验证分词效果。
执行如下代码，对输入文本这是个测试进行分词。
GET ik_pinyin/_analyze
{
"text": "这是个测试",
"analyzer": "ik_pinyin_analyzer"
}预期的返回结果如下。
{
"tokens" : [
{
"token" : "zhe",
"start_offset" : 0,
"end_offset" : 2,
"type" : "CN_WORD",
"position" : 0
},
{
"token" : "这是",
"start_offset" : 0,
"end_offset" : 2,
"type" : "CN_WORD",
"position" : 0
},
{
"token" : "zs",
"start_offset" : 0,
"end_offset" : 2,
"type" : "CN_WORD",
"position" : 0
},
{
"token" : "shi",
"start_offset" : 0,
"end_offset" : 2,
"type" : "CN_WORD",
"position" : 1
},
{
"token" : "ge",
"start_offset" : 2,
"end_offset" : 3,
"type" : "CN_CHAR",
"position" : 2
},
{
"token" : "个",
"start_offset" : 2,
"end_offset" : 3,
"type" : "CN_CHAR",
"position" : 2
},
{
"token" : "g",
"start_offset" : 2,
"end_offset" : 3,
"type" : "CN_CHAR",
"position" : 2
},
{
"token" : "ce",
"start_offset" : 3,
"end_offset" : 5,
"type" : "CN_WORD",
"position" : 3
},
{
"token" : "shi",
"start_offset" : 3,
"end_offset" : 5,
"type" : "CN_WORD",
"position" : 4
},
{
"token" : "测试",
"start_offset" : 3,
"end_offset" : 5,
"type" : "CN_WORD",
"position" : 4
},
{
"token" : "cs",
"start_offset" : 3,
"end_offset" : 5,
"type" : "CN_WORD",
"position" : 4
}
]
}