Elasticsearch-IK分詞器（二）IK分詞器的使用
命令行查看結果
ik_smart模式
| [itstar@hadoop102 elasticsearch]$ curl -XGET 'http://hadoop104:9200/_analyze?pretty&analyzer=ik_smart' -d '中華人民共和國'
curl -H "Content-Type:application/json" -XGET 'http://192.168.109.133:9200/_analyze?pretty' -d '{"analyzer":"ik_smart","text":"中華人民共和國"}'
{ "tokens" : [ { "token" : "中華人民共和國", "start_offset" : 0, "end_offset" : 7, "type" : "CN_WORD", "position" : 0 } ] } |
ik_max_word模式
| [itstar@hadoop102 elasticsearch]$ curl -XGET 'http://hadoop104:9200/_analyze?pretty&analyzer=ik_max_word' -d '中華人民共和國'
curl -H "Content-Type:application/json" -XGET 'http://192.168.109.133:9200/_analyze?pretty' -d '{"analyzer":"ik_max_word","text":"中華人民共和國"}'
{ "tokens" : [ { "token" : "中華人民共和國", "start_offset" : 0, "end_offset" : 7, "type" : "CN_WORD", "position" : 0 }, { "token" : "中華人民", "start_offset" : 0, "end_offset" : 4, "type" : "CN_WORD", "position" : 1 }, { "token" : "中華", "start_offset" : 0, "end_offset" : 2, "type" : "CN_WORD", "position" : 2 }, { "token" : "華人", "start_offset" : 1, "end_offset" : 3, "type" : "CN_WORD", "position" : 3 }, { "token" : "人民共和國", "start_offset" : 2, "end_offset" : 7, "type" : "CN_WORD", "position" : 4 }, { "token" : "人民", "start_offset" : 2, "end_offset" : 4, "type" : "CN_WORD", "position" : 5 }, { "token" : "共和國", "start_offset" : 4, "end_offset" : 7, "type" : "CN_WORD", "position" : 6 }, { "token" : "共和", "start_offset" : 4, "end_offset" : 6, "type" : "CN_WORD", "position" : 7 }, { "token" : "國", "start_offset" : 6, "end_offset" : 7, "type" : "CN_CHAR", "position" : 8 } ] } |