[RCD] attachments with national characters

There're problems with attachment names in parts without charset specification. Example message can be found here http://trac.roundcube.net/ticket/1484969

I think we have two solutions:

1. Check charset of first (all) part(s) of message and convert filename

according to it, but what when there's no charset data? 2. Detect charset using ie. mb_detect_encoding().

Here's a patch for 2.

diff -ruN rc-beta3/program/include/rcube_imap.php rc-beta2/program/include/rcube_imap.php --- rc-beta3/program/include/rcube_imap.php 2008-06-06 10:20:39.672800689 +0200 +++ rc-beta2/program/include/rcube_imap.php 2008-06-06 09:39:49.031952834 +0200 @@ -1159,10 +1159,13 @@ if (is_array($part[8]) && empty($struct->parts)) $struct->parts[] = $this->_structure_part($part[8], ++$count, $struct->mime_id); }

• // normalize filename property if ($filename_mime = $struct->d_parameters['filename'] ? $struct->d_parameters['filename'] : $struct->ctype_parameters['name'])

•  $struct->filename = rcube_imap::decode_mime_string($filename_mime, $this->default_charset);
  

• {

•  $struct->filename = rcube_imap::decode_mime_string($filename_mime, 
  

•     $struct->charset ? $struct->charset : rc_detect_encoding($filename_mime, $this->default_charset));
  

• } else if ($filename_encoded = $struct->d_parameters['filename*'] ? $struct->d_parameters['filename*'] : $struct->ctype_parameters['name*']) { // decode filename according to RFC 2231, Section 4

@@ -1170,7 +1173,8 @@ $struct->filename = rcube_charset_convert(urldecode($filename_urlencoded), $filename_charset); } else if (!empty($struct->headers['content-description']))

•  $struct->filename = rcube_imap::decode_mime_string($struct->headers['content-description'], $this->default_charset);
  

•  $struct->filename = rcube_imap::decode_mime_string($struct->headers['content-description'],
  

•     $struct->charset ? $struct->charset : rc_detect_encoding($struct->headers['content-description'],$this->default_charset));
  
  

  return $struct; }

diff -ruN rc-beta3/program/include/rcube_shared.inc rc-beta2/program/include/rcube_shared.inc --- rc-beta3/program/include/rcube_shared.inc 2008-06-06 10:20:39.416799300 +0200 +++ rc-beta2/program/include/rcube_shared.inc 2008-06-06 10:07:39.177963387 +0200 @@ -581,4 +581,33 @@ return $mime_type; }

-?> \ Brak znaku nowej linii na ko�cu pliku

+/**

• • A method to guess encoding of a string.
• • @param string $string String.
• • @param string $failover Default result for failover.
• • @return string
• */

+function rc_detect_encoding($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', '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'
• );
• $result = mb_detect_encoding($string, join(',', $enc));
• return $result ? $result : $failover;

+}

+?>