software/hadoop-demo/gutenberg/mapper.py

   1 #!/usr/bin/env python
   2 # http://www.michael-noll.com/tutorials/writing-an-hadoop-mapreduce-program-in-python/
   3
   4 import sys
   5
   6 # input comes from STDIN (standard input)
   7 for line in sys.stdin:
   8     # remove leading and trailing whitespace
   9     line = line.strip()
  10     # split the line into words
  11     words = line.split()
  12     # increase counters
  13     for word in words:
  14         # write the results to STDOUT (standard output);
  15         # what we output here will be the input for the
  16         # Reduce step, i.e. the input for reducer.py
  17         #
  18         # tab-delimited; the trivial word count is 1
  19         print '%s\t%s' % (word, 1)