From 63ab52db5ba7f362266cfed03109387ca73e5eb5 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:51 -0700 Subject: scripts/get_maintainer.pl: Add --git-blame --rolestats "Authored lines" information 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 (authored lines:406/613=66%,commits:7/20=35%) Akinobu Mita (authored lines:87/613=14%,commits:3/20=15%) Reinette Chatre (authored lines:42/613=7%) Andrew Morton (commits:16/20=80%) Paul Mundt (commits:3/20=15%) Randy Dunlap (commits:2/20=10%) $ ./scripts/get_maintainer.pl --git-blame --git --rolestats -f lib/bitmap.c Andrew Morton (commit_signer:4/5=80%,commits:16/20=80%) Akinobu Mita (commit_signer:2/5=40%,authored lines:87/613=14%,commits:3/20=15%) Jack Steiner (commit_signer:1/5=20%) Ben Hutchings (commit_signer:1/5=20%) Lee Schermerhorn (commit_signer:1/5=20%) Paul Jackson (authored lines:406/613=66%,commits:7/20=35%) Reinette Chatre (authored lines:42/613=7%) Paul Mundt (commits:3/20=15%) Randy Dunlap (commits:2/20=10%) linux-kernel@vger.kernel.org (open list) Signed-off-by: Joe Perches Cc: Mark Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 60 ++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 57 insertions(+), 3 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index b2281982f52..a91ae631840 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); -- cgit v1.2.3-70-g09d2 From 6ffd9485f5c9c0b2d2aea9f904dff08e7088010a Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:51 -0700 Subject: scripts/get_maintainer.pl: use correct indentation Fix an overly indented block. Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index a91ae631840..65c6acf1bb3 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) { -- cgit v1.2.3-70-g09d2 From fab9ed12fcd0c182a72509382c3da55c527963e3 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:52 -0700 Subject: scripts/get_maintainer.pl: don't search MAINTAINERS for keywords or emails 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 Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 65c6acf1bb3..77f4f2e4cd8 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> }; -- cgit v1.2.3-70-g09d2 From e3e9d11479737692f797bad1762f71468d577a93 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:53 -0700 Subject: scripts/get_maintainer.pl: add default --git-fallback, remove default --git 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 M: Ingo Molnar M: "H. Peter Anvin" 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 (maintainer:X86 ARCHITECTURE...) Ingo Molnar (maintainer:X86 ARCHITECTURE...) "H. Peter Anvin" (maintainer:X86 ARCHITECTURE...,commit_signer:1/1=100%) x86@kernel.org (maintainer:X86 ARCHITECTURE...) Luca Barbieri (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 Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 77f4f2e4cd8..f46576949cc 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) -- cgit v1.2.3-70-g09d2 From bcde44ed7d2a58733efdf04b5392c027d1348bac Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:53 -0700 Subject: scripts/get_maintainer.pl: use .get_maintainer.conf from . then $HOME then scripts 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 $HOME user global configuration when per-tree configs don't exist ./scripts lk defaults to override script Signed-off-by: Joe Perches Cc: Valdis Kletnieks Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index f46576949cc..e5a400c53bf 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -110,10 +110,12 @@ my %VCS_cmds_hg = ( "blame_commit_pattern" => "^([0-9a-f]+):" ); -if (-f "${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; -- cgit v1.2.3-70-g09d2 From dace8e300d6820c2842de750d12b498a743bcfe5 Mon Sep 17 00:00:00 2001 From: Florian Mickler Date: Tue, 26 Oct 2010 14:22:54 -0700 Subject: scripts/get_maintainer.pl: add interactive mode This is a first version of an interactive mode for scripts/get_maintainer.pl. It allows the user to interact with the script. Each cc candidate can be selected and deselected and a shortlog of authored commits can be displayed for each candidate. The menu is displayed via STDERR, the end result is outputted to STDOUT. This unusual mechanism allows using get_maintainer.pl in interactive mode via git send-email --cc-cmd. Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 146 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 141 insertions(+), 5 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index e5a400c53bf..1ae8c50f190 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -33,6 +33,7 @@ my $email_git_max_maintainers = 5; my $email_git_min_percent = 5; my $email_git_since = "1-year-ago"; my $email_hg_since = "-365"; +my $interactive = 0; my $email_remove_duplicates = 1; my $output_multiline = 1; my $output_separator = ", "; @@ -52,6 +53,8 @@ my $help = 0; my $exit = 0; +my %shortlog_buffer; + my @penguin_chief = (); push(@penguin_chief, "Linus Torvalds:torvalds\@linux-foundation.org"); #Andrew wants in on most everything - 2009/01/14 @@ -93,7 +96,8 @@ my %VCS_cmds_git = ( "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]+) " + "blame_commit_pattern" => "^([0-9a-f]+) ", + "shortlog_cmd" => "git log --no-color --oneline --since=\$email_git_since --author=\"\$email\" -- \$file" ); my %VCS_cmds_hg = ( @@ -107,7 +111,8 @@ my %VCS_cmds_hg = ( "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]+):" + "blame_commit_pattern" => "^([0-9a-f]+):", + "shortlog_cmd" => "ht log --date=\$email_hg_since" ); my $conf = which_conf(".get_maintainer.conf"); @@ -148,6 +153,7 @@ if (!GetOptions( 'git-min-percent=i' => \$email_git_min_percent, 'git-since=s' => \$email_git_since, 'hg-since=s' => \$email_hg_since, + 'i|interactive!' => \$interactive, 'remove-duplicates!' => \$email_remove_duplicates, 'm!' => \$email_maintainer, 'n!' => \$email_usename, @@ -225,6 +231,8 @@ if ($email_git_all_signature_types) { $signaturePattern = "(.+?)[Bb][Yy]:"; } + + ## Read MAINTAINERS for type/value pairs my @typevalue = (); @@ -450,10 +458,13 @@ foreach my $file (@files) { ($email_git || ($email_git_fallback && !$exact_pattern_match))) { vcs_file_signoffs($file); } - if ($email && $email_git_blame) { vcs_file_blame($file); } + if ($email && $interactive){ + vcs_file_shortlogs($file); + + } } if ($keywords) { @@ -486,9 +497,13 @@ if ($email) { } } + if ($email || $email_list) { my @to = (); if ($email) { + if ($interactive) { + @email_to = @{vcs_interactive_menu(\@email_to)}; + } @to = (@to, @email_to); } if ($email_list) { @@ -501,7 +516,6 @@ if ($scm) { @scm = uniq(@scm); output(@scm); } - if ($status) { @status = uniq(@status); output(@status); @@ -556,6 +570,7 @@ MAINTAINER field selection options: --git-blame => use git blame to find modified commits for patch or file --git-since => git history to use (default: $email_git_since) --hg-since => hg history to use (default: $email_hg_since) + --interactive => display a menu (mostly useful if used with the --git option) --m => include maintainer(s) if any --n => include name 'Full Name ' --l => include list(s) if any @@ -1156,6 +1171,127 @@ sub vcs_exists { return 0; } +sub vcs_interactive_menu { + my $list_ref = shift; + my @list = @$list_ref; + + return if (!vcs_exists()); + + my %selected; + my %shortlog; + my $input; + my $count = 0; + + #select maintainers by default + foreach my $entry (@list){ + my $role = $entry->[1]; + $selected{$count} = ($role =~ /maintainer:|supporter:/); + $count++; + } + + #menu loop + do { + my $count = 0; + foreach my $entry (@list){ + my $email = $entry->[0]; + my $role = $entry->[1]; + if ($selected{$count}){ + print STDERR "* "; + } else { + print STDERR " "; + } + print STDERR "$count: $email,\t\t $role"; + print STDERR "\n"; + if ($shortlog{$count}){ + my $entries_ref = vcs_get_shortlog($email); + foreach my $entry_ref (@{$entries_ref}){ + my $filename = @{$entry_ref}[0]; + my @shortlog = @{@{$entry_ref}[1]}; + print STDERR "\tshortlog for $filename (authored commits: " . @shortlog . ").\n"; + foreach my $commit (@shortlog){ + print STDERR "\t $commit\n"; + } + print STDERR "\n"; + } + } + $count++; + } + print STDERR "\n"; + print STDERR "Choose whom to cc by entering a commaseperated list of numbers and hitting enter.\n"; + print STDERR "To show a short list of commits, precede the number by a '?',\n"; + print STDERR "A blank line indicates that you are satisfied with your choice.\n"; + $input = ; + chomp($input); + + my @wish = split(/[, ]+/,$input); + foreach my $nr (@wish){ + my $logtoggle = 0; + if ($nr =~ /\?/){ + $nr =~ s/\?//; + $logtoggle = 1; + } + + #skip out of bounds numbers + next unless ($nr <= $count && $nr >= 0); + + if ($logtoggle){ + $shortlog{$nr} = !$shortlog{$nr}; + } else { + $selected{$nr} = !$selected{$nr}; + + #switch shortlog on if an entry get's selected + if ($selected{$nr}){ + $shortlog{$nr}=1; + } + } + }; + } while(length($input) > 0); + + #drop not selected entries + $count = 0; + my @new_emailto; + foreach my $entry (@list){ + if ($selected{$count}){ + push(@new_emailto,$list[$count]); + print STDERR "$count: "; + print STDERR $email_to[$count]->[0]; + print STDERR ",\t\t "; + print STDERR $email_to[$count]->[1]; + print STDERR "\n"; + } + $count++; + } + return \@new_emailto; +} + +sub vcs_get_shortlog { + my $arg = shift; + my ($name, $address) = parse_email($arg); + return $shortlog_buffer{$address}; +} + +sub vcs_file_shortlogs { + my ($file) = @_; + print STDERR "shortlog processing $file:"; + foreach my $entry (@email_to){ + my ($name, $address) = parse_email($entry->[0]); + print STDERR "."; + my $commits_ref = vcs_email_shortlog($address, $file); + push(@{$shortlog_buffer{$address}}, [ $file, $commits_ref ]); + } + print STDERR "\n"; +} + +sub vcs_email_shortlog { + my $email = shift; + my ($file) = @_; + + my $cmd = $VCS_cmds{"shortlog_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables + my @lines = &{$VCS_cmds{"execute_cmd"}}($cmd); + return \@lines; +} + sub vcs_assign { my ($role, $divisor, @lines) = @_; @@ -1236,7 +1372,7 @@ sub vcs_file_blame { my @commit_signers = (); my $cmd = $VCS_cmds{"find_commit_signers_cmd"}; - $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd + $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables in $cmd ($commit_count, @commit_signers) = vcs_find_signers($cmd); -- cgit v1.2.3-70-g09d2 From 683c6f8fcbcb6de8d07545ba70aff49e50d8bcf2 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:55 -0700 Subject: scripts/get_maintainer.pl: improve --interactive UI o Added searching by git-blame as well as git-history o Added different selection toggles o Added ability to list commits by author or by sign-off-type o Use custom git and hg formats to make searching for subject/author a bit easier. o Move inlined section matching and searching git/hg history to new get_maintainer subroutine o Added subroutines save_commits_by_author and save_commits_by_signer o Removed subroutines vcs_get_shortlog and vcs_email_shortlog o Rename camelcase signaturePattern to signature_pattern Update to 0.26 beta3 Signed-off-by: Joe Perches Cc: Florian Mickler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 871 +++++++++++++++++++++++++++++++--------------- 1 file changed, 596 insertions(+), 275 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 1ae8c50f190..f51176039ff 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -13,7 +13,7 @@ use strict; my $P = $0; -my $V = '0.25'; +my $V = '0.26-beta3'; use Getopt::Long qw(:config no_auto_abbrev); @@ -27,6 +27,7 @@ my $email_git_penguin_chiefs = 0; my $email_git = 0; my $email_git_all_signature_types = 0; my $email_git_blame = 0; +my $email_git_blame_signatures = 1; my $email_git_fallback = 1; my $email_git_min_signatures = 1; my $email_git_max_maintainers = 5; @@ -51,9 +52,12 @@ my $pattern_depth = 0; my $version = 0; my $help = 0; +my $vcs_used = 0; + my $exit = 0; -my %shortlog_buffer; +my %commit_author_hash; +my %commit_signer_hash; my @penguin_chief = (); push(@penguin_chief, "Linus Torvalds:torvalds\@linux-foundation.org"); @@ -77,7 +81,6 @@ my @signature_tags = (); push(@signature_tags, "Signed-off-by:"); push(@signature_tags, "Reviewed-by:"); push(@signature_tags, "Acked-by:"); -my $signaturePattern = "\(" . join("|", @signature_tags) . "\)"; # rfc822 email address - preloaded methods go here. my $rfc822_lwsp = "(?:(?:\\r\\n)?[ \\t])"; @@ -90,29 +93,62 @@ my %VCS_cmds; my %VCS_cmds_git = ( "execute_cmd" => \&git_execute_cmd, "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", + "find_signers_cmd" => + "git log --no-color --since=\$email_git_since " . + '--format="GitCommit: %H%n' . + 'GitAuthor: %an <%ae>%n' . + 'GitDate: %aD%n' . + 'GitSubject: %s%n' . + '%b%n"' . + " -- \$file", + "find_commit_signers_cmd" => + "git log --no-color " . + '--format="GitCommit: %H%n' . + 'GitAuthor: %an <%ae>%n' . + 'GitDate: %aD%n' . + 'GitSubject: %s%n' . + '%b%n"' . + " -1 \$commit", + "find_commit_author_cmd" => + "git log --no-color " . + '--format="GitCommit: %H%n' . + 'GitAuthor: %an <%ae>%n' . + 'GitDate: %aD%n' . + 'GitSubject: %s%n"' . + " -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}", + "commit_pattern" => "^GitCommit: ([0-9a-f]{40,40})", "blame_commit_pattern" => "^([0-9a-f]+) ", - "shortlog_cmd" => "git log --no-color --oneline --since=\$email_git_since --author=\"\$email\" -- \$file" + "author_pattern" => "^GitAuthor: (.*)", + "subject_pattern" => "^GitSubject: (.*)", ); 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", - "find_commit_author_cmd" => "hg log -l 1 --template='{author}\\n' -r \$commit", + "hg log --date=\$email_hg_since " . + "--template='HgCommit: {node}\\n" . + "HgAuthor: {author}\\n" . + "HgSubject: {desc}\\n'" . + " -- \$file", + "find_commit_signers_cmd" => + "hg log " . + "--template='HgSubject: {desc}\\n'" . + " -r \$commit", + "find_commit_author_cmd" => + "hg log " . + "--template='HgCommit: {node}\\n" . + "HgAuthor: {author}\\n" . + "HgSubject: {desc|firstline}\\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]+):", - "shortlog_cmd" => "ht log --date=\$email_hg_since" + "blame_file_cmd" => "hg blame -n \$file", + "commit_pattern" => "^HgCommit: ([0-9a-f]{40,40})", + "blame_commit_pattern" => "^([ 0-9a-f]+):", + "author_pattern" => "^HgAuthor: (.*)", + "subject_pattern" => "^HgSubject: (.*)", ); my $conf = which_conf(".get_maintainer.conf"); @@ -146,6 +182,7 @@ if (!GetOptions( 'git!' => \$email_git, 'git-all-signature-types!' => \$email_git_all_signature_types, 'git-blame!' => \$email_git_blame, + 'git-blame-signatures!' => \$email_git_blame_signatures, 'git-fallback!' => \$email_git_fallback, 'git-chief-penguins!' => \$email_git_penguin_chiefs, 'git-min-signatures=i' => \$email_git_min_signatures, @@ -193,13 +230,9 @@ if (-t STDIN && !@ARGV) { die "$P: missing patchfile or -f file - use --help if necessary\n"; } -if ($output_separator ne ", ") { - $output_multiline = 0; -} - -if ($output_rolestats) { - $output_roles = 1; -} +$output_multiline = 0 if ($output_separator ne ", "); +$output_rolestats = 1 if ($interactive); +$output_roles = 1 if ($output_rolestats); if ($sections) { $email = 0; @@ -227,12 +260,6 @@ if (!top_of_kernel_tree($lk_path)) { . "a linux kernel source tree.\n"; } -if ($email_git_all_signature_types) { - $signaturePattern = "(.+?)[Bb][Yy]:"; -} - - - ## Read MAINTAINERS for type/value pairs my @typevalue = (); @@ -371,168 +398,193 @@ foreach my $file (@ARGV) { @file_emails = uniq(@file_emails); +my %email_hash_name; +my %email_hash_address; my @email_to = (); +my %hash_list_to; my @list_to = (); my @scm = (); my @web = (); my @subsystem = (); my @status = (); +my $signature_pattern; -# Find responsible parties +my @to = get_maintainer(); -foreach my $file (@files) { +@to = merge_email(@to); - my %hash; - my $exact_pattern_match = 0; - my $tvi = find_first_section(); - while ($tvi < @typevalue) { - my $start = find_starting_index($tvi); - my $end = find_ending_index($tvi); - my $exclude = 0; - my $i; - - #Do not match excluded file patterns - - for ($i = $start; $i < $end; $i++) { - my $line = $typevalue[$i]; - if ($line =~ m/^(\C):\s*(.*)/) { - my $type = $1; - my $value = $2; - if ($type eq 'X') { - if (file_match_pattern($file, $value)) { - $exclude = 1; - last; - } - } - } - } +output(@to) if (@to); + +if ($scm) { + @scm = uniq(@scm); + output(@scm); +} + +if ($status) { + @status = uniq(@status); + output(@status); +} + +if ($subsystem) { + @subsystem = uniq(@subsystem); + output(@subsystem); +} + +if ($web) { + @web = uniq(@web); + output(@web); +} + +exit($exit); + +sub get_maintainer { + %email_hash_name = (); + %email_hash_address = (); + %commit_author_hash = (); + %commit_signer_hash = (); + @email_to = (); + %hash_list_to = (); + @list_to = (); + @scm = (); + @web = (); + @subsystem = (); + @status = (); + + if ($email_git_all_signature_types) { + $signature_pattern = "(.+?)[Bb][Yy]:"; + } else { + $signature_pattern = "\(" . join("|", @signature_tags) . "\)"; + } + + # Find responsible parties + + 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); + my $end = find_ending_index($tvi); + my $exclude = 0; + my $i; + + #Do not match excluded file patterns - if (!$exclude) { for ($i = $start; $i < $end; $i++) { my $line = $typevalue[$i]; if ($line =~ m/^(\C):\s*(.*)/) { my $type = $1; my $value = $2; - if ($type eq 'F') { + if ($type eq 'X') { if (file_match_pattern($file, $value)) { - 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; + $exclude = 1; + last; + } + } + } + } + + if (!$exclude) { + for ($i = $start; $i < $end; $i++) { + my $line = $typevalue[$i]; + if ($line =~ m/^(\C):\s*(.*)/) { + my $type = $1; + my $value = $2; + if ($type eq 'F') { + if (file_match_pattern($file, $value)) { + 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; + } } } } } } + $tvi = $end + 1; } - $tvi = $end + 1; - } - - 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 * + 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"); } - $line =~ s/^([A-Z]):/$1:\t/g; - print("$line\n"); + print("\n"); } - print("\n"); } - } - - if ($email && - ($email_git || ($email_git_fallback && !$exact_pattern_match))) { - vcs_file_signoffs($file); - } - if ($email && $email_git_blame) { - vcs_file_blame($file); - } - if ($email && $interactive){ - vcs_file_shortlogs($file); + if ($email && ($email_git || + ($email_git_fallback && !$exact_pattern_match))) { + vcs_file_signoffs($file); + } + if ($email && $email_git_blame) { + vcs_file_blame($file); + } } -} -if ($keywords) { - @keyword_tvi = sort_and_uniq(@keyword_tvi); - foreach my $line (@keyword_tvi) { - add_categories($line); + 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) { + foreach my $chief (@penguin_chief) { + if ($chief =~ m/^(.*):(.*)/) { + my $email_address; - $email_address = format_email($1, $2, $email_usename); - if ($email_git_penguin_chiefs) { - push(@email_to, [$email_address, 'chief penguin']); - } else { - @email_to = grep($_->[0] !~ /${email_address}/, @email_to); + $email_address = format_email($1, $2, $email_usename); + if ($email_git_penguin_chiefs) { + push(@email_to, [$email_address, 'chief penguin']); + } else { + @email_to = grep($_->[0] !~ /${email_address}/, @email_to); + } } } - } - foreach my $email (@file_emails) { - my ($name, $address) = parse_email($email); + foreach my $email (@file_emails) { + my ($name, $address) = parse_email($email); - my $tmp_email = format_email($name, $address, $email_usename); - push_email_address($tmp_email, ''); - add_role($tmp_email, 'in file'); + my $tmp_email = format_email($name, $address, $email_usename); + push_email_address($tmp_email, ''); + add_role($tmp_email, 'in file'); + } } -} - -if ($email || $email_list) { my @to = (); - if ($email) { - if ($interactive) { - @email_to = @{vcs_interactive_menu(\@email_to)}; + if ($email || $email_list) { + if ($email) { + @to = (@to, @email_to); + } + if ($email_list) { + @to = (@to, @list_to); } - @to = (@to, @email_to); - } - if ($email_list) { - @to = (@to, @list_to); } - output(merge_email(@to)); -} -if ($scm) { - @scm = uniq(@scm); - output(@scm); -} -if ($status) { - @status = uniq(@status); - output(@status); -} + @to = interactive_get_maintainer(\@to) if ($interactive); -if ($subsystem) { - @subsystem = uniq(@subsystem); - output(@subsystem); + return @to; } -if ($web) { - @web = uniq(@web); - output(@web); -} - -exit($exit); - sub file_match_pattern { my ($file, $pattern) = @_; if (substr($pattern, -1) eq "/") { @@ -561,7 +613,7 @@ MAINTAINER field selection options: --email => print email address(es) if any --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) + or use only ${signature_pattern} 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: $email_git_min_signatures) @@ -847,11 +899,19 @@ sub add_categories { } if ($list_additional =~ m/subscribers-only/) { if ($email_subscriber_list) { - push(@list_to, [$list_address, "subscriber list${list_role}"]); + if (!$hash_list_to{$list_address}) { + $hash_list_to{$list_address} = 1; + push(@list_to, [$list_address, + "subscriber list${list_role}"]); + } } } else { if ($email_list) { - push(@list_to, [$list_address, "open list${list_role}"]); + if (!$hash_list_to{$list_address}) { + $hash_list_to{$list_address} = 1; + push(@list_to, [$list_address, + "open list${list_role}"]); + } } } } elsif ($ptype eq "M") { @@ -882,9 +942,6 @@ sub add_categories { } } -my %email_hash_name; -my %email_hash_address; - sub email_inuse { my ($name, $address) = @_; @@ -1037,10 +1094,31 @@ sub hg_execute_cmd { return @lines; } +sub extract_formatted_signatures { + my (@signature_lines) = @_; + + my @type = @signature_lines; + + s/\s*(.*):.*/$1/ for (@type); + + # cut -f2- -d":" + s/\s*.*:\s*(.+)\s*/$1/ for (@signature_lines); + +## Reformat email addresses (with names) to avoid badly written signatures + + foreach my $signer (@signature_lines) { + my ($name, $address) = parse_email($signer); + $signer = format_email($name, $address, 1); + } + + return (\@type, \@signature_lines); +} + sub vcs_find_signers { my ($cmd) = @_; - my @lines = (); my $commits; + my @lines = (); + my @signatures = (); @lines = &{$VCS_cmds{"execute_cmd"}}($cmd); @@ -1048,24 +1126,20 @@ sub vcs_find_signers { $commits = grep(/$pattern/, @lines); # of commits - @lines = grep(/^[ \t]*${signaturePattern}.*\@.*$/, @lines); - if (!$email_git_penguin_chiefs) { - @lines = grep(!/${penguin_chiefs}/i, @lines); - } + @signatures = grep(/^[ \t]*${signature_pattern}.*\@.*$/, @lines); - return (0, @lines) if !@lines; + return (0, @signatures) if !@signatures; - # cut -f2- -d":" - s/.*:\s*(.+)\s*/$1/ for (@lines); + save_commits_by_author(@lines) if ($interactive); + save_commits_by_signer(@lines) if ($interactive); -## Reformat email addresses (with names) to avoid badly written signatures - - foreach my $line (@lines) { - my ($name, $address) = parse_email($line); - $line = format_email($name, $address, 1); + if (!$email_git_penguin_chiefs) { + @signatures = grep(!/${penguin_chiefs}/i, @signatures); } - return ($commits, @lines); + my ($types_ref, $signers_ref) = extract_formatted_signatures(@signatures); + + return ($commits, @$signers_ref); } sub vcs_find_author { @@ -1080,14 +1154,20 @@ sub vcs_find_author { return @lines if !@lines; -## Reformat email addresses (with names) to avoid badly written signatures - + my @authors = (); foreach my $line (@lines) { - my ($name, $address) = parse_email($line); - $line = format_email($name, $address, 1); + if ($line =~ m/$VCS_cmds{"author_pattern"}/) { + my $author = $1; + my ($name, $address) = parse_email($author); + $author = format_email($name, $address, 1); + push(@authors, $author); + } } - return @lines; + save_commits_by_author(@lines) if ($interactive); + save_commits_by_signer(@lines) if ($interactive); + + return @authors; } sub vcs_save_commits { @@ -1159,7 +1239,7 @@ 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"}; + return 2 if eval $VCS_cmds{"available"}; %VCS_cmds = (); if (!$printed_novcs) { warn("$P: No supported VCS found. Add --nogit to options?\n"); @@ -1171,125 +1251,309 @@ sub vcs_exists { return 0; } -sub vcs_interactive_menu { - my $list_ref = shift; +sub vcs_is_git { + return $vcs_used == 1; +} + +sub vcs_is_hg { + return $vcs_used == 2; +} + +sub interactive_get_maintainer { + my ($list_ref) = @_; my @list = @$list_ref; - return if (!vcs_exists()); + vcs_exists(); my %selected; - my %shortlog; - my $input; + my %authored; + my %signed; my $count = 0; #select maintainers by default foreach my $entry (@list){ - my $role = $entry->[1]; - $selected{$count} = ($role =~ /maintainer:|supporter:/); - $count++; + my $role = $entry->[1]; + $selected{$count} = ($role =~ /^(maintainer|supporter|open list)/); + $authored{$count} = 0; + $signed{$count} = 0; + $count++; } #menu loop - do { - my $count = 0; - foreach my $entry (@list){ - my $email = $entry->[0]; - my $role = $entry->[1]; - if ($selected{$count}){ - print STDERR "* "; - } else { - print STDERR " "; - } - print STDERR "$count: $email,\t\t $role"; - print STDERR "\n"; - if ($shortlog{$count}){ - my $entries_ref = vcs_get_shortlog($email); - foreach my $entry_ref (@{$entries_ref}){ - my $filename = @{$entry_ref}[0]; - my @shortlog = @{@{$entry_ref}[1]}; - print STDERR "\tshortlog for $filename (authored commits: " . @shortlog . ").\n"; - foreach my $commit (@shortlog){ - print STDERR "\t $commit\n"; + my $done = 0; + my $print_options = 0; + my $redraw = 1; + while (!$done) { + $count = 0; + if ($redraw) { + printf STDERR "\n%1s %2s %-65sauth sign\n", + "*", "#", "email/list and role:stats"; + foreach my $entry (@list) { + my $email = $entry->[0]; + my $role = $entry->[1]; + my $sel = ""; + $sel = "*" if ($selected{$count}); + my $commit_author = $commit_author_hash{$email}; + my $commit_signer = $commit_signer_hash{$email}; + my $authored = 0; + my $signed = 0; + $authored++ for (@{$commit_author}); + $signed++ for (@{$commit_signer}); + printf STDERR "%1s %2d %-65s", $sel, $count + 1, $email; + printf STDERR "%4d %4d", $authored, $signed + if ($authored > 0 || $signed > 0); + printf STDERR "\n %s\n", $role; + if ($authored{$count}) { + my $commit_author = $commit_author_hash{$email}; + foreach my $ref (@{$commit_author}) { + print STDERR " Author: @{$ref}[1]\n"; } - print STDERR "\n"; } + if ($signed{$count}) { + my $commit_signer = $commit_signer_hash{$email}; + foreach my $ref (@{$commit_signer}) { + print STDERR " @{$ref}[2]: @{$ref}[1]\n"; + } + } + + $count++; } - $count++; } - print STDERR "\n"; - print STDERR "Choose whom to cc by entering a commaseperated list of numbers and hitting enter.\n"; - print STDERR "To show a short list of commits, precede the number by a '?',\n"; - print STDERR "A blank line indicates that you are satisfied with your choice.\n"; - $input = ; + my $date_ref = \$email_git_since; + $date_ref = \$email_hg_since if (vcs_is_hg()); + if ($print_options) { + $print_options = 0; + if (vcs_exists()) { + print STDERR +"\nVersion Control options:\n" . +"g use git history [$email_git]\n" . +"gf use git-fallback [$email_git_fallback]\n" . +"b use git blame [$email_git_blame]\n" . +"bs use blame signatures [$email_git_blame_signatures]\n" . +"c# minimum commits [$email_git_min_signatures]\n" . +"%# min percent [$email_git_min_percent]\n" . +"d# history to use [$$date_ref]\n" . +"x# max maintainers [$email_git_max_maintainers]\n" . +"t all signature types [$email_git_all_signature_types]\n"; + } + print STDERR "\nAdditional options:\n" . +"0 toggle all\n" . +"f emails in file [$file_emails]\n" . +"k keywords in file [$keywords]\n" . +"r remove duplicates [$email_remove_duplicates]\n" . +"p# pattern match depth [$pattern_depth]\n"; + } + print STDERR +"\n#(toggle), A#(author), S#(signed) *(all), ^(none), O(options), Y(approve): "; + + my $input = ; chomp($input); - my @wish = split(/[, ]+/,$input); - foreach my $nr (@wish){ - my $logtoggle = 0; - if ($nr =~ /\?/){ - $nr =~ s/\?//; - $logtoggle = 1; + $redraw = 1; + my $rerun = 0; + my @wish = split(/[, ]+/, $input); + foreach my $nr (@wish) { + $nr = lc($nr); + my $sel = substr($nr, 0, 1); + my $str = substr($nr, 1); + my $val = 0; + $val = $1 if $str =~ /^(\d+)$/; + + if ($sel eq "y") { + $interactive = 0; + $done = 1; + $output_rolestats = 0; + $output_roles = 0; + last; + } elsif ($nr =~ /^\d+$/ && $nr > 0 && $nr <= $count) { + $selected{$nr - 1} = !$selected{$nr - 1}; + } elsif ($sel eq "*" || $sel eq '^') { + my $toggle = 0; + $toggle = 1 if ($sel eq '*'); + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = $toggle; } - - #skip out of bounds numbers - next unless ($nr <= $count && $nr >= 0); - - if ($logtoggle){ - $shortlog{$nr} = !$shortlog{$nr}; + } elsif ($sel eq "0") { + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = !$selected{$i}; + } + } elsif ($sel eq "a") { + if ($val > 0 && $val <= $count) { + $authored{$val - 1} = !$authored{$val - 1}; + } elsif ($str eq '*' || $str eq '^') { + my $toggle = 0; + $toggle = 1 if ($str eq '*'); + for (my $i = 0; $i < $count; $i++) { + $authored{$i} = $toggle; + } + } + } elsif ($sel eq "s") { + if ($val > 0 && $val <= $count) { + $signed{$val - 1} = !$signed{$val - 1}; + } elsif ($str eq '*' || $str eq '^') { + my $toggle = 0; + $toggle = 1 if ($str eq '*'); + for (my $i = 0; $i < $count; $i++) { + $signed{$i} = $toggle; + } + } + } elsif ($sel eq "o") { + $print_options = 1; + $redraw = 1; + } elsif ($sel eq "g") { + if ($str eq "f") { + bool_invert(\$email_git_fallback); } else { - $selected{$nr} = !$selected{$nr}; - - #switch shortlog on if an entry get's selected - if ($selected{$nr}){ - $shortlog{$nr}=1; - } + bool_invert(\$email_git); + } + $rerun = 1; + } elsif ($sel eq "b") { + if ($str eq "s") { + bool_invert(\$email_git_blame_signatures); + } else { + bool_invert(\$email_git_blame); + } + $rerun = 1; + } elsif ($sel eq "c") { + if ($val > 0) { + $email_git_min_signatures = $val; + $rerun = 1; + } + } elsif ($sel eq "x") { + if ($val > 0) { + $email_git_max_maintainers = $val; + $rerun = 1; + } + } elsif ($sel eq "%") { + if ($str ne "" && $val >= 0) { + $email_git_min_percent = $val; + $rerun = 1; } - }; - } while(length($input) > 0); + } elsif ($sel eq "d") { + if (vcs_is_git()) { + $email_git_since = $str; + } elsif (vcs_is_hg()) { + $email_hg_since = $str; + } + $rerun = 1; + } elsif ($sel eq "t") { + bool_invert(\$email_git_all_signature_types); + $rerun = 1; + } elsif ($sel eq "f") { + bool_invert(\$file_emails); + $rerun = 1; + } elsif ($sel eq "r") { + bool_invert(\$email_remove_duplicates); + $rerun = 1; + } elsif ($sel eq "k") { + bool_invert(\$keywords); + $rerun = 1; + } elsif ($sel eq "p") { + if ($str ne "" && $val >= 0) { + $pattern_depth = $val; + $rerun = 1; + } + } else { + print STDERR "invalid option: '$nr'\n"; + $redraw = 0; + } + } + if ($rerun) { + print STDERR "git-blame can be very slow, please have patience..." + if ($email_git_blame); + goto &get_maintainer; + } + } #drop not selected entries $count = 0; - my @new_emailto; - foreach my $entry (@list){ - if ($selected{$count}){ - push(@new_emailto,$list[$count]); - print STDERR "$count: "; - print STDERR $email_to[$count]->[0]; - print STDERR ",\t\t "; - print STDERR $email_to[$count]->[1]; - print STDERR "\n"; + my @new_emailto = (); + foreach my $entry (@list) { + if ($selected{$count}) { + push(@new_emailto, $list[$count]); } $count++; } - return \@new_emailto; + return @new_emailto; } -sub vcs_get_shortlog { - my $arg = shift; - my ($name, $address) = parse_email($arg); - return $shortlog_buffer{$address}; +sub bool_invert { + my ($bool_ref) = @_; + + if ($$bool_ref) { + $$bool_ref = 0; + } else { + $$bool_ref = 1; + } } -sub vcs_file_shortlogs { - my ($file) = @_; - print STDERR "shortlog processing $file:"; - foreach my $entry (@email_to){ - my ($name, $address) = parse_email($entry->[0]); - print STDERR "."; - my $commits_ref = vcs_email_shortlog($address, $file); - push(@{$shortlog_buffer{$address}}, [ $file, $commits_ref ]); +sub save_commits_by_author { + my (@lines) = @_; + + my @authors = (); + my @commits = (); + my @subjects = (); + + foreach my $line (@lines) { + if ($line =~ m/$VCS_cmds{"author_pattern"}/) { + my $author = $1; + my ($name, $address) = parse_email($author); + $author = format_email($name, $address, 1); + push(@authors, $author); + } + push(@commits, $1) if ($line =~ m/$VCS_cmds{"commit_pattern"}/); + push(@subjects, $1) if ($line =~ m/$VCS_cmds{"subject_pattern"}/); + } + + for (my $i = 0; $i < @authors; $i++) { + my $exists = 0; + foreach my $ref(@{$commit_author_hash{$authors[$i]}}) { + if (@{$ref}[0] eq $commits[$i] && + @{$ref}[1] eq $subjects[$i]) { + $exists = 1; + last; + } + } + if (!$exists) { + push(@{$commit_author_hash{$authors[$i]}}, + [ ($commits[$i], $subjects[$i]) ]); + } } - print STDERR "\n"; } -sub vcs_email_shortlog { - my $email = shift; - my ($file) = @_; +sub save_commits_by_signer { + my (@lines) = @_; + + my $commit = ""; + my $subject = ""; - my $cmd = $VCS_cmds{"shortlog_cmd"}; - $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables - my @lines = &{$VCS_cmds{"execute_cmd"}}($cmd); - return \@lines; + foreach my $line (@lines) { + $commit = $1 if ($line =~ m/$VCS_cmds{"commit_pattern"}/); + $subject = $1 if ($line =~ m/$VCS_cmds{"subject_pattern"}/); + if ($line =~ /^[ \t]*${signature_pattern}.*\@.*$/) { + my @signatures = ($line); + my ($types_ref, $signers_ref) = extract_formatted_signatures(@signatures); + my @types = @$types_ref; + my @signers = @$signers_ref; + + my $type = $types[0]; + my $signer = $signers[0]; + + my $exists = 0; + foreach my $ref(@{$commit_signer_hash{$signer}}) { + if (@{$ref}[0] eq $commit && + @{$ref}[1] eq $subject && + @{$ref}[2] eq $type) { + $exists = 1; + last; + } + } + if (!$exists) { + push(@{$commit_signer_hash{$signer}}, + [ ($commit, $subject, $type) ]); + } + } + } } sub vcs_assign { @@ -1342,7 +1606,8 @@ sub vcs_file_signoffs { my @signers = (); my $commits; - return if (!vcs_exists()); + $vcs_used = vcs_exists(); + return if (!$vcs_used); my $cmd = $VCS_cmds{"find_signers_cmd"}; $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd @@ -1360,37 +1625,93 @@ sub vcs_file_blame { my $total_commits; my $total_lines; - return if (!vcs_exists()); + $vcs_used = vcs_exists(); + return if (!$vcs_used); @all_commits = vcs_blame($file); @commits = uniq(@all_commits); $total_commits = @commits; $total_lines = @all_commits; - foreach my $commit (@commits) { - my $commit_count; - my @commit_signers = (); + if ($email_git_blame_signatures) { + if (vcs_is_hg()) { + my $commit_count; + my @commit_signers = (); + my $commit = join(" -r ", @commits); + my $cmd; - my $cmd = $VCS_cmds{"find_commit_signers_cmd"}; - $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables in $cmd + $cmd = $VCS_cmds{"find_commit_signers_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables in $cmd - ($commit_count, @commit_signers) = vcs_find_signers($cmd); + ($commit_count, @commit_signers) = vcs_find_signers($cmd); - push(@signers, @commit_signers); + push(@signers, @commit_signers); + } else { + foreach my $commit (@commits) { + my $commit_count; + my @commit_signers = (); + my $cmd; + + $cmd = $VCS_cmds{"find_commit_signers_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables in $cmd + + ($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 (vcs_is_hg()) {{ # Double brace for last exit + my $commit_count; + my @commit_signers = (); + @commits = uniq(@commits); + @commits = sort(@commits); + my $commit = join(" -r ", @commits); + my $cmd; + + $cmd = $VCS_cmds{"find_commit_author_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables in $cmd + + my @lines = (); + + @lines = &{$VCS_cmds{"execute_cmd"}}($cmd); + + if (!$email_git_penguin_chiefs) { + @lines = grep(!/${penguin_chiefs}/i, @lines); + } + + last if !@lines; + + my @authors = (); + foreach my $line (@lines) { + if ($line =~ m/$VCS_cmds{"author_pattern"}/) { + my $author = $1; + my ($name, $address) = parse_email($author); + $author = format_email($name, $address, 1); + push(@authors, $1); + } + } + + save_commits_by_author(@lines) if ($interactive); + save_commits_by_signer(@lines) if ($interactive); + + push(@signers, @authors); + }} + else { + 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) { -- cgit v1.2.3-70-g09d2 From 6ef1c52e122b675acc88a8b016d6477f67988b91 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:56 -0700 Subject: scripts/get_maintainer.pl: use case insensitive name de-duplication Case insensitive name and email address matching can help reduce duplication when authors don't always use the exact same signature. o Add a --interactive per-file exact_match hash so git history can be checked on per-file only when there is no direct maintainer o Make @interactive_to list global so save_commits_by_ can check email names & addresses against this list for duplication o Don't allow --interactive and --sections o rename subroutine get_maintainer to get_maintainers o Added help text option to --interactive menu prompt Update version to 0.26-beta4 Signed-off-by: Joe Perches Cc: Florian Mickler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 135 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 101 insertions(+), 34 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index f51176039ff..61d3bb51bdd 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -13,7 +13,7 @@ use strict; my $P = $0; -my $V = '0.26-beta3'; +my $V = '0.26-beta4'; use Getopt::Long qw(:config no_auto_abbrev); @@ -242,6 +242,7 @@ if ($sections) { $subsystem = 0; $web = 0; $keywords = 0; + $interactive = 0; } else { my $selections = $email + $scm + $status + $subsystem + $web; if ($selections == 0) { @@ -407,13 +408,15 @@ my @scm = (); my @web = (); my @subsystem = (); my @status = (); +my @interactive_to = (); my $signature_pattern; -my @to = get_maintainer(); +my @maintainers = get_maintainers(); -@to = merge_email(@to); - -output(@to) if (@to); +if (@maintainers) { + @maintainers = merge_email(@maintainers); + output(@maintainers); +} if ($scm) { @scm = uniq(@scm); @@ -437,7 +440,7 @@ if ($web) { exit($exit); -sub get_maintainer { +sub get_maintainers { %email_hash_name = (); %email_hash_address = (); %commit_author_hash = (); @@ -449,7 +452,7 @@ sub get_maintainer { @web = (); @subsystem = (); @status = (); - + @interactive_to = (); if ($email_git_all_signature_types) { $signature_pattern = "(.+?)[Bb][Yy]:"; } else { @@ -458,10 +461,11 @@ sub get_maintainer { # Find responsible parties + my %exact_pattern_match_hash; + 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); @@ -497,7 +501,9 @@ sub get_maintainer { 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 >= $file_pd); + if ($value_pd >= $file_pd) { + $exact_pattern_match_hash{$file} = 1; + } if ($pattern_depth == 0 || (($file_pd - $value_pd) < $pattern_depth)) { $hash{$tvi} = $value_pd; @@ -530,14 +536,6 @@ sub get_maintainer { print("\n"); } } - - if ($email && ($email_git || - ($email_git_fallback && !$exact_pattern_match))) { - vcs_file_signoffs($file); - } - if ($email && $email_git_blame) { - vcs_file_blame($file); - } } if ($keywords) { @@ -547,6 +545,19 @@ sub get_maintainer { } } + @interactive_to = (@email_to, @list_to); + + foreach my $file (@files) { + if ($email && + ($email_git || ($email_git_fallback && + !$exact_pattern_match_hash{$file}))) { + vcs_file_signoffs($file); + } + if ($email && $email_git_blame) { + vcs_file_blame($file); + } + } + if ($email) { foreach my $chief (@penguin_chief) { if ($chief =~ m/^(.*):(.*)/) { @@ -580,7 +591,10 @@ sub get_maintainer { } } - @to = interactive_get_maintainer(\@to) if ($interactive); + if ($interactive) { + @interactive_to = @to; + @to = interactive_get_maintainers(\@interactive_to); + } return @to; } @@ -899,16 +913,16 @@ sub add_categories { } if ($list_additional =~ m/subscribers-only/) { if ($email_subscriber_list) { - if (!$hash_list_to{$list_address}) { - $hash_list_to{$list_address} = 1; + if (!$hash_list_to{lc($list_address)}) { + $hash_list_to{lc($list_address)} = 1; push(@list_to, [$list_address, "subscriber list${list_role}"]); } } } else { if ($email_list) { - if (!$hash_list_to{$list_address}) { - $hash_list_to{$list_address} = 1; + if (!$hash_list_to{lc($list_address)}) { + $hash_list_to{lc($list_address)} = 1; push(@list_to, [$list_address, "open list${list_role}"]); } @@ -946,8 +960,8 @@ 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{$address})); + return 1 if (($name ne "") && exists($email_hash_name{lc($name)})); + return 1 if (($address ne "") && exists($email_hash_address{lc($address)})); return 0; } @@ -965,8 +979,8 @@ sub push_email_address { push(@email_to, [format_email($name, $address, $email_usename), $role]); } elsif (!email_inuse($name, $address)) { push(@email_to, [format_email($name, $address, $email_usename), $role]); - $email_hash_name{$name}++; - $email_hash_address{$address}++; + $email_hash_name{lc($name)}++; + $email_hash_address{lc($address)}++; } return 1; @@ -1259,7 +1273,7 @@ sub vcs_is_hg { return $vcs_used == 2; } -sub interactive_get_maintainer { +sub interactive_get_maintainers { my ($list_ref) = @_; my @list = @$list_ref; @@ -1269,11 +1283,12 @@ sub interactive_get_maintainer { my %authored; my %signed; my $count = 0; - + my $maintained = 0; #select maintainers by default - foreach my $entry (@list){ + foreach my $entry (@list) { my $role = $entry->[1]; - $selected{$count} = ($role =~ /^(maintainer|supporter|open list)/); + $selected{$count} = ($role =~ /^(maintainer|supporter|open list)/i); + $maintained = 1 if ($role =~ /^(maintainer|supporter)/i); $authored{$count} = 0; $signed{$count} = 0; $count++; @@ -1286,8 +1301,14 @@ sub interactive_get_maintainer { while (!$done) { $count = 0; if ($redraw) { - printf STDERR "\n%1s %2s %-65sauth sign\n", - "*", "#", "email/list and role:stats"; + printf STDERR "\n%1s %2s %-65s", + "*", "#", "email/list and role:stats"; + if ($email_git || + ($email_git_fallback && !$maintained) || + $email_git_blame) { + print STDERR "auth sign"; + } + print STDERR "\n"; foreach my $entry (@list) { my $email = $entry->[0]; my $role = $entry->[1]; @@ -1453,6 +1474,27 @@ sub interactive_get_maintainer { $pattern_depth = $val; $rerun = 1; } + } elsif ($sel eq "h" || $sel eq "?") { + print STDERR <[0]); + if ($email_remove_duplicates && + ((lc($name) eq lc($to_name)) || + (lc($address) eq lc($to_address)))) { + $author = $to->[0]; + $matched = 1; + last; + } + } + $author = format_email($name, $address, 1) if (!$matched); push(@authors, $author); } push(@commits, $1) if ($line =~ m/$VCS_cmds{"commit_pattern"}/); @@ -1539,6 +1592,20 @@ sub save_commits_by_signer { my $type = $types[0]; my $signer = $signers[0]; + my $matched = 0; + my ($name, $address) = parse_email($signer); + foreach my $to (@interactive_to) { + my ($to_name, $to_address) = parse_email($to->[0]); + if ($email_remove_duplicates && + ((lc($name) eq lc($to_name)) || + (lc($address) eq lc($to_address)))) { + $signer = $to->[0]; + $matched = 1; + last; + } + $signer = format_email($name, $address, 1) if (!$matched); + } + my $exists = 0; foreach my $ref(@{$commit_signer_hash{$signer}}) { if (@{$ref}[0] eq $commit && -- cgit v1.2.3-70-g09d2 From 7fa8ff2e0c0f326cdaaa4ae7d00f5d021e43ffa2 Mon Sep 17 00:00:00 2001 From: Florian Mickler Date: Tue, 26 Oct 2010 14:22:56 -0700 Subject: scripts/get_maintainer.pl: fix mailmap handling Implement it, like it is described in git-shortlog. Signed-off-by: Florian Mickler Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 147 ++++++++++++++++++++++++++++++++++------------ 1 file changed, 109 insertions(+), 38 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 61d3bb51bdd..faeace4e1fd 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -295,31 +295,76 @@ while (<$maint>) { } close($maint); -my %mailmap; -if ($email_remove_duplicates) { - open(my $mailmap, '<', "${lk_path}.mailmap") +# +# Read mail address map +# + +my $mailmap = read_mailmap(); + +sub read_mailmap { + my $mailmap = { + names => {}, + addresses => {} + }; + + if (!$email_remove_duplicates) { + return $mailmap; + } + + open(my $mailmap_file, '<', "${lk_path}.mailmap") or warn "$P: Can't open .mailmap: $!\n"; - while (<$mailmap>) { - my $line = $_; - next if ($line =~ m/^\s*#/); - next if ($line =~ m/^\s*$/); + while (<$mailmap_file>) { + s/#.*$//; #strip comments + s/^\s+|\s+$//g; #trim - my ($name, $address) = parse_email($line); - $line = format_email($name, $address, $email_usename); + next if (/^\s*$/); #skip empty lines + #entries have one of the following formats: + # name1 + # + # name1 + # name1 name2 + # (see man git-shortlog) + if (/^(.+)<(.+)>$/) { + my $real_name = $1; + my $address = $2; - next if ($line =~ m/^\s*$/); + $real_name =~ s/\s+$//; + $mailmap->{names}->{$address} = $real_name; - if (exists($mailmap{$name})) { - my $obj = $mailmap{$name}; - push(@$obj, $address); - } else { - my @arr = ($address); - $mailmap{$name} = \@arr; + } elsif (/^<([^\s]+)>\s*<([^\s]+)>$/) { + my $real_address = $1; + my $wrong_address = $2; + + $mailmap->{addresses}->{$wrong_address} = $real_address; + + } elsif (/^(.+)<([^\s]+)>\s*<([^\s]+)>$/) { + my $real_name= $1; + my $real_address = $2; + my $wrong_address = $3; + + $real_name =~ s/\s+$//; + + $mailmap->{names}->{$wrong_address} = $real_name; + $mailmap->{addresses}->{$wrong_address} = $real_address; + + } elsif (/^(.+)<([^\s]+)>\s*([^\s].*)<([^\s]+)>$/) { + my $real_name = $1; + my $real_address = $2; + my $wrong_name = $3; + my $wrong_address = $4; + + $real_name =~ s/\s+$//; + $wrong_name =~ s/\s+$//; + + $mailmap->{names}->{format_email($wrong_name,$wrong_address,1)} = $real_name; + $mailmap->{addresses}->{format_email($wrong_name,$wrong_address,1)} = $real_address; } } - close($mailmap); + close($mailmap_file); + + return $mailmap; } ## use the filenames on the command line or find the filenames in the patchfiles @@ -1061,30 +1106,58 @@ sub which_conf { return ""; } -sub mailmap { - my (@lines) = @_; - my %hash; +sub mailmap_email { + my $line = shift; - 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, $email_usename); - } - if (exists($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}, $email_usename); + my $email = format_email($name, $address, 1); + my $real_name = $name; + my $real_address = $address; + + if (exists $mailmap->{names}->{$email} || exists $mailmap->{addresses}->{$email}) { + if (exists $mailmap->{names}->{$email}) { + $real_name = $mailmap->{names}->{$email}; + } + if (exists $mailmap->{addresses}->{$email}) { + $real_address = $mailmap->{addresses}->{$email}; + } + } else { + if (exists $mailmap->{names}->{$address}) { + $real_name = $mailmap->{names}->{$address}; + } + if (exists $mailmap->{addresses}->{$address}) { + $real_address = $mailmap->{addresses}->{$address}; } - } } + return format_email($real_name, $real_address, 1); +} + +sub mailmap { + my (@addresses) = @_; + + my @ret = (); + foreach my $line (@addresses) { + push(@ret, mailmap_email($line), 1); } - return @lines; + merge_by_realname(@ret) if $email_remove_duplicates; + + return @ret; +} + +sub merge_by_realname { + my %address_map; + my (@emails) = @_; + foreach my $email (@emails) { + my ($name, $address) = parse_email($email); + if (!exists $address_map{$name}) { + $address_map{$name} = $address; + } else { + $address = $address_map{$name}; + $email = format_email($name,$address,1); + } + } + } sub git_execute_cmd { @@ -1636,9 +1709,7 @@ sub vcs_assign { $divisor = 1; } - if ($email_remove_duplicates) { - @lines = mailmap(@lines); - } + @lines = mailmap(@lines); return if (@lines <= 0); -- cgit v1.2.3-70-g09d2 From 47abc7225761faf28be52b3ac4dc26ffeac7b750 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:57 -0700 Subject: scripts/get_maintainer.pl: correct indentation in a few places And a miscellaneous conversion of You to you in a help message Signed-off-by: Joe Perches Cc: Florian Mickler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 156 +++++++++++++++++++++++----------------------- 1 file changed, 78 insertions(+), 78 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index faeace4e1fd..0abfdbc5cdf 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -306,7 +306,7 @@ sub read_mailmap { my $mailmap = { names => {}, addresses => {} - }; + }; if (!$email_remove_duplicates) { return $mailmap; @@ -327,39 +327,39 @@ sub read_mailmap { # name1 name2 # (see man git-shortlog) if (/^(.+)<(.+)>$/) { - my $real_name = $1; - my $address = $2; + my $real_name = $1; + my $address = $2; - $real_name =~ s/\s+$//; - $mailmap->{names}->{$address} = $real_name; + $real_name =~ s/\s+$//; + $mailmap->{names}->{$address} = $real_name; } elsif (/^<([^\s]+)>\s*<([^\s]+)>$/) { - my $real_address = $1; - my $wrong_address = $2; + my $real_address = $1; + my $wrong_address = $2; - $mailmap->{addresses}->{$wrong_address} = $real_address; + $mailmap->{addresses}->{$wrong_address} = $real_address; } elsif (/^(.+)<([^\s]+)>\s*<([^\s]+)>$/) { - my $real_name= $1; - my $real_address = $2; - my $wrong_address = $3; + my $real_name= $1; + my $real_address = $2; + my $wrong_address = $3; - $real_name =~ s/\s+$//; + $real_name =~ s/\s+$//; - $mailmap->{names}->{$wrong_address} = $real_name; - $mailmap->{addresses}->{$wrong_address} = $real_address; + $mailmap->{names}->{$wrong_address} = $real_name; + $mailmap->{addresses}->{$wrong_address} = $real_address; } elsif (/^(.+)<([^\s]+)>\s*([^\s].*)<([^\s]+)>$/) { - my $real_name = $1; - my $real_address = $2; - my $wrong_name = $3; - my $wrong_address = $4; + my $real_name = $1; + my $real_address = $2; + my $wrong_name = $3; + my $wrong_address = $4; - $real_name =~ s/\s+$//; - $wrong_name =~ s/\s+$//; + $real_name =~ s/\s+$//; + $wrong_name =~ s/\s+$//; - $mailmap->{names}->{format_email($wrong_name,$wrong_address,1)} = $real_name; - $mailmap->{addresses}->{format_email($wrong_name,$wrong_address,1)} = $real_address; + $mailmap->{names}->{format_email($wrong_name,$wrong_address,1)} = $real_name; + $mailmap->{addresses}->{format_email($wrong_name,$wrong_address,1)} = $real_address; } } close($mailmap_file); @@ -743,30 +743,30 @@ EOT } sub top_of_kernel_tree { - my ($lk_path) = @_; + my ($lk_path) = @_; - if ($lk_path ne "" && substr($lk_path,length($lk_path)-1,1) ne "/") { - $lk_path .= "/"; - } - if ( (-f "${lk_path}COPYING") - && (-f "${lk_path}CREDITS") - && (-f "${lk_path}Kbuild") - && (-f "${lk_path}MAINTAINERS") - && (-f "${lk_path}Makefile") - && (-f "${lk_path}README") - && (-d "${lk_path}Documentation") - && (-d "${lk_path}arch") - && (-d "${lk_path}include") - && (-d "${lk_path}drivers") - && (-d "${lk_path}fs") - && (-d "${lk_path}init") - && (-d "${lk_path}ipc") - && (-d "${lk_path}kernel") - && (-d "${lk_path}lib") - && (-d "${lk_path}scripts")) { - return 1; - } - return 0; + if ($lk_path ne "" && substr($lk_path,length($lk_path)-1,1) ne "/") { + $lk_path .= "/"; + } + if ( (-f "${lk_path}COPYING") + && (-f "${lk_path}CREDITS") + && (-f "${lk_path}Kbuild") + && (-f "${lk_path}MAINTAINERS") + && (-f "${lk_path}Makefile") + && (-f "${lk_path}README") + && (-d "${lk_path}Documentation") + && (-d "${lk_path}arch") + && (-d "${lk_path}include") + && (-d "${lk_path}drivers") + && (-d "${lk_path}fs") + && (-d "${lk_path}init") + && (-d "${lk_path}ipc") + && (-d "${lk_path}kernel") + && (-d "${lk_path}lib") + && (-d "${lk_path}scripts")) { + return 1; + } + return 0; } sub parse_email { @@ -1107,29 +1107,30 @@ sub which_conf { } sub mailmap_email { - my $line = shift; + my $line = shift; - my ($name, $address) = parse_email($line); - my $email = format_email($name, $address, 1); - my $real_name = $name; - my $real_address = $address; - - if (exists $mailmap->{names}->{$email} || exists $mailmap->{addresses}->{$email}) { - if (exists $mailmap->{names}->{$email}) { - $real_name = $mailmap->{names}->{$email}; - } - if (exists $mailmap->{addresses}->{$email}) { - $real_address = $mailmap->{addresses}->{$email}; - } - } else { - if (exists $mailmap->{names}->{$address}) { - $real_name = $mailmap->{names}->{$address}; - } - if (exists $mailmap->{addresses}->{$address}) { - $real_address = $mailmap->{addresses}->{$address}; - } + my ($name, $address) = parse_email($line); + my $email = format_email($name, $address, 1); + my $real_name = $name; + my $real_address = $address; + + if (exists $mailmap->{names}->{$email} || + exists $mailmap->{addresses}->{$email}) { + if (exists $mailmap->{names}->{$email}) { + $real_name = $mailmap->{names}->{$email}; + } + if (exists $mailmap->{addresses}->{$email}) { + $real_address = $mailmap->{addresses}->{$email}; + } + } else { + if (exists $mailmap->{names}->{$address}) { + $real_name = $mailmap->{names}->{$address}; + } + if (exists $mailmap->{addresses}->{$address}) { + $real_address = $mailmap->{addresses}->{$address}; } - return format_email($real_name, $real_address, 1); + } + return format_email($real_name, $real_address, 1); } sub mailmap { @@ -1146,18 +1147,17 @@ sub mailmap { } sub merge_by_realname { - my %address_map; - my (@emails) = @_; - foreach my $email (@emails) { - my ($name, $address) = parse_email($email); - if (!exists $address_map{$name}) { - $address_map{$name} = $address; - } else { - $address = $address_map{$name}; - $email = format_email($name,$address,1); - } + my %address_map; + my (@emails) = @_; + foreach my $email (@emails) { + my ($name, $address) = parse_email($email); + if (!exists $address_map{$name}) { + $address_map{$name} = $address; + } else { + $address = $address_map{$name}; + $email = format_email($name,$address,1); } - + } } sub git_execute_cmd { @@ -1555,7 +1555,7 @@ commit signers and mailing lists that could be CC'd on a patch. Any *'d entry is selected. -If you have git or hg installed, You can choose to summarize the commit +If you have git or hg installed, you can choose to summarize the commit history of files in the patch. Also, each line of the current file can be matched to its commit author and that commits signers with blame. -- cgit v1.2.3-70-g09d2 From b9e2331dd1e0e04f7f2a6f8aa0c05bac2a7f0d7b Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:58 -0700 Subject: scripts/get_maintainer.pl: use mailmap in name deduplication and other updates Use Florian Mickler's mailmap routine to reduce name duplication. o Add subroutine deduplicate_email to centralize code o Add hashes for deduplicate_(name|address)_hash o Remove now unused @interactive_to o Whitespace neatening o Add command line --help text o Add --mailmap command line option control o Interactive changes: - Add toggles for maintainer, git and list selections - Default selection is all - Add mailmap control Update to 0.26-beta5 Signed-off-by: Joe Perches Cc: Florian Mickler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 232 +++++++++++++++++++++++++++++----------------- 1 file changed, 148 insertions(+), 84 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 0abfdbc5cdf..e822518bc61 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -13,7 +13,7 @@ use strict; my $P = $0; -my $V = '0.26-beta4'; +my $V = '0.26-beta5'; use Getopt::Long qw(:config no_auto_abbrev); @@ -36,6 +36,7 @@ my $email_git_since = "1-year-ago"; my $email_hg_since = "-365"; my $interactive = 0; my $email_remove_duplicates = 1; +my $email_use_mailmap = 1; my $output_multiline = 1; my $output_separator = ", "; my $output_roles = 0; @@ -192,6 +193,7 @@ if (!GetOptions( 'hg-since=s' => \$email_hg_since, 'i|interactive!' => \$interactive, 'remove-duplicates!' => \$email_remove_duplicates, + 'mailmap!' => \$email_use_mailmap, 'm!' => \$email_maintainer, 'n!' => \$email_usename, 'l!' => \$email_list, @@ -300,17 +302,17 @@ close($maint); # Read mail address map # -my $mailmap = read_mailmap(); +my $mailmap; + +read_mailmap(); sub read_mailmap { - my $mailmap = { + $mailmap = { names => {}, addresses => {} }; - if (!$email_remove_duplicates) { - return $mailmap; - } + return if (!$email_use_mailmap || !(-f "${lk_path}.mailmap")); open(my $mailmap_file, '<', "${lk_path}.mailmap") or warn "$P: Can't open .mailmap: $!\n"; @@ -331,6 +333,7 @@ sub read_mailmap { my $address = $2; $real_name =~ s/\s+$//; + ($real_name, $address) = parse_email("$real_name <$address>"); $mailmap->{names}->{$address} = $real_name; } elsif (/^<([^\s]+)>\s*<([^\s]+)>$/) { @@ -340,12 +343,13 @@ sub read_mailmap { $mailmap->{addresses}->{$wrong_address} = $real_address; } elsif (/^(.+)<([^\s]+)>\s*<([^\s]+)>$/) { - my $real_name= $1; + my $real_name = $1; my $real_address = $2; my $wrong_address = $3; $real_name =~ s/\s+$//; - + ($real_name, $real_address) = + parse_email("$real_name <$real_address>"); $mailmap->{names}->{$wrong_address} = $real_name; $mailmap->{addresses}->{$wrong_address} = $real_address; @@ -356,15 +360,19 @@ sub read_mailmap { my $wrong_address = $4; $real_name =~ s/\s+$//; + ($real_name, $real_address) = + parse_email("$real_name <$real_address>"); + $wrong_name =~ s/\s+$//; + ($wrong_name, $wrong_address) = + parse_email("$wrong_name <$wrong_address>"); - $mailmap->{names}->{format_email($wrong_name,$wrong_address,1)} = $real_name; - $mailmap->{addresses}->{format_email($wrong_name,$wrong_address,1)} = $real_address; + my $wrong_email = format_email($wrong_name, $wrong_address, 1); + $mailmap->{names}->{$wrong_email} = $real_name; + $mailmap->{addresses}->{$wrong_email} = $real_address; } } close($mailmap_file); - - return $mailmap; } ## use the filenames on the command line or find the filenames in the patchfiles @@ -453,7 +461,8 @@ my @scm = (); my @web = (); my @subsystem = (); my @status = (); -my @interactive_to = (); +my %deduplicate_name_hash = (); +my %deduplicate_address_hash = (); my $signature_pattern; my @maintainers = get_maintainers(); @@ -497,7 +506,8 @@ sub get_maintainers { @web = (); @subsystem = (); @status = (); - @interactive_to = (); + %deduplicate_name_hash = (); + %deduplicate_address_hash = (); if ($email_git_all_signature_types) { $signature_pattern = "(.+?)[Bb][Yy]:"; } else { @@ -506,7 +516,7 @@ sub get_maintainers { # Find responsible parties - my %exact_pattern_match_hash; + my %exact_pattern_match_hash = (); foreach my $file (@files) { @@ -590,7 +600,9 @@ sub get_maintainers { } } - @interactive_to = (@email_to, @list_to); + foreach my $email (@email_to, @list_to) { + $email->[0] = deduplicate_email($email->[0]); + } foreach my $file (@files) { if ($email && @@ -637,8 +649,7 @@ sub get_maintainers { } if ($interactive) { - @interactive_to = @to; - @to = interactive_get_maintainers(\@interactive_to); + @to = interactive_get_maintainers(\@to); } return @to; @@ -702,8 +713,9 @@ Output type options: Other options: --pattern-depth => Number of pattern directory traversals (default: 0 (all)) - --keywords => scan patch for keywords (default: 1 (on)) - --sections => print the entire subsystem sections with pattern matches + --keywords => scan patch for keywords (default: $keywords) + --sections => print all of the subsystem sections with pattern matches + --mailmap => use .mailmap file (default: $email_use_mailmap) --version => show version --help => show this help information @@ -1107,7 +1119,7 @@ sub which_conf { } sub mailmap_email { - my $line = shift; + my ($line) = @_; my ($name, $address) = parse_email($line); my $email = format_email($name, $address, 1); @@ -1136,26 +1148,25 @@ sub mailmap_email { sub mailmap { my (@addresses) = @_; - my @ret = (); + my @mapped_emails = (); foreach my $line (@addresses) { - push(@ret, mailmap_email($line), 1); + push(@mapped_emails, mailmap_email($line)); } - - merge_by_realname(@ret) if $email_remove_duplicates; - - return @ret; + merge_by_realname(@mapped_emails) if ($email_use_mailmap); + return @mapped_emails; } sub merge_by_realname { my %address_map; my (@emails) = @_; + foreach my $email (@emails) { my ($name, $address) = parse_email($email); - if (!exists $address_map{$name}) { - $address_map{$name} = $address; - } else { + if (exists $address_map{$name}) { $address = $address_map{$name}; - $email = format_email($name,$address,1); + $email = format_email($name, $address, 1); + } else { + $address_map{$name} = $address; } } } @@ -1194,8 +1205,7 @@ sub extract_formatted_signatures { ## Reformat email addresses (with names) to avoid badly written signatures foreach my $signer (@signature_lines) { - my ($name, $address) = parse_email($signer); - $signer = format_email($name, $address, 1); + $signer = deduplicate_email($signer); } return (\@type, \@signature_lines); @@ -1339,6 +1349,7 @@ sub vcs_exists { } sub vcs_is_git { + vcs_exists(); return $vcs_used == 1; } @@ -1357,11 +1368,9 @@ sub interactive_get_maintainers { my %signed; my $count = 0; my $maintained = 0; - #select maintainers by default foreach my $entry (@list) { - my $role = $entry->[1]; - $selected{$count} = ($role =~ /^(maintainer|supporter|open list)/i); - $maintained = 1 if ($role =~ /^(maintainer|supporter)/i); + $maintained = 1 if ($entry->[1] =~ /^(maintainer|supporter)/i); + $selected{$count} = 1; $authored{$count} = 0; $signed{$count} = 0; $count++; @@ -1418,24 +1427,34 @@ sub interactive_get_maintainers { if ($print_options) { $print_options = 0; if (vcs_exists()) { - print STDERR -"\nVersion Control options:\n" . -"g use git history [$email_git]\n" . -"gf use git-fallback [$email_git_fallback]\n" . -"b use git blame [$email_git_blame]\n" . -"bs use blame signatures [$email_git_blame_signatures]\n" . -"c# minimum commits [$email_git_min_signatures]\n" . -"%# min percent [$email_git_min_percent]\n" . -"d# history to use [$$date_ref]\n" . -"x# max maintainers [$email_git_max_maintainers]\n" . -"t all signature types [$email_git_all_signature_types]\n"; + print STDERR <[1] =~ /^(maintainer|supporter)/i); + } + } elsif (lc($str) eq "g") { + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = !$selected{$i} + if ($list[$i]->[1] =~ /^(author|commit|signer)/i); + } + } elsif (lc($str) eq "l") { + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = !$selected{$i} + if ($list[$i]->[1] =~ /^(open list)/i); + } + } elsif (lc($str) eq "s") { + for (my $i = 0; $i < $count; $i++) { + $selected{$i} = !$selected{$i} + if ($list[$i]->[1] =~ /^(subscriber list)/i); + } + } } elsif ($sel eq "a") { if ($val > 0 && $val <= $count) { $authored{$val - 1} = !$authored{$val - 1}; @@ -1539,6 +1580,10 @@ sub interactive_get_maintainers { } elsif ($sel eq "r") { bool_invert(\$email_remove_duplicates); $rerun = 1; + } elsif ($sel eq "m") { + bool_invert(\$email_use_mailmap); + read_mailmap(); + $rerun = 1; } elsif ($sel eq "k") { bool_invert(\$keywords); $rerun = 1; @@ -1602,6 +1647,36 @@ sub bool_invert { } } +sub deduplicate_email { + my ($email) = @_; + + my $matched = 0; + my ($name, $address) = parse_email($email); + $email = format_email($name, $address, 1); + $email = mailmap_email($email); + + return $email if (!$email_remove_duplicates); + + ($name, $address) = parse_email($email); + + if ($deduplicate_name_hash{lc($name)}) { + $name = $deduplicate_name_hash{lc($name)}->[0]; + $address = $deduplicate_name_hash{lc($name)}->[1]; + $matched = 1; + } elsif ($deduplicate_address_hash{lc($address)}) { + $name = $deduplicate_address_hash{lc($address)}->[0]; + $address = $deduplicate_address_hash{lc($address)}->[1]; + $matched = 1; + } + if (!$matched) { + $deduplicate_name_hash{lc($name)} = [ $name, $address ]; + $deduplicate_address_hash{lc($address)} = [ $name, $address ]; + } + $email = format_email($name, $address, 1); + $email = mailmap_email($email); + return $email; +} + sub save_commits_by_author { my (@lines) = @_; @@ -1611,20 +1686,8 @@ sub save_commits_by_author { foreach my $line (@lines) { if ($line =~ m/$VCS_cmds{"author_pattern"}/) { - my $matched = 0; my $author = $1; - my ($name, $address) = parse_email($author); - foreach my $to (@interactive_to) { - my ($to_name, $to_address) = parse_email($to->[0]); - if ($email_remove_duplicates && - ((lc($name) eq lc($to_name)) || - (lc($address) eq lc($to_address)))) { - $author = $to->[0]; - $matched = 1; - last; - } - } - $author = format_email($name, $address, 1) if (!$matched); + $author = deduplicate_email($author); push(@authors, $author); } push(@commits, $1) if ($line =~ m/$VCS_cmds{"commit_pattern"}/); @@ -1665,19 +1728,7 @@ sub save_commits_by_signer { my $type = $types[0]; my $signer = $signers[0]; - my $matched = 0; - my ($name, $address) = parse_email($signer); - foreach my $to (@interactive_to) { - my ($to_name, $to_address) = parse_email($to->[0]); - if ($email_remove_duplicates && - ((lc($name) eq lc($to_name)) || - (lc($address) eq lc($to_address)))) { - $signer = $to->[0]; - $matched = 1; - last; - } - $signer = format_email($name, $address, 1) if (!$matched); - } + $signer = deduplicate_email($signer); my $exists = 0; foreach my $ref(@{$commit_signer_hash{$signer}}) { @@ -1751,6 +1802,11 @@ sub vcs_file_signoffs { $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd ($commits, @signers) = vcs_find_signers($cmd); + + foreach my $signer (@signers) { + $signer = deduplicate_email($signer); + } + vcs_assign("commit_signer", $commits, @signers); } @@ -1828,9 +1884,8 @@ sub vcs_file_blame { foreach my $line (@lines) { if ($line =~ m/$VCS_cmds{"author_pattern"}/) { my $author = $1; - my ($name, $address) = parse_email($author); - $author = format_email($name, $address, 1); - push(@authors, $1); + $author = deduplicate_email($author); + push(@authors, $author); } } @@ -1846,9 +1901,12 @@ sub vcs_file_blame { $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd my @author = vcs_find_author($cmd); next if !@author; + + my $formatted_author = deduplicate_email($author[0]); + my $count = grep(/$commit/, @all_commits); for ($i = 0; $i < $count ; $i++) { - push(@blame_signers, $author[0]); + push(@blame_signers, $formatted_author); } } } @@ -1856,8 +1914,14 @@ sub vcs_file_blame { vcs_assign("authored lines", $total_lines, @blame_signers); } } + foreach my $signer (@signers) { + $signer = deduplicate_email($signer); + } vcs_assign("commits", $total_commits, @signers); } else { + foreach my $signer (@signers) { + $signer = deduplicate_email($signer); + } vcs_assign("modified commits", $total_commits, @signers); } } -- cgit v1.2.3-70-g09d2 From fae99206769b6bbf8a20ab883726b164945771d7 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 26 Oct 2010 14:22:58 -0700 Subject: scripts/get_maintainer.pl: don't deduplicate unnamed addresses ie: mailing lists Fix a defect with the first mailing list address being used for each subsequent mailing list. Updated to 0.26-beta6. Signed-off-by: Joe Perches Cc: Florian Mickler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/get_maintainer.pl | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'scripts/get_maintainer.pl') diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index e822518bc61..d21ec3a8960 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -13,7 +13,7 @@ use strict; my $P = $0; -my $V = '0.26-beta5'; +my $V = '0.26-beta6'; use Getopt::Long qw(:config no_auto_abbrev); @@ -1036,7 +1036,7 @@ sub push_email_address { push(@email_to, [format_email($name, $address, $email_usename), $role]); } elsif (!email_inuse($name, $address)) { push(@email_to, [format_email($name, $address, $email_usename), $role]); - $email_hash_name{lc($name)}++; + $email_hash_name{lc($name)}++ if ($name ne ""); $email_hash_address{lc($address)}++; } @@ -1659,7 +1659,7 @@ sub deduplicate_email { ($name, $address) = parse_email($email); - if ($deduplicate_name_hash{lc($name)}) { + if ($name ne "" && $deduplicate_name_hash{lc($name)}) { $name = $deduplicate_name_hash{lc($name)}->[0]; $address = $deduplicate_name_hash{lc($name)}->[1]; $matched = 1; -- cgit v1.2.3-70-g09d2