|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace PhpXmlRpc\Helper; |
|
4
|
|
|
|
|
5
|
|
|
use PhpXmlRpc\PhpXmlRpc; |
|
6
|
|
|
|
|
7
|
|
|
/** |
|
8
|
|
|
* @todo implement an interface |
|
9
|
|
|
*/ |
|
10
|
|
|
class Charset |
|
11
|
|
|
{ |
|
12
|
|
|
// tables used for transcoding different charsets into us-ascii xml |
|
13
|
|
|
protected $xml_iso88591_Entities = array("in" => array(), "out" => array()); |
|
14
|
|
|
|
|
15
|
|
|
//protected $xml_cp1252_Entities = array('in' => array(), out' => array()); |
|
16
|
|
|
|
|
17
|
|
|
protected $charset_supersets = array( |
|
18
|
|
|
'US-ASCII' => array('ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4', |
|
19
|
|
|
'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', |
|
20
|
|
|
'ISO-8859-9', 'ISO-8859-10', 'ISO-8859-11', 'ISO-8859-12', |
|
21
|
|
|
'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'UTF-8', |
|
22
|
|
|
'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN',), |
|
23
|
|
|
); |
|
24
|
|
|
|
|
25
|
|
|
/** @var Charset $instance */ |
|
26
|
|
|
protected static $instance = null; |
|
27
|
|
|
|
|
28
|
|
|
/** |
|
29
|
|
|
* This class is singleton for performance reasons. |
|
30
|
|
|
* @todo should we just make $xml_iso88591_Entities a static variable instead ? |
|
31
|
|
|
* |
|
32
|
|
|
* @return Charset |
|
33
|
|
|
*/ |
|
34
|
605 |
|
public static function instance() |
|
35
|
|
|
{ |
|
36
|
605 |
|
if (self::$instance === null) { |
|
37
|
383 |
|
self::$instance = new static(); |
|
38
|
|
|
} |
|
39
|
|
|
|
|
40
|
605 |
|
return self::$instance; |
|
41
|
|
|
} |
|
42
|
|
|
|
|
43
|
|
|
/** |
|
44
|
|
|
* Force usage as singleton |
|
45
|
|
|
*/ |
|
46
|
383 |
|
protected function __construct() |
|
47
|
|
|
{ |
|
48
|
383 |
|
} |
|
49
|
|
|
|
|
50
|
|
|
/** |
|
51
|
|
|
* @param string $tableName |
|
52
|
|
|
* @throws \Exception for unsupported $tableName |
|
53
|
|
|
* @todo add support for cp1252 as well as latin-2 .. latin-10 |
|
54
|
|
|
* @todo should we add to the latin-1 table the characters from cp_1252 range, i.e. 128 to 159 ? |
|
55
|
|
|
* Those will NOT be present in true ISO-8859-1, but will save the unwary windows user from sending junk |
|
56
|
|
|
* (though no luck when receiving them...) |
|
57
|
|
|
* Note also that, apparently, while 'ISO/IEC 8859-1' has no characters defined for bytes 128 to 159, |
|
58
|
|
|
* IANA ISO-8859-1 does have well-defined 'C1' control codes for those - wikipedia's page on latin-1 says: |
|
59
|
|
|
* "ISO-8859-1 is the IANA preferred name for this standard when supplemented with the C0 and C1 control codes from ISO/IEC 6429." |
|
60
|
|
|
* Check what mbstring/iconv do by default with those? |
|
61
|
|
|
*/ |
|
62
|
494 |
|
protected function buildConversionTable($tableName) |
|
63
|
|
|
{ |
|
64
|
494 |
|
switch($tableName) { |
|
65
|
494 |
|
case 'xml_iso88591_Entities': |
|
66
|
494 |
|
if (count($this->xml_iso88591_Entities['in'])) { |
|
67
|
492 |
|
return; |
|
68
|
|
|
} |
|
69
|
19 |
|
for ($i = 0; $i < 32; $i++) { |
|
70
|
19 |
|
$this->xml_iso88591_Entities["in"][] = chr($i); |
|
71
|
19 |
|
$this->xml_iso88591_Entities["out"][] = "&#{$i};"; |
|
72
|
|
|
} |
|
73
|
|
|
|
|
74
|
|
|
/// @todo to be 'print safe', should we encode as well character 127 (DEL) ? |
|
75
|
|
|
|
|
76
|
19 |
|
for ($i = 160; $i < 256; $i++) { |
|
77
|
19 |
|
$this->xml_iso88591_Entities["in"][] = chr($i); |
|
78
|
19 |
|
$this->xml_iso88591_Entities["out"][] = "&#{$i};"; |
|
79
|
|
|
} |
|
80
|
19 |
|
break; |
|
81
|
|
|
|
|
82
|
|
|
/*case 'xml_cp1252_Entities': |
|
83
|
|
|
if (count($this->xml_cp1252_Entities['in'])) { |
|
84
|
|
|
return; |
|
85
|
|
|
} |
|
86
|
|
|
for ($i = 128; $i < 160; $i++) |
|
87
|
|
|
{ |
|
88
|
|
|
$this->xml_cp1252_Entities['in'][] = chr($i); |
|
89
|
|
|
} |
|
90
|
|
|
$this->xml_cp1252_Entities['out'] = array( |
|
91
|
|
|
'€', '?', '‚', 'ƒ', |
|
92
|
|
|
'„', '…', '†', '‡', |
|
93
|
|
|
'ˆ', '‰', 'Š', '‹', |
|
94
|
|
|
'Œ', '?', 'Ž', '?', |
|
95
|
|
|
'?', '‘', '’', '“', |
|
96
|
|
|
'”', '•', '–', '—', |
|
97
|
|
|
'˜', '™', 'š', '›', |
|
98
|
|
|
'œ', '?', 'ž', 'Ÿ' |
|
99
|
|
|
); |
|
100
|
|
|
$this->buildConversionTable('xml_iso88591_Entities'); |
|
101
|
|
|
break;*/ |
|
102
|
|
|
|
|
103
|
|
|
default: |
|
104
|
|
|
throw new \Exception('Unsupported table: ' . $tableName); |
|
105
|
|
|
} |
|
106
|
19 |
|
} |
|
107
|
|
|
|
|
108
|
|
|
/** |
|
109
|
|
|
* Convert a string to the correct XML representation in a target charset. |
|
110
|
|
|
* This involves: |
|
111
|
|
|
* - character transformation for all characters which have a different representation in source and dest charsets |
|
112
|
|
|
* - using 'charset entity' representation for all characters which are outside of the target charset |
|
113
|
|
|
* |
|
114
|
|
|
* To help correct communication of non-ascii chars inside strings, regardless of the charset used when sending |
|
115
|
|
|
* requests, parsing them, sending responses and parsing responses, an option is to convert all non-ascii chars |
|
116
|
|
|
* present in the message into their equivalent 'charset entity'. Charset entities enumerated this way are |
|
117
|
|
|
* independent of the charset encoding used to transmit them, and all XML parsers are bound to understand them. |
|
118
|
|
|
* |
|
119
|
|
|
* Note that when not sending a charset encoding mime type along with http headers, we are bound by RFC 3023 to emit |
|
120
|
|
|
* strict us-ascii for 'text/xml' payloads (but we should review RFC 7303, which seems to have changed the rules...) |
|
121
|
|
|
* |
|
122
|
|
|
* @todo do a bit of basic benchmarking (strtr vs. str_replace) |
|
123
|
|
|
* @todo make usage of iconv() or mb_string() where available |
|
124
|
|
|
* @todo support aliases for charset names, eg ASCII, LATIN1, ISO-88591 (see f.e. polyfill-iconv for a list), |
|
125
|
|
|
* but then take those into account as well in other methods, ie.isValidCharset) |
|
126
|
|
|
* @todo when converting to ASCII, allow to choose whether to escape the range 0-31,127 (non-print chars) or not |
|
127
|
|
|
* @todo allow picking different strategies to deal w. invalid chars? eg. source in latin-1 and chars 128-159 |
|
128
|
|
|
* |
|
129
|
|
|
* @param string $data |
|
130
|
|
|
* @param string $srcEncoding |
|
131
|
|
|
* @param string $destEncoding |
|
132
|
|
|
* |
|
133
|
|
|
* @return string |
|
134
|
|
|
*/ |
|
135
|
586 |
|
public function encodeEntities($data, $srcEncoding = '', $destEncoding = '') |
|
136
|
|
|
{ |
|
137
|
586 |
|
if ($srcEncoding == '') { |
|
138
|
|
|
// lame, but we know no better... |
|
139
|
|
|
$srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding; |
|
140
|
|
|
} |
|
141
|
|
|
|
|
142
|
586 |
|
if ($destEncoding == '') { |
|
143
|
556 |
|
$destEncoding = 'US-ASCII'; |
|
144
|
|
|
} |
|
145
|
|
|
|
|
146
|
586 |
|
$conversion = strtoupper($srcEncoding . '_' . $destEncoding); |
|
147
|
|
|
|
|
148
|
|
|
// list ordered with (expected) most common scenarios first |
|
149
|
586 |
|
switch ($conversion) { |
|
150
|
586 |
|
case 'UTF-8_UTF-8': |
|
151
|
585 |
|
case 'ISO-8859-1_ISO-8859-1': |
|
152
|
574 |
|
case 'US-ASCII_UTF-8': |
|
153
|
574 |
|
case 'US-ASCII_US-ASCII': |
|
154
|
574 |
|
case 'US-ASCII_ISO-8859-1': |
|
155
|
|
|
//case 'CP1252_CP1252': |
|
156
|
46 |
|
$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
|
157
|
46 |
|
break; |
|
158
|
|
|
|
|
159
|
574 |
|
case 'UTF-8_US-ASCII': |
|
160
|
522 |
|
case 'UTF-8_ISO-8859-1': |
|
161
|
|
|
// NB: this will choke on invalid UTF-8, going most likely beyond EOF |
|
162
|
353 |
|
$escapedData = ''; |
|
163
|
|
|
// be kind to users creating string xmlrpc values out of different php types |
|
164
|
353 |
|
$data = (string)$data; |
|
165
|
353 |
|
$ns = strlen($data); |
|
166
|
353 |
|
for ($nn = 0; $nn < $ns; $nn++) { |
|
167
|
353 |
|
$ch = $data[$nn]; |
|
168
|
353 |
|
$ii = ord($ch); |
|
169
|
|
|
// 7 bits in 1 byte: 0bbbbbbb (127) |
|
170
|
353 |
|
if ($ii < 32) { |
|
171
|
40 |
|
if ($conversion == 'UTF-8_US-ASCII') { |
|
172
|
37 |
|
$escapedData .= sprintf('&#%d;', $ii); |
|
173
|
|
|
} else { |
|
174
|
3 |
|
$escapedData .= $ch; |
|
175
|
|
|
} |
|
176
|
|
|
} |
|
177
|
353 |
|
else if ($ii < 128) { |
|
178
|
|
|
/// @todo shall we replace this with a (supposedly) faster str_replace? |
|
179
|
346 |
|
switch ($ii) { |
|
180
|
346 |
|
case 34: |
|
181
|
20 |
|
$escapedData .= '"'; |
|
182
|
20 |
|
break; |
|
183
|
346 |
|
case 38: |
|
184
|
21 |
|
$escapedData .= '&'; |
|
185
|
21 |
|
break; |
|
186
|
346 |
|
case 39: |
|
187
|
22 |
|
$escapedData .= '''; |
|
188
|
22 |
|
break; |
|
189
|
346 |
|
case 60: |
|
190
|
21 |
|
$escapedData .= '<'; |
|
191
|
21 |
|
break; |
|
192
|
346 |
|
case 62: |
|
193
|
21 |
|
$escapedData .= '>'; |
|
194
|
21 |
|
break; |
|
195
|
|
|
default: |
|
196
|
346 |
|
$escapedData .= $ch; |
|
197
|
|
|
} // switch |
|
198
|
|
|
} // 11 bits in 2 bytes: 110bbbbb 10bbbbbb (2047) |
|
199
|
71 |
|
elseif ($ii >> 5 == 6) { |
|
200
|
67 |
|
$b1 = ($ii & 31); |
|
201
|
67 |
|
$b2 = (ord($data[$nn + 1]) & 63); |
|
202
|
67 |
|
$ii = ($b1 * 64) + $b2; |
|
203
|
67 |
|
$escapedData .= sprintf('&#%d;', $ii); |
|
204
|
67 |
|
$nn += 1; |
|
205
|
|
|
} // 16 bits in 3 bytes: 1110bbbb 10bbbbbb 10bbbbbb |
|
206
|
31 |
|
elseif ($ii >> 4 == 14) { |
|
207
|
31 |
|
$b1 = ($ii & 15); |
|
208
|
31 |
|
$b2 = (ord($data[$nn + 1]) & 63); |
|
209
|
31 |
|
$b3 = (ord($data[$nn + 2]) & 63); |
|
210
|
31 |
|
$ii = ((($b1 * 64) + $b2) * 64) + $b3; |
|
211
|
31 |
|
$escapedData .= sprintf('&#%d;', $ii); |
|
212
|
31 |
|
$nn += 2; |
|
213
|
|
|
} // 21 bits in 4 bytes: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb |
|
214
|
|
|
elseif ($ii >> 3 == 30) { |
|
215
|
|
|
$b1 = ($ii & 7); |
|
216
|
|
|
$b2 = (ord($data[$nn + 1]) & 63); |
|
217
|
|
|
$b3 = (ord($data[$nn + 2]) & 63); |
|
218
|
|
|
$b4 = (ord($data[$nn + 3]) & 63); |
|
219
|
|
|
$ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4; |
|
220
|
|
|
$escapedData .= sprintf('&#%d;', $ii); |
|
221
|
|
|
$nn += 3; |
|
222
|
|
|
} |
|
223
|
|
|
} |
|
224
|
|
|
|
|
225
|
|
|
// when converting to latin-1, do not be so eager with using entities for characters 160-255 |
|
226
|
353 |
|
if ($conversion == 'UTF-8_ISO-8859-1') { |
|
227
|
24 |
|
$this->buildConversionTable('xml_iso88591_Entities'); |
|
228
|
24 |
|
$escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData); |
|
229
|
|
|
} |
|
230
|
353 |
|
break; |
|
231
|
|
|
|
|
232
|
515 |
|
case 'ISO-8859-1_UTF-8': |
|
233
|
28 |
|
$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
|
234
|
28 |
|
$escapedData = utf8_encode($escapedData); |
|
235
|
28 |
|
break; |
|
236
|
|
|
|
|
237
|
487 |
|
case 'ISO-8859-1_US-ASCII': |
|
238
|
487 |
|
$this->buildConversionTable('xml_iso88591_Entities'); |
|
239
|
487 |
|
$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
|
240
|
487 |
|
$escapedData = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escapedData); |
|
241
|
487 |
|
break; |
|
242
|
|
|
|
|
243
|
|
|
/* |
|
244
|
|
|
case 'CP1252_US-ASCII': |
|
245
|
|
|
$this->buildConversionTable('xml_cp1252_Entities'); |
|
246
|
|
|
$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
|
247
|
|
|
$escapedData = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escapedData); |
|
248
|
|
|
$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); |
|
249
|
|
|
break; |
|
250
|
|
|
case 'CP1252_UTF-8': |
|
251
|
|
|
$this->buildConversionTable('xml_cp1252_Entities'); |
|
252
|
|
|
$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
|
253
|
|
|
/// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all alone will NOT convert them) |
|
254
|
|
|
$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); |
|
255
|
|
|
$escapedData = utf8_encode($escapedData); |
|
256
|
|
|
break; |
|
257
|
|
|
case 'CP1252_ISO-8859-1': |
|
258
|
|
|
$this->buildConversionTable('xml_cp1252_Entities'); |
|
259
|
|
|
$escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); |
|
260
|
|
|
// we might as well replace all funky chars with a '?' here, but we are kind and leave it to the receiving application layer to decide what to do with these weird entities... |
|
261
|
|
|
$escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); |
|
262
|
|
|
break; |
|
263
|
|
|
*/ |
|
264
|
|
|
|
|
265
|
|
|
default: |
|
266
|
|
|
$escapedData = ''; |
|
267
|
|
|
Logger::instance()->errorLog('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported..."); |
|
268
|
|
|
} |
|
269
|
|
|
|
|
270
|
586 |
|
return $escapedData; |
|
271
|
|
|
} |
|
272
|
|
|
|
|
273
|
|
|
/** |
|
274
|
|
|
* Checks if a given charset encoding is present in a list of encodings or if it is a valid subset of any encoding |
|
275
|
|
|
* in the list. |
|
276
|
|
|
* |
|
277
|
|
|
* @param string $encoding charset to be tested |
|
278
|
|
|
* @param string|array $validList comma separated list of valid charsets (or array of charsets) |
|
279
|
|
|
* |
|
280
|
|
|
* @return bool |
|
281
|
|
|
*/ |
|
282
|
|
|
public function isValidCharset($encoding, $validList) |
|
283
|
|
|
{ |
|
284
|
|
|
if (is_string($validList)) { |
|
285
|
|
|
$validList = explode(',', $validList); |
|
286
|
|
|
} |
|
287
|
|
|
if (@in_array(strtoupper($encoding), $validList)) { |
|
288
|
|
|
return true; |
|
289
|
|
|
} else { |
|
290
|
|
|
if (array_key_exists($encoding, $this->charset_supersets)) { |
|
291
|
|
|
foreach ($validList as $allowed) { |
|
292
|
|
|
if (in_array($allowed, $this->charset_supersets[$encoding])) { |
|
293
|
|
|
return true; |
|
294
|
|
|
} |
|
295
|
|
|
} |
|
296
|
|
|
} |
|
297
|
|
|
|
|
298
|
|
|
return false; |
|
299
|
|
|
} |
|
300
|
|
|
} |
|
301
|
|
|
|
|
302
|
|
|
/** |
|
303
|
|
|
* Used only for backwards compatibility |
|
304
|
|
|
* @deprecated |
|
305
|
|
|
* |
|
306
|
|
|
* @param string $charset |
|
307
|
|
|
* |
|
308
|
|
|
* @return array |
|
309
|
|
|
* |
|
310
|
|
|
* @throws \Exception for unknown/unsupported charsets |
|
311
|
|
|
*/ |
|
312
|
|
|
public function getEntities($charset) |
|
313
|
|
|
{ |
|
314
|
|
|
//trigger_error('Method ' . __METHOD__ . ' is deprecated', E_USER_DEPRECATED); |
|
315
|
|
|
|
|
316
|
|
|
switch ($charset) |
|
317
|
|
|
{ |
|
318
|
|
|
case 'iso88591': |
|
319
|
|
|
return $this->xml_iso88591_Entities; |
|
320
|
|
|
default: |
|
321
|
|
|
throw new \Exception('Unsupported charset: ' . $charset); |
|
322
|
|
|
} |
|
323
|
|
|
} |
|
324
|
|
|
} |
|
325
|
|
|
|
gggeek /
phpxmlrpc
