use strict;
my $P = $0;
-my $V = '0.22';
+my $V = '0.23';
use Getopt::Long qw(:config no_auto_abbrev);
my $email_maintainer = 1;
my $email_list = 1;
my $email_subscriber_list = 0;
-my $email_git = 1;
my $email_git_penguin_chiefs = 0;
+my $email_git = 1;
+my $email_git_blame = 0;
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_git_blame = 0;
+my $email_hg_since = "-365";
my $email_remove_duplicates = 1;
my $output_multiline = 1;
my $output_separator = ", ";
my $rfc822_lwsp = "(?:(?:\\r\\n)?[ \\t])";
my $rfc822_char = '[\\000-\\377]';
+# VCS command support: class-like functions and strings
+
+my %VCS_cmds;
+
+my %VCS_cmds_git = (
+ "execute_cmd" => \&git_execute_cmd,
+ "available" => '(which("git") ne "") && (-d ".git")',
+ "find_signers_cmd" => "git log --since=\$email_git_since -- \$file",
+ "find_commit_signers_cmd" => "git log -1 \$commit",
+ "blame_range_cmd" => "git blame -l -L \$diff_start,+\$diff_length \$file",
+ "blame_file_cmd" => "git blame -l \$file",
+ "commit_pattern" => "^commit [0-9a-f]{40,40}",
+ "blame_commit_pattern" => "^([0-9a-f]+) "
+);
+
+my %VCS_cmds_hg = (
+ "execute_cmd" => \&hg_execute_cmd,
+ "available" => '(which("hg") ne "") && (-d ".hg")',
+ "find_signers_cmd" =>
+ "hg log --date=\$email_hg_since" .
+ " --template='commit {node}\\n{desc}\\n' -- \$file",
+ "find_commit_signers_cmd" => "hg log --template='{desc}\\n' -r \$commit",
+ "blame_range_cmd" => "", # not supported
+ "blame_file_cmd" => "hg blame -c \$file",
+ "commit_pattern" => "^commit [0-9a-f]{40,40}",
+ "blame_commit_pattern" => "^([0-9a-f]+):"
+);
+
if (!GetOptions(
'email!' => \$email,
'git!' => \$email_git,
+ 'git-blame!' => \$email_git_blame,
'git-chief-penguins!' => \$email_git_penguin_chiefs,
'git-min-signatures=i' => \$email_git_min_signatures,
'git-max-maintainers=i' => \$email_git_max_maintainers,
'git-min-percent=i' => \$email_git_min_percent,
'git-since=s' => \$email_git_since,
- 'git-blame!' => \$email_git_blame,
+ 'hg-since=s' => \$email_hg_since,
'remove-duplicates!' => \$email_remove_duplicates,
'm!' => \$email_maintainer,
'n!' => \$email_usename,
next if ($line =~ m/^\s*$/);
my ($name, $address) = parse_email($line);
- $line = format_email($name, $address);
+ $line = format_email($name, $address, $email_usename);
next if ($line =~ m/^\s*$/);
push(@files, $file);
if (-f $file && $keywords) {
open(FILE, "<$file") or die "$P: Can't open ${file}\n";
- while (<FILE>) {
- my $patch_line = $_;
- foreach my $line (keys %keyword_hash) {
- if ($patch_line =~ m/^.*$keyword_hash{$line}/x) {
- push(@keyword_tvi, $line);
- }
+ my $text = do { local($/) ; <FILE> };
+ foreach my $line (keys %keyword_hash) {
+ if ($text =~ m/$keyword_hash{$line}/x) {
+ push(@keyword_tvi, $line);
}
}
close(FILE);
}
if ($email && $email_git) {
- recent_git_signoffs($file);
+ vcs_file_signoffs($file);
}
if ($email && $email_git_blame) {
- git_assign_blame($file);
+ vcs_file_blame($file);
}
}
if ($chief =~ m/^(.*):(.*)/) {
my $email_address;
- $email_address = format_email($1, $2);
+ $email_address = format_email($1, $2, $email_usename);
if ($email_git_penguin_chiefs) {
push(@email_to, [$email_address, 'chief penguin']);
} else {
--git-min-signatures => number of signatures required (default: 1)
--git-max-maintainers => maximum maintainers to add (default: 5)
--git-min-percent => minimum percentage of commits required (default: 5)
- --git-since => git history to use (default: 1-year-ago)
--git-blame => use git blame to find modified commits for patch or file
+ --git-since => git history to use (default: 1-year-ago)
+ --hg-since => hg history to use (default: -365)
--m => include maintainer(s) if any
--n => include name 'Full Name <addr\@domain.tld>'
--l => include list(s) if any
directory are examined as git recurses directories.
Any specified X: (exclude) pattern matches are _not_ ignored.
Used with "--nogit", directory is used as a pattern match,
- no individual file within the directory or subdirectory
- is matched.
+ no individual file within the directory or subdirectory
+ is matched.
Used with "--git-blame", does not iterate all files in directory
Using "--git-blame" is slow and may add old committers and authors
that are no longer active maintainers to the output.
not the percentage of the entire file authored. # of commits is
not a good measure of amount of code authored. 1 major commit may
contain a thousand lines, 5 trivial commits may modify a single line.
+ If git is not installed, but mercurial (hg) is installed and an .hg
+ repository exists, the following options apply to mercurial:
+ --git,
+ --git-min-signatures, --git-max-maintainers, --git-min-percent, and
+ --git-blame
+ Use --hg-since not --git-since to control date selection
EOT
}
}
sub format_email {
- my ($name, $address) = @_;
+ my ($name, $address, $usename) = @_;
my $formatted_email;
$name = "\"$name\"";
}
- if ($email_usename) {
+ if ($usename) {
if ("$name" eq "") {
$formatted_email = "$address";
} else {
- $formatted_email = "$name <${address}>";
+ $formatted_email = "$name <$address>";
}
} else {
$formatted_email = $address;
if ($tv =~ m/^(\C):\s*(.*)/) {
if ($1 eq "P") {
$name = $2;
- $pvalue = format_email($name, $address);
+ $pvalue = format_email($name, $address, $email_usename);
}
}
}
}
if (!$email_remove_duplicates) {
- push(@email_to, [format_email($name, $address), $role]);
+ push(@email_to, [format_email($name, $address, $email_usename), $role]);
} elsif (!email_inuse($name, $address)) {
- push(@email_to, [format_email($name, $address), $role]);
+ push(@email_to, [format_email($name, $address, $email_usename), $role]);
$email_hash_name{$name}++;
$email_hash_address{$address}++;
}
my ($line, $role) = @_;
my ($name, $address) = parse_email($line);
- my $email = format_email($name, $address);
+ my $email = format_email($name, $address, $email_usename);
foreach my $entry (@email_to) {
if ($email_remove_duplicates) {
}
sub mailmap {
- my @lines = @_;
+ my (@lines) = @_;
my %hash;
foreach my $line (@lines) {
$hash{$name} = $address;
} elsif ($address ne $hash{$name}) {
$address = $hash{$name};
- $line = format_email($name, $address);
+ $line = format_email($name, $address, $email_usename);
}
if (exists($mailmap{$name})) {
my $obj = $mailmap{$name};
foreach my $map_address (@$obj) {
if (($map_address eq $address) &&
($map_address ne $hash{$name})) {
- $line = format_email($name, $hash{$name});
+ $line = format_email($name, $hash{$name}, $email_usename);
}
}
}
return @lines;
}
-sub recent_git_signoffs {
- my ($file) = @_;
-
- my $sign_offs = "";
- my $cmd = "";
- my $output = "";
- my $count = 0;
+sub git_execute_cmd {
+ my ($cmd) = @_;
my @lines = ();
- my %hash;
- my $total_sign_offs;
- if (which("git") eq "") {
- warn("$P: git not found. Add --nogit to options?\n");
- return;
- }
- if (!(-d ".git")) {
- warn("$P: .git directory not found. Use a git repository for better results.\n");
- warn("$P: perhaps 'git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git'\n");
- return;
- }
+ my $output = `$cmd`;
+ $output =~ s/^\s*//gm;
+ @lines = split("\n", $output);
- $cmd = "git log --since=${email_git_since} -- ${file}";
+ return @lines;
+}
- $output = `${cmd}`;
- $output =~ s/^\s*//gm;
+sub hg_execute_cmd {
+ my ($cmd) = @_;
+ my @lines = ();
+ my $output = `$cmd`;
@lines = split("\n", $output);
+ return @lines;
+}
+
+sub vcs_find_signers {
+ my ($cmd) = @_;
+ my @lines = ();
+ my $commits;
+
+ @lines = &{$VCS_cmds{"execute_cmd"}}($cmd);
+
+ my $pattern = $VCS_cmds{"commit_pattern"};
+
+ $commits = grep(/$pattern/, @lines); # of commits
+
@lines = grep(/^[-_ a-z]+by:.*\@.*$/i, @lines);
if (!$email_git_penguin_chiefs) {
@lines = grep(!/${penguin_chiefs}/i, @lines);
# cut -f2- -d":"
s/.*:\s*(.+)\s*/$1/ for (@lines);
- $total_sign_offs = @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, $address);
- }
-
- if ($email_remove_duplicates) {
- @lines = mailmap(@lines);
+ $line = format_email($name, $address, 1);
}
- @lines = sort(@lines);
-
- # uniq -c
- $hash{$_}++ for @lines;
-
- # sort -rn
- foreach my $line (sort {$hash{$b} <=> $hash{$a}} keys %hash) {
- my $sign_offs = $hash{$line};
- my $role;
-
- $count++;
- last if ($sign_offs < $email_git_min_signatures ||
- $count > $email_git_max_maintainers ||
- $sign_offs * 100 / $total_sign_offs < $email_git_min_percent);
- push_email_address($line, '');
- $role = "git-signer";
- if ($output_rolestats) {
- my $percent = sprintf("%.0f", $sign_offs * 100 / $total_sign_offs);
- $role = "$role:$sign_offs/$total_sign_offs=$percent%";
- }
- add_role($line, $role);
- }
+ return ($commits, @lines);
}
-sub save_commits {
- my ($cmd, @commits) = @_;
- my $output;
+sub vcs_save_commits {
+ my ($cmd) = @_;
my @lines = ();
+ my @commits = ();
- $output = `${cmd}`;
+ @lines = &{$VCS_cmds{"execute_cmd"}}($cmd);
- @lines = split("\n", $output);
foreach my $line (@lines) {
- if ($line =~ m/^(\w+) /) {
- push (@commits, $1);
+ if ($line =~ m/$VCS_cmds{"blame_commit_pattern"}/) {
+ push(@commits, $1);
}
}
+
return @commits;
}
-sub git_assign_blame {
+sub vcs_blame {
my ($file) = @_;
-
- my @lines = ();
- my @commits = ();
my $cmd;
- my $output;
- my %hash;
- my $total_sign_offs;
- my $count;
+ my @commits = ();
+
+ return @commits if (!(-f $file));
+
+ if (@range && $VCS_cmds{"blame_range_cmd"} eq "") {
+ my @all_commits = ();
+
+ $cmd = $VCS_cmds{"blame_file_cmd"};
+ $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd
+ @all_commits = vcs_save_commits($cmd);
- if (@range) {
foreach my $file_range_diff (@range) {
next if (!($file_range_diff =~ m/(.+):(.+):(.+)/));
my $diff_file = $1;
my $diff_start = $2;
my $diff_length = $3;
- next if (!("$file" eq "$diff_file"));
- $cmd = "git blame -l -L $diff_start,+$diff_length $file";
- @commits = save_commits($cmd, @commits);
+ next if ("$file" ne "$diff_file");
+ for (my $i = $diff_start; $i < $diff_start + $diff_length; $i++) {
+ push(@commits, $all_commits[$i]);
+ }
}
- } else {
- if (-f $file) {
- $cmd = "git blame -l $file";
- @commits = save_commits($cmd, @commits);
+ } elsif (@range) {
+ foreach my $file_range_diff (@range) {
+ next if (!($file_range_diff =~ m/(.+):(.+):(.+)/));
+ my $diff_file = $1;
+ my $diff_start = $2;
+ my $diff_length = $3;
+ next if ("$file" ne "$diff_file");
+ $cmd = $VCS_cmds{"blame_range_cmd"};
+ $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd
+ push(@commits, vcs_save_commits($cmd));
}
+ } else {
+ $cmd = $VCS_cmds{"blame_file_cmd"};
+ $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd
+ @commits = vcs_save_commits($cmd);
}
- $total_sign_offs = 0;
- @commits = uniq(@commits);
- foreach my $commit (@commits) {
- $cmd = "git log -1 ${commit}";
+ return @commits;
+}
- $output = `${cmd}`;
- $output =~ s/^\s*//gm;
- @lines = split("\n", $output);
+my $printed_novcs = 0;
+sub vcs_exists {
+ %VCS_cmds = %VCS_cmds_git;
+ return 1 if eval $VCS_cmds{"available"};
+ %VCS_cmds = %VCS_cmds_hg;
+ return 1 if eval $VCS_cmds{"available"};
+ %VCS_cmds = ();
+ if (!$printed_novcs) {
+ warn("$P: No supported VCS found. Add --nogit to options?\n");
+ warn("Using a git repository produces better results.\n");
+ warn("Try Linus Torvalds' latest git repository using:\n");
+ warn("git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git\n");
+ $printed_novcs = 1;
+ }
+ return 0;
+}
- @lines = grep(/^[-_ a-z]+by:.*\@.*$/i, @lines);
- if (!$email_git_penguin_chiefs) {
- @lines = grep(!/${penguin_chiefs}/i, @lines);
- }
+sub vcs_assign {
+ my ($role, $divisor, @lines) = @_;
- # cut -f2- -d":"
- s/.*:\s*(.+)\s*/$1/ for (@lines);
+ my %hash;
+ my $count = 0;
- $total_sign_offs += @lines;
+ return if (@lines <= 0);
- if ($email_remove_duplicates) {
- @lines = mailmap(@lines);
- }
+ if ($divisor <= 0) {
+ warn("Bad divisor in " . (caller(0))[3] . ": $divisor\n");
+ $divisor = 1;
+ }
- $hash{$_}++ for @lines;
+ if ($email_remove_duplicates) {
+ @lines = mailmap(@lines);
}
- $count = 0;
+ @lines = sort(@lines);
+
+ # uniq -c
+ $hash{$_}++ for @lines;
+
+ # sort -rn
foreach my $line (sort {$hash{$b} <=> $hash{$a}} keys %hash) {
my $sign_offs = $hash{$line};
- my $role;
+ my $percent = $sign_offs * 100 / $divisor;
+ $percent = 100 if ($percent > 100);
$count++;
last if ($sign_offs < $email_git_min_signatures ||
$count > $email_git_max_maintainers ||
- $sign_offs * 100 / $total_sign_offs < $email_git_min_percent);
+ $percent < $email_git_min_percent);
push_email_address($line, '');
- if ($from_filename) {
- $role = "commits";
- } else {
- $role = "modified commits";
- }
if ($output_rolestats) {
- my $percent = sprintf("%.0f", $sign_offs * 100 / $total_sign_offs);
- $role = "$role:$sign_offs/$total_sign_offs=$percent%";
+ my $fmt_percent = sprintf("%.0f", $percent);
+ add_role($line, "$role:$sign_offs/$divisor=$fmt_percent%");
+ } else {
+ add_role($line, $role);
}
- add_role($line, $role);
+ }
+}
+
+sub vcs_file_signoffs {
+ my ($file) = @_;
+
+ my @signers = ();
+ my $commits;
+
+ return if (!vcs_exists());
+
+ my $cmd = $VCS_cmds{"find_signers_cmd"};
+ $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd
+
+ ($commits, @signers) = vcs_find_signers($cmd);
+ vcs_assign("commit_signer", $commits, @signers);
+}
+
+sub vcs_file_blame {
+ my ($file) = @_;
+
+ my @signers = ();
+ my @commits = ();
+ my $total_commits;
+
+ return if (!vcs_exists());
+
+ @commits = vcs_blame($file);
+ @commits = uniq(@commits);
+ $total_commits = @commits;
+
+ foreach my $commit (@commits) {
+ my $commit_count;
+ my @commit_signers = ();
+
+ my $cmd = $VCS_cmds{"find_commit_signers_cmd"};
+ $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd
+
+ ($commit_count, @commit_signers) = vcs_find_signers($cmd);
+ push(@signers, @commit_signers);
+ }
+
+ if ($from_filename) {
+ vcs_assign("commits", $total_commits, @signers);
+ } else {
+ vcs_assign("modified commits", $total_commits, @signers);
}
}
sub uniq {
- my @parms = @_;
+ my (@parms) = @_;
my %saw;
@parms = grep(!$saw{$_}++, @parms);
}
sub sort_and_uniq {
- my @parms = @_;
+ my (@parms) = @_;
my %saw;
@parms = sort @parms;
my ($address, $role) = @$_;
if (!$saw{$address}) {
if ($output_roles) {
- push @lines, "$address ($role)";
+ push(@lines, "$address ($role)");
} else {
- push @lines, $address;
+ push(@lines, $address);
}
$saw{$address} = 1;
}
}
sub output {
- my @parms = @_;
+ my (@parms) = @_;
if ($output_multiline) {
foreach my $line (@parms) {
if ($s =~ m/^(?:$rfc822re)?(?:,(?:$rfc822re)?)*$/so &&
$s =~ m/^$rfc822_char*$/) {
while ($s =~ m/(?:^|,$rfc822_lwsp*)($rfc822re)/gos) {
- push @r, $1;
+ push(@r, $1);
}
return wantarray ? (scalar(@r), @r) : 1;
}
- else {
- return wantarray ? () : 0;
- }
+ return wantarray ? () : 0;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff