update copyrights for 2021

[public-inbox.git] / lib / PublicInbox / ViewDiff.pm

diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index 3d6058a93b5b528e83aa2e8b83b53c50e05043dc..8fe7261ff2909220b7e3e28c6f7f07b97c9e173f 100644 (file)
--- a/lib/PublicInbox/ViewDiff.pm
+++ b/lib/PublicInbox/ViewDiff.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2019-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2019-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # used by PublicInbox::View
@@ -18,8 +18,8 @@ use PublicInbox::Git qw(git_unquote);
 
 sub UNSAFE () { "^A-Za-z0-9\-\._~/" }
 
-my $OID_NULL = '0{7,40}';
-my $OID_BLOB = '[a-f0-9]{7,40}';
+my $OID_NULL = '0{7,}';
+my $OID_BLOB = '[a-f0-9]{7,}';
 my $LF = qr!\n!;
 my $ANY = qr![^\n]!;
 my $FN = qr!(?:"?[^/\n]+/[^\n]+|/dev/null)!;
@@ -50,12 +50,12 @@ sub diff_hunk ($$$$) {
 
        if (defined($spfx) && defined($oid_a) && defined($oid_b)) {
                my ($n) = ($ca =~ /^-([0-9]+)/);
-               $n = defined($n) ? do { ++$n; "#n$n" } : '';
+               $n = defined($n) ? "#n$n" : '';
 
                $$dst .= qq(@@ <a\nhref="$spfx$oid_a/s/$dctx->{Q}$n">$ca</a>);
 
                ($n) = ($cb =~ /^\+([0-9]+)/);
-               $n = defined($n) ? do { ++$n; "#n$n" } : '';
+               $n = defined($n) ? "#n$n" : '';
                $$dst .= qq( <a\nhref="$spfx$oid_b/s/$dctx->{Q}$n">$cb</a> @@);
        } else {
                $$dst .= "@@ $ca $cb @@";
@@ -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
 }
@@ -170,10 +165,12 @@ sub diff_before_or_after ($$) {
        my ($ctx, $x) = @_;
        my $linkify = $ctx->{-linkify};
        my $dst = $ctx->{obuf};
+       my $anchors = exists($ctx->{-anchors}) ? 1 : 0;
        for my $y (split(/(^---\n)/sm, $$x)) {
                if ($y =~ /\A---\n\z/s) {
                        $$dst .= "---\n"; # all HTML is "\r\n" => "\n"
-               } elsif ($y =~ /^ [0-9]+ files? changed, /sm) {
+                       $anchors |= 2;
+               } elsif ($anchors == 3 && $y =~ /^ [0-9]+ files? changed, /sm) {
                        # ok, looks like a diffstat, go line-by-line:
                        for my $l (split(/^/m, $y)) {
                                if ($l =~ /^ (.+)( +\| .*\z)/s) {