From f53e5933315a316bb94d8d27cebbb95554aca6ba Mon Sep 17 00:00:00 2001
From: David Phillips <david@sighup.nz>
Date: Tue, 10 Apr 2018 23:53:18 +1200
Subject: Decode HTML body before passing to to head parser
From the HTML::HeadParser docs:
> Note that the HTML::HeadParser might get confused if raw undecoded UTF-8 is
> passed to the parse() method. Make sure the strings are properly decoded
> before passing them on.
This explains some hard-to-trace bugs with character mangling
---
Plugin/URL_Title.pm | 1 +
1 file changed, 1 insertion(+)
diff --git a/Plugin/URL_Title.pm b/Plugin/URL_Title.pm
index 495df8e..8248560 100644
--- a/Plugin/URL_Title.pm
+++ b/Plugin/URL_Title.pm
@@ -45,6 +45,7 @@ sub message
}
my $html = $response->{content};
+ utf8::decode($html);
my $parser = HTML::HeadParser->new;
$parser->parse($html);
--
cgit v1.1