Elasticsearch__Analyzer

分词器的组成：

Character Filter、Tokenizer、Token Filter

1. Character Filter 分成

HTML strip   去除html标签；     Mapping   字符串替换；   Pattern replace  正则匹配替换

2. Tokenizer 分成

whitespace/standard/uax_url_email/pattern/keyword/path hierarchy 路径分词器

3. Token Filter 分成

Lowercase/stop/synonym(近义词)

 

POST _analyze
{
  "tokenizer": "keyword",
  "char_filter": ["html_strip"],
  "text": "<b>hello world</b>"
}

POST _analyze
{
  "tokenizer": "standard",
  "char_filter": [
    {
      "type":"mapping",
      "mappings":[":) => happy",":( => sad"]
    }
    ],
    "text": ["I am felling :)","Feeling :( today"]
}

POST _analyze
{
  "tokenizer": "standard",
  "char_filter": [
    {
      "type":"pattern_replace",
      "pattern":"http://(.*)",
      "replacement":"$1"
    }
    ],
    "text": "http://www.elasti.co"
}

POST _analyze
{
  "tokenizer": "path_hierarchy",
  "text":"/user/ymruan/a/b"
}

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

POST my_index/_analyze
{
  "analyzer": "my_custom_analyzer",
  "text": "I`m a :) person,and you?"
}