diff options
Diffstat (limited to 'vendor/symfony/polyfill-mbstring/Mbstring.php')
| -rw-r--r-- | vendor/symfony/polyfill-mbstring/Mbstring.php | 415 |
1 files changed, 342 insertions, 73 deletions
diff --git a/vendor/symfony/polyfill-mbstring/Mbstring.php b/vendor/symfony/polyfill-mbstring/Mbstring.php index 85a0668..693749f 100644 --- a/vendor/symfony/polyfill-mbstring/Mbstring.php +++ b/vendor/symfony/polyfill-mbstring/Mbstring.php @@ -15,20 +15,27 @@ namespace Symfony\Polyfill\Mbstring; * Partial mbstring implementation in PHP, iconv based, UTF-8 centric. * * Implemented: + * - mb_chr - Returns a specific character from its Unicode code point * - mb_convert_encoding - Convert character encoding * - mb_convert_variables - Convert character code in variable(s) * - mb_decode_mimeheader - Decode string in MIME header field * - mb_encode_mimeheader - Encode string for MIME header XXX NATIVE IMPLEMENTATION IS REALLY BUGGED + * - mb_decode_numericentity - Decode HTML numeric string reference to character + * - mb_encode_numericentity - Encode character to HTML numeric string reference * - mb_convert_case - Perform case folding on a string + * - mb_detect_encoding - Detect character encoding * - mb_get_info - Get internal settings of mbstring * - mb_http_input - Detect HTTP input character encoding * - mb_http_output - Set/Get HTTP output character encoding * - mb_internal_encoding - Set/Get internal character encoding * - mb_list_encodings - Returns an array of all supported encodings + * - mb_ord - Returns the Unicode code point of a character * - mb_output_handler - Callback function converts character encoding in output buffer + * - mb_scrub - Replaces ill-formed byte sequences with substitute characters * - mb_strlen - Get string length * - mb_strpos - Find position of first occurrence of string in a string * - mb_strrpos - Find position of last occurrence of a string in a string + * - mb_str_split - Convert a string to an array * - mb_strtolower - Make a string lowercase * - mb_strtoupper - Make a string uppercase * - mb_substitute_character - Set/Get substitution character @@ -38,14 +45,12 @@ namespace Symfony\Polyfill\Mbstring; * - mb_strrchr - Finds the last occurrence of a character in a string within another * - mb_strrichr - Finds the last occurrence of a character in a string within another, case insensitive * - mb_strripos - Finds position of last occurrence of a string within another, case insensitive - * - mb_strstr - Finds first occurrence of a string within anothers + * - mb_strstr - Finds first occurrence of a string within another * - mb_strwidth - Return width of string * - mb_substr_count - Count the number of substring occurrences * * Not implemented: * - mb_convert_kana - Convert "kana" one from another ("zen-kaku", "han-kaku" and more) - * - mb_decode_numericentity - Decode HTML numeric string reference to character - * - mb_encode_numericentity - Encode character to HTML numeric string reference * - mb_ereg_* - Regular expression with multibyte support * - mb_parse_str - Parse GET/POST/COOKIE data and set global variable * - mb_preferred_mime_name - Get MIME charset string @@ -62,19 +67,20 @@ namespace Symfony\Polyfill\Mbstring; */ final class Mbstring { - const MB_CASE_FOLD = PHP_INT_MAX; + public const MB_CASE_FOLD = \PHP_INT_MAX; + + private const CASE_FOLD = [ + ['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"], + ['μ', 's', 'ι', 'σ', 'β', 'θ', 'φ', 'π', 'κ', 'ρ', 'ε', "\xE1\xB9\xA1", 'ι'], + ]; - private static $encodingList = array('ASCII', 'UTF-8'); + private static $encodingList = ['ASCII', 'UTF-8']; private static $language = 'neutral'; private static $internalEncoding = 'UTF-8'; - private static $caseFold = array( - array('µ','ſ',"\xCD\x85",'ς',"\xCF\x90","\xCF\x91","\xCF\x95","\xCF\x96","\xCF\xB0","\xCF\xB1","\xCF\xB5","\xE1\xBA\x9B","\xE1\xBE\xBE"), - array('μ','s','ι', 'σ','β', 'θ', 'φ', 'π', 'κ', 'ρ', 'ε', "\xE1\xB9\xA1",'ι'), - ); public static function mb_convert_encoding($s, $toEncoding, $fromEncoding = null) { - if (is_array($fromEncoding) || false !== strpos($fromEncoding, ',')) { + if (\is_array($fromEncoding) || ($fromEncoding !== null && false !== strpos($fromEncoding, ','))) { $fromEncoding = self::mb_detect_encoding($s, $fromEncoding); } else { $fromEncoding = self::getEncoding($fromEncoding); @@ -96,27 +102,25 @@ final class Mbstring $fromEncoding = 'Windows-1252'; } if ('UTF-8' !== $fromEncoding) { - $s = iconv($fromEncoding, 'UTF-8', $s); + $s = \iconv($fromEncoding, 'UTF-8//IGNORE', $s); } - return preg_replace_callback('/[\x80-\xFF]+/', array(__CLASS__, 'html_encoding_callback'), $s); + return preg_replace_callback('/[\x80-\xFF]+/', [__CLASS__, 'html_encoding_callback'], $s); } if ('HTML-ENTITIES' === $fromEncoding) { - $s = html_entity_decode($s, ENT_COMPAT, 'UTF-8'); + $s = html_entity_decode($s, \ENT_COMPAT, 'UTF-8'); $fromEncoding = 'UTF-8'; } - return iconv($fromEncoding, $toEncoding, $s); + return \iconv($fromEncoding, $toEncoding.'//IGNORE', $s); } - public static function mb_convert_variables($toEncoding, $fromEncoding, &$a = null, &$b = null, &$c = null, &$d = null, &$e = null, &$f = null) + public static function mb_convert_variables($toEncoding, $fromEncoding, &...$vars) { - $vars = array(&$a, &$b, &$c, &$d, &$e, &$f); - $ok = true; array_walk_recursive($vars, function (&$v) use (&$ok, $toEncoding, $fromEncoding) { - if (false === $v = Mbstring::mb_convert_encoding($v, $toEncoding, $fromEncoding)) { + if (false === $v = self::mb_convert_encoding($v, $toEncoding, $fromEncoding)) { $ok = false; } }); @@ -126,17 +130,148 @@ final class Mbstring public static function mb_decode_mimeheader($s) { - return iconv_mime_decode($s, 2, self::$internalEncoding); + return \iconv_mime_decode($s, 2, self::$internalEncoding); } public static function mb_encode_mimeheader($s, $charset = null, $transferEncoding = null, $linefeed = null, $indent = null) { - trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', E_USER_WARNING); + trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', \E_USER_WARNING); + } + + public static function mb_decode_numericentity($s, $convmap, $encoding = null) + { + if (null !== $s && !is_scalar($s) && !(\is_object($s) && method_exists($s, '__toString'))) { + trigger_error('mb_decode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', \E_USER_WARNING); + + return null; + } + + if (!\is_array($convmap) || (80000 > \PHP_VERSION_ID && !$convmap)) { + return false; + } + + if (null !== $encoding && !is_scalar($encoding)) { + trigger_error('mb_decode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', \E_USER_WARNING); + + return ''; // Instead of null (cf. mb_encode_numericentity). + } + + $s = (string) $s; + if ('' === $s) { + return ''; + } + + $encoding = self::getEncoding($encoding); + + if ('UTF-8' === $encoding) { + $encoding = null; + if (!preg_match('//u', $s)) { + $s = @\iconv('UTF-8', 'UTF-8//IGNORE', $s); + } + } else { + $s = \iconv($encoding, 'UTF-8//IGNORE', $s); + } + + $cnt = floor(\count($convmap) / 4) * 4; + + for ($i = 0; $i < $cnt; $i += 4) { + // collector_decode_htmlnumericentity ignores $convmap[$i + 3] + $convmap[$i] += $convmap[$i + 2]; + $convmap[$i + 1] += $convmap[$i + 2]; + } + + $s = preg_replace_callback('/&#(?:0*([0-9]+)|x0*([0-9a-fA-F]+))(?!&);?/', function (array $m) use ($cnt, $convmap) { + $c = isset($m[2]) ? (int) hexdec($m[2]) : $m[1]; + for ($i = 0; $i < $cnt; $i += 4) { + if ($c >= $convmap[$i] && $c <= $convmap[$i + 1]) { + return self::mb_chr($c - $convmap[$i + 2]); + } + } + + return $m[0]; + }, $s); + + if (null === $encoding) { + return $s; + } + + return \iconv('UTF-8', $encoding.'//IGNORE', $s); + } + + public static function mb_encode_numericentity($s, $convmap, $encoding = null, $is_hex = false) + { + if (null !== $s && !is_scalar($s) && !(\is_object($s) && method_exists($s, '__toString'))) { + trigger_error('mb_encode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', \E_USER_WARNING); + + return null; + } + + if (!\is_array($convmap) || (80000 > \PHP_VERSION_ID && !$convmap)) { + return false; + } + + if (null !== $encoding && !is_scalar($encoding)) { + trigger_error('mb_encode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', \E_USER_WARNING); + + return null; // Instead of '' (cf. mb_decode_numericentity). + } + + if (null !== $is_hex && !is_scalar($is_hex)) { + trigger_error('mb_encode_numericentity() expects parameter 4 to be boolean, '.\gettype($s).' given', \E_USER_WARNING); + + return null; + } + + $s = (string) $s; + if ('' === $s) { + return ''; + } + + $encoding = self::getEncoding($encoding); + + if ('UTF-8' === $encoding) { + $encoding = null; + if (!preg_match('//u', $s)) { + $s = @\iconv('UTF-8', 'UTF-8//IGNORE', $s); + } + } else { + $s = \iconv($encoding, 'UTF-8//IGNORE', $s); + } + + static $ulenMask = ["\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4]; + + $cnt = floor(\count($convmap) / 4) * 4; + $i = 0; + $len = \strlen($s); + $result = ''; + + while ($i < $len) { + $ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"]; + $uchr = substr($s, $i, $ulen); + $i += $ulen; + $c = self::mb_ord($uchr); + + for ($j = 0; $j < $cnt; $j += 4) { + if ($c >= $convmap[$j] && $c <= $convmap[$j + 1]) { + $cOffset = ($c + $convmap[$j + 2]) & $convmap[$j + 3]; + $result .= $is_hex ? sprintf('&#x%X;', $cOffset) : '&#'.$cOffset.';'; + continue 2; + } + } + $result .= $uchr; + } + + if (null === $encoding) { + return $result; + } + + return \iconv('UTF-8', $encoding.'//IGNORE', $result); } public static function mb_convert_case($s, $mode, $encoding = null) { - if ('' === $s .= '') { + $s = (string) $s; + if ('' === $s) { return ''; } @@ -144,15 +279,21 @@ final class Mbstring if ('UTF-8' === $encoding) { $encoding = null; + if (!preg_match('//u', $s)) { + $s = @\iconv('UTF-8', 'UTF-8//IGNORE', $s); + } } else { - $s = iconv($encoding, 'UTF-8', $s); + $s = \iconv($encoding, 'UTF-8//IGNORE', $s); } - if (MB_CASE_TITLE == $mode) { - $s = preg_replace_callback('/\b\p{Ll}/u', array(__CLASS__, 'title_case_upper'), $s); - $s = preg_replace_callback('/\B[\p{Lu}\p{Lt}]+/u', array(__CLASS__, 'title_case_lower'), $s); + if (\MB_CASE_TITLE == $mode) { + static $titleRegexp = null; + if (null === $titleRegexp) { + $titleRegexp = self::getData('titleCaseRegexp'); + } + $s = preg_replace_callback($titleRegexp, [__CLASS__, 'title_case'], $s); } else { - if (MB_CASE_UPPER == $mode) { + if (\MB_CASE_UPPER == $mode) { static $upper = null; if (null === $upper) { $upper = self::getData('upperCase'); @@ -160,7 +301,7 @@ final class Mbstring $map = $upper; } else { if (self::MB_CASE_FOLD === $mode) { - $s = str_replace(self::$caseFold[0], self::$caseFold[1], $s); + $s = str_replace(self::CASE_FOLD[0], self::CASE_FOLD[1], $s); } static $lower = null; @@ -170,10 +311,10 @@ final class Mbstring $map = $lower; } - static $ulenMask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4); + static $ulenMask = ["\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4]; $i = 0; - $len = strlen($s); + $len = \strlen($s); while ($i < $len) { $ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"]; @@ -182,7 +323,7 @@ final class Mbstring if (isset($map[$uchr])) { $uchr = $map[$uchr]; - $nlen = strlen($uchr); + $nlen = \strlen($uchr); if ($nlen == $ulen) { $nlen = $i; @@ -192,7 +333,7 @@ final class Mbstring } else { $s = substr_replace($s, $uchr, $i - $ulen, $ulen); $len += $nlen - $ulen; - $i += $nlen - $ulen; + $i += $nlen - $ulen; } } } @@ -202,7 +343,7 @@ final class Mbstring return $s; } - return iconv('UTF-8', $encoding, $s); + return \iconv('UTF-8', $encoding.'//IGNORE', $s); } public static function mb_internal_encoding($encoding = null) @@ -211,15 +352,19 @@ final class Mbstring return self::$internalEncoding; } - $encoding = self::getEncoding($encoding); + $normalizedEncoding = self::getEncoding($encoding); - if ('UTF-8' === $encoding || false !== @iconv($encoding, $encoding, ' ')) { - self::$internalEncoding = $encoding; + if ('UTF-8' === $normalizedEncoding || false !== @\iconv($normalizedEncoding, $normalizedEncoding, ' ')) { + self::$internalEncoding = $normalizedEncoding; return true; } - return false; + if (80000 > \PHP_VERSION_ID) { + return false; + } + + throw new \ValueError(sprintf('Argument #1 ($encoding) must be a valid encoding, "%s" given', $encoding)); } public static function mb_language($lang = null) @@ -228,20 +373,24 @@ final class Mbstring return self::$language; } - switch ($lang = strtolower($lang)) { + switch ($normalizedLang = strtolower($lang)) { case 'uni': case 'neutral': - self::$language = $lang; + self::$language = $normalizedLang; return true; } - return false; + if (80000 > \PHP_VERSION_ID) { + return false; + } + + throw new \ValueError(sprintf('Argument #1 ($language) must be a valid language, "%s" given', $lang)); } public static function mb_list_encodings() { - return array('UTF-8'); + return ['UTF-8']; } public static function mb_encoding_aliases($encoding) @@ -249,7 +398,7 @@ final class Mbstring switch (strtoupper($encoding)) { case 'UTF8': case 'UTF-8': - return array('utf8'); + return ['utf8']; } return false; @@ -264,7 +413,7 @@ final class Mbstring $encoding = self::$internalEncoding; } - return self::mb_detect_encoding($var, array($encoding)) || false !== @iconv($encoding, $encoding, $var); + return self::mb_detect_encoding($var, [$encoding]) || false !== @\iconv($encoding, $encoding, $var); } public static function mb_detect_encoding($str, $encodingList = null, $strict = false) @@ -272,7 +421,7 @@ final class Mbstring if (null === $encodingList) { $encodingList = self::$encodingList; } else { - if (!is_array($encodingList)) { + if (!\is_array($encodingList)) { $encodingList = array_map('trim', explode(',', $encodingList)); } $encodingList = array_map('strtoupper', $encodingList); @@ -309,7 +458,7 @@ final class Mbstring return self::$encodingList; } - if (!is_array($encodingList)) { + if (!\is_array($encodingList)) { $encodingList = array_map('trim', explode(',', $encodingList)); } $encodingList = array_map('strtoupper', $encodingList); @@ -320,6 +469,7 @@ final class Mbstring if (strncmp($enc, 'ISO-8859-', 9)) { return false; } + // no break case 'ASCII': case 'UTF8': case 'UTF-8': @@ -334,68 +484,140 @@ final class Mbstring public static function mb_strlen($s, $encoding = null) { $encoding = self::getEncoding($encoding); + if ('CP850' === $encoding || 'ASCII' === $encoding) { + return \strlen($s); + } - return iconv_strlen($s, $encoding); + return @\iconv_strlen($s, $encoding); } public static function mb_strpos($haystack, $needle, $offset = 0, $encoding = null) { $encoding = self::getEncoding($encoding); + if ('CP850' === $encoding || 'ASCII' === $encoding) { + return strpos($haystack, $needle, $offset); + } - if ('' === $needle .= '') { - trigger_error(__METHOD__.': Empty delimiter', E_USER_WARNING); + $needle = (string) $needle; + if ('' === $needle) { + if (80000 > \PHP_VERSION_ID) { + trigger_error(__METHOD__.': Empty delimiter', \E_USER_WARNING); - return false; + return false; + } + + return 0; } - return iconv_strpos($haystack, $needle, $offset, $encoding); + return \iconv_strpos($haystack, $needle, $offset, $encoding); } public static function mb_strrpos($haystack, $needle, $offset = 0, $encoding = null) { $encoding = self::getEncoding($encoding); + if ('CP850' === $encoding || 'ASCII' === $encoding) { + return strrpos($haystack, $needle, $offset); + } if ($offset != (int) $offset) { $offset = 0; } elseif ($offset = (int) $offset) { if ($offset < 0) { - $haystack = self::mb_substr($haystack, 0, $offset, $encoding); + if (0 > $offset += self::mb_strlen($needle)) { + $haystack = self::mb_substr($haystack, 0, $offset, $encoding); + } $offset = 0; } else { $haystack = self::mb_substr($haystack, $offset, 2147483647, $encoding); } } - $pos = iconv_strrpos($haystack, $needle, $encoding); + $pos = '' !== $needle || 80000 > \PHP_VERSION_ID + ? \iconv_strrpos($haystack, $needle, $encoding) + : self::mb_strlen($haystack, $encoding); return false !== $pos ? $offset + $pos : false; } + public static function mb_str_split($string, $split_length = 1, $encoding = null) + { + if (null !== $string && !is_scalar($string) && !(\is_object($string) && method_exists($string, '__toString'))) { + trigger_error('mb_str_split() expects parameter 1 to be string, '.\gettype($string).' given', \E_USER_WARNING); + + return null; + } + + if (1 > $split_length = (int) $split_length) { + if (80000 > \PHP_VERSION_ID) { + trigger_error('The length of each segment must be greater than zero', \E_USER_WARNING); + return false; + } + + throw new \ValueError('Argument #2 ($length) must be greater than 0'); + } + + if (null === $encoding) { + $encoding = mb_internal_encoding(); + } + + if ('UTF-8' === $encoding = self::getEncoding($encoding)) { + $rx = '/('; + while (65535 < $split_length) { + $rx .= '.{65535}'; + $split_length -= 65535; + } + $rx .= '.{'.$split_length.'})/us'; + + return preg_split($rx, $string, -1, \PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY); + } + + $result = []; + $length = mb_strlen($string, $encoding); + + for ($i = 0; $i < $length; $i += $split_length) { + $result[] = mb_substr($string, $i, $split_length, $encoding); + } + + return $result; + } + public static function mb_strtolower($s, $encoding = null) { - return self::mb_convert_case($s, MB_CASE_LOWER, $encoding); + return self::mb_convert_case($s, \MB_CASE_LOWER, $encoding); } public static function mb_strtoupper($s, $encoding = null) { - return self::mb_convert_case($s, MB_CASE_UPPER, $encoding); + return self::mb_convert_case($s, \MB_CASE_UPPER, $encoding); } public static function mb_substitute_character($c = null) { + if (null === $c) { + return 'none'; + } if (0 === strcasecmp($c, 'none')) { return true; } + if (80000 > \PHP_VERSION_ID) { + return false; + } + if (\is_int($c) || 'long' === $c || 'entity' === $c) { + return false; + } - return null !== $c ? false : 'none'; + throw new \ValueError('Argument #1 ($substitute_character) must be "none", "long", "entity" or a valid codepoint'); } public static function mb_substr($s, $start, $length = null, $encoding = null) { $encoding = self::getEncoding($encoding); + if ('CP850' === $encoding || 'ASCII' === $encoding) { + return (string) substr($s, $start, null === $length ? 2147483647 : $length); + } if ($start < 0) { - $start = iconv_strlen($s, $encoding) + $start; + $start = \iconv_strlen($s, $encoding) + $start; if ($start < 0) { $start = 0; } @@ -404,13 +626,13 @@ final class Mbstring if (null === $length) { $length = 2147483647; } elseif ($length < 0) { - $length = iconv_strlen($s, $encoding) + $length - $start; + $length = \iconv_strlen($s, $encoding) + $length - $start; if ($length < 0) { return ''; } } - return iconv_substr($s, $start, $length, $encoding).''; + return (string) \iconv_substr($s, $start, $length, $encoding); } public static function mb_stripos($haystack, $needle, $offset = 0, $encoding = null) @@ -431,8 +653,12 @@ final class Mbstring public static function mb_strrchr($haystack, $needle, $part = false, $encoding = null) { $encoding = self::getEncoding($encoding); - $needle = self::mb_substr($needle, 0, 1, $encoding); - $pos = iconv_strrpos($haystack, $needle, $encoding); + if ('CP850' === $encoding || 'ASCII' === $encoding) { + $pos = strrpos($haystack, $needle); + } else { + $needle = self::mb_substr($needle, 0, 1, $encoding); + $pos = \iconv_strrpos($haystack, $needle, $encoding); + } return self::getSubpart($pos, $part, $haystack, $encoding); } @@ -468,7 +694,7 @@ final class Mbstring public static function mb_get_info($type = 'all') { - $info = array( + $info = [ 'internal_encoding' => self::$internalEncoding, 'http_output' => 'pass', 'http_output_conv_mimetypes' => '^(text/|application/xhtml\+xml)', @@ -483,7 +709,7 @@ final class Mbstring 'detect_order' => self::$encodingList, 'substitute_character' => 'none', 'strict_detection' => 'Off', - ); + ]; if ('all' === $type) { return $info; @@ -510,12 +736,12 @@ final class Mbstring $encoding = self::getEncoding($encoding); if ('UTF-8' !== $encoding) { - $s = iconv($encoding, 'UTF-8', $s); + $s = \iconv($encoding, 'UTF-8//IGNORE', $s); } $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, $wide); - return ($wide << 1) + iconv_strlen($s, 'UTF-8'); + return ($wide << 1) + \iconv_strlen($s, 'UTF-8'); } public static function mb_substr_count($haystack, $needle, $encoding = null) @@ -528,6 +754,49 @@ final class Mbstring return $contents; } + public static function mb_chr($code, $encoding = null) + { + if (0x80 > $code %= 0x200000) { + $s = \chr($code); + } elseif (0x800 > $code) { + $s = \chr(0xC0 | $code >> 6).\chr(0x80 | $code & 0x3F); + } elseif (0x10000 > $code) { + $s = \chr(0xE0 | $code >> 12).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F); + } else { + $s = \chr(0xF0 | $code >> 18).\chr(0x80 | $code >> 12 & 0x3F).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F); + } + + if ('UTF-8' !== $encoding = self::getEncoding($encoding)) { + $s = mb_convert_encoding($s, $encoding, 'UTF-8'); + } + + return $s; + } + + public static function mb_ord($s, $encoding = null) + { + if ('UTF-8' !== $encoding = self::getEncoding($encoding)) { + $s = mb_convert_encoding($s, 'UTF-8', $encoding); + } + + if (1 === \strlen($s)) { + return \ord($s); + } + + $code = ($s = unpack('C*', substr($s, 0, 4))) ? $s[1] : 0; + if (0xF0 <= $code) { + return (($code - 0xF0) << 18) + (($s[2] - 0x80) << 12) + (($s[3] - 0x80) << 6) + $s[4] - 0x80; + } + if (0xE0 <= $code) { + return (($code - 0xE0) << 12) + (($s[2] - 0x80) << 6) + $s[3] - 0x80; + } + if (0xC0 <= $code) { + return (($code - 0xC0) << 6) + $s[2] - 0x80; + } + + return $code; + } + private static function getSubpart($pos, $part, $haystack, $encoding) { if (false === $pos) { @@ -540,15 +809,15 @@ final class Mbstring return self::mb_substr($haystack, $pos, null, $encoding); } - private static function html_encoding_callback($m) + private static function html_encoding_callback(array $m) { $i = 1; $entities = ''; - $m = unpack('C*', htmlentities($m[0], ENT_COMPAT, 'UTF-8')); + $m = unpack('C*', htmlentities($m[0], \ENT_COMPAT, 'UTF-8')); while (isset($m[$i])) { if (0x80 > $m[$i]) { - $entities .= chr($m[$i++]); + $entities .= \chr($m[$i++]); continue; } if (0xF0 <= $m[$i]) { @@ -565,14 +834,9 @@ final class Mbstring return $entities; } - private static function title_case_lower($s) + private static function title_case(array $s) { - return self::mb_convert_case($s[0], MB_CASE_LOWER, 'UTF-8'); - } - - private static function title_case_upper($s) - { - return self::mb_convert_case($s[0], MB_CASE_UPPER, 'UTF-8'); + return self::mb_convert_case($s[1], \MB_CASE_UPPER, 'UTF-8').self::mb_convert_case($s[2], \MB_CASE_LOWER, 'UTF-8'); } private static function getData($file) @@ -590,11 +854,16 @@ final class Mbstring return self::$internalEncoding; } + if ('UTF-8' === $encoding) { + return 'UTF-8'; + } + $encoding = strtoupper($encoding); if ('8BIT' === $encoding || 'BINARY' === $encoding) { return 'CP850'; } + if ('UTF8' === $encoding) { return 'UTF-8'; } |