one_article_per_line.rb

gistfile1.rb

#!/usr/bin/env ruby

article = ''

STDIN.each do |line|
  begin
    line.chomp!
    if line == '---END.OF.DOCUMENT---'
      puts "0\t#{article}"
      article = ''
      warn "reporter:counter:article_per_line,num_articles,1"
    else
      article += line.
        gsub(%r{<URL>},' ').
        gsub(%r{<EMAILADDRESS>},' ').
        gsub(%r{<NEWSURL>},' ').
        gsub(%r{[<>]},' ') + ' '
    end
  rescue
    warn "reporter:counter:article_per_line,parse_errors,1"
  end
end

puts "0\t#{article}"
warn "reporter:counter:article_per_line,num_articles,1"