summaryrefslogtreecommitdiff
path: root/lib/rdoc/text.rb
blob: 22c3777ff910e19f0c75c7ba5506424cc228ab49 (plain)
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
285
286
287
288
289
290
291
292
293
294
295
296
297
298
# frozen_string_literal: true

##
# For RDoc::Text#to_html

require 'strscan'

##
# Methods for manipulating comment text

module RDoc::Text

  ##
  # Maps markup formats to classes that can parse them.  If the format is
  # unknown, "rdoc" format is used.

  MARKUP_FORMAT = {
    'markdown' => RDoc::Markdown,
    'rdoc'     => RDoc::Markup,
    'rd'       => RDoc::RD,
    'tomdoc'   => RDoc::TomDoc,
  }

  MARKUP_FORMAT.default = RDoc::Markup

  ##
  # Maps an encoding to a Hash of characters properly transcoded for that
  # encoding.
  #
  # See also encode_fallback.

  TO_HTML_CHARACTERS = Hash.new do |h, encoding|
    h[encoding] = {
      :close_dquote => encode_fallback('”', encoding, '"'),
      :close_squote => encode_fallback('’', encoding, '\''),
      :copyright    => encode_fallback('©', encoding, '(c)'),
      :ellipsis     => encode_fallback('…', encoding, '...'),
      :em_dash      => encode_fallback('—', encoding, '---'),
      :en_dash      => encode_fallback('–', encoding, '--'),
      :open_dquote  => encode_fallback('“', encoding, '"'),
      :open_squote  => encode_fallback('‘', encoding, '\''),
      :trademark    => encode_fallback('®', encoding, '(r)'),
    }
  end

  ##
  # Transcodes +character+ to +encoding+ with a +fallback+ character.

  def self.encode_fallback character, encoding, fallback
    character.encode(encoding, :fallback => { character => fallback },
                     :undef => :replace, :replace => fallback)
  end

  ##
  # Expands tab characters in +text+ to eight spaces

  def expand_tabs text
    expanded = []

    text.each_line do |line|
      nil while line.gsub!(/(?:\G|\r)((?:.{8})*?)([^\t\r\n]{0,7})\t/) do
        r = "#{$1}#{$2}#{' ' * (8 - $2.size)}"
        r = RDoc::Encoding.change_encoding r, text.encoding
        r
      end

      expanded << line
    end

    expanded.join
  end

  ##
  # Flush +text+ left based on the shortest line

  def flush_left text
    indent = 9999

    text.each_line do |line|
      line_indent = line =~ /\S/ || 9999
      indent = line_indent if indent > line_indent
    end

    empty = ''
    empty = RDoc::Encoding.change_encoding empty, text.encoding

    text.gsub(/^ {0,#{indent}}/, empty)
  end

  ##
  # Convert a string in markup format into HTML.
  #
  # Requires the including class to implement #formatter

  def markup text
    if @store.rdoc.options
      locale = @store.rdoc.options.locale
    else
      locale = nil
    end
    if locale
      i18n_text = RDoc::I18n::Text.new(text)
      text = i18n_text.translate(locale)
    end
    parse(text).accept formatter
  end

  ##
  # Strips hashes, expands tabs then flushes +text+ to the left

  def normalize_comment text
    return text if text.empty?

    text = strip_stars    text
    text = strip_hashes   text
    text = expand_tabs    text
    text = flush_left     text
    text = strip_newlines text
    text
  end

  ##
  # Normalizes +text+ then builds a RDoc::Markup::Document from it

  def parse text, format = 'rdoc'
    return text if RDoc::Markup::Document === text
    return text.parse if RDoc::Comment === text

    text = normalize_comment text # TODO remove, should not be necessary

    return RDoc::Markup::Document.new if text =~ /\A\n*\z/

    MARKUP_FORMAT[format].parse text
  end

  ##
  # The first +limit+ characters of +text+ as HTML

  def snippet text, limit = 100
    document = parse text

    RDoc::Markup::ToHtmlSnippet.new(options, limit).convert document
  end

  ##
  # Strips leading # characters from +text+

  def strip_hashes text
    return text if text =~ /^(?>\s*)[^\#]/

    empty = ''
    empty = RDoc::Encoding.change_encoding empty, text.encoding

    text.gsub(/^\s*(#+)/) { $1.tr '#', ' ' }.gsub(/^\s+$/, empty)
  end

  ##
  # Strips leading and trailing \n characters from +text+

  def strip_newlines text
    text.gsub(/\A\n*(.*?)\n*\z/m) do $1 end # block preserves String encoding
  end

  ##
  # Strips /* */ style comments

  def strip_stars text
    return text unless text =~ %r%/\*.*\*/%m

    encoding = text.encoding

    text = text.gsub %r%Document-method:\s+[\w:.#=!?|^&<>~+\-/*\%@`\[\]]+%, ''

    space = ' '
    space = RDoc::Encoding.change_encoding space, encoding if encoding

    text.sub!  %r%/\*+%       do space * $&.length end
    text.sub!  %r%\*+/%       do space * $&.length end
    text.gsub! %r%^[ \t]*\*%m do space * $&.length end

    empty = ''
    empty = RDoc::Encoding.change_encoding empty, encoding if encoding
    text.gsub(/^\s+$/, empty)
  end

  ##
  # Converts ampersand, dashes, ellipsis, quotes, copyright and registered
  # trademark symbols in +text+ to properly encoded characters.

  def to_html text
    html = (''.encode text.encoding).dup

    encoded = RDoc::Text::TO_HTML_CHARACTERS[text.encoding]

    s = StringScanner.new text
    insquotes = false
    indquotes = false
    after_word = nil

    until s.eos? do
      case
      when s.scan(/<(tt|code)>.*?<\/\1>/) then # skip contents of tt
        html << s.matched.gsub('\\\\', '\\')
      when s.scan(/<(tt|code)>.*?/) then
        warn "mismatched <#{s[1]}> tag" # TODO signal file/line
        html << s.matched
      when s.scan(/<[^>]+\/?s*>/) then # skip HTML tags
        html << s.matched
      when s.scan(/\\(\S)/) then # unhandled suppressed crossref
        html << s[1]
        after_word = nil
      when s.scan(/\.\.\.(\.?)/) then
        html << s[1] << encoded[:ellipsis]
        after_word = nil
      when s.scan(/\(c\)/) then
        html << encoded[:copyright]
        after_word = nil
      when s.scan(/\(r\)/) then
        html << encoded[:trademark]
        after_word = nil
      when s.scan(/---/) then
        html << encoded[:em_dash]
        after_word = nil
      when s.scan(/--/) then
        html << encoded[:en_dash]
        after_word = nil
      when s.scan(/&quot;|"/) then
        html << encoded[indquotes ? :close_dquote : :open_dquote]
        indquotes = !indquotes
        after_word = nil
      when s.scan(/``/) then # backtick double quote
        html << encoded[:open_dquote]
        after_word = nil
      when s.scan(/''/) then # tick double quote
        html << encoded[:close_dquote]
        after_word = nil
      when s.scan(/'/) then # single quote
        if insquotes
          html << encoded[:close_squote]
          insquotes = false
        elsif after_word
          # Mary's dog, my parents' house: do not start paired quotes
          html << encoded[:close_squote]
        else
          html << encoded[:open_squote]
          insquotes = true
        end

        after_word = nil
      else # advance to the next potentially significant character
        match = s.scan(/.+?(?=[<\\.("'`&-])/) #"

        if match then
          html << match
          after_word = match =~ /\w$/
        else
          html << s.rest
          break
        end
      end
    end

    html
  end

  ##
  # Wraps +txt+ to +line_len+

  def wrap(txt, line_len = 76)
    res = []
    sp = 0
    ep = txt.length

    while sp < ep
      # scan back for a space
      p = sp + line_len - 1
      if p >= ep
        p = ep
      else
        while p > sp and txt[p] != ?\s
          p -= 1
        end
        if p <= sp
          p = sp + line_len
          while p < ep and txt[p] != ?\s
            p += 1
          end
        end
      end
      res << txt[sp...p] << "\n"
      sp = p
      sp += 1 while sp < ep and txt[sp] == ?\s
    end

    res.join.strip
  end

end