Elasticsearch 混合 NGram 与简单查询字符串查询

Question

目前，我正在使用 Ngram 标记器对员工进行部分匹配。

我可以匹配全名、电子邮件地址和员工编号

我当前的设置如下：

"tokenizer": {
  "my_tokenizer": {
    "type": "ngram",
    "min_gram": 3,
    "max_gram": 3,
    "token_chars": [
      "letter",
      "digit"
    ]
  }
}

我面临的问题是 Employee Number 可以是 1 个字符长，并且由于 min_gram 和 max_gram，我永远不能匹配。我也无法将 min_gram 设为 1，因为结果看起来不正确。

所以我尝试将 Ngram 与标准标记器混合，而不是在 Multimatch 搜索中进行，而是在做 simple_query_string。

这似乎也部分起作用。

我的问题是如何在所有 3 个字段上进行部分匹配，记住员工编号可以是 1 或 2 个字符长。如果我在单词或数字周围使用半引号，则完全匹配

在下面的示例中，如何搜索 11 并返回文档 4 和 5？ 另外，如果我必须搜索部分匹配的 706，我希望返回文档 2，但如果我必须使用“7061”进行搜索，我只会返回文档 2

完整代码

PUT index
{
  "settings": {
    "analysis": {
      "analyzer": {
        "english_exact": {
          "tokenizer": "standard",
          "filter": [
            "lowercase"
          ]
        },
        "my_analyzer": {
            "filter": [
              "lowercase",
              "asciifolding"
            ],
            "tokenizer": "my_tokenizer"
          }
      },
       "tokenizer": {
          "my_tokenizer": {
            "type": "ngram",
            "min_gram": 3,
            "max_gram": 3,
            "token_chars": [
              "letter",
              "digit"
            ]
          }
        },
       "normalizer": {
          "lowersort": {
            "type": "custom",
            "filter": [
              "lowercase"
            ]
          }
        }
    }
  },
  "mappings": {
    "properties": {
      "number": {
        "type": "text",
        "analyzer": "english",
        "fields": {
          "exact": {
            "type": "text",
            "analyzer": "english_exact"
          }
        }
      },
       "fullName": {
        "type": "text",
        "fields": {
          "ngram": {
            "type": "text",
            "analyzer": "my_analyzer"
          }
        },
        "analyzer": "standard"
      }
    }
  }
}
PUT index/_doc/1
{
  "number" : 1,
  "fullName": "Brenda eaton"
}

PUT index/_doc/2
{
  "number" : 7061,
  "fullName": "Bruce wayne"
}

PUT index/_doc/3
{
  "number" : 23,
  "fullName": "Bruce Banner"
}

PUT index/_doc/4
{
  "number" : 111,
  "fullName": "Cat woman"
}

PUT index/_doc/5
{
  "number" : 1112,
  "fullName": "0723568521"
}

GET index/_search
{
  "query": {
    "simple_query_string": {
      "fields": [ "fullName.ngram", "number.exact"],
      "query": "11"
    }
  }
}

Answer 1

您需要更改number.exact字段的分析器并减少min_gram 计数为2。修改索引映射如下图

添加一个工作示例

索引映射：

    {
  "settings": {
    "analysis": {
      "analyzer": {
        "english_exact": {
          "tokenizer": "standard",
          "filter": [
            "lowercase"
          ]
        },
        "my_analyzer": {
          "filter": [
            "lowercase",
            "asciifolding"
          ],
          "tokenizer": "my_tokenizer"
        }
      },
      "tokenizer": {
        "my_tokenizer": {
          "type": "ngram",
          "min_gram": 2,
          "max_gram": 3,
          "token_chars": [
            "letter",
            "digit"
          ]
        }
      },
      "normalizer": {
        "lowersort": {
          "type": "custom",
          "filter": [
            "lowercase"
          ]
        }
      }
    }
  },
  "mappings": {
    "properties": {
      "number": {
        "type": "keyword",          // note this
        "fields": {
          "exact": {
            "type": "text",
            "analyzer": "my_analyzer"
          }
        }
      },
      "fullName": {
        "type": "text",
        "fields": {
          "ngram": {
            "type": "text",
            "analyzer": "my_analyzer"
          }
        },
        "analyzer": "standard"
      }
    }
  }
}

搜索查询：

{
  "query": {
    "simple_query_string": {
      "fields": [ "fullName.ngram", "number.exact"],
      "query": "11"
    }
  }
}

搜索结果：

"hits": [
      {
        "_index": "66311552",
        "_type": "_doc",
        "_id": "4",
        "_score": 0.9929736,
        "_source": {
          "number": 111,
          "fullName": "Cat woman"
        }
      },
      {
        "_index": "66311552",
        "_type": "_doc",
        "_id": "5",
        "_score": 0.8505551,
        "_source": {
          "number": 1112,
          "fullName": "0723568521"
        }
      }
    ]

更新 1：

如果只需要搜索1，将number字段的数据类型从text类型修改为keyword类型，如上面的索引映射所示。

搜索查询：

{
  "query": {
    "simple_query_string": {
      "fields": [ "fullName.ngram", "number.exact","number"],
      "query": "1"
    }
  }
}

搜索结果将是

"hits": [
      {
        "_index": "66311552",
        "_type": "_doc",
        "_id": "1",
        "_score": 1.3862942,
        "_source": {
          "number": 1,
          "fullName": "Brenda eaton"
        }
      }
    ]

更新 2：

您可以为 fullName 字段和 number 字段使用两个带有 n-gram 标记器的单独分析器。使用以下索引映射进行修改：

{
  "settings": {
    "analysis": {
      "analyzer": {
        "english_exact": {
          "tokenizer": "standard",
          "filter": [
            "lowercase"
          ]
        },
        "name_analyzer": {
          "filter": [
            "lowercase",
            "asciifolding"
          ],
          "tokenizer": "name_tokenizer"
        },
        "number_analyzer": {
          "filter": [
            "lowercase",
            "asciifolding"
          ],
          "tokenizer": "number_tokenizer"
        }
      },
      "tokenizer": {
        "name_tokenizer": {
          "type": "ngram",
          "min_gram": 3,
          "max_gram": 3,
          "token_chars": [
            "letter",
            "digit"
          ]
        },
         "number_tokenizer": {
          "type": "ngram",
          "min_gram": 2,
          "max_gram": 3,
          "token_chars": [
            "letter",
            "digit"
          ]
        }
      },
      "normalizer": {
        "lowersort": {
          "type": "custom",
          "filter": [
            "lowercase"
          ]
        }
      }
    }
  },
  "mappings": {
    "properties": {
      "number": {
        "type": "keyword",
        "fields": {
          "exact": {
            "type": "text",
            "analyzer": "number_analyzer"
          }
        }
      },
      "fullName": {
        "type": "text",
        "fields": {
          "ngram": {
            "type": "text",
            "analyzer": "name_analyzer"
          }
        },
        "analyzer": "standard"
      }
    }
  }
}