| 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 |
public const MB_CASE_FOLD = \PHP_INT_MAX; |
| 71 |
|
| 72 |
private const SIMPLE_CASE_FOLD = [ |
| 73 |
['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"], |
| 74 |
['μ', 's', 'ι', 'σ', 'β', 'θ', 'φ', 'π', 'κ', 'ρ', 'ε', "\xE1\xB9\xA1", 'ι'], |
| 75 |
]; |
| 76 |
|
| 77 |
private static $encodingList = ['ASCII', 'UTF-8']; |
| 78 |
private static $language = 'neutral'; |
| 79 |
private static $internalEncoding = 'UTF-8'; |
| 80 |
|
| 81 |
public static function mb_convert_encoding($s, $toEncoding, $fromEncoding = null) |
| 82 |
{ |
| 83 |
if (\is_array($fromEncoding) || (null !== $fromEncoding && false !== strpos($fromEncoding, ','))) { |
| 84 |
$fromEncoding = self::mb_detect_encoding($s, $fromEncoding); |
| 85 |
} else { |
| 86 |
$fromEncoding = self::getEncoding($fromEncoding); |
| 87 |
} |
| 88 |
|
| 89 |
$toEncoding = self::getEncoding($toEncoding); |
| 90 |
|
| 91 |
if ('BASE64' === $fromEncoding) { |
| 92 |
$s = base64_decode($s); |
| 93 |
$fromEncoding = $toEncoding; |
| 94 |
} |
| 95 |
|
| 96 |
if ('BASE64' === $toEncoding) { |
| 97 |
return base64_encode($s); |
| 98 |
} |
| 99 |
|
| 100 |
if ('HTML-ENTITIES' === $toEncoding || 'HTML' === $toEncoding) { |
| 101 |
if ('HTML-ENTITIES' === $fromEncoding || 'HTML' === $fromEncoding) { |
| 102 |
$fromEncoding = 'Windows-1252'; |
| 103 |
} |
| 104 |
if ('UTF-8' !== $fromEncoding) { |
| 105 |
$s = iconv($fromEncoding, 'UTF-8//IGNORE', $s); |
| 106 |
} |
| 107 |
|
| 108 |
return preg_replace_callback('/[\x80-\xFF]+/', [__CLASS__, 'html_encoding_callback'], $s); |
| 109 |
} |
| 110 |
|
| 111 |
if ('HTML-ENTITIES' === $fromEncoding) { |
| 112 |
$s = html_entity_decode($s, \ENT_COMPAT, 'UTF-8'); |
| 113 |
$fromEncoding = 'UTF-8'; |
| 114 |
} |
| 115 |
|
| 116 |
return iconv($fromEncoding, $toEncoding.'//IGNORE', $s); |
| 117 |
} |
| 118 |
|
| 119 |
public static function mb_convert_variables($toEncoding, $fromEncoding, &...$vars) |
| 120 |
{ |
| 121 |
$ok = true; |
| 122 |
array_walk_recursive($vars, function (&$v) use (&$ok, $toEncoding, $fromEncoding) { |
| 123 |
if (false === $v = self::mb_convert_encoding($v, $toEncoding, $fromEncoding)) { |
| 124 |
$ok = false; |
| 125 |
} |
| 126 |
}); |
| 127 |
|
| 128 |
return $ok ? $fromEncoding : false; |
| 129 |
} |
| 130 |
|
| 131 |
public static function mb_decode_mimeheader($s) |
| 132 |
{ |
| 133 |
return iconv_mime_decode($s, 2, self::$internalEncoding); |
| 134 |
} |
| 135 |
|
| 136 |
public static function mb_encode_mimeheader($s, $charset = null, $transferEncoding = null, $linefeed = null, $indent = null) |
| 137 |
{ |
| 138 |
trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', \E_USER_WARNING); |
| 139 |
} |
| 140 |
|
| 141 |
public static function mb_decode_numericentity($s, $convmap, $encoding = null) |
| 142 |
{ |
| 143 |
if (null !== $s && !\is_scalar($s) && !(\is_object($s) && method_exists($s, '__toString'))) { |
| 144 |
trigger_error('mb_decode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', \E_USER_WARNING); |
| 145 |
|
| 146 |
return null; |
| 147 |
} |
| 148 |
|
| 149 |
if (!\is_array($convmap) || (80000 > \PHP_VERSION_ID && !$convmap)) { |
| 150 |
return false; |
| 151 |
} |
| 152 |
|
| 153 |
if (null !== $encoding && !\is_scalar($encoding)) { |
| 154 |
trigger_error('mb_decode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', \E_USER_WARNING); |
| 155 |
|
| 156 |
return ''; // Instead of null (cf. mb_encode_numericentity). |
| 157 |
} |
| 158 |
|
| 159 |
$s = (string) $s; |
| 160 |
if ('' === $s) { |
| 161 |
return ''; |
| 162 |
} |
| 163 |
|
| 164 |
$encoding = self::getEncoding($encoding); |
| 165 |
|
| 166 |
if ('UTF-8' === $encoding) { |
| 167 |
$encoding = null; |
| 168 |
if (!preg_match('//u', $s)) { |
| 169 |
$s = @iconv('UTF-8', 'UTF-8//IGNORE', $s); |
| 170 |
} |
| 171 |
} else { |
| 172 |
$s = iconv($encoding, 'UTF-8//IGNORE', $s); |
| 173 |
} |
| 174 |
|
| 175 |
$cnt = floor(\count($convmap) / 4) * 4; |
| 176 |
|
| 177 |
for ($i = 0; $i < $cnt; $i += 4) { |
| 178 |
// collector_decode_htmlnumericentity ignores $convmap[$i + 3] |
| 179 |
$convmap[$i] += $convmap[$i + 2]; |
| 180 |
$convmap[$i + 1] += $convmap[$i + 2]; |
| 181 |
} |
| 182 |
|
| 183 |
$s = preg_replace_callback('/&#(?:0*([0-9]+)|x0*([0-9a-fA-F]+))(?!&);?/', function (array $m) use ($cnt, $convmap) { |
| 184 |
$c = isset($m[2]) ? (int) hexdec($m[2]) : $m[1]; |
| 185 |
for ($i = 0; $i < $cnt; $i += 4) { |
| 186 |
if ($c >= $convmap[$i] && $c <= $convmap[$i + 1]) { |
| 187 |
return self::mb_chr($c - $convmap[$i + 2]); |
| 188 |
} |
| 189 |
} |
| 190 |
|
| 191 |
return $m[0]; |
| 192 |
}, $s); |
| 193 |
|
| 194 |
if (null === $encoding) { |
| 195 |
return $s; |
| 196 |
} |
| 197 |
|
| 198 |
return iconv('UTF-8', $encoding.'//IGNORE', $s); |
| 199 |
} |
| 200 |
|
| 201 |
public static function mb_encode_numericentity($s, $convmap, $encoding = null, $is_hex = false) |
| 202 |
{ |
| 203 |
if (null !== $s && !\is_scalar($s) && !(\is_object($s) && method_exists($s, '__toString'))) { |
| 204 |
trigger_error('mb_encode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', \E_USER_WARNING); |
| 205 |
|
| 206 |
return null; |
| 207 |
} |
| 208 |
|
| 209 |
if (!\is_array($convmap) || (80000 > \PHP_VERSION_ID && !$convmap)) { |
| 210 |
return false; |
| 211 |
} |
| 212 |
|
| 213 |
if (null !== $encoding && !\is_scalar($encoding)) { |
| 214 |
trigger_error('mb_encode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', \E_USER_WARNING); |
| 215 |
|
| 216 |
return null; // Instead of '' (cf. mb_decode_numericentity). |
| 217 |
} |
| 218 |
|
| 219 |
if (null !== $is_hex && !\is_scalar($is_hex)) { |
| 220 |
trigger_error('mb_encode_numericentity() expects parameter 4 to be boolean, '.\gettype($s).' given', \E_USER_WARNING); |
| 221 |
|
| 222 |
return null; |
| 223 |
} |
| 224 |
|
| 225 |
$s = (string) $s; |
| 226 |
if ('' === $s) { |
| 227 |
return ''; |
| 228 |
} |
| 229 |
|
| 230 |
$encoding = self::getEncoding($encoding); |
| 231 |
|
| 232 |
if ('UTF-8' === $encoding) { |
| 233 |
$encoding = null; |
| 234 |
if (!preg_match('//u', $s)) { |
| 235 |
$s = @iconv('UTF-8', 'UTF-8//IGNORE', $s); |
| 236 |
} |
| 237 |
} else { |
| 238 |
$s = iconv($encoding, 'UTF-8//IGNORE', $s); |
| 239 |
} |
| 240 |
|
| 241 |
static $ulenMask = ["\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4]; |
| 242 |
|
| 243 |
$cnt = floor(\count($convmap) / 4) * 4; |
| 244 |
$i = 0; |
| 245 |
$len = \strlen($s); |
| 246 |
$result = ''; |
| 247 |
|
| 248 |
while ($i < $len) { |
| 249 |
$ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"]; |
| 250 |
$uchr = substr($s, $i, $ulen); |
| 251 |
$i += $ulen; |
| 252 |
$c = self::mb_ord($uchr); |
| 253 |
|
| 254 |
for ($j = 0; $j < $cnt; $j += 4) { |
| 255 |
if ($c >= $convmap[$j] && $c <= $convmap[$j + 1]) { |
| 256 |
$cOffset = ($c + $convmap[$j + 2]) & $convmap[$j + 3]; |
| 257 |
$result .= $is_hex ? sprintf('&#x%X;', $cOffset) : '&#'.$cOffset.';'; |
| 258 |
continue 2; |
| 259 |
} |
| 260 |
} |
| 261 |
$result .= $uchr; |
| 262 |
} |
| 263 |
|
| 264 |
if (null === $encoding) { |
| 265 |
return $result; |
| 266 |
} |
| 267 |
|
| 268 |
return iconv('UTF-8', $encoding.'//IGNORE', $result); |
| 269 |
} |
| 270 |
|
| 271 |
public static function mb_convert_case($s, $mode, $encoding = null) |
| 272 |
{ |
| 273 |
$s = (string) $s; |
| 274 |
if ('' === $s) { |
| 275 |
return ''; |
| 276 |
} |
| 277 |
|
| 278 |
$encoding = self::getEncoding($encoding); |
| 279 |
|
| 280 |
if ('UTF-8' === $encoding) { |
| 281 |
$encoding = null; |
| 282 |
if (!preg_match('//u', $s)) { |
| 283 |
$s = @iconv('UTF-8', 'UTF-8//IGNORE', $s); |
| 284 |
} |
| 285 |
} else { |
| 286 |
$s = iconv($encoding, 'UTF-8//IGNORE', $s); |
| 287 |
} |
| 288 |
|
| 289 |
if (\MB_CASE_TITLE == $mode) { |
| 290 |
static $titleRegexp = null; |
| 291 |
if (null === $titleRegexp) { |
| 292 |
$titleRegexp = self::getData('titleCaseRegexp'); |
| 293 |
} |
| 294 |
$s = preg_replace_callback($titleRegexp, [__CLASS__, 'title_case'], $s); |
| 295 |
} else { |
| 296 |
if (\MB_CASE_UPPER == $mode) { |
| 297 |
static $upper = null; |
| 298 |
if (null === $upper) { |
| 299 |
$upper = self::getData('upperCase'); |
| 300 |
} |
| 301 |
$map = $upper; |
| 302 |
} else { |
| 303 |
if (self::MB_CASE_FOLD === $mode) { |
| 304 |
static $caseFolding = null; |
| 305 |
if (null === $caseFolding) { |
| 306 |
$caseFolding = self::getData('caseFolding'); |
| 307 |
} |
| 308 |
$s = strtr($s, $caseFolding); |
| 309 |
} |
| 310 |
|
| 311 |
static $lower = null; |
| 312 |
if (null === $lower) { |
| 313 |
$lower = self::getData('lowerCase'); |
| 314 |
} |
| 315 |
$map = $lower; |
| 316 |
} |
| 317 |
|
| 318 |
static $ulenMask = ["\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4]; |
| 319 |
|
| 320 |
$i = 0; |
| 321 |
$len = \strlen($s); |
| 322 |
|
| 323 |
while ($i < $len) { |
| 324 |
$ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"]; |
| 325 |
$uchr = substr($s, $i, $ulen); |
| 326 |
$i += $ulen; |
| 327 |
|
| 328 |
if (isset($map[$uchr])) { |
| 329 |
$uchr = $map[$uchr]; |
| 330 |
$nlen = \strlen($uchr); |
| 331 |
|
| 332 |
if ($nlen == $ulen) { |
| 333 |
$nlen = $i; |
| 334 |
do { |
| 335 |
$s[--$nlen] = $uchr[--$ulen]; |
| 336 |
} while ($ulen); |
| 337 |
} else { |
| 338 |
$s = substr_replace($s, $uchr, $i - $ulen, $ulen); |
| 339 |
$len += $nlen - $ulen; |
| 340 |
$i += $nlen - $ulen; |
| 341 |
} |
| 342 |
} |
| 343 |
} |
| 344 |
} |
| 345 |
|
| 346 |
if (null === $encoding) { |
| 347 |
return $s; |
| 348 |
} |
| 349 |
|
| 350 |
return iconv('UTF-8', $encoding.'//IGNORE', $s); |
| 351 |
} |
| 352 |
|
| 353 |
public static function mb_internal_encoding($encoding = null) |
| 354 |
{ |
| 355 |
if (null === $encoding) { |
| 356 |
return self::$internalEncoding; |
| 357 |
} |
| 358 |
|
| 359 |
$normalizedEncoding = self::getEncoding($encoding); |
| 360 |
|
| 361 |
if ('UTF-8' === $normalizedEncoding || false !== @iconv($normalizedEncoding, $normalizedEncoding, ' ')) { |
| 362 |
self::$internalEncoding = $normalizedEncoding; |
| 363 |
|
| 364 |
return true; |
| 365 |
} |
| 366 |
|
| 367 |
if (80000 > \PHP_VERSION_ID) { |
| 368 |
return false; |
| 369 |
} |
| 370 |
|
| 371 |
throw new \ValueError(sprintf('Argument #1 ($encoding) must be a valid encoding, "%s" given', $encoding)); |
| 372 |
} |
| 373 |
|
| 374 |
public static function mb_language($lang = null) |
| 375 |
{ |
| 376 |
if (null === $lang) { |
| 377 |
return self::$language; |
| 378 |
} |
| 379 |
|
| 380 |
switch ($normalizedLang = strtolower($lang)) { |
| 381 |
case 'uni': |
| 382 |
case 'neutral': |
| 383 |
self::$language = $normalizedLang; |
| 384 |
|
| 385 |
return true; |
| 386 |
} |
| 387 |
|
| 388 |
if (80000 > \PHP_VERSION_ID) { |
| 389 |
return false; |
| 390 |
} |
| 391 |
|
| 392 |
throw new \ValueError(sprintf('Argument #1 ($language) must be a valid language, "%s" given', $lang)); |
| 393 |
} |
| 394 |
|
| 395 |
public static function mb_list_encodings() |
| 396 |
{ |
| 397 |
return ['UTF-8']; |
| 398 |
} |
| 399 |
|
| 400 |
public static function mb_encoding_aliases($encoding) |
| 401 |
{ |
| 402 |
switch (strtoupper($encoding)) { |
| 403 |
case 'UTF8': |
| 404 |
case 'UTF-8': |
| 405 |
return ['utf8']; |
| 406 |
} |
| 407 |
|
| 408 |
return false; |
| 409 |
} |
| 410 |
|
| 411 |
public static function mb_check_encoding($var = null, $encoding = null) |
| 412 |
{ |
| 413 |
if (PHP_VERSION_ID < 70200 && \is_array($var)) { |
| 414 |
trigger_error('mb_check_encoding() expects parameter 1 to be string, array given', \E_USER_WARNING); |
| 415 |
|
| 416 |
return null; |
| 417 |
} |
| 418 |
|
| 419 |
if (null === $encoding) { |
| 420 |
if (null === $var) { |
| 421 |
return false; |
| 422 |
} |
| 423 |
$encoding = self::$internalEncoding; |
| 424 |
} |
| 425 |
|
| 426 |
if (!\is_array($var)) { |
| 427 |
return self::mb_detect_encoding($var, [$encoding]) || false !== @iconv($encoding, $encoding, $var); |
| 428 |
} |
| 429 |
|
| 430 |
foreach ($var as $key => $value) { |
| 431 |
if (!self::mb_check_encoding($key, $encoding)) { |
| 432 |
return false; |
| 433 |
} |
| 434 |
if (!self::mb_check_encoding($value, $encoding)) { |
| 435 |
return false; |
| 436 |
} |
| 437 |
} |
| 438 |
|
| 439 |
return true; |
| 440 |
|
| 441 |
} |
| 442 |
|
| 443 |
public static function mb_detect_encoding($str, $encodingList = null, $strict = false) |
| 444 |
{ |
| 445 |
if (null === $encodingList) { |
| 446 |
$encodingList = self::$encodingList; |
| 447 |
} else { |
| 448 |
if (!\is_array($encodingList)) { |
| 449 |
$encodingList = array_map('trim', explode(',', $encodingList)); |
| 450 |
} |
| 451 |
$encodingList = array_map('strtoupper', $encodingList); |
| 452 |
} |
| 453 |
|
| 454 |
foreach ($encodingList as $enc) { |
| 455 |
switch ($enc) { |
| 456 |
case 'ASCII': |
| 457 |
if (!preg_match('/[\x80-\xFF]/', $str)) { |
| 458 |
return $enc; |
| 459 |
} |
| 460 |
break; |
| 461 |
|
| 462 |
case 'UTF8': |
| 463 |
case 'UTF-8': |
| 464 |
if (preg_match('//u', $str)) { |
| 465 |
return 'UTF-8'; |
| 466 |
} |
| 467 |
break; |
| 468 |
|
| 469 |
default: |
| 470 |
if (0 === strncmp($enc, 'ISO-8859-', 9)) { |
| 471 |
return $enc; |
| 472 |
} |
| 473 |
} |
| 474 |
} |
| 475 |
|
| 476 |
return false; |
| 477 |
} |
| 478 |
|
| 479 |
public static function mb_detect_order($encodingList = null) |
| 480 |
{ |
| 481 |
if (null === $encodingList) { |
| 482 |
return self::$encodingList; |
| 483 |
} |
| 484 |
|
| 485 |
if (!\is_array($encodingList)) { |
| 486 |
$encodingList = array_map('trim', explode(',', $encodingList)); |
| 487 |
} |
| 488 |
$encodingList = array_map('strtoupper', $encodingList); |
| 489 |
|
| 490 |
foreach ($encodingList as $enc) { |
| 491 |
switch ($enc) { |
| 492 |
default: |
| 493 |
if (strncmp($enc, 'ISO-8859-', 9)) { |
| 494 |
return false; |
| 495 |
} |
| 496 |
// no break |
| 497 |
case 'ASCII': |
| 498 |
case 'UTF8': |
| 499 |
case 'UTF-8': |
| 500 |
} |
| 501 |
} |
| 502 |
|
| 503 |
self::$encodingList = $encodingList; |
| 504 |
|
| 505 |
return true; |
| 506 |
} |
| 507 |
|
| 508 |
public static function mb_strlen($s, $encoding = null) |
| 509 |
{ |
| 510 |
$encoding = self::getEncoding($encoding); |
| 511 |
if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 512 |
return \strlen($s); |
| 513 |
} |
| 514 |
|
| 515 |
return @iconv_strlen($s, $encoding); |
| 516 |
} |
| 517 |
|
| 518 |
public static function mb_strpos($haystack, $needle, $offset = 0, $encoding = null) |
| 519 |
{ |
| 520 |
$encoding = self::getEncoding($encoding); |
| 521 |
if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 522 |
return strpos($haystack, $needle, $offset); |
| 523 |
} |
| 524 |
|
| 525 |
$needle = (string) $needle; |
| 526 |
if ('' === $needle) { |
| 527 |
if (80000 > \PHP_VERSION_ID) { |
| 528 |
trigger_error(__METHOD__.': Empty delimiter', \E_USER_WARNING); |
| 529 |
|
| 530 |
return false; |
| 531 |
} |
| 532 |
|
| 533 |
return 0; |
| 534 |
} |
| 535 |
|
| 536 |
return iconv_strpos($haystack, $needle, $offset, $encoding); |
| 537 |
} |
| 538 |
|
| 539 |
public static function mb_strrpos($haystack, $needle, $offset = 0, $encoding = null) |
| 540 |
{ |
| 541 |
$encoding = self::getEncoding($encoding); |
| 542 |
if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 543 |
return strrpos($haystack, $needle, $offset); |
| 544 |
} |
| 545 |
|
| 546 |
if ($offset != (int) $offset) { |
| 547 |
$offset = 0; |
| 548 |
} elseif ($offset = (int) $offset) { |
| 549 |
if ($offset < 0) { |
| 550 |
if (0 > $offset += self::mb_strlen($needle)) { |
| 551 |
$haystack = self::mb_substr($haystack, 0, $offset, $encoding); |
| 552 |
} |
| 553 |
$offset = 0; |
| 554 |
} else { |
| 555 |
$haystack = self::mb_substr($haystack, $offset, 2147483647, $encoding); |
| 556 |
} |
| 557 |
} |
| 558 |
|
| 559 |
$pos = '' !== $needle || 80000 > \PHP_VERSION_ID |
| 560 |
? iconv_strrpos($haystack, $needle, $encoding) |
| 561 |
: self::mb_strlen($haystack, $encoding); |
| 562 |
|
| 563 |
return false !== $pos ? $offset + $pos : false; |
| 564 |
} |
| 565 |
|
| 566 |
public static function mb_str_split($string, $split_length = 1, $encoding = null) |
| 567 |
{ |
| 568 |
if (null !== $string && !\is_scalar($string) && !(\is_object($string) && method_exists($string, '__toString'))) { |
| 569 |
trigger_error('mb_str_split() expects parameter 1 to be string, '.\gettype($string).' given', \E_USER_WARNING); |
| 570 |
|
| 571 |
return null; |
| 572 |
} |
| 573 |
|
| 574 |
if (1 > $split_length = (int) $split_length) { |
| 575 |
if (80000 > \PHP_VERSION_ID) { |
| 576 |
trigger_error('The length of each segment must be greater than zero', \E_USER_WARNING); |
| 577 |
|
| 578 |
return false; |
| 579 |
} |
| 580 |
|
| 581 |
throw new \ValueError('Argument #2 ($length) must be greater than 0'); |
| 582 |
} |
| 583 |
|
| 584 |
if (null === $encoding) { |
| 585 |
$encoding = mb_internal_encoding(); |
| 586 |
} |
| 587 |
|
| 588 |
if ('UTF-8' === $encoding = self::getEncoding($encoding)) { |
| 589 |
$rx = '/('; |
| 590 |
while (65535 < $split_length) { |
| 591 |
$rx .= '.{65535}'; |
| 592 |
$split_length -= 65535; |
| 593 |
} |
| 594 |
$rx .= '.{'.$split_length.'})/us'; |
| 595 |
|
| 596 |
return preg_split($rx, $string, -1, \PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY); |
| 597 |
} |
| 598 |
|
| 599 |
$result = []; |
| 600 |
$length = mb_strlen($string, $encoding); |
| 601 |
|
| 602 |
for ($i = 0; $i < $length; $i += $split_length) { |
| 603 |
$result[] = mb_substr($string, $i, $split_length, $encoding); |
| 604 |
} |
| 605 |
|
| 606 |
return $result; |
| 607 |
} |
| 608 |
|
| 609 |
public static function mb_strtolower($s, $encoding = null) |
| 610 |
{ |
| 611 |
return self::mb_convert_case($s, \MB_CASE_LOWER, $encoding); |
| 612 |
} |
| 613 |
|
| 614 |
public static function mb_strtoupper($s, $encoding = null) |
| 615 |
{ |
| 616 |
return self::mb_convert_case($s, \MB_CASE_UPPER, $encoding); |
| 617 |
} |
| 618 |
|
| 619 |
public static function mb_substitute_character($c = null) |
| 620 |
{ |
| 621 |
if (null === $c) { |
| 622 |
return 'none'; |
| 623 |
} |
| 624 |
if (0 === strcasecmp($c, 'none')) { |
| 625 |
return true; |
| 626 |
} |
| 627 |
if (80000 > \PHP_VERSION_ID) { |
| 628 |
return false; |
| 629 |
} |
| 630 |
if (\is_int($c) || 'long' === $c || 'entity' === $c) { |
| 631 |
return false; |
| 632 |
} |
| 633 |
|
| 634 |
throw new \ValueError('Argument #1 ($substitute_character) must be "none", "long", "entity" or a valid codepoint'); |
| 635 |
} |
| 636 |
|
| 637 |
public static function mb_substr($s, $start, $length = null, $encoding = null) |
| 638 |
{ |
| 639 |
$encoding = self::getEncoding($encoding); |
| 640 |
if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 641 |
return (string) substr($s, $start, null === $length ? 2147483647 : $length); |
| 642 |
} |
| 643 |
|
| 644 |
if ($start < 0) { |
| 645 |
$start = iconv_strlen($s, $encoding) + $start; |
| 646 |
if ($start < 0) { |
| 647 |
$start = 0; |
| 648 |
} |
| 649 |
} |
| 650 |
|
| 651 |
if (null === $length) { |
| 652 |
$length = 2147483647; |
| 653 |
} elseif ($length < 0) { |
| 654 |
$length = iconv_strlen($s, $encoding) + $length - $start; |
| 655 |
if ($length < 0) { |
| 656 |
return ''; |
| 657 |
} |
| 658 |
} |
| 659 |
|
| 660 |
return (string) iconv_substr($s, $start, $length, $encoding); |
| 661 |
} |
| 662 |
|
| 663 |
public static function mb_stripos($haystack, $needle, $offset = 0, $encoding = null) |
| 664 |
{ |
| 665 |
[$haystack, $needle] = str_replace(self::SIMPLE_CASE_FOLD[0], self::SIMPLE_CASE_FOLD[1], [ |
| 666 |
self::mb_convert_case($haystack, \MB_CASE_LOWER, $encoding), |
| 667 |
self::mb_convert_case($needle, \MB_CASE_LOWER, $encoding), |
| 668 |
]); |
| 669 |
|
| 670 |
return self::mb_strpos($haystack, $needle, $offset, $encoding); |
| 671 |
} |
| 672 |
|
| 673 |
public static function mb_stristr($haystack, $needle, $part = false, $encoding = null) |
| 674 |
{ |
| 675 |
$pos = self::mb_stripos($haystack, $needle, 0, $encoding); |
| 676 |
|
| 677 |
return self::getSubpart($pos, $part, $haystack, $encoding); |
| 678 |
} |
| 679 |
|
| 680 |
public static function mb_strrchr($haystack, $needle, $part = false, $encoding = null) |
| 681 |
{ |
| 682 |
$encoding = self::getEncoding($encoding); |
| 683 |
if ('CP850' === $encoding || 'ASCII' === $encoding) { |
| 684 |
$pos = strrpos($haystack, $needle); |
| 685 |
} else { |
| 686 |
$needle = self::mb_substr($needle, 0, 1, $encoding); |
| 687 |
$pos = iconv_strrpos($haystack, $needle, $encoding); |
| 688 |
} |
| 689 |
|
| 690 |
return self::getSubpart($pos, $part, $haystack, $encoding); |
| 691 |
} |
| 692 |
|
| 693 |
public static function mb_strrichr($haystack, $needle, $part = false, $encoding = null) |
| 694 |
{ |
| 695 |
$needle = self::mb_substr($needle, 0, 1, $encoding); |
| 696 |
$pos = self::mb_strripos($haystack, $needle, $encoding); |
| 697 |
|
| 698 |
return self::getSubpart($pos, $part, $haystack, $encoding); |
| 699 |
} |
| 700 |
|
| 701 |
public static function mb_strripos($haystack, $needle, $offset = 0, $encoding = null) |
| 702 |
{ |
| 703 |
$haystack = self::mb_convert_case($haystack, \MB_CASE_LOWER, $encoding); |
| 704 |
$needle = self::mb_convert_case($needle, \MB_CASE_LOWER, $encoding); |
| 705 |
|
| 706 |
$haystack = str_replace(self::SIMPLE_CASE_FOLD[0], self::SIMPLE_CASE_FOLD[1], $haystack); |
| 707 |
$needle = str_replace(self::SIMPLE_CASE_FOLD[0], self::SIMPLE_CASE_FOLD[1], $needle); |
| 708 |
|
| 709 |
return self::mb_strrpos($haystack, $needle, $offset, $encoding); |
| 710 |
} |
| 711 |
|
| 712 |
public static function mb_strstr($haystack, $needle, $part = false, $encoding = null) |
| 713 |
{ |
| 714 |
$pos = strpos($haystack, $needle); |
| 715 |
if (false === $pos) { |
| 716 |
return false; |
| 717 |
} |
| 718 |
if ($part) { |
| 719 |
return substr($haystack, 0, $pos); |
| 720 |
} |
| 721 |
|
| 722 |
return substr($haystack, $pos); |
| 723 |
} |
| 724 |
|
| 725 |
public static function mb_get_info($type = 'all') |
| 726 |
{ |
| 727 |
$info = [ |
| 728 |
'internal_encoding' => self::$internalEncoding, |
| 729 |
'http_output' => 'pass', |
| 730 |
'http_output_conv_mimetypes' => '^(text/|application/xhtml\+xml)', |
| 731 |
'func_overload' => 0, |
| 732 |
'func_overload_list' => 'no overload', |
| 733 |
'mail_charset' => 'UTF-8', |
| 734 |
'mail_header_encoding' => 'BASE64', |
| 735 |
'mail_body_encoding' => 'BASE64', |
| 736 |
'illegal_chars' => 0, |
| 737 |
'encoding_translation' => 'Off', |
| 738 |
'language' => self::$language, |
| 739 |
'detect_order' => self::$encodingList, |
| 740 |
'substitute_character' => 'none', |
| 741 |
'strict_detection' => 'Off', |
| 742 |
]; |
| 743 |
|
| 744 |
if ('all' === $type) { |
| 745 |
return $info; |
| 746 |
} |
| 747 |
if (isset($info[$type])) { |
| 748 |
return $info[$type]; |
| 749 |
} |
| 750 |
|
| 751 |
return false; |
| 752 |
} |
| 753 |
|
| 754 |
public static function mb_http_input($type = '') |
| 755 |
{ |
| 756 |
return false; |
| 757 |
} |
| 758 |
|
| 759 |
public static function mb_http_output($encoding = null) |
| 760 |
{ |
| 761 |
return null !== $encoding ? 'pass' === $encoding : 'pass'; |
| 762 |
} |
| 763 |
|
| 764 |
public static function mb_strwidth($s, $encoding = null) |
| 765 |
{ |
| 766 |
$encoding = self::getEncoding($encoding); |
| 767 |
|
| 768 |
if ('UTF-8' !== $encoding) { |
| 769 |
$s = iconv($encoding, 'UTF-8//IGNORE', $s); |
| 770 |
} |
| 771 |
|
| 772 |
$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, $wide); |
| 773 |
|
| 774 |
return ($wide << 1) + iconv_strlen($s, 'UTF-8'); |
| 775 |
} |
| 776 |
|
| 777 |
public static function mb_substr_count($haystack, $needle, $encoding = null) |
| 778 |
{ |
| 779 |
return substr_count($haystack, $needle); |
| 780 |
} |
| 781 |
|
| 782 |
public static function mb_output_handler($contents, $status) |
| 783 |
{ |
| 784 |
return $contents; |
| 785 |
} |
| 786 |
|
| 787 |
public static function mb_chr($code, $encoding = null) |
| 788 |
{ |
| 789 |
if (0x80 > $code %= 0x200000) { |
| 790 |
$s = \chr($code); |
| 791 |
} elseif (0x800 > $code) { |
| 792 |
$s = \chr(0xC0 | $code >> 6).\chr(0x80 | $code & 0x3F); |
| 793 |
} elseif (0x10000 > $code) { |
| 794 |
$s = \chr(0xE0 | $code >> 12).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F); |
| 795 |
} else { |
| 796 |
$s = \chr(0xF0 | $code >> 18).\chr(0x80 | $code >> 12 & 0x3F).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F); |
| 797 |
} |
| 798 |
|
| 799 |
if ('UTF-8' !== $encoding = self::getEncoding($encoding)) { |
| 800 |
$s = mb_convert_encoding($s, $encoding, 'UTF-8'); |
| 801 |
} |
| 802 |
|
| 803 |
return $s; |
| 804 |
} |
| 805 |
|
| 806 |
public static function mb_ord($s, $encoding = null) |
| 807 |
{ |
| 808 |
if ('UTF-8' !== $encoding = self::getEncoding($encoding)) { |
| 809 |
$s = mb_convert_encoding($s, 'UTF-8', $encoding); |
| 810 |
} |
| 811 |
|
| 812 |
if (1 === \strlen($s)) { |
| 813 |
return \ord($s); |
| 814 |
} |
| 815 |
|
| 816 |
$code = ($s = unpack('C*', substr($s, 0, 4))) ? $s[1] : 0; |
| 817 |
if (0xF0 <= $code) { |
| 818 |
return (($code - 0xF0) << 18) + (($s[2] - 0x80) << 12) + (($s[3] - 0x80) << 6) + $s[4] - 0x80; |
| 819 |
} |
| 820 |
if (0xE0 <= $code) { |
| 821 |
return (($code - 0xE0) << 12) + (($s[2] - 0x80) << 6) + $s[3] - 0x80; |
| 822 |
} |
| 823 |
if (0xC0 <= $code) { |
| 824 |
return (($code - 0xC0) << 6) + $s[2] - 0x80; |
| 825 |
} |
| 826 |
|
| 827 |
return $code; |
| 828 |
} |
| 829 |
|
| 830 |
public static function mb_str_pad(string $string, int $length, string $pad_string = ' ', int $pad_type = \STR_PAD_RIGHT, string $encoding = null): string |
| 831 |
{ |
| 832 |
if (!\in_array($pad_type, [\STR_PAD_RIGHT, \STR_PAD_LEFT, \STR_PAD_BOTH], true)) { |
| 833 |
throw new \ValueError('mb_str_pad(): Argument #4 ($pad_type) must be STR_PAD_LEFT, STR_PAD_RIGHT, or STR_PAD_BOTH'); |
| 834 |
} |
| 835 |
|
| 836 |
if (null === $encoding) { |
| 837 |
$encoding = self::mb_internal_encoding(); |
| 838 |
} |
| 839 |
|
| 840 |
try { |
| 841 |
$validEncoding = @self::mb_check_encoding('', $encoding); |
| 842 |
} catch (\ValueError $e) { |
| 843 |
throw new \ValueError(sprintf('mb_str_pad(): Argument #5 ($encoding) must be a valid encoding, "%s" given', $encoding)); |
| 844 |
} |
| 845 |
|
| 846 |
// BC for PHP 7.3 and lower |
| 847 |
if (!$validEncoding) { |
| 848 |
throw new \ValueError(sprintf('mb_str_pad(): Argument #5 ($encoding) must be a valid encoding, "%s" given', $encoding)); |
| 849 |
} |
| 850 |
|
| 851 |
if (self::mb_strlen($pad_string, $encoding) <= 0) { |
| 852 |
throw new \ValueError('mb_str_pad(): Argument #3 ($pad_string) must be a non-empty string'); |
| 853 |
} |
| 854 |
|
| 855 |
$paddingRequired = $length - self::mb_strlen($string, $encoding); |
| 856 |
|
| 857 |
if ($paddingRequired < 1) { |
| 858 |
return $string; |
| 859 |
} |
| 860 |
|
| 861 |
switch ($pad_type) { |
| 862 |
case \STR_PAD_LEFT: |
| 863 |
return self::mb_substr(str_repeat($pad_string, $paddingRequired), 0, $paddingRequired, $encoding).$string; |
| 864 |
case \STR_PAD_RIGHT: |
| 865 |
return $string.self::mb_substr(str_repeat($pad_string, $paddingRequired), 0, $paddingRequired, $encoding); |
| 866 |
default: |
| 867 |
$leftPaddingLength = floor($paddingRequired / 2); |
| 868 |
$rightPaddingLength = $paddingRequired - $leftPaddingLength; |
| 869 |
|
| 870 |
return self::mb_substr(str_repeat($pad_string, $leftPaddingLength), 0, $leftPaddingLength, $encoding).$string.self::mb_substr(str_repeat($pad_string, $rightPaddingLength), 0, $rightPaddingLength, $encoding); |
| 871 |
} |
| 872 |
} |
| 873 |
|
| 874 |
private static function getSubpart($pos, $part, $haystack, $encoding) |
| 875 |
{ |
| 876 |
if (false === $pos) { |
| 877 |
return false; |
| 878 |
} |
| 879 |
if ($part) { |
| 880 |
return self::mb_substr($haystack, 0, $pos, $encoding); |
| 881 |
} |
| 882 |
|
| 883 |
return self::mb_substr($haystack, $pos, null, $encoding); |
| 884 |
} |
| 885 |
|
| 886 |
private static function html_encoding_callback(array $m) |
| 887 |
{ |
| 888 |
$i = 1; |
| 889 |
$entities = ''; |
| 890 |
$m = unpack('C*', htmlentities($m[0], \ENT_COMPAT, 'UTF-8')); |
| 891 |
|
| 892 |
while (isset($m[$i])) { |
| 893 |
if (0x80 > $m[$i]) { |
| 894 |
$entities .= \chr($m[$i++]); |
| 895 |
continue; |
| 896 |
} |
| 897 |
if (0xF0 <= $m[$i]) { |
| 898 |
$c = (($m[$i++] - 0xF0) << 18) + (($m[$i++] - 0x80) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80; |
| 899 |
} elseif (0xE0 <= $m[$i]) { |
| 900 |
$c = (($m[$i++] - 0xE0) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80; |
| 901 |
} else { |
| 902 |
$c = (($m[$i++] - 0xC0) << 6) + $m[$i++] - 0x80; |
| 903 |
} |
| 904 |
|
| 905 |
$entities .= '&#'.$c.';'; |
| 906 |
} |
| 907 |
|
| 908 |
return $entities; |
| 909 |
} |
| 910 |
|
| 911 |
private static function title_case(array $s) |
| 912 |
{ |
| 913 |
return self::mb_convert_case($s[1], \MB_CASE_UPPER, 'UTF-8').self::mb_convert_case($s[2], \MB_CASE_LOWER, 'UTF-8'); |
| 914 |
} |
| 915 |
|
| 916 |
private static function getData($file) |
| 917 |
{ |
| 918 |
if (file_exists($file = __DIR__.'/Resources/unidata/'.$file.'.php')) { |
| 919 |
return require $file; |
| 920 |
} |
| 921 |
|
| 922 |
return false; |
| 923 |
} |
| 924 |
|
| 925 |
private static function getEncoding($encoding) |
| 926 |
{ |
| 927 |
if (null === $encoding) { |
| 928 |
return self::$internalEncoding; |
| 929 |
} |
| 930 |
|
| 931 |
if ('UTF-8' === $encoding) { |
| 932 |
return 'UTF-8'; |
| 933 |
} |
| 934 |
|
| 935 |
$encoding = strtoupper($encoding); |
| 936 |
|
| 937 |
if ('8BIT' === $encoding || 'BINARY' === $encoding) { |
| 938 |
return 'CP850'; |
| 939 |
} |
| 940 |
|
| 941 |
if ('UTF8' === $encoding) { |
| 942 |
return 'UTF-8'; |
| 943 |
} |
| 944 |
|
| 945 |
return $encoding; |
| 946 |
} |
| 947 |
} |
| 948 |
|
