ElasticSearch学习：文档的基本操作

上一个我们基本是围绕索引操作，里面的指定类型，或者文档里面的一些属性。

这里是主要关注文档操作，毕竟主要常见的操作就是围绕文档内容来进行的，毕竟主要是做搜索。

首先先导入一些数据进去。
一 简单的查询操作

put /testdoc/user/1
{
  "name": "张三",
  "age": 28,
  "desc": "法外狂徒",
  "tags": ["旅游", "渣男", "交友"]
}
 
put /testdoc/user/2
{
  "name": "李四",
  "age": 30,
  "desc": "佳木斯大拐",
  "tags": ["旅游", "靓女", "唱歌"]
}
 

#以下是查询
#id查询
GET testdoc/user/1
 
 #分词查询
GET testdoc/user/_search?q=name:张

以下是GET testdoc/user/_search?q=name:张 的返回结果：

{
  "took" : 9,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1,
      "relation" : "eq"
    },
    "max_score" : 0.6931471,
    "hits" : [
      {
        "_index" : "testdoc",
        "_type" : "user",
        "_id" : "1",
        "_score" : 0.6931471,
        "_source" : {
          "name" : "张三",
          "age" : 28,
          "desc" : "法外狂徒",
          "tags" : [
            "旅游",
            "渣男",
            "交友"
          ]
        }
      }
    ]
  }
}

二 复杂的查询
排序、分页、高亮、模糊查询、标准查询
首先再添加俩用户

put /testdoc/user/3
{
  "name": "王二麻子",
  "age": 28,
  "desc": "买豆腐",
  "tags": ["游戏", "猛男", "宅"]
}
 
put /testdoc/user/4
{
  "name": "王二麻",
  "age": 30,
  "desc": "主播",
  "tags": ["直播", "购物", "吹牛"]
}

模糊查询

GET testdoc/user/_search
{
  "query": {
    "match": {
      "name": "王二麻"
    }
  }
}

返回结果

{
  "took" : 0,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 2.5518394,
    "hits" : [
      {
        "_index" : "testdoc",
        "_type" : "user",
        "_id" : "4",
        "_score" : 2.5518394,
        "_source" : {
          "name" : "王二麻",
          "age" : 30,
          "desc" : "主播",
          "tags" : [
            "直播",
            "购物",
            "吹牛"
          ]
        }
      },
      {
        "_index" : "testdoc",
        "_type" : "user",
        "_id" : "3",
        "_score" : 2.234622,
        "_source" : {
          "name" : "王二麻子",
          "age" : 28,
          "desc" : "买豆腐",
          "tags" : [
            "游戏",
            "猛男",
            "宅"
          ]
        }
      }
    ]
  }
}

套用一下别人的截图

针对模糊搜索的添加过滤

#真对_source的过滤
#_source先看一下都有些什么
{
  "_index" : "testdoc",
  "_type" : "user",
  "_id" : "4",
  "_version" : 2,
  "_seq_no" : 4,
  "_primary_term" : 1,
  "found" : true,
  "_source" : {
    "name" : "王二麻",
    "age" : 30,
    "desc" : "主播",
    "tags" : [
      "直播",
      "购物",
      "吹牛"
    ]
  }
}



#根据_source里面的name和desc来过滤
GET testdoc/user/_search
{
  "query": {
    "match": {
      "name": "王二麻"
    }
  },
  "_source": ["name", "desc"]
}

排序过滤

# ASC 升序 DESC降序
GET testdoc/user/_search
{
  "query": {
    "match": {
      "name": "王二麻"
    }
  },
  "sort":[{
    "age": "asc"
  }]
}

分页查询

#这里的form和size类似我们的分页参数的pageNum和pageSize
GET testdoc/user/_search
{
  "query": {
    "match": {
      "name": "王二麻"
    }
  },
  "sort":[{
    "age": "asc"
  }],
  "from":0,
  "size":1
}

布尔值查询
这里要注意bool的几个设置，must shuould must_not gt大于 lt小于 (当然还有gte 大于等于 lte 小于等于)

# 多条件查询 must 相当于and
GET testdoc/user/_search
{
  "query": {
    "bool": {
      "must": [
        {"match": {
          "name": "王二麻"
        }},
        {"match": {
          "age": 30
        }}
      ]
    }
  }
}


# 多条件查询 should 相当于or
GET testdoc/user/_search
{
  "query": {
    "bool": {
      "should": [
        {"match": {
          "name": "王二麻"
        }},
        {"match": {
          "age": 30
        }}
      ]
    }
  }
}


# 多条件查询 must_not 相当于 not
GET testdoc/user/_search
{
  "query": {
    "bool": {
      "must_not": [
        {"match": {
          "name": "王二麻"
        }},
        {"match": {
          "age": 30
        }}
      ]
    }
  }
}


# 过滤查询1 age > 24

GET testdoc/user/_search
{
  "query": {
    "bool": {
      "must_not": [
        {"match": {
          "name": "王二麻"
        }}
      ],
      
       "filter": [
        {"range": {
          "age": {
            "gt": 24
          }
        }}
      ]

    }
  }
}


# 过滤器2  22<age<30
GET testdoc/user/_search
{
  "query": {
    "bool": {
      "must_not": [
        {"match": {
          "name": "王二麻"
        }}
      ],
      
        "filter": [
        {"range": {
          "age": {
            "lt": 28,
            "gt": 25
          }
        }}
      ]

    }
  }
}

多条件查询
实际还是match匹配的引用，只不过不是完全用上面那些关键字来

GET testdoc/user/_search
{
  "query": {
    "match": {
      "tags": "主播 男"
    }
  }
}

精确插叙
term关键字根据底层的倒排索引
于match对比：

• term直接精确查找
• match根据分词器来查找

keyword类型和text类型
keyword类型不会被分词器解析，term: 精确匹配

PUT test4
{
  "mappings": {
    "properties": {
      "name": {
        "type": "text"
      },
      "desc": {
        "type": "keyword"
      }
    }
  }
}


PUT /test4/_doc/1
{
  "name": "Java Name",
  "desc": "Java Desc"
}

PUT /test4/_doc/2
{
  "name": "Java Name",
  "desc": "Java Desc 2"
}


GET test4/_search
{
  "query": {
    "term": {
      "desc": "ZP Java Desc"
    }
  }
}

# 按照text类型匹配(查不到可能是自己的分词器不行我这个用的是ik，没加别的分词器，单词的匹配就不行)
GET test4/_search
{
  "query": {
    "term": {
      "desc": "Java"
    }
  }
}

_analyze, _explain是Elasticsearch提供的辅助API，经常不为人所知和所用。_explain 用来帮助分析文档的relevance score是如何计算出来的，而_analyze是Elasticsearch一个非常有用的API，它可以帮助你分析每一个field或者某个analyzer/tokenizer是如何分析和索引一段文字。

GET test4/_search
{
  "query": {
    "term": {
      "desc": "ZP Java Desc"
    }
  }
}




GET _analyze
{
  "analyzer": "standard",
  "text":"ZP JAVA"
}

多个值精确匹配

PUT /test_db/_doc/3
{
  "t1": "22",
  "t2": "2020-09-10"
}
 
PUT /test_db/_doc/4
{
  "t1": "33",
  "t2": "2020-09-11"
}
 
GET test_db/_search
{
  "query": {
    "bool": {
      "should": [
        {
          "term": {
            "t1": "22"
          }
        },
         {
          "term": {
            "t1": "33"
          }
        }
      ]
    }
  }
}

高亮查询

GET test5/user/_search
{
  "query": {
    "match": {
      "name": "张三"
    }
  },
  "highlight": {
    "pre_tags": "<p class='key' style='color:red'>",
    "post_tags": "</p>", 
    "fields": {
      "name": {}
    }
  }
}