elasticsearch学习笔记

头像
沧浪水
    阅读 12 分钟

    参考【阮一峰：全文搜索引擎 Elasticsearch 入门教程】

    1、安装初始化环境

    a.使用单机开发版

    #数据保存到本地
docker run -d --name es --restart=always \
    --net mybridge --ip=172.1.111.12 \
    -v /home/tools/elasticsearch/single/data/:/usr/share/elasticsearch/data/ \
    -e "discovery.type=single-node" \
    elasticsearch:7.7.0

    b.数据库请求

    启动检查
    ### 系统info
curl -X GET http://172.1.111.12:9200
### 分片索引列表
curl -X GET 'http://172.1.111.12:9200/_cat/indices?v'
### 分片索引列表info
curl -X GET 'http://172.1.111.12:9200/_mapping?pretty=true'
    安装中文分词插件，数据库初始化
    docker exec -it es bash
./bin/elasticsearch-plugin install 'https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v7.7.0/elasticsearch-analysis-ik-7.7.0.zip'
exit
docker restart es

### 建立索引目录 accounts
curl -X GET 'http://172.1.111.12:9200/accounts'
### 删除索引
curl -X DELETE 'http://172.1.111.12:9200/accounts'

    c.索引类型修改

    # 分词设置和修改，可以添加时已经指定、无需修改
# https://www.elastic.co/guide/en/elasticsearch/reference/current/analysis-custom-analyzer.html
# https://github.com/medcl/elasticsearch-analysis-ik
curl -X PUT 'http://172.1.111.12:9200/accounts' -d '
{
    "settings" : {
        "index" : {
            "analysis.analyzer.default.type": "ik_max_word"
        }
    }
}'
# 中文语句分词查询测试：analyzer项可以省略，[ik_max_word|standard]
curl -X PUT 'http://172.1.111.12:9200/accounts/_analyze' -d '
{
  "analyzer": "standard",
  "text": " ES的默认分词设置是standard，这个在中文分词时就比较尴尬了，会单字拆分"
}' -H 'Content-Type:application/json'

    2、增删改查操作

    建库建表：建立索引下的对象

    这里注意POST、PUT参数 -H 'Content-Type:application/json' 参数。

    Content-Type header [application/x-www-form-urlencoded] is not supported
    #新建一个名称为accounts的 Index，里面有一个名称为person的 Type。person有三个字段
curl -X PUT 'http://172.1.111.12:9200/accounts' -d '
{
  "mappings": {
    "person": {
      "properties": {
        "user": {
          "type": "text",
          "analyzer": "ik_max_word",
          "search_analyzer": "ik_max_word"
        },
        "title": {
          "type": "text",
          "analyzer": "ik_max_word",
          "search_analyzer": "ik_max_word"
        },
        "desc": {
          "type": "text",
          "analyzer": "ik_max_word",
          "search_analyzer": "ik_max_word"
        }
      }
    }
  }
}' -H 'Content-Type:application/json'

    a.数据添加

    curl -X PUT 'http://172.1.111.12:9200/accounts/person/2' -d '
{
  "user": "张三",
  "title": "工程师",
  "desc": "数据库管理"
}' -H 'Content-Type:application/json'
# 返回
{
    "_index": "accounts",
    "_type": "person",
    "_id": "1",
    "_version": 1,
    "result": "created",
    "_shards": {
        "total": 2,
        "successful": 1,
        "failed": 0
    },
    "_seq_no": 0,
    "_primary_term": 2
}
# 再添加一条
curl -X PUT 'http://172.1.111.12:9200/accounts/person/2' -d '
{
  "user": "张三2",
  "title": "工程师",
  "desc": "数据库管理"
}' -H 'Content-Type:application/json'

    b.数据查看

    # 查询总人数，不加-d报错
curl -X POST 'http://172.1.111.12:9200/accounts/person' -d '{}' -H 'Content-Type:application/json'
# 返回
{
    "_index": "accounts",
    "_type": "person",
    "_id": "5oypSXIBsIkVNyXrn1o5",
    "_version": 1,
    "result": "created",
    "_shards": {
        "total": 2,
        "successful": 1,
        "failed": 0
    },
    "_seq_no": 3,
    "_primary_term": 3
}

# 查询单条记录
curl -X GET 'http://172.1.111.12:9200/accounts/person/1'
# 返回
{"_index":"accounts","_type":"person","_id":"1","_version":1,"_seq_no":0,"_primary_term":2,"found":true,"_source":
{
  "user": "张三",
  "title": "工程师",
  "desc": "数据库管理"
}}

    c.数据删除

    curl -X DELETE 'http://172.1.111.12:9200/accounts/person/2'
# 返回
{
    "_index": "accounts",
    "_type": "person",
    "_id": "2",
    "_version": 2,
    "result": "deleted",
    "_shards": {
        "total": 2,
        "successful": 1,
        "failed": 0
    }
}

    d.数据更新

    curl -X PUT 'http://172.1.111.12:9200/accounts/person/2' -d '
{
  "user": "张三2",
  "title": "工程师",
  "desc": "数据库管理"
}' -H 'Content-Type:application/json'
# 返回
{"_index":"accounts","_type":"person","_id":"2","_version":1,"result":"created","_shards":{"total":2,"successful":1,"failed":0},"_seq_no":6,"_primary_term":3}
curl -X PUT 'http://172.1.111.12:9200/accounts/person/2' -d '
{
  "user": "张三233",
  "title": "工程师",
  "desc": "数据库管理"
}' -H 'Content-Type:application/json'
# 返回
{"_index":"accounts","_type":"person","_id":"2","_version":2,"result":"updated","_shards":{"total":2,"successful":1,"failed":0},"_seq_no":7,"_primary_term":3}

    两次返回情况：

    _version: 增加
    _seq_no: 增加
    created -> updated

    3、复杂查询

    a.查询列表页

    curl -X PUT http://172.1.111.12:9200/accounts/person/_search
# 返回
{
    "took": 1,
    "timed_out": false,
    "_shards": {
        "total": 1,
        "successful": 1,
        "skipped": 0,
        "failed": 0
    },
    "hits": {
        "total": {
            "value": 5,
            "relation": "eq"
        },
        "max_score": 1.0,
        "hits": [{
            "_index": "accounts",
            "_type": "person",
            "_id": "1",
            "_score": 1.0,
            "_source": {
                "user": "张三",
                "title": "工程师",
                "desc": "数据库管理"
            }
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "sYynSXIBsIkVNyXrfVpX",
            "_score": 1.0,
            "_source": {
                "analyzer": "ik_max_word",
                "text": " ES的默认分词设置是standard，这个在中文分词时就比较尴尬了，会单字拆分"
            }
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "5oypSXIBsIkVNyXrn1o5",
            "_score": 1.0,
            "_source": {}
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "9IyqSXIBsIkVNyXrLVrA",
            "_score": 1.0,
            "_source": {}
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "2",
            "_score": 1.0,
            "_source": {
                "user": "张三233",
                "title": "工程师",
                "desc": "数据库管理"
            }
        }]
    }
}

    由于前面在 ApiPost 的误操作，产生了一些垃圾数据。

    total：返回记录数，本例是2条。
max_score：最高的匹配程度，本例是1.0。
hits：返回的记录组成的数组。

    b.匹配查询

    https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl-script-query.html

    指定标题搜索[=]
    curl -X GET 'http://172.1.111.12:9200/accounts/person/_search'  -d '
{
    "query": {
        "bool": {
            "must": [{
                "match": {
                    "title": "师"
                }
            }],
            "filter": []
        }
    }
}' -H 'Content-Type:application/json'
# 返回
{
    "took": 2,
    "timed_out": false,
    "_shards": {
        "total": 1,
        "successful": 1,
        "skipped": 0,
        "failed": 0
    },
    "hits": {
        "total": {
            "value": 2,
            "relation": "eq"
        },
        "max_score": 0.10536051,
        "hits": [{
            "_index": "accounts",
            "_type": "person",
            "_id": "1",
            "_score": 0.10536051,
            "_source": {
                "user": "张三",
                "title": "工程师",
                "desc": "数据库管理"
            }
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "2",
            "_score": 0.10536051,
            "_source": {
                "user": "张三233",
                "title": "工程师",
                "desc": "数据库管理"
            }
        }]
    }
}
    增加词量
    curl -X GET 'http://172.1.111.12:9200/accounts/person/_search'  -d '
{
    "query": {
        "bool": {
            "must": [{
                "match": {
                    "title": "工程师"
                }
            }],
            "filter": []
        }
    }
}' -H 'Content-Type:application/json'
# 返回
{
    "took": 5,
    "timed_out": false,
    "_shards": {
        "total": 1,
        "successful": 1,
        "skipped": 0,
        "failed": 0
    },
    "hits": {
        "total": {
            "value": 2,
            "relation": "eq"
        },
        "max_score": 0.31608152,
        "hits": [{
            "_index": "accounts",
            "_type": "person",
            "_id": "1",
            "_score": 0.31608152,
            "_source": {
                "user": "张三",
                "title": "工程师",
                "desc": "数据库管理"
            }
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "2",
            "_score": 0.31608152,
            "_source": {
                "user": "张三233",
                "title": "工程师",
                "desc": "数据库管理"
            }
        }]
    }
}

    会提高 hits.hits._score。

    #添加size，限制返回数
{
    "query": {"bool":{"must":[{"match":{"title":"工程师"}}],"filter":[]}},
    "size": 1
}

    c.多条件查询

    测试数据

    curl -X PUT 'http://172.1.111.12:9200/accounts/person/3' -d '
{
  "user": "李明",
  "title": "工程师 学习",
  "desc": "运维 架构师"
}' -H 'Content-Type:application/json'

curl -X PUT 'http://172.1.111.12:9200/accounts/person/4' -d '
{
  "user": "夏天",
  "title": "工程师 教育",
  "desc": "软件 系统"
}' -H 'Content-Type:application/json'

curl -X PUT 'http://172.1.111.12:9200/accounts/person/5' -d '
{
  "user": "呃呃",
  "title": "呵呵 123 学习",
  "desc": "系统 运维 学习"
}' -H 'Content-Type:application/json'

curl -X PUT 'http://172.1.111.12:9200/accounts/person/6' -d '
{
  "user": "明白",
  "title": "问问 123 学习",
  "desc": "系统 软件 看看"
}' -H 'Content-Type:application/json'

    and搜索，必须使用布尔查询

    ### or并集查询
curl 'http://172.1.111.12:9200/accounts/person/_search'  -d '
{
  "query" : { "match" : { "desc" : "软件 系统" }}
}' -H 'Content-Type: application/json'
# 返回
{
    "took": 1,
    "timed_out": false,
    "_shards": {
        "total": 1,
        "successful": 1,
        "skipped": 0,
        "failed": 0
    },
    "hits": {
        "total": {
            "value": 3,
            "relation": "eq"
        },
        "max_score": 5.4819746,
        "hits": [{
            "_index": "accounts",
            "_type": "person",
            "_id": "4",
            "_score": 5.4819746,
            "_source": {
                "user": "夏天",
                "title": "工程师 教育",
                "desc": "软件 系统"
            }
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "6",
            "_score": 4.7037764,
            "_source": {
                "user": "明白",
                "title": "问问 123 学习",
                "desc": "系统 软件 看看"
            }
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "5",
            "_score": 1.7504241,
            "_source": {
                "user": "呃呃",
                "title": "呵呵 123 学习",
                "desc": "系统 运维 学习"
            }
        }]
    }
}

### 布尔查询交集
curl 'http://172.1.111.12:9200/accounts/person/_search'  -d '
{
  "query": {
    "bool": {
      "must": [
        { "match": { "desc": "软件" } },
        { "match": { "desc": "系统" } }
      ]
    }
  }
}' -H 'Content-Type: application/json'
# 返回
{
    "took": 1,
    "timed_out": false,
    "_shards": {
        "total": 1,
        "successful": 1,
        "skipped": 0,
        "failed": 0
    },
    "hits": {
        "total": {
            "value": 2,
            "relation": "eq"
        },
        "max_score": 5.4819746,
        "hits": [{
            "_index": "accounts",
            "_type": "person",
            "_id": "4",
            "_score": 5.4819746,
            "_source": {
                "user": "夏天",
                "title": "工程师 教育",
                "desc": "软件 系统"
            }
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "6",
            "_score": 4.7037764,
            "_source": {
                "user": "明白",
                "title": "问问 123 学习",
                "desc": "系统 软件 看看"
            }
        }]
    }
}
    布尔查询排除
    query.bool: {must: [],must_not: []}

    d.分页排序

    排序输出 sort
    # sort by asc/desc
{
  "query": { "match_all": {"desc": "软件"} },
  "sort": [
    { "_id": "asc" }
  ]
}

    返回

    {
    "took": 22,
    "timed_out": false,
    "_shards": {
        "total": 1,
        "successful": 1,
        "skipped": 0,
        "failed": 0
    },
    "hits": {
        "total": {
            "value": 3,
            "relation": "eq"
        },
        "max_score": null,
        "hits": [{
            "_index": "accounts",
            "_type": "person",
            "_id": "4",
            "_score": null,
            "_source": {
                "user": "夏天",
                "title": "工程师 教育",
                "desc": "软件 系统"
            },
            "sort": ["4"]
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "5",
            "_score": null,
            "_source": {
                "user": "呃呃",
                "title": "呵呵 123 学习",
                "desc": "系统 运维 学习"
            },
            "sort": ["5"]
        }, {
            "_index": "accounts",
            "_type": "person",
            "_id": "6",
            "_score": null,
            "_source": {
                "user": "明白",
                "title": "问问 123 学习",
                "desc": "系统 软件 看看"
            },
            "sort": ["6"]
        }]
    }
}
    分页输出 from-size
    {
    "query": {
        "match_all": {"desc": "软件"}
    },
    "sort": [{
        "account_number": "asc"
    }],
    "from": 10,
    "size": 10
}

    f.有限范围查询

    # filter.range.[范围字段balance]: {"gte": 2000,"lte": 30000}
{
  "query": {
    "bool": {
      "must": { "match_all": {} },
      "filter": {
        "range": {
          "balance": {
            "gte": 20000,
            "lte": 30000
          }
        }
      }
    }
  }
}

    总结

    a.查询

    query.match_all

    简单查询

    query.match: {字段1:值1, 字段2:值2}

    交集查询

    query.bool: {must: [match{}],must_not: []}

    排序分页

    sort: [{ "_id": "asc" }]
    from: 10,
    size: 10

    限定范围

    filter.range.[范围字段balance]: {"gte": 2000,"lte": 30000}

    b.官方文档

    查询文档https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html

    c.小结

    使用约定的JSON数组查询，省去了DDL语句解析的时间；典型的使用RESTFUL-API风格请求响应，可以简化后端操作，基本功能甚至不需要后端开发的参与。

    elasticsearch后端
    沧浪水
    97 声望12 粉丝
    « 上一篇
    win10安装使用Vagrant
    下一篇 »
    K8S集群学习笔记整理（三）

    引用和评论

    推荐阅读
    头像
    其它工具安装

    沧浪水阅读 736

    头像
    Spring 实现 3 种异步流式接口，干掉接口超时烦恼

    程序员小富赞 5阅读 1.7k

    头像
    高质量代码的原则

    寒青赞 4阅读 5.4k

    头像
    日志与追踪的完美融合：OpenTelemetry MDC 实践指南

    crossoverJie赞 3阅读 1.7k

    头像
    Go 程序如何实现优雅退出？来看看 K8s 是怎么做的——上篇

    江湖十年赞 5阅读 750

    头像
    一文讲清楚static关键字

    seven97_top赞 4阅读 414

    头像
    每一个前端，都要拥有属于自己的埋点库~

    幸福的闹钟赞 2阅读 171

    0 条评论
    得票最新