X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=scripts%2Fget_maintainer.pl;h=090f2483970038e074d7be9593d635a6f1303e6a;hb=86d08e569f63a71a2d259507e335beea32b4d2aa;hp=278a45bd45a5ea705b3d5bdb36e72a52b41ac08c;hpb=3d202aeb7b7b33d5a5b2040ee5af5b309782941c;p=safe%2Fjmp%2Flinux-2.6 diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 278a45b..090f248 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 = '0.17'; +my $V = '0.23'; use Getopt::Long qw(:config no_auto_abbrev); @@ -23,19 +23,26 @@ my $email_usename = 1; my $email_maintainer = 1; my $email_list = 1; my $email_subscriber_list = 0; -my $email_git = 1; my $email_git_penguin_chiefs = 0; +my $email_git = 1; +my $email_git_blame = 0; my $email_git_min_signatures = 1; my $email_git_max_maintainers = 5; my $email_git_min_percent = 5; my $email_git_since = "1-year-ago"; +my $email_hg_since = "-365"; +my $email_remove_duplicates = 1; my $output_multiline = 1; my $output_separator = ", "; +my $output_roles = 0; +my $output_rolestats = 0; my $scm = 0; my $web = 0; my $subsystem = 0; my $status = 0; +my $keywords = 1; my $from_filename = 0; +my $pattern_depth = 0; my $version = 0; my $help = 0; @@ -60,30 +67,64 @@ my $penguin_chiefs = "\(" . join("|",@penguin_chief_names) . "\)"; my $rfc822_lwsp = "(?:(?:\\r\\n)?[ \\t])"; my $rfc822_char = '[\\000-\\377]'; +# VCS command support: class-like functions and strings + +my %VCS_cmds; + +my %VCS_cmds_git = ( + "execute_cmd" => \&git_execute_cmd, + "available" => '(which("git") ne "") && (-d ".git")', + "find_signers_cmd" => "git log --since=\$email_git_since -- \$file", + "find_commit_signers_cmd" => "git log -1 \$commit", + "blame_range_cmd" => "git blame -l -L \$diff_start,+\$diff_length \$file", + "blame_file_cmd" => "git blame -l \$file", + "commit_pattern" => "^commit [0-9a-f]{40,40}", + "blame_commit_pattern" => "^([0-9a-f]+) " +); + +my %VCS_cmds_hg = ( + "execute_cmd" => \&hg_execute_cmd, + "available" => '(which("hg") ne "") && (-d ".hg")', + "find_signers_cmd" => + "hg log --date=\$email_hg_since" . + " --template='commit {node}\\n{desc}\\n' -- \$file", + "find_commit_signers_cmd" => "hg log --template='{desc}\\n' -r \$commit", + "blame_range_cmd" => "", # not supported + "blame_file_cmd" => "hg blame -c \$file", + "commit_pattern" => "^commit [0-9a-f]{40,40}", + "blame_commit_pattern" => "^([0-9a-f]+):" +); + if (!GetOptions( 'email!' => \$email, 'git!' => \$email_git, + 'git-blame!' => \$email_git_blame, 'git-chief-penguins!' => \$email_git_penguin_chiefs, 'git-min-signatures=i' => \$email_git_min_signatures, 'git-max-maintainers=i' => \$email_git_max_maintainers, 'git-min-percent=i' => \$email_git_min_percent, 'git-since=s' => \$email_git_since, + 'hg-since=s' => \$email_hg_since, + 'remove-duplicates!' => \$email_remove_duplicates, 'm!' => \$email_maintainer, 'n!' => \$email_usename, 'l!' => \$email_list, 's!' => \$email_subscriber_list, 'multiline!' => \$output_multiline, + 'roles!' => \$output_roles, + 'rolestats!' => \$output_rolestats, 'separator=s' => \$output_separator, 'subsystem!' => \$subsystem, 'status!' => \$status, 'scm!' => \$scm, 'web!' => \$web, + 'pattern-depth=i' => \$pattern_depth, + 'k|keywords!' => \$keywords, 'f|file' => \$from_filename, 'v|version' => \$version, 'h|help' => \$help, )) { - usage(); - die "$P: invalid argument\n"; + die "$P: invalid argument - use --help if necessary\n"; } if ($help != 0) { @@ -101,14 +142,23 @@ if ($#ARGV < 0) { die "$P: argument missing: patchfile or -f file please\n"; } +if ($output_separator ne ", ") { + $output_multiline = 0; +} + +if ($output_rolestats) { + $output_roles = 1; +} + 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"; } @@ -121,6 +171,8 @@ 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 = $_; @@ -138,6 +190,8 @@ while () { if ((-d $value)) { $value =~ s@([^/])$@$1/@; } + } elsif ($type eq "K") { + $keyword_hash{@typevalue} = $value; } push(@typevalue, "$type:$value"); } elsif (!/^(\s)*$/) { @@ -147,9 +201,37 @@ 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, $email_usename); + + next if ($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) { ##if $file is a directory and it lacks a trailing slash, add one @@ -160,15 +242,38 @@ foreach my $file (@ARGV) { } if ($from_filename) { push(@files, $file); + if (-f $file && $keywords) { + open(FILE, "<$file") or die "$P: Can't open ${file}\n"; + my $text = do { local($/) ; }; + foreach my $line (keys %keyword_hash) { + if ($text =~ 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); @@ -191,56 +296,84 @@ my @status = (); foreach my $file (@files) { -#Do not match excluded file patterns + my %hash; + 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; - my $exclude = 0; - foreach my $line (@typevalue) { - if ($line =~ m/^(\C):\s*(.*)/) { - my $type = $1; - my $value = $2; - if ($type eq 'X') { - if (file_match_pattern($file, $value)) { - $exclude = 1; - } - } - } - } + #Do not match excluded file patterns - if (!$exclude) { - my $tvi = 0; - foreach my $line (@typevalue) { + for ($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, $value)) { - add_categories($tvi); + $exclude = 1; + } + } + } + } + + if (!$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 "/"); + if ($pattern_depth == 0 || + (($file_pd - $value_pd) < $pattern_depth)) { + $hash{$tvi} = $value_pd; + } + } } } } - $tvi++; } + + $tvi += ($end - $start); + + } + + foreach my $line (sort {$hash{$b} <=> $hash{$a}} keys %hash) { + add_categories($line); } if ($email && $email_git) { - recent_git_signoffs($file); + 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 ($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, $email_usename); if ($email_git_penguin_chiefs) { - push(@email_to, $email_address); + push(@email_to, [$email_address, 'chief penguin']); } else { - @email_to = grep(!/${email_address}/, @email_to); + @email_to = grep($_->[0] !~ /${email_address}/, @email_to); } } } @@ -254,26 +387,26 @@ if ($email || $email_list) { if ($email_list) { @to = (@to, @list_to); } - output(uniq(@to)); + output(merge_email(@to)); } 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); } @@ -310,11 +443,16 @@ MAINTAINER field selection options: --git-min-signatures => number of signatures required (default: 1) --git-max-maintainers => maximum maintainers to add (default: 5) --git-min-percent => minimum percentage of commits required (default: 5) + --git-blame => use git blame to find modified commits for patch or file --git-since => git history to use (default: 1-year-ago) + --hg-since => hg history to use (default: -365) --m => include maintainer(s) if any --n => include name 'Full Name ' --l => include list(s) if any --s => include subscriber only list(s) if any + --remove-duplicates => minimize duplicate email names/addresses + --roles => show roles (status:subsystem, git-signer, list, etc...) + --rolestats => show roles and statistics (commits/total_commits, %) --scm => print SCM tree(s) if any --status => print status if any --subsystem => print subsystem name if any @@ -322,24 +460,42 @@ 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", 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. + Using "--roles" or "--rolestats" with git send-email --cc-cmd or any + other automated tools that expect only ["name"] + may not work because of additional output after . + Using "--rolestats" and "--git-blame" shows the #/total=% commits, + not the percentage of the entire file authored. # of commits is + not a good measure of amount of code authored. 1 major commit may + contain a thousand lines, 5 trivial commits may modify a single line. + If git is not installed, but mercurial (hg) is installed and an .hg + repository exists, the following options apply to mercurial: + --git, + --git-min-signatures, --git-max-maintainers, --git-min-percent, and + --git-blame + Use --hg-since not --git-since to control date selection EOT } @@ -370,64 +526,218 @@ 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; - my $formatted_email = ""; + if ($name =~ /[^a-z0-9 \.\-]/i) { ##has "must quote" chars + $name =~ s/(?"; + $name = "\"$name\""; + } + + if ($usename) { + if ("$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_first_section { + my $index = 0; + + while ($index < @typevalue) { + my $tv = $typevalue[$index]; + if (($tv =~ m/^(\C):\s*(.*)/)) { + last; + } + $index++; + } + + return $index; +} + +sub find_starting_index { my ($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 $index; +} + +sub get_maintainer_role { + my ($index) = @_; + + my $i; + my $start = find_starting_index($index); + my $end = find_ending_index($index); + + my $role; + my $subsystem = $typevalue[$start]; + if (length($subsystem) > 20) { + $subsystem = substr($subsystem, 0, 17); + $subsystem =~ s/\s*$//; + $subsystem = $subsystem . "..."; + } + + for ($i = $start + 1; $i < $end; $i++) { + my $tv = $typevalue[$i]; + if ($tv =~ m/^(\C):\s*(.*)/) { + my $ptype = $1; + my $pvalue = $2; + if ($ptype eq "S") { + $role = $pvalue; + } + } + } + + $role = lc($role); + if ($role eq "supported") { + $role = "supporter"; + } elsif ($role eq "maintained") { + $role = "maintainer"; + } elsif ($role eq "odd fixes") { + $role = "odd fixer"; + } elsif ($role eq "orphan") { + $role = "orphan minder"; + } elsif ($role eq "obsolete") { + $role = "obsolete minder"; + } elsif ($role eq "buried alive in reporters") { + $role = "chief penguin"; + } + + return $role . ":" . $subsystem; +} + +sub get_list_role { + my ($index) = @_; + + my $i; + my $start = find_starting_index($index); + my $end = find_ending_index($index); + + my $subsystem = $typevalue[$start]; + if (length($subsystem) > 20) { + $subsystem = substr($subsystem, 0, 17); + $subsystem =~ s/\s*$//; + $subsystem = $subsystem . "..."; + } + + if ($subsystem eq "THE REST") { + $subsystem = ""; + } + + return $subsystem; +} + +sub add_categories { + my ($index) = @_; + + 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 = $2; if ($ptype eq "L") { my $list_address = $pvalue; my $list_additional = ""; + my $list_role = get_list_role($i); + + if ($list_role ne "") { + $list_role = ":" . $list_role; + } if ($list_address =~ m/([^\s]+)\s+(.*)$/) { $list_address = $1; $list_additional = $2; } if ($list_additional =~ m/subscribers-only/) { if ($email_subscriber_list) { - push(@list_to, $list_address); + push(@list_to, [$list_address, "subscriber list${list_role}"]); } } else { if ($email_list) { - push(@list_to, $list_address); + push(@list_to, [$list_address, "open list${list_role}"]); } } } elsif ($ptype eq "M") { - my $p_used = 0; - if ($index >= 0) { - my $tv = $typevalue[$index - 1]; - if ($tv =~ m/^(\C):\s*(.*)/) { - if ($1 eq "P") { - if ($email_usename) { - push_email_address(format_email($2, $pvalue)); - $p_used = 1; + my ($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, $email_usename); } } } } - if (!$p_used) { - push_email_addresses($pvalue); + if ($email_maintainer) { + my $role = get_maintainer_role($i); + push_email_addresses($pvalue, $role); } } elsif ($ptype eq "T") { push(@scm, $pvalue); @@ -436,47 +746,87 @@ sub add_categories { } elsif ($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, $role) = @_; - my $email_name = ""; - if ($email_address =~ m/([^<]+)<(.*\@.*)>$/) { - $email_name = $1; - $email_address = $2; + my ($name, $address) = parse_email($line); + + if ($address eq "") { + return 0; } - if ($email_maintainer) { - 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, $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}++; } + + return 1; } sub push_email_addresses { - my ($address) = @_; + my ($address, $role) = @_; my @address_list = (); if (rfc822_valid($address)) { - push_email_address($address); + push_email_address($address, $role); } elsif (@address_list = rfc822_validlist($address)) { my $array_count = shift(@address_list); while (my $entry = shift(@address_list)) { - push_email_address($entry); + push_email_address($entry, $role); } } else { - warn("Invalid MAINTAINERS address: '" . $address . "'\n"); + if (!push_email_address($address, $role)) { + warn("Invalid MAINTAINERS address: '" . $address . "'\n"); + } + } +} + +sub add_role { + my ($line, $role) = @_; + + my ($name, $address) = parse_email($line); + my $email = format_email($name, $address, $email_usename); + + foreach my $entry (@email_to) { + if ($email_remove_duplicates) { + my ($entry_name, $entry_address) = parse_email($entry->[0]); + if ($name eq $entry_name || $address eq $entry_address) { + if ($entry->[1] eq "") { + $entry->[1] = "$role"; + } else { + $entry->[1] = "$entry->[1],$role"; + } + } + } else { + if ($email eq $entry->[0]) { + if ($entry->[1] eq "") { + $entry->[1] = "$role"; + } else { + $entry->[1] = "$entry->[1],$role"; + } + } + } } } @@ -492,78 +842,248 @@ sub which { return ""; } -sub recent_git_signoffs { - my ($file) = @_; +sub mailmap { + my (@lines) = @_; + my %hash; - my $sign_offs = ""; - my $cmd = ""; - my $output = ""; - my $count = 0; + 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}, $email_usename); + } + } + } + } + + return @lines; +} + +sub git_execute_cmd { + my ($cmd) = @_; my @lines = (); - my $total_sign_offs; - if (which("git") eq "") { - warn("$P: git not found. Add --nogit to options?\n"); - return; - } - if (!(-d ".git")) { - warn("$P: .git directory not found. Use a git repository for better results.\n"); - warn("$P: perhaps 'git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git'\n"); - return; - } + my $output = `$cmd`; + $output =~ s/^\s*//gm; + @lines = split("\n", $output); + + return @lines; +} - $cmd = "git log --since=${email_git_since} -- ${file}"; - $cmd .= " | grep -Ei \"^[-_ a-z]+by:.*\\\@.*\$\""; +sub hg_execute_cmd { + my ($cmd) = @_; + my @lines = (); + + my $output = `$cmd`; + @lines = split("\n", $output); + + return @lines; +} + +sub vcs_find_signers { + my ($cmd) = @_; + my @lines = (); + my $commits; + + @lines = &{$VCS_cmds{"execute_cmd"}}($cmd); + + my $pattern = $VCS_cmds{"commit_pattern"}; + + $commits = grep(/$pattern/, @lines); # of commits + + @lines = grep(/^[-_ a-z]+by:.*\@.*$/i, @lines); if (!$email_git_penguin_chiefs) { - $cmd .= " | grep -Ev \"${penguin_chiefs}\""; + @lines = grep(!/${penguin_chiefs}/i, @lines); } - $cmd .= " | cut -f2- -d\":\""; - $cmd .= " | sort | uniq -c | sort -rn"; + # cut -f2- -d":" + s/.*:\s*(.+)\s*/$1/ for (@lines); - $output = `${cmd}`; - $output =~ s/^\s*//gm; +## Reformat email addresses (with names) to avoid badly written signatures - @lines = split("\n", $output); + foreach my $line (@lines) { + my ($name, $address) = parse_email($line); + $line = format_email($name, $address, 1); + } + + return ($commits, @lines); +} + +sub vcs_save_commits { + my ($cmd) = @_; + my @lines = (); + my @commits = (); + + @lines = &{$VCS_cmds{"execute_cmd"}}($cmd); - $total_sign_offs = 0; foreach my $line (@lines) { - if ($line =~ m/([0-9]+)\s+(.*)/) { - $total_sign_offs += $1; - } else { - die("$P: Unexpected git output: ${line}\n"); + if ($line =~ m/$VCS_cmds{"blame_commit_pattern"}/) { + push(@commits, $1); } } - 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 || - $sign_offs * 100 / $total_sign_offs < $email_git_min_percent) { - last; + return @commits; +} + +sub vcs_blame { + my ($file) = @_; + my $cmd; + my @commits = (); + + return @commits if (!(-f $file)); + + if (@range && $VCS_cmds{"blame_range_cmd"} eq "") { + my @all_commits = (); + + $cmd = $VCS_cmds{"blame_file_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd + @all_commits = vcs_save_commits($cmd); + + foreach my $file_range_diff (@range) { + next if (!($file_range_diff =~ m/(.+):(.+):(.+)/)); + my $diff_file = $1; + my $diff_start = $2; + my $diff_length = $3; + next if ("$file" ne "$diff_file"); + for (my $i = $diff_start; $i < $diff_start + $diff_length; $i++) { + push(@commits, $all_commits[$i]); } } - 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); + } elsif (@range) { + foreach my $file_range_diff (@range) { + next if (!($file_range_diff =~ m/(.+):(.+):(.+)/)); + my $diff_file = $1; + my $diff_start = $2; + my $diff_length = $3; + next if ("$file" ne "$diff_file"); + $cmd = $VCS_cmds{"blame_range_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd + push(@commits, vcs_save_commits($cmd)); + } + } else { + $cmd = $VCS_cmds{"blame_file_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd + @commits = vcs_save_commits($cmd); + } + + return @commits; +} + +my $printed_novcs = 0; +sub vcs_exists { + %VCS_cmds = %VCS_cmds_git; + return 1 if eval $VCS_cmds{"available"}; + %VCS_cmds = %VCS_cmds_hg; + return 1 if eval $VCS_cmds{"available"}; + %VCS_cmds = (); + if (!$printed_novcs) { + warn("$P: No supported VCS found. Add --nogit to options?\n"); + warn("Using a git repository produces better results.\n"); + warn("Try Linus Torvalds' latest git repository using:\n"); + warn("git clone git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git\n"); + $printed_novcs = 1; + } + return 0; +} + +sub vcs_assign { + my ($role, $divisor, @lines) = @_; + + my %hash; + my $count = 0; + + return if (@lines <= 0); + + if ($divisor <= 0) { + warn("Bad divisor in " . (caller(0))[3] . ": $divisor\n"); + $divisor = 1; + } + + if ($email_remove_duplicates) { + @lines = mailmap(@lines); + } + + @lines = sort(@lines); + + # uniq -c + $hash{$_}++ for @lines; + + # sort -rn + foreach my $line (sort {$hash{$b} <=> $hash{$a}} keys %hash) { + my $sign_offs = $hash{$line}; + my $percent = $sign_offs * 100 / $divisor; + + $percent = 100 if ($percent > 100); + $count++; + last if ($sign_offs < $email_git_min_signatures || + $count > $email_git_max_maintainers || + $percent < $email_git_min_percent); + push_email_address($line, ''); + if ($output_rolestats) { + my $fmt_percent = sprintf("%.0f", $percent); + add_role($line, "$role:$sign_offs/$divisor=$fmt_percent%"); } else { - push(@email_to, $line); + add_role($line, $role); } } } +sub vcs_file_signoffs { + my ($file) = @_; + + my @signers = (); + my $commits; + + return if (!vcs_exists()); + + my $cmd = $VCS_cmds{"find_signers_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd + + ($commits, @signers) = vcs_find_signers($cmd); + vcs_assign("commit_signer", $commits, @signers); +} + +sub vcs_file_blame { + my ($file) = @_; + + my @signers = (); + my @commits = (); + my $total_commits; + + return if (!vcs_exists()); + + @commits = vcs_blame($file); + @commits = uniq(@commits); + $total_commits = @commits; + + foreach my $commit (@commits) { + my $commit_count; + my @commit_signers = (); + + my $cmd = $VCS_cmds{"find_commit_signers_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #interpolate $cmd + + ($commit_count, @commit_signers) = vcs_find_signers($cmd); + push(@signers, @commit_signers); + } + + if ($from_filename) { + vcs_assign("commits", $total_commits, @signers); + } else { + vcs_assign("modified commits", $total_commits, @signers); + } +} + sub uniq { - my @parms = @_; + my (@parms) = @_; my %saw; @parms = grep(!$saw{$_}++, @parms); @@ -571,7 +1091,7 @@ sub uniq { } sub sort_and_uniq { - my @parms = @_; + my (@parms) = @_; my %saw; @parms = sort @parms; @@ -579,8 +1099,27 @@ sub sort_and_uniq { return @parms; } +sub merge_email { + my @lines; + my %saw; + + for (@_) { + my ($address, $role) = @$_; + if (!$saw{$address}) { + if ($output_roles) { + push(@lines, "$address ($role)"); + } else { + push(@lines, $address); + } + $saw{$address} = 1; + } + } + + return @lines; +} + sub output { - my @parms = @_; + my (@parms) = @_; if ($output_multiline) { foreach my $line (@parms) { @@ -677,11 +1216,9 @@ sub rfc822_validlist ($) { if ($s =~ m/^(?:$rfc822re)?(?:,(?:$rfc822re)?)*$/so && $s =~ m/^$rfc822_char*$/) { while ($s =~ m/(?:^|,$rfc822_lwsp*)($rfc822re)/gos) { - push @r, $1; + push(@r, $1); } return wantarray ? (scalar(@r), @r) : 1; } - else { - return wantarray ? () : 0; - } + return wantarray ? () : 0; }