|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/** |
|
4
|
|
|
* Rss/Atom Bundle for Symfony. |
|
5
|
|
|
* |
|
6
|
|
|
* |
|
7
|
|
|
* @license http://opensource.org/licenses/lgpl-3.0.html LGPL |
|
8
|
|
|
* @copyright (c) 2013, Alexandre Debril |
|
9
|
|
|
*/ |
|
10
|
|
|
namespace Debril\RssAtomBundle\Protocol; |
|
11
|
|
|
|
|
12
|
|
|
use Debril\RssAtomBundle\Protocol\Filter\ModifiedSince; |
|
13
|
|
|
use Debril\RssAtomBundle\Protocol\Parser\Item; |
|
14
|
|
|
use Debril\RssAtomBundle\Exception\ParserException; |
|
15
|
|
|
use Debril\RssAtomBundle\Protocol\Parser\Factory; |
|
16
|
|
|
use Debril\RssAtomBundle\Protocol\Parser\Media; |
|
17
|
|
|
|
|
18
|
|
|
/** |
|
19
|
|
|
* Class Parser. |
|
20
|
|
|
*/ |
|
21
|
|
|
abstract class Parser |
|
22
|
|
|
{ |
|
23
|
|
|
/** |
|
24
|
|
|
* System's time zone. |
|
25
|
|
|
* |
|
26
|
|
|
* @var \DateTimeZone |
|
27
|
|
|
*/ |
|
28
|
|
|
protected static $timezone; |
|
29
|
|
|
|
|
30
|
|
|
/** |
|
31
|
|
|
* List of mandatory fields. |
|
32
|
|
|
* |
|
33
|
|
|
* @var string[] |
|
34
|
|
|
*/ |
|
35
|
|
|
protected $mandatoryFields = array(); |
|
36
|
|
|
|
|
37
|
|
|
/** |
|
38
|
|
|
* Feed's date format. |
|
39
|
|
|
* |
|
40
|
|
|
* @var string[] |
|
41
|
|
|
*/ |
|
42
|
|
|
protected $dateFormats = array(); |
|
43
|
|
|
|
|
44
|
|
|
/** |
|
45
|
|
|
* @var Factory |
|
46
|
|
|
*/ |
|
47
|
|
|
protected $factory; |
|
48
|
|
|
|
|
49
|
|
|
/** |
|
50
|
|
|
* Parses the feed's body to create a FeedContent instance. |
|
51
|
|
|
* |
|
52
|
|
|
* @param \SimpleXMLElement $xmlBody |
|
53
|
|
|
* @param \Debril\RssAtomBundle\Protocol\FeedInterface $feed |
|
54
|
|
|
* @param array $filters |
|
55
|
|
|
* |
|
56
|
|
|
* @throws ParserException |
|
57
|
|
|
* |
|
58
|
|
|
* @return FeedInterface |
|
59
|
|
|
*/ |
|
60
|
5 |
|
public function parse(\SimpleXMLElement $xmlBody, FeedInterface $feed, array $filters = array()) |
|
61
|
|
|
{ |
|
62
|
5 |
|
if (!$this->canHandle($xmlBody)) { |
|
63
|
1 |
|
throw new ParserException('this is not a supported format'); |
|
64
|
|
|
} |
|
65
|
|
|
|
|
66
|
4 |
|
$this->checkBodyStructure($xmlBody); |
|
67
|
|
|
|
|
68
|
4 |
|
$xmlBody = $this->registerNamespaces($xmlBody); |
|
69
|
|
|
|
|
70
|
4 |
|
return $this->parseBody($xmlBody, $feed, $filters); |
|
71
|
|
|
} |
|
72
|
|
|
|
|
73
|
|
|
/** |
|
74
|
|
|
* @param \SimpleXMLElement $body |
|
75
|
|
|
* |
|
76
|
|
|
* @throws ParserException |
|
77
|
|
|
*/ |
|
78
|
5 |
|
protected function checkBodyStructure(\SimpleXMLElement $body) |
|
79
|
|
|
{ |
|
80
|
5 |
|
$errors = array(); |
|
81
|
|
|
|
|
82
|
5 |
|
foreach ($this->mandatoryFields as $field) { |
|
83
|
5 |
|
if (!isset($body->$field)) { |
|
84
|
2 |
|
$errors[] = "missing {$field}"; |
|
85
|
2 |
|
} |
|
86
|
5 |
|
} |
|
87
|
|
|
|
|
88
|
5 |
|
if (0 < count($errors)) { |
|
89
|
2 |
|
$report = implode(', ', $errors); |
|
90
|
2 |
|
throw new ParserException( |
|
91
|
2 |
|
"error while parsing the feed : {$report}" |
|
92
|
2 |
|
); |
|
93
|
|
|
} |
|
94
|
3 |
|
} |
|
95
|
|
|
|
|
96
|
|
|
/** |
|
97
|
|
|
* @param array $dates |
|
98
|
|
|
*/ |
|
99
|
10 |
|
public function setDateFormats(array $dates) |
|
100
|
|
|
{ |
|
101
|
10 |
|
$this->dateFormats = $dates; |
|
102
|
10 |
|
} |
|
103
|
|
|
|
|
104
|
|
|
/** |
|
105
|
|
|
* @param string $date |
|
106
|
|
|
* |
|
107
|
|
|
* @return string date Format |
|
108
|
|
|
* |
|
109
|
|
|
* @throws ParserException |
|
110
|
|
|
*/ |
|
111
|
9 |
|
public function guessDateFormat($date) |
|
112
|
|
|
{ |
|
113
|
9 |
|
foreach ($this->dateFormats as $format) { |
|
114
|
9 |
|
$test = \DateTime::createFromFormat($format, $date); |
|
115
|
9 |
|
if ($test instanceof \DateTime) { |
|
116
|
6 |
|
return $format; |
|
117
|
|
|
} |
|
118
|
6 |
|
} |
|
119
|
|
|
|
|
120
|
3 |
|
throw new ParserException('Impossible to guess date format : '.$date); |
|
121
|
|
|
} |
|
122
|
|
|
|
|
123
|
|
|
/** |
|
124
|
|
|
* @return ItemInInterface |
|
125
|
|
|
*/ |
|
126
|
3 |
|
public function newItem() |
|
127
|
|
|
{ |
|
128
|
3 |
|
if ($this->getFactory() instanceof Factory) { |
|
129
|
1 |
|
return $this->getFactory()->newItem(); |
|
130
|
|
|
} |
|
131
|
|
|
|
|
132
|
2 |
|
return new Item(); |
|
133
|
|
|
} |
|
134
|
|
|
|
|
135
|
|
|
/** |
|
136
|
|
|
* @return Factory |
|
137
|
|
|
*/ |
|
138
|
3 |
|
public function getFactory() |
|
139
|
|
|
{ |
|
140
|
3 |
|
return $this->factory; |
|
141
|
|
|
} |
|
142
|
|
|
|
|
143
|
|
|
/** |
|
144
|
|
|
* @param Factory $factory |
|
145
|
|
|
* |
|
146
|
|
|
* @return Parser |
|
147
|
|
|
*/ |
|
148
|
2 |
|
public function setFactory(Factory $factory) |
|
149
|
|
|
{ |
|
150
|
2 |
|
$this->factory = $factory; |
|
151
|
|
|
|
|
152
|
2 |
|
return $this; |
|
153
|
|
|
} |
|
154
|
|
|
|
|
155
|
|
|
/** |
|
156
|
|
|
* @deprecated since 1.3.0 replaced by addValidItem |
|
157
|
|
|
* |
|
158
|
|
|
* @param FeedInInterface $feed |
|
159
|
|
|
* @param ItemInInterface $item |
|
160
|
|
|
* @param \DateTime $modifiedSince |
|
161
|
|
|
* |
|
162
|
|
|
* @return $this |
|
163
|
|
|
*/ |
|
164
|
2 |
|
public function addAcceptableItem(FeedInInterface $feed, ItemInInterface $item, \DateTime $modifiedSince) |
|
165
|
|
|
{ |
|
166
|
|
|
$filters = array( |
|
167
|
2 |
|
new ModifiedSince($modifiedSince), |
|
168
|
2 |
|
); |
|
169
|
|
|
|
|
170
|
2 |
|
return $this->addValidItem($feed, $item, $filters); |
|
171
|
|
|
} |
|
172
|
|
|
|
|
173
|
|
|
/** |
|
174
|
|
|
* @param FeedInInterface $feed |
|
175
|
|
|
* @param ItemInInterface $item |
|
176
|
|
|
* @param array $filters |
|
177
|
|
|
* |
|
178
|
|
|
* @return $this |
|
179
|
|
|
*/ |
|
180
|
3 |
|
public function addValidItem(FeedInInterface $feed, ItemInInterface $item, array $filters = array()) |
|
181
|
|
|
{ |
|
182
|
3 |
|
if ($this->isValid($item, $filters)) { |
|
183
|
3 |
|
$feed->addItem($item); |
|
184
|
3 |
|
} |
|
185
|
|
|
|
|
186
|
3 |
|
return $this; |
|
187
|
|
|
} |
|
188
|
|
|
|
|
189
|
|
|
/** |
|
190
|
|
|
* @param ItemInInterface $item |
|
191
|
|
|
* @param array $filters |
|
192
|
|
|
* |
|
193
|
|
|
* @return bool |
|
194
|
|
|
*/ |
|
195
|
3 |
|
public function isValid(ItemInInterface $item, array $filters = array()) |
|
196
|
|
|
{ |
|
197
|
3 |
|
$valid = true; |
|
198
|
3 |
|
foreach ($filters as $filter) { |
|
199
|
3 |
|
if ($filter instanceof FilterInterface) { |
|
200
|
3 |
|
$valid = $filter->isValid($item) ? $valid : false; |
|
|
|
|
|
|
201
|
3 |
|
} |
|
202
|
3 |
|
} |
|
203
|
|
|
|
|
204
|
3 |
|
return $valid; |
|
205
|
|
|
} |
|
206
|
|
|
|
|
207
|
|
|
/** |
|
208
|
|
|
* Creates a DateTime instance for the given string. Default format is RFC2822. |
|
209
|
|
|
* |
|
210
|
|
|
* @param string $string |
|
211
|
|
|
* @param string $format |
|
212
|
|
|
* |
|
213
|
|
|
* @return \DateTime |
|
214
|
|
|
*/ |
|
215
|
5 |
|
public static function convertToDateTime($string, $format = \DateTime::RFC2822) |
|
216
|
|
|
{ |
|
217
|
5 |
|
$date = \DateTime::createFromFormat($format, $string); |
|
218
|
|
|
|
|
219
|
5 |
|
if (!$date instanceof \DateTime) { |
|
220
|
1 |
|
throw new ParserException("date is the wrong format : {$string} - expected {$format}"); |
|
221
|
|
|
} |
|
222
|
|
|
|
|
223
|
4 |
|
$date->setTimezone(static::getSystemTimezone()); |
|
224
|
|
|
|
|
225
|
4 |
|
return $date; |
|
226
|
|
|
} |
|
227
|
|
|
|
|
228
|
|
|
/** |
|
229
|
|
|
* Returns the system's timezone. |
|
230
|
|
|
* |
|
231
|
|
|
* @return \DateTimeZone |
|
232
|
|
|
*/ |
|
233
|
4 |
|
public static function getSystemTimezone() |
|
234
|
|
|
{ |
|
235
|
4 |
|
if (is_null(static::$timezone)) { |
|
236
|
1 |
|
static::$timezone = new \DateTimeZone(date_default_timezone_get()); |
|
237
|
1 |
|
} |
|
238
|
|
|
|
|
239
|
4 |
|
return static::$timezone; |
|
240
|
|
|
} |
|
241
|
|
|
|
|
242
|
|
|
/** |
|
243
|
|
|
* Reset the system's time zone. |
|
244
|
|
|
*/ |
|
245
|
1 |
|
public static function resetTimezone() |
|
246
|
|
|
{ |
|
247
|
1 |
|
static::$timezone = null; |
|
248
|
1 |
|
} |
|
249
|
|
|
|
|
250
|
|
|
/** |
|
251
|
|
|
* register Namespaces. |
|
252
|
|
|
* |
|
253
|
|
|
* @param \SimpleXMLElement $xmlBody |
|
254
|
|
|
* |
|
255
|
|
|
* @return \SimpleXMLElement |
|
256
|
|
|
*/ |
|
257
|
3 |
|
protected function registerNamespaces(\SimpleXMLElement $xmlBody) |
|
258
|
|
|
{ |
|
259
|
3 |
|
$namespaces = $xmlBody->getNamespaces(true); |
|
260
|
3 |
|
foreach ($namespaces as $prefix => $ns) { |
|
261
|
3 |
|
if ($prefix != '') { |
|
262
|
1 |
|
$xmlBody->registerXPathNamespace($prefix, $ns); |
|
263
|
1 |
|
} |
|
264
|
3 |
|
} |
|
265
|
|
|
|
|
266
|
3 |
|
return $xmlBody; |
|
267
|
|
|
} |
|
268
|
|
|
|
|
269
|
|
|
/** |
|
270
|
|
|
* @param \SimpleXMLElement $xmlElement |
|
271
|
|
|
* @param array $namespaces |
|
272
|
|
|
* |
|
273
|
|
|
* @return array |
|
274
|
|
|
*/ |
|
275
|
3 |
|
protected function getAdditionalNamespacesElements(\SimpleXMLElement $xmlElement, $namespaces) |
|
276
|
|
|
{ |
|
277
|
3 |
|
$additional = array(); |
|
278
|
3 |
|
foreach ($namespaces as $prefix => $ns) { |
|
279
|
3 |
|
if ($prefix != '') { |
|
280
|
1 |
|
$additionalElement = $xmlElement->children($ns); |
|
281
|
1 |
|
if (!empty($additionalElement)) { |
|
282
|
1 |
|
$additional[$prefix] = $additionalElement; |
|
283
|
1 |
|
} |
|
284
|
1 |
|
} |
|
285
|
3 |
|
} |
|
286
|
|
|
|
|
287
|
3 |
|
return $additional; |
|
288
|
|
|
} |
|
289
|
|
|
|
|
290
|
|
|
/** |
|
291
|
|
|
* @param \SimpleXMLElement $element |
|
292
|
|
|
* @param string $attributeName |
|
293
|
|
|
* |
|
294
|
|
|
* @return string|null |
|
295
|
|
|
*/ |
|
296
|
6 |
|
public function getAttributeValue(\SimpleXMLElement $element, $attributeName) |
|
297
|
|
|
{ |
|
298
|
6 |
|
$attributes = $element[0]->attributes(); |
|
299
|
6 |
|
foreach ($attributes as $name => $value) { |
|
300
|
6 |
|
if (strcasecmp($name, $attributeName) === 0) { |
|
301
|
6 |
|
return (string) $value; |
|
302
|
|
|
} |
|
303
|
6 |
|
} |
|
304
|
|
|
|
|
305
|
5 |
|
return; |
|
306
|
|
|
} |
|
307
|
|
|
|
|
308
|
|
|
/** |
|
309
|
|
|
* @param \SimpleXMLElement $element |
|
310
|
|
|
* |
|
311
|
|
|
* @return Media |
|
312
|
|
|
*/ |
|
313
|
2 |
|
public function createMedia(\SimpleXMLElement $element) |
|
314
|
|
|
{ |
|
315
|
2 |
|
$media = new Media(); |
|
316
|
2 |
|
$media->setUrl($this->searchAttributeValue($element, array('url', 'href', 'link'))) |
|
317
|
2 |
|
->setType($this->getAttributeValue($element, 'type')) |
|
318
|
2 |
|
->setLength($this->getAttributeValue($element, 'length')); |
|
319
|
|
|
|
|
320
|
2 |
|
return $media; |
|
321
|
|
|
} |
|
322
|
|
|
|
|
323
|
|
|
/** |
|
324
|
|
|
* Looks for an attribute value under different possible names. |
|
325
|
|
|
* |
|
326
|
|
|
* @param \SimpleXMLElement $element |
|
327
|
|
|
* @param array $names |
|
328
|
|
|
* |
|
329
|
|
|
* @return null|string|void |
|
330
|
|
|
*/ |
|
331
|
3 |
|
public function searchAttributeValue(\SimpleXMLElement $element, array $names) |
|
332
|
|
|
{ |
|
333
|
3 |
|
foreach ($names as $name) { |
|
334
|
3 |
|
$value = $this->getAttributeValue($element, $name); |
|
335
|
3 |
|
if (!is_null($value)) { |
|
336
|
3 |
|
return (string) $value; |
|
337
|
|
|
} |
|
338
|
3 |
|
} |
|
339
|
|
|
|
|
340
|
2 |
|
return; |
|
341
|
|
|
} |
|
342
|
|
|
|
|
343
|
|
|
/** |
|
344
|
|
|
* Tells if the parser can handle the feed or not. |
|
345
|
|
|
* |
|
346
|
|
|
* @param \SimpleXMLElement $xmlBody |
|
347
|
|
|
* |
|
348
|
|
|
* @return bool |
|
349
|
|
|
*/ |
|
350
|
|
|
abstract public function canHandle(\SimpleXMLElement $xmlBody); |
|
351
|
|
|
|
|
352
|
|
|
/** |
|
353
|
|
|
* Performs the actual conversion into a FeedContent instance. |
|
354
|
|
|
* |
|
355
|
|
|
* @param \SimpleXMLElement $body |
|
356
|
|
|
* @param FeedInterface $feed |
|
357
|
|
|
* @param array $filters |
|
358
|
|
|
* |
|
359
|
|
|
* @return FeedInInterface |
|
360
|
|
|
*/ |
|
361
|
|
|
abstract protected function parseBody(\SimpleXMLElement $body, FeedInterface $feed, array $filters); |
|
362
|
|
|
|
|
363
|
|
|
/** |
|
364
|
|
|
* Handles enclosures if any. |
|
365
|
|
|
* |
|
366
|
|
|
* @param \SimpleXMLElement $element |
|
367
|
|
|
* @param ItemInInterface $item |
|
368
|
|
|
* |
|
369
|
|
|
* @return $this |
|
370
|
|
|
*/ |
|
371
|
|
|
abstract protected function handleEnclosure(\SimpleXMLElement $element, ItemInInterface $item); |
|
372
|
|
|
} |
|
373
|
|
|
|
It seems like the type of the argument is not accepted by the function/method which you are calling.
In some cases, in particular if PHP’s automatic type-juggling kicks in this might be fine. In other cases, however this might be a bug.
We suggest to add an explicit type cast like in the following example: