ElasticSearch 安裝中文分詞器


    1、安裝中文分詞器IK

      下載地址:https://github.com/medcl/elasticsearch-analysis-ik

      在線下載安裝: elasticsearch-plugin.bat install https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v5.5.2/elasticsearch-analysis-ik-5.5.2.zip  

      先下載后安裝:elasticsearch-plugin.bat install file:///D:\work\ElasticSearch\plugin\elasticsearch-analysis-ik-5.5.2.zip

      

 

 

      

 

       

    2、重啟 elasticsearch

    3、創建空索引

      curl -XPUT http://127.0.0.1:9200/index_china

      

      

      在kibana的Dev Tools中用  PUT /index_american/

      

 

    4、創建映射

      curl -XPOST http://127.0.0.1:9200/index_china/fulltext/_mapping -d "{\"properties\": {\"content\": {\"type\": \"text\",\"analyzer\": \"ik_max_word\",\"search_analyzer\": \"ik_max_word\"}}}"

      

      或

      POST /index_american/fulltext/_mapping 

      {

        "properties":
        {
        "content": 
          {
          "type": "text",
          "analyzer": 
          "ik_max_word",
          "search_analyzer": "ik_max_word"
          }
        }
      }

      

    5、索引數據

      POST /index_china/fulltext

      {
        "content" : "中國是世界上人口最多的國家",
        "title" : "中國",
        "tags" : [ "中國", "人口" ]
      }

      

 

      批量索引數據

      

POST /_bulk
{ "create": { "_index": "index_china", "_type": "fulltext", "_id": 1 } }
{ "title": "周星馳最新電影" }
{ "create": { "_index": "index_china", "_type": "fulltext", "_id": 2 } }
{ "title": "周星馳最好看的新電影" }
{ "create": { "_index": "index_china", "_type": "fulltext", "_id": 3 } }
{ "title": "周星馳最新電影,最好,新電影" }
{ "create": { "_index": "index_china", "_type": "fulltext", "_id": 4 } }
{ "title": "最最最最好的新新新新電影" }
{ "create": { "_index": "index_china", "_type": "fulltext", "_id": 5 } }
{ "title": "I'm not happy about the foxes" }

 

 

    6、查詢

       

      GET /index_china/fulltext/_search
      {
      "query": {
        "match": {
            "content": "中國"
            }
          }
      }

      

      

    7、最大分詞和最小分詞

      ik_smart,

      ik_max_word

      

 

      

GET /_analyze
{
 "analyzer": "ik_smart",
 "text": "中華人民共和國"
}
GET /_analyze
{
 "analyzer": "ik_max_word",
 "text": "中華人民共和國"
}

 

#刪除索引
DELETE /ott_test

#創建索引

PUT /ott_test 
{
  "mappings": {
    "ott_type" : {
      "properties" : {
        "title" : {
          "type" :    "text",
          "index":true,
          "analyzer": "ik_max_word",
          "search_analyzer": "ik_max_word"
        },
        "date" : {
          "type" :   "date"
        },
        "keyword" : {
          "type" :   "keyword"
        },
        "source" : {
          "type" :   "keyword"
        },
        "link" : {
          "type" :   "keyword"
        }
      }
    }
  }
}



#索引數據
POST /ott_test/ott_type
{
  "title":"微博新規惹爭議:用戶原創內容版權歸屬於微博?",
  "link":"http://www.yidianzixun.com/article/0HHoxgVq",
  "date":"2017-09-17",
  "source":"虎嗅網",
  "keyword":"內容"
}

#分析
GET /ott_test/_analyze
{
  "field": "title",
  "text": "內容" 
}

#查詢

GET /ott_test/ott_type/_search
{
   "query": {
    "match": {
      "title": "內容"
    }
  }
}

#只查詢title和date兩個字段的數據

GET /ott_test/ott_type/_search
{
   "query": {"match_all": {}},
    "_source": ["title","date"]
}

 


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM