Index: head/tools/tools/locale/tools/charmaps.pm
===================================================================
--- head/tools/tools/locale/tools/charmaps.pm	(revision 352273)
+++ head/tools/tools/locale/tools/charmaps.pm	(revision 352274)
@@ -1,160 +1,184 @@
 #!/usr/local/bin/perl -w
 
+# SPDX-License-Identifier: BSD-2-Clause-FreeBSD
+#
+# Copyright 2009 Edwin Groothuis <edwin@FreeBSD.org>
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
 #
 # $FreeBSD$
 #
 
 use strict;
 use XML::Parser;
 use Data::Dumper;
 
 my %data = ();
 my %d = ();
 my $index = -1;
 
 sub get_xmldata {
 	my $etcdir = shift;
 
 	open(FIN, "$etcdir/charmaps.xml");
 	my @xml = <FIN>;
 	chomp(@xml);
 	close(FIN);
 
 	my $xml = new XML::Parser(Handlers => {
 					Start	=> \&h_start,
 					End	=> \&h_end,
 					Char	=> \&h_char
 					});
 	$xml->parse(join("", @xml));
 	return %d;
 }
 
 sub h_start {
 	my $expat = shift;
 	my $element = shift;
 	my @attrs = @_;
 	my %attrs = ();
 
 
 	while ($#attrs >= 0) {
 		$attrs{$attrs[0]} = $attrs[1];
 		shift(@attrs);
 		shift(@attrs);
 	}
 
 	$data{element}{++$index} = $element;
 
 	if ($index == 2
 	 && $data{element}{1} eq "languages"
 	 && $element eq "language") {
 		my $name = $attrs{name};
 		my $countries = $attrs{countries};
 		my $encoding = $attrs{encoding};
 		my $family = $attrs{family};
 		my $f = defined $attrs{family} ? $attrs{family} : "x";
 		my $nc_link = $attrs{namecountry_link};
 		my $e_link = $attrs{encoding_link};
 		my $fallback = $attrs{fallback};
 		my $definitions = $attrs{definitions};
 
 		$d{L}{$name}{$f}{fallback} = $fallback;
 		$d{L}{$name}{$f}{e_link} = $e_link;
 		$d{L}{$name}{$f}{nc_link} = $nc_link;
 		$d{L}{$name}{$f}{family} = $family;
 		$d{L}{$name}{$f}{encoding} = $encoding;
 		$d{L}{$name}{$f}{definitions} = $definitions;
 		$d{L}{$name}{$f}{countries} = $countries;
 		foreach my $c (split(" ", $countries)) {
 			if (defined $encoding) {
 				foreach my $e (split(" ", $encoding)) {
 					$d{L}{$name}{$f}{data}{$c}{$e} = undef;
 					$d{E}{$e} = 0;	# not read
 				}
 			}
 			$d{L}{$name}{$f}{data}{$c}{"UTF-8"} = undef;
 		}
 		return;
 	}
 
 	if ($index == 2
 	 && $data{element}{1} eq "translations"
 	 && $element eq "translation") {
 		foreach my $e (split(" ", $attrs{encoding})) {
 			if (defined $attrs{hex}) {
 				my $k = $attrs{cldr};
 				my $hs = $attrs{hex};
 				$d{T}{$e}{$k}{hex} = $hs;
 			}
 			if (defined $attrs{string}) {
 				my $s = "";
 				for (my $i = 0; $i < length($attrs{string}); $i++) {
 					$s .= sprintf("%02x",
 					    ord(substr($attrs{string}, $i, 1)));
 				}
 				$d{T}{$e}{$attrs{cldr}}{hex} = $s;
 			}
 			if (defined $attrs{unicode}) {
 				my $k = $attrs{cldr};
 				my $uc = $attrs{unicode};
 				$d{T}{$e}{$k}{unicode} = $uc;
 			}
 			if (defined $attrs{ucc}) {
 				my $k = $attrs{cldr};
 				my $uc = $attrs{ucc};
 				$d{T}{$e}{$k}{ucc} = $uc;
 			}
 		}
 		return;
 	}
 
 	if ($index == 2
 	 && $data{element}{1} eq "alternativemonths"
 	 && $element eq "language") {
 		my $name = $attrs{name};
 		my $countries = $attrs{countries};
 
 		$data{fields}{name} = $name;
 		$data{fields}{countries} = $countries;
 		$data{fields}{text} = "";
 
 		return;
 	}
 }
 
 sub h_end {
 	my $expat = shift;
 	my $element = shift;
 
 	if ($index == "2") {
 		if ($data{element}{1} eq "alternativemonths"
 		 && $data{element}{2} eq "language") {
 			foreach my $c (split(/,/, $data{fields}{countries})) {
 				my $m = $data{fields}{text};
 
 				$m =~ s/^[\t ]//g;
 				$m =~ s/[\t ]$//g;
 				$d{AM}{$data{fields}{name}}{$c} = $m;
 			}
 			$data{fields} = ();
 		}
 	}
 
 	$index--;
 }
 
 sub h_char {
 	my $expat = shift;
 	my $string = shift;
 
 	if ($index == "2") {
 		if ($data{element}{1} eq "alternativemonths"
 		 && $data{element}{2} eq "language") {
 			$data{fields}{text} .= $string;
 		}
 	}
 }
 
 #use Data::Dumper;
 #my %D = get_xmldata();
 #print Dumper(%D);
 1;
Index: head/tools/tools/locale/tools/cldr2def.pl
===================================================================
--- head/tools/tools/locale/tools/cldr2def.pl	(revision 352273)
+++ head/tools/tools/locale/tools/cldr2def.pl	(revision 352274)
@@ -1,1017 +1,1044 @@
 #!/usr/local/bin/perl -wC
+
+# SPDX-License-Identifier: BSD-2-Clause-FreeBSD
+#
+# Copyright 2009 Edwin Groothuis <edwin@FreeBSD.org>
+# Copyright 2015 John Marino <draco@marino.st>
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
 # $FreeBSD$
 
 use strict;
 use File::Copy;
 use XML::Parser;
 use Tie::IxHash;
 use Text::Iconv;
 #use Data::Dumper;
 use Getopt::Long;
 use Digest::SHA qw(sha1_hex);
 require "charmaps.pm";
 
 
 if ($#ARGV < 2) {
 	print "Usage: $0 --unidir=<unidir> --etc=<etcdir> --type=<type>\n";
 	exit(1);
 }
 
 my $DEFENCODING = "UTF-8";
 
 my $UNIDIR = undef;
 my $ETCDIR = undef;
 my $TYPE = undef;
 
 my $result = GetOptions (
 		"unidir=s"	=> \$UNIDIR,
 		"etc=s"		=> \$ETCDIR,
 		"type=s"	=> \$TYPE,
 	    );
 
 my %convertors = ();
 
 my %ucd = ();
 my %values = ();
 my %hashtable = ();
 my %languages = ();
 my %translations = ();
 my %encodings = ();
 my %alternativemonths = ();
 get_languages();
 
 my %utf8map = ();
 my %utf8aliases = ();
 get_unidata($UNIDIR);
 get_utf8map("$UNIDIR/posix/$DEFENCODING.cm");
 get_encodings("$ETCDIR/charmaps");
 
 my %keys = ();
 tie(%keys, "Tie::IxHash");
 tie(%hashtable, "Tie::IxHash");
 
 my %FILESNAMES = (
 	"monetdef"	=> "LC_MONETARY",
 	"timedef"	=> "LC_TIME",
 	"msgdef"	=> "LC_MESSAGES",
 	"numericdef"	=> "LC_NUMERIC",
 	"colldef"	=> "LC_COLLATE",
 	"ctypedef"	=> "LC_CTYPE"
 );
 
 my %callback = (
 	mdorder => \&callback_mdorder,
 	altmon => \&callback_altmon,
 	cformat => \&callback_cformat,
 	dformat => \&callback_dformat,
 	dtformat => \&callback_dtformat,
 	cbabmon => \&callback_abmon,
 	cbampm => \&callback_ampm,
 	data => undef,
 );
 
 my %DESC = (
 
 	# numericdef
 	"decimal_point"	=> "decimal_point",
 	"thousands_sep"	=> "thousands_sep",
 	"grouping"	=> "grouping",
 
 	# monetdef
 	"int_curr_symbol"	=> "int_curr_symbol (last character always " .
 				   "SPACE)",
 	"currency_symbol"	=> "currency_symbol",
 	"mon_decimal_point"	=> "mon_decimal_point",
 	"mon_thousands_sep"	=> "mon_thousands_sep",
 	"mon_grouping"		=> "mon_grouping",
 	"positive_sign"		=> "positive_sign",
 	"negative_sign"		=> "negative_sign",
 	"int_frac_digits"	=> "int_frac_digits",
 	"frac_digits"		=> "frac_digits",
 	"p_cs_precedes"		=> "p_cs_precedes",
 	"p_sep_by_space"	=> "p_sep_by_space",
 	"n_cs_precedes"		=> "n_cs_precedes",
 	"n_sep_by_space"	=> "n_sep_by_space",
 	"p_sign_posn"		=> "p_sign_posn",
 	"n_sign_posn"		=> "n_sign_posn",
 
 	# msgdef
 	"yesexpr"	=> "yesexpr",
 	"noexpr"	=> "noexpr",
 	"yesstr"	=> "yesstr",
 	"nostr"		=> "nostr",
 
 	# timedef
 	"abmon"		=> "Short month names",
 	"mon"		=> "Long month names (as in a date)",
 	"abday"		=> "Short weekday names",
 	"day"		=> "Long weekday names",
 	"t_fmt"		=> "X_fmt",
 	"d_fmt"		=> "x_fmt",
 	"c_fmt"		=> "c_fmt",
 	"am_pm"		=> "AM/PM",
 	"d_t_fmt"	=> "date_fmt",
 	"altmon"	=> "Long month names (without case ending)",
 	"md_order"	=> "md_order",
 	"t_fmt_ampm"	=> "ampm_fmt",
 );
 
 if ($TYPE eq "colldef") {
 	transform_collation();
 	make_makefile();
 }
 
 if ($TYPE eq "ctypedef") {
 	transform_ctypes();
 	make_makefile();
 }
 
 if ($TYPE eq "numericdef") {
 	%keys = (
 	    "decimal_point"	=> "s",
 	    "thousands_sep"	=> "s",
 	    "grouping"		=> "ai",
 	);
 	get_fields();
 	print_fields();
 	make_makefile();
 }
 
 if ($TYPE eq "monetdef") {
 	%keys = (
 	    "int_curr_symbol"	=> "s",
 	    "currency_symbol"	=> "s",
 	    "mon_decimal_point"	=> "s",
 	    "mon_thousands_sep"	=> "s",
 	    "mon_grouping"	=> "ai",
 	    "positive_sign"	=> "s",
 	    "negative_sign"	=> "s",
 	    "int_frac_digits"	=> "i",
 	    "frac_digits"	=> "i",
 	    "p_cs_precedes"	=> "i",
 	    "p_sep_by_space"	=> "i",
 	    "n_cs_precedes"	=> "i",
 	    "n_sep_by_space"	=> "i",
 	    "p_sign_posn"	=> "i",
 	    "n_sign_posn"	=> "i"
 	);
 	get_fields();
 	print_fields();
 	make_makefile();
 }
 
 if ($TYPE eq "msgdef") {
 	%keys = (
 	    "yesexpr"		=> "s",
 	    "noexpr"		=> "s",
 	    "yesstr"		=> "s",
 	    "nostr"		=> "s"
 	);
 	get_fields();
 	print_fields();
 	make_makefile();
 }
 
 if ($TYPE eq "timedef") {
 	%keys = (
 	    "abmon"		=> "<cbabmon<abmon<as",
 	    "mon"		=> "as",
 	    "abday"		=> "as",
 	    "day"		=> "as",
 	    "t_fmt"		=> "s",
 	    "d_fmt"		=> "<dformat<d_fmt<s",
 	    "c_fmt"		=> "<cformat<d_t_fmt<s",
 	    "am_pm"		=> "<cbampm<am_pm<as",
 	    "d_t_fmt"		=> "<dtformat<d_t_fmt<s",
 	    "altmon"		=> "<altmon<mon<as",
 	    "md_order"		=> "<mdorder<d_fmt<s",
 	    "t_fmt_ampm"	=> "s",
 	);
 	get_fields();
 	print_fields();
 	make_makefile();
 }
 
 sub callback_ampm {
 	my $s = shift;
 	my $nl = $callback{data}{l} . "_" . $callback{data}{c};
 	my $enc = $callback{data}{e};
 
 	if ($nl eq 'ru_RU') {
 		if ($enc eq 'UTF-8') {
 			$s = 'дп;пп';
 		} else {
 			my  $converter = Text::Iconv->new("utf-8", "$enc");
 			$s = $converter->convert("дп;пп");
 		}
 	}
 	return $s;
 }
 
 sub callback_cformat {
 	my $s = shift;
 	my $nl = $callback{data}{l} . "_" . $callback{data}{c};
 
 	if ($nl eq 'ko_KR') {
 		$s =~ s/(> )(%p)/$1%A $2/;
 	}
 	$s =~ s/\.,/\./;
 	$s =~ s/ %Z//;
 	$s =~ s/ %z//;
 	$s =~ s/^"%e\./%A %e/;
 	$s =~ s/^"(%B %e, )/"%A, $1/;
 	$s =~ s/^"(%e %B )/"%A $1/;
 	return $s;
 };
 
 sub callback_dformat {
 	my $s = shift;
 
 	$s =~ s/(%m(<SOLIDUS>|[-.]))%e/$1%d/;
 	$s =~ s/%e((<SOLIDUS>|[-.])%m)/%d$1/;
 	return $s;
 };
 
 sub callback_dtformat {
 	my $s = shift;
 	my $nl = $callback{data}{l} . "_" . $callback{data}{c};
 
 	if ($nl eq 'ja_JP') {
 		$s =~ s/(> )(%H)/$1%A $2/;
 	} elsif ($nl eq 'ko_KR' || $nl eq 'zh_CN' || $nl eq 'zh_TW') {
 		if ($nl ne 'ko_KR') {
 			$s =~ s/%m/%_m/;
 		}
 		$s =~ s/(> )(%p)/$1%A $2/;
 	}
 	$s =~ s/\.,/\./;
 	$s =~ s/^"%e\./%A %e/;
 	$s =~ s/^"(%B %e, )/"%A, $1/;
 	$s =~ s/^"(%e %B )/"%A $1/;
 	return $s;
 };
 
 sub callback_mdorder {
 	my $s = shift;
 	return undef if (!defined $s);
 	$s =~ s/[^dem]//g;
 	$s =~ s/e/d/g;
 	return $s;
 };
 
 sub callback_altmon {
 	# if the language/country is known in %alternative months then
 	# return that, otherwise repeat mon
 	my $s = shift;
 
 	if (defined $alternativemonths{$callback{data}{l}}{$callback{data}{c}}) {
 		my @altnames = split(";",$alternativemonths{$callback{data}{l}}{$callback{data}{c}});
 		my @cleaned;
 		foreach (@altnames)
 		{
 			$_ =~ s/^\s+//;
 			$_ =~ s/\s+$//;
 			push @cleaned, $_;
 		}
 		return join(";",@cleaned);
 	}
 
 	return $s;
 }
 
 sub callback_abmon {
 	# for specified CJK locales, pad result with a space to enable
 	# columns to line up (style established in FreeBSD in 2001)
 	my $s = shift;
 	my $nl = $callback{data}{l} . "_" . $callback{data}{c};
 
 	if ($nl eq 'ja_JP' || $nl eq 'ko_KR' || $nl eq 'zh_CN' ||
 	    $nl eq 'zh_HK' || $nl eq 'zh_TW') {
 		my @monthnames = split(";", $s);
 		my @cleaned;
 		foreach (@monthnames)
 		{
 			if ($_ =~ /^"<(two|three|four|five|six|seven|eight|nine)>/ ||
 			   ($_ =~ /^"<one>/ && $_ !~ /^"<one>(<zero>|<one>|<two>)/))
 			{
 				$_ =~ s/^"/"<space>/;
 			}
 			push @cleaned, $_;
 		}
 		return join(";",@cleaned);
 	}
 	return $s;
 }
 
 ############################
 
 sub get_unidata {
 	my $directory = shift;
 
 	open(FIN, "$directory/UnicodeData.txt")
 	    or die("Cannot open $directory/UnicodeData.txt");;
 	my @lines = <FIN>;
 	chomp(@lines);
 	close(FIN);
 
 	foreach my $l (@lines) {
 		my @a = split(/;/, $l);
 
 		$ucd{code2name}{"$a[0]"} = $a[1];	# Unicode name
 		$ucd{name2code}{"$a[1]"} = $a[0];	# Unicode code
 	}
 }
 
 sub get_utf8map {
 	my $file = shift;
 
 	open(FIN, $file);
 	my @lines = <FIN>;
 	close(FIN);
 	chomp(@lines);
 
 	my $prev_k = undef;
 	my $prev_v = "";
 	my $incharmap = 0;
 	foreach my $l (@lines) {
 		$l =~ s/\r//;
 		next if ($l =~ /^\#/);
 		next if ($l eq "");
 
 		if ($l eq "CHARMAP") {
 			$incharmap = 1;
 			next;
 		}
 
 		next if (!$incharmap);
 		last if ($l eq "END CHARMAP");
 
 		$l =~ /^<([^\s]+)>\s+(.*)/;
 		my $k = $1;
 		my $v = $2;
 		$k =~ s/_/ /g;		# unicode char string
 		$v =~ s/\\x//g;		# UTF-8 char code
 		$utf8map{$k} = $v;
 
 		$utf8aliases{$k} = $prev_k if ($prev_v eq $v);
 
 		$prev_v = $v;
 		$prev_k = $k;
 	}
 }
 
 sub get_encodings {
 	my $dir = shift;
 	foreach my $e (sort(keys(%encodings))) {
 		if (!open(FIN, "$dir/$e.TXT")) {
 			print "Cannot open charmap for $e\n";
 			next;
 
 		}
 		$encodings{$e} = 1;
 		my @lines = <FIN>;
 		close(FIN);
 		chomp(@lines);
 		foreach my $l (@lines) {
 			$l =~ s/\r//;
 			next if ($l =~ /^\#/);
 			next if ($l eq "");
 
 			my @a = split(" ", $l);
 			next if ($#a < 1);
 			$a[0] =~ s/^0[xX]//;	# local char code
 			$a[1] =~ s/^0[xX]//;	# unicode char code
 			$convertors{$e}{uc($a[1])} = uc($a[0]);
 		}
 	}
 }
 
 sub get_languages {
 	my %data = get_xmldata($ETCDIR);
 	%languages = %{$data{L}}; 
 	%translations = %{$data{T}}; 
 	%alternativemonths = %{$data{AM}}; 
 	%encodings = %{$data{E}}; 
 }
 
 sub transform_ctypes {
 	# Add the C.UTF-8
 	$languages{"C"}{"x"}{data}{"x"}{$DEFENCODING} = undef;
 
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 0;	# unread
 		my $file = $l;
 		$file .= "_" . $f if ($f ne "x");
 		$file .= "_" . $c if ($c ne "x");
 		my $actfile = $file;
 
 		my $filename = "$UNIDIR/posix/xx_Comm_C.UTF-8.src";
 		if (! -f $filename) {
 			print STDERR "Cannot open $filename\n";
 			next;
 		}
 		open(FIN, "$filename");
 		print "Reading from $filename for ${l}_${f}_${c}\n";
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 1;	# read
 		my @lines;
 		my $shex;
 		my $uhex;
 		while (<FIN>) {
 			push @lines, $_;
 		}
 		close(FIN);
 		$shex = sha1_hex(join("\n", @lines));
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = $shex;
 		$hashtable{$shex}{"${l}_${f}_${c}.$DEFENCODING"} = 1;
 		open(FOUT, ">$TYPE.draft/$actfile.$DEFENCODING.src");
 		print FOUT @lines;
 		close(FOUT);
 		foreach my $enc (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 			next if ($enc eq $DEFENCODING);
 			$filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 			if (! -f $filename) {
 				print STDERR "Cannot open $filename\n";
 				next;
 			}
 			@lines = ();
 			open(FIN, "$filename");
 			while (<FIN>) {
 				if ((/^comment_char\s/) || (/^escape_char\s/)){
 					push @lines, $_;
 				}
 				if (/^LC_CTYPE/../^END LC_CTYPE/) {
 					push @lines, $_;
 				}
 			}
 			close(FIN);
 			$uhex = sha1_hex(join("\n", @lines) . $enc);
 			$languages{$l}{$f}{data}{$c}{$enc} = $uhex;
 			$hashtable{$uhex}{"${l}_${f}_${c}.$enc"} = 1;
 			open(FOUT, ">$TYPE.draft/$actfile.$enc.src");
 			print FOUT <<EOF;
 # Warning: Do not edit. This file is automatically extracted from the
 # tools in /usr/src/tools/tools/locale. The data is obtained from the
 # CLDR project, obtained from http://cldr.unicode.org/
 # -----------------------------------------------------------------------------
 EOF
 			print FOUT @lines;
 			close(FOUT);
 		}
 	}
 	}
 	}
 }
 
 
 sub transform_collation {
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 0;	# unread
 		my $file;
 		$file = $l . "_";
 		$file .= $f . "_" if ($f ne "x");
 		$file .= $c;
 		my $actfile = $file;
 
 		my $filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 		$filename = "$ETCDIR/$file.$DEFENCODING.src"
 		    if (! -f $filename);
 		if (! -f $filename
 		 && defined $languages{$l}{$f}{fallback}) {
 			$file = $languages{$l}{$f}{fallback};
 			$filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 		}
 		$filename = "$UNIDIR/posix/$file.$DEFENCODING.src"
 		    if (! -f $filename);
 		if (! -f $filename) {
 			print STDERR
 			    "Cannot open $file.$DEFENCODING.src or fallback\n";
 			next;
 		}
 		open(FIN, "$filename");
 		print "Reading from $filename for ${l}_${f}_${c}\n";
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 1;	# read
 		my @lines;
 		my $shex;
 		while (<FIN>) {
 			if ((/^comment_char\s/) || (/^escape_char\s/)){
 				push @lines, $_;
 			}
 			if (/^LC_COLLATE/../^END LC_COLLATE/) {
 				$_ =~ s/[ ]+/ /g;
 				push @lines, $_;
 			}
 		}
 		close(FIN);
 		$shex = sha1_hex(join("\n", @lines));
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = $shex;
 		$hashtable{$shex}{"${l}_${f}_${c}.$DEFENCODING"} = 1;
 		open(FOUT, ">$TYPE.draft/$actfile.$DEFENCODING.src");
 		print FOUT <<EOF;
 # Warning: Do not edit. This file is automatically extracted from the
 # tools in /usr/src/tools/tools/locale. The data is obtained from the
 # CLDR project, obtained from http://cldr.unicode.org/
 # -----------------------------------------------------------------------------
 EOF
 		print FOUT @lines;
 		close(FOUT);
 
 		foreach my $enc (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 			next if ($enc eq $DEFENCODING);
 			copy ("$TYPE.draft/$actfile.$DEFENCODING.src",
 			      "$TYPE.draft/$actfile.$enc.src");
 			$languages{$l}{$f}{data}{$c}{$enc} = $shex;
 			$hashtable{$shex}{"${l}_${f}_${c}.$enc"} = 1;
 		}
 	}
 	}
 	}
 }
 
 sub get_fields {
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 0;	# unread
 		my $file;
 		$file = $l . "_";
 		$file .= $f . "_" if ($f ne "x");
 		$file .= $c;
 
 		my $filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 		$filename = "$ETCDIR/$file.$DEFENCODING.src"
 		    if (! -f $filename);
 		if (! -f $filename
 		 && defined $languages{$l}{$f}{fallback}) {
 			$file = $languages{$l}{$f}{fallback};
 			$filename = "$UNIDIR/posix/$file.$DEFENCODING.src";
 		}
 		$filename = "$UNIDIR/posix/$file.$DEFENCODING.src"
 		    if (! -f $filename);
 		if (! -f $filename) {
 			print STDERR
 			    "Cannot open $file.$DEFENCODING.src or fallback\n";
 			next;
 		}
 		open(FIN, "$filename");
 		print "Reading from $filename for ${l}_${f}_${c}\n";
 		$languages{$l}{$f}{data}{$c}{$DEFENCODING} = 1;	# read
 		my @lines = <FIN>;
 		chomp(@lines);
 		close(FIN);
 		my $continue = 0;
 		foreach my $k (keys(%keys)) {
 			foreach my $line (@lines) {
 				$line =~ s/\r//;
 				next if (!$continue && $line !~ /^$k\s/);
 				if ($continue) {
 					$line =~ s/^\s+//;
 				} else {
 					$line =~ s/^$k\s+//;
 				}
 
 				$values{$l}{$f}{$c}{$k} = ""
 					if (!defined $values{$l}{$f}{$c}{$k});
 
 				$continue = ($line =~ /\/$/);
 				$line =~ s/\/$// if ($continue);
 
 				while ($line =~ /_/) {
 					$line =~
 					    s/\<([^>_]+)_([^>]+)\>/<$1 $2>/;
 				}
 				die "_ in data - $line" if ($line =~ /_/);
 				$values{$l}{$f}{$c}{$k} .= $line;
 
 				last if (!$continue);
 			}
 		}
 	}
 	}
 	}
 }
 
 sub decodecldr {
 	my $e = shift;
 	my $s = shift;
 
 	my $v = undef;
 
 	if ($e eq "UTF-8") {
 		#
 		# Conversion to UTF-8 can be done from the Unicode name to
 		# the UTF-8 character code.
 		#
 		$v = $utf8map{$s};
 		die "Cannot convert $s in $e (charmap)" if (!defined $v);
 	} else {
 		#
 		# Conversion to these encodings can be done from the Unicode
 		# name to Unicode code to the encodings code.
 		#
 		my $ucc = undef;
 		$ucc = $ucd{name2code}{$s} if (defined $ucd{name2code}{$s});
 		$ucc = $ucd{name2code}{$utf8aliases{$s}}
 			if (!defined $ucc
 			 && $utf8aliases{$s}
 			 && defined $ucd{name2code}{$utf8aliases{$s}});
 
 		if (!defined $ucc) {
 			if (defined $translations{$e}{$s}{hex}) {
 				$v = $translations{$e}{$s}{hex};
 				$ucc = 0;
 			} elsif (defined $translations{$e}{$s}{ucc}) {
 				$ucc = $translations{$e}{$s}{ucc};
 			}
 		}
 
 		die "Cannot convert $s in $e (ucd string)" if (!defined $ucc);
 		$v = $convertors{$e}{$ucc} if (!defined $v);
 
 		$v = $translations{$e}{$s}{hex}
 			if (!defined $v && defined $translations{$e}{$s}{hex});
 
 		if (!defined $v && defined $translations{$e}{$s}{unicode}) {
 			my $ucn = $translations{$e}{$s}{unicode};
 			$ucc = $ucd{name2code}{$ucn}
 				if (defined $ucd{name2code}{$ucn});
 			$ucc = $ucd{name2code}{$utf8aliases{$ucn}}
 				if (!defined $ucc
 				 && defined $ucd{name2code}{$utf8aliases{$ucn}});
 			$v = $convertors{$e}{$ucc};
 		}
 
 		die "Cannot convert $s in $e (charmap)" if (!defined $v);
 	}
 
 	return pack("C", hex($v)) if (length($v) == 2);
 	return pack("CC", hex(substr($v, 0, 2)), hex(substr($v, 2, 2)))
 		if (length($v) == 4);
 	return pack("CCC", hex(substr($v, 0, 2)), hex(substr($v, 2, 2)),
 	    hex(substr($v, 4, 2))) if (length($v) == 6);
 	print STDERR "Cannot convert $e $s\n";
 	return "length = " . length($v);
 
 }
 
 sub translate {
 	my $enc = shift;
 	my $v = shift;
 
 	return $translations{$enc}{$v} if (defined $translations{$enc}{$v});
 	return undef;
 }
 
 sub print_fields {
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 		foreach my $enc (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 			if ($languages{$l}{$f}{data}{$c}{$DEFENCODING} eq "0") {
 				print "Skipping ${l}_" .
 				    ($f eq "x" ? "" : "${f}_") .
 				    "${c} - not read\n";
 				next;
 			}
 			my $file = $l;
 			$file .= "_" . $f if ($f ne "x");
 			$file .= "_" . $c;
 			print "Writing to $file in $enc\n";
 
 			if ($enc ne $DEFENCODING &&
 			    !defined $convertors{$enc}) {
 				print "Failed! Cannot convert to $enc.\n";
 				next;
 			};
 
 			open(FOUT, ">$TYPE.draft/$file.$enc.new");
 			my $okay = 1;
 			my $output = "";
 			print FOUT <<EOF;
 # Warning: Do not edit. This file is automatically generated from the
 # tools in /usr/src/tools/tools/locale. The data is obtained from the
 # CLDR project, obtained from http://cldr.unicode.org/
 # -----------------------------------------------------------------------------
 EOF
 			foreach my $k (keys(%keys)) {
 				my $g = $keys{$k};
 
 				die("Unknown $k in \%DESC")
 					if (!defined $DESC{$k});
 
 				$output .= "#\n# $DESC{$k}\n";
 
 				# Replace one row with another
 				if ($g =~ /^>/) {
 					$k = substr($g, 1);
 					$g = $keys{$k};
 				}
 
 				# Callback function
 				if ($g =~ /^\</) {
 					$callback{data}{c} = $c;
 					$callback{data}{k} = $k;
 					$callback{data}{f} = $f;
 					$callback{data}{l} = $l;
 					$callback{data}{e} = $enc;
 					my @a = split(/\</, substr($g, 1));
 					my $rv =
 					    &{$callback{$a[0]}}($values{$l}{$f}{$c}{$a[1]});
 					$values{$l}{$f}{$c}{$k} = $rv;
 					$g = $a[2];
 					$callback{data} = ();
 				}
 
 				my $v = $values{$l}{$f}{$c}{$k};
 				$v = "undef" if (!defined $v);
 
 				if ($g eq "i") {
 					$output .= "$v\n";
 					next;
 				}
 				if ($g eq "ai") {
 					$output .= "$v\n";
 					next;
 				}
 				if ($g eq "s") {
 					$v =~ s/^"//;
 					$v =~ s/"$//;
 					my $cm = "";
 					while ($v =~ /^(.*?)<(.*?)>(.*)/) {
 						my $p1 = $1;
 						$cm = $2;
 						my $p3 = $3;
 
 						my $rv = decodecldr($enc, $cm);
 #						$rv = translate($enc, $cm)
 #							if (!defined $rv);
 						if (!defined $rv) {
 							print STDERR 
 "Could not convert $k ($cm) from $DEFENCODING to $enc\n";
 							$okay = 0;
 							next;
 						}
 
 						$v = $p1 . $rv . $p3;
 					}
 					$output .= "$v\n";
 					next;
 				}
 				if ($g eq "as") {
 					foreach my $v (split(/;/, $v)) {
 						$v =~ s/^"//;
 						$v =~ s/"$//;
 						my $cm = "";
 						while ($v =~ /^(.*?)<(.*?)>(.*)/) {
 							my $p1 = $1;
 							$cm = $2;
 							my $p3 = $3;
 
 							my $rv =
 							    decodecldr($enc,
 								$cm);
 #							$rv = translate($enc,
 #							    $cm)
 #							    if (!defined $rv);
 							if (!defined $rv) {
 								print STDERR 
 "Could not convert $k ($cm) from $DEFENCODING to $enc\n";
 								$okay = 0;
 								next;
 							}
 
 							$v = $1 . $rv . $3;
 						}
 						$output .= "$v\n";
 					}
 					next;
 				}
 
 				die("$k is '$g'");
 
 			}
 
 			$languages{$l}{$f}{data}{$c}{$enc} = sha1_hex($output);
 			$hashtable{sha1_hex($output)}{"${l}_${f}_${c}.$enc"} = 1;
 			print FOUT "$output# EOF\n";
 			close(FOUT);
 
 			if ($okay) {
 				rename("$TYPE.draft/$file.$enc.new",
 				    "$TYPE.draft/$file.$enc.src");
 			} else {
 				rename("$TYPE.draft/$file.$enc.new",
 				    "$TYPE.draft/$file.$enc.failed");
 			}
 		}
 	}
 	}
 	}
 }
 
 sub make_makefile {
 	print "Creating Makefile for $TYPE\n";
 	my $SRCOUT;
 	my $SRCOUT2;
 	my $SRCOUT3 = "";
 	my $SRCOUT4 = "";
 	my $MAPLOC;
 	if ($TYPE eq "colldef") {
 		$SRCOUT = "localedef \${LOCALEDEF_ENDIAN} -D -U " .
 			"-i \${.IMPSRC} \\\n" .
 			"\t-f \${MAPLOC}/map.\${.TARGET:T:R:E:C/@.*//} " .
 			"\${.OBJDIR}/\${.IMPSRC:T:R}";
 		$MAPLOC = "MAPLOC=\t\t\${.CURDIR}/../../tools/tools/" .
 				"locale/etc/final-maps\n";
 		$SRCOUT2 = "LC_COLLATE";
 		$SRCOUT3 = "" .
 			".for f t in \${LOCALES_MAPPED}\n" .
 			"FILES+=\t\$t.LC_COLLATE\n" .
 			"FILESDIR_\$t.LC_COLLATE=\t\${LOCALEDIR}/\$t\n" .
 			"\$t.LC_COLLATE: \${.CURDIR}/\$f.src\n" .
 			"\tlocaledef \${LOCALEDEF_ENDIAN} -D -U " .
 			"-i \${.ALLSRC} \\\n" .
 			"\t\t-f \${MAPLOC}/map.\${.TARGET:T:R:E:C/@.*//} \\\n" .
 			"\t\t\${.OBJDIR}/\${.TARGET:T:R}\n" .
 			".endfor\n\n";
 		$SRCOUT4 = "## LOCALES_MAPPED\n";
 	}
 	elsif ($TYPE eq "ctypedef") {
 		$SRCOUT = "localedef \${LOCALEDEF_ENDIAN} -D -U -c " .
 			"-w \${MAPLOC}/widths.txt \\\n" .
 			"\t-f \${MAPLOC}/map.\${.IMPSRC:T:R:E} " .
 			"\\\n\t-i \${.IMPSRC} \${.OBJDIR}/\${.IMPSRC:T:R} " .
 			" || true";
 		$SRCOUT2 = "LC_CTYPE";
 		$MAPLOC = "MAPLOC=\t\t\${.CURDIR}/../../tools/tools/" .
 				"locale/etc/final-maps\n";
 		$SRCOUT3 = "## SYMPAIRS\n\n" .
 			".for s t in \${SYMPAIRS}\n" .
 			"\${t:S/src\$/LC_CTYPE/}: " .
 			"\$s\n" .
 			"\tlocaledef \${LOCALEDEF_ENDIAN} -D -U -c " .
 			"-w \${MAPLOC}/widths.txt \\\n" .
 			"\t-f \${MAPLOC}/map.\${.TARGET:T:R:C/^.*\\.//} " .
 			"\\\n\t-i \${.ALLSRC} \${.OBJDIR}/\${.TARGET:T:R} " .
 			" || true\n" .
 			".endfor\n\n";
 	}
 	else {
 		$SRCOUT = "grep -v -E '^(\#\$\$|\#[ ])' < \${.IMPSRC} > \${.TARGET}";
 		$SRCOUT2 = "out";
 		$MAPLOC = "";
 	}
 	open(FOUT, ">$TYPE.draft/Makefile");
 	print FOUT <<EOF;
 # \$FreeBSD\$
 # Warning: Do not edit. This file is automatically generated from the
 # tools in /usr/src/tools/tools/locale.
 
 LOCALEDIR=	\${SHAREDIR}/locale
 FILESNAME=	$FILESNAMES{$TYPE}
 .SUFFIXES:	.src .${SRCOUT2}
 ${MAPLOC}
 EOF
 
 	if ($TYPE eq "colldef" || $TYPE eq "ctypedef") {
 		print FOUT <<EOF;
 .include <bsd.endian.mk>
 
 EOF
 	}
 
 	print FOUT <<EOF;
 .src.${SRCOUT2}:
 	$SRCOUT
 
 ## PLACEHOLDER
 
 ${SRCOUT4}
 
 EOF
 
 	foreach my $hash (keys(%hashtable)) {
 		# For colldef, weight LOCALES to UTF-8
 		#     Sort as upper-case and reverse to achieve it
 		#     Make en_US, ru_RU, and ca_AD preferred
 		my @files;
 		if ($TYPE eq "colldef") {
 			@files = sort {
 				if ($a eq 'en_x_US.UTF-8' ||
 				    $a eq 'ru_x_RU.UTF-8' ||
 				    $a eq 'ca_x_AD.UTF-8') { return -1; }
 				elsif ($b eq 'en_x_US.UTF-8' ||
 				       $b eq 'ru_x_RU.UTF-8' ||
 				       $b eq 'ca_x_AD.UTF-8') { return 1; }
 				else { return uc($b) cmp uc($a); }
 				} keys(%{$hashtable{$hash}});
 		} elsif ($TYPE eq "ctypedef") {
 			@files = sort {
 				if ($a eq 'C_x_x.UTF-8') { return -1; }
 				elsif ($b eq 'C_x_x.UTF-8') { return 1; }
 				if ($a =~ /^en_x_US/) { return -1; }
 				elsif ($b =~ /^en_x_US/) { return 1; }
 
 				if ($a =~ /^en_x_GB.ISO8859-15/ ||
 				    $a =~ /^ru_x_RU/) { return -1; }
 				elsif ($b =~ /^en_x_GB.ISO8859-15/ ||
 				       $b =~ /ru_x_RU/) { return 1; }
 				else { return uc($b) cmp uc($a); }
 
 				} keys(%{$hashtable{$hash}});
 		} else {
 			@files = sort {
 				if ($a =~ /_Comm_/ ||
 				    $b eq 'en_x_US.UTF-8') { return 1; }
 				elsif ($b =~ /_Comm_/ ||
 				       $a eq 'en_x_US.UTF-8') { return -1; }
 				else { return uc($b) cmp uc($a); }
 				} keys(%{$hashtable{$hash}});
 		}
 		if ($#files > 0) {
 			my $link = shift(@files);
 			$link =~ s/_x_x//;	# special case for C
 			$link =~ s/_x_/_/;	# strip family if none there
 			foreach my $file (@files) {
 				my @a = split(/_/, $file);
 				my @b = split(/\./, $a[-1]);
 				$file =~ s/_x_/_/;
 				print FOUT "SAME+=\t\t$link $file\n";
 				undef($languages{$a[0]}{$a[1]}{data}{$b[0]}{$b[1]});
 			}
 		}
 	}
 
 	foreach my $l (sort keys(%languages)) {
 	foreach my $f (sort keys(%{$languages{$l}})) {
 	foreach my $c (sort keys(%{$languages{$l}{$f}{data}})) {
 		next if (defined $languages{$l}{$f}{definitions}
 		    && $languages{$l}{$f}{definitions} !~ /$TYPE/);
 		if (defined $languages{$l}{$f}{data}{$c}{$DEFENCODING}
 		 && $languages{$l}{$f}{data}{$c}{$DEFENCODING} eq "0") {
 			print "Skipping ${l}_" . ($f eq "x" ? "" : "${f}_") .
 			    "${c} - not read\n";
 			next;
 		}
 		foreach my $e (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 			my $file = $l;
 			$file .= "_" . $f if ($f ne "x");
 			$file .= "_" . $c if ($c ne "x");
 			next if (!defined $languages{$l}{$f}{data}{$c}{$e});
 			print FOUT "LOCALES+=\t$file.$e\n";
 		}
 
 		if (defined $languages{$l}{$f}{nc_link}) {
 			foreach my $e (sort keys(%{$languages{$l}{$f}{data}{$c}})) {
 				my $file = $l . "_";
 				$file .= $f . "_" if ($f ne "x");
 				$file .= $c;
 				print FOUT "SAME+=\t\t$file.$e $languages{$l}{$f}{nc_link}.$e\t# legacy (lang/country change)\n";
 			}
 		}
 
 		if (defined $languages{$l}{$f}{e_link}) {
 			foreach my $el (split(" ", $languages{$l}{$f}{e_link})) {
 				my @a = split(/:/, $el);
 				my $file = $l . "_";
 				$file .= $f . "_" if ($f ne "x");
 				$file .= $c;
 				print FOUT "SAME+=\t\t$file.$a[0] $file.$a[1]\t# legacy (same charset)\n";
 			}
 		}
 
 	}
 	}
 	}
 
 	print FOUT <<EOF;
 
 FILES=		\${LOCALES:S/\$/.${SRCOUT2}/}
 CLEANFILES=	\${FILES}
 
 .for f t in \${SAME}
 SYMLINKS+=	../\$f/\${FILESNAME} \\
     \${LOCALEDIR}/\$t/\${FILESNAME}
 .endfor
 
 .for f in \${LOCALES}
 FILESDIR_\${f}.${SRCOUT2}= \${LOCALEDIR}/\${f}
 .endfor
 
 ${SRCOUT3}.include <bsd.prog.mk>
 EOF
 
 	close(FOUT);
 }
Index: head/tools/tools/locale/tools/extract-colldef.awk
===================================================================
--- head/tools/tools/locale/tools/extract-colldef.awk	(revision 352273)
+++ head/tools/tools/locale/tools/extract-colldef.awk	(revision 352274)
@@ -1,12 +1,38 @@
+#
+# SPDX-License-Identifier: BSD-2-Clause-FreeBSD
+#
+# Copyright 2016 Baptiste Daroussin <bapt@FreeBSD.org>
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
 # $FreeBSD$
 
 BEGIN {
 	print "# Warning: Do not edit. This is automatically extracted"
 	print "# from CLDR project data, obtained from http://cldr.unicode.org/"
 	print "# -----------------------------------------------------------------------------"
 }
 $1 == "comment_char" { print }
 $1 == "escape_char" { print }
 $1 == "LC_COLLATE" { doprint = 1 }
 doprint == 1 { print }
 $1 == "END" && $2 == "LC_COLLATE" { exit 0 }
Index: head/tools/tools/locale/tools/finalize
===================================================================
--- head/tools/tools/locale/tools/finalize	(revision 352273)
+++ head/tools/tools/locale/tools/finalize	(revision 352274)
@@ -1,182 +1,207 @@
 #!/bin/sh
 #
+# SPDX-License-Identifier: BSD-2-Clause-FreeBSD
+#
+# Copyright 2015 John Marino <draco@marino.st>
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
 # $FreeBSD$
 #
 # This is a helper script for the Makefile in the parent directory.
 # When the localization definitions are generated in the draft area,
 # this script will copy base ones that others symlink to, and rearrange
 # the generate makefile to pull the LOCALES first.
 #
 
 set -e
 
 usage ()
 {
 	echo "finalize <type>' to package standard localization"
 	echo "type must be one of { monetdef, msgdef, numericdef, timedef, colldef, ctypedef }"
 	exit 1
 }
 
 [ $# -ne 1 ] && usage
 [ $1 = "monetdef" -o $1 = "msgdef" -o $1 = "colldef" -o \
   $1 = "numericdef" -o $1 = "timedef" -o $1 = "ctypedef" ] || usage
 
 self=$(realpath $0)
 base=$(dirname ${self})
 old=${base}/../${1}.draft
 new=${base}/../${1}
 TEMP=/tmp/${1}.locales
 TEMP2=/tmp/${1}.hashes
 TEMP3=/tmp/${1}.symlinks
 TEMP4=/tmp/${1}.mapped
 FULLMAP=/tmp/utf8-map
 FULLEXTRACT=/tmp/extracted-names
 AWKCMD="/## PLACEHOLDER/ { \
 	  while ( getline line < \"${TEMP}\" ) {print line} } \
 	/## SYMPAIRS/ { \
 	  while ( getline line < \"${TEMP3}\" ) {print line} } \
 	/## LOCALES_MAPPED/ { \
 	  while ( getline line < \"${TEMP4}\" ) {print line} } \
 	!/## / { print \$0 }"
 
 # Rename the sources with 3 components name into the POSIX version of the name using @modifier
 cd $old
 pwd
 for i in *_*_*.*.src; do
 	if [ "$i" = "*_*_*.*.src" ]; then
 		break
 	fi
 	oldname=${i%.*}
 	nname=`echo $oldname | awk '{ split($0, a, "_"); print a[1]"_"a[3]"@"a[2];} '`
 	mv -f ${oldname}.src ${nname}.src
 	sed -i '' -e "s/${oldname}/${nname}/g" Makefile
 	COLLATIONS_SPECIAL=$(echo ${COLLATIONS_SPECIAL} | sed -e "s/${oldname}/${nname}/g")
 done
 
 # For variable without @modifier ambiguity do not keep the @modifier
 for i in *@*.src; do
 	if [ "$i" = "*@*.src" ]; then
 		break
 	fi
 	oldname=${i%.*}
 	shortname=${oldname%@*}
 	if [ $(ls ${shortname}@* | wc -l) -eq 1 ] ; then
 		mv -f $i ${shortname}.src
 		sed -i '' -e "s/${oldname}/${shortname}/g" Makefile
 		COLLATIONS_SPECIAL=$(echo ${COLLATIONS_SPECIAL} | sed -e "s/${oldname}/${shortname}/g")
 	fi
 done
 
 # Rename the modifiers into non abbreviated version
 for i in *@Latn.src; do
 	if [ "$i" = "*@Latn.src" ]; then
 		break
 	fi
 	mv -f ${i} ${i%@*}@latin.src
 	sed -i '' -e "s/${i%.*}/${i%@*}@latin/g" Makefile
 	COLLATIONS_SPECIAL=$(echo ${COLLATIONS_SPECIAL} | sed -e "s/${i%.*}/${i%@*}@latin/g")
 done
 
 for i in *@Cyrl.src; do
 	if [ "$i" = "*@Cyrl.src" ]; then
 		break
 	fi
 	mv -f ${i} ${i%@*}@cyrillic.src
 	sed -i '' -e "s/${i%.*}/${i%@*}@cyrillic/g" Makefile
 	COLLATIONS_SPECIAL=$(echo ${COLLATIONS_SPECIAL} | sed -e "s/${i%.*}/${i%@*}@cyrillic/g")
 done
 
 # On locales with multiple modifiers rename the "default" version without the @modifier
 default_locales="sr_RS@cyrillic"
 for i in ${default_locales}; do
 	localename=${i%@*}
 	mod=${i#*@}
 	for l in ${localename}.*@${mod}.src; do
 		if [ "$l" = "${localename}.*@${mod}.src" ]; then
 			break
 		fi
 		mv -f ${l} ${l%@*}.src
 		sed -i '' -e "s/${l%.*}/${l%@*}/g" Makefile
 	done
 done
 cd -
 
 grep '^LOCALES+' ${old}/Makefile > ${TEMP}
 
 if [ $1 = "ctypedef" ]
 then
 	keep=$(cat ${TEMP} | awk '{ print $2 ".src" }')
 	(cd ${old} && md5 -r ${keep} | sort) > ${TEMP2}
 	keep=$(awk '{ if ($1 != last1) print $2; last1 = $1; }' ${TEMP2})
 	for original in ${keep}
 	do
 		cp ${old}/${original} ${new}/
 	done
 	awk '{ if ($1 == last1) { print "SYMPAIRS+=\t" last2 " " $2 } \
 	else {last1 = $1; last2 = $2}}' ${TEMP2} > ${TEMP3}
 	rm -f ${TEMP2}
 	/usr/bin/sed -E -e 's/[ ]+/ /g' \
 		${UNIDIR}/posix/UTF-8.cm \
 		> ${base}/../etc/final-maps/map.UTF-8
 	/usr/bin/sed -E -e 's/[ ]+/ /g' \
 		${UNIDIR}/posix/eucCN.cm \
 		> ${base}/../etc/final-maps/map.eucCN
 	/usr/bin/sed -E -e 's/[ ]+/ /g' \
 		${UNIDIR}/posix/eucCN.cm \
 		> ${base}/../etc/final-maps/map.GB2312
 	CHARMAPS="ARMSCII-8 Big5 CP1131 CP1251 \
 		CP866 GBK ISCII-DEV ISO8859-1 \
 		ISO8859-13 ISO8859-15 ISO8859-2 ISO8859-4 \
 		ISO8859-5 ISO8859-7 ISO8859-9 KOI8-R KOI8-U \
 		PT154 SJIS US-ASCII eucJP eucKR"
 
 	# GB18030 blows up, use pre-generate Illumos version
 
 	for map in ${CHARMAPS}
 	do
 		encoding=${map}
 		/usr/local/bin/perl ${base}/convert_map.pl \
 			${base}/../etc/charmaps/${map}.TXT ${encoding} \
 			| /usr/bin/sed -E -e 's/	+/ /g' \
 		> ${base}/../etc/final-maps/map.${map}
 		echo map ${map} converted.
 	done
 
 elif [ $1 = "colldef" ]
 then
 	awk -v tmp4=${TEMP4} '$1 == "SAME+=" && $0 !~ /legacy/ {
 		orig=$2
 		dest=$3
 		gsub(/.*\./, "", orig)
 		gsub(/.*\./, "", dest)
 		if (orig != dest )
 			print "LOCALES_MAPPED+=\t"$2 " "$3 > tmp4
 		}' ${old}/Makefile
 
 	for line in $(awk '{ print $3 }' ${TEMP4}); do
 		sed -i '' "/^SAME.*$line$/d" ${old}/Makefile
 	done
 	echo "" >> ${TEMP4}
 	for enc in ${COLLATIONS_SPECIAL}; do
 		sed -i '' "/^.*${enc}$/d" ${TEMP4}
 		echo "LOCALES+=	${enc}" >> ${TEMP4}
 	done
 
 	keep=$(cat ${TEMP} | awk '{ print $2 }')
 	for original in ${keep} ${COLLATIONS_SPECIAL}
 	do
 		cp ${old}/${original}.src ${new}/
 	done
 else  # below is everything but ctypedef
 
 	keep=$(cat ${TEMP} | awk '{ print $2 }')
 	for original in ${keep}
 	do
 		cp ${old}/${original}.src ${new}/
 	done
 
 fi
 
 grep -v '^LOCALES+' ${old}/Makefile | awk "${AWKCMD}" > ${new}/Makefile
 
 rm -f ${TEMP} ${TEMP3} ${TEMP4}
Index: head/tools/tools/locale/tools/utf8-rollup.pl
===================================================================
--- head/tools/tools/locale/tools/utf8-rollup.pl	(revision 352273)
+++ head/tools/tools/locale/tools/utf8-rollup.pl	(revision 352274)
@@ -1,192 +1,219 @@
 #!/usr/local/bin/perl -wC
+
+# SPDX-License-Identifier: BSD-2-Clause-FreeBSD
+#
+# Copyright 2009 Edwin Groothuis <edwin@FreeBSD.org>
+# Copyright 2015 John Marino <draco@marino.st>
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions
+# are met:
+# 1. Redistributions of source code must retain the above copyright
+#    notice, this list of conditions and the following disclaimer.
+# 2. Redistributions in binary form must reproduce the above copyright
+#    notice, this list of conditions and the following disclaimer in the
+#    documentation and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
+# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+# SUCH DAMAGE.
+#
 # $FreeBSD$
 
 use strict;
 use Getopt::Long;
 
 if ($#ARGV != 0) {
 	print "Usage: $0 --unidir=<unidir>\n";
 	exit(1);
 }
 
 my $UNIDIR = undef;
 
 my $result = GetOptions (
 		"unidir=s"	=> \$UNIDIR
 	    );
 
 my %utf8map = ();
 my $outfilename = "$UNIDIR/posix/xx_Comm_C.UTF-8.src";
 
 get_utf8map("$UNIDIR/posix/UTF-8.cm");
 generate_header ();
 parse_unidata ("$UNIDIR/UnicodeData.txt");
 generate_footer ();
 
 ############################
 
 sub get_utf8map {
 	my $file = shift;
 
 	open(FIN, $file);
 	my @lines = <FIN>;
 	close(FIN);
 	chomp(@lines);
 
 	my $incharmap = 0;
 	foreach my $l (@lines) {
 		$l =~ s/\r//;
 		next if ($l =~ /^\#/);
 		next if ($l eq "");
 
 		if ($l eq "CHARMAP") {
 			$incharmap = 1;
 			next;
 		}
 
 		next if (!$incharmap);
 		last if ($l eq "END CHARMAP");
 
 		$l =~ /^(<[^\s]+>)\s+(.*)/;
 		my $k = $2;
 		my $v = $1;
 		$k =~ s/\\x//g;		# UTF-8 char code
 		$utf8map{$k} = $v;
 	}
 }
 
 sub generate_header {
 	open(FOUT, ">", "$outfilename")
 		or die ("can't write to $outfilename\n");
 	print FOUT <<EOF;
 # Warning: Do not edit. This file is automatically generated from the
 # tools in /usr/src/tools/tools/locale. The data is obtained from the
 # CLDR project, obtained from http://cldr.unicode.org/
 # -----------------------------------------------------------------------------
 
 comment_char *
 escape_char /
 
 LC_CTYPE
 EOF
 }
 
 sub generate_footer {
 	print FOUT "\nEND LC_CTYPE\n";
 	close (FOUT);
 }
 
 sub wctomb {
 	my $wc = hex(shift);
 	my $lead;
 	my $len;
 	my $ret = "";
 	my $i;
 
 	if (($wc & ~0x7f) == 0) {
 		return sprintf "%02X", $wc;
 	} elsif (($wc & ~0x7ff) == 0) {
 		$lead = 0xc0;
 		$len = 2;
 	} elsif (($wc & ~0xffff) == 0) {
 		$lead = 0xe0;
 		$len = 3;
 	} elsif ($wc >= 0 && $wc <= 0x10ffff) {
 		$lead = 0xf0;
 		$len = 4;
 	}
 
 	for ($i = $len - 1; $i > 0; $i--) {
 		$ret = (sprintf "%02X", ($wc & 0x3f) | 0x80) . $ret;
 		$wc >>= 6;
 	}
 	$ret = (sprintf "%02X", ($wc & 0xff) | $lead) . $ret;
 
 	return $ret;
 }
 
 sub parse_unidata {
 	my $file = shift;
 	my %data = ();
 
 	open(FIN, $file);
 	my @lines = <FIN>;
 	close(FIN);
 	chomp(@lines);
 
 	foreach my $l (@lines) {
 		my @d = split(/;/, $l, -1);
 		my $mb = wctomb($d[0]);
 		my $cat;
 
 		# XXX There are code points present in UnicodeData.txt
 		# and missing from UTF-8.cm
 		next if !defined $utf8map{$mb};
 
 		# Define the category
 		if ($d[2] =~ /^Lu/) {
 			$cat = "upper";
 		} elsif ($d[2] =~ /^Ll/) {
 			$cat = "lower";
 		} elsif ($d[2] =~ /^Nd/) {
 			$cat = "digit";
 		} elsif ($d[2] =~ /^L/) {
 			$cat = "alpha";
 		} elsif ($d[2] =~ /^P/) {
 			$cat = "punct";
 		} elsif ($d[2] =~ /^M/ || $d[2] =~ /^N/ || $d[2] =~ /^S/) {
 			$cat = "graph";
 		} elsif ($d[2] =~ /^C/) {
 			$cat = "cntrl";
 		} elsif ($d[2] =~ /^Z/) {
 			$cat = "space";
 		}
 		$data{$cat}{$mb}{'wc'} = $d[0];
 
 		# Check if it's a start or end of range
 		if ($d[1] =~ /First>$/) {
 			$data{$cat}{$mb}{'start'} = 1;
 		} elsif ($d[1] =~ /Last>$/) {
 			$data{$cat}{$mb}{'end'} = 1;
 		}
 
 		# Check if there's upper/lower mapping
 		if ($d[12] ne "") {
 			$data{'toupper'}{$mb} = wctomb($d[12]);
 		} elsif ($d[13] ne "") {
 			$data{'tolower'}{$mb} = wctomb($d[13]);
 		}
 	}
 
 	my $first;
 	my $inrange = 0;
 
 	# Now write out the categories
 	foreach my $cat (sort keys (%data)) {
 		print FOUT "$cat\t";
 		$first = 1;
 	foreach my $mb (sort keys (%{$data{$cat}})) {
 		if ($first == 1) {
 			$first = 0;
 		} elsif ($inrange == 1) {
 			# Safety belt
 			die "broken range end wc=$data{$cat}{$mb}{'wc'}"
 			    if !defined $data{$cat}{$mb}{'end'};
 			print FOUT ";...;";
 			$inrange = 0;
 		} else {
 			print FOUT ";/\n\t";
 		}
 
 		if ($cat eq "tolower" || $cat eq "toupper") {
 			print FOUT "($utf8map{$mb},$utf8map{$data{$cat}{$mb}})";
 		} else {
 			if (defined($data{$cat}{$mb}{'start'})) {
 				$inrange = 1;
 			}
 			print FOUT "$utf8map{$mb}";
 		}
 	}
 		print FOUT "\n";
 	}
 }