fixup.rb

   1 #!/usr/bin/ruby
   2 # coding: utf-8
   3 raise ArgumentError, 'Source file 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 # Join erroneously split paragraphs
  12 ['At a minimum, a CC-',
  13  'easier to trust a',
  14  'free download, the',
  15  'openness to fans remixing the game—give',
  16  'Attribution-',
  17  'both journal publishers and researchers. Figshare now provides',
  18  'get the “network effect”—',
  19  'access to scholarly books. For Frances, the current scholarly-',
  20  'for-',
  21  'sales',
  22  'contributing to the open',
  23  'doesn’t seem like it should be sung about',
  24  'songwriter, and he has found a way to keep it interesting for',
  25  'building trust is the top',
  26  'license',
  27  'authors and Shuttleworth; Mark remains incredibly proud of this',
  28  'BY-SA and opting in others with collecting societies like',
  29  'Cecilie Maria, Cedric Howe, Cefn Hoile,',
  30  'Braddlee, Drew Spencer, Duncan',
  31  'Elizabeth Holloway, Ellen Buecher, Ellen Kaye-',
  32  'Helen',
  33 ].each do |line|
  34   at = data.index {|i| i == line}
  35   if !at.nil? and data[at+1] == ''
  36     data.delete_at(at+1)
  37   end
  38 end
  39
  40 File.open(dstfile, 'w') {|f| f.puts data.join("\n")}