ElasticSearch(一)-入门之基础语法

钗头风

已于 2023-11-07 13:42:28 修改

阅读量37

点赞数

分类专栏： elasticsearch 文章标签： elasticsearch 大数据搜索引擎

于 2023-10-23 14:45:40 首次发布

本文链接：https://blog.csdn.net/weixin_45876411/article/details/133906413

版权

elasticsearch 专栏收录该内容

7 篇文章 2 订阅

订阅专栏

ElasticSearch与传统关系型数据库对比

在ES中每条记录就是一个Document对象

基础命令：

创建索引(创建索引相当于创建数据库)

PUT /shopping

根据索引名称获取索引信息

GET /shopping

获取所有索引信息

GET /_cat/indices?v # 说明：参数v表示获取详细信息

根据索引名称删除索引

DELETE /shopping

创建文档(即为索引写入一条记录)

POST /shopping/_doc # 说明：_doc代表添加一条文档记录
{
  "name":"zs",
  "age":18,
  "address":"四川省"
}


响应：
    _id字段为ES自动生成的这条记录的唯一标识,相当于数据库的主键
{
  "_index" : "shopping",
  "_id" : "H_HxSosBy1IIAtuiyzK2", 
  "_version" : 1,
  "result" : "created",
  "_shards" : {
    "total" : 2,
    "successful" : 1,
    "failed" : 0
  },
  "_seq_no" : 0,
  "_primary_term" : 2
}


我们可以通过响应的_id去查询记录，但由于ES随机生成的ID不好记，所以我们可以在写入记录时手动指定id(在_doc后面跟上自定义ID)
POST /shopping/_doc/1001
{
  "name":"ls",
  "age":26,
  "address":"重庆市"
}

响应：
{
  "_index" : "shopping",
  "_id" : "1001",
  "_version" : 1,
  "result" : "created",
  "_shards" : {
    "total" : 2,
    "successful" : 1,
    "failed" : 0
  },
  "_seq_no" : 1,
  "_primary_term" : 2
}

根据主键查询文档记录

# 查询主键为1001的数据
GET /shopping/_doc/1001

查询索引下面的所有记录

GET /shopping/_search

更新记录

# 全量更新(覆盖)[使用PUT请求，PUT具有幂等性]
PUT /shopping/_doc/1001
{
  "name":"ls02",
  "age":26,
  "address":"重庆市"
}

# 局部更新[使用POST请求，POST不具有幂等性]
POST /shopping/_update/1001
{
  "doc":{ # doc中传入局部更新的字段及值
    "name":"ls03"
  }
}

删除记录

DELETE /shopping/_doc/1001

单条件查询&取指定字段&排序&分页(单条件使用match)

# 单条件查询&取指定字段&排序&分页
GET /shopping/_search
{
  "query": { # query代表查询
    "match": { # match代表匹配查询,类似于Where
      "category": "小米"
    }
  },
  "_source": ["title","price"], # _source代表要展示哪些字段
  "sort": [ # sort代表排序
    {
      "price": { # 根据"price"字段排序
        "order": "desc" # order 用于指定排序规则(升序/降序)
      }
    }
  ],
  "from": 0, # from代表分页的页码(计算规则同SQL Limit的计算规则一样)
  "size": 2 # size代表每页取多少条
}


# 查询索引下所有数据写法也可如下
GET /shopping/_search
{
  "query": {
    "match_all": {
      
    }
  }
}

多条件查询&范围查询(多条件使用bool)

# 多条件(AND-且)同时成立(查询category(品牌)为小米，且price为3200的商品)
GET /shopping/_search
{
  "query": { # 查询
    "bool": { # 多条件使用bool
      "must": [ # 多条件同时成立用must
        {
          "match": { # 每个match用于匹配一个条件
            "category": "小米"
          }
        },
          {
          "match": { # 每个match用于匹配一个条件
            "price": 3200
          }
        }
      ]
    }
  }
}



多条件(OR-或)同时成立(查询category(品牌)为小米或华为且价格大于3000的商品)
GET /shopping/_search
{
  "query": {
    "bool": { # 多条件查询使用bool
      "should": [ # 多条件 "OR-或"使用should表示
        {
          "match": { # 每个match用于匹配一个条件
            "category": "小米"
          }
        },
        {
          "match": { # 每个match用于匹配一个条件
            "category": "华为"
          }
        }
      ],
      "filter": [ # 过滤
        {
          "range": { # 范围过滤使用range
            "price": { 
              "gte": 3000 # 过滤price(价格)字段。取price大于等于3000的商品
            }
          }
        }
      ]
    }
  }
}

全文检索&完全匹配&高亮查询

# 全文检索的含义是将你match中的字符串进行分词再去索引库中匹配对应的记录
例一：全文检索 + 高亮
GET /shopping/_search
{
  "query": {
    "match": { # match会进行全文检索
      "category": "小华"
    }
  },
  "highlight": { # highlight代表高亮
    "fields": { # fields中指定高亮的字段
      "category": {} # 高亮字段为“category”
    }
  }
}

# 响应：因为全文检索是先分词再去匹配，所以其查询出来的数据会把category含有“小”或“华”的数据都匹配出来
{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : 1.3862942,
    "hits" : [
      {
        "_index" : "shopping",
        "_id" : "1003",
        "_score" : 1.3862942,
        "_source" : {
          "title" : "华为手机",
          "category" : "华为",
          "price" : 4200
        },
        "highlight" : {
          "category" : [
            "<em>华</em>为"
          ]
        }
      },
      {
        "_index" : "shopping",
        "_id" : "1001",
        "_score" : 0.2876821,
        "_source" : {
          "title" : "小米手机",
          "category" : "小米",
          "price" : 3200
        },
        "highlight" : {
          "category" : [
            "<em>小</em>米"
          ]
        }
      },
      {
        "_index" : "shopping",
        "_id" : "1002",
        "_score" : 0.2876821,
        "_source" : {
          "title" : "红米手机",
          "category" : "小米",
          "price" : 2200
        },
        "highlight" : {
          "category" : [
            "<em>小</em>米"
          ]
        }
      }
    ]
  }
}


例二：完全匹配 + 高亮
# 完全匹配则是对于输入的匹配词不进行分词进行完全匹配,如上匹配词为"小华",进行完全匹配是没有记录的
GET /shopping/_search
{
  "query": {
    "match_phrase": { # match_phrase会进行完全匹配
      "category": "小华" # 完全匹配的字段为category，值为“小华”
    }
  },
  "highlight": { # 指定高亮字段
    "fields": {
      "category": {}
    }
  }
}

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


例三：完全匹配 + 高亮
# 使用完全匹配去匹配category字段为“小米”，并且高亮category字段中匹配到的“小米”字符串
GET /shopping/_search
{
  "query": {
    "match_phrase": { # match_phrase表示完全匹配
      "category": "小米"
    }
  },
  "highlight": {
    "fields": {
      "category": {}
    }
  }
}


# 响应
{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : 0.5753642,
    "hits" : [
      {
        "_index" : "shopping",
        "_id" : "1001",
        "_score" : 0.5753642,
        "_source" : {
          "title" : "小米手机",
          "category" : "小米",
          "price" : 3200
        },
        "highlight" : {
          "category" : [
            "<em>小</em><em>米</em>"
          ]
        }
      },
      {
        "_index" : "shopping",
        "_id" : "1002",
        "_score" : 0.5753642,
        "_source" : {
          "title" : "红米手机",
          "category" : "小米",
          "price" : 2200
        },
        "highlight" : {
          "category" : [
            "<em>小</em><em>米</em>"
          ]
        }
      }
    ]
  }
}

聚合查询

# 例一：根据price字段聚合(取原始数据 + 聚合数据)
GET /shopping/_search
{
  "aggs": {
    "price_group": { # 自定义聚合名称
      "terms": {
        "field": "price"
      }
    }
  }
}


响应：
{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [ # 原始数据
      {
        "_index" : "shopping",
        "_id" : "1001",
        "_score" : 1.0,
        "_source" : {
          "title" : "小米手机",
          "category" : "小米",
          "price" : 3200
        }
      },
      {
        "_index" : "shopping",
        "_id" : "1002",
        "_score" : 1.0,
        "_source" : {
          "title" : "红米手机",
          "category" : "小米",
          "price" : 2200
        }
      },
      {
        "_index" : "shopping",
        "_id" : "1003",
        "_score" : 1.0,
        "_source" : {
          "title" : "华为手机",
          "category" : "华为",
          "price" : 4200
        }
      }
    ]
  },
  "aggregations" : { # 聚合数据
    "price_group" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : 2200,
          "doc_count" : 1
        },
        {
          "key" : 3200,
          "doc_count" : 1
        },
        {
          "key" : 4200,
          "doc_count" : 1
        }
      ]
    }
  }
}




# 例二：根据price字段聚合(只取聚合数据)
GET /shopping/_search
{
  "aggs": { # 聚合操作
    "price_group": { # 自定义本次聚合名称(随意取名)
      "terms": { # terms代表聚合分组
        "field": "price" # 分组字段
      }
    }
  },
  "size": 0 # 去掉原始数据(即只取聚合数据)
}


响应：
{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : { # 聚合数据
    "price_group" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : 2200,
          "doc_count" : 1 # 本次根据price聚合,price为2200的总条数
        },
        {
          "key" : 3200,
          "doc_count" : 1
        },
        {
          "key" : 4200,
          "doc_count" : 1
        }
      ]
    }
  }
}


# 例三：求price平均值
GET /shopping/_search
{
  "aggs": {
    "price_avg": { # 自定义聚合名称
      "avg": { # avg 代表求平均值
        "field": "price" # price为聚合字段
      }
    }
  },
  "size": 0
}


响应：
{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 3,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "price_avg" : { # 平均值
      "value" : 3200.0
    }
  }
}

映射关系(即创建索引时为“字段”指定是否分词,是否支持检索)

# 创建user索引库
PUT /user

# 为user索引库字段指定是否分词,是否能被索引
PUT /user/_mapping
{
  "properties":{
    "name":{ # 字段name
     "type":"text", # text支持分词
     "index":true # 支持被检索
    },
    "sex":{ # 字段sex
     "type":"keyword", # keyword不支持分词
     "index":true # 支持被检索
    },
    "tel":{ # 字段tel
     "type":"keyword", # 不支持分词
     "index":false # 不支持检索
    }
  }
}


# 为user索引库新加一条记录
PUT /user/_doc/1001
{
  "name":"张三",
  "sex":"男的",
  "tel":"110"
}



# 测试一：测试name支持分词，支持检索
GET /user/_search
{
  "query": {
    "match": {
      "name": "张"
    }
  }
}

响应：
{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1,
      "relation" : "eq"
    },
    "max_score" : 0.2876821,
    "hits" : [
      {
        "_index" : "user",
        "_id" : "1001",
        "_score" : 0.2876821,
        "_source" : {
          "name" : "张三",
          "sex" : "男的",
          "tel" : "110"
        }
      }
    ]
  }
}


# 测试二：测试sex不支持分词，支持检索
GET /user/_search
{
  "query": {
    "match": {
      "name": "男" # 因为name字段不支持分词,故传"男"检索不到数据
    }
  }
}

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

# 测试三：测试tel不支持分词，不支持检索(特别说明：ES8.1.0可以检索到，以前老的ES版本index为false是检索不到的)
GET /user/_search
{
  "query": {
    "match": {
      "tel": "110"
    }
  }
}

响应：
{
  "took" : 0,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "user",
        "_id" : "1001",
        "_score" : 1.0,
        "_source" : {
          "name" : "张三",
          "sex" : "男的",
          "tel" : "110"
        }
      }
    ]
  }
}

钗头风

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
ElasticSearch(一)-入门之基础语法

映射关系(即创建索引时为“字段”指定是否分词,是否支持检索)单条件查询&取指定字段&排序&分页(单条件使用match)多条件查询&范围查询(多条件使用bool)创建索引(创建索引相当于创建数据库)创建文档(即为索引写入一条记录)在ES中每条记录就是一个Document对象。全文检索&完全匹配&高亮查询。根据索引名称获取索引信息。根据索引名称删除索引。查询索引下面的所有记录。根据主键查询文档记录。
复制链接

扫一扫