Hive 11、Hive嵌入Python

Hive嵌入Python

Python的输入输出都是\t为分隔符，否则会出错，python脚本输入print出规定格式的数据

用法为先add file，使用语法为TRANSFORM (name, items)   USING 'python test.py'  AS (name string, item1 string,item2 string,item3 string)，这里后面几个字段对应python的类型

下面是一个将一列转成多列表小案例：

create table test (name string,items string) 

ROW FORMAT DELIMITED 

FIELDS TERMINATED BY '\t';

LOAD DATA local INPATH '/opt/data/tt.txt' OVERWRITE INTO TABLE test ;

tt.txt的内容：

tom	shu fa,wei qi,chang ge
jack	game,kan shu,shang wang
lusi	lv you,guang jie,gou wu

表2：

create table test2 (name string,item1 string,item2 string,item3 string) 

ROW FORMAT DELIMITED 

FIELDS TERMINATED BY '\t';

-- 将python脚本上传到Hive
Hive> add file /root/test.py

-- 将结果放到test2中
INSERT OVERWRITE TABLE test2  

SELECT  TRANSFORM (name, items)
USING 'python test.py'
AS (name string, item1 string,item2 string,item3 string)
FROM test;

#!/usr/bin/python  

import sys
for line in sys.stdin:
     line = line.strip()
     name,it = line.split('\t')
     count = it.count(',')+1
     for i in range(0,3-count):
          it = it+',NULL'
     result = it.split(',')[0:3]
     print '%s\t%s'%(name,'\t'.join(result))

结果：
-- 表1
hive> select * from test;
OK
tom    shu fa,wei qi,chang ge
jack    game,kan shu,shang wang
lusi    lv you,guang jie,gou wu
Time taken: 0.07 seconds, Fetched: 3 row(s)

　hive> desc test2;
　OK
　name string
　item1 string
　item2 string
　item3 string
　Time taken: 0.141 seconds, Fetched: 4 row(s)

-- 表2
hive> select * from test2;
OK
tom    shu fa    wei qi    chang ge
jack    game    kan shu    shang wang
lusi    lv you    guang jie    gou wu
Time taken: 1.368 seconds, Fetched: 3 row(s)