#!/usr/bin/perl

# List people who might be interested in a patch.  Useful as the argument to
# git-send-email --cc-cmd option, and in other situations.
#
# Usage: git contacts <file | rev-list option> ...

use strict;
use warnings;
use IPC::Open2;

my $since = '5-years-ago';
my $min_percent = 10;
my $labels_rx = qr/Signed-off-by|Reviewed-by|Acked-by|Cc/i;
my %seen;

sub format_contact {
        my ($name, $email) = @_;
        return "$name <$email>";
}

sub parse_commit {
        my ($commit, $data) = @_;
        my $contacts = $commit->{contacts};
        my $inbody = 0;
        for (split(/^/m, $data)) {
                if (not $inbody) {
                        if (/^author ([^<>]+) <(\S+)> .+$/) {
                                $contacts->{format_contact($1, $2)} = 1;
                        } elsif (/^$/) {
                                $inbody = 1;
                        }
                } elsif (/^$labels_rx:\s+([^<>]+)\s+<(\S+?)>$/o) {
                        $contacts->{format_contact($1, $2)} = 1;
                }
        }
}

sub import_commits {
        my ($commits) = @_;
        return unless %$commits;
        my $pid = open2 my $reader, my $writer, qw(git cat-file --batch);
        for my $id (keys(%$commits)) {
                print $writer "$id\n";
                my $line = <$reader>;
                if ($line =~ /^([0-9a-f]{40}) commit (\d+)/) {
                        my ($cid, $len) = ($1, $2);
                        die "expected $id but got $cid\n" unless $id eq $cid;
                        my $data;
                        # cat-file emits newline after data, so read len+1
                        read $reader, $data, $len + 1;
                        parse_commit($commits->{$id}, $data);
                }
        }
        close $reader;
        close $writer;
        waitpid($pid, 0);
        die "git-cat-file error: $?\n" if $?;
}

sub get_blame {
        my ($commits, $source, $start, $len, $from) = @_;
        open my $f, '-|',
                qw(git blame --porcelain -C), '-L', "$start,+$len",
                '--since', $since, "$from^", '--', $source or die;
        while (<$f>) {
                if (/^([0-9a-f]{40}) \d+ \d+ \d+$/) {
                        my $id = $1;
                        $commits->{$id} = { id => $id, contacts => {} }
                                unless $seen{$id};
                        $seen{$id} = 1;
                }
        }
        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 ($sources, $id, $f) = @_;
        my $source;
        while (<$f>) {
                if (/^From ([0-9a-f]{40}) Mon Sep 17 00:00:00 2001$/) {
                        $id = $1;
                        $seen{$id} = 1;
                }
                next unless $id;
                if (m{^--- (?:a/(.+)|/dev/null)$}) {
                        $source = $1;
                } elsif (/^--- /) {
                        die "Cannot parse hunk source: $_\n";
                } elsif (/^@@ -(\d+)(?:,(\d+))?/ && $source) {
                        my $len = defined($2) ? $2 : 1;
                        push @{$sources->{$source}{$id}}, [$1, $len] if $len;
                }
        }
}

sub scan_patch_file {
        my ($commits, $file) = @_;
        open my $f, '<', $file or die "read failure: $file: $!\n";
        scan_patches($commits, undef, $f);
        close $f;
}

sub parse_rev_args {
        my @args = @_;
        open my $f, '-|',
                qw(git rev-parse --revs-only --default HEAD --symbolic), @args
                or die;
        my @revs;
        while (<$f>) {
                chomp;
                push @revs, $_;
        }
        close $f;
        return @revs if scalar(@revs) != 1;
        return "^$revs[0]", 'HEAD' unless $revs[0] =~ /^-/;
        return $revs[0], 'HEAD';
}

sub scan_rev_args {
        my ($commits, $args) = @_;
        my @revs = parse_rev_args(@$args);
        open my $f, '-|', qw(git rev-list --reverse), @revs or die;
        while (<$f>) {
                chomp;
                my $id = $_;
                $seen{$id} = 1;
                open my $g, '-|', qw(git show -C --oneline), $id or die;
                scan_patches($commits, $id, $g);
                close $g;
        }
        close $f;
}

sub mailmap_contacts {
        my ($contacts) = @_;
        my %mapped;
        my $pid = open2 my $reader, my $writer, qw(git check-mailmap --stdin);
        for my $contact (keys(%$contacts)) {
                print $writer "$contact\n";
                my $canonical = <$reader>;
                chomp $canonical;
                $mapped{$canonical} += $contacts->{$contact};
        }
        close $reader;
        close $writer;
        waitpid($pid, 0);
        die "git-check-mailmap error: $?\n" if $?;
        return \%mapped;
}

if (!@ARGV) {
        die "No input revisions or patch files\n";
}

my (@files, @rev_args);
for (@ARGV) {
        if (-e) {
                push @files, $_;
        } else {
                push @rev_args, $_;
        }
}

my %sources;
for (@files) {
        scan_patch_file(\%sources, $_);
}
if (@rev_args) {
        scan_rev_args(\%sources, \@rev_args)
}

my %commits;
blame_sources(\%sources, \%commits);
import_commits(\%commits);

my $contacts = {};
for my $commit (values %commits) {
        for my $contact (keys %{$commit->{contacts}}) {
                $contacts->{$contact}++;
        }
}
$contacts = mailmap_contacts($contacts);

my $ncommits = scalar(keys %commits);
for my $contact (keys %$contacts) {
        my $percent = $contacts->{$contact} * 100 / $ncommits;
        next if $percent < $min_percent;
        print "$contact\n";
}