File: line_scanner.ex

package info (click to toggle)
elixir-earmark-parser 1.4.44-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 1,148 kB
  • sloc: makefile: 9
file content (317 lines) | stat: -rw-r--r-- 8,928 bytes parent folder | download
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
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
defmodule EarmarkParser.LineScanner do
  @moduledoc false

  alias EarmarkParser.{Helpers, Line, Options}
  import EarmarkParser.LineScanner.Rgx

  # This is the re that matches the ridiculous "[id]: url title" syntax

  @doc false
  def void_tag?(tag) do
    Regex.match?(void_tag_rgx(), "<#{tag}>")
  end

  def scan_lines(lines, options, recursive) do
    _lines_with_count(lines, options.line - 1)
    |> _with_lookahead(options, recursive)
  end

  def type_of(line, recursive)
      when is_boolean(recursive) do
    type_of(line, %Options{}, recursive)
  end

  def type_of({line, lnb}, options = %Options{annotations: annotations}, recursive)
      when is_binary(line) do
    {line1, annotation} = line |> Helpers.expand_tabs() |> Helpers.remove_line_ending(annotations)
    %{_type_of(line1, options, recursive) | annotation: annotation, lnb: lnb}
  end

  def type_of({line, lnb}, _, _) do
    raise ArgumentError, "line number #{lnb} #{inspect(line)} is not a binary"
  end

  defp _type_of(line, options = %Options{}, recursive) do
    {ial, stripped_line} = Helpers.extract_ial(line)
    {content, indent} = _count_indent(line, 0)
    lt_four? = indent < 4

    cond do
      content == "" ->
        _create_text(line, content, indent)

      lt_four? && !recursive && html_comment_matches(content) ->
        %Line.HtmlComment{complete: true, indent: indent, line: line}

      lt_four? && !recursive && html_comment_start_matches(content) ->
        %Line.HtmlComment{complete: false, indent: indent, line: line}

      lt_four? && dash_ruler_matches(content) ->
        %Line.Ruler{type: "-", indent: indent, line: line}

      lt_four? && star_ruler_matches(content) ->
        %Line.Ruler{type: "*", indent: indent, line: line}

      lt_four? && underline_ruler_matches(content) ->
        %Line.Ruler{type: "_", indent: indent, line: line}

      match = heading_matches(stripped_line) ->
        [_, level, heading] = match

        %Line.Heading{
          level: String.length(level),
          content: String.trim(heading),
          indent: 0,
          ial: ial,
          line: line
        }

      match = lt_four? && block_quote_matches(content) ->
        [_, quote] = match
        %Line.BlockQuote{content: quote, indent: indent, ial: ial, line: line}

      match = indent_matches(line) ->
        [_, spaces, more_spaces, rest] = match
        sl = byte_size(spaces)

        %Line.Indent{
          level: div(sl, 4),
          content: more_spaces <> rest,
          indent: byte_size(more_spaces) + sl,
          line: line
        }

      match = fence_matches(line) ->
        [_, leading, fence, language] = match

        %Line.Fence{
          delimiter: fence,
          language: _attribute_escape(language),
          indent: byte_size(leading),
          line: line
        }

      # Although no block tags I still think they should close a preceding para as do many other
      # implementations.
      match = !recursive && void_tag_matches(line) ->
        [_, tag] = match
        %Line.HtmlOneLine{tag: tag, content: line, indent: 0, line: line}

      match = !recursive && html_one_line_matches(line) ->
        [_, tag] = match
        %Line.HtmlOneLine{tag: tag, content: line, indent: 0, line: line}

      match = !recursive && html_self_closing_matches(line) ->
        [_, tag] = match
        %Line.HtmlOneLine{tag: tag, content: line, indent: 0, line: line}

      match = !recursive && html_open_tag_matches(line) ->
        [_, tag] = match
        %Line.HtmlOpenTag{tag: tag, content: line, indent: 0, line: line}

      match = lt_four? && !recursive && html_close_tag_matches(content) ->
        [_, tag] = match
        %Line.HtmlCloseTag{tag: tag, indent: indent, line: line}

      match = lt_four? && id_def_matches(content) ->
        [_, id, url | title] = match

        title =
          if(Enum.empty?(title)) do
            ""
          else
            hd(title)
          end

        %Line.IdDef{id: id, url: url, title: title, indent: indent, line: line}

      match = options.footnotes && footnote_def_matches(line) ->
        [_, id, first_line] = match
        %Line.FnDef{id: id, content: first_line, indent: 0, line: line}

      match = lt_four? && bullet_list_item_matches(content) ->
        [_, bullet, spaces, text] = match

        %Line.ListItem{
          type: :ul,
          bullet: bullet,
          content: spaces <> text,
          indent: indent,
          list_indent: String.length(bullet <> spaces) + indent + 1,
          line: line
        }

      match = lt_four? && numbered_list_item_matches(content) ->
        _create_list_item(match, indent, line)

      match = table_line_matches(content) ->
        [body] = match

        body =
          body
          |> String.trim()
          |> String.trim("|")

        columns = _split_table_columns(body)

        %Line.TableLine{
          content: line,
          columns: columns,
          is_header: _determine_if_header(columns),
          indent: indent,
          line: line
        }

      line
      |> String.replace(table_header_rgx(), "")
      |> String.match?(table_first_column_rgx()) ->
        columns = _split_table_columns(line)

        %Line.TableLine{
          content: line,
          columns: columns,
          is_header: _determine_if_header(columns),
          indent: indent,
          line: line
        }

      options.gfm_tables &&
          line |> String.replace(table_header_rgx(), "") |> String.match?(table_column_rgx()) ->
        columns = _split_table_columns(line)

        %Line.TableLine{
          content: line,
          columns: columns,
          is_header: _determine_if_header(columns),
          needs_header: true,
          indent: indent,
          line: line
        }

      match = set_ext_underline_matches(line) ->
        [_, type] = match

        level =
          if(String.starts_with?(type, "=")) do
            1
          else
            2
          end

        %Line.SetextUnderlineHeading{level: level, indent: 0, line: line}

      match = lt_four? && ial_matches(content) ->
        [_, ial] = match
        %Line.Ial{attrs: String.trim(ial), verbatim: ial, indent: indent, line: line}

      true ->
        _create_text(line, content, indent)
    end
  end

  defp _attribute_escape(string) do
    string
    |> String.replace("&", "&amp;")
    |> String.replace("<", "&lt;")
  end

  defp _create_list_item(match, indent, line)

  defp _create_list_item([_, bullet, spaces, text], indent, line) do
    sl = byte_size(spaces)

    sl1 =
      if sl > 3 do
        1
      else
        sl + 1
      end

    sl2 = sl1 + byte_size(bullet)

    %Line.ListItem{
      type: :ol,
      bullet: bullet,
      content: spaces <> text,
      indent: indent,
      list_indent: indent + sl2,
      line: line
    }
  end

  defp _create_text(line) do
    {content, indent} = _count_indent(line, 0)
    _create_text(line, content, indent)
  end

  defp _create_text(line, "", indent) do
    %Line.Blank{indent: indent, line: line}
  end

  defp _create_text(line, content, indent) do
    %Line.Text{content: content, indent: indent, line: line}
  end

  defp _count_indent(<<space, rest::binary>>, indent) when space in [?\s, ?\t] do
    _count_indent(rest, indent + 1)
  end

  defp _count_indent(rest, indent) do
    {rest, indent}
  end

  defp _lines_with_count(lines, offset) do
    Enum.zip(lines, offset..(offset + Enum.count(lines)))
  end

  defp _with_lookahead([line_lnb | lines], options, recursive) do
    case type_of(line_lnb, options, recursive) do
      %Line.Fence{delimiter: delimiter, indent: 0} = fence ->
        stop = ~r/\A (\s*) (?: #{delimiter} ) \s* ([^`\s]*) \s* \z/xu
        [fence | _lookahead_until_match(lines, stop, options, recursive)]

      %Line.HtmlComment{complete: false} = html_comment ->
        [html_comment | _lookahead_until_match(lines, ~r/-->/u, options, recursive)]

      other ->
        [other | _with_lookahead(lines, options, recursive)]
    end
  end

  defp _with_lookahead([], _options, _recursive) do
    []
  end

  defp _lookahead_until_match([], _, _, _) do
    []
  end

  defp _lookahead_until_match([{line, lnb} | lines], regex, options, recursive) do
    if line =~ regex do
      [type_of({line, lnb}, options, recursive) | _with_lookahead(lines, options, recursive)]
    else
      [
        %{_create_text(line) | lnb: lnb}
        | _lookahead_until_match(lines, regex, options, recursive)
      ]
    end
  end

  defp _determine_if_header(columns) do
    column_rgx = ~r{\A[\s|:-]+\z}

    columns
    |> Enum.all?(fn col -> Regex.run(column_rgx, col) end)
  end

  defp _split_table_columns(line) do
    col_sep_rgx = ~r/\\\|/

    line
    |> String.split(~r{(?<!\\)\|})
    |> Enum.map(&String.trim/1)
    |> Enum.map(fn col -> Regex.replace(col_sep_rgx, col, "|") end)
  end
end

#  SPDX-License-Identifier: Apache-2.0