1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
declare(strict_types=1); |
4
|
|
|
|
5
|
|
|
namespace PHPHtmlParser\Dom\Node; |
6
|
|
|
|
7
|
|
|
use PHPHtmlParser\Contracts\Selector\SelectorInterface; |
8
|
|
|
use PHPHtmlParser\Exceptions\ChildNotFoundException; |
9
|
|
|
use PHPHtmlParser\Exceptions\CircularException; |
10
|
|
|
use PHPHtmlParser\Exceptions\ParentNotFoundException; |
11
|
|
|
use PHPHtmlParser\Exceptions\Tag\AttributeNotFoundException; |
12
|
|
|
use PHPHtmlParser\Dom\Tag; |
13
|
|
|
use PHPHtmlParser\Finder; |
14
|
|
|
use PHPHtmlParser\Selector\Selector; |
15
|
|
|
use stringEncode\Encode; |
16
|
|
|
|
17
|
|
|
/** |
18
|
|
|
* Dom node object. |
19
|
|
|
* |
20
|
|
|
* @property string $outerhtml |
21
|
|
|
* @property string $innerhtml |
22
|
|
|
* @property string $text |
23
|
|
|
* @property int $prev |
24
|
|
|
* @property int $next |
25
|
|
|
* @property Tag $tag |
26
|
|
|
* @property InnerNode $parent |
27
|
|
|
*/ |
28
|
|
|
abstract class AbstractNode |
29
|
|
|
{ |
30
|
|
|
/** |
31
|
|
|
* Contains the tag name/type. |
32
|
|
|
* |
33
|
|
|
* @var ?Tag |
34
|
|
|
*/ |
35
|
|
|
protected $tag; |
36
|
|
|
|
37
|
|
|
/** |
38
|
|
|
* Contains a list of attributes on this tag. |
39
|
|
|
* |
40
|
|
|
* @var array |
41
|
|
|
*/ |
42
|
|
|
protected $attr = []; |
43
|
|
|
|
44
|
|
|
/** |
45
|
|
|
* Contains the parent Node. |
46
|
|
|
* |
47
|
|
|
* @var ?InnerNode |
48
|
|
|
*/ |
49
|
|
|
protected $parent; |
50
|
|
|
|
51
|
|
|
/** |
52
|
|
|
* The unique id of the class. Given by PHP. |
53
|
|
|
* |
54
|
|
|
* @var int |
55
|
|
|
*/ |
56
|
|
|
protected $id; |
57
|
|
|
|
58
|
|
|
/** |
59
|
|
|
* The encoding class used to encode strings. |
60
|
|
|
* |
61
|
|
|
* @var mixed |
62
|
|
|
*/ |
63
|
|
|
protected $encode; |
64
|
|
|
|
65
|
|
|
/** |
66
|
|
|
* An array of all the children. |
67
|
|
|
* |
68
|
|
|
* @var array |
69
|
|
|
*/ |
70
|
|
|
protected $children = []; |
71
|
|
|
|
72
|
|
|
/** |
73
|
|
|
* @var bool |
74
|
|
|
*/ |
75
|
|
|
protected $htmlSpecialCharsDecode = false; |
76
|
|
|
/** |
77
|
|
|
* @var int |
78
|
|
|
*/ |
79
|
|
|
private static $count = 0; |
80
|
|
|
|
81
|
|
|
/** |
82
|
|
|
* Creates a unique id for this node. |
83
|
|
|
*/ |
84
|
552 |
|
public function __construct() |
85
|
|
|
{ |
86
|
552 |
|
$this->id = self::$count; |
87
|
552 |
|
++self::$count; |
88
|
552 |
|
} |
89
|
|
|
|
90
|
|
|
/** |
91
|
|
|
* Attempts to clear out any object references. |
92
|
|
|
*/ |
93
|
133 |
|
public function __destruct() |
94
|
|
|
{ |
95
|
133 |
|
$this->tag = null; |
96
|
133 |
|
$this->parent = null; |
97
|
133 |
|
$this->attr = []; |
98
|
133 |
|
$this->children = []; |
99
|
133 |
|
} |
100
|
|
|
|
101
|
|
|
/** |
102
|
|
|
* Magic get method for attributes and certain methods. |
103
|
|
|
* |
104
|
|
|
* @return mixed |
105
|
|
|
*/ |
106
|
318 |
|
public function __get(string $key) |
107
|
|
|
{ |
108
|
|
|
// check attribute first |
109
|
318 |
|
if ($this->getAttribute($key) !== null) { |
110
|
18 |
|
return $this->getAttribute($key); |
111
|
|
|
} |
112
|
315 |
|
switch (\strtolower($key)) { |
113
|
315 |
|
case 'outerhtml': |
114
|
39 |
|
return $this->outerHtml(); |
115
|
306 |
|
case 'innerhtml': |
116
|
78 |
|
return $this->innerHtml(); |
117
|
303 |
|
case 'text': |
118
|
51 |
|
return $this->text(); |
119
|
288 |
|
case 'tag': |
120
|
288 |
|
return $this->getTag(); |
121
|
3 |
|
case 'parent': |
122
|
|
|
return $this->getParent(); |
123
|
|
|
} |
124
|
3 |
|
} |
125
|
|
|
|
126
|
|
|
/** |
127
|
|
|
* Simply calls the outer text method. |
128
|
|
|
* |
129
|
|
|
* @return string |
130
|
|
|
*/ |
131
|
9 |
|
public function __toString() |
132
|
|
|
{ |
133
|
9 |
|
return $this->outerHtml(); |
134
|
|
|
} |
135
|
|
|
|
136
|
|
|
/** |
137
|
|
|
* @param bool $htmlSpecialCharsDecode |
138
|
|
|
*/ |
139
|
285 |
|
public function setHtmlSpecialCharsDecode($htmlSpecialCharsDecode = false): void |
140
|
|
|
{ |
141
|
285 |
|
$this->htmlSpecialCharsDecode = $htmlSpecialCharsDecode; |
142
|
285 |
|
} |
143
|
|
|
|
144
|
|
|
/** |
145
|
|
|
* Returns the id of this object. |
146
|
|
|
*/ |
147
|
483 |
|
public function id(): int |
148
|
|
|
{ |
149
|
483 |
|
return $this->id; |
150
|
|
|
} |
151
|
|
|
|
152
|
|
|
/** |
153
|
|
|
* Returns the parent of node. |
154
|
|
|
* |
155
|
|
|
* @return AbstractNode |
156
|
|
|
*/ |
157
|
258 |
|
public function getParent() |
158
|
|
|
{ |
159
|
258 |
|
return $this->parent; |
160
|
|
|
} |
161
|
|
|
|
162
|
|
|
/** |
163
|
|
|
* Sets the parent node. |
164
|
|
|
* |
165
|
|
|
* @throws ChildNotFoundException |
166
|
|
|
* @throws CircularException |
167
|
|
|
*/ |
168
|
477 |
|
public function setParent(InnerNode $parent): AbstractNode |
169
|
|
|
{ |
170
|
|
|
// remove from old parent |
171
|
477 |
|
if ($this->parent !== null) { |
172
|
33 |
|
if ($this->parent->id() == $parent->id()) { |
173
|
|
|
// already the parent |
174
|
27 |
|
return $this; |
175
|
|
|
} |
176
|
|
|
|
177
|
9 |
|
$this->parent->removeChild($this->id); |
178
|
|
|
} |
179
|
|
|
|
180
|
477 |
|
$this->parent = $parent; |
181
|
|
|
|
182
|
|
|
// assign child to parent |
183
|
477 |
|
$this->parent->addChild($this); |
184
|
|
|
|
185
|
477 |
|
return $this; |
186
|
|
|
} |
187
|
|
|
|
188
|
|
|
/** |
189
|
|
|
* Removes this node and all its children from the |
190
|
|
|
* DOM tree. |
191
|
|
|
* |
192
|
|
|
* @return void |
193
|
|
|
*/ |
194
|
3 |
|
public function delete() |
195
|
|
|
{ |
196
|
3 |
|
if ($this->parent !== null) { |
197
|
3 |
|
$this->parent->removeChild($this->id); |
198
|
|
|
} |
199
|
3 |
|
$this->parent->clear(); |
200
|
3 |
|
$this->clear(); |
201
|
3 |
|
} |
202
|
|
|
|
203
|
|
|
/** |
204
|
|
|
* Sets the encoding class to this node. |
205
|
|
|
* |
206
|
|
|
* @return void |
207
|
|
|
*/ |
208
|
243 |
|
public function propagateEncoding(Encode $encode) |
209
|
|
|
{ |
210
|
243 |
|
$this->encode = $encode; |
211
|
243 |
|
$this->tag->setEncoding($encode); |
212
|
243 |
|
} |
213
|
|
|
|
214
|
|
|
/** |
215
|
|
|
* Checks if the given node id is an ancestor of |
216
|
|
|
* the current node. |
217
|
|
|
*/ |
218
|
480 |
|
public function isAncestor(int $id): bool |
219
|
|
|
{ |
220
|
480 |
|
if ($this->getAncestor($id) !== null) { |
221
|
6 |
|
return true; |
222
|
|
|
} |
223
|
|
|
|
224
|
480 |
|
return false; |
225
|
|
|
} |
226
|
|
|
|
227
|
|
|
/** |
228
|
|
|
* Attempts to get an ancestor node by the given id. |
229
|
|
|
* |
230
|
|
|
* @return AbstractNode|null |
231
|
|
|
*/ |
232
|
483 |
|
public function getAncestor(int $id) |
233
|
|
|
{ |
234
|
483 |
|
if ($this->parent !== null) { |
235
|
327 |
|
if ($this->parent->id() == $id) { |
236
|
12 |
|
return $this->parent; |
237
|
|
|
} |
238
|
|
|
|
239
|
318 |
|
return $this->parent->getAncestor($id); |
240
|
|
|
} |
241
|
483 |
|
} |
242
|
|
|
|
243
|
|
|
/** |
244
|
|
|
* Checks if the current node has a next sibling. |
245
|
|
|
*/ |
246
|
|
|
public function hasNextSibling(): bool |
247
|
|
|
{ |
248
|
|
|
try { |
249
|
|
|
$this->nextSibling(); |
250
|
|
|
|
251
|
|
|
// sibling found, return true; |
252
|
|
|
return true; |
253
|
|
|
} catch (ParentNotFoundException $e) { |
254
|
|
|
// no parent, no next sibling |
255
|
|
|
unset($e); |
256
|
|
|
|
257
|
|
|
return false; |
258
|
|
|
} catch (ChildNotFoundException $e) { |
259
|
|
|
// no sibling found |
260
|
|
|
unset($e); |
261
|
|
|
|
262
|
|
|
return false; |
263
|
|
|
} |
264
|
|
|
} |
265
|
|
|
|
266
|
|
|
/** |
267
|
|
|
* Attempts to get the next sibling. |
268
|
|
|
* |
269
|
|
|
* @throws ChildNotFoundException |
270
|
|
|
* @throws ParentNotFoundException |
271
|
|
|
*/ |
272
|
30 |
|
public function nextSibling(): AbstractNode |
273
|
|
|
{ |
274
|
30 |
|
if ($this->parent === null) { |
275
|
3 |
|
throw new ParentNotFoundException('Parent is not set for this node.'); |
276
|
|
|
} |
277
|
|
|
|
278
|
27 |
|
return $this->parent->nextChild($this->id); |
279
|
|
|
} |
280
|
|
|
|
281
|
|
|
/** |
282
|
|
|
* Attempts to get the previous sibling. |
283
|
|
|
* |
284
|
|
|
* @throws ChildNotFoundException |
285
|
|
|
* @throws ParentNotFoundException |
286
|
|
|
*/ |
287
|
9 |
|
public function previousSibling(): AbstractNode |
288
|
|
|
{ |
289
|
9 |
|
if ($this->parent === null) { |
290
|
3 |
|
throw new ParentNotFoundException('Parent is not set for this node.'); |
291
|
|
|
} |
292
|
|
|
|
293
|
6 |
|
return $this->parent->previousChild($this->id); |
294
|
|
|
} |
295
|
|
|
|
296
|
|
|
/** |
297
|
|
|
* Gets the tag object of this node. |
298
|
|
|
*/ |
299
|
354 |
|
public function getTag(): Tag |
300
|
|
|
{ |
301
|
354 |
|
return $this->tag; |
302
|
|
|
} |
303
|
|
|
|
304
|
|
|
/** |
305
|
|
|
* Replaces the tag for this node. |
306
|
|
|
* |
307
|
|
|
* @param string|Tag $tag |
308
|
|
|
* |
309
|
|
|
*/ |
310
|
3 |
|
public function setTag($tag): AbstractNode |
311
|
|
|
{ |
312
|
3 |
|
if (\is_string($tag)) { |
313
|
3 |
|
$tag = new Tag($tag); |
314
|
|
|
} |
315
|
|
|
|
316
|
3 |
|
$this->tag = $tag; |
317
|
|
|
|
318
|
|
|
// clear any cache |
319
|
3 |
|
$this->clear(); |
320
|
|
|
|
321
|
3 |
|
return $this; |
322
|
|
|
} |
323
|
|
|
|
324
|
|
|
/** |
325
|
|
|
* A wrapper method that simply calls the getAttribute method |
326
|
|
|
* on the tag of this node. |
327
|
|
|
*/ |
328
|
6 |
|
public function getAttributes(): array |
329
|
|
|
{ |
330
|
6 |
|
$attributes = $this->tag->getAttributes(); |
331
|
6 |
|
foreach ($attributes as $name => $attributeDTO) { |
332
|
3 |
|
$attributes[$name] = $attributeDTO->getValue(); |
333
|
|
|
} |
334
|
|
|
|
335
|
6 |
|
return $attributes; |
336
|
|
|
} |
337
|
|
|
|
338
|
|
|
/** |
339
|
|
|
* A wrapper method that simply calls the getAttribute method |
340
|
|
|
* on the tag of this node. |
341
|
|
|
*/ |
342
|
339 |
|
public function getAttribute(string $key): ?string |
343
|
|
|
{ |
344
|
|
|
try { |
345
|
339 |
|
$attributeDTO = $this->tag->getAttribute($key); |
346
|
318 |
|
} catch (AttributeNotFoundException $e) { |
347
|
|
|
// no attribute with this key exists, returning null. |
348
|
318 |
|
unset($e); |
349
|
|
|
|
350
|
318 |
|
return null; |
351
|
|
|
} |
352
|
|
|
|
353
|
144 |
|
return $attributeDTO->getValue(); |
354
|
|
|
} |
355
|
|
|
|
356
|
|
|
/** |
357
|
|
|
* A wrapper method that simply calls the hasAttribute method |
358
|
|
|
* on the tag of this node. |
359
|
|
|
*/ |
360
|
120 |
|
public function hasAttribute(string $key): bool |
361
|
|
|
{ |
362
|
120 |
|
return $this->tag->hasAttribute($key); |
363
|
|
|
} |
364
|
|
|
|
365
|
|
|
/** |
366
|
|
|
* A wrapper method that simply calls the setAttribute method |
367
|
|
|
* on the tag of this node. |
368
|
|
|
* |
369
|
|
|
* |
370
|
|
|
*/ |
371
|
24 |
|
public function setAttribute(string $key, ?string $value, bool $doubleQuote = true): AbstractNode |
372
|
|
|
{ |
373
|
24 |
|
$this->tag->setAttribute($key, $value, $doubleQuote); |
374
|
|
|
|
375
|
|
|
//clear any cache |
376
|
24 |
|
$this->clear(); |
377
|
|
|
|
378
|
24 |
|
return $this; |
379
|
|
|
} |
380
|
|
|
|
381
|
|
|
/** |
382
|
|
|
* A wrapper method that simply calls the removeAttribute method |
383
|
|
|
* on the tag of this node. |
384
|
|
|
*/ |
385
|
3 |
|
public function removeAttribute(string $key): void |
386
|
|
|
{ |
387
|
3 |
|
$this->tag->removeAttribute($key); |
388
|
|
|
|
389
|
|
|
//clear any cache |
390
|
3 |
|
$this->clear(); |
391
|
3 |
|
} |
392
|
|
|
|
393
|
|
|
/** |
394
|
|
|
* A wrapper method that simply calls the removeAllAttributes |
395
|
|
|
* method on the tag of this node. |
396
|
|
|
*/ |
397
|
3 |
|
public function removeAllAttributes(): void |
398
|
|
|
{ |
399
|
3 |
|
$this->tag->removeAllAttributes(); |
400
|
|
|
|
401
|
|
|
//clear any cache |
402
|
3 |
|
$this->clear(); |
403
|
3 |
|
} |
404
|
|
|
|
405
|
|
|
/** |
406
|
|
|
* Function to locate a specific ancestor tag in the path to the root. |
407
|
|
|
* |
408
|
|
|
* @throws ParentNotFoundException |
409
|
|
|
*/ |
410
|
6 |
|
public function ancestorByTag(string $tag): AbstractNode |
411
|
|
|
{ |
412
|
|
|
// Start by including ourselves in the comparison. |
413
|
6 |
|
$node = $this; |
414
|
|
|
|
415
|
|
|
do { |
416
|
6 |
|
if ($node->tag->name() == $tag) { |
417
|
3 |
|
return $node; |
418
|
|
|
} |
419
|
|
|
|
420
|
3 |
|
$node = $node->getParent(); |
421
|
3 |
|
} while ($node !== null); |
422
|
|
|
|
423
|
3 |
|
throw new ParentNotFoundException('Could not find an ancestor with "' . $tag . '" tag'); |
424
|
|
|
} |
425
|
|
|
|
426
|
|
|
/** |
427
|
|
|
* Find elements by css selector. |
428
|
|
|
* |
429
|
|
|
* @throws ChildNotFoundException |
430
|
|
|
* |
431
|
|
|
* @return mixed|Collection|null |
432
|
|
|
*/ |
433
|
279 |
|
public function find(string $selectorString, ?int $nth = null, ?SelectorInterface $selector = null) |
434
|
|
|
{ |
435
|
279 |
|
if (\is_null($selector)) { |
436
|
279 |
|
$selector = new Selector($selectorString); |
437
|
|
|
} |
438
|
|
|
|
439
|
279 |
|
$nodes = $selector->find($this); |
440
|
|
|
|
441
|
279 |
|
if ($nth !== null) { |
442
|
|
|
// return nth-element or array |
443
|
279 |
|
if (isset($nodes[$nth])) { |
444
|
129 |
|
return $nodes[$nth]; |
445
|
|
|
} |
446
|
|
|
|
447
|
249 |
|
return; |
448
|
|
|
} |
449
|
|
|
|
450
|
111 |
|
return $nodes; |
451
|
|
|
} |
452
|
|
|
|
453
|
|
|
/** |
454
|
|
|
* Find node by id. |
455
|
|
|
* |
456
|
|
|
* @throws ChildNotFoundException |
457
|
|
|
* @throws ParentNotFoundException |
458
|
|
|
* |
459
|
|
|
* @return bool|AbstractNode |
460
|
|
|
*/ |
461
|
|
|
public function findById(int $id) |
462
|
|
|
{ |
463
|
|
|
$finder = new Finder($id); |
464
|
|
|
|
465
|
|
|
return $finder->find($this); |
466
|
|
|
} |
467
|
|
|
|
468
|
|
|
/** |
469
|
|
|
* Gets the inner html of this node. |
470
|
|
|
*/ |
471
|
|
|
abstract public function innerHtml(): string; |
472
|
|
|
|
473
|
|
|
/** |
474
|
|
|
* Gets the html of this node, including it's own |
475
|
|
|
* tag. |
476
|
|
|
*/ |
477
|
|
|
abstract public function outerHtml(): string; |
478
|
|
|
|
479
|
|
|
/** |
480
|
|
|
* Gets the text of this node (if there is any text). |
481
|
|
|
*/ |
482
|
|
|
abstract public function text(): string; |
483
|
|
|
|
484
|
|
|
/** |
485
|
|
|
* Check is node type textNode. |
486
|
|
|
*/ |
487
|
|
|
public function isTextNode(): bool |
488
|
|
|
{ |
489
|
|
|
return false; |
490
|
|
|
} |
491
|
|
|
|
492
|
|
|
/** |
493
|
|
|
* Call this when something in the node tree has changed. Like a child has been added |
494
|
|
|
* or a parent has been changed. |
495
|
|
|
*/ |
496
|
|
|
abstract protected function clear(): void; |
497
|
|
|
} |
498
|
|
|
|