import sys 
 for line in sys.stdin:
 word_list = line.strip().split(' ') 
 for word in word_list: print '	'.join([word.strip(), str(1)])

 import sys
 
 cur_word = None
 sum = 0 
 for line in sys.stdin:
 ss = line.strip().split('	') 
 if len(ss) < 2: continue
 
 word = ss[0].strip()
 count = ss[1].strip() 
 if cur_word == None:
 cur_word = word 
 if cur_word != word: print '	'.join([cur_word, str(sum)])
 cur_word = word
 sum = 0
 
 sum += int(count) 
 print '	'.join([cur_word, str(sum)])
 sum = 0

hello 
 ni hao ni haoni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ao ni haoni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ni haoao ni haoni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao ni hao
 Dad would get out his mandolin and play for the family
 Dad loved to play the mandolin for his family he knew we enjoyed singing
 I had to mature into a man and have children of my own before I realized how much he had sacrificed
 I had to,mature into a man and,have children of my own before.I realized how much he had sacrificed

cat src.txt | python map.py | sort -k 1 | python reduce.py

a 2
 and 2
 and,have 1
 ao 1
 before 1
 before.I 1
 children 2
 Dad 2
 enjoyed 1
 family 2
 for 2
 get 1
 had 4
 hao 33
 haoao 1
 haoni 3
 have 1
 he 3
 hello 1
 his 2
 how 2
 I 3
 into 2
 knew 1
 loved 1
 man 2
 mandolin 2
 mature 1
 much 2
 my 2
 ni 34
 of 2
 out 1
 own 2
 play 2
 realized 2
 sacrificed 2
 singing 1
 the 2
 to 2
 to,mature 1
 we 1
 would 1

HADOOP_CMD="/home/hadoop/hadoop/bin/hadoop"
 STREAM_JAR_PATH="/home/hadoop/hadoop/contrib/streaming/hadoop-streaming-1.2.1.jar"
 
 INPUT_FILE_PATH="/home/input/src.txt"
 OUTPUT_PATH="/home/output"
 
 $HADOOP_CMD fs -rmr $OUTPUT_PATH 
 
 $HADOOP_CMD jar $STREAM_JAR_PATH -input $INPUT_FILE_PATH -output $OUTPUT_PATH 
 -mapper "python map.py" -reducer "python reduce.py" -file ./map.py -file ./reduce.py

　HADOOP_CMD： hadoop的bin的路徑
 STREAM_JAR_PATH：streaming jar包的路徑
 INPUT_FILE_PATH：hadoop集群上的資源輸入路徑
 OUTPUT_PATH：hadoop集群上的結果

cat src.txt | python map.py | sort -k 1 | python reduce.py | wc -l
命令行中

Kind % Complete Num Tasks Pending Running Complete Killed Failed/Killed Task Attempts
map 100.00% 2 0 0 2 0 0 / 0
reduce 100.00% 1 0 0 1 0 0 / 0

Counter 　　Map Reduce Total
Reduce output records 0 　　0 　　 43