diff options
Diffstat (limited to 'scripts/get_maintainer.pl')
| -rwxr-xr-x | scripts/get_maintainer.pl | 274 |
1 files changed, 223 insertions, 51 deletions
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 60dc0c48c92..278a45bd45a 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -13,7 +13,7 @@ use strict; my $P = $0; -my $V = '0.15'; +my $V = '0.17'; use Getopt::Long qw(:config no_auto_abbrev); @@ -27,6 +27,7 @@ my $email_git = 1; my $email_git_penguin_chiefs = 0; my $email_git_min_signatures = 1; my $email_git_max_maintainers = 5; +my $email_git_min_percent = 5; my $email_git_since = "1-year-ago"; my $output_multiline = 1; my $output_separator = ", "; @@ -55,12 +56,17 @@ foreach my $chief (@penguin_chief) { } my $penguin_chiefs = "\(" . join("|",@penguin_chief_names) . "\)"; +# rfc822 email address - preloaded methods go here. +my $rfc822_lwsp = "(?:(?:\\r\\n)?[ \\t])"; +my $rfc822_char = '[\\000-\\377]'; + if (!GetOptions( 'email!' => \$email, 'git!' => \$email_git, '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, 'm!' => \$email_maintainer, 'n!' => \$email_usename, @@ -128,6 +134,10 @@ while (<MAINT>) { $value =~ s@\.@\\\.@g; ##Convert . to \. $value =~ s/\*/\.\*/g; ##Convert * to .* $value =~ s/\?/\./g; ##Convert ? to . + ##if pattern is a directory and it lacks a trailing slash, add one + if ((-d $value)) { + $value =~ s@([^/])$@$1/@; + } } push(@typevalue, "$type:$value"); } elsif (!/^(\s)*$/) { @@ -142,8 +152,10 @@ close(MAINT); my @files = (); foreach my $file (@ARGV) { - next if ((-d $file)); - if (!(-f $file)) { + ##if $file is a directory and it lacks a trailing slash, add one + if ((-d $file)) { + $file =~ s@([^/])$@$1/@; + } elsif (!(-f $file)) { die "$P: file '${file}' not found\n"; } if ($from_filename) { @@ -161,7 +173,7 @@ foreach my $file (@ARGV) { } close(PATCH); if ($file_cnt == @files) { - die "$P: file '${file}' doesn't appear to be a patch. " + warn "$P: file '${file}' doesn't appear to be a patch. " . "Add -f to options?\n"; } @files = sort_and_uniq(@files); @@ -169,6 +181,7 @@ foreach my $file (@ARGV) { } my @email_to = (); +my @list_to = (); my @scm = (); my @web = (); my @subsystem = (); @@ -182,7 +195,7 @@ foreach my $file (@files) { my $exclude = 0; foreach my $line (@typevalue) { - if ($line =~ m/^(\C):(.*)/) { + if ($line =~ m/^(\C):\s*(.*)/) { my $type = $1; my $value = $2; if ($type eq 'X') { @@ -196,7 +209,7 @@ foreach my $file (@files) { if (!$exclude) { my $tvi = 0; foreach my $line (@typevalue) { - if ($line =~ m/^(\C):(.*)/) { + if ($line =~ m/^(\C):\s*(.*)/) { my $type = $1; my $value = $2; if ($type eq 'F') { @@ -215,29 +228,33 @@ foreach my $file (@files) { } -if ($email_git_penguin_chiefs) { +if ($email) { foreach my $chief (@penguin_chief) { if ($chief =~ m/^(.*):(.*)/) { - my $chief_name = $1; - my $chief_addr = $2; + my $email_address; if ($email_usename) { - push(@email_to, format_email($chief_name, $chief_addr)); + $email_address = format_email($1, $2); + } else { + $email_address = $2; + } + if ($email_git_penguin_chiefs) { + push(@email_to, $email_address); } else { - push(@email_to, $chief_addr); + @email_to = grep(!/${email_address}/, @email_to); } } } } -if ($email) { - my $address_cnt = @email_to; - if ($address_cnt == 0 && $email_list) { - push(@email_to, "linux-kernel\@vger.kernel.org"); +if ($email || $email_list) { + my @to = (); + if ($email) { + @to = (@to, @email_to); } - -#Don't sort email address list, but do remove duplicates - @email_to = uniq(@email_to); - output(@email_to); + if ($email_list) { + @to = (@to, @list_to); + } + output(uniq(@to)); } if ($scm) { @@ -283,7 +300,7 @@ sub file_match_pattern { sub usage { print <<EOT; usage: $P [options] patchfile - $P [options] -f file + $P [options] -f file|directory version: $V MAINTAINER field selection options: @@ -292,6 +309,7 @@ MAINTAINER field selection options: --git-chief-penguins => include ${penguin_chiefs} --git-min-signatures => number of signatures required (default: 1) --git-max-maintainers => maximum maintainers to add (default: 5) + --git-min-percent => minimum percentage of commits required (default: 5) --git-since => git history to use (default: 1-year-ago) --m => include maintainer(s) if any --n => include name 'Full Name <addr\@domain.tld>' @@ -307,12 +325,21 @@ Output type options: --multiline => print 1 entry per line Default options: - [--email --git --m --l --multiline] + [--email --git --m --n --l --multiline] Other options: - --version -> show version + --version => show version --help => show this help information +Notes: + Using "-f directory" may give unexpected results: + + Used with "--git", git signators for _all_ files in and below + directory are examined as git recurses directories. + Any specified X: (exclude) pattern matches are _not_ ignored. + Used with "--nogit", directory is used as a pattern match, + no individual file within the directory or subdirectory + is matched. EOT } @@ -347,6 +374,7 @@ sub format_email { my ($name, $email) = @_; $name =~ s/^\s+|\s+$//g; + $name =~ s/^\"|\"$//g; $email =~ s/^\s+|\s+$//g; my $formatted_email = ""; @@ -366,36 +394,41 @@ sub add_categories { $index = $index - 1; while ($index >= 0) { my $tv = $typevalue[$index]; - if ($tv =~ m/^(\C):(.*)/) { + if ($tv =~ m/^(\C):\s*(.*)/) { my $ptype = $1; my $pvalue = $2; if ($ptype eq "L") { - my $subscr = $pvalue; - if ($subscr =~ m/\s*\(subscribers-only\)/) { + my $list_address = $pvalue; + my $list_additional = ""; + if ($list_address =~ m/([^\s]+)\s+(.*)$/) { + $list_address = $1; + $list_additional = $2; + } + if ($list_additional =~ m/subscribers-only/) { if ($email_subscriber_list) { - $subscr =~ s/\s*\(subscribers-only\)//g; - push(@email_to, $subscr); + push(@list_to, $list_address); } } else { if ($email_list) { - push(@email_to, $pvalue); + push(@list_to, $list_address); } } } elsif ($ptype eq "M") { - if ($email_maintainer) { - if ($index >= 0) { - my $tv = $typevalue[$index - 1]; - if ($tv =~ m/^(\C):(.*)/) { - if ($1 eq "P" && $email_usename) { - push(@email_to, format_email($2, $pvalue)); - } else { - push(@email_to, $pvalue); + 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; } } - } else { - push(@email_to, $pvalue); } } + if (!$p_used) { + push_email_addresses($pvalue); + } } elsif ($ptype eq "T") { push(@scm, $pvalue); } elsif ($ptype eq "W") { @@ -412,10 +445,45 @@ sub add_categories { } } +sub push_email_address { + my ($email_address) = @_; + + my $email_name = ""; + if ($email_address =~ m/([^<]+)<(.*\@.*)>$/) { + $email_name = $1; + $email_address = $2; + } + + if ($email_maintainer) { + if ($email_usename && $email_name) { + push(@email_to, format_email($email_name, $email_address)); + } else { + push(@email_to, $email_address); + } + } +} + +sub push_email_addresses { + my ($address) = @_; + + my @address_list = (); + + if (rfc822_valid($address)) { + push_email_address($address); + } elsif (@address_list = rfc822_validlist($address)) { + my $array_count = shift(@address_list); + while (my $entry = shift(@address_list)) { + push_email_address($entry); + } + } else { + warn("Invalid MAINTAINERS address: '" . $address . "'\n"); + } +} + sub which { my ($bin) = @_; - foreach my $path (split /:/, $ENV{PATH}) { + foreach my $path (split(/:/, $ENV{PATH})) { if (-e "$path/$bin") { return "$path/$bin"; } @@ -432,43 +500,54 @@ sub recent_git_signoffs { my $output = ""; my $count = 0; my @lines = (); + my $total_sign_offs; if (which("git") eq "") { - die("$P: git not found. Add --nogit to options?\n"); + 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; } $cmd = "git log --since=${email_git_since} -- ${file}"; - $cmd .= " | grep -Pi \"^[-_ a-z]+by:.*\\\@\""; + $cmd .= " | grep -Ei \"^[-_ a-z]+by:.*\\\@.*\$\""; if (!$email_git_penguin_chiefs) { - $cmd .= " | grep -Pv \"${penguin_chiefs}\""; + $cmd .= " | grep -Ev \"${penguin_chiefs}\""; } $cmd .= " | cut -f2- -d\":\""; - $cmd .= " | sed -e \"s/^\\s+//g\""; $cmd .= " | sort | uniq -c | sort -rn"; $output = `${cmd}`; $output =~ s/^\s*//gm; @lines = split("\n", $output); + + $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"); + } + } + 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) { + $count > $email_git_max_maintainers || + $sign_offs * 100 / $total_sign_offs < $email_git_min_percent) { last; } - } else { - die("$P: Unexpected git output: ${line}\n"); } if ($line =~ m/(.+)<(.+)>/) { my $git_name = $1; my $git_addr = $2; - $git_name =~ tr/^\"//; - $git_name =~ tr/^\\s*//; - $git_name =~ tr/\"$//; - $git_name =~ tr/\\s*$//; if ($email_usename) { push(@email_to, format_email($git_name, $git_addr)); } else { @@ -481,7 +560,6 @@ sub recent_git_signoffs { push(@email_to, $line); } } - return $output; } sub uniq { @@ -513,3 +591,97 @@ sub output { print("\n"); } } + +my $rfc822re; + +sub make_rfc822re { +# Basic lexical tokens are specials, domain_literal, quoted_string, atom, and +# comment. We must allow for rfc822_lwsp (or comments) after each of these. +# This regexp will only work on addresses which have had comments stripped +# and replaced with rfc822_lwsp. + + my $specials = '()<>@,;:\\\\".\\[\\]'; + my $controls = '\\000-\\037\\177'; + + my $dtext = "[^\\[\\]\\r\\\\]"; + my $domain_literal = "\\[(?:$dtext|\\\\.)*\\]$rfc822_lwsp*"; + + my $quoted_string = "\"(?:[^\\\"\\r\\\\]|\\\\.|$rfc822_lwsp)*\"$rfc822_lwsp*"; + +# Use zero-width assertion to spot the limit of an atom. A simple +# $rfc822_lwsp* causes the regexp engine to hang occasionally. + my $atom = "[^$specials $controls]+(?:$rfc822_lwsp+|\\Z|(?=[\\[\"$specials]))"; + my $word = "(?:$atom|$quoted_string)"; + my $localpart = "$word(?:\\.$rfc822_lwsp*$word)*"; + + my $sub_domain = "(?:$atom|$domain_literal)"; + my $domain = "$sub_domain(?:\\.$rfc822_lwsp*$sub_domain)*"; + + my $addr_spec = "$localpart\@$rfc822_lwsp*$domain"; + + my $phrase = "$word*"; + my $route = "(?:\@$domain(?:,\@$rfc822_lwsp*$domain)*:$rfc822_lwsp*)"; + my $route_addr = "\\<$rfc822_lwsp*$route?$addr_spec\\>$rfc822_lwsp*"; + my $mailbox = "(?:$addr_spec|$phrase$route_addr)"; + + my $group = "$phrase:$rfc822_lwsp*(?:$mailbox(?:,\\s*$mailbox)*)?;\\s*"; + my $address = "(?:$mailbox|$group)"; + + return "$rfc822_lwsp*$address"; +} + +sub rfc822_strip_comments { + my $s = shift; +# Recursively remove comments, and replace with a single space. The simpler +# regexps in the Email Addressing FAQ are imperfect - they will miss escaped +# chars in atoms, for example. + + while ($s =~ s/^((?:[^"\\]|\\.)* + (?:"(?:[^"\\]|\\.)*"(?:[^"\\]|\\.)*)*) + \((?:[^()\\]|\\.)*\)/$1 /osx) {} + return $s; +} + +# valid: returns true if the parameter is an RFC822 valid address +# +sub rfc822_valid ($) { + my $s = rfc822_strip_comments(shift); + + if (!$rfc822re) { + $rfc822re = make_rfc822re(); + } + + return $s =~ m/^$rfc822re$/so && $s =~ m/^$rfc822_char*$/; +} + +# validlist: In scalar context, returns true if the parameter is an RFC822 +# valid list of addresses. +# +# In list context, returns an empty list on failure (an invalid +# address was found); otherwise a list whose first element is the +# number of addresses found and whose remaining elements are the +# addresses. This is needed to disambiguate failure (invalid) +# from success with no addresses found, because an empty string is +# a valid list. + +sub rfc822_validlist ($) { + my $s = rfc822_strip_comments(shift); + + if (!$rfc822re) { + $rfc822re = make_rfc822re(); + } + # * null list items are valid according to the RFC + # * the '1' business is to aid in distinguishing failure from no results + + my @r; + if ($s =~ m/^(?:$rfc822re)?(?:,(?:$rfc822re)?)*$/so && + $s =~ m/^$rfc822_char*$/) { + while ($s =~ m/(?:^|,$rfc822_lwsp*)($rfc822re)/gos) { + push @r, $1; + } + return wantarray ? (scalar(@r), @r) : 1; + } + else { + return wantarray ? () : 0; + } +} |