#!/usr/bin/env ruby

#   This filter changes all words to Title Caps, and attempts to be clever
#   about *un*capitalizing small words like a/an/the in the input.
#
#   The list of "small words" which are not capped comes from
#   the New York Times Manual of Style, plus 'vs' and 'v'. 
#
#   Original Perl version by:
#     John Gruber
#     http://daringfireball.net/
#     10 May 2008
#
#   Adapted to Ruby by:
#     Marshall Elfstrand
#     http://vengefulcow.com/
#     21 May 2008
#
#   License: http://www.opensource.org/licenses/mit-license.php
#

$KCODE = "UTF-8"

small_words = %w( a an and as at but by en for if in of on or the to v[.]? via vs[.]? )
small_re = small_words.join('|')

STDIN.each_line do |input_line|

  line = ""
  input_line.split(/( [:.;?!][ ] | (?:[ ]|^)["“] )/x).each do |s|
    
    s.gsub!(/ \b( [[:alpha:]] [[:lower:].'’]* )\b /x) do |w|
      # Skip words with inline dots, e.g. "del.icio.us" or "example.com"
      (w =~ / [[:alpha:]] [.] [[:alpha:]] /x) ? w : w.capitalize
    end #gsub!
    
    # Lowercase our list of small words:
    s.gsub!(/\b(#{small_re})\b/io) { |w| w.downcase }
    
    # If the first word in the title is a small word, then capitalize it:
    s.gsub!(/\A([[:punct:]]*)(#{small_re})\b/io) { |w| $1 + $2.capitalize }
    
    # If the last word in the title is a small word, then capitalize it:
    s.gsub!(/\b(#{small_re})([[:punct:]]*)\Z/io) { |w| $1.capitalize + $2 }
    
    # Append current substring to output
    line += s
    
  end #each
  
  # Special Cases:
  line.gsub!(/ V(s?)\. /, ' v\1. ')               # "v." and "vs."
  line.gsub!(/(['’])S\b/, '\1s')                  # 'S (otherwise you get "the SEC'S decision")
  line.gsub!(/\b(AT&T|Q&A)\b/i) { |w| w.upcase }  # "AT&T" and "Q&A", which get tripped up by
                                                  # self-contained small words "at" and "a"

  puts line

end #each_line