/**
* Decode euc-kr encoded string
* @param string $string euc-kr string
* @param boolean $save_html don't html encode special characters if true
* @return string $string decoded string
*/
function charset_decode_euc_kr($string, $save_html = false)
{
// global $aggressive_decoding;
// don't do decoding when there are no 8bit symbols
if (!sq_is8bit($string, 'euc-kr')) {
return $string;
}
// this is CPU intensive task. Use recode functions if they are available.
if (function_exists('recode_string')) {
// if string is already sanitized, undo htmlspecial chars
if (!$save_html) {
$string = str_replace(array('"', '<', '>', '&'), array('"', '<', '>', '&'), $string);
}
$string = recode_string("euc-kr..html", $string);
// if string sanitizing is not needed, undo htmlspecialchars applied by recode.
if ($save_html) {
$string = str_replace(array('"', '<', '>', '&'), array('"', '<', '>', '&'), $string);
}
return $string;
}
/*
* iconv does not support html target, but internal utf-8 decoding is faster
* than pure php implementation.
*/
if (function_exists('iconv') && file_exists(SM_PATH . 'functions/decode/utf_8.php')) {
include_once SM_PATH . 'functions/decode/utf_8.php';
$string = iconv('euc-kr', 'utf-8', $string);
return charset_decode_utf_8($string);
}
// try mbstring
if (function_exists('mb_convert_encoding') && function_exists('sq_mb_list_encodings') && check_php_version(4, 3, 0) && in_array('euc-kr', sq_mb_list_encodings())) {
return mb_convert_encoding($string, 'HTML-ENTITIES', 'EUC-KR');
}
return $string;
}
/**
* @param string $str
* @param string $to_encoding
* @param string $from_encoding
* @param string $default_charset
* @return string
*/
function sqimap_mb_convert_encoding($str, $to_encoding, $from_encoding, $default_charset)
{
$supported_encodings = sq_mb_list_encodings();
if (in_array(strtolower($default_charset), $supported_encodings) && function_exists('mb_convert_encoding')) {
return mb_convert_encoding($str, $to_encoding, $from_encoding);
}
return '';
}
/**
* Function returns number of characters in string.
*
* Returned number might be different from number of bytes in string,
* if $charset is multibyte charset. Detection depends on mbstring
* functions. If mbstring does not support tested multibyte charset,
* vanilla string length function is used.
* @param string $str string
* @param string $charset charset
* @since 1.5.1 and 1.4.6
* @return integer number of characters in string
*/
function sq_strlen($str, $charset = null)
{
// default option
if (is_null($charset)) {
return strlen($str);
}
// lowercase charset name
$charset = strtolower($charset);
// use automatic charset detection, if function call asks for it
if ($charset == 'auto') {
global $default_charset;
set_my_charset();
$charset = $default_charset;
}
// Use mbstring only with listed charsets
$aList_of_mb_charsets = array('utf-8', 'big5', 'gb2312', 'gb18030', 'euc-jp', 'euc-cn', 'euc-tw', 'euc-kr');
// calculate string length according to charset
if (in_array($charset, $aList_of_mb_charsets) && in_array($charset, sq_mb_list_encodings())) {
$real_length = mb_strlen($str, $charset);
} else {
// own strlen detection code is removed because missing strpos,
// strtoupper and substr implementations break string wrapping.
$real_length = strlen($str);
}
return $real_length;
}
/**
* Encodes header as quoted-printable
*
* Encode a string according to RFC 1522 for use in headers if it
* contains 8-bit characters or anything that looks like it should
* be encoded.
*/
function encodeHeader($string)
{
global $default_charset, $languages, $squirrelmail_language;
if (isset($languages[$squirrelmail_language]['XTRA_CODE']) && function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
return $languages[$squirrelmail_language]['XTRA_CODE']('encodeheader', $string);
}
// Use B encoding for multibyte charsets
$mb_charsets = array('utf-8', 'big5', 'gb2313', 'euc-kr');
if (in_array($default_charset, $mb_charsets) && in_array($default_charset, sq_mb_list_encodings()) && sq_is8bit($string)) {
return encodeHeaderBase64($string, $default_charset);
} elseif (in_array($default_charset, $mb_charsets) && sq_is8bit($string) && !in_array($default_charset, sq_mb_list_encodings())) {
// Add E_USER_NOTICE error here (can cause 'Cannot add header information' warning in compose.php)
// trigger_error('encodeHeader: Multibyte character set unsupported by mbstring extension.',E_USER_NOTICE);
}
// Encode only if the string contains 8-bit characters or =?
$j = strlen($string);
$max_l = 75 - strlen($default_charset) - 7;
$aRet = array();
$ret = '';
$iEncStart = $enc_init = false;
$cur_l = $iOffset = 0;
for ($i = 0; $i < $j; ++$i) {
switch ($string[$i]) {
case '=':
case '<':
case '>':
case ',':
case '?':
case '_':
if ($iEncStart === false) {
$iEncStart = $i;
}
$cur_l += 3;
if ($cur_l > $max_l - 2) {
/* if there is an stringpart that doesn't need encoding, add it */
$aRet[] = substr($string, $iOffset, $iEncStart - $iOffset);
$aRet[] = "=?{$default_charset}?Q?{$ret}?=";
$iOffset = $i;
$cur_l = 0;
$ret = '';
$iEncStart = false;
} else {
$ret .= sprintf("=%02X", ord($string[$i]));
}
break;
case '(':
case ')':
if ($iEncStart !== false) {
$aRet[] = substr($string, $iOffset, $iEncStart - $iOffset);
$aRet[] = "=?{$default_charset}?Q?{$ret}?=";
$iOffset = $i;
$cur_l = 0;
$ret = '';
$iEncStart = false;
}
break;
case ' ':
if ($iEncStart !== false) {
$cur_l++;
if ($cur_l > $max_l) {
$aRet[] = substr($string, $iOffset, $iEncStart - $iOffset);
$aRet[] = "=?{$default_charset}?Q?{$ret}?=";
$iOffset = $i;
$cur_l = 0;
$ret = '';
$iEncStart = false;
} else {
$ret .= '_';
}
}
break;
default:
$k = ord($string[$i]);
if ($k > 126) {
if ($iEncStart === false) {
// do not start encoding in the middle of a string, also take the rest of the word.
$sLeadString = substr($string, 0, $i);
$aLeadString = explode(' ', $sLeadString);
$sToBeEncoded = array_pop($aLeadString);
$iEncStart = $i - strlen($sToBeEncoded);
$ret .= $sToBeEncoded;
$cur_l += strlen($sToBeEncoded);
}
$cur_l += 3;
/* first we add the encoded string that reached it's max size */
if ($cur_l > $max_l - 2) {
$aRet[] = substr($string, $iOffset, $iEncStart - $iOffset);
$aRet[] = "=?{$default_charset}?Q?{$ret}?= ";
/* the next part is also encoded => separate by space */
$cur_l = 3;
$ret = '';
$iOffset = $i;
$iEncStart = $i;
}
$enc_init = true;
$ret .= sprintf("=%02X", $k);
} else {
if ($iEncStart !== false) {
$cur_l++;
if ($cur_l > $max_l) {
$aRet[] = substr($string, $iOffset, $iEncStart - $iOffset);
$aRet[] = "=?{$default_charset}?Q?{$ret}?=";
$iEncStart = false;
$iOffset = $i;
$cur_l = 0;
$ret = '';
} else {
$ret .= $string[$i];
}
}
}
break;
}
}
if ($enc_init) {
if ($iEncStart !== false) {
$aRet[] = substr($string, $iOffset, $iEncStart - $iOffset);
$aRet[] = "=?{$default_charset}?Q?{$ret}?=";
} else {
$aRet[] = substr($string, $iOffset);
}
$string = implode('', $aRet);
}
return $string;
}
/**
* Wrapper that is used to switch between vanilla and multibyte strtoupper
* functions.
* @param string $string
* @param string $charset
* @return string
* @since 1.5.1
* @link http://www.php.net/strtoupper
* @link http://www.php.net/mb_strtoupper
*/
function sq_strtoupper($string, $charset = 'auto')
{
// use automatic charset detection, if function call asks for it
static $charset_auto, $bUse_mb;
if ($charset == 'auto') {
if (!isset($charset_auto)) {
global $default_charset, $squirrelmail_language;
set_my_charset();
$charset = $default_charset;
if ($squirrelmail_language == 'ja_JP') {
$charset = 'euc-jp';
}
$charset_auto = $charset;
} else {
$charset = $charset_auto;
}
}
$charset = strtolower($charset);
// in_array call is expensive => do it once and use a static var for
// storing the results
if (!isset($bUse_mb)) {
if (function_exists('mb_strtoupper') && in_array($charset, sq_mb_list_encodings())) {
$bUse_mb = true;
} else {
$bUse_mb = false;
}
}
if ($bUse_mb) {
return mb_strtoupper($string, $charset);
}
// TODO: add mbstring independent code
// use vanilla string functions as last option
return strtoupper($string);
}
