自定义分词器和自动补全

自定义分词器

我们可以在创建索引库时，通过settings来配置自定义的analyzer(分词器)：

PUT /test
{
	"settings":{
		"analysis":{
			"analyzer":{ //自定义分词器
			  "my_analyzer":{ //分词器名称
			  	"tokenizer": "ik_max_word",
			  	"filter":"pinyin"
			  	}
			},
"filter":{ //自定义tokenizer filter
 "py":{ //过滤器名称
 	"type": "pinyin", //过滤器类型，这里是pinyin
 	"keep_full_pinyin": false,
 	"keep_joined_full_pinyin": true,
 	"keep_original": true,
 	"limit_first_letter_length": 16,
 	"remove_duplicated_term": true,
 	"none_chinese_pinyin_tokenize": false	
} 
}
}
},

}

案例

POST /test/_analyze
{
  "text":["如家酒店还不错"],
  "analyzer": "my_analyzer"
}



PUT /test
{
	"settings":{
		"analysis":{
			"analyzer":{ 
			  "my_analyzer":{ 
			  	"tokenizer": "ik_max_word",
			  	"filter":"pinyin"
			  	}
			},
"filter":{ 
 "py":{ 
 	"type": "pinyin", 
 	"keep_full_pinyin": false,
 	"keep_joined_full_pinyin": true,
 	"keep_original": true,
 	"limit_first_letter_length": 16,
 	"remove_duplicated_term": true,
 	"none_chinese_pinyin_tokenize": false	
} 
}
}
},
"mappings": {
  "properties": {
    "name": {
      "type": "text",
      "analyzer": "my_analyzer"
    }
  }
}
}

拼音分词器适合在创建倒排索引的时候使用，但不能在搜索的时候使用
因此字段在创建倒排索引时应该用my_analyzer分词器；字段在搜索时应该使用ik_smart分词器；

PUT /test
{
	"settings":{
		"analysis":{
			"analyzer":{ 
			  "my_analyzer":{ 
			  	"tokenizer": "ik_max_word",
			  	"filter":"py"
			  	}
			},
"filter":{ 
 "py":{ 
 	"type": "pinyin", 
 	"keep_full_pinyin": false,
 	"keep_joined_full_pinyin": true,
 	"keep_original": true,
 	"limit_first_letter_length": 16,
 	"remove_duplicated_term": true,
 	"none_chinese_pinyin_tokenize": false	
} 
}
}
},
"mappings": {
  "properties": {
    "name": {
      "type": "text",
      "analyzer": "my_analyzer",
      "search_analyzer": "ik_smart"
    }
  }
}
}

自动补全

elasticsearch提供了Completion Suggester查询来实现自动补全功能。这个查询会匹配以用户输入内容开头的词条并返回。为了提高补全查询的效率，对于文档中字段的类型有一些约束。

参与补全查询的字段必须是completion类型

//创建索引库
PUT test2
{
	"mappings":{
		"properties":{
			"title":{
				"type":"completion"
			}
		}
}
}

//示例数据
POST test2/_doc
{
	"title": ["Sony","WH-1000XM3"]
}
POST test2/_doc
{
	"title": ["SK-II","PITERA"]
}
POST test2/_doc
{
	"title": ["Nintedo","switch"]
}

案例

查询语法如下:

//自动补全查询
#自动补全
GET /test2/_search
{
	"suggest": {
	  "title_suggest": {
	    "text": "s", 
	    "completion": {
	      "FIELD": "title",
	      "skip_duplicates":true,
	      "size":10
	    }
	  }
	}
}