Merge branch 'jk/mailmap-cleanup' into maint

* jk/mailmap-cleanup:
  contrib: update stats/mailmap script
  .mailmap: normalize emails for Linus Torvalds
  .mailmap: normalize emails for Jeff King
  .mailmap: fix broken entry for Martin Langhoff
  .mailmap: match up some obvious names/emails

2 files changed, 82 insertions, 33 deletions

diff --git a/.mailmap b/.mailmap
index bcf4f8770f..c7e8618300 100644
--- a/.mailmap
+++ b/.mailmap
@@ -9,7 +9,9 @@ Alex Bennée <kernel-hacker@bennee.com>
 Alexander Gavrilov <angavrilov@gmail.com>
 Aneesh Kumar K.V <aneesh.kumar@gmail.com>
 Brian M. Carlson <sandals@crustytoothpaste.ath.cx>
+Cheng Renquan <crquan@gmail.com>
 Chris Shoemaker <c.shoemaker@cox.net>
+Dan Johnson <computerdruid@gmail.com>
 Dana L. How <danahow@gmail.com>
 Dana L. How <how@deathvalley.cswitch.com>
 Daniel Barkalow <barkalow@iabervon.org>
@@ -18,14 +20,18 @@ David Kågedal <davidk@lysator.liu.se>
 David S. Miller <davem@davemloft.net>
 Deskin Miller <deskinm@umich.edu>
 Dirk Süsserott <newsletter@dirk.my1.cc>
+Eric S. Raymond <esr@thyrsus.com>
 Erik Faye-Lund <kusmabite@gmail.com> <kusmabite@googlemail.com>
 Fredrik Kuivinen <freku045@student.liu.se>
+Frédéric Heitzmann <frederic.heitzmann@gmail.com>
 H. Peter Anvin <hpa@bonde.sc.orionmulti.com>
 H. Peter Anvin <hpa@tazenda.sc.orionmulti.com>
 H. Peter Anvin <hpa@trantor.hos.anvin.org>
 Horst H. von Brand <vonbrand@inf.utfsm.cl>
 İsmail Dönmez <ismail@pardus.org.tr>
+Jakub Narębski <jnareb@gmail.com>
 Jay Soffian <jaysoffian+git@gmail.com>
+Jeff King <peff@peff.net> <peff@github.com>
 Joachim Berdal Haga <cjhaga@fys.uio.no>
 Johannes Sixt <j6t@kdbg.org> <johannes.sixt@telecom.at>
 Johannes Sixt <j6t@kdbg.org> <j.sixt@viscovery.net>
@@ -41,12 +47,21 @@ Junio C Hamano <gitster@pobox.com> <junio@hera.kernel.org>
 Junio C Hamano <gitster@pobox.com> <junio@kernel.org>
 Junio C Hamano <gitster@pobox.com> <junkio@cox.net>
 Karl Hasselström <kha@treskal.com>
+Kevin Leung <kevinlsk@gmail.com>
 Kent Engstrom <kent@lysator.liu.se>
 Lars Doelle <lars.doelle@on-line ! de>
 Lars Doelle <lars.doelle@on-line.de>
 Li Hong <leehong@pku.edu.cn>
+Linus Torvalds <torvalds@linux-foundation.org> <torvalds@woody.linux-foundation.org>
+Linus Torvalds <torvalds@linux-foundation.org> <torvalds@osdl.org>
+Linus Torvalds <torvalds@linux-foundation.org> <torvalds@g5.osdl.org>
+Linus Torvalds <torvalds@linux-foundation.org> <torvalds@evo.osdl.org>
+Linus Torvalds <torvalds@linux-foundation.org> <torvalds@ppc970.osdl.org>
+Linus Torvalds <torvalds@linux-foundation.org> <torvalds@ppc970.osdl.org.(none)>
 Lukas Sandström <lukass@etek.chalmers.se>
-Martin Langhoff <martin@laptop.org>
+Marc-André Lureau <marcandre.lureau@gmail.com>
+Mark Rada <marada@uwaterloo.ca>
+Martin Langhoff <martin@laptop.org> <martin@catalyst.net.nz>
 Martin von Zweigbergk <martinvonz@gmail.com> <martin.von.zweigbergk@gmail.com>
 Michael Coleman <tutufan@gmail.com>
 Michael J Gruber <git@drmicha.warpmail.net> <michaeljgruber+gmane@fastmail.fm>
@@ -63,11 +78,13 @@ Ralf Thielow <ralf.thielow@gmail.com> <ralf.thielow@googlemail.com>
 Ramsay Allan Jones <ramsay@ramsay1.demon.co.uk>
 René Scharfe <rene.scharfe@lsrfire.ath.cx>
 Robert Fitzsimons <robfitz@273k.net>
+Robert Zeh <robert.a.zeh@gmail.com>
 Sam Vilain <sam@vilain.net>
 Santi Béjar <sbejar@gmail.com>
 Sean Estabrooks <seanlkml@sympatico.ca>
 Shawn O. Pearce <spearce@spearce.org>
 Steven Grimm <koreth@midwinter.com>
+Tay Ray Chuan <rctay89@gmail.com>
 Theodore Ts'o <tytso@mit.edu>
 Thomas Rast <trast@inf.ethz.ch> <trast@student.ethz.ch>
 Tony Luck <tony.luck@intel.com>
diff --git a/contrib/stats/mailmap.pl b/contrib/stats/mailmap.pl
index 4b852e2455..9513f5e35b 100755
--- a/contrib/stats/mailmap.pl
+++ b/contrib/stats/mailmap.pl
@@ -1,38 +1,70 @@
-#!/usr/bin/perl -w
-my %mailmap = ();
-open I, "<", ".mailmap";
-while (<I>) {
-	chomp;
-	next if /^#/;
-	if (my ($author, $mail) = /^(.*?)\s+<(.+)>$/) {
-		$mailmap{$mail} = $author;
-	}
+#!/usr/bin/perl
+
+use warnings 'all';
+use strict;
+use Getopt::Long;
+
+my $match_emails;
+my $match_names;
+my $order_by = 'count';
+Getopt::Long::Configure(qw(bundling));
+GetOptions(
+	'emails|e!' => \$match_emails,
+	'names|n!'  => \$match_names,
+	'count|c'   => sub { $order_by = 'count' },
+	'time|t'    => sub { $order_by = 'stamp' },
+) or exit 1;
+$match_emails = 1 unless $match_names;
+
+my $email = {};
+my $name = {};
+
+open(my $fh, '-|', "git log --format='%at <%aE> %aN'");
+while(<$fh>) {
+	my ($t, $e, $n) = /(\S+) <(\S+)> (.*)/;
+	mark($email, $e, $n, $t);
+	mark($name, $n, $e, $t);
 }
-close I;
-
-my %mail2author = ();
-open I, "git log --pretty='format:%ae	%an' |";
-while (<I>) {
-	chomp;
-	my ($mail, $author) = split(/\t/, $_);
-	next if exists $mailmap{$mail};
-	$mail2author{$mail} ||= {};
-	$mail2author{$mail}{$author} ||= 0;
-	$mail2author{$mail}{$author}++;
+close($fh);
+
+if ($match_emails) {
+	foreach my $e (dups($email)) {
+		foreach my $n (vals($email->{$e})) {
+			show($n, $e, $email->{$e}->{$n});
+		}
+		print "\n";
+	}
 }
-close I;
-
-while (my ($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 %$authorcount);
-	if (1 < @names) {
-		for (@names) {
-			print "$_ <$mail>\n";
+if ($match_names) {
+	foreach my $n (dups($name)) {
+		foreach my $e (vals($name->{$n})) {
+			show($n, $e, $name->{$n}->{$e});
 		}
+		print "\n";
 	}
 }
+exit 0;
 
+sub mark {
+	my ($h, $k, $v, $t) = @_;
+	my $e = $h->{$k}->{$v} ||= { count => 0, stamp => 0 };
+	$e->{count}++;
+	$e->{stamp} = $t unless $t < $e->{stamp};
+}
+
+sub dups {
+	my $h = shift;
+	return grep { keys($h->{$_}) > 1 } keys($h);
+}
+
+sub vals {
+	my $h = shift;
+	return sort {
+		$h->{$b}->{$order_by} <=> $h->{$a}->{$order_by}
+	} keys($h);
+}
+
+sub show {
+	my ($n, $e, $h) = @_;
+	print "$n <$e> ($h->{$order_by})\n";
+}