|
|
@@ -0,0 +1,581 @@
|
|
|
1
|
+<?php
|
|
|
2
|
+declare(strict_types=1);
|
|
|
3
|
+
|
|
|
4
|
+class MDUtils {
|
|
|
5
|
+ // Modified from https://urlregex.com/ to remove capture groups. Matches fully qualified URLs only.
|
|
|
6
|
+ public static $baseURLRegex = '(?:(?:(?:[a-z]{3,9}:(?:\\/\\/)?)(?:[\\-;:&=\\+\\$,\\w]+@)?[a-z0-9\\.\\-]+|(?:www\\.|[\\-;:&=\\+\\$,\\w]+@)[a-z0-9\\.\\-]+)(?:(?:\\/[\\+~%\\/\\.\\w\\-_]*)?\\??(?:[\\-\\+=&;%@\\.\\w_]*)#?(?:[\\.\\!\\/\\\\\\w]*))?)';
|
|
|
7
|
+ // Modified from https://emailregex.com/ to remove capture groups.
|
|
|
8
|
+ public static $baseEmailRegex = '(?:(?:[^<>()\\[\\]\\\\.,;:\\s@"]+(?:\\.[^<>()\\[\\]\\\\.,;:\\s@"]+)*)|(?:".+"))@(?:(?:\\[[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}\\.[0-9]{1,3}])|(?:(?:[a-z\\-0-9]+\\.)+[a-z]{2,}))';
|
|
|
9
|
+
|
|
|
10
|
+ /**
|
|
|
11
|
+ * Encodes characters as HTML numeric entities to make it marginally more
|
|
|
12
|
+ * difficult for web scrapers to grab sensitive info. If `text` starts with
|
|
|
13
|
+ * `mailto:` only the email address following it will be obfuscated.
|
|
|
14
|
+ */
|
|
|
15
|
+ public static function escapeObfuscated(string $text): string {
|
|
|
16
|
+ if (str_starts_with($text, 'mailto:')) {
|
|
|
17
|
+ return 'mailto:' . escapeObfuscated(mb_substr($text, 7));
|
|
|
18
|
+ }
|
|
|
19
|
+ $html = '';
|
|
|
20
|
+ $l = mb_strlen($text);
|
|
|
21
|
+ for ($p = 0; $p < $l; $p++) {
|
|
|
22
|
+ $cp = mb_ord(mb_substr($text, $p, 1));
|
|
|
23
|
+ $html .= "&#{{$cp}}";
|
|
|
24
|
+ }
|
|
|
25
|
+ return $html;
|
|
|
26
|
+ }
|
|
|
27
|
+
|
|
|
28
|
+ /**
|
|
|
29
|
+ * Removes illegal characters from an HTML attribute name.
|
|
|
30
|
+ */
|
|
|
31
|
+ public static function scrubAttributeName(string $name): string {
|
|
|
32
|
+ return mb_ereg_replace('[\\t\\n\\f \\/>"\'=]+', '');
|
|
|
33
|
+ }
|
|
|
34
|
+
|
|
|
35
|
+ /**
|
|
|
36
|
+ * Strips one or more leading indents from a line or lines of markdown. An
|
|
|
37
|
+ * indent is defined as 4 spaces or one tab. Incomplete indents (i.e. 1-3
|
|
|
38
|
+ * spaces) are treated like one indent level.
|
|
|
39
|
+ *
|
|
|
40
|
+ * @param string|string[] $line
|
|
|
41
|
+ * @param int $levels
|
|
|
42
|
+ * @return string|string[]
|
|
|
43
|
+ */
|
|
|
44
|
+ public static function stripIndent(string|array $line, int $levels=1): string|array {
|
|
|
45
|
+ $regex = "^(?: {1,4}|\\t){{$levels}}";
|
|
|
46
|
+ return is_array($line) ? array_map(fn(string $l): string => mb_ereg_replace($regex, '', $l)) : mb_ereg_replace($regex, '', $line);
|
|
|
47
|
+ }
|
|
|
48
|
+
|
|
|
49
|
+ /**
|
|
|
50
|
+ * Counts the number of indent levels in a line of text. Partial indents
|
|
|
51
|
+ * (1 to 3 spaces) are counted as one indent level unless `fullIndentsOnly`
|
|
|
52
|
+ * is `true`.
|
|
|
53
|
+ */
|
|
|
54
|
+ public static function countIndents(string $line, bool $fullIndentsOnly=false): int {
|
|
|
55
|
+ // normalize indents to tabs
|
|
|
56
|
+ $t = mb_ereg_replace($fullIndentsOnly ? "(?: {4}|\\t)" : "(?: {1,4}|\\t)", "\t", $line);
|
|
|
57
|
+ // remove content after indent
|
|
|
58
|
+ $t = mb_ereg_replace("^(\\t*)(.*?)$", "\\1", $t);
|
|
|
59
|
+ // count tabs
|
|
|
60
|
+ return mb_strlen($t);
|
|
|
61
|
+ }
|
|
|
62
|
+
|
|
|
63
|
+ /**
|
|
|
64
|
+ * Returns a copy of an array without any whitespace-only lines at the end.
|
|
|
65
|
+ *
|
|
|
66
|
+ * @param string[] $lines
|
|
|
67
|
+ * @return string[]
|
|
|
68
|
+ */
|
|
|
69
|
+ public static function withoutTrailingBlankLines(array $lines): array {
|
|
|
70
|
+ $stripped = $lines;
|
|
|
71
|
+ while (sizeof($stripped) > 0 && sizeof(mb_trim($stripped[sizeof($stripped) - 1])) == 0) {
|
|
|
72
|
+ array_pop($stripped);
|
|
|
73
|
+ }
|
|
|
74
|
+ return $stripped;
|
|
|
75
|
+ }
|
|
|
76
|
+
|
|
|
77
|
+ /**
|
|
|
78
|
+ * Tests if an array of lines contains at least one blank. A blank line
|
|
|
79
|
+ * can contain whitespace.
|
|
|
80
|
+ *
|
|
|
81
|
+ * @param string[] $lines
|
|
|
82
|
+ */
|
|
|
83
|
+ public static function containsBlankLine(array $lines): bool {
|
|
|
84
|
+ foreach ($lines as $line) {
|
|
|
85
|
+ if (mb_len(mb_trim($line)) == 0) return true;
|
|
|
86
|
+ }
|
|
|
87
|
+ return false;
|
|
|
88
|
+ }
|
|
|
89
|
+
|
|
|
90
|
+ public static function equalAssocArrays(array $a, array $b) {
|
|
|
91
|
+ return empty(array_diff_assoc($a, $b));
|
|
|
92
|
+ }
|
|
|
93
|
+}
|
|
|
94
|
+
|
|
|
95
|
+/**
|
|
|
96
|
+ * Token type enum for `MDToken`.
|
|
|
97
|
+ */
|
|
|
98
|
+enum MDTokenType {
|
|
|
99
|
+ case Text;
|
|
|
100
|
+ /**
|
|
|
101
|
+ * Only used for the leading and trailing whitespace around a run of text,
|
|
|
102
|
+ * not every single whitespace character.
|
|
|
103
|
+ */
|
|
|
104
|
+ case Whitespace;
|
|
|
105
|
+
|
|
|
106
|
+ case Underscore;
|
|
|
107
|
+ case Asterisk;
|
|
|
108
|
+ case Slash;
|
|
|
109
|
+ case Tilde;
|
|
|
110
|
+ case Bang;
|
|
|
111
|
+ case Backtick;
|
|
|
112
|
+ case Equal;
|
|
|
113
|
+ case Caret;
|
|
|
114
|
+
|
|
|
115
|
+ case Label; // content=label
|
|
|
116
|
+ case URL; // content=URL, extra=title
|
|
|
117
|
+ case Email; // content=email address, extra=title
|
|
|
118
|
+ case SimpleLink; // content=URL
|
|
|
119
|
+ case SimpleEmail; // content=email address
|
|
|
120
|
+ case Footnote; // content=symbol
|
|
|
121
|
+ case Modifier; // modifier=MDTagModifier
|
|
|
122
|
+
|
|
|
123
|
+ case HTMLTag; // tag=MDHTMLTag
|
|
|
124
|
+
|
|
|
125
|
+ /** Wildcard for `MDToken.findFirstTokens` */
|
|
|
126
|
+ case META_AnyNonWhitespace;
|
|
|
127
|
+ /** Wildcard for `MDToken.findFirstTokens` */
|
|
|
128
|
+ case META_OptionalWhitespace;
|
|
|
129
|
+}
|
|
|
130
|
+
|
|
|
131
|
+/**
|
|
|
132
|
+ * Search results from `MDToken.findFirstTokens`.
|
|
|
133
|
+ */
|
|
|
134
|
+class MDTokenMatch {
|
|
|
135
|
+ /** @var MDToken{} */
|
|
|
136
|
+ public array $tokens;
|
|
|
137
|
+ public int $index;
|
|
|
138
|
+
|
|
|
139
|
+ /**
|
|
|
140
|
+ * @param MDToken[] $tokens
|
|
|
141
|
+ * @param int $index
|
|
|
142
|
+ */
|
|
|
143
|
+ public function __construct($tokens, $index) {
|
|
|
144
|
+ $this->tokens = $tokens;
|
|
|
145
|
+ $this->index = $index;
|
|
|
146
|
+ }
|
|
|
147
|
+}
|
|
|
148
|
+
|
|
|
149
|
+/**
|
|
|
150
|
+ * Search results from `MDToken.findPairedTokens`.
|
|
|
151
|
+ */
|
|
|
152
|
+class MDPairedTokenMatch {
|
|
|
153
|
+ /** @var MDToken[] */
|
|
|
154
|
+ public array $startTokens;
|
|
|
155
|
+ /** @var MDToken[] */
|
|
|
156
|
+ public array $contentTokens;
|
|
|
157
|
+ /** @var MDToken[] */
|
|
|
158
|
+ public array $endTokens;
|
|
|
159
|
+ public int $startIndex;
|
|
|
160
|
+ public int $contentIndex;
|
|
|
161
|
+ public int $endIndex;
|
|
|
162
|
+ public int $totalLength;
|
|
|
163
|
+
|
|
|
164
|
+ public function __construct($startTokens, $contentTokens, $endTokens, $startIndex, $contentIndex, $endIndex, $totalLength) {
|
|
|
165
|
+ $this->startTokens = $startTokens;
|
|
|
166
|
+ $this->contentTokens = $contentTokens;
|
|
|
167
|
+ $this->endTokens = $endTokens;
|
|
|
168
|
+ $this->startIndex = $startIndex;
|
|
|
169
|
+ $this->contentIndex = $contentIndex;
|
|
|
170
|
+ $this->endIndex = $endIndex;
|
|
|
171
|
+ $this->totalLength = $totalLength;
|
|
|
172
|
+ }
|
|
|
173
|
+}
|
|
|
174
|
+
|
|
|
175
|
+/**
|
|
|
176
|
+ * One lexical unit in inline markdown syntax parsing.
|
|
|
177
|
+ */
|
|
|
178
|
+class MDToken {
|
|
|
179
|
+ /**
|
|
|
180
|
+ * The original verbatim token string. Required as a plaintext fallback if
|
|
|
181
|
+ * the token remains unresolved.
|
|
|
182
|
+ */
|
|
|
183
|
+ public string $original;
|
|
|
184
|
+ public MDTokenType $type;
|
|
|
185
|
+ public ?string $content = null;
|
|
|
186
|
+ public ?string $extra = null;
|
|
|
187
|
+ public ?MDHTMLTag $tag = null;
|
|
|
188
|
+ public ?MDTagModifier $modifier = null;
|
|
|
189
|
+
|
|
|
190
|
+ /**
|
|
|
191
|
+ * Creates a token.
|
|
|
192
|
+ *
|
|
|
193
|
+ * @param string original verbatim token string
|
|
|
194
|
+ * @param MDTokenType type token type
|
|
|
195
|
+ * @param string|MDTagModifier|MDHTMLTag|null content primary content of the token
|
|
|
196
|
+ * @param string|null extra additional content
|
|
|
197
|
+ */
|
|
|
198
|
+ public function __construct(string $original, MDTokenType $type,
|
|
|
199
|
+ string|MDTagModifier|MDHTMLTag|null $content=null,
|
|
|
200
|
+ ?string $extra=null) {
|
|
|
201
|
+ $this->original = $original;
|
|
|
202
|
+ $this->type = $type;
|
|
|
203
|
+ if ($content instanceof MDTagModifier) {
|
|
|
204
|
+ $this->modifier = $content;
|
|
|
205
|
+ } elseif ($content instanceof MDHTMLTag) {
|
|
|
206
|
+ $this->tag = $content;
|
|
|
207
|
+ } else {
|
|
|
208
|
+ $this->content = $content;
|
|
|
209
|
+ }
|
|
|
210
|
+ $this->extra = $extra;
|
|
|
211
|
+ }
|
|
|
212
|
+
|
|
|
213
|
+ public function __toString() {
|
|
|
214
|
+ $classname = get_class($this);
|
|
|
215
|
+ return "({$classname} type={$this->type} content={$this->content})";
|
|
|
216
|
+ }
|
|
|
217
|
+
|
|
|
218
|
+ /**
|
|
|
219
|
+ * Attempts to parse a label token from the beginning of `line`. A label is
|
|
|
220
|
+ * of the form `[content]`. If found, returns an array:
|
|
|
221
|
+ * - `0`: the entire label including brackets
|
|
|
222
|
+ * - `1`: the content of the label
|
|
|
223
|
+ *
|
|
|
224
|
+ * @param string $line
|
|
|
225
|
+ * @return ?string[] match groups or null if not found
|
|
|
226
|
+ */
|
|
|
227
|
+ public static function tokenizeLabel(string $line): ?array {
|
|
|
228
|
+ if (!str_starts_with($line, '[')) return null;
|
|
|
229
|
+ $parenCount = 0;
|
|
|
230
|
+ $bracketCount = 0;
|
|
|
231
|
+ $l = mb_strlen($line);
|
|
|
232
|
+ for ($p = 1; $p < $l; $p++) {
|
|
|
233
|
+ $ch = mb_substr($line, $p, 1);
|
|
|
234
|
+ if ($ch == '\\') {
|
|
|
235
|
+ $p++;
|
|
|
236
|
+ } elseif ($ch == '(') {
|
|
|
237
|
+ $parenCount++;
|
|
|
238
|
+ } elseif ($ch == ')') {
|
|
|
239
|
+ $parenCount--;
|
|
|
240
|
+ if ($parenCount < 0) return null;
|
|
|
241
|
+ } elseif ($ch == '[') {
|
|
|
242
|
+ $bracketCount++;
|
|
|
243
|
+ } elseif ($ch == ']') {
|
|
|
244
|
+ if ($bracketCount > 0) {
|
|
|
245
|
+ $bracketCount--;
|
|
|
246
|
+ } else {
|
|
|
247
|
+ return [ mb_substr($line, 0, $p + 1), mb_substr($line, 1, $p) ];
|
|
|
248
|
+ }
|
|
|
249
|
+ }
|
|
|
250
|
+ }
|
|
|
251
|
+ return null;
|
|
|
252
|
+ }
|
|
|
253
|
+
|
|
|
254
|
+ private static $urlWithTitleRegex = '^\\((\\S+?)\\s+"(.*?)"\\)'; // 1=URL, 2=title
|
|
|
255
|
+ private static $urlRegex = '^\\((\\S+?)\\)'; // 1=URL
|
|
|
256
|
+
|
|
|
257
|
+ /**
|
|
|
258
|
+ * Attempts to parse a URL token from the beginning of `line`. A URL token
|
|
|
259
|
+ * is of the form `(url)` or `(url "title")`. If found, returns an array:
|
|
|
260
|
+ * - `0`: the entire URL token including parentheses
|
|
|
261
|
+ * - `1`: the URL
|
|
|
262
|
+ * - `2`: the optional title, or `null`
|
|
|
263
|
+ *
|
|
|
264
|
+ * @param string $line
|
|
|
265
|
+ * @return ?array token tuple
|
|
|
266
|
+ */
|
|
|
267
|
+ public static function tokenizeURL(string $line): ?array {
|
|
|
268
|
+ $groups = [];
|
|
|
269
|
+ if (mb_eregi($urlWithTitleRegex, $line, $groups)) {
|
|
|
270
|
+ if (tokenizeEmail($line)) return null; // make sure it's not better described as an email address
|
|
|
271
|
+ return $groups;
|
|
|
272
|
+ }
|
|
|
273
|
+ if (mb_eregi($urlRegex, $line, $groups)) {
|
|
|
274
|
+ if (tokenizeEmail($line)) return null;
|
|
|
275
|
+ return [ $groups[0], $groups[1], null ];
|
|
|
276
|
+ }
|
|
|
277
|
+ return null;
|
|
|
278
|
+ }
|
|
|
279
|
+
|
|
|
280
|
+ /**
|
|
|
281
|
+ * Attempts to parse an email address from the beginning of `line`. An
|
|
|
282
|
+ * email address is of the form `(user@example.com)` or
|
|
|
283
|
+ * `(user@example.com "link title")`. If found, returns an array:
|
|
|
284
|
+ * - `0`: the entire token including parentheses
|
|
|
285
|
+ * - `1`: the email address
|
|
|
286
|
+ * - `2`: the optional link title, or `null`
|
|
|
287
|
+ *
|
|
|
288
|
+ * @param string $line
|
|
|
289
|
+ * @return string[] token tuple
|
|
|
290
|
+ */
|
|
|
291
|
+ public static function tokenizeEmail(string $line): array {
|
|
|
292
|
+ $groups;
|
|
|
293
|
+ if (mb_eregi("^\\(\\s*(" . MDUtils::$baseEmailRegex . ")\\s+\"(.*?)\"\\s*\\)",
|
|
|
294
|
+ $line, $groups)) {
|
|
|
295
|
+ return $groups;
|
|
|
296
|
+ }
|
|
|
297
|
+ if (mb_eregi("^\\(\\s*(" . MDUtils::$baseEmailRegex . ")\\s*\\)", $line, $groups)) {
|
|
|
298
|
+ return [ $groups[0], $groups[1], null ];
|
|
|
299
|
+ }
|
|
|
300
|
+ return null;
|
|
|
301
|
+ }
|
|
|
302
|
+
|
|
|
303
|
+ /**
|
|
|
304
|
+ * Searches an array of `MDToken` for the given pattern of `MDTokenType`s.
|
|
|
305
|
+ * If found, returns a `MDTokenMatch`, otherwise `null`.
|
|
|
306
|
+ *
|
|
|
307
|
+ * Special token types `META_AnyNonWhitespace` and `META_OptionalWhitespace`
|
|
|
308
|
+ * are special supported token types. Note that `META_OptionalWhitespace`
|
|
|
309
|
+ * may give a result with a variable number of tokens.
|
|
|
310
|
+ *
|
|
|
311
|
+ * @param (MDToken|MDNode)[] tokensToSearch - mixed array of `MDToken` and
|
|
|
312
|
+ * `MDNode` elements
|
|
|
313
|
+ * @param MDTokenType[] pattern - contiguous run of token types to find
|
|
|
314
|
+ * @param int startIndex - token index to begin searching (defaults to 0)
|
|
|
315
|
+ * @return ?MDTokenMatch match object, or `null` if not found
|
|
|
316
|
+ */
|
|
|
317
|
+ public static function findFirstTokens(array $tokensToSearch, array $pattern, int $startIndex=0): ?MDTokenMatch {
|
|
|
318
|
+ $matched = [];
|
|
|
319
|
+ for ($t = $startIndex; $t < sizeof($tokensToSearch); $t++) {
|
|
|
320
|
+ $matchedAll = true;
|
|
|
321
|
+ $matched = [];
|
|
|
322
|
+ $patternOffset = 0;
|
|
|
323
|
+ for ($p = 0; $p < mb_strlen($pattern); $p++) {
|
|
|
324
|
+ $t0 = $t + $p + $patternOffset;
|
|
|
325
|
+ if ($t0 >= sizeof($tokensToSearch)) return null;
|
|
|
326
|
+ $token = $tokensToSearch[$t0];
|
|
|
327
|
+ $elem = $pattern[$p];
|
|
|
328
|
+ if ($elem == MDTokenType::META_OptionalWhitespace) {
|
|
|
329
|
+ if ($token instanceof MDToken && $token->type == MDTokenType::Whitespace) {
|
|
|
330
|
+ array_push($matched, $token);
|
|
|
331
|
+ } else {
|
|
|
332
|
+ $patternOffset--;
|
|
|
333
|
+ }
|
|
|
334
|
+ } elseif ($elem == MDTokenType::META_AnyNonWhitespace) {
|
|
|
335
|
+ if ($token instanceof MDToken && $token->type == MDTokenType::Whitespace) {
|
|
|
336
|
+ $matchedAll = false;
|
|
|
337
|
+ break;
|
|
|
338
|
+ }
|
|
|
339
|
+ array_push($matched, $token);
|
|
|
340
|
+ } else {
|
|
|
341
|
+ if (!($token instanceof MDToken) || $token->type != $elem) {
|
|
|
342
|
+ $matchedAll = false;
|
|
|
343
|
+ break;
|
|
|
344
|
+ }
|
|
|
345
|
+ array_push($matched, $token);
|
|
|
346
|
+ }
|
|
|
347
|
+ }
|
|
|
348
|
+ if ($matchedAll) {
|
|
|
349
|
+ return new MDTokenMatch($matched, $t);
|
|
|
350
|
+ }
|
|
|
351
|
+ }
|
|
|
352
|
+ return null;
|
|
|
353
|
+ }
|
|
|
354
|
+
|
|
|
355
|
+ /**
|
|
|
356
|
+ * Searches an array of MDToken for a given starting pattern and ending
|
|
|
357
|
+ * pattern and returns match info about both and the tokens in between.
|
|
|
358
|
+ *
|
|
|
359
|
+ * If `contentValidator` is specified, it will be called with the content
|
|
|
360
|
+ * tokens of a potential match. If the validator returns `true`, the result
|
|
|
361
|
+ * will be accepted and returned by this method. If the validator returns
|
|
|
362
|
+ * `false`, this method will keep looking for another matching pair. If no
|
|
|
363
|
+ * validator is given the first match will be returned regardless of content.
|
|
|
364
|
+ *
|
|
|
365
|
+ * If a match is found, a `MDPairedTokenMatch` is returned with details
|
|
|
366
|
+ * of the opening tokens, closing tokens, and content tokens between. Otherwise
|
|
|
367
|
+ * `null` is returned.
|
|
|
368
|
+ *
|
|
|
369
|
+ * @param MDToken[] $tokensToSearch - array of `MDToken` to search in
|
|
|
370
|
+ * @param MDTokenType[] $startPattern - array of `MDTokenType` to find first
|
|
|
371
|
+ * @param MDTokenType[] $endPattern - array of `MDTokenType` to find positioned after `startPattern`
|
|
|
372
|
+ * @param ?callable $contentValidator - optional validator function. If provided, will be passed an array of inner `MDToken`, and the function can return `true` to accept the contents or `false` to keep searching
|
|
|
373
|
+ * @param number $startIndex - token index where searching should begin
|
|
|
374
|
+ * @return ?MDPairedTokenMatch match, or `null`
|
|
|
375
|
+ */
|
|
|
376
|
+ public static function findPairedTokens(array $tokensToSearch,
|
|
|
377
|
+ array $startPattern, array $endPattern, ?callable $contentValidator=null,
|
|
|
378
|
+ int $startIndex=0): ?MDPairedTokenMatch {
|
|
|
379
|
+ for ($s = $startIndex; $s < sizeof($tokensToSearch); $s++) {
|
|
|
380
|
+ $startMatch = findFirstTokens($tokensToSearch, $startPattern, $s);
|
|
|
381
|
+ if ($startMatch === null) return null;
|
|
|
382
|
+ $endStart = $startMatch->index + sizeof($startMatch->tokens);
|
|
|
383
|
+ while ($endStart < sizeof($tokensToSearch)) {
|
|
|
384
|
+ $endMatch = findFirstTokens($tokensToSearch, $endPattern, $endStart);
|
|
|
385
|
+ if ($endMatch === null) break;
|
|
|
386
|
+ $contentStart = $startMatch->index + sizeof($startMatch->tokens);
|
|
|
387
|
+ $contentLength = $endMatch->index - $contentStart;
|
|
|
388
|
+ $contents = array_slice($tokensToSearch, $contentStart, $contentLength);
|
|
|
389
|
+ if (sizeof($contents) > 0 && ($contentValidator === null || $contentValidator($contents))) {
|
|
|
390
|
+ return new MDPairedTokenMatch($startMatch->tokens,
|
|
|
391
|
+ $contents,
|
|
|
392
|
+ $endMatch->tokens,
|
|
|
393
|
+ $startMatch->index,
|
|
|
394
|
+ $startMatch->index + sizeof($startMatch->tokens),
|
|
|
395
|
+ $endMatch->index,
|
|
|
396
|
+ $endMatch->index + sizeof($endMatch->tokens) - $startMatch->index);
|
|
|
397
|
+ } else {
|
|
|
398
|
+ // Contents rejected. Try next end match.
|
|
|
399
|
+ $endStart = $endMatch->index + 1;
|
|
|
400
|
+ }
|
|
|
401
|
+ }
|
|
|
402
|
+ // No end matches. Increment start match.
|
|
|
403
|
+ $s = $startMatch->index;
|
|
|
404
|
+ }
|
|
|
405
|
+ return null;
|
|
|
406
|
+ }
|
|
|
407
|
+
|
|
|
408
|
+ public function equals($other) {
|
|
|
409
|
+ if (!($other instanceof MDToken)) return false;
|
|
|
410
|
+ if ($other->original !== $this->original) return false;
|
|
|
411
|
+ if ($other->type != $this->type) return false;
|
|
|
412
|
+ if ($other->content !== $this->content) return false;
|
|
|
413
|
+ if ($other->extra !== $this->extra) return false;
|
|
|
414
|
+ if ($other->tag !== $this->tag) return false;
|
|
|
415
|
+ if ($other->modifier != $this->modifier) return false;
|
|
|
416
|
+ return true;
|
|
|
417
|
+ }
|
|
|
418
|
+}
|
|
|
419
|
+
|
|
|
420
|
+class MDState {}
|
|
|
421
|
+
|
|
|
422
|
+class MDHTMLFilter {}
|
|
|
423
|
+
|
|
|
424
|
+class MDHTMLTag {}
|
|
|
425
|
+
|
|
|
426
|
+class MDTagModifier {}
|
|
|
427
|
+
|
|
|
428
|
+
|
|
|
429
|
+// -- Readers ---------------------------------------------------------------
|
|
|
430
|
+
|
|
|
431
|
+
|
|
|
432
|
+class MDReader {}
|
|
|
433
|
+
|
|
|
434
|
+class MDUnderlinedHeadingReader extends MDReader {}
|
|
|
435
|
+
|
|
|
436
|
+class MDHashHeadingReader extends MDReader {}
|
|
|
437
|
+
|
|
|
438
|
+class MDSubtextReader extends MDReader {}
|
|
|
439
|
+
|
|
|
440
|
+class MDBlockQuoteReader extends MDReader {}
|
|
|
441
|
+
|
|
|
442
|
+class _MDListReader extends MDReader {}
|
|
|
443
|
+
|
|
|
444
|
+class MDUnorderedListReader extends _MDListReader {}
|
|
|
445
|
+
|
|
|
446
|
+class MDOrderedListReader extends _MDListReader {}
|
|
|
447
|
+
|
|
|
448
|
+class MDFencedCodeBlockReader extends MDReader {}
|
|
|
449
|
+
|
|
|
450
|
+class MDIndentedCodeBlockReader extends MDReader {}
|
|
|
451
|
+
|
|
|
452
|
+class MDHorizontalRuleReader extends MDReader {}
|
|
|
453
|
+
|
|
|
454
|
+class MDTableReader extends MDReader {}
|
|
|
455
|
+
|
|
|
456
|
+class MDDefinitionListReader extends MDReader {}
|
|
|
457
|
+
|
|
|
458
|
+class MDFootnoteReader extends MDReader {}
|
|
|
459
|
+
|
|
|
460
|
+class MDAbbreviationReader extends MDReader {}
|
|
|
461
|
+
|
|
|
462
|
+class MDParagraphReader extends MDReader {}
|
|
|
463
|
+
|
|
|
464
|
+class MDSimplePairInlineReader extends MDReader {}
|
|
|
465
|
+
|
|
|
466
|
+class MDEmphasisReader extends MDSimplePairInlineReader {}
|
|
|
467
|
+
|
|
|
468
|
+class MDStrongReader extends MDSimplePairInlineReader {}
|
|
|
469
|
+
|
|
|
470
|
+class MDStrikethroughReader extends MDSimplePairInlineReader {}
|
|
|
471
|
+
|
|
|
472
|
+class MDUnderlineReader extends MDSimplePairInlineReader {}
|
|
|
473
|
+
|
|
|
474
|
+class MDHighlightReader extends MDSimplePairInlineReader {}
|
|
|
475
|
+
|
|
|
476
|
+class MDCodeSpanReader extends MDSimplePairInlineReader {}
|
|
|
477
|
+
|
|
|
478
|
+class MDSubscriptReader extends MDSimplePairInlineReader {}
|
|
|
479
|
+
|
|
|
480
|
+class MDSuperscriptReader extends MDSimplePairInlineReader {}
|
|
|
481
|
+
|
|
|
482
|
+class MDLinkReader extends MDReader {}
|
|
|
483
|
+
|
|
|
484
|
+class MDReferencedLinkReader extends MDLinkReader {}
|
|
|
485
|
+
|
|
|
486
|
+class MDImageReader extends MDLinkReader {}
|
|
|
487
|
+
|
|
|
488
|
+class MDReferencedImageReader extends MDReferencedLinkReader {}
|
|
|
489
|
+
|
|
|
490
|
+class MDLineBreakReader extends MDReader {}
|
|
|
491
|
+
|
|
|
492
|
+class MDHTMLTagReader extends MDReader {}
|
|
|
493
|
+
|
|
|
494
|
+class MDModifierReader extends MDReader {}
|
|
|
495
|
+
|
|
|
496
|
+
|
|
|
497
|
+// -- Nodes -----------------------------------------------------------------
|
|
|
498
|
+
|
|
|
499
|
+
|
|
|
500
|
+class MDNode {}
|
|
|
501
|
+
|
|
|
502
|
+class MDBlockNode extends MDNode {}
|
|
|
503
|
+
|
|
|
504
|
+class MDParagraphNode extends MDBlockNode {}
|
|
|
505
|
+
|
|
|
506
|
+class MDHeadingNode extends MDBlockNode {}
|
|
|
507
|
+
|
|
|
508
|
+class MDSubtextNode extends MDBlockNode {}
|
|
|
509
|
+
|
|
|
510
|
+class MDHorizontalRuleNode extends MDBlockNode {}
|
|
|
511
|
+
|
|
|
512
|
+class MDBlockquoteNode extends MDBlockNode {}
|
|
|
513
|
+
|
|
|
514
|
+class MDUnorderedListNode extends MDBlockNode {}
|
|
|
515
|
+
|
|
|
516
|
+class MDOrderedListNode extends MDBlockNode {}
|
|
|
517
|
+
|
|
|
518
|
+class MDListItemNode extends MDBlockNode {}
|
|
|
519
|
+
|
|
|
520
|
+class MDCodeBlockNode extends MDBlockNode {}
|
|
|
521
|
+
|
|
|
522
|
+class MDTableNode extends MDBlockNode {}
|
|
|
523
|
+
|
|
|
524
|
+class MDTableRowNode extends MDBlockNode {}
|
|
|
525
|
+
|
|
|
526
|
+class MDTableCellNode extends MDBlockNode {}
|
|
|
527
|
+
|
|
|
528
|
+class MDTableHeaderCellNode extends MDBlockNode {}
|
|
|
529
|
+
|
|
|
530
|
+class MDDefinitionListNode extends MDBlockNode {}
|
|
|
531
|
+
|
|
|
532
|
+class MDDefinitionListTermNode extends MDBlockNode {}
|
|
|
533
|
+
|
|
|
534
|
+class MDDefinitionListDefinitionNode extends MDBlockNode {}
|
|
|
535
|
+
|
|
|
536
|
+class MDFootnoteListNode extends MDBlockNode {}
|
|
|
537
|
+
|
|
|
538
|
+class MDInlineNode extends MDNode {}
|
|
|
539
|
+
|
|
|
540
|
+class MDTextNode extends MDInlineNode {}
|
|
|
541
|
+
|
|
|
542
|
+class MDObfuscatedTextNode extends MDTextNode {}
|
|
|
543
|
+
|
|
|
544
|
+class MDEmphasisNode extends MDInlineNode {}
|
|
|
545
|
+
|
|
|
546
|
+class MDStrongNode extends MDInlineNode {}
|
|
|
547
|
+
|
|
|
548
|
+class MDStrikethroughNode extends MDInlineNode {}
|
|
|
549
|
+
|
|
|
550
|
+class MDUnderlineNode extends MDInlineNode {}
|
|
|
551
|
+
|
|
|
552
|
+class MDHighlightNode extends MDInlineNode {}
|
|
|
553
|
+
|
|
|
554
|
+class MDSuperscriptNode extends MDInlineNode {}
|
|
|
555
|
+
|
|
|
556
|
+class MDSubscriptNode extends MDInlineNode {}
|
|
|
557
|
+
|
|
|
558
|
+class MDCodeNode extends MDInlineNode {}
|
|
|
559
|
+
|
|
|
560
|
+class MDFootnoteNode extends MDInlineNode {}
|
|
|
561
|
+
|
|
|
562
|
+class MDLinkNode extends MDInlineNode {}
|
|
|
563
|
+
|
|
|
564
|
+class MDReferencedLinkNode extends MDLinkNode {}
|
|
|
565
|
+
|
|
|
566
|
+class MDImageNode extends MDInlineNode {}
|
|
|
567
|
+
|
|
|
568
|
+class MDReferencedImageNode extends MDImageNode {}
|
|
|
569
|
+
|
|
|
570
|
+class MDAbbreviationNode extends MDInlineNode {}
|
|
|
571
|
+
|
|
|
572
|
+class MDLineBreakNode extends MDInlineNode {}
|
|
|
573
|
+
|
|
|
574
|
+class MDHTMLTagNode extends MDInlineNode {}
|
|
|
575
|
+
|
|
|
576
|
+
|
|
|
577
|
+// -- Main class ------------------------------------------------------------
|
|
|
578
|
+
|
|
|
579
|
+
|
|
|
580
|
+class Markdown {}
|
|
|
581
|
+?>
|
