Elasticsearchのkuromoji_analyzer設定サンプル

elasticsearch_kuromoji_analyzer

PUT /test-index/
{
  "settings": {
    "index":{
      "analysis": {
        "filter": {
          "pos_filter": {
            "type": "kuromoji_part_of_speech",
            "stoptags": [
              "助詞-格助詞-一般",
              "助詞-終助詞"
            ]
          },
          "greek_lowercase_filter": {
            "type": "lowercase",
            "language": "greek"
          }
        },
        "tokenizer": {
          "kuromoji": {
            "type": "kuromoji_tokenizer"
          },
          "ngram_tokenizer": {
            "type": "nGram",
            "min_gram": "2",
            "max_gram": "3",
            "token_chars": [
              "letter",
              "digit"
            ]
          }
        },
        "analyzer": {
          "kuromoji_analyzer": {
            "type": "custom",
            "tokenizer": "kuromoji_tokenizer",
            "filter": [
              "kuromoji_baseform",
              "pos_filter",
              "greek_lowercase_filter",
              "cjk_width"
            ]
          },
          "ngram_analyzer": {
            "tokenizer": "ngram_tokenizer"
          }
        }
      }
    }
  }
}