ELasticSearch设置ik+pinyin分词器

1

$ cd ${docker-compose-file-dir}

1

$ docker-compose exec es01 elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v7.6.0/elasticsearch-analysis-ik-7.6.0.zip

1

$ docker-compose exec es01 elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-pinyin/releases/download/v7.6.0/elasticsearch-analysis-pinyin-7.6.0.zip

1

$ docker-compose restart

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64

PUT /my_index
{
    "settings": {
        "index": {
            "number_of_shards": "1",
            "analysis": {
                "analyzer": {
                    "default": {
                        "tokenizer": "ik_max_word"
                    },
                    "pinyin_analyzer": {
                        "type": "custom",
                        "tokenizer": "my_pinyin",
                        "filter": [
                            "word_delimiter"
                        ]
                    }
                },
                "tokenizer": {
                    "my_pinyin": {
                        "type": "pinyin",
                        "keep_first_letter": true,
                        "keep_separate_first_letter": false,
                        "keep_full_pinyin": true,
                        "keep_original": false,
                        "limit_first_letter_length": 16,
                        "lowercase": true
                    }
                },
                "number_of_replicas": "1"
            }
        }
    },
    "mappings": {
        "properties": {
            "id": {
                "type": "keyword",
                "fields": {
                    "keyword": {
                        "type": "keyword",
                        "ignore_above": 256
                    }
                }
            },
            "name": {
                "type": "text",
                "analyzer": "ik_max_word",
                "copy_to": true,
                "fields": {
                    "pinyin": {
                        "type": "text",
                        "term_vector": "with_positions_offsets",
                        "analyzer": "pinyin_analyzer",
                        "boost": 10
                    },
                    "keyword": {
                        "type": "keyword",
                        "ignore_above": 256
                    }
                }
            }
        }
    }
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

## 请求
POST /my_index/_analyze
{
  "text":"sao的一逼",
  "analyzer":"pinyin_analyzer"
}
## 结果
{
  "tokens" : [
    {
      "token" : "sao",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "saodyb",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "de",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 1
    },
    {
      "token" : "yi",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 2
    },
    {
      "token" : "bi",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 3
    }
  ]
}

1

略

1
2
3
4
5
6
7
8

POST /my_index/_search
{
    "query":{
      "match":{
        "name.pinyin":"liudehua"
      }
    }
}

1
2
3
4
5
6
7
8

POST /my_index/_search
{
    "query":{
      "match":{
        "name":"靖哥哥"
      }
    }
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

POST /my_index/_search
{
	"query": {
    "multi_match": {
      "type":"most_fields",
      "query":"jing",
      "fields":["name", "name.pinyin"]
    }
  }
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

GET my_index/_validate/query?explain
{
  "query": {
    "multi_match": {
      "type":"most_fields",
      "query":"靖g哥",
      "fields":["name", "name.pinyin"]
    }
  }
}
## 结果
{
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "failed" : 0
  },
  "valid" : true,
  "explanations" : [
    {
      "index" : "my_index",
      "valid" : true,
      "explanation" : "((Synonym(name.pinyin:jgg name.pinyin:jing) (name.pinyin:g)^10.0 (name.pinyin:ge)^10.0) | (name:靖 name:g name:哥))~1.0"
    }
  ]
}