ElasticSearch(四) ElasticSearch中文分词插件IK的简单测试详解程序员

# curl -XPOST  "http://192.168.9.155:9200/_analyze?analyzer=standard&pretty" -d 'PHP是世界上最好的语言'   //_analyze表示分析分词；analyzer=standard，表示分词方式standard; -d表示测试的一段文字

{ 
"tokens" : [ 
{ 
"token" : "php", 
"start_offset" : 0, 
"end_offset" : 3, 
"type" : "<ALPHANUM>", 
"position" : 0 
}, 
{ 
"token" : "是", 
"start_offset" : 3, 
"end_offset" : 4, 
"type" : "<IDEOGRAPHIC>", 
"position" : 1 
}, 
{ 
"token" : "世", 
"start_offset" : 4, 
"end_offset" : 5, 
"type" : "<IDEOGRAPHIC>", 
"position" : 2 
}, 
{ 
"token" : "界", 
"start_offset" : 5, 
"end_offset" : 6, 
"type" : "<IDEOGRAPHIC>", 
"position" : 3 
}, 
{ 
"token" : "上", 
"start_offset" : 6, 
"end_offset" : 7, 
"type" : "<IDEOGRAPHIC>", 
"position" : 4 
}, 
{ 
"token" : "最", 
"start_offset" : 7, 
"end_offset" : 8, 
"type" : "<IDEOGRAPHIC>", 
"position" : 5 
}, 
{ 
"token" : "好", 
"start_offset" : 8, 
"end_offset" : 9, 
"type" : "<IDEOGRAPHIC>", 
"position" : 6 
}, 
{ 
"token" : "的", 
"start_offset" : 9, 
"end_offset" : 10, 
"type" : "<IDEOGRAPHIC>", 
"position" : 7 
}, 
{ 
"token" : "语", 
"start_offset" : 10, 
"end_offset" : 11, 
"type" : "<IDEOGRAPHIC>", 
"position" : 8 
}, 
{ 
"token" : "言", 
"start_offset" : 11, 
"end_offset" : 12, 
"type" : "<IDEOGRAPHIC>", 
"position" : 9 
} 
] 
}

curl -XPOST  "http://192.168.9.155:9200/_analyze?analyzer=ik_smart&pretty" -d 'PHP是世界上最好的语言'  //ik_smart方式

{ 
"tokens" : [ 
{ 
"token" : "php", 
"start_offset" : 0, 
"end_offset" : 3, 
"type" : "ENGLISH", 
"position" : 0 
}, 
{ 
"token" : "世界上", 
"start_offset" : 4, 
"end_offset" : 7, 
"type" : "CN_WORD", 
"position" : 1 
}, 
{ 
"token" : "最好", 
"start_offset" : 7, 
"end_offset" : 9, 
"type" : "CN_WORD", 
"position" : 2 
}, 
{ 
"token" : "语言", 
"start_offset" : 10, 
"end_offset" : 12, 
"type" : "CN_WORD", 
"position" : 3 
} 
] 
}

curl -XPOST  "http://192.168.9.155:9200/_analyze?analyzer=ik_max_word&pretty" -d 'PHP是世界上最好的语言'    //ik_max_word方式

{ 
"tokens" : [ 
{ 
"token" : "php", 
"start_offset" : 0, 
"end_offset" : 3, 
"type" : "ENGLISH", 
"position" : 0 
}, 
{ 
"token" : "世界上", 
"start_offset" : 4, 
"end_offset" : 7, 
"type" : "CN_WORD", 
"position" : 1 
}, 
{ 
"token" : "世界", 
"start_offset" : 4, 
"end_offset" : 6, 
"type" : "CN_WORD", 
"position" : 2 
}, 
{ 
"token" : "上", 
"start_offset" : 6, 
"end_offset" : 7, 
"type" : "CN_CHAR", 
"position" : 3 
}, 
{ 
"token" : "最好", 
"start_offset" : 7, 
"end_offset" : 9, 
"type" : "CN_WORD", 
"position" : 4 
}, 
{ 
"token" : "语言", 
"start_offset" : 10, 
"end_offset" : 12, 
"type" : "CN_WORD", 
"position" : 5 
} 
] 
}