viewdiff: assume diffstat and diff order are identical

For non-malicious messages, we can assume the diffstat and actual
diff appear in the same order.  Thus we can store {-long_paths} as
an arrayref and only compare the first element when we encounter
a truncated path.

This should make HTML rendering stable when there's basename
conflicts in message such as
https://lore.kernel.org/backports/1393202754-12919-13-git-send-email-hauke@hauke-m.de/

This diffstat anchor linkification can still be defeated by
users who make actual path names beginning with "...", but we
won't waste CPU cycles on it, either.

diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index 3d6058a93b5b528e83aa2e8b83b53c50e05043dc..34df8ad447c53a78460eb04c479f97be7c033262 100644 (file)
--- a/lib/PublicInbox/ViewDiff.pm
+++ b/lib/PublicInbox/ViewDiff.pm
@@ -82,10 +82,8 @@ sub anchor0 ($$$$) {
        $fn =~ s/{(?:.+) => (.+)}/$1/ or $fn =~ s/.* => (.+)/$1/;
        $fn = git_unquote($fn);
 
-       # long filenames will require us to walk backwards in anchor1
-       if ($fn =~ s!\A\.\.\./?!!) {
-               $ctx->{-long_path}->{$fn} = qr/\Q$fn\E\z/s;
-       }
+       # long filenames will require us to check in anchor1()
+       push(@{$ctx->{-long_path}}, $fn) if $fn =~ s!\A\.\.\./?!!;
 
        if (my $attr = to_attr($ctx->{-apfx}.$fn)) {
                $ctx->{-anchors}->{$attr} = 1;
@@ -105,17 +103,14 @@ sub anchor1 ($$) {
 
        my $ok = delete $ctx->{-anchors}->{$attr};
 
-       # unlikely, check the end of all long path names we captured:
+       # unlikely, check the end of long path names we captured,
+       # assume diffstat and diff output follow the same order,
+       # and ignore different ordering (could be malicious input)
        unless ($ok) {
-               my $lp = $ctx->{-long_path} or return;
-               foreach my $fn (keys %$lp) {
-                       $pb =~ $lp->{$fn} or next;
-
-                       delete $lp->{$fn};
-                       $attr = to_attr($ctx->{-apfx}.$fn) or return;
-                       $ok = delete $ctx->{-anchors}->{$attr} or return;
-                       last;
-               }
+               my $fn = shift(@{$ctx->{-long_path}}) or return;
+               $pb =~ /\Q$fn\E\z/s or return;
+               $attr = to_attr($ctx->{-apfx}.$fn) or return;
+               $ok = delete $ctx->{-anchors}->{$attr} or return;
        }
        $ok ? "<a\nhref=#i$attr\nid=$attr>diff</a> --git" : undef
 }