diff --git a/include/class.api.php b/include/class.api.php
index 2382a70e406d2b3f114fc4f1fd280b5ba67aed91..082cc178d5704598742df3b7dfda646261e71967 100644
--- a/include/class.api.php
+++ b/include/class.api.php
@@ -345,7 +345,7 @@ class ApiXmlDataParser extends XmlDataParser {
unset($value[":text"]);
}
if (isset($value['encoding']))
- $value['body'] = Format::utf8encode($value['body'], $value['encoding']);
+ $value['body'] = Charset::utf8($value['body'], $value['encoding']);
if (!strcasecmp($value['type'], 'text/html'))
$value = new HtmlThreadBody($value['body']);
diff --git a/include/class.charset.php b/include/class.charset.php
new file mode 100644
index 0000000000000000000000000000000000000000..5411e6b4abcb1347a0e22998678b13d57fe119d3
--- /dev/null
+++ b/include/class.charset.php
@@ -0,0 +1,75 @@
+<?php
+/*********************************************************************
+ class.charset.php
+
+ Charset util class
+
+ Copyright (c) 2015 osTicket
+ http://www.osticket.com
+
+ Released under the GNU General Public License WITHOUT ANY WARRANTY.
+ See LICENSE.TXT for details.
+
+ vim: expandtab sw=4 ts=4 sts=4:
+**********************************************************************/
+
+class Charset {
+
+ const UTF8 = 'utf-8';
+
+ // Cleanup invalid charsets
+ // Thanks in part to https://github.com/mikel/mail/commit/88457e
+ static function normalize($charset) {
+
+ $match = array();
+ switch (true) {
+ // Windows charsets - force correct format
+ case preg_match('`^Windows-?(\d+)$`', $charset, $match):
+ return 'Windows-'.$match[1];
+ // ks_c_5601-1987: Korean alias for cp949
+ case preg_match('`^ks_c_5601-1987`', $charset):
+ return 'cp949';
+ // Incorrect, bogus, ambiguous or empty charsets
+ // ISO-8859-1 is assumed
+ case preg_match('`^(default|x-user-defined|iso|us-ascii)`', $charset):
+ case preg_match('`^\s*$`', $charset):
+ return 'ISO-8859-1';
+ }
+
+ // Hmmmm
+ return $charset;
+ }
+
+ // Translate characters ($text) from one encoding ($from) to another ($to)
+ static function transcode($text, $from, $to) {
+
+ //Try auto-detecting charset/encoding
+ if (!$from && function_exists('mb_detect_encoding'))
+ $from = mb_detect_encoding($text);
+
+ // Normalize bogus or ambiguous charsets
+ $from = self::normalize(trim($from));
+ $to = self::normalize(trim($to));
+
+ $original = $text;
+ if (function_exists('iconv'))
+ $text = iconv($from, $to.'//IGNORE', $text);
+ elseif (function_exists('mb_convert_encoding'))
+ $text = mb_convert_encoding($text, $to, $from);
+ elseif (!strcasecmp($to, 'utf-8')
+ && function_exists('utf8_encode')
+ && !strcasecmp($from, 'ISO-8859-1'))
+ $text = utf8_encode($text);
+
+ // If $text is false, then we have a (likely) invalid charset, use
+ // the original text and assume 8-bit (latin-1 / iso-8859-1)
+ // encoding
+ return (!$text && $original) ? $original : $text;
+ }
+
+ //Wrapper for utf-8 transcoding.
+ function utf8($text, $charset=null) {
+ return self::transcode($text, $charset, self::UTF8);
+ }
+}
+?>
diff --git a/include/class.format.php b/include/class.format.php
index a124a577f60a0cc88beff06dce0c3953fa8d96d6..e597de6185788bab00167f6e866623388f6ffa6b 100644
--- a/include/class.format.php
+++ b/include/class.format.php
@@ -14,6 +14,7 @@
vim: expandtab sw=4 ts=4 sts=4:
**********************************************************************/
+include_once INCLUDE_DIR.'class.charset.php';
class Format {
@@ -40,47 +41,13 @@ class Format {
return $size;
}
- /* encode text into desired encoding - taking into accout charset when available. */
- function encode($text, $charset=null, $encoding='utf-8') {
-
- //Try auto-detecting charset/encoding
- if (!$charset && function_exists('mb_detect_encoding'))
- $charset = mb_detect_encoding($text);
-
- // Cleanup - incorrect, bogus, or ambiguous charsets
- // ISO-8859-1 is assumed for empty charset.
- if (!$charset || in_array(strtolower(trim($charset)),
- array('default','x-user-defined','iso','us-ascii')))
- $charset = 'ISO-8859-1';
-
- $original = $text;
- if (function_exists('iconv'))
- $text = iconv($charset, $encoding.'//IGNORE', $text);
- elseif (function_exists('mb_convert_encoding'))
- $text = mb_convert_encoding($text, $encoding, $charset);
- elseif (!strcasecmp($encoding, 'utf-8')
- && function_exists('utf8_encode')
- && !strcasecmp($charset, 'ISO-8859-1'))
- $text = utf8_encode($text);
-
- // If $text is false, then we have a (likely) invalid charset, use
- // the original text and assume 8-bit (latin-1 / iso-8859-1)
- // encoding
- return (!$text && $original) ? $original : $text;
- }
-
- //Wrapper for utf-8 encoding.
- function utf8encode($text, $charset=null) {
- return Format::encode($text, $charset, 'utf-8');
- }
-
function mimedecode($text, $encoding='UTF-8') {
if(function_exists('imap_mime_header_decode')
&& ($parts = imap_mime_header_decode($text))) {
$str ='';
foreach ($parts as $part)
- $str.= Format::encode($part->text, $part->charset, $encoding);
+ $str.= Charset::transcode($part->text, $part->charset, $encoding);
$text = $str;
} elseif($text[0] == '=' && function_exists('iconv_mime_decode')) {
@@ -105,7 +72,7 @@ class Format {
$filename, $match))
// XXX: Currently we don't care about the language component.
// The encoding hint is sufficient.
- return self::utf8encode(urldecode($match[3]), $match[1]);
+ return Charset::utf8(urldecode($match[3]), $match[1]);
else
return $filename;
}
@@ -555,7 +522,7 @@ class Format {
$contents = base64_decode($contents);
}
if ($output_encoding && $charset)
- $contents = Format::encode($contents, $charset, $output_encoding);
+ $contents = Charset::transcode($contents, $charset, $output_encoding);
return array(
'data' => $contents,
diff --git a/include/class.mailfetch.php b/include/class.mailfetch.php
index 1210bffa3f3bfd924169e87939d369c229a4a9ce..363589b46ab2f9720960ac4a8084e80793d9f67c 100644
--- a/include/class.mailfetch.php
+++ b/include/class.mailfetch.php
@@ -206,7 +206,7 @@ class MailFetcher {
//Convert text to desired encoding..defaults to utf8
function mime_encode($text, $charset=null, $encoding='utf-8') { //Thank in part to afterburner
- return Format::encode($text, $charset, $encoding);
+ return Charset::transcode($text, $charset, $encoding);
}
function mailbox_encode($mailbox) {
@@ -240,7 +240,7 @@ class MailFetcher {
if (function_exists('mb_detect_encoding'))
if (($src_enc = mb_detect_encoding($text))
&& (strcasecmp($src_enc, 'ASCII') !== 0))
- return Format::encode($text, $src_enc, $encoding);
+ return Charset::transcode($text, $src_enc, $encoding);
// Handle ASCII text and RFC-2047 encoding
$str = '';
diff --git a/include/class.mailparse.php b/include/class.mailparse.php
index 4038f1226fa53b3a038bbea912ada03e3ceaf108..2a91faf7f451b789a107e4fbe691b4ff50ac0bb5 100644
--- a/include/class.mailparse.php
+++ b/include/class.mailparse.php
@@ -335,7 +335,7 @@ class Mail_Parse {
$content = $struct->body;
//Encode to desired encoding - ONLY if charset is known??
if (isset($struct->ctype_parameters['charset']))
- $content = Format::encode($content,
+ $content = Charset::transcode($content,
$struct->ctype_parameters['charset'], $this->charset);
return $content;
@@ -358,7 +358,7 @@ class Mail_Parse {
function mime_encode($text, $charset=null, $encoding='utf-8') {
- return Format::encode($text, $charset, $encoding);
+ return Charset::transcode($text, $charset, $encoding);
}
function getAttachments($part=null){
diff --git a/include/class.translation.php b/include/class.translation.php
index cc21848a31e9153f8940c939a48d624bed36d461..0f0924ed299a2adabae8e56156085d6b0e7781a1 100644
--- a/include/class.translation.php
+++ b/include/class.translation.php
@@ -576,7 +576,7 @@ class Translation extends gettext_reader implements Serializable {
if (!$this->encode)
return $string;
- return Format::encode($string, 'utf-8', $this->charset);
+ return Charset::transcode($string, 'utf-8', $this->charset);
}
static function buildHashFile($mofile, $outfile=false, $return=false) {
@@ -626,9 +626,8 @@ class Translation extends gettext_reader implements Serializable {
}
if ($charset && strcasecmp($charset, 'utf-8') !== 0) {
foreach ($table as $orig=>$trans) {
- // Format::encode defaults to UTF-8 output
- $table[Format::encode($orig, $charset)] =
- Format::encode($trans, $charset);
+ $table[Charset::utf8($orig, $charset)] =
+ Charset::utf8($trans, $charset);
unset($table[$orig]);
}
}
diff --git a/include/tnef_decoder.php b/include/tnef_decoder.php
index e0f7869ba82b4ce554ada486efbfb1ae9cc4bb67..70e455851fc69d236f822ed033fdb7e731219f57 100644
--- a/include/tnef_decoder.php
+++ b/include/tnef_decoder.php
@@ -341,7 +341,7 @@ class TnefAttributeStreamReader extends TnefStreamReader {
/* Read and truncate to length. */
$text = substr($this->_getx($datalen), 0, $length);
if ($type == self::TypeUnicode) {
- $text = Format::encode($text, 'ucs2');
+ $text = Charset::utf8($text, 'ucs2');
}
return $text;
@@ -543,7 +543,7 @@ class TnefMessage extends AbstractTnefObject {
// Transcode it
if ($encoding && $charset)
- $body = Format::encode($body, $charset, $encoding);
+ $body = Charset::transcode($body, $charset, $encoding);
return $body;
}