#!/usr/bin/env perl
-use 5.012;
+use 5.014;
use warnings;
+our $VERSION = '1.04';
+
my %cc; # map of country code to info array
%cc = (
# transitional reservations
# exceptional reservations
ac => ["exceptionally reserved: Ascension Island", "c-oc Xr", "Ascension Island", 'sh'],
cp => ["exceptionally reserved: Clipperton Island", "c-na Xr", "Clipperton Island"],
+ cq => ["exceptionally reserved by gb: Island of Sark", "c-eu Xr", "Island of Sark", 'gg'],
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", "European OTC"],
- fx => ["exceptionally reserved: Metropolitan France", "c-eu Xr", "Metropolitan France", 'fr'],
+ ez => ["exceptionally reserved: European OTC derivatives", "c-eu Xr", "Eurozone"],
+ fx => ["exceptionally reserved by fr: 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'],
+ uk => ["exceptionally reserved by gb: United Kingdom", "c-eu Xr", "(United Kingdom)", 'gb'],
un => ["exceptionally reserved: United Nations", "Xi Xr", "United Nations"],
# indeterminate reservations
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"],
+
+ # common user-assigned
+ xa => ["user-assigned by Russia: Abkhazia", "c-az Co Xi", "Abkhazia", 'ge'], # also IC alias by CH
+ xo => ["user-assigned by Russia: South Ossetia", "c-az Co Xi", "South Ossetia", 'ge'],
+ xi => ["user-assigned for UK/EU trade: Northern Ireland", "c-eu Co Xi", "Northern Ireland", 'gb'],
+ xn => ["user-assigned by WIPO: Nordic Patent Institute", "c-eu Co Xi", "Nordic", 'dk is no se'],
+ xu => ["user-assigned by WIPO: international org UPOV", "Co Xi", "UPOV"],
+ xv => ["user-assigned by WIPO: Visegrad Patent Institute", "c-eu Co Xi", "Visegrad", 'cz hu pl sk'],
+ xx => ["user-assigned by WIPO: unknown state or other entity", "Co Xi", "other"],
+ xz => ["UN/LOCODE semantics: international waters", "Co Xi", "international"],
+ qm => ["user-assigned by ISRC: United States alternative", "c-na Co Xi", "USA"],
+ 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"],
+ oo => ["escape to indicate additional code", "Co Xi", "escape"],
);
while (<>) {
s/(?<=.)\(.*\)\s*//;
s/ republic\b//gi;
s/ islands?\b//gi;
- s/\bthe //g;
+ s/\bthe //gi;
s/ and / & /g and s/(?<=.)[a-z ]+//g;
s/ of / /g;
s/\bsa?int /st /gi;
- s/United /Un. /gi;
+ s/Un\Kited /. /gi;
s/South(?:ern)? /S-/g;
s/North(?:ern)? /N-/g;
+ s/West(?:ern)? /W-/g;
+ s/East(?:ern)? /E-/g;
s/New /n./g;
- s/(\S)(\S+)-/$1-/g; # strip most chars preceding dash
+ s/(\w)(\w+)-/$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)
$_;
};