X-Git-Url: https://pere.pagekite.me/gitweb/text-madewithcc.git/blobdiff_plain/bec5f77092a50adc94c8563c186c1ab8fc5d89f4..1a0a0a629b107b35a860195d77c84c48876d20c6:/fixup.rb?ds=sidebyside

diff --git a/fixup.rb b/fixup.rb
index 728b4f0..c55798c 100644
--- a/fixup.rb
+++ b/fixup.rb
@@ -1,15 +1,181 @@
 #!/usr/bin/ruby
 # coding: utf-8
-raise ArgumentError, 'Source file not specified' if ARGV.size != 2
+LogLevel=1
+raise ArgumentError, 'Source/destination files not specified' if ARGV.size != 2
 srcfile = ARGV[0]
 dstfile = ARGV[1]
 
 data=File.open(srcfile).readlines.map {|l| l.chomp!}
 
-data.map {|lin| lin.gsub!(/<span id="anchor-?\d*"><\/span>/, '')}
+data.map {|lin| lin.gsub!(/\[\]{#anchor-?\d*}/, '')}
 
-# Join erroneously split paragraphs
-['At a minimum, a CC-',
+def log(level,what)
+  indicators = %w(! • # -)
+  if level >= LogLevel
+    print indicators[level]
+  else
+    print "\n%s %s\n" % ['*' * (level+1), what]
+  end
+end
+
+# There are several titles that are spread in more than one line. Make
+# them into translatable sentences.
+log 0, 'Merging multiline sentences '
+[ ['Made', '', 'with', '', 'Creative', '', 'Commons'],
+  ['The New','', 'World of', '', 'Digital', '', 'Commons'],
+  ['How', '', 'to Be', '', 'Made with', '', 'Creative', '', 'Commons'],
+  ['Providing a custom service to consumers of your work *', '\[MARKET-BASED\]*'],
+  ['Memberships and individual donations', '*\[RECIPROCITY-BASED\]*'],
+  ['The', '', 'Creative', '', 'Commons', '', 'Licenses'],
+  ['PLOS','', '(Public Library of Science)']
+].each do |str|
+  # This should be done more generic, more robust... But before
+  # burning brain cells, verify if it's needed!
+  log 1, str
+  matches=[]
+  data.each_with_index do |lin, idx|
+    if lin == str[0]
+      matches << idx
+    end
+  end
+  if matches.size == 0
+    raise RuntimeError, 'Anchor string («%s» for «%s») not found' %
+                        [str[0], str.reject {|word| word==''}.join(' ')]
+  elsif matches.size > 1
+    raise RuntimeError, 'Anchor string (%s) appears multiple times: %s' %
+                        [str[0], matches.map {|i| i.to_s}.join(', ')]
+  end
+  log 2, 'Matches %s: %d - %s' % [str.join(' '), matches.size, matches.join(',')]
+
+  len = str.size
+  at = data.index(str[0])
+  joined = str.reject {|word| word==''}.join(' ')
+  len.times do |offset|
+    if str[offset] != data[at+offset]
+      raise RuntimeError,
+            'Warning: String does not match ("%s" of "%s", offset %d, book at %d)' %
+            [str[offset], joined, offset, at+offset]
+    end
+  end
+
+  data[at] = joined
+  (str.size - 1).times { data.delete_at(at+1) }
+end
+
+# Mark up headings: Very artisanal and suboptimal, but should do the
+# trick.
+#
+# For every heading, put here the full string and its heading level,
+# as follows:
+#
+# 1 - Part
+# 2 - Chapter
+# 3 - Section
+# 4 - Subsection
+#
+# Try to keep this ordered as it appears within the book, as it will
+# help us spot omissions and mistakes!
+log 0, 'Mark up headings'
+[ [2, 'Foreword'],
+  [2, 'Introduction'],
+  [1, 'Part 1'],
+  [1, 'The Big Picture'],
+  [2, 'The New World of Digital Commons'],
+  [3, 'The Commons, the Market, and the State'],
+  [3, 'The Four Aspects of a Resource'],
+  [4, 'Characteristics'],
+  [4, 'People and processes'],
+  [4, 'Norms and rules'],
+  [4, 'Goals'],
+  [3, 'A Short History of the Commons'],
+  [3, 'The Digital Revolution'],
+  [3, 'The Birth of Creative Commons'],
+  [3, 'The Changing Market'],
+  [3, 'Benefits of the Digital Commons'],
+  [3, 'Our Case Studies'],
+  [3, 'Notes'],
+  [2, 'How to Be Made with Creative Commons'],
+  [3, 'Problem Zero: Getting Discovered'],
+  [4, 'Use CC to grow a larger audience'],
+  [4, 'Use CC to get attribution and name recognition'],
+  [4, 'Use CC-licensed content as a marketing tool'],
+  [4, 'Use CC to enable hands-on engagement with your work'],
+  [4, 'Use CC to differentiate yourself'],
+  [3, 'Making Money'],
+  [4, 'Market-based revenue streams'],
+  [4, 'Providing a custom service to consumers of your work * \[MARKET-BASED\]*'],
+  [4, 'Charging for the physical copy * \[MARKET-BASED\]*'],
+  [4, 'Charging for the in-person version * \[MARKET-BASED\]*'],
+  [4, 'Selling merchandise * \[MARKET-BASED\]*'],
+  [4, 'Charging advertisers or sponsors * \[MARKET-BASED\]*'],
+  [4, 'Charging your content creators * \[MARKET-BASED\]*'],
+  [4, 'Charging a transaction fee * \[MARKET-BASED\]*'],
+  [4, 'Providing a service to your creators* \[MARKET-BASED\]*'],
+  [4, 'Licensing a trademark* \[MARKET-BASED\]*'],
+  [4, 'Reciprocity-based revenue streams'],
+  [4, 'Memberships and individual donations *\[RECIPROCITY-BASED\]*'],
+  [4, 'The pay-what-you-want model *\[RECIPROCITY-BASED\]*'],
+  [4, 'Crowdfunding *\[RECIPROCITY-BASED\]*'],
+  [3, 'Making Human Connections'],
+  [4, 'Be human'],
+  [4, 'Be open and accountable'],
+  [4, 'Design for the good actors'],
+  [4, 'Treat humans like, well, humans'],
+  [4, 'State your principles and stick to them'],
+  [4, 'Build a community'],
+  [4, 'Give more to the commons than you take'],
+  [4, 'Involve people in what you do'],
+  [4, 'Notes'],
+  [2, 'The Creative Commons Licenses'],
+  [1, 'Part 2'],
+  [1, 'The Case Studies'],
+  [2, 'Arduino'],
+  [2, 'Ártica'],
+  [2, 'Blender Institute'],
+  [2, 'Cards Against Humanity'],
+  [2, 'The Conversation'],
+  [2, 'Cory Doctorow'],
+  [2, 'Figshare'],
+  [2, 'Figure.NZ'],
+  [2, 'Knowledge Unlatched'],
+  [2, 'Lumen Learning'],
+  [2, 'Jonathan Mann'],
+  [2, 'Noun Project'],
+  [2, 'Open Data Institute'],
+  [2, 'OpenDesk'],
+  [2, 'OpenStax'],
+  [2, 'Amanda Palmer'],
+  [2, 'PLOS (Public Library of Science)'],
+  [2, 'Rijksmuseum'],
+  [2, 'Shareable'],
+  [2, 'Siyavula'],
+  [2, 'Sparkfun'],
+  [2, 'TeachAIDS'],
+  [2, 'Tribe of Noise'],
+  [2, 'Wikimedia Foundation'],
+  [2, 'Bibliography'],
+  [2, 'Acknowledgments'],
+  
+].each do |item|
+  log 1, item.join(' -> ')
+  at = data.index {|i| i == item[1]}
+  if at.nil?
+    raise RuntimeError, 'Heading string (level %d) not found: «%s»' % item
+  end
+  data[at] = '%s %s' % ['#' * item[0], data[at]]
+end
+
+
+
+# Join erroneously split paragraphs: Write the contents of the line
+# _preceding_ the unneeded break, the break will be removed.
+log 0, 'Join erroneously split paragraphs'
+['content and, in turn, spend money and',
+ 'still other',
+ 'content functions as a marketing tool for the paid product or',
+ 'to the values symbolized by',
+ 'the kinds of participative communities that drive open',
+ 'At a minimum, a CC-',
  'easier to trust a',
  'free download, the',
  'openness to fans remixing the game—give',
@@ -31,10 +197,12 @@ data.map {|lin| lin.gsub!(/<span id="anchor-?\d*"><\/span>/, '')}
  'Elizabeth Holloway, Ellen Buecher, Ellen Kaye-',
  'Helen',
 ].each do |line|
+  log 1, line
   at = data.index {|i| i == line}
   if !at.nil? and data[at+1] == ''
     data.delete_at(at+1)
   end
 end
 
+log 0, 'Writing processed file'
 File.open(dstfile, 'w') {|f| f.puts data.join("\n")}