viewdiff: stricter highlighting and linkification check

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

diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index d22c80b97b4871a00dba47f3e8b055bd1659ab06..6fe9a0d7610e5a345ede4c74abd362514502ce61 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;
@@ -105,23 +103,20 @@ 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
 }
 
-sub diff_header ($$$$) {
-       my ($dst, $x, $ctx, $top) = @_;
+sub diff_header ($$$) {
+       my ($x, $ctx, $top) = @_;
        my (undef, undef, $pa, $pb) = splice(@$top, 0, 4); # ignore oid_{a,b}
        my $spfx = $ctx->{-spfx};
        my $dctx = { spfx => $spfx };
@@ -159,19 +154,23 @@ sub diff_header ($$$$) {
                warn "BUG? <$$x> had no ^index line";
        }
        $$x =~ s!^diff --git!anchor1($ctx, $pb) // 'diff --git'!ems;
+       my $dst = $ctx->{obuf};
        $$dst .= qq(<span\nclass="head">);
        $$dst .= $$x;
        $$dst .= '</span>';
        $dctx;
 }
 
-sub diff_before_or_after ($$$) {
-       my ($dst, $ctx, $x) = @_;
+sub diff_before_or_after ($$) {
+       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) {
@@ -186,22 +185,34 @@ sub diff_before_or_after ($$$) {
 }
 
 # callers must do CRLF => LF conversion before calling this
-sub flush_diff ($$$) {
-       my ($dst, $ctx, $cur) = @_;
+sub flush_diff ($$) {
+       my ($ctx, $cur) = @_;
 
        my @top = split($EXTRACT_DIFFS, $$cur);
-       $$cur = undef;
+       undef $$cur; # free memory
 
        my $linkify = $ctx->{-linkify};
+       my $dst = $ctx->{obuf};
        my $dctx; # {}, keys: Q, oid_a, oid_b
 
        while (defined(my $x = shift @top)) {
                if (scalar(@top) >= 4 &&
                                $top[1] =~ $IS_OID &&
                                $top[0] =~ $IS_OID) {
-                       $dctx = diff_header($dst, \$x, $ctx, \@top);
+                       $dctx = diff_header(\$x, $ctx, \@top);
                } elsif ($dctx) {
                        my $after = '';
+
+                       # Quiet "Complex regular subexpression recursion limit"
+                       # warning.  Perl will truncate matches upon hitting
+                       # that limit, giving us more (and shorter) scalars than
+                       # would be ideal, but otherwise it's harmless.
+                       #
+                       # We could replace the `+' metacharacter with `{1,100}'
+                       # to limit the matches ourselves to 100, but we can
+                       # let Perl do it for us, quietly.
+                       no warnings 'regexp';
+
                        for my $s (split(/((?:(?:^\+[^\n]*\n)+)|
                                        (?:(?:^-[^\n]*\n)+)|
                                        (?:^@@ [^\n]+\n))/xsm, $x)) {
@@ -227,9 +238,9 @@ sub flush_diff ($$$) {
                                        $$dst .= $linkify->to_html($s);
                                }
                        }
-                       diff_before_or_after($dst, $ctx, \$after) unless $dctx;
+                       diff_before_or_after($ctx, \$after) unless $dctx;
                } else {
-                       diff_before_or_after($dst, $ctx, \$x);
+                       diff_before_or_after($ctx, \$x);
                }
        }
 }