Module: MaRuKu::In::Markdown::SpanLevelParser

Includes:
Helpers
Included in:
BlockLevelParser, MDDocument
Defined in:
lib/maruku.rb,
lib/maruku/attributes.rb,
lib/maruku/input/charsource.rb,
lib/maruku/input/parse_span.rb,
lib/maruku/input/html_helper.rb

Defined Under Namespace

Classes: CharSourceDebug, CharSourceManual, CharSourceStrscan, HTMLHelper, SpanContext

Constant Summary collapse

CharSource =

Choose!

CharSourceManual
EscapedCharInText =
'\\`*_{}[]()#.!|:+->'.split(//)
EscapedCharInQuotes =
EscapedCharInText + ["'", '"']
EscapedCharInInlineCode =
['\\', '`']
MaRuKu::Globals[:ignore_wikilinks]

Instance Method Summary collapse

Methods included from Helpers

#md_abbr, #md_abbr_def, #md_ald, #md_br, #md_code, #md_codeblock, #md_el, #md_em, #md_email, #md_emstrong, #md_entity, #md_foot_ref, #md_footnote, #md_header, #md_hrule, #md_html, #md_ial, #md_im_image, #md_im_link, #md_image, #md_li, #md_link, #md_par, #md_quote, #md_ref_def, #md_strong, #md_url, #md_xml_instr

Instance Method Details

#extension_meta(src, con, break_on_chars = nil) ⇒ Object


351
352
353
354
355
356
357
358
359
360
361
# File 'lib/maruku/input/parse_span.rb', line 351

def extension_meta(src, con, break_on_chars=nil)
  if m = src.read_regexp(/([^\s\:\"\'}]+?):/)
    name = m[1]
    al = read_attribute_list(src, con, break_on_chars)
    self.doc.ald[name] = al
    con.push md_ald(name, al)
  else
    al = read_attribute_list(src, con, break_on_chars)
    con.push md_ial(al)
  end
end

#interpret_extension(src, con, break_on_chars = nil) ⇒ Object

Start: cursor on character after 'End: curson on '' or EOF


330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
# File 'lib/maruku/input/parse_span.rb', line 330

def interpret_extension(src, con, break_on_chars=nil)
  case src.cur_char
  when ':'
    src.ignore_char # :
    extension_meta(src, con, break_on_chars)
  when '#', '.'
    extension_meta(src, con, break_on_chars)
  else
    stuff = read_simple(src, '}', break_on_chars)
    if stuff =~ /^(\w+\s|[^\w])/
      extension_id = $1.strip

      maruku_recover "I don't know what to do with extension '#{extension_id}'\n" +
        "I will treat this:\n\t{#{stuff}} \n as meta-data.\n", src, con
    else
      maruku_recover "I will treat this:\n\t{#{stuff}} \n as meta-data.\n", src, con
    end
    extension_meta(src, con, break_on_chars)
  end
end

#md_al(s = []) ⇒ Object


28
29
30
# File 'lib/maruku/attributes.rb', line 28

def md_al(s = [])
  AttributeList.new(s)
end

#merge_ial(elements, src, con) ⇒ Object


91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
# File 'lib/maruku/attributes.rb', line 91

def merge_ial(elements, src, con)
  # Apply each IAL to the element before
  (elements + [nil]).each_cons(3) do |before, e, after|
    next unless ial?(e)

    if before.kind_of? MDElement
      before.al = e.ial
    elsif after.kind_of? MDElement
      after.al = e.ial
    else
      maruku_error <<ERR, src, con
It's unclear which element the attribute list {:#{e.ial.to_s}}
is referring to. The element before is a #{before.class},
the element after is a #{after.class}.
  before: #{before.inspect}
  after: #{after.inspect}
ERR
    end
  end

  unless Globals[:debug_keep_ials]
    elements.delete_if {|x| ial?(x) && x != elements.first}
  end
end

#parse_span(string, parent = nil) ⇒ Object


11
12
13
14
15
# File 'lib/maruku/input/parse_span.rb', line 11

def parse_span(string, parent=nil)
  string = Array(string).join("\n") unless string.kind_of? String
  src = MaRuKu::In::Markdown::SpanLevelParser::CharSource.new(string, parent)
  read_span(src, EscapedCharInText, [nil])
end

#read_attribute_list(src, con = nil, break_on_chars = nil) ⇒ AttributeList?

Returns:


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
# File 'lib/maruku/attributes.rb', line 33

def read_attribute_list(src, con=nil, break_on_chars=nil)
  break_on_chars = Array(break_on_chars)
  separators = break_on_chars + ['=', ' ', "\t"]
  escaped = Maruku::EscapedCharInQuotes

  al = AttributeList.new
  loop do
    src.consume_whitespace
    break if break_on_chars.include? src.cur_char

    case src.cur_char
    when ':'
      src.ignore_char
    when nil
      break      # we're done here.
    when '='     # error
      src.ignore_char
      maruku_error "In attribute lists, cannot start identifier with `=`."
      tell_user "Ignoring and continuing."
    when '#'     # id definition
      src.ignore_char
      if id = read_quoted_or_unquoted(src, con, escaped, separators)
        al << [:id, id]
      else
        maruku_error 'Could not read `id` attribute.', src, con
        tell_user 'Ignoring bad `id` attribute.'
      end
    when '.'     # class definition
      src.ignore_char
      if klass = read_quoted_or_unquoted(src, con, escaped, separators)
        al << [:class, klass]
      else
        maruku_error 'Could not read `class` attribute.', src, con
        tell_user 'Ignoring bad `class` attribute.'
      end
    else
      unless key = read_quoted_or_unquoted(src, con, escaped, separators)
        maruku_error 'Could not read key or reference.'
        next
      end

      if src.cur_char != '=' && key.length > 0
        al << [:ref, key]
        next
      end

      src.ignore_char # skip the =
      if val = read_quoted_or_unquoted(src, con, escaped, separators)
        al << [key, val]
      else
        maruku_error "Could not read value for key #{key.inspect}.", src, con
        tell_user "Ignoring key #{key.inspect}"
      end
    end
  end
  al
end

#read_em(src, delim) ⇒ Object


459
460
461
462
463
464
# File 'lib/maruku/input/parse_span.rb', line 459

def read_em(src, delim)
  src.ignore_char
  children = read_span(src, EscapedCharInText, nil, delim)
  src.ignore_char
  md_em(children)
end

#read_email_el(src, con) ⇒ Object


371
372
373
374
375
376
377
378
# File 'lib/maruku/input/parse_span.rb', line 371

def read_email_el(src,con)
  src.ignore_char # leading <
  mail = read_simple(src, nil, '>')
  src.ignore_char # closing >

  address = mail.gsub(/^mailto:/, '')
  con.push_element md_email(address)
end

#read_emstrong(src, delim) ⇒ Object


473
474
475
476
477
478
# File 'lib/maruku/input/parse_span.rb', line 473

def read_emstrong(src, delim)
  src.ignore_chars(3)
  children = read_span(src, EscapedCharInText, nil, delim)
  src.ignore_chars(3)
  md_emstrong(children)
end

#read_footnote_ref(src, con) ⇒ Object


490
491
492
493
# File 'lib/maruku/input/parse_span.rb', line 490

def read_footnote_ref(src,con)
  ref = read_ref_id(src,con)
  con.push_element md_foot_ref(ref)
end

#read_image(src, con) ⇒ Object

read link


624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
# File 'lib/maruku/input/parse_span.rb', line 624

def read_image(src, con)
  src.ignore_chars(2) # opening "!["
  alt_text = read_span(src, EscapedCharInText, ']')
  src.ignore_char # closing bracket
  # ignore space
  if src.cur_char == ' ' && ['[', '('].include?(src.next_char)
    src.ignore_char
  end
  case src.cur_char
  when '('
    src.ignore_char # opening (
    src.consume_whitespace
    url = read_url(src, [' ', "\t", ')'])
    unless url
      maruku_error "Could not read url from #{src.cur_chars(10).inspect}", src, con
    end
    src.consume_whitespace
    title = nil
    if src.cur_char != ')' # we have a title
      quote_char = src.cur_char
      title = read_quoted(src, con)
      if !title
        maruku_error 'Must quote title', src, con
      else
        # Tries to read a title with quotes: ![a](url "ti"tle")
        # this is the most ugly thing in Markdown
        if !src.next_matches(/\s*\)/)
          # if there is not a closing par ), then read
          # the rest and guess it's title with quotes
          rest = read_simple(src, nil, ')', nil)
          # chop the closing char
          rest.chop!
          title << quote_char << rest
        end
      end
    end
    src.consume_whitespace
    closing = src.shift_char # closing )
    if closing != ')'
      maruku_error "Unclosed link: '#{closing}'" +
        " Read url=#{url.inspect} title=#{title.inspect}", src, con
    end
    con.push_element md_im_image(alt_text, url, title)
  when '[' # link ref
    ref_id = read_ref_id(src, con)
    if !ref_id # TODO: check around
      maruku_error 'Reference not closed.', src, con
      ref_id = ""
    end

    con.push_element md_image(alt_text, ref_id)
  else # no stuff
    ref_id = alt_text.join
    con.push_element md_image(alt_text, ref_id)
  end
end

#read_inline_code(src, con) ⇒ Object


521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
# File 'lib/maruku/input/parse_span.rb', line 521

def read_inline_code(src, con)
  # Count the number of ticks
  num_ticks = 0
  while src.cur_char == '`'
    num_ticks += 1
    src.ignore_char
  end
  # We will read until this string
  end_string = "`" * num_ticks

  # Try to handle empty single-ticks
  if num_ticks > 1 && !src.next_matches(/.*#{Regexp.escape(end_string)}/)
    con.push_element md_entity('ldquo')
    src.ignore_chars(2)
    return
  end

  code = read_simple(src, nil, nil, end_string)

  # We didn't find a closing batch!
  if !code || src.cur_char != '`'
    con.push_element(end_string + (code || '')) and return
  end

  #   puts "Now I expects #{num_ticks} ticks: #{src.cur_chars(10).inspect}"
  src.ignore_chars num_ticks

  # Ignore at most one space
  if num_ticks > 1 && code[0, 1] == ' '
    code = code[1..-1]
  end

  # drop last space
  if num_ticks > 1 && code[-1, 1] == ' '
    code = code[0..-2]
  end

  #   puts "Read `` code: #{code.inspect}; after: #{src.cur_chars(10).inspect} "
  con.push_element md_code(code)
end

#read_inline_html(src, con) ⇒ Object


495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
# File 'lib/maruku/input/parse_span.rb', line 495

def read_inline_html(src, con)
  h = HTMLHelper.new
  begin
    # This is our current buffer in the context
    next_stuff = src.current_remaining_buffer

    consumed = 0
    while true
      if consumed >= next_stuff.size
        maruku_error "Malformed HTML starting at #{next_stuff.inspect}", src, con
        break
      end

      h.eat_this next_stuff[consumed].chr
      consumed += 1
      break if h.is_finished?
    end
    src.ignore_chars(consumed)
    con.push_element md_html(h.stuff_you_read)
  rescue => e
    maruku_error "Bad html: \n" +
      e.inspect.gsub(/^/, '>'), src, con, "I will try to continue after bad HTML."
    con.push_char src.shift_char
  end
end

562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
# File 'lib/maruku/input/parse_span.rb', line 562

def read_link(src, con)
  # we read the string and see what happens
  src.ignore_char # opening bracket
  children = read_span(src, EscapedCharInText, ']')
  src.ignore_char # closing bracket

  # ignore space
  if src.cur_char == ' ' && ['[', '('].include?(src.next_char)
    src.shift_char
  end

  case src.cur_char
  when '('
    src.ignore_char # opening (
    src.consume_whitespace
    url = read_url(src, [' ', "\t", ")"]) || ''

    src.consume_whitespace
    title = nil
    if src.cur_char != ')' # we have a title
      quote_char = src.cur_char
      title = read_quoted(src, con)

      if not title
        maruku_error 'Must quote title', src, con
      else
        # Tries to read a title with quotes: ![a](url "ti"tle")
        # this is the most ugly thing in Markdown
        unless src.next_matches(/\s*\)/)
          # if there is not a closing par ), then read
          # the rest and guess it's title with quotes
          rest = read_simple(src, nil, ')', nil)
          # chop the closing char
          rest.chop!
          title << quote_char << rest
        end
      end
    end
    src.consume_whitespace
    closing = src.shift_char # closing )
    if closing != ')'
      maruku_error 'Unclosed link', src, con, "No closing ): I will not create" +
        " the link for #{children.inspect}"
      con.push_elements children
      return
    end
    con.push_element md_im_link(children, url, title)
  when '[' # link ref
    ref_id = read_ref_id(src, con)
    if ref_id
      con.push_element md_link(children, ref_id)
    else
      maruku_error "Could not read ref_id", src, con, "I will not create the link for " +
        "#{children.inspect}"
      con.push_elements children
      return
    end
  else # empty [link]
    con.push_element md_link(children, nil)
  end
end

#read_quoted(src, con) ⇒ Object

Tries to read a quoted value. If stream does not start with ' or “, returns nil.


407
408
409
410
411
412
413
414
415
416
417
# File 'lib/maruku/input/parse_span.rb', line 407

def read_quoted(src, con)
  case src.cur_char
  when "'", '"'
    quote_char = src.shift_char # opening quote
    string = read_simple(src, EscapedCharInQuotes, quote_char)
    src.ignore_char # closing quote
    string
  else
    nil
  end
end

#read_quoted_or_unquoted(src, con, escaped, exit_on_chars) ⇒ Object


396
397
398
399
400
401
402
403
# File 'lib/maruku/input/parse_span.rb', line 396

def read_quoted_or_unquoted(src, con, escaped, exit_on_chars)
  case src.cur_char
  when "'", '"'
    read_quoted(src, con)
  else
    read_simple(src, escaped, exit_on_chars, nil, false)
  end
end

#read_ref_id(src, con) ⇒ Object

Reads a bracketed id “[refid]”. Consumes also both brackets.


481
482
483
484
485
486
487
488
# File 'lib/maruku/input/parse_span.rb', line 481

def read_ref_id(src, con)
  src.ignore_char # [
  if m = src.read_regexp(/([^\]]*?)\]/)
    m[1]
  else
    nil
  end
end

#read_simple(src, escaped, exit_on_chars = nil, exit_on_strings = nil, warn = true) ⇒ Object

Reads a simple string (no formatting) until one of exit_on_chars, while escaping the escaped. If the string is empty, it returns nil. By default, raises on error if the string terminates unexpectedly. This can be by setting the last argument to false.


424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
# File 'lib/maruku/input/parse_span.rb', line 424

def read_simple(src, escaped, exit_on_chars=nil, exit_on_strings=nil, warn=true)
  text = ""
  escaped = Array(escaped)
  exit_on_chars = Array(exit_on_chars)
  exit_on_strings = Array(exit_on_strings)
  while true
    c = src.cur_char

    break if exit_on_chars.include?(c)
    break if exit_on_strings.any? {|x| src.cur_chars_are x }

    case c
    when nil
      if warn
        maruku_error "String finished while reading (break on " +
          "#{(exit_on_chars + exit_on_strings).inspect})" +
          " already read: #{text.inspect}", src
      end
      break
    when "\\"
      d = src.next_char
      if escaped.include? d
        src.ignore_chars(2)
        text << d
      else
        text << src.shift_char
      end
    else
      text << src.shift_char
    end
  end

  text.empty? ? nil : text
end

#read_span(src, escaped, exit_on_chars = nil, exit_on_strings = nil) ⇒ Object

This is the main loop for reading span elements

It's long, but not complex or difficult to understand.


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
299
300
301
302
303
304
# File 'lib/maruku/input/parse_span.rb', line 22

def read_span(src, escaped, exit_on_chars=nil, exit_on_strings=nil)
  escaped = Array(escaped)
  con = SpanContext.new
  dquote_state = squote_state = :closed
  c = d = prev_char = nil
  while true
    c = src.cur_char

    # This is only an optimization which cuts 50% of the time used.
    # (but you can't use a-zA-z in exit_on_chars)
    if c && c =~  /[[:alnum:]]/
      con.push_char src.shift_char
      prev_char = c
      next
    end

    break if Array(exit_on_chars).include?(c)
    if Array(exit_on_strings).any? {|x| src.cur_chars_are x }
      # Special case: bold nested in italic
      break unless !(['*', '_'] & Array(exit_on_strings)).empty? &&
        ['**', '__'].include?(src.cur_chars(2)) &&
        !['***', '___'].include?(src.cur_chars(3))
    end

    # check if there are extensions
    next if check_span_extensions(src, con)

    case c = src.cur_char
    when ' '
      if src.cur_chars_are "  \n"
        src.ignore_chars(3)
        con.push_element md_br
        prev_char = ' '
        next
      elsif src.cur_chars_are ' >>' # closing guillemettes
        src.ignore_chars(3)
        con.push_element md_entity('nbsp')
        con.push_element md_entity('raquo')
      elsif src.cur_chars(5) =~ / '\d\ds/ # special case: '80s
        src.ignore_chars(2)
        con.push_space
        con.push_element md_entity('rsquo')
      elsif src.cur_chars_are " '" # opening single-quote
        src.ignore_chars(2)
        con.push_space
        con.push_element md_entity('lsquo')
        squote_state = :open
      else
        src.ignore_char
        con.push_space
      end
    when "\n", "\t"
      src.ignore_char
      con.push_space
    when '`'
      read_inline_code(src, con)
    when '<'
      # It could be:
      # 1) HTML "<div ..."
      # 2) HTML "<!-- ..."
      # 3) url "<http:// ", "<ftp:// ..."
      # 4) email "<[email protected] ", "<mailto:[email protected]"
      # 5) on itself! "a < b  "
      # 6) Start of <<guillemettes>>

      case d = src.next_char
      when '<'  # guillemettes
        if src.cur_chars_are '<< '
          src.ignore_chars(3)
          con.push_element md_entity('laquo')
          con.push_element md_entity('nbsp')
        else
          src.ignore_chars(2)
          con.push_element md_entity('laquo')
        end
      when '!'
        if src.cur_chars_are '<!--'
          read_inline_html(src, con)
        else
          con.push_char src.shift_char
        end
      when '?'
        read_xml_instr_span(src, con)
      when ' ', "\t"
        con.push_char src.shift_char
      else
        if src.next_matches(/<mailto:/) ||
            src.next_matches(/<[\w\.]+\@/)
          read_email_el(src, con)
        elsif src.next_matches(/<\w+:/)
          read_url_el(src, con)
        elsif src.next_matches(/<\w/)
          #puts "This is HTML: #{src.cur_chars(20)}"
          read_inline_html(src, con)
        else
          #puts "This is NOT HTML: #{src.cur_chars(20)}"
          con.push_char src.shift_char
        end
      end
    when '>'
      if src.next_char == '>'
        src.ignore_chars(2)
        con.push_element md_entity('raquo')
      else
        con.push_char src.shift_char
      end
    when "\\"
      d = src.next_char
      if d == "'"
        src.ignore_chars(2)
        con.push_element md_entity('apos')
      elsif d == '"'
        src.ignore_chars(2)
        con.push_element md_entity('quot')
      elsif escaped.include? d
        src.ignore_chars(2)
        con.push_char d
      else
        con.push_char src.shift_char
      end
    when '['
      if markdown_extra? && src.next_char == '^'
        read_footnote_ref(src,con)
      elsif IgnoreWikiLinks && src.next_char == '['
        con.push_char src.shift_char
        con.push_char src.shift_char
      else
        read_link(src, con)
      end
    when '!'
      if src.next_char == '['
        read_image(src, con)
      else
        con.push_char src.shift_char
      end
    when '&'
      # named references
      if m = src.read_regexp(/\&(\w+);/)
        con.push_element md_entity(m[1])
        # numeric
      elsif m = src.read_regexp(/\&\#(x)?(\w+);/)
        num = m[1] ? m[2].hex : m[2].to_i
        con.push_element md_entity(num)
      else
        con.push_char src.shift_char
      end
    when '*'
      if !src.next_char
        maruku_error "Opening * as last char.", src, con, 'Treating as literal'
        con.push_char src.shift_char
      else
        follows = src.cur_chars(4)
        if follows =~ /^\*\*\*[^\s\*]/
          con.push_element read_emstrong(src, '***')
        elsif follows  =~ /^\*\*[^\s\*]/
          con.push_element read_strong(src, '**')
        elsif follows =~ /^\*[^\s\*]/
          con.push_element read_em(src, '*')
        else # * is just a normal char
          con.push_char src.shift_char
        end
      end
    when '_'
      if !src.next_char
        maruku_error "Opening _ as last char", src, con, 'Treating as literal'
        con.push_char src.shift_char
      else
        # we don't want "mod_ruby" to start an emphasis
        # so we start one only if
        # 1) there's nothing else in the span (first char)
        # or 2) the last char was a space
        # or 3) the current string is empty
        #if con.elements.empty? ||
        if con.is_end?
          # also, we check the next characters
          follows = src.cur_chars(4)
          if  follows =~ /^\_\_\_[^\s\_]/
            con.push_element read_emstrong(src, '___')
          elsif follows  =~ /^\_\_[^\s\_]/
            con.push_element read_strong(src, '__')
          elsif follows =~ /^\_[^\s\_]/
            con.push_element read_em(src, '_')
          else # _ is just a normal char
            con.push_char src.shift_char
          end
        else
          # _ is just a normal char
          con.push_char src.shift_char
        end
      end
    when '{' # extension
      if ['#', '.', ':'].include? src.next_char
        src.ignore_char # {
        interpret_extension(src, con, '}')
        src.ignore_char # }
      else
        con.push_char src.shift_char
      end
    when nil
      maruku_error( ("Unclosed span (waiting for %s" +
                     "#{exit_on_strings.inspect})") %
                    [ exit_on_chars ? "#{exit_on_chars.inspect} or" : "" ],
                    src, con)
      break
    when '-' # dashes
      if src.next_char == '-'
        if src.cur_chars_are '---'
          src.ignore_chars(3)
          con.push_element md_entity('mdash')
        else
          src.ignore_chars(2)
          con.push_element md_entity('ndash')
        end
      else
        con.push_char src.shift_char
      end
    when '.' # ellipses
      if src.cur_chars_are '...'
        src.ignore_chars(3)
        con.push_element md_entity('hellip')
      elsif src.cur_chars_are '. . .'
        src.ignore_chars(5)
        con.push_element md_entity('hellip')
      else
        con.push_char src.shift_char
      end
    when '"'
      if dquote_state == :closed
        dquote_state = :open
        src.ignore_char
        con.push_element md_entity('ldquo')
      else
        dquote_state = :closed
        src.ignore_char
        con.push_element md_entity('rdquo')
      end
    when "'"
      if src.cur_chars(4) =~ /'\d\ds/ # special case: '80s
        src.ignore_char
        con.push_element md_entity('rsquo')
      elsif squote_state == :open
        squote_state = :closed unless src.next_char =~ /[[:alpha:]]/
        src.ignore_char
        con.push_element md_entity('rsquo')
      else
        if prev_char =~ /[[:alpha:]]/
          src.ignore_char
          con.push_element md_entity('rsquo')
        else
          src.ignore_char
          con.push_element md_entity('lsquo')
          squote_state = :open
        end
      end
    else # normal text
      con.push_char src.shift_char
    end # end case
    prev_char = c
  end # end while true

  con.push_string_if_present

  # Assign IAL to elements
  merge_ial(con.elements, src, con)

  # Remove leading space
  if (s = con.elements.first).kind_of? String
    if s[0, 1] == ' '
      con.elements[0] = s[1..-1]
    end
    con.elements.shift if s.empty?
  end
  
  con.elements.shift if (con.elements.first.kind_of?(String) && con.elements.first.empty?)

  # Remove final spaces
  if (s = con.elements.last).kind_of? String
    s.chop! if s[-1, 1] == ' '
    con.elements.pop if s.empty?
  end

  con.elements
end

#read_strong(src, delim) ⇒ Object


466
467
468
469
470
471
# File 'lib/maruku/input/parse_span.rb', line 466

def read_strong(src, delim)
  src.ignore_chars(2)
  children = read_span(src, EscapedCharInText, nil, delim)
  src.ignore_chars(2)
  md_strong(children)
end

#read_url(src, break_on) ⇒ Object


380
381
382
383
384
385
386
387
388
389
390
391
392
393
# File 'lib/maruku/input/parse_span.rb', line 380

def read_url(src, break_on)
  if ["'", '"'].include? src.cur_char
    maruku_error 'Invalid char for url', src
  end

  url = read_simple(src, nil, break_on) || ''

  if url[0, 1] == '<' && url[-1, 1] == '>'
    url = url[1, url.size-2]
  end

  return nil if url.empty?
  url
end

#read_url_el(src, con) ⇒ Object


363
364
365
366
367
368
369
# File 'lib/maruku/input/parse_span.rb', line 363

def read_url_el(src,con)
  src.ignore_char # leading <
  url = read_simple(src, nil, '>')
  src.ignore_char # closing >

  con.push_element md_url(url)
end

#read_xml_instr_span(src, con) ⇒ Object


307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
# File 'lib/maruku/input/parse_span.rb', line 307

def read_xml_instr_span(src, con)
  src.ignore_chars(2) # starting <?

  # read target <?target code... ?>
  target = if m = src.read_regexp(/^(\w+)/)
             m[1]
           else
             # XML instructions are invalid without a target
             ''
           end

  delim = "?>"

  code = read_simple(src, nil, nil, delim)

  src.ignore_chars delim.size

  code = (code || "").strip
  con.push_element md_xml_instr(target, code)
end