elasticsearch 索引创建 基本查询语句 分词设计建议

elasticsearch 索引创建

put data_index
{
    "mappings":{
    "data_index":{
        "properties": {
            "docId": {
              "type": "text"
            },
            "taskId": {
              "type": "text",
              "fielddata" : true
            },
            "title": {
              "type": "text",
              "index":true,
              "analyzer":"ik_max_word",
              "search_analyzer": "ik_smart"
            },
            "summary": {
              "type": "text",
              "index":true,
              "analyzer":"ik_max_word",
              "search_analyzer": "ik_smart"
            },
            "releaseTime": {
              "type": "date",
              "format": "yyyy-MM-dd HH:mm:ss"
            },
            "siteName": {
              "type": "text"
            },
            "siteUrl": {
              "type": "text"
            },
            "siteDetailUrl": {
              "type": "text"
            },
            "content": {
              "type": "text",
              "analyzer":"ik_smart"
            },
            "contentSentenceSplit": {
              "type": "text",
              "analyzer":"ik_smart"
            },
            "md5Code": {
              "type": "keyword"
            },
            "pageId": {
              "type": "text"
            },
            "pointsFavorite": {
              "type": "long"
            },
            "pointsReading": {
              "type": "long"
            },
            "pointsPraise": {
              "type": "long"
            },
            "deleteFlag": {
              "type": "text"
            },
            "userId": {
              "type": "text",
              "fielddata":true
            },
            "monitorSolutionId": {
              "type": "keyword"
            },
            "accountId": {
              "type": "keyword"
            },
            "orgCode": {
              "type": "text"
            },
            "iframeStatus": {
              "type": "text"
            },
            "updateTime": {
              "type": "date",
              "format": "yyyy-MM-dd HH:mm:ss"
            },
            "createTime": {
              "type": "date",
              "format": "yyyy-MM-dd HH:mm:ss"
            }
      }
    }
}
}

说明：

data_index:索引名
data_type:类型

elasticsearch 常用查询

1.查询分词结果

GET /_analyze
{
  "text":"发明专利",
  "analyzer": "ik_max_word"
}

2.词项查询
GET data_index/data_type/_search
{ 
  "_source": {
    "includes": ["praiseType","content"]
  }, 
  "query": {
     "term": {
        "mediaType": {
            "value": "3"
          }
       }
  },
  "from": 0,
  "size": 20
}


3.复合查询

GET data_index/data_type/_search
{ 
  "_source": {
    "includes": ["praiseType","content"]
  }, 
  "query": {
    "bool": {
      "must": [
        {
          "term": {
            "mediaType": {
              "value": "3"
            }
          }
        }
      ],
      "must_not":[
        {
          "term": {
            "deleteFlag": {
              "value": "1"
            }
          }
        }
      ]
    }
  },
  "from": 0,
  "size": 20
}

4.聚合

GET data_index/data_type/_search
{ 
  "query": {
     "term": {
        "crawlerType": {
            "value": "1"
          }
       }
  },
  "aggs": {
     "mediaType": {
        "terms": {
            "field": "mediaType"
          }
       }
  },
  "size": 0
}


GET data_index/data_type/_search
{ 
  "aggs": {
     "mediaType": {
        "terms": {
            "field": "mediaType"
          }
       }
  },
  "size": 0
}

查询更新
POST data_index/_update_by_query
{ 
  "script":{
    "source":"ctx._source.praiseType = '2'",
    "lang":"painless"
  },
  "query": {
    "bool": {
      "must_not":[
        {
          "exists": {
            "field":"praiseType"
          }
        }
      ]
    }
  }
}

GET data_index/data_type/_search
{ 
  "_source": {
    "includes": ["praiseType"]
  },
  "script":{
    "inline":"ctx.source.praiseType" = params.praiseType,
    "lang":"painless",
    "params":{"praiseType":"2"}
  },
  "query": {
    "bool": {
      "must":[
        {
          "term": {
            "md5Code":"b42ca83c7eb3e2c4b5c95db90edffc51"
          }
        }
      ]
    }
  },
  "from": 0,
  "size": 20
}


POST twitter/_update_by_query
{
  "script": {
    "source": "ctx._source.likes++",
    "lang": "painless"
  },
  "query": {
    "term": {
      "user": "kimchy"
    }
  }
}

索引别名设置：
POST /_aliases
{
    "actions": [
        { "remove": { "index": "old_index", "alias": "data_index" }},
        { "add":    { "index": "new_index", "alias": "data_index" }}
    ]
}

ik 分词设计 建议

1. 建索引时使用： ik_max_word 做细粒度的拆分

• 查询时用： ik_smart 做粗粒度的方式 拆分