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

From: Joe Perches
Date: Fri Sep 10 2010 - 20:22:26 EST


> > 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@xxxxxxx> (authored lines:406/613=66%,commits:7/20=35%)
Akinobu Mita <mita@xxxxxxxxxxxxxxxx> (authored lines:87/613=14%,commits:3/20=15%)
Reinette Chatre <reinette.chatre@xxxxxxxxxxxxxxx> (authored lines:42/613=7%)
Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> (commits:16/20=80%)
Paul Mundt <lethal@xxxxxxxxxxxx> (commits:3/20=15%)
Randy Dunlap <randy.dunlap@xxxxxxxxxx> (commits:2/20=10%)

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

Signed-off-by: Joe Perches <joe@xxxxxxxxxxx>
---
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);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/