get_maintainer.pl

#!/usr/bin/perl -w
# (c) 2007, Joe Perches <joe@perches.com>
#           created from checkpatch.pl
#
# Print selected MAINTAINERS information for
# the files modified in a patch or for a file
#
# usage: perl scripts/get_maintainer.pl [OPTIONS] <patch>
#        perl scripts/get_maintainer.pl [OPTIONS] -f <file>
#
# Licensed under the terms of the GNU GPL License version 2

use strict;

my $P = $0;
my $V = '0.26';

use Getopt::Long qw(:config no_auto_abbrev);

my $lk_path = "./";
my $email = 1;
my $email_usename = 1;
my $email_maintainer = 1;
my $email_list = 1;
my $email_subscriber_list = 0;
my $email_git_penguin_chiefs = 0;
my $email_git = 0;
my $email_git_all_signature_types = 0;
my $email_git_blame = 0;
my $email_git_blame_signatures = 1;
my $email_git_fallback = 1;
my $email_git_min_signatures = 1;
my $email_git_max_maintainers = 5;
my $email_git_min_percent = 5;
my $email_git_since = "1-year-ago";
my $email_hg_since = "-365";
my $interactive = 0;
my $email_remove_duplicates = 1;
my $email_use_mailmap = 1;
my $output_multiline = 1;
my $output_separator = ", ";
my $output_roles = 0;
my $output_rolestats = 1;
my $scm = 0;
my $web = 0;
my $subsystem = 0;
my $status = 0;
my $keywords = 1;
my $sections = 0;
my $file_emails = 0;
my $from_filename = 0;
my $pattern_depth = 0;
my $version = 0;
my $help = 0;

my $vcs_used = 0;

my $exit = 0;

my %commit_author_hash;
my %commit_signer_hash;

my @penguin_chief = ();
push(@penguin_chief, "Linus Torvalds:torvalds\@linux-foundation.org");
#Andrew wants in on most everything - 2009/01/14
#push(@penguin_chief, "Andrew Morton:akpm\@linux-foundation.org");

my @penguin_chief_names = ();
foreach my $chief (@penguin_chief) {
    if ($chief =~ m/^(.*):(.*)/) {
	my $chief_name = $1;
	my $chief_addr = $2;
	push(@penguin_chief_names, $chief_name);
    }
}
my $penguin_chiefs = "\(" . join("|", @penguin_chief_names) . "\)";

# Signature types of people who are either
# 	a) responsible for the code in question, or
# 	b) familiar enough with it to give relevant feedback
my @signature_tags = ();
push(@signature_tags, "Signed-off-by:");
push(@signature_tags, "Reviewed-by:");
push(@signature_tags, "Acked-by:");

my $signature_pattern = "\(" . join("|", @signature_tags) . "\)";

# rfc822 email address - preloaded methods go here.
my $rfc822_lwsp = "(?:(?:\\r\\n)?[ \\t])";
my $rfc822_char = '[\\000-\\377]';

# VCS command support: class-like functions and strings

my %VCS_cmds;

my %VCS_cmds_git = (
    "execute_cmd" => \&git_execute_cmd,
    "available" => '(which("git") ne "") && (-d ".git")',
    "find_signers_cmd" =>
	"git log --no-color --follow --since=\$email_git_since " .
	    '--format="GitCommit: %H%n' .
		      'GitAuthor: %an <%ae>%n' .
		      'GitDate: %aD%n' .
		      'GitSubject: %s%n' .
		      '%b%n"' .
	    " -- \$file",
    "find_commit_signers_cmd" =>
	"git log --no-color " .
	    '--format="GitCommit: %H%n' .
		      'GitAuthor: %an <%ae>%n' .
		      'GitDate: %aD%n' .
		      'GitSubject: %s%n' .
		      '%b%n"' .
	    " -1 \$commit",
    "find_commit_author_cmd" =>
	"git log --no-color " .
	    '--format="GitCommit: %H%n' .
		      'GitAuthor: %an <%ae>%n' .
		      'GitDate: %aD%n' .
		      'GitSubject: %s%n"' .
	    " -1 \$commit",
    "blame_range_cmd" => "git blame -l -L \$diff_start,+\$diff_length \$file",
    "blame_file_cmd" => "git blame -l \$file",
    "commit_pattern" => "^GitCommit: ([0-9a-f]{40,40})",
    "blame_commit_pattern" => "^([0-9a-f]+) ",
    "author_pattern" => "^GitAuthor: (.*)",
    "subject_pattern" => "^GitSubject: (.*)",
);

my %VCS_cmds_hg = (
    "execute_cmd" => \&hg_execute_cmd,
    "available" => '(which("hg") ne "") && (-d ".hg")',
    "find_signers_cmd" =>
	"hg log --date=\$email_hg_since " .
	    "--template='HgCommit: {node}\\n" .
	                "HgAuthor: {author}\\n" .
			"HgSubject: {desc}\\n'" .
	    " -- \$file",
    "find_commit_signers_cmd" =>
	"hg log " .
	    "--template='HgSubject: {desc}\\n'" .
	    " -r \$commit",
    "find_commit_author_cmd" =>
	"hg log " .
	    "--template='HgCommit: {node}\\n" .
		        "HgAuthor: {author}\\n" .
			"HgSubject: {desc|firstline}\\n'" .
	    " -r \$commit",
    "blame_range_cmd" => "",		# not supported
    "blame_file_cmd" => "hg blame -n \$file",
    "commit_pattern" => "^HgCommit: ([0-9a-f]{40,40})",
    "blame_commit_pattern" => "^([ 0-9a-f]+):",
    "author_pattern" => "^HgAuthor: (.*)",
    "subject_pattern" => "^HgSubject: (.*)",
);

my $conf = which_conf(".get_maintainer.conf");
if (-f $conf) {
    my @conf_args;
    open(my $conffile, '<', "$conf")
	or warn "$P: Can't find a readable .get_maintainer.conf file $!\n";

    while (<$conffile>) {
	my $line = $_;

	$line =~ s/\s*\n?$//g;
	$line =~ s/^\s*//g;
	$line =~ s/\s+/ /g;

	next if ($line =~ m/^\s*#/);
	next if ($line =~ m/^\s*$/);

	my @words = split(" ", $line);
	foreach my $word (@words) {
	    last if ($word =~ m/^#/);
	    push (@conf_args, $word);
	}
    }
    close($conffile);
    unshift(@ARGV, @conf_args) if @conf_args;
}

if (!GetOptions(
		'email!' => \$email,
		'git!' => \$email_git,
		'git-all-signature-types!' => \$email_git_all_signature_types,
		'git-blame!' => \$email_git_blame,
		'git-blame-signatures!' => \$email_git_blame_signatures,
		'git-fallback!' => \$email_git_fallback,
		'git-chief-penguins!' => \$email_git_penguin_chiefs,
		'git-min-signatures=i' => \$email_git_min_signatures,
		'git-max-maintainers=i' => \$email_git_max_maintainers,
		'git-min-percent=i' => \$email_git_min_percent,
		'git-since=s' => \$email_git_since,
		'hg-since=s' => \$email_hg_since,
		'i|interactive!' => \$interactive,
		'remove-duplicates!' => \$email_remove_duplicates,
		'mailmap!' => \$email_use_mailmap,
		'm!' => \$email_maintainer,
		'n!' => \$email_usename,
		'l!' => \$email_list,
		's!' => \$email_subscriber_list,
		'multiline!' => \$output_multiline,
		'roles!' => \$output_roles,
		'rolestats!' => \$output_rolestats,
		'separator=s' => \$output_separator,
		'subsystem!' => \$subsystem,
		'status!' => \$status,
		'scm!' => \$scm,
		'web!' => \$web,
		'pattern-depth=i' => \$pattern_depth,
		'k|keywords!' => \$keywords,
		'sections!' => \$sections,
		'fe|file-emails!' => \$file_emails,
		'f|file' => \$from_filename,
		'v|version' => \$version,
		'h|help|usage' => \$help,
		)) {
    die "$P: invalid argument - use --help if necessary\n";
}

if ($help != 0) {
    usage();
    exit 0;
}

if ($version != 0) {
    print("${P} ${V}\n");
    exit 0;
}

if (-t STDIN && !@ARGV) {
    # We're talking to a terminal, but have no command line arguments.
    die "$P: missing patchfile or -f file - use --help if necessary\n";
}

$output_multiline = 0 if ($output_separator ne ", ");
$output_rolestats = 1 if ($interactive);
$output_roles = 1 if ($output_rolestats);

if ($sections) {
    $email = 0;
    $email_list = 0;
    $scm = 0;
    $status = 0;
    $subsystem = 0;
    $web = 0;
    $keywords = 0;
    $interactive = 0;
} else {
    my $selections = $email + $scm + $status + $subsystem + $web;
    if ($selections == 0) {
	die "$P:  Missing required option: email, scm, status, subsystem or web\n";
    }
}

if ($email &&
    ($email_maintainer + $email_list + $email_subscriber_list +
     $email_git + $email_git_penguin_chiefs + $email_git_blame) == 0) {
    die "$P: Please select at least 1 email option\n";
}

if (!top_of_kernel_tree($lk_path)) {
    die "$P: The current directory does not appear to be "
	. "a linux kernel source tree.\n";
}

## Read MAINTAINERS for type/value pairs

my @typevalue = ();
my %keyword_hash;

open (my $maint, '<', "${lk_path}MAINTAINERS")
    or die "$P: Can't open MAINTAINERS: $!\n";
while (<$maint>) {
    my $line = $_;

    if ($line =~ m/^(\C):\s*(.*)/) {
	my $type = $1;
	my $value = $2;

	##Filename pattern matching
	if ($type eq "F" || $type eq "X") {
	    $value =~ s@\.@\\\.@g;       ##Convert . to \.
	    $value =~ s/\*/\.\*/g;       ##Convert * to .*
	    $value =~ s/\?/\./g;         ##Convert ? to .
	    ##if pattern is a directory and it lacks a trailing slash, add one
	    if ((-d $value)) {
		$value =~ s@([^/])$@$1/@;
	    }
	} elsif ($type eq "K") {
	    $keyword_hash{@typevalue} = $value;
	}
	push(@typevalue, "$type:$value");
    } elsif (!/^(\s)*$/) {
	$line =~ s/\n$//g;
	push(@typevalue, $line);
    }
}
close($maint);


#
# Read mail address map
#

my $mailmap;

read_mailmap();

sub read_mailmap {
    $mailmap = {
	names => {},
	addresses => {}
    };

    return if (!$email_use_mailmap || !(-f "${lk_path}.mailmap"));

    open(my $mailmap_file, '<', "${lk_path}.mailmap")
	or warn "$P: Can't open .mailmap: $!\n";

    while (<$mailmap_file>) {
	s/#.*$//; #strip comments
	s/^\s+|\s+$//g; #trim

	next if (/^\s*$/); #skip empty lines
	#entries have one of the following formats:
	# name1 <mail1>
	# <mail1> <mail2>
	# name1 <mail1> <mail2>
	# name1 <mail1> name2 <mail2>
	# (see man git-shortlog)

	if (/^([^<]+)<([^>]+)>$/) {
	    my $real_name = $1;
	    my $address = $2;

	    $real_name =~ s/\s+$//;
	    ($real_name, $address) = parse_email("$real_name <$address>");
	    $mailmap->{names}->{$address} = $real_name;

	} elsif (/^<([^>]+)>\s*<([^>]+)>$/) {
	    my $real_address = $1;
	    my $wrong_address = $2;

	    $mailmap->{addresses}->{$wrong_address} = $real_address;

	} elsif (/^(.+)<([^>]+)>\s*<([^>]+)>$/) {
	    my $real_name = $1;
	    my $real_address = $2;
	    my $wrong_address = $3;

	    $real_name =~ s/\s+$//;
	    ($real_name, $real_address) =
		parse_email("$real_name <$real_address>");
	    $mailmap->{names}->{$wrong_address} = $real_name;
	    $mailmap->{addresses}->{$wrong_address} = $real_address;

	} elsif (/^(.+)<([^>]+)>\s*(.+)\s*<([^>]+)>$/) {
	    my $real_name = $1;
	    my $real_address = $2;
	    my $wrong_name = $3;
	    my $wrong_address = $4;

	    $real_name =~ s/\s+$//;
	    ($real_name, $real_address) =
		parse_email("$real_name <$real_address>");

	    $wrong_name =~ s/\s+$//;
	    ($wrong_name, $wrong_address) =
		parse_email("$wrong_name <$wrong_address>");

	    my $wrong_email = format_email($wrong_name, $wrong_address, 1);
	    $mailmap->{names}->{$wrong_email} = $real_name;
	    $mailmap->{addresses}->{$wrong_email} = $real_address;
	}
    }
    close($mailmap_file);
}

## use the filenames on the command line or find the filenames in the patchfiles

my @files = ();
my @range = ();
my @keyword_tvi = ();
my @file_emails = ();

if (!@ARGV) {
    push(@ARGV, "&STDIN");
}

foreach my $file (@ARGV) {
    if ($file ne "&STDIN") {
	##if $file is a directory and it lacks a trailing slash, add one
	if ((-d $file)) {
	    $file =~ s@([^/])$@$1/@;
	} elsif (!(-f $file)) {
	    die "$P: file '${file}' not found\n";
	}
    }
    if ($from_filename) {
	push(@files, $file);
	if ($file ne "MAINTAINERS" && -f $file && ($keywords || $file_emails)) {
	    open(my $f, '<', $file)
		or die "$P: Can't open $file: $!\n";
	    my $text = do { local($/) ; <$f> };
	    close($f);
	    if ($keywords) {
		foreach my $line (keys %keyword_hash) {
		    if ($text =~ m/$keyword_hash{$line}/x) {
			push(@keyword_tvi, $line);
		    }
		}
	    }
	    if ($file_emails) {
		my @poss_addr = $text =~ m$[A-Za-zÀ-ÿ\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g;
		push(@file_emails, clean_file_emails(@poss_addr));
	    }
	}
    } else {
	my $file_cnt = @files;
	my $lastfile;

	open(my $patch, "< $file")
	    or die "$P: Can't open $file: $!\n";

	# We can check arbitrary information before the patch
	# like the commit message, mail headers, etc...
	# This allows us to match arbitrary keywords against any part
	# of a git format-patch generated file (subject tags, etc...)

	my $patch_prefix = "";			#Parsing the intro

	while (<$patch>) {
	    my $patch_line = $_;
	    if (m/^\+\+\+\s+(\S+)/ or m/^---\s+(\S+)/) {
		my $filename = $1;
		$filename =~ s@^[^/]*/@@;
		$filename =~ s@\n@@;
		$lastfile = $filename;
		push(@files, $filename);
		$patch_prefix = "^[+-].*";	#Now parsing the actual patch
	    } elsif (m/^\@\@ -(\d+),(\d+)/) {
		if ($email_git_blame) {
		    push(@range, "$lastfile:$1:$2");
		}
	    } elsif ($keywords) {
		foreach my $line (keys %keyword_hash) {
		    if ($patch_line =~ m/${patch_prefix}$keyword_hash{$line}/x) {
			push(@keyword_tvi, $line);
		    }
		}
	    }
	}
	close($patch);

	if ($file_cnt == @files) {
	    warn "$P: file '${file}' doesn't appear to be a patch.  "
		. "Add -f to options?\n";
	}
	@files = sort_and_uniq(@files);
    }
}

@file_emails = uniq(@file_emails);

my %email_hash_name;
my %email_hash_address;
my @email_to = ();
my %hash_list_to;
my @list_to = ();
my @scm = ();
my @web = ();
my @subsystem = ();
my @status = ();
my %deduplicate_name_hash = ();
my %deduplicate_address_hash = ();

my @maintainers = get_maintainers();

if (@maintainers) {
    @maintainers = merge_email(@maintainers);
    output(@maintainers);
}

if ($scm) {
    @scm = uniq(@scm);
    output(@scm);
}

if ($status) {
    @status = uniq(@status);
    output(@status);
}

if ($subsystem) {
    @subsystem = uniq(@subsystem);
    output(@subsystem);
}

if ($web) {
    @web = uniq(@web);
    output(@web);
}

exit($exit);

sub range_is_maintained {
    my ($start, $end) = @_;

    for (my $i = $start; $i < $end; $i++) {
	my $line = $typevalue[$i];
	if ($line =~ m/^(\C):\s*(.*)/) {
	    my $type = $1;
	    my $value = $2;
	    if ($type eq 'S') {
		if ($value =~ /(maintain|support)/i) {
		    return 1;
		}
	    }
	}
    }
    return 0;
}

sub range_has_maintainer {
    my ($start, $end) = @_;

    for (my $i = $start; $i < $end; $i++) {
	my $line = $typevalue[$i];
	if ($line =~ m/^(\C):\s*(.*)/) {
	    my $type = $1;
	    my $value = $2;
	    if ($type eq 'M') {
		return 1;
	    }
	}
    }
    return 0;
}

sub get_maintainers {
    %email_hash_name = ();
    %email_hash_address = ();
    %commit_author_hash = ();
    %commit_signer_hash = ();
    @email_to = ();
    %hash_list_to = ();
    @list_to = ();
    @scm = ();
    @web = ();
    @subsystem = ();
    @status = ();
    %deduplicate_name_hash = ();
    %deduplicate_address_hash = ();
    if ($email_git_all_signature_types) {
	$signature_pattern = "(.+?)[Bb][Yy]:";
    } else {
	$signature_pattern = "\(" . join("|", @signature_tags) . "\)";
    }

    # Find responsible parties

    my %exact_pattern_match_hash = ();

    foreach my $file (@files) {

	my %hash;
	my $tvi = find_first_section();
	while ($tvi < @typevalue) {
	    my $start = find_starting_index($tvi);
	    my $end = find_ending_index($tvi);
	    my $exclude = 0;
	    my $i;

	    #Do not match excluded file patterns

	    for ($i = $start; $i < $end; $i++) {
		my $line = $typevalue[$i];
		if ($line =~ m/^(\C):\s*(.*)/) {
		    my $type = $1;
		    my $value = $2;
		    if ($type eq 'X') {
			if (file_match_pattern($file, $value)) {
			    $exclude = 1;
			    last;
			}
		    }
		}
	    }

	    if (!$exclude) {
		for ($i = $start; $i < $end; $i++) {
		    my $line = $typevalue[$i];
		    if ($line =~ m/^(\C):\s*(.*)/) {
			my $type = $1;
			my $value = $2;
			if ($type eq 'F') {
			    if (file_match_pattern($file, $value)) {
				my $value_pd = ($value =~ tr@/@@);
				my $file_pd = ($file  =~ tr@/@@);
				$value_pd++ if (substr($value,-1,1) ne "/");
				$value_pd = -1 if ($value =~ /^\.\*/);
				if ($value_pd >= $file_pd &&
				    range_is_maintained($start, $end) &&
				    range_has_maintainer($start, $end)) {
				    $exact_pattern_match_hash{$file} = 1;
				}
				if ($pattern_depth == 0 ||
				    (($file_pd - $value_pd) < $pattern_depth)) {
				    $hash{$tvi} = $value_pd;
				}
			    }
			} elsif ($type eq 'N') {
			    if ($file =~ m/$value/x) {
				$hash{$tvi} = 0;
			    }
			}
		    }
		}
	    }
	    $tvi = $end + 1;
	}

	foreach my $line (sort {$hash{$b} <=> $hash{$a}} keys %hash) {
	    add_categories($line);
	    if ($sections) {
		my $i;
		my $start = find_starting_index($line);
		my $end = find_ending_index($line);
		for ($i = $start; $i < $end; $i++) {
		    my $line = $typevalue[$i];
		    if ($line =~ /^[FX]:/) {		##Restore file patterns
			$line =~ s/([^\\])\.([^\*])/$1\?$2/g;
			$line =~ s/([^\\])\.$/$1\?/g;	##Convert . back to ?
			$line =~ s/\\\./\./g;       	##Convert \. to .
			$line =~ s/\.\*/\*/g;       	##Convert .* to *
		    }
		    $line =~ s/^([A-Z]):/$1:\t/g;
		    print("$line\n");
		}
		print("\n");
	    }
	}
    }

    if ($keywords) {
	@keyword_tvi = sort_and_uniq(@keyword_tvi);
	foreach my $line (@keyword_tvi) {
	    add_categories($line);
	}
    }

    foreach my $email (@email_to, @list_to) {
	$email->[0] = deduplicate_email($email->[0]);
    }

    foreach my $file (@files) {
	if ($email &&
	    ($email_git || ($email_git_fallback &&
			    !$exact_pattern_match_hash{$file}))) {
	    vcs_file_signoffs($file);
	}
	if ($email && $email_git_blame) {
	    vcs_file_blame($file);
	}
    }

    if ($email) {
	foreach my $chief (@penguin_chief) {
	    if ($chief =~ m/^(.*):(.*)/) {
		my $email_address;

		$email_address = format_email($1, $2, $email_usename);
		if ($email_git_penguin_chiefs) {
		    push(@email_to, [$email_address, 'chief penguin']);
		} else {
		    @email_to = grep($_->[0] !~ /${email_address}/, @email_to);
		}
	    }
	}

	foreach my $email (@file_emails) {
	    my ($name, $address) = parse_email($email);

	    my $tmp_email = format_email($name, $address, $email_usename);
	    push_email_address($tmp_email, '');
	    add_role($tmp_email, 'in file');
	}
    }

    my @to = ();
    if ($email || $email_list) {
	if ($email) {
	    @to = (@to, @email_to);
	}
	if ($email_list) {
	    @to = (@to, @list_to);
	}
    }

    if ($interactive) {
	@to = interactive_get_maintainers(\@to);
    }

    return @to;
}

sub file_match_pattern {
    my ($file, $pattern) = @_;
    if (substr($pattern, -1) eq "/") {
	if ($file =~ m@^$pattern@) {
	    return 1;
	}
    } else {
	if ($file =~ m@^$pattern@) {
	    my $s1 = ($file =~ tr@/@@);
	    my $s2 = ($pattern =~ tr@/@@);
	    if ($s1 == $s2) {
		return 1;
	    }
	}
    }
    return 0;
}

sub usage {
    print <<EOT;
usage: $P [options] patchfile
       $P [options] -f file|directory
version: $V

MAINTAINER field selection options:
  --email => print email address(es) if any
    --git => include recent git \*-by: signers
    --git-all-signature-types => include signers regardless of signature type
        or use only ${signature_pattern} signers (default: $email_git_all_signature_types)
    --git-fallback => use git when no exact MAINTAINERS pattern (default: $email_git_fallback)
    --git-chief-penguins => include ${penguin_chiefs}
    --git-min-signatures => number of signatures required (default: $email_git_min_signatures)
    --git-max-maintainers => maximum maintainers to add (default: $email_git_max_maintainers)
    --git-min-percent => minimum percentage of commits required (default: $email_git_min_percent)
    --git-blame => use git blame to find modified commits for patch or file
    --git-since => git history to use (default: $email_git_since)
    --hg-since => hg history to use (default: $email_hg_since)
    --interactive => display a menu (mostly useful if used with the --git option)
    --m => include maintainer(s) if any
    --n => include name 'Full Name <addr\@domain.tld>'
    --l => include list(s) if any
    --s => include subscriber only list(s) if any
    --remove-duplicates => minimize duplicate email names/addresses
    --roles => show roles (status:subsystem, git-signer, list, etc...)
    --rolestats => show roles and statistics (commits/total_commits, %)
    --file-emails => add email addresses found in -f file (default: 0 (off))
  --scm => print SCM tree(s) if any
  --status => print status if any
  --subsystem => print subsystem name if any
  --web => print website(s) if any

Output type options:
  --separator [, ] => separator for multiple entries on 1 line
    using --separator also sets --nomultiline if --separator is not [, ]
  --multiline => print 1 entry per line

Other options:
  --pattern-depth => Number of pattern directory traversals (default: 0 (all))
  --keywords => scan patch for keywords (default: $keywords)
  --sections => print all of the subsystem sections with pattern matches
  --mailmap => use .mailmap file (default: $email_use_mailmap)
  --version => show version
  --help => show this help information

Default options:
  [--email --nogit --git-fallback --m --n --l --multiline -pattern-depth=0
   --remove-duplicates --rolestats]

Notes:
  Using "-f directory" may give unexpected results:
      Used with "--git", git signators for _all_ files in and below
          directory are examined as git recurses directories.
          Any specified X: (exclude) pattern matches are _not_ ignored.
      Used with "--nogit", directory is used as a pattern match,
          no individual file within the directory or subdirectory
          is matched.
      Used with "--git-blame", does not iterate all files in directory
  Using "--git-blame" is slow and may add old committers and authors
      that are no longer active maintainers to the output.
  Using "--roles" or "--rolestats" with git send-email --cc-cmd or any
      other automated tools that expect only ["name"] <email address>
      may not work because of additional output after <email address>.
  Using "--rolestats" and "--git-blame" shows the #/total=% commits,
      not the percentage of the entire file authored.  # of commits is
      not a good measure of amount of code authored.  1 major commit may
      contain a thousand lines, 5 trivial commits may modify a single line.
  If git is not installed, but mercurial (hg) is installed and an .hg
      repository exists, the following options apply to mercurial:
          --git,
          --git-min-signatures, --git-max-maintainers, --git-min-percent, and
          --git-blame
      Use --hg-since not --git-since to control date selection
  File ".get_maintainer.conf", if it exists in the linux kernel source root
      directory, can change whatever get_maintainer defaults are desired.
      Entries in this file can be any command line argument.
      This file is prepended to any additional command line arguments.
      Multiple lines and # comments are allowed.
EOT
}

sub top_of_kernel_tree {
    my ($lk_path) = @_;

    if ($lk_path ne "" && substr($lk_path,length($lk_path)-1,1) ne "/") {
	$lk_path .= "/";
    }
    if (   (-f "${lk_path}COPYING")
	&& (-f "${lk_path}CREDITS")
	&& (-f "${lk_path}Kbuild")
	&& (-f "${lk_path}MAINTAINERS")
	&& (-f "${lk_path}Makefile")
	&& (-f "${lk_path}README")
	&& (-d "${lk_path}Documentation")
	&& (-d "${lk_path}arch")
	&& (-d "${lk_path}include")
	&& (-d "${lk_path}drivers")
	&& (-d "${lk_path}fs")
	&& (-d "${lk_path}init")
	&& (-d "${lk_path}ipc")
	&& (-d "${lk_path}kernel")
	&& (-d "${lk_path}lib")
	&& (-d "${lk_path}scripts")) {
	return 1;
    }
    return 0;
}

sub parse_email {
    my ($formatted_email) = @_;

    my $name = "";
    my $address = "";

    if ($formatted_email =~ /^([^<]+)<(.+\@.*)>.*$/) {
	$name = $1;
	$address = $2;
    } elsif ($formatted_email =~ /^\s*<(.+\@\S*)>.*$/) {
	$address = $1;
    } elsif ($formatted_email =~ /^(.+\@\S*).*$/) {
	$address = $1;
    }

    $name =~ s/^\s+|\s+$//g;
    $name =~ s/^\"|\"$//g;
    $address =~ s/^\s+|\s+$//g;

    if ($name =~ /[^\w \-]/i) {  	 ##has "must quote" chars
	$name =~ s/(?<!\\)"/\\"/g;       ##escape quotes
	$name = "\"$name\"";
    }

    return ($name, $address);
}

sub format_email {
    my ($name, $address, $usename) = @_;

    my $formatted_email;

    $name =~ s/^\s+|\s+$//g;
    $name =~ s/^\"|\"$//g;
    $address =~ s/^\s+|\s+$//g;

    if ($name =~ /[^\w \-]/i) {          ##has "must quote" chars
	$name =~ s/(?<!\\)"/\\"/g;       ##escape quotes
	$name = "\"$name\"";
    }

    if ($usename) {
	if ("$name" eq "") {
	    $formatted_email = "$address";
	} else {
	    $formatted_email = "$name <$address>";
	}
    } else {
	$formatted_email = $address;
    }

    return $formatted_email;
}

sub find_first_section {
    my $index = 0;

    while ($index < @typevalue) {
	my $tv = $typevalue[$index];
	if (($tv =~ m/^(\C):\s*(.*)/)) {
	    last;
	}
	$index++;
    }

    return $index;
}

sub find_starting_index {
    my ($index) = @_;

    while ($index > 0) {
	my $tv = $typevalue[$index];
	if (!($tv =~ m/^(\C):\s*(.*)/)) {
	    last;
	}
	$index--;
    }

    return $index;
}

sub find_ending_index {
    my ($index) = @_;

    while ($index < @typevalue) {
	my $tv = $typevalue[$index];
	if (!($tv =~ m/^(\C):\s*(.*)/)) {
	    last;
	}
	$index++;
    }

    return $index;
}

sub get_maintainer_role {
    my ($index) = @_;

    my $i;
    my $start = find_starting_index($index);
    my $end = find_ending_index($index);

    my $role = "unknown";
    my $subsystem = $typevalue[$start];
    if (length($subsystem) > 20) {
	$subsystem = substr($subsystem, 0, 17);
	$subsystem =~ s/\s*$//;
	$subsystem = $subsystem . "...";
    }

    for ($i = $start + 1; $i < $end; $i++) {
	my $tv = $typevalue[$i];
	if ($tv =~ m/^(\C):\s*(.*)/) {
	    my $ptype = $1;
	    my $pvalue = $2;
	    if ($ptype eq "S") {
		$role = $pvalue;
	    }
	}
    }

    $role = lc($role);
    if      ($role eq "supported") {
	$role = "supporter";
    } elsif ($role eq "maintained") {
	$role = "maintainer";
    } elsif ($role eq "odd fixes") {
	$role = "odd fixer";
    } elsif ($role eq "orphan") {
	$role = "orphan minder";
    } elsif ($role eq "obsolete") {
	$role = "obsolete minder";
    } elsif ($role eq "buried alive in reporters") {
	$role = "chief penguin";
    }

    return $role . ":" . $subsystem;
}

sub get_list_role {
    my ($index) = @_;

    my $i;
    my $start = find_starting_index($index);
    my $end = find_ending_index($index);

    my $subsystem = $typevalue[$start];
    if (length($subsystem) > 20) {
	$subsystem = substr($subsystem, 0, 17);
	$subsystem =~ s/\s*$//;
	$subsystem = $subsystem . "...";
    }

    if ($subsystem eq "THE REST") {
	$subsystem = "";
    }

    return $subsystem;
}

sub add_categories {
    my ($index) = @_;

    my $i;