tools/generate_authors.pl: avoid duplicates

Officially, the local part of an email address is case sensitive, but in
practice this is ignored. Ensure that duplicate email addresses are not
listed.

While at it, detect duplicates using `grep -Po '<\K[^>]+' AUTHORS |
tr '[:upper:]' '[:lower:]' | sort | uniq -cd` and resolve them.

Change-Id: Ie1e853d6253758c8454d9583f0a11f317c8390cb
Reviewed-on: https://code.wireshark.org/review/14659
Reviewed-by: Peter Wu <peter@lekensteyn.nl>
Petri-Dish: Peter Wu <peter@lekensteyn.nl>
Tested-by: Petri Dish Buildbot <buildbot-no-reply@wireshark.org>
Reviewed-by: Michael Mann <mmann78@netscape.net>

AUTHORS

@@ -3523,6 +3523,7 @@ Subramanian Ramachandran <sramach6[AT]ncsu.edu> {
 
 Manuel Hofer		<manuel[At]mnlhfr.at> {
 	OpenVPN dissector
+	SSTP Dissection
 }
 
 Gaurav Patwardhan	<gspatwar[AT]ncsu.edu> {
@@ -3658,10 +3659,6 @@ Dario Lombardo		<lomato[AT]gmail.com> {
 	HCrt (Hotline Command-Response Transaction) dissector
 }
 
-Manuel Hofer		<manuel[AT]mnlhfr.at> {
-  SSTP Dissection
-}
-
 Pratik Yeole		<pyeole[AT]ncsu.edu> {
          Fixed incorrect decoding of Network Layer Reachability Information (NLRI) in BGP UPDATE message with add-path support
 }
@@ -3952,7 +3949,6 @@ Andreas Urke		<arurke[AT]netwurke.com>
 Andrei Cipu		<acipu[AT]ixiacom.com>
 Andrew Chernyh		<andrew.chernyh[AT]gmail.com>
 Andrew Hoag		<Andrew.Hoag[AT]aireon.com>
-Andrew Hoag		<andrew.hoag[AT]aireon.com>
 Andy Ling		<Andy.Ling[AT]quantel.com>
 Andy Ling		<andy.ling[AT]s-a-m.com>
 Anndy Ke		<anndymaktub[AT]yahoo.com.tw>
@@ -4064,7 +4060,6 @@ Joseph Huffman		<jhuffman[AT]codeaurora.org>
 Josip Medved		<jmedved[AT]jmedved.com>
 Juan Jose Martin Carrascosa <juanjo[AT]rti.com>
 Juan Matias		<jmrepetti[AT]gmail.com>
-Juanjo Martin		<juanjo[AT]rti.com>
 Julien STAUB		<atsju2[AT]yahoo.fr>
 Jun Wang		<sdn_app[AT]163.com>
 JustinKu		<jiunrong[AT]gmail.com>
@@ -4143,7 +4138,6 @@ Pedro Jose Marron	<pjmarron[AT]locoslab.com>
 Peng Li			<seudut[AT]gmail.com>
 Peng Tao		<tao.peng[AT]primarydata.com>
 Peter Membrey		<peter[AT]membrey.hk>
-Peter Palúch		<Peter.Paluch[AT]fri.uniza.sk>
 Peter Ross		<peter.ross[AT]dsto.defence.gov.au>
 Petr Gotthard		<petr.gotthard[AT]honeywell.com>
 Petr Štetiar		<petr.stetiar[AT]gaben.cz>

AUTHORS.src

@@ -3523,6 +3523,7 @@ Subramanian Ramachandran <sramach6[AT]ncsu.edu> {
 
 Manuel Hofer		<manuel[At]mnlhfr.at> {
 	OpenVPN dissector
+	SSTP Dissection
 }
 
 Gaurav Patwardhan	<gspatwar[AT]ncsu.edu> {
@@ -3658,10 +3659,6 @@ Dario Lombardo		<lomato[AT]gmail.com> {
 	HCrt (Hotline Command-Response Transaction) dissector
 }
 
-Manuel Hofer		<manuel[AT]mnlhfr.at> {
-  SSTP Dissection
-}
-
 Pratik Yeole		<pyeole[AT]ncsu.edu> {
          Fixed incorrect decoding of Network Layer Reachability Information (NLRI) in BGP UPDATE message with add-path support
 }

tools/generate_authors.pl

@@ -1,10 +1,5 @@
 #!/usr/bin/perl
 
-my $debug = 0;
-# 0: off
-# 1: specific debug
-# 2: full debug
-
 #
 # Generate the AUTHORS file combining existing AUTHORS file with
 # git commit log.
@@ -103,11 +98,13 @@ sub trim($)
 
 sub parse_author_name {
 	my $full_name = $_[0];
+	my $email_key;
 
 	if ($full_name =~ /^([\w\.\-\'\x80-\xff]+(\s*[\w+\.\-\'\x80-\xff])*)\s+<([^>]*)>/) {
 		#Make an exception for Gerald because he's part of the header
 		if ($3 ne "gerald[AT]wireshark.org") {
-			$contributors{$3} = $1;
+			$email_key = lc($3);
+			$contributors{$email_key} = $1;
 			print encode('UTF-8', "$full_name\n");
 		}
 	} elsif ($full_name =~ /^([\w\.\-\'\x80-\xff]+(\s*[\w+\.\-\'\x80-\xff])*)\s+\(/) {
@@ -120,6 +117,7 @@ sub parse_git_name {
 	my $full_name = $_[0];
 	my $name;
 	my $email;
+	my $email_key;
 	my $len;
 	my $ntab = 3;
 	my $line;
@@ -130,8 +128,9 @@ sub parse_git_name {
 		#Convert real email address to "spam proof" one
 		$email = trim($2);
 		$email =~ s/@/[AT]/g;
+		$email_key = lc($email);
 
-		if (!exists($contributors{ $email })) {
+		if (!exists($contributors{ $email_key })) {
 			#Make an exception for Gerald because he's part of the header
 			if ($email ne "gerald[AT]wireshark.org") {
 				$len = length $name;
@@ -142,6 +141,7 @@ sub parse_git_name {
 					$ntab +=1 if ($len % 8);
 					$line = $name . "\t" x $ntab . "<$email>";
 				}
+				$contributors{$email_key} = $1;
 				print encode('UTF-8', "$line\n");
 			}
 		}