elasticsearch学习笔记高级篇（一）——在案例中实战使用term filter来搜索数据

头像
郑国
    阅读 8 分钟

    下面以IT技术论坛为案例背景

    1、根据用户ID、是否隐藏、帖子ID、发帖日期来搜索帖子

    （1）插入一些测试帖子的数据

    POST /forum/_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" }

    输出：

    {
  "took" : 269,
  "errors" : false,
  "items" : [
    {
      "index" : {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "1",
        "_version" : 1,
        "result" : "created",
        "_shards" : {
          "total" : 2,
          "successful" : 1,
          "failed" : 0
        },
        "_seq_no" : 0,
        "_primary_term" : 1,
        "status" : 201
      }
    },
    {
      "index" : {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "2",
        "_version" : 1,
        "result" : "created",
        "_shards" : {
          "total" : 2,
          "successful" : 1,
          "failed" : 0
        },
        "_seq_no" : 1,
        "_primary_term" : 1,
        "status" : 201
      }
    },
    {
      "index" : {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "3",
        "_version" : 1,
        "result" : "created",
        "_shards" : {
          "total" : 2,
          "successful" : 1,
          "failed" : 0
        },
        "_seq_no" : 2,
        "_primary_term" : 1,
        "status" : 201
      }
    },
    {
      "index" : {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "4",
        "_version" : 1,
        "result" : "created",
        "_shards" : {
          "total" : 2,
          "successful" : 1,
          "failed" : 0
        },
        "_seq_no" : 3,
        "_primary_term" : 1,
        "status" : 201
      }
    }
  ]
}

    注意：初步来讲，先搞4个字段，因为整个es是支持json document格式的，所以说扩展性和灵活性非常之好。如果后续随着业务需求的增加，要在document中增加更多的field，那么我们可以很方便的随时添加field。但是如果是在关系型数据库中，比如mysql，我们建立了一个表，现在要给表中新增一些column，那么就很坑爹了，必须用复杂的修改表结构的语法去执行。而且可能对系统代码还有一定的影响。

    （2）根据用户ID搜索帖子

    GET /forum/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "userID": 1
        }
      }
    }
  }
}

    输出:

    {
  "took" : 6,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "articleID" : "XHDK-A-1293-#fJ3",
          "userID" : 1,
          "hidden" : false,
          "postDate" : "2017-01-01"
        }
      },
      {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "2",
        "_score" : 1.0,
        "_source" : {
          "articleID" : "KDKE-B-9947-#kL5",
          "userID" : 1,
          "hidden" : false,
          "postDate" : "2017-01-02"
        }
      }
    ]
  }
}

    term filter/query : 对搜索文本不分词，直接拿去倒排索引中去匹配，你输入的是什么，就去匹配什么

    （3）搜索没有隐藏的帖子

    GET /forum/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "hidden": false
        }
      }
    }
  }
}

    输出：

    {
  "took" : 2,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "articleID" : "XHDK-A-1293-#fJ3",
          "userID" : 1,
          "hidden" : false,
          "postDate" : "2017-01-01"
        }
      },
      {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "2",
        "_score" : 1.0,
        "_source" : {
          "articleID" : "KDKE-B-9947-#kL5",
          "userID" : 1,
          "hidden" : false,
          "postDate" : "2017-01-02"
        }
      },
      {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "3",
        "_score" : 1.0,
        "_source" : {
          "articleID" : "JODL-X-1937-#pV7",
          "userID" : 2,
          "hidden" : false,
          "postDate" : "2017-01-01"
        }
      }
    ]
  }
}

    （4）根据发帖日期搜索帖子

    GET /forum/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "postDate": "2017-01-01"
        }
      }
    }
  }
}

    输出:

    {
  "took" : 5,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "articleID" : "XHDK-A-1293-#fJ3",
          "userID" : 1,
          "hidden" : false,
          "postDate" : "2017-01-01"
        }
      },
      {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "3",
        "_score" : 1.0,
        "_source" : {
          "articleID" : "JODL-X-1937-#pV7",
          "userID" : 2,
          "hidden" : false,
          "postDate" : "2017-01-01"
        }
      }
    ]
  }
}

    （5）根据帖子ID搜索帖子

    GET /forum/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "articleID.keyword": "XHDK-A-1293-#fJ3"
        }
      }
    }
  }
}

    输出:

    {
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "articleID" : "XHDK-A-1293-#fJ3",
          "userID" : 1,
          "hidden" : false,
          "postDate" : "2017-01-01"
        }
      }
    ]
  }
}

    如果不使用keyword

    GET /forum/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "articleID": "XHDK-A-1293-#fJ3"
        }
      }
    }
  }
}

    输出：

    {
  "took" : 0,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 0,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  }
}

    articleID.keyword是ES最新版本内置建立的field，就是不分词的，所以一个articleID过来的时候，会建立两次索引，一次是自己本省，是要分词的，分词后放入倒排索引，另外一次是基于articleID.keyword不分词的，保留最多256个字符，直接一个字符串放入倒排索引中。在实际使用的时候如果有必要可以手动指定type=keyword，那样就可以避免自动创建默认保留256个字符

    （6）查看分词

    GET /forum/_analyze
{
  "field": "articleID",
  "text": ["XHDK-A-1293-#fJ3"]
}

    输出：

    {
  "tokens" : [
    {
      "token" : "xhdk",
      "start_offset" : 0,
      "end_offset" : 4,
      "type" : "<ALPHANUM>",
      "position" : 0
    },
    {
      "token" : "a",
      "start_offset" : 5,
      "end_offset" : 6,
      "type" : "<ALPHANUM>",
      "position" : 1
    },
    {
      "token" : "1293",
      "start_offset" : 7,
      "end_offset" : 11,
      "type" : "<NUM>",
      "position" : 2
    },
    {
      "token" : "fj3",
      "start_offset" : 13,
      "end_offset" : 16,
      "type" : "<ALPHANUM>",
      "position" : 3
    }
  ]
}

    默认的分词的text类型的field，建立倒排索引的时候，就会对所有的articleID分词，分词之后，原本的articleID就没有了，之后分词后的各个word存在于倒排索引中。

    （7）重建索引

    DELETE /forum
PUT /forum
{
  "mappings": {
    "properties": {
      "articleID": {
        "type": "keyword"
      }
    }
  }
}

POST /forum/_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" }

    （8）重新根据帖子ID和发帖日期进行搜索

    GET /forum/_search
{
  "query": {
    "constant_score": {
      "filter": {
        "term": {
          "articleID": "XHDK-A-1293-#fJ3"
        }
      }
    }
  }
}

    输出：

    {
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "forum",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "articleID" : "XHDK-A-1293-#fJ3",
          "userID" : 1,
          "hidden" : false,
          "postDate" : "2017-01-01"
        }
      }
    ]
  }
}

    2、总结

    （1）term filter:根据exact value进行搜索，像数字、boolean、date是天然支持
    （2）text需要建立索引时指定为not_analyzed,才能使用term
    （3）相当于SQL中的单个where条件

    select * from forum where articleID = 'XHDK-A-1293-#fJ3'
    elasticsearch
    郑国
    301 声望88 粉丝
    « 上一篇
    Elasticsearch实战Java High Level REST Client实现员工管理案例
    下一篇 »
    elasticsearch学习笔记高级篇（二）——filter执行原理深度剖析

    引用和评论

    推荐阅读
    头像
    elasticsearch学习笔记高级篇（十五）——实战搜索推荐

    郑国赞 1阅读 2.2k评论 1

    头像
    查询性能提升 10 倍、存储空间节省 65%，Apache Doris 半结构化数据分析方案及典型场景

    SelectDB技术团队赞 1阅读 345

    头像
    Elasticsearch 8.x 重要变化（qbit）

    qbit阅读 574

    头像
    关于 Elasticsearch 同义词的困惑（qbit）

    qbit阅读 353评论 1

    头像
    Elasticsearch搭建、结合spring boot、简单示例

    LLL_赞 1阅读 319

    头像
    Elasticsearch 8 RAG 技术分享

    阿里云大数据AI阅读 284

    头像
    Docker如何修改Elasticsearch容器的密码

    Smoke阅读 285

    0 条评论
    得票最新