Updated web version.

[text-madewithcc.git] / fixup.rb

diff --git a/fixup.rb b/fixup.rb
index cd025c15f39a04cf574214da6599b48b0b31bd2b..3c7709e6ad0f563b89c2d6bd939effccde1c115b 100644 (file)
--- a/fixup.rb
+++ b/fixup.rb
@@ -86,8 +86,8 @@ data[1].sub!(/ and /, ';') # authors
 # 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'
 # 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, 'Foreword'],
+  [1, 'Introduction'],

   [1, 'Part 1'],
   [1, 'The Big Picture'],
   [2, 'The New World of Digital Commons'],
   [1, 'Part 1'],
   [1, 'The Big Picture'],
   [2, 'The New World of Digital Commons'],


@@ -163,8 +163,8 @@ log 0, 'Mark up headings'
   [2, 'TeachAIDS'],
   [2, 'Tribe of Noise'],
   [2, 'Wikimedia Foundation'],
   [2, 'TeachAIDS'],
   [2, 'Tribe of Noise'],
   [2, 'Wikimedia Foundation'],

-  [2, 'Bibliography'],
-  [2, 'Acknowledgments'],
+  [1, 'Bibliography'],
+  [1, 'Acknowledgments'],

   
 ].each do |item|
   log 1, item.join(' -> ')
   
 ].each do |item|
   log 1, item.join(' -> ')


@@ -181,6 +181,12 @@ end
 data.delete("# Part 1")
 data.delete("# Part 2")
 
 data.delete("# Part 1")
 data.delete("# Part 2")
 

+log 0, 'add heading to colophon page'
+data.insert(data.index('Made With Creative Commons'), '# Colophon {-}')
+
+log 0, 'add dedication as separeate chapter'
+data.insert(data.index('"I don\'t know a whole lot about nonfiction journalism. . .'), '# Dedication {-}')
+

 # Join erroneously split paragraphs: Write the contents of the line
 # _preceding_ the unneeded break, the break will be removed.
 #
 # Join erroneously split paragraphs: Write the contents of the line
 # _preceding_ the unneeded break, the break will be removed.
 #


@@ -195,23 +201,25 @@ log 0, 'Join erroneously split paragraphs'
  'the kinds of participative communities that drive open', # 2157
  'time', # 2220
  'At a minimum, a CC-', # 2375
  'the kinds of participative communities that drive open', # 2157
  'time', # 2220
  'At a minimum, a CC-', # 2375

+ '"Share Your Work" at', # 2508

  'easier to trust a', # 2580
  'easier to trust a', # 2580

- 'free download, the', # 3086
- 'openness to fans remixing the game—give', # 3087
+ 'the free download, the', # 3086
+ 'openness to fans remixing the game---give', # 3087

  'Attribution-', # 3307
  'Attribution-', # 3307

- 'both journal publishers and researchers. Figshare now provides', # 3672
- 'get the “network effect”—', # 4002
+ 'to both journal publishers and researchers. Figshare now provides', # 3672
+ 'get the "network effect"---', # 4002

  'access to scholarly books. For Frances, the current scholarly-', # 4033
  'for-', # 4288
  'sales', # 4410
  'contributing to the open', # 4438
  'access to scholarly books. For Frances, the current scholarly-', # 4033
  'for-', # 4288
  'sales', # 4410
  'contributing to the open', # 4438

- 'doesn’t seem like it should be sung about', # 4616
+ 'doesn\'t seem like it should be sung about', # 4616

  'songwriter, and he has found a way to keep it interesting for', # 4624
  'building trust is the top', # 4793
  'version', # 6023
  'license', # 6169
  'authors and Shuttleworth; Mark remains incredibly proud of this', # 6452
  'BY-SA and opting in others with collecting societies like', # 7218
  'songwriter, and he has found a way to keep it interesting for', # 4624
  'building trust is the top', # 4793
  'version', # 6023
  'license', # 6169
  'authors and Shuttleworth; Mark remains incredibly proud of this', # 6452
  'BY-SA and opting in others with collecting societies like', # 7218

+ 'Journeys to a Generative Economy. San Francisco:', # 7553

  'Cecilie Maria, Cedric Howe, Cefn Hoile,', # 7796
  'Braddlee, Drew Spencer, Duncan', # 7839
  'Elizabeth Holloway, Ellen Buecher, Ellen Kaye-', # 7844
  'Cecilie Maria, Cedric Howe, Cefn Hoile,', # 7796
  'Braddlee, Drew Spencer, Duncan', # 7839
  'Elizabeth Holloway, Ellen Buecher, Ellen Kaye-', # 7844


@@ -224,24 +232,109 @@ log 0, 'Join erroneously split paragraphs'
   end
 end
 
   end
 end
 

-log 0, 'Mark quote in dedication as quote with attribute in markdown'
-start = "“I don’t know a whole lot about nonfiction journalism. . ."
-stop = "- David Foster Wallace"
+log 0, 'Identify and mark footnotes/endnodes'
+scope="unknown"
+noteblock=false
+data.each_with_index do |lin, idx|
+  if lin =~ /^## (.+)$/
+    scope=$1.gsub(" ", "-")
+  end
+  # First, mark note reference
+  lin.sub!(/([a-z][\.\)]+["”]?)(\d+)(\s)/, "\\1[^" + scope + "-\\2]\\3")
+  lin.sub!(/([a-z][\.\)]+["”]?)(\d+)$/, "\\1[^" + scope + "-\\2]")
+  # Special case some refs hard to match otherwise
+  lin.sub!(/(section.\)) 36 /, "\\1[^" + scope + "-36] ")
+  lin.sub!(/(Data Futures Forum in 2014,)1 /, "\\1[^" + scope + "-1] ")
+  lin.sub!(/(5,080)5/, "\\1[^" + scope + "-5]")
+  lin.sub!(/(sustain her creative work.) 1/, "\\1[^" + scope + "-1]")
+  # Next, mark note content, only between /Web Links?|Notes/ and next heading
+  if noteblock
+    lin.sub!(/^(\d+)\. /, "[^" + scope + "-\\1]: ")
+    if lin =~ /^##?.+/
+      noteblock=false
+    end
+  end
+  if lin =~ /^(### Notes|Web links?)/
+    noteblock=true
+    # Turn web link line into section header, to make it easier to
+    # find by fixup-docbook.rb.
+    lin.gsub!(/^(Web links?)/, "### \\1")
+  end
+end
+
+log 0, 'verify every footnote/endnote is unique and used'
+notes = Hash.new
+data.each_with_index do |lin, idx|
+  if lin =~ /(\[\^[^\]]+\])(:)?/
+#    log 0, "*** found %s %s" % [$1, $2]
+    if not notes.has_key?($1)
+      notes[$1] = Hash.new
+    end
+    if $2 == ':'
+      notes[$1]['def'] = true
+    else
+      notes[$1]['ref'] = true
+    end
+  end
+end
+notes.each do |key, val|
+  if val.has_key?('def') != val.has_key?('ref')
+    log 0, "error: check use of footnote %s" % key
+  end
+end
+
+log 0, 'Turn indented block after use cases into block quotes'
+inscope=false

 quote=false
 data.each_with_index do |lin, idx|
 quote=false
 data.each_with_index do |lin, idx|

-  if lin == stop
-    lin.sub!(/^- /, "> — ")
-    lin.sub!("David Foster Wallace", "*David Foster Wallace*")
+  if quote
+    lin.sub!(/^/, "> ")
+  end
+  if lin =~ /^> Profile written by/

     quote=false
     quote=false

-    break

   end
   end

-  if lin == start
+  # To this heading
+  if lin =~ /^## Bibliography/
+    inscope=false
+  end
+  # From this heading
+  if lin =~ /^## Arduino/
+    inscope=true
+  end
+  if inscope and lin =~ /^## /

     quote=true
     quote=true

+    next

   end
   end

-  if quote
-    lin.sub!(/^/, "> ")
+end
+
+log 0, 'emphesize keywords'
+data.map {|lin| lin.gsub!(/^(>\s*)(Revenue model|Interview date|Interviewees?):/, '\\1**\\2**:')}
+
+log 0, 'make figure sizes relative to text body width while keeping aspect ratio'
+data.map {|lin| lin.gsub!(/width="6.5in"/, 'width="80%"')}
+data.map {|lin| lin.gsub!(/width="4.198in"/, 'width="40%"')}
+data.map {|lin| lin.gsub!(/width="4.1665in"/, 'width="40%"')}
+data.map {|lin| lin.gsub!(/height="[0-9.]+in"/, '')}
+
+log 0, 'add figure titles required by Docbook for referable figures'
+[
+  ['10000201000008000000045C30360249076453E6.png', 'Enterprise engagement with commons, state and market.'],
+  ['10000201000007D0000007D0ACF13F8B71EAF0B9.png', 'Four aspects of resource management'],
+  ['10000201000009C40000065D9EC4F530BD4DFBE0.png', 'How the market, commons and state concieve of resources.'],
+  ['10000201000009C4000005153EACBD62F00F6BA9.png', 'In preindustrialized society.'],
+  ['10000201000009C4000005150F069409C1CC12F0.png', 'The commons is gradually superseded by the state.'],
+  ['10000201000009C400000515F1CAA15B223F6BAF.png', 'How the market, the state and the commons look today.'],
+].each do |fig|
+  at = data.index {|i| i.include? fig[0]}
+  if at.nil?
+    raise RuntimeError, 'No figure named «%s» found' % fig[0]

   end
   end

+  data[at].gsub!(/!\[\]\(Pictures/, '![%s](Pictures' % fig[1])

 end
 
 end
 

+log 0, 'adding http:// to all URLs and turn them into links'
+data.map {|lin| lin.gsub!(/(^|\s+)([-a-z0-9\\.]+\.(ca|cc|com|edu|eu|io|is|it|kr|net|nl|nz|org|se))/, '\\1http://\\2')}
+data.map {|lin| lin.gsub!(/\b(https?:\/\/[-a-z0-9\\.]+)(\/[-\\.\/a-zA-Z0-9#_\?&=,]+[-\/a-zA-Z0-9#_\?&=,])?/, '[](\\1\\2)')}
+

 log 0, 'Writing processed file'
 File.open(dstfile, 'w') {|f| f.puts data.join("\n")}
 log 0, 'Writing processed file'
 File.open(dstfile, 'w') {|f| f.puts data.join("\n")}