python transform hive_Hive 中写Transform

#!/usr/bin/python

#coding:utf8

import sys

for line in sys.stdin:

line = line.strip('\n')

arr = line.split('\t')

arr[1] = arr[1].replace("sutao","biansutao").replace("bian","biansutao")

print '\t'.join([arr[0],arr[1]])

'''

add file /home/hadoop/demo.py

select transform(t.id,t.name) using '/usr/bin/python demo.py' as (a int,b string) from test t;

'''

'''

ADD FILE mapper.py;

ADD FILE reducer.py;

FROM (

FROM tweets_parsed

MAP tweets_parsed.time, tweets_parsed.id, tweets_parsed.tweet

USING 'python mapper.py'

AS word, count

CLUSTER BY word) map_output

INSERT OVERWRITE TABLE word_count

REDUCE map_output.word, map_output.count

USING 'python reducer.py'

AS word, count;

'''

分享到：

2012-03-09 18:05

浏览 5077

评论