diff options
Diffstat (limited to 'scripts')
| -rwxr-xr-x | scripts/get_maintainer.pl | 499 |
1 files changed, 371 insertions, 128 deletions
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 81a67a4..445e884 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -13,7 +13,7 @@ use strict; my $P = $0; -my $V = '0.21'; +my $V = '0.23'; use Getopt::Long qw(:config no_auto_abbrev); @@ -23,16 +23,19 @@ my $email_usename = 1; 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 $output_roles = 0; +my $output_rolestats = 0; my $scm = 0; my $web = 0; my $subsystem = 0; @@ -64,21 +67,52 @@ my $penguin_chiefs = "\(" . join("|",@penguin_chief_names) . "\)"; my $rfc822_lwsp = "(?:(?:\\r\\n)?[ \\t])"; my $rfc822_char = '[\\000-\\377]'; +# VCS command support: class-like functions and strings + +my %VCS_cmds; + +my %VCS_cmds_git = ( + "execute_cmd" => \&git_execute_cmd, + "available" => '(which("git") ne "") && (-d ".git")', + "find_signers_cmd" => "git log --since=\$email_git_since -- \$file", + "find_commit_signers_cmd" => "git log -1 \$commit", + "blame_range_cmd" => "git blame -l -L \$diff_start,+\$diff_length \$file", + "blame_file_cmd" => "git blame -l \$file", + "commit_pattern" => "^commit [0-9a-f]{40,40}", + "blame_commit_pattern" => "^([0-9a-f]+) " +); + +my %VCS_cmds_hg = ( + "execute_cmd" => \&hg_execute_cmd, + "available" => '(which("hg") ne "") && (-d ".hg")', + "find_signers_cmd" => + "hg log --date=\$email_hg_since" . + " --template='commit {node}\\n{desc}\\n' -- \$file", + "find_commit_signers_cmd" => "hg log --template='{desc}\\n' -r \$commit", + "blame_range_cmd" => "", # not supported + "blame_file_cmd" => "hg blame -c \$file", + "commit_pattern" => "^commit [0-9a-f]{40,40}", + "blame_commit_pattern" => "^([0-9a-f]+):" +); + if (!GetOptions( 'email!' => \$email, 'git!' => \$email_git, + 'git-blame!' => \$email_git_blame, 'git-chief-penguins!' => \$email_git_penguin_chiefs, 'git-min-signatures=i' => \$email_git_min_signatures, 'git-max-maintainers=i' => \$email_git_max_maintainers, 'git-min-percent=i' => \$email_git_min_percent, 'git-since=s' => \$email_git_since, - 'git-blame!' => \$email_git_blame, + 'hg-since=s' => \$email_hg_since, 'remove-duplicates!' => \$email_remove_duplicates, 'm!' => \$email_maintainer, 'n!' => \$email_usename, 'l!' => \$email_list, 's!' => \$email_subscriber_list, 'multiline!' => \$output_multiline, + 'roles!' => \$output_roles, + 'rolestats!' => \$output_rolestats, 'separator=s' => \$output_separator, 'subsystem!' => \$subsystem, 'status!' => \$status, @@ -90,8 +124,7 @@ if (!GetOptions( 'v|version' => \$version, 'h|help' => \$help, )) { - usage(); - die "$P: invalid argument\n"; + die "$P: invalid argument - use --help if necessary\n"; } if ($help != 0) { @@ -113,6 +146,10 @@ if ($output_separator ne ", ") { $output_multiline = 0; } +if ($output_rolestats) { + $output_roles = 1; +} + my $selections = $email + $scm + $status + $subsystem + $web; if ($selections == 0) { usage(); @@ -175,7 +212,7 @@ if ($email_remove_duplicates) { next if ($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*$/); @@ -207,12 +244,10 @@ foreach my $file (@ARGV) { 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); @@ -304,11 +339,11 @@ foreach my $file (@files) { } if ($email && $email_git) { - recent_git_signoffs($file); + vcs_file_signoffs($file); } if ($email && $email_git_blame) { - git_assign_blame($file); + vcs_file_blame($file); } } @@ -324,11 +359,11 @@ if ($email) { 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, $email_address); + push(@email_to, [$email_address, 'chief penguin']); } else { - @email_to = grep(!/${email_address}/, @email_to); + @email_to = grep($_->[0] !~ /${email_address}/, @email_to); } } } @@ -342,7 +377,7 @@ if ($email || $email_list) { if ($email_list) { @to = (@to, @list_to); } - output(uniq(@to)); + output(merge_email(@to)); } if ($scm) { @@ -398,13 +433,16 @@ MAINTAINER field selection options: --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 --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, %) --scm => print SCM tree(s) if any --status => print status if any --subsystem => print subsystem name if any @@ -430,11 +468,24 @@ Notes: 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. + 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 EOT } @@ -493,7 +544,7 @@ sub parse_email { } sub format_email { - my ($name, $address) = @_; + my ($name, $address, $usename) = @_; my $formatted_email; @@ -506,11 +557,11 @@ sub format_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; @@ -547,6 +598,71 @@ sub find_ending_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; + 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) = @_; @@ -564,17 +680,22 @@ sub add_categories { if ($ptype eq "L") { my $list_address = $pvalue; my $list_additional = ""; + my $list_role = get_list_role($i); + + if ($list_role ne "") { + $list_role = ":" . $list_role; + } if ($list_address =~ m/([^\s]+)\s+(.*)$/) { $list_address = $1; $list_additional = $2; } if ($list_additional =~ m/subscribers-only/) { if ($email_subscriber_list) { - push(@list_to, $list_address); + push(@list_to, [$list_address, "subscriber list${list_role}"]); } } else { if ($email_list) { - push(@list_to, $list_address); + push(@list_to, [$list_address, "open list${list_role}"]); } } } elsif ($ptype eq "M") { @@ -585,13 +706,14 @@ sub add_categories { 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_maintainer) { - push_email_addresses($pvalue); + my $role = get_maintainer_role($i); + push_email_addresses($pvalue, $role); } } elsif ($ptype eq "T") { push(@scm, $pvalue); @@ -618,7 +740,7 @@ sub email_inuse { } sub push_email_address { - my ($line) = @_; + my ($line, $role) = @_; my ($name, $address) = parse_email($line); @@ -627,9 +749,9 @@ sub push_email_address { } if (!$email_remove_duplicates) { - push(@email_to, format_email($name, $address)); + push(@email_to, [format_email($name, $address, $email_usename), $role]); } elsif (!email_inuse($name, $address)) { - push(@email_to, format_email($name, $address)); + push(@email_to, [format_email($name, $address, $email_usename), $role]); $email_hash_name{$name}++; $email_hash_address{$address}++; } @@ -638,24 +760,52 @@ sub push_email_address { } sub push_email_addresses { - my ($address) = @_; + my ($address, $role) = @_; my @address_list = (); if (rfc822_valid($address)) { - push_email_address($address); + push_email_address($address, $role); } elsif (@address_list = rfc822_validlist($address)) { my $array_count = shift(@address_list); while (my $entry = shift(@address_list)) { - push_email_address($entry); + push_email_address($entry, $role); } } else { - if (!push_email_address($address)) { + if (!push_email_address($address, $role)) { warn("Invalid MAINTAINERS address: '" . $address . "'\n"); } } } +sub add_role { + my ($line, $role) = @_; + + my ($name, $address) = parse_email($line); + my $email = format_email($name, $address, $email_usename); + + foreach my $entry (@email_to) { + if ($email_remove_duplicates) { + my ($entry_name, $entry_address) = parse_email($entry->[0]); + if ($name eq $entry_name || $address eq $entry_address) { + if ($entry->[1] eq "") { + $entry->[1] = "$role"; + } else { + $entry->[1] = "$entry->[1],$role"; + } + } + } else { + if ($email eq $entry->[0]) { + if ($entry->[1] eq "") { + $entry->[1] = "$role"; + } else { + $entry->[1] = "$entry->[1],$role"; + } + } + } + } +} + sub which { my ($bin) = @_; @@ -669,7 +819,7 @@ sub which { } sub mailmap { - my @lines = @_; + my (@lines) = @_; my %hash; foreach my $line (@lines) { @@ -678,14 +828,14 @@ sub mailmap { $hash{$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}, $email_usename); } } } @@ -694,34 +844,38 @@ sub mailmap { return @lines; } -sub recent_git_signoffs { - my ($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); @@ -729,111 +883,183 @@ sub recent_git_signoffs { # cut -f2- -d":" s/.*:\s*(.+)\s*/$1/ for (@lines); - $total_sign_offs = @lines; +## Reformat email addresses (with names) to avoid badly written signatures - if ($email_remove_duplicates) { - @lines = mailmap(@lines); + foreach my $line (@lines) { + my ($name, $address) = parse_email($line); + $line = format_email($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}; - $count++; - last if ($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); - } + 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 $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 < $email_git_min_percent); - push_email_address($line); + $percent < $email_git_min_percent); + push_email_address($line, ''); + if ($output_rolestats) { + my $fmt_percent = sprintf("%.0f", $percent); + add_role($line, "$role:$sign_offs/$divisor=$fmt_percent%"); + } else { + 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{$_}++, @parms); @@ -841,7 +1067,7 @@ sub uniq { } sub sort_and_uniq { - my @parms = @_; + my (@parms) = @_; my %saw; @parms = sort @parms; @@ -849,8 +1075,27 @@ sub sort_and_uniq { return @parms; } +sub merge_email { + my @lines; + my %saw; + + for (@_) { + my ($address, $role) = @$_; + if (!$saw{$address}) { + if ($output_roles) { + push(@lines, "$address ($role)"); + } else { + push(@lines, $address); + } + $saw{$address} = 1; + } + } + + return @lines; +} + sub output { - my @parms = @_; + my (@parms) = @_; if ($output_multiline) { foreach my $line (@parms) { @@ -947,11 +1192,9 @@ sub rfc822_validlist ($) { 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; } |
