Hive 多分隔符的使用 (转载)

方法一)通过org.apache.hadoop.hive.contrib.serde2.RegexSerDe格式的serde。

1) 建表语句

#指定以^|~作为分隔符

CREATE TABlE tableex3(id STRING, name STRING)

ROW FORMAT SERDE'org.apache.hadoop.hive.contrib.serde2.RegexSerDe'

WITH SERDEPROPERTIES (

"input.regex" = "^(.)\^\|~(.)$"

)

STORED AS TEXTFILE;

2) 准备数据

1^|~wee

2^|~do

we^|~xml

%^|~we

3) 转载数据

load data local inpath '/var/lib/hadoop-hdfs/tee.txt'into table tableex3;

4) 验证:

select * from tableex3;

+--------------+----------------+--+

| tableex3.id | tableex3.name |

+--------------+----------------+--+

| 1 | wee |

| 2 | do |

| we | xml |

| % | we |

| NULL | NULL |

+--------------+----------------+--+

方法二)通过org.apache.hadoop.hive.contrib.serde2.MultiDelimitSerDe格式的serde。

#指定以^|~作为分隔符

CREATE TABLE multi_delim (col1 STRING, col2 STRING,Col3STRING) ROW FORMAT SERDE'org.apache.hadoop.hive.contrib.serde2.MultiDelimitSerDe' WITH SERDEPROPERTIES("field.delim"="^|~");

cat /var/lib/hadoop-hdfs/tee3.txt

1^|~wee^|~hi

2^|~do^|~where

we^|~xml^|~rice

%^|~we^|~^|

load data local inpath '/var/lib/hadoop-hdfs/tee.txt'into table tableex3;

select * from multi_delim;

+-------------------+-------------------+-------------------+--+

| multi_delim.col1 | multi_delim.col2 | multi_delim.col3 |

+-------------------+-------------------+-------------------+--+

| 1 | wee | hi |

| 2 | do | where |

| we | xml | rice |

| % | we | ^| |

| | NULL | NULL |