POST _analyze
{
  "tokenizer": "standard",
  "filter": ["lowercase"],
  "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}

# analyzer = char_filter + tokenizer + token filter
# standard anylyzer = {
#  standard tokenizer 
#  + 
#  standard lower filter
#  lower case filter
#  stop filter (默认禁用)
# }
POST _analyze
{
  "analyzer": "standard",
  "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}

# simple analyzer = {
#   lower case tokenizer
# }
POST _analyze
{
  "analyzer": "simple",
  "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}

# whitespace analyzer = {
#   whitespace tokenizer
# }
POST _analyze
{
  "analyzer": "whitespace", 
  "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}


# stop analyzer = {
#   lower case tokenizer
#   +
#   stop filter
# }
POST _analyze
{
  "analyzer": "stop",
  "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}


# keyword analyzer = {
#   keyword tokenizer
# }
POST _analyze
{
  "analyzer": "keyword",
  "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}


# pattern analyzer = {
#   pattern tokenizer
#   +
#   lower case filter
#   stop filter (默认禁用)
# }
# 默认是\W+
POST _analyze
{
  "analyzer": "pattern",
  "text": "The 2 QUICK Brown-Foxes jumped over the lazy dog's bone."
}

中文分词

• elasticsearch-analysis-ik
• jieba
• Hanlp
• THULAC

自定义分词

PUT test_index2
{
  "settings": {
    "analysis": {
      "analyzer": {
        "my_custom_analyzer": {
          "type": "custom",
          "char_filter": [
            "emoticons"  
          ],
          "tokenizer": "punctuation",
          "filter": [
            "lowercase",
            "english_stop"
          ]
        }
      },
      "char_filter": {
        "emoticons": {
          "type": "mapping",
          "mappings": [
            ":) => _happy_",
            ":( => _sad_"
          ]
        }
      },
      "tokenizer": {
        "punctuation": {
          "type": "pattern",
          "pattern": "[.,!?]"
        }
      },
      "filter": {
        "english_stop": {
          "type": "stop",
          "stopwords": "_english_"
        }
      }
    }
  }
}

POST test_index2/_analyze
{
  "analyzer": "my_custom_analyzer",
  "text": "I'm a :) person, and you"
}