Page MenuHomePhorge
Files F224219

No OneTemporary
Actions

View Options

diff --git a/program/include/rcube_charset.php b/program/include/rcube_charset.php
index ff4c2bbce..e6da882ac 100644
--- a/program/include/rcube_charset.php
+++ b/program/include/rcube_charset.php
@@ -1,763 +1,790 @@
<?php
/*
+-----------------------------------------------------------------------+
| program/include/rcube_charset.php |
| |
| This file is part of the Roundcube Webmail client |
| Copyright (C) 2005-2012, The Roundcube Dev Team |
| Copyright (C) 2011-2012, Kolab Systems AG |
| Copyright (C) 2000 Edmund Grimley Evans <edmundo@rano.org> |
| |
| Licensed under the GNU General Public License version 3 or |
| any later version with exceptions for skins & plugins. |
| See the README file for a full license statement. |
| |
| PURPOSE: |
| Provide charset conversion functionality |
| |
+-----------------------------------------------------------------------+
| Author: Thomas Bruederli <roundcube@gmail.com> |
| Author: Aleksander Machniak <alec@alec.pl> |
+-----------------------------------------------------------------------+
*/
/**
* Character sets conversion functionality
*
* @package Core
* @author Thomas Bruederli <roundcube@gmail.com>
* @author Aleksander Machniak <alec@alec.pl>
* @author Edmund Grimley Evans <edmundo@rano.org>
*/
class rcube_charset
{
// Aliases: some of them from HTML5 spec.
static public $aliases = array(
'USASCII' => 'WINDOWS-1252',
'ANSIX31101983' => 'WINDOWS-1252',
'ANSIX341968' => 'WINDOWS-1252',
'UNKNOWN8BIT' => 'ISO-8859-15',
'UNKNOWN' => 'ISO-8859-15',
'USERDEFINED' => 'ISO-8859-15',
'KSC56011987' => 'EUC-KR',
'GB2312' => 'GBK',
'GB231280' => 'GBK',
'UNICODE' => 'UTF-8',
'UTF7IMAP' => 'UTF7-IMAP',
'TIS620' => 'WINDOWS-874',
'ISO88599' => 'WINDOWS-1254',
'ISO885911' => 'WINDOWS-874',
'MACROMAN' => 'MACINTOSH',
'77' => 'MAC',
'128' => 'SHIFT-JIS',
'129' => 'CP949',
'130' => 'CP1361',
'134' => 'GBK',
'136' => 'BIG5',
'161' => 'WINDOWS-1253',
'162' => 'WINDOWS-1254',
'163' => 'WINDOWS-1258',
'177' => 'WINDOWS-1255',
'178' => 'WINDOWS-1256',
'186' => 'WINDOWS-1257',
'204' => 'WINDOWS-1251',
'222' => 'WINDOWS-874',
'238' => 'WINDOWS-1250',
'MS950' => 'CP950',
'WINDOWS949' => 'UHC',
);
/**
* Catch an error and throw an exception.
*
* @param int Level of the error
* @param string Error message
*/
public static function error_handler($errno, $errstr)
{
throw new ErrorException($errstr, 0, $errno);
}
/**
* Parse and validate charset name string (see #1485758).
* Sometimes charset string is malformed, there are also charset aliases
* but we need strict names for charset conversion (specially utf8 class)
*
* @param string $input Input charset name
*
* @return string The validated charset name
*/
public static function parse_charset($input)
{
static $charsets = array();
$charset = strtoupper($input);
if (isset($charsets[$input])) {
return $charsets[$input];
}
$charset = preg_replace(array(
'/^[^0-9A-Z]+/', // e.g. _ISO-8859-JP$SIO
'/\$.*$/', // e.g. _ISO-8859-JP$SIO
'/UNICODE-1-1-*/', // RFC1641/1642
'/^X-/', // X- prefix (e.g. X-ROMAN8 => ROMAN8)
), '', $charset);
if ($charset == 'BINARY') {
return $charsets[$input] = null;
}
// allow A-Z and 0-9 only
$str = preg_replace('/[^A-Z0-9]/', '', $charset);
if (isset(self::$aliases[$str])) {
$result = self::$aliases[$str];
}
// UTF
else if (preg_match('/U[A-Z][A-Z](7|8|16|32)(BE|LE)*/', $str, $m)) {
$result = 'UTF-' . $m[1] . $m[2];
}
// ISO-8859
else if (preg_match('/ISO8859([0-9]{0,2})/', $str, $m)) {
$iso = 'ISO-8859-' . ($m[1] ? $m[1] : 1);
// some clients sends windows-1252 text as latin1,
// it is safe to use windows-1252 for all latin1
$result = $iso == 'ISO-8859-1' ? 'WINDOWS-1252' : $iso;
}
// handle broken charset names e.g. WINDOWS-1250HTTP-EQUIVCONTENT-TYPE
else if (preg_match('/(WIN|WINDOWS)([0-9]+)/', $str, $m)) {
$result = 'WINDOWS-' . $m[2];
}
// LATIN
else if (preg_match('/LATIN(.*)/', $str, $m)) {
$aliases = array('2' => 2, '3' => 3, '4' => 4, '5' => 9, '6' => 10,
'7' => 13, '8' => 14, '9' => 15, '10' => 16,
'ARABIC' => 6, 'CYRILLIC' => 5, 'GREEK' => 7, 'GREEK1' => 7, 'HEBREW' => 8
);
// some clients sends windows-1252 text as latin1,
// it is safe to use windows-1252 for all latin1
if ($m[1] == 1) {
$result = 'WINDOWS-1252';
}
// if iconv is not supported we need ISO labels, it's also safe for iconv
else if (!empty($aliases[$m[1]])) {
$result = 'ISO-8859-'.$aliases[$m[1]];
}
// iconv requires convertion of e.g. LATIN-1 to LATIN1
else {
$result = $str;
}
}
else {
$result = $charset;
}
$charsets[$input] = $result;
return $result;
}
/**
* Convert a string from one charset to another.
* Uses mbstring and iconv functions if possible
*
* @param string Input string
* @param string Suspected charset of the input string
* @param string Target charset to convert to; defaults to RCMAIL_CHARSET
*
* @return string Converted string
*/
public static function convert($str, $from, $to = null)
{
static $iconv_options = null;
static $mbstring_list = null;
static $mbstring_sch = null;
static $conv = null;
$to = empty($to) ? RCMAIL_CHARSET : $to;
$from = self::parse_charset($from);
// It is a common case when UTF-16 charset is used with US-ASCII content (#1488654)
// In that case we can just skip the conversion (use UTF-8)
if ($from == 'UTF-16' && !preg_match('/[^\x00-\x7F]/', $str)) {
$from = 'UTF-8';
}
if ($from == $to || empty($str) || empty($from)) {
return $str;
}
if ($iconv_options === null) {
if (function_exists('iconv')) {
// ignore characters not available in output charset
$iconv_options = '//IGNORE';
if (iconv('', $iconv_options, '') === false) {
// iconv implementation does not support options
$iconv_options = '';
}
}
}
// convert charset using iconv module
if ($iconv_options !== null && $from != 'UTF7-IMAP' && $to != 'UTF7-IMAP') {
// throw an exception if iconv reports an illegal character in input
// it means that input string has been truncated
set_error_handler(array('rcube_charset', 'error_handler'), E_NOTICE);
try {
$_iconv = iconv($from, $to . $iconv_options, $str);
} catch (ErrorException $e) {
$_iconv = false;
}
restore_error_handler();
if ($_iconv !== false) {
return $_iconv;
}
}
if ($mbstring_list === null) {
if (extension_loaded('mbstring')) {
$mbstring_sch = mb_substitute_character();
$mbstring_list = mb_list_encodings();
$mbstring_list = array_map('strtoupper', $mbstring_list);
}
}
// convert charset using mbstring module
if ($mbstring_list !== null) {
$aliases['WINDOWS-1257'] = 'ISO-8859-13';
// it happens that mbstring supports ASCII but not US-ASCII
if (($from == 'US-ASCII' || $to == 'US-ASCII') && !in_array('US-ASCII', $mbstring_list)) {
$aliases['US-ASCII'] = 'ASCII';
}
$mb_from = $aliases[$from] ? $aliases[$from] : $from;
$mb_to = $aliases[$to] ? $aliases[$to] : $to;
// return if encoding found, string matches encoding and convert succeeded
if (in_array($mb_from, $mbstring_list) && in_array($mb_to, $mbstring_list)) {
if (mb_check_encoding($str, $mb_from)) {
// Do the same as //IGNORE with iconv
mb_substitute_character('none');
$out = mb_convert_encoding($str, $mb_to, $mb_from);
mb_substitute_character($mbstring_sch);
if ($out !== false) {
return $out;
}
}
}
}
// convert charset using bundled classes/functions
if ($to == 'UTF-8') {
if ($from == 'UTF7-IMAP') {
if ($_str = self::utf7imap_to_utf8($str)) {
return $_str;
}
}
else if ($from == 'UTF-7') {
if ($_str = self::utf7_to_utf8($str)) {
return $_str;
}
}
else if ($from == 'ISO-8859-1' && function_exists('utf8_encode')) {
return utf8_encode($str);
}
else if (class_exists('utf8')) {
if (!$conv) {
$conv = new utf8($from);
}
else {
$conv->loadCharset($from);
}
if ($_str = $conv->strToUtf8($str)) {
return $_str;
}
}
}
// encode string for output
if ($from == 'UTF-8') {
// @TODO: we need a function for UTF-7 (RFC2152) conversion
if ($to == 'UTF7-IMAP' || $to == 'UTF-7') {
if ($_str = self::utf8_to_utf7imap($str)) {
return $_str;
}
}
else if ($to == 'ISO-8859-1' && function_exists('utf8_decode')) {
return utf8_decode($str);
}
else if (class_exists('utf8')) {
if (!$conv) {
$conv = new utf8($to);
}
else {
$conv->loadCharset($from);
}
if ($_str = $conv->strToUtf8($str)) {
return $_str;
}
}
}
// return original string
return $str;
}
/**
* Converts string from standard UTF-7 (RFC 2152) to UTF-8.
*
* @param string Input string (UTF-7)
*
* @return string Converted string (UTF-8)
*/
public static function utf7_to_utf8($str)
{
$Index_64 = array(
0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
0,0,0,0, 0,0,0,0, 0,0,0,1, 0,0,0,0,
1,1,1,1, 1,1,1,1, 1,1,0,0, 0,0,0,0,
0,1,1,1, 1,1,1,1, 1,1,1,1, 1,1,1,1,
1,1,1,1, 1,1,1,1, 1,1,1,0, 0,0,0,0,
0,1,1,1, 1,1,1,1, 1,1,1,1, 1,1,1,1,
1,1,1,1, 1,1,1,1, 1,1,1,0, 0,0,0,0,
);
$u7len = strlen($str);
$str = strval($str);
$res = '';
for ($i=0; $u7len > 0; $i++, $u7len--) {
$u7 = $str[$i];
if ($u7 == '+') {
$i++;
$u7len--;
$ch = '';
for (; $u7len > 0; $i++, $u7len--) {
$u7 = $str[$i];
if (!$Index_64[ord($u7)]) {
break;
}
$ch .= $u7;
}
if ($ch == '') {
if ($u7 == '-') {
$res .= '+';
}
continue;
}
$res .= self::utf16_to_utf8(base64_decode($ch));
}
else {
$res .= $u7;
}
}
return $res;
}
/**
* Converts string from UTF-16 to UTF-8 (helper for utf-7 to utf-8 conversion)
*
* @param string Input string
*
* @return string The converted string
*/
public static function utf16_to_utf8($str)
{
$len = strlen($str);
$dec = '';
for ($i = 0; $i < $len; $i += 2) {
$c = ord($str[$i]) << 8 | ord($str[$i + 1]);
if ($c >= 0x0001 && $c <= 0x007F) {
$dec .= chr($c);
}
else if ($c > 0x07FF) {
$dec .= chr(0xE0 | (($c >> 12) & 0x0F));
$dec .= chr(0x80 | (($c >> 6) & 0x3F));
$dec .= chr(0x80 | (($c >> 0) & 0x3F));
}
else {
$dec .= chr(0xC0 | (($c >> 6) & 0x1F));
$dec .= chr(0x80 | (($c >> 0) & 0x3F));
}
}
return $dec;
}
/**
* Convert the data ($str) from RFC 2060's UTF-7 to UTF-8.
* If input data is invalid, return the original input string.
* RFC 2060 obviously intends the encoding to be unique (see
* point 5 in section 5.1.3), so we reject any non-canonical
* form, such as &ACY- (instead of &-) or &AMA-&AMA- (instead
* of &AMAAwA-).
*
* Translated from C to PHP by Thomas Bruederli <roundcube@gmail.com>
*
* @param string $str Input string (UTF7-IMAP)
*
* @return string Output string (UTF-8)
*/
public static function utf7imap_to_utf8($str)
{
$Index_64 = array(
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,62, 63,-1,-1,-1,
52,53,54,55, 56,57,58,59, 60,61,-1,-1, -1,-1,-1,-1,
-1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,10, 11,12,13,14,
15,16,17,18, 19,20,21,22, 23,24,25,-1, -1,-1,-1,-1,
-1,26,27,28, 29,30,31,32, 33,34,35,36, 37,38,39,40,
41,42,43,44, 45,46,47,48, 49,50,51,-1, -1,-1,-1,-1
);
$u7len = strlen($str);
$str = strval($str);
$p = '';
$err = '';
for ($i=0; $u7len > 0; $i++, $u7len--) {
$u7 = $str[$i];
if ($u7 == '&') {
$i++;
$u7len--;
$u7 = $str[$i];
if ($u7len && $u7 == '-') {
$p .= '&';
continue;
}
$ch = 0;
$k = 10;
for (; $u7len > 0; $i++, $u7len--) {
$u7 = $str[$i];
if ((ord($u7) & 0x80) || ($b = $Index_64[ord($u7)]) == -1) {
break;
}
if ($k > 0) {
$ch |= $b << $k;
$k -= 6;
}
else {
$ch |= $b >> (-$k);
if ($ch < 0x80) {
// Printable US-ASCII
if (0x20 <= $ch && $ch < 0x7f) {
return $err;
}
$p .= chr($ch);
}
else if ($ch < 0x800) {
$p .= chr(0xc0 | ($ch >> 6));
$p .= chr(0x80 | ($ch & 0x3f));
}
else {
$p .= chr(0xe0 | ($ch >> 12));
$p .= chr(0x80 | (($ch >> 6) & 0x3f));
$p .= chr(0x80 | ($ch & 0x3f));
}
$ch = ($b << (16 + $k)) & 0xffff;
$k += 10;
}
}
// Non-zero or too many extra bits
if ($ch || $k < 6) {
return $err;
}
// BASE64 not properly terminated
if (!$u7len || $u7 != '-') {
return $err;
}
// Adjacent BASE64 sections
if ($u7len > 2 && $str[$i+1] == '&' && $str[$i+2] != '-') {
return $err;
}
}
// Not printable US-ASCII
else if (ord($u7) < 0x20 || ord($u7) >= 0x7f) {
return $err;
}
else {
$p .= $u7;
}
}
return $p;
}
/**
* Convert the data ($str) from UTF-8 to RFC 2060's UTF-7.
* Unicode characters above U+FFFF are replaced by U+FFFE.
* If input data is invalid, return an empty string.
*
* Translated from C to PHP by Thomas Bruederli <roundcube@gmail.com>
*
* @param string $str Input string (UTF-8)
*
* @return string Output string (UTF7-IMAP)
*/
public static function utf8_to_utf7imap($str)
{
$B64Chars = array(
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O',
'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd',
'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's',
't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7',
'8', '9', '+', ','
);
$u8len = strlen($str);
$base64 = 0;
$i = 0;
$p = '';
$err = '';
while ($u8len) {
$u8 = $str[$i];
$c = ord($u8);
if ($c < 0x80) {
$ch = $c;
$n = 0;
}
else if ($c < 0xc2) {
return $err;
}
else if ($c < 0xe0) {
$ch = $c & 0x1f;
$n = 1;
}
else if ($c < 0xf0) {
$ch = $c & 0x0f;
$n = 2;
}
else if ($c < 0xf8) {
$ch = $c & 0x07;
$n = 3;
}
else if ($c < 0xfc) {
$ch = $c & 0x03;
$n = 4;
}
else if ($c < 0xfe) {
$ch = $c & 0x01;
$n = 5;
}
else {
return $err;
}
$i++;
$u8len--;
if ($n > $u8len) {
return $err;
}
for ($j=0; $j < $n; $j++) {
$o = ord($str[$i+$j]);
if (($o & 0xc0) != 0x80) {
return $err;
}
$ch = ($ch << 6) | ($o & 0x3f);
}
if ($n > 1 && !($ch >> ($n * 5 + 1))) {
return $err;
}
$i += $n;
$u8len -= $n;
if ($ch < 0x20 || $ch >= 0x7f) {
if (!$base64) {
$p .= '&';
$base64 = 1;
$b = 0;
$k = 10;
}
if ($ch & ~0xffff) {
$ch = 0xfffe;
}
$p .= $B64Chars[($b | $ch >> $k)];
$k -= 6;
for (; $k >= 0; $k -= 6) {
$p .= $B64Chars[(($ch >> $k) & 0x3f)];
}
$b = ($ch << (-$k)) & 0x3f;
$k += 16;
}
else {
if ($base64) {
if ($k > 10) {
$p .= $B64Chars[$b];
}
$p .= '-';
$base64 = 0;
}
$p .= chr($ch);
if (chr($ch) == '&') {
$p .= '-';
}
}
}
if ($base64) {
if ($k > 10) {
$p .= $B64Chars[$b];
}
$p .= '-';
}
return $p;
}
/**
* A method to guess character set of a string.
*
* @param string $string String.
* @param string $failover Default result for failover.
*
* @return string Charset name
*/
public static function detect($string, $failover='')
{
- if (!function_exists('mb_detect_encoding')) {
- return $failover;
- }
-
- // FIXME: the order is important, because sometimes
- // iso string is detected as euc-jp and etc.
- $enc = array(
- 'UTF-8', 'SJIS', 'BIG5', 'GB2312',
- 'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4',
- 'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9',
- 'ISO-8859-10', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16',
- 'WINDOWS-1252', 'WINDOWS-1251', 'EUC-JP', 'EUC-TW', 'KOI8-R',
- 'ISO-2022-KR', 'ISO-2022-JP'
- );
+ if (substr($string, 0, 4) == "\0\0\xFE\xFF") return 'UTF-32BE'; // Big Endian
+ if (substr($string, 0, 4) == "\xFF\xFE\0\0") return 'UTF-32LE'; // Little Endian
+ if (substr($string, 0, 2) == "\xFE\xFF") return 'UTF-16BE'; // Big Endian
+ if (substr($string, 0, 2) == "\xFF\xFE") return 'UTF-16LE'; // Little Endian
+ if (substr($string, 0, 3) == "\xEF\xBB\xBF") return 'UTF-8';
+
+ // heuristics
+ if ($string[0] == "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-32BE';
+ if ($string[0] != "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] == "\0") return 'UTF-32LE';
+ if ($string[0] == "\0" && $string[1] != "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-16BE';
+ if ($string[0] != "\0" && $string[1] == "\0" && $string[2] != "\0" && $string[3] == "\0") return 'UTF-16LE';
+
+ if (function_exists('mb_detect_encoding')) {
+ // FIXME: the order is important, because sometimes
+ // iso string is detected as euc-jp and etc.
+ $enc = array(
+ 'UTF-8', 'SJIS', 'BIG5', 'GB2312',
+ 'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4',
+ 'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9',
+ 'ISO-8859-10', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16',
+ 'WINDOWS-1252', 'WINDOWS-1251', 'EUC-JP', 'EUC-TW', 'KOI8-R',
+ 'ISO-2022-KR', 'ISO-2022-JP'
+ );
- $result = mb_detect_encoding($string, join(',', $enc));
+ $result = mb_detect_encoding($string, join(',', $enc));
+ }
+ else {
+ // No match, check for UTF-8
+ // from http://w3.org/International/questions/qa-forms-utf-8.html
+ if (preg_match('/\A(
+ [\x09\x0A\x0D\x20-\x7E]
+ | [\xC2-\xDF][\x80-\xBF]
+ | \xE0[\xA0-\xBF][\x80-\xBF]
+ | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}
+ | \xED[\x80-\x9F][\x80-\xBF]
+ | \xF0[\x90-\xBF][\x80-\xBF]{2}
+ | [\xF1-\xF3][\x80-\xBF]{3}
+ | \xF4[\x80-\x8F][\x80-\xBF]{2}
+ )*\z/xs', substr($string, 0, 2048))
+ ) {
+ return 'UTF-8';
+ }
+ }
return $result ? $result : $failover;
}
/**
* Removes non-unicode characters from input.
*
* @param mixed $input String or array.
*
* @return mixed String or array
*/
public static function clean($input)
{
// handle input of type array
if (is_array($input)) {
foreach ($input as $idx => $val) {
$input[$idx] = self::clean($val);
}
return $input;
}
if (!is_string($input) || $input == '') {
return $input;
}
// iconv/mbstring are much faster (especially with long strings)
if (function_exists('mb_convert_encoding')) {
if (($res = mb_convert_encoding($input, 'UTF-8', 'UTF-8')) !== false) {
return $res;
}
}
if (function_exists('iconv')) {
if (($res = @iconv('UTF-8', 'UTF-8//IGNORE', $input)) !== false) {
return $res;
}
}
$seq = '';
$out = '';
$regexp = '/^('.
// '[\x00-\x7F]'. // UTF8-1
'|[\xC2-\xDF][\x80-\xBF]'. // UTF8-2
'|\xE0[\xA0-\xBF][\x80-\xBF]'. // UTF8-3
'|[\xE1-\xEC][\x80-\xBF][\x80-\xBF]'. // UTF8-3
'|\xED[\x80-\x9F][\x80-\xBF]'. // UTF8-3
'|[\xEE-\xEF][\x80-\xBF][\x80-\xBF]'. // UTF8-3
'|\xF0[\x90-\xBF][\x80-\xBF][\x80-\xBF]'. // UTF8-4
'|[\xF1-\xF3][\x80-\xBF][\x80-\xBF][\x80-\xBF]'.// UTF8-4
'|\xF4[\x80-\x8F][\x80-\xBF][\x80-\xBF]'. // UTF8-4
')$/';
for ($i = 0, $len = strlen($input); $i < $len; $i++) {
$chr = $input[$i];
$ord = ord($chr);
// 1-byte character
if ($ord <= 0x7F) {
if ($seq) {
$out .= preg_match($regexp, $seq) ? $seq : '';
}
$seq = '';
$out .= $chr;
// first (or second) byte of multibyte sequence
}
else if ($ord >= 0xC0) {
if (strlen($seq) > 1) {
$out .= preg_match($regexp, $seq) ? $seq : '';
$seq = '';
}
else if ($seq && ord($seq) < 0xC0) {
$seq = '';
}
$seq .= $chr;
// next byte of multibyte sequence
}
else if ($seq) {
$seq .= $chr;
}
}
if ($seq) {
$out .= preg_match($regexp, $seq) ? $seq : '';
}
return $out;
}
}
diff --git a/program/include/rcube_vcard.php b/program/include/rcube_vcard.php
index 00903c257..65598e735 100644
--- a/program/include/rcube_vcard.php
+++ b/program/include/rcube_vcard.php
@@ -1,825 +1,792 @@
<?php
/*
+-----------------------------------------------------------------------+
| program/include/rcube_vcard.php |
| |
| This file is part of the Roundcube Webmail client |
| Copyright (C) 2008-2011, The Roundcube Dev Team |
| |
| Licensed under the GNU General Public License version 3 or |
| any later version with exceptions for skins & plugins. |
| See the README file for a full license statement. |
| |
| PURPOSE: |
| Logical representation of a vcard address record |
+-----------------------------------------------------------------------+
| Author: Thomas Bruederli <roundcube@gmail.com> |
+-----------------------------------------------------------------------+
*/
/**
* Logical representation of a vcard-based address record
* Provides functions to parse and export vCard data format
*
* @package Addressbook
* @author Thomas Bruederli <roundcube@gmail.com>
*/
class rcube_vcard
{
private static $values_decoded = false;
private $raw = array(
'FN' => array(),
'N' => array(array('','','','','')),
);
private static $fieldmap = array(
'phone' => 'TEL',
'birthday' => 'BDAY',
'website' => 'URL',
'notes' => 'NOTE',
'email' => 'EMAIL',
'address' => 'ADR',
'jobtitle' => 'TITLE',
'department' => 'X-DEPARTMENT',
'gender' => 'X-GENDER',
'maidenname' => 'X-MAIDENNAME',
'anniversary' => 'X-ANNIVERSARY',
'assistant' => 'X-ASSISTANT',
'manager' => 'X-MANAGER',
'spouse' => 'X-SPOUSE',
'edit' => 'X-AB-EDIT',
);
private $typemap = array('IPHONE' => 'mobile', 'CELL' => 'mobile', 'WORK,FAX' => 'workfax');
private $phonetypemap = array('HOME1' => 'HOME', 'BUSINESS1' => 'WORK', 'BUSINESS2' => 'WORK2', 'BUSINESSFAX' => 'WORK,FAX');
private $addresstypemap = array('BUSINESS' => 'WORK');
private $immap = array('X-JABBER' => 'jabber', 'X-ICQ' => 'icq', 'X-MSN' => 'msn', 'X-AIM' => 'aim', 'X-YAHOO' => 'yahoo', 'X-SKYPE' => 'skype', 'X-SKYPE-USERNAME' => 'skype');
public $business = false;
public $displayname;
public $surname;
public $firstname;
public $middlename;
public $nickname;
public $organization;
public $notes;
public $email = array();
public static $eol = "\r\n";
/**
* Constructor
*/
public function __construct($vcard = null, $charset = RCMAIL_CHARSET, $detect = false, $fieldmap = array())
{
if (!empty($fielmap))
$this->extend_fieldmap($fieldmap);
if (!empty($vcard))
$this->load($vcard, $charset, $detect);
}
/**
* Load record from (internal, unfolded) vcard 3.0 format
*
* @param string vCard string to parse
* @param string Charset of string values
* @param boolean True if loading a 'foreign' vcard and extra heuristics for charset detection is required
*/
public function load($vcard, $charset = RCMAIL_CHARSET, $detect = false)
{
self::$values_decoded = false;
$this->raw = self::vcard_decode($vcard);
// resolve charset parameters
if ($charset == null) {
$this->raw = self::charset_convert($this->raw);
}
// vcard has encoded values and charset should be detected
else if ($detect && self::$values_decoded &&
($detected_charset = self::detect_encoding(self::vcard_encode($this->raw))) && $detected_charset != RCMAIL_CHARSET) {
$this->raw = self::charset_convert($this->raw, $detected_charset);
}
// consider FN empty if the same as the primary e-mail address
if ($this->raw['FN'][0][0] == $this->raw['EMAIL'][0][0])
$this->raw['FN'][0][0] = '';
// find well-known address fields
$this->displayname = $this->raw['FN'][0][0];
$this->surname = $this->raw['N'][0][0];
$this->firstname = $this->raw['N'][0][1];
$this->middlename = $this->raw['N'][0][2];
$this->nickname = $this->raw['NICKNAME'][0][0];
$this->organization = $this->raw['ORG'][0][0];
$this->business = ($this->raw['X-ABSHOWAS'][0][0] == 'COMPANY') || (join('', (array)$this->raw['N'][0]) == '' && !empty($this->organization));
foreach ((array)$this->raw['EMAIL'] as $i => $raw_email)
$this->email[$i] = is_array($raw_email) ? $raw_email[0] : $raw_email;
// make the pref e-mail address the first entry in $this->email
$pref_index = $this->get_type_index('EMAIL', 'pref');
if ($pref_index > 0) {
$tmp = $this->email[0];
$this->email[0] = $this->email[$pref_index];
$this->email[$pref_index] = $tmp;
}
}
/**
* Return vCard data as associative array to be unsed in Roundcube address books
*
* @return array Hash array with key-value pairs
*/
public function get_assoc()
{
$out = array('name' => $this->displayname);
$typemap = $this->typemap;
// copy name fields to output array
foreach (array('firstname','surname','middlename','nickname','organization') as $col) {
if (strlen($this->$col))
$out[$col] = $this->$col;
}
if ($this->raw['N'][0][3])
$out['prefix'] = $this->raw['N'][0][3];
if ($this->raw['N'][0][4])
$out['suffix'] = $this->raw['N'][0][4];
// convert from raw vcard data into associative data for Roundcube
foreach (array_flip(self::$fieldmap) as $tag => $col) {
foreach ((array)$this->raw[$tag] as $i => $raw) {
if (is_array($raw)) {
$k = -1;
$key = $col;
$subtype = '';
if (!empty($raw['type'])) {
$combined = join(',', self::array_filter((array)$raw['type'], 'internet,pref', true));
$combined = strtoupper($combined);
if ($typemap[$combined]) {
$subtype = $typemap[$combined];
}
else if ($typemap[$raw['type'][++$k]]) {
$subtype = $typemap[$raw['type'][$k]];
}
else {
$subtype = strtolower($raw['type'][$k]);
}
while ($k < count($raw['type']) && ($subtype == 'internet' || $subtype == 'pref'))
$subtype = $typemap[$raw['type'][++$k]] ? $typemap[$raw['type'][$k]] : strtolower($raw['type'][$k]);
}
// read vcard 2.1 subtype
if (!$subtype) {
foreach ($raw as $k => $v) {
if (!is_numeric($k) && $v === true && ($k = strtolower($k))
&& !in_array($k, array('pref','internet','voice','base64'))
) {
$k_uc = strtoupper($k);
$subtype = $typemap[$k_uc] ? $typemap[$k_uc] : $k;
break;
}
}
}
// force subtype if none set
if (!$subtype && preg_match('/^(email|phone|address|website)/', $key))
$subtype = 'other';
if ($subtype)
$key .= ':' . $subtype;
// split ADR values into assoc array
if ($tag == 'ADR') {
list(,, $value['street'], $value['locality'], $value['region'], $value['zipcode'], $value['country']) = $raw;
$out[$key][] = $value;
}
else
$out[$key][] = $raw[0];
}
else {
$out[$col][] = $raw;
}
}
}
// handle special IM fields as used by Apple
foreach ($this->immap as $tag => $type) {
foreach ((array)$this->raw[$tag] as $i => $raw) {
$out['im:'.$type][] = $raw[0];
}
}
// copy photo data
if ($this->raw['PHOTO'])
$out['photo'] = $this->raw['PHOTO'][0][0];
return $out;
}
/**
* Convert the data structure into a vcard 3.0 string
*/
public function export($folded = true)
{
$vcard = self::vcard_encode($this->raw);
return $folded ? self::rfc2425_fold($vcard) : $vcard;
}
/**
* Clear the given fields in the loaded vcard data
*
* @param array List of field names to be reset
*/
public function reset($fields = null)
{
if (!$fields)
$fields = array_merge(array_values(self::$fieldmap), array_keys($this->immap), array('FN','N','ORG','NICKNAME','EMAIL','ADR','BDAY'));
foreach ($fields as $f)
unset($this->raw[$f]);
if (!$this->raw['N'])
$this->raw['N'] = array(array('','','','',''));
if (!$this->raw['FN'])
$this->raw['FN'] = array();
$this->email = array();
}
/**
* Setter for address record fields
*
* @param string Field name
* @param string Field value
* @param string Type/section name
*/
public function set($field, $value, $type = 'HOME')
{
$field = strtolower($field);
$type_uc = strtoupper($type);
$typemap = array_flip($this->typemap);
switch ($field) {
case 'name':
case 'displayname':
$this->raw['FN'][0][0] = $value;
break;
case 'surname':
$this->raw['N'][0][0] = $value;
break;
case 'firstname':
$this->raw['N'][0][1] = $value;
break;
case 'middlename':
$this->raw['N'][0][2] = $value;
break;
case 'prefix':
$this->raw['N'][0][3] = $value;
break;
case 'suffix':
$this->raw['N'][0][4] = $value;
break;
case 'nickname':
$this->raw['NICKNAME'][0][0] = $value;
break;
case 'organization':
$this->raw['ORG'][0][0] = $value;
break;
case 'photo':
if (strpos($value, 'http:') === 0) {
// TODO: fetch file from URL and save it locally?
$this->raw['PHOTO'][0] = array(0 => $value, 'url' => true);
}
else {
$this->raw['PHOTO'][0] = array(0 => $value, 'base64' => (bool) preg_match('![^a-z0-9/=+-]!i', $value));
}
break;
case 'email':
$this->raw['EMAIL'][] = array(0 => $value, 'type' => array_filter(array('INTERNET', $type_uc)));
$this->email[] = $value;
break;
case 'im':
// save IM subtypes into extension fields
$typemap = array_flip($this->immap);
if ($field = $typemap[strtolower($type)])
$this->raw[$field][] = array(0 => $value);
break;
case 'birthday':
case 'anniversary':
if (($val = rcube_utils::strtotime($value)) && ($fn = self::$fieldmap[$field]))
$this->raw[$fn][] = array(0 => date('Y-m-d', $val), 'value' => array('date'));
break;
case 'address':
if ($this->addresstypemap[$type_uc])
$type = $this->addresstypemap[$type_uc];
$value = $value[0] ? $value : array('', '', $value['street'], $value['locality'], $value['region'], $value['zipcode'], $value['country']);
// fall through if not empty
if (!strlen(join('', $value)))
break;
default:
if ($field == 'phone' && $this->phonetypemap[$type_uc])
$type = $this->phonetypemap[$type_uc];
if (($tag = self::$fieldmap[$field]) && (is_array($value) || strlen($value))) {
$index = count($this->raw[$tag]);
$this->raw[$tag][$index] = (array)$value;
if ($type)
$this->raw[$tag][$index]['type'] = explode(',', ($typemap[$type_uc] ? $typemap[$type_uc] : $type));
}
break;
}
}
/**
* Setter for individual vcard properties
*
* @param string VCard tag name
* @param array Value-set of this vcard property
* @param boolean Set to true if the value-set should be appended instead of replacing any existing value-set
*/
public function set_raw($tag, $value, $append = false)
{
$index = $append ? count($this->raw[$tag]) : 0;
$this->raw[$tag][$index] = (array)$value;
}
/**
* Find index with the '$type' attribute
*
* @param string Field name
* @return int Field index having $type set
*/
private function get_type_index($field, $type = 'pref')
{
$result = 0;
if ($this->raw[$field]) {
foreach ($this->raw[$field] as $i => $data) {
if (is_array($data['type']) && in_array_nocase('pref', $data['type']))
$result = $i;
}
}
return $result;
}
/**
* Convert a whole vcard (array) to UTF-8.
* If $force_charset is null, each member value that has a charset parameter will be converted
*/
private static function charset_convert($card, $force_charset = null)
{
foreach ($card as $key => $node) {
foreach ($node as $i => $subnode) {
if (is_array($subnode) && (($charset = $force_charset) || ($subnode['charset'] && ($charset = $subnode['charset'][0])))) {
foreach ($subnode as $j => $value) {
if (is_numeric($j) && is_string($value))
$card[$key][$i][$j] = rcube_charset::convert($value, $charset);
}
unset($card[$key][$i]['charset']);
}
}
}
return $card;
}
/**
* Extends fieldmap definition
*/
public function extend_fieldmap($map)
{
if (is_array($map))
self::$fieldmap = array_merge($map, self::$fieldmap);
}
/**
* Factory method to import a vcard file
*
* @param string vCard file content
* @return array List of rcube_vcard objects
*/
public static function import($data)
{
$out = array();
// check if charsets are specified (usually vcard version < 3.0 but this is not reliable)
if (preg_match('/charset=/i', substr($data, 0, 2048)))
$charset = null;
// detect charset and convert to utf-8
else if (($charset = self::detect_encoding($data)) && $charset != RCMAIL_CHARSET) {
$data = rcube_charset::convert($data, $charset);
$data = preg_replace(array('/^[\xFE\xFF]{2}/', '/^\xEF\xBB\xBF/', '/^\x00+/'), '', $data); // also remove BOM
$charset = RCMAIL_CHARSET;
}
$vcard_block = '';
$in_vcard_block = false;
foreach (preg_split("/[\r\n]+/", $data) as $i => $line) {
if ($in_vcard_block && !empty($line))
$vcard_block .= $line . "\n";
$line = trim($line);
if (preg_match('/^END:VCARD$/i', $line)) {
// parse vcard
$obj = new rcube_vcard(self::cleanup($vcard_block), $charset, true, self::$fieldmap);
if (!empty($obj->displayname) || !empty($obj->email))
$out[] = $obj;
$in_vcard_block = false;
}
else if (preg_match('/^BEGIN:VCARD$/i', $line)) {
$vcard_block = $line . "\n";
$in_vcard_block = true;
}
}
return $out;
}
/**
* Normalize vcard data for better parsing
*
* @param string vCard block
* @return string Cleaned vcard block
*/
private static function cleanup($vcard)
{
// Convert special types (like Skype) to normal type='skype' classes with this simple regex ;)
$vcard = preg_replace(
'/item(\d+)\.(TEL|EMAIL|URL)([^:]*?):(.*?)item\1.X-ABLabel:(?:_\$!<)?([\w-() ]*)(?:>!\$_)?./s',
'\2;type=\5\3:\4',
$vcard);
// convert Apple X-ABRELATEDNAMES into X-* fields for better compatibility
$vcard = preg_replace_callback(
'/item(\d+)\.(X-ABRELATEDNAMES)([^:]*?):(.*?)item\1.X-ABLabel:(?:_\$!<)?([\w-() ]*)(?:>!\$_)?./s',
array('self', 'x_abrelatednames_callback'),
$vcard);
// Remove cruft like item1.X-AB*, item1.ADR instead of ADR, and empty lines
$vcard = preg_replace(array('/^item\d*\.X-AB.*$/m', '/^item\d*\./m', "/\n+/"), array('', '', "\n"), $vcard);
// convert X-WAB-GENDER to X-GENDER
if (preg_match('/X-WAB-GENDER:(\d)/', $vcard, $matches)) {
$value = $matches[1] == '2' ? 'male' : 'female';
$vcard = preg_replace('/X-WAB-GENDER:\d/', 'X-GENDER:' . $value, $vcard);
}
// if N doesn't have any semicolons, add some
$vcard = preg_replace('/^(N:[^;\R]*)$/m', '\1;;;;', $vcard);
return $vcard;
}
private static function x_abrelatednames_callback($matches)
{
return 'X-' . strtoupper($matches[5]) . $matches[3] . ':'. $matches[4];
}
private static function rfc2425_fold_callback($matches)
{
// chunk_split string and avoid lines breaking multibyte characters
$c = 71;
$out .= substr($matches[1], 0, $c);
for ($n = $c; $c < strlen($matches[1]); $c++) {
// break if length > 75 or mutlibyte character starts after position 71
if ($n > 75 || ($n > 71 && ord($matches[1][$c]) >> 6 == 3)) {
$out .= "\r\n ";
$n = 0;
}
$out .= $matches[1][$c];
$n++;
}
return $out;
}
public static function rfc2425_fold($val)
{
return preg_replace_callback('/([^\n]{72,})/', array('self', 'rfc2425_fold_callback'), $val);
}
/**
* Decodes a vcard block (vcard 3.0 format, unfolded)
* into an array structure
*
* @param string vCard block to parse
* @return array Raw data structure
*/
private static function vcard_decode($vcard)
{
// Perform RFC2425 line unfolding and split lines
$vcard = preg_replace(array("/\r/", "/\n\s+/"), '', $vcard);
$lines = explode("\n", $vcard);
$data = array();
for ($i=0; $i < count($lines); $i++) {
if (!preg_match('/^([^:]+):(.+)$/', $lines[$i], $line))
continue;
if (preg_match('/^(BEGIN|END)$/i', $line[1]))
continue;
// convert 2.1-style "EMAIL;internet;home:" to 3.0-style "EMAIL;TYPE=internet;TYPE=home:"
if (($data['VERSION'][0] == "2.1") && preg_match('/^([^;]+);([^:]+)/', $line[1], $regs2) && !preg_match('/^TYPE=/i', $regs2[2])) {
$line[1] = $regs2[1];
foreach (explode(';', $regs2[2]) as $prop)
$line[1] .= ';' . (strpos($prop, '=') ? $prop : 'TYPE='.$prop);
}
if (preg_match_all('/([^\\;]+);?/', $line[1], $regs2)) {
$entry = array();
$field = strtoupper($regs2[1][0]);
$enc = null;
foreach($regs2[1] as $attrid => $attr) {
if ((list($key, $value) = explode('=', $attr)) && $value) {
$value = trim($value);
if ($key == 'ENCODING') {
$value = strtoupper($value);
// add next line(s) to value string if QP line end detected
if ($value == 'QUOTED-PRINTABLE') {
while (preg_match('/=$/', $lines[$i]))
$line[2] .= "\n" . $lines[++$i];
}
$enc = $value;
}
else {
$lc_key = strtolower($key);
$entry[$lc_key] = array_merge((array)$entry[$lc_key], (array)self::vcard_unquote($value, ','));
}
}
else if ($attrid > 0) {
$entry[strtolower($key)] = true; // true means attr without =value
}
}
// decode value
if ($enc || !empty($entry['base64'])) {
// save encoding type (#1488432)
if ($enc == 'B') {
$entry['encoding'] = 'B';
// should we use vCard 3.0 instead?
// $entry['base64'] = true;
}
$line[2] = self::decode_value($line[2], $enc ? $enc : 'base64');
}
if ($enc != 'B' && empty($entry['base64'])) {
$line[2] = self::vcard_unquote($line[2]);
}
$entry = array_merge($entry, (array) $line[2]);
$data[$field][] = $entry;
}
}
unset($data['VERSION']);
return $data;
}
/**
* Decode a given string with the encoding rule from ENCODING attributes
*
* @param string String to decode
* @param string Encoding type (quoted-printable and base64 supported)
* @return string Decoded 8bit value
*/
private static function decode_value($value, $encoding)
{
switch (strtolower($encoding)) {
case 'quoted-printable':
self::$values_decoded = true;
return quoted_printable_decode($value);
case 'base64':
case 'b':
self::$values_decoded = true;
return base64_decode($value);
default:
return $value;
}
}
/**
* Encodes an entry for storage in our database (vcard 3.0 format, unfolded)
*
* @param array Raw data structure to encode
* @return string vCard encoded string
*/
static function vcard_encode($data)
{
foreach((array)$data as $type => $entries) {
/* valid N has 5 properties */
while ($type == "N" && is_array($entries[0]) && count($entries[0]) < 5)
$entries[0][] = "";
// make sure FN is not empty (required by RFC2426)
if ($type == "FN" && empty($entries))
$entries[0] = $data['EMAIL'][0][0];
foreach((array)$entries as $entry) {
$attr = '';
if (is_array($entry)) {
$value = array();
foreach($entry as $attrname => $attrvalues) {
if (is_int($attrname)) {
if (!empty($entry['base64']) || $entry['encoding'] == 'B') {
$attrvalues = base64_encode($attrvalues);
}
$value[] = $attrvalues;
}
else if (is_bool($attrvalues)) {
if ($attrvalues) {
$attr .= strtoupper(";$attrname"); // true means just tag, not tag=value, as in PHOTO;BASE64:...
}
}
else {
foreach((array)$attrvalues as $attrvalue)
$attr .= strtoupper(";$attrname=") . self::vcard_quote($attrvalue, ',');
}
}
}
else {
$value = $entry;
}
// skip empty entries
if (self::is_empty($value))
continue;
$vcard .= self::vcard_quote($type) . $attr . ':' . self::vcard_quote($value) . self::$eol;
}
}
return 'BEGIN:VCARD' . self::$eol . 'VERSION:3.0' . self::$eol . $vcard . 'END:VCARD';
}
/**
* Join indexed data array to a vcard quoted string
*
* @param array Field data
* @param string Separator
* @return string Joined and quoted string
*/
private static function vcard_quote($s, $sep = ';')
{
if (is_array($s)) {
foreach($s as $part) {
$r[] = self::vcard_quote($part, $sep);
}
return(implode($sep, (array)$r));
}
else {
return strtr($s, array('\\' => '\\\\', "\r" => '', "\n" => '\n', ',' => '\,', ';' => '\;'));
}
}
/**
* Split quoted string
*
* @param string vCard string to split
* @param string Separator char/string
* @return array List with splited values
*/
private static function vcard_unquote($s, $sep = ';')
{
// break string into parts separated by $sep, but leave escaped $sep alone
if (count($parts = explode($sep, strtr($s, array("\\$sep" => "\007")))) > 1) {
foreach($parts as $s) {
$result[] = self::vcard_unquote(strtr($s, array("\007" => "\\$sep")), $sep);
}
return $result;
}
else {
return strtr($s, array("\r" => '', '\\\\' => '\\', '\n' => "\n", '\N' => "\n", '\,' => ',', '\;' => ';', '\:' => ':'));
}
}
/**
* Check if vCard entry is empty: empty string or an array with
* all entries empty.
*
* @param mixed $value Attribute value (string or array)
*
* @return bool True if the value is empty, False otherwise
*/
private static function is_empty($value)
{
foreach ((array)$value as $v) {
if (((string)$v) !== '') {
return false;
}
}
return true;
}
/**
* Extract array values by a filter
*
* @param array Array to filter
* @param keys Array or comma separated list of values to keep
* @param boolean Invert key selection: remove the listed values
* @return array The filtered array
*/
private static function array_filter($arr, $values, $inverse = false)
{
if (!is_array($values))
$values = explode(',', $values);
$result = array();
$keep = array_flip((array)$values);
foreach ($arr as $key => $val)
if ($inverse != isset($keep[strtolower($val)]))
$result[$key] = $val;
return $result;
}
/**
* Returns UNICODE type based on BOM (Byte Order Mark)
*
* @param string Input string to test
* @return string Detected encoding
*/
private static function detect_encoding($string)
{
- if (substr($string, 0, 4) == "\0\0\xFE\xFF") return 'UTF-32BE'; // Big Endian
- if (substr($string, 0, 4) == "\xFF\xFE\0\0") return 'UTF-32LE'; // Little Endian
- if (substr($string, 0, 2) == "\xFE\xFF") return 'UTF-16BE'; // Big Endian
- if (substr($string, 0, 2) == "\xFF\xFE") return 'UTF-16LE'; // Little Endian
- if (substr($string, 0, 3) == "\xEF\xBB\xBF") return 'UTF-8';
-
- // heuristics
- if ($string[0] == "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-32BE';
- if ($string[0] != "\0" && $string[1] == "\0" && $string[2] == "\0" && $string[3] == "\0") return 'UTF-32LE';
- if ($string[0] == "\0" && $string[1] != "\0" && $string[2] == "\0" && $string[3] != "\0") return 'UTF-16BE';
- if ($string[0] != "\0" && $string[1] == "\0" && $string[2] != "\0" && $string[3] == "\0") return 'UTF-16LE';
-
- // use mb_detect_encoding()
- $encodings = array('UTF-8', 'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3',
- 'ISO-8859-4', 'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9',
- 'ISO-8859-10', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16',
- 'WINDOWS-1252', 'WINDOWS-1251', 'BIG5', 'GB2312');
-
- if (function_exists('mb_detect_encoding') && ($enc = mb_detect_encoding($string, $encodings)))
- return $enc;
-
- // No match, check for UTF-8
- // from http://w3.org/International/questions/qa-forms-utf-8.html
- if (preg_match('/\A(
- [\x09\x0A\x0D\x20-\x7E]
- | [\xC2-\xDF][\x80-\xBF]
- | \xE0[\xA0-\xBF][\x80-\xBF]
- | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}
- | \xED[\x80-\x9F][\x80-\xBF]
- | \xF0[\x90-\xBF][\x80-\xBF]{2}
- | [\xF1-\xF3][\x80-\xBF]{3}
- | \xF4[\x80-\x8F][\x80-\xBF]{2}
- )*\z/xs', substr($string, 0, 2048)))
- return 'UTF-8';
-
- return rcube::get_instance()->config->get('default_charset', 'ISO-8859-1'); # fallback to Latin-1
+ $fallback = rcube::get_instance()->config->get('default_charset', 'ISO-8859-1'); // fallback to Latin-1
+
+ return rcube_charset::detect($string, $fallback);
}
}

File Metadata

Mime Type
text/x-diff
Expires
Sat, Mar 1, 8:43 AM (1 d, 16 h)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
166411
Default Alt Text
(54 KB)

Event Timeline