72 private static $encodingList = array(
'ASCII',
'UTF-8');
73 private static $language =
'neutral';
74 private static $internalEncoding =
'UTF-8';
75 private static $caseFold = array(
76 array(
'µ',
'ſ',
"\xCD\x85",
'ς',
"\xCF\x90",
"\xCF\x91",
"\xCF\x95",
"\xCF\x96",
"\xCF\xB0",
"\xCF\xB1",
"\xCF\xB5",
"\xE1\xBA\x9B",
"\xE1\xBE\xBE"),
77 array(
'μ',
's',
'ι',
'σ',
'β',
'θ',
'φ',
'π',
'κ',
'ρ',
'ε',
"\xE1\xB9\xA1",
'ι'),
82 if (\is_array($fromEncoding) ||
false !== strpos($fromEncoding,
',')) {
85 $fromEncoding = self::getEncoding($fromEncoding);
88 $toEncoding = self::getEncoding($toEncoding);
90 if (
'BASE64' === $fromEncoding) {
91 $s = base64_decode($s);
92 $fromEncoding = $toEncoding;
95 if (
'BASE64' === $toEncoding) {
96 return base64_encode($s);
99 if (
'HTML-ENTITIES' === $toEncoding ||
'HTML' === $toEncoding) {
100 if (
'HTML-ENTITIES' === $fromEncoding ||
'HTML' === $fromEncoding) {
101 $fromEncoding =
'Windows-1252';
103 if (
'UTF-8' !== $fromEncoding) {
104 $s = iconv($fromEncoding,
'UTF-8//IGNORE', $s);
107 return preg_replace_callback(
'/[\x80-\xFF]+/', array(__CLASS__,
'html_encoding_callback'), $s);
110 if (
'HTML-ENTITIES' === $fromEncoding) {
111 $s = html_entity_decode($s, ENT_COMPAT,
'UTF-8');
112 $fromEncoding =
'UTF-8';
115 return iconv($fromEncoding, $toEncoding.
'//IGNORE', $s);
118 public static function mb_convert_variables($toEncoding, $fromEncoding, &$a =
null, &$b =
null, &$c =
null, &$d =
null, &$e =
null, &$f =
null)
120 $vars = array(&$a, &$b, &$c, &$d, &$e, &$f);
123 array_walk_recursive($vars,
function (&$v) use (&$ok, $toEncoding, $fromEncoding) {
129 return $ok ? $fromEncoding :
false;
134 return iconv_mime_decode($s, 2, self::$internalEncoding);
137 public static function mb_encode_mimeheader($s, $charset =
null, $transferEncoding =
null, $linefeed =
null, $indent =
null)
139 trigger_error(
'mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', E_USER_WARNING);
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($s).
' given', E_USER_WARNING);
150 if (!\is_array($convmap) || !$convmap) {
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);
165 $encoding = self::getEncoding($encoding);
167 if (
'UTF-8' === $encoding) {
169 if (!preg_match(
'//u', $s)) {
170 $s = @iconv(
'UTF-8',
'UTF-8//IGNORE', $s);
173 $s = iconv($encoding,
'UTF-8//IGNORE', $s);
176 $cnt = floor(\count($convmap) / 4) * 4;
178 for ($i = 0; $i < $cnt; $i += 4) {
180 $convmap[$i] += $convmap[$i + 2];
181 $convmap[$i + 1] += $convmap[$i + 2];
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]) {
195 if (
null === $encoding) {
199 return iconv(
'UTF-8', $encoding.
'//IGNORE', $s);
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($s).
' given', E_USER_WARNING);
210 if (!\is_array($convmap) || !$convmap) {
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);
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);
231 $encoding = self::getEncoding($encoding);
233 if (
'UTF-8' === $encoding) {
235 if (!preg_match(
'//u', $s)) {
236 $s = @iconv(
'UTF-8',
'UTF-8//IGNORE', $s);
239 $s = iconv($encoding,
'UTF-8//IGNORE', $s);
242 static $ulenMask = array(
"\xC0" => 2,
"\xD0" => 2,
"\xE0" => 3,
"\xF0" => 4);
244 $cnt = floor(\count($convmap) / 4) * 4;
250 $ulen = $s[$i] <
"\x80" ? 1 : $ulenMask[$s[$i] &
"\xF0"];
251 $uchr = substr($s, $i, $ulen);
255 for ($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.
';';
265 if (
null === $encoding) {
269 return iconv(
'UTF-8', $encoding.
'//IGNORE', $result);
279 $encoding = self::getEncoding($encoding);
281 if (
'UTF-8' === $encoding) {
283 if (!preg_match(
'//u', $s)) {
284 $s = @iconv(
'UTF-8',
'UTF-8//IGNORE', $s);
287 $s = iconv($encoding,
'UTF-8//IGNORE', $s);
290 if (MB_CASE_TITLE == $mode) {
291 static $titleRegexp =
null;
292 if (
null === $titleRegexp) {
293 $titleRegexp = self::getData(
'titleCaseRegexp');
295 $s = preg_replace_callback($titleRegexp, array(__CLASS__,
'title_case'), $s);
297 if (MB_CASE_UPPER == $mode) {
298 static $upper =
null;
299 if (
null === $upper) {
300 $upper = self::getData(
'upperCase');
304 if (self::MB_CASE_FOLD === $mode) {
305 $s = str_replace(self::$caseFold[0], self::$caseFold[1], $s);
308 static $lower =
null;
309 if (
null === $lower) {
310 $lower = self::getData(
'lowerCase');
315 static $ulenMask = array(
"\xC0" => 2,
"\xD0" => 2,
"\xE0" => 3,
"\xF0" => 4);
321 $ulen = $s[$i] <
"\x80" ? 1 : $ulenMask[$s[$i] &
"\xF0"];
322 $uchr = substr($s, $i, $ulen);
325 if (isset($map[$uchr])) {
327 $nlen = \strlen($uchr);
329 if ($nlen == $ulen) {
332 $s[--$nlen] = $uchr[--$ulen];
335 $s = substr_replace($s, $uchr, $i - $ulen, $ulen);
336 $len += $nlen - $ulen;
343 if (
null === $encoding) {
347 return iconv(
'UTF-8', $encoding.
'//IGNORE', $s);
352 if (
null === $encoding) {
353 return self::$internalEncoding;
356 $encoding = self::getEncoding($encoding);
358 if (
'UTF-8' === $encoding ||
false !== @iconv($encoding, $encoding,
' ')) {
359 self::$internalEncoding = $encoding;
369 if (
null === $lang) {
370 return self::$language;
373 switch ($lang = strtolower($lang)) {
376 self::$language = $lang;
386 return array(
'UTF-8');
391 switch (strtoupper($encoding)) {
394 return array(
'utf8');
402 if (
null === $encoding) {
406 $encoding = self::$internalEncoding;
414 if (
null === $encodingList) {
415 $encodingList = self::$encodingList;
417 if (!\is_array($encodingList)) {
418 $encodingList = array_map(
'trim', explode(
',', $encodingList));
420 $encodingList = array_map(
'strtoupper', $encodingList);
423 foreach ($encodingList as $enc) {
426 if (!preg_match(
'/[\x80-\xFF]/', $str)) {
433 if (preg_match(
'//u', $str)) {
439 if (0 === strncmp($enc,
'ISO-8859-', 9)) {
450 if (
null === $encodingList) {
451 return self::$encodingList;
454 if (!\is_array($encodingList)) {
455 $encodingList = array_map(
'trim', explode(
',', $encodingList));
457 $encodingList = array_map(
'strtoupper', $encodingList);
459 foreach ($encodingList as $enc) {
462 if (strncmp($enc,
'ISO-8859-', 9)) {
472 self::$encodingList = $encodingList;
479 $encoding = self::getEncoding($encoding);
480 if (
'CP850' === $encoding ||
'ASCII' === $encoding) {
484 return @iconv_strlen($s, $encoding);
487 public static function mb_strpos($haystack, $needle, $offset = 0, $encoding =
null)
489 $encoding = self::getEncoding($encoding);
490 if (
'CP850' === $encoding ||
'ASCII' === $encoding) {
491 return strpos($haystack, $needle, $offset);
494 $needle = (string) $needle;
495 if (
'' === $needle) {
496 trigger_error(__METHOD__.
': Empty delimiter', E_USER_WARNING);
501 return iconv_strpos($haystack, $needle, $offset, $encoding);
504 public static function mb_strrpos($haystack, $needle, $offset = 0, $encoding =
null)
506 $encoding = self::getEncoding($encoding);
507 if (
'CP850' === $encoding ||
'ASCII' === $encoding) {
508 return strrpos($haystack, $needle, $offset);
511 if ($offset != (
int) $offset) {
513 } elseif ($offset = (
int) $offset) {
515 if (0 > $offset += self::mb_strlen($needle)) {
520 $haystack =
self::mb_substr($haystack, $offset, 2147483647, $encoding);
524 $pos = iconv_strrpos($haystack, $needle, $encoding);
526 return false !== $pos ? $offset + $pos :
false;
529 public static function mb_str_split($string, $split_length = 1, $encoding =
null)
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);
537 if (1 > $split_length = (
int) $split_length) {
538 trigger_error(
'The length of each segment must be greater than zero', E_USER_WARNING);
543 if (
null === $encoding) {
547 if (
'UTF-8' === $encoding = self::getEncoding($encoding)) {
549 while (65535 < $split_length) {
551 $split_length -= 65535;
553 $rx .=
'.{'.$split_length.
'})/us';
555 return preg_split($rx, $string,
null, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY);
561 for ($i = 0; $i < $length; $i += $split_length) {
562 $result[] =
mb_substr($string, $i, $split_length, $encoding);
580 if (0 === strcasecmp($c,
'none')) {
584 return null !== $c ? false :
'none';
587 public static function mb_substr($s, $start, $length =
null, $encoding =
null)
589 $encoding = self::getEncoding($encoding);
590 if (
'CP850' === $encoding ||
'ASCII' === $encoding) {
591 return (
string) substr($s, $start,
null === $length ? 2147483647 : $length);
595 $start = iconv_strlen($s, $encoding) + $start;
601 if (
null === $length) {
602 $length = 2147483647;
603 } elseif ($length < 0) {
604 $length = iconv_strlen($s, $encoding) + $length - $start;
610 return (
string) iconv_substr($s, $start, $length, $encoding);
613 public static function mb_stripos($haystack, $needle, $offset = 0, $encoding =
null)
621 public static function mb_stristr($haystack, $needle, $part =
false, $encoding =
null)
625 return self::getSubpart($pos, $part, $haystack, $encoding);
628 public static function mb_strrchr($haystack, $needle, $part =
false, $encoding =
null)
630 $encoding = self::getEncoding($encoding);
631 if (
'CP850' === $encoding ||
'ASCII' === $encoding) {
632 return strrchr($haystack, $needle, $part);
635 $pos = iconv_strrpos($haystack, $needle, $encoding);
637 return self::getSubpart($pos, $part, $haystack, $encoding);
640 public static function mb_strrichr($haystack, $needle, $part =
false, $encoding =
null)
645 return self::getSubpart($pos, $part, $haystack, $encoding);
648 public static function mb_strripos($haystack, $needle, $offset = 0, $encoding =
null)
656 public static function mb_strstr($haystack, $needle, $part =
false, $encoding =
null)
658 $pos = strpos($haystack, $needle);
659 if (
false === $pos) {
663 return substr($haystack, 0, $pos);
666 return substr($haystack, $pos);
672 'internal_encoding' => self::$internalEncoding,
673 'http_output' =>
'pass',
674 'http_output_conv_mimetypes' =>
'^(text/|application/xhtml\+xml)',
675 'func_overload' => 0,
676 'func_overload_list' =>
'no overload',
677 'mail_charset' =>
'UTF-8',
678 'mail_header_encoding' =>
'BASE64',
679 'mail_body_encoding' =>
'BASE64',
680 'illegal_chars' => 0,
681 'encoding_translation' =>
'Off',
682 'language' => self::$language,
683 'detect_order' => self::$encodingList,
684 'substitute_character' =>
'none',
685 'strict_detection' =>
'Off',
688 if (
'all' === $type) {
691 if (isset($info[$type])) {
705 return null !== $encoding ?
'pass' === $encoding :
'pass';
710 $encoding = self::getEncoding($encoding);
712 if (
'UTF-8' !== $encoding) {
713 $s = iconv($encoding,
'UTF-8//IGNORE', $s);
716 $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, $wide);
718 return ($wide << 1) + iconv_strlen($s,
'UTF-8');
723 return substr_count($haystack, $needle);
731 public static function mb_chr($code, $encoding =
null)
733 if (0x80 > $code %= 0x200000) {
735 } elseif (0x800 > $code) {
736 $s = \chr(0xC0 | $code >> 6).\chr(0x80 | $code & 0x3F);
737 } elseif (0x10000 > $code) {
738 $s = \chr(0xE0 | $code >> 12).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F);
740 $s = \chr(0xF0 | $code >> 18).\chr(0x80 | $code >> 12 & 0x3F).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F);
743 if (
'UTF-8' !== $encoding = self::getEncoding($encoding)) {
750 public static function mb_ord($s, $encoding =
null)
752 if (
'UTF-8' !== $encoding = self::getEncoding($encoding)) {
756 if (1 === \strlen($s)) {
760 $code = ($s = unpack(
'C*', substr($s, 0, 4))) ? $s[1] : 0;
762 return (($code - 0xF0) << 18) + (($s[2] - 0x80) << 12) + (($s[3] - 0x80) << 6) + $s[4] - 0x80;
765 return (($code - 0xE0) << 12) + (($s[2] - 0x80) << 6) + $s[3] - 0x80;
768 return (($code - 0xC0) << 6) + $s[2] - 0x80;
774 private static function getSubpart($pos, $part, $haystack, $encoding)
776 if (
false === $pos) {
786 private static function html_encoding_callback(array $m)
790 $m = unpack(
'C*', htmlentities($m[0], ENT_COMPAT,
'UTF-8'));
792 while (isset($m[$i])) {
794 $entities .= \chr($m[$i++]);
797 if (0xF0 <= $m[$i]) {
798 $c = (($m[$i++] - 0xF0) << 18) + (($m[$i++] - 0x80) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
799 } elseif (0xE0 <= $m[$i]) {
800 $c = (($m[$i++] - 0xE0) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
802 $c = (($m[$i++] - 0xC0) << 6) + $m[$i++] - 0x80;
805 $entities .=
'&#'.$c.
';';
811 private static function title_case(array $s)
813 return self::mb_convert_case($s[1], MB_CASE_UPPER,
'UTF-8').self::mb_convert_case($s[2], MB_CASE_LOWER,
'UTF-8');
816 private static function getData($file)
818 if (file_exists($file = __DIR__.
'/Resources/unidata/'.$file.
'.php')) {
819 return require $file;
825 private static function getEncoding($encoding)
827 if (
null === $encoding) {
828 return self::$internalEncoding;
831 if (
'UTF-8' === $encoding) {
835 $encoding = strtoupper($encoding);
837 if (
'8BIT' === $encoding ||
'BINARY' === $encoding) {
841 if (
'UTF8' === $encoding) {