contacts: gather all blame sources prior to invoking git-blame

git-contacts invokes git-blame immediately upon encountering a patch
hunk. No attempt is made to consolidate invocations for multiple hunks
referencing the same file at the same revision. This can become
expensive quickly.

Any effort to reduce the number of times git-blame is run will need to
to know in advance which line ranges to blame per file per revision.
Make this information available by collecting all sources as a distinct
step from invoking git-blame.  A subsequent patch will utilize the
information to optimize git-blame invocations.

Signed-off-by: Eric Sunshine <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: sunshineco

contrib/contacts/git-contacts

@@ -74,8 +74,20 @@ sub get_blame {
 	close $f;
 }
 
+sub blame_sources {
+	my ($sources, $commits) = @_;
+	for my $s (keys %$sources) {
+		for my $id (keys %{$sources->{$s}}) {
+			for my $range (@{$sources->{$s}{$id}}) {
+				get_blame($commits, $s,
+					  $range->[0], $range->[1], $id);
+			}
+		}
+	}
+}
+
 sub scan_patches {
-	my ($commits, $id, $f) = @_;
+	my ($sources, $id, $f) = @_;
 	my $source;
 	while (<$f>) {
 		if (/^From ([0-9a-f]{40}) Mon Sep 17 00:00:00 2001$/) {
@@ -89,7 +101,7 @@ sub scan_patches {
 			die "Cannot parse hunk source: $_\n";
 		} elsif (/^@@ -(\d+)(?:,(\d+))?/ && $source) {
 			my $len = defined($2) ? $2 : 1;
-			get_blame($commits, $source, $1, $len, $id) if $len;
+			push @{$sources->{$source}{$id}}, [$1, $len] if $len;
 		}
 	}
 }
@@ -162,13 +174,16 @@ for (@ARGV) {
 	}
 }
 
-my %commits;
+my %sources;
 for (@files) {
-	scan_patch_file(\%commits, $_);
+	scan_patch_file(\%sources, $_);
 }
 if (@rev_args) {
-	scan_rev_args(\%commits, \@rev_args)
+	scan_rev_args(\%sources, \@rev_args)
 }
+
+my %commits;
+blame_sources(\%sources, \%commits);
 import_commits(\%commits);
 
 my $contacts = {};