http://git-wip-us.apache.org/repos/asf/airavata-php-gateway/blob/80fd786e/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Mbstring.php ---------------------------------------------------------------------- diff --git a/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Mbstring.php b/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Mbstring.php deleted file mode 100644 index d299c4d..0000000 --- a/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Mbstring.php +++ /dev/null @@ -1,523 +0,0 @@ -<?php // vi: set fenc=utf-8 ts=4 sw=4 et: -/* - * Copyright (C) 2013 Nicolas Grekas - [email protected] - * - * This library is free software; you can redistribute it and/or modify it - * under the terms of the (at your option): - * Apache License v2.0 (http://apache.org/licenses/LICENSE-2.0.txt), or - * GNU General Public License v2.0 (http://gnu.org/licenses/gpl-2.0.txt). - */ - -namespace Patchwork\PHP\Shim; - -/** - * Partial mbstring implementation in PHP, iconv based, UTF-8 centric. - * - * Implemented: - * - mb_convert_encoding - Convert character encoding - * - mb_decode_mimeheader - Decode string in MIME header field - * - mb_encode_mimeheader - Encode string for MIME header XXX NATIVE IMPLEMENTATION IS REALLY BUGGED - * - mb_convert_case - Perform case folding on a string - * - 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_output_handler - Callback function converts character encoding in output buffer - * - 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_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 anothers - * - 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_convert_variables - Convert character code in variable(s) - * - 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 - * - 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 - */ -class Mbstring -{ - const MB_CASE_FOLD = PHP_INT_MAX; - - protected static - - $encoding_list = array('ASCII', 'UTF-8'), - $language = 'neutral', - $internal_encoding = 'UTF-8', - $caseFold = array( - array('µ','Å¿',"\xCD\x85",'Ï',"\xCF\x90","\xCF\x91","\xCF\x95","\xCF\x96","\xCF\xB0","\xCF\xB1","\xCF\xB5","\xE1\xBA\x9B","\xE1\xBE\xBE"), - array('μ','s','ι', 'Ï','β', 'θ', 'Ï', 'Ï', 'κ', 'Ï', 'ε', "\xE1\xB9\xA1",'ι' ) - ); - - - static function mb_convert_encoding($s, $to_encoding, $from_encoding = INF) - { - INF === $from_encoding && $from_encoding = self::$internal_encoding; - - $from_encoding = strtolower($from_encoding); - $to_encoding = strtolower($to_encoding); - - if ('base64' === $from_encoding) - { - $s = base64_decode($s); - $from_encoding = $to_encoding; - } - - if ('base64' === $to_encoding) return base64_encode($s); - - if ('html-entities' === $to_encoding) - { - 'html-entities' === $from_encoding && $from_encoding = 'Windows-1252'; - 'utf-8' === $from_encoding - || 'utf8' === $from_encoding - || $s = iconv($from_encoding, 'UTF-8//IGNORE', $s); - return preg_replace_callback('/[\x80-\xFF]+/', array(__CLASS__, 'html_encoding_callback'), $s); - } - - if ('html-entities' === $from_encoding) - { - $s = html_entity_decode($s, ENT_COMPAT, 'UTF-8'); - $from_encoding = 'UTF-8'; - } - - return iconv($from_encoding, $to_encoding . '//IGNORE', $s); - } - - static function mb_decode_mimeheader($s) - { - return iconv_mime_decode($s, 2, self::$internal_encoding . '//IGNORE'); - } - - static function mb_encode_mimeheader($s, $charset = INF, $transfer_encoding = INF, $linefeed = INF, $indent = INF) - { - user_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', E_USER_WARNING); - } - - - static function mb_convert_case($s, $mode, $encoding = INF) - { - if ('' === $s .= '') return ''; - - if (INF === $encoding) $encoding = self::$internal_encoding; - else $encoding = strtoupper($encoding); - - if ('UTF-8' === $encoding || 'UTF8' === $encoding) $encoding = INF; - else $s = iconv($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); - } - else - { - if (MB_CASE_UPPER == $mode) - { - static $upper; - isset($upper) || $upper = static::getData('upperCase'); - $map = $upper; - } - else - { - if (self::MB_CASE_FOLD === $mode) $s = str_replace(self::$caseFold[0], self::$caseFold[1], $s); - - static $lower; - isset($lower) || $lower = static::getData('lowerCase'); - $map = $lower; - } - - static $ulen_mask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4); - - $i = 0; - $len = strlen($s); - - while ($i < $len) - { - $ulen = $s[$i] < "\x80" ? 1 : $ulen_mask[$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 (INF === $encoding) return $s; - else return iconv('UTF-8', $encoding, $s); - } - - static function mb_internal_encoding($encoding = INF) - { - if (INF === $encoding) return self::$internal_encoding; - else $encoding = strtoupper($encoding); - - if ('UTF-8' === $encoding || 'UTF8' === $encoding || false !== @iconv($encoding, $encoding, ' ')) - { - self::$internal_encoding = 'UTF8' === $encoding ? 'UTF-8' : $encoding; - - return true; - } - - return false; - } - - static function mb_language($lang = INF) - { - if (INF === $lang) return self::$language; - - switch ($lang = strtolower($lang)) - { - case 'uni': - case 'neutral': - self::$language = $lang; - return true; - } - - return false; - } - - static function mb_list_encodings() - { - return array('UTF-8'); - } - - static function mb_encoding_aliases($encoding) - { - switch (strtolower($encoding)) - { - case 'utf8': - case 'utf-8': return array('utf8'); - } - - return false; - } - - static function mb_check_encoding($var = INF, $encoding = INF) - { - if (INF === $encoding) - { - if (INF === $var) return false; - $encoding = self::$internal_encoding; - } - - return false !== mb_detect_encoding($var, array($encoding), true); - } - - static function mb_detect_encoding($str, $encoding_list = INF, $strict = false) - { - if (INF === $encoding_list) $encoding_list = self::$encoding_list; - else - { - if (! is_array($encoding_list)) $encoding_list = array_map('trim', explode(',', $encoding_list)); - $encoding_list = array_map('strtoupper', $encoding_list); - } - - foreach ($encoding_list 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 $enc; - break; - - default: - return strncmp($enc, 'ISO-8859-', 9) ? false : $enc; - } - } - - return false; - } - - static function mb_detect_order($encoding_list = INF) - { - if (INF === $encoding_list) return self::$encoding_list; - - if (! is_array($encoding_list)) $encoding_list = array_map('trim', explode(',', $encoding_list)); - $encoding_list = array_map('strtoupper', $encoding_list); - - foreach ($encoding_list as $enc) - { - switch ($enc) - { - default: if (strncmp($enc, 'ISO-8859-', 9)) return false; - case 'ASCII': - case 'UTF8': - case 'UTF-8': - } - } - - self::$encoding_list = $encoding_list; - - return true; - } - - static function mb_strlen($s, $encoding = INF) - { - INF === $encoding && $encoding = self::$internal_encoding; - return iconv_strlen($s, $encoding . '//IGNORE'); - } - - static function mb_strpos($haystack, $needle, $offset = 0, $encoding = INF) - { - INF === $encoding && $encoding = self::$internal_encoding; - if ('' === $needle .= '') - { - user_error(__METHOD__ . ': Empty delimiter', E_USER_WARNING); - return false; - } - else return iconv_strpos($haystack, $needle, $offset, $encoding . '//IGNORE'); - } - - static function mb_strrpos($haystack, $needle, $offset = 0, $encoding = INF) - { - INF === $encoding && $encoding = self::$internal_encoding; - - if ($offset != (int) $offset) - { - $offset = 0; - } - else if ($offset = (int) $offset) - { - $haystack = self::mb_substr($haystack, $offset, 2147483647, $encoding); - } - - $pos = iconv_strrpos($haystack, $needle, $encoding . '//IGNORE'); - - return false !== $pos ? $offset + $pos : false; - } - - static function mb_strtolower($s, $encoding = INF) - { - return self::mb_convert_case($s, MB_CASE_LOWER, $encoding); - } - - static function mb_strtoupper($s, $encoding = INF) - { - return self::mb_convert_case($s, MB_CASE_UPPER, $encoding); - } - - static function mb_substitute_character($c = INF) - { - return INF !== $c ? false : 'none'; - } - - static function mb_substr($s, $start, $length = null, $encoding = INF) - { - INF === $encoding && $encoding = self::$internal_encoding; - - if ($start < 0) - { - $start = iconv_strlen($s, $encoding . '//IGNORE') + $start; - if ($start < 0) $start = 0; - } - - if (null === $length) $length = 2147483647; - else if ($length < 0) - { - $length = iconv_strlen($s, $encoding . '//IGNORE') + $length - $start; - if ($length < 0) return ''; - } - - return iconv_substr($s, $start, $length, $encoding . '//IGNORE') . ''; - } - - static function mb_stripos($haystack, $needle, $offset = 0, $encoding = INF) - { - INF === $encoding && $encoding = self::$internal_encoding; - $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding); - $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding); - return self::mb_strpos($haystack, $needle, $offset, $encoding); - } - - static function mb_stristr($haystack, $needle, $part = false, $encoding = INF) - { - $pos = self::mb_stripos($haystack, $needle, 0, $encoding); - return self::getSubpart($pos, $part, $haystack, $encoding); - } - - static function mb_strrchr($haystack, $needle, $part = false, $encoding = INF) - { - INF === $encoding && $encoding = self::$internal_encoding; - $needle = self::mb_substr($needle, 0, 1, $encoding); - $pos = iconv_strrpos($haystack, $needle, $encoding); - return self::getSubpart($pos, $part, $haystack, $encoding); - } - - static function mb_strrichr($haystack, $needle, $part = false, $encoding = INF) - { - $needle = self::mb_substr($needle, 0, 1, $encoding); - $pos = self::mb_strripos($haystack, $needle, $encoding); - return self::getSubpart($pos, $part, $haystack, $encoding); - } - - static function mb_strripos($haystack, $needle, $offset = 0, $encoding = INF) - { - INF === $encoding && $encoding = self::$internal_encoding; - $haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding); - $needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding); - return self::mb_strrpos($haystack, $needle, $offset, $encoding); - } - - static function mb_strstr($haystack, $needle, $part = false, $encoding = INF) - { - $pos = strpos($haystack, $needle); - if (false === $pos) return false; - if ($part) return substr($haystack, 0, $pos); - else return substr($haystack, $pos); - } - - static function mb_get_info($type = 'all') - { - $info = array( - 'internal_encoding' => self::$internal_encoding, - '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::$language, - 'detect_order' => self::$encoding_list, - 'substitute_character' => 'none', - 'strict_detection' => 'Off', - ); - - if ('all' === $type) { - return $info; - } elseif (isset($info[$type])) { - return $info[$type]; - } else { - return false; - } - } - - static function mb_http_input($type = '') - { - return false; - } - - static function mb_http_output($encoding = INF) - { - return INF !== $encoding ? 'pass' === $encoding : 'pass'; - } - - static function mb_strwidth($s, $encoding = INF) - { - $encoding = INF === $encoding ? self::$internal_encoding : strtoupper($encoding); - - if ('UTF-8' !== $encoding && 'UTF8' !== $encoding) { - $s = iconv($encoding, 'UTF-8//IGNORE', $s); - } - - $s = preg_replace('/[\x00-\x19]/', '', $s); - - preg_replace('/[\x{0020}-\x{1FFF}\x{FF61}-\x{FF9F}]/u', '', $s, -1, $narrow); - - return (iconv_strlen($s, 'UTF-8') << 1) - $narrow; - } - - static function mb_substr_count($haystack, $needle, $encoding = INF) - { - return substr_count($haystack, $needle); - } - - static function mb_output_handler($contents, $status) - { - return $contents; - } - - protected static function getSubpart($pos, $part, $haystack, $encoding) - { - INF === $encoding && $encoding = self::$internal_encoding; - - if (false === $pos) return false; - if ($part) return self::mb_substr($haystack, 0, $pos, $encoding); - else return self::mb_substr($haystack, $pos, null, $encoding); - } - - protected static function html_encoding_callback($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 $entities; - } - - protected static function title_case_lower($s) - { - return self::mb_convert_case($s[0], MB_CASE_LOWER, 'UTF-8'); - } - - protected static function title_case_upper($s) - { - return self::mb_convert_case($s[0], MB_CASE_UPPER, 'UTF-8'); - } - - protected static function getData($file) - { - $file = __DIR__ . '/unidata/' . $file . '.ser'; - if (file_exists($file)) return unserialize(file_get_contents($file)); - else return false; - } -}
http://git-wip-us.apache.org/repos/asf/airavata-php-gateway/blob/80fd786e/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Normalizer.php ---------------------------------------------------------------------- diff --git a/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Normalizer.php b/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Normalizer.php deleted file mode 100644 index c296470..0000000 --- a/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Normalizer.php +++ /dev/null @@ -1,295 +0,0 @@ -<?php // vi: set fenc=utf-8 ts=4 sw=4 et: -/* - * Copyright (C) 2013 Nicolas Grekas - [email protected] - * - * This library is free software; you can redistribute it and/or modify it - * under the terms of the (at your option): - * Apache License v2.0 (http://apache.org/licenses/LICENSE-2.0.txt), or - * GNU General Public License v2.0 (http://gnu.org/licenses/gpl-2.0.txt). - */ - -namespace Patchwork\PHP\Shim; - -/** - * Normalizer is a PHP fallback implementation of the Normalizer class provided by the intl extension. - * - * It has been validated with Unicode 6.3 Normalization Conformance Test. - * See http://www.unicode.org/reports/tr15/ for detailed info about Unicode normalizations. - */ -class Normalizer -{ - const - - NONE = 1, - FORM_D = 2, NFD = 2, - FORM_KD = 3, NFKD = 3, - FORM_C = 4, NFC = 4, - FORM_KC = 5, NFKC = 5; - - - protected static - - $C, $D, $KD, $cC, - $ulen_mask = array("\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4), - $ASCII = "\x20\x65\x69\x61\x73\x6E\x74\x72\x6F\x6C\x75\x64\x5D\x5B\x63\x6D\x70\x27\x0A\x67\x7C\x68\x76\x2E\x66\x62\x2C\x3A\x3D\x2D\x71\x31\x30\x43\x32\x2A\x79\x78\x29\x28\x4C\x39\x41\x53\x2F\x50\x22\x45\x6A\x4D\x49\x6B\x33\x3E\x35\x54\x3C\x44\x34\x7D\x42\x7B\x38\x46\x77\x52\x36\x37\x55\x47\x4E\x3B\x4A\x7A\x56\x23\x48\x4F\x57\x5F\x26\x21\x4B\x3F\x58\x51\x25\x59\x5C\x09\x5A\x2B\x7E\x5E\x24\x40\x60\x7F\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0B\x0C\x0D\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F"; - - - static function isNormalized($s, $form = self::NFC) - { - if (strspn($s .= '', self::$ASCII) === strlen($s)) return true; - if (self::NFC === $form && preg_match('//u', $s) && !preg_match('/[^\x00-\x{2FF}]/u', $s)) return true; - return false; // Pretend false as quick checks implementented in PHP won't be so quick - } - - static function normalize($s, $form = self::NFC) - { - if (!preg_match('//u', $s .= '')) return false; - - switch ($form) - { - case self::NONE: return $s; - case self::NFC: $C = true; $K = false; break; - case self::NFD: $C = false; $K = false; break; - case self::NFKC: $C = true; $K = true; break; - case self::NFKD: $C = false; $K = true; break; - default: return false; - } - - if ('' === $s) return ''; - - if ($K && empty(self::$KD)) self::$KD = static::getData('compatibilityDecomposition'); - - if (empty(self::$D)) - { - self::$D = static::getData('canonicalDecomposition'); - self::$cC = static::getData('combiningClass'); - } - - if ($C) - { - if (empty(self::$C)) self::$C = static::getData('canonicalComposition'); - return self::recompose(self::decompose($s, $K)); - } - else return self::decompose($s, $K); - } - - protected static function recompose($s) - { - $ASCII = self::$ASCII; - $compMap = self::$C; - $combClass = self::$cC; - $ulen_mask = self::$ulen_mask; - - $result = $tail = ''; - - $i = $s[0] < "\x80" ? 1 : $ulen_mask[$s[0] & "\xF0"]; - $len = strlen($s); - - $last_uchr = substr($s, 0, $i); - $last_ucls = isset($combClass[$last_uchr]) ? 256 : 0; - - while ($i < $len) - { - if ($s[$i] < "\x80") - { - // ASCII chars - - if ($tail) - { - $last_uchr .= $tail; - $tail = ''; - } - - if ($j = strspn($s, $ASCII, $i+1)) - { - $last_uchr .= substr($s, $i, $j); - $i += $j; - } - - $result .= $last_uchr; - $last_uchr = $s[$i]; - ++$i; - } - else - { - $ulen = $ulen_mask[$s[$i] & "\xF0"]; - $uchr = substr($s, $i, $ulen); - - if ($last_uchr < "\xE1\x84\x80" || "\xE1\x84\x92" < $last_uchr - || $uchr < "\xE1\x85\xA1" || "\xE1\x85\xB5" < $uchr - || $last_ucls) - { - // Table lookup and combining chars composition - - $ucls = isset($combClass[$uchr]) ? $combClass[$uchr] : 0; - - if (isset($compMap[$last_uchr . $uchr]) && (!$last_ucls || $last_ucls < $ucls)) - { - $last_uchr = $compMap[$last_uchr . $uchr]; - } - else if ($last_ucls = $ucls) $tail .= $uchr; - else - { - if ($tail) - { - $last_uchr .= $tail; - $tail = ''; - } - - $result .= $last_uchr; - $last_uchr = $uchr; - } - } - else - { - // Hangul chars - - $L = ord($last_uchr[2]) - 0x80; - $V = ord($uchr[2]) - 0xA1; - $T = 0; - - $uchr = substr($s, $i + $ulen, 3); - - if ("\xE1\x86\xA7" <= $uchr && $uchr <= "\xE1\x87\x82") - { - $T = ord($uchr[2]) - 0xA7; - 0 > $T && $T += 0x40; - $ulen += 3; - } - - $L = 0xAC00 + ($L * 21 + $V) * 28 + $T; - $last_uchr = chr(0xE0 | $L>>12) . chr(0x80 | $L>>6 & 0x3F) . chr(0x80 | $L & 0x3F); - } - - $i += $ulen; - } - } - - return $result . $last_uchr . $tail; - } - - protected static function decompose($s, $c) - { - $result = ''; - - $ASCII = self::$ASCII; - $decompMap = self::$D; - $combClass = self::$cC; - $ulen_mask = self::$ulen_mask; - if ($c) $compatMap = self::$KD; - - $c = array(); - $i = 0; - $len = strlen($s); - - while ($i < $len) - { - if ($s[$i] < "\x80") - { - // ASCII chars - - if ($c) - { - ksort($c); - $result .= implode('', $c); - $c = array(); - } - - $j = 1 + strspn($s, $ASCII, $i+1); - $result .= substr($s, $i, $j); - $i += $j; - } - else - { - $ulen = $ulen_mask[$s[$i] & "\xF0"]; - $uchr = substr($s, $i, $ulen); - $i += $ulen; - - if (isset($combClass[$uchr])) - { - // Combining chars, for sorting - - isset($c[$combClass[$uchr]]) || $c[$combClass[$uchr]] = ''; - $c[$combClass[$uchr]] .= isset($compatMap[$uchr]) ? $compatMap[$uchr] : (isset($decompMap[$uchr]) ? $decompMap[$uchr] : $uchr); - } - else - { - if ($c) - { - ksort($c); - $result .= implode('', $c); - $c = array(); - } - - if ($uchr < "\xEA\xB0\x80" || "\xED\x9E\xA3" < $uchr) - { - // Table lookup - - $j = isset($compatMap[$uchr]) ? $compatMap[$uchr] : (isset($decompMap[$uchr]) ? $decompMap[$uchr] : $uchr); - - if ($uchr != $j) - { - $uchr = $j; - - $j = strlen($uchr); - $ulen = $uchr[0] < "\x80" ? 1 : $ulen_mask[$uchr[0] & "\xF0"]; - - if ($ulen != $j) - { - // Put trailing chars in $s - - $j -= $ulen; - $i -= $j; - - if (0 > $i) - { - $s = str_repeat(' ', -$i) . $s; - $len -= $i; - $i = 0; - } - - while ($j--) $s[$i+$j] = $uchr[$ulen+$j]; - - $uchr = substr($uchr, 0, $ulen); - } - } - } - else - { - // Hangul chars - - $uchr = unpack('C*', $uchr); - $j = (($uchr[1]-224) << 12) + (($uchr[2]-128) << 6) + $uchr[3] - 0xAC80; - - $uchr = "\xE1\x84" . chr(0x80 + (int) ($j / 588)) - . "\xE1\x85" . chr(0xA1 + (int) (($j % 588) / 28)); - - if ($j %= 28) - { - $uchr .= $j < 25 - ? ("\xE1\x86" . chr(0xA7 + $j)) - : ("\xE1\x87" . chr(0x67 + $j)); - } - } - - $result .= $uchr; - } - } - } - - if ($c) - { - ksort($c); - $result .= implode('', $c); - } - - return $result; - } - - protected static function getData($file) - { - $file = __DIR__ . '/unidata/' . $file . '.ser'; - if (file_exists($file)) return unserialize(file_get_contents($file)); - else return false; - } -} http://git-wip-us.apache.org/repos/asf/airavata-php-gateway/blob/80fd786e/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Xml.php ---------------------------------------------------------------------- diff --git a/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Xml.php b/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Xml.php deleted file mode 100644 index 6a44df8..0000000 --- a/vendor/patchwork/utf8/class/Patchwork/PHP/Shim/Xml.php +++ /dev/null @@ -1,61 +0,0 @@ -<?php // vi: set fenc=utf-8 ts=4 sw=4 et: -/* - * Copyright (C) 2013 Nicolas Grekas - [email protected] - * - * This library is free software; you can redistribute it and/or modify it - * under the terms of the (at your option): - * Apache License v2.0 (http://apache.org/licenses/LICENSE-2.0.txt), or - * GNU General Public License v2.0 (http://gnu.org/licenses/gpl-2.0.txt). - */ - -namespace Patchwork\PHP\Shim; - -/** - * utf8_encode/decode - */ -class Xml -{ - static function utf8_encode($s) - { - $s .= $s; - $len = strlen($s); - - for ($i = $len >> 1, $j = 0; $i < $len; ++$i, ++$j) switch (true) - { - case $s[$i] < "\x80": $s[$j] = $s[$i]; break; - case $s[$i] < "\xC0": $s[$j] = "\xC2"; $s[++$j] = $s[$i]; break; - default: $s[$j] = "\xC3"; $s[++$j] = chr(ord($s[$i]) - 64); break; - } - - return substr($s, 0, $j); - } - - static function utf8_decode($s) - { - $s .= ''; - $len = strlen($s); - - for ($i = 0, $j = 0; $i < $len; ++$i, ++$j) - { - switch ($s[$i] & "\xF0") - { - case "\xC0": - case "\xD0": - $c = (ord($s[$i] & "\x1F") << 6) | ord($s[++$i] & "\x3F"); - $s[$j] = $c < 256 ? chr($c) : '?'; - break; - - case "\xF0": ++$i; - case "\xE0": - $s[$j] = '?'; - $i += 2; - break; - - default: - $s[$j] = $s[$i]; - } - } - - return substr($s, 0, $j); - } -}
