elasticsearch ik分词插件的扩展字典和扩展停止词字典用法

最新推荐文章于 2024-07-28 17:12:40 发布

knife1220

最新推荐文章于 2024-07-28 17:12:40 发布

阅读量3.8k

点赞数 1

分类专栏： elasticsearch

本文链接：https://blog.csdn.net/caideb/article/details/81632154

版权

elasticsearch 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

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

[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/1.1 200 OK
Content-Type: application/json; charset=UTF-8
Content-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
  } ]
}

ik_smart

[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-8
Content-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
  } ]
}

ik_max_word

[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/1.1 200 OK
Content-Type: application/json; charset=UTF-8
Content-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

test.dic

刀扇
背刺

teststop.dic

自古
过

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

[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/1.1 200 OK
Content-Type: application/json; charset=UTF-8
Content-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
  } ]
}

ik_smart

[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-8
Content-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
  } ]
}

ik_max_word

[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/1.1 200 OK
Content-Type: application/json; charset=UTF-8
Content-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
  } ]
}