www: viewdiff: fix UTF-8 names inside mbox attachments

This avoids `Wide character in print' warnings and ensures the
UTF-8 characters in `Signed-off-by' trailers are properly rendered
in HTML even when attempting to decode and display
application/octet-stream mbox attachments as HTML.

Linkification and reconstruction for coderepos is probably
still broken, but that is a much bigger task to fix, I think.

Fixes: ab9c03ff4aa369b3 ("www: use PerlIO::scalar (zfh) for buffering")

1 files changed, 8 insertions, 5 deletions

diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index fba3d76c..9a7adb57 100644
--- a/lib/PublicInbox/ViewDiff.pm
+++ b/lib/PublicInbox/ViewDiff.pm
@@ -7,8 +7,7 @@
 # (or reconstruct) blobs.
 
 package PublicInbox::ViewDiff;
-use strict;
-use v5.10.1;
+use v5.12;
 use parent qw(Exporter);
 our @EXPORT_OK = qw(flush_diff uri_escape_path);
 use URI::Escape qw(uri_escape_utf8);
@@ -197,7 +196,8 @@ sub flush_diff ($$) {
                                 $top[0] =~ $IS_OID) {
                         $dctx = diff_header(\$x, $ctx, \@top);
                 } elsif ($dctx) {
-                        open(my $afh, '>>', \(my $after='')) or die "open: $!";
+                        open(my $afh, '>>:utf8', \(my $after='')) or
+                                die "open: $!";
 
                         # Quiet "Complex regular subexpression recursion limit"
                         # warning.  Perl will truncate matches upon hitting
@@ -213,7 +213,7 @@ sub flush_diff ($$) {
                                         (?:(?:^-[^\n]*\n)+)|
                                         (?:^@@ [^\n]+\n))/xsm, $x)) {
                                 if (!defined($dctx)) {
-                                        print $afh $s;
+                                        print $afh $x;
                                 } elsif ($s =~ s/\A@@ (\S+) (\S+) @@//) {
                                         print $zfh qq(<span\nclass="hunk">),
                                                 diff_hunk($dctx, $1, $2),
@@ -234,7 +234,10 @@ sub flush_diff ($$) {
                                         print $zfh $lnk->to_html($s);
                                 }
                         }
-                        diff_before_or_after($ctx, \$after) if !$dctx;
+                        if (!$dctx) {
+                                utf8::decode($after);
+                                diff_before_or_after($ctx, \$after);
+                        }
                 } else {
                         diff_before_or_after($ctx, \$x);
                 }