Added two tools to check the contents of /usr/share/misc/iso* with

the data from the sources.

PR:		misc/127430 and misc/misc/127428

3 files changed, 264 insertions, 0 deletions

diff --git a/tools/tools/README b/tools/tools/README
index 9190f6b..de7e80f 100644
--- a/tools/tools/README
+++ b/tools/tools/README
@@ -32,6 +32,8 @@ hcomp		Compress header files by removing comments and whitespace.
 html-mv         Rename HTML generated filenames to human readable filenames.
 ifinfo		Uses the interface MIB to print out all the information
 		an interface exports in an ugly form.
+iso             Tool to compare the iso3166 and iso639 files in
+		/usr/share/misc with the data from the master sites.
 iwi		Tools specific to the Intel PRO/Wireless 2200BG/2225BG/2915ABG
 		support.
 kdrv		KernelDriver; add/list/remove third-party kernel driver
diff --git a/tools/tools/iso/check-iso3166.pl b/tools/tools/iso/check-iso3166.pl
new file mode 100755
index 0000000..b85c188
--- /dev/null
+++ b/tools/tools/iso/check-iso3166.pl
@@ -0,0 +1,164 @@
+#!/usr/bin/perl -w
+
+#
+# $FreeBSD$
+#
+# This script compares the file iso3166 (from head/share/misc) with the files
+# list-en1-semic-2.txt (from
+# http://www.iso.org/iso/list-en1-semic-2.txt) and iso3166-countrycodes.txt
+# (from ftp://ftp.ripe.net/) to see if there any differences.
+#
+# Created by Edwin Groothuis <edwin@FreeBSD.org> for the FreeBSD project.
+#
+
+use strict;
+use Data::Dumper;
+
+my %old = ();
+{
+	open(FIN, "iso3166") or die "Cannot open iso3166 (should be in head/share/misc)";
+	my @lines = <FIN>;
+	close(FIN);
+	chomp(@lines);
+
+	foreach my $l (@lines) {
+		next if ($l =~ /^#/);
+		next if ($l eq "");
+
+		die "Bad line: $l\n"
+			if ($l !~ /^([A-Z\-]*)[ \t]+([A-Z\-]+)[ \t]+(\d+)[ \t]+(.*)/);
+		my $two = $1;
+		my $three = $2;
+		my $number = $3;
+		my $name = $4;
+
+		$old{$two}{two} = $two;
+		$old{$two}{three} = $three;
+		$old{$two}{number} = $number;
+		$old{$two}{name} = $name;
+	}
+}
+
+my %new1 = ();
+{
+	open(FIN, "iso3166-countrycodes.txt") or die "Cannot open iso3166-countrycodes.txt, which can be retrieved from ftp://ftp.ripe.net/";
+	my @lines = <FIN>;
+	close(FIN);
+	chomp(@lines);
+
+	my $noticed = 0;
+	foreach my $l (@lines) {
+		if ($l =~ /\-\-\-\-\-\-\-/) {
+			$noticed = 1;
+			next;
+		}
+		next if (!$noticed);
+		next if ($l eq "");
+
+		die "Invalid line: $l\n"
+			if ($l !~ /^(.+?)[\t ][\t ]+([A-Z]{2})[\t ]+([A-Z]{3})[\t ]+(\d+)[\t ]*$/);
+		my $two = $2;
+		my $three = $3;
+		my $number = $4;
+		my $name = $1;
+
+		$new1{$two}{two} = $two;
+		$new1{$two}{three} = $three;
+		$new1{$two}{number} = $number;
+		$new1{$two}{name} = $name;
+	}
+}
+
+my %new2 = ();
+{
+	open(FIN, "list-en1-semic-2.txt") or die "Cannot open list-en1-semic-2.txt, which can be retrieved from http://www.iso.org/iso/list-en1-semic-2.txt";
+	my @lines = <FIN>;
+	close(FIN);
+	chomp(@lines);
+
+	my $noticed = 0;
+	foreach my $l (@lines) {
+		$l =~ s/\x0d//g;
+		if (!$noticed) {	# skip the first line
+			$noticed = 1;
+			next;
+		}
+		next if ($l eq "");
+
+		my @a = split(/;/, $l);
+		die "Invalid line: $l\n" if ($#a != 1);
+		my $two = $a[1];
+		my $name = $a[0];
+
+		$new2{$two}{two} = $two;
+		$new2{$two}{name} = $name;
+	}
+}
+
+{
+	my $c = 0;
+	foreach my $two (sort(keys(%old))) {
+		if (!defined $new1{$two}) {
+			print "In old but not new1: $old{$two}{two}\t$old{$two}{three}\t$old{$two}{number}\t$old{$two}{name}\n";
+			$c++;
+		}
+		if (!defined $new2{$two}) {
+			print "In old but not new2: $old{$two}{two}\t$old{$two}{name}\n";
+			$c++;
+		}
+	}
+	print "Found $c issues\n";
+}
+
+{
+	my $c = 0;
+	foreach my $two (sort(keys(%new1))) {
+		next if (defined $old{$two});
+		print "In new1 but not old: $new1{$two}{two}\t$new1{$two}{three}\t$new1{$two}{number}\t$new1{$two}{name}\n";
+		$c++;
+	}
+	print "Found $c issues\n";
+}
+
+{
+	my $c = 0;
+	foreach my $two (sort(keys(%new2))) {
+		next if (defined $old{$two});
+		print "In new2 but not old: $new2{$two}{two}\t$new2{$two}{name}\n";
+		$c++;
+	}
+	print "Found $c issues\n";
+}
+
+{
+	my $c = 0;
+	foreach my $two (sort(keys(%old))) {
+		if (defined $new1{$two}) {
+			if ($old{$two}{two} ne $new1{$two}{two} ||
+			    $old{$two}{three} ne $new1{$two}{three} ||
+			    $old{$two}{number} ne $new1{$two}{number} ||
+			    lc($old{$two}{name}) ne lc($new1{$two}{name})) {
+				print "In old : $old{$two}{two}\t$old{$two}{three}\t$old{$two}{number}\t$old{$two}{name}\n";
+				print "In new1: $new1{$two}{two}\t$new1{$two}{three}\t$new1{$two}{number}\t$new1{$two}{name}\n";
+				$c++;
+			}
+		}
+	}
+	print "Found $c issues\n";
+}
+
+{
+	my $c = 0;
+	foreach my $two (sort(keys(%old))) {
+		if (defined $new2{$two}) {
+			if ($old{$two}{two} ne $new2{$two}{two} ||
+			    lc($old{$two}{name}) ne lc($new2{$two}{name})) {
+				print "In old : $old{$two}{two}\t$old{$two}{name}\n";
+				print "In new2: $new2{$two}{two}\t$new2{$two}{name}\n";
+				$c++;
+			}
+		}
+	}
+	print "Found $c issues\n";
+}
+
diff --git a/tools/tools/iso/check-iso639.pl b/tools/tools/iso/check-iso639.pl
new file mode 100755
index 0000000..9350df0
--- /dev/null
+++ b/tools/tools/iso/check-iso639.pl
@@ -0,0 +1,98 @@
+#!/usr/bin/perl -w
+
+#
+# $FreeBSD$
+#
+# This script compares the file iso639 (from head/share/misc) with the file
+# ISO-639-2_8859-1.txt (from
+# http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt) to see if there
+# any differences.
+#
+# Created by Edwin Groothuis <edwin@FreeBSD.org> for the FreeBSD project.
+#
+
+use strict;
+use Data::Dumper;
+
+my %old = ();
+{
+	open(FIN, "iso639") or die "Cannot open iso639 (should be in head/share/misc)";
+	my @lines = <FIN>;
+	close(FIN);
+	chomp(@lines);
+
+	foreach my $l (@lines) {
+		next if ($l =~ /^#/);
+		next if ($l eq "");
+
+		die "Bad line: $l\n"
+			if ($l !~ /^([a-z\-]*)[ \t]+([a-z\-]+)[ \t]+([a-z\-]+)[ \t]+(.*)/);
+		my $a2 = $1;
+		my $bib = $2;
+		my $term = $3;
+		my $name = $4;
+
+		$old{$bib}{a2} = $a2;
+		$old{$bib}{bib} = $bib;
+		$old{$bib}{term} = $term;
+		$old{$bib}{name} = $name;
+	}
+}
+
+my %new = ();
+{
+	open(FIN, "ISO-639-2_utf-8.txt") or die "Cannot open ISO-639-2_utf-8.txt, which can be retrieved from http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt";
+	my @lines = <FIN>;
+	close(FIN);
+	chomp(@lines);
+
+	foreach my $l (@lines) {
+		my @a = split(/\|/, $l);
+		my $a2 = $a[2];
+		my $bib = $a[0];
+		my $term = $a[1];
+		my $name = $a[3];
+
+		$term = $bib if ($term eq "");
+
+		$new{$bib}{a2} = $a2;
+		$new{$bib}{bib} = $bib;
+		$new{$bib}{term} = $term;
+		$new{$bib}{name} = $name;
+	}
+}
+
+{
+	my $c = 0;
+	foreach my $bib (sort(keys(%old))) {
+		next if (defined $new{$bib});
+		print "In old but not new: $old{$bib}{a2}\t$old{$bib}{bib}\t$old{$bib}{term}\t$old{$bib}{name}\n";
+		$c++;
+	}
+	print "Found $c issues\n";
+}
+
+{
+	my $c = 0;
+	foreach my $bib (sort(keys(%new))) {
+		next if (defined $old{$bib});
+		print "In new but not old: $new{$bib}{a2}\t$new{$bib}{bib}\t$new{$bib}{term}\t$new{$bib}{name}\n";
+		$c++;
+	}
+	print "Found $c issues\n";
+}
+
+{
+	my $c = 0;
+	foreach my $bib (sort(keys(%old))) {
+		next if (!defined $new{$bib});
+		next if ($old{$bib}{a2} eq $new{$bib}{a2} &&
+			 $old{$bib}{bib} eq $new{$bib}{bib} &&
+			 $old{$bib}{term} eq $new{$bib}{term} &&
+			 $old{$bib}{name} eq $new{$bib}{name});
+		print "In old: $old{$bib}{a2}\t$old{$bib}{bib}\t$old{$bib}{term}\t$old{$bib}{name}\n";
+		print "In new: $new{$bib}{a2}\t$new{$bib}{bib}\t$new{$bib}{term}\t$new{$bib}{name}\n";
+		$c++;
+	}
+	print "Found $c issues\n";
+}