Resources
2 years ago
Iconv.php
3 months ago
LICENSE
2 years ago
README.md
4 years ago
bootstrap.php
8 months ago
bootstrap80.php
8 months ago
Iconv.php
518 lines
| 1 | <?php |
| 2 | |
| 3 | /* |
| 4 | * This file is part of the Symfony package. |
| 5 | * |
| 6 | * (c) Fabien Potencier <fabien@symfony.com> |
| 7 | * |
| 8 | * For the full copyright and license information, please view the LICENSE |
| 9 | * file that was distributed with this source code. |
| 10 | */ |
| 11 | namespace Symfony\Polyfill\Iconv; |
| 12 | |
| 13 | /** |
| 14 | * iconv implementation in pure PHP, UTF-8 centric. |
| 15 | * |
| 16 | * Implemented: |
| 17 | * - iconv - Convert string to requested character encoding |
| 18 | * - iconv_mime_decode - Decodes a MIME header field |
| 19 | * - iconv_mime_decode_headers - Decodes multiple MIME header fields at once |
| 20 | * - iconv_get_encoding - Retrieve internal configuration variables of iconv extension |
| 21 | * - iconv_set_encoding - Set current setting for character encoding conversion |
| 22 | * - iconv_mime_encode - Composes a MIME header field |
| 23 | * - iconv_strlen - Returns the character count of string |
| 24 | * - iconv_strpos - Finds position of first occurrence of a needle within a haystack |
| 25 | * - iconv_strrpos - Finds the last occurrence of a needle within a haystack |
| 26 | * - iconv_substr - Cut out part of a string |
| 27 | * |
| 28 | * Charsets available for conversion are defined by files |
| 29 | * in the charset/ directory and by Iconv::$alias below. |
| 30 | * You're welcome to send back any addition you make. |
| 31 | * |
| 32 | * @author Nicolas Grekas <p@tchwork.com> |
| 33 | * |
| 34 | * @internal |
| 35 | */ |
| 36 | final class Iconv |
| 37 | { |
| 38 | public const ERROR_ILLEGAL_CHARACTER = 'iconv(): Detected an illegal character in input string'; |
| 39 | public const ERROR_WRONG_CHARSET = 'iconv(): Wrong charset, conversion from `%s\' to `%s\' is not allowed'; |
| 40 | public static $inputEncoding = 'utf-8'; |
| 41 | public static $outputEncoding = 'utf-8'; |
| 42 | public static $internalEncoding = 'utf-8'; |
| 43 | private static $alias = ['utf8' => 'utf-8', 'ascii' => 'us-ascii', 'tis-620' => 'iso-8859-11', 'cp1250' => 'windows-1250', 'cp1251' => 'windows-1251', 'cp1252' => 'windows-1252', 'cp1253' => 'windows-1253', 'cp1254' => 'windows-1254', 'cp1255' => 'windows-1255', 'cp1256' => 'windows-1256', 'cp1257' => 'windows-1257', 'cp1258' => 'windows-1258', 'shift-jis' => 'cp932', 'shift_jis' => 'cp932', 'latin1' => 'iso-8859-1', 'latin2' => 'iso-8859-2', 'latin3' => 'iso-8859-3', 'latin4' => 'iso-8859-4', 'latin5' => 'iso-8859-9', 'latin6' => 'iso-8859-10', 'latin7' => 'iso-8859-13', 'latin8' => 'iso-8859-14', 'latin9' => 'iso-8859-15', 'latin10' => 'iso-8859-16', 'iso8859-1' => 'iso-8859-1', 'iso8859-2' => 'iso-8859-2', 'iso8859-3' => 'iso-8859-3', 'iso8859-4' => 'iso-8859-4', 'iso8859-5' => 'iso-8859-5', 'iso8859-6' => 'iso-8859-6', 'iso8859-7' => 'iso-8859-7', 'iso8859-8' => 'iso-8859-8', 'iso8859-9' => 'iso-8859-9', 'iso8859-10' => 'iso-8859-10', 'iso8859-11' => 'iso-8859-11', 'iso8859-12' => 'iso-8859-12', 'iso8859-13' => 'iso-8859-13', 'iso8859-14' => 'iso-8859-14', 'iso8859-15' => 'iso-8859-15', 'iso8859-16' => 'iso-8859-16', 'iso_8859-1' => 'iso-8859-1', 'iso_8859-2' => 'iso-8859-2', 'iso_8859-3' => 'iso-8859-3', 'iso_8859-4' => 'iso-8859-4', 'iso_8859-5' => 'iso-8859-5', 'iso_8859-6' => 'iso-8859-6', 'iso_8859-7' => 'iso-8859-7', 'iso_8859-8' => 'iso-8859-8', 'iso_8859-9' => 'iso-8859-9', 'iso_8859-10' => 'iso-8859-10', 'iso_8859-11' => 'iso-8859-11', 'iso_8859-12' => 'iso-8859-12', 'iso_8859-13' => 'iso-8859-13', 'iso_8859-14' => 'iso-8859-14', 'iso_8859-15' => 'iso-8859-15', 'iso_8859-16' => 'iso-8859-16', 'iso88591' => 'iso-8859-1', 'iso88592' => 'iso-8859-2', 'iso88593' => 'iso-8859-3', 'iso88594' => 'iso-8859-4', 'iso88595' => 'iso-8859-5', 'iso88596' => 'iso-8859-6', 'iso88597' => 'iso-8859-7', 'iso88598' => 'iso-8859-8', 'iso88599' => 'iso-8859-9', 'iso885910' => 'iso-8859-10', 'iso885911' => 'iso-8859-11', 'iso885912' => 'iso-8859-12', 'iso885913' => 'iso-8859-13', 'iso885914' => 'iso-8859-14', 'iso885915' => 'iso-8859-15', 'iso885916' => 'iso-8859-16']; |
| 44 | private static $translitMap = []; |
| 45 | private static $convertMap = []; |
| 46 | private static $errorHandler; |
| 47 | private static $lastError; |
| 48 | private static $ulenMask = ["\xc0" => 2, "\xd0" => 2, "\xe0" => 3, "\xf0" => 4]; |
| 49 | private static $isValidUtf8; |
| 50 | public static function iconv($inCharset, $outCharset, $str) |
| 51 | { |
| 52 | $str = (string) $str; |
| 53 | if ('' === $str) { |
| 54 | return ''; |
| 55 | } |
| 56 | // Prepare for //IGNORE and //TRANSLIT |
| 57 | $translit = $ignore = ''; |
| 58 | $outCharset = strtolower($outCharset); |
| 59 | $inCharset = strtolower($inCharset); |
| 60 | if ('' === $outCharset) { |
| 61 | $outCharset = 'iso-8859-1'; |
| 62 | } |
| 63 | if ('' === $inCharset) { |
| 64 | $inCharset = 'iso-8859-1'; |
| 65 | } |
| 66 | do { |
| 67 | $loop = \false; |
| 68 | if ('//translit' === substr($outCharset, -10)) { |
| 69 | $loop = $translit = \true; |
| 70 | $outCharset = substr($outCharset, 0, -10); |
| 71 | } |
| 72 | if ('//ignore' === substr($outCharset, -8)) { |
| 73 | $loop = $ignore = \true; |
| 74 | $outCharset = substr($outCharset, 0, -8); |
| 75 | } |
| 76 | } while ($loop); |
| 77 | do { |
| 78 | $loop = \false; |
| 79 | if ('//translit' === substr($inCharset, -10)) { |
| 80 | $loop = \true; |
| 81 | $inCharset = substr($inCharset, 0, -10); |
| 82 | } |
| 83 | if ('//ignore' === substr($inCharset, -8)) { |
| 84 | $loop = \true; |
| 85 | $inCharset = substr($inCharset, 0, -8); |
| 86 | } |
| 87 | } while ($loop); |
| 88 | if (isset(self::$alias[$inCharset])) { |
| 89 | $inCharset = self::$alias[$inCharset]; |
| 90 | } |
| 91 | if (isset(self::$alias[$outCharset])) { |
| 92 | $outCharset = self::$alias[$outCharset]; |
| 93 | } |
| 94 | // Load charset maps |
| 95 | if ('utf-8' !== $inCharset && !self::loadMap('from.', $inCharset, $inMap) || 'utf-8' !== $outCharset && !self::loadMap('to.', $outCharset, $outMap)) { |
| 96 | trigger_error(\sprintf(self::ERROR_WRONG_CHARSET, $inCharset, $outCharset)); |
| 97 | return \false; |
| 98 | } |
| 99 | if ('utf-8' !== $inCharset) { |
| 100 | // Convert input to UTF-8 |
| 101 | $result = ''; |
| 102 | if (self::mapToUtf8($result, $inMap, $str, $ignore)) { |
| 103 | $str = $result; |
| 104 | } else { |
| 105 | $str = \false; |
| 106 | } |
| 107 | self::$isValidUtf8 = \true; |
| 108 | } else { |
| 109 | self::$isValidUtf8 = preg_match('//u', $str); |
| 110 | if (!self::$isValidUtf8 && !$ignore) { |
| 111 | trigger_error(self::ERROR_ILLEGAL_CHARACTER); |
| 112 | return \false; |
| 113 | } |
| 114 | if ('utf-8' === $outCharset) { |
| 115 | // UTF-8 validation |
| 116 | $str = self::utf8ToUtf8($str, $ignore); |
| 117 | } |
| 118 | } |
| 119 | if ('utf-8' !== $outCharset && \false !== $str) { |
| 120 | // Convert output to UTF-8 |
| 121 | $result = ''; |
| 122 | if (self::mapFromUtf8($result, $outMap, $str, $ignore, $translit)) { |
| 123 | return $result; |
| 124 | } |
| 125 | return \false; |
| 126 | } |
| 127 | return $str; |
| 128 | } |
| 129 | public static function iconv_mime_decode_headers($str, $mode = 0, $charset = null) |
| 130 | { |
| 131 | if (null === $charset) { |
| 132 | $charset = self::$internalEncoding; |
| 133 | } |
| 134 | if (\false !== strpos($str, "\r")) { |
| 135 | $str = strtr(str_replace("\r\n", "\n", $str), "\r", "\n"); |
| 136 | } |
| 137 | $str = explode("\n\n", $str, 2); |
| 138 | $headers = []; |
| 139 | $str = preg_split('/\\n(?![ \\t])/', $str[0]); |
| 140 | foreach ($str as $str) { |
| 141 | $str = self::iconv_mime_decode($str, $mode, $charset); |
| 142 | if (\false === $str) { |
| 143 | return \false; |
| 144 | } |
| 145 | $str = explode(':', $str, 2); |
| 146 | if (2 === \count($str)) { |
| 147 | if (isset($headers[$str[0]])) { |
| 148 | if (!\is_array($headers[$str[0]])) { |
| 149 | $headers[$str[0]] = [$headers[$str[0]]]; |
| 150 | } |
| 151 | $headers[$str[0]][] = ltrim($str[1]); |
| 152 | } else { |
| 153 | $headers[$str[0]] = ltrim($str[1]); |
| 154 | } |
| 155 | } |
| 156 | } |
| 157 | return $headers; |
| 158 | } |
| 159 | public static function iconv_mime_decode($str, $mode = 0, $charset = null) |
| 160 | { |
| 161 | if (null === $charset) { |
| 162 | $charset = self::$internalEncoding; |
| 163 | } |
| 164 | if (\ICONV_MIME_DECODE_CONTINUE_ON_ERROR & $mode) { |
| 165 | $charset .= '//IGNORE'; |
| 166 | } |
| 167 | if (\false !== strpos($str, "\r")) { |
| 168 | $str = strtr(str_replace("\r\n", "\n", $str), "\r", "\n"); |
| 169 | } |
| 170 | $str = preg_split('/\\n(?![ \\t])/', rtrim($str), 2); |
| 171 | $str = preg_replace('/[ \\t]*\\n[ \\t]+/', ' ', rtrim($str[0])); |
| 172 | $str = preg_split('/=\\?([^?]+)\\?([bqBQ])\\?(.*?)\\?=/', $str, -1, \PREG_SPLIT_DELIM_CAPTURE); |
| 173 | $result = self::iconv('utf-8', $charset, $str[0]); |
| 174 | if (\false === $result) { |
| 175 | return \false; |
| 176 | } |
| 177 | $i = 1; |
| 178 | $len = \count($str); |
| 179 | while ($i < $len) { |
| 180 | $c = strtolower($str[$i]); |
| 181 | if (\ICONV_MIME_DECODE_CONTINUE_ON_ERROR & $mode && 'utf-8' !== $c && !isset(self::$alias[$c]) && !self::loadMap('from.', $c, $d)) { |
| 182 | $d = \false; |
| 183 | } elseif ('B' === strtoupper($str[$i + 1])) { |
| 184 | $d = base64_decode($str[$i + 2]); |
| 185 | } else { |
| 186 | $d = rawurldecode(strtr(str_replace('%', '%25', $str[$i + 2]), '=_', '% ')); |
| 187 | } |
| 188 | if (\false !== $d) { |
| 189 | if ('' !== $d) { |
| 190 | if ('' === ($d = self::iconv($c, $charset, $d))) { |
| 191 | $str[$i + 3] = substr($str[$i + 3], 1); |
| 192 | } else { |
| 193 | $result .= $d; |
| 194 | } |
| 195 | } |
| 196 | $d = self::iconv('utf-8', $charset, $str[$i + 3]); |
| 197 | if ('' !== trim($d)) { |
| 198 | $result .= $d; |
| 199 | } |
| 200 | } elseif (\ICONV_MIME_DECODE_CONTINUE_ON_ERROR & $mode) { |
| 201 | $result .= "=?{$str[$i]}?{$str[$i + 1]}?{$str[$i + 2]}?={$str[$i + 3]}"; |
| 202 | } else { |
| 203 | $result = \false; |
| 204 | break; |
| 205 | } |
| 206 | $i += 4; |
| 207 | } |
| 208 | return $result; |
| 209 | } |
| 210 | public static function iconv_get_encoding($type = 'all') |
| 211 | { |
| 212 | switch ($type) { |
| 213 | case 'input_encoding': |
| 214 | return self::$inputEncoding; |
| 215 | case 'output_encoding': |
| 216 | return self::$outputEncoding; |
| 217 | case 'internal_encoding': |
| 218 | return self::$internalEncoding; |
| 219 | } |
| 220 | return ['input_encoding' => self::$inputEncoding, 'output_encoding' => self::$outputEncoding, 'internal_encoding' => self::$internalEncoding]; |
| 221 | } |
| 222 | public static function iconv_set_encoding($type, $charset) |
| 223 | { |
| 224 | switch ($type) { |
| 225 | case 'input_encoding': |
| 226 | self::$inputEncoding = $charset; |
| 227 | break; |
| 228 | case 'output_encoding': |
| 229 | self::$outputEncoding = $charset; |
| 230 | break; |
| 231 | case 'internal_encoding': |
| 232 | self::$internalEncoding = $charset; |
| 233 | break; |
| 234 | default: |
| 235 | return \false; |
| 236 | } |
| 237 | return \true; |
| 238 | } |
| 239 | public static function iconv_mime_encode($fieldName, $fieldValue, $pref = null) |
| 240 | { |
| 241 | if (!\is_array($pref)) { |
| 242 | $pref = []; |
| 243 | } |
| 244 | $pref += ['scheme' => 'B', 'input-charset' => self::$internalEncoding, 'output-charset' => self::$internalEncoding, 'line-length' => 76, 'line-break-chars' => "\r\n"]; |
| 245 | if (preg_match('/[\\x80-\\xFF]/', $fieldName)) { |
| 246 | $fieldName = ''; |
| 247 | } |
| 248 | $scheme = strtoupper(substr($pref['scheme'], 0, 1)); |
| 249 | $in = strtolower($pref['input-charset']); |
| 250 | $out = strtolower($pref['output-charset']); |
| 251 | if ('utf-8' !== $in && \false === ($fieldValue = self::iconv($in, 'utf-8', $fieldValue))) { |
| 252 | return \false; |
| 253 | } |
| 254 | preg_match_all('/./us', $fieldValue, $chars); |
| 255 | $chars = $chars[0] ?? []; |
| 256 | $lineBreak = (int) $pref['line-length']; |
| 257 | $lineStart = "=?{$pref['output-charset']}?{$scheme}?"; |
| 258 | $lineLength = \strlen($fieldName) + 2 + \strlen($lineStart) + 2; |
| 259 | $lineOffset = \strlen($lineStart) + 3; |
| 260 | $lineData = ''; |
| 261 | $fieldValue = []; |
| 262 | $Q = 'Q' === $scheme; |
| 263 | foreach ($chars as $c) { |
| 264 | if ('utf-8' !== $out && \false === ($c = self::iconv('utf-8', $out, $c))) { |
| 265 | return \false; |
| 266 | } |
| 267 | $o = $Q ? $c = preg_replace_callback('/[=_\\?\\x00-\\x1F\\x80-\\xFF]/', [__CLASS__, 'qpByteCallback'], $c) : base64_encode($lineData . $c); |
| 268 | if (isset($o[$lineBreak - $lineLength])) { |
| 269 | if (!$Q) { |
| 270 | $lineData = base64_encode($lineData); |
| 271 | } |
| 272 | $fieldValue[] = $lineStart . $lineData . '?='; |
| 273 | $lineLength = $lineOffset; |
| 274 | $lineData = ''; |
| 275 | } |
| 276 | $lineData .= $c; |
| 277 | $Q && ($lineLength += \strlen($c)); |
| 278 | } |
| 279 | if ('' !== $lineData) { |
| 280 | if (!$Q) { |
| 281 | $lineData = base64_encode($lineData); |
| 282 | } |
| 283 | $fieldValue[] = $lineStart . $lineData . '?='; |
| 284 | } |
| 285 | return $fieldName . ': ' . implode($pref['line-break-chars'] . ' ', $fieldValue); |
| 286 | } |
| 287 | public static function iconv_strlen($s, $encoding = null) |
| 288 | { |
| 289 | if (null === $encoding) { |
| 290 | $encoding = self::$internalEncoding; |
| 291 | } |
| 292 | if (0 !== stripos($encoding, 'utf-8') && \false === ($s = self::iconv($encoding, 'utf-8', $s))) { |
| 293 | return \false; |
| 294 | } |
| 295 | $ulenMask = self::$ulenMask; |
| 296 | $i = 0; |
| 297 | $j = 0; |
| 298 | $len = \strlen($s); |
| 299 | while ($i < $len) { |
| 300 | $u = $s[$i] & "\xf0"; |
| 301 | $i += $ulenMask[$u] ?? 1; |
| 302 | ++$j; |
| 303 | } |
| 304 | return $j; |
| 305 | } |
| 306 | public static function iconv_strpos($haystack, $needle, $offset = 0, $encoding = null) |
| 307 | { |
| 308 | if (null === $encoding) { |
| 309 | $encoding = self::$internalEncoding; |
| 310 | } |
| 311 | if (0 !== stripos($encoding, 'utf-8')) { |
| 312 | if (\false === ($haystack = self::iconv($encoding, 'utf-8', $haystack))) { |
| 313 | return \false; |
| 314 | } |
| 315 | if (\false === ($needle = self::iconv($encoding, 'utf-8', $needle))) { |
| 316 | return \false; |
| 317 | } |
| 318 | } |
| 319 | if ($offset = (int) $offset) { |
| 320 | $haystack = self::iconv_substr($haystack, $offset, 2147483647, 'utf-8'); |
| 321 | } |
| 322 | $pos = strpos($haystack, $needle); |
| 323 | return \false === $pos ? \false : $offset + ($pos ? self::iconv_strlen(substr($haystack, 0, $pos), 'utf-8') : 0); |
| 324 | } |
| 325 | public static function iconv_strrpos($haystack, $needle, $encoding = null) |
| 326 | { |
| 327 | if (null === $encoding) { |
| 328 | $encoding = self::$internalEncoding; |
| 329 | } |
| 330 | if (0 !== stripos($encoding, 'utf-8')) { |
| 331 | if (\false === ($haystack = self::iconv($encoding, 'utf-8', $haystack))) { |
| 332 | return \false; |
| 333 | } |
| 334 | if (\false === ($needle = self::iconv($encoding, 'utf-8', $needle))) { |
| 335 | return \false; |
| 336 | } |
| 337 | } |
| 338 | $pos = isset($needle[0]) ? strrpos($haystack, $needle) : \false; |
| 339 | return \false === $pos ? \false : self::iconv_strlen($pos ? substr($haystack, 0, $pos) : $haystack, 'utf-8'); |
| 340 | } |
| 341 | public static function iconv_substr($s, $start, $length = 2147483647, $encoding = null) |
| 342 | { |
| 343 | if (null === $encoding) { |
| 344 | $encoding = self::$internalEncoding; |
| 345 | } |
| 346 | if (0 !== stripos($encoding, 'utf-8')) { |
| 347 | $encoding = null; |
| 348 | } elseif (\false === ($s = self::iconv($encoding, 'utf-8', $s))) { |
| 349 | return \false; |
| 350 | } |
| 351 | $s = (string) $s; |
| 352 | $slen = self::iconv_strlen($s, 'utf-8'); |
| 353 | $start = (int) $start; |
| 354 | if (0 > $start) { |
| 355 | $start += $slen; |
| 356 | } |
| 357 | if (0 > $start) { |
| 358 | if (\PHP_VERSION_ID < 80000) { |
| 359 | return \false; |
| 360 | } |
| 361 | $start = 0; |
| 362 | } |
| 363 | if ($start >= $slen) { |
| 364 | return \PHP_VERSION_ID >= 80000 ? '' : \false; |
| 365 | } |
| 366 | $rx = $slen - $start; |
| 367 | if (0 > $length) { |
| 368 | $length += $rx; |
| 369 | } |
| 370 | if (0 === $length) { |
| 371 | return ''; |
| 372 | } |
| 373 | if (0 > $length) { |
| 374 | return \PHP_VERSION_ID >= 80000 ? '' : \false; |
| 375 | } |
| 376 | if ($length > $rx) { |
| 377 | $length = $rx; |
| 378 | } |
| 379 | $rx = '/^' . ($start ? self::pregOffset($start) : '') . '(' . self::pregOffset($length) . ')/u'; |
| 380 | $s = preg_match($rx, $s, $s) ? $s[1] : ''; |
| 381 | if (null === $encoding) { |
| 382 | return $s; |
| 383 | } |
| 384 | return self::iconv('utf-8', $encoding, $s); |
| 385 | } |
| 386 | private static function loadMap($type, $charset, &$map) |
| 387 | { |
| 388 | if (!isset(self::$convertMap[$type . $charset])) { |
| 389 | if (\false === ($map = self::getData($type . $charset))) { |
| 390 | if ('to.' === $type && self::loadMap('from.', $charset, $map)) { |
| 391 | $map = array_flip($map); |
| 392 | } else { |
| 393 | return \false; |
| 394 | } |
| 395 | } |
| 396 | self::$convertMap[$type . $charset] = $map; |
| 397 | } else { |
| 398 | $map = self::$convertMap[$type . $charset]; |
| 399 | } |
| 400 | return \true; |
| 401 | } |
| 402 | private static function utf8ToUtf8($str, $ignore) |
| 403 | { |
| 404 | $ulenMask = self::$ulenMask; |
| 405 | $valid = self::$isValidUtf8; |
| 406 | $u = $str; |
| 407 | $i = $j = 0; |
| 408 | $len = \strlen($str); |
| 409 | while ($i < $len) { |
| 410 | if ($str[$i] < "\x80") { |
| 411 | $u[$j++] = $str[$i++]; |
| 412 | } else { |
| 413 | $ulen = $str[$i] & "\xf0"; |
| 414 | $ulen = $ulenMask[$ulen] ?? 1; |
| 415 | $uchr = substr($str, $i, $ulen); |
| 416 | if (1 === $ulen || !($valid || preg_match('/^.$/us', $uchr))) { |
| 417 | if ($ignore) { |
| 418 | ++$i; |
| 419 | continue; |
| 420 | } |
| 421 | trigger_error(self::ERROR_ILLEGAL_CHARACTER); |
| 422 | return \false; |
| 423 | } |
| 424 | $i += $ulen; |
| 425 | $u[$j++] = $uchr[0]; |
| 426 | isset($uchr[1]) && 0 !== ($u[$j++] = $uchr[1]) && isset($uchr[2]) && 0 !== ($u[$j++] = $uchr[2]) && isset($uchr[3]) && 0 !== ($u[$j++] = $uchr[3]); |
| 427 | } |
| 428 | } |
| 429 | return substr($u, 0, $j); |
| 430 | } |
| 431 | private static function mapToUtf8(&$result, array $map, $str, $ignore) |
| 432 | { |
| 433 | $len = \strlen($str); |
| 434 | for ($i = 0; $i < $len; ++$i) { |
| 435 | if (isset($str[$i + 1], $map[$str[$i] . $str[$i + 1]])) { |
| 436 | $result .= $map[$str[$i] . $str[++$i]]; |
| 437 | } elseif (isset($map[$str[$i]])) { |
| 438 | $result .= $map[$str[$i]]; |
| 439 | } elseif (!$ignore) { |
| 440 | trigger_error(self::ERROR_ILLEGAL_CHARACTER); |
| 441 | return \false; |
| 442 | } |
| 443 | } |
| 444 | return \true; |
| 445 | } |
| 446 | private static function mapFromUtf8(&$result, array $map, $str, $ignore, $translit) |
| 447 | { |
| 448 | $ulenMask = self::$ulenMask; |
| 449 | $valid = self::$isValidUtf8; |
| 450 | if ($translit && !self::$translitMap) { |
| 451 | self::$translitMap = self::getData('translit'); |
| 452 | } |
| 453 | $i = 0; |
| 454 | $len = \strlen($str); |
| 455 | while ($i < $len) { |
| 456 | if ($str[$i] < "\x80") { |
| 457 | $uchr = $str[$i++]; |
| 458 | } else { |
| 459 | $ulen = $str[$i] & "\xf0"; |
| 460 | $ulen = $ulenMask[$ulen] ?? 1; |
| 461 | $uchr = substr($str, $i, $ulen); |
| 462 | if ($ignore && (1 === $ulen || !($valid || preg_match('/^.$/us', $uchr)))) { |
| 463 | ++$i; |
| 464 | continue; |
| 465 | } |
| 466 | $i += $ulen; |
| 467 | } |
| 468 | if (isset($map[$uchr])) { |
| 469 | $result .= $map[$uchr]; |
| 470 | } elseif ($translit) { |
| 471 | if (isset(self::$translitMap[$uchr])) { |
| 472 | $uchr = self::$translitMap[$uchr]; |
| 473 | } elseif ($uchr >= "À") { |
| 474 | $uchr = \Normalizer::normalize($uchr, \Normalizer::NFD); |
| 475 | if ($uchr[0] < "\x80") { |
| 476 | $uchr = $uchr[0]; |
| 477 | } elseif ($ignore) { |
| 478 | continue; |
| 479 | } else { |
| 480 | return \false; |
| 481 | } |
| 482 | } elseif ($ignore) { |
| 483 | continue; |
| 484 | } else { |
| 485 | return \false; |
| 486 | } |
| 487 | $str = $uchr . substr($str, $i); |
| 488 | $len = \strlen($str); |
| 489 | $i = 0; |
| 490 | } elseif (!$ignore) { |
| 491 | return \false; |
| 492 | } |
| 493 | } |
| 494 | return \true; |
| 495 | } |
| 496 | private static function qpByteCallback(array $m) |
| 497 | { |
| 498 | return '=' . strtoupper(dechex(\ord($m[0]))); |
| 499 | } |
| 500 | private static function pregOffset($offset) |
| 501 | { |
| 502 | $rx = []; |
| 503 | $offset = (int) $offset; |
| 504 | while ($offset > 65535) { |
| 505 | $rx[] = '.{65535}'; |
| 506 | $offset -= 65535; |
| 507 | } |
| 508 | return implode('', $rx) . '.{' . $offset . '}'; |
| 509 | } |
| 510 | private static function getData($file) |
| 511 | { |
| 512 | if (file_exists($file = __DIR__ . '/Resources/charset/' . $file . '.php')) { |
| 513 | return require $file; |
| 514 | } |
| 515 | return \false; |
| 516 | } |
| 517 | } |
| 518 |