mapper

#-*- coding:utf-8 -*-
#!/usr/bin/env python
import sys
#读取输入的文件
for line in sys.stdin:
#去除开头与结尾的空格
    line = line.strip()
#把每行单词切开，输出<word> 1
    words = line.split()
    for word in words:
        print '%s\t%s' % (word, 1)

#-*- coding:utf-8 -*-
#!/usr/bin/env python
import sys
word2count = {}
#文件会读取mapper.py 的结果作为reducer.py 的输入
for line in sys.stdin:
    #去除头尾空格
    line = line.strip()
    #按照Tab键进行切分
    word, count = line.split('\t', 1)
    try:
        count = int(count)
        word2count[word] = word2count.get(word, 0) + count
    except ValueError:  #count如果不是数字的话，直接忽略掉
        pass
#读取数据并筛选含有“Hadoop”的单词，把最终的结果输出到STDOUT。
for word, count in word2count.items():
    if word == 'Hadoop':
        print '%s\t%s'% (word, count)