elasticsearch安裝中文分詞擴充套件elasticsearch-analysis-ik
阿新 • • 發佈:2019-01-03
github:
https://github.com/medcl/elasticsearch-analysis-ik
安裝方式
1、先檢視版本號:
http://localhost:9200/
2、安裝
./bin/elasticsearch-plugin install https://github.com/medcl/elasticsearch-analysis-ik/releases/download/v6.3.0/elasticsearch-analysis-ik-6.3.0.zip
3、重啟es
4、分詞測試
curl -X PUT 'localhost:9200/website' curl -XGET "http://localhost:9200/website/_analyze" -H 'Content-Type: application/json' -d' { "text":"中華人民共和國國歌","tokenizer": "ik_max_word" }'
返回內容
{
"tokens": [
{
"token": "中華人民共和國",
"start_offset": 0,
"end_offset": 7,
"type": "CN_WORD",
"position": 0
},
{
"token": "中華人民",
"start_offset": 0,
"end_offset": 4,
"type" : "CN_WORD",
"position": 1
},
{
"token": "中華",
"start_offset": 0,
"end_offset": 2,
"type": "CN_WORD",
"position": 2
},
{
"token": "華人",
"start_offset": 1,
"end_offset" : 3,
"type": "CN_WORD",
"position": 3
},
{
"token": "人民共和國",
"start_offset": 2,
"end_offset": 7,
"type": "CN_WORD",
"position": 4
},
{
"token": "人民",
"start_offset": 2,
"end_offset": 4,
"type": "CN_WORD",
"position": 5
},
{
"token": "共和國",
"start_offset": 4,
"end_offset": 7,
"type": "CN_WORD",
"position": 6
},
{
"token": "共和",
"start_offset": 4,
"end_offset": 6,
"type": "CN_WORD",
"position": 7
},
{
"token": "國",
"start_offset": 6,
"end_offset": 7,
"type": "CN_CHAR",
"position": 8
},
{
"token": "國歌",
"start_offset": 7,
"end_offset": 9,
"type": "CN_WORD",
"position": 9
}
]
}