passwd_HDFS.txt

--->cp /etc/passwd /home/cloudera/passwd

reducer.py
#!/usr/bin/python
import sys


password= None
oldKey= None


for line in sys.stdin:
     data_mapped = line.strip().split(":")
     if len(data_mapped) != 2:
          continue
     thisKey, thisPass = data_mapped
     if oldKey and oldKey != thisKey:
          print(oldKey,":", password)
          oldKey = thisKey;
          password = thisPass;
     oldKey = thisKey
if oldKey != None:
     print(oldKey,":", password)

mapper.py
#!/usr/bin/python
import sys
for line in sys.stdin:
     data = line.strip().split(":")
     if len(data) == 7:
          username, password, uid, gid, fullname,hdirect, loginshell = data
          print("{0}:{1}".format(username, password))

> hadoop jar /usr/lib/hadoop-mapreduce/hadoop-streaming.jar \
-input /user/cloudera/input \
-output /user/cloudera/output \
-mapper /home/cloudera/mapper.py \
-reducer /home/cloudera/reducer.py

>hdfs dfsadmin -safemode leave