Module: Przn::Parser

Defined in:
lib/przn/parser.rb

Constant Summary collapse

SIZE_SCALES =

Size names → Kitty text sizing scale (1-7)

{
  'xx-small' => 1,
  'x-small'  => 1,
  'small'    => 2,
  'large'    => 3,
  'x-large'  => 4,
  'xx-large' => 5,
  'xxx-large' => 6,
  'xxxx-large' => 7,
  '1' => 1, '2' => 2, '3' => 3, '4' => 4, '5' => 5, '6' => 6, '7' => 7,
}.freeze
NAMED_COLORS = 
{
  'red' => 31, 'green' => 32, 'yellow' => 33, 'blue' => 34,
  'magenta' => 35, 'cyan' => 36, 'white' => 37,
  'bright_red' => 91, 'bright_green' => 92, 'bright_yellow' => 93,
  'bright_blue' => 94, 'bright_magenta' => 95, 'bright_cyan' => 96,
  'bright_white' => 97,
}.freeze

Class Method Summary collapse

Class Method Details

.parse(markdown) ⇒ Object 



30
31
32
33
 
# File 'lib/przn/parser.rb', line 30

def parse(markdown)
  slides = split_slides(markdown)
  Presentation.new(slides.map { |raw| parse_slide(raw) })
end

.parse_font_attrs(str) ⇒ Object

HTML4-style <font face=“…” size=“…” color=“…”> attributes. Kramdown’s name=“…” legacy spelling for the family is also accepted and folded into :face so the renderer has one shape to handle.



234
235
236
237
238
 
# File 'lib/przn/parser.rb', line 234

def parse_font_attrs(str)
  attrs = parse_xml_attrs(str)
  attrs[:face] = attrs.delete(:name) if attrs.key?(:name) && !attrs.key?(:face)
  attrs.slice(:face, :size, :color)
end

.parse_image_attrs(str, attrs) ⇒ Object 



250
251
252
253
254
255
 
# File 'lib/przn/parser.rb', line 250

def parse_image_attrs(str, attrs)
  str = str.sub(/\A:?\s*/, '')
  str.scan(/([\w-]+)=['"]([^'"]*)['"]/) do |key, value|
    attrs[key.tr('-', '_')] = value
  end
end

.parse_inline(text) ⇒ Object

Parse inline text with Rabbit-compatible markup



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
 
# File 'lib/przn/parser.rb', line 269

def parse_inline(text)
  segments = []
  scanner = StringScanner.new(text)

  until scanner.eos?
    if scanner.scan(/\{::tag\s+name="([^"]+)"\}(.*?)\{:\/tag\}/)
      segments << [:tag, scanner[2], scanner[1]]
    elsif scanner.scan(/<size=([^>\s]+)>(.*?)<\/size>/)
      segments << [:tag, scanner[2], scanner[1]]
    elsif scanner.scan(/<font((?:\s+\w+="[^"]+")+)\s*>(.*?)<\/font>/)
      segments << [:font, scanner[2], parse_font_attrs(scanner[1])]
    elsif scanner.scan(/\{::font((?:\s+\w+="[^"]+")+)\}(.*?)\{:\/font\}/)
      segments << [:font, scanner[2], parse_font_attrs(scanner[1])]
    elsif scanner.scan(/\{::note\}(.*?)\{:\/note\}/)
      segments << [:note, scanner[1]]
    elsif scanner.scan(/<note>(.*?)<\/note>/)
      segments << [:note, scanner[1]]
    elsif scanner.scan(/\{::wait\/\}/) || scanner.scan(/<wait\s*\/>/)
      # skip wait markers in inline text
    elsif scanner.scan(/&lt;/)
      segments << [:text, "<"]
    elsif scanner.scan(/&gt;/)
      segments << [:text, ">"]
    elsif scanner.scan(/&amp;/)
      segments << [:text, "&"]
    elsif scanner.scan(/`([^`]+)`/)
      segments << [:code, scanner[1]]
    elsif scanner.scan(/\*\*(.+?)\*\*/)
      segments << [:bold, scanner[1]]
    elsif scanner.scan(/\*(.+?)\*/)
      segments << [:italic, scanner[1]]
    elsif scanner.scan(/~~(.+?)~~/)
      segments << [:strikethrough, scanner[1]]
    else
      segments << [:text, scanner.scan(/[^`*~{<&]+|./)]
    end
  end

  segments
end

.parse_slide(raw) ⇒ Object 



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
 
# File 'lib/przn/parser.rb', line 56

def parse_slide(raw)
  blocks = []
  lines = raw.lines
  i = 0

  while i < lines.size
    line = lines[i]

    case line
    # {::comment} ... {:/comment} block — skip entirely
    when /\A\s*\{::comment\}/
      i += 1
      i += 1 while i < lines.size && !lines[i].match?(/\{:\/comment\}/)

    # Block alignment: {:.center} or {:.right}
    when /\A\s*\{:\.(\w+)\}\s*\z/
      blocks << {type: :align, align: Regexp.last_match(1).to_sym}

    # Block alignment, XML form: <center>content</center> or <right>content</right>
    when /\A\s*<(center|right)>(.*)<\/\1>\s*\z/
      blocks << {type: :align, align: Regexp.last_match(1).to_sym}
      blocks << {type: :paragraph, content: Regexp.last_match(2)}

    # Slide background (Echoes OSC 7772):
    #   <bg color="#..."/>                              — solid (bg-color)
    #   <bg from="#..." to="#..." angle="N"/>           — linear gradient (bg-gradient)
    when /\A\s*<bg((?:\s+\w+="[^"]+")*)\s*\/>\s*\z/
      blocks << {type: :bg, attrs: parse_xml_attrs(Regexp.last_match(1))}

    # Fenced code block
    when /\A\s*```(\w*)\s*\z/
      lang = Regexp.last_match(1)
      lang = nil if lang.empty?
      code_lines = []
      i += 1
      while i < lines.size && !lines[i].match?(/\A\s*```\s*\z/)
        code_lines << lines[i]
        i += 1
      end
      # Check for kramdown IAL on next line: {: lang="ruby"}
      if (i + 1) < lines.size && lines[i + 1]&.match?(/\A\s*\{:/)
        i += 1
        if lines[i].match(/lang="(\w+)"/)
          lang = Regexp.last_match(1)
        end
      end
      blocks << {type: :code_block, content: code_lines.join, language: lang}

    # Indented code block (4 spaces)
    when /\A {4}(.*)$/
      code_lines = [Regexp.last_match(1)]
      while (i + 1) < lines.size && lines[i + 1].match?(/\A {4}/)
        i += 1
        code_lines << lines[i].sub(/\A {4}/, '')
      end
      # Check for kramdown IAL: {: lang="ruby"}
      lang = nil
      if (i + 1) < lines.size && lines[i + 1]&.match?(/\A\s*\{:/)
        i += 1
        if lines[i].match(/lang="(\w+)"/)
          lang = Regexp.last_match(1)
        end
      end
      blocks << {type: :code_block, content: code_lines.join("\n") + "\n", language: lang}

    # h1 (slide title)
    when /\A#\s+(.*)/
      blocks << {type: :heading, level: 1, content: Regexp.last_match(1).strip}

    # h2-h6 (sub-headings within slide)
    when /\A(\#{2,6})\s+(.*)/
      level = Regexp.last_match(1).size
      text = Regexp.last_match(2).strip
      blocks << {type: :heading, level: level, content: text}

    # Block quote
    when /\A>\s?(.*)/
      quote_lines = [Regexp.last_match(1)]
      while (i + 1) < lines.size && (m = lines[i + 1].match(/\A>\s?(.*)/))
        i += 1
        quote_lines << m[1]
      end
      blocks << {type: :blockquote, content: quote_lines.join("\n")}

    # Table
    when /\A\|/
      table_lines = [line.strip]
      while (i + 1) < lines.size && lines[i + 1].match?(/\A\|/)
        i += 1
        table_lines << lines[i].strip
      end
      blocks << parse_table(table_lines)

    # Unordered list (* or - item)
    when /\A[*\-]\s+(.*)/
      items = []
      while i < lines.size && (lines[i].match?(/\A[*\-]\s+/) || lines[i].match?(/\A {2,}[*\-]\s+/) || lines[i].match?(/\A {2,}\S/))
        if lines[i].match(/\A(\s*)[*\-]\s+(.*)/)
          depth = Regexp.last_match(1).size / 2
          items << {text: Regexp.last_match(2), depth: depth}
        elsif lines[i].match(/\A {2,}(\S.*)/)
          # Continuation line
          items.last[:text] << " " << Regexp.last_match(1) if items.last
        else
          break
        end
        i += 1
      end
      i -= 1
      blocks << {type: :unordered_list, items: items}

    # Ordered list
    when /\A(\s*)\d+\.\s+(.*)/
      items = []
      while i < lines.size && lines[i].match?(/\A\s*\d+\.\s+/)
        lines[i].match(/\A(\s*)\d+\.\s+(.*)/)
        depth = Regexp.last_match(1).size / 3
        items << {text: Regexp.last_match(2), depth: depth}
        i += 1
      end
      i -= 1
      blocks << {type: :ordered_list, items: items}

    # Image: ![alt](path "title"){:attrs}
    when /\A!\[([^\]]*)\]\((\S+?)(?:\s+"([^"]*)")?\)(.*)/
      alt = Regexp.last_match(1)
      path = Regexp.last_match(2)
      title = Regexp.last_match(3)
      rest = Regexp.last_match(4).strip
      attrs = {}
      if rest.match(/\{([^}]+)\}/)
        parse_image_attrs(Regexp.last_match(1), attrs)
      elsif rest.match(/\{(.+)/) || ((i + 1) < lines.size && lines[i + 1]&.match?(/\A\s*\{/))
        attr_str = rest.sub(/\A\{:?\s*/, '')
        while !attr_str.include?('}') && (i + 1) < lines.size
          i += 1
          attr_str << " " << lines[i].strip
        end
        attr_str = attr_str.sub(/\}\s*\z/, '')
        parse_image_attrs(attr_str, attrs)
      end
      blocks << {type: :image, path: path, alt: alt, title: title, attrs: attrs}

    # Definition list: term on one line, :   definition on next
    when /\A(\S.*)\s*\z/
      if (i + 1) < lines.size && lines[i + 1].match?(/\A:\s{3}/)
        term = Regexp.last_match(1).strip
        i += 1
        definition_lines = []
        while i < lines.size && lines[i].match?(/\A:\s{3}(.*)|\A {4}(.*)/)
          if lines[i].match(/\A:\s{3}(.*)/)
            definition_lines << Regexp.last_match(1)
          elsif lines[i].match(/\A {4}(.*)/)
            definition_lines << Regexp.last_match(1)
          end
          i += 1
        end
        i -= 1
        blocks << {type: :definition_list, term: term, definition: definition_lines.join("\n")}
      else
        blocks << {type: :paragraph, content: Regexp.last_match(1).strip}
      end

    when /\A\s*\z/
      blocks << {type: :blank}

    else
      blocks << {type: :paragraph, content: line.strip}
    end
    i += 1
  end

  Slide.new(blocks)
end

.parse_table(lines) ⇒ Object 



257
258
259
260
261
262
263
264
265
266
 
# File 'lib/przn/parser.rb', line 257

def parse_table(lines)
  rows = []
  lines.each do |line|
    next if line.match?(/\A\|[-|:\s]+\|\s*\z/)  # separator row

    cells = line.split('|').map(&:strip).reject(&:empty?)
    rows << cells
  end
  {type: :table, header: rows.first, rows: rows.drop(1)}
end

.parse_xml_attrs(str) ⇒ Object

Generic attribute scanner — ‘key=“value”` pairs, returned as a hash with symbolized keys. Doesn’t validate which keys are allowed; callers slice.



242
243
244
245
246
247
248
 
# File 'lib/przn/parser.rb', line 242

def parse_xml_attrs(str)
  attrs = {}
  str.scan(/(\w+)="([^"]+)"/) do |key, value|
    attrs[key.to_sym] = value
  end
  attrs
end

.split_slides(markdown) ⇒ Object

Split on h1 headings (Rabbit-compatible)



36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
 
# File 'lib/przn/parser.rb', line 36

def split_slides(markdown)
  chunks = []
  current = +""
  in_fence = false

  markdown.each_line do |line|
    if line.match?(/\A\s*```/)
      in_fence = !in_fence
      current << line
    elsif !in_fence && line.match?(/\A#\s/)
      chunks << current unless current.strip.empty?
      current = +line
    else
      current << line
    end
  end
  chunks << current unless current.strip.empty?
  chunks
end