fixup.rb

   1 #!/usr/bin/ruby
   2 # coding: utf-8
   3 raise ArgumentError, 'Source/destination files not specified' if ARGV.size != 2
   4 srcfile = ARGV[0]
   5 dstfile = ARGV[1]
   6
   7 data=File.open(srcfile).readlines.map {|l| l.chomp!}
   8
   9 data.map {|lin| lin.gsub!(/<span id="anchor-?\d*"><\/span>/, '')}
  10
  11 # There are several titles that are spread in more than one line. Make
  12 # them into translatable sentences.
  13 [ ['Made', '', 'with', '', 'Creative', '', 'Commons'],
  14   ['The New','', 'World of', '', 'Digital', '', 'Commons'],
  15   ['How', '', 'to Be', '', 'Made with', '', 'Creative', '', 'Commons'],
  16   ['Use CC to get attribution and name', 'recognition'],
  17   ['Use CC to enable hands-on engagement with', 'your work'],
  18   ['Providing a custom service to consumers of', 'your work * \[MARKET-BASED\]*'],
  19   ['Charging for the physical copy *', '\[MARKET-BASED\]*'],
  20   ['Charging for the in-person version *','\[MARKET-BASED\]*'],
  21   ['Charging advertisers or sponsors *', '\[MARKET-BASED\]*'],
  22   ['Charging your content creators *', '\[MARKET-BASED\]*'],
  23   ['Charging a transaction fee *', '\[MARKET-BASED\]*'],
  24   ['Providing a service to your creators*', '\[MARKET-BASED\]*'],
  25   ['Memberships and individual donations', '*\[RECIPROCITY-BASED\]*'],
  26   ['The pay-what-you-want model', '*\[RECIPROCITY-BASED\]*'],
  27   ['The', '', 'Creative', '', 'Commons', '', 'Licenses'],
  28   ['PLOS','', '(Public Library of Science)']
  29 ].each do |str|
  30   # This should be done more generic, more robust... But before
  31   # burning brain cells, verify if it's needed!
  32   if (data.select {|i| i == str[0]}.size != 1)
  33     raise RuntimeError, 'First string appears multiple times: %s (%s)' %
  34                         [str.reject{|i| i==''}.join(' '), str[0]]
  35   end
  36
  37   len = str.size
  38   at = data.index(str[0])
  39   joined = str.reject {|word| word==''}.join(' ')
  40   len.times do |offset|
  41     if str[offset] != data[at+offset]
  42       raise RuntimeError,
  43             'Warning: String does not match ("%s" of "%s", offset %d, book at %d)' %
  44             [str[offset], joined, offset, at+offset]
  45     end
  46   end
  47
  48   data[at] = joined
  49   (str.size - 1).times { data.delete_at(at+1) }
  50 end
  51
  52 # Mark up headings: Very artisanal and suboptimal, but should do the
  53 # trick.
  54 #
  55 # For every heading, put here the full string and its heading level,
  56 # as follows:
  57 #
  58 # 1 - Part
  59 # 2 - Chapter
  60 # 3 - Section
  61 # 4 - Subsection
  62 #
  63 # Try to keep this ordered as it appears within the book, as it will
  64 # help us spot omissions and mistakes!
  65 [ [2, 'Foreword'],
  66   [2, 'Introduction'],
  67   [1, 'Part 1'],
  68   [1, 'The Big Picture'],
  69   [2, 'The New World of Digital Commons'],
  70   [3, 'The Commons, the Market, and the State'],
  71   [3, 'The Four Aspects of a Resource'],
  72   [4, 'Characteristics'],
  73   [4, 'People and processes'],
  74   [4, 'Norms and rules'],
  75   [4, 'Goals'],
  76   [3, 'A Short History of the Commons'],
  77   [3, 'The Digital Revolution'],
  78   [3, 'The Birth of Creative Commons'],
  79   [3, 'The Changing Market'],
  80   [3, 'Benefits of the Digital Commons'],
  81   [3, 'Our Case Studies'],
  82   [3, 'Notes'],
  83   [2, 'How to Be Made with Creative Commons'],
  84   [3, 'Problem Zero: Getting Discovered'],
  85   [4, 'Use CC to grow a larger audience'],
  86   [4, 'Use CC to get attribution and name recognition'],
  87   [4, 'Use CC-licensed content as a marketing tool'],
  88   [4, 'Use CC to enable hands-on engagement with your work'],
  89   [4, 'Use CC to differentiate yourself'],
  90   [3, 'Making Money'],
  91   [4, 'Market-based revenue streams'],
  92   [4, 'Providing a custom service to consumers of your work * \[MARKET-BASED\]*'],
  93   [4, 'Charging for the physical copy * \[MARKET-BASED\]*'],
  94   [4, 'Charging for the in-person version * \[MARKET-BASED\]*'],
  95   [4, 'Selling merchandise * \[MARKET-BASED\]*'],
  96   [4, 'Charging advertisers or sponsors * \[MARKET-BASED\]*'],
  97   [4, 'Charging your content creators * \[MARKET-BASED\]*'],
  98   [4, 'Charging a transaction fee * \[MARKET-BASED\]*'],
  99   [4, 'Providing a service to your creators* \[MARKET-BASED\]*'],
 100   [4, 'Licensing a trademark* \[MARKET-BASED\]*'],
 101   [4, 'Reciprocity-based revenue streams'],
 102   [4, 'Memberships and individual donations *\[RECIPROCITY-BASED\]*'],
 103   [4, 'The pay-what-you-want model *\[RECIPROCITY-BASED\]*'],
 104   [4, 'Crowdfunding *\[RECIPROCITY-BASED\]*'],
 105   [3, 'Making Human Connections'],
 106   [4, 'Be human'],
 107   [4, 'Be open and accountable'],
 108   [4, 'Design for the good actors'],
 109   [4, 'Treat humans like, well, humans'],
 110   [4, 'State your principles and stick to them'],
 111   [4, 'Build a community'],
 112   [4, 'Give more to the commons than you take'],
 113   [4, 'Involve people in what you do'],
 114   [4, 'Notes'],
 115   [2, 'The Creative Commons Licenses'],
 116   [1, 'Part 2'],
 117   [1, 'The Case Studies'],
 118   [2, 'Arduino'],
 119   [2, 'Ártica'],
 120   [2, 'Blender Institute'],
 121   [2, 'Cards Against Humanity'],
 122   [2, 'The Conversation'],
 123   [2, 'Cory Doctorow'],
 124   [2, 'Figshare'],
 125   [2, 'Figure.NZ'],
 126   [2, 'Knowledge Unlatched'],
 127   [2, 'Lumen Learning'],
 128   [2, 'Jonathan Mann'],
 129   [2, 'Noun Project'],
 130   [2, 'Open Data Institute'],
 131   [2, 'OpenDesk'],
 132   [2, 'OpenStax'],
 133   [2, 'Amanda Palmer'],
 134   [2, 'PLOS (Public Library of Science)'],
 135   [2, 'Rijksmuseum'],
 136   [2, 'Shareable'],
 137   [2, 'Siyavula'],
 138   [2, 'Sparkfun'],
 139   [2, 'TeachAIDS'],
 140   [2, 'Tribe of Noise'],
 141   [2, 'Wikimedia Foundation'],
 142   [2, 'Bibliography'],
 143   [2, 'Acknowledgments'],
 144
 145 ].each do |item|
 146   at = data.index {|i| i == item[1]}
 147   if at.nil?
 148     raise RuntimeError, 'Heading string (level %d) not found: «%s»' % item
 149   end
 150   data[at] = '%s %s' % ['#' * item[0], data[at]]
 151 end
 152
 153
 154
 155 # Join erroneously split paragraphs
 156 ['to the values symbolized by',
 157  'the kinds of participative communities that drive open',
 158  'At a minimum, a CC-',
 159  'easier to trust a',
 160  'free download, the',
 161  'openness to fans remixing the game—give',
 162  'Attribution-',
 163  'both journal publishers and researchers. Figshare now provides',
 164  'get the “network effect”—',
 165  'access to scholarly books. For Frances, the current scholarly-',
 166  'for-',
 167  'sales',
 168  'contributing to the open',
 169  'doesn’t seem like it should be sung about',
 170  'songwriter, and he has found a way to keep it interesting for',
 171  'building trust is the top',
 172  'license',
 173  'authors and Shuttleworth; Mark remains incredibly proud of this',
 174  'BY-SA and opting in others with collecting societies like',
 175  'Cecilie Maria, Cedric Howe, Cefn Hoile,',
 176  'Braddlee, Drew Spencer, Duncan',
 177  'Elizabeth Holloway, Ellen Buecher, Ellen Kaye-',
 178  'Helen',
 179 ].each do |line|
 180   at = data.index {|i| i == line}
 181   if !at.nil? and data[at+1] == ''
 182     data.delete_at(at+1)
 183   end
 184 end
 185
 186 File.open(dstfile, 'w') {|f| f.puts data.join("\n")}