hduser@benjamin-VirtualBox:~/data$ 
hduser@benjamin-VirtualBox:~/data$ ls
DataDict.txt  FIPS_CountyName.txt  smplReducer1-Original.py  smplReducer2Original.py  smplReducer.py
DataSet.txt   smplMapper.py        smplReducer1.py           smplReducer2.py
hduser@benjamin-VirtualBox:~/data$ cat smplMapper.py 
#!/usr/bin/env python
 
import sys
import re

# input comes from STDIN (standard input)
for line in sys.stdin:
    try: #sometimes bad data can cause errors use this how you like to deal with lint and bad data
         
        cid = "z" #default sorted as first
        county = "z" #default sorted as first
        state2digit = "z" #default sorted as first
        population = "z" #default sorted as first
         
        # remove leading and trailing whitespace
        line = line.strip()
         
        #splits = line.split("|")

	# finds lines from DataSet.txt, outputs first 2 items as array
	if line.count(",")>5: 
		splits = line.split(",", 2)[0:2]
		# removes the country and the state lines from DataSet
		if re.match('..000',splits[0]): splits= "" 
	# finds lines from Fips_CountyName.txt, cleans them, outputs  3 items as array
	else:
		# replaces a comma followed by space (state) w/comma
		splits = line.replace(', ',',')
		# replaces all remaining spaces w/comma
		splits = splits.replace(" ",",",1) 
		splits = splits.split(",")
	#print splits
        if len(splits) == 2: 
            cid = splits[0]
            population = splits[1]
        else: #people data
            cid = splits[0]
            county = splits[1]
            state2digit = splits[2]          

        print '%s^%s^%s^%s' % (cid, county, state2digit, population)
    except: #errors are going to make your job fail which you may or may not want
        pass
hduser@benjamin-VirtualBox:~/data$