summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorthomascube <thomas@roundcube.net>2008-11-12 22:36:09 +0000
committerthomascube <thomas@roundcube.net>2008-11-12 22:36:09 +0000
commit6fa87f3fa5579da0935dc6ee29af77aea19ad872 (patch)
treed37a8488999eaa59342a5b846749d74bd993e9b0
parent146977e30e81b6098e2f40f2879c219b695439a5 (diff)
Improve charset encoding + remove BOM before parsing vcards
-rw-r--r--program/include/rcube_vcard.php9
1 files changed, 8 insertions, 1 deletions
diff --git a/program/include/rcube_vcard.php b/program/include/rcube_vcard.php
index 5ce1d367f..412582d31 100644
--- a/program/include/rcube_vcard.php
+++ b/program/include/rcube_vcard.php
@@ -172,6 +172,7 @@ class rcube_vcard
$encoding = self::detect_encoding($data);
if ($encoding && $encoding != RCMAIL_CHARSET) {
$data = rcube_charset_convert($data, $encoding);
+ $data = preg_replace(array('/^[\xFE\xFF]{2}/', '/^\xEF\xBB\xBF/', '/^\x00+/'), '', $data); // also remove BOM
}
$vcard_block = '';
@@ -409,7 +410,13 @@ class rcube_vcard
if (substr($string, 0, 2) == "\xFF\xFE") return 'UTF-16LE'; // Little Endian
if (substr($string, 0, 3) == "\xEF\xBB\xBF") return 'UTF-8';
- if ($enc = rc_detect_encoding($string))
+ // use mb_detect_encoding()
+ $encodings = array('UTF-8', 'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3',
+ 'ISO-8859-4', 'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9',
+ 'ISO-8859-10', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16',
+ 'WINDOWS-1252', 'WINDOWS-1251', 'BIG5', 'GB2312');
+
+ if (function_exists('mb_detect_encoding') && ($enc = mb_detect_encoding($string, join(',', $encodings))))
return $enc;
// No match, check for UTF-8