正则表达式

create external table mytable (c1 string,c2 string,c3 string,c4 string,c5 string)
row format serde 'org.apache.hadoop.hive.contrib.serde2.RegexSerDe'
with serdeproperties  
(
    'input.regex' = '(".*?"|[^|]*)\\|(".*?"|[^|]*)\\|(".*?"|[^|]*)\\|(".*?"|[^|]*)\\|(.*)'
)
;

select * from mytable
;

+------+-----------+------+-------+-----------------+
|  c1  |    c2     |  c3  |  c4   |       c5        |
+------+-----------+------+-------+-----------------+
| "hi" | "welcome" | "to" | India | <xml>data</xml> |
+------+-----------+------+-------+-----------------+