« meta normalizer »
Elastic 文档 ›Elasticsearch 指南 [8.17] ›映射 ›映射参数

fields

编辑

fields

编辑

在不同的场景下，以不同的方式索引同一个字段通常很有用。这就是多字段的目的。例如，一个 string 字段可以被映射为用于全文搜索的 text 字段，以及用于排序或聚合的 keyword 字段。

resp = client.indices.create(
    index="my-index-000001",
    mappings={
        "properties": {
            "city": {
                "type": "text",
                "fields": {
                    "raw": {
                        "type": "keyword"
                    }
                }
            }
        }
    },
)
print(resp)

resp1 = client.index(
    index="my-index-000001",
    id="1",
    document={
        "city": "New York"
    },
)
print(resp1)

resp2 = client.index(
    index="my-index-000001",
    id="2",
    document={
        "city": "York"
    },
)
print(resp2)

resp3 = client.search(
    index="my-index-000001",
    query={
        "match": {
            "city": "york"
        }
    },
    sort={
        "city.raw": "asc"
    },
    aggs={
        "Cities": {
            "terms": {
                "field": "city.raw"
            }
        }
    },
)
print(resp3)
response = client.indices.create(
  index: 'my-index-000001',
  body: {
    mappings: {
      properties: {
        city: {
          type: 'text',
          fields: {
            raw: {
              type: 'keyword'
            }
          }
        }
      }
    }
  }
)
puts response

response = client.index(
  index: 'my-index-000001',
  id: 1,
  body: {
    city: 'New York'
  }
)
puts response

response = client.index(
  index: 'my-index-000001',
  id: 2,
  body: {
    city: 'York'
  }
)
puts response

response = client.search(
  index: 'my-index-000001',
  body: {
    query: {
      match: {
        city: 'york'
      }
    },
    sort: {
      'city.raw' => 'asc'
    },
    aggregations: {
      "Cities": {
        terms: {
          field: 'city.raw'
        }
      }
    }
  }
)
puts response
{
	res, err := es.Indices.Create(
		"my-index-000001",
		es.Indices.Create.WithBody(strings.NewReader(`{
	  "mappings": {
	    "properties": {
	      "city": {
	        "type": "text",
	        "fields": {
	          "raw": {
	            "type": "keyword"
	          }
	        }
	      }
	    }
	  }
	}`)),
	)
	fmt.Println(res, err)
}

{
	res, err := es.Index(
		"my-index-000001",
		strings.NewReader(`{
	  "city": "New York"
	}`),
		es.Index.WithDocumentID("1"),
		es.Index.WithPretty(),
	)
	fmt.Println(res, err)
}

{
	res, err := es.Index(
		"my-index-000001",
		strings.NewReader(`{
	  "city": "York"
	}`),
		es.Index.WithDocumentID("2"),
		es.Index.WithPretty(),
	)
	fmt.Println(res, err)
}

{
	res, err := es.Search(
		es.Search.WithIndex("my-index-000001"),
		es.Search.WithBody(strings.NewReader(`{
	  "query": {
	    "match": {
	      "city": "york"
	    }
	  },
	  "sort": {
	    "city.raw": "asc"
	  },
	  "aggs": {
	    "Cities": {
	      "terms": {
	        "field": "city.raw"
	      }
	    }
	  }
	}`)),
		es.Search.WithPretty(),
	)
	fmt.Println(res, err)
}
const response = await client.indices.create({
  index: "my-index-000001",
  mappings: {
    properties: {
      city: {
        type: "text",
        fields: {
          raw: {
            type: "keyword",
          },
        },
      },
    },
  },
});
console.log(response);

const response1 = await client.index({
  index: "my-index-000001",
  id: 1,
  document: {
    city: "New York",
  },
});
console.log(response1);

const response2 = await client.index({
  index: "my-index-000001",
  id: 2,
  document: {
    city: "York",
  },
});
console.log(response2);

const response3 = await client.search({
  index: "my-index-000001",
  query: {
    match: {
      city: "york",
    },
  },
  sort: {
    "city.raw": "asc",
  },
  aggs: {
    Cities: {
      terms: {
        field: "city.raw",
      },
    },
  },
});
console.log(response3);
PUT my-index-000001
{
  "mappings": {
    "properties": {
      "city": {
        "type": "text",
        "fields": {
          "raw": { 
            "type":  "keyword"
          }
        }
      }
    }
  }
}

PUT my-index-000001/_doc/1
{
  "city": "New York"
}

PUT my-index-000001/_doc/2
{
  "city": "York"
}

GET my-index-000001/_search
{
  "query": {
    "match": {
      "city": "york" 
    }
  },
  "sort": {
    "city.raw": "asc" 
  },
  "aggs": {
    "Cities": {
      "terms": {
        "field": "city.raw" 
      }
    }
  }
}

city.raw 字段是 city 字段的 keyword 版本。

city 字段可以用于全文搜索。

city.raw 字段可以用于排序和聚合。

您可以使用 更新映射 API 将多字段添加到现有字段。

如果在添加多字段时索引（或数据流）中包含文档，则这些文档将没有新多字段的值。您可以使用 按查询更新 API 填充新的多字段。

多字段映射与父字段的映射完全分离。多字段不继承其父字段的任何映射选项。多字段不会更改原始的 _source 字段。

具有多个分析器的多字段

编辑

多字段的另一个用例是以不同的方式分析同一个字段，以获得更好的相关性。例如，我们可以使用 standard 分析器来索引一个字段，该分析器将文本分解为单词，并再次使用 english 分析器，该分析器将单词词干化为它们的词根形式。

resp = client.indices.create(
    index="my-index-000001",
    mappings={
        "properties": {
            "text": {
                "type": "text",
                "fields": {
                    "english": {
                        "type": "text",
                        "analyzer": "english"
                    }
                }
            }
        }
    },
)
print(resp)

resp1 = client.index(
    index="my-index-000001",
    id="1",
    document={
        "text": "quick brown fox"
    },
)
print(resp1)

resp2 = client.index(
    index="my-index-000001",
    id="2",
    document={
        "text": "quick brown foxes"
    },
)
print(resp2)

resp3 = client.search(
    index="my-index-000001",
    query={
        "multi_match": {
            "query": "quick brown foxes",
            "fields": [
                "text",
                "text.english"
            ],
            "type": "most_fields"
        }
    },
)
print(resp3)
response = client.indices.create(
  index: 'my-index-000001',
  body: {
    mappings: {
      properties: {
        text: {
          type: 'text',
          fields: {
            english: {
              type: 'text',
              analyzer: 'english'
            }
          }
        }
      }
    }
  }
)
puts response

response = client.index(
  index: 'my-index-000001',
  id: 1,
  body: {
    text: 'quick brown fox'
  }
)
puts response

response = client.index(
  index: 'my-index-000001',
  id: 2,
  body: {
    text: 'quick brown foxes'
  }
)
puts response

response = client.search(
  index: 'my-index-000001',
  body: {
    query: {
      multi_match: {
        query: 'quick brown foxes',
        fields: [
          'text',
          'text.english'
        ],
        type: 'most_fields'
      }
    }
  }
)
puts response
{
	res, err := es.Indices.Create(
		"my-index-000001",
		es.Indices.Create.WithBody(strings.NewReader(`{
	  "mappings": {
	    "properties": {
	      "text": {
	        "type": "text",
	        "fields": {
	          "english": {
	            "type": "text",
	            "analyzer": "english"
	          }
	        }
	      }
	    }
	  }
	}`)),
	)
	fmt.Println(res, err)
}

{
	res, err := es.Index(
		"my-index-000001",
		strings.NewReader(`{
	  "text": "quick brown fox"
	} `),
		es.Index.WithDocumentID("1"),
		es.Index.WithPretty(),
	)
	fmt.Println(res, err)
}

{
	res, err := es.Index(
		"my-index-000001",
		strings.NewReader(`{
	  "text": "quick brown foxes"
	} `),
		es.Index.WithDocumentID("2"),
		es.Index.WithPretty(),
	)
	fmt.Println(res, err)
}

{
	res, err := es.Search(
		es.Search.WithIndex("my-index-000001"),
		es.Search.WithBody(strings.NewReader(`{
	  "query": {
	    "multi_match": {
	      "query": "quick brown foxes",
	      "fields": [
	        "text",
	        "text.english"
	      ],
	      "type": "most_fields"
	    }
	  }
	}`)),
		es.Search.WithPretty(),
	)
	fmt.Println(res, err)
}
const response = await client.indices.create({
  index: "my-index-000001",
  mappings: {
    properties: {
      text: {
        type: "text",
        fields: {
          english: {
            type: "text",
            analyzer: "english",
          },
        },
      },
    },
  },
});
console.log(response);

const response1 = await client.index({
  index: "my-index-000001",
  id: 1,
  document: {
    text: "quick brown fox",
  },
});
console.log(response1);

const response2 = await client.index({
  index: "my-index-000001",
  id: 2,
  document: {
    text: "quick brown foxes",
  },
});
console.log(response2);

const response3 = await client.search({
  index: "my-index-000001",
  query: {
    multi_match: {
      query: "quick brown foxes",
      fields: ["text", "text.english"],
      type: "most_fields",
    },
  },
});
console.log(response3);
PUT my-index-000001
{
  "mappings": {
    "properties": {
      "text": { 
        "type": "text",
        "fields": {
          "english": { 
            "type":     "text",
            "analyzer": "english"
          }
        }
      }
    }
  }
}

PUT my-index-000001/_doc/1
{ "text": "quick brown fox" } 

PUT my-index-000001/_doc/2
{ "text": "quick brown foxes" } 

GET my-index-000001/_search
{
  "query": {
    "multi_match": {
      "query": "quick brown foxes",
      "fields": [ 
        "text",
        "text.english"
      ],
      "type": "most_fields" 
    }
  }
}

text 字段使用 standard 分析器。

text.english 字段使用 english 分析器。

索引两个文档，一个包含 fox，另一个包含 foxes。

查询 text 和 text.english 字段并组合分数。

text 字段在第一个文档中包含术语 fox，在第二个文档中包含 foxes。text.english 字段对于两个文档都包含 fox，因为 foxes 被词干化为 fox。

查询字符串也由 text 字段的 standard 分析器分析，并由 text.english 字段的 english 分析器分析。词干化字段允许对 foxes 的查询也匹配仅包含 fox 的文档。这使我们能够匹配尽可能多的文档。通过也查询未词干化的 text 字段，我们提高了完全匹配 foxes 的文档的相关性得分。

« meta normalizer »