es 使用ik停词_elasticsearch ik分词插件的扩展字典和扩展停止词字典用法

cnblog的排版好看很多，所以在这里建一篇分享博客。

-----------------------------------------------------------------------------------------------

扩展字典中的词会被筛选出来，扩展停止词中的词会被过滤掉

1.没有加入扩展字典 停止词字典用法

1) ik分词器

[root@localhost custom]# curl -i -X GET -H 'Content-type:application/json' -d '{"analyzer":"ik","text":"自古刀扇过背刺"}' http://192.168.0.110:9200/_analyze?pretty

HTTP/1.1 200OK

Content-Type: application/json; charset=UTF-8Content-Length: 725

{"tokens": [ {"token" : "自古","start_offset" : 0,"end_offset" : 2,"type" : "CN_WORD","position" : 0}, {"token" : "刀","start_offset" : 2,"end_offset" : 3,"type" : "CN_WORD","position" : 1}, {"token" : "扇","start_offset" : 3,"end_offset" : 4,"type" : "CN_WORD","position" : 2}, {"token" : "过","start_offset" : 4,"end_offset" : 5,"type" : "CN_CHAR","position" : 3}, {"token" : "背","start_offset" : 5,"end_offset" : 6,"type" : "CN_WORD","position" : 4}, {"token" : "刺","start_offset" : 6,"end_offset" : 7,"type" : "CN_CHAR","position" : 5} ]

}

2) ik_smart分词器

[root@localhost custom]# curl -i -X GET -H 'Content-type:application/json' -d '{"analyzer":"ik_smart","text":"自古刀扇过背刺"}' http://192.168.0.110:9200/_analyze?pretty HTTP/1.1 200 OK

Content-Type: application/json; charset=UTF-8Content-Length: 725

{"tokens": [ {"token" : "自古","start_offset" : 0,"end_offset" : 2,"type" : "CN_WORD","position" : 0}, {"token" : "刀","start_offset" : 2,"end_offset" : 3,"type" : "CN_WORD","position" : 1}, {"token" : "扇","start_offset" : 3,"end_offset" : 4,"type" : "CN_WORD","position" : 2}, {"token" : "过","start_offset" : 4,"end_offset" : 5,"type" : "CN_CHAR","position" : 3}, {"token" : "背","start_offset" : 5,"end_offset" : 6,"type" : "CN_WORD","position" : 4}, {"token" : "刺","start_offset" : 6,"end_offset" : 7,"type" : "CN_CHAR","position" : 5} ]

}

3) ik_max_word分词器

[root@localhost custom]# curl -i -X GET -H 'Content-type:application/json' -d '{"analyzer":"ik_max_word","text":"自古刀扇过背刺"}' http://192.168.0.110:9200/_analyze?pretty

HTTP/1.1 200OK

Content-Type: application/json; charset=UTF-8Content-Length: 725

{"tokens": [ {"token" : "自古","start_offset" : 0,"end_offset" : 2,"type" : "CN_WORD","position" : 0}, {"token" : "刀","start_offset" : 2,"end_offset" : 3,"type" : "CN_WORD","position" : 1}, {"token" : "扇","start_offset" : 3,"end_offset" : 4,"type" : "CN_WORD","position" : 2}, {"token" : "过","start_offset" : 4,"end_offset" : 5,"type" : "CN_CHAR","position" : 3}, {"token" : "背","start_offset" : 5,"end_offset" : 6,"type" : "CN_WORD","position" : 4}, {"token" : "刺","start_offset" : 6,"end_offset" : 7,"type" : "CN_CHAR","position" : 5} ]

}

2.加入自定义字典

扩展字典：用于创建分词的字典

停止字典：用于过滤的字典，也就是说，该字典的单词或者字符串都会进行过滤

test.dic

刀扇

背刺

teststop.dic

自古

过

/analysis-ik/config/IKAnalyzer.cfg.xml

1) ik分词器

[root@localhost config]# curl -i -X GET -H 'Content-type:application/json' -d '{"analyzer":"ik","text":"自古刀扇过背刺"}' http://192.168.0.110:9200/_analyze?pretty

HTTP/1.1 200OK

Content-Type: application/json; charset=UTF-8Content-Length: 728

{"tokens": [ {"token" : "刀扇","start_offset" : 2,"end_offset" : 4,"type" : "CN_WORD","position" : 0}, {"token" : "刀","start_offset" : 2,"end_offset" : 3,"type" : "CN_WORD","position" : 1}, {"token" : "扇","start_offset" : 3,"end_offset" : 4,"type" : "CN_WORD","position" : 2}, {"token" : "背刺","start_offset" : 5,"end_offset" : 7,"type" : "CN_WORD","position" : 3}, {"token" : "背","start_offset" : 5,"end_offset" : 6,"type" : "CN_WORD","position" : 4}, {"token" : "刺","start_offset" : 6,"end_offset" : 7,"type" : "CN_CHAR","position" : 5} ]

}

2) ik_smart分词器

[root@localhost config]# curl -i -X GET -H 'Content-type:application/json' -d '{"analyzer":"ik_smart","text":"自古刀扇过背刺"}' http://192.168.0.110:9200/_analyze?pretty HTTP/1.1 200 OK

Content-Type: application/json; charset=UTF-8Content-Length: 260

{"tokens": [ {"token" : "刀扇","start_offset" : 2,"end_offset" : 4,"type" : "CN_WORD","position" : 0}, {"token" : "背刺","start_offset" : 5,"end_offset" : 7,"type" : "CN_WORD","position" : 1} ]

}

3) ik_max_word分词器

[root@localhost config]# curl -i -X GET -H 'Content-type:application/json' -d '{"analyzer":"ik_max_word","text":"自古刀扇过背刺"}' http://192.168.0.110:9200/_analyze?pretty

HTTP/1.1 200OK

Content-Type: application/json; charset=UTF-8Content-Length: 728

{"tokens": [ {"token" : "刀扇","start_offset" : 2,"end_offset" : 4,"type" : "CN_WORD","position" : 0}, {"token" : "刀","start_offset" : 2,"end_offset" : 3,"type" : "CN_WORD","position" : 1}, {"token" : "扇","start_offset" : 3,"end_offset" : 4,"type" : "CN_WORD","position" : 2}, {"token" : "背刺","start_offset" : 5,"end_offset" : 7,"type" : "CN_WORD","position" : 3}, {"token" : "背","start_offset" : 5,"end_offset" : 6,"type" : "CN_WORD","position" : 4}, {"token" : "刺","start_offset" : 6,"end_offset" : 7,"type" : "CN_CHAR","position" : 5} ]

}