Class: Mdlint::Parser::BlockParser

Inherits:
Object
  • Object
show all
Defined in:
lib/mdlint/parser/block_parser.rb,
sig/internal.rbs

Constant Summary collapse

ATX_HEADING_REGEXP = 
/\A {0,3}(\#{1,6})(?:\s+(.*))?$/
SETEXT_HEADING_REGEXP = 
/\A {0,3}(=+|-+)\s*\z/
FENCE_OPEN_REGEXP = 
/\A {0,3}(`{3,}|~{3,})(.*)\z/
BLOCKQUOTE_REGEXP = 
/\A {0,3}> ?/
HR_REGEXP = 
/\A {0,3}([-*_])(?:\s*\1){2,}\s*\z/
BULLET_LIST_REGEXP = 
/\A( {0,3})([-*+])\s+/
ORDERED_LIST_REGEXP = 
/\A( {0,3})(\d{1,9})([.)])\s+/
CODE_BLOCK_INDENT = 
/\A {4}/
HTML_BLOCK_START_1 = 
/\A {0,3}<(script|pre|style|textarea)(?:[\s>]|\z)/i
HTML_BLOCK_START_2 = 
/\A {0,3}<!--/
HTML_BLOCK_START_3 = 
/\A {0,3}<\?/
HTML_BLOCK_START_4 = 
/\A {0,3}<![A-Z]/
HTML_BLOCK_START_5 = 
/\A {0,3}<!\[CDATA\[/
HTML_BLOCK_START_6 = 
/\A {0,3}<\/?(?:address|article|aside|base|basefont|blockquote|body|caption|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption|figure|footer|form|frame|frameset|h1|h2|h3|h4|h5|h6|head|header|hr|html|iframe|legend|li|link|main|menu|menuitem|nav|noframes|ol|optgroup|option|p|param|search|section|summary|table|tbody|td|tfoot|th|thead|title|tr|track|ul)(?:\s|\/?>|$)/i
HTML_BLOCK_START_7 = 
/\A {0,3}<\/?[A-Za-z][A-Za-z0-9]*(?:\.[A-Za-z0-9_-]+)?(?:\s[^>]*>|\/?>)\s*\z/
REFERENCE_DEF_REGEXP =

Reference definition: [label]: url "title"

/\A {0,3}\[((?:\\.|[^\]])+)\]:/
FOOTNOTE_DEF_REGEXP = 
/\A {0,3}\[\^([^\]]+)\]:\s*(.*?)\s*$/
MATH_BLOCK_REGEXP = 
/\A {0,3}\$\$\s*$/

Instance Method Summary collapse

Constructor Details

#initialize(options = {}) ⇒ BlockParser

Returns a new instance of BlockParser.

Parameters:

  • options (Object) (defaults to: {}) 


29
30
31
32
 
# File 'lib/mdlint/parser/block_parser.rb', line 29

def initialize(options = {})
  @options = options
  @dialect = Dialect.resolve(options[:dialect])
end

Instance Method Details

#alert_attributes(content_lines) ⇒ Object

Parameters:

  • content_lines (Object)

Returns:

  • (Object) 


1074
1075
1076
1077
 
# File 'lib/mdlint/parser/block_parser.rb', line 1074

def alert_attributes(content_lines)
  match = content_lines.first.to_s.match(/\A\[!(NOTE|TIP|IMPORTANT|WARNING|CAUTION)\]\s*/i)
  match ? { alert: match[1].downcase } : {}
end

#append_loose_paragraph(state, content, start_line) ⇒ Object

Parameters:

  • state (Object)
  • content (Object)
  • start_line (Object)

Returns:

  • (Object) 


763
764
765
766
767
768
769
 
# File 'lib/mdlint/parser/block_parser.rb', line 763

def append_loose_paragraph(state, content, start_line)
  return if content.to_s.empty?

  state.tokens << Token.new(type: :paragraph_open, tag: "p", nesting: 1, level: state.level, map: [start_line, state.line])
  state.tokens << Token.new(type: :inline, content: content, level: state.level + 1, map: [start_line, state.line])
  state.tokens << Token.new(type: :paragraph_close, tag: "p", nesting: -1, level: state.level)
end

#append_nested_tokens(state, nested_lines, start_line) ⇒ Object

Parameters:

  • state (Object)
  • nested_lines (Object)
  • start_line (Object)

Returns:

  • (Object) 


709
710
711
712
713
714
715
716
717
718
 
# File 'lib/mdlint/parser/block_parser.rb', line 709

def append_nested_tokens(state, nested_lines, start_line)
  return if nested_lines.empty?

  nested_tokens = BlockParser.new(@options).parse(nested_lines.join("\n"))
  nested_tokens.each do |token|
    token.level += state.level
    token.map = token.map.map { |line| line + start_line } if token.map
    state.tokens << token
  end
end

#block_boundary?(line) ⇒ Boolean

Parameters:

  • line (Object)

Returns:

  • (Boolean) 


1079
1080
1081
1082
1083
1084
 
# File 'lib/mdlint/parser/block_parser.rb', line 1079

def block_boundary?(line)
  line.match?(ATX_HEADING_REGEXP) || fence_match(line) ||
    line.match?(HR_REGEXP) || line.match?(BLOCKQUOTE_REGEXP) ||
    line.match?(BULLET_LIST_REGEXP) || line.match?(ORDERED_LIST_REGEXP) ||
    line.match?(REFERENCE_DEF_REGEXP) || line.match?(FOOTNOTE_DEF_REGEXP)
end

#collect_loose_item_content(state, pattern, base_indent, nested_lines = nil, content_indent = base_indent + 2) ⇒ Object

Parameters:

  • state (Object)
  • pattern (Object)
  • base_indent (Object)
  • nested_lines (Object) (defaults to: nil)
  • content_indent (Object) (defaults to: base_indent + 2)

Returns:

  • (Object) 


720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
 
# File 'lib/mdlint/parser/block_parser.rb', line 720

def collect_loose_item_content(state, pattern, base_indent, nested_lines = nil, content_indent = base_indent + 2)
  return unless state.blank_line?

  state.skip_blank_lines
  return if state.eof?

  next_match = state.current_line.match(pattern)
  if next_match && next_match[1].length <= base_indent
    mark_current_list_loose(state)
    return
  end
  return unless state.current_line.match?(/\A {#{content_indent},}/)

  mark_current_list_loose(state)
  if state.current_line.match?(/\A {#{base_indent + 4},}/) && nested_lines
    while !state.eof?
      if state.blank_line?
        index = state.line
        index += 1 while index < state.lines.length && state.blank_line?(index)
        break if index >= state.lines.length || !state.lines[index].match?(/\A\s+/)

        nested_lines << ""
        state.next_line
      elsif state.current_line.match?(/\A\s+/)
        nested_lines << dedent_list_line(state.current_line, base_indent)
        state.next_line
      else
        break
      end
    end
    return nil
  end

  content_lines = []
  while !state.eof? && !state.blank_line? && !state.current_line.match?(pattern)
    break unless state.current_line.match?(/\A {#{content_indent},}/)

    content_lines << state.raw_line.sub(/\A\s+/, "")
    state.next_line
  end
  content_lines.join("\n").strip
end

#dedent_list_line(line, base_indent) ⇒ String

Parameters:

  • line (Object)
  • base_indent (Object)

Returns:

  • (String) 


705
706
707
 
# File 'lib/mdlint/parser/block_parser.rb', line 705

def dedent_list_line(line, base_indent)
  line[(base_indent + 2)..] || line.lstrip
end

#fence_match(line) ⇒ Object

Parameters:

  • line (Object)

Returns:

  • (Object) 


1117
1118
1119
1120
1121
1122
1123
 
# File 'lib/mdlint/parser/block_parser.rb', line 1117

def fence_match(line)
  match = line.to_s.match(FENCE_OPEN_REGEXP)
  return unless match
  return if match[1].start_with?("`") && match[2].include?("`")

  match
end

#find_directive_closing_line(state, name) ⇒ Object

Parameters:

  • state (Object)
  • name (Object)

Returns:

  • (Object) 


1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
 
# File 'lib/mdlint/parser/block_parser.rb', line 1086

def find_directive_closing_line(state, name)
  depth = 1
  index = state.line + 1
  while index < state.lines.length
    candidate = state.lines[index]
    nested = candidate.match(/\A {0,3}:::([A-Za-z][\w-]*)(?:\s+.*)?\s*\z/)
    if nested
      depth += 1
    elsif candidate.strip == ":::"
      depth -= 1
      return index if depth.zero?
    end
    index += 1
  end
  nil
end

#front_matter_markers(opener) ⇒ Object

Parameters:

  • opener (Object)

Returns:

  • (Object) 


206
207
208
209
210
211
212
213
214
215
216
217
 
# File 'lib/mdlint/parser/block_parser.rb', line 206

def front_matter_markers(opener)
  case opener.strip
  when "---"
    [:yaml, "---"]
  when "+++"
    [:toml, "+++"]
  when ";;;"
    [:json, ";;;"]
  when "{"
    [:json, "}"]
  end
end

#front_matter_payload?(format, lines) ⇒ Boolean

Parameters:

  • format (Object)
  • lines (Object)

Returns:

  • (Boolean) 


1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
 
# File 'lib/mdlint/parser/block_parser.rb', line 1125

def front_matter_payload?(format, lines)
  return false if lines.empty? || lines.all? { |line| line.strip.empty? }

  case format
  when :yaml
    lines.any? { |line| line.match?(/\A\s*[^#\s][^:]*:/) }
  when :toml
    lines.any? { |line| line.match?(/\A\s*[^#\s=]+\s*=/) }
  when :json
    lines.join.match?(/[{}\[\]]|\A\s*\"[^\"]+\"\s*:/)
  else
    false
  end
end

#html_block_start?(line) ⇒ Boolean

Parameters:

  • line (Object)

Returns:

  • (Boolean) 


838
839
840
841
 
# File 'lib/mdlint/parser/block_parser.rb', line 838

def html_block_start?(line)
  [HTML_BLOCK_START_1, HTML_BLOCK_START_2, HTML_BLOCK_START_3, HTML_BLOCK_START_4,
   HTML_BLOCK_START_5, HTML_BLOCK_START_6, HTML_BLOCK_START_7].any? { |pattern| line.match?(pattern) }
end

#lazy_blockquote_continuation?(line) ⇒ Boolean

Parameters:

  • line (Object)

Returns:

  • (Boolean) 


843
844
845
846
847
848
 
# File 'lib/mdlint/parser/block_parser.rb', line 843

def lazy_blockquote_continuation?(line)
  !line.match?(ATX_HEADING_REGEXP) && !fence_match(line) && !line.match?(HR_REGEXP) &&
    !line.match?(BLOCKQUOTE_REGEXP) && !line.match?(BULLET_LIST_REGEXP) &&
    !line.match?(ORDERED_LIST_REGEXP) && !html_block_start?(line) &&
    !line.match?(REFERENCE_DEF_REGEXP) && !line.match?(FOOTNOTE_DEF_REGEXP)
end

#mark_current_list_loose(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


771
772
773
774
775
776
777
778
779
780
 
# File 'lib/mdlint/parser/block_parser.rb', line 771

def mark_current_list_loose(state)
  list_index = state.tokens.rindex { |token| %i[bullet_list_open ordered_list_open].include?(token.type) }
  return unless list_index

  state.tokens[list_index].attrs[:tight] = false
  state.tokens[(list_index + 1)..].to_a.reverse_each do |token|
    break if %i[bullet_list_open ordered_list_open].include?(token.type)
    token.attrs[:tight] = false if token.type == :list_item_open
  end
end

#normalize_reference_label(label) ⇒ String

Parameters:

  • label (Object)

Returns:

  • (String) 


934
935
936
 
# File 'lib/mdlint/parser/block_parser.rb', line 934

def normalize_reference_label(label)
  label.to_s.gsub(/\\([!"#$%&'()*+,\-.\/:;<=>?@\[\\\]^_`{|}~])/, '\\1').gsub(/\s+/, " ").strip.downcase
end

#parse(src) ⇒ Object

Parameters:

  • src (Object)

Returns:

  • (Object) 


34
35
36
37
38
39
40
41
42
 
# File 'lib/mdlint/parser/block_parser.rb', line 34

def parse(src)
  state = State.new(src)

  until state.eof?
    parse_block(state)
  end

  state.tokens
end

#parse_atx_heading(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


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
 
# File 'lib/mdlint/parser/block_parser.rb', line 226

def parse_atx_heading(state)
  line = state.current_line
  match = line.match(ATX_HEADING_REGEXP)
  return false unless match

  level = match[1].length
  content = match[2].to_s.gsub(/\s+#+\s*\z/, "").strip
  content = "" if content.match?(/\A#+\s*\z/)

  start_line = state.line

  state.tokens << Token.new(
    type: :heading_open,
    tag: "h#{level}",
    nesting: 1,
    level: state.level,
    markup: "#" * level,
    map: [start_line, start_line + 1]
  )

  inline_token = Token.new(
    type: :inline,
    content: content,
    level: state.level + 1,
    map: [start_line, start_line + 1]
  )
  state.tokens << inline_token

  state.tokens << Token.new(
    type: :heading_close,
    tag: "h#{level}",
    nesting: -1,
    level: state.level,
    markup: "#" * level
  )

  state.next_line
  true
end

#parse_blank_line(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


219
220
221
222
223
224
 
# File 'lib/mdlint/parser/block_parser.rb', line 219

def parse_blank_line(state)
  return false unless state.blank_line?

  state.next_line
  true
end

#parse_block(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
 
# File 'lib/mdlint/parser/block_parser.rb', line 46

def parse_block(state)
  return if state.eof?

  parse_front_matter(state) ||
    parse_blank_line(state) ||
    parse_atx_heading(state) ||
    parse_directive(state) ||
    parse_math_block(state) ||
    parse_fence(state) ||
    parse_hr(state) ||
    parse_blockquote(state) ||
    parse_bullet_list(state) ||
    parse_ordered_list(state) ||
    parse_table(state) ||
    parse_html_block(state) ||
    parse_footnote_definition(state) ||
    parse_reference_definition(state) ||
    parse_code_block(state) ||
    parse_setext_heading(state) ||
    parse_paragraph(state)
end

#parse_blockquote(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
 
# File 'lib/mdlint/parser/block_parser.rb', line 369

def parse_blockquote(state)
  line = state.current_line
  return false unless line.match?(BLOCKQUOTE_REGEXP)

  start_line = state.line
  content_lines = []

  while !state.eof?
    if state.current_line.match?(BLOCKQUOTE_REGEXP)
      content_lines << state.raw_line.sub(BLOCKQUOTE_REGEXP, "")
      state.next_line
    elsif !state.blank_line? && lazy_blockquote_continuation?(state.current_line)
      content_lines << state.raw_line.sub(/\A\s+/, "")
      state.next_line
    else
      break
    end
  end

  state.tokens << Token.new(
    type: :blockquote_open,
    tag: "blockquote",
    nesting: 1,
    level: state.level,
    markup: ">",
    attrs: alert_attributes(content_lines),
    map: [start_line, state.line]
  )

  content_lines[0] = content_lines[0].sub(/\A\[!(?:NOTE|TIP|IMPORTANT|WARNING|CAUTION)\]\s*/i, "") if alert_attributes(content_lines)[:alert]

  state.level += 1
  inner_content = content_lines.join("\n")
  inner_parser = BlockParser.new(@options)
  inner_tokens = inner_parser.parse(inner_content)

  inner_tokens.each do |token|
    token.level += state.level
    if token.map
      token.map = token.map.map { |l| l + start_line }
    end
    state.tokens << token
  end

  state.level -= 1

  state.tokens << Token.new(
    type: :blockquote_close,
    tag: "blockquote",
    nesting: -1,
    level: state.level,
    markup: ">"
  )

  true
end

#parse_bullet_list(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


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
458
459
460
 
# File 'lib/mdlint/parser/block_parser.rb', line 426

def parse_bullet_list(state)
  line = state.current_line
  match = line.match(BULLET_LIST_REGEXP)
  return false unless match

  marker = match[2]
  start_line = state.line

  state.tokens << Token.new(
    type: :bullet_list_open,
    tag: "ul",
    nesting: 1,
    level: state.level,
    markup: marker,
    attrs: { tight: true },
    map: [start_line, nil]
  )
  list_token_index = state.tokens.length - 1

  state.level += 1
  parse_list_items(state, BULLET_LIST_REGEXP, marker, match[1].length)
  state.level -= 1

  state.tokens[list_token_index].map[1] = state.line

  state.tokens << Token.new(
    type: :bullet_list_close,
    tag: "ul",
    nesting: -1,
    level: state.level,
    markup: marker
  )

  true
end

#parse_code_block(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
 
# File 'lib/mdlint/parser/block_parser.rb', line 850

def parse_code_block(state)
  return false unless state.current_line.match?(CODE_BLOCK_INDENT)

  start_line = state.line
  content_lines = []

  while !state.eof?
    if state.current_line.match?(CODE_BLOCK_INDENT)
      content_lines << strip_code_indent(state.raw_line, state.current_line)
      state.next_line
    elsif state.blank_line? && state.line < state.lines.length - 1
      content_lines << ""
      state.next_line
    else
      break
    end
  end
  content_lines.pop while content_lines.last == ""

  state.tokens << Token.new(
    type: :code_block,
    tag: "code",
    content: content_lines.join("\n") + "\n",
    map: [start_line, state.line]
  )

  true
end

#parse_directive(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
 
# File 'lib/mdlint/parser/block_parser.rb', line 68

def parse_directive(state)
  line = state.current_line
  match = line.match(/\A {0,3}:::([A-Za-z][\w-]*)(?:\s+(.*?))?\s*\z/)
  return false unless match

  closing_line = find_directive_closing_line(state, match[1])
  return false unless closing_line

  start_line = state.line
  content = state.raw_lines[start_line..closing_line].join("\n")
  content += "\n" if closing_line < state.lines.length - 1 || state.src.end_with?("\n")
  state.tokens << Token.new(
    type: :directive,
    content: content,
    meta: { name: match[1], title: match[2] },
    map: [start_line, closing_line + 1]
  )
  state.line = closing_line + 1
  true
end

#parse_fence(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
 
# File 'lib/mdlint/parser/block_parser.rb', line 314

def parse_fence(state)
  line = state.current_line
  match = fence_match(line)
  return false unless match

  marker = match[1]
  info = match[2].strip

  fence_char = marker[0]
  fence_length = marker.length
  opening_indent = line[/\A */].length
  start_line = state.line
  state.next_line

  content_lines = []
  until state.eof?
    current = state.current_line
    break if state.line == state.lines.length - 1 && current.empty?

    close_match = current.match(/\A {0,3}#{fence_char}{#{fence_length},}\s*\z/)
    if close_match
      state.next_line
      break
    end
    content_lines << strip_fence_indent(state.raw_line, opening_indent)
    state.next_line
  end

  state.tokens << Token.new(
    type: :fence,
    tag: "code",
    content: content_lines.join("\n") + (content_lines.any? ? "\n" : ""),
    markup: marker,
    info: info,
    map: [start_line, state.line]
  )

  true
end

#parse_footnote_definition(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
 
# File 'lib/mdlint/parser/block_parser.rb', line 993

def parse_footnote_definition(state)
  match = state.current_line.match(FOOTNOTE_DEF_REGEXP)
  return false unless match

  start_line = state.line
  raw_lines = [state.current_line]
  content = match[2]
  state.next_line
  while !state.eof? && state.current_line.match?(/\A {4}/)
    raw_lines << state.current_line
    content = "#{content}\n#{state.current_line.sub(/\A {4}/, "")}"
    state.next_line
  end

  state.tokens << Token.new(
    type: :footnote_definition,
    content: raw_lines.join("\n") + "\n",
    attrs: { label: match[1].downcase, content: content },
    map: [start_line, state.line]
  )
  true
end

#parse_front_matter(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


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
 
# File 'lib/mdlint/parser/block_parser.rb', line 175

def parse_front_matter(state)
  return false unless state.line.zero?

  opener = state.current_line
  format, closing_marker = front_matter_markers(opener)
  return false unless format

  closing_line = state.lines[(state.line + 1)..]&.index do |line|
    line.strip == closing_marker
  end
  return false unless closing_line

  closing_line += state.line + 1
  start_line = state.line
  raw_lines = state.raw_lines[start_line..closing_line]
  payload = state.lines[(start_line + 1)...closing_line].to_a
  return false unless front_matter_payload?(format, payload)

  content = raw_lines.join("\n")
  content += "\n" if closing_line < state.lines.length - 1 || state.src.end_with?("\n")

  state.tokens << Token.new(
    type: :front_matter,
    content: content,
    meta: { format: format, delimiter: closing_marker },
    map: [start_line, closing_line + 1]
  )
  state.line = closing_line + 1
  true
end

#parse_hr(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


354
355
356
357
358
359
360
361
362
363
364
365
366
367
 
# File 'lib/mdlint/parser/block_parser.rb', line 354

def parse_hr(state)
  line = state.current_line
  return false unless line.match?(HR_REGEXP)

  state.tokens << Token.new(
    type: :hr,
    tag: "hr",
    markup: line.strip[0],
    map: [state.line, state.line + 1]
  )

  state.next_line
  true
end

#parse_html_block(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
 
# File 'lib/mdlint/parser/block_parser.rb', line 782

def parse_html_block(state)
  line = state.current_line

  return false unless html_block_start?(line)

  start_line = state.line
  content_lines = []

  if line.match?(HTML_BLOCK_START_2)
    until state.eof?
      current_line = state.current_line
      content_lines << current_line
      state.next_line
      break if current_line.include?("-->")
    end
  elsif line.match?(HTML_BLOCK_START_1)
    tag = line[/\A {0,3}<([A-Za-z][A-Za-z0-9]*)/i, 1]
    until state.eof?
      current_line = state.current_line
      content_lines << state.raw_line
      state.next_line
      break if current_line.match?(%r{</#{Regexp.escape(tag)}\s*>}i)
    end
  elsif line.match?(HTML_BLOCK_START_3)
    until state.eof?
      current_line = state.current_line
      content_lines << state.raw_line
      state.next_line
      break if current_line.include?("?>")
    end
  elsif line.match?(HTML_BLOCK_START_5)
    until state.eof?
      current_line = state.current_line
      content_lines << state.raw_line
      state.next_line
      break if current_line.include?("]]>")
    end
  else
    until state.eof?
      current_line = state.current_line
      content_lines << state.raw_line
      state.next_line
      break if line.match?(HTML_BLOCK_START_7) && current_line.match?(%r{</[A-Z][A-Za-z0-9]*(?:\.[A-Za-z0-9_-]+)?>})
      break if state.blank_line?
    end
  end

  state.tokens << Token.new(
    type: :html_block,
    content: content_lines.join("\n") + "\n",
    map: [start_line, state.line]
  )

  true
end

#parse_list_items(state, pattern, _marker, base_indent = 0) ⇒ Object

Parameters:

  • state (Object)
  • pattern (Object)
  • marker (Object)
  • base_indent (Object) (defaults to: 0)

Returns:

  • (Object) 


499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
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
561
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
 
# File 'lib/mdlint/parser/block_parser.rb', line 499

def parse_list_items(state, pattern, _marker, base_indent = 0)
  while !state.eof?
    line = state.current_line
    match = line.match(pattern)
    break unless match
    break if line.match?(HR_REGEXP) && match[1].length <= base_indent

    item_start = state.line
    content = line.sub(pattern, "")

    state.tokens << Token.new(
      type: :list_item_open,
      tag: "li",
      nesting: 1,
      level: state.level,
      attrs: task_attributes(content).merge(tight: true),
      map: [item_start, nil]
    )
    item_token_index = state.tokens.length - 1

    state.level += 1
    state.next_line

    content = strip_task_marker(content)

    item_content_lines = [content]
    nested_lines = []
    nested_start_line = state.line
    while !state.eof? && !state.blank_line? && !state.current_line.match?(pattern)
      if nested_lines.any? && state.current_line.match?(/\A\s+/)
        nested_lines << dedent_list_line(state.current_line, base_indent)
        state.next_line
      elsif state.current_line.match?(/\A\s+/)
        item_content_lines << state.raw_line.sub(/\A\s+/, "")
        state.next_line
      else
        break
      end
    end

    while !state.eof? && !state.blank_line?
      nested_match = state.current_line.match(pattern)
      break unless nested_match && nested_match[1].length > base_indent

      nested_lines << dedent_list_line(state.current_line, base_indent)
      state.next_line
      while !state.eof? && !state.blank_line? && !state.current_line.match?(pattern)
        break unless state.current_line.match?(/\A\s+/)

        nested_lines << dedent_list_line(state.current_line, base_indent)
        state.next_line
      end
    end

    loose_content = collect_loose_item_content(state, pattern, base_indent, nested_lines, match[0].length)

    paragraph_content = item_content_lines.join("\n").strip
    if paragraph_content.match?(HR_REGEXP)
      state.tokens << Token.new(type: :hr, tag: "hr", markup: paragraph_content.strip[0], map: [item_start, state.line])
      paragraph_content = ""
    end
    unless paragraph_content.empty?
      state.tokens << Token.new(
        type: :paragraph_open,
        tag: "p",
        nesting: 1,
        level: state.level,
        map: [item_start, state.line]
      )

      state.tokens << Token.new(
        type: :inline,
        content: paragraph_content,
        level: state.level + 1,
        map: [item_start, state.line]
      )

      state.tokens << Token.new(
        type: :paragraph_close,
        tag: "p",
        nesting: -1,
        level: state.level
      )
    end

    append_nested_tokens(state, nested_lines, nested_start_line)
    append_loose_paragraph(state, loose_content, item_start) if loose_content

    state.level -= 1
    state.tokens[item_token_index].map[1] = state.line

    state.tokens << Token.new(
      type: :list_item_close,
      tag: "li",
      nesting: -1,
      level: state.level
    )

    state.skip_blank_lines
  end
end

#parse_math_block(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
 
# File 'lib/mdlint/parser/block_parser.rb', line 89

def parse_math_block(state)
  return false unless state.current_line.match?(MATH_BLOCK_REGEXP)

  start_line = state.line
  content_lines = [state.current_line]
  state.next_line
  until state.eof?
    content_lines << state.raw_line
    state.next_line
    break if content_lines.last.match?(MATH_BLOCK_REGEXP)
  end

  state.tokens << Token.new(
    type: :math_block,
    content: content_lines.join("\n") + "\n",
    map: [start_line, state.line]
  )
  true
end

#parse_ordered_list(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
 
# File 'lib/mdlint/parser/block_parser.rb', line 462

def parse_ordered_list(state)
  line = state.current_line
  match = line.match(ORDERED_LIST_REGEXP)
  return false unless match

  start_num = match[2].to_i
  delimiter = match[3]
  start_line = state.line

  state.tokens << Token.new(
    type: :ordered_list_open,
    tag: "ol",
    nesting: 1,
    level: state.level,
    markup: delimiter,
    attrs: { start: start_num, tight: true },
    map: [start_line, nil]
  )
  list_token_index = state.tokens.length - 1

  state.level += 1
  parse_ordered_list_items(state, delimiter, match[1].length)
  state.level -= 1

  state.tokens[list_token_index].map[1] = state.line

  state.tokens << Token.new(
    type: :ordered_list_close,
    tag: "ol",
    nesting: -1,
    level: state.level,
    markup: delimiter
  )

  true
end

#parse_ordered_list_items(state, delimiter, base_indent = 0) ⇒ Object

Parameters:

  • state (Object)
  • delimiter (Object)
  • base_indent (Object) (defaults to: 0)

Returns:

  • (Object) 


601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
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
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
 
# File 'lib/mdlint/parser/block_parser.rb', line 601

def parse_ordered_list_items(state, delimiter, base_indent = 0)
  pattern = /\A( {0,3})(\d{1,9})([#{Regexp.escape(delimiter)}])\s+/

  while !state.eof?
    line = state.current_line
    match = line.match(pattern)
    break unless match
    break if line.match?(HR_REGEXP) && match[1].length <= base_indent

    item_start = state.line
    content = line.sub(pattern, "")

    state.tokens << Token.new(
      type: :list_item_open,
      tag: "li",
      nesting: 1,
      level: state.level,
      attrs: task_attributes(content).merge(tight: true),
      map: [item_start, nil]
    )
    item_token_index = state.tokens.length - 1

    state.level += 1
    state.next_line

    content = strip_task_marker(content)

    item_content_lines = [content]
    nested_lines = []
    nested_start_line = state.line
    while !state.eof? && !state.blank_line? && !state.current_line.match?(pattern)
      if nested_lines.any? && state.current_line.match?(/\A\s+/)
        nested_lines << dedent_list_line(state.current_line, base_indent)
        state.next_line
      elsif state.current_line.match?(/\A\s+/)
        item_content_lines << state.raw_line.sub(/\A\s+/, "")
        state.next_line
      else
        break
      end
    end

    while !state.eof? && !state.blank_line?
      nested_match = state.current_line.match(pattern)
      break unless nested_match && nested_match[1].length > base_indent

      nested_lines << dedent_list_line(state.current_line, base_indent)
      state.next_line
      while !state.eof? && !state.blank_line? && !state.current_line.match?(pattern)
        break unless state.current_line.match?(/\A\s+/)

        nested_lines << dedent_list_line(state.current_line, base_indent)
        state.next_line
      end
    end

    loose_content = collect_loose_item_content(state, pattern, base_indent, nested_lines, match[0].length)

    paragraph_content = item_content_lines.join("\n").strip
    if paragraph_content.match?(HR_REGEXP)
      state.tokens << Token.new(type: :hr, tag: "hr", markup: paragraph_content.strip[0], map: [item_start, state.line])
      paragraph_content = ""
    end
    unless paragraph_content.empty?
      state.tokens << Token.new(
        type: :paragraph_open,
        tag: "p",
        nesting: 1,
        level: state.level,
        map: [item_start, state.line]
      )

      state.tokens << Token.new(
        type: :inline,
        content: paragraph_content,
        level: state.level + 1,
        map: [item_start, state.line]
      )

      state.tokens << Token.new(
        type: :paragraph_close,
        tag: "p",
        nesting: -1,
        level: state.level
      )
    end

    append_nested_tokens(state, nested_lines, nested_start_line)
    append_loose_paragraph(state, loose_content, item_start) if loose_content

    state.level -= 1
    state.tokens[item_token_index].map[1] = state.line

    state.tokens << Token.new(
      type: :list_item_close,
      tag: "li",
      nesting: -1,
      level: state.level
    )

    state.skip_blank_lines
  end
end

#parse_paragraph(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
 
# File 'lib/mdlint/parser/block_parser.rb', line 1016

def parse_paragraph(state)
  return false if state.blank_line?

  start_line = state.line
  content_lines = []

  while !state.eof? && !state.blank_line?
    line = state.current_line
    break if line.match?(ATX_HEADING_REGEXP) ||
             line.match?(MATH_BLOCK_REGEXP) ||
             fence_match(line) ||
             line.match?(HR_REGEXP) ||
             line.match?(BLOCKQUOTE_REGEXP) ||
             line.match?(BULLET_LIST_REGEXP) ||
             line.match?(ORDERED_LIST_REGEXP) ||
             (html_block_start?(line) && !line.match?(HTML_BLOCK_START_7)) ||
             (reference_definition_candidate?(state) && content_lines.empty?) ||
             line.match?(FOOTNOTE_DEF_REGEXP)

    if state.peek_line&.match?(SETEXT_HEADING_REGEXP)
      break if content_lines.any?
    end

    content_lines << if content_lines.empty?
                       state.raw_line.sub(/\A {0,3}/, "")
                     else
                       state.raw_line.sub(/\A\s+/, "")
                     end
    state.next_line
  end

  return false if content_lines.empty?

  state.tokens << Token.new(
    type: :paragraph_open,
    tag: "p",
    nesting: 1,
    level: state.level,
    map: [start_line, state.line]
  )

  state.tokens << Token.new(
    type: :inline,
    content: content_lines.join("\n").strip.gsub(/(?<! ) \n/, "\n"),
    level: state.level + 1,
    map: [start_line, state.line]
  )

  state.tokens << Token.new(
    type: :paragraph_close,
    tag: "p",
    nesting: -1,
    level: state.level
  )

  true
end

#parse_reference_definition(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
 
# File 'lib/mdlint/parser/block_parser.rb', line 879

def parse_reference_definition(state)
  line = state.raw_line
  match = line.match(REFERENCE_DEF_REGEXP)
  return false unless match

  label = normalize_reference_label(match[1])
  tail = line[match[0].length..].to_s.strip
  parsed = parse_reference_tail(tail)
  consumed = 1

  if parsed.nil? && tail.empty?
    url_line = state.peek_line
    return false if url_line.nil? || state.blank_line?(state.line + 1)

    parsed = parse_reference_tail(url_line.to_s.strip)
    consumed += 1 if parsed
  end
  if parsed && parsed[1].nil?
    title_line = state.peek_line(consumed)
    if title_line && !state.blank_line?(state.line + consumed) && title_line.match?(/\A\s+/)
      title = parse_reference_title(title_line.to_s.strip)
      parsed = [parsed[0], title] if title
      consumed += 1 if title
    end
  end
  return false unless parsed

  url, title = parsed

  state.tokens << Token.new(
    type: :reference_definition,
    attrs: {
      label: label,
      url: url,
      title: title
    }.compact,
    map: [state.line, state.line + 1]
  )

  state.line += consumed
  true
end

#parse_reference_tail(tail) ⇒ Object

Parameters:

  • tail (Object)

Returns:

  • (Object) 


938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
 
# File 'lib/mdlint/parser/block_parser.rb', line 938

def parse_reference_tail(tail)
  value = tail.to_s
  return nil if value.empty?

  if value.start_with?("<")
    closing = value.index(">", 1)
    return nil unless closing

    url = value[1...closing]
    raw_remainder = value[(closing + 1)..].to_s
    return nil unless raw_remainder.empty? || raw_remainder.match?(/\A\s/)

    remainder = raw_remainder.strip
  else
    index = 0
    depth = 0
    while index < value.length
      character = value[index]
      if character == "\\"
        index += 2
        next
      end
      if character == "("
        depth += 1
      elsif character == ")"
        break if depth.zero?

        depth -= 1
      elsif character.match?( /\s/ ) && depth.zero?
        break
      end
      index += 1
    end
    return nil if index.zero?

    url = value[0...index]
    remainder = value[index..].to_s.strip
  end

  return [url, nil] if remainder.empty?

  title = parse_reference_title(remainder)
  title ? [url, title] : nil
end

#parse_reference_title(value) ⇒ Object

Parameters:

  • value (Object)

Returns:

  • (Object) 


983
984
985
986
987
988
989
990
991
 
# File 'lib/mdlint/parser/block_parser.rb', line 983

def parse_reference_title(value)
  return nil unless value.length >= 2

  opener = value[0]
  closer = { '"' => '"', "'" => "'", "(" => ")" }[opener]
  return nil unless closer && value.end_with?(closer)

  value[1...-1]
end

#parse_setext_heading(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


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
305
306
307
308
309
310
311
312
 
# File 'lib/mdlint/parser/block_parser.rb', line 266

def parse_setext_heading(state)
  line = state.current_line
  return false if line.match?(/\A\s*\z/)

  underline_index = state.line + 1
  while underline_index < state.lines.length && !state.blank_line?(underline_index)
    break if state.lines[underline_index].match?(SETEXT_HEADING_REGEXP)
    break if block_boundary?(state.lines[underline_index])

    underline_index += 1
  end
  return false if underline_index >= state.lines.length

  match = state.lines[underline_index].match(SETEXT_HEADING_REGEXP)
  return false unless match

  level = match[1][0] == "=" ? 1 : 2
  content = state.lines[state.line...underline_index].join("\n").strip
  start_line = state.line

  state.tokens << Token.new(
    type: :heading_open,
    tag: "h#{level}",
    nesting: 1,
    level: state.level,
    markup: match[1][0],
    map: [start_line, underline_index + 1]
  )

  state.tokens << Token.new(
    type: :inline,
    content: content,
    level: state.level + 1,
    map: [start_line, underline_index]
  )

  state.tokens << Token.new(
    type: :heading_close,
    tag: "h#{level}",
    nesting: -1,
    level: state.level,
    markup: match[1][0]
  )

  state.line = underline_index + 1
  true
end

#parse_table(state) ⇒ Object

Parameters:

  • state (Object)

Returns:

  • (Object) 


109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
 
# File 'lib/mdlint/parser/block_parser.rb', line 109

def parse_table(state)
  return false unless @dialect.feature?(:tables)
  return false unless table_delimiter?(state.peek_line)
  return false unless state.current_line.include?("|")

  start_line = state.line
  header = split_table_row(state.current_line)
  alignments = split_table_row(state.peek_line).map { |cell| table_alignment(cell) }
  rows = [header]
  state.next_line
  state.next_line

  while !state.eof? && table_row?(state.current_line)
    rows << split_table_row(state.current_line)
    state.next_line
  end

  state.tokens << Token.new(
    type: :table,
    meta: { rows: rows, alignments: alignments },
    map: [start_line, state.line]
  )
  true
end

#reference_definition_candidate?(state) ⇒ Boolean

Parameters:

  • state (Object)

Returns:

  • (Boolean) 


922
923
924
925
926
927
928
929
930
931
932
 
# File 'lib/mdlint/parser/block_parser.rb', line 922

def reference_definition_candidate?(state)
  match = state.raw_line.match(REFERENCE_DEF_REGEXP)
  return false unless match

  tail = state.raw_line[match[0].length..].to_s.strip
  return true if parse_reference_tail(tail)
  return false unless tail.empty?

  next_line = state.peek_line
  next_line && !state.blank_line?(state.line + 1) && parse_reference_tail(next_line.to_s.strip)
end

#split_table_row(line) ⇒ Object

Parameters:

  • line (Object)

Returns:

  • (Object) 


145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
 
# File 'lib/mdlint/parser/block_parser.rb', line 145

def split_table_row(line)
  value = line.to_s.strip
  value = value[1..] if value.start_with?("|")
  value = value[0...-1] if value.end_with?("|") && !value.end_with?("\\|")
  cells = []
  current = +""
  escaped = false
  value.each_char do |character|
    if character == "|" && !escaped
      cells << current.strip
      current = +""
    else
      current << character
    end
    escaped = character == "\\" && !escaped
    escaped = false if character != "\\"
  end
  cells << current.strip
  cells
end

#strip_code_indent(raw_line, expanded_line) ⇒ String

Parameters:

  • raw_line (Object)
  • expanded_line (Object)

Returns:

  • (String) 


1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
 
# File 'lib/mdlint/parser/block_parser.rb', line 1103

def strip_code_indent(raw_line, expanded_line)
  return raw_line unless expanded_line.start_with?("    ")

  consumed = 0
  index = 0
  raw_line.each_char do |character|
    break if consumed >= 4

    consumed += character == "\t" ? 4 - (consumed % 4) : 1
    index += 1
  end
  raw_line[index..] || ""
end

#strip_fence_indent(raw_line, indent) ⇒ String

Parameters:

  • raw_line (Object)
  • indent (Object)

Returns:

  • (String) 


1140
1141
1142
1143
1144
 
# File 'lib/mdlint/parser/block_parser.rb', line 1140

def strip_fence_indent(raw_line, indent)
  return raw_line if indent.zero?

  raw_line.sub(/\A {0,#{indent}}/, "")
end

#strip_task_marker(content) ⇒ Object

Parameters:

  • content (Object)

Returns:

  • (Object) 


1155
1156
1157
1158
1159
 
# File 'lib/mdlint/parser/block_parser.rb', line 1155

def strip_task_marker(content)
  return content unless @dialect.feature?(:task_lists)

  content.sub(/\A\[[ xX]\]\s+/, "")
end

#table_alignment(cell) ⇒ Object

Parameters:

  • cell (Object)

Returns:

  • (Object) 


166
167
168
169
170
171
172
173
 
# File 'lib/mdlint/parser/block_parser.rb', line 166

def table_alignment(cell)
  value = cell.strip
  return :center if value.start_with?(":") && value.end_with?(":")
  return :left if value.start_with?(":")
  return :right if value.end_with?(":")

  nil
end

#table_delimiter?(line) ⇒ Boolean

Parameters:

  • line (Object)

Returns:

  • (Boolean) 


134
135
136
137
138
139
 
# File 'lib/mdlint/parser/block_parser.rb', line 134

def table_delimiter?(line)
  return false unless line

  cells = split_table_row(line)
  cells.length > 0 && cells.all? { |cell| cell.match?(/\A\s*:?-{3,}:?\s*\z/) }
end

#table_row?(line) ⇒ Boolean

Parameters:

  • line (Object)

Returns:

  • (Boolean) 


141
142
143
 
# File 'lib/mdlint/parser/block_parser.rb', line 141

def table_row?(line)
  line && line.include?("|") && !line.strip.empty?
end

#task_attributes(content) ⇒ Object

Parameters:

  • content (Object)

Returns:

  • (Object) 


1146
1147
1148
1149
1150
1151
1152
1153
 
# File 'lib/mdlint/parser/block_parser.rb', line 1146

def task_attributes(content)
  return {} unless @dialect.feature?(:task_lists)

  match = content.match(/\A\[([ xX])\]\s+/)
  return {} unless match

  { task: true, checked: match[1].downcase == "x" }
end