Class: ReVIEW::Epub2Html

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

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Epub2Html

Returns a new instance of Epub2Html.



34
35
36
37
38
39
 
# File 'lib/review/epub2html.rb', line 34

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

Class Method Details

.execute(*args) ⇒ Object 



15
16
17
 
# File 'lib/review/epub2html.rb', line 15

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

Instance Method Details

#execute(*args) ⇒ Object 



19
20
21
22
23
24
25
26
27
28
29
30
31
32
 
# File 'lib/review/epub2html.rb', line 19

def execute(*args)
  if args[0].nil? || !File.exist?(args[0])
    STDERR.puts <<EOT
Usage: #{File.basename($PROGRAM_NAME)} 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
    exit 1
  end

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

#join_html(reffile) ⇒ Object 



107
108
109
110
111
112
113
114
115
116
117
 
# File 'lib/review/epub2html.rb', line 107

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_list ⇒ Object 



119
120
121
122
123
124
125
126
127
128
129
130
131
 
# File 'lib/review/epub2html.rb', line 119

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 



67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
 
# File 'lib/review/epub2html.rb', line 67

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)
    if anc
      if file.empty?
        anc = "#{sanitize(fname)}_#{sanitize(anc)}"
      else
        anc = "#{sanitize(file)}_#{sanitize(anc)}"
      end
    else
      anc = sanitize(file)
    end

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

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

#parse_epub(epubname) ⇒ Object 



41
42
43
44
45
46
47
48
49
50
51
52
53
 
# File 'lib/review/epub2html.rb', line 41

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

#sanitize(s) ⇒ Object 



60
61
62
63
64
65
 
# File 'lib/review/epub2html.rb', line 60

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

#take_headtail(html) ⇒ Object 



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

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