ES支持汉字、拼音、简拼搜索的自定义分词器

我会带着你远行 2022-05-21 04:07 388阅读 0赞

\{  
  "settings": \{  
    "refresh\_interval": "2s",  
    "number\_of\_shards": 5,  
    "number\_of\_replicas": 1,  
    "analysis": \{  
      "filter": \{  
        "edge\_ngram\_filter": \{  
          "type": "edge\_ngram",  
          "min\_gram": 2,  
          "max\_gram": 20  
        \},  
        "pinyin\_jianpin": \{  
          "type": "pinyin",  
          "first\_letter": "none",  
          "padding\_char": ""  
        \},  
        "pinyin\_simple\_filter": \{  
          "type": "pinyin",  
          "keep\_first\_letter": true,  
          "keep\_separate\_first\_letter": true,  
          "keep\_full\_pinyin": false,  
          "keep\_original": false,  
          "limit\_first\_letter\_length": 20,  
          "lowercase": true  
        \},  
        "pinyin\_full\_filter": \{  
          "type": "pinyin",  
          "keep\_first\_letter": false,  
          "keep\_separate\_first\_letter": false,  
          "keep\_full\_pinyin": true,  
          "none\_chinese\_pinyin\_tokenize": true,  
          "keep\_original": false,  
          "limit\_first\_letter\_length": 20,  
          "lowercase": true  
        \}  
      \},  
      "tokenizer": \{  
        "ik\_smart": \{  
          "type": "ik",  
          "use\_smart": true  
        \}  
      \},  
      "analyzer": \{  
        "ngramIndexAnalyzer": \{  
          "type": "custom",  
          "tokenizer": "ik\_max\_word",  
          "filter": \[  
            "edge\_ngram\_filter",  
            "lowercase"  
          \]  
        \},  
        "ngramSearchAnalyzer": \{  
          "type": "custom",  
          "tokenizer": "whitespace",  
          "filter": \[  
            "lowercase"  
          \]  
        \},  
        "ikIndexAnalyzer": \{  
          "type": "custom",  
          "tokenizer": "ik"  
        \},  
        "ikSearchAnalyzer": \{  
          "type": "custom",  
          "tokenizer": "ik"  
        \},  
        "pinyinSimpleIndexAnalyzer": \{  
          "tokenizer": "ik\_max\_word",  
          "filter": \[  
            "pinyin\_simple\_filter",  
            "edge\_ngram\_filter",  
            "lowercase"  
          \]  
        \},  
        "pinyinSimpleSearchAnalyzer": \{  
          "tokenizer": "whitespace",  
          "filter": \[  
            "pinyin\_simple\_filter",  
            "lowercase"  
          \]  
        \},  
        "jianpinIndexAnalyzer": \{  
          "type": "custom",  
          "tokenizer": "keyword",  
          "filter": \[  
            "pinyin\_first\_letter",  
            "edge\_ngram\_filter",  
            "lowercase"  
          \]  
        \},  
        "jianpinSearchAnalyzer": \{  
          "type": "custom",  
          "tokenizer": "whitespace",  
          "filter": \[  
            "pinyin\_first\_letter",  
            "lowercase"  
          \]  
        \},  
        "pinyinFullIndexAnalyzer": \{  
          "tokenizer": "keyword",  
          "filter": \[  
            "pinyin\_full\_filter",  
            "lowercase"  
          \]  
        \},  
        "pinyinFullSearchAnalyzer": \{  
          "tokenizer": "whitespace",  
          "filter": \[  
            "pinyin\_full\_filter",  
            "lowercase"  
          \]  
        \}  
      \}  
    \}  
  \}  
\}