hduser@benjamin-VirtualBox:~/data$ 
hduser@benjamin-VirtualBox:~/data$ 
hduser@benjamin-VirtualBox:~/data$ 
hduser@benjamin-VirtualBox:~/data$ cat smplReducer2.py 
#!/usr/bin/env python
  
import sys
  
# maps words to their counts
foundKey = ""
foundValue = ""
isFirst = 1
currentCount = 0
currentCounty2digit = "z"
isCountryMappingLine = False
 
# input comes from STDIN
for line in sys.stdin:
    # remove leading and trailing whitespace
    line = line.strip()
     
    try:
        # parse the input we got from mapper.py
        cid, county, state2digit, population = line.split('^')
         
        #the first line should be a mapping line, otherwise we need to set the currentCountryName to not known
        if  county != "z": #this is a new country which may or may not have people in it
            currentCounty2digit = state2digit
            isCountryMappingLine = True
        else:
            isCountryMappingLine = False # this is a person we want to count
         
        if not isCountryMappingLine: #we only want to count people but use the country line to get the right name
 
            currentKey = '%s' % (currentCounty2digit)
             
            if foundKey != currentKey: #new combo of keys to count
                if isFirst == 0:
                    print '%s\t%s' % (foundKey,currentCount)
                    currentCount = 0 #reset the count
                else:
                    isFirst = 0
             
                foundKey = currentKey #make the found key what we see so when we loop again can see if we increment or print out
             
            currentCount += int(population) # we increment anything not in the map list
    except:
        pass
 
try:
    print '%s\t%s' % (foundKey,currentCount)
except:
    pass
hduser@benjamin-VirtualBox:~/data$