repobrowse: /commit/ forces everything to UTF-8

Hopefully we'll show some names properly in our pages now,
as well as simplify our code when escaping text for HTML
display.

Additionally, tweak our diff display by using <ins> and
<del> tags for added/removed text, respectively.  This should
allow users to choose their own styles when viewing diffs
in their browser while being meaningful to people who cannot
differentiate colors.

1 files changed, 6 insertions, 1 deletions

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index a16cd4a1..2974c683 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -10,7 +10,7 @@ use Encode qw(find_encoding);
 use URI::Escape qw(uri_escape_utf8);
 use PublicInbox::MID qw/mid_clean/;
 use base qw/Exporter/;
-our @EXPORT_OK = qw/ascii_html/;
+our @EXPORT_OK = qw/ascii_html utf8_html/;
 
 # for user-generated content (UGC) which may have excessively long lines
 # and screw up rendering on some browsers.  This is the only CSS style
@@ -71,6 +71,11 @@ sub ascii_html {
         $enc_ascii->encode($s, Encode::HTMLCREF);
 }
 
+sub utf8_html {
+        my ($raw) = @_;
+        ascii_html($enc_utf8->decode($raw));
+}
+
 sub as_html { ascii_html($_[0]->{raw}) }
 sub as_href { ascii_html(uri_escape_utf8($_[0]->{href})) }