X-Git-Url: http://git.shiar.nl/sheet.git/blobdiff_plain/d96b16650836046f79dc76641681445f97bd60ce..c133e6ad3027e095811931f3e0d21b818865e0e8:/tools/mkcountries-geonames

diff --git a/tools/mkcountries-geonames b/tools/mkcountries-geonames
index d9b938a..b7fb27e 100755
--- a/tools/mkcountries-geonames
+++ b/tools/mkcountries-geonames
@@ -3,29 +3,101 @@ use 5.012;
 use warnings;
 
 my %cc;  # map of country code to info array
+%cc = (
+	# transitional reservations
+	an => ["transitionally reserved: Netherlands Antilles", "c-na Xr", "Netherlands Antilles", 'bq cw sx'], # 2060
+	bu => ["transitionally reserved: Burma", "c-as Xr", "Burma", 'mm'], # 2039
+	cs => ["transitionally reserved: Serbia and Montenegro", "c-eu Xr", "Serbia and Montenegro", 'rs me'], # 2056
+	nt => ["transitionally reserved: Neutral Zone", "c-as Xr", "N. Zone", 'iq sa'], # 2043
+	tp => ["transitionally reserved: East Timor", "c-oc Xr", "(East Timor)", 'tl'], # 2052
+	yu => ["transitionally reserved: Yugoslavia", "c-eu Xr", "Yugoslavia", 'cs ba hr mk si'], # 2053
+	zr => ["transitionally reserved: Zaire", "c-af Xr", "Zaire", 'cd'], # 2047
+
+	# exceptional reservations
+	ac => ["exceptionally reserved: Ascension Island", "c-oc Xr", "Ascension Island", 'sh'],
+	cp => ["exceptionally reserved: Clipperton Island", "c-na Xr", "Clipperton Island"],
+	dg => ["exceptionally reserved: Diego Garcia", "c-as Xr", "Diego Garcia", 'io'],
+	ea => ["exceptionally reserved: Ceuta and Melilla", "c-af Xr", "Ceuta and Melilla"],
+	eu => ["exceptionally reserved: European Union", "c-eu Xr", "European Union"],
+	ez => ["exceptionally reserved: European OTC derivatives", "c-eu Xr", "Eurozone"],
+	fx => ["exceptionally reserved: Metropolitan France", "c-eu Xr", "Metropolitan France", 'fr'],
+	ic => ["exceptionally reserved: Canary Islands", "c-af Xr", "Canary Islands"],
+	su => ["exceptionally reserved: former USSR", "c-eu Xr", "USSR"],
+	ta => ["exceptionally reserved: Tristan da Cunha", "c-oc Xr", "Tristan da Cunha", 'sh'],
+	uk => ["exceptionally reserved: United Kingdom", "c-eu Xr", "(United Kingdom)", 'gb'],
+	un => ["exceptionally reserved: United Nations", "Xi Xr", "United Nations"],
+
+	# indeterminate reservations
+	dy => ["indeterminately reserved: Benin", "c-af Xr", "(Benin)", 'bj'],
+	ew => ["indeterminately reserved: Estonia", "c-eu Xr", "(Estonia)", 'ee'],
+	fl => ["indeterminately reserved: Liechtenstein", "c-eu Xr", "(Liechtenstein)", 'li'],
+	ja => ["indeterminately reserved: Jamaica", "c-na Xr", "(Jamaica)", 'jm'],
+	lf => ["indeterminately reserved: Libya Fezzan", "c-af Xr", "Fezzan", 'ly'],
+	pi => ["indeterminately reserved: Philippines", "c-as Xr", "(Philippines)", 'ph'],
+	ra => ["indeterminately reserved: Argentina", "c-sa Xr", "(Argentina)", 'ar'],
+	rb => ["indeterminately reserved: Botswana, Bolivia", "c-sa Xr", "(Bots...)", 'bw bo'],
+	rc => ["indeterminately reserved: Republic of China", "c-as Xr", "(RoC)", 'tw'],
+	rh => ["indeterminately reserved: Haiti", "c-na Xr", "(Haiti)", 'ht'],
+	ri => ["indeterminately reserved: Indonesia", "c-as Xr", "(Indonesia)", 'id'],
+	rl => ["indeterminately reserved: Lebanon", "c-as Xr", "(Lebanon)", 'lb'],
+	rm => ["indeterminately reserved: Madagascar", "c-af Xr", "(Madagascar)", 'mg'],
+	rn => ["indeterminately reserved: Niger", "c-af Xr", "(Niger)", 'ne'],
+	rp => ["indeterminately reserved: Philippines", "c-as Xr", "(Philippines)", 'ph'],
+	sf => ["indeterminately reserved: Finland", "c-eu Xr", "(Finland)", 'fi'],
+	wg => ["indeterminately reserved: Grenada", "c-na Xr", "(Grenada)", 'gd'],
+	wl => ["indeterminately reserved: Saint Lucia", "c-na Xr", "(Saint Luc.)", 'lc'],
+	wv => ["indeterminately reserved: Saint Vincent", "c-na Xr", "(Saint Vin.)", 'vc'],
+	yv => ["indeterminately reserved: Venezuela", "c-sa Xr", "(Venezuela)", 've'],
+
+	# WIPO, agreed not to use
+	ap => ["not used: African Regional Industrial Property Organization", "Xi", "ARIPO"], # c-af
+	bx => ["not used: Benelux Office for Intellectual Property", "Xi", "BOIP"], # c-eu
+	ef => ["not used: European Community Patent Convention", "Xi", "CPC"], # c-eu
+	em => ["not used: European Trademark Office", "Xi", "OHIM"], # c-eu
+	ep => ["not used: European Patent Organization", "Xi", "EPOrg"], # c-eu
+	ev => ["not used: Eurasian Patent Organization", "Xi", "EAPO"], # c-as
+	gc => ["not used: Gulf Patent Office", "Xi", "GCCPO"], # c-as
+	ib => ["not used: International Bureau of WIPO", "Xi", "IB"],
+	oa => ["not used: African Intellectual Property Organization", "Xi", "OAPI"], # c-af
+	wo => ["not used: World Intellectual Property Organization", "Xi", "WIPO"],
+
+	# unicode identifiers
+	qo => ["Unicode semantics: Outlying Oceania", "c-oc Co Xi", "Oceania"],
+	qu => ["Unicode semantics: European Union deprecated reserve", "c-eu Co Xi", "EU", 'eu'],
+	zz => ["Unicode semantics: unknown or invalid territory", "Co Xi","unknown"],
+);
 
 while (<>) {
 	/^#/ and next;  # skip comments
-	my ($iso, $name, $cont) = (split /\t/)[0, 4, 8];
-	my $class = "c-\L$cont";
-	$cc{ lc $iso } = [ $name, $class ];
+	my ($iso, $name, $cont, $tld) = (split /\t/)[0, 4, 8, 9];
+	my @info = ($name, "c-\L$cont");
+	$info[3] = $tld if $tld =~ s/\A\.// and $tld ne lc $iso;
+	$cc{ lc $iso } //= \@info;
 }
 
+$cc{io}->[2] = "Chagos Islands";
+$cc{um}->[2] = "U.S. isl.";
+
 for (values %cc) {
-	for ($_->[2] //= $_->[0]) {
+	my $abbr = do {
+		local $_ = $_->[2] // $_->[0];
 		s/,.*//;
 		s/(?<=.)\(.*\)\s*//;
 		s/ republic\b//gi;
 		s/ islands?\b//gi;
 		s/\bthe //g;
 		s/ and / & /g and s/(?<=.)[a-z ]+//g;
-		s/\bsaint /st /gi;
+		s/ of / /g;
+		s/\bsa?int /st /gi;
+		s/United /Un. /gi;
 		s/South(?:ern)? /S-/g;
 		s/North(?:ern)? /N-/g;
 		s/New /n./g;
 		s/(\S)(\S+)-/$1-/g;  # strip most chars preceding dash
 		s/(\S{4}[b-df-hj-np-tv-xz])((?<!Austr)(?!land)\w{2,})/$1./g;  # abbreviate (at consonant)
-	}
+		$_;
+	};
+	$_->[2] = $abbr if $abbr ne $_->[0];  # short name if different
 }
 
 say "# automatically generated by $0";