123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847 |
- <?php
- /*
- * This file is part of the Symfony package.
- *
- * (c) Fabien Potencier <fabien@symfony.com>
- *
- * For the full copyright and license information, please view the LICENSE
- * file that was distributed with this source code.
- */
- 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
- * - mb_substr - Get part of string
- * - mb_stripos - Finds position of first occurrence of a string within another, case insensitive
- * - mb_stristr - Finds first occurrence of a string within another, case insensitive
- * - 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 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_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
- * - mb_regex_encoding - Returns current encoding for multibyte regex as string
- * - mb_regex_set_options - Set/Get the default options for mbregex functions
- * - mb_send_mail - Send encoded mail
- * - mb_split - Split multibyte string using regular expression
- * - mb_strcut - Get part of string
- * - mb_strimwidth - Get truncated string with specified width
- *
- * @author Nicolas Grekas <p@tchwork.com>
- *
- * @internal
- */
- final class Mbstring
- {
- const MB_CASE_FOLD = PHP_INT_MAX;
- private static $encodingList = array('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, ',')) {
- $fromEncoding = self::mb_detect_encoding($s, $fromEncoding);
- } else {
- $fromEncoding = self::getEncoding($fromEncoding);
- }
- $toEncoding = self::getEncoding($toEncoding);
- if ('BASE64' === $fromEncoding) {
- $s = base64_decode($s);
- $fromEncoding = $toEncoding;
- }
- if ('BASE64' === $toEncoding) {
- return base64_encode($s);
- }
- if ('HTML-ENTITIES' === $toEncoding || 'HTML' === $toEncoding) {
- if ('HTML-ENTITIES' === $fromEncoding || 'HTML' === $fromEncoding) {
- $fromEncoding = 'Windows-1252';
- }
- if ('UTF-8' !== $fromEncoding) {
- $s = iconv($fromEncoding, 'UTF-8//IGNORE', $s);
- }
- return preg_replace_callback('/[\x80-\xFF]+/', array(__CLASS__, 'html_encoding_callback'), $s);
- }
- if ('HTML-ENTITIES' === $fromEncoding) {
- $s = html_entity_decode($s, ENT_COMPAT, 'UTF-8');
- $fromEncoding = 'UTF-8';
- }
- return iconv($fromEncoding, $toEncoding.'//IGNORE', $s);
- }
- public static function mb_convert_variables($toEncoding, $fromEncoding, &$a = null, &$b = null, &$c = null, &$d = null, &$e = null, &$f = null)
- {
- $vars = array(&$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)) {
- $ok = false;
- }
- });
- return $ok ? $fromEncoding : false;
- }
- public static function mb_decode_mimeheader($s)
- {
- return iconv_mime_decode($s, 2, self::$internalEncoding);
- }
- public static function mb_encode_mimeheader($s, $charset = null, $transferEncoding = null, $linefeed = null, $indent = null)
- {
- trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', E_USER_WARNING);
- }
- public static function mb_decode_numericentity($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) || !$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 Mbstring::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) || !$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 = array("\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)
- {
- $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);
- }
- if (MB_CASE_TITLE == $mode) {
- static $titleRegexp = null;
- if (null === $titleRegexp) {
- $titleRegexp = self::getData('titleCaseRegexp');
- }
- $s = preg_replace_callback($titleRegexp, array(__CLASS__, 'title_case'), $s);
- } else {
- if (MB_CASE_UPPER == $mode) {
- static $upper = null;
- if (null === $upper) {
- $upper = self::getData('upperCase');
- }
- $map = $upper;
- } else {
- if (self::MB_CASE_FOLD === $mode) {
- $s = str_replace(self::$caseFold[0], self::$caseFold[1], $s);
- }
- static $lower = null;
- if (null === $lower) {
- $lower = self::getData('lowerCase');
- }
- $map = $lower;
- }
- static $ulenMask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4);
- $i = 0;
- $len = \strlen($s);
- while ($i < $len) {
- $ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"];
- $uchr = substr($s, $i, $ulen);
- $i += $ulen;
- if (isset($map[$uchr])) {
- $uchr = $map[$uchr];
- $nlen = \strlen($uchr);
- if ($nlen == $ulen) {
- $nlen = $i;
- do {
- $s[--$nlen] = $uchr[--$ulen];
- } while ($ulen);
- } else {
- $s = substr_replace($s, $uchr, $i - $ulen, $ulen);
- $len += $nlen - $ulen;
- $i += $nlen - $ulen;
- }
- }
- }
- }
- if (null === $encoding) {
- return $s;
- }
- return iconv('UTF-8', $encoding.'//IGNORE', $s);
- }
- public static function mb_internal_encoding($encoding = null)
- {
- if (null === $encoding) {
- return self::$internalEncoding;
- }
- $encoding = self::getEncoding($encoding);
- if ('UTF-8' === $encoding || false !== @iconv($encoding, $encoding, ' ')) {
- self::$internalEncoding = $encoding;
- return true;
- }
- return false;
- }
- public static function mb_language($lang = null)
- {
- if (null === $lang) {
- return self::$language;
- }
- switch ($lang = strtolower($lang)) {
- case 'uni':
- case 'neutral':
- self::$language = $lang;
- return true;
- }
- return false;
- }
- public static function mb_list_encodings()
- {
- return array('UTF-8');
- }
- public static function mb_encoding_aliases($encoding)
- {
- switch (strtoupper($encoding)) {
- case 'UTF8':
- case 'UTF-8':
- return array('utf8');
- }
- return false;
- }
- public static function mb_check_encoding($var = null, $encoding = null)
- {
- if (null === $encoding) {
- if (null === $var) {
- return false;
- }
- $encoding = self::$internalEncoding;
- }
- return self::mb_detect_encoding($var, array($encoding)) || false !== @iconv($encoding, $encoding, $var);
- }
- public static function mb_detect_encoding($str, $encodingList = null, $strict = false)
- {
- if (null === $encodingList) {
- $encodingList = self::$encodingList;
- } else {
- if (!\is_array($encodingList)) {
- $encodingList = array_map('trim', explode(',', $encodingList));
- }
- $encodingList = array_map('strtoupper', $encodingList);
- }
- foreach ($encodingList as $enc) {
- switch ($enc) {
- case 'ASCII':
- if (!preg_match('/[\x80-\xFF]/', $str)) {
- return $enc;
- }
- break;
- case 'UTF8':
- case 'UTF-8':
- if (preg_match('//u', $str)) {
- return 'UTF-8';
- }
- break;
- default:
- if (0 === strncmp($enc, 'ISO-8859-', 9)) {
- return $enc;
- }
- }
- }
- return false;
- }
- public static function mb_detect_order($encodingList = null)
- {
- if (null === $encodingList) {
- return self::$encodingList;
- }
- if (!\is_array($encodingList)) {
- $encodingList = array_map('trim', explode(',', $encodingList));
- }
- $encodingList = array_map('strtoupper', $encodingList);
- foreach ($encodingList as $enc) {
- switch ($enc) {
- default:
- if (strncmp($enc, 'ISO-8859-', 9)) {
- return false;
- }
- // no break
- case 'ASCII':
- case 'UTF8':
- case 'UTF-8':
- }
- }
- self::$encodingList = $encodingList;
- return true;
- }
- public static function mb_strlen($s, $encoding = null)
- {
- $encoding = self::getEncoding($encoding);
- if ('CP850' === $encoding || 'ASCII' === $encoding) {
- return \strlen($s);
- }
- return @iconv_strlen($s, $encoding);
- }
- public static function mb_strpos($haystack, $needle, $offset = 0, $encoding = null)
- {
- $encoding = self::getEncoding($encoding);
- if ('CP850' === $encoding || 'ASCII' === $encoding) {
- return strpos($haystack, $needle, $offset);
- }
- $needle = (string) $needle;
- if ('' === $needle) {
- trigger_error(__METHOD__.': Empty delimiter', E_USER_WARNING);
- return false;
- }
- return iconv_strpos($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) {
- 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);
- 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) {
- trigger_error('The length of each segment must be greater than zero', E_USER_WARNING);
- return false;
- }
- 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, null, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY);
- }
- $result = array();
- $length = mb_strlen($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, $encoding);
- }
- public static function mb_strtoupper($s, $encoding = null)
- {
- return self::mb_convert_case($s, MB_CASE_UPPER, $encoding);
- }
- public static function mb_substitute_character($c = null)
- {
- if (0 === strcasecmp($c, 'none')) {
- return true;
- }
- return null !== $c ? false : 'none';
- }
- public static function mb_substr($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) + $start;
- if ($start < 0) {
- $start = 0;
- }
- }
- if (null === $length) {
- $length = 2147483647;
- } elseif ($length < 0) {
- $length = iconv_strlen($s, $encoding) + $length - $start;
- if ($length < 0) {
- return '';
- }
- }
- return (string) iconv_substr($s, $start, $length, $encoding);
- }
- public static function mb_stripos($haystack, $needle, $offset = 0, $encoding = null)
- {
- $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
- $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);
- return self::mb_strpos($haystack, $needle, $offset, $encoding);
- }
- public static function mb_stristr($haystack, $needle, $part = false, $encoding = null)
- {
- $pos = self::mb_stripos($haystack, $needle, 0, $encoding);
- return self::getSubpart($pos, $part, $haystack, $encoding);
- }
- public static function mb_strrchr($haystack, $needle, $part = false, $encoding = null)
- {
- $encoding = self::getEncoding($encoding);
- if ('CP850' === $encoding || 'ASCII' === $encoding) {
- return strrchr($haystack, $needle, $part);
- }
- $needle = self::mb_substr($needle, 0, 1, $encoding);
- $pos = iconv_strrpos($haystack, $needle, $encoding);
- return self::getSubpart($pos, $part, $haystack, $encoding);
- }
- public static function mb_strrichr($haystack, $needle, $part = false, $encoding = null)
- {
- $needle = self::mb_substr($needle, 0, 1, $encoding);
- $pos = self::mb_strripos($haystack, $needle, $encoding);
- return self::getSubpart($pos, $part, $haystack, $encoding);
- }
- public static function mb_strripos($haystack, $needle, $offset = 0, $encoding = null)
- {
- $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
- $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);
- return self::mb_strrpos($haystack, $needle, $offset, $encoding);
- }
- public static function mb_strstr($haystack, $needle, $part = false, $encoding = null)
- {
- $pos = strpos($haystack, $needle);
- if (false === $pos) {
- return false;
- }
- if ($part) {
- return substr($haystack, 0, $pos);
- }
- return substr($haystack, $pos);
- }
- public static function mb_get_info($type = 'all')
- {
- $info = array(
- 'internal_encoding' => self::$internalEncoding,
- 'http_output' => 'pass',
- 'http_output_conv_mimetypes' => '^(text/|application/xhtml\+xml)',
- 'func_overload' => 0,
- 'func_overload_list' => 'no overload',
- 'mail_charset' => 'UTF-8',
- 'mail_header_encoding' => 'BASE64',
- 'mail_body_encoding' => 'BASE64',
- 'illegal_chars' => 0,
- 'encoding_translation' => 'Off',
- 'language' => self::$language,
- 'detect_order' => self::$encodingList,
- 'substitute_character' => 'none',
- 'strict_detection' => 'Off',
- );
- if ('all' === $type) {
- return $info;
- }
- if (isset($info[$type])) {
- return $info[$type];
- }
- return false;
- }
- public static function mb_http_input($type = '')
- {
- return false;
- }
- public static function mb_http_output($encoding = null)
- {
- return null !== $encoding ? 'pass' === $encoding : 'pass';
- }
- public static function mb_strwidth($s, $encoding = null)
- {
- $encoding = self::getEncoding($encoding);
- if ('UTF-8' !== $encoding) {
- $s = iconv($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($s, 'UTF-8');
- }
- public static function mb_substr_count($haystack, $needle, $encoding = null)
- {
- return substr_count($haystack, $needle);
- }
- public static function mb_output_handler($contents, $status)
- {
- 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 === $pos) {
- return false;
- }
- if ($part) {
- return self::mb_substr($haystack, 0, $pos, $encoding);
- }
- return self::mb_substr($haystack, $pos, null, $encoding);
- }
- private static function html_encoding_callback(array $m)
- {
- $i = 1;
- $entities = '';
- $m = unpack('C*', htmlentities($m[0], ENT_COMPAT, 'UTF-8'));
- while (isset($m[$i])) {
- if (0x80 > $m[$i]) {
- $entities .= \chr($m[$i++]);
- continue;
- }
- if (0xF0 <= $m[$i]) {
- $c = (($m[$i++] - 0xF0) << 18) + (($m[$i++] - 0x80) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
- } elseif (0xE0 <= $m[$i]) {
- $c = (($m[$i++] - 0xE0) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
- } else {
- $c = (($m[$i++] - 0xC0) << 6) + $m[$i++] - 0x80;
- }
- $entities .= '&#'.$c.';';
- }
- return $entities;
- }
- private static function title_case(array $s)
- {
- return self::mb_convert_case($s[1], MB_CASE_UPPER, 'UTF-8').self::mb_convert_case($s[2], MB_CASE_LOWER, 'UTF-8');
- }
- private static function getData($file)
- {
- if (file_exists($file = __DIR__.'/Resources/unidata/'.$file.'.php')) {
- return require $file;
- }
- return false;
- }
- private static function getEncoding($encoding)
- {
- if (null === $encoding) {
- return self::$internalEncoding;
- }
- if ('UTF-8' === $encoding) {
- return 'UTF-8';
- }
- $encoding = strtoupper($encoding);
- if ('8BIT' === $encoding || 'BINARY' === $encoding) {
- return 'CP850';
- }
- if ('UTF8' === $encoding) {
- return 'UTF-8';
- }
- return $encoding;
- }
- }
|