ElasticSearch 入门

最新推荐文章于 2024-08-15 15:48:28 发布

chenxi004

最新推荐文章于 2024-08-15 15:48:28 发布

阅读量127

点赞数

分类专栏： elasticsearch 文章标签： elasticsearch

本文链接：https://blog.csdn.net/chenxi004/article/details/97929844

版权

elasticsearch 专栏收录该内容

6 篇文章 0 订阅

订阅专栏

GET _search
{
  "query": {
    "match_all": {}
  }
}

/获取所有的索引/

GET /_cat/indices

/检查es健康状况/

GET /_cat/health

/创建索引为twitter（要先在索引模式中创建索引模式，并与之匹配）；type为_doc,id为1 的一个索引/

POST twitter/_doc/1
{
  "user":"QCX",
  "uid":1,
  "city":"beijing",
  "province":"Beijing",
  "country":"China"
}

/查询数据通过id搜索/

GET twitter/_doc/1

/put 更新数据/

PUT twitter/_doc/1
{
  "user":"乔晨曦",
  "uid":1,
  "city":"北京",
  "province":"北京",
  "country":"中国",
  "location":{
    "lat":"29.884661",
    "lon":"111.335210"
  }
}

/通过查询更新数据，API:_update_by_query/

POST twitter/_update_by_query
{
  "script":{
    "source":"ctx._source.city=params.city;ctx._source.province=params.province;",
    "lang":"painless",
    "params":{
      "city":"上海",
      "province":"上海"
    }
  },
  "query":{
    "match":{
      "user":"乔晨曦"
    }
  }
}

/删除 index twitter/

DELETE twitter

/批量插入数据 _bulk接口针对twitter这个index操作/

POST _bulk
{"index":{"_index":"twitter"}}
{"user":"双榆树-张三","message":"今天天气不错 出去转转去","uid":2,"age":20,"city":"北京","province":"北京","country":"中国","address":"中国北京市海淀区","location":{"lat":"39.970718","lon":"116.325747"}}
{"index":{"_index":"twitter"}}
{"user":"东城区-老刘","message":"出发，下一站云南","uid":3,"age":30,"city":"北京","province":"北京","country":"中国","address":"中国北京市东城区","location":{"lat":"39.904313","lon":"116.412757"}}
{"index":{"_index":"twitter"}}
{"user":"东城区-李四","message":"happy birthday","uid":4,"age":30,"city":"北京","province":"北京","country":"中国","address":"中国北京市海淀区","location":{"lat":"39.893801","lon":"116.408986"}}
{"index":{"_index":"twitter"}}
{"user":"朝阳区区-老贾","message":"123 gogogo","uid":5,"age":35,"city":"北京","province":"北京","country":"中国","address":"中国北京市朝阳区建国门","location":{"lat":"39.718256","lon":"116.367910"}}
{"index":{"_index":"twitter"}}
{"user":"朝阳区-老王","message":"Happy Birthday My Friend！","uid":6,"age":50,"city":"北京","province":"北京","country":"中国","address":"中国北京市朝阳区国贸","location":{"lat":"39.918256","lon":"116.467910"}}
{"index":{"_index":"twitter"}}
{"user":"红桥-老吴","message":"好朋友来了都今天我生日，好友来了，什么 birthday happy 就成！","uid":7,"age":90,"city":"上海","province":"上海","country":"中国","address":"中国上海市闵行区","location":{"lat":"31.175927","lon":"121.383328"}}
GET twitter/_search

/类似数据库中的表里面的type：text：这个字段可以用于全文索引，keywords：表示这个字段可以用于聚合查询或者统计分析,text比keywords占用更多存储空间；这个mapping是自动发生的我们叫做dynamic mapping。动态mapping有一个问题：有些字段不会正确的mapping，比如location字段没有mapping到geo位置信息。解决方法就是重新配置这个mapping/

GET twitter/_mapping

DELETE twitter

/设置 twitter 这个索引的基本信息有一个分片/

PUT twitter
{
  "settings":{"number_of_shards": 1}
}

/用 _mapping这个接口对twitter的mapping重新定义/

PUT twitter/_mapping
{
  "properties" : {
        "address" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        },
        "city" : {
          "type" : "keyword"
        },
        "country" : {
          "type" : "keyword"
        },
        "location" : {
          "type" : "geo_point"
        },
        "province" : {
          "type" : "keyword"
        },
        "uid" : {
          "type" : "long"
        },
        "user" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 256
            }
          }
        }
      }
}

/查询数据用接口_search/
GET twitter/_search
{
“query”:{
“match”:{
“city”:“上海”
}
}
}
/使用bool表达式，使用了must条件，必须满足里面的两个条件，北京的年龄是30的；must 等同于sql中的and条件/

GET twitter/_search
{
  "query":{
    "bool":{
      "must":[
        {
          "match":{
            "city":"北京"
          }
        },
        {
          "match":{
            "age":"30"
          }
        }
      ]
    }
    
  }
}

/使用bool表达式，使用了must_not条件，查询不在北京的/

GET twitter/_search
{
  "query":{
    "bool":{
      "must_not":[
        {
          "match":{
            "city":"北京"
          }
        }
      ]
    }
    
  }
}

/使用bool表达式，使用了should条件，满足里面的两个条件之一即可，北京的或者上海的；should 等同于sql中的or条件/

GET twitter/_search
{
  "query":{
    "bool":{
      "should":[
        {
          "match":{
            "city":"北京"
          }
        },
        {
          "match":{
            "city":"上海"
          }
        }
      ]
    }
    
  }
}

/使用_count接口查询满足条件的数量/

GET twitter/_count
{
  "query":{
    "bool":{
      "should":[
        {
          "match":{
            "city":"北京"
          }
        },
        {
          "match":{
            "city":"上海"
          }
        }
      ]
    }
    
  }
}

/基于地理位置的查询；
朝外soho 39.920086,116.454182
查询距离朝外soho 5km范围内的
上面query是查询条件
下面post_filter对查询结果过滤，按照地理位置过滤/

GET twitter/_search
{
  "query":{
    "bool":{
      "must":[
        {
          "match":{
            "address":"北京"
          }
        }
      ]
    }
  },
  "post_filter": {
    "geo_distance": {
      "distance": "5km",
      "location": {
        "lat": 39.920086,
        "lon": 116.454182
      }
    }
  }
}

/查询距离朝外soho 5km范围内的按距离排序/

GET twitter/_search
{
  "query":{
    "bool":{
      "must":[
        {
          "match":{
            "address":"北京"
          }
        }
      ]
    }
  },
  "post_filter": {
    "geo_distance": {
      "distance": "5km",
      "location": {
        "lat": 39.920086,
        "lon": 116.454182
      }
    }
  },
  "sort": [
    {
      "_geo_distance": {
        "location": {
          "lat": 39.920086,
          "lon": 116.454182
        }, 
        "order": "asc",
        "unit": "km"
      }
    }
  ]
}

/范围查询大于等于30岁，小于等于40岁之间的降序排/

GET twitter/_search
{
  "query":{
    "range":{
      "age":{
        "gte":30,
        "lte":40
      }
    }
  },
  "sort": [
    {
      "age": {
        "order": "desc"
      }
    }
  ]
}

/查询除了包含happy 和 birthday 的记录/

GET twitter/_search
{
  "query":{
    "match":{
      "message":"happy birthday"
    }
  }
}

/注意大小写的自动处理这里没有区分大小写
Happy birthday 按照一个词组查询/

GET twitter/_search
{
  "query":{
    "match_phrase":{
      "message":"Happy birthday"
    }
  }
}

/对结果进行高亮展示 highlight,查询结果多出一个highlight属性，返回一个带有标签的字符串/

GET twitter/_search
{
  "query":{
    "match_phrase":{
      "message":"Happy birthday"
    }
  }, 
  "highlight": {
    "fields": {
      "message": {}
    }
  }
}

/聚合操作 aggs，range 操作/
/size:0 不会把命中内容展示出来/

GET twitter/_search
{
  "size":10,
  "aggs":{
    "age":{
      "range":{
        "field":"age",
        "ranges":[
          {
            "from":20,
            "to":30
          },
          {
            "from":30,
            "to":40
          },
          {
            "from":40,
            "to":50
          }
        ]
          
      }
    }
  }
}

/聚合操作 aggs，term 操作类似sql的group by,按照某个字段分组运算/

GET twitter/_search
{
  "query":{
    "match":{
      "message":"happy birthday"
    }
  }, 
  "size":0,
  "aggs":{
    "city":{
      "terms":{
        "field":"city",
        "size":10
      }
    }
  }
}

/_analyze：分词器，分析器；分词过滤操作再形成倒排索引
一个分词器由三个部分组成：
1、char filter 对字段进行过滤
2、tokenizer 形成分词器，讲一句话分成各个短语各个
3、filter 过滤器对分开的词进行过滤
在对index做mapping时是可以指定分词器的，默认分词器时standard
下面测试_analyzer分词器/
/standard 只能用空格做分词/

GET twitter/_analyze
{
  "text":["Happy Birthday"],
  "analyzer":"standard"
}

/analyzer simple/

GET twitter/_analyze
{
  "text":["Happy.Birthday"],
  "analyzer":"simple"
}

/自己设定tokenizer 和 filter来实现分词
如果一开始没有指定filter，只指定了tokenizer，把词组分成了Happy 和 Birthday 两个词，但是没有转为小写，这时候指定filter 把两个词都转为小写/

GET twitter/_analyze
{
  "text":["Happy Birthday"],
  "tokenizer":"standard",
  "filter":["lowercase"]
}

chenxi004

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
复制链接

分享到 QQ

分享到新浪微博

扫一扫

专栏目录