" globbed: $refname\n";
}
my $u = (::cmt_metadata("$refname"))[0];
+ if (!defined($u)) {
+ warn
+"W: $refname: no associated commit metadata from SVN, skipping\n";
+ next;
+ }
$u =~ s!^\Q$url\E(/|$)!! or die
"$refname: '$url' not found in '$u'\n";
if ($pathname ne $u) {
sub mkemptydirs {
my ($self, $r) = @_;
+ # add/remove/collect a paths table
+ #
+ # Paths are split into a tree of nodes, stored as a hash of hashes.
+ #
+ # Each node contains a 'path' entry for the path (if any) associated
+ # with that node and a 'children' entry for any nodes under that
+ # location.
+ #
+ # Removing a path requires a hash lookup for each component then
+ # dropping that node (and anything under it), which is substantially
+ # faster than a grep slice into a single hash of paths for large
+ # numbers of paths.
+ #
+ # For a large (200K) number of empty_dir directives this reduces
+ # scanning time to 3 seconds vs 10 minutes for grep+delete on a single
+ # hash of paths.
+ sub add_path {
+ my ($paths_table, $path) = @_;
+ my $node_ref;
+
+ foreach my $x (split('/', $path)) {
+ if (!exists($paths_table->{$x})) {
+ $paths_table->{$x} = { children => {} };
+ }
+
+ $node_ref = $paths_table->{$x};
+ $paths_table = $paths_table->{$x}->{children};
+ }
+
+ $node_ref->{path} = $path;
+ }
+
+ sub remove_path {
+ my ($paths_table, $path) = @_;
+ my $nodes_ref;
+ my $node_name;
+
+ foreach my $x (split('/', $path)) {
+ if (!exists($paths_table->{$x})) {
+ return;
+ }
+
+ $nodes_ref = $paths_table;
+ $node_name = $x;
+
+ $paths_table = $paths_table->{$x}->{children};
+ }
+
+ delete($nodes_ref->{$node_name});
+ }
+
+ sub collect_paths {
+ my ($paths_table, $paths_ref) = @_;
+
+ foreach my $v (values %$paths_table) {
+ my $p = $v->{path};
+ my $c = $v->{children};
+
+ collect_paths($c, $paths_ref);
+
+ if (defined($p)) {
+ push(@$paths_ref, $p);
+ }
+ }
+ }
+
sub scan {
- my ($r, $empty_dirs, $line) = @_;
+ my ($r, $paths_table, $line) = @_;
if (defined $r && $line =~ /^r(\d+)$/) {
return 0 if $1 > $r;
} elsif ($line =~ /^ \+empty_dir: (.+)$/) {
- $empty_dirs->{$1} = 1;
+ add_path($paths_table, $1);
} elsif ($line =~ /^ \-empty_dir: (.+)$/) {
- my @d = grep {m[^\Q$1\E(/|$)]} (keys %$empty_dirs);
- delete @$empty_dirs{@d};
+ remove_path($paths_table, $1);
}
1; # continue
};
- my %empty_dirs = ();
+ my @empty_dirs;
+ my %paths_table;
+
my $gz_file = "$self->{dir}/unhandled.log.gz";
if (-f $gz_file) {
if (!can_compress()) {
die "Unable to open $gz_file: $!\n";
my $line;
while ($gz->gzreadline($line) > 0) {
- scan($r, \%empty_dirs, $line) or last;
+ scan($r, \%paths_table, $line) or last;
}
$gz->gzclose;
}
if (open my $fh, '<', "$self->{dir}/unhandled.log") {
binmode $fh or croak "binmode: $!";
while (<$fh>) {
- scan($r, \%empty_dirs, $_) or last;
+ scan($r, \%paths_table, $_) or last;
}
close $fh;
}
+ collect_paths(\%paths_table, \@empty_dirs);
my $strip = qr/\A\Q@{[$self->path]}\E(?:\/|$)/;
- foreach my $d (sort keys %empty_dirs) {
+ foreach my $d (sort @empty_dirs) {
$d = uri_decode($d);
$d =~ s/$strip//;
next unless length($d);
my @parents = @$parents;
my $props = $ed->{dir_prop}{$self->path};
- if ( $props->{"svk:merge"} ) {
- $self->find_extra_svk_parents($props->{"svk:merge"}, \@parents);
- }
- if ( $props->{"svn:mergeinfo"} ) {
- my $mi_changes = $self->mergeinfo_changes
- ($parent_path, $parent_rev,
- $self->path, $rev,
- $props->{"svn:mergeinfo"});
- $self->find_extra_svn_parents($mi_changes, \@parents);
+ if ($self->follow_parent) {
+ my $tickets = $props->{"svk:merge"};
+ if ($tickets) {
+ $self->find_extra_svk_parents($tickets, \@parents);
+ }
+
+ my $mergeinfo_prop = $props->{"svn:mergeinfo"};
+ if ($mergeinfo_prop) {
+ my $mi_changes = $self->mergeinfo_changes(
+ $parent_path,
+ $parent_rev,
+ $self->path,
+ $rev,
+ $mergeinfo_prop);
+ $self->find_extra_svn_parents($mi_changes, \@parents);
+ }
}
open my $un, '>>', "$self->{dir}/unhandled.log" or croak $!;