Class: ReVIEW::Epub2Html

Inherits:
Object show all
Defined in:
lib/review/epub2html.rb

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initializeEpub2Html

Returns a new instance of Epub2Html.



54
55
56
57
58
59
60
# File 'lib/review/epub2html.rb', line 54

def initialize
  @opfxml = nil
  @htmls = {}
  @head = nil
  @tail = nil
  @inline_footnote = nil
end

Class Method Details

.execute(*args) ⇒ Object



22
23
24
# File 'lib/review/epub2html.rb', line 22

def self.execute(*args)
  new.execute(*args)
end

Instance Method Details

#execute(*args) ⇒ Object



26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
# File 'lib/review/epub2html.rb', line 26

def execute(*args)
  opts = OptionParser.new

  opts.banner = <<EOT
Usage: review-epub2html [options] EPUBfile [file_for_head_and_foot] > HTMLfile
   file_for_head_and_foot: HTML file to extract header and footer area.
                           This file must be contained in the EPUB.
                           If omitted, the first found file is used.

EOT
  opts.version = ReVIEW::VERSION
  opts.on('--help', 'Prints this message and quit.') do
    puts opts.help
    exit 0
  end
  opts.on('--inline-footnote', 'Embed footnote blocks in paragraph.') { @inline_footnote = true }

  opts.parse!(args)

  if args[0].nil? || !File.exist?(args[0])
    puts opts.help
    exit 1
  end

  parse_epub(args[0])
  puts join_html(args[1])
end

#join_html(reffile) ⇒ Object



145
146
147
148
149
150
151
152
153
154
155
# File 'lib/review/epub2html.rb', line 145

def join_html(reffile)
  body = []
  make_list.each do |fname|
    if @head.nil? && (reffile.nil? || reffile == fname)
      take_headtail(@htmls[fname])
    end

    body << modify_html(fname, @htmls[fname])
  end
  "#{@head}\n#{body.join("\n")}\n#{@tail}"
end

#make_listObject



157
158
159
160
161
162
163
164
165
166
167
168
169
# File 'lib/review/epub2html.rb', line 157

def make_list
  items = {}
  @opfxml.each_element("/package/manifest/item[@media-type='application/xhtml+xml']") do |e|
    items[e.attributes['id']] = e.attributes['href']
  end

  files = []
  @opfxml.each_element('/package/spine/itemref') do |e|
    files.push(items[e.attributes['idref']])
  end

  files
end

#modify_html(fname, html) ⇒ Object



88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
# File 'lib/review/epub2html.rb', line 88

def modify_html(fname, html)
  doc = REXML::Document.new(html)
  doc.context[:attribute_quote] = :quote

  ids = {}

  doc.each_element('//*[@id]') do |e|
    sid = "#{sanitize(fname)}_#{sanitize(e.attributes['id'])}"
    while ids[sid]
      sid += 'E'
    end
    ids[sid] = true
    e.attributes['id'] = sid
  end

  doc.each_element('//a[@href]') do |e|
    href = e.attributes['href']
    if href.start_with?('http:', 'https:', 'ftp:', 'ftps:', 'mailto:')
      next
    end

    file, anc = href.split('#', 2)
    anc = if anc
            if file.empty?
              "#{sanitize(fname)}_#{sanitize(anc)}"
            else
              "#{sanitize(file)}_#{sanitize(anc)}"
            end
          else
            sanitize(file)
          end

    e.attributes['href'] = "##{anc}"
  end

  if @inline_footnote
    # move footnotes to inline as same as LaTeX.
    footnotes = {}

    doc.each_element("//div[@class='footnote']") do |e|
      e.name = 'span'
      e.attributes.delete('epub:type')
      footnotes[e.attributes['id']] = e
      e.remove
    end

    doc.each_element("//a[@class='noteref']") do |e|
      e.parent.insert_after(e, footnotes[e.attributes['href'].sub('#', '')])
      e.remove
    end
  end

  doc.to_s.
    sub(/.*(<body.*?>)/m, %Q(<section id="#{sanitize(fname)}">)).
    sub(%r{(</body>).*}m, '</section>')
end

#parse_epub(epubname) ⇒ Object



62
63
64
65
66
67
68
69
70
71
72
73
74
# File 'lib/review/epub2html.rb', line 62

def parse_epub(epubname)
  Zip::File.open(epubname) do |zio|
    zio.each do |entry|
      if /.+\.opf\Z/.match?(entry.name)
        opf = entry.get_input_stream.read
        @opfxml = REXML::Document.new(opf)
      elsif /.+\.x?html\Z/.match?(entry.name)
        @htmls[entry.name.sub('OEBPS/', '')] = entry.get_input_stream.read.force_encoding('utf-8')
      end
    end
  end
  nil
end

#sanitize(s) ⇒ Object



81
82
83
84
85
86
# File 'lib/review/epub2html.rb', line 81

def sanitize(s)
  s = s.sub(/\.x?html\Z/, '').
      sub(%r{\A\./}, '')
  's_' + CGI.escape(s).
         gsub(/[.,+%]/, '_')
end

#take_headtail(html) ⇒ Object



76
77
78
79
# File 'lib/review/epub2html.rb', line 76

def take_headtail(html)
  @head = html.sub(/(<body.*?>).*/m, '\1')
  @tail = html.sub(%r{.*(</body>)}m, '\1')
end