scripts/get_maintainer.pl: add --file-emails, find embedded email add…

…resses

Add an imperfect option to search a source file for email addresses.

New option:  --file-emails or --fe

email addresses in files are freeform text and are nearly impossible to
parse.  Still, might as well try to do a somewhat acceptable job of
finding them.  This code should find all addresses that are in the form
[email protected]

The code assumes that up to 3 alphabetic words along with dashes, commas,
and periods that preceed the email address are a name.

If 3 words are found for the name, and one of the first two words are a
single letter and period, or just a single letter then the 3 words are use
as name otherwise the last 2 words are used.

Some variants that are shown correctly:
    John Smith <[email protected]>
    Random J. Developer <[email protected]>
    Random J. Developer ([email protected])
    J. Random Developer [email protected]

Variants that are shown nominally correctly:
    Written by First Last ([email protected])
is shown as:
    First Last <[email protected]>

Variants that are shown incorrectly:
    Some Really Long Name <[email protected]>
    MontaVista Software, Inc. <[email protected]>
are returned as:
    Long Name <[email protected]>
    "Software, Inc" <[email protected]>

--roles and --rolestats show "(in file)" for matches.

For instance:

Without -file-emails:

$ ./scripts/get_maintainer.pl -f -nogit -roles net/core/netpoll.c
David S. Miller <[email protected]> (maintainer:NETWORKING [GENERAL])
[email protected] (open list)

With -fe:

$ ./scripts/get_maintainer.pl -f -fe -nogit -roles net/core/netpoll.c
David S. Miller <[email protected]> (maintainer:NETWORKING [GENERAL])
Matt Mackall <[email protected]> (in file)
Ingo Molnar <[email protected]> (in file)
[email protected] (open list)
[email protected] (open list:NETWORKING [GENERAL])

The number of email addresses in the file in not limited.  Neither is the
number of returned email addresses.

Signed-off-by: Joe Perches <[email protected]>
Cc: Matt Mackall <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

scripts/get_maintainer.pl

@@ -41,6 +41,7 @@
 my $subsystem = 0;
 my $status = 0;
 my $keywords = 1;
+my $file_emails = 0;
 my $from_filename = 0;
 my $pattern_depth = 0;
 my $version = 0;
@@ -120,6 +121,7 @@
 		'web!' => \$web,
 		'pattern-depth=i' => \$pattern_depth,
 		'k|keywords!' => \$keywords,
+		'fe|file-emails!' => \$file_emails,
 		'f|file' => \$from_filename,
 		'v|version' => \$version,
 		'h|help' => \$help,
@@ -232,6 +234,7 @@
 my @files = ();
 my @range = ();
 my @keyword_tvi = ();
+my @file_emails = ();
 
 foreach my $file (@ARGV) {
     ##if $file is a directory and it lacks a trailing slash, add one
@@ -242,15 +245,21 @@
     }
     if ($from_filename) {
 	push(@files, $file);
-	if (-f $file && $keywords) {
+	if (-f $file && ($keywords || $file_emails)) {
 	    open(FILE, "<$file") or die "$P: Can't open ${file}\n";
 	    my $text = do { local($/) ; <FILE> };
-	    foreach my $line (keys %keyword_hash) {
-		if ($text =~ m/$keyword_hash{$line}/x) {
-		    push(@keyword_tvi, $line);
+	    close(FILE);
+	    if ($keywords) {
+		foreach my $line (keys %keyword_hash) {
+		    if ($text =~ m/$keyword_hash{$line}/x) {
+			push(@keyword_tvi, $line);
+		    }
 		}
 	    }
-	    close(FILE);
+	    if ($file_emails) {
+		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;
+		push(@file_emails, clean_file_emails(@poss_addr));
+	    }
 	}
     } else {
 	my $file_cnt = @files;
@@ -285,6 +294,8 @@
     }
 }
 
+@file_emails = uniq(@file_emails);
+
 my @email_to = ();
 my @list_to = ();
 my @scm = ();
@@ -377,6 +388,14 @@
 	    }
 	}
     }
+
+    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');
+    }
 }
 
 if ($email || $email_list) {
@@ -453,6 +472,7 @@ sub usage {
     --remove-duplicates => minimize duplicate email names/addresses
     --roles => show roles (status:subsystem, git-signer, list, etc...)
     --rolestats => show roles and statistics (commits/total_commits, %)
+    --file-emails => add email addresses found in -f file (default: 0 (off))
   --scm => print SCM tree(s) if any
   --status => print status if any
   --subsystem => print subsystem name if any
@@ -811,15 +831,19 @@ sub add_role {
     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 $entry_address) {
+	    if (($name eq $entry_name || $address eq $entry_address)
+		&& ($role eq "" || !($entry->[1] =~ m/$role/))
+	    ) {
 		if ($entry->[1] eq "") {
 		    $entry->[1] = "$role";
 		} else {
 		    $entry->[1] = "$entry->[1],$role";
 		}
 	    }
 	} else {
-	    if ($email eq $entry->[0]) {
+	    if ($email eq $entry->[0]
+		&& ($role eq "" || !($entry->[1] =~ m/$role/))
+	    ) {
 		if ($entry->[1] eq "") {
 		    $entry->[1] = "$role";
 		} else {
@@ -1099,6 +1123,51 @@ sub sort_and_uniq {
     return @parms;
 }
 
+sub clean_file_emails {
+    my (@file_emails) = @_;
+    my @fmt_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);
+	if (@nw > 2) {
+	    my $first = $nw[@nw - 3];
+	    my $middle = $nw[@nw - 2];
+	    my $last = $nw[@nw - 1];
+
+	    if (((length($first) == 1 && $first =~ m/[A-Za-z]/) ||
+		 (length($first) == 2 && substr($first, -1) eq ".")) ||
+		(length($middle) == 1 ||
+		 (length($middle) == 2 && substr($middle, -1) eq "."))) {
+		$name = "$first $middle $last";
+	    } else {
+		$name = "$middle $last";
+	    }
+	}
+
+	if (substr($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);
+	push(@fmt_emails, $fmt_email);
+    }
+    return @fmt_emails;
+}
+
 sub merge_email {
     my @lines;
     my %saw;