[PATCH 0/5] scripts/get_maintainer.pl: Update to 0.25

[PATCH 0/5] scripts/get_maintainer.pl: Update to 0.25

[Joe Perches]

Some miscellaneous improvements to the script.  Please apply.

Command line option changes:
--git-fallback is added and becomes the default
--git is no longer a default
--git-blame --rolestats shows "authored lines"

The default option changes reduces the number of people cc'd on patches when
a maintainer exists for particular files, but not necessarily the files in
subdirectories of patterns like "F: net/" or "F: arch/arm/".

Joe Perches (5):
  scripts/get_maintainer.pl: Add --git-blame --rolestats "Authored lines" information
  scripts/get_maintainer.pl: Use correct indentation
  scripts/get_maintainer.pl: Don't search MAINTAINERS for keywords or emails
  scripts/get_maintainer.pl: Add default --git-fallback, remove default --git
  scripts/get_maintainer.pl: Use .get_maintainer.conf from . then $HOME then scripts

 scripts/get_maintainer.pl |  123 ++++++++++++++++++++++++++++++++++++---------
 1 files changed, 99 insertions(+), 24 deletions(-)

-- 
1.7.3.rc1

[PATCH 1/5] scripts/get_maintainer.pl: Add --git-blame --rolestats "Authored lines" information

[Joe Perches]

> > Something based on percentage of the driver written rather than log
> > entry counts might also be interesting.
> There is a --git-blame option, but it uses a count of file commits
> active in the file rather than % of lines authored.

When options --git-blame and --rolestats are specified, add
the maintainers with the qualifying --git-min-percent amount
of lines authored of the complete file.  Does not add more
authors than specified by --git-max-maintainers.

For anyone using hg, this option works but is _very_ slow.
It's orders of magnitude slower than git slow.

The get_maintainer.pl version was incremented to 0.25.

This can be used with or without --git.

For instance:

$ ./scripts/get_maintainer.pl --git-blame --nogit --rolestats -f lib/bitmap.c
Paul Jackson <pj@sgi.com> (authored lines:406/613=66%,commits:7/20=35%)
Akinobu Mita <mita@miraclelinux.com> (authored lines:87/613=14%,commits:3/20=15%)
Reinette Chatre <reinette.chatre@linux.intel.com> (authored lines:42/613=7%)
Andrew Morton <akpm@linux-foundation.org> (commits:16/20=80%)
Paul Mundt <lethal@linux-sh.org> (commits:3/20=15%)
Randy Dunlap <randy.dunlap@oracle.com> (commits:2/20=10%)

$ ./scripts/get_maintainer.pl --git-blame --git --rolestats -f lib/bitmap.c
Andrew Morton <akpm@linux-foundation.org> (commit_signer:4/5=80%,commits:16/20=80%)
Akinobu Mita <akinobu.mita@gmail.com> (commit_signer:2/5=40%,authored lines:87/613=14%,commits:3/20=15%)
Jack Steiner <steiner@sgi.com> (commit_signer:1/5=20%)
Ben Hutchings <ben@decadent.org.uk> (commit_signer:1/5=20%)
Lee Schermerhorn <lee.schermerhorn@hp.com> (commit_signer:1/5=20%)
Paul Jackson <pj@sgi.com> (authored lines:406/613=66%,commits:7/20=35%)
Reinette Chatre <reinette.chatre@linux.intel.com> (authored lines:42/613=7%)
Paul Mundt <lethal@linux-sh.org> (commits:3/20=15%)
Randy Dunlap <randy.dunlap@oracle.com> (commits:2/20=10%)
linux-kernel@vger.kernel.org (open list)

Signed-off-by: Joe Perches <joe@perches.com>
---
 scripts/get_maintainer.pl |   60 ++++++++++++++++++++++++++++++++++++++++++--
 1 files changed, 57 insertions(+), 3 deletions(-)

diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index b228198..a91ae63 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -13,7 +13,7 @@
 use strict;
 
 my $P = $0;
-my $V = '0.24';
+my $V = '0.25';
 
 use Getopt::Long qw(:config no_auto_abbrev);
 
@@ -88,6 +88,7 @@ my %VCS_cmds_git = (
     "available" => '(which("git") ne "") && (-d ".git")',
     "find_signers_cmd" => "git log --no-color --since=\$email_git_since -- \$file",
     "find_commit_signers_cmd" => "git log --no-color -1 \$commit",
+    "find_commit_author_cmd" => "git log -1 --format=\"%an <%ae>\" \$commit",
     "blame_range_cmd" => "git blame -l -L \$diff_start,+\$diff_length \$file",
     "blame_file_cmd" => "git blame -l \$file",
     "commit_pattern" => "^commit [0-9a-f]{40,40}",
@@ -101,6 +102,7 @@ my %VCS_cmds_hg = (
 	"hg log --date=\$email_hg_since" .
 		" --template='commit {node}\\n{desc}\\n' -- \$file",
     "find_commit_signers_cmd" => "hg log --template='{desc}\\n' -r \$commit",
+    "find_commit_author_cmd" => "hg log -l 1 --template='{author}\\n' -r \$commit",
     "blame_range_cmd" => "",		# not supported
     "blame_file_cmd" => "hg blame -c \$file",
     "commit_pattern" => "^commit [0-9a-f]{40,40}",
@@ -1014,6 +1016,9 @@ sub vcs_find_signers {
     if (!$email_git_penguin_chiefs) {
 	@lines = grep(!/${penguin_chiefs}/i, @lines);
     }
+
+    return (0, @lines) if !@lines;
+
     # cut -f2- -d":"
     s/.*:\s*(.+)\s*/$1/ for (@lines);
 
@@ -1027,6 +1032,28 @@ sub vcs_find_signers {
     return ($commits, @lines);
 }
 
+sub vcs_find_author {
+    my ($cmd) = @_;
+    my @lines = ();
+
+    @lines = &{$VCS_cmds{"execute_cmd"}}($cmd);
+
+    if (!$email_git_penguin_chiefs) {
+	@lines = grep(!/${penguin_chiefs}/i, @lines);
+    }
+
+    return @lines if !@lines;
+
+## Reformat email addresses (with names) to avoid badly written signatures
+
+    foreach my $line (@lines) {
+	my ($name, $address) = parse_email($line);
+	$line = format_email($name, $address, 1);
+    }
+
+    return @lines;
+}
+
 sub vcs_save_commits {
     my ($cmd) = @_;
     my @lines = ();
@@ -1084,6 +1111,10 @@ sub vcs_blame {
 	@commits = vcs_save_commits($cmd);
     }
 
+    foreach my $commit (@commits) {
+	$commit =~ s/^\^//g;
+    }
+
     return @commits;
 }
 
@@ -1121,6 +1152,8 @@ sub vcs_assign {
 	@lines = mailmap(@lines);
     }
 
+    return if (@lines <= 0);
+
     @lines = sort(@lines);
 
     # uniq -c
@@ -1165,14 +1198,17 @@ sub vcs_file_blame {
     my ($file) = @_;
 
     my @signers = ();
+    my @all_commits = ();
     my @commits = ();
     my $total_commits;
+    my $total_lines;
 
     return if (!vcs_exists());
 
-    @commits = vcs_blame($file);
-    @commits = uniq(@commits);
+    @all_commits = vcs_blame($file);
+    @commits = uniq(@all_commits);
     $total_commits = @commits;
+    $total_lines = @all_commits;
 
     foreach my $commit (@commits) {
 	my $commit_count;
@@ -1182,10 +1218,28 @@ sub vcs_file_blame {
 	$cmd =~ s/(\$\w+)/$1/eeg;	#interpolate $cmd
 
 	($commit_count, @commit_signers) = vcs_find_signers($cmd);
+
 	push(@signers, @commit_signers);
     }
 
     if ($from_filename) {
+	if ($output_rolestats) {
+	    my @blame_signers;
+	    foreach my $commit (@commits) {
+		my $i;
+		my $cmd = $VCS_cmds{"find_commit_author_cmd"};
+		$cmd =~ s/(\$\w+)/$1/eeg;	#interpolate $cmd
+		my @author = vcs_find_author($cmd);
+		next if !@author;
+		my $count = grep(/$commit/, @all_commits);
+		for ($i = 0; $i < $count ; $i++) {
+		    push(@blame_signers, $author[0]);
+		}
+	    }
+	    if (@blame_signers) {
+		vcs_assign("authored lines", $total_lines, @blame_signers);
+	    }
+	}
 	vcs_assign("commits", $total_commits, @signers);
     } else {
 	vcs_assign("modified commits", $total_commits, @signers);
-- 
1.7.3.rc1

[PATCH 2/5] scripts/get_maintainer.pl: Use correct indentation

[Joe Perches]

Fixed an overly indented block.

Signed-off-by: Joe Perches <joe@perches.com>
---
 scripts/get_maintainer.pl |   30 +++++++++++++++---------------
 1 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index a91ae63..65c6acf 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -420,23 +420,23 @@ foreach my $file (@files) {
 
     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");
+	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 *
 		}
-		print("\n");
+		$line =~ s/^([A-Z]):/$1:\t/g;
+		print("$line\n");
 	    }
+	    print("\n");
+	}
     }
 
     if ($email && $email_git) {
-- 
1.7.3.rc1

[PATCH 3/5] scripts/get_maintainer.pl: Don't search MAINTAINERS for keywords or emails

[Joe Perches]

Keyword matching uses K: patterns from MAINTAINERS, so if
looking for the MAINTAINERS maintainer, don't search MAINTAINERS
for pattern matches.  MAINTAINERS also has rather a lot of email
addresses and is easily searched using grep "^M:", so skip it.

Signed-off-by: Joe Perches <joe@perches.com>
---
 scripts/get_maintainer.pl |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 65c6acf..36e889f 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -304,7 +304,7 @@ foreach my $file (@ARGV) {
     }
     if ($from_filename) {
 	push(@files, $file);
-	if (-f $file && ($keywords || $file_emails)) {
+	if ($file ne "MAINTAINERS" && -f $file && $file_emails) {
 	    open(my $f, '<', $file)
 		or die "$P: Can't open $file: $!\n";
 	    my $text = do { local($/) ; <$f> };
-- 
1.7.3.rc1

[PATCH 4/5] scripts/get_maintainer.pl: Add default --git-fallback, remove default --git

[Joe Perches]

Adding commit signers when there is a listed MAINTAINER for a file
can make the output list longer than necessary.

Change the --git default from on to off.

Add a new --git-fallback option (default on) used to add commit signers
only when there is no MAINTAINER for a file.

git history is used when --git-fallback is enabled and the pattern
directory depth is not the same as the file directory depth.

For instance:

X86 ARCHITECTURE (32-BIT AND 64-BIT)
M:	Thomas Gleixner <tglx@linutronix.de>
M:	Ingo Molnar <mingo@redhat.com>
M:	"H. Peter Anvin" <hpa@zytor.com>
M:	x86@kernel.org
T:	git git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
S:	Maintained
F:	Documentation/x86/
F:	arch/x86/

If using "./scripts/get_maintainer -f arch/x86/lib/atomic64_32.c", the pattern
for "arch/x86/" does not match the directory depth of "arch/x86/lib"
so the MAINTAINERS entries and git history is used to produce:

$ ./scripts/get_maintainer.pl -f --rolestats arch/x86/lib/atomic64_32.c
Thomas Gleixner <tglx@linutronix.de> (maintainer:X86 ARCHITECTURE...)
Ingo Molnar <mingo@redhat.com> (maintainer:X86 ARCHITECTURE...)
"H. Peter Anvin" <hpa@zytor.com> (maintainer:X86 ARCHITECTURE...,commit_signer:1/1=100%)
x86@kernel.org (maintainer:X86 ARCHITECTURE...)
Luca Barbieri <luca@luca-barbieri.com> (commit_signer:1/1=100%)
linux-kernel@vger.kernel.org (open list)

Luca Barbieri is added because he signed the only commit to
arch/x86/lib/atomic64_32.c during the last year and he meets the
other default qualifications.
	--git-min-percent (default:10)
	--git-min-signatures (default:1)

If current users of ./scripts/get_maintainers.pl have scripts
that use --nogit that expect git history to be excluded, those
scripts should be updated to include --nogit-fallback or a
.get_maintainer.conf file should be created with --nogit-fallback.

Signed-off-by: Joe Perches <joe@perches.com>
---
 scripts/get_maintainer.pl |   11 +++++++++--
 1 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 36e889f..ac20d58 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -24,9 +24,10 @@ my $email_maintainer = 1;
 my $email_list = 1;
 my $email_subscriber_list = 0;
 my $email_git_penguin_chiefs = 0;
-my $email_git = 1;
+my $email_git = 0;
 my $email_git_all_signature_types = 0;
 my $email_git_blame = 0;
+my $email_git_fallback = 1;
 my $email_git_min_signatures = 1;
 my $email_git_max_maintainers = 5;
 my $email_git_min_percent = 5;
@@ -138,6 +139,7 @@ if (!GetOptions(
 		'git!' => \$email_git,
 		'git-all-signature-types!' => \$email_git_all_signature_types,
 		'git-blame!' => \$email_git_blame,
+		'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,
@@ -371,6 +373,7 @@ my @status = ();
 foreach my $file (@files) {
 
     my %hash;
+    my $exact_pattern_match = 0;
     my $tvi = find_first_section();
     while ($tvi < @typevalue) {
 	my $start = find_starting_index($tvi);
@@ -405,6 +408,8 @@ foreach my $file (@files) {
 			    my $value_pd = ($value =~ tr@/@@);
 			    my $file_pd = ($file  =~ tr@/@@);
 			    $value_pd++ if (substr($value,-1,1) ne "/");
+			    $value_pd = -1 if ($value =~ /^\.\*/);
+			    $exact_pattern_match = 1 if ($value_pd >= $file_pd);
 			    if ($pattern_depth == 0 ||
 				(($file_pd - $value_pd) < $pattern_depth)) {
 				$hash{$tvi} = $value_pd;
@@ -439,7 +444,8 @@ foreach my $file (@files) {
 	}
     }
 
-    if ($email && $email_git) {
+    if ($email &&
+	($email_git || ($email_git_fallback && !$exact_pattern_match))) {
 	vcs_file_signoffs($file);
     }
 
@@ -540,6 +546,7 @@ MAINTAINER field selection options:
     --git => include recent git \*-by: signers
     --git-all-signature-types => include signers regardless of signature type
         or use only ${signaturePattern} 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)
-- 
1.7.3.rc1

[PATCH 5/5] scripts/get_maintainer.pl: Use .get_maintainer.conf from . then $HOME then scripts

[Joe Perches]

On Mon, 2010-09-13 at 00:01 -0400, Valdis.Kletnieks@vt.edu wrote:
> Any chance of getting that to be ~/.get_maintainer.conf rather than
> ./.get_maintainer.conf? I've just gotten bit like the 3rd or 4th time by
> "oh but you didn't create that file in *this* tree"
> (I usually have a linus git tree, a linux-next tree, and 3-4 -mm trees)

Sure.

Add a search path for the .conf file.

3 paths are added:

.             customized per-tree configurations
$HOME         user global configuration when per-tree configs don't exist
./scripts     lk defaults to override script

Signed-off-by: Joe Perches <joe@perches.com>
---
 scripts/get_maintainer.pl |   20 +++++++++++++++++---
 1 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index ac20d58..b7f93db 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -110,10 +110,12 @@ my %VCS_cmds_hg = (
     "blame_commit_pattern" => "^([0-9a-f]+):"
 );
 
-if (-f "${lk_path}.get_maintainer.conf") {
+my $conf = which_conf(".get_maintainer.conf");
+if (-f $conf) {
     my @conf_args;
-    open(my $conffile, '<', "${lk_path}.get_maintainer.conf")
-	or warn "$P: Can't open .get_maintainer.conf: $!\n";
+    open(my $conffile, '<', "$conf")
+	or warn "$P: Can't find a readable .get_maintainer.conf file $!\n";
+
     while (<$conffile>) {
 	my $line = $_;
 
@@ -961,6 +963,18 @@ sub which {
     return "";
 }
 
+sub which_conf {
+    my ($conf) = @_;
+
+    foreach my $path (split(/:/, ".:$ENV{HOME}:.scripts")) {
+	if (-e "$path/$conf") {
+	    return "$path/$conf";
+	}
+    }
+
+    return "";
+}
+
 sub mailmap {
     my (@lines) = @_;
     my %hash;
-- 
1.7.3.rc1

[PATCH V2 3/5] scripts/get_maintainer.pl: Don't search MAINTAINERS for keywords or emails

[Joe Perches]

Keyword matching uses K: patterns from MAINTAINERS, so if
looking for the MAINTAINERS maintainer, don't search MAINTAINERS
for pattern matches.  MAINTAINERS also has rather a lot of email
addresses and is easily searched using grep "^M:", so skip it.

Signed-off-by: Joe Perches <joe@perches.com>
---
 scripts/get_maintainer.pl |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 65c6acf..36e889f 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -304,7 +304,7 @@ foreach my $file (@ARGV) {
     }
     if ($from_filename) {
 	push(@files, $file);
-	if (-f $file && ($keywords || $file_emails)) {
+	if ($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> };