phrase": {
      "name": "zs"
    }
  }
}