Updated fixup with a paragraph fx, and reflect Pandoc version changes

[text-madewithcc.git] / fixup.rb

diff --git a/fixup.rb b/fixup.rb
index 595a8c868a1629746d7d8c5df97b952a51da27ba..c55798cc29a1f193c9acb8225dc4fbe0483e6cd1 100644 (file)
--- a/fixup.rb
+++ b/fixup.rb
@@ -1,38 +1,51 @@
 #!/usr/bin/ruby
 # coding: utf-8
+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*}/, '')}
+
+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'],
-  ['Use CC to get attribution and name', 'recognition'],
-  ['Use CC to enable hands-on engagement with', 'your work'],
-  ['Providing a custom service to consumers of', 'your work * \[MARKET-BASED\]*'],
-  ['Charging for the physical copy *', '\[MARKET-BASED\]*'],
-  ['Charging for the in-person version *','\[MARKET-BASED\]*'],
-  ['Charging advertisers or sponsors *', '\[MARKET-BASED\]*'],
-  ['Charging your content creators *', '\[MARKET-BASED\]*'],
-  ['Charging a transaction fee *', '\[MARKET-BASED\]*'],
-  ['Providing a service to your creators*', '\[MARKET-BASED\]*'],
+  ['Providing a custom service to consumers of your work *', '\[MARKET-BASED\]*'],
   ['Memberships and individual donations', '*\[RECIPROCITY-BASED\]*'],
-  ['The pay-what-you-want model', '*\[RECIPROCITY-BASED\]*'],
   ['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!
-  if (data.select {|i| i == str[0]}.size != 1)
-    raise RuntimeError, 'First string appears multiple times: %s (%s)' %
-                        [str.reject{|i| i==''}.join(' '), str[0]]
+  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])
@@ -62,6 +75,7 @@ end
 #
 # 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'],
@@ -143,6 +157,7 @@ end
   [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
@@ -152,9 +167,12 @@ end
 
 
 
-# Join erroneously split paragraphs
+# 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-',
@@ -179,10 +197,12 @@ end
  '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")}