3-11的自定义分词不生效

Question

跟着视频敲的， 不生效

PUT test_index_2
{
	"settings": {
		"analysis": {
			"analyzer": {
				"my_custom_analyzer": {
					"type": "custom",
					"char_filter": [
						"emoticons"
					],
					"tokenizer": "punctuation",
					"filter": [
						"lowercase",
						"english_stop"
					]
				}
			},
			"tokenizer": {
				"punctuation": {
					"type": "pattern",
					"pattern": "[.,?!]"
				}
			},
			"char_filter": {
				"emoticons": {
					"type": "mapping",
					"mappings": [
						":)=>happy",
						":(=>cry"
					]
        }
			},
			"filter": {
				"english_stop": {
					"type": "stop",
					"stopwords": "_english_"
				}
			}
		}
	}
}

Answer 1

rockybean 2021-02-28 07:58:41

这个是因为你 :) 配置和测试不一致，前者英文，后者中文，参见下面

GET test_index_2/_analyze

{

  "analyzer": "my_custom_analyzer",

  "text": "hi, he drink milk! :)"

}

PUT test_index_2

{

"settings": {

"analysis": {

"analyzer": {

"my_custom_analyzer": {

"type": "custom",

"char_filter": [

"emoticons"

],

"tokenizer": "punctuation",

"filter": [

"lowercase",

"english_stop"

]

}

},

"tokenizer": {

"punctuation": {

"type": "pattern",

"pattern": "[.,?!]"

}

},

"char_filter": {

"emoticons": {

"type": "mapping",

"mappings": [

":)=>happy",

":(=>cry"

]

        }

},

"filter": {

"english_stop": {

"type": "stop",

"stopwords": "_english_"

}

}

}

}

}

Answer 2

rockybean 2021-02-27 18:19:45

es 的版本是多少？

报错是什么？

• 提问者 rick_and_ #1

  版本7.X 没有报错，但是分词没生效.
  POST test_index_1/_analyze
  {
  	"analyzer": "my_analyzer",
  	"text": "hi, he drink milk! :）"
  }
  分词的结果是这样
  {
    "tokens" : [
      {
        "token" : "hi",
        "start_offset" : 0,
        "end_offset" : 2,
        "type" : "word",
        "position" : 0
      },
      {
        "token" : " he drink milk",
        "start_offset" : 3,
        "end_offset" : 17,
        "type" : "word",
        "position" : 1
      },
      {
        "token" : " :）",
        "start_offset" : 18,
        "end_offset" : 21,
        "type" : "word",
        "position" : 2
      }
    ]
  }