|
|
@ -245,14 +245,10 @@ class rcube_charset |
|
|
|
if ($m[1] == 1) { |
|
|
|
$result = 'WINDOWS-1252'; |
|
|
|
} |
|
|
|
// if iconv is not supported we need ISO labels, it's also safe for iconv
|
|
|
|
// we need ISO labels
|
|
|
|
else if (!empty($aliases[$m[1]])) { |
|
|
|
$result = 'ISO-8859-'.$aliases[$m[1]]; |
|
|
|
} |
|
|
|
// iconv requires conversion of e.g. LATIN-1 to LATIN1
|
|
|
|
else { |
|
|
|
$result = $str; |
|
|
|
} |
|
|
|
} |
|
|
|
else { |
|
|
|
$result = $charset; |
|
|
@ -265,7 +261,6 @@ class rcube_charset |
|
|
|
|
|
|
|
/** |
|
|
|
* Convert a string from one charset to another. |
|
|
|
* Uses mbstring and iconv functions if possible |
|
|
|
* |
|
|
|
* @param string $str Input string |
|
|
|
* @param string $from Suspected charset of the input string |
|
|
@ -275,9 +270,6 @@ class rcube_charset |
|
|
|
*/ |
|
|
|
public static function convert($str, $from, $to = null) |
|
|
|
{ |
|
|
|
static $iconv_options = null; |
|
|
|
static $mbstring_sc = null; |
|
|
|
|
|
|
|
$to = empty($to) ? RCUBE_CHARSET : strtoupper($to); |
|
|
|
$from = self::parse_charset($from); |
|
|
|
|
|
|
@ -291,105 +283,37 @@ class rcube_charset |
|
|
|
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 = ''; |
|
|
|
} |
|
|
|
} |
|
|
|
else { |
|
|
|
$iconv_options = false; |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
// convert charset using iconv module
|
|
|
|
if ($iconv_options !== false && $from != 'UTF7-IMAP' && $to != 'UTF7-IMAP' |
|
|
|
&& $from !== 'ISO-2022-JP' |
|
|
|
) { |
|
|
|
// 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 { |
|
|
|
$out = iconv($from, $to . $iconv_options, $str); |
|
|
|
} |
|
|
|
catch (ErrorException $e) { |
|
|
|
$out = false; |
|
|
|
} |
|
|
|
restore_error_handler(); |
|
|
|
|
|
|
|
if ($out !== false) { |
|
|
|
return $out; |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
if ($mbstring_sc === null) { |
|
|
|
$mbstring_sc = extension_loaded('mbstring') ? mb_substitute_character() : false; |
|
|
|
} |
|
|
|
|
|
|
|
// convert charset using mbstring module
|
|
|
|
if ($mbstring_sc !== false) { |
|
|
|
$aliases = array( |
|
|
|
'WINDOWS-1257' => 'ISO-8859-13', |
|
|
|
'US-ASCII' => 'ASCII', |
|
|
|
'ISO-2022-JP' => 'ISO-2022-JP-MS', |
|
|
|
); |
|
|
|
|
|
|
|
$mb_from = $aliases[$from] ?: $from; |
|
|
|
$mb_to = $aliases[$to] ?: $to; |
|
|
|
|
|
|
|
// Do the same as //IGNORE with iconv
|
|
|
|
mb_substitute_character('none'); |
|
|
|
$aliases = array( |
|
|
|
'WINDOWS-1257' => 'ISO-8859-13', |
|
|
|
'US-ASCII' => 'ASCII', |
|
|
|
'ISO-2022-JP' => 'ISO-2022-JP-MS', |
|
|
|
); |
|
|
|
|
|
|
|
// throw an exception if mbstring reports an illegal character in input
|
|
|
|
// using mb_check_encoding() is much slower
|
|
|
|
set_error_handler(array('rcube_charset', 'error_handler'), E_WARNING); |
|
|
|
try { |
|
|
|
$out = mb_convert_encoding($str, $mb_to, $mb_from); |
|
|
|
} |
|
|
|
catch (ErrorException $e) { |
|
|
|
$out = false; |
|
|
|
} |
|
|
|
restore_error_handler(); |
|
|
|
$mb_from = $aliases[$from] ?: $from; |
|
|
|
$mb_to = $aliases[$to] ?: $to; |
|
|
|
|
|
|
|
mb_substitute_character($mbstring_sc); |
|
|
|
// Ignore invalid characters
|
|
|
|
$mbstring_sc = mb_substitute_character(); |
|
|
|
mb_substitute_character('none'); |
|
|
|
|
|
|
|
if ($out !== false) { |
|
|
|
return $out; |
|
|
|
} |
|
|
|
// throw an exception if mbstring reports an illegal character in input
|
|
|
|
// using mb_check_encoding() is much slower
|
|
|
|
set_error_handler(array('rcube_charset', 'error_handler'), E_WARNING); |
|
|
|
try { |
|
|
|
$out = mb_convert_encoding($str, $mb_to, $mb_from); |
|
|
|
} |
|
|
|
|
|
|
|
// convert charset using bundled classes/functions
|
|
|
|
if ($to == 'UTF-8') { |
|
|
|
if ($from == 'UTF7-IMAP') { |
|
|
|
if ($out = self::utf7imap_to_utf8($str)) { |
|
|
|
return $out; |
|
|
|
} |
|
|
|
} |
|
|
|
else if ($from == 'UTF-7') { |
|
|
|
if ($out = self::utf7_to_utf8($str)) { |
|
|
|
return $out; |
|
|
|
} |
|
|
|
} |
|
|
|
catch (ErrorException $e) { |
|
|
|
$out = false; |
|
|
|
} |
|
|
|
restore_error_handler(); |
|
|
|
|
|
|
|
// encode string for output
|
|
|
|
if ($from == 'UTF-8') { |
|
|
|
// @TODO: we need a function for UTF-7 (RFC2152) conversion
|
|
|
|
if ($to == 'UTF7-IMAP' || $to == 'UTF-7') { |
|
|
|
if ($out = self::utf8_to_utf7imap($str)) { |
|
|
|
return $out; |
|
|
|
} |
|
|
|
} |
|
|
|
} |
|
|
|
mb_substitute_character($mbstring_sc); |
|
|
|
|
|
|
|
if (!isset($out)) { |
|
|
|
trigger_error("No suitable function found for '$from' to '$to' conversion"); |
|
|
|
if ($out !== false) { |
|
|
|
return $out; |
|
|
|
} |
|
|
|
|
|
|
|
// return original string
|
|
|
|
// return the original string
|
|
|
|
return $str; |
|
|
|
} |
|
|
|
|
|
|
@ -399,57 +323,11 @@ class rcube_charset |
|
|
|
* @param string $str Input string (UTF-7) |
|
|
|
* |
|
|
|
* @return string Converted string (UTF-8) |
|
|
|
* @deprecated use self::convert() |
|
|
|
*/ |
|
|
|
public static function utf7_to_utf8($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 $res; |
|
|
|
return self::convert($str, 'UTF-7', 'UTF-8'); |
|
|
|
} |
|
|
|
|
|
|
|
/** |
|
|
@ -458,29 +336,11 @@ class rcube_charset |
|
|
|
* @param string $str Input string |
|
|
|
* |
|
|
|
* @return string The converted string |
|
|
|
* @deprecated use self::convert() |
|
|
|
*/ |
|
|
|
public static function utf16_to_utf8($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 $dec; |
|
|
|
return self::convert($str, 'UTF-16BE', 'UTF-8'); |
|
|
|
} |
|
|
|
|
|
|
|
/** |
|
|
@ -491,104 +351,14 @@ class rcube_charset |
|
|
|
* 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 $str Input string (UTF7-IMAP) |
|
|
|
* |
|
|
|
* @return string Output string (UTF-8) |
|
|
|
* @deprecated use self::convert() |
|
|
|
*/ |
|
|
|
public static function utf7imap_to_utf8($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 $p; |
|
|
|
return self::convert($str, 'UTF7-IMAP', 'UTF-8'); |
|
|
|
} |
|
|
|
|
|
|
|
/** |
|
|
@ -596,129 +366,14 @@ class rcube_charset |
|
|
|
* 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 $str Input string (UTF-8) |
|
|
|
* |
|
|
|
* @return string Output string (UTF7-IMAP) |
|
|
|
* @deprecated use self::convert() |
|
|
|
*/ |
|
|
|
public static function utf8_to_utf7imap($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 $p; |
|
|
|
return self::convert($str, 'UTF-8', 'UTF7-IMAP'); |
|
|
|
} |
|
|
|
|
|
|
|
/** |
|
|
@ -841,7 +496,7 @@ class rcube_charset |
|
|
|
return $input; |
|
|
|
} |
|
|
|
|
|
|
|
// iconv/mbstring are much faster (especially with long strings)
|
|
|
|
// mbstring is much faster (especially with long strings)
|
|
|
|
if (function_exists('mb_convert_encoding')) { |
|
|
|
$msch = mb_substitute_character(); |
|
|
|
mb_substitute_character('none'); |
|
|
@ -853,12 +508,6 @@ class rcube_charset |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
if (function_exists('iconv')) { |
|
|
|
if (($res = @iconv('UTF-8', 'UTF-8//IGNORE', $input)) !== false) { |
|
|
|
return $res; |
|
|
|
} |
|
|
|
} |
|
|
|
|
|
|
|
$seq = ''; |
|
|
|
$out = ''; |
|
|
|
$regexp = '/^('. |
|
|
|