OpenSearch/plugins/analysis-kuromoji/rest-api-spec/test/analysis_kuromoji/10_basic.yaml

# Integration tests for Kuromoji analysis components
#
"Tokenizer":
    - do:
        indices.analyze:
          text:         関西国際空港
          tokenizer:    kuromoji_tokenizer
    - length: { tokens: 4 }
    - match:  { tokens.0.token: 関西 }
    - match:  { tokens.1.token: 関西国際空港 }
    - match:  { tokens.2.token: 国際 }
    - match:  { tokens.3.token: 空港 }
---
"Baseform filter":
    - do:
        indices.analyze:
          text:         飲み
          tokenizer:    kuromoji_tokenizer
          filters:      kuromoji_baseform
    - length: { tokens: 1 }
    - match:  { tokens.0.token: 飲む }
---
"Reading filter":
    - do:
        indices.analyze:
          text:         寿司
          tokenizer:    kuromoji_tokenizer
          filters:      kuromoji_readingform
    - length: { tokens: 1 }
    - match:  { tokens.0.token: sushi }
---
"Stemming filter":
    - do:
        indices.analyze:
          text:         サーバー
          tokenizer:    kuromoji_tokenizer
          filters:      kuromoji_stemmer
    - length: { tokens: 1 }
    - match:  { tokens.0.token: サーバ }