1. Toy模板网首页
  2. > Toy博客

es线上处理命令记录

9月前 作者：gitxuzan_ 分类：Toy博客 阅读(30) 违法举报

这篇具有很好参考价值的文章主要介绍了es线上处理命令记录。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

常用命令

搜索

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

获取全部模版

GET _index_template
GET _index_template/yst_crawler_template

获取全部索引

GET /_cat/indices?v

获取当前mapping

GET /yst_crawler/_mapping

创建一个mapping

PUT /yst_crawler
{
  "settings": {
    "number_of_shards": 1,
    "number_of_replicas": 1
  },
  "mappings": {
    "properties": {
			"id":{
					"type": "long"
			},
      "cover_url": {
        "type": "keyword"
      },
      "title": {
        "type": "text",
        "analyzer": "english"
      },
      "create_at": {
        "type": "date",
        "format": "epoch_second"
      },
      "article_time": {
        "type": "date",
        "format": "epoch_second"
      },
      "milli_at": {
        "type": "date",
        "format": "epoch_millis"
      }
    }
  }
}

GET /yst_crawler/_mapping

删除一个索引

DELETE /yst_crawler

当前分词使用

POST /_analyze
{
  "analyzer": "standard",
  "text": "In a polarized US, how to define a patriot increasingly depends on who’s being asked"

}

查找数据

GET /yst_crawler/_search
{
 	"query": { "match_all": {} },
 	  "sort": [
    {
      "milli_at": {
        "order": "desc"
      }
    }
  ],
 	"from": 0,
  "size": 20
}

精确查询

GET /yst_crawler/_search
{
  "query": {
    "term": {
      "id": {
        "value": "1"
      }
    }
  }
}


GET /yst_crawler/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "title": "$20 million settlement"
          }
        },
        {
          "range": {
            "milli_at": {
              "gte": "now-30d/d",
              "lte": "now/d"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "milli_at": {
        "order": "desc"
      }
    }
  ],
  "_source": ["id", "title", "milli_at", "s3_url", "article_time", "detail_url", "ref_id", "req_md5", "tags", "category", "content", "milli_at"],
  "from": 0,
  "size": 20
}

GET /yst_crawler/_search
{
  "query": {
    "match_all": {}
  },
  "sort": [
    {
      "milli_at": {
        "order": "desc"
      }
    }
  ],
  "_source": ["id", "title","milli_at","s3_url","article_time","detail_url","ref_id","req_md5","tags","category","content","milli_at"],
  "from": 0,
  "size": 10
}

媒体和分页查询

GET /yst_crawler/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "title": "$20 million settlement"
          }
        },
        {
          "terms": {
            "ref_id": ["8fac888ae06647c3a7d6093c60c9d9b5"]
          }
        },
        {
          "range": {
            "milli_at": {
              "gte": "now-30d/d",
              "lte": "now/d"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "milli_at": {
        "order": "desc"
      }
    }
  ],
  "_source": ["id", "title", "milli_at", "s3_url", "article_time", "detail_url", "ref_id", "req_md5", "tags", "category", "content", "milli_at"],
  "from": 0,
  "size": 20
}



GET /yst_crawler/_search
{
  "query": {
    "match": {
      "id": "22111"
    }
  },
  "sort": [
    {
      "milli_at": {
        "order": "desc"
      }
    }
  ],
  "_source": ["id", "title","milli_at","s3_url","article_time","detail_url","ref_id","req_md5","tags","category","content","milli_at"],
  "from": 0,
  "size": 20
}

GET /yst_crawler/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "title": "$20 million settlement"
          }
        },
        {
          "range": {
            "milli_at": {
              "gte": "now-30d/d",
              "lte": "now/d"
            }
          }
        }
      ]
    }
  },
  "sort": [
    {
      "milli_at": {
        "order": "desc"
      }
    }
  ],
  "_source": ["id", "title", "milli_at", "s3_url", "article_time", "detail_url", "ref_id", "req_md5", "tags", "category", "content", "milli_at","article_id"],
  "from": 0,
  "size": 19
}


GET /yst_crawler/_search
{
  "query": {
    "bool": {
      "must": [
  	    {
  	      "term": {
  	        "is_status": 0
  	      }
  	    },
        {
          "term": {
            "category": "for_you"
          }
        },
        {
          "range": {
            "milli_at": {
              "gte": "now-30d/d",
              "lte": "1690362492000"
            }
          }
        }
      ]
    }
  },
  "_source": ["id", "title", "milli_at", "s3_url", "article_time", "detail_url", "ref_id", "req_md5", "tags", "category", "content", "milli_at","article_id","desc","state"],
  "from": 0,
  "sort": [
    {
      "milli_at": {
        "order": "desc"
      }
    }
  ],
  "size": 20
}

修改mapping

GET /yst_crawler/_mapping

PUT /yst_crawler/_mapping
{
  "properties": {
    "state": {
      "type": "keyword"
    }
  }
}

查看setting

PUT /yst_city
{
  "settings": {
    "index.max_ngram_diff": 2,
    "analysis": {
      "analyzer": {
        "comma_analyzer": {
          "type": "pattern",
          "pattern": ","
        },
        "code_ngram_analyzer": {
          "tokenizer": "code_ngram_tokenizer"
        }
      },
      "tokenizer": {
        "code_ngram_tokenizer": {
          "type": "ngram",
          "min_gram": 2,
          "max_gram": 4
        }
      }
    }
  },
  "mappings": {
    "properties": {
      "id": {
        "type": "integer"
      },
      "state": {
        "type": "keyword"
      },
      "country": {
        "type": "keyword"
      },
      "city": {
        "type": "text"
      },
      "code": {
        "type": "text",
        "analyzer": "comma_analyzer",
        "fields": {
          "ngram": {
            "type": "text",
            "analyzer": "code_ngram_analyzer"
          }
        }
      },
      "create_at": {
        "type": "integer"
      },
      "is_popular": {
        "type": "byte"
      },
      "sort": {
        "type": "short"
      },
      "location": {
        "type": "geo_point"
      }
    }
  }
}

搜索 city 和 code

GET /yst_city/_search
{
  "query": {
    "match": {
      "code": "36310"
    }
  },
  "_source": ["id","state","city","code","is_popular","location"],
  "from": 0,
  "size": 20
}

GET /yst_city/_search
{
  "query": {
    "match": {
      "code.ngram": "31"
    }
  },
    "_source": ["id","state","city","code","is_popular","location"],
  "from": 0,
  "size": 20
}


GET /yst_city/_search
{
  "query": {
    "bool": {
      "filter": [
        {
          "term": {
            "is_popular": 1
          }
        }
      ]
    }
  },
  "sort": [
    {
      "sort": {
        "order": "asc"
      }
    }
  ],
  "_source": ["id","state","city","code","is_popular","location"],
  "from": 0,
  "size": 20
}




GET /yst_city/_search
{
  "query": {
    "function_score": {
      "query": {
        "query_string": {
          "default_field": "city",
          "query": "e york"
        }
      },
      "field_value_factor": {
        "field": "is_popular",
        "factor": 1.2,
        "modifier": "sqrt",
        "missing": 1
      },
      "boost_mode": "multiply"
    }
  },
  "_source": ["id","state","city","is_popular","location"],
  "from": 0,
  "size": 20
}


GET /yst_crawler/_search
{
  "query": {
    "term": {
      "title.keyword": {
        "value": "Man kicks in door, assaults ex-girlfriend: Solon Police Blotter"
      }
    }
  }
}


GET /yst_crawler/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "title": "110"
          }
        },
        {
          "range": {
            "milli_at": {
              "gte": "now-8d/d",
              "lte": "now/d"
            }
          }
        }
      ]
    }
  },
  "_source": ["id", "title", "milli_at", "s3_url", "article_time", "detail_url", "ref_id", "req_md5", "tags", "category", "content", "milli_at","article_id","desc"],
  "from": 0,
  "size": 10
}

认证分词

GET /yst_crawler/_analyze
{
  "analyzer": "my_custom_analyzer",
  "text": "这里填入你想要分析的文本，例如：110"
}

GET /yst_crawler/_analyze
{
  "analyzer": "standard",
  "text": "这里填入你想要分析的文本，例如：110"
}




POST /_analyze
{
  "tokenizer": "standard",
  "filter": [
    "lowercase",
    {
      "type": "stop",
      "stopwords": [
        "a", "an", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"
      ]
    }
  ],
  "text": "hello 110th 10223"
}

删除一个模版

DELETE _index_template/yst_crawler_template

创建一个索引模版

该模版下，创建的索引前缀都会使用这个模版 yst_crawler

PUT _index_template/yst_crawler_template
{
  "index_patterns": ["yst_crawler*"],
  "template": {
    "settings": {
      "number_of_shards": 1,
      "number_of_replicas": 0,
      "analysis": {
        "filter": {
          "my_stop_filter": {
            "type": "stop",
            "stopwords": [
              "a", "an", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"
            ]
          }
        },
        "analyzer": {
          "my_new_custom_analyzer": {
            "type": "custom",
            "tokenizer": "standard",
            "filter": [
              "lowercase",
              "my_stop_filter"
            ]
          }
        }
      }
    },
    "mappings": {
      "properties": {
        "id": {
          "type": "long"
        },
        "is_status": {
          "type": "byte"
        },
        "detail_url": {
          "type": "keyword"
        },
        "ref_id": {
          "type": "keyword"
        },
        "article_id": {
          "type": "keyword"
        },
        "tags": {
          "type": "text",
          "analyzer": "english"
        },
        "s3_url": {
          "type": "keyword"
        },
        "title": {
          "type": "text",
          "analyzer": "my_new_custom_analyzer",
          "fields": {
            "keyword": {
              "type": "keyword"
            }
          }
        },
        "article_time": {
          "type": "date",
          "format": "epoch_second"
        },
        "desc": {
          "type": "keyword"
        },
        "content": {
          "type": "keyword"
        },
        "milli_at": {
          "type": "date",
          "format": "epoch_millis"
        },
        "category": {
          "type": "keyword"
        },
        "score": {
          "type": "integer"
        },
        "state": {
          "type": "keyword"
        }
      }
    }
  }
}

迁移工作

1.设置别名
POST /_aliases
{
  "actions": [
    {
      "add": {
        "index": "yst_crawler",
        "alias": "yst_crawler_alias"
      }
    }
  ]
}
2 .查看状态
GET yst_crawler/_stats

PUT /yst_crawler_v2
GET /yst_crawler_v2/_mapping
3.验证分词
GET /yst_crawler_v2/_analyze
{
  "analyzer": "my_new_custom_analyzer",
  "text": "xxx 110 2323"
}
4.把数据同步到新的索引
4.1 同步方式迁移
POST /_reindex
{
  "source": {
    "index": "yst_crawler"
  },
  "dest": {
    "index": "yst_crawler_v2"
  }
}
4.2 异步方式迁移，设置了9个并发
POST /_reindex?slices=9&refresh&wait_for_completion=false
{
  "source": {
      "index": "yst_crawler",
      "size": 10000
  },
  "dest": {
      "index": "yst_crawler_v2"
  }
}

}

4.3 异步方式迁移，查看完成状态
GET /_tasks

GET /_tasks/eiPlKw2_T3iKReTflMHkEQ:39797979
5.修改别名，去除别名
POST /_aliases
{
  "actions": [
    {
      "remove": {
        "index": "yst_crawler",
        "alias": "yst_crawler_alias"
      }
    },
    {
      "add": {
        "index": "yst_crawler_v2",
        "alias": "yst_crawler_alias"
      }
    }
  ]
}
6.验证数据

主要看数据量total

GET yst_crawler/_stats
GET yst_crawler_v2/_stats
7.最后确认没问题后，删除老的索引
DELETE /yst_crawler

GET /_cat/indices?v

GET /yst_crawler_alias/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "match": {
            "title": "Pass State Park"
          }
        },
        {
          "range": {
            "milli_at": {
              "gte": "now-4d/d",
              "lte": "now/d"
            }
          }
        }
      ]
    }
  },
  "_source": ["id", "title", "milli_at", "s3_url", "article_time", "detail_url", "ref_id", "req_md5", "tags", "category", "content", "milli_at","article_id","desc"],
  "from": 0,
  "size": 20
}
8.改索引方式备份，改过去，然后再改过来
# yst_city_v2 分词

PUT /yst_city_v2
{
  "settings": {
    "index.max_ngram_diff": 30,
    "analysis": {
      "tokenizer": {
        "ngram_tokenizer": {
          "type": "ngram",
          "min_gram": 1,
          "max_gram": 25,
          "token_chars": ["letter", "digit", "punctuation", "symbol"]
        },
        "code_ngram_tokenizer": {
          "type": "ngram",
          "min_gram": 2,
          "max_gram": 4
        }
      },
      "analyzer": {
        "ngram_analyzer": {
          "type": "custom",
          "tokenizer": "ngram_tokenizer",
          "filter": ["lowercase"]
        },
        "comma_analyzer": {
          "type": "pattern",
          "pattern": ","
        },
        "code_ngram_analyzer": {
          "tokenizer": "code_ngram_tokenizer"
        }
      },
      "normalizer": {
        "lowercase_normalizer": {
          "type": "custom",
          "filter": ["lowercase"]
        }
      }
    }
  },
  "mappings": {
    "properties": {
      "id": {
        "type": "integer"
      },
      "state": {
        "type": "keyword"
      },
      "country": {
        "type": "keyword"
      },
      "city": {
        "type": "text",
        "analyzer": "ngram_analyzer",
        "fields": {
          "exact": {
            "type": "keyword",
            "normalizer": "lowercase_normalizer"
          }
        }
      },
      "code": {
        "type": "text",
        "analyzer": "comma_analyzer",
        "fields": {
          "ngram": {
            "type": "text",
            "analyzer": "code_ngram_analyzer"
          }
        }
      },
      "create_at": {
        "type": "integer"
      },
      "is_popular": {
        "type": "byte"
      },
      "sort": {
        "type": "short"
      },
      "location": {
        "type": "geo_point"
      }
    }
  }
}




GET yst_city/_stats
GET yst_city_v2/_stats

GET /yst_city/_mapping

GET /yst_city_v2/_analyze
{
  "analyzer": "ngram_analyzer",
  "text": "New 110 2323"
}


POST /_reindex?slices=9&refresh&wait_for_completion=false
{
  "source": {
      "index": "yst_city",
      "size": 10000
  },
  "dest": {
      "index": "yst_city_v2"
  }
}

GET /_tasks/eiPlKw2_T3iKReTflMHkEQ:40031239

DELETE yst_city 


PUT /yst_city
{
  "settings": {
    "index.max_ngram_diff": 30,
    "analysis": {
      "tokenizer": {
        "ngram_tokenizer": {
          "type": "ngram",
          "min_gram": 1,
          "max_gram": 25,
          "token_chars": ["letter", "digit", "punctuation", "symbol"]
        },
        "code_ngram_tokenizer": {
          "type": "ngram",
          "min_gram": 2,
          "max_gram": 4
        }
      },
      "analyzer": {
        "ngram_analyzer": {
          "type": "custom",
          "tokenizer": "ngram_tokenizer",
          "filter": ["lowercase"]
        },
        "comma_analyzer": {
          "type": "pattern",
          "pattern": ","
        },
        "code_ngram_analyzer": {
          "tokenizer": "code_ngram_tokenizer"
        }
      },
      "normalizer": {
        "lowercase_normalizer": {
          "type": "custom",
          "filter": ["lowercase"]
        }
      }
    }
  },
  "mappings": {
    "properties": {
      "id": {
        "type": "integer"
      },
      "state": {
        "type": "keyword"
      },
      "country": {
        "type": "keyword"
      },
      "city": {
        "type": "text",
        "analyzer": "ngram_analyzer",
        "fields": {
          "exact": {
            "type": "keyword",
            "normalizer": "lowercase_normalizer"
          }
        }
      },
      "code": {
        "type": "text",
        "analyzer": "comma_analyzer",
        "fields": {
          "ngram": {
            "type": "text",
            "analyzer": "code_ngram_analyzer"
          }
        }
      },
      "create_at": {
        "type": "integer"
      },
      "is_popular": {
        "type": "byte"
      },
      "sort": {
        "type": "short"
      },
      "location": {
        "type": "geo_point"
      }
    }
  }
}



POST /_reindex?slices=9&refresh&wait_for_completion=false
{
  "source": {
      "index": "yst_city_v2",
      "size": 10000
  },
  "dest": {
      "index": "yst_city"
  }
}


GET yst_city/_stats
GET yst_city_v2/_stats

DELETE yst_city_v2
9.如果迁移某个字段默认值的方式

异步迁移 新增了字段，把以前的数据is_repeat 全部填充为0文章来源地址https://www.toymoban.com/news/detail-659911.html

POST /_reindex?slices=9&refresh&wait_for_completion=false
{
 
    "source": {
        "index": "yst_crawler",
        "size": 10000
    },
    "dest": {
        "index": "yst_crawler_v2"
    },
    
  "script": {
    "lang": "painless",
    "source": "if (ctx._source.is_repeat == null) { ctx._source.is_repeat = 0; }"
  }
}
10. 更新某个字段
POST /yst_city/_update/17737
{
  "doc": {
    "location": {
      "lat": 40.7321967,
      "lon": -74.0097151
    }
  }
}

到了这里，关于es线上处理命令记录的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！

本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若转载，请注明出处： 如若内容造成侵权/违法违规/事实不符，请点击违法举报进行投诉反馈，一经查实，立即删除！

分享到：
领支付宝红包 赞助服务器费用

相关文章

觉得文章有用就打赏一下文章作者

支付宝扫一扫打赏

博客赞助

微信扫一扫打赏

请作者喝杯咖啡吧~博客赞助

支付宝扫一扫领取红包，优惠每天领

二维码1

领取红包

二维码2

领红包