ElasticSearch Nested类型全文检索、聚合查询

ElasticSearch Nested类型全文检索、聚合查询

Nested类型全文检索

1. 创建索引

PUT /products1
{
  "mappings": {
    "properties": {
      "fulltext": {
          "type": "text"
        },
      "name": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword",
            "ignore_above": 256
          }
        }
      },
      "reviews": {
        "type": "nested",
        "properties": {
          "rating": {
            "type": "integer"
          },
          "author": {
            "type": "text",
            "copy_to": "fulltext"
          },
          "date": {
            "type": "date"
          }
        }
      }
    }
  }
}

以上创建索引语句中实现全文检索重点为"fulltext": { "type": "text" }和"copy_to": "fulltext"，nested类型中哪个text类型的字段需要全文检索，就在字段上加"copy_to": "fulltext"

2. 添加数据

PUT /products1/_doc/1
{
  "name": "Product A",
  "reviews": [
    {
      "rating": 5,
      "author": "Alice",
      "date": "2021-01-01"
    },
    {
      "rating": 4,
      "author": "Bob",
      "date": "2021-01-02"
    }
  ]
}

PUT /products1/_doc/2
{
  "name": "Product B",
  "reviews": [
    {
      "rating": 1,
      "author": "John",
      "date": "2021-01-03"
    },
    {
      "rating": 2,
      "author": "Mary",
      "date": "2021-01-04"
    },
    {
      "rating": 3,
      "author": "James",
      "date": "2021-01-05"
    },
    {
      "rating": 4,
      "author": "Elisabeth",
      "date": "2021-01-06"
    },
    {
      "rating": 5,
      "author": "Richard",
      "date": "2021-01-07"
    }
  ]
}


PUT /products1/_doc/3
{
  "name": "Product C",
  "reviews": [
    {
      "rating": 1,
      "author": "Alex",
      "date": "2021-01-03"
    },
    {
      "rating": 2,
      "author": "Alice",
      "date": "2021-01-04"
    }
  ]
}

3. 执行查询

POST products1/_search
{
  "query": {
    "simple_query_string": {
      "query": "Alice"
    }
  }
}

4. 结果如下，可以看到nested类型中包含Alice的数据也被检索出来了

{
  "took" : 2,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 0.5442147,
    "hits" : [
      {
        "_index" : "products1",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 0.5442147,
        "_source" : {
          "name" : "Product A",
          "reviews" : [
            {
              "rating" : 5,
              "author" : "Alice",
              "date" : "2021-01-01"
            },
            {
              "rating" : 4,
              "author" : "Bob",
              "date" : "2021-01-02"
            }
          ]
        }
      },
      {
        "_index" : "products1",
        "_type" : "_doc",
        "_id" : "3",
        "_score" : 0.5442147,
        "_source" : {
          "name" : "Product C",
          "reviews" : [
            {
              "rating" : 1,
              "author" : "Alex",
              "date" : "2021-01-03"
            },
            {
              "rating" : 2,
              "author" : "Alice",
              "date" : "2021-01-04"
            }
          ]
        }
      }
    ]
  }
}

以上可以看到实现nested类型全文检索

nested类型聚合查询

还是在上面product1索引中测试

1. 现在，您可以对嵌套文档执行嵌套聚合。例如，让我们计算每个产品的平均评分：

GET /products1/_search
{
  "size": 0,
  "aggs": {
    "聚合名称": {
      "terms": {
        "field": "name.keyword"
      },
      "aggs": {
        "reviews": {
          "nested": {
            "path": "reviews"
          },
          "aggs": {
            "average_rating": {
              "avg": {
                "field": "reviews.rating"
              }
            }
          }
        }
      }
    }
  }
}

2. 我们首先使用术语聚合为每个产品创建存储桶。然后，对于每个产品，我们运行嵌套聚合，以便我们可以访问嵌套文档的集合。最后，我们可以计算这些嵌套文档的指标聚合，在我们的示例中是平均评分

{
  "took" : 3,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "products" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : "Product A",
          "doc_count" : 1,
          "reviews" : {
            "doc_count" : 2,
            "average_rating" : {
              "value" : 4.5
            }
          }
        },
        {
          "key" : "Product B",
          "doc_count" : 1,
          "reviews" : {
            "doc_count" : 5,
            "average_rating" : {
              "value" : 3.0
            }
          }
        },
        {
          "key" : "Product C",
          "doc_count" : 1,
          "reviews" : {
            "doc_count" : 2,
            "average_rating" : {
              "value" : 1.5
            }
          }
        }
      ]
    }
  }
}