1、只获取文本中的字母,汉字和数字,剔除标点和特殊符号
- select regexp_replace('assseewfew@@@###$%%.....~~~京津冀123','[[^0-9a-zA-Z\\u4e00-\\u9fa5]]','')
- assseewfew京津冀123
- select locate('123','124123')
- 4
- select sort_array(collect_set(concat_ws(':',cast(sn as string),sp))) from
- (select locate(sp,'妈妈做的土豆炖排骨') as sn, sp from item_ci
- where locate(sp,'妈妈做的土豆炖排骨')>0)a
- ["5:土豆","8:排骨"]
- select levenshtein('秘制红烧肉盖饭十炒时蔬+赠饮','红烧肉盖饭时蔬')
- 7
- #需要解析的json
- select
- get_json_object(ss.list, '$.sid') as sid,
- get_json_object(ss.list, '$.price') as price,
- get_json_object(ss.list, '$.sn') as sn,
- get_json_object(ss.list, '$.number') as number,
- get_json_object(ss.list, '$.outr') as outr,
- get_json_object(ss.list, '$.deli') as deli,
- get_json_object(ss.list, '$.outs') as outs,
- get_json_object(ss.list, '$.act') as act
- from
- (
- select
- split(
- regexp_replace(
- regexp_extract(
- '[{"sid":"3458764527033385083","sn":1,"number":200,"price":33,"outr":0,"outs":0,"deli":0,"act":["3458764719724101804"]},{"sid":"3458764702871191593","sn":1,"number":2000,"price":39,"outr":0,"outs":0,"deli":0,"act":["3458764730620903593"]},{"sid":"3458764712379678782","sn":1,"number":900,"price":42,"outr":0,"outs":0,"deli":0,"act":["3458764738128707753"]}]',
- '^\\[(.+)\\][table=98%]
- [tr] [td=87]sid[/td] [td=87]price[/td] [td=87]sn[/td] [td=87]number[/td] [td=87]outr[/td] [td=87]deli[/td] [td=87]outs[/td] [td=87]act[/td] [/tr]
- [tr] [td]3458764527033385083[/td] [td]33[/td] [td]1[/td] [td]200[/td] [td]0[/td] [td]0[/td] [td]0[/td] [td]["3458764719724101804"][/td] [/tr]
- [tr] [td]3458764702871191593[/td] [td]39[/td] [td]1[/td] [td]2000[/td] [td]0[/td] [td]0[/td] [td]0[/td] [td]["3458764730620903593"][/td] [/tr]
- [tr] [td]3458764712379678782[/td] [td]42[/td] [td]1[/td] [td]900[/td] [td]0[/td] [td]0[/td] [td]0[/td] [td]["3458764738128707753"][/td] [/tr]
- [/table]
- ,
- 1
- ),
- '\\}\\,\\{',
- '\\}\\|\\|\\{'
- ),
- '\\|\\|'
- ) as str
- ) pp lateral view explode(pp.str) ss as list
| sid | price | sn | number | outr | deli | outs | act |
| 3458764527033385083 | 33 | 1 | 200 | 0 | 0 | 0 | ["3458764719724101804"] |
| 3458764702871191593 | 39 | 1 | 2000 | 0 | 0 | 0 | ["3458764730620903593"] |
| 3458764712379678782 | 42 | 1 | 900 | 0 | 0 | 0 | ["3458764738128707753"] |


雷达卡




京公网安备 11010802022788号







