X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=scripts%2Fget_maintainer.pl;h=81a67a458e78ddd494343e5746a195ef4e821440;hb=32197c7ffb06b1319850f8fdfa1a49d32a63b79b;hp=159ce64ad26b6c233b0b26e6645b87a3d60bee30;hpb=d789504ab03c27b194170262cb4ffda38905c5c0;p=safe%2Fjmp%2Flinux-2.6 diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 159ce64..81a67a4 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -5,15 +5,15 @@ # Print selected MAINTAINERS information for # the files modified in a patch or for a file # -# usage: perl scripts/get_maintainers.pl [OPTIONS] -# perl scripts/get_maintainers.pl [OPTIONS] -f +# usage: perl scripts/get_maintainer.pl [OPTIONS] +# perl scripts/get_maintainer.pl [OPTIONS] -f # # Licensed under the terms of the GNU GPL License version 2 use strict; my $P = $0; -my $V = '0.16'; +my $V = '0.21'; use Getopt::Long qw(:config no_auto_abbrev); @@ -27,14 +27,19 @@ my $email_git = 1; my $email_git_penguin_chiefs = 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_remove_duplicates = 1; my $output_multiline = 1; my $output_separator = ", "; my $scm = 0; my $web = 0; my $subsystem = 0; my $status = 0; +my $keywords = 1; my $from_filename = 0; +my $pattern_depth = 0; my $version = 0; my $help = 0; @@ -55,9 +60,9 @@ foreach my $chief (@penguin_chief) { } my $penguin_chiefs = "\(" . join("|",@penguin_chief_names) . "\)"; -# rfc822 - preloaded methods go here. +# rfc822 email address - preloaded methods go here. my $rfc822_lwsp = "(?:(?:\\r\\n)?[ \\t])"; -my $rfc822_char = '[\\000-\\177]'; +my $rfc822_char = '[\\000-\\377]'; if (!GetOptions( 'email!' => \$email, @@ -65,7 +70,10 @@ if (!GetOptions( 'git-chief-penguins!' => \$email_git_penguin_chiefs, 'git-min-signatures=i' => \$email_git_min_signatures, 'git-max-maintainers=i' => \$email_git_max_maintainers, + 'git-min-percent=i' => \$email_git_min_percent, 'git-since=s' => \$email_git_since, + 'git-blame!' => \$email_git_blame, + 'remove-duplicates!' => \$email_remove_duplicates, 'm!' => \$email_maintainer, 'n!' => \$email_usename, 'l!' => \$email_list, @@ -76,6 +84,8 @@ if (!GetOptions( 'status!' => \$status, 'scm!' => \$scm, 'web!' => \$web, + 'pattern-depth=i' => \$pattern_depth, + 'k|keywords!' => \$keywords, 'f|file' => \$from_filename, 'v|version' => \$version, 'h|help' => \$help, @@ -99,14 +109,19 @@ if ($#ARGV < 0) { die "$P: argument missing: patchfile or -f file please\n"; } +if ($output_separator ne ", ") { + $output_multiline = 0; +} + my $selections = $email + $scm + $status + $subsystem + $web; if ($selections == 0) { usage(); die "$P: Missing required option: email, scm, status, subsystem or web\n"; } -if ($email && ($email_maintainer + $email_list + $email_subscriber_list - + $email_git + $email_git_penguin_chiefs) == 0) { +if ($email && + ($email_maintainer + $email_list + $email_subscriber_list + + $email_git + $email_git_penguin_chiefs + $email_git_blame) == 0) { usage(); die "$P: Please select at least 1 email option\n"; } @@ -119,6 +134,8 @@ if (!top_of_kernel_tree($lk_path)) { ## Read MAINTAINERS for type/value pairs my @typevalue = (); +my %keyword_hash; + open(MAINT, "<${lk_path}MAINTAINERS") || die "$P: Can't open MAINTAINERS\n"; while () { my $line = $_; @@ -132,6 +149,12 @@ while () { $value =~ s@\.@\\\.@g; ##Convert . to \. $value =~ s/\*/\.\*/g; ##Convert * to .* $value =~ s/\?/\./g; ##Convert ? to . + ##if pattern is a directory and it lacks a trailing slash, add one + if ((-d $value)) { + $value =~ s@([^/])$@$1/@; + } + } elsif ($type eq "K") { + $keyword_hash{@typevalue} = $value; } push(@typevalue, "$type:$value"); } elsif (!/^(\s)*$/) { @@ -141,31 +164,86 @@ while () { } close(MAINT); +my %mailmap; + +if ($email_remove_duplicates) { + open(MAILMAP, "<${lk_path}.mailmap") || warn "$P: Can't open .mailmap\n"; + while () { + my $line = $_; + + next if ($line =~ m/^\s*#/); + next if ($line =~ m/^\s*$/); + + my ($name, $address) = parse_email($line); + $line = format_email($name, $address); + + next if ($line =~ m/^\s*$/); + + if (exists($mailmap{$name})) { + my $obj = $mailmap{$name}; + push(@$obj, $address); + } else { + my @arr = ($address); + $mailmap{$name} = \@arr; + } + } + close(MAILMAP); +} + ## use the filenames on the command line or find the filenames in the patchfiles my @files = (); +my @range = (); +my @keyword_tvi = (); foreach my $file (@ARGV) { - next if ((-d $file)); - if (!(-f $file)) { + ##if $file is a directory and it lacks a trailing slash, add one + if ((-d $file)) { + $file =~ s@([^/])$@$1/@; + } elsif (!(-f $file)) { die "$P: file '${file}' not found\n"; } if ($from_filename) { push(@files, $file); + if (-f $file && $keywords) { + open(FILE, "<$file") or die "$P: Can't open ${file}\n"; + while () { + my $patch_line = $_; + foreach my $line (keys %keyword_hash) { + if ($patch_line =~ m/^.*$keyword_hash{$line}/x) { + push(@keyword_tvi, $line); + } + } + } + close(FILE); + } } else { my $file_cnt = @files; + my $lastfile; open(PATCH, "<$file") or die "$P: Can't open ${file}\n"; while () { + my $patch_line = $_; if (m/^\+\+\+\s+(\S+)/) { my $filename = $1; $filename =~ s@^[^/]*/@@; $filename =~ s@\n@@; + $lastfile = $filename; push(@files, $filename); + } elsif (m/^\@\@ -(\d+),(\d+)/) { + if ($email_git_blame) { + push(@range, "$lastfile:$1:$2"); + } + } elsif ($keywords) { + foreach my $line (keys %keyword_hash) { + if ($patch_line =~ m/^[+-].*$keyword_hash{$line}/x) { + push(@keyword_tvi, $line); + } + } } } close(PATCH); if ($file_cnt == @files) { - die "$P: file '${file}' doesn't appear to be a patch. " + warn "$P: file '${file}' doesn't appear to be a patch. " . "Add -f to options?\n"; } @files = sort_and_uniq(@files); @@ -193,6 +271,7 @@ foreach my $file (@files) { if ($type eq 'X') { if (file_match_pattern($file, $value)) { $exclude = 1; + last; } } } @@ -200,35 +279,52 @@ foreach my $file (@files) { if (!$exclude) { my $tvi = 0; + my %hash; foreach my $line (@typevalue) { if ($line =~ m/^(\C):\s*(.*)/) { my $type = $1; my $value = $2; if ($type eq 'F') { if (file_match_pattern($file, $value)) { - add_categories($tvi); + my $value_pd = ($value =~ tr@/@@); + my $file_pd = ($file =~ tr@/@@); + $value_pd++ if (substr($value,-1,1) ne "/"); + if ($pattern_depth == 0 || + (($file_pd - $value_pd) < $pattern_depth)) { + $hash{$tvi} = $value_pd; + } } } } $tvi++; } + foreach my $line (sort {$hash{$b} <=> $hash{$a}} keys %hash) { + add_categories($line); + } } if ($email && $email_git) { recent_git_signoffs($file); } + if ($email && $email_git_blame) { + git_assign_blame($file); + } +} + +if ($keywords) { + @keyword_tvi = sort_and_uniq(@keyword_tvi); + foreach my $line (@keyword_tvi) { + add_categories($line); + } } if ($email) { foreach my $chief (@penguin_chief) { if ($chief =~ m/^(.*):(.*)/) { my $email_address; - if ($email_usename) { - $email_address = format_email($1, $2); - } else { - $email_address = $2; - } + + $email_address = format_email($1, $2); if ($email_git_penguin_chiefs) { push(@email_to, $email_address); } else { @@ -250,22 +346,22 @@ if ($email || $email_list) { } if ($scm) { - @scm = sort_and_uniq(@scm); + @scm = uniq(@scm); output(@scm); } if ($status) { - @status = sort_and_uniq(@status); + @status = uniq(@status); output(@status); } if ($subsystem) { - @subsystem = sort_and_uniq(@subsystem); + @subsystem = uniq(@subsystem); output(@subsystem); } if ($web) { - @web = sort_and_uniq(@web); + @web = uniq(@web); output(@web); } @@ -292,7 +388,7 @@ sub file_match_pattern { sub usage { print < include ${penguin_chiefs} --git-min-signatures => number of signatures required (default: 1) --git-max-maintainers => maximum maintainers to add (default: 5) + --git-min-percent => minimum percentage of commits required (default: 5) --git-since => git history to use (default: 1-year-ago) + --git-blame => use git blame to find modified commits for patch or file --m => include maintainer(s) if any --n => include name 'Full Name ' --l => include list(s) if any --s => include subscriber only list(s) if any + --remove-duplicates => minimize duplicate email names/addresses --scm => print SCM tree(s) if any --status => print status if any --subsystem => print subsystem name if any @@ -313,15 +412,29 @@ MAINTAINER field selection options: Output type options: --separator [, ] => separator for multiple entries on 1 line + using --separator also sets --nomultiline if --separator is not [, ] --multiline => print 1 entry per line -Default options: - [--email --git --m --n --l --multiline] - Other options: + --pattern-depth => Number of pattern directory traversals (default: 0 (all)) + --keywords => scan patch for keywords (default: 1 (on)) --version => show version --help => show this help information +Default options: + [--email --git --m --n --l --multiline --pattern-depth=0 --remove-duplicates] + +Notes: + Using "-f directory" may give unexpected results: + Used with "--git", git signators for _all_ files in and below + directory are examined as git recurses directories. + Any specified X: (exclude) pattern matches are _not_ ignored. + Used with "--nogit", directory is used as a pattern match, + no individual file within the directory or subdirectory + is matched. + Used with "--git-blame", does not iterate all files in directory + Using "--git-blame" is slow and may add old committers and authors + that are no longer active maintainers to the output. EOT } @@ -352,30 +465,99 @@ sub top_of_kernel_tree { return 0; } -sub format_email { - my ($name, $email) = @_; +sub parse_email { + my ($formatted_email) = @_; + + my $name = ""; + my $address = ""; + + if ($formatted_email =~ /^([^<]+)<(.+\@.*)>.*$/) { + $name = $1; + $address = $2; + } elsif ($formatted_email =~ /^\s*<(.+\@\S*)>.*$/) { + $address = $1; + } elsif ($formatted_email =~ /^(.+\@\S*).*$/) { + $address = $1; + } $name =~ s/^\s+|\s+$//g; $name =~ s/^\"|\"$//g; - $email =~ s/^\s+|\s+$//g; + $address =~ s/^\s+|\s+$//g; + + if ($name =~ /[^a-z0-9 \.\-]/i) { ##has "must quote" chars + $name =~ s/(?"; + $name = "\"$name\""; + } + + if ($email_usename) { + if ("$name" eq "") { + $formatted_email = "$address"; + } else { + $formatted_email = "$name <${address}>"; + } } else { - $formatted_email = "${name} \<${email}\>"; + $formatted_email = $address; } + return $formatted_email; } -sub add_categories { +sub find_starting_index { my ($index) = @_; - $index = $index - 1; - while ($index >= 0) { + while ($index > 0) { my $tv = $typevalue[$index]; + if (!($tv =~ m/^(\C):\s*(.*)/)) { + last; + } + $index--; + } + + return $index; +} + +sub find_ending_index { + my ($index) = @_; + + while ($index < @typevalue) { + my $tv = $typevalue[$index]; + if (!($tv =~ m/^(\C):\s*(.*)/)) { + last; + } + $index++; + } + + return $index; +} + +sub add_categories { + my ($index) = @_; + + my $i; + my $start = find_starting_index($index); + my $end = find_ending_index($index); + + push(@subsystem, $typevalue[$start]); + + for ($i = $start + 1; $i < $end; $i++) { + my $tv = $typevalue[$i]; if ($tv =~ m/^(\C):\s*(.*)/) { my $ptype = $1; my $pvalue = $2; @@ -396,6 +578,18 @@ sub add_categories { } } } elsif ($ptype eq "M") { + my ($name, $address) = parse_email($pvalue); + if ($name eq "") { + if ($i > 0) { + my $tv = $typevalue[$i - 1]; + if ($tv =~ m/^(\C):\s*(.*)/) { + if ($1 eq "P") { + $name = $2; + $pvalue = format_email($name, $address); + } + } + } + } if ($email_maintainer) { push_email_addresses($pvalue); } @@ -406,29 +600,41 @@ sub add_categories { } elsif ($ptype eq "S") { push(@status, $pvalue); } - - $index--; - } else { - push(@subsystem,$tv); - $index = -1; } } } +my %email_hash_name; +my %email_hash_address; + +sub email_inuse { + my ($name, $address) = @_; + + return 1 if (($name eq "") && ($address eq "")); + return 1 if (($name ne "") && exists($email_hash_name{$name})); + return 1 if (($address ne "") && exists($email_hash_address{$address})); + + return 0; +} + sub push_email_address { - my ($email_address) = @_; + my ($line) = @_; + + my ($name, $address) = parse_email($line); - my $email_name = ""; - if ($email_address =~ m/([^<]+)<(.*\@.*)>$/) { - $email_name = $1; - $email_address = $2; + if ($address eq "") { + return 0; } - if ($email_usename && $email_name) { - push(@email_to, format_email($email_name, $email_address)); - } else { - push(@email_to, $email_address); + if (!$email_remove_duplicates) { + push(@email_to, format_email($name, $address)); + } elsif (!email_inuse($name, $address)) { + push(@email_to, format_email($name, $address)); + $email_hash_name{$name}++; + $email_hash_address{$address}++; } + + return 1; } sub push_email_addresses { @@ -436,13 +642,18 @@ sub push_email_addresses { my @address_list = (); - if (@address_list = rfc822_validlist($address)) { + if (rfc822_valid($address)) { + push_email_address($address); + } elsif (@address_list = rfc822_validlist($address)) { my $array_count = shift(@address_list); while (my $entry = shift(@address_list)) { push_email_address($entry); } + } else { + if (!push_email_address($address)) { + warn("Invalid MAINTAINERS address: '" . $address . "'\n"); + } } - } sub which { @@ -457,6 +668,32 @@ sub which { return ""; } +sub mailmap { + my @lines = @_; + my %hash; + + foreach my $line (@lines) { + my ($name, $address) = parse_email($line); + if (!exists($hash{$name})) { + $hash{$name} = $address; + } elsif ($address ne $hash{$name}) { + $address = $hash{$name}; + $line = format_email($name, $address); + } + if (exists($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}); + } + } + } + } + + return @lines; +} + sub recent_git_signoffs { my ($file) = @_; @@ -465,57 +702,134 @@ sub recent_git_signoffs { my $output = ""; my $count = 0; 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("$P: .git repository not found.\n"); - warn("Use a .git repository for better results.\n"); - warn("ie: git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git\n"); + warn("$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; } $cmd = "git log --since=${email_git_since} -- ${file}"; - $cmd .= " | grep -Ei \"^[-_ a-z]+by:.*\\\@.*\$\""; + + $output = `${cmd}`; + $output =~ s/^\s*//gm; + + @lines = split("\n", $output); + + @lines = grep(/^[-_ a-z]+by:.*\@.*$/i, @lines); if (!$email_git_penguin_chiefs) { - $cmd .= " | grep -Ev \"${penguin_chiefs}\""; + @lines = grep(!/${penguin_chiefs}/i, @lines); + } + # cut -f2- -d":" + s/.*:\s*(.+)\s*/$1/ for (@lines); + + $total_sign_offs = @lines; + + if ($email_remove_duplicates) { + @lines = mailmap(@lines); } - $cmd .= " | cut -f2- -d\":\""; - $cmd .= " | sort | uniq -c | sort -rn"; + + @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); + } +} + +sub save_commits { + my ($cmd, @commits) = @_; + my $output; + my @lines = (); $output = `${cmd}`; - $output =~ s/^\s*//gm; @lines = split("\n", $output); foreach my $line (@lines) { - if ($line =~ m/([0-9]+)\s+(.*)/) { - my $sign_offs = $1; - $line = $2; - $count++; - if ($sign_offs < $email_git_min_signatures || - $count > $email_git_max_maintainers) { - last; - } - } else { - die("$P: Unexpected git output: ${line}\n"); + if ($line =~ m/^(\w+) /) { + push (@commits, $1); } - if ($line =~ m/(.+)<(.+)>/) { - my $git_name = $1; - my $git_addr = $2; - if ($email_usename) { - push(@email_to, format_email($git_name, $git_addr)); - } else { - push(@email_to, $git_addr); - } - } elsif ($line =~ m/<(.+)>/) { - my $git_addr = $1; - push(@email_to, $git_addr); - } else { - push(@email_to, $line); + } + return @commits; +} + +sub git_assign_blame { + my ($file) = @_; + + my @lines = (); + my @commits = (); + my $cmd; + my $output; + my %hash; + my $total_sign_offs; + my $count; + + 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); + } + } else { + if (-f $file) { + $cmd = "git blame -l $file"; + @commits = save_commits($cmd, @commits); } } + + $total_sign_offs = 0; + @commits = uniq(@commits); + foreach my $commit (@commits) { + $cmd = "git log -1 ${commit}"; + + $output = `${cmd}`; + $output =~ s/^\s*//gm; + @lines = split("\n", $output); + + @lines = grep(/^[-_ a-z]+by:.*\@.*$/i, @lines); + if (!$email_git_penguin_chiefs) { + @lines = grep(!/${penguin_chiefs}/i, @lines); + } + + # cut -f2- -d":" + s/.*:\s*(.+)\s*/$1/ for (@lines); + + $total_sign_offs += @lines; + + if ($email_remove_duplicates) { + @lines = mailmap(@lines); + } + + $hash{$_}++ for @lines; + } + + $count = 0; + 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); + } } sub uniq { @@ -632,7 +946,7 @@ sub rfc822_validlist ($) { my @r; if ($s =~ m/^(?:$rfc822re)?(?:,(?:$rfc822re)?)*$/so && $s =~ m/^$rfc822_char*$/) { - while($s =~ m/(?:^|,$rfc822_lwsp*)($rfc822re)/gos) { + while ($s =~ m/(?:^|,$rfc822_lwsp*)($rfc822re)/gos) { push @r, $1; } return wantarray ? (scalar(@r), @r) : 1;