Add contrib/stats/mailmap.pl script

This script reads the existing commit log and .mailmap file,
and outputs author e-mail addresses that would map to more
than one names (most likely due to difference in the way they
are spelled, but some are due to ancient botched commits).

Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 38 insertions, 0 deletions

diff --git a/contrib/stats/mailmap.pl b/contrib/stats/mailmap.pl
new file mode 100755
index 0000000000..4b852e2455
--- /dev/null
+++ b/contrib/stats/mailmap.pl
@@ -0,0 +1,38 @@
+#!/usr/bin/perl -w
+my %mailmap = ();
+open I, "<", ".mailmap";
+while (<I>) {
+	chomp;
+	next if /^#/;
+	if (my ($author, $mail) = /^(.*?)\s+<(.+)>$/) {
+		$mailmap{$mail} = $author;
+	}
+}
+close I;
+
+my %mail2author = ();
+open I, "git log --pretty='format:%ae	%an' |";
+while (<I>) {
+	chomp;
+	my ($mail, $author) = split(/\t/, $_);
+	next if exists $mailmap{$mail};
+	$mail2author{$mail} ||= {};
+	$mail2author{$mail}{$author} ||= 0;
+	$mail2author{$mail}{$author}++;
+}
+close I;
+
+while (my ($mail, $authorcount) = each %mail2author) {
+	# %$authorcount is ($author => $count);
+	# sort and show the names from the most frequent ones.
+	my @names = (map { $_->[0] }
+		sort { $b->[1] <=> $a->[1] }
+		map { [$_, $authorcount->{$_}] }
+		keys %$authorcount);
+	if (1 < @names) {
+		for (@names) {
+			print "$_ <$mail>\n";
+		}
+	}
+}
+