安装pinyin分词
地址:https://github.com/medcl/elasticsearch-analysis-pinyin
PUT py_test
{
"index" : {
"analysis" : {
"analyzer" : {
"pinyin_analyzer" : {
"tokenizer" : "my_pinyin",
"filter" : "word_delimiter"
}
},
"tokenizer" : {
"my_pinyin" : {
"type" : "pinyin",
"first_letter" : "none",
"padding_char" : " "
}
}
}
}
}
GET py_test/_analyze
{
"text":"刘德华",
"analyzer":"pinyin_analyzer"
}
得到
{
"tokens": [
{
"token": "liu",
"start_offset": 0,
"end_offset": 1,
"type": "word",
"position": 0
},
{
"token": "ldh",
"start_offset": 0,
"end_offset": 3,
"type": "word",
"position": 0
},
{
"token": "de",
"start_offset": 1,
"end_offset": 2,
"type": "word",
"position": 1
},
{
"token": "hua",
"start_offset": 2,
"end_offset": 3,
"type": "word",
"position": 2
}
]
}