diff options
Diffstat (limited to 'scripts/get_maintainer.pl')
| -rwxr-xr-x | scripts/get_maintainer.pl | 86 |
1 files changed, 48 insertions, 38 deletions
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index ab123b498f..ee1aed7e09 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -20,6 +20,7 @@ use Getopt::Long qw(:config no_auto_abbrev); use Cwd; use File::Find; use File::Spec::Functions; +use open qw(:std :encoding(UTF-8)); my $cur_path = fastgetcwd() . '/'; my $lk_path = "./"; @@ -57,6 +58,7 @@ my $subsystem = 0; my $status = 0; my $letters = ""; my $keywords = 1; +my $keywords_in_file = 0; my $sections = 0; my $email_file_emails = 0; my $from_filename = 0; @@ -272,6 +274,7 @@ if (!GetOptions( 'letters=s' => \$letters, 'pattern-depth=i' => \$pattern_depth, 'k|keywords!' => \$keywords, + 'kf|keywords-in-file!' => \$keywords_in_file, 'sections!' => \$sections, 'fe|file-emails!' => \$email_file_emails, 'f|file' => \$from_filename, @@ -318,6 +321,7 @@ if ($sections || $letters ne "") { $subsystem = 0; $web = 0; $keywords = 0; + $keywords_in_file = 0; $interactive = 0; } else { my $selections = $email + $scm + $status + $subsystem + $web; @@ -442,7 +446,7 @@ sub maintainers_in_file { my $text = do { local($/) ; <$f> }; close($f); - my @poss_addr = $text =~ m$[A-Za-zÀ-ÿ\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g; + my @poss_addr = $text =~ m$[\p{L}\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g; push(@file_emails, clean_file_emails(@poss_addr)); } } @@ -548,16 +552,14 @@ foreach my $file (@ARGV) { $file =~ s/^\Q${cur_path}\E//; #strip any absolute path $file =~ s/^\Q${lk_path}\E//; #or the path to the lk tree push(@files, $file); - if ($file ne "MAINTAINERS" && -f $file && $keywords) { + if ($file ne "MAINTAINERS" && -f $file && $keywords && $keywords_in_file) { open(my $f, '<', $file) or die "$P: Can't open $file: $!\n"; my $text = do { local($/) ; <$f> }; close($f); - if ($keywords) { - foreach my $line (keys %keyword_hash) { - if ($text =~ m/$keyword_hash{$line}/x) { - push(@keyword_tvi, $line); - } + foreach my $line (keys %keyword_hash) { + if ($text =~ m/$keyword_hash{$line}/x) { + push(@keyword_tvi, $line); } } } @@ -919,7 +921,7 @@ sub get_maintainers { } foreach my $line (sort {$hash{$b} <=> $hash{$a}} keys %hash) { - add_categories($line); + add_categories($line, ""); if ($sections) { my $i; my $start = find_starting_index($line); @@ -947,7 +949,7 @@ sub get_maintainers { if ($keywords) { @keyword_tvi = sort_and_uniq(@keyword_tvi); foreach my $line (@keyword_tvi) { - add_categories($line); + add_categories($line, ":Keyword:$keyword_hash{$line}"); } } @@ -1076,6 +1078,7 @@ Output type options: Other options: --pattern-depth => Number of pattern directory traversals (default: 0 (all)) --keywords => scan patch for keywords (default: $keywords) + --keywords-in-file => scan file for keywords (default: $keywords_in_file) --sections => print all of the subsystem sections with pattern matches --letters => print all matching 'letter' types from all matching sections --mailmap => use .mailmap file (default: $email_use_mailmap) @@ -1086,7 +1089,7 @@ Other options: Default options: [--email --tree --nogit --git-fallback --m --r --n --l --multiline - --pattern-depth=0 --remove-duplicates --rolestats] + --pattern-depth=0 --remove-duplicates --rolestats --keywords] Notes: Using "-f directory" may give unexpected results: @@ -1150,6 +1153,17 @@ sub top_of_kernel_tree { return 0; } +sub escape_name { + my ($name) = @_; + + if ($name =~ /[^\w \-]/ai) { ##has "must quote" chars + $name =~ s/(?<!\\)"/\\"/g; ##escape quotes + $name = "\"$name\""; + } + + return $name; +} + sub parse_email { my ($formatted_email) = @_; @@ -1167,13 +1181,9 @@ sub parse_email { $name =~ s/^\s+|\s+$//g; $name =~ s/^\"|\"$//g; + $name = escape_name($name); $address =~ s/^\s+|\s+$//g; - if ($name =~ /[^\w \-]/i) { ##has "must quote" chars - $name =~ s/(?<!\\)"/\\"/g; ##escape quotes - $name = "\"$name\""; - } - return ($name, $address); } @@ -1184,13 +1194,9 @@ sub format_email { $name =~ s/^\s+|\s+$//g; $name =~ s/^\"|\"$//g; + $name = escape_name($name); $address =~ s/^\s+|\s+$//g; - if ($name =~ /[^\w \-]/i) { ##has "must quote" chars - $name =~ s/(?<!\\)"/\\"/g; ##escape quotes - $name = "\"$name\""; - } - if ($usename) { if ("$name" eq "") { $formatted_email = "$address"; @@ -1312,7 +1318,7 @@ sub get_list_role { } sub add_categories { - my ($index) = @_; + my ($index, $suffix) = @_; my $i; my $start = find_starting_index($index); @@ -1342,7 +1348,7 @@ sub add_categories { if (!$hash_list_to{lc($list_address)}) { $hash_list_to{lc($list_address)} = 1; push(@list_to, [$list_address, - "subscriber list${list_role}"]); + "subscriber list${list_role}" . $suffix]); } } } else { @@ -1352,12 +1358,12 @@ sub add_categories { if ($email_moderated_list) { $hash_list_to{lc($list_address)} = 1; push(@list_to, [$list_address, - "moderated list${list_role}"]); + "moderated list${list_role}" . $suffix]); } } else { $hash_list_to{lc($list_address)} = 1; push(@list_to, [$list_address, - "open list${list_role}"]); + "open list${list_role}" . $suffix]); } } } @@ -1365,19 +1371,19 @@ sub add_categories { } elsif ($ptype eq "M") { if ($email_maintainer) { my $role = get_maintainer_role($i); - push_email_addresses($pvalue, $role); + push_email_addresses($pvalue, $role . $suffix); } } elsif ($ptype eq "R") { if ($email_reviewer) { my $subsystem = get_subsystem_name($i); - push_email_addresses($pvalue, "reviewer:$subsystem"); + push_email_addresses($pvalue, "reviewer:$subsystem" . $suffix); } } elsif ($ptype eq "T") { - push(@scm, $pvalue); + push(@scm, $pvalue . $suffix); } elsif ($ptype eq "W") { - push(@web, $pvalue); + push(@web, $pvalue . $suffix); } elsif ($ptype eq "S") { - push(@status, $pvalue); + push(@status, $pvalue . $suffix); } } } @@ -2456,17 +2462,23 @@ sub clean_file_emails { foreach my $email (@file_emails) { $email =~ s/[\(\<\{]{0,1}([A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+)[\)\>\}]{0,1}/\<$1\>/g; my ($name, $address) = parse_email($email); - if ($name eq '"[,\.]"') { - $name = ""; - } - my @nw = split(/[^A-Za-zÀ-ÿ\'\,\.\+-]/, $name); + # Strip quotes for easier processing, format_email will add them back + $name =~ s/^"(.*)"$/$1/; + + # Split into name-like parts and remove stray punctuation particles + my @nw = split(/[^\p{L}\'\,\.\+-]/, $name); + @nw = grep(!/^[\'\,\.\+-]$/, @nw); + + # Make a best effort to extract the name, and only the name, by taking + # only the last two names, or in the case of obvious initials, the last + # three names. if (@nw > 2) { my $first = $nw[@nw - 3]; my $middle = $nw[@nw - 2]; my $last = $nw[@nw - 1]; - if (((length($first) == 1 && $first =~ m/[A-Za-z]/) || + if (((length($first) == 1 && $first =~ m/\p{L}/) || (length($first) == 2 && substr($first, -1) eq ".")) || (length($middle) == 1 || (length($middle) == 2 && substr($middle, -1) eq "."))) { @@ -2474,18 +2486,16 @@ sub clean_file_emails { } else { $name = "$middle $last"; } + } else { + $name = "@nw"; } if (substr($name, -1) =~ /[,\.]/) { $name = substr($name, 0, length($name) - 1); - } elsif (substr($name, -2) =~ /[,\.]"/) { - $name = substr($name, 0, length($name) - 2) . '"'; } if (substr($name, 0, 1) =~ /[,\.]/) { $name = substr($name, 1, length($name) - 1); - } elsif (substr($name, 0, 2) =~ /"[,\.]/) { - $name = '"' . substr($name, 2, length($name) - 2); } my $fmt_email = format_email($name, $address, $email_usename); |