HIVE数据清洗

佚名 6年前 (2019-05-12) 随笔 1079人围观抢沙发百度已收录

INSERT OVERWRITE TABLE mktmall.tmall_201412_uid_pid select regexp_extract(uid,
'^[0-9]*$', 0),regexp_extract(pid, '^[0-9]*$', 0) from mktmall.tmall_201412 where
regexp_extract(uid, '^[0-9]*$', 0) is not null and regexp_extract(uid, '^[0-9]*$',
0) != 'NULL' and regexp_extract(uid, '^[0-9]*$', 0) !='' and regexp_extract(uid,
'^[0-9]*$', 0) != ' ' and regexp_extract(uid, '^[0-9]*$', 0) != 'null'
and regexp_extract(pid, '^[0-9]*$', 0) is not null and regexp_extract(pid,
'^[0-9]*$', 0) != 'NULL' and regexp_extract(pid, '^[0-9]*$', 0) !='' and
regexp_extract(pid, '^[0-9]*$', 0) != ' ' and regexp_extract(pid, '^[0-9]*$', 0) !=
'null' ;