File: roff.rb

package info (click to toggle)
ruby-ronn 0.7.3-2
  • links: PTS
  • area: main
  • in suites: wheezy
  • size: 512 kB
  • sloc: ruby: 1,405; makefile: 2
file content (284 lines) | stat: -rw-r--r-- 7,676 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
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
53
54
55
56
57
58
59
60
61
62
63
64
65
66
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
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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
require 'hpricot'
require 'ronn/utils'

module Ronn
  class RoffFilter
    include Ronn::Utils

    # Convert Ronn HTML to roff.
    def initialize(html, name, section, tagline, manual=nil, version=nil, date=nil)
      @buf = []
      title_heading name, section, tagline, manual, version, date
      doc = Hpricot(html)
      remove_extraneous_elements! doc
      normalize_whitespace! doc
      block_filter doc
      write "\n"
    end

    def to_s
      @buf.join.gsub(/[ \t]+$/, '')
    end

  protected
    def previous(node)
      if node.respond_to?(:previous)
        prev = node.previous
        prev = prev.previous until prev.nil? || prev.elem?
        prev
      end
    end

    def title_heading(name, section, tagline, manual, version, date)
      comment "generated with Ronn/v#{Ronn.version}"
      comment "http://github.com/rtomayko/ronn/tree/#{Ronn.revision}"
      return if name.nil?
      macro "TH", %["#{escape(name.upcase)}" "#{section}" "#{date.strftime('%B %Y')}" "#{version}" "#{manual}"]
    end

    def remove_extraneous_elements!(doc)
      doc.traverse_all_element do |node|
        if node.comment? || node.procins? || node.doctype? || node.xmldecl?
          node.parent.children.delete(node)
        end
      end
    end

    def normalize_whitespace!(node)
      case
      when node.kind_of?(Array) || node.kind_of?(Hpricot::Elements)
        node.to_a.dup.each { |ch| normalize_whitespace! ch }
      when node.text?
        preceding, following = node.previous, node.next
        content = node.content.gsub(/[\n ]+/m, ' ')
        if preceding.nil? || block_element?(preceding.name) ||
           preceding.name == 'br'
          content.lstrip!
        end
        if following.nil? || block_element?(following.name) ||
           following.name == 'br'
          content.rstrip!
        end
        if content.empty?
          node.parent.children.delete(node)
        else
          node.content = content
        end
      when node.elem? && node.name == 'pre'
        # stop traversing
      when node.elem? && node.children
        normalize_whitespace! node.children
      when node.elem?
        # element has no children
      when node.doc?
        normalize_whitespace! node.children
      else
        warn "unexpected node during whitespace normalization: %p", node
      end
    end

    def block_filter(node)
      if node.kind_of?(Array) || node.kind_of?(Hpricot::Elements)
        node.each { |ch| block_filter(ch) }

      elsif node.doc?
        block_filter(node.children)

      elsif node.text?
        warn "unexpected text: %p",  node

      elsif node.elem?
        case node.name
        when 'div'
          block_filter(node.children)
        when 'h1'
          # discard
        when 'h2'
          macro "SH", quote(escape(node.html))
        when 'h3'
          macro "SS", quote(escape(node.html))

        when 'p'
          prev = previous(node)
          if prev && %w[dd li].include?(node.parent.name)
            macro "IP"
          elsif prev && !%w[h1 h2 h3].include?(prev.name)
            macro "P"
          end
          inline_filter(node.children)

        when 'pre'
          prev = previous(node)
          indent = prev.nil? || !%w[h1 h2 h3].include?(prev.name)
          macro "IP", %w["" 4] if indent
          macro "nf"
          write "\n"
          inline_filter(node.children)
          macro "fi"
          macro "IP", %w["" 0] if indent

        when 'dl'
          macro "TP"
          block_filter(node.children)
        when 'dt'
          prev = previous(node)
          macro "TP" unless prev.nil?
          inline_filter(node.children)
          write "\n"
        when 'dd'
          if node.at('p')
            block_filter(node.children)
          else
            inline_filter(node.children)
          end
          write "\n"

        when 'ol', 'ul'
          block_filter(node.children)
          macro "IP", %w["" 0]
        when 'li'
          case node.parent.name
          when 'ol'
            macro "IP", %W["#{node.position + 1}." 4]
          when 'ul'
            macro "IP", %w["\(bu" 4]
          end
          if node.at('p|ol|ul|dl|div')
            block_filter(node.children)
          else
            inline_filter(node.children)
          end
          write "\n"

        else
          warn "unrecognized block tag: %p", node.name
        end

      else
        fail "unexpected node: #{node.inspect}"
      end
    end

    def inline_filter(node)
      return unless node # is an empty node

      if node.kind_of?(Array) || node.kind_of?(Hpricot::Elements)
        node.each { |ch| inline_filter(ch) }

      elsif node.text?
        text = node.to_html.dup
        write escape(text)

      elsif node.elem?
        case node.name
        when 'span'
          inline_filter(node.children)
        when 'code'
          if child_of?(node, 'pre')
            inline_filter(node.children)
          else
            write '\fB'
            inline_filter(node.children)
            write '\fR'
          end

        when 'b', 'strong', 'kbd', 'samp'
          write '\fB'
          inline_filter(node.children)
          write '\fR'

        when 'var', 'em', 'i', 'u'
          write '\fI'
          inline_filter(node.children)
          write '\fR'

        when 'br'
          macro 'br'

        when 'a'
          if node.classes.include?('man-ref')
            inline_filter(node.children)
          elsif node.has_attribute?('data-bare-link')
            write '\fI'
            inline_filter(node.children)
            write '\fR'
          else
            inline_filter(node.children)
            write ' '
            write '\fI'
            write escape(node.attributes['href'])
            write '\fR'
          end
        else
          warn "unrecognized inline tag: %p", node.name
        end

      else
        fail "unexpected node: #{node.inspect}"
      end
    end

    def macro(name, value=nil)
      writeln ".\n.#{[name, value].compact.join(' ')}"
    end

    HTML_ROFF_ENTITIES = {
      '•'  => '\(bu',
      '&lt;'    => '<',
      '&gt;'    => '>',
      '&nbsp;'  => '\~',
      '&copy;'  => '\(co',
      '&rdquo;' => '\(rs',
      '&mdash;' => '\(em',
      '&reg;'   => '\(rg',
      '&sec;'   => '\(sc',
      '&ge;'    => '\(>=',
      '&le;'    => '\(<=',
      '&ne;'    => '\(!=',
      '&equiv;' => '\(=='
    }

    def escape(text)
      return text.to_s if text.nil? || text.empty?
      ent = HTML_ROFF_ENTITIES
      text = text.dup
      text.gsub!(/&#x([0-9A-Fa-f]+);/) { $1.to_i(16).chr }  # hex entities
      text.gsub!(/&#(\d+);/) { $1.to_i.chr }                # dec entities
      text.gsub!('\\', '\e')                                # backslash
      text.gsub!(/['.-]/) { |m| "\\#{m}" }                  # control chars
      text.gsub!(/(&[A-Za-z]+;)/) { ent[$1] || $1 }         # named entities
      text.gsub!('&amp;',  '&')                             # amps
      text
    end

    def quote(text)
      "\"#{text.gsub(/"/, '\\"')}\""
    end

    # write text to output buffer
    def write(text)
      return if text.nil? || text.empty?
      # lines cannot start with a '.'. insert zero-width character before.
      if text[0,2] == '\.' &&
        (@buf.last && @buf.last[-1] == ?\n)
        @buf << '\&'
      end
      @buf << text
    end

    # write text to output buffer on a new line.
    def writeln(text)
      write "\n" if @buf.last && @buf.last[-1] != ?\n
      write text
      write "\n"
    end

    def comment(text)
      writeln %[.\\" #{text}]
    end

    def warn(text, *args)
      $stderr.puts "warn: #{text}" % args
    end
  end
end