1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/** |
4
|
|
|
* |
5
|
|
|
* Location: xml/SaxParser.class |
6
|
|
|
* |
7
|
|
|
* Provides basic functionality to read and parse XML documents. Subclasses |
8
|
|
|
* must implement all the their custom handlers by using add* function methods. |
9
|
|
|
* They may also use the handle*() methods to parse a specific XML begin and end |
10
|
|
|
* tags, but this is not recommended as it is more difficult. |
11
|
|
|
* |
12
|
|
|
* Copyright © 2001 eXtremePHP. All rights reserved. |
13
|
|
|
* |
14
|
|
|
* @author Ken Egervari |
15
|
|
|
*/ |
16
|
|
|
|
17
|
|
|
class SaxParser |
18
|
|
|
{ |
19
|
|
|
public $level; |
20
|
|
|
public $parser; |
21
|
|
|
|
22
|
|
|
public $isCaseFolding; |
23
|
|
|
public $targetEncoding; |
24
|
|
|
|
25
|
|
|
/* Custom Handler Variables */ |
26
|
|
|
public $tagHandlers = array(); |
27
|
|
|
|
28
|
|
|
/* Tag stack */ |
29
|
|
|
public $tags = array(); |
30
|
|
|
|
31
|
|
|
/* Xml Source Input */ |
32
|
|
|
public $xmlInput; |
33
|
|
|
|
34
|
|
|
public $errors = array(); |
35
|
|
|
|
36
|
|
|
/** |
37
|
|
|
* Creates a SaxParser object using a FileInput to represent the stream |
38
|
|
|
* of XML data to parse. Use the static methods createFileInput or |
39
|
|
|
* createStringInput to construct xml input source objects to supply |
40
|
|
|
* to the constructor, or the implementor can construct them individually. |
41
|
|
|
* |
42
|
|
|
* @param $input |
43
|
|
|
*/ |
44
|
60 |
|
public function __construct(&$input) |
45
|
|
|
{ |
46
|
60 |
|
$this->level = 0; |
47
|
60 |
|
$this->parser = xml_parser_create('UTF-8'); |
48
|
60 |
|
xml_set_object($this->parser, $this); |
49
|
60 |
|
$this->input = $input; |
|
|
|
|
50
|
60 |
|
$this->setCaseFolding(false); |
51
|
60 |
|
$this->useUtfEncoding(); |
52
|
60 |
|
xml_set_element_handler($this->parser, 'handleBeginElement', 'handleEndElement'); |
53
|
60 |
|
xml_set_character_data_handler($this->parser, 'handleCharacterData'); |
54
|
60 |
|
xml_set_processing_instruction_handler($this->parser, 'handleProcessingInstruction'); |
55
|
60 |
|
xml_set_default_handler($this->parser, 'handleDefault'); |
56
|
60 |
|
xml_set_unparsed_entity_decl_handler($this->parser, 'handleUnparsedEntityDecl'); |
57
|
60 |
|
xml_set_notation_decl_handler($this->parser, 'handleNotationDecl'); |
58
|
60 |
|
xml_set_external_entity_ref_handler($this->parser, 'handleExternalEntityRef'); |
59
|
60 |
|
} |
60
|
|
|
|
61
|
|
|
/*--------------------------------------------------------------------------- |
62
|
|
|
Property Methods |
63
|
|
|
---------------------------------------------------------------------------*/ |
64
|
|
|
|
65
|
|
|
/** |
66
|
|
|
* @return int |
67
|
|
|
*/ |
68
|
4 |
|
public function getCurrentLevel() |
69
|
|
|
{ |
70
|
4 |
|
return $this->level; |
71
|
|
|
} |
72
|
|
|
|
73
|
|
|
/** |
74
|
|
|
* @param boolean $isCaseFolding |
75
|
|
|
* @return void |
76
|
|
|
*/ |
77
|
60 |
|
public function setCaseFolding($isCaseFolding) |
78
|
|
|
{ |
79
|
60 |
|
assert(is_bool($isCaseFolding)); |
80
|
|
|
|
81
|
60 |
|
$this->isCaseFolding = $isCaseFolding; |
82
|
60 |
|
xml_parser_set_option($this->parser, XML_OPTION_CASE_FOLDING, $this->isCaseFolding); |
83
|
60 |
|
} |
84
|
|
|
|
85
|
|
|
/** |
86
|
|
|
* @return void |
87
|
|
|
*/ |
88
|
|
|
public function useIsoEncoding() |
89
|
|
|
{ |
90
|
|
|
$this->targetEncoding = 'ISO-8859-1'; |
91
|
|
|
xml_parser_set_option($this->parser, XML_OPTION_TARGET_ENCODING, $this->targetEncoding); |
92
|
|
|
} |
93
|
|
|
|
94
|
|
|
/** |
95
|
|
|
* @return void |
96
|
|
|
*/ |
97
|
|
|
public function useAsciiEncoding() |
98
|
|
|
{ |
99
|
|
|
$this->targetEncoding = 'US-ASCII'; |
100
|
|
|
xml_parser_set_option($this->parser, XML_OPTION_TARGET_ENCODING, $this->targetEncoding); |
101
|
|
|
} |
102
|
|
|
|
103
|
|
|
/** |
104
|
|
|
* @return void |
105
|
|
|
*/ |
106
|
60 |
|
public function useUtfEncoding() |
107
|
|
|
{ |
108
|
60 |
|
$this->targetEncoding = 'UTF-8'; |
109
|
60 |
|
xml_parser_set_option($this->parser, XML_OPTION_TARGET_ENCODING, $this->targetEncoding); |
110
|
60 |
|
} |
111
|
|
|
|
112
|
|
|
/** |
113
|
|
|
* Returns the name of the xml tag being parsed |
114
|
|
|
* @return string |
115
|
|
|
*/ |
116
|
|
|
public function getCurrentTag() |
117
|
|
|
{ |
118
|
|
|
return $this->tags[count($this->tags) - 1]; |
119
|
|
|
} |
120
|
|
|
|
121
|
11 |
|
public function getParentTag() |
122
|
|
|
{ |
123
|
11 |
|
if (isset($this->tags[count($this->tags) - 2])) { |
124
|
11 |
|
return $this->tags[count($this->tags) - 2]; |
125
|
|
|
} |
126
|
|
|
return false; |
127
|
|
|
} |
128
|
|
|
|
129
|
|
|
|
130
|
|
|
/*--------------------------------------------------------------------------- |
131
|
|
|
Parser methods |
132
|
|
|
---------------------------------------------------------------------------*/ |
133
|
|
|
|
134
|
|
|
/** |
135
|
|
|
* @return bool |
136
|
|
|
*/ |
137
|
|
|
public function parse() |
138
|
|
|
{ |
139
|
|
|
if (!is_resource($this->input)) { |
140
|
|
|
if (!xml_parse($this->parser, $this->input)) { |
141
|
|
|
$this->setErrors($this->getXmlError()); |
142
|
|
|
return false; |
143
|
|
|
} |
144
|
|
|
//if (!$fp = fopen($this->input, 'r')) { |
145
|
|
|
// $this->setErrors('Could not open file: '.$this->input); |
146
|
|
|
// return false; |
147
|
|
|
//} |
148
|
|
|
} else { |
149
|
|
|
while ($data = fread($this->input, 4096)) { |
150
|
|
|
if (!xml_parse($this->parser, str_replace("'", "'", $data), feof($this->input))) { |
151
|
|
|
$this->setErrors($this->getXmlError()); |
152
|
|
|
fclose($this->input); |
153
|
|
|
return false; |
154
|
|
|
} |
155
|
|
|
} |
156
|
|
|
fclose($this->input); |
157
|
|
|
} |
158
|
|
|
return true; |
159
|
|
|
} |
160
|
|
|
|
161
|
|
|
/** |
162
|
|
|
* @return void |
163
|
|
|
*/ |
164
|
|
|
public function free() |
165
|
|
|
{ |
166
|
|
|
xml_parser_free($this->parser); |
167
|
|
|
} |
168
|
|
|
|
169
|
|
|
/** |
170
|
|
|
* @private |
171
|
|
|
* @return string |
172
|
|
|
*/ |
173
|
|
|
public function getXmlError() |
174
|
|
|
{ |
175
|
|
|
return sprintf("XmlParse error: %s at line %d", xml_error_string(xml_get_error_code($this->parser)), xml_get_current_line_number($this->parser)); |
176
|
|
|
} |
177
|
|
|
|
178
|
|
|
/*--------------------------------------------------------------------------- |
179
|
|
|
Custom Handler Methods |
180
|
|
|
---------------------------------------------------------------------------*/ |
181
|
|
|
|
182
|
|
|
/** |
183
|
|
|
* Adds a callback function to be called when a tag is encountered.<br> |
184
|
|
|
* @param XmlTagHandler $tagHandler |
185
|
|
|
* @return void |
186
|
|
|
*/ |
187
|
60 |
|
public function addTagHandler(XmlTagHandler $tagHandler) |
188
|
|
|
{ |
189
|
60 |
|
$name = $tagHandler->getName(); |
190
|
60 |
|
if (is_array($name)) { |
191
|
35 |
|
foreach ($name as $n) { |
192
|
35 |
|
$this->tagHandlers[$n] = $tagHandler; |
193
|
|
|
} |
194
|
|
|
} else { |
195
|
60 |
|
$this->tagHandlers[$name] = $tagHandler; |
196
|
|
|
} |
197
|
60 |
|
} |
198
|
|
|
|
199
|
|
|
|
200
|
|
|
/*--------------------------------------------------------------------------- |
201
|
|
|
Private Handler Methods |
202
|
|
|
---------------------------------------------------------------------------*/ |
203
|
|
|
|
204
|
|
|
/** |
205
|
|
|
* Callback function that executes whenever a the start of a tag |
206
|
|
|
* occurs when being parsed. |
207
|
|
|
* @param int $parser The handle to the parser. |
208
|
|
|
* @param string $tagName The name of the tag currently being parsed. |
209
|
|
|
* @param array $attributesArray The list of attributes associated with the tag. |
210
|
|
|
* @private |
211
|
|
|
* @return void |
212
|
|
|
*/ |
213
|
|
|
public function handleBeginElement($parser, $tagName, $attributesArray) |
214
|
|
|
{ |
215
|
|
|
array_push($this->tags, $tagName); |
216
|
|
|
$this->level++; |
217
|
|
View Code Duplication |
if (isset($this->tagHandlers[$tagName]) && is_subclass_of($this->tagHandlers[$tagName], 'xmltaghandler')) { |
218
|
|
|
$this->tagHandlers[$tagName]->handleBeginElement($this, $attributesArray); |
219
|
|
|
} else { |
220
|
|
|
$this->handleBeginElementDefault($parser, $tagName, $attributesArray); |
221
|
|
|
} |
222
|
|
|
} |
223
|
|
|
|
224
|
|
|
/** |
225
|
|
|
* Callback function that executes whenever the end of a tag |
226
|
|
|
* occurs when being parsed. |
227
|
|
|
* @param int $parser The handle to the parser. |
228
|
|
|
* @param string $tagName The name of the tag currently being parsed. |
229
|
|
|
* @private |
230
|
|
|
* @return void |
231
|
|
|
*/ |
232
|
|
|
public function handleEndElement($parser, $tagName) |
233
|
|
|
{ |
234
|
|
|
array_pop($this->tags); |
235
|
|
View Code Duplication |
if (isset($this->tagHandlers[$tagName]) && is_subclass_of($this->tagHandlers[$tagName], 'xmltaghandler')) { |
236
|
|
|
$this->tagHandlers[$tagName]->handleEndElement($this); |
237
|
|
|
} else { |
238
|
|
|
$this->handleEndElementDefault($parser, $tagName); |
239
|
|
|
} |
240
|
|
|
$this->level--; |
241
|
|
|
} |
242
|
|
|
|
243
|
|
|
/** |
244
|
|
|
* Callback function that executes whenever character data is encountered |
245
|
|
|
* while being parsed. |
246
|
|
|
* @param int $parser The handle to the parser. |
247
|
|
|
* @param string $data Character data inside the tag |
248
|
|
|
* @return void |
249
|
|
|
*/ |
250
|
|
|
public function handleCharacterData($parser, $data) |
251
|
|
|
{ |
252
|
|
|
$tagHandler = isset($this->tagHandlers[$this->getCurrentTag()]) ? $this->tagHandlers[$this->getCurrentTag()] : null; |
253
|
|
|
if (null != $tagHandler && is_subclass_of($tagHandler, 'xmltaghandler')) { |
254
|
|
|
$tagHandler->handleCharacterData($this, $data); |
255
|
|
|
} else { |
256
|
|
|
$this->handleCharacterDataDefault($parser, $data); |
257
|
|
|
} |
258
|
|
|
} |
259
|
|
|
|
260
|
|
|
/** |
261
|
|
|
* @param int $parser The handle to the parser. |
262
|
|
|
* @param $target |
263
|
|
|
* @param $data |
264
|
|
|
* @return void |
265
|
|
|
*/ |
266
|
|
|
public function handleProcessingInstruction($parser, &$target, &$data) |
|
|
|
|
267
|
|
|
{ |
268
|
|
|
// if($target == 'php') { |
269
|
|
|
// eval($data); |
270
|
|
|
// } |
271
|
|
|
} |
272
|
|
|
|
273
|
|
|
/** |
274
|
|
|
* @param $parser |
275
|
|
|
* @param $data |
276
|
|
|
* @return void |
277
|
|
|
*/ |
278
|
|
|
public function handleDefault($parser, $data) |
|
|
|
|
279
|
|
|
{ |
280
|
|
|
|
281
|
|
|
} |
282
|
|
|
|
283
|
|
|
/** |
284
|
|
|
* @param $parser |
285
|
|
|
* @param $entityName |
286
|
|
|
* @param $base |
287
|
|
|
* @param $systemId |
288
|
|
|
* @param $publicId |
289
|
|
|
* @param $notationName |
290
|
|
|
* @return void |
291
|
|
|
*/ |
292
|
|
|
public function handleUnparsedEntityDecl($parser, $entityName, $base, $systemId, $publicId, $notationName) |
|
|
|
|
293
|
|
|
{ |
294
|
|
|
|
295
|
|
|
} |
296
|
|
|
|
297
|
|
|
/** |
298
|
|
|
* @param $parser |
299
|
|
|
* @param $notationName |
300
|
|
|
* @param $base |
301
|
|
|
* @param $systemId |
302
|
|
|
* @param $publicId |
303
|
|
|
* @return void |
304
|
|
|
*/ |
305
|
|
|
public function handleNotationDecl($parser, $notationName, $base, $systemId, $publicId) |
|
|
|
|
306
|
|
|
{ |
307
|
|
|
|
308
|
|
|
} |
309
|
|
|
|
310
|
|
|
/** |
311
|
|
|
* @param $parser |
312
|
|
|
* @param $openEntityNames |
313
|
|
|
* @param $base |
314
|
|
|
* @param $systemId |
315
|
|
|
* @param $publicId |
316
|
|
|
* @return void |
317
|
|
|
*/ |
318
|
|
|
public function handleExternalEntityRef($parser, $openEntityNames, $base, $systemId, $publicId) |
|
|
|
|
319
|
|
|
{ |
320
|
|
|
|
321
|
|
|
} |
322
|
|
|
|
323
|
|
|
/** |
324
|
|
|
* The default tag handler method for a tag with no handler |
325
|
|
|
* |
326
|
|
|
* @param $parser |
327
|
|
|
* @param $tagName |
328
|
|
|
* @param $attributesArray |
329
|
|
|
* @return void |
330
|
|
|
*/ |
331
|
|
|
public function handleBeginElementDefault($parser, $tagName, $attributesArray) |
|
|
|
|
332
|
|
|
{ |
333
|
|
|
} |
334
|
|
|
|
335
|
|
|
/** |
336
|
|
|
* The default tag handler method for a tag with no handler |
337
|
|
|
* |
338
|
|
|
* @param $parser |
339
|
|
|
* @param $tagName |
340
|
|
|
* @return void |
341
|
|
|
*/ |
342
|
|
|
public function handleEndElementDefault($parser, $tagName) |
|
|
|
|
343
|
|
|
{ |
344
|
|
|
} |
345
|
|
|
|
346
|
|
|
/** |
347
|
|
|
* The default tag handler method for a tag with no handler |
348
|
|
|
* |
349
|
|
|
* @abstract |
350
|
|
|
* |
351
|
|
|
* @param $parser |
352
|
|
|
* @param $data |
353
|
|
|
* @return void |
354
|
|
|
*/ |
355
|
|
|
public function handleCharacterDataDefault($parser, $data) |
|
|
|
|
356
|
|
|
{ |
357
|
|
|
} |
358
|
|
|
|
359
|
|
|
/** |
360
|
|
|
* Sets error messages |
361
|
|
|
* |
362
|
|
|
* @param string $error string an error message |
363
|
|
|
*/ |
364
|
|
|
public function setErrors($error) |
365
|
|
|
{ |
366
|
|
|
$this->errors[] = trim($error); |
367
|
|
|
} |
368
|
|
|
|
369
|
|
|
/** |
370
|
|
|
* Gets all the error messages |
371
|
|
|
* |
372
|
|
|
* @param bool $ashtml return as html? |
373
|
|
|
* @return mixed |
374
|
|
|
*/ |
375
|
|
|
public function getErrors($ashtml = true) |
376
|
|
|
{ |
377
|
|
|
if (!$ashtml) { |
378
|
|
|
return $this->errors; |
379
|
|
|
} else { |
380
|
|
|
$ret = ''; |
381
|
|
|
if (count($this->errors) > 0) { |
382
|
|
|
foreach ($this->errors as $error) { |
383
|
|
|
$ret .= $error . '<br />'; |
384
|
|
|
} |
385
|
|
|
} |
386
|
|
|
return $ret; |
387
|
|
|
} |
388
|
|
|
} |
389
|
|
|
} |
390
|
|
|
|
In PHP it is possible to write to properties without declaring them. For example, the following is perfectly valid PHP code:
Generally, it is a good practice to explictly declare properties to avoid accidental typos and provide IDE auto-completion: