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
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
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
|
<?php
namespace Masterminds\HTML5\Parser;
use Masterminds\HTML5\Exception;
/**
* The scanner scans over a given data input to react appropriately to characters.
*/
class Scanner
{
const CHARS_HEX = 'abcdefABCDEF01234567890';
const CHARS_ALNUM = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01234567890';
const CHARS_ALPHA = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ';
/**
* The string data we're parsing.
*/
private $data;
/**
* The current integer byte position we are in $data
*/
private $char;
/**
* Length of $data; when $char === $data, we are at the end-of-file.
*/
private $EOF;
/**
* Parse errors.
*/
public $errors = array();
/**
* Create a new Scanner.
*
* @param string $data Data to parse
* @param string $encoding The encoding to use for the data.
*
* @throws Exception If the given data cannot be encoded to UTF-8.
*/
public function __construct($data, $encoding = 'UTF-8')
{
if ($data instanceof InputStream) {
@trigger_error('InputStream objects are deprecated since version 2.4 and will be removed in 3.0. Use strings instead.', E_USER_DEPRECATED);
$data = (string) $data;
}
$data = UTF8Utils::convertToUTF8($data, $encoding);
// There is good reason to question whether it makes sense to
// do this here, since most of these checks are done during
// parsing, and since this check doesn't actually *do* anything.
$this->errors = UTF8Utils::checkForIllegalCodepoints($data);
$data = $this->replaceLinefeeds($data);
$this->data = $data;
$this->char = 0;
$this->EOF = strlen($data);
}
/**
* Check if upcomming chars match the given sequence.
*
* This will read the stream for the $sequence. If it's
* found, this will return true. If not, return false.
* Since this unconsumes any chars it reads, the caller
* will still need to read the next sequence, even if
* this returns true.
*
* Example: $this->scanner->sequenceMatches('</script>') will
* see if the input stream is at the start of a
* '</script>' string.
*
* @param string $sequence
* @param bool $caseSensitive
*
* @return bool
*/
public function sequenceMatches($sequence, $caseSensitive = true)
{
$portion = substr($this->data, $this->char, strlen($sequence));
return $caseSensitive ? $portion === $sequence : strcasecmp($portion, $sequence) === 0;
}
/**
* Get the current position.
*
* @return int The current intiger byte position.
*/
public function position()
{
return $this->char;
}
/**
* Take a peek at the next character in the data.
*
* @return string The next character.
*/
public function peek()
{
if (($this->char + 1) <= $this->EOF) {
return $this->data[$this->char + 1];
}
return false;
}
/**
* Get the next character.
*
* Note: This advances the pointer.
*
* @return string The next character.
*/
public function next()
{
$this->char++;
if ($this->char < $this->EOF) {
return $this->data[$this->char];
}
return false;
}
/**
* Get the current character.
*
* Note, this does not advance the pointer.
*
* @return string The current character.
*/
public function current()
{
if ($this->char < $this->EOF) {
return $this->data[$this->char];
}
return false;
}
/**
* Silently consume N chars.
*
* @param int $count
*/
public function consume($count = 1)
{
$this->char += $count;
}
/**
* Unconsume some of the data.
* This moves the data pointer backwards.
*
* @param int $howMany
* The number of characters to move the pointer back.
*/
public function unconsume($howMany = 1)
{
if (($this->char - $howMany) >= 0) {
$this->char = $this->char - $howMany;
}
}
/**
* Get the next group of that contains hex characters.
*
* Note, along with getting the characters the pointer in the data will be
* moved as well.
*
* @return string The next group that is hex characters.
*/
public function getHex()
{
return $this->doCharsWhile(static::CHARS_HEX);
}
/**
* Get the next group of characters that are ASCII Alpha characters.
*
* Note, along with getting the characters the pointer in the data will be
* moved as well.
*
* @return string The next group of ASCII alpha characters.
*/
public function getAsciiAlpha()
{
return $this->doCharsWhile(static::CHARS_ALPHA);
}
/**
* Get the next group of characters that are ASCII Alpha characters and numbers.
*
* Note, along with getting the characters the pointer in the data will be
* moved as well.
*
* @return string The next group of ASCII alpha characters and numbers.
*/
public function getAsciiAlphaNum()
{
return $this->doCharsWhile(static::CHARS_ALNUM);
}
/**
* Get the next group of numbers.
*
* Note, along with getting the characters the pointer in the data will be
* moved as well.
*
* @return string The next group of numbers.
*/
public function getNumeric()
{
return $this->doCharsWhile('0123456789');
}
/**
* Consume whitespace.
*
* Whitespace in HTML5 is: formfeed, tab, newline, space.
*/
public function whitespace()
{
return $this->doCharsWhile("\n\t\f ");
}
/**
* Returns the current line that is being consumed.
*
* @return int The current line number.
*/
public function currentLine()
{
if (empty($this->EOF) || $this->char == 0) {
return 1;
}
// Add one to $this->char because we want the number for the next
// byte to be processed.
return substr_count($this->data, "\n", 0, min($this->char, $this->EOF)) + 1;
}
/**
* Read chars until something in the mask is encountered.
*
* @param string $mask
*
* @return mixed
*/
public function charsUntil($mask)
{
return $this->doCharsUntil($mask);
}
/**
* Read chars as long as the mask matches.
*
* @param string $mask
*
* @return int
*/
public function charsWhile($mask)
{
return $this->doCharsWhile($mask);
}
/**
* Returns the current column of the current line that the tokenizer is at.
*
* Newlines are column 0. The first char after a newline is column 1.
*
* @return int The column number.
*/
public function columnOffset()
{
// Short circuit for the first char.
if ($this->char == 0) {
return 0;
}
// strrpos is weird, and the offset needs to be negative for what we
// want (i.e., the last \n before $this->char). This needs to not have
// one (to make it point to the next character, the one we want the
// position of) added to it because strrpos's behaviour includes the
// final offset byte.
$backwardFrom = $this->char - 1 - strlen($this->data);
$lastLine = strrpos($this->data, "\n", $backwardFrom);
// However, for here we want the length up until the next byte to be
// processed, so add one to the current byte ($this->char).
if ($lastLine !== false) {
$findLengthOf = substr($this->data, $lastLine + 1, $this->char - 1 - $lastLine);
} else {
// After a newline.
$findLengthOf = substr($this->data, 0, $this->char);
}
return UTF8Utils::countChars($findLengthOf);
}
/**
* Get all characters until EOF.
*
* This consumes characters until the EOF.
*
* @return int The number of characters remaining.
*/
public function remainingChars()
{
if ($this->char < $this->EOF) {
$data = substr($this->data, $this->char);
$this->char = $this->EOF;
return $data;
}
return ''; // false;
}
/**
* Replace linefeed characters according to the spec.
*
* @param $data
*
* @return string
*/
private function replaceLinefeeds($data)
{
/*
* U+000D CARRIAGE RETURN (CR) characters and U+000A LINE FEED (LF) characters are treated specially.
* Any CR characters that are followed by LF characters must be removed, and any CR characters not
* followed by LF characters must be converted to LF characters. Thus, newlines in HTML DOMs are
* represented by LF characters, and there are never any CR characters in the input to the tokenization
* stage.
*/
$crlfTable = array(
"\0" => "\xEF\xBF\xBD",
"\r\n" => "\n",
"\r" => "\n"
);
return strtr($data, $crlfTable);
}
/**
* Read to a particular match (or until $max bytes are consumed).
*
* This operates on byte sequences, not characters.
*
* Matches as far as possible until we reach a certain set of bytes
* and returns the matched substring.
*
* @param string $bytes
* Bytes to match.
* @param int $max
* Maximum number of bytes to scan.
* @return mixed Index or false if no match is found. You should use strong
* equality when checking the result, since index could be 0.
*/
private function doCharsUntil($bytes, $max = null)
{
if ($this->char >= $this->EOF) {
return false;
}
if ($max === 0 || $max) {
$len = strcspn($this->data, $bytes, $this->char, $max);
} else {
$len = strcspn($this->data, $bytes, $this->char);
}
$string = (string) substr($this->data, $this->char, $len);
$this->char += $len;
return $string;
}
/**
* Returns the string so long as $bytes matches.
*
* Matches as far as possible with a certain set of bytes
* and returns the matched substring.
*
* @param string $bytes
* A mask of bytes to match. If ANY byte in this mask matches the
* current char, the pointer advances and the char is part of the
* substring.
* @param int $max
* The max number of chars to read.
*
* @return string
*/
private function doCharsWhile($bytes, $max = null)
{
if ($this->char >= $this->EOF) {
return false;
}
if ($max === 0 || $max) {
$len = strspn($this->data, $bytes, $this->char, $max);
} else {
$len = strspn($this->data, $bytes, $this->char);
}
$string = (string) substr($this->data, $this->char, $len);
$this->char += $len;
return $string;
}
}
|