| @@ -1,1218 +1,0 @@ | ||
| 1 | -<?php | |
| 2 | - | |
| 3 | -/** | |
| 4 | - * +-----------------------------------------------------------------------+ | |
| 5 | - * | This file is part of the Roundcube Webmail client | | |
| 6 | - * | | | |
| 7 | - * | Copyright (C) The Roundcube Dev Team | | |
| 8 | - * | Copyright (C) Kolab Systems AG | | |
| 9 | - * | Copyright (C) 2000 Edmund Grimley Evans <[email protected]> | | |
| 10 | - * | | | |
| 11 | - * | Licensed under the GNU General Public License version 3 or | | |
| 12 | - * | any later version with exceptions for skins & plugins. | | |
| 13 | - * | See the README file for a full license statement. | | |
| 14 | - * | | | |
| 15 | - * | PURPOSE: | | |
| 16 | - * | Provide charset conversion functionality | | |
| 17 | - * +-----------------------------------------------------------------------+ | |
| 18 | - * | Author: Thomas Bruederli <[email protected]> | | |
| 19 | - * | Author: Aleksander Machniak <[email protected]> | | |
| 20 | - * | Author: Edmund Grimley Evans <[email protected]> | | |
| 21 | - * +-----------------------------------------------------------------------+ | |
| 22 | - */ | |
| 23 | - | |
| 24 | -namespace AcyMailing\Libraries\Imap2\Roundcube; | |
| 25 | - | |
| 26 | -/** | |
| 27 | - * Character sets conversion functionality | |
| 28 | - * | |
| 29 | - * @package Framework | |
| 30 | - * @subpackage Core | |
| 31 | - */ | |
| 32 | -class Charset | |
| 33 | -{ | |
| 34 | - // Aliases: some of them from HTML5 spec. | |
| 35 | - static public $aliases = [ | |
| 36 | - 'USASCII' => 'WINDOWS-1252', | |
| 37 | - 'ANSIX31101983' => 'WINDOWS-1252', | |
| 38 | - 'ANSIX341968' => 'WINDOWS-1252', | |
| 39 | - 'UNKNOWN8BIT' => 'ISO-8859-15', | |
| 40 | - 'UNKNOWN' => 'ISO-8859-15', | |
| 41 | - 'USERDEFINED' => 'ISO-8859-15', | |
| 42 | - 'KSC56011987' => 'EUC-KR', | |
| 43 | - 'GB2312' => 'GBK', | |
| 44 | - 'GB231280' => 'GBK', | |
| 45 | - 'UNICODE' => 'UTF-8', | |
| 46 | - 'UTF7IMAP' => 'UTF7-IMAP', | |
| 47 | - 'TIS620' => 'WINDOWS-874', | |
| 48 | - 'ISO88599' => 'WINDOWS-1254', | |
| 49 | - 'ISO885911' => 'WINDOWS-874', | |
| 50 | - 'MACROMAN' => 'MACINTOSH', | |
| 51 | - '77' => 'MAC', | |
| 52 | - '128' => 'SHIFT-JIS', | |
| 53 | - '129' => 'CP949', | |
| 54 | - '130' => 'CP1361', | |
| 55 | - '134' => 'GBK', | |
| 56 | - '136' => 'BIG5', | |
| 57 | - '161' => 'WINDOWS-1253', | |
| 58 | - '162' => 'WINDOWS-1254', | |
| 59 | - '163' => 'WINDOWS-1258', | |
| 60 | - '177' => 'WINDOWS-1255', | |
| 61 | - '178' => 'WINDOWS-1256', | |
| 62 | - '186' => 'WINDOWS-1257', | |
| 63 | - '204' => 'WINDOWS-1251', | |
| 64 | - '222' => 'WINDOWS-874', | |
| 65 | - '238' => 'WINDOWS-1250', | |
| 66 | - 'MS950' => 'CP950', | |
| 67 | - 'WINDOWS949' => 'UHC', | |
| 68 | - ]; | |
| 69 | - | |
| 70 | - /** | |
| 71 | - * Windows codepages | |
| 72 | - * | |
| 73 | - * @var array | |
| 74 | - */ | |
| 75 | - static public $windows_codepages = [ | |
| 76 | - 37 => 'IBM037', // IBM EBCDIC US-Canada | |
| 77 | - 437 => 'IBM437', // OEM United States | |
| 78 | - 500 => 'IBM500', // IBM EBCDIC International | |
| 79 | - 708 => 'ASMO-708', // Arabic (ASMO 708) | |
| 80 | - 720 => 'DOS-720', // Arabic (Transparent ASMO); Arabic (DOS) | |
| 81 | - 737 => 'IBM737', // OEM Greek (formerly 437G); Greek (DOS) | |
| 82 | - 775 => 'IBM775', // OEM Baltic; Baltic (DOS) | |
| 83 | - 850 => 'IBM850', // OEM Multilingual Latin 1; Western European (DOS) | |
| 84 | - 852 => 'IBM852', // OEM Latin 2; Central European (DOS) | |
| 85 | - 855 => 'IBM855', // OEM Cyrillic (primarily Russian) | |
| 86 | - 857 => 'IBM857', // OEM Turkish; Turkish (DOS) | |
| 87 | - 858 => 'IBM00858', // OEM Multilingual Latin 1 + Euro symbol | |
| 88 | - 860 => 'IBM860', // OEM Portuguese; Portuguese (DOS) | |
| 89 | - 861 => 'IBM861', // OEM Icelandic; Icelandic (DOS) | |
| 90 | - 862 => 'DOS-862', // OEM Hebrew; Hebrew (DOS) | |
| 91 | - 863 => 'IBM863', // OEM French Canadian; French Canadian (DOS) | |
| 92 | - 864 => 'IBM864', // OEM Arabic; Arabic (864) | |
| 93 | - 865 => 'IBM865', // OEM Nordic; Nordic (DOS) | |
| 94 | - 866 => 'cp866', // OEM Russian; Cyrillic (DOS) | |
| 95 | - 869 => 'IBM869', // OEM Modern Greek; Greek, Modern (DOS) | |
| 96 | - 870 => 'IBM870', // IBM EBCDIC Multilingual/ROECE (Latin 2); IBM EBCDIC Multilingual Latin 2 | |
| 97 | - 874 => 'windows-874', // ANSI/OEM Thai (ISO 8859-11); Thai (Windows) | |
| 98 | - 875 => 'cp875', // IBM EBCDIC Greek Modern | |
| 99 | - 932 => 'shift_jis', // ANSI/OEM Japanese; Japanese (Shift-JIS) | |
| 100 | - 936 => 'gb2312', // ANSI/OEM Simplified Chinese (PRC, Singapore); Chinese Simplified (GB2312) | |
| 101 | - 950 => 'big5', // ANSI/OEM Traditional Chinese (Taiwan; Hong Kong SAR, PRC); Chinese Traditional (Big5) | |
| 102 | - 1026 => 'IBM1026', // IBM EBCDIC Turkish (Latin 5) | |
| 103 | - 1047 => 'IBM01047', // IBM EBCDIC Latin 1/Open System | |
| 104 | - 1140 => 'IBM01140', // IBM EBCDIC US-Canada (037 + Euro symbol); IBM EBCDIC (US-Canada-Euro) | |
| 105 | - 1141 => 'IBM01141', // IBM EBCDIC Germany (20273 + Euro symbol); IBM EBCDIC (Germany-Euro) | |
| 106 | - 1142 => 'IBM01142', // IBM EBCDIC Denmark-Norway (20277 + Euro symbol); IBM EBCDIC (Denmark-Norway-Euro) | |
| 107 | - 1143 => 'IBM01143', // IBM EBCDIC Finland-Sweden (20278 + Euro symbol); IBM EBCDIC (Finland-Sweden-Euro) | |
| 108 | - 1144 => 'IBM01144', // IBM EBCDIC Italy (20280 + Euro symbol); IBM EBCDIC (Italy-Euro) | |
| 109 | - 1145 => 'IBM01145', // IBM EBCDIC Latin America-Spain (20284 + Euro symbol); IBM EBCDIC (Spain-Euro) | |
| 110 | - 1146 => 'IBM01146', // IBM EBCDIC United Kingdom (20285 + Euro symbol); IBM EBCDIC (UK-Euro) | |
| 111 | - 1147 => 'IBM01147', // IBM EBCDIC France (20297 + Euro symbol); IBM EBCDIC (France-Euro) | |
| 112 | - 1148 => 'IBM01148', // IBM EBCDIC International (500 + Euro symbol); IBM EBCDIC (International-Euro) | |
| 113 | - 1149 => 'IBM01149', // IBM EBCDIC Icelandic (20871 + Euro symbol); IBM EBCDIC (Icelandic-Euro) | |
| 114 | - 1200 => 'UTF-16', // Unicode UTF-16, little endian byte order (BMP of ISO 10646); available only to managed applications | |
| 115 | - 1201 => 'UTF-16BE', // Unicode UTF-16, big endian byte order; available only to managed applications | |
| 116 | - 1250 => 'windows-1250', // ANSI Central European; Central European (Windows) | |
| 117 | - 1251 => 'windows-1251', // ANSI Cyrillic; Cyrillic (Windows) | |
| 118 | - 1252 => 'windows-1252', // ANSI Latin 1; Western European (Windows) | |
| 119 | - 1253 => 'windows-1253', // ANSI Greek; Greek (Windows) | |
| 120 | - 1254 => 'windows-1254', // ANSI Turkish; Turkish (Windows) | |
| 121 | - 1255 => 'windows-1255', // ANSI Hebrew; Hebrew (Windows) | |
| 122 | - 1256 => 'windows-1256', // ANSI Arabic; Arabic (Windows) | |
| 123 | - 1257 => 'windows-1257', // ANSI Baltic; Baltic (Windows) | |
| 124 | - 1258 => 'windows-1258', // ANSI/OEM Vietnamese; Vietnamese (Windows) | |
| 125 | - 10000 => 'macintosh', // MAC Roman; Western European (Mac) | |
| 126 | - 12000 => 'UTF-32', // Unicode UTF-32, little endian byte order; available only to managed applications | |
| 127 | - 12001 => 'UTF-32BE', // Unicode UTF-32, big endian byte order; available only to managed applications | |
| 128 | - 20127 => 'US-ASCII', // US-ASCII (7-bit) | |
| 129 | - 20273 => 'IBM273', // IBM EBCDIC Germany | |
| 130 | - 20277 => 'IBM277', // IBM EBCDIC Denmark-Norway | |
| 131 | - 20278 => 'IBM278', // IBM EBCDIC Finland-Sweden | |
| 132 | - 20280 => 'IBM280', // IBM EBCDIC Italy | |
| 133 | - 20284 => 'IBM284', // IBM EBCDIC Latin America-Spain | |
| 134 | - 20285 => 'IBM285', // IBM EBCDIC United Kingdom | |
| 135 | - 20290 => 'IBM290', // IBM EBCDIC Japanese Katakana Extended | |
| 136 | - 20297 => 'IBM297', // IBM EBCDIC France | |
| 137 | - 20420 => 'IBM420', // IBM EBCDIC Arabic | |
| 138 | - 20423 => 'IBM423', // IBM EBCDIC Greek | |
| 139 | - 20424 => 'IBM424', // IBM EBCDIC Hebrew | |
| 140 | - 20838 => 'IBM-Thai', // IBM EBCDIC Thai | |
| 141 | - 20866 => 'koi8-r', // Russian (KOI8-R); Cyrillic (KOI8-R) | |
| 142 | - 20871 => 'IBM871', // IBM EBCDIC Icelandic | |
| 143 | - 20880 => 'IBM880', // IBM EBCDIC Cyrillic Russian | |
| 144 | - 20905 => 'IBM905', // IBM EBCDIC Turkish | |
| 145 | - 20924 => 'IBM00924', // IBM EBCDIC Latin 1/Open System (1047 + Euro symbol) | |
| 146 | - 20932 => 'EUC-JP', // Japanese (JIS 0208-1990 and 0212-1990) | |
| 147 | - 20936 => 'cp20936', // Simplified Chinese (GB2312); Chinese Simplified (GB2312-80) | |
| 148 | - 20949 => 'cp20949', // Korean Wansung | |
| 149 | - 21025 => 'cp1025', // IBM EBCDIC Cyrillic Serbian-Bulgarian | |
| 150 | - 21866 => 'koi8-u', // Ukrainian (KOI8-U); Cyrillic (KOI8-U) | |
| 151 | - 28591 => 'iso-8859-1', // ISO 8859-1 Latin 1; Western European (ISO) | |
| 152 | - 28592 => 'iso-8859-2', // ISO 8859-2 Central European; Central European (ISO) | |
| 153 | - 28593 => 'iso-8859-3', // ISO 8859-3 Latin 3 | |
| 154 | - 28594 => 'iso-8859-4', // ISO 8859-4 Baltic | |
| 155 | - 28595 => 'iso-8859-5', // ISO 8859-5 Cyrillic | |
| 156 | - 28596 => 'iso-8859-6', // ISO 8859-6 Arabic | |
| 157 | - 28597 => 'iso-8859-7', // ISO 8859-7 Greek | |
| 158 | - 28598 => 'iso-8859-8', // ISO 8859-8 Hebrew; Hebrew (ISO-Visual) | |
| 159 | - 28599 => 'iso-8859-9', // ISO 8859-9 Turkish | |
| 160 | - 28603 => 'iso-8859-13', // ISO 8859-13 Estonian | |
| 161 | - 28605 => 'iso-8859-15', // ISO 8859-15 Latin 9 | |
| 162 | - 38598 => 'iso-8859-8-i', // ISO 8859-8 Hebrew; Hebrew (ISO-Logical) | |
| 163 | - 50220 => 'iso-2022-jp', // ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS) | |
| 164 | - 50221 => 'csISO2022JP', // ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow 1 byte Kana) | |
| 165 | - 50222 => 'iso-2022-jp', // ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte Kana - SO/SI) | |
| 166 | - 50225 => 'iso-2022-kr', // ISO 2022 Korean | |
| 167 | - 51932 => 'EUC-JP', // EUC Japanese | |
| 168 | - 51936 => 'EUC-CN', // EUC Simplified Chinese; Chinese Simplified (EUC) | |
| 169 | - 51949 => 'EUC-KR', // EUC Korean | |
| 170 | - 52936 => 'hz-gb-2312', // HZ-GB2312 Simplified Chinese; Chinese Simplified (HZ) | |
| 171 | - 54936 => 'GB18030', // Windows XP and later: GB18030 Simplified Chinese (4 byte); Chinese Simplified (GB18030) | |
| 172 | - 65000 => 'UTF-7', | |
| 173 | - 65001 => 'UTF-8', | |
| 174 | - ]; | |
| 175 | - | |
| 176 | - /** | |
| 177 | - * Catch an error and throw an exception. | |
| 178 | - * | |
| 179 | - * @param int $errno Level of the error | |
| 180 | - * @param string $errstr Error message | |
| 181 | - */ | |
| 182 | - public static function error_handler($errno, $errstr) | |
| 183 | - { | |
| 184 | - throw new \Exception($errstr, 0, $errno); | |
| 185 | - } | |
| 186 | - | |
| 187 | - /** | |
| 188 | - * Parse and validate charset name string. | |
| 189 | - * Sometimes charset string is malformed, there are also charset aliases, | |
| 190 | - * but we need strict names for charset conversion (specially utf8 class) | |
| 191 | - * | |
| 192 | - * @param string $input Input charset name | |
| 193 | - * | |
| 194 | - * @return string The validated charset name | |
| 195 | - */ | |
| 196 | - public static function parse_charset($input) | |
| 197 | - { | |
| 198 | - static $charsets = []; | |
| 199 | - $charset = strtoupper($input); | |
| 200 | - | |
| 201 | - if (isset($charsets[$input])) { | |
| 202 | - return $charsets[$input]; | |
| 203 | - } | |
| 204 | - | |
| 205 | - $charset = preg_replace([ | |
| 206 | - '/^[^0-9A-Z]+/', // e.g. _ISO-8859-JP$SIO | |
| 207 | - '/\$.*$/', // e.g. _ISO-8859-JP$SIO | |
| 208 | - '/UNICODE-1-1-*/', // RFC1641/1642 | |
| 209 | - '/^X-/', // X- prefix (e.g. X-ROMAN8 => ROMAN8) | |
| 210 | - '/\*.*$/', // lang code according to RFC 2231.5 | |
| 211 | - ], '', $charset); | |
| 212 | - | |
| 213 | - if ($charset == 'BINARY') { | |
| 214 | - return $charsets[$input] = null; | |
| 215 | - } | |
| 216 | - | |
| 217 | - // allow A-Z and 0-9 only | |
| 218 | - $str = preg_replace('/[^A-Z0-9]/', '', $charset); | |
| 219 | - | |
| 220 | - if (isset(self::$aliases[$str])) { | |
| 221 | - $result = self::$aliases[$str]; | |
| 222 | - } // UTF | |
| 223 | - elseif (preg_match('/U[A-Z][A-Z](7|8|16|32)(BE|LE)*/', $str, $m)) { | |
| 224 | - $result = 'UTF-'.$m[1].@$m[2]; | |
| 225 | - } // ISO-8859 | |
| 226 | - elseif (preg_match('/ISO8859([0-9]{0,2})/', $str, $m)) { | |
| 227 | - $iso = 'ISO-8859-'.($m[1] ? : 1); | |
| 228 | - // some clients sends windows-1252 text as latin1, | |
| 229 | - // it is safe to use windows-1252 for all latin1 | |
| 230 | - $result = $iso == 'ISO-8859-1' ? 'WINDOWS-1252' : $iso; | |
| 231 | - } // handle broken charset names e.g. WINDOWS-1250HTTP-EQUIVCONTENT-TYPE | |
| 232 | - elseif (preg_match('/(WIN|WINDOWS)([0-9]+)/', $str, $m)) { | |
| 233 | - $result = 'WINDOWS-'.$m[2]; | |
| 234 | - } // LATIN | |
| 235 | - elseif (preg_match('/LATIN(.*)/', $str, $m)) { | |
| 236 | - $aliases = [ | |
| 237 | - '2' => 2, | |
| 238 | - '3' => 3, | |
| 239 | - '4' => 4, | |
| 240 | - '5' => 9, | |
| 241 | - '6' => 10, | |
| 242 | - '7' => 13, | |
| 243 | - '8' => 14, | |
| 244 | - '9' => 15, | |
| 245 | - '10' => 16, | |
| 246 | - 'ARABIC' => 6, | |
| 247 | - 'CYRILLIC' => 5, | |
| 248 | - 'GREEK' => 7, | |
| 249 | - 'GREEK1' => 7, | |
| 250 | - 'HEBREW' => 8, | |
| 251 | - ]; | |
| 252 | - | |
| 253 | - // some clients sends windows-1252 text as latin1, | |
| 254 | - // it is safe to use windows-1252 for all latin1 | |
| 255 | - if ($m[1] == 1) { | |
| 256 | - $result = 'WINDOWS-1252'; | |
| 257 | - } // if iconv is not supported we need ISO labels, it's also safe for iconv | |
| 258 | - elseif (!empty($aliases[$m[1]])) { | |
| 259 | - $result = 'ISO-8859-'.$aliases[$m[1]]; | |
| 260 | - } // iconv requires conversion of e.g. LATIN-1 to LATIN1 | |
| 261 | - else { | |
| 262 | - $result = $str; | |
| 263 | - } | |
| 264 | - } else { | |
| 265 | - $result = $charset; | |
| 266 | - } | |
| 267 | - | |
| 268 | - $charsets[$input] = $result; | |
| 269 | - | |
| 270 | - return $result; | |
| 271 | - } | |
| 272 | - | |
| 273 | - /** | |
| 274 | - * Convert a string from one charset to another. | |
| 275 | - * Uses mbstring and iconv functions if possible | |
| 276 | - * | |
| 277 | - * @param string $str Input string | |
| 278 | - * @param string $from Suspected charset of the input string | |
| 279 | - * @param string $to Target charset to convert to; defaults to RCUBE_CHARSET | |
| 280 | - * | |
| 281 | - * @return string Converted string | |
| 282 | - */ | |
| 283 | - public static function convert($str, $from, $to = null) | |
| 284 | - { | |
| 285 | - static $iconv_options = null; | |
| 286 | - static $mbstring_sc = null; | |
| 287 | - | |
| 288 | - $to = empty($to) ? IMAP2_CHARSET : strtoupper($to); | |
| 289 | - $from = self::parse_charset($from); | |
| 290 | - | |
| 291 | - // It is a common case when UTF-16 charset is used with US-ASCII content (#1488654) | |
| 292 | - // In that case we can just skip the conversion (use UTF-8) | |
| 293 | - if ($from == 'UTF-16' && !preg_match('/[^\x00-\x7F]/', $str)) { | |
| 294 | - $from = 'UTF-8'; | |
| 295 | - } | |
| 296 | - | |
| 297 | - if ($from == $to || empty($str) || empty($from)) { | |
| 298 | - return $str; | |
| 299 | - } | |
| 300 | - | |
| 301 | - if ($iconv_options === null) { | |
| 302 | - if (function_exists('iconv')) { | |
| 303 | - // ignore characters not available in output charset | |
| 304 | - $iconv_options = '//IGNORE'; | |
| 305 | - if (iconv('', $iconv_options, '') === false) { | |
| 306 | - // iconv implementation does not support options | |
| 307 | - $iconv_options = ''; | |
| 308 | - } | |
| 309 | - } else { | |
| 310 | - $iconv_options = false; | |
| 311 | - } | |
| 312 | - } | |
| 313 | - | |
| 314 | - // convert charset using iconv module | |
| 315 | - if ($iconv_options !== false && $from != 'UTF7-IMAP' && $to != 'UTF7-IMAP' | |
| 316 | - && $from !== 'ISO-2022-JP' | |
| 317 | - ) { | |
| 318 | - // throw an exception if iconv reports an illegal character in input | |
| 319 | - // it means that input string has been truncated | |
| 320 | - #set_error_handler(array('rcube_charset', 'error_handler'), E_NOTICE); | |
| 321 | - try { | |
| 322 | - $out = iconv($from, $to.$iconv_options, $str); | |
| 323 | - } catch (\Exception $e) { | |
| 324 | - $out = false; | |
| 325 | - } | |
| 326 | - #restore_error_handler(); | |
| 327 | - | |
| 328 | - if ($out !== false) { | |
| 329 | - return $out; | |
| 330 | - } | |
| 331 | - } | |
| 332 | - | |
| 333 | - if ($mbstring_sc === null) { | |
| 334 | - $mbstring_sc = extension_loaded('mbstring') ? mb_substitute_character() : false; | |
| 335 | - } | |
| 336 | - | |
| 337 | - // convert charset using mbstring module | |
| 338 | - if ($mbstring_sc !== false) { | |
| 339 | - $aliases = [ | |
| 340 | - 'WINDOWS-1257' => 'ISO-8859-13', | |
| 341 | - 'US-ASCII' => 'ASCII', | |
| 342 | - 'ISO-2022-JP' => 'ISO-2022-JP-MS', | |
| 343 | - ]; | |
| 344 | - | |
| 345 | - $mb_from = $aliases[$from] ? : $from; | |
| 346 | - $mb_to = $aliases[$to] ? : $to; | |
| 347 | - | |
| 348 | - // Do the same as //IGNORE with iconv | |
| 349 | - mb_substitute_character('none'); | |
| 350 | - | |
| 351 | - // throw an exception if mbstring reports an illegal character in input | |
| 352 | - // using mb_check_encoding() is much slower | |
| 353 | - #set_error_handler(array('rcube_charset', 'error_handler'), E_WARNING); | |
| 354 | - try { | |
| 355 | - $out = mb_convert_encoding($str, $mb_to, $mb_from); | |
| 356 | - } catch (\Exception $e) { | |
| 357 | - $out = false; | |
| 358 | - } | |
| 359 | - #restore_error_handler(); | |
| 360 | - | |
| 361 | - mb_substitute_character($mbstring_sc); | |
| 362 | - | |
| 363 | - if ($out !== false) { | |
| 364 | - return $out; | |
| 365 | - } | |
| 366 | - } | |
| 367 | - | |
| 368 | - // convert charset using bundled classes/functions | |
| 369 | - if ($to == 'UTF-8') { | |
| 370 | - if ($from == 'UTF7-IMAP') { | |
| 371 | - if ($out = self::utf7imap_to_utf8($str)) { | |
| 372 | - return $out; | |
| 373 | - } | |
| 374 | - } elseif ($from == 'UTF-7') { | |
| 375 | - if ($out = self::utf7_to_utf8($str)) { | |
| 376 | - return $out; | |
| 377 | - } | |
| 378 | - } | |
| 379 | - } | |
| 380 | - | |
| 381 | - // encode string for output | |
| 382 | - if ($from == 'UTF-8') { | |
| 383 | - // @TODO: we need a function for UTF-7 (RFC2152) conversion | |
| 384 | - if ($to == 'UTF7-IMAP' || $to == 'UTF-7') { | |
| 385 | - if ($out = self::utf8_to_utf7imap($str)) { | |
| 386 | - return $out; | |
| 387 | - } | |
| 388 | - } | |
| 389 | - } | |
| 390 | - | |
| 391 | - if (!isset($out)) { | |
| 392 | - trigger_error("No suitable function found for '$from' to '$to' conversion"); | |
| 393 | - } | |
| 394 | - | |
| 395 | - // return original string | |
| 396 | - return $str; | |
| 397 | - } | |
| 398 | - | |
| 399 | - /** | |
| 400 | - * Converts string from standard UTF-7 (RFC 2152) to UTF-8. | |
| 401 | - * | |
| 402 | - * @param string $str Input string (UTF-7) | |
| 403 | - * | |
| 404 | - * @return string Converted string (UTF-8) | |
| 405 | - */ | |
| 406 | - public static function utf7_to_utf8($str) | |
| 407 | - { | |
| 408 | - $Index_64 = [ | |
| 409 | - 0, | |
| 410 | - 0, | |
| 411 | - 0, | |
| 412 | - 0, | |
| 413 | - 0, | |
| 414 | - 0, | |
| 415 | - 0, | |
| 416 | - 0, | |
| 417 | - 0, | |
| 418 | - 0, | |
| 419 | - 0, | |
| 420 | - 0, | |
| 421 | - 0, | |
| 422 | - 0, | |
| 423 | - 0, | |
| 424 | - 0, | |
| 425 | - 0, | |
| 426 | - 0, | |
| 427 | - 0, | |
| 428 | - 0, | |
| 429 | - 0, | |
| 430 | - 0, | |
| 431 | - 0, | |
| 432 | - 0, | |
| 433 | - 0, | |
| 434 | - 0, | |
| 435 | - 0, | |
| 436 | - 0, | |
| 437 | - 0, | |
| 438 | - 0, | |
| 439 | - 0, | |
| 440 | - 0, | |
| 441 | - 0, | |
| 442 | - 0, | |
| 443 | - 0, | |
| 444 | - 0, | |
| 445 | - 0, | |
| 446 | - 0, | |
| 447 | - 0, | |
| 448 | - 0, | |
| 449 | - 0, | |
| 450 | - 0, | |
| 451 | - 0, | |
| 452 | - 1, | |
| 453 | - 0, | |
| 454 | - 0, | |
| 455 | - 0, | |
| 456 | - 0, | |
| 457 | - 1, | |
| 458 | - 1, | |
| 459 | - 1, | |
| 460 | - 1, | |
| 461 | - 1, | |
| 462 | - 1, | |
| 463 | - 1, | |
| 464 | - 1, | |
| 465 | - 1, | |
| 466 | - 1, | |
| 467 | - 0, | |
| 468 | - 0, | |
| 469 | - 0, | |
| 470 | - 0, | |
| 471 | - 0, | |
| 472 | - 0, | |
| 473 | - 0, | |
| 474 | - 1, | |
| 475 | - 1, | |
| 476 | - 1, | |
| 477 | - 1, | |
| 478 | - 1, | |
| 479 | - 1, | |
| 480 | - 1, | |
| 481 | - 1, | |
| 482 | - 1, | |
| 483 | - 1, | |
| 484 | - 1, | |
| 485 | - 1, | |
| 486 | - 1, | |
| 487 | - 1, | |
| 488 | - 1, | |
| 489 | - 1, | |
| 490 | - 1, | |
| 491 | - 1, | |
| 492 | - 1, | |
| 493 | - 1, | |
| 494 | - 1, | |
| 495 | - 1, | |
| 496 | - 1, | |
| 497 | - 1, | |
| 498 | - 1, | |
| 499 | - 1, | |
| 500 | - 0, | |
| 501 | - 0, | |
| 502 | - 0, | |
| 503 | - 0, | |
| 504 | - 0, | |
| 505 | - 0, | |
| 506 | - 1, | |
| 507 | - 1, | |
| 508 | - 1, | |
| 509 | - 1, | |
| 510 | - 1, | |
| 511 | - 1, | |
| 512 | - 1, | |
| 513 | - 1, | |
| 514 | - 1, | |
| 515 | - 1, | |
| 516 | - 1, | |
| 517 | - 1, | |
| 518 | - 1, | |
| 519 | - 1, | |
| 520 | - 1, | |
| 521 | - 1, | |
| 522 | - 1, | |
| 523 | - 1, | |
| 524 | - 1, | |
| 525 | - 1, | |
| 526 | - 1, | |
| 527 | - 1, | |
| 528 | - 1, | |
| 529 | - 1, | |
| 530 | - 1, | |
| 531 | - 1, | |
| 532 | - 0, | |
| 533 | - 0, | |
| 534 | - 0, | |
| 535 | - 0, | |
| 536 | - 0, | |
| 537 | - ]; | |
| 538 | - | |
| 539 | - $u7len = strlen($str); | |
| 540 | - $str = strval($str); | |
| 541 | - $res = ''; | |
| 542 | - | |
| 543 | - for ($i = 0 ; $u7len > 0 ; $i++, $u7len--) { | |
| 544 | - $u7 = $str[$i]; | |
| 545 | - if ($u7 == '+') { | |
| 546 | - $i++; | |
| 547 | - $u7len--; | |
| 548 | - $ch = ''; | |
| 549 | - | |
| 550 | - for (; $u7len > 0 ; $i++, $u7len--) { | |
| 551 | - $u7 = $str[$i]; | |
| 552 | - | |
| 553 | - if (!$Index_64[ord($u7)]) { | |
| 554 | - break; | |
| 555 | - } | |
| 556 | - | |
| 557 | - $ch .= $u7; | |
| 558 | - } | |
| 559 | - | |
| 560 | - if ($ch == '') { | |
| 561 | - if ($u7 == '-') { | |
| 562 | - $res .= '+'; | |
| 563 | - } | |
| 564 | - | |
| 565 | - continue; | |
| 566 | - } | |
| 567 | - | |
| 568 | - $res .= self::utf16_to_utf8(base64_decode($ch)); | |
| 569 | - } else { | |
| 570 | - $res .= $u7; | |
| 571 | - } | |
| 572 | - } | |
| 573 | - | |
| 574 | - return $res; | |
| 575 | - } | |
| 576 | - | |
| 577 | - /** | |
| 578 | - * Converts string from UTF-16 to UTF-8 (helper for utf-7 to utf-8 conversion) | |
| 579 | - * | |
| 580 | - * @param string $str Input string | |
| 581 | - * | |
| 582 | - * @return string The converted string | |
| 583 | - */ | |
| 584 | - public static function utf16_to_utf8($str) | |
| 585 | - { | |
| 586 | - $len = strlen($str); | |
| 587 | - $dec = ''; | |
| 588 | - | |
| 589 | - for ($i = 0 ; $i < $len ; $i += 2) { | |
| 590 | - $c = ord($str[$i]) << 8 | ord($str[$i + 1]); | |
| 591 | - if ($c >= 0x0001 && $c <= 0x007F) { | |
| 592 | - $dec .= chr($c); | |
| 593 | - } elseif ($c > 0x07FF) { | |
| 594 | - $dec .= chr(0xE0 | (($c >> 12) & 0x0F)); | |
| 595 | - $dec .= chr(0x80 | (($c >> 6) & 0x3F)); | |
| 596 | - $dec .= chr(0x80 | (($c >> 0) & 0x3F)); | |
| 597 | - } else { | |
| 598 | - $dec .= chr(0xC0 | (($c >> 6) & 0x1F)); | |
| 599 | - $dec .= chr(0x80 | (($c >> 0) & 0x3F)); | |
| 600 | - } | |
| 601 | - } | |
| 602 | - | |
| 603 | - return $dec; | |
| 604 | - } | |
| 605 | - | |
| 606 | - /** | |
| 607 | - * Convert the data ($str) from RFC 2060's UTF-7 to UTF-8. | |
| 608 | - * If input data is invalid, return the original input string. | |
| 609 | - * RFC 2060 obviously intends the encoding to be unique (see | |
| 610 | - * point 5 in section 5.1.3), so we reject any non-canonical | |
| 611 | - * form, such as &ACY- (instead of &-) or &AMA-&AMA- (instead | |
| 612 | - * of &AMAAwA-). | |
| 613 | - * | |
| 614 | - * Translated from C to PHP by Thomas Bruederli <[email protected]> | |
| 615 | - * | |
| 616 | - * @param string $str Input string (UTF7-IMAP) | |
| 617 | - * | |
| 618 | - * @return string Output string (UTF-8) | |
| 619 | - */ | |
| 620 | - public static function utf7imap_to_utf8($str) | |
| 621 | - { | |
| 622 | - $Index_64 = [ | |
| 623 | - -1, | |
| 624 | - -1, | |
| 625 | - -1, | |
| 626 | - -1, | |
| 627 | - -1, | |
| 628 | - -1, | |
| 629 | - -1, | |
| 630 | - -1, | |
| 631 | - -1, | |
| 632 | - -1, | |
| 633 | - -1, | |
| 634 | - -1, | |
| 635 | - -1, | |
| 636 | - -1, | |
| 637 | - -1, | |
| 638 | - -1, | |
| 639 | - -1, | |
| 640 | - -1, | |
| 641 | - -1, | |
| 642 | - -1, | |
| 643 | - -1, | |
| 644 | - -1, | |
| 645 | - -1, | |
| 646 | - -1, | |
| 647 | - -1, | |
| 648 | - -1, | |
| 649 | - -1, | |
| 650 | - -1, | |
| 651 | - -1, | |
| 652 | - -1, | |
| 653 | - -1, | |
| 654 | - -1, | |
| 655 | - -1, | |
| 656 | - -1, | |
| 657 | - -1, | |
| 658 | - -1, | |
| 659 | - -1, | |
| 660 | - -1, | |
| 661 | - -1, | |
| 662 | - -1, | |
| 663 | - -1, | |
| 664 | - -1, | |
| 665 | - -1, | |
| 666 | - 62, | |
| 667 | - 63, | |
| 668 | - -1, | |
| 669 | - -1, | |
| 670 | - -1, | |
| 671 | - 52, | |
| 672 | - 53, | |
| 673 | - 54, | |
| 674 | - 55, | |
| 675 | - 56, | |
| 676 | - 57, | |
| 677 | - 58, | |
| 678 | - 59, | |
| 679 | - 60, | |
| 680 | - 61, | |
| 681 | - -1, | |
| 682 | - -1, | |
| 683 | - -1, | |
| 684 | - -1, | |
| 685 | - -1, | |
| 686 | - -1, | |
| 687 | - -1, | |
| 688 | - 0, | |
| 689 | - 1, | |
| 690 | - 2, | |
| 691 | - 3, | |
| 692 | - 4, | |
| 693 | - 5, | |
| 694 | - 6, | |
| 695 | - 7, | |
| 696 | - 8, | |
| 697 | - 9, | |
| 698 | - 10, | |
| 699 | - 11, | |
| 700 | - 12, | |
| 701 | - 13, | |
| 702 | - 14, | |
| 703 | - 15, | |
| 704 | - 16, | |
| 705 | - 17, | |
| 706 | - 18, | |
| 707 | - 19, | |
| 708 | - 20, | |
| 709 | - 21, | |
| 710 | - 22, | |
| 711 | - 23, | |
| 712 | - 24, | |
| 713 | - 25, | |
| 714 | - -1, | |
| 715 | - -1, | |
| 716 | - -1, | |
| 717 | - -1, | |
| 718 | - -1, | |
| 719 | - -1, | |
| 720 | - 26, | |
| 721 | - 27, | |
| 722 | - 28, | |
| 723 | - 29, | |
| 724 | - 30, | |
| 725 | - 31, | |
| 726 | - 32, | |
| 727 | - 33, | |
| 728 | - 34, | |
| 729 | - 35, | |
| 730 | - 36, | |
| 731 | - 37, | |
| 732 | - 38, | |
| 733 | - 39, | |
| 734 | - 40, | |
| 735 | - 41, | |
| 736 | - 42, | |
| 737 | - 43, | |
| 738 | - 44, | |
| 739 | - 45, | |
| 740 | - 46, | |
| 741 | - 47, | |
| 742 | - 48, | |
| 743 | - 49, | |
| 744 | - 50, | |
| 745 | - 51, | |
| 746 | - -1, | |
| 747 | - -1, | |
| 748 | - -1, | |
| 749 | - -1, | |
| 750 | - -1, | |
| 751 | - ]; | |
| 752 | - | |
| 753 | - $u7len = strlen($str); | |
| 754 | - $str = strval($str); | |
| 755 | - $p = ''; | |
| 756 | - $err = ''; | |
| 757 | - | |
| 758 | - for ($i = 0 ; $u7len > 0 ; $i++, $u7len--) { | |
| 759 | - $u7 = $str[$i]; | |
| 760 | - if ($u7 == '&') { | |
| 761 | - $i++; | |
| 762 | - $u7len--; | |
| 763 | - $u7 = $str[$i]; | |
| 764 | - | |
| 765 | - if ($u7len && $u7 == '-') { | |
| 766 | - $p .= '&'; | |
| 767 | - continue; | |
| 768 | - } | |
| 769 | - | |
| 770 | - $ch = 0; | |
| 771 | - $k = 10; | |
| 772 | - for (; $u7len > 0 ; $i++, $u7len--) { | |
| 773 | - $u7 = $str[$i]; | |
| 774 | - | |
| 775 | - if ((ord($u7) & 0x80) || ($b = $Index_64[ord($u7)]) == -1) { | |
| 776 | - break; | |
| 777 | - } | |
| 778 | - | |
| 779 | - if ($k > 0) { | |
| 780 | - $ch |= $b << $k; | |
| 781 | - $k -= 6; | |
| 782 | - } else { | |
| 783 | - $ch |= $b >> (-$k); | |
| 784 | - if ($ch < 0x80) { | |
| 785 | - // Printable US-ASCII | |
| 786 | - if (0x20 <= $ch && $ch < 0x7f) { | |
| 787 | - return $err; | |
| 788 | - } | |
| 789 | - $p .= chr($ch); | |
| 790 | - } elseif ($ch < 0x800) { | |
| 791 | - $p .= chr(0xc0 | ($ch >> 6)); | |
| 792 | - $p .= chr(0x80 | ($ch & 0x3f)); | |
| 793 | - } else { | |
| 794 | - $p .= chr(0xe0 | ($ch >> 12)); | |
| 795 | - $p .= chr(0x80 | (($ch >> 6) & 0x3f)); | |
| 796 | - $p .= chr(0x80 | ($ch & 0x3f)); | |
| 797 | - } | |
| 798 | - | |
| 799 | - $ch = ($b << (16 + $k)) & 0xffff; | |
| 800 | - $k += 10; | |
| 801 | - } | |
| 802 | - } | |
| 803 | - | |
| 804 | - // Non-zero or too many extra bits | |
| 805 | - if ($ch || $k < 6) { | |
| 806 | - return $err; | |
| 807 | - } | |
| 808 | - | |
| 809 | - // BASE64 not properly terminated | |
| 810 | - if (!$u7len || $u7 != '-') { | |
| 811 | - return $err; | |
| 812 | - } | |
| 813 | - | |
| 814 | - // Adjacent BASE64 sections | |
| 815 | - if ($u7len > 2 && $str[$i + 1] == '&' && $str[$i + 2] != '-') { | |
| 816 | - return $err; | |
| 817 | - } | |
| 818 | - } // Not printable US-ASCII | |
| 819 | - elseif (ord($u7) < 0x20 || ord($u7) >= 0x7f) { | |
| 820 | - return $err; | |
| 821 | - } else { | |
| 822 | - $p .= $u7; | |
| 823 | - } | |
| 824 | - } | |
| 825 | - | |
| 826 | - return $p; | |
| 827 | - } | |
| 828 | - | |
| 829 | - /** | |
| 830 | - * Convert the data ($str) from UTF-8 to RFC 2060's UTF-7. | |
| 831 | - * Unicode characters above U+FFFF are replaced by U+FFFE. | |
| 832 | - * If input data is invalid, return an empty string. | |
| 833 | - * | |
| 834 | - * Translated from C to PHP by Thomas Bruederli <[email protected]> | |
| 835 | - * | |
| 836 | - * @param string $str Input string (UTF-8) | |
| 837 | - * | |
| 838 | - * @return string Output string (UTF7-IMAP) | |
| 839 | - */ | |
| 840 | - public static function utf8_to_utf7imap($str) | |
| 841 | - { | |
| 842 | - $B64Chars = [ | |
| 843 | - 'A', | |
| 844 | - 'B', | |
| 845 | - 'C', | |
| 846 | - 'D', | |
| 847 | - 'E', | |
| 848 | - 'F', | |
| 849 | - 'G', | |
| 850 | - 'H', | |
| 851 | - 'I', | |
| 852 | - 'J', | |
| 853 | - 'K', | |
| 854 | - 'L', | |
| 855 | - 'M', | |
| 856 | - 'N', | |
| 857 | - 'O', | |
| 858 | - 'P', | |
| 859 | - 'Q', | |
| 860 | - 'R', | |
| 861 | - 'S', | |
| 862 | - 'T', | |
| 863 | - 'U', | |
| 864 | - 'V', | |
| 865 | - 'W', | |
| 866 | - 'X', | |
| 867 | - 'Y', | |
| 868 | - 'Z', | |
| 869 | - 'a', | |
| 870 | - 'b', | |
| 871 | - 'c', | |
| 872 | - 'd', | |
| 873 | - 'e', | |
| 874 | - 'f', | |
| 875 | - 'g', | |
| 876 | - 'h', | |
| 877 | - 'i', | |
| 878 | - 'j', | |
| 879 | - 'k', | |
| 880 | - 'l', | |
| 881 | - 'm', | |
| 882 | - 'n', | |
| 883 | - 'o', | |
| 884 | - 'p', | |
| 885 | - 'q', | |
| 886 | - 'r', | |
| 887 | - 's', | |
| 888 | - 't', | |
| 889 | - 'u', | |
| 890 | - 'v', | |
| 891 | - 'w', | |
| 892 | - 'x', | |
| 893 | - 'y', | |
| 894 | - 'z', | |
| 895 | - '0', | |
| 896 | - '1', | |
| 897 | - '2', | |
| 898 | - '3', | |
| 899 | - '4', | |
| 900 | - '5', | |
| 901 | - '6', | |
| 902 | - '7', | |
| 903 | - '8', | |
| 904 | - '9', | |
| 905 | - '+', | |
| 906 | - ',', | |
| 907 | - ]; | |
| 908 | - | |
| 909 | - $u8len = strlen($str); | |
| 910 | - $base64 = 0; | |
| 911 | - $i = 0; | |
| 912 | - $p = ''; | |
| 913 | - $err = ''; | |
| 914 | - | |
| 915 | - while ($u8len) { | |
| 916 | - $u8 = $str[$i]; | |
| 917 | - $c = ord($u8); | |
| 918 | - | |
| 919 | - if ($c < 0x80) { | |
| 920 | - $ch = $c; | |
| 921 | - $n = 0; | |
| 922 | - } elseif ($c < 0xc2) { | |
| 923 | - return $err; | |
| 924 | - } elseif ($c < 0xe0) { | |
| 925 | - $ch = $c & 0x1f; | |
| 926 | - $n = 1; | |
| 927 | - } elseif ($c < 0xf0) { | |
| 928 | - $ch = $c & 0x0f; | |
| 929 | - $n = 2; | |
| 930 | - } elseif ($c < 0xf8) { | |
| 931 | - $ch = $c & 0x07; | |
| 932 | - $n = 3; | |
| 933 | - } elseif ($c < 0xfc) { | |
| 934 | - $ch = $c & 0x03; | |
| 935 | - $n = 4; | |
| 936 | - } elseif ($c < 0xfe) { | |
| 937 | - $ch = $c & 0x01; | |
| 938 | - $n = 5; | |
| 939 | - } else { | |
| 940 | - return $err; | |
| 941 | - } | |
| 942 | - | |
| 943 | - $i++; | |
| 944 | - $u8len--; | |
| 945 | - | |
| 946 | - if ($n > $u8len) { | |
| 947 | - return $err; | |
| 948 | - } | |
| 949 | - | |
| 950 | - for ($j = 0 ; $j < $n ; $j++) { | |
| 951 | - $o = ord($str[$i + $j]); | |
| 952 | - if (($o & 0xc0) != 0x80) { | |
| 953 | - return $err; | |
| 954 | - } | |
| 955 | - $ch = ($ch << 6) | ($o & 0x3f); | |
| 956 | - } | |
| 957 | - | |
| 958 | - if ($n > 1 && !($ch >> ($n * 5 + 1))) { | |
| 959 | - return $err; | |
| 960 | - } | |
| 961 | - | |
| 962 | - $i += $n; | |
| 963 | - $u8len -= $n; | |
| 964 | - | |
| 965 | - if ($ch < 0x20 || $ch >= 0x7f) { | |
| 966 | - if (!$base64) { | |
| 967 | - $p .= '&'; | |
| 968 | - $base64 = 1; | |
| 969 | - $b = 0; | |
| 970 | - $k = 10; | |
| 971 | - } | |
| 972 | - if ($ch & ~0xffff) { | |
| 973 | - $ch = 0xfffe; | |
| 974 | - } | |
| 975 | - | |
| 976 | - $p .= $B64Chars[($b | $ch >> $k)]; | |
| 977 | - $k -= 6; | |
| 978 | - for (; $k >= 0 ; $k -= 6) { | |
| 979 | - $p .= $B64Chars[(($ch >> $k) & 0x3f)]; | |
| 980 | - } | |
| 981 | - | |
| 982 | - $b = ($ch << (-$k)) & 0x3f; | |
| 983 | - $k += 16; | |
| 984 | - } else { | |
| 985 | - if ($base64) { | |
| 986 | - if ($k > 10) { | |
| 987 | - $p .= $B64Chars[$b]; | |
| 988 | - } | |
| 989 | - $p .= '-'; | |
| 990 | - $base64 = 0; | |
| 991 | - } | |
| 992 | - | |
| 993 | - $p .= chr($ch); | |
| 994 | - if (chr($ch) == '&') { | |
| 995 | - $p .= '-'; | |
| 996 | - } | |
| 997 | - } | |
| 998 | - } | |
| 999 | - | |
| 1000 | - if ($base64) { | |
| 1001 | - if ($k > 10) { | |
| 1002 | - $p .= $B64Chars[$b]; | |
| 1003 | - } | |
| 1004 | - $p .= '-'; | |
| 1005 | - } | |
| 1006 | - | |
| 1007 | - return $p; | |
| 1008 | - } | |
| 1009 | - | |
| 1010 | - /** | |
| 1011 | - * A method to guess character set of a string. | |
| 1012 | - * | |
| 1013 | - * @param string $string String | |
| 1014 | - * @param string $failover Default result for failover | |
| 1015 | - * @param string $language User language | |
| 1016 | - * | |
| 1017 | - * @return string Charset name | |
| 1018 | - */ | |
| 1019 | - public static function detect($string, $failover = null, $language = null) | |
| 1020 | - { | |
| 1021 | - if (substr($string, 0, 4) == "\0\0\xFE\xFF") return 'UTF-32BE'; // Big Endian | |
| 1022 | - if (substr($string, 0, 4) == "\xFF\xFE\0\0") return 'UTF-32LE'; // Little Endian | |
| 1023 | - if (substr($string, 0, 2) == "\xFE\xFF") return 'UTF-16BE'; // Big Endian | |
| 1024 | - if (substr($string, 0, 2) == "\xFF\xFE") return 'UTF-16LE'; // Little Endian | |
| 1025 | - if (substr($string, 0, 3) == "\xEF\xBB\xBF") return 'UTF-8'; | |
| 1026 | - | |
| 1027 | - // heuristics | |
| 1028 | - if ($string[0] == "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-32BE'; | |
| 1029 | - if ($string[0] != "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] == "\0") return 'UTF-32LE'; | |
| 1030 | - if ($string[0] == "\0" && $string[1] != "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-16BE'; | |
| 1031 | - if ($string[0] != "\0" && $string[1] == "\0" && $string[2] != "\0" && $string[3] == "\0") return 'UTF-16LE'; | |
| 1032 | - | |
| 1033 | - if (empty($language)) { | |
| 1034 | - $rcube = rcube::get_instance(); | |
| 1035 | - $language = $rcube->get_user_language(); | |
| 1036 | - } | |
| 1037 | - | |
| 1038 | - // Prioritize charsets according to current language (#1485669) | |
| 1039 | - switch ($language) { | |
| 1040 | - case 'ja_JP': | |
| 1041 | - $prio = ['ISO-2022-JP', 'JIS', 'UTF-8', 'EUC-JP', 'eucJP-win', 'SJIS', 'SJIS-win']; | |
| 1042 | - break; | |
| 1043 | - | |
| 1044 | - case 'zh_CN': | |
| 1045 | - case 'zh_TW': | |
| 1046 | - $prio = ['UTF-8', 'BIG-5', 'GB2312', 'EUC-TW']; | |
| 1047 | - break; | |
| 1048 | - | |
| 1049 | - case 'ko_KR': | |
| 1050 | - $prio = ['UTF-8', 'EUC-KR', 'ISO-2022-KR']; | |
| 1051 | - break; | |
| 1052 | - | |
| 1053 | - case 'ru_RU': | |
| 1054 | - $prio = ['UTF-8', 'WINDOWS-1251', 'KOI8-R']; | |
| 1055 | - break; | |
| 1056 | - | |
| 1057 | - case 'tr_TR': | |
| 1058 | - $prio = ['UTF-8', 'ISO-8859-9', 'WINDOWS-1254']; | |
| 1059 | - break; | |
| 1060 | - } | |
| 1061 | - | |
| 1062 | - // mb_detect_encoding() is not reliable for some charsets (#1490135) | |
| 1063 | - // use mb_check_encoding() to make charset priority lists really working | |
| 1064 | - if ($prio && function_exists('mb_check_encoding')) { | |
| 1065 | - foreach ($prio as $encoding) { | |
| 1066 | - if (mb_check_encoding($string, $encoding)) { | |
| 1067 | - return $encoding; | |
| 1068 | - } | |
| 1069 | - } | |
| 1070 | - } | |
| 1071 | - | |
| 1072 | - if (function_exists('mb_detect_encoding')) { | |
| 1073 | - if (!$prio) { | |
| 1074 | - $prio = [ | |
| 1075 | - 'UTF-8', | |
| 1076 | - 'SJIS', | |
| 1077 | - 'GB2312', | |
| 1078 | - 'ISO-8859-1', | |
| 1079 | - 'ISO-8859-2', | |
| 1080 | - 'ISO-8859-3', | |
| 1081 | - 'ISO-8859-4', | |
| 1082 | - 'ISO-8859-5', | |
| 1083 | - 'ISO-8859-6', | |
| 1084 | - 'ISO-8859-7', | |
| 1085 | - 'ISO-8859-8', | |
| 1086 | - 'ISO-8859-9', | |
| 1087 | - 'ISO-8859-10', | |
| 1088 | - 'ISO-8859-13', | |
| 1089 | - 'ISO-8859-14', | |
| 1090 | - 'ISO-8859-15', | |
| 1091 | - 'ISO-8859-16', | |
| 1092 | - 'WINDOWS-1252', | |
| 1093 | - 'WINDOWS-1251', | |
| 1094 | - 'EUC-JP', | |
| 1095 | - 'EUC-TW', | |
| 1096 | - 'KOI8-R', | |
| 1097 | - 'BIG-5', | |
| 1098 | - 'ISO-2022-KR', | |
| 1099 | - 'ISO-2022-JP', | |
| 1100 | - ]; | |
| 1101 | - } | |
| 1102 | - | |
| 1103 | - $encodings = array_unique(array_merge($prio, mb_list_encodings())); | |
| 1104 | - | |
| 1105 | - if ($encoding = mb_detect_encoding($string, $encodings)) { | |
| 1106 | - return $encoding; | |
| 1107 | - } | |
| 1108 | - } | |
| 1109 | - | |
| 1110 | - // No match, check for UTF-8 | |
| 1111 | - // from http://w3.org/International/questions/qa-forms-utf-8.html | |
| 1112 | - if (preg_match( | |
| 1113 | - '/\A( | |
| 1114 | - [\x09\x0A\x0D\x20-\x7E] | |
| 1115 | - | [\xC2-\xDF][\x80-\xBF] | |
| 1116 | - | \xE0[\xA0-\xBF][\x80-\xBF] | |
| 1117 | - | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} | |
| 1118 | - | \xED[\x80-\x9F][\x80-\xBF] | |
| 1119 | - | \xF0[\x90-\xBF][\x80-\xBF]{2} | |
| 1120 | - | [\xF1-\xF3][\x80-\xBF]{3} | |
| 1121 | - | \xF4[\x80-\x8F][\x80-\xBF]{2} | |
| 1122 | - )*\z/xs', | |
| 1123 | - substr($string, 0, 2048) | |
| 1124 | - ) | |
| 1125 | - ) { | |
| 1126 | - return 'UTF-8'; | |
| 1127 | - } | |
| 1128 | - | |
| 1129 | - return $failover; | |
| 1130 | - } | |
| 1131 | - | |
| 1132 | - /** | |
| 1133 | - * Removes non-unicode characters from input. | |
| 1134 | - * | |
| 1135 | - * @param mixed $input String or array. | |
| 1136 | - * | |
| 1137 | - * @return mixed String or array | |
| 1138 | - */ | |
| 1139 | - public static function clean($input) | |
| 1140 | - { | |
| 1141 | - // handle input of type array | |
| 1142 | - if (is_array($input)) { | |
| 1143 | - foreach ($input as $idx => $val) { | |
| 1144 | - $input[$idx] = self::clean($val); | |
| 1145 | - } | |
| 1146 | - | |
| 1147 | - return $input; | |
| 1148 | - } | |
| 1149 | - | |
| 1150 | - if (!is_string($input) || $input == '') { | |
| 1151 | - return $input; | |
| 1152 | - } | |
| 1153 | - | |
| 1154 | - // iconv/mbstring are much faster (especially with long strings) | |
| 1155 | - if (function_exists('mb_convert_encoding')) { | |
| 1156 | - $msch = mb_substitute_character(); | |
| 1157 | - mb_substitute_character('none'); | |
| 1158 | - $res = mb_convert_encoding($input, 'UTF-8', 'UTF-8'); | |
| 1159 | - mb_substitute_character($msch); | |
| 1160 | - | |
| 1161 | - if ($res !== false) { | |
| 1162 | - return $res; | |
| 1163 | - } | |
| 1164 | - } | |
| 1165 | - | |
| 1166 | - if (function_exists('iconv')) { | |
| 1167 | - if (($res = @iconv('UTF-8', 'UTF-8//IGNORE', $input)) !== false) { | |
| 1168 | - return $res; | |
| 1169 | - } | |
| 1170 | - } | |
| 1171 | - | |
| 1172 | - $seq = ''; | |
| 1173 | - $out = ''; | |
| 1174 | - $regexp = '/^('. | |
| 1175 | - // '[\x00-\x7F]'. // UTF8-1 | |
| 1176 | - '|[\xC2-\xDF][\x80-\xBF]'. // UTF8-2 | |
| 1177 | - '|\xE0[\xA0-\xBF][\x80-\xBF]'. // UTF8-3 | |
| 1178 | - '|[\xE1-\xEC][\x80-\xBF][\x80-\xBF]'. // UTF8-3 | |
| 1179 | - '|\xED[\x80-\x9F][\x80-\xBF]'. // UTF8-3 | |
| 1180 | - '|[\xEE-\xEF][\x80-\xBF][\x80-\xBF]'. // UTF8-3 | |
| 1181 | - '|\xF0[\x90-\xBF][\x80-\xBF][\x80-\xBF]'. // UTF8-4 | |
| 1182 | - '|[\xF1-\xF3][\x80-\xBF][\x80-\xBF][\x80-\xBF]'.// UTF8-4 | |
| 1183 | - '|\xF4[\x80-\x8F][\x80-\xBF][\x80-\xBF]'. // UTF8-4 | |
| 1184 | - ')$/'; | |
| 1185 | - | |
| 1186 | - for ($i = 0, $len = strlen($input) ; $i < $len ; $i++) { | |
| 1187 | - $chr = $input[$i]; | |
| 1188 | - $ord = ord($chr); | |
| 1189 | - | |
| 1190 | - // 1-byte character | |
| 1191 | - if ($ord <= 0x7F) { | |
| 1192 | - if ($seq !== '') { | |
| 1193 | - $out .= preg_match($regexp, $seq) ? $seq : ''; | |
| 1194 | - $seq = ''; | |
| 1195 | - } | |
| 1196 | - | |
| 1197 | - $out .= $chr; | |
| 1198 | - } // first byte of multibyte sequence | |
| 1199 | - elseif ($ord >= 0xC0) { | |
| 1200 | - if ($seq !== '') { | |
| 1201 | - $out .= preg_match($regexp, $seq) ? $seq : ''; | |
| 1202 | - $seq = ''; | |
| 1203 | - } | |
| 1204 | - | |
| 1205 | - $seq = $chr; | |
| 1206 | - } // next byte of multibyte sequence | |
| 1207 | - elseif ($seq !== '') { | |
| 1208 | - $seq .= $chr; | |
| 1209 | - } | |
| 1210 | - } | |
| 1211 | - | |
| 1212 | - if ($seq !== '') { | |
| 1213 | - $out .= preg_match($regexp, $seq) ? $seq : ''; | |
| 1214 | - } | |
| 1215 | - | |
| 1216 | - return $out; | |
| 1217 | - } | |
| 1218 | -} | |
