From 795fcca0ce8f78de4a3d25c5e262e294218f35f5 Mon Sep 17 00:00:00 2001
From: Jared Hancock <jared@osticket.com>
Date: Mon, 1 Jul 2013 13:33:15 -0500
Subject: [PATCH] Use a failsafe encoding for unrecognized charsets
If the body of an email message is written and encoded with an unrecognized
charset (like 'iso', for instance), then use the original text, assumed to
be 8-bit encoded. This patch will create idiosyncrasies, where text might be
transcoded to utf-8 incorrectly, but it should eliminate instances where
email message bodies are missing due to incorrect charset labels.
---
include/class.format.php | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/include/class.format.php b/include/class.format.php
index 7a339e429..10859d15a 100644
--- a/include/class.format.php
+++ b/include/class.format.php
@@ -41,18 +41,23 @@ class Format {
if(!$charset && function_exists('mb_detect_encoding'))
$charset = mb_detect_encoding($text);
- //Cleanup - junk
- if($charset && in_array(trim($charset), array('default','x-user-defined')))
+ // Cleanup - incorrect, bogus, or ambiguous charsets
+ if($charset && in_array(strtolower(trim($charset)),
+ array('default','x-user-defined','iso')))
$charset = 'ISO-8859-1';
+ $original = $text;
if(function_exists('iconv') && $charset)
$text = iconv($charset, $encoding.'//IGNORE', $text);
elseif(function_exists('mb_convert_encoding') && $charset && $encoding)
$text = mb_convert_encoding($text, $encoding, $charset);
elseif(!strcasecmp($encoding, 'utf-8')) //forced blind utf8 encoding.
$text = function_exists('imap_utf8')?imap_utf8($text):utf8_encode($text);
-
- return $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.
--
GitLab