E.g。
根据以下表格和数据,找到包含单词“on”的行(不区分大小写)
create table t (i int,dt date,s1 string,s2 string,s3 string)
;
insert into t
select inline
(
array
(
struct(1,date '2017-03-15','Now we take our time','so nonchalant','And spend our nights so bon vivant')
,struct(2,date '2017-03-16','Quick as a wink','She changed her mind','She stood on the tracks')
,struct(3,date '2017-03-17','But I’m talking a Greyhound','On the Hudson River Line','I’m in a New York state of mind')
)
)
;
select * from t
;
+-----+------------+-----------------------------+--------------------------+------------------------------------+
| t.i | t.dt | t.s1 | t.s2 | t.s3 |
+-----+------------+-----------------------------+--------------------------+------------------------------------+
| 1 | 2017-03-15 | Now we take our time | so nonchalant | And spend our nights so bon vivant |
| 2 | 2017-03-16 | Quick as a wink | She changed her mind | She stood on the tracks |
| 3 | 2017-03-17 | But I’m talking a Greyhound | On the Hudson River Line | I’m in a New York state of mind |
+-----+------------+-----------------------------+--------------------------+------------------------------------+
答案 0 :(得分:1)
此解决方案仅与包含“原始”类型的表相关 (没有结构,数组,地图等)。
该解决方案的问题在于所有列在没有分隔符的情况下连接(不,concat_ws(*)
产生异常),因此边界中的单词变为单个单词,例如 -
Greyhound
和On
成为GreyhoundOn
select i
,regexp_replace(concat(*),'(?i)on','==>$0<==') as rec
from t
where concat(*) rlike '(?i)on'
;
+---+-----------------------------------------------------------------------------------------------------------+
| | rec |
+---+-----------------------------------------------------------------------------------------------------------+
| 1 | 12017-03-15Now we take our timeso n==>on<==chalantAnd spend our nights so b==>on<== vivant |
| 2 | 22017-03-16Quick as a winkShe changed her mindShe stood ==>on<== the tracks |
| 3 | 32017-03-17But I’m talking a Greyhound==>On<== the Huds==>on<== River LineI’m in a New York state of mind |
+---+-----------------------------------------------------------------------------------------------------------+
此解决方案仅与包含“原始”类型的表相关 (没有结构,数组,地图等)。
我把信封推到了这里但是成功地生成了一个包含所有列的分隔字符串 现在可以查找整个单词。
(?ix)
http://www.regular-expressions.info/modifiers.html
select i
,regexp_replace(concat(*),'(?ix)\\b on \\b','==>$0<==') as delim_rec
from (select i
,printf(concat('%s',repeat('|||%s',field(unhex(1),*,unhex(1))-2)),*) as delim_rec
from t
) t
where delim_rec rlike '(?ix)\\b on \\b'
;
+---+------------------------------------------------------------------------------------------------------------------+
| i | delim_rec |
+---+------------------------------------------------------------------------------------------------------------------+
| 2 | 22|||2017-03-16|||Quick as a wink|||She changed her mind|||She stood ==>on<== the tracks |
| 3 | 33|||2017-03-17|||But I’m talking a Greyhound|||==>On<== the Hudson River Line|||I’m in a New York state of mind |
+---+------------------------------------------------------------------------------------------------------------------+
create external table t_ext (rec string)
row format delimited
fields terminated by '0'
location '/user/hive/warehouse/t'
;
select cast(split(rec,'\\x01')[0] as int) as i
,regexp_replace(regexp_replace(rec,'(?ix)\\b on \\b','==>$0<=='),'\\x01','|||') as rec
from t_ext
where rec rlike '(?ix)\\b on \\b'
;
+---+-----------------------------------------------------------------------------------------------------------------+
| i | rec |
+---+-----------------------------------------------------------------------------------------------------------------+
| 2 | 2|||2017-03-16|||Quick as a wink|||She changed her mind|||She stood ==>on<== the tracks |
| 3 | 3|||2017-03-17|||But I’m talking a Greyhound|||==>On<== the Hudson River Line|||I’m in a New York state of mind |
+---+-----------------------------------------------------------------------------------------------------------------+