分词

(.py3) localhost:~ play$ curl -X GET "localhost:9200/_analyze" -H 'Content-Type: application/json' -d'{
>   "analyzer" : "ik_smart",
>   "text" : "410年,日耳曼的西哥特人在领袖阿拉里克率领下,进入意大利,围攻罗马城,在城内奴隶的配合下 打开城门,掠夺而去"
> }'

{"tokens":[{"token":"410年","start_offset":0,"end_offset":4,"type":"TYPE_CQUAN","position":0},{"token":"日耳曼","start_offset":5,"end_offset":8,"type":"CN_WORD","position":1},{"token":"的","start_offset":8,"end_offset":9,"type":"CN_CHAR","position":2},{"token":"西","start_offset":9,"end_offset":10,"type":"CN_CHAR","position":3},{"token":"哥","start_offset":10,"end_offset":11,"type":"CN_CHAR","position":4},{"token":"特","start_offset":11,"end_offset":12,"type":"CN_CHAR","position":5},{"token":"人在","start_offset":12,"end_offset":14,"type":"CN_WORD","position":6},{"token":"领袖","start_offset":14,"end_offset":16,"type":"CN_WORD","position":7},{"token":"阿拉","start_offset":16,"end_offset":18,"type":"CN_WORD","position":8},{"token":"里","start_offset":18,"end_offset":19,"type":"CN_CHAR","position":9},{"token":"克","start_offset":19,"end_offset":20,"type":"CN_CHAR","position":10},{"token":"率领","start_offset":20,"end_offset":22,"type":"CN_WORD","position":11},{"token":"下","start_offset":22,"end_offset":23,"type":"CN_CHAR","position":12},{"token":"进入","start_offset":24,"end_offset":26,"type":"CN_WORD","position":13},{"token":"意大利","start_offset":26,"end_offset":29,"type":"CN_WORD","position":14},{"token":"围攻","start_offset":30,"end_offset":32,"type":"CN_WORD","position":15},{"token":"罗马","start_offset":32,"end_offset":34,"type":"CN_WORD","position":16},{"token":"城","start_offset":34,"end_offset":35,"type":"CN_CHAR","position":17},{"token":"在","start_offset":36,"end_offset":37,"type":"CN_CHAR","position":18},{"token":"城内","start_offset":37,"end_offset":39,"type":"CN_WORD","position":19},{"token":"奴隶","start_offset":39,"end_offset":41,"type":"CN_WORD","position":20},{"token":"的","start_offset":41,"end_offset":42,"type":"CN_CHAR","position":21},{"token":"配合","start_offset":42,"end_offset":44,"type":"CN_WORD","position":22},{"token":"下","start_offset":44,"end_offset":45,"type":"CN_CHAR","position":23},{"token":"打开","start_offset":45,"end_offset":47,"type":"CN_WORD","position":24},{"token":"城门","start_offset":47,"end_offset":49,"type":"CN_WORD","position":25},{"token":"掠夺","start_offset":50,"end_offset":52,"type":"CN_WORD","position":26},{"token":"而去","start_offset":52,"end_offset":54,"type":"CN_WORD","position":27}]}
(.py3) localhost:~ play$ curl -X GET "localhost:9200/_analyze" -H 'Content-Type: application/json' -d'{
>   "analyzer" : "ik_max_word",
>   "text" : "410年,日耳曼的西哥特人在领袖阿拉里克率领下,进入意大利,围攻罗马城,在城内奴隶的配合下 打开城门,掠夺而去"
> }'

{"tokens":[{"token":"410","start_offset":0,"end_offset":3,"type":"ARABIC","position":0},{"token":"年","start_offset":3,"end_offset":4,"type":"COUNT","position":1},{"token":"日耳曼","start_offset":5,"end_offset":8,"type":"CN_WORD","position":2},{"token":"的","start_offset":8,"end_offset":9,"type":"CN_CHAR","position":3},{"token":"西","start_offset":9,"end_offset":10,"type":"CN_CHAR","position":4},{"token":"哥","start_offset":10,"end_offset":11,"type":"CN_CHAR","position":5},{"token":"特","start_offset":11,"end_offset":12,"type":"CN_CHAR","position":6},{"token":"人在","start_offset":12,"end_offset":14,"type":"CN_WORD","position":7},{"token":"领袖","start_offset":14,"end_offset":16,"type":"CN_WORD","position":8},{"token":"阿拉","start_offset":16,"end_offset":18,"type":"CN_WORD","position":9},{"token":"里","start_offset":18,"end_offset":19,"type":"CN_CHAR","position":10},{"token":"克","start_offset":19,"end_offset":20,"type":"CN_CHAR","position":11},{"token":"率领","start_offset":20,"end_offset":22,"type":"CN_WORD","position":12},{"token":"下","start_offset":22,"end_offset":23,"type":"CN_CHAR","position":13},{"token":"进入","start_offset":24,"end_offset":26,"type":"CN_WORD","position":14},{"token":"意大利","start_offset":26,"end_offset":29,"type":"CN_WORD","position":15},{"token":"围攻","start_offset":30,"end_offset":32,"type":"CN_WORD","position":16},{"token":"罗马","start_offset":32,"end_offset":34,"type":"CN_WORD","position":17},{"token":"城","start_offset":34,"end_offset":35,"type":"CN_CHAR","position":18},{"token":"在","start_offset":36,"end_offset":37,"type":"CN_CHAR","position":19},{"token":"城内","start_offset":37,"end_offset":39,"type":"CN_WORD","position":20},{"token":"奴隶","start_offset":39,"end_offset":41,"type":"CN_WORD","position":21},{"token":"的","start_offset":41,"end_offset":42,"type":"CN_CHAR","position":22},{"token":"配合","start_offset":42,"end_offset":44,"type":"CN_WORD","position":23},{"token":"下","start_offset":44,"end_offset":45,"type":"CN_CHAR","position":24},{"token":"打开","start_offset":45,"end_offset":47,"type":"CN_WORD","position":25},{"token":"开城","start_offset":46,"end_offset":48,"type":"CN_WORD","position":26},{"token":"城门","start_offset":47,"end_offset":49,"type":"CN_WORD","position":27},{"token":"掠夺","start_offset":50,"end_offset":52,"type":"CN_WORD","position":28},{"token":"而去","start_offset":52,"end_offset":54,"type":"CN_WORD","position":29}]}(.py3) localhost:~ play$