paulgoughbooks_old
This repository has no backups
This repository's network speed is throttled to 100KB/sec
Upgrade your account to fix these warnings, or use backups.vc for automated backups
@ 2
paulgoughbooks_old / trunk / system / ThirdParty / Escaper / Escaper.php
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 |
<?php /** * @see https://github.com/laminas/laminas-escaper for the canonical source repository * @copyright https://github.com/laminas/laminas-escaper/blob/master/COPYRIGHT.md * @license https://github.com/laminas/laminas-escaper/blob/master/LICENSE.md New BSD License */ namespace Laminas\Escaper; /** * Context specific methods for use in secure output escaping */ class Escaper { /** * Entity Map mapping Unicode codepoints to any available named HTML entities. * * While HTML supports far more named entities, the lowest common denominator * has become HTML5's XML Serialisation which is restricted to the those named * entities that XML supports. Using HTML entities would result in this error: * XML Parsing Error: undefined entity * * @var array */ protected static $htmlNamedEntityMap = [ 34 => 'quot', // quotation mark 38 => 'amp', // ampersand 60 => 'lt', // less-than sign 62 => 'gt', // greater-than sign ]; /** * Current encoding for escaping. If not UTF-8, we convert strings from this encoding * pre-escaping and back to this encoding post-escaping. * * @var string */ protected $encoding = 'utf-8'; /** * Holds the value of the special flags passed as second parameter to * htmlspecialchars(). * * @var int */ protected $htmlSpecialCharsFlags; /** * Static Matcher which escapes characters for HTML Attribute contexts * * @var callable */ protected $htmlAttrMatcher; /** * Static Matcher which escapes characters for Javascript contexts * * @var callable */ protected $jsMatcher; /** * Static Matcher which escapes characters for CSS Attribute contexts * * @var callable */ protected $cssMatcher; /** * List of all encoding supported by this class * * @var array */ protected $supportedEncodings = [ 'iso-8859-1', 'iso8859-1', 'iso-8859-5', 'iso8859-5', 'iso-8859-15', 'iso8859-15', 'utf-8', 'cp866', 'ibm866', '866', 'cp1251', 'windows-1251', 'win-1251', '1251', 'cp1252', 'windows-1252', '1252', 'koi8-r', 'koi8-ru', 'koi8r', 'big5', '950', 'gb2312', '936', 'big5-hkscs', 'shift_jis', 'sjis', 'sjis-win', 'cp932', '932', 'euc-jp', 'eucjp', 'eucjp-win', 'macroman' ]; /** * Constructor: Single parameter allows setting of global encoding for use by * the current object. * * @param string $encoding * @throws Exception\InvalidArgumentException */ public function __construct($encoding = null) { if ($encoding !== null) { if (! is_string($encoding)) { throw new Exception\InvalidArgumentException( get_class($this) . ' constructor parameter must be a string, received ' . gettype($encoding) ); } if ($encoding === '') { throw new Exception\InvalidArgumentException( get_class($this) . ' constructor parameter does not allow a blank value' ); } $encoding = strtolower($encoding); if (! in_array($encoding, $this->supportedEncodings)) { throw new Exception\InvalidArgumentException( 'Value of \'' . $encoding . '\' passed to ' . get_class($this) . ' constructor parameter is invalid. Provide an encoding supported by htmlspecialchars()' ); } $this->encoding = $encoding; } // We take advantage of ENT_SUBSTITUTE flag to correctly deal with invalid UTF-8 sequences. $this->htmlSpecialCharsFlags = ENT_QUOTES | ENT_SUBSTITUTE; // set matcher callbacks $this->htmlAttrMatcher = [$this, 'htmlAttrMatcher']; $this->jsMatcher = [$this, 'jsMatcher']; $this->cssMatcher = [$this, 'cssMatcher']; } /** * Return the encoding that all output/input is expected to be encoded in. * * @return string */ public function getEncoding() { return $this->encoding; } /** * Escape a string for the HTML Body context where there are very few characters * of special meaning. Internally this will use htmlspecialchars(). * * @param string $string * @return string */ public function escapeHtml($string) { return htmlspecialchars($string, $this->htmlSpecialCharsFlags, $this->encoding); } /** * Escape a string for the HTML Attribute context. We use an extended set of characters * to escape that are not covered by htmlspecialchars() to cover cases where an attribute * might be unquoted or quoted illegally (e.g. backticks are valid quotes for IE). * * @param string $string * @return string */ public function escapeHtmlAttr($string) { $string = $this->toUtf8($string); if ($string === '' || ctype_digit($string)) { return $string; } $result = preg_replace_callback('/[^a-z0-9,\.\-_]/iSu', $this->htmlAttrMatcher, $string); return $this->fromUtf8($result); } /** * Escape a string for the Javascript context. This does not use json_encode(). An extended * set of characters are escaped beyond ECMAScript's rules for Javascript literal string * escaping in order to prevent misinterpretation of Javascript as HTML leading to the * injection of special characters and entities. The escaping used should be tolerant * of cases where HTML escaping was not applied on top of Javascript escaping correctly. * Backslash escaping is not used as it still leaves the escaped character as-is and so * is not useful in a HTML context. * * @param string $string * @return string */ public function escapeJs($string) { $string = $this->toUtf8($string); if ($string === '' || ctype_digit($string)) { return $string; } $result = preg_replace_callback('/[^a-z0-9,\._]/iSu', $this->jsMatcher, $string); return $this->fromUtf8($result); } /** * Escape a string for the URI or Parameter contexts. This should not be used to escape * an entire URI - only a subcomponent being inserted. The function is a simple proxy * to rawurlencode() which now implements RFC 3986 since PHP 5.3 completely. * * @param string $string * @return string */ public function escapeUrl($string) { return rawurlencode($string); } /** * Escape a string for the CSS context. CSS escaping can be applied to any string being * inserted into CSS and escapes everything except alphanumerics. * * @param string $string * @return string */ public function escapeCss($string) { $string = $this->toUtf8($string); if ($string === '' || ctype_digit($string)) { return $string; } $result = preg_replace_callback('/[^a-z0-9]/iSu', $this->cssMatcher, $string); return $this->fromUtf8($result); } /** * Callback function for preg_replace_callback that applies HTML Attribute * escaping to all matches. * * @param array $matches * @return string */ protected function htmlAttrMatcher($matches) { $chr = $matches[0]; $ord = ord($chr); /** * The following replaces characters undefined in HTML with the * hex entity for the Unicode replacement character. */ if (($ord <= 0x1f && $chr != "\t" && $chr != "\n" && $chr != "\r") || ($ord >= 0x7f && $ord <= 0x9f) ) { return '�'; } /** * Check if the current character to escape has a name entity we should * replace it with while grabbing the integer value of the character. */ if (strlen($chr) > 1) { $chr = $this->convertEncoding($chr, 'UTF-32BE', 'UTF-8'); } $hex = bin2hex($chr); $ord = hexdec($hex); if (isset(static::$htmlNamedEntityMap[$ord])) { return '&' . static::$htmlNamedEntityMap[$ord] . ';'; } /** * Per OWASP recommendations, we'll use upper hex entities * for any other characters where a named entity does not exist. */ if ($ord > 255) { return sprintf('&#x%04X;', $ord); } return sprintf('&#x%02X;', $ord); } /** * Callback function for preg_replace_callback that applies Javascript * escaping to all matches. * * @param array $matches * @return string */ protected function jsMatcher($matches) { $chr = $matches[0]; if (strlen($chr) == 1) { return sprintf('\\x%02X', ord($chr)); } $chr = $this->convertEncoding($chr, 'UTF-16BE', 'UTF-8'); $hex = strtoupper(bin2hex($chr)); if (strlen($hex) <= 4) { return sprintf('\\u%04s', $hex); } $highSurrogate = substr($hex, 0, 4); $lowSurrogate = substr($hex, 4, 4); return sprintf('\\u%04s\\u%04s', $highSurrogate, $lowSurrogate); } /** * Callback function for preg_replace_callback that applies CSS * escaping to all matches. * * @param array $matches * @return string */ protected function cssMatcher($matches) { $chr = $matches[0]; if (strlen($chr) == 1) { $ord = ord($chr); } else { $chr = $this->convertEncoding($chr, 'UTF-32BE', 'UTF-8'); $ord = hexdec(bin2hex($chr)); } return sprintf('\\%X ', $ord); } /** * Converts a string to UTF-8 from the base encoding. The base encoding is set via this * class' constructor. * * @param string $string * @throws Exception\RuntimeException * @return string */ protected function toUtf8($string) { if ($this->getEncoding() === 'utf-8') { $result = $string; } else { $result = $this->convertEncoding($string, 'UTF-8', $this->getEncoding()); } if (! $this->isUtf8($result)) { throw new Exception\RuntimeException( sprintf('String to be escaped was not valid UTF-8 or could not be converted: %s', $result) ); } return $result; } /** * Converts a string from UTF-8 to the base encoding. The base encoding is set via this * class' constructor. * @param string $string * @return string */ protected function fromUtf8($string) { if ($this->getEncoding() === 'utf-8') { return $string; } return $this->convertEncoding($string, $this->getEncoding(), 'UTF-8'); } /** * Checks if a given string appears to be valid UTF-8 or not. * * @param string $string * @return bool */ protected function isUtf8($string) { return ($string === '' || preg_match('/^./su', $string)); } /** * Encoding conversion helper which wraps iconv and mbstring where they exist or throws * and exception where neither is available. * * @param string $string * @param string $to * @param array|string $from * @throws Exception\RuntimeException * @return string */ protected function convertEncoding($string, $to, $from) { if (function_exists('iconv')) { $result = iconv($from, $to, $string); } elseif (function_exists('mb_convert_encoding')) { $result = mb_convert_encoding($string, $to, $from); } else { throw new Exception\RuntimeException( get_class($this) . ' requires either the iconv or mbstring extension to be installed' . ' when escaping for non UTF-8 strings.' ); } if ($result === false) { return ''; // return non-fatal blank string on encoding errors from users } return $result; } } |
Commits for paulgoughbooks_old/trunk/system/ThirdParty/Escaper/Escaper.php
Revision | Author | Commited | Message |
---|---|---|---|
2 | tporter | Tue 03 Nov, 2020 08:50:21 +0000 | Migration of Paul Goughs Books site to Codeignitor 4 |