From 3dcc0583c11d364124b5c98ee93913f5b7c93f8d Mon Sep 17 00:00:00 2001
From: Jared Hancock <jared@osticket.com>
Date: Tue, 4 Mar 2014 17:17:08 -0600
Subject: [PATCH] html2text: Fix Unicode character munging
This issue was addressed for htmLawed, where the UTF-8 version of a
non-breaking space, 0xc2a0 would be collapsed to 0xa0, which would very
likely create an invalid Unicode character, and the text block would be
dropped or truncated.
---
include/html2text.php | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/html2text.php b/include/html2text.php
index c44997614..48b0b3ee1 100644
--- a/include/html2text.php
+++ b/include/html2text.php
@@ -201,7 +201,7 @@ class HtmlInlineElement {
case 'normal':
default:
if ($after_block) $more = ltrim($more);
- $more = preg_replace('/\s+/m', ' ', $more);
+ $more = preg_replace('/[ \r\n\t\f]+/mu', ' ', $more);
}
}
elseif ($c instanceof HtmlInlineElement) {
--
GitLab