ES terms多值搜索及范围过滤深入剖析-搜索系统线上实战

专注于大数据及容器云核心技术解密，可提供全栈的大数据+云原生平台咨询方案，请持续关注本套博客。QQ邮箱地址：1120746959@qq.com，如有任何学术交流，可随时联系。详情请关注《数据云技术社区》公众号。

1 制造数据

新增索引
POST /forum/article/_bulk
{ "index": { "_id": 1 }}
{ "articleID" : "XHDK-A-1293-#fJ3", "userID" : 1, "hidden": false, "postDate": "2017-01-01" }
{ "index": { "_id": 2 }}
{ "articleID" : "KDKE-B-9947-#kL5", "userID" : 1, "hidden": false, "postDate": "2017-01-02" }
{ "index": { "_id": 3 }}
{ "articleID" : "JODL-X-1937-#pV7", "userID" : 2, "hidden": false, "postDate": "2017-01-01" }
{ "index": { "_id": 4 }}
{ "articleID" : "QQPX-R-3956-#aD8", "userID" : 2, "hidden": true, "postDate": "2017-01-02" }

追加新增字段
POST /forum/article/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"tag" : ["java", "hadoop"]} }
{ "update": { "_id": "2"} }
{ "doc" : {"tag" : ["java"]} }
{ "update": { "_id": "3"} }
{ "doc" : {"tag" : ["hadoop"]} }
{ "update": { "_id": "4"} }
{ "doc" : {"tag" : ["java", "elasticsearch"]} }

2 多值搜索案例

• 搜索articleID为KDKE-B-9947-#kL5或QQPX-R-3956-#aD8的帖子，搜索tag中包含java的帖子

    GET /forum/article/_search 
    {
      "query": {
        "constant_score": {
          "filter": {
            "terms": {
              "articleID": [
                "KDKE-B-9947-#kL5",
                "QQPX-R-3956-#aD8"
              ]
            }
          }
        }
      }
    }

    GET /forum/article/_search
    {
        "query" : {
            "constant_score" : {
                "filter" : {
                    "terms" : { 
                        "tag" : ["java"]
                    }
                }
            }
        }
    }
    
  "took": 2,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 3,
    "max_score": 1,
    "hits": [
      {
        "_index": "forum",
        "_type": "article",
        "_id": "2",
        "_score": 1,
        "_source": {
          "articleID": "KDKE-B-9947-#kL5",
          "userID": 1,
          "hidden": false,
          "postDate": "2017-01-02",
          "tag": [
            "java"
          ]
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "4",
        "_score": 1,
        "_source": {
          "articleID": "QQPX-R-3956-#aD8",
          "userID": 2,
          "hidden": true,
          "postDate": "2017-01-02",
          "tag": [
            "java",
            "elasticsearch"
          ]
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "1",
        "_score": 1,
        "_source": {
          "articleID": "XHDK-A-1293-#fJ3",
          "userID": 1,
          "hidden": false,
          "postDate": "2017-01-01",
          "tag": [
            "java",
            "hadoop"
          ]
        }
      }
    ]
  }
}

优化搜索结果，仅仅搜索tag只包含java的帖子
POST /forum/article/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"tag_cnt" : 2} }
{ "update": { "_id": "2"} }
{ "doc" : {"tag_cnt" : 1} }
{ "update": { "_id": "3"} }
{ "doc" : {"tag_cnt" : 1} }
{ "update": { "_id": "4"} }
{ "doc" : {"tag_cnt" : 2} }

GET /forum/article/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "bool": {
          "must": [
            {
              "term": {
                "tag_cnt": 1
              }
            },
            {
              "terms": {
                "tag": ["java"]
              }
            }
          ]
        }
      }
    }
  }
}

2 范围搜索案例

2.1 制造数据

POST /forum/article/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"view_cnt" : 30} }
{ "update": { "_id": "2"} }
{ "doc" : {"view_cnt" : 50} }
{ "update": { "_id": "3"} }
{ "doc" : {"view_cnt" : 100} }
{ "update": { "_id": "4"} }
{ "doc" : {"view_cnt" : 80} }

2.2 搜索浏览量在30~60之间的帖子

GET /forum/article/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "range": {
          "view_cnt": {
            "gt": 30,
            "lt": 60
          }
        }
      }
    }
  }
}

2.3 搜索发帖日期在最近1个月的帖子

POST /forum/article/_bulk
{ "index": { "_id": 5 }}
{ "articleID" : "DHJK-B-1395-#Ky5", "userID" : 3, "hidden": false, "postDate": "2017-03-01", "tag": ["elasticsearch"], "tag_cnt": 1, "view_cnt": 10 }

GET /forum/article/_search 
{
  "query": {
    "constant_score": {
      "filter": {
        "range": {
          "postDate": {
            "gt": "2017-03-10||-30d"
          }
        }
      }
    }
  }
}

GET /forum/article/_search 
{
  "query": {
    "constant_score": {
      "filter": {
        "range": {
          "postDate": {
            "gt": "now-30d"
          }
        }
      }
    }
  }
}

3 总结

专注于大数据及容器云核心技术解密，可提供全栈的大数据+云原生平台咨询方案，请持续关注本套博客。QQ邮箱地址：1120746959@qq.com，如有任何学术交流，可随时联系。详情请关注《数据云技术社区》公众号。