util/scripts: Update get_maintainer.pl to latest from linux kernel

This is version 03aed21 from linux/scripts, updated on Dec 12, 2016.

The version needs to be updated because Perl version 5.20 deprecated the
/C regex expression.  Perl version 5.24 removed it completely, so the
old version fails to run on the coreboot builders.

Change-Id: Ib97997237ca64c65d7f91d568ae4bec000804331
Signed-off-by: Martin Roth <martinroth@google.com>
Reviewed-on: https://review.coreboot.org/18571
Tested-by: build bot (Jenkins)
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Paul Menzel <paulepanter@users.sourceforge.net>
Reviewed-by: Patrick Georgi <pgeorgi@google.com>

util/scripts/get_maintainer.pl

@@ -16,7 +16,9 @@ my $P = $0;
 my $V = '0.26';
 
 use Getopt::Long qw(:config no_auto_abbrev);
+use Cwd;
 
+my $cur_path = fastgetcwd() . '/';
 my $lk_path = "./";
 my $email = 1;
 my $email_usename = 1;
@@ -42,10 +44,12 @@ my $output_multiline = 1;
 my $output_separator = ", ";
 my $output_roles = 0;
 my $output_rolestats = 1;
+my $output_section_maxlen = 50;
 my $scm = 0;
 my $web = 0;
 my $subsystem = 0;
 my $status = 0;
+my $letters = "";
 my $keywords = 1;
 my $sections = 0;
 my $file_emails = 0;
@@ -130,6 +134,7 @@ my %VCS_cmds_git = (
     "author_pattern" => "^GitAuthor: (.*)",
     "subject_pattern" => "^GitSubject: (.*)",
     "stat_pattern" => "^(\\d+)\\t(\\d+)\\t\$file\$",
+    "file_exists_cmd" => "git ls-files \$file",
 );
 
 my %VCS_cmds_hg = (
@@ -158,6 +163,7 @@ my %VCS_cmds_hg = (
     "author_pattern" => "^HgAuthor: (.*)",
     "subject_pattern" => "^HgSubject: (.*)",
     "stat_pattern" => "^(\\d+)\t(\\d+)\t\$file\$",
+    "file_exists_cmd" => "hg files \$file",
 );
 
 my $conf = which_conf(".get_maintainer.conf");
@@ -186,6 +192,27 @@ if (-f $conf) {
     unshift(@ARGV, @conf_args) if @conf_args;
 }
 
+my @ignore_emails = ();
+my $ignore_file = which_conf(".get_maintainer.ignore");
+if (-f $ignore_file) {
+    open(my $ignore, '<', "$ignore_file")
+	or warn "$P: Can't find a readable .get_maintainer.ignore file $!\n";
+    while (<$ignore>) {
+	my $line = $_;
+
+	$line =~ s/\s*\n?$//;
+	$line =~ s/^\s*//;
+	$line =~ s/\s+$//;
+	$line =~ s/#.*$//;
+
+	next if ($line =~ m/^\s*$/);
+	if (rfc822_valid($line)) {
+	    push(@ignore_emails, $line);
+	}
+    }
+    close($ignore);
+}
+
 if (!GetOptions(
 		'email!' => \$email,
 		'git!' => \$email_git,
@@ -215,6 +242,7 @@ if (!GetOptions(
 		'status!' => \$status,
 		'scm!' => \$scm,
 		'web!' => \$web,
+		'letters=s' => \$letters,
 		'pattern-depth=i' => \$pattern_depth,
 		'k|keywords!' => \$keywords,
 		'sections!' => \$sections,
@@ -245,7 +273,8 @@ $output_multiline = 0 if ($output_separator ne ", ");
 $output_rolestats = 1 if ($interactive);
 $output_roles = 1 if ($output_rolestats);
 
-if ($sections) {
+if ($sections || $letters ne "") {
+    $sections = 1;
     $email = 0;
     $email_list = 0;
     $scm = 0;
@@ -270,7 +299,7 @@ if ($email &&
 
 if (!top_of_kernel_tree($lk_path)) {
     die "$P: The current directory does not appear to be "
-	. "a coreboot source tree.\n";
+	. "a linux kernel source tree.\n";
 }
 
 ## Read MAINTAINERS for type/value pairs
@@ -283,7 +312,7 @@ open (my $maint, '<', "${lk_path}MAINTAINERS")
 while (<$maint>) {
     my $line = $_;
 
-    if ($line =~ m/^(\C):\s*(.*)/) {
+    if ($line =~ m/^([A-Z]):\s*(.*)/) {
 	my $type = $1;
 	my $value = $2;
 
@@ -406,7 +435,9 @@ foreach my $file (@ARGV) {
 	    die "$P: file '${file}' not found\n";
 	}
     }
-    if ($from_filename) {
+    if ($from_filename || ($file ne "&STDIN" && vcs_file_exists($file))) {
+	$file =~ s/^\Q${cur_path}\E//;	#strip any absolute path
+	$file =~ s/^\Q${lk_path}\E//;	#or the path to the lk tree
 	push(@files, $file);
 	if ($file ne "MAINTAINERS" && -f $file && ($keywords || $file_emails)) {
 	    open(my $f, '<', $file)
@@ -513,12 +544,22 @@ if ($web) {
 
 exit($exit);
 
+sub ignore_email_address {
+    my ($address) = @_;
+
+    foreach my $ignore (@ignore_emails) {
+	return 1 if ($ignore eq $address);
+    }
+
+    return 0;
+}
+
 sub range_is_maintained {
     my ($start, $end) = @_;
 
     for (my $i = $start; $i < $end; $i++) {
 	my $line = $typevalue[$i];
-	if ($line =~ m/^(\C):\s*(.*)/) {
+	if ($line =~ m/^([A-Z]):\s*(.*)/) {
 	    my $type = $1;
 	    my $value = $2;
 	    if ($type eq 'S') {
@@ -536,7 +577,7 @@ sub range_has_maintainer {
 
     for (my $i = $start; $i < $end; $i++) {
 	my $line = $typevalue[$i];
-	if ($line =~ m/^(\C):\s*(.*)/) {
+	if ($line =~ m/^([A-Z]):\s*(.*)/) {
 	    my $type = $1;
 	    my $value = $2;
 	    if ($type eq 'M') {
@@ -585,7 +626,7 @@ sub get_maintainers {
 
 	    for ($i = $start; $i < $end; $i++) {
 		my $line = $typevalue[$i];
-		if ($line =~ m/^(\C):\s*(.*)/) {
+		if ($line =~ m/^([A-Z]):\s*(.*)/) {
 		    my $type = $1;
 		    my $value = $2;
 		    if ($type eq 'X') {
@@ -600,7 +641,7 @@ sub get_maintainers {
 	    if (!$exclude) {
 		for ($i = $start; $i < $end; $i++) {
 		    my $line = $typevalue[$i];
-		    if ($line =~ m/^(\C):\s*(.*)/) {
+		    if ($line =~ m/^([A-Z]):\s*(.*)/) {
 			my $type = $1;
 			my $value = $2;
 			if ($type eq 'F') {
@@ -644,9 +685,11 @@ sub get_maintainers {
 			$line =~ s/\\\./\./g;       	##Convert \. to .
 			$line =~ s/\.\*/\*/g;       	##Convert .* to *
 		    }
-		    $line =~ s/^([A-Z]):/$1:\t/g;
+		    my $count = $line =~ s/^([A-Z]):/$1:\t/g;
+		    if ($letters eq "" || (!$count || $letters =~ /$1/i)) {
 			print("$line\n");
 		    }
+		}
 		print("\n");
 	    }
 	}
@@ -749,6 +792,7 @@ MAINTAINER field selection options:
     --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-blame-signatures => when used with --git-blame, also include all commit signers
     --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)
@@ -775,12 +819,13 @@ 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
+  --letters => print all matching 'letter' types from all matching sections
   --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
+  [--email --nogit --git-fallback --m --r --n --l --multiline --pattern-depth=0
    --remove-duplicates --rolestats]
 
 Notes:
@@ -812,6 +857,9 @@ Notes:
       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.
+  Most options have both positive and negative forms.
+      The negative forms for --<foo> are --no<foo> and --no-<foo>.
+
 EOT
 }
 
@@ -821,11 +869,22 @@ sub top_of_kernel_tree {
     if ($lk_path ne "" && substr($lk_path,length($lk_path)-1,1) ne "/") {
 	$lk_path .= "/";
     }
-    if (   (-f "${lk_path}MAINTAINERS")
+    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}src")
+	&& (-d "${lk_path}arch")
-	&& (-d "${lk_path}util")) {
+	&& (-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;
@@ -890,7 +949,7 @@ sub find_first_section {
 
     while ($index < @typevalue) {
 	my $tv = $typevalue[$index];
-	if (($tv =~ m/^(\C):\s*(.*)/)) {
+	if (($tv =~ m/^([A-Z]):\s*(.*)/)) {
 	    last;
 	}
 	$index++;
@@ -904,7 +963,7 @@ sub find_starting_index {
 
     while ($index > 0) {
 	my $tv = $typevalue[$index];
-	if (!($tv =~ m/^(\C):\s*(.*)/)) {
+	if (!($tv =~ m/^([A-Z]):\s*(.*)/)) {
 	    last;
 	}
 	$index--;
@@ -918,7 +977,7 @@ sub find_ending_index {
 
     while ($index < @typevalue) {
 	my $tv = $typevalue[$index];
-	if (!($tv =~ m/^(\C):\s*(.*)/)) {
+	if (!($tv =~ m/^([A-Z]):\s*(.*)/)) {
 	    last;
 	}
 	$index++;
@@ -927,6 +986,20 @@ sub find_ending_index {
     return $index;
 }
 
+sub get_subsystem_name {
+    my ($index) = @_;
+
+    my $start = find_starting_index($index);
+
+    my $subsystem = $typevalue[$start];
+    if ($output_section_maxlen && length($subsystem) > $output_section_maxlen) {
+	$subsystem = substr($subsystem, 0, $output_section_maxlen - 3);
+	$subsystem =~ s/\s*$//;
+	$subsystem = $subsystem . "...";
+    }
+    return $subsystem;
+}
+
 sub get_maintainer_role {
     my ($index) = @_;
 
@@ -935,16 +1008,11 @@ sub get_maintainer_role {
     my $end = find_ending_index($index);
 
     my $role = "unknown";
-    my $subsystem = $typevalue[$start];
+    my $subsystem = get_subsystem_name($index);
-    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 ($tv =~ m/^(\C):\s*(.*)/) {
+	if ($tv =~ m/^([A-Z]):\s*(.*)/) {
 	    my $ptype = $1;
 	    my $pvalue = $2;
 	    if ($ptype eq "S") {
@@ -974,16 +1042,7 @@ sub get_maintainer_role {
 sub get_list_role {
     my ($index) = @_;
 
-    my $i;
+    my $subsystem = get_subsystem_name($index);
-    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 = "";
@@ -1003,7 +1062,7 @@ sub add_categories {
 
     for ($i = $start + 1; $i < $end; $i++) {
 	my $tv = $typevalue[$i];
-	if ($tv =~ m/^(\C):\s*(.*)/) {
+	if ($tv =~ m/^([A-Z]):\s*(.*)/) {
 	    my $ptype = $1;
 	    my $pvalue = $2;
 	    if ($ptype eq "L") {
@@ -1045,7 +1104,7 @@ sub add_categories {
 		if ($name eq "") {
 		    if ($i > 0) {
 			my $tv = $typevalue[$i - 1];
-			if ($tv =~ m/^(\C):\s*(.*)/) {
+			if ($tv =~ m/^([A-Z]):\s*(.*)/) {
 			    if ($1 eq "P") {
 				$name = $2;
 				$pvalue = format_email($name, $address, $email_usename);
@@ -1062,7 +1121,7 @@ sub add_categories {
 		if ($name eq "") {
 		    if ($i > 0) {
 			my $tv = $typevalue[$i - 1];
-			if ($tv =~ m/^(\C):\s*(.*)/) {
+			if ($tv =~ m/^([A-Z]):\s*(.*)/) {
 			    if ($1 eq "P") {
 				$name = $2;
 				$pvalue = format_email($name, $address, $email_usename);
@@ -1071,7 +1130,8 @@ sub add_categories {
 		    }
 		}
 		if ($email_reviewer) {
-		    push_email_addresses($pvalue, 'reviewer');
+		    my $subsystem = get_subsystem_name($i);
+		    push_email_addresses($pvalue, "reviewer:$subsystem");
 		}
 	    } elsif ($ptype eq "T") {
 		push(@scm, $pvalue);
@@ -1857,6 +1917,7 @@ sub vcs_assign {
 	my $percent = $sign_offs * 100 / $divisor;
 
 	$percent = 100 if ($percent > 100);
+	next if (ignore_email_address($line));
 	$count++;
 	last if ($sign_offs < $email_git_min_signatures ||
 		 $count > $email_git_max_maintainers ||
@@ -2071,6 +2132,24 @@ sub vcs_file_blame {
     }
 }
 
+sub vcs_file_exists {
+    my ($file) = @_;
+
+    my $exists;
+
+    my $vcs_used = vcs_exists();
+    return 0 if (!$vcs_used);
+
+    my $cmd = $VCS_cmds{"file_exists_cmd"};
+    $cmd =~ s/(\$\w+)/$1/eeg;		# interpolate $cmd
+    $cmd .= " 2>&1";
+    $exists = &{$VCS_cmds{"execute_cmd"}}($cmd);
+
+    return 0 if ($? != 0);
+
+    return $exists;
+}
+
 sub uniq {
     my (@parms) = @_;