Mbstring.php
849 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 | |
| 12 | namespace Symfony\Polyfill\Mbstring; |
| 13 | |
| 14 | /** |
| 15 | * Partial mbstring implementation in PHP, iconv based, UTF-8 centric. |
| 16 | * |
| 17 | * Implemented: |
| 18 | * - mb_chr - Returns a specific character from its Unicode code point |
| 19 | * - mb_convert_encoding - Convert character encoding |
| 20 | * - mb_convert_variables - Convert character code in variable(s) |
| 21 | * - mb_decode_mimeheader - Decode string in MIME header field |
| 22 | * - mb_encode_mimeheader - Encode string for MIME header XXX NATIVE IMPLEMENTATION IS REALLY BUGGED |
| 23 | * - mb_decode_numericentity - Decode HTML numeric string reference to character |
| 24 | * - mb_encode_numericentity - Encode character to HTML numeric string reference |
| 25 | * - mb_convert_case - Perform case folding on a string |
| 26 | * - mb_detect_encoding - Detect character encoding |
| 27 | * - mb_get_info - Get internal settings of mbstring |
| 28 | * - mb_http_input - Detect HTTP input character encoding |
| 29 | * - mb_http_output - Set/Get HTTP output character encoding |
| 30 | * - mb_internal_encoding - Set/Get internal character encoding |
| 31 | * - mb_list_encodings - Returns an array of all supported encodings |
| 32 | * - mb_ord - Returns the Unicode code point of a character |
| 33 | * - mb_output_handler - Callback function converts character encoding in output buffer |
| 34 | * - mb_scrub - Replaces ill-formed byte sequences with substitute characters |
| 35 | * - mb_strlen - Get string length |
| 36 | * - mb_strpos - Find position of first occurrence of string in a string |
| 37 | * - mb_strrpos - Find position of last occurrence of a string in a string |
| 38 | * - mb_str_split - Convert a string to an array |
| 39 | * - mb_strtolower - Make a string lowercase |
| 40 | * - mb_strtoupper - Make a string uppercase |
| 41 | * - mb_substitute_character - Set/Get substitution character |
| 42 | * - mb_substr - Get part of string |
| 43 | * - mb_stripos - Finds position of first occurrence of a string within another, case insensitive |
| 44 | * - mb_stristr - Finds first occurrence of a string within another, case insensitive |
| 45 | * - mb_strrchr - Finds the last occurrence of a character in a string within another |
| 46 | * - mb_strrichr - Finds the last occurrence of a character in a string within another, case insensitive |
| 47 | * - mb_strripos - Finds position of last occurrence of a string within another, case insensitive |
| 48 | * - mb_strstr - Finds first occurrence of a string within another |
| 49 | * - mb_strwidth - Return width of string |
| 50 | * - mb_substr_count - Count the number of substring occurrences |
| 51 | * |
| 52 | * Not implemented: |
| 53 | * - mb_convert_kana - Convert "kana" one from another ("zen-kaku", "han-kaku" and more) |
| 54 | * - mb_ereg_* - Regular expression with multibyte support |
| 55 | * - mb_parse_str - Parse GET/POST/COOKIE data and set global variable |
| 56 | * - mb_preferred_mime_name - Get MIME charset string |
| 57 | * - mb_regex_encoding - Returns current encoding for multibyte regex as string |
| 58 | * - mb_regex_set_options - Set/Get the default options for mbregex functions |
| 59 | * - mb_send_mail - Send encoded mail |
| 60 | * - mb_split - Split multibyte string using regular expression |
| 61 | * - mb_strcut - Get part of string |
| 62 | * - mb_strimwidth - Get truncated string with specified width |
| 63 | * |
| 64 | * @author Nicolas Grekas <p@tchwork.com> |
| 65 | * |
| 66 | * @internal |
| 67 | */ |
| 68 | final class Mbstring |
| 69 | { |
| 70 | const MB_CASE_FOLD = PHP_INT_MAX; |
| 71 | |
| 72 | private static $encodingList = array('ASCII', 'UTF-8'); |
| 73 | private static $language = 'neutral'; |
| 74 | private static $internalEncoding = 'UTF-8'; |
| 75 | private static $caseFold = array( |
| 76 | array('µ', 'ſ', "\xCD\x85", 'ς', "\xCF\x90", "\xCF\x91", "\xCF\x95", "\xCF\x96", "\xCF\xB0", "\xCF\xB1", "\xCF\xB5", "\xE1\xBA\x9B", "\xE1\xBE\xBE"), |
| 77 | array('μ', 's', 'ι', 'σ', 'β', 'θ', 'φ', 'π', 'κ', 'ρ', 'ε', "\xE1\xB9\xA1", 'ι'), |
| 78 | ); |
| 79 | |
| 80 | public static function mb_convert_encoding($s, $toEncoding, $fromEncoding = null) |
| 81 | { |
| 82 | if (\is_array($fromEncoding) || false !== strpos($fromEncoding, ',')) { |
| 83 | $fromEncoding = self::mb_detect_encoding($s, $fromEncoding); |
| 84 | } else { |
| 85 | $fromEncoding = self::getEncoding($fromEncoding); |
| 86 | } |
| 87 | |
| 88 | $toEncoding = self::getEncoding($toEncoding); |
| 89 | |
| 90 | if ('BASE64' === $fromEncoding) { |
| 91 | $s = base64_decode($s); |
| 92 | $fromEncoding = $toEncoding; |
| 93 | } |
| 94 | |
| 95 | if ('BASE64' === $toEncoding) { |
| 96 | return base64_encode($s); |
| 97 | } |
| 98 | |
| 99 | if ('HTML-ENTITIES' === $toEncoding || 'HTML' === $toEncoding) { |
| 100 | if ('HTML-ENTITIES' === $fromEncoding || 'HTML' === $fromEncoding) { |
| 101 | $fromEncoding = 'Windows-1252'; |
| 102 | } |
| 103 | if ('UTF-8' !== $fromEncoding) { |
| 104 | $s = iconv($fromEncoding, 'UTF-8//IGNORE', $s); |
| 105 | } |
| 106 | |
| 107 | return preg_replace_callback('/[\x80-\xFF]+/', array(__CLASS__, 'html_encoding_callback'), $s); |
| 108 | } |
| 109 | |
| 110 | if ('HTML-ENTITIES' === $fromEncoding) { |
| 111 | $s = html_entity_decode($s, ENT_COMPAT, 'UTF-8'); |
| 112 | $fromEncoding = 'UTF-8'; |
| 113 | } |
| 114 | |
| 115 | return iconv($fromEncoding, $toEncoding.'//IGNORE', $s); |
| 116 | } |
| 117 | |
| 118 | public static function mb_convert_variables($toEncoding, $fromEncoding, &$a = null, &$b = null, &$c = null, &$d = null, &$e = null, &$f = null) |
| 119 | { |
| 120 | $vars = array(&$a, &$b, &$c, &$d, &$e, &$f); |
| 121 | |
| 122 | $ok = true; |
| 123 | array_walk_recursive($vars, function (&$v) use (&$ok, $toEncoding, $fromEncoding) { |
| 124 | if (false === $v = Mbstring::mb_convert_encoding($v, $toEncoding, $fromEncoding)) { |
| 125 | $ok = false; |
| 126 | } |
| 127 | }); |
| 128 | |
| 129 | return $ok ? $fromEncoding : false; |
| 130 | } |
| 131 | |
| 132 | public static function mb_decode_mimeheader($s) |
| 133 | { |
| 134 | return iconv_mime_decode($s, 2, self::$internalEncoding); |
| 135 | } |
| 136 | |
| 137 | public static function mb_encode_mimeheader($s, $charset = null, $transferEncoding = null, $linefeed = null, $indent = null) |
| 138 | { |
| 139 | trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', E_USER_WARNING); |
| 140 | } |
| 141 | |
| 142 | public static function mb_decode_numericentity($s, $convmap, $encoding = null) |
| 143 | { |
| 144 | if (null !== $s && !\is_scalar($s) && !(\is_object($s) && \method_exists($s, '__toString'))) { |
| 145 | trigger_error('mb_decode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', E_USER_WARNING); |
| 146 | |
| 147 | return null; |
| 148 | } |
| 149 | |
| 150 | if (!\is_array($convmap) || !$convmap) { |
| 151 | return false; |
| 152 | } |
| 153 | |
| 154 | if (null !== $encoding && !\is_scalar($encoding)) { |
| 155 | trigger_error('mb_decode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', E_USER_WARNING); |
| 156 | |
| 157 | return ''; // Instead of null (cf. mb_encode_numericentity). |
| 158 | } |
| 159 | |
| 160 | $s = (string) $s; |
| 161 | if ('' === $s) { |
| 162 | return ''; |
| 163 | } |
| 164 | |
| 165 | $encoding = self::getEncoding($encoding); |
| 166 | |
| 167 | if ('UTF-8' === $encoding) { |
| 168 | $encoding = null; |
| 169 | if (!preg_match('//u', $s)) { |
| 170 | $s = @iconv('UTF-8', 'UTF-8//IGNORE', $s); |
| 171 | } |
| 172 | } else { |
| 173 | $s = iconv($encoding, 'UTF-8//IGNORE', $s); |
| 174 | } |
| 175 | |
| 176 | $cnt = floor(\count($convmap) / 4) * 4; |
| 177 | |
| 178 | for ($i = 0; $i < $cnt; $i += 4) { |
| 179 | // collector_decode_htmlnumericentity ignores $convmap[$i + 3] |
| 180 | $convmap[$i] += $convmap[$i + 2]; |
| 181 | $convmap[$i + 1] += $convmap[$i + 2]; |
| 182 | } |
| 183 | |
| 184 | $s = preg_replace_callback('/&#(?:0*([0-9]+)|x0*([0-9a-fA-F]+))(?!&);?/', function (array $m) use ($cnt, $convmap) { |
| 185 | $c = isset($m[2]) ? (int) hexdec($m[2]) : $m[1]; |
| 186 | for ($i = 0; $i < $cnt; $i += 4) { |
| 187 | if ($c >= $convmap[$i] && $c <= $convmap[$i + 1]) { |
| 188 | return Mbstring::mb_chr($c - $convmap[$i + 2]); |
| 189 | } |
| 190 | } |
| 191 | |
| 192 | return $m[0]; |
| 193 | }, $s); |
| 194 | |
| 195 | if (null === $encoding) { |
| 196 | return $s; |
| 197 | } |
| 198 | |
| 199 | return iconv('UTF-8', $encoding.'//IGNORE', $s); |
| 200 | } |
| 201 | |
| 202 | public static function mb_encode_numericentity($s, $convmap, $encoding = null, $is_hex = false) |
| 203 | { |
| 204 | if (null !== $s && !\is_scalar($s) && !(\is_object($s) && \method_exists($s, '__toString'))) { |
| 205 | trigger_error('mb_encode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', E_USER_WARNING); |
| 206 | |
| 207 | return null; |
| 208 | } |
| 209 | |
| 210 | if (!\is_array($convmap) || !$convmap) { |
| 211 | return false; |
| 212 | } |
| 213 | |
| 214 | if (null !== $encoding && !\is_scalar($encoding)) { |
| 215 | trigger_error('mb_encode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', E_USER_WARNING); |
| 216 | |
| 217 | return null; // Instead of '' (cf. mb_decode_numericentity). |
| 218 | } |
| 219 | |
| 220 | if (null !== $is_hex && !\is_scalar($is_hex)) { |
| 221 | trigger_error('mb_encode_numericentity() expects parameter 4 to be boolean, '.\gettype($s).' given', E_USER_WARNING); |
| 222 | |
| 223 | return null; |
| 224 | } |
| 225 | |
| 226 | $s = (string) $s; |
| 227 | if ('' === $s) { |
| 228 | return ''; |
| 229 | } |
| 230 | |
| 231 | $encoding = self::getEncoding($encoding); |
| 232 | |
| 233 | if ('UTF-8' === $encoding) { |
| 234 | $encoding = null; |
| 235 | if (!preg_match('//u', $s)) { |
| 236 | $s = @iconv('UTF-8', 'UTF-8//IGNORE', $s); |
| 237 | } |
| 238 | } else { |
| 239 | $s = iconv($encoding, 'UTF-8//IGNORE', $s); |
| 240 | } |
| 241 | |
| 242 | static $ulenMask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4); |
| 243 | |
| 244 | $cnt = floor(\count($convmap) / 4) * 4; |
| 245 | $i = 0; |
| 246 | $len = \strlen($s); |
| 247 | $result = ''; |
| 248 | |
| 249 | while ($i < $len) { |
| 250 | $ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"]; |
| 251 | $uchr = substr($s, $i, $ulen); |
| 252 | $i += $ulen; |
| 253 | $c = self::mb_ord($uchr); |
| 254 | |
| 255 | for ($j = 0; $j < $cnt; $j += 4) { |
| 256 | if ($c >= $convmap[$j] && $c <= $convmap[$j + 1]) { |
| 257 | $cOffset = ($c + $convmap[$j + 2]) & $convmap[$j + 3]; |
| 258 | $result .= $is_hex ? sprintf('&#x%X;', $cOffset) : '&#'.$cOffset.';'; |
| 259 | continue 2; |
| 260 | } |
| 261 | } |
| 262 | $result .= $uchr; |
| 263 | } |
| 264 | |
| 265 | if (null === $encoding) { |
| 266 | return $result; |
| 267 | } |
| 268 | |
| 269 | return iconv('UTF-8', $encoding.'//IGNORE', $result); |
| 270 | } |
| 271 | |
| 272 | public static function mb_convert_case($s, $mode, $encoding = null) |
| 273 | { |
| 274 | $s = (string) $s; |
| 275 | if ('' === $s) { |
| 276 | return ''; |
| 277 | } |
| 278 | |
| 279 | $encoding = self::getEncoding($encoding); |
| 280 | |
| 281 | if ('UTF-8' === $encoding) { |
| 282 | $encoding = null; |
| 283 | if (!preg_match('//u', $s)) { |
| 284 | $s = @iconv('UTF-8', 'UTF-8//IGNORE', $s); |
| 285 | } |
| 286 | } else { |
| 287 | $s = iconv($encoding, 'UTF-8//IGNORE', $s); |
| 288 | } |
| 289 | |
| 290 | if (MB_CASE_TITLE == $mode) { |
| 291 | static $titleRegexp = null; |
| 292 | if (null === $titleRegexp) { |
| 293 | $titleRegexp = self::getData('titleCaseRegexp'); |
| 294 | } |
| 295 | $s = preg_replace_callback($titleRegexp, array(__CLASS__, 'title_case'), $s); |
| 296 | } else { |
| 297 | if (MB_CASE_UPPER == $mode) { |
| 298 | static $upper = null; |
| 299 | if (null === $upper) { |
| 300 | $upper = self::getData('upperCase'); |
| 301 | } |
| 302 | $map = $upper; |
| 303 | } else { |
| 304 | if (self::MB_CASE_FOLD === $mode) { |
| 305 | $s = str_replace(self::$caseFold[0], self::$caseFold[1], $s); |
| 306 | } |
| 307 | |
| 308 | static $lower = null; |
| 309 | if (null === $lower) { |
| 310 | $lower = self::getData('lowerCase'); |
| 311 | } |
| 312 | $map = $lower; |
| 313 | } |
| 314 | |
| 315 | static $ulenMask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4); |
| 316 | |
| 317 | $i = 0; |
| 318 | $len = \strlen($s); |
| 319 | |
| 320 | while ($i < $len) { |
| 321 | $ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"]; |
| 322 | $uchr = substr($s, $i, $ulen); |
| 323 | $i += $ulen; |
| 324 | |
| 325 | if (isset($map[$uchr])) { |
| 326 | $uchr = $map[$uchr]; |
| 327 | $nlen = \strlen($uchr); |
| 328 | |
| 329 | if ($nlen == $ulen) { |
| 330 | $nlen = $i; |
| 331 | do { |
| 332 | $s[--$nlen] = $uchr[--$ulen]; |
| 333 | } while ($ulen); |
| 334 | } else { |
| 335 | $s = substr_replace($s, $uchr, $i - $ulen, $ulen); |
| 336 | $len += $nlen - $ulen; |
| 337 | $i += $nlen - $ulen; |
| 338 | } |
| 339 | } |
| 340 | } |
| 341 | } |
| 342 | |
| 343 | if (null === $encoding) { |
| 344 | return $s; |
| 345 | } |
| 346 | |
| 347 | return iconv('UTF-8', $encoding.'//IGNORE', $s); |
| 348 | } |
| 349 | |
| 350 | public static function mb_internal_encoding($encoding = null) |
| 351 | { |
| 352 | if (null === $encoding) { |
| 353 | return self::$internalEncoding; |
| 354 | } |
| 355 | |
| 356 | $encoding = self::getEncoding($encoding); |
| 357 | |
| 358 | if ('UTF-8' === $encoding || false !== @iconv($encoding, $encoding, ' ')) { |
| 359 | self::$internalEncoding = $encoding; |
| 360 | |
| 361 | return true; |
| 362 | } |
| 363 | |
| 364 | return false; |
| 365 | } |
| 366 | |
| 367 | public static function mb_language($lang = null) |
| 368 | { |
| 369 | if (null === $lang) { |
| 370 | return self::$language; |
| 371 | } |
| 372 | |
| 373 | switch ($lang = strtolower($lang)) { |
| 374 | case 'uni': |
| 375 | case 'neutral': |
| 376 | self::$language = $lang; |
| 377 | |
| 378 | return true; |
| 379 | } |
| 380 | |
| 381 | return false; |
| 382 | } |
| 383 | |
| 384 | public static function mb_list_encodings() |
| 385 | { |
| 386 | return array('UTF-8'); |
| 387 | } |
| 388 | |
| 389 | public static function mb_encoding_aliases($encoding) |
| 390 | { |
| 391 | switch (strtoupper($encoding)) { |
| 392 | case 'UTF8': |
| 393 | case 'UTF-8': |
| 394 | return array('utf8'); |
| 395 | } |
| 396 | |
| 397 | return false; |
| 398 | } |
| 399 | |
| 400 | public static function mb_check_encoding($var = null, $encoding = null) |
| 401 | { |
| 402 | if (null === $encoding) { |
| 403 | if (null === $var) { |
| 404 | return false; |
| 405 | } |
| 406 | $encoding = self::$internalEncoding; |
| 407 | } |
| 408 | |
| 409 | return self::mb_detect_encoding($var, array($encoding)) || false !== @iconv($encoding, $encoding, $var); |
| 410 | } |
| 411 | |
| 412 | public static function mb_detect_encoding($str, $encodingList = null, $strict = false) |
| 413 | { |
| 414 | if (null === $encodingList) { |
| 415 | $encodingList = self::$encodingList; |
| 416 | } else { |
| 417 | if (!\is_array($encodingList)) { |
| 418 | $encodingList = array_map('trim', explode(',', $encodingList)); |
| 419 | } |
| 420 | $encodingList = array_map('strtoupper', $encodingList); |
| 421 | } |
| 422 | |
| 423 | foreach ($encodingList as $enc) { |
| 424 | switch ($enc) { |
| 425 | case 'ASCII': |
| 426 | if (!preg_match('/[\x80-\xFF]/', $str)) { |
| 427 | return $enc; |
| 428 | } |
| 429 | break; |
| 430 | |
| 431 | case 'UTF8': |
| 432 | case 'UTF-8': |
| 433 | if (preg_match('//u', $str)) { |
| 434 | return 'UTF-8'; |
| 435 | } |
| 436 | break; |
| 437 | |
| 438 | default: |
| 439 | if (0 === strncmp($enc, 'ISO-8859-', 9)) { |
| 440 | return $enc; |
| 441 | } |
| 442 | } |
| 443 | } |
| 444 | |
| 445 | return false; |
| 446 | } |
| 447 | |
| 448 | public static function mb_detect_order($encodingList = null) |
| 449 | { |
| 450 | if (null === $encodingList) { |
| 451 | return self::$encodingList; |
| 452 | } |
| 453 | |
| 454 | if (!\is_array($encodingList)) { |
| 455 | $encodingList = array_map('trim', explode(',', $encodingList)); |
| 456 | } |
| 457 | $encodingList = array_map('strtoupper', $encodingList); |
| 458 | |
| 459 | foreach ($encodingList as $enc) { |
| 460 | switch ($enc) { |
| 461 | default: |
| 462 | if (strncmp($enc, 'ISO-8859-', 9)) { |
| 463 | return false; |
| 464 | } |
| 465 | // no break |
| 466 | case 'ASCII': |
| 467 | case 'UTF8': |
| 468 | case 'UTF-8': |
| 469 | } |
| 470 | } |
| 471 | |
| 472 | self::$encodingList = $encodingList; |
| 473 | |
| 474 | return true; |
| 475 | } |
| 476 | |
| 477 | public static function mb_strlen($s, $encoding = null) |
| 478 | { |
| 479 | $encoding = self::getEncoding($encoding); |
| 480 | if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 481 | return \strlen($s); |
| 482 | } |
| 483 | |
| 484 | return @iconv_strlen($s, $encoding); |
| 485 | } |
| 486 | |
| 487 | public static function mb_strpos($haystack, $needle, $offset = 0, $encoding = null) |
| 488 | { |
| 489 | $encoding = self::getEncoding($encoding); |
| 490 | if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 491 | return strpos($haystack, $needle, $offset); |
| 492 | } |
| 493 | |
| 494 | $needle = (string) $needle; |
| 495 | if ('' === $needle) { |
| 496 | trigger_error(__METHOD__.': Empty delimiter', E_USER_WARNING); |
| 497 | |
| 498 | return false; |
| 499 | } |
| 500 | |
| 501 | return iconv_strpos($haystack, $needle, $offset, $encoding); |
| 502 | } |
| 503 | |
| 504 | public static function mb_strrpos($haystack, $needle, $offset = 0, $encoding = null) |
| 505 | { |
| 506 | $encoding = self::getEncoding($encoding); |
| 507 | if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 508 | return strrpos($haystack, $needle, $offset); |
| 509 | } |
| 510 | |
| 511 | if ($offset != (int) $offset) { |
| 512 | $offset = 0; |
| 513 | } elseif ($offset = (int) $offset) { |
| 514 | if ($offset < 0) { |
| 515 | if (0 > $offset += self::mb_strlen($needle)) { |
| 516 | $haystack = self::mb_substr($haystack, 0, $offset, $encoding); |
| 517 | } |
| 518 | $offset = 0; |
| 519 | } else { |
| 520 | $haystack = self::mb_substr($haystack, $offset, 2147483647, $encoding); |
| 521 | } |
| 522 | } |
| 523 | |
| 524 | $pos = iconv_strrpos($haystack, $needle, $encoding); |
| 525 | |
| 526 | return false !== $pos ? $offset + $pos : false; |
| 527 | } |
| 528 | |
| 529 | public static function mb_str_split($string, $split_length = 1, $encoding = null) |
| 530 | { |
| 531 | if (null !== $string && !\is_scalar($string) && !(\is_object($string) && \method_exists($string, '__toString'))) { |
| 532 | trigger_error('mb_str_split() expects parameter 1 to be string, '.\gettype($string).' given', E_USER_WARNING); |
| 533 | |
| 534 | return null; |
| 535 | } |
| 536 | |
| 537 | if (1 > $split_length = (int) $split_length) { |
| 538 | trigger_error('The length of each segment must be greater than zero', E_USER_WARNING); |
| 539 | |
| 540 | return false; |
| 541 | } |
| 542 | |
| 543 | if (null === $encoding) { |
| 544 | $encoding = mb_internal_encoding(); |
| 545 | } |
| 546 | |
| 547 | if ('UTF-8' === $encoding = self::getEncoding($encoding)) { |
| 548 | $rx = '/('; |
| 549 | while (65535 < $split_length) { |
| 550 | $rx .= '.{65535}'; |
| 551 | $split_length -= 65535; |
| 552 | } |
| 553 | $rx .= '.{'.$split_length.'})/us'; |
| 554 | |
| 555 | return preg_split($rx, $string, null, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY); |
| 556 | } |
| 557 | |
| 558 | $result = array(); |
| 559 | $length = mb_strlen($string, $encoding); |
| 560 | |
| 561 | for ($i = 0; $i < $length; $i += $split_length) { |
| 562 | $result[] = mb_substr($string, $i, $split_length, $encoding); |
| 563 | } |
| 564 | |
| 565 | return $result; |
| 566 | } |
| 567 | |
| 568 | public static function mb_strtolower($s, $encoding = null) |
| 569 | { |
| 570 | return self::mb_convert_case($s, MB_CASE_LOWER, $encoding); |
| 571 | } |
| 572 | |
| 573 | public static function mb_strtoupper($s, $encoding = null) |
| 574 | { |
| 575 | return self::mb_convert_case($s, MB_CASE_UPPER, $encoding); |
| 576 | } |
| 577 | |
| 578 | public static function mb_substitute_character($c = null) |
| 579 | { |
| 580 | if (0 === strcasecmp($c, 'none')) { |
| 581 | return true; |
| 582 | } |
| 583 | |
| 584 | return null !== $c ? false : 'none'; |
| 585 | } |
| 586 | |
| 587 | public static function mb_substr($s, $start, $length = null, $encoding = null) |
| 588 | { |
| 589 | $encoding = self::getEncoding($encoding); |
| 590 | if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 591 | return (string) substr($s, $start, null === $length ? 2147483647 : $length); |
| 592 | } |
| 593 | |
| 594 | if ($start < 0) { |
| 595 | $start = iconv_strlen($s, $encoding) + $start; |
| 596 | if ($start < 0) { |
| 597 | $start = 0; |
| 598 | } |
| 599 | } |
| 600 | |
| 601 | if (null === $length) { |
| 602 | $length = 2147483647; |
| 603 | } elseif ($length < 0) { |
| 604 | $length = iconv_strlen($s, $encoding) + $length - $start; |
| 605 | if ($length < 0) { |
| 606 | return ''; |
| 607 | } |
| 608 | } |
| 609 | |
| 610 | return (string) iconv_substr($s, $start, $length, $encoding); |
| 611 | } |
| 612 | |
| 613 | public static function mb_stripos($haystack, $needle, $offset = 0, $encoding = null) |
| 614 | { |
| 615 | $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding); |
| 616 | $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding); |
| 617 | |
| 618 | return self::mb_strpos($haystack, $needle, $offset, $encoding); |
| 619 | } |
| 620 | |
| 621 | public static function mb_stristr($haystack, $needle, $part = false, $encoding = null) |
| 622 | { |
| 623 | $pos = self::mb_stripos($haystack, $needle, 0, $encoding); |
| 624 | |
| 625 | return self::getSubpart($pos, $part, $haystack, $encoding); |
| 626 | } |
| 627 | |
| 628 | public static function mb_strrchr($haystack, $needle, $part = false, $encoding = null) |
| 629 | { |
| 630 | $encoding = self::getEncoding($encoding); |
| 631 | if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 632 | $pos = strrpos($haystack, $needle); |
| 633 | } else { |
| 634 | $needle = self::mb_substr($needle, 0, 1, $encoding); |
| 635 | $pos = iconv_strrpos($haystack, $needle, $encoding); |
| 636 | } |
| 637 | |
| 638 | return self::getSubpart($pos, $part, $haystack, $encoding); |
| 639 | } |
| 640 | |
| 641 | public static function mb_strrichr($haystack, $needle, $part = false, $encoding = null) |
| 642 | { |
| 643 | $needle = self::mb_substr($needle, 0, 1, $encoding); |
| 644 | $pos = self::mb_strripos($haystack, $needle, $encoding); |
| 645 | |
| 646 | return self::getSubpart($pos, $part, $haystack, $encoding); |
| 647 | } |
| 648 | |
| 649 | public static function mb_strripos($haystack, $needle, $offset = 0, $encoding = null) |
| 650 | { |
| 651 | $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding); |
| 652 | $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding); |
| 653 | |
| 654 | return self::mb_strrpos($haystack, $needle, $offset, $encoding); |
| 655 | } |
| 656 | |
| 657 | public static function mb_strstr($haystack, $needle, $part = false, $encoding = null) |
| 658 | { |
| 659 | $pos = strpos($haystack, $needle); |
| 660 | if (false === $pos) { |
| 661 | return false; |
| 662 | } |
| 663 | if ($part) { |
| 664 | return substr($haystack, 0, $pos); |
| 665 | } |
| 666 | |
| 667 | return substr($haystack, $pos); |
| 668 | } |
| 669 | |
| 670 | public static function mb_get_info($type = 'all') |
| 671 | { |
| 672 | $info = array( |
| 673 | 'internal_encoding' => self::$internalEncoding, |
| 674 | 'http_output' => 'pass', |
| 675 | 'http_output_conv_mimetypes' => '^(text/|application/xhtml\+xml)', |
| 676 | 'func_overload' => 0, |
| 677 | 'func_overload_list' => 'no overload', |
| 678 | 'mail_charset' => 'UTF-8', |
| 679 | 'mail_header_encoding' => 'BASE64', |
| 680 | 'mail_body_encoding' => 'BASE64', |
| 681 | 'illegal_chars' => 0, |
| 682 | 'encoding_translation' => 'Off', |
| 683 | 'language' => self::$language, |
| 684 | 'detect_order' => self::$encodingList, |
| 685 | 'substitute_character' => 'none', |
| 686 | 'strict_detection' => 'Off', |
| 687 | ); |
| 688 | |
| 689 | if ('all' === $type) { |
| 690 | return $info; |
| 691 | } |
| 692 | if (isset($info[$type])) { |
| 693 | return $info[$type]; |
| 694 | } |
| 695 | |
| 696 | return false; |
| 697 | } |
| 698 | |
| 699 | public static function mb_http_input($type = '') |
| 700 | { |
| 701 | return false; |
| 702 | } |
| 703 | |
| 704 | public static function mb_http_output($encoding = null) |
| 705 | { |
| 706 | return null !== $encoding ? 'pass' === $encoding : 'pass'; |
| 707 | } |
| 708 | |
| 709 | public static function mb_strwidth($s, $encoding = null) |
| 710 | { |
| 711 | $encoding = self::getEncoding($encoding); |
| 712 | |
| 713 | if ('UTF-8' !== $encoding) { |
| 714 | $s = iconv($encoding, 'UTF-8//IGNORE', $s); |
| 715 | } |
| 716 | |
| 717 | $s = preg_replace('/[\x{1100}-\x{115F}\x{2329}\x{232A}\x{2E80}-\x{303E}\x{3040}-\x{A4CF}\x{AC00}-\x{D7A3}\x{F900}-\x{FAFF}\x{FE10}-\x{FE19}\x{FE30}-\x{FE6F}\x{FF00}-\x{FF60}\x{FFE0}-\x{FFE6}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}]/u', '', $s, -1, $wide); |
| 718 | |
| 719 | return ($wide << 1) + iconv_strlen($s, 'UTF-8'); |
| 720 | } |
| 721 | |
| 722 | public static function mb_substr_count($haystack, $needle, $encoding = null) |
| 723 | { |
| 724 | return substr_count($haystack, $needle); |
| 725 | } |
| 726 | |
| 727 | public static function mb_output_handler($contents, $status) |
| 728 | { |
| 729 | return $contents; |
| 730 | } |
| 731 | |
| 732 | public static function mb_chr($code, $encoding = null) |
| 733 | { |
| 734 | if (0x80 > $code %= 0x200000) { |
| 735 | $s = \chr($code); |
| 736 | } elseif (0x800 > $code) { |
| 737 | $s = \chr(0xC0 | $code >> 6).\chr(0x80 | $code & 0x3F); |
| 738 | } elseif (0x10000 > $code) { |
| 739 | $s = \chr(0xE0 | $code >> 12).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F); |
| 740 | } else { |
| 741 | $s = \chr(0xF0 | $code >> 18).\chr(0x80 | $code >> 12 & 0x3F).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F); |
| 742 | } |
| 743 | |
| 744 | if ('UTF-8' !== $encoding = self::getEncoding($encoding)) { |
| 745 | $s = mb_convert_encoding($s, $encoding, 'UTF-8'); |
| 746 | } |
| 747 | |
| 748 | return $s; |
| 749 | } |
| 750 | |
| 751 | public static function mb_ord($s, $encoding = null) |
| 752 | { |
| 753 | if ('UTF-8' !== $encoding = self::getEncoding($encoding)) { |
| 754 | $s = mb_convert_encoding($s, 'UTF-8', $encoding); |
| 755 | } |
| 756 | |
| 757 | if (1 === \strlen($s)) { |
| 758 | return \ord($s); |
| 759 | } |
| 760 | |
| 761 | $code = ($s = unpack('C*', substr($s, 0, 4))) ? $s[1] : 0; |
| 762 | if (0xF0 <= $code) { |
| 763 | return (($code - 0xF0) << 18) + (($s[2] - 0x80) << 12) + (($s[3] - 0x80) << 6) + $s[4] - 0x80; |
| 764 | } |
| 765 | if (0xE0 <= $code) { |
| 766 | return (($code - 0xE0) << 12) + (($s[2] - 0x80) << 6) + $s[3] - 0x80; |
| 767 | } |
| 768 | if (0xC0 <= $code) { |
| 769 | return (($code - 0xC0) << 6) + $s[2] - 0x80; |
| 770 | } |
| 771 | |
| 772 | return $code; |
| 773 | } |
| 774 | |
| 775 | private static function getSubpart($pos, $part, $haystack, $encoding) |
| 776 | { |
| 777 | if (false === $pos) { |
| 778 | return false; |
| 779 | } |
| 780 | if ($part) { |
| 781 | return self::mb_substr($haystack, 0, $pos, $encoding); |
| 782 | } |
| 783 | |
| 784 | return self::mb_substr($haystack, $pos, null, $encoding); |
| 785 | } |
| 786 | |
| 787 | private static function html_encoding_callback(array $m) |
| 788 | { |
| 789 | $i = 1; |
| 790 | $entities = ''; |
| 791 | $m = unpack('C*', htmlentities($m[0], ENT_COMPAT, 'UTF-8')); |
| 792 | |
| 793 | while (isset($m[$i])) { |
| 794 | if (0x80 > $m[$i]) { |
| 795 | $entities .= \chr($m[$i++]); |
| 796 | continue; |
| 797 | } |
| 798 | if (0xF0 <= $m[$i]) { |
| 799 | $c = (($m[$i++] - 0xF0) << 18) + (($m[$i++] - 0x80) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80; |
| 800 | } elseif (0xE0 <= $m[$i]) { |
| 801 | $c = (($m[$i++] - 0xE0) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80; |
| 802 | } else { |
| 803 | $c = (($m[$i++] - 0xC0) << 6) + $m[$i++] - 0x80; |
| 804 | } |
| 805 | |
| 806 | $entities .= '&#'.$c.';'; |
| 807 | } |
| 808 | |
| 809 | return $entities; |
| 810 | } |
| 811 | |
| 812 | private static function title_case(array $s) |
| 813 | { |
| 814 | return self::mb_convert_case($s[1], MB_CASE_UPPER, 'UTF-8').self::mb_convert_case($s[2], MB_CASE_LOWER, 'UTF-8'); |
| 815 | } |
| 816 | |
| 817 | private static function getData($file) |
| 818 | { |
| 819 | if (file_exists($file = __DIR__.'/Resources/unidata/'.$file.'.php')) { |
| 820 | return require $file; |
| 821 | } |
| 822 | |
| 823 | return false; |
| 824 | } |
| 825 | |
| 826 | private static function getEncoding($encoding) |
| 827 | { |
| 828 | if (null === $encoding) { |
| 829 | return self::$internalEncoding; |
| 830 | } |
| 831 | |
| 832 | if ('UTF-8' === $encoding) { |
| 833 | return 'UTF-8'; |
| 834 | } |
| 835 | |
| 836 | $encoding = strtoupper($encoding); |
| 837 | |
| 838 | if ('8BIT' === $encoding || 'BINARY' === $encoding) { |
| 839 | return 'CP850'; |
| 840 | } |
| 841 | |
| 842 | if ('UTF8' === $encoding) { |
| 843 | return 'UTF-8'; |
| 844 | } |
| 845 | |
| 846 | return $encoding; |
| 847 | } |
| 848 | } |
| 849 |