wordcount_ruby.yaml

%YAML 1.1
---
VERSION:         1.0.0.1

DEFINE:
  - INPUT:
      NAME:      book
      FILE:
        # change seghostname and file_path to reflect your
        # runtime file location
        - localhost.localdomain:/home/gpadmin/gpmrdata/whitepaper.txt

  - MAP:
      NAME:      wordsplit_ruby
      FUNCTION:  |
        h = {}
        value.split.each { |w|
          if h.has_key?(w)
            h[w] = h[w] + 1
          else
            h[w] = 1
         end
        }
        h.each_pair {|k,v| yield [k,v]}
        return
      LANGUAGE:   ruby
      OPTIMIZE:   STRICT IMMUTABLE
      PARAMETERS: value text
      RETURNS:
        - key text
        - value integer

EXECUTE:
  - RUN:
      SOURCE:    book
      MAP:       wordsplit_ruby
      REDUCE:    SUM