| 1 |
<?php |
| 2 |
|
| 3 |
|
| 4 |
namespace Javanile\Imap2\Roundcube; |
| 5 |
|
| 6 |
use Javanile\Imap2\ErrorException; |
| 7 |
use Javanile\Imap2\rcube; |
| 8 |
|
| 9 |
class Charset |
| 10 |
{ |
| 11 |
static public $aliases = array( |
| 12 |
'USASCII' => 'WINDOWS-1252', |
| 13 |
'ANSIX31101983' => 'WINDOWS-1252', |
| 14 |
'ANSIX341968' => 'WINDOWS-1252', |
| 15 |
'UNKNOWN8BIT' => 'ISO-8859-15', |
| 16 |
'UNKNOWN' => 'ISO-8859-15', |
| 17 |
'USERDEFINED' => 'ISO-8859-15', |
| 18 |
'KSC56011987' => 'EUC-KR', |
| 19 |
'GB2312' => 'GBK', |
| 20 |
'GB231280' => 'GBK', |
| 21 |
'UNICODE' => 'UTF-8', |
| 22 |
'UTF7IMAP' => 'UTF7-IMAP', |
| 23 |
'TIS620' => 'WINDOWS-874', |
| 24 |
'ISO88599' => 'WINDOWS-1254', |
| 25 |
'ISO885911' => 'WINDOWS-874', |
| 26 |
'MACROMAN' => 'MACINTOSH', |
| 27 |
'77' => 'MAC', |
| 28 |
'128' => 'SHIFT-JIS', |
| 29 |
'129' => 'CP949', |
| 30 |
'130' => 'CP1361', |
| 31 |
'134' => 'GBK', |
| 32 |
'136' => 'BIG5', |
| 33 |
'161' => 'WINDOWS-1253', |
| 34 |
'162' => 'WINDOWS-1254', |
| 35 |
'163' => 'WINDOWS-1258', |
| 36 |
'177' => 'WINDOWS-1255', |
| 37 |
'178' => 'WINDOWS-1256', |
| 38 |
'186' => 'WINDOWS-1257', |
| 39 |
'204' => 'WINDOWS-1251', |
| 40 |
'222' => 'WINDOWS-874', |
| 41 |
'238' => 'WINDOWS-1250', |
| 42 |
'MS950' => 'CP950', |
| 43 |
'WINDOWS949' => 'UHC', |
| 44 |
); |
| 45 |
|
| 46 |
static public $windows_codepages = array( |
| 47 |
37 => 'IBM037', // IBM EBCDIC US-Canada |
| 48 |
437 => 'IBM437', // OEM United States |
| 49 |
500 => 'IBM500', // IBM EBCDIC International |
| 50 |
708 => 'ASMO-708', // Arabic (ASMO 708) |
| 51 |
720 => 'DOS-720', // Arabic (Transparent ASMO); Arabic (DOS) |
| 52 |
737 => 'IBM737', // OEM Greek (formerly 437G); Greek (DOS) |
| 53 |
775 => 'IBM775', // OEM Baltic; Baltic (DOS) |
| 54 |
850 => 'IBM850', // OEM Multilingual Latin 1; Western European (DOS) |
| 55 |
852 => 'IBM852', // OEM Latin 2; Central European (DOS) |
| 56 |
855 => 'IBM855', // OEM Cyrillic (primarily Russian) |
| 57 |
857 => 'IBM857', // OEM Turkish; Turkish (DOS) |
| 58 |
858 => 'IBM00858', // OEM Multilingual Latin 1 + Euro symbol |
| 59 |
860 => 'IBM860', // OEM Portuguese; Portuguese (DOS) |
| 60 |
861 => 'IBM861', // OEM Icelandic; Icelandic (DOS) |
| 61 |
862 => 'DOS-862', // OEM Hebrew; Hebrew (DOS) |
| 62 |
863 => 'IBM863', // OEM French Canadian; French Canadian (DOS) |
| 63 |
864 => 'IBM864', // OEM Arabic; Arabic (864) |
| 64 |
865 => 'IBM865', // OEM Nordic; Nordic (DOS) |
| 65 |
866 => 'cp866', // OEM Russian; Cyrillic (DOS) |
| 66 |
869 => 'IBM869', // OEM Modern Greek; Greek, Modern (DOS) |
| 67 |
870 => 'IBM870', // IBM EBCDIC Multilingual/ROECE (Latin 2); IBM EBCDIC Multilingual Latin 2 |
| 68 |
874 => 'windows-874', // ANSI/OEM Thai (ISO 8859-11); Thai (Windows) |
| 69 |
875 => 'cp875', // IBM EBCDIC Greek Modern |
| 70 |
932 => 'shift_jis', // ANSI/OEM Japanese; Japanese (Shift-JIS) |
| 71 |
936 => 'gb2312', // ANSI/OEM Simplified Chinese (PRC, Singapore); Chinese Simplified (GB2312) |
| 72 |
950 => 'big5', // ANSI/OEM Traditional Chinese (Taiwan; Hong Kong SAR, PRC); Chinese Traditional (Big5) |
| 73 |
1026 => 'IBM1026', // IBM EBCDIC Turkish (Latin 5) |
| 74 |
1047 => 'IBM01047', // IBM EBCDIC Latin 1/Open System |
| 75 |
1140 => 'IBM01140', // IBM EBCDIC US-Canada (037 + Euro symbol); IBM EBCDIC (US-Canada-Euro) |
| 76 |
1141 => 'IBM01141', // IBM EBCDIC Germany (20273 + Euro symbol); IBM EBCDIC (Germany-Euro) |
| 77 |
1142 => 'IBM01142', // IBM EBCDIC Denmark-Norway (20277 + Euro symbol); IBM EBCDIC (Denmark-Norway-Euro) |
| 78 |
1143 => 'IBM01143', // IBM EBCDIC Finland-Sweden (20278 + Euro symbol); IBM EBCDIC (Finland-Sweden-Euro) |
| 79 |
1144 => 'IBM01144', // IBM EBCDIC Italy (20280 + Euro symbol); IBM EBCDIC (Italy-Euro) |
| 80 |
1145 => 'IBM01145', // IBM EBCDIC Latin America-Spain (20284 + Euro symbol); IBM EBCDIC (Spain-Euro) |
| 81 |
1146 => 'IBM01146', // IBM EBCDIC United Kingdom (20285 + Euro symbol); IBM EBCDIC (UK-Euro) |
| 82 |
1147 => 'IBM01147', // IBM EBCDIC France (20297 + Euro symbol); IBM EBCDIC (France-Euro) |
| 83 |
1148 => 'IBM01148', // IBM EBCDIC International (500 + Euro symbol); IBM EBCDIC (International-Euro) |
| 84 |
1149 => 'IBM01149', // IBM EBCDIC Icelandic (20871 + Euro symbol); IBM EBCDIC (Icelandic-Euro) |
| 85 |
1200 => 'UTF-16', // Unicode UTF-16, little endian byte order (BMP of ISO 10646); available only to managed applications |
| 86 |
1201 => 'UTF-16BE', // Unicode UTF-16, big endian byte order; available only to managed applications |
| 87 |
1250 => 'windows-1250', // ANSI Central European; Central European (Windows) |
| 88 |
1251 => 'windows-1251', // ANSI Cyrillic; Cyrillic (Windows) |
| 89 |
1252 => 'windows-1252', // ANSI Latin 1; Western European (Windows) |
| 90 |
1253 => 'windows-1253', // ANSI Greek; Greek (Windows) |
| 91 |
1254 => 'windows-1254', // ANSI Turkish; Turkish (Windows) |
| 92 |
1255 => 'windows-1255', // ANSI Hebrew; Hebrew (Windows) |
| 93 |
1256 => 'windows-1256', // ANSI Arabic; Arabic (Windows) |
| 94 |
1257 => 'windows-1257', // ANSI Baltic; Baltic (Windows) |
| 95 |
1258 => 'windows-1258', // ANSI/OEM Vietnamese; Vietnamese (Windows) |
| 96 |
10000 => 'macintosh', // MAC Roman; Western European (Mac) |
| 97 |
12000 => 'UTF-32', // Unicode UTF-32, little endian byte order; available only to managed applications |
| 98 |
12001 => 'UTF-32BE', // Unicode UTF-32, big endian byte order; available only to managed applications |
| 99 |
20127 => 'US-ASCII', // US-ASCII (7-bit) |
| 100 |
20273 => 'IBM273', // IBM EBCDIC Germany |
| 101 |
20277 => 'IBM277', // IBM EBCDIC Denmark-Norway |
| 102 |
20278 => 'IBM278', // IBM EBCDIC Finland-Sweden |
| 103 |
20280 => 'IBM280', // IBM EBCDIC Italy |
| 104 |
20284 => 'IBM284', // IBM EBCDIC Latin America-Spain |
| 105 |
20285 => 'IBM285', // IBM EBCDIC United Kingdom |
| 106 |
20290 => 'IBM290', // IBM EBCDIC Japanese Katakana Extended |
| 107 |
20297 => 'IBM297', // IBM EBCDIC France |
| 108 |
20420 => 'IBM420', // IBM EBCDIC Arabic |
| 109 |
20423 => 'IBM423', // IBM EBCDIC Greek |
| 110 |
20424 => 'IBM424', // IBM EBCDIC Hebrew |
| 111 |
20838 => 'IBM-Thai', // IBM EBCDIC Thai |
| 112 |
20866 => 'koi8-r', // Russian (KOI8-R); Cyrillic (KOI8-R) |
| 113 |
20871 => 'IBM871', // IBM EBCDIC Icelandic |
| 114 |
20880 => 'IBM880', // IBM EBCDIC Cyrillic Russian |
| 115 |
20905 => 'IBM905', // IBM EBCDIC Turkish |
| 116 |
20924 => 'IBM00924', // IBM EBCDIC Latin 1/Open System (1047 + Euro symbol) |
| 117 |
20932 => 'EUC-JP', // Japanese (JIS 0208-1990 and 0212-1990) |
| 118 |
20936 => 'cp20936', // Simplified Chinese (GB2312); Chinese Simplified (GB2312-80) |
| 119 |
20949 => 'cp20949', // Korean Wansung |
| 120 |
21025 => 'cp1025', // IBM EBCDIC Cyrillic Serbian-Bulgarian |
| 121 |
21866 => 'koi8-u', // Ukrainian (KOI8-U); Cyrillic (KOI8-U) |
| 122 |
28591 => 'iso-8859-1', // ISO 8859-1 Latin 1; Western European (ISO) |
| 123 |
28592 => 'iso-8859-2', // ISO 8859-2 Central European; Central European (ISO) |
| 124 |
28593 => 'iso-8859-3', // ISO 8859-3 Latin 3 |
| 125 |
28594 => 'iso-8859-4', // ISO 8859-4 Baltic |
| 126 |
28595 => 'iso-8859-5', // ISO 8859-5 Cyrillic |
| 127 |
28596 => 'iso-8859-6', // ISO 8859-6 Arabic |
| 128 |
28597 => 'iso-8859-7', // ISO 8859-7 Greek |
| 129 |
28598 => 'iso-8859-8', // ISO 8859-8 Hebrew; Hebrew (ISO-Visual) |
| 130 |
28599 => 'iso-8859-9', // ISO 8859-9 Turkish |
| 131 |
28603 => 'iso-8859-13', // ISO 8859-13 Estonian |
| 132 |
28605 => 'iso-8859-15', // ISO 8859-15 Latin 9 |
| 133 |
38598 => 'iso-8859-8-i', // ISO 8859-8 Hebrew; Hebrew (ISO-Logical) |
| 134 |
50220 => 'iso-2022-jp', // ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS) |
| 135 |
50221 => 'csISO2022JP', // ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS-Allow 1 byte Kana) |
| 136 |
50222 => 'iso-2022-jp', // ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS-Allow 1 byte Kana - SO/SI) |
| 137 |
50225 => 'iso-2022-kr', // ISO 2022 Korean |
| 138 |
51932 => 'EUC-JP', // EUC Japanese |
| 139 |
51936 => 'EUC-CN', // EUC Simplified Chinese; Chinese Simplified (EUC) |
| 140 |
51949 => 'EUC-KR', // EUC Korean |
| 141 |
52936 => 'hz-gb-2312', // HZ-GB2312 Simplified Chinese; Chinese Simplified (HZ) |
| 142 |
54936 => 'GB18030', // Windows XP and later: GB18030 Simplified Chinese (4 byte); Chinese Simplified (GB18030) |
| 143 |
65000 => 'UTF-7', |
| 144 |
65001 => 'UTF-8', |
| 145 |
); |
| 146 |
|
| 147 |
public static function error_handler($errno, $errstr) |
| 148 |
{ |
| 149 |
throw new ErrorException($errstr, 0, $errno); |
| 150 |
} |
| 151 |
|
| 152 |
public static function parse_charset($input) |
| 153 |
{ |
| 154 |
static $charsets = array(); |
| 155 |
$charset = strtoupper($input); |
| 156 |
|
| 157 |
if (isset($charsets[$input])) { |
| 158 |
return $charsets[$input]; |
| 159 |
} |
| 160 |
|
| 161 |
$charset = preg_replace(array( |
| 162 |
'/^[^0-9A-Z]+/', // e.g. _ISO-8859-JP$SIO |
| 163 |
'/\$.*$/', // e.g. _ISO-8859-JP$SIO |
| 164 |
'/UNICODE-1-1-*/', // RFC1641/1642 |
| 165 |
'/^X-/', // X- prefix (e.g. X-ROMAN8 => ROMAN8) |
| 166 |
'/\*.*$/' // lang code according to RFC 2231.5 |
| 167 |
), '', $charset); |
| 168 |
|
| 169 |
if ($charset == 'BINARY') { |
| 170 |
return $charsets[$input] = null; |
| 171 |
} |
| 172 |
|
| 173 |
$str = preg_replace('/[^A-Z0-9]/', '', $charset); |
| 174 |
|
| 175 |
if (isset(self::$aliases[$str])) { |
| 176 |
$result = self::$aliases[$str]; |
| 177 |
} |
| 178 |
else if (preg_match('/U[A-Z][A-Z](7|8|16|32)(BE|LE)*/', $str, $m)) { |
| 179 |
$result = 'UTF-' . $m[1] . @$m[2]; |
| 180 |
} |
| 181 |
else if (preg_match('/ISO8859([0-9]{0,2})/', $str, $m)) { |
| 182 |
$iso = 'ISO-8859-' . ($m[1] ?: 1); |
| 183 |
$result = $iso == 'ISO-8859-1' ? 'WINDOWS-1252' : $iso; |
| 184 |
} |
| 185 |
else if (preg_match('/(WIN|WINDOWS)([0-9]+)/', $str, $m)) { |
| 186 |
$result = 'WINDOWS-' . $m[2]; |
| 187 |
} |
| 188 |
else if (preg_match('/LATIN(.*)/', $str, $m)) { |
| 189 |
$aliases = array('2' => 2, '3' => 3, '4' => 4, '5' => 9, '6' => 10, |
| 190 |
'7' => 13, '8' => 14, '9' => 15, '10' => 16, |
| 191 |
'ARABIC' => 6, 'CYRILLIC' => 5, 'GREEK' => 7, 'GREEK1' => 7, 'HEBREW' => 8 |
| 192 |
); |
| 193 |
|
| 194 |
if ($m[1] == 1) { |
| 195 |
$result = 'WINDOWS-1252'; |
| 196 |
} |
| 197 |
else if (!empty($aliases[$m[1]])) { |
| 198 |
$result = 'ISO-8859-'.$aliases[$m[1]]; |
| 199 |
} |
| 200 |
else { |
| 201 |
$result = $str; |
| 202 |
} |
| 203 |
} |
| 204 |
else { |
| 205 |
$result = $charset; |
| 206 |
} |
| 207 |
|
| 208 |
$charsets[$input] = $result; |
| 209 |
|
| 210 |
return $result; |
| 211 |
} |
| 212 |
|
| 213 |
public static function convert($str, $from, $to = null) |
| 214 |
{ |
| 215 |
static $iconv_options = null; |
| 216 |
static $mbstring_sc = null; |
| 217 |
|
| 218 |
$to = empty($to) ? IMAP2_CHARSET : strtoupper($to); |
| 219 |
$from = self::parse_charset($from); |
| 220 |
|
| 221 |
if ($from == 'UTF-16' && !preg_match('/[^\x00-\x7F]/', $str)) { |
| 222 |
$from = 'UTF-8'; |
| 223 |
} |
| 224 |
|
| 225 |
if ($from == $to || empty($str) || empty($from)) { |
| 226 |
return $str; |
| 227 |
} |
| 228 |
|
| 229 |
if ($iconv_options === null) { |
| 230 |
if (function_exists('iconv')) { |
| 231 |
$iconv_options = '//IGNORE'; |
| 232 |
if (iconv('', $iconv_options, '') === false) { |
| 233 |
$iconv_options = ''; |
| 234 |
} |
| 235 |
} |
| 236 |
else { |
| 237 |
$iconv_options = false; |
| 238 |
} |
| 239 |
} |
| 240 |
|
| 241 |
if ($iconv_options !== false && $from != 'UTF7-IMAP' && $to != 'UTF7-IMAP' |
| 242 |
&& $from !== 'ISO-2022-JP' |
| 243 |
) { |
| 244 |
#set_error_handler(array('rcube_charset', 'error_handler'), E_NOTICE); |
| 245 |
try { |
| 246 |
$out = iconv($from, $to . $iconv_options, $str); |
| 247 |
} |
| 248 |
catch (ErrorException $e) { |
| 249 |
$out = false; |
| 250 |
} |
| 251 |
#restore_error_handler(); |
| 252 |
|
| 253 |
if ($out !== false) { |
| 254 |
return $out; |
| 255 |
} |
| 256 |
} |
| 257 |
|
| 258 |
if ($mbstring_sc === null) { |
| 259 |
$mbstring_sc = extension_loaded('mbstring') ? mb_substitute_character() : false; |
| 260 |
} |
| 261 |
|
| 262 |
if ($mbstring_sc !== false) { |
| 263 |
$aliases = array( |
| 264 |
'WINDOWS-1257' => 'ISO-8859-13', |
| 265 |
'US-ASCII' => 'ASCII', |
| 266 |
'ISO-2022-JP' => 'ISO-2022-JP-MS', |
| 267 |
); |
| 268 |
|
| 269 |
$mb_from = $aliases[$from] ?: $from; |
| 270 |
$mb_to = $aliases[$to] ?: $to; |
| 271 |
|
| 272 |
mb_substitute_character('none'); |
| 273 |
|
| 274 |
#set_error_handler(array('rcube_charset', 'error_handler'), E_WARNING); |
| 275 |
try { |
| 276 |
$out = mb_convert_encoding($str, $mb_to, $mb_from); |
| 277 |
} |
| 278 |
catch (ErrorException $e) { |
| 279 |
$out = false; |
| 280 |
} |
| 281 |
#restore_error_handler(); |
| 282 |
|
| 283 |
mb_substitute_character($mbstring_sc); |
| 284 |
|
| 285 |
if ($out !== false) { |
| 286 |
return $out; |
| 287 |
} |
| 288 |
} |
| 289 |
|
| 290 |
if ($to == 'UTF-8') { |
| 291 |
if ($from == 'UTF7-IMAP') { |
| 292 |
if ($out = self::utf7imap_to_utf8($str)) { |
| 293 |
return $out; |
| 294 |
} |
| 295 |
} |
| 296 |
else if ($from == 'UTF-7') { |
| 297 |
if ($out = self::utf7_to_utf8($str)) { |
| 298 |
return $out; |
| 299 |
} |
| 300 |
} |
| 301 |
} |
| 302 |
|
| 303 |
if ($from == 'UTF-8') { |
| 304 |
if ($to == 'UTF7-IMAP' || $to == 'UTF-7') { |
| 305 |
if ($out = self::utf8_to_utf7imap($str)) { |
| 306 |
return $out; |
| 307 |
} |
| 308 |
} |
| 309 |
} |
| 310 |
|
| 311 |
if (!isset($out)) { |
| 312 |
trigger_error("No suitable function found for '$from' to '$to' conversion"); |
| 313 |
} |
| 314 |
|
| 315 |
return $str; |
| 316 |
} |
| 317 |
|
| 318 |
public static function utf7_to_utf8($str) |
| 319 |
{ |
| 320 |
$Index_64 = array( |
| 321 |
0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0, |
| 322 |
0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0, |
| 323 |
0,0,0,0, 0,0,0,0, 0,0,0,1, 0,0,0,0, |
| 324 |
1,1,1,1, 1,1,1,1, 1,1,0,0, 0,0,0,0, |
| 325 |
0,1,1,1, 1,1,1,1, 1,1,1,1, 1,1,1,1, |
| 326 |
1,1,1,1, 1,1,1,1, 1,1,1,0, 0,0,0,0, |
| 327 |
0,1,1,1, 1,1,1,1, 1,1,1,1, 1,1,1,1, |
| 328 |
1,1,1,1, 1,1,1,1, 1,1,1,0, 0,0,0,0, |
| 329 |
); |
| 330 |
|
| 331 |
$u7len = strlen($str); |
| 332 |
$str = strval($str); |
| 333 |
$res = ''; |
| 334 |
|
| 335 |
for ($i=0; $u7len > 0; $i++, $u7len--) { |
| 336 |
$u7 = $str[$i]; |
| 337 |
if ($u7 == '+') { |
| 338 |
$i++; |
| 339 |
$u7len--; |
| 340 |
$ch = ''; |
| 341 |
|
| 342 |
for (; $u7len > 0; $i++, $u7len--) { |
| 343 |
$u7 = $str[$i]; |
| 344 |
|
| 345 |
if (!$Index_64[ord($u7)]) { |
| 346 |
break; |
| 347 |
} |
| 348 |
|
| 349 |
$ch .= $u7; |
| 350 |
} |
| 351 |
|
| 352 |
if ($ch == '') { |
| 353 |
if ($u7 == '-') { |
| 354 |
$res .= '+'; |
| 355 |
} |
| 356 |
|
| 357 |
continue; |
| 358 |
} |
| 359 |
|
| 360 |
$res .= self::utf16_to_utf8(base64_decode($ch)); |
| 361 |
} |
| 362 |
else { |
| 363 |
$res .= $u7; |
| 364 |
} |
| 365 |
} |
| 366 |
|
| 367 |
return $res; |
| 368 |
} |
| 369 |
|
| 370 |
public static function utf16_to_utf8($str) |
| 371 |
{ |
| 372 |
$len = strlen($str); |
| 373 |
$dec = ''; |
| 374 |
|
| 375 |
for ($i = 0; $i < $len; $i += 2) { |
| 376 |
$c = ord($str[$i]) << 8 | ord($str[$i + 1]); |
| 377 |
if ($c >= 0x0001 && $c <= 0x007F) { |
| 378 |
$dec .= chr($c); |
| 379 |
} |
| 380 |
else if ($c > 0x07FF) { |
| 381 |
$dec .= chr(0xE0 | (($c >> 12) & 0x0F)); |
| 382 |
$dec .= chr(0x80 | (($c >> 6) & 0x3F)); |
| 383 |
$dec .= chr(0x80 | (($c >> 0) & 0x3F)); |
| 384 |
} |
| 385 |
else { |
| 386 |
$dec .= chr(0xC0 | (($c >> 6) & 0x1F)); |
| 387 |
$dec .= chr(0x80 | (($c >> 0) & 0x3F)); |
| 388 |
} |
| 389 |
} |
| 390 |
|
| 391 |
return $dec; |
| 392 |
} |
| 393 |
|
| 394 |
public static function utf7imap_to_utf8($str) |
| 395 |
{ |
| 396 |
$Index_64 = array( |
| 397 |
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, |
| 398 |
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, |
| 399 |
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,62, 63,-1,-1,-1, |
| 400 |
52,53,54,55, 56,57,58,59, 60,61,-1,-1, -1,-1,-1,-1, |
| 401 |
-1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,10, 11,12,13,14, |
| 402 |
15,16,17,18, 19,20,21,22, 23,24,25,-1, -1,-1,-1,-1, |
| 403 |
-1,26,27,28, 29,30,31,32, 33,34,35,36, 37,38,39,40, |
| 404 |
41,42,43,44, 45,46,47,48, 49,50,51,-1, -1,-1,-1,-1 |
| 405 |
); |
| 406 |
|
| 407 |
$u7len = strlen($str); |
| 408 |
$str = strval($str); |
| 409 |
$p = ''; |
| 410 |
$err = ''; |
| 411 |
|
| 412 |
for ($i=0; $u7len > 0; $i++, $u7len--) { |
| 413 |
$u7 = $str[$i]; |
| 414 |
if ($u7 == '&') { |
| 415 |
$i++; |
| 416 |
$u7len--; |
| 417 |
$u7 = $str[$i]; |
| 418 |
|
| 419 |
if ($u7len && $u7 == '-') { |
| 420 |
$p .= '&'; |
| 421 |
continue; |
| 422 |
} |
| 423 |
|
| 424 |
$ch = 0; |
| 425 |
$k = 10; |
| 426 |
for (; $u7len > 0; $i++, $u7len--) { |
| 427 |
$u7 = $str[$i]; |
| 428 |
|
| 429 |
if ((ord($u7) & 0x80) || ($b = $Index_64[ord($u7)]) == -1) { |
| 430 |
break; |
| 431 |
} |
| 432 |
|
| 433 |
if ($k > 0) { |
| 434 |
$ch |= $b << $k; |
| 435 |
$k -= 6; |
| 436 |
} |
| 437 |
else { |
| 438 |
$ch |= $b >> (-$k); |
| 439 |
if ($ch < 0x80) { |
| 440 |
if (0x20 <= $ch && $ch < 0x7f) { |
| 441 |
return $err; |
| 442 |
} |
| 443 |
$p .= chr($ch); |
| 444 |
} |
| 445 |
else if ($ch < 0x800) { |
| 446 |
$p .= chr(0xc0 | ($ch >> 6)); |
| 447 |
$p .= chr(0x80 | ($ch & 0x3f)); |
| 448 |
} |
| 449 |
else { |
| 450 |
$p .= chr(0xe0 | ($ch >> 12)); |
| 451 |
$p .= chr(0x80 | (($ch >> 6) & 0x3f)); |
| 452 |
$p .= chr(0x80 | ($ch & 0x3f)); |
| 453 |
} |
| 454 |
|
| 455 |
$ch = ($b << (16 + $k)) & 0xffff; |
| 456 |
$k += 10; |
| 457 |
} |
| 458 |
} |
| 459 |
|
| 460 |
if ($ch || $k < 6) { |
| 461 |
return $err; |
| 462 |
} |
| 463 |
|
| 464 |
if (!$u7len || $u7 != '-') { |
| 465 |
return $err; |
| 466 |
} |
| 467 |
|
| 468 |
if ($u7len > 2 && $str[$i+1] == '&' && $str[$i+2] != '-') { |
| 469 |
return $err; |
| 470 |
} |
| 471 |
} |
| 472 |
else if (ord($u7) < 0x20 || ord($u7) >= 0x7f) { |
| 473 |
return $err; |
| 474 |
} |
| 475 |
else { |
| 476 |
$p .= $u7; |
| 477 |
} |
| 478 |
} |
| 479 |
|
| 480 |
return $p; |
| 481 |
} |
| 482 |
|
| 483 |
public static function utf8_to_utf7imap($str) |
| 484 |
{ |
| 485 |
$B64Chars = array( |
| 486 |
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', |
| 487 |
'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd', |
| 488 |
'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', |
| 489 |
't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7', |
| 490 |
'8', '9', '+', ',' |
| 491 |
); |
| 492 |
|
| 493 |
$u8len = strlen($str); |
| 494 |
$base64 = 0; |
| 495 |
$i = 0; |
| 496 |
$p = ''; |
| 497 |
$err = ''; |
| 498 |
|
| 499 |
while ($u8len) { |
| 500 |
$u8 = $str[$i]; |
| 501 |
$c = ord($u8); |
| 502 |
|
| 503 |
if ($c < 0x80) { |
| 504 |
$ch = $c; |
| 505 |
$n = 0; |
| 506 |
} |
| 507 |
else if ($c < 0xc2) { |
| 508 |
return $err; |
| 509 |
} |
| 510 |
else if ($c < 0xe0) { |
| 511 |
$ch = $c & 0x1f; |
| 512 |
$n = 1; |
| 513 |
} |
| 514 |
else if ($c < 0xf0) { |
| 515 |
$ch = $c & 0x0f; |
| 516 |
$n = 2; |
| 517 |
} |
| 518 |
else if ($c < 0xf8) { |
| 519 |
$ch = $c & 0x07; |
| 520 |
$n = 3; |
| 521 |
} |
| 522 |
else if ($c < 0xfc) { |
| 523 |
$ch = $c & 0x03; |
| 524 |
$n = 4; |
| 525 |
} |
| 526 |
else if ($c < 0xfe) { |
| 527 |
$ch = $c & 0x01; |
| 528 |
$n = 5; |
| 529 |
} |
| 530 |
else { |
| 531 |
return $err; |
| 532 |
} |
| 533 |
|
| 534 |
$i++; |
| 535 |
$u8len--; |
| 536 |
|
| 537 |
if ($n > $u8len) { |
| 538 |
return $err; |
| 539 |
} |
| 540 |
|
| 541 |
for ($j=0; $j < $n; $j++) { |
| 542 |
$o = ord($str[$i+$j]); |
| 543 |
if (($o & 0xc0) != 0x80) { |
| 544 |
return $err; |
| 545 |
} |
| 546 |
$ch = ($ch << 6) | ($o & 0x3f); |
| 547 |
} |
| 548 |
|
| 549 |
if ($n > 1 && !($ch >> ($n * 5 + 1))) { |
| 550 |
return $err; |
| 551 |
} |
| 552 |
|
| 553 |
$i += $n; |
| 554 |
$u8len -= $n; |
| 555 |
|
| 556 |
if ($ch < 0x20 || $ch >= 0x7f) { |
| 557 |
if (!$base64) { |
| 558 |
$p .= '&'; |
| 559 |
$base64 = 1; |
| 560 |
$b = 0; |
| 561 |
$k = 10; |
| 562 |
} |
| 563 |
if ($ch & ~0xffff) { |
| 564 |
$ch = 0xfffe; |
| 565 |
} |
| 566 |
|
| 567 |
$p .= $B64Chars[($b | $ch >> $k)]; |
| 568 |
$k -= 6; |
| 569 |
for (; $k >= 0; $k -= 6) { |
| 570 |
$p .= $B64Chars[(($ch >> $k) & 0x3f)]; |
| 571 |
} |
| 572 |
|
| 573 |
$b = ($ch << (-$k)) & 0x3f; |
| 574 |
$k += 16; |
| 575 |
} |
| 576 |
else { |
| 577 |
if ($base64) { |
| 578 |
if ($k > 10) { |
| 579 |
$p .= $B64Chars[$b]; |
| 580 |
} |
| 581 |
$p .= '-'; |
| 582 |
$base64 = 0; |
| 583 |
} |
| 584 |
|
| 585 |
$p .= chr($ch); |
| 586 |
if (chr($ch) == '&') { |
| 587 |
$p .= '-'; |
| 588 |
} |
| 589 |
} |
| 590 |
} |
| 591 |
|
| 592 |
if ($base64) { |
| 593 |
if ($k > 10) { |
| 594 |
$p .= $B64Chars[$b]; |
| 595 |
} |
| 596 |
$p .= '-'; |
| 597 |
} |
| 598 |
|
| 599 |
return $p; |
| 600 |
} |
| 601 |
|
| 602 |
public static function detect($string, $failover = null, $language = null) |
| 603 |
{ |
| 604 |
if (substr($string, 0, 4) == "\0\0\xFE\xFF") return 'UTF-32BE'; // Big Endian |
| 605 |
if (substr($string, 0, 4) == "\xFF\xFE\0\0") return 'UTF-32LE'; // Little Endian |
| 606 |
if (substr($string, 0, 2) == "\xFE\xFF") return 'UTF-16BE'; // Big Endian |
| 607 |
if (substr($string, 0, 2) == "\xFF\xFE") return 'UTF-16LE'; // Little Endian |
| 608 |
if (substr($string, 0, 3) == "\xEF\xBB\xBF") return 'UTF-8'; |
| 609 |
|
| 610 |
if ($string[0] == "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-32BE'; |
| 611 |
if ($string[0] != "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] == "\0") return 'UTF-32LE'; |
| 612 |
if ($string[0] == "\0" && $string[1] != "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-16BE'; |
| 613 |
if ($string[0] != "\0" && $string[1] == "\0" && $string[2] != "\0" && $string[3] == "\0") return 'UTF-16LE'; |
| 614 |
|
| 615 |
if (empty($language)) { |
| 616 |
$rcube = rcube::get_instance(); |
| 617 |
$language = $rcube->get_user_language(); |
| 618 |
} |
| 619 |
|
| 620 |
switch ($language) { |
| 621 |
case 'ja_JP': |
| 622 |
$prio = array('ISO-2022-JP', 'JIS', 'UTF-8', 'EUC-JP', 'eucJP-win', 'SJIS', 'SJIS-win'); |
| 623 |
break; |
| 624 |
|
| 625 |
case 'zh_CN': |
| 626 |
case 'zh_TW': |
| 627 |
$prio = array('UTF-8', 'BIG-5', 'GB2312', 'EUC-TW'); |
| 628 |
break; |
| 629 |
|
| 630 |
case 'ko_KR': |
| 631 |
$prio = array('UTF-8', 'EUC-KR', 'ISO-2022-KR'); |
| 632 |
break; |
| 633 |
|
| 634 |
case 'ru_RU': |
| 635 |
$prio = array('UTF-8', 'WINDOWS-1251', 'KOI8-R'); |
| 636 |
break; |
| 637 |
|
| 638 |
case 'tr_TR': |
| 639 |
$prio = array('UTF-8', 'ISO-8859-9', 'WINDOWS-1254'); |
| 640 |
break; |
| 641 |
} |
| 642 |
|
| 643 |
if ($prio && function_exists('mb_check_encoding')) { |
| 644 |
foreach ($prio as $encoding) { |
| 645 |
if (mb_check_encoding($string, $encoding)) { |
| 646 |
return $encoding; |
| 647 |
} |
| 648 |
} |
| 649 |
} |
| 650 |
|
| 651 |
if (function_exists('mb_detect_encoding')) { |
| 652 |
if (!$prio) { |
| 653 |
$prio = array('UTF-8', 'SJIS', 'GB2312', |
| 654 |
'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4', |
| 655 |
'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9', |
| 656 |
'ISO-8859-10', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16', |
| 657 |
'WINDOWS-1252', 'WINDOWS-1251', 'EUC-JP', 'EUC-TW', 'KOI8-R', 'BIG-5', |
| 658 |
'ISO-2022-KR', 'ISO-2022-JP', |
| 659 |
); |
| 660 |
} |
| 661 |
|
| 662 |
$encodings = array_unique(array_merge($prio, mb_list_encodings())); |
| 663 |
|
| 664 |
if ($encoding = mb_detect_encoding($string, $encodings)) { |
| 665 |
return $encoding; |
| 666 |
} |
| 667 |
} |
| 668 |
|
| 669 |
if (preg_match('/\A( |
| 670 |
[\x09\x0A\x0D\x20-\x7E] |
| 671 |
| [\xC2-\xDF][\x80-\xBF] |
| 672 |
| \xE0[\xA0-\xBF][\x80-\xBF] |
| 673 |
| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} |
| 674 |
| \xED[\x80-\x9F][\x80-\xBF] |
| 675 |
| \xF0[\x90-\xBF][\x80-\xBF]{2} |
| 676 |
| [\xF1-\xF3][\x80-\xBF]{3} |
| 677 |
| \xF4[\x80-\x8F][\x80-\xBF]{2} |
| 678 |
)*\z/xs', substr($string, 0, 2048)) |
| 679 |
) { |
| 680 |
return 'UTF-8'; |
| 681 |
} |
| 682 |
|
| 683 |
return $failover; |
| 684 |
} |
| 685 |
|
| 686 |
public static function clean($input) |
| 687 |
{ |
| 688 |
if (is_array($input)) { |
| 689 |
foreach ($input as $idx => $val) { |
| 690 |
$input[$idx] = self::clean($val); |
| 691 |
} |
| 692 |
return $input; |
| 693 |
} |
| 694 |
|
| 695 |
if (!is_string($input) || $input == '') { |
| 696 |
return $input; |
| 697 |
} |
| 698 |
|
| 699 |
if (function_exists('mb_convert_encoding')) { |
| 700 |
$msch = mb_substitute_character(); |
| 701 |
mb_substitute_character('none'); |
| 702 |
$res = mb_convert_encoding($input, 'UTF-8', 'UTF-8'); |
| 703 |
mb_substitute_character($msch); |
| 704 |
|
| 705 |
if ($res !== false) { |
| 706 |
return $res; |
| 707 |
} |
| 708 |
} |
| 709 |
|
| 710 |
if (function_exists('iconv')) { |
| 711 |
if (($res = @iconv('UTF-8', 'UTF-8//IGNORE', $input)) !== false) { |
| 712 |
return $res; |
| 713 |
} |
| 714 |
} |
| 715 |
|
| 716 |
$seq = ''; |
| 717 |
$out = ''; |
| 718 |
$regexp = '/^('. |
| 719 |
'|[\xC2-\xDF][\x80-\xBF]'. // UTF8-2 |
| 720 |
'|\xE0[\xA0-\xBF][\x80-\xBF]'. // UTF8-3 |
| 721 |
'|[\xE1-\xEC][\x80-\xBF][\x80-\xBF]'. // UTF8-3 |
| 722 |
'|\xED[\x80-\x9F][\x80-\xBF]'. // UTF8-3 |
| 723 |
'|[\xEE-\xEF][\x80-\xBF][\x80-\xBF]'. // UTF8-3 |
| 724 |
'|\xF0[\x90-\xBF][\x80-\xBF][\x80-\xBF]'. // UTF8-4 |
| 725 |
'|[\xF1-\xF3][\x80-\xBF][\x80-\xBF][\x80-\xBF]'.// UTF8-4 |
| 726 |
'|\xF4[\x80-\x8F][\x80-\xBF][\x80-\xBF]'. // UTF8-4 |
| 727 |
')$/'; |
| 728 |
|
| 729 |
for ($i = 0, $len = strlen($input); $i < $len; $i++) { |
| 730 |
$chr = $input[$i]; |
| 731 |
$ord = ord($chr); |
| 732 |
|
| 733 |
if ($ord <= 0x7F) { |
| 734 |
if ($seq !== '') { |
| 735 |
$out .= preg_match($regexp, $seq) ? $seq : ''; |
| 736 |
$seq = ''; |
| 737 |
} |
| 738 |
|
| 739 |
$out .= $chr; |
| 740 |
} |
| 741 |
else if ($ord >= 0xC0) { |
| 742 |
if ($seq !== '') { |
| 743 |
$out .= preg_match($regexp, $seq) ? $seq : ''; |
| 744 |
$seq = ''; |
| 745 |
} |
| 746 |
|
| 747 |
$seq = $chr; |
| 748 |
} |
| 749 |
else if ($seq !== '') { |
| 750 |
$seq .= $chr; |
| 751 |
} |
| 752 |
} |
| 753 |
|
| 754 |
if ($seq !== '') { |
| 755 |
$out .= preg_match($regexp, $seq) ? $seq : ''; |
| 756 |
} |
| 757 |
|
| 758 |
return $out; |
| 759 |
} |
| 760 |
} |
| 761 |
|
