ElasticSearch自定义分词器

ElasticSearch自定义分词器

酒店数据索引库

DELETE /hotel
# 酒店数据索引库
PUT /hotel
{
  "settings": {
    "analysis": {
      "analyzer": {
        "text_anlyzer": {
          "tokenizer": "ik_max_word",
          "filter": "py"
        },
        "completion_analyzer": {
          "tokenizer": "keyword",
          "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": {
      "id": {
        "type": "keyword"
      },
      "name": {
        "type": "text",
        "analyzer": "text_anlyzer",
        "search_analyzer": "ik_smart",
        "copy_to": "all"
      },
      "address": {
        "type": "keyword",
        "index": false
      },
      "price": {
        "type": "integer"
      },
      "score": {
        "type": "integer"
      },
      "brand": {
        "type": "keyword",
        "copy_to": "all"
      },
      "city": {
        "type": "keyword"
      },
      "starName": {
        "type": "keyword"
      },
      "business": {
        "type": "keyword",
        "copy_to": "all"
      },
      "location": {
        "type": "geo_point"
      },
      "pic": {
        "type": "keyword",
        "index": false
      },
      "all": {
        "type": "text",
        "analyzer": "text_anlyzer",
        "search_analyzer": "ik_smart"
      },
      "suggestion": {
        "type": "completion",
        "analyzer": "completion_analyzer"
      }
    }
  }
}

DELETE /test

# 自定义分词器
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"
      }
    }
  }
}

POST /test/_doc/3
{
  "id": 1,
  "name": "狮子"
}


POST /test/_doc/4
{
  "id": 2,
  "name": "柿子"
}

GET /test/_search
{
  "query": {
    "match": {
      "name": "调入狮子笼怎么办"
    }
  }
}