From bc1e4faa70fb0fcfdeabb6e76597cb3ec5952975 Mon Sep 17 00:00:00 2001
From: Aleksander Machniak <alec@alec.pl>
Date: Thu, 13 Sep 2012 05:14:26 -0400
Subject: [PATCH] Fix convertion to/from US-ASCII using mbstring Define mbstring substitute_character to work as iconv //IGNORE
---
program/include/rcube_charset.php | 21 +++++++++++++++++----
1 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/program/include/rcube_charset.php b/program/include/rcube_charset.php
index 039d5b1..35c6972 100644
--- a/program/include/rcube_charset.php
+++ b/program/include/rcube_charset.php
@@ -176,6 +176,7 @@
{
static $iconv_options = null;
static $mbstring_list = null;
+ static $mbstring_sch = null;
static $conv = null;
$to = empty($to) ? strtoupper(RCMAIL_CHARSET) : $to;
@@ -221,6 +222,7 @@
if ($mbstring_list === null) {
if (extension_loaded('mbstring')) {
+ $mbstring_sch = mb_substitute_character();
$mbstring_list = mb_list_encodings();
$mbstring_list = array_map('strtoupper', $mbstring_list);
}
@@ -229,14 +231,25 @@
// convert charset using mbstring module
if ($mbstring_list !== null) {
$aliases['WINDOWS-1257'] = 'ISO-8859-13';
+ // it happens that mbstring supports ASCII but not US-ASCII
+ if (($from == 'US-ASCII' || $to == 'US-ASCII') && !in_array('US-ASCII', $mbstring_list)) {
+ $aliases['US-ASCII'] = 'ASCII';
+ }
$mb_from = $aliases[$from] ? $aliases[$from] : $from;
$mb_to = $aliases[$to] ? $aliases[$to] : $to;
// return if encoding found, string matches encoding and convert succeeded
if (in_array($mb_from, $mbstring_list) && in_array($mb_to, $mbstring_list)) {
- if (mb_check_encoding($str, $mb_from) && ($out = mb_convert_encoding($str, $mb_to, $mb_from))) {
- return $out;
+ if (mb_check_encoding($str, $mb_from)) {
+ // Do the same as //IGNORE with iconv
+ mb_substitute_character('none');
+ $out = mb_convert_encoding($str, $mb_to, $mb_from);
+ mb_substitute_character($mbstring_sch);
+
+ if ($out !== false) {
+ return $out;
+ }
}
}
}
@@ -646,14 +659,14 @@
return $failover;
}
- // FIXME: the order is important, because sometimes
+ // FIXME: the order is important, because sometimes
// iso string is detected as euc-jp and etc.
$enc = array(
'UTF-8', 'SJIS', 'BIG5', 'GB2312',
'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',
+ 'WINDOWS-1252', 'WINDOWS-1251', 'EUC-JP', 'EUC-TW', 'KOI8-R',
'ISO-2022-KR', 'ISO-2022-JP'
);
--
Gitblit v1.9.1