Search moodle.org's
Developer Documentation
Developer Documentation
- Bug fixes for general core bugs in 4.2.x will end 22 April 2024 (12 months).
- Bug fixes for security issues in 4.2.x will end 7 October 2024 (18 months).
- PHP version: minimum PHP 8.0.0 Note: minimum PHP version has increased since Moodle 4.1. PHP 8.1.x is supported too.
/lib/phpxmlrpc/Helper/ -> Charset.php (source)
Differences Between: [Versions 401 and 402]
1 <?php 2 3 namespace PhpXmlRpc\Helper; 4 5 use PhpXmlRpc\Exception\ValueErrorException; 6 use PhpXmlRpc\PhpXmlRpc; 7 use PhpXmlRpc\Traits\DeprecationLogger; 8 9 /** 10 * @todo implement an interface 11 */ 12 class Charset 13 { 14 use DeprecationLogger; 15 16 // tables used for transcoding different charsets into us-ascii xml 17 protected $xml_iso88591_Entities = array("in" => array(), "out" => array()); 18 19 //protected $xml_cp1252_Entities = array('in' => array(), out' => array()); 20 21 protected $charset_supersets = array( 22 'US-ASCII' => array('ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4', 23 'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 24 'ISO-8859-9', 'ISO-8859-10', 'ISO-8859-11', 'ISO-8859-12', 25 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'UTF-8', 26 'EUC-JP', 'EUC-', 'EUC-KR', 'EUC-CN',), 27 ); 28 29 /** @var Charset $instance */ 30 protected static $instance = null; 31 32 /** 33 * This class is singleton for performance reasons. 34 * 35 * @return Charset 36 * 37 * @todo should we just make $xml_iso88591_Entities a static variable instead ? 38 */ 39 public static function instance() 40 { 41 if (self::$instance === null) { 42 self::$instance = new static(); 43 } 44 45 return self::$instance; 46 } 47 48 /** 49 * Force usage as singleton. 50 */ 51 protected function __construct() 52 { 53 } 54 55 /** 56 * @param string $tableName 57 * @return void 58 * 59 * @throws ValueErrorException for unsupported $tableName 60 * 61 * @todo add support for cp1252 as well as latin-2 .. latin-10 62 * Optimization creep: instead of building all those tables on load, keep them ready-made php files 63 * which are not even included until needed 64 * @todo should we add to the latin-1 table the characters from cp_1252 range, i.e. 128 to 159 ? 65 * Those will NOT be present in true ISO-8859-1, but will save the unwary windows user from sending junk 66 * (though no luck when receiving them...) 67 * Note also that, apparently, while 'ISO/IEC 8859-1' has no characters defined for bytes 128 to 159, 68 * IANA ISO-8859-1 does have well-defined 'C1' control codes for those - wikipedia's page on latin-1 says: 69 * "ISO-8859-1 is the IANA preferred name for this standard when supplemented with the C0 and C1 control codes 70 * from ISO/IEC 6429." Check what mbstring/iconv do by default with those? 71 */ 72 protected function buildConversionTable($tableName) 73 { 74 switch ($tableName) { 75 case 'xml_iso88591_Entities': 76 if (count($this->xml_iso88591_Entities['in'])) { 77 return; 78 } 79 for ($i = 0; $i < 32; $i++) { 80 $this->xml_iso88591_Entities["in"][] = chr($i); 81 $this->xml_iso88591_Entities["out"][] = "&#{$i};"; 82 } 83 84 /// @todo to be 'print safe', should we encode as well character 127 (DEL) ? 85 86 for ($i = 160; $i < 256; $i++) { 87 $this->xml_iso88591_Entities["in"][] = chr($i); 88 $this->xml_iso88591_Entities["out"][] = "&#{$i};"; 89 } 90 break; 91 92 /*case 'xml_cp1252_Entities': 93 if (count($this->xml_cp1252_Entities['in'])) { 94 return; 95 } 96 for ($i = 128; $i < 160; $i++) 97 { 98 $this->xml_cp1252_Entities['in'][] = chr($i); 99 } 100 $this->xml_cp1252_Entities['out'] = array( 101 '€', '?', '‚', 'ƒ', 102 '„', '…', '†', '‡', 103 'ˆ', '‰', 'Š', '‹', 104 'Œ', '?', 'Ž', '?', 105 '?', '‘', '’', '“', 106 '”', '•', '–', '—', 107 '˜', '™', 'š', '›', 108 'œ', '?', 'ž', 'Ÿ' 109 ); 110 $this->buildConversionTable('xml_iso88591_Entities'); 111 break;*/ 112 113 default: 114 throw new ValueErrorException('Unsupported table: ' . $tableName); 115 } 116 } 117 118 /** 119 * Convert a string to the correct XML representation in a target charset. 120 * This involves: 121 * - character transformation for all characters which have a different representation in source and dest charsets 122 * - using 'charset entity' representation for all characters which are outside the target charset 123 * 124 * To help correct communication of non-ascii chars inside strings, regardless of the charset used when sending 125 * requests, parsing them, sending responses and parsing responses, an option is to convert all non-ascii chars 126 * present in the message into their equivalent 'charset entity'. Charset entities enumerated this way are 127 * independent of the charset encoding used to transmit them, and all XML parsers are bound to understand them. 128 * 129 * Note that when not sending a charset encoding mime type along with http headers, we are bound by RFC 3023 to emit 130 * strict us-ascii for 'text/xml' payloads (but we should review RFC 7303, which seems to have changed the rules...) 131 * 132 * @param string $data 133 * @param string $srcEncoding 134 * @param string $destEncoding 135 * @return string 136 * 137 * @todo do a bit of basic benchmarking: strtr vs. str_replace, str_replace vs htmlspecialchars, hand-coded conversion 138 * vs mbstring when that is enabled 139 * @todo make use of iconv when it is available and mbstring is not 140 * @todo support aliases for charset names, eg ASCII, LATIN1, ISO-88591 (see f.e. polyfill-iconv for a list), 141 * but then take those into account as well in other methods, ie. isValidCharset) 142 * @todo when converting to ASCII, allow to choose whether to escape the range 0-31,127 (non-print chars) or not 143 * @todo allow picking different strategies to deal w. invalid chars? eg. source in latin-1 and chars 128-159 144 * @todo add support for escaping using CDATA sections? (add cdata start and end tokens, replace only ']]>' with ']]]]><![CDATA[>') 145 */ 146 public function encodeEntities($data, $srcEncoding = '', $destEncoding = '') 147 { 148 if ($srcEncoding == '') { 149 // lame, but we know no better... 150 $srcEncoding = PhpXmlRpc::$xmlrpc_internalencoding; 151 } 152 153 if ($destEncoding == '') { 154 $destEncoding = 'US-ASCII'; 155 } 156 157 // in case there is transcoding going on, let's upscale to UTF8 158 /// @todo we should do this as well when $srcEncoding == $destEncoding and the encoding is not supported by 159 /// htmlspecialchars 160 if (!in_array($srcEncoding, array('UTF-8', 'ISO-8859-1', 'US-ASCII')) && $srcEncoding != $destEncoding && 161 function_exists('mb_convert_encoding')) { 162 $data = mb_convert_encoding($data, 'UTF-8', str_replace('US-ASCII', 'ASCII', $srcEncoding)); 163 $srcEncoding = 'UTF-8'; 164 } 165 166 $conversion = strtoupper($srcEncoding . '_' . $destEncoding); 167 168 // list ordered with (expected) most common scenarios first 169 switch ($conversion) { 170 case 'UTF-8_UTF-8': 171 case 'ISO-8859-1_ISO-8859-1': 172 case 'US-ASCII_UTF-8': 173 case 'US-ASCII_US-ASCII': 174 case 'US-ASCII_ISO-8859-1': 175 //case 'CP1252_CP1252': 176 $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); 177 break; 178 179 case 'UTF-8_US-ASCII': 180 case 'UTF-8_ISO-8859-1': 181 // NB: this will choke on invalid UTF-8, going most likely beyond EOF 182 $escapedData = ''; 183 // be kind to users creating string xml-rpc values out of different php types 184 $data = (string)$data; 185 $ns = strlen($data); 186 for ($nn = 0; $nn < $ns; $nn++) { 187 $ch = $data[$nn]; 188 $ii = ord($ch); 189 // 7 bits in 1 byte: 0bbbbbbb (127) 190 if ($ii < 32) { 191 if ($conversion == 'UTF-8_US-ASCII') { 192 $escapedData .= sprintf('&#%d;', $ii); 193 } else { 194 $escapedData .= $ch; 195 } 196 } 197 else if ($ii < 128) { 198 /// @todo shall we replace this with a (supposedly) faster str_replace? 199 /// @todo to be 'print safe', should we encode as well character 127 (DEL) ? 200 switch ($ii) { 201 case 34: 202 $escapedData .= '"'; 203 break; 204 case 38: 205 $escapedData .= '&'; 206 break; 207 case 39: 208 $escapedData .= '''; 209 break; 210 case 60: 211 $escapedData .= '<'; 212 break; 213 case 62: 214 $escapedData .= '>'; 215 break; 216 default: 217 $escapedData .= $ch; 218 } // switch 219 } // 11 bits in 2 bytes: 110bbbbb 10bbbbbb (2047) 220 elseif ($ii >> 5 == 6) { 221 $b1 = ($ii & 31); 222 $b2 = (ord($data[$nn + 1]) & 63); 223 $ii = ($b1 * 64) + $b2; 224 $escapedData .= sprintf('&#%d;', $ii); 225 $nn += 1; 226 } // 16 bits in 3 bytes: 1110bbbb 10bbbbbb 10bbbbbb 227 elseif ($ii >> 4 == 14) { 228 $b1 = ($ii & 15); 229 $b2 = (ord($data[$nn + 1]) & 63); 230 $b3 = (ord($data[$nn + 2]) & 63); 231 $ii = ((($b1 * 64) + $b2) * 64) + $b3; 232 $escapedData .= sprintf('&#%d;', $ii); 233 $nn += 2; 234 } // 21 bits in 4 bytes: 11110bbb 10bbbbbb 10bbbbbb 10bbbbbb 235 elseif ($ii >> 3 == 30) { 236 $b1 = ($ii & 7); 237 $b2 = (ord($data[$nn + 1]) & 63); 238 $b3 = (ord($data[$nn + 2]) & 63); 239 $b4 = (ord($data[$nn + 3]) & 63); 240 $ii = ((((($b1 * 64) + $b2) * 64) + $b3) * 64) + $b4; 241 $escapedData .= sprintf('&#%d;', $ii); 242 $nn += 3; 243 } 244 } 245 246 // when converting to latin-1, do not be so eager with using entities for characters 160-255 247 if ($conversion == 'UTF-8_ISO-8859-1') { 248 $this->buildConversionTable('xml_iso88591_Entities'); 249 $escapedData = str_replace(array_slice($this->xml_iso88591_Entities['out'], 32), array_slice($this->xml_iso88591_Entities['in'], 32), $escapedData); 250 } 251 break; 252 253 case 'ISO-8859-1_UTF-8': 254 $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); 255 /// @todo if on php >= 8.2, prefer using mbstring or iconv. Also: suppress the warning! 256 if (function_exists('mb_convert_encoding')) { 257 $escapedData = mb_convert_encoding($escapedData, 'UTF-8', 'ISO-8859-1'); 258 } else { 259 $escapedData = utf8_encode($escapedData); 260 } 261 break; 262 263 case 'ISO-8859-1_US-ASCII': 264 $this->buildConversionTable('xml_iso88591_Entities'); 265 $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); 266 $escapedData = str_replace($this->xml_iso88591_Entities['in'], $this->xml_iso88591_Entities['out'], $escapedData); 267 break; 268 269 /* 270 case 'CP1252_US-ASCII': 271 $this->buildConversionTable('xml_cp1252_Entities'); 272 $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); 273 $escapedData = str_replace($this->xml_iso88591_Entities']['in'], $this->xml_iso88591_Entities['out'], $escapedData); 274 $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); 275 break; 276 case 'CP1252_UTF-8': 277 $this->buildConversionTable('xml_cp1252_Entities'); 278 $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); 279 /// @todo we could use real UTF8 chars here instead of xml entities... (note that utf_8 encode all alone will NOT convert them) 280 $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); 281 $escapedData = utf8_encode($escapedData); 282 break; 283 case 'CP1252_ISO-8859-1': 284 $this->buildConversionTable('xml_cp1252_Entities'); 285 $escapedData = str_replace(array('&', '"', "'", '<', '>'), array('&', '"', ''', '<', '>'), $data); 286 // 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... 287 $escapedData = str_replace($this->xml_cp1252_Entities['in'], $this->xml_cp1252_Entities['out'], $escapedData); 288 break; 289 */ 290 291 default: 292 if (function_exists('mb_convert_encoding')) { 293 // If reaching where, there are only 2 cases possible: UTF8->XXX or XXX->XXX 294 // If src is UTF8, we run htmlspecialchars before converting to the target charset, as 295 // htmlspecialchars has limited charset support, but it groks utf8 296 if ($srcEncoding === 'UTF-8') { 297 $data = htmlspecialchars($data, defined('ENT_XML1') ? ENT_XML1 | ENT_QUOTES : ENT_QUOTES, 'UTF-8'); 298 } 299 if ($srcEncoding !== $destEncoding) { 300 try { 301 // php 7.4 and lower: a warning is generated. php 8.0 and up: an Error is thrown. So much for BC... 302 $data = @mb_convert_encoding($data, str_replace('US-ASCII', 'ASCII', $destEncoding), str_replace('US-ASCII', 'ASCII', $srcEncoding)); 303 } catch (\ValueError $e) { 304 $data = false; 305 } 306 } 307 if ($data === false) { 308 $escapedData = ''; 309 $this->getLogger()->error('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding via mbstring: failed..."); 310 } else { 311 if ($srcEncoding === 'UTF-8') { 312 $escapedData = $data; 313 } else { 314 $escapedData = htmlspecialchars($data, defined('ENT_XML1') ? ENT_XML1 | ENT_QUOTES : ENT_QUOTES, $destEncoding); 315 } 316 } 317 } else { 318 $escapedData = ''; 319 $this->getLogger()->error('XML-RPC: ' . __METHOD__ . ": Converting from $srcEncoding to $destEncoding: not supported..."); 320 } 321 } 322 323 return $escapedData; 324 } 325 326 /** 327 * @return string[] 328 */ 329 public function knownCharsets() 330 { 331 $knownCharsets = array('UTF-8', 'ISO-8859-1', 'US-ASCII'); 332 // Add all charsets which mbstring can handle, but remove junk not found in IANA registry at 333 // http://www.iana.org/assignments/character-sets/character-sets.xhtml 334 if (function_exists('mb_list_encodings')) { 335 $knownCharsets = array_unique(array_merge($knownCharsets, array_diff(mb_list_encodings(), array( 336 'pass', 'auto', 'wchar', 'BASE64', 'UUENCODE', 'ASCII', 'HTML-ENTITIES', 'Quoted-Printable', 337 '7bit','8bit', 'byte2be', 'byte2le', 'byte4be', 'byte4le' 338 )))); 339 } 340 return $knownCharsets; 341 } 342 343 // *** BC layer *** 344 345 /** 346 * Checks if a given charset encoding is present in a list of encodings or if it is a valid subset of any encoding 347 * in the list. 348 * @deprecated kept around for BC, as it is not in use by the lib 349 * 350 * @param string $encoding charset to be tested 351 * @param string|array $validList comma separated list of valid charsets (or array of charsets) 352 * @return bool 353 */ 354 public function isValidCharset($encoding, $validList) 355 { 356 $this->logDeprecation('Method ' . __METHOD__ . ' is deprecated'); 357 358 if (is_string($validList)) { 359 $validList = explode(',', $validList); 360 } 361 if (in_array(strtoupper($encoding), $validList)) { 362 return true; 363 } else { 364 if (array_key_exists($encoding, $this->charset_supersets)) { 365 foreach ($validList as $allowed) { 366 if (in_array($allowed, $this->charset_supersets[$encoding])) { 367 return true; 368 } 369 } 370 } 371 372 return false; 373 } 374 } 375 376 /** 377 * Used only for backwards compatibility (the .inc shims). 378 * @deprecated 379 * 380 * @param string $charset 381 * @return array 382 * @throws ValueErrorException for unknown/unsupported charsets 383 */ 384 public function getEntities($charset) 385 { 386 $this->logDeprecation('Method ' . __METHOD__ . ' is deprecated'); 387 388 switch ($charset) 389 { 390 case 'iso88591': 391 return $this->xml_iso88591_Entities; 392 default: 393 throw new ValueErrorException('Unsupported charset: ' . $charset); 394 } 395 } 396 }
title
Description
Body
title
Description
Body
title
Description
Body
title
Body
