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 12namespace 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 * - mb_ucfirst - Make a string's first character uppercase 52 * - mb_lcfirst - Make a string's first character lowercase 53 * - mb_trim - Strip whitespace (or other characters) from the beginning and end of a string 54 * - mb_ltrim - Strip whitespace (or other characters) from the beginning of a string 55 * - mb_rtrim - Strip whitespace (or other characters) from the end of a string 56 * 57 * Not implemented: 58 * - mb_convert_kana - Convert "kana" one from another ("zen-kaku", "han-kaku" and more) 59 * - mb_ereg_* - Regular expression with multibyte support 60 * - mb_parse_str - Parse GET/POST/COOKIE data and set global variable 61 * - mb_preferred_mime_name - Get MIME charset string 62 * - mb_regex_encoding - Returns current encoding for multibyte regex as string 63 * - mb_regex_set_options - Set/Get the default options for mbregex functions 64 * - mb_send_mail - Send encoded mail 65 * - mb_split - Split multibyte string using regular expression 66 * - mb_strcut - Get part of string 67 * - mb_strimwidth - Get truncated string with specified width 68 * 69 * @author Nicolas Grekas <p@tchwork.com> 70 * 71 * @internal 72 */ 73final class Mbstring 74{ 75 public const MB_CASE_FOLD = \PHP_INT_MAX; 76 77 private const SIMPLE_CASE_FOLD = [ 78 ['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"], 79 ['μ', 's', 'ι', 'σ', 'β', 'θ', 'φ', 'π', 'κ', 'ρ', 'ε', "\xE1\xB9\xA1", 'ι'], 80 ]; 81 82 private static $encodingList = ['ASCII', 'UTF-8']; 83 private static $language = 'neutral'; 84 private static $internalEncoding = 'UTF-8'; 85 86 public static function mb_convert_encoding($s, $toEncoding, $fromEncoding = null) 87 { 88 if (\is_array($s)) { 89 $r = []; 90 foreach ($s as $str) { 91 $r[] = self::mb_convert_encoding($str, $toEncoding, $fromEncoding); 92 } 93 94 return $r; 95 } 96 97 if (\is_array($fromEncoding) || (null !== $fromEncoding && false !== strpos($fromEncoding, ','))) { 98 $fromEncoding = self::mb_detect_encoding($s, $fromEncoding); 99 } else { 100 $fromEncoding = self::getEncoding($fromEncoding); 101 } 102 103 $toEncoding = self::getEncoding($toEncoding); 104 105 if ('BASE64' === $fromEncoding) { 106 $s = base64_decode($s); 107 $fromEncoding = $toEncoding; 108 } 109 110 if ('BASE64' === $toEncoding) { 111 return base64_encode($s); 112 } 113 114 if ('HTML-ENTITIES' === $toEncoding || 'HTML' === $toEncoding) { 115 if ('HTML-ENTITIES' === $fromEncoding || 'HTML' === $fromEncoding) { 116 $fromEncoding = 'Windows-1252'; 117 } 118 if ('UTF-8' !== $fromEncoding) { 119 $s = iconv($fromEncoding, 'UTF-8//IGNORE', $s); 120 } 121 122 return preg_replace_callback('/[\x80-\xFF]+/', [__CLASS__, 'html_encoding_callback'], $s); 123 } 124 125 if ('HTML-ENTITIES' === $fromEncoding) { 126 $s = html_entity_decode($s, \ENT_COMPAT, 'UTF-8'); 127 $fromEncoding = 'UTF-8'; 128 } 129 130 return iconv($fromEncoding, $toEncoding.'//IGNORE', $s); 131 } 132 133 public static function mb_convert_variables($toEncoding, $fromEncoding, &...$vars) 134 { 135 $ok = true; 136 array_walk_recursive($vars, function (&$v) use (&$ok, $toEncoding, $fromEncoding) { 137 if (false === $v = self::mb_convert_encoding($v, $toEncoding, $fromEncoding)) { 138 $ok = false; 139 } 140 }); 141 142 return $ok ? $fromEncoding : false; 143 } 144 145 public static function mb_decode_mimeheader($s) 146 { 147 return iconv_mime_decode($s, 2, self::$internalEncoding); 148 } 149 150 public static function mb_encode_mimeheader($s, $charset = null, $transferEncoding = null, $linefeed = null, $indent = null) 151 { 152 trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', \E_USER_WARNING); 153 } 154 155 public static function mb_decode_numericentity($s, $convmap, $encoding = null) 156 { 157 if (null !== $s && !\is_scalar($s) && !(\is_object($s) && method_exists($s, '__toString'))) { 158 trigger_error('mb_decode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', \E_USER_WARNING); 159 160 return null; 161 } 162 163 if (!\is_array($convmap) || (80000 > \PHP_VERSION_ID && !$convmap)) { 164 return false; 165 } 166 167 if (null !== $encoding && !\is_scalar($encoding)) { 168 trigger_error('mb_decode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', \E_USER_WARNING); 169 170 return ''; // Instead of null (cf. mb_encode_numericentity). 171 } 172 173 $s = (string) $s; 174 if ('' === $s) { 175 return ''; 176 } 177 178 $encoding = self::getEncoding($encoding); 179 180 if ('UTF-8' === $encoding) { 181 $encoding = null; 182 if (!preg_match('//u', $s)) { 183 $s = @iconv('UTF-8', 'UTF-8//IGNORE', $s); 184 } 185 } else { 186 $s = iconv($encoding, 'UTF-8//IGNORE', $s); 187 } 188 189 $cnt = floor(\count($convmap) / 4) * 4; 190 191 for ($i = 0; $i < $cnt; $i += 4) { 192 // collector_decode_htmlnumericentity ignores $convmap[$i + 3] 193 $convmap[$i] += $convmap[$i + 2]; 194 $convmap[$i + 1] += $convmap[$i + 2]; 195 } 196 197 $s = preg_replace_callback('/&#(?:0*([0-9]+)|x0*([0-9a-fA-F]+))(?!&);?/', function (array $m) use ($cnt, $convmap) { 198 $c = isset($m[2]) ? (int) hexdec($m[2]) : $m[1]; 199 for ($i = 0; $i < $cnt; $i += 4) { 200 if ($c >= $convmap[$i] && $c <= $convmap[$i + 1]) { 201 return self::mb_chr($c - $convmap[$i + 2]); 202 } 203 } 204 205 return $m[0]; 206 }, $s); 207 208 if (null === $encoding) { 209 return $s; 210 } 211 212 return iconv('UTF-8', $encoding.'//IGNORE', $s); 213 } 214 215 public static function mb_encode_numericentity($s, $convmap, $encoding = null, $is_hex = false) 216 { 217 if (null !== $s && !\is_scalar($s) && !(\is_object($s) && method_exists($s, '__toString'))) { 218 trigger_error('mb_encode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', \E_USER_WARNING); 219 220 return null; 221 } 222 223 if (!\is_array($convmap) || (80000 > \PHP_VERSION_ID && !$convmap)) { 224 return false; 225 } 226 227 if (null !== $encoding && !\is_scalar($encoding)) { 228 trigger_error('mb_encode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', \E_USER_WARNING); 229 230 return null; // Instead of '' (cf. mb_decode_numericentity). 231 } 232 233 if (null !== $is_hex && !\is_scalar($is_hex)) { 234 trigger_error('mb_encode_numericentity() expects parameter 4 to be boolean, '.\gettype($s).' given', \E_USER_WARNING); 235 236 return null; 237 } 238 239 $s = (string) $s; 240 if ('' === $s) { 241 return ''; 242 } 243 244 $encoding = self::getEncoding($encoding); 245 246 if ('UTF-8' === $encoding) { 247 $encoding = null; 248 if (!preg_match('//u', $s)) { 249 $s = @iconv('UTF-8', 'UTF-8//IGNORE', $s); 250 } 251 } else { 252 $s = iconv($encoding, 'UTF-8//IGNORE', $s); 253 } 254 255 static $ulenMask = ["\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4]; 256 257 $cnt = floor(\count($convmap) / 4) * 4; 258 $i = 0; 259 $len = \strlen($s); 260 $result = ''; 261 262 while ($i < $len) { 263 $ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"]; 264 $uchr = substr($s, $i, $ulen); 265 $i += $ulen; 266 $c = self::mb_ord($uchr); 267 268 for ($j = 0; $j < $cnt; $j += 4) { 269 if ($c >= $convmap[$j] && $c <= $convmap[$j + 1]) { 270 $cOffset = ($c + $convmap[$j + 2]) & $convmap[$j + 3]; 271 $result .= $is_hex ? sprintf('&#x%X;', $cOffset) : '&#'.$cOffset.';'; 272 continue 2; 273 } 274 } 275 $result .= $uchr; 276 } 277 278 if (null === $encoding) { 279 return $result; 280 } 281 282 return iconv('UTF-8', $encoding.'//IGNORE', $result); 283 } 284 285 public static function mb_convert_case($s, $mode, $encoding = null) 286 { 287 $s = (string) $s; 288 if ('' === $s) { 289 return ''; 290 } 291 292 $encoding = self::getEncoding($encoding); 293 294 if ('UTF-8' === $encoding) { 295 $encoding = null; 296 if (!preg_match('//u', $s)) { 297 $s = @iconv('UTF-8', 'UTF-8//IGNORE', $s); 298 } 299 } else { 300 $s = iconv($encoding, 'UTF-8//IGNORE', $s); 301 } 302 303 if (\MB_CASE_TITLE == $mode) { 304 static $titleRegexp = null; 305 if (null === $titleRegexp) { 306 $titleRegexp = self::getData('titleCaseRegexp'); 307 } 308 $s = preg_replace_callback($titleRegexp, [__CLASS__, 'title_case'], $s); 309 } else { 310 if (\MB_CASE_UPPER == $mode) { 311 static $upper = null; 312 if (null === $upper) { 313 $upper = self::getData('upperCase'); 314 } 315 $map = $upper; 316 } else { 317 if (self::MB_CASE_FOLD === $mode) { 318 static $caseFolding = null; 319 if (null === $caseFolding) { 320 $caseFolding = self::getData('caseFolding'); 321 } 322 $s = strtr($s, $caseFolding); 323 } 324 325 static $lower = null; 326 if (null === $lower) { 327 $lower = self::getData('lowerCase'); 328 } 329 $map = $lower; 330 } 331 332 static $ulenMask = ["\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4]; 333 334 $i = 0; 335 $len = \strlen($s); 336 337 while ($i < $len) { 338 $ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"]; 339 $uchr = substr($s, $i, $ulen); 340 $i += $ulen; 341 342 if (isset($map[$uchr])) { 343 $uchr = $map[$uchr]; 344 $nlen = \strlen($uchr); 345 346 if ($nlen == $ulen) { 347 $nlen = $i; 348 do { 349 $s[--$nlen] = $uchr[--$ulen]; 350 } while ($ulen); 351 } else { 352 $s = substr_replace($s, $uchr, $i - $ulen, $ulen); 353 $len += $nlen - $ulen; 354 $i += $nlen - $ulen; 355 } 356 } 357 } 358 } 359 360 if (null === $encoding) { 361 return $s; 362 } 363 364 return iconv('UTF-8', $encoding.'//IGNORE', $s); 365 } 366 367 public static function mb_internal_encoding($encoding = null) 368 { 369 if (null === $encoding) { 370 return self::$internalEncoding; 371 } 372 373 $normalizedEncoding = self::getEncoding($encoding); 374 375 if ('UTF-8' === $normalizedEncoding || false !== @iconv($normalizedEncoding, $normalizedEncoding, ' ')) { 376 self::$internalEncoding = $normalizedEncoding; 377 378 return true; 379 } 380 381 if (80000 > \PHP_VERSION_ID) { 382 return false; 383 } 384 385 throw new \ValueError(sprintf('Argument #1 ($encoding) must be a valid encoding, "%s" given', $encoding)); 386 } 387 388 public static function mb_language($lang = null) 389 { 390 if (null === $lang) { 391 return self::$language; 392 } 393 394 switch ($normalizedLang = strtolower($lang)) { 395 case 'uni': 396 case 'neutral': 397 self::$language = $normalizedLang; 398 399 return true; 400 } 401 402 if (80000 > \PHP_VERSION_ID) { 403 return false; 404 } 405 406 throw new \ValueError(sprintf('Argument #1 ($language) must be a valid language, "%s" given', $lang)); 407 } 408 409 public static function mb_list_encodings() 410 { 411 return ['UTF-8']; 412 } 413 414 public static function mb_encoding_aliases($encoding) 415 { 416 switch (strtoupper($encoding)) { 417 case 'UTF8': 418 case 'UTF-8': 419 return ['utf8']; 420 } 421 422 return false; 423 } 424 425 public static function mb_check_encoding($var = null, $encoding = null) 426 { 427 if (null === $encoding) { 428 if (null === $var) { 429 return false; 430 } 431 $encoding = self::$internalEncoding; 432 } 433 434 if (!\is_array($var)) { 435 return self::mb_detect_encoding($var, [$encoding]) || false !== @iconv($encoding, $encoding, $var); 436 } 437 438 foreach ($var as $key => $value) { 439 if (!self::mb_check_encoding($key, $encoding)) { 440 return false; 441 } 442 if (!self::mb_check_encoding($value, $encoding)) { 443 return false; 444 } 445 } 446 447 return true; 448 } 449 450 public static function mb_detect_encoding($str, $encodingList = null, $strict = false) 451 { 452 if (null === $encodingList) { 453 $encodingList = self::$encodingList; 454 } else { 455 if (!\is_array($encodingList)) { 456 $encodingList = array_map('trim', explode(',', $encodingList)); 457 } 458 $encodingList = array_map('strtoupper', $encodingList); 459 } 460 461 foreach ($encodingList as $enc) { 462 switch ($enc) { 463 case 'ASCII': 464 if (!preg_match('/[\x80-\xFF]/', $str)) { 465 return $enc; 466 } 467 break; 468 469 case 'UTF8': 470 case 'UTF-8': 471 if (preg_match('//u', $str)) { 472 return 'UTF-8'; 473 } 474 break; 475 476 default: 477 if (0 === strncmp($enc, 'ISO-8859-', 9)) { 478 return $enc; 479 } 480 } 481 } 482 483 return false; 484 } 485 486 public static function mb_detect_order($encodingList = null) 487 { 488 if (null === $encodingList) { 489 return self::$encodingList; 490 } 491 492 if (!\is_array($encodingList)) { 493 $encodingList = array_map('trim', explode(',', $encodingList)); 494 } 495 $encodingList = array_map('strtoupper', $encodingList); 496 497 foreach ($encodingList as $enc) { 498 switch ($enc) { 499 default: 500 if (strncmp($enc, 'ISO-8859-', 9)) { 501 return false; 502 } 503 // no break 504 case 'ASCII': 505 case 'UTF8': 506 case 'UTF-8': 507 } 508 } 509 510 self::$encodingList = $encodingList; 511 512 return true; 513 } 514 515 public static function mb_strlen($s, $encoding = null) 516 { 517 $encoding = self::getEncoding($encoding); 518 if ('CP850' === $encoding || 'ASCII' === $encoding) { 519 return \strlen($s); 520 } 521 522 return @iconv_strlen($s, $encoding); 523 } 524 525 public static function mb_strpos($haystack, $needle, $offset = 0, $encoding = null) 526 { 527 $encoding = self::getEncoding($encoding); 528 if ('CP850' === $encoding || 'ASCII' === $encoding) { 529 return strpos($haystack, $needle, $offset); 530 } 531 532 $needle = (string) $needle; 533 if ('' === $needle) { 534 if (80000 > \PHP_VERSION_ID) { 535 trigger_error(__METHOD__.': Empty delimiter', \E_USER_WARNING); 536 537 return false; 538 } 539 540 return 0; 541 } 542 543 return iconv_strpos($haystack, $needle, $offset, $encoding); 544 } 545 546 public static function mb_strrpos($haystack, $needle, $offset = 0, $encoding = null) 547 { 548 $encoding = self::getEncoding($encoding); 549 if ('CP850' === $encoding || 'ASCII' === $encoding) { 550 return strrpos($haystack, $needle, $offset); 551 } 552 553 if ($offset != (int) $offset) { 554 $offset = 0; 555 } elseif ($offset = (int) $offset) { 556 if ($offset < 0) { 557 if (0 > $offset += self::mb_strlen($needle)) { 558 $haystack = self::mb_substr($haystack, 0, $offset, $encoding); 559 } 560 $offset = 0; 561 } else { 562 $haystack = self::mb_substr($haystack, $offset, 2147483647, $encoding); 563 } 564 } 565 566 $pos = '' !== $needle || 80000 > \PHP_VERSION_ID 567 ? iconv_strrpos($haystack, $needle, $encoding) 568 : self::mb_strlen($haystack, $encoding); 569 570 return false !== $pos ? $offset + $pos : false; 571 } 572 573 public static function mb_str_split($string, $split_length = 1, $encoding = null) 574 { 575 if (null !== $string && !\is_scalar($string) && !(\is_object($string) && method_exists($string, '__toString'))) { 576 trigger_error('mb_str_split() expects parameter 1 to be string, '.\gettype($string).' given', \E_USER_WARNING); 577 578 return null; 579 } 580 581 if (1 > $split_length = (int) $split_length) { 582 if (80000 > \PHP_VERSION_ID) { 583 trigger_error('The length of each segment must be greater than zero', \E_USER_WARNING); 584 585 return false; 586 } 587 588 throw new \ValueError('Argument #2 ($length) must be greater than 0'); 589 } 590 591 if (null === $encoding) { 592 $encoding = mb_internal_encoding(); 593 } 594 595 if ('UTF-8' === $encoding = self::getEncoding($encoding)) { 596 $rx = '/('; 597 while (65535 < $split_length) { 598 $rx .= '.{65535}'; 599 $split_length -= 65535; 600 } 601 $rx .= '.{'.$split_length.'})/us'; 602 603 return preg_split($rx, $string, -1, \PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY); 604 } 605 606 $result = []; 607 $length = mb_strlen($string, $encoding); 608 609 for ($i = 0; $i < $length; $i += $split_length) { 610 $result[] = mb_substr($string, $i, $split_length, $encoding); 611 } 612 613 return $result; 614 } 615 616 public static function mb_strtolower($s, $encoding = null) 617 { 618 return self::mb_convert_case($s, \MB_CASE_LOWER, $encoding); 619 } 620 621 public static function mb_strtoupper($s, $encoding = null) 622 { 623 return self::mb_convert_case($s, \MB_CASE_UPPER, $encoding); 624 } 625 626 public static function mb_substitute_character($c = null) 627 { 628 if (null === $c) { 629 return 'none'; 630 } 631 if (0 === strcasecmp($c, 'none')) { 632 return true; 633 } 634 if (80000 > \PHP_VERSION_ID) { 635 return false; 636 } 637 if (\is_int($c) || 'long' === $c || 'entity' === $c) { 638 return false; 639 } 640 641 throw new \ValueError('Argument #1 ($substitute_character) must be "none", "long", "entity" or a valid codepoint'); 642 } 643 644 public static function mb_substr($s, $start, $length = null, $encoding = null) 645 { 646 $encoding = self::getEncoding($encoding); 647 if ('CP850' === $encoding || 'ASCII' === $encoding) { 648 return (string) substr($s, $start, null === $length ? 2147483647 : $length); 649 } 650 651 if ($start < 0) { 652 $start = iconv_strlen($s, $encoding) + $start; 653 if ($start < 0) { 654 $start = 0; 655 } 656 } 657 658 if (null === $length) { 659 $length = 2147483647; 660 } elseif ($length < 0) { 661 $length = iconv_strlen($s, $encoding) + $length - $start; 662 if ($length < 0) { 663 return ''; 664 } 665 } 666 667 return (string) iconv_substr($s, $start, $length, $encoding); 668 } 669 670 public static function mb_stripos($haystack, $needle, $offset = 0, $encoding = null) 671 { 672 [$haystack, $needle] = str_replace(self::SIMPLE_CASE_FOLD[0], self::SIMPLE_CASE_FOLD[1], [ 673 self::mb_convert_case($haystack, \MB_CASE_LOWER, $encoding), 674 self::mb_convert_case($needle, \MB_CASE_LOWER, $encoding), 675 ]); 676 677 return self::mb_strpos($haystack, $needle, $offset, $encoding); 678 } 679 680 public static function mb_stristr($haystack, $needle, $part = false, $encoding = null) 681 { 682 $pos = self::mb_stripos($haystack, $needle, 0, $encoding); 683 684 return self::getSubpart($pos, $part, $haystack, $encoding); 685 } 686 687 public static function mb_strrchr($haystack, $needle, $part = false, $encoding = null) 688 { 689 $encoding = self::getEncoding($encoding); 690 if ('CP850' === $encoding || 'ASCII' === $encoding) { 691 $pos = strrpos($haystack, $needle); 692 } else { 693 $needle = self::mb_substr($needle, 0, 1, $encoding); 694 $pos = iconv_strrpos($haystack, $needle, $encoding); 695 } 696 697 return self::getSubpart($pos, $part, $haystack, $encoding); 698 } 699 700 public static function mb_strrichr($haystack, $needle, $part = false, $encoding = null) 701 { 702 $needle = self::mb_substr($needle, 0, 1, $encoding); 703 $pos = self::mb_strripos($haystack, $needle, $encoding); 704 705 return self::getSubpart($pos, $part, $haystack, $encoding); 706 } 707 708 public static function mb_strripos($haystack, $needle, $offset = 0, $encoding = null) 709 { 710 $haystack = self::mb_convert_case($haystack, \MB_CASE_LOWER, $encoding); 711 $needle = self::mb_convert_case($needle, \MB_CASE_LOWER, $encoding); 712 713 $haystack = str_replace(self::SIMPLE_CASE_FOLD[0], self::SIMPLE_CASE_FOLD[1], $haystack); 714 $needle = str_replace(self::SIMPLE_CASE_FOLD[0], self::SIMPLE_CASE_FOLD[1], $needle); 715 716 return self::mb_strrpos($haystack, $needle, $offset, $encoding); 717 } 718 719 public static function mb_strstr($haystack, $needle, $part = false, $encoding = null) 720 { 721 $pos = strpos($haystack, $needle); 722 if (false === $pos) { 723 return false; 724 } 725 if ($part) { 726 return substr($haystack, 0, $pos); 727 } 728 729 return substr($haystack, $pos); 730 } 731 732 public static function mb_get_info($type = 'all') 733 { 734 $info = [ 735 'internal_encoding' => self::$internalEncoding, 736 'http_output' => 'pass', 737 'http_output_conv_mimetypes' => '^(text/|application/xhtml\+xml)', 738 'func_overload' => 0, 739 'func_overload_list' => 'no overload', 740 'mail_charset' => 'UTF-8', 741 'mail_header_encoding' => 'BASE64', 742 'mail_body_encoding' => 'BASE64', 743 'illegal_chars' => 0, 744 'encoding_translation' => 'Off', 745 'language' => self::$language, 746 'detect_order' => self::$encodingList, 747 'substitute_character' => 'none', 748 'strict_detection' => 'Off', 749 ]; 750 751 if ('all' === $type) { 752 return $info; 753 } 754 if (isset($info[$type])) { 755 return $info[$type]; 756 } 757 758 return false; 759 } 760 761 public static function mb_http_input($type = '') 762 { 763 return false; 764 } 765 766 public static function mb_http_output($encoding = null) 767 { 768 return null !== $encoding ? 'pass' === $encoding : 'pass'; 769 } 770 771 public static function mb_strwidth($s, $encoding = null) 772 { 773 $encoding = self::getEncoding($encoding); 774 775 if ('UTF-8' !== $encoding) { 776 $s = iconv($encoding, 'UTF-8//IGNORE', $s); 777 } 778 779 $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, $wide); 780 781 return ($wide << 1) + iconv_strlen($s, 'UTF-8'); 782 } 783 784 public static function mb_substr_count($haystack, $needle, $encoding = null) 785 { 786 return substr_count($haystack, $needle); 787 } 788 789 public static function mb_output_handler($contents, $status) 790 { 791 return $contents; 792 } 793 794 public static function mb_chr($code, $encoding = null) 795 { 796 if (0x80 > $code %= 0x200000) { 797 $s = \chr($code); 798 } elseif (0x800 > $code) { 799 $s = \chr(0xC0 | $code >> 6).\chr(0x80 | $code & 0x3F); 800 } elseif (0x10000 > $code) { 801 $s = \chr(0xE0 | $code >> 12).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F); 802 } else { 803 $s = \chr(0xF0 | $code >> 18).\chr(0x80 | $code >> 12 & 0x3F).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F); 804 } 805 806 if ('UTF-8' !== $encoding = self::getEncoding($encoding)) { 807 $s = mb_convert_encoding($s, $encoding, 'UTF-8'); 808 } 809 810 return $s; 811 } 812 813 public static function mb_ord($s, $encoding = null) 814 { 815 if ('UTF-8' !== $encoding = self::getEncoding($encoding)) { 816 $s = mb_convert_encoding($s, 'UTF-8', $encoding); 817 } 818 819 if (1 === \strlen($s)) { 820 return \ord($s); 821 } 822 823 $code = ($s = unpack('C*', substr($s, 0, 4))) ? $s[1] : 0; 824 if (0xF0 <= $code) { 825 return (($code - 0xF0) << 18) + (($s[2] - 0x80) << 12) + (($s[3] - 0x80) << 6) + $s[4] - 0x80; 826 } 827 if (0xE0 <= $code) { 828 return (($code - 0xE0) << 12) + (($s[2] - 0x80) << 6) + $s[3] - 0x80; 829 } 830 if (0xC0 <= $code) { 831 return (($code - 0xC0) << 6) + $s[2] - 0x80; 832 } 833 834 return $code; 835 } 836 837 public static function mb_str_pad(string $string, int $length, string $pad_string = ' ', int $pad_type = \STR_PAD_RIGHT, ?string $encoding = null): string 838 { 839 if (!\in_array($pad_type, [\STR_PAD_RIGHT, \STR_PAD_LEFT, \STR_PAD_BOTH], true)) { 840 throw new \ValueError('mb_str_pad(): Argument #4 ($pad_type) must be STR_PAD_LEFT, STR_PAD_RIGHT, or STR_PAD_BOTH'); 841 } 842 843 if (null === $encoding) { 844 $encoding = self::mb_internal_encoding(); 845 } else { 846 self::assertEncoding($encoding, 'mb_str_pad(): Argument #5 ($encoding) must be a valid encoding, "%s" given'); 847 } 848 849 if (self::mb_strlen($pad_string, $encoding) <= 0) { 850 throw new \ValueError('mb_str_pad(): Argument #3 ($pad_string) must be a non-empty string'); 851 } 852 853 $paddingRequired = $length - self::mb_strlen($string, $encoding); 854 855 if ($paddingRequired < 1) { 856 return $string; 857 } 858 859 switch ($pad_type) { 860 case \STR_PAD_LEFT: 861 return self::mb_substr(str_repeat($pad_string, $paddingRequired), 0, $paddingRequired, $encoding).$string; 862 case \STR_PAD_RIGHT: 863 return $string.self::mb_substr(str_repeat($pad_string, $paddingRequired), 0, $paddingRequired, $encoding); 864 default: 865 $leftPaddingLength = floor($paddingRequired / 2); 866 $rightPaddingLength = $paddingRequired - $leftPaddingLength; 867 868 return self::mb_substr(str_repeat($pad_string, $leftPaddingLength), 0, $leftPaddingLength, $encoding).$string.self::mb_substr(str_repeat($pad_string, $rightPaddingLength), 0, $rightPaddingLength, $encoding); 869 } 870 } 871 872 public static function mb_ucfirst(string $string, ?string $encoding = null): string 873 { 874 if (null === $encoding) { 875 $encoding = self::mb_internal_encoding(); 876 } else { 877 self::assertEncoding($encoding, 'mb_ucfirst(): Argument #2 ($encoding) must be a valid encoding, "%s" given'); 878 } 879 880 $firstChar = mb_substr($string, 0, 1, $encoding); 881 $firstChar = mb_convert_case($firstChar, \MB_CASE_TITLE, $encoding); 882 883 return $firstChar.mb_substr($string, 1, null, $encoding); 884 } 885 886 public static function mb_lcfirst(string $string, ?string $encoding = null): string 887 { 888 if (null === $encoding) { 889 $encoding = self::mb_internal_encoding(); 890 } else { 891 self::assertEncoding($encoding, 'mb_lcfirst(): Argument #2 ($encoding) must be a valid encoding, "%s" given'); 892 } 893 894 $firstChar = mb_substr($string, 0, 1, $encoding); 895 $firstChar = mb_convert_case($firstChar, \MB_CASE_LOWER, $encoding); 896 897 return $firstChar.mb_substr($string, 1, null, $encoding); 898 } 899 900 private static function getSubpart($pos, $part, $haystack, $encoding) 901 { 902 if (false === $pos) { 903 return false; 904 } 905 if ($part) { 906 return self::mb_substr($haystack, 0, $pos, $encoding); 907 } 908 909 return self::mb_substr($haystack, $pos, null, $encoding); 910 } 911 912 private static function html_encoding_callback(array $m) 913 { 914 $i = 1; 915 $entities = ''; 916 $m = unpack('C*', htmlentities($m[0], \ENT_COMPAT, 'UTF-8')); 917 918 while (isset($m[$i])) { 919 if (0x80 > $m[$i]) { 920 $entities .= \chr($m[$i++]); 921 continue; 922 } 923 if (0xF0 <= $m[$i]) { 924 $c = (($m[$i++] - 0xF0) << 18) + (($m[$i++] - 0x80) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80; 925 } elseif (0xE0 <= $m[$i]) { 926 $c = (($m[$i++] - 0xE0) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80; 927 } else { 928 $c = (($m[$i++] - 0xC0) << 6) + $m[$i++] - 0x80; 929 } 930 931 $entities .= '&#'.$c.';'; 932 } 933 934 return $entities; 935 } 936 937 private static function title_case(array $s) 938 { 939 return self::mb_convert_case($s[1], \MB_CASE_UPPER, 'UTF-8').self::mb_convert_case($s[2], \MB_CASE_LOWER, 'UTF-8'); 940 } 941 942 private static function getData($file) 943 { 944 if (file_exists($file = __DIR__.'/Resources/unidata/'.$file.'.php')) { 945 return require $file; 946 } 947 948 return false; 949 } 950 951 private static function getEncoding($encoding) 952 { 953 if (null === $encoding) { 954 return self::$internalEncoding; 955 } 956 957 if ('UTF-8' === $encoding) { 958 return 'UTF-8'; 959 } 960 961 $encoding = strtoupper($encoding); 962 963 if ('8BIT' === $encoding || 'BINARY' === $encoding) { 964 return 'CP850'; 965 } 966 967 if ('UTF8' === $encoding) { 968 return 'UTF-8'; 969 } 970 971 return $encoding; 972 } 973 974 public static function mb_trim(string $string, ?string $characters = null, ?string $encoding = null): string 975 { 976 return self::mb_internal_trim('{^[%s]+|[%1$s]+$}Du', $string, $characters, $encoding, __FUNCTION__); 977 } 978 979 public static function mb_ltrim(string $string, ?string $characters = null, ?string $encoding = null): string 980 { 981 return self::mb_internal_trim('{^[%s]+}Du', $string, $characters, $encoding, __FUNCTION__); 982 } 983 984 public static function mb_rtrim(string $string, ?string $characters = null, ?string $encoding = null): string 985 { 986 return self::mb_internal_trim('{[%s]+$}D', $string, $characters, $encoding, __FUNCTION__); 987 } 988 989 private static function mb_internal_trim(string $regex, string $string, ?string $characters, ?string $encoding, string $function): string 990 { 991 if (null === $encoding) { 992 $encoding = self::mb_internal_encoding(); 993 } else { 994 self::assertEncoding($encoding, $function.'(): Argument #3 ($encoding) must be a valid encoding, "%s" given'); 995 } 996 997 if ('' === $characters) { 998 return null === $encoding ? $string : self::mb_convert_encoding($string, $encoding); 999 } 1000 1001 if ('UTF-8' === $encoding) { 1002 $encoding = null; 1003 if (!preg_match('//u', $string)) { 1004 $string = @iconv('UTF-8', 'UTF-8//IGNORE', $string); 1005 } 1006 if (null !== $characters && !preg_match('//u', $characters)) { 1007 $characters = @iconv('UTF-8', 'UTF-8//IGNORE', $characters); 1008 } 1009 } else { 1010 $string = iconv($encoding, 'UTF-8//IGNORE', $string); 1011 1012 if (null !== $characters) { 1013 $characters = iconv($encoding, 'UTF-8//IGNORE', $characters); 1014 } 1015 } 1016 1017 if (null === $characters) { 1018 $characters = "\\0 \f\n\r\t\v\u{00A0}\u{1680}\u{2000}\u{2001}\u{2002}\u{2003}\u{2004}\u{2005}\u{2006}\u{2007}\u{2008}\u{2009}\u{200A}\u{2028}\u{2029}\u{202F}\u{205F}\u{3000}\u{0085}\u{180E}"; 1019 } else { 1020 $characters = preg_quote($characters); 1021 } 1022 1023 $string = preg_replace(sprintf($regex, $characters), '', $string); 1024 1025 if (null === $encoding) { 1026 return $string; 1027 } 1028 1029 return iconv('UTF-8', $encoding.'//IGNORE', $string); 1030 } 1031 1032 private static function assertEncoding(string $encoding, string $errorFormat): void 1033 { 1034 try { 1035 $validEncoding = @self::mb_check_encoding('', $encoding); 1036 } catch (\ValueError $e) { 1037 throw new \ValueError(sprintf($errorFormat, $encoding)); 1038 } 1039 1040 // BC for PHP 7.3 and lower 1041 if (!$validEncoding) { 1042 throw new \ValueError(sprintf($errorFormat, $encoding)); 1043 } 1044 } 1045} 1046