summaryrefslogtreecommitdiff
path: root/src/scanners.re
blob: 77d30cd548de6863404359ded0c4fde38709ade1 (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
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
#include <stdlib.h>
#include "chunk.h"
#include "scanners.h"

bufsize_t _scan_at(bufsize_t (*scanner)(const unsigned char *), cmark_chunk *c, bufsize_t offset)
{
	bufsize_t res;
	unsigned char *ptr = (unsigned char *)c->data;

        if (ptr == NULL || offset > c->len) {
          return 0;
        } else {
	  unsigned char lim = ptr[c->len];

	  ptr[c->len] = '\0';
	  res = scanner(ptr + offset);
	  ptr[c->len] = lim;
        }

	return res;
}

/*!re2c
  re2c:define:YYCTYPE  = "unsigned char";
  re2c:define:YYCURSOR = p;
  re2c:define:YYMARKER = marker;
  re2c:define:YYCTXMARKER = marker;
  re2c:yyfill:enable = 0;

  wordchar = [^\x00-\x20];

  spacechar = [ \t\v\f\r\n];

  reg_char     = [^\\()\x00-\x20];

  escaped_char = [\\][!"#$%&'()*+,./:;<=>?@[\\\]^_`{|}~-];

  tagname = [A-Za-z][A-Za-z0-9-]*;

  blocktagname = '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'|'meta'|'nav'|'noframes'|'ol'|'optgroup'|'option'|'p'|'param'|'section'|'source'|'title'|'summary'|'table'|'tbody'|'td'|'tfoot'|'th'|'thead'|'title'|'tr'|'track'|'ul';

  attributename = [a-zA-Z_:][a-zA-Z0-9:._-]*;

  unquotedvalue = [^\"'=<>`\x00]+;
  singlequotedvalue = ['][^'\x00]*['];
  doublequotedvalue = [\"][^\"\x00]*[\"];

  attributevalue = unquotedvalue | singlequotedvalue | doublequotedvalue;

  attributevaluespec = spacechar* [=] spacechar* attributevalue;

  attribute = spacechar+ attributename attributevaluespec?;

  opentag = tagname attribute* spacechar* [/]? [>];
  closetag = [/] tagname spacechar* [>];

  htmlcomment = "!---->" | ("!--" ([-]? [^\x00>-]) ([-]? [^\x00-])* "-->");

  processinginstruction = "?" ([^?>\x00]+ | [?][^>\x00] | [>])* "?>";

  declaration = "!" [A-Z]+ spacechar+ [^>\x00]* ">";

  cdata = "![CDATA[" ([^\]\x00]+ | "]" [^\]\x00] | "]]" [^>\x00])* "]]>";

  htmltag = opentag | closetag | htmlcomment | processinginstruction |
            declaration | cdata;

  in_parens_nosp   = [(] (reg_char|escaped_char|[\\])* [)];

  in_double_quotes = ["] (escaped_char|[^"\x00])* ["];
  in_single_quotes = ['] (escaped_char|[^'\x00])* ['];
  in_parens        = [(] (escaped_char|[^)\x00])* [)];

  scheme           = [A-Za-z][A-Za-z0-9.+-]{1,31};
*/

// Try to match a scheme including colon.
bufsize_t _scan_scheme(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  scheme [:] { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match URI autolink after first <, returning number of chars matched.
bufsize_t _scan_autolink_uri(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  scheme [:][^\x00-\x20<>]*[>]  { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match email autolink after first <, returning num of chars matched.
bufsize_t _scan_autolink_email(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  [a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+
    [@]
    [a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?
    ([.][a-zA-Z0-9]([a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*
    [>] { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match an HTML tag after first <, returning num of chars matched.
bufsize_t _scan_html_tag(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  htmltag { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match an HTML block tag start line, returning
// an integer code for the type of block (1-6, matching the spec).
// #7 is handled by a separate function, below.
bufsize_t _scan_html_block_start(const unsigned char *p)
{
  const unsigned char *marker = NULL;
/*!re2c
  [<] ('script'|'pre'|'style') (spacechar | [>]) { return 1; }
  '<!--' { return 2; }
  '<?' { return 3; }
  '<!' [A-Z] { return 4; }
  '<![CDATA[' { return 5; }
  [<] [/]? blocktagname (spacechar | [/]? [>])  { return 6; }
  .? { return 0; }
*/
}

// Try to match an HTML block tag start line of type 7, returning
// 7 if successful, 0 if not.
bufsize_t _scan_html_block_start_7(const unsigned char *p)
{
  const unsigned char *marker = NULL;
/*!re2c
  [<] (opentag | closetag) [\t\n\f ]* [\r\n] { return 7; }
  .? { return 0; }
*/
}

// Try to match an HTML block end line of type 1
bufsize_t _scan_html_block_end_1(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  .* [<] [/] ('script'|'pre'|'style') [>] { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match an HTML block end line of type 2
bufsize_t _scan_html_block_end_2(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  .* '-->' { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match an HTML block end line of type 3
bufsize_t _scan_html_block_end_3(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  .* '?>' { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match an HTML block end line of type 4
bufsize_t _scan_html_block_end_4(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  .* '>' { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match an HTML block end line of type 5
bufsize_t _scan_html_block_end_5(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  .* ']]>' { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match a URL in a link or reference, return number of chars matched.
// This may optionally be contained in <..>; otherwise
// whitespace and unbalanced right parentheses aren't allowed.
// Newlines aren't ever allowed.
bufsize_t _scan_link_url(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  [ \r\n]* [<] ([^<> \t\r\n\\\x00] | escaped_char | [\\])* [>] { return (bufsize_t)(p - start); }
  [ \r\n]* (reg_char+ | escaped_char | [\\] [^() \t\v\f\r\n] | in_parens_nosp)* [\\]? { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Try to match a link title (in single quotes, in double quotes, or
// in parentheses), returning number of chars matched.  Allow one
// level of internal nesting (quotes within quotes).
bufsize_t _scan_link_title(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  ["] (escaped_char|[^"\x00])* ["]   { return (bufsize_t)(p - start); }
  ['] (escaped_char|[^'\x00])* ['] { return (bufsize_t)(p - start); }
  [(] (escaped_char|[^)\x00])* [)]  { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Match space characters, including newlines.
bufsize_t _scan_spacechars(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p; \
/*!re2c
  [ \t\v\f\r\n]* { return (bufsize_t)(p - start); }
  . { return 0; }
*/
}

// Match ATX heading start.
bufsize_t _scan_atx_heading_start(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  [#]{1,6} ([ \t]+|[\r\n])  { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Match setext heading line.  Return 1 for level-1 heading,
// 2 for level-2, 0 for no match.
bufsize_t _scan_setext_heading_line(const unsigned char *p)
{
  const unsigned char *marker = NULL;
/*!re2c
  [=]+ [ \t]* [\r\n] { return 1; }
  [-]+ [ \t]* [\r\n] { return 2; }
  .? { return 0; }
*/
}

// Scan a thematic break line: "...three or more hyphens, asterisks,
// or underscores on a line by themselves. If you wish, you may use
// spaces between the hyphens or asterisks."
bufsize_t _scan_thematic_break(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  ([*][ \t]*){3,} [ \t]* [\r\n] { return (bufsize_t)(p - start); }
  ([_][ \t]*){3,} [ \t]* [\r\n] { return (bufsize_t)(p - start); }
  ([-][ \t]*){3,} [ \t]* [\r\n] { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Scan an opening code fence.
bufsize_t _scan_open_code_fence(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  [`]{3,} / [^`\r\n\x00]*[\r\n] { return (bufsize_t)(p - start); }
  [~]{3,} / [^~\r\n\x00]*[\r\n] { return (bufsize_t)(p - start); }
  .?                        { return 0; }
*/
}

// Scan a closing code fence with length at least len.
bufsize_t _scan_close_code_fence(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  [`]{3,} / [ \t]*[\r\n] { return (bufsize_t)(p - start); }
  [~]{3,} / [ \t]*[\r\n] { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Scans an entity.
// Returns number of chars matched.
bufsize_t _scan_entity(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  [&] ([#] ([Xx][A-Fa-f0-9]{1,8}|[0-9]{1,8}) |[A-Za-z][A-Za-z0-9]{1,31} ) [;]
     { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}

// Returns positive value if a URL begins in a way that is potentially
// dangerous, with javascript:, vbscript:, file:, or data:, otherwise 0.
bufsize_t _scan_dangerous_url(const unsigned char *p)
{
  const unsigned char *marker = NULL;
  const unsigned char *start = p;
/*!re2c
  'data:image/' ('png'|'gif'|'jpeg'|'webp') { return 0; }
  'javascript:' | 'vbscript:' | 'file:' | 'data:' { return (bufsize_t)(p - start); }
  .? { return 0; }
*/
}