mapper.py 624 Bytes
Newer Older
Marco Mariani's avatar
Marco Mariani committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19
#!/usr/bin/env python
# http://www.michael-noll.com/tutorials/writing-an-hadoop-mapreduce-program-in-python/

import sys

# input comes from STDIN (standard input)
for line in sys.stdin:
    # remove leading and trailing whitespace
    line = line.strip()
    # split the line into words
    words = line.split()
    # increase counters
    for word in words:
        # write the results to STDOUT (standard output);
        # what we output here will be the input for the
        # Reduce step, i.e. the input for reducer.py
        #
        # tab-delimited; the trivial word count is 1
        print '%s\t%s' % (word, 1)