Elasticsearch简单学习5:入门学习-2

最新推荐文章于 2024-08-19 15:15:31 发布

chunyanhuai6598

最新推荐文章于 2024-08-19 15:15:31 发布

阅读量227

点赞数

文章标签：大数据 java swift

原文链接：https://my.oschina.net/hanchao/blog/3080131

版权

一、基础说明

1.Search API

《1.》URI Search

在URL中使用查询参数

《2.》Request Body Search

使用Elasticsearch提供的，基于JSON格式的更加完备的Query Domain Specific Language (DSL)

2.指定查询的索引

3.URI查询

4.Request Body

5.search Response

6.搜索的相关性 Relevance

7.参考文档

https://www.elastic.co/guide/en/elasticsearch/reference/7.1/search-search.html

https://searchenginewatch.com/sew/news/2065080/search-engines-101

https://www.entrepreneur.com/article/176398

https://baike.baidu.com/item/%E6%90%9C%E7%B4%A2%E5%BC%95%E6%93%8E%E5%8F%91%E5%B1%95%E5%8F%B2/2422574

https://www.searchtechnologies.com/meaning-of-relevancy

二、URI Search详解

1.说明

2.指定字段&泛查询

#基本查询
GET /movies/_search?q=2012&df=title&sort=year:desc&from=0&size=10&timeout=1s

################# 结果 #####################
{
  "took" : 28,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [
      {
        "_index" : "movies",
        "_type" : "_doc",
        "_id" : "105254",
        "_score" : null,
        "_source" : {
          "id" : "105254",
          "title" : "Crystal Fairy & the Magical Cactus and 2012",
          "year" : 2013,
          "@version" : "1",
          "genre" : [
            "Adventure",
            "Comedy"
          ]
        },
        "sort" : [
          2013
        ]
      },
      {
        "_index" : "movies",
        "_type" : "_doc",
        "_id" : "72378",
        "_score" : null,
        "_source" : {
          "id" : "72378",
          "title" : "2012",
          "year" : 2009,
          "@version" : "1",
          "genre" : [
            "Action",
            "Drama",
            "Sci-Fi",
            "Thriller"
          ]
        },
        "sort" : [
          2009
        ]
      }
    ]
  }
}

例子2:profile显示是termQuery

#带profile ，指定df字段为title =>>查询title中含有2012的数据
GET /movies/_search?q=2012&df=title
{
	"profile":"true"
}

################### 返回的结果 #########################
{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 11.303033,
    "hits" : [
      {
        "_index" : "movies",
        "_type" : "_doc",
        "_id" : "72378",
        "_score" : 11.303033,
        "_source" : {
          "id" : "72378",
          "title" : "2012",
          "year" : 2009,
          "@version" : "1",
          "genre" : [
            "Action",
            "Drama",
            "Sci-Fi",
            "Thriller"
          ]
        }
      },
      {
        "_index" : "movies",
        "_type" : "_doc",
        "_id" : "105254",
        "_score" : 5.2497,
        "_source" : {
          "id" : "105254",
          "title" : "Crystal Fairy & the Magical Cactus and 2012",
          "year" : 2013,
          "@version" : "1",
          "genre" : [
            "Adventure",
            "Comedy"
          ]
        }
      }
    ]
  },
  "profile" : {
    "shards" : [
      {
        "id" : "[IFYvrFIHTDiAFmTdfyB9AQ][movies][0]",
        "searches" : [
          {
            "query" : [
              {
                "type" : "TermQuery",
                "description" : "title:2012",
                "time_in_nanos" : 95582,
                "breakdown" : {
                  "set_min_competitive_score_count" : 0,
                  "match_count" : 0,
                  "shallow_advance_count" : 0,
                  "set_min_competitive_score" : 0,
                  "next_doc" : 5548,
                  "match" : 0,
                  "next_doc_count" : 3,
                  "score_count" : 2,
                  "compute_max_score_count" : 0,
                  "compute_max_score" : 0,
                  "advance" : 0,
                  "advance_count" : 0,
                  "score" : 5120,
                  "build_scorer_count" : 3,
                  "create_weight" : 59732,
                  "shallow_advance" : 0,
                  "create_weight_count" : 1,
                  "build_scorer" : 25173
                }
              }
            ],
            "rewrite_time" : 2133,
            "collector" : [
              {
                "name" : "CancellableCollector",
                "reason" : "search_cancelled",
                "time_in_nanos" : 20055,
                "children" : [
                  {
                    "name" : "SimpleTopScoreDocCollector",
                    "reason" : "search_top_hits",
                    "time_in_nanos" : 13227
                  }
                ]
              }
            ]
          }
        ],
        "aggregations" : [ ]
      }
    ]
  }
}

例子3：泛查询-性能低

#泛查询，正对_all,所有字段
GET /movies/_search?q=2012
{
	"profile":"true"
}

3.Term & Phrase

例子1：

#使用引号，Phrase查询
GET /movies/_search?q=title:"Beautiful Mind"
{
	"profile":"true"
}

例子2：

#查找美丽心灵, Mind为泛查询
GET /movies/_search?q=title:Beautiful Mind
{
	"profile":"true"
}

例子3：

#分组，Bool查询
GET /movies/_search?q=title:(Beautiful Mind)
{
	"profile":"true"
}

4.布尔操作

例子1：

# 查找美丽心灵
GET /movies/_search?q=title:(Beautiful AND Mind)
{
	"profile":"true"
}

例子2：

# 查找美丽心灵
GET /movies/_search?q=title:(Beautiful NOT Mind)
{
	"profile":"true"
}

例子3：

# 查找美丽心灵 ,%2B代表+
GET /movies/_search?q=title:(Beautiful %2BMind)
{
	"profile":"true"
}

5.范围查询和算术符号

例子1：

#范围查询 , 区间写法
GET /movies/_search?q=year:>=1980
{
  "profile": "true"
}

例子2：

#范围查询 ,区间写法
GET /movies/_search?q=title:beautiful AND year:[2002 TO 2018%7D
{
	"profile":"true"
}

6.通配符查询&模糊查询

例子1：

#通配符查询
GET /movies/_search?q=title:b*
{
	"profile":"true"
}

例子2：

//模糊匹配&近似度匹配
GET /movies/_search?q=title:beautifl~1
{
	"profile":"true"
}

例子3：

GET /movies/_search?q=title:"Lord Rings"~2
{
	"profile":"true"
}

三、Request Body和DSL

1.Request Body Search

例子1：

ignore_unavailable=true，可以忽略尝试访问不存在的索引“404_idx”导致的报错

POST /movies,404_idx/_search?ignore_unavailable=true
{
  "profile": "true",
  "query": {
      "match_all": {}
  }
}

#From从0开始，默认返回10个结果
POST /kibana_sample_data_ecommerce/_search
{
  "from": 10, 
  "size": 20,
  "query": {
    "match_all": {}
  }
}

#对日期排序
POST kibana_sample_data_ecommerce/_search
{
  "sort":[{"order_date":"desc"}],
  "query":{
    "match_all": {}
  }
}

说明：最好在“数字型” 与“日期型”字段上排序

例子2：

#source filtering
POST kibana_sample_data_ecommerce/_search
{
  "_source":["order_date"],
  "query":{
    "match_all": {}
  }
}

例子3：

#脚本字段-订单中有不同的汇率，需要结合汇率对订单价格进行排序
#painless是ES的脚本
GET kibana_sample_data_ecommerce/_search
{
  "script_fields": {
    "new_field": {
      "script": {
        "lang": "painless",
        "source": "doc['order_date'].value+'hello'"
      }
    }
  },
  "query": {
    "match_all": {}
  }
}

例子4：

#或的关系
POST movies/_search
{
  "query": {
    "match": {
      "title": "last christmas"
    }
  }
}

#与的关系
POST movies/_search
{
  "query": {
    "match": {
      "title": {
        "query": "last christmas",
        "operator": "and"
      }
    }
  }
}

#match_phrase查询
POST movies/_search
{
  "query": {
    "match_phrase": {
      "title":{
        "query": "one love"

      }
    }
  }
}

#slop的用法参考官网
POST movies/_search
{
  "query": {
    "match_phrase": {
      "title":{
        "query": "one love",
        "slop": 1

      }
    }
  }
}

https://www.elastic.co/guide/en/elasticsearch/reference/7.0/search-uri-request.html

https://www.elastic.co/guide/en/elasticsearch/reference/7.0/search-search.html

2.Query String Query

类似URI的Query

#插入用户赵一花
PUT /users/_doc/1
{
  "name":"Zhao YiHua",
  "about":"java, golang, node, swift, elasticsearch"
}

#插入用户李一花
PUT /users/_doc/2
{
  "name":"Li YiHua",
  "about":"java, golang, node, swift, elasticsearch"
}

#支持AND查询
POST users/_search
{
  "query": {
    "query_string": {
      "default_field": "name",
      "query": "Zhao AND YiHua"
    }
  }
}

#支持分组和多字段
POST users/_search
{
  "query": {
    "query_string": {
      "fields":["name","about"],
      "query": "(Zhao AND YiHua) OR (Java AND Elasticsearch)"
    }
  }
}

==============================================
#default_field相当于URI查询的df字段
GET /movies/_search
{
	"profile": true,
	"query":{
		"query_string":{
			"default_field": "title",
			"query": "Beafiful AND Mind"
		}
	}
}

# 多fields
GET /movies/_search
{
	"profile": true,
	"query":{
		"query_string":{
			"fields":[
				"title",
				"year"
			],
			"query": "2012"
		}
	}
}

3.Simple Query String Query

#Simple Query 默认的operator是 Or
POST users/_search
{
  "query": {
    "simple_query_string": {
      "query": "Zhao AND YiHua",
      "fields": ["name"]
    }
  }
}

#支持AND
POST users/_search
{
  "query": {
    "simple_query_string": {
      "query": "Zhao YiHua",
      "fields": ["name"],
      "default_operator": "AND"
    }
  }
}

#####
GET /movies/_search
{
	"profile":true,
	"query":{
		"simple_query_string":{
			"query":"Beautiful +mind",
			"fields":["title"]
		}
	}
}

四、Dynamic Mapping和常见的字段类型

1.什么是Mapping?

2.字段的数据类型？

3.什么是Dynamic Mapping?

4.类型的自动识别？

#写入文档，查看 Mapping
PUT mapping_test/_doc/1
{
  "firstName":"Chan",
  "lastName": "Jackie",
  "loginDate":"2018-07-24T10:29:48.103Z"
}

#查看 Mapping文件 ,firstName和lastName设置成text,loginDate设置成了Date
GET mapping_test/_mapping

#Delete index
DELETE mapping_test

#dynamic mapping，推断字段的类型
PUT mapping_test/_doc/1
{
    "uid" : "123",
    "isVip" : false,
    "isAdmin": "true",
    "age":19,
    "heigh":180
}

#查看 Dynamic ,age,heigh设置成了long ,isVip设置成了boolean,isAdmin设置成text,uid设置成text
GET mapping_test/_mapping

5.能否修改Mapping的字段类型？

#默认Mapping支持dynamic，写入的文档中加入新的字段
PUT dynamic_mapping_test/_doc/1
{
  "newField":"someValue"
}

#该字段可以被搜索，数据也在_source中出现
POST dynamic_mapping_test/_search
{
  "query":{
    "match":{
      "newField":"someValue"
    }
  }
}


===================================================
#修改为dynamic false
PUT dynamic_mapping_test/_mapping
{
  "dynamic": false
}

#新增 anotherField
PUT dynamic_mapping_test/_doc/10
{
  "anotherField":"someValue"
}

#该字段不可以被搜索，【match_all是可以的】应为dynamic已经被设置为false
POST dynamic_mapping_test/_search
{
  "query":{
    "match":{
      "anotherField":"someValue"
    }
  }
}

get dynamic_mapping_test/_doc/10


============================================
#修改为strict
PUT dynamic_mapping_test/_mapping
{
  "dynamic": "strict"
}

#写入数据出错，HTTP Code 400
PUT dynamic_mapping_test/_doc/12
{
  "lastField":"value"
}

#删除索引！！
DELETE dynamic_mapping_test

阅读：https://www.elastic.co/guide/en/elasticsearch/reference/7.1/dynamic-mapping.html

五、★显式Mapping的设置与常见参数介绍★

1.如何显式顶一个一个Mapping?

2.自定义Mapping的一些建议

《1.》为了减少输入的工作量，减少出错概率，可以依照如下步骤

① 创建一个临时的Index , 写入一些样本数据

② 通过访问Mapping API获得该临时文件的动态Mapping定义

③ 修改后用，使用该配置创建你的索引

④ 删除临时索引

3.控制当前字段是否被索引

4.Index Options

5.null_value

6.copy_to设置

7.数组类型

DELETE users

#自定义mapping ,mobile设置为false,不为被搜索,设置 index 为 false
PUT users
{
    "mappings" : {
      "properties" : {
        "firstName" : {
          "type" : "text"
        },
        "lastName" : {
          "type" : "text"
        },
        "mobile" : {
          "type" : "text",
          "index": false
        }
      }
    }
}

#查看mapping
GET users/_mapping

#添加数据一
PUT users/_doc/1
{
  "firstName":"Zhao",
  "lastName": "YiDan",
  "mobile": "1358174623"
}

//搜索--提示错误！！
POST /users/_search
{
  "query": {
    "match": {
      "mobile":"1358174623"
    }
  }
}

########################## 
#设定Null_value
DELETE users
PUT users
{
    "mappings" : {
      "properties" : {
        "firstName" : {
          "type" : "text"
        },
        "lastName" : {
          "type" : "text"
        },
        "mobile" : {
          "type" : "keyword",
          "null_value": "NULL"
        }

      }
    }
}

#添加测试数据
PUT users/_doc/1
{
  "firstName":"Zhao",
  "lastName": "YiDan",
  "mobile": null
}

#测试测试数据2
PUT users/_doc/2
{
  "firstName":"Zhao2",
  "lastName": "YiDan2"
}

#搜索mobole为null的数据，而不是不存在的数据
GET users/_search
{
  "query": {
    "match": {
      "mobile":"NULL"
    }
  }
}

######################## 设置Copy to ############
DELETE users
#设置Mapping
PUT users
{
  "mappings": {
    "properties": {
      "firstName":{
        "type": "text",
        "copy_to": "fullName"
      },
      "lastName":{
        "type": "text",
        "copy_to": "fullName"
      }
    }
  }
}

#添加测试数据
PUT users/_doc/1
{
  "firstName":"Zhao",
  "lastName": "YiDan"
}


#搜索多个字段中内容，但是_source中没有fullName
GET users/_search?q=fullName:(Zhao YiDan)

POST users/_search
{
  "query": {
    "match": {
       "fullName":{
        "query": "Zhao YiDan",
        "operator": "and"
      }
    }
  }
}

############# 数组类型 ##############
DELETE users
#设置数组类型
PUT users/_doc/1
{
  "name":"onebird",
  "interests":"reading"
}

#添加测试数据
PUT users/_doc/1
{
  "name":"onebird",
  "interests":"reading"
}
PUT users/_doc/2
{
  "name":"twobirds",
  "interests":["reading","music"]
}

#查询
POST users/_search
{
  "query": {
		"match_all": {}
	}
}

#查看mapping
GET users/_mapping

https://www.elastic.co/guide/en/elasticsearch/reference/7.1/mapping-params.html

注意事项：

1.一切文本类型的字符串可以定义成 “text”或“keyword”两种类型。区别在于，text类型会使用默认分词器分词，当然你也可以为他指定特定的分词器。如果定义成keyword类型，那么默认就不会对其进行分词。

es对字符串类型的mapping设定，会将其定义成text，同时为他定义一个叫做keyword的子字段。keyword只是他的名字，你也可以定义成kw。这个字段的类型是keyword（这是一个类型的关键字）

多字段类型情况下，你可以查询 title，也可以查询title.keyword查询类型为keyword的子字段

转载于:https://my.oschina.net/hanchao/blog/3080131

chunyanhuai6598

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
Elasticsearch简单学习5:入门学习-2

一、基础说明 1.Search API 《1.》URI Search 在URL中使用查询参数《2.》Request Body Search 使用Elasticsearch提供的，基于JSON格式的更加完备的Query Domain Spe...
复制链接

扫一扫