fixup.rb

   1 #!/usr/bin/ruby
   2 # coding: utf-8
   3 LogLevel=1
   4 raise ArgumentError, 'Source/destination files not specified' if ARGV.size != 2
   5 srcfile = ARGV[0]
   6 dstfile = ARGV[1]
   7
   8 data=File.open(srcfile).readlines.map {|l| l.chomp!}
   9
  10 data.map {|lin| lin.gsub!(/\[\]{#anchor-?\d*}/, '')}
  11
  12 def log(level,what)
  13   indicators = %w(! • # -)
  14   if level >= LogLevel
  15     print indicators[level]
  16   else
  17     print "\n%s %s\n" % ['*' * (level+1), what]
  18   end
  19 end
  20
  21 # There are several titles that are spread in more than one line. Make
  22 # them into translatable sentences.
  23 log 0, 'Merging multiline sentences '
  24 [ ['Made', '', 'with', '', 'Creative', '', 'Commons'],
  25   ['The New','', 'World of', '', 'Digital', '', 'Commons'],
  26   ['How', '', 'to Be', '', 'Made with', '', 'Creative', '', 'Commons'],
  27   ['Providing a custom service to consumers of your work *', '\[MARKET-BASED\]*'],
  28   ['Memberships and individual donations', '*\[RECIPROCITY-BASED\]*'],
  29   ['The', '', 'Creative', '', 'Commons', '', 'Licenses'],
  30   ['jonathanmann.net and', '', 'jonathanmann.bandcamp.com'],
  31   ['PLOS','', '(Public Library of Science)']
  32 ].each do |str|
  33   # This should be done more generic, more robust... But before
  34   # burning brain cells, verify if it's needed!
  35   log 1, str
  36   matches=[]
  37   data.each_with_index do |lin, idx|
  38     if lin == str[0]
  39       matches << idx
  40     end
  41   end
  42   if matches.size == 0
  43     raise RuntimeError, 'Anchor string («%s» for «%s») not found' %
  44                         [str[0], str.reject {|word| word==''}.join(' ')]
  45   elsif matches.size > 1
  46     raise RuntimeError, 'Anchor string (%s) appears multiple times: %s' %
  47                         [str[0], matches.map {|i| i.to_s}.join(', ')]
  48   end
  49   log 2, 'Matches %s: %d - %s' % [str.join(' '), matches.size, matches.join(',')]
  50
  51   len = str.size
  52   at = data.index(str[0])
  53   joined = str.reject {|word| word==''}.join(' ')
  54   len.times do |offset|
  55     if str[offset] != data[at+offset]
  56       raise RuntimeError,
  57             'Warning: String does not match ("%s" of "%s", offset %d, book at %d)' %
  58             [str[offset], joined, offset, at+offset]
  59     end
  60   end
  61
  62   data[at] = joined
  63   (str.size - 1).times { data.delete_at(at+1) }
  64 end
  65
  66 # Mark up headings: Very artisanal and suboptimal, but should do the
  67 # trick.
  68 #
  69 # For every heading, put here the full string and its heading level,
  70 # as follows:
  71 #
  72 # 1 - Part
  73 # 2 - Chapter
  74 # 3 - Section
  75 # 4 - Subsection
  76 #
  77 # Try to keep this ordered as it appears within the book, as it will
  78 # help us spot omissions and mistakes!
  79 log 0, 'Mark up headings'
  80 [ [2, 'Foreword'],
  81   [2, 'Introduction'],
  82   [1, 'Part 1'],
  83   [1, 'The Big Picture'],
  84   [2, 'The New World of Digital Commons'],
  85   [3, 'The Commons, the Market, and the State'],
  86   [3, 'The Four Aspects of a Resource'],
  87   [4, 'Characteristics'],
  88   [4, 'People and processes'],
  89   [4, 'Norms and rules'],
  90   [4, 'Goals'],
  91   [3, 'A Short History of the Commons'],
  92   [3, 'The Digital Revolution'],
  93   [3, 'The Birth of Creative Commons'],
  94   [3, 'The Changing Market'],
  95   [3, 'Benefits of the Digital Commons'],
  96   [3, 'Our Case Studies'],
  97   [3, 'Notes'],
  98   [2, 'How to Be Made with Creative Commons'],
  99   [3, 'Problem Zero: Getting Discovered'],
 100   [4, 'Use CC to grow a larger audience'],
 101   [4, 'Use CC to get attribution and name recognition'],
 102   [4, 'Use CC-licensed content as a marketing tool'],
 103   [4, 'Use CC to enable hands-on engagement with your work'],
 104   [4, 'Use CC to differentiate yourself'],
 105   [3, 'Making Money'],
 106   [4, 'Market-based revenue streams'],
 107   [4, 'Providing a custom service to consumers of your work * \[MARKET-BASED\]*'],
 108   [4, 'Charging for the physical copy * \[MARKET-BASED\]*'],
 109   [4, 'Charging for the in-person version * \[MARKET-BASED\]*'],
 110   [4, 'Selling merchandise * \[MARKET-BASED\]*'],
 111   [4, 'Charging advertisers or sponsors * \[MARKET-BASED\]*'],
 112   [4, 'Charging your content creators * \[MARKET-BASED\]*'],
 113   [4, 'Charging a transaction fee * \[MARKET-BASED\]*'],
 114   [4, 'Providing a service to your creators* \[MARKET-BASED\]*'],
 115   [4, 'Licensing a trademark* \[MARKET-BASED\]*'],
 116   [4, 'Reciprocity-based revenue streams'],
 117   [4, 'Memberships and individual donations *\[RECIPROCITY-BASED\]*'],
 118   [4, 'The pay-what-you-want model *\[RECIPROCITY-BASED\]*'],
 119   [4, 'Crowdfunding *\[RECIPROCITY-BASED\]*'],
 120   [3, 'Making Human Connections'],
 121   [4, 'Be human'],
 122   [4, 'Be open and accountable'],
 123   [4, 'Design for the good actors'],
 124   [4, 'Treat humans like, well, humans'],
 125   [4, 'State your principles and stick to them'],
 126   [4, 'Build a community'],
 127   [4, 'Give more to the commons than you take'],
 128   [4, 'Involve people in what you do'],
 129   [3, 'Notes'],
 130   [2, 'The Creative Commons Licenses'],
 131   [1, 'Part 2'],
 132   [1, 'The Case Studies'],
 133   [2, 'Arduino'],
 134   [2, 'Ártica'],
 135   [2, 'Blender Institute'],
 136   [2, 'Cards Against Humanity'],
 137   [2, 'The Conversation'],
 138   [2, 'Cory Doctorow'],
 139   [2, 'Figshare'],
 140   [2, 'Figure.NZ'],
 141   [2, 'Knowledge Unlatched'],
 142   [2, 'Lumen Learning'],
 143   [2, 'Jonathan Mann'],
 144   [2, 'Noun Project'],
 145   [2, 'Open Data Institute'],
 146   [2, 'OpenDesk'],
 147   [2, 'OpenStax'],
 148   [2, 'Amanda Palmer'],
 149   [2, 'PLOS (Public Library of Science)'],
 150   [2, 'Rijksmuseum'],
 151   [2, 'Shareable'],
 152   [2, 'Siyavula'],
 153   [2, 'SparkFun'],
 154   [2, 'TeachAIDS'],
 155   [2, 'Tribe of Noise'],
 156   [2, 'Wikimedia Foundation'],
 157   [2, 'Bibliography'],
 158   [2, 'Acknowledgments'],
 159
 160 ].each do |item|
 161   log 1, item.join(' -> ')
 162   at = data.index {|i| i == item[1]}
 163   if at.nil?
 164     raise RuntimeError, 'Heading string (level %d) not found: «%s»' % item
 165   end
 166   data[at] = '%s %s' % ['#' * item[0], data[at]]
 167 end
 168
 169 # We have the explicit strings "Part 1" and "Part 2" as structural
 170 # elements — They are to be generated upon book compilation. Nuke
 171 # them.
 172 data.delete("# Part 1")
 173 data.delete("# Part 2")
 174
 175 # Join erroneously split paragraphs: Write the contents of the line
 176 # _preceding_ the unneeded break, the break will be removed.
 177 #
 178 # I'm noting the line number for each _after_ corrections so it's
 179 # easier to find them; please keep them sorted! :-P
 180 log 0, 'Join erroneously split paragraphs'
 181 ['content and, in turn, spend money and', # 1595
 182  'still other', # 1662
 183  'content functions as a marketing tool for the paid product or', # 1724
 184  'lowest-common-denominator solutions and', #2035
 185  'to the values symbolized by', # 2145
 186  'the kinds of participative communities that drive open', # 2157
 187  'time', # 2220
 188  'At a minimum, a CC-', # 2375
 189  'easier to trust a', # 2580
 190  'free download, the', # 3086
 191  'openness to fans remixing the game—give', # 3087
 192  'Attribution-', # 3307
 193  'both journal publishers and researchers. Figshare now provides', # 3672
 194  'get the “network effect”—', # 4002
 195  'access to scholarly books. For Frances, the current scholarly-', # 4033
 196  'for-', # 4288
 197  'sales', # 4410
 198  'contributing to the open', # 4438
 199  'doesn’t seem like it should be sung about', # 4616
 200  'songwriter, and he has found a way to keep it interesting for', # 4624
 201  'building trust is the top', # 4793
 202  'version', # 6023
 203  'license', # 6169
 204  'authors and Shuttleworth; Mark remains incredibly proud of this', # 6452
 205  'BY-SA and opting in others with collecting societies like', # 7218
 206  'Cecilie Maria, Cedric Howe, Cefn Hoile,', # 7796
 207  'Braddlee, Drew Spencer, Duncan', # 7839
 208  'Elizabeth Holloway, Ellen Buecher, Ellen Kaye-', # 7844
 209  'Helen', # 7874
 210 ].each do |line|
 211   log 1, line
 212   at = data.index {|i| i == line}
 213   if !at.nil? and data[at+1] == ''
 214     data.delete_at(at+1)
 215   end
 216 end
 217
 218 log 0, 'Mark quote in dedication as quote with attribute in markdown'
 219 start = "“I don’t know a whole lot about nonfiction journalism. . ."
 220 stop = "- David Foster Wallace"
 221 quote=false
 222 data.each_with_index do |lin, idx|
 223   if lin == stop
 224     lin.sub!(/^- /, "> &mdash; ")
 225     lin.sub!("David Foster Wallace", "*David Foster Wallace*")
 226     quote=false
 227     break
 228   end
 229   if lin == start
 230     quote=true
 231   end
 232   if quote
 233     lin.sub!(/^/, "> ")
 234   end
 235 end
 236
 237 log 0, 'Writing processed file'
 238 File.open(dstfile, 'w') {|f| f.puts data.join("\n")}