lib/lib_pm.PL For "use lib", produces lib/lib.pm
lib/locale.pm For "use locale"
lib/locale.t See if locale support works
+lib/Locale/Codes/ChangeLog Locale::Codes
+lib/Locale/Codes/README Locale::Codes
lib/Locale/Codes/t/all.t See if Locale::Codes work
lib/Locale/Codes/t/constants.t See if Locale::Codes work
lib/Locale/Codes/t/country.t See if Locale::Codes work
lib/Locale/Codes/t/currency.t See if Locale::Codes work
lib/Locale/Codes/t/languages.t See if Locale::Codes work
+lib/Locale/Codes/t/script.t See if Locale::Codes work
lib/Locale/Codes/t/uk.t See if Locale::Codes work
lib/Locale/Constants.pm Locale::Codes
lib/Locale/Country.pm Locale::Codes
lib/Locale/Maketext/README Locale::Maketext
lib/Locale/Maketext/test.pl See if Locale::Maketext works
lib/Locale/Maketext/TPJ13.pod Locale::Maketext documentation article
+lib/Locale/Script.pm Locale::Codes
lib/look.pl A "look" equivalent
lib/Math/BigFloat.pm An arbitrary precision floating-point arithmetic package
lib/Math/BigInt.pm An arbitrary precision integer arithmetic package
--- /dev/null
+
+ ChangeLog for Locale-Codes Distribution
+
+2.00 2002-02-17 neilb
+
+ * Created Locale::Script which provides an interface to the
+ ISO codes for identification of scripts (writing scripts,
+ rather than perl style scripts). The codes are defined
+ by ISO 15924, which is currently in final draft.
+ Thanks to Jarkko for pointing out this new standard.
+ All three code sets are supported, and a test-suite added.
+
+ * Added support for country name variants to Locale::Country,
+ so that
+ country2code('USA')
+ country2code('United States')
+ country2code('United States of America')
+ will all return 'us'.
+ This had been in the LIMITATIONS section since the first version.
+ Patch from TJ Mather <tjmather@tjmather.com> with additional
+ variants from me. Added test-cases for these.
+
+ * Added VERSION to Locale::Constants. Thanks to Jarkko for
+ pointing that it was missing.
+
+ * Should really have bumped major version with previous release,
+ since there was a change to the API.
+
+1.06 2001-03-04 neilb
+
+ Added Locale::Constants, which defines three symbols
+ for identifying which codeset is being used:
+
+ LOCALE_CODE_ALPHA_2
+ LOCALE_CODE_ALPHA_3
+ LOCALE_CODE_NUMERIC
+
+ Updated Locale::Country to support all three code sets
+ defined by ISO 3166. This was requested by Keith Wall.
+ I haven't added multiple codeset support to the other
+ modules yet - I'll wait until someone asks for them.
+
+1.05 Feb 2001
+
+ Added Locale::Currency, contribution from Michael Hennecke.
+ Added testsuite for it (t/currency.t) and added testcases
+ to t/all.t for the all_* functions.
+
+1.04 Dec 2000
+
+ Fixed very minor typos from 1.03!
+
+1.03 Dec 2000
+
+ Updated Locale::Country:
+ - fixed spelling of a few countries
+ - added link to a relevant page from CIA world factbook
+
+ Updated Locale::Language:
+ - fixed typo in the documentation (ISO 939 should be 639)
+
+1.02 May 2000
+
+ Updated Locale::Country and Locale::Language to reflect changes
+ in the relevant ISO standards. These mainly reflect languages
+ which are new to the relevant standard, and changes in the
+ spelling of some country names.
+
+ Added official URLs for the standards to the SEE ALSO sections
+ of the doc for each module.
+
+ Thanks to Jarkko Hietaniemi for pointing me at the pages
+ with latest versions of ISO 3166 and 639.
+
+1.00 March 1998
+
+ Added Locale::Country::_alias_code() so that 'uk' can be added
+ as the code for "United Kingdom", if you want it.
+ This was prompted by Ed Jordan <ed@chronos.net>
+
+ Added a new testsuite for handling this case, and extended the
+ existing test-suite to include testing of the case where
+ 'uk' hasn't been defined as a valid code.
+
+0.003 May 1997
+
+ First public release to CPAN
+
--- /dev/null
+
+ Locale-Codes Distribution
+ v2.00
+
+This distribution contains four Perl modules which can be used to process
+ISO codes for identifying languages, countries, scripts,
+and currencies & funds.
+
+ Locale::Language
+ Two letter codes for language identification (ISO 639).
+ For example, 'en' is the code for 'English'.
+
+ Locale::Country
+ Codes for country identification (ISO 3166). This module
+ supports the three different code sets defined by the
+ standard: alpha-2, alpha-3, and numeric codes.
+ For example, 'bo' is the code for 'Bolivia'.
+
+ Locale::Currency
+ Three letter codes for currency and fund identification (ISO 4217).
+ For example, 'sek' is the code for 'Swedish Krona'.
+
+ Locale::Script
+ Codes for script identification (ISO 15924). This module supports
+ the three different code sets defined by the standard:
+ alpha-2, alpha-3, and numeric codes.
+
+To install these modules, you should just have to run the following:
+
+ % perl Makefile.PL
+ % make
+ % make test
+ % make install
+
+The modules are documented using pod. When you "make install", you
+will get three man-pages: Locale::Language, Locale::Country,
+Locale::Currency, Locale::Script.
+
+The first version of Locale::Currency was written by Michael Hennecke,
+with modifications for inclusion by me. Kudos to Michael.
+
+Please let me know if you experience any problems with these modules,
+or have any ideas for additions.
+
+
+Neil Bowers
+<neil@bowers.com>
# Locale::Country
# Locale::Language
# Locale::Currency
+# Locale::Script
#
# There are four tests. We get a list of all codes, convert to
# language/country/currency, # convert back to code,
use Locale::Country;
use Locale::Language;
use Locale::Currency;
+use Locale::Script;
-print "1..12\n";
+print "1..20\n";
my $code;
my $language;
my $ok;
my $reverse;
my $currency;
+my $script;
#-----------------------------------------------------------------------
}
}
print ($ok ? "ok 12\n" : "not ok 12\n");
+
+#=======================================================================
+#
+# Locale::Script tests
+#
+#=======================================================================
+
+#-----------------------------------------------------------------------
+# Old API - without codeset specified, default to ALPHA_2
+#-----------------------------------------------------------------------
+$ok = 1;
+foreach $code (all_script_codes())
+{
+ $script = code2script($code);
+ if (!defined $script)
+ {
+ $ok = 0;
+ last;
+ }
+ $reverse = script2code($script);
+ if (!defined $reverse)
+ {
+ $ok = 0;
+ last;
+ }
+ if ($reverse ne $code)
+ {
+ $ok = 0;
+ last;
+ }
+}
+print ($ok ? "ok 13\n" : "not ok 13\n");
+
+#-----------------------------------------------------------------------
+# code to script, back to code, for ALPHA2
+#-----------------------------------------------------------------------
+$ok = 1;
+foreach $code (all_script_codes(LOCALE_CODE_ALPHA_2))
+{
+ $script = code2script($code, LOCALE_CODE_ALPHA_2);
+ if (!defined $script)
+ {
+ $ok = 0;
+ last;
+ }
+ $reverse = script2code($script, LOCALE_CODE_ALPHA_2);
+ if (!defined $reverse)
+ {
+ $ok = 0;
+ last;
+ }
+ if ($reverse ne $code)
+ {
+ $ok = 0;
+ last;
+ }
+}
+print ($ok ? "ok 14\n" : "not ok 14\n");
+
+#-----------------------------------------------------------------------
+# code to script, back to code, for ALPHA3
+#-----------------------------------------------------------------------
+$ok = 1;
+foreach $code (all_script_codes(LOCALE_CODE_ALPHA_3))
+{
+ $script = code2script($code, LOCALE_CODE_ALPHA_3);
+ if (!defined $script)
+ {
+ $ok = 0;
+ last;
+ }
+ $reverse = script2code($script, LOCALE_CODE_ALPHA_3);
+ if (!defined $reverse)
+ {
+ $ok = 0;
+ last;
+ }
+ if ($reverse ne $code)
+ {
+ $ok = 0;
+ last;
+ }
+}
+print ($ok ? "ok 15\n" : "not ok 15\n");
+
+#-----------------------------------------------------------------------
+# code to script, back to code, for NUMERIC
+#-----------------------------------------------------------------------
+$ok = 1;
+foreach $code (all_script_codes(LOCALE_CODE_NUMERIC))
+{
+ $script = code2script($code, LOCALE_CODE_NUMERIC);
+ if (!defined $script)
+ {
+ $ok = 0;
+ last;
+ }
+ $reverse = script2code($script, LOCALE_CODE_NUMERIC);
+ if (!defined $reverse)
+ {
+ $ok = 0;
+ last;
+ }
+ if ($reverse ne $code)
+ {
+ $ok = 0;
+ last;
+ }
+}
+print ($ok ? "ok 16\n" : "not ok 16\n");
+
+
+#-----------------------------------------------------------------------
+# Old API - script to code, back to script, using default of ALPHA_2
+#-----------------------------------------------------------------------
+$ok = 1;
+foreach $script (all_script_names())
+{
+ $code = script2code($script);
+ if (!defined $code)
+ {
+ $ok = 0;
+ last;
+ }
+ $reverse = code2script($code);
+ if (!defined $reverse)
+ {
+ $ok = 0;
+ last;
+ }
+ if ($reverse ne $script)
+ {
+ $ok = 0;
+ last;
+ }
+}
+print ($ok ? "ok 17\n" : "not ok 17\n");
+
+#-----------------------------------------------------------------------
+# script to code, back to script, using LOCALE_CODE_ALPHA_2
+#-----------------------------------------------------------------------
+$ok = 1;
+foreach $script (all_script_names())
+{
+ $code = script2code($script, LOCALE_CODE_ALPHA_2);
+ if (!defined $code)
+ {
+ $ok = 0;
+ last;
+ }
+ $reverse = code2script($code, LOCALE_CODE_ALPHA_2);
+ if (!defined $reverse)
+ {
+ $ok = 0;
+ last;
+ }
+ if ($reverse ne $script)
+ {
+ $ok = 0;
+ last;
+ }
+}
+print ($ok ? "ok 18\n" : "not ok 18\n");
+
+#-----------------------------------------------------------------------
+# script to code, back to script, using LOCALE_CODE_ALPHA_3
+#-----------------------------------------------------------------------
+$ok = 1;
+foreach $script (all_script_names())
+{
+ $code = script2code($script, LOCALE_CODE_ALPHA_3);
+ if (!defined $code)
+ {
+ $ok = 0;
+ last;
+ }
+ $reverse = code2script($code, LOCALE_CODE_ALPHA_3);
+ if (!defined $reverse)
+ {
+ $ok = 0;
+ last;
+ }
+ if ($reverse ne $script)
+ {
+ $ok = 0;
+ last;
+ }
+}
+print ($ok ? "ok 19\n" : "not ok 19\n");
+
+#-----------------------------------------------------------------------
+# script to code, back to script, using LOCALE_CODE_NUMERIC
+#-----------------------------------------------------------------------
+$ok = 1;
+foreach $script (all_script_names())
+{
+ $code = script2code($script, LOCALE_CODE_NUMERIC);
+ if (!defined $code)
+ {
+ $ok = 0;
+ last;
+ }
+ $reverse = code2script($code, LOCALE_CODE_NUMERIC);
+ if (!defined $reverse)
+ {
+ $ok = 0;
+ last;
+ }
+ if ($reverse ne $script)
+ {
+ $ok = 0;
+ last;
+ }
+}
+print ($ok ? "ok 20\n" : "not ok 20\n");
+
['!defined country2code("Banana")', 0], # illegal country name
#---- some successful examples -----------------------------------------
- ['country2code("japan") eq "jp"', 0],
- ['country2code("japan") ne "ja"', 0],
- ['country2code("Japan") eq "jp"', 0],
- ['country2code("United States") eq "us"', 0],
- ['country2code("United Kingdom") eq "gb"', 0],
- ['country2code("Andorra") eq "ad"', 0], # first in DATA segment
- ['country2code("Zimbabwe") eq "zw"', 0], # last in DATA segment
+ ['country2code("japan") eq "jp"', 0],
+ ['country2code("japan") ne "ja"', 0],
+ ['country2code("Japan") eq "jp"', 0],
+ ['country2code("United States") eq "us"', 0],
+ ['country2code("United Kingdom") eq "gb"', 0],
+ ['country2code("Andorra") eq "ad"', 0], # first in DATA
+ ['country2code("Zimbabwe") eq "zw"', 0], # last in DATA
+ ['country2code("Iran") eq "ir"', 0], # alias
+ ['country2code("North Korea") eq "kp"', 0], # alias
+ ['country2code("South Korea") eq "kr"', 0], # alias
+ ['country2code("Libya") eq "ly"', 0], # alias
+ ['country2code("Syria") eq "sy"', 0], # alias
+ ['country2code("Svalbard") eq "sj"', 0], # alias
+ ['country2code("Jan Mayen") eq "sj"', 0], # alias
+ ['country2code("USA") eq "us"', 0], # alias
+ ['country2code("United States of America") eq "us"', 0], # alias
+ ['country2code("Great Britain") eq "gb"', 0], # alias
#================================================
# TESTS FOR country_code2code
--- /dev/null
+#!./perl
+#
+# script.t - tests for Locale::Script
+#
+
+use Locale::Script;
+
+#-----------------------------------------------------------------------
+# This is an array of tests specs. Each spec is [TEST, OK_TO_DIE]
+# Each TEST is eval'd as an expression.
+# If it evaluates to FALSE, then "not ok N" is printed for the test,
+# otherwise "ok N". If the eval dies, then the OK_TO_DIE flag is checked.
+# If it is true (1), the test is treated as passing, otherwise it failed.
+#-----------------------------------------------------------------------
+@TESTS =
+(
+ #================================================
+ # TESTS FOR code2script
+ #================================================
+
+ #---- selection of examples which should all result in undef -----------
+ ['!defined code2script()', 0], # no argument
+ ['!defined code2script(undef)', 0], # undef argument
+ ['!defined code2script("aa")', 0], # illegal code
+ ['!defined code2script("aa", LOCALE_CODE_ALPHA_2)', 0], # illegal code
+ ['!defined code2script("aa", LOCALE_CODE_ALPHA_3)', 0], # illegal code
+ ['!defined code2script("aa", LOCALE_CODE_NUMERIC)', 0], # illegal code
+
+ #---- some successful examples -----------------------------------------
+ ['code2script("BO") eq "Tibetan"', 0],
+ ['code2script("Bo") eq "Tibetan"', 0],
+ ['code2script("bo") eq "Tibetan"', 0],
+ ['code2script("bo", LOCALE_CODE_ALPHA_2) eq "Tibetan"', 0],
+ ['code2script("bod", LOCALE_CODE_ALPHA_3) eq "Tibetan"', 0],
+ ['code2script("330", LOCALE_CODE_NUMERIC) eq "Tibetan"', 0],
+
+ ['code2script("yi", LOCALE_CODE_ALPHA_2) eq "Yi"', 0], # last in DATA
+ ['code2script("Yii", LOCALE_CODE_ALPHA_3) eq "Yi"', 0],
+ ['code2script("460", LOCALE_CODE_NUMERIC) eq "Yi"', 0],
+
+ ['code2script("am") eq "Aramaic"', 0], # first in DATA segment
+
+
+ #================================================
+ # TESTS FOR script2code
+ #================================================
+
+ #---- selection of examples which should all result in undef -----------
+ ['!defined code2script("BO", LOCALE_CODE_ALPHA_3)', 0],
+ ['!defined code2script("BO", LOCALE_CODE_NUMERIC)', 0],
+ ['!defined script2code()', 0], # no argument
+ ['!defined script2code(undef)', 0], # undef argument
+ ['!defined script2code("Banana")', 0], # illegal script name
+
+ #---- some successful examples -----------------------------------------
+ ['script2code("meroitic") eq "me"', 0],
+ ['script2code("burmese") eq "my"', 0],
+ ['script2code("Pahlavi") eq "ph"', 0],
+ ['script2code("Vai", LOCALE_CODE_ALPHA_3) eq "vai"', 0],
+ ['script2code("Tamil", LOCALE_CODE_NUMERIC) eq "346"', 0],
+ ['script2code("Latin") eq "la"', 0],
+ ['script2code("Latin", LOCALE_CODE_ALPHA_3) eq "lat"', 0],
+
+ #================================================
+ # TESTS FOR script_code2code
+ #================================================
+
+ #---- selection of examples which should all result in undef -----------
+ ['!defined script_code2code("bo", LOCALE_CODE_ALPHA_3, LOCALE_CODE_ALPHA_3)', 0],
+ ['!defined script_code2code("aa", LOCALE_CODE_ALPHA_2, LOCALE_CODE_ALPHA_3)', 0],
+ ['!defined script_code2code("aa", LOCALE_CODE_ALPHA_3, LOCALE_CODE_ALPHA_3)', 0],
+ ['!defined script_code2code("aa", LOCALE_CODE_ALPHA_2)', 1],
+ ['!defined script_code2code()', 1], # no argument
+ ['!defined script_code2code(undef)', 1], # undef argument
+
+ #---- some successful examples -----------------------------------------
+ ['script_code2code("BO", LOCALE_CODE_ALPHA_2, LOCALE_CODE_ALPHA_3) eq "bod"', 0],
+ ['script_code2code("bod", LOCALE_CODE_ALPHA_3, LOCALE_CODE_ALPHA_2) eq "bo"', 0],
+ ['script_code2code("Phx", LOCALE_CODE_ALPHA_3, LOCALE_CODE_ALPHA_2) eq "ph"', 0],
+ ['script_code2code("295", LOCALE_CODE_NUMERIC, LOCALE_CODE_ALPHA_3) eq "pqd"', 0],
+ ['script_code2code(170, LOCALE_CODE_NUMERIC, LOCALE_CODE_ALPHA_3) eq "tna"', 0],
+ ['script_code2code("rr", LOCALE_CODE_ALPHA_2, LOCALE_CODE_NUMERIC) eq "620"', 0],
+
+);
+
+print "1..", int(@TESTS), "\n";
+
+$testid = 1;
+foreach $test (@TESTS)
+{
+ eval "print (($test->[0]) ? \"ok $testid\\n\" : \"not ok $testid\\n\" )";
+ if ($@)
+ {
+ if (!$test->[1])
+ {
+ print "not ok $testid\n";
+ }
+ else
+ {
+ print "ok $testid\n";
+ }
+ }
+ ++$testid;
+}
+
+exit 0;
#
# Locale::Constants - defined constants for identifying codesets
#
-# $Id: Constants.pm,v 1.1 2001/03/04 17:58:15 neilb Exp $
+# $Id: Constants.pm,v 2.0 2002/02/05 22:37:58 neilb Exp $
#
use strict;
require Exporter;
use vars qw($VERSION @ISA @EXPORT);
+$VERSION = sprintf("%d.%02d", q$Revision: 2.0 $ =~ /(\d+)\.(\d+)/);
@ISA = qw(Exporter);
@EXPORT = qw(LOCALE_CODE_ALPHA_2 LOCALE_CODE_ALPHA_3 LOCALE_CODE_NUMERIC
LOCALE_CODE_DEFAULT);
use constant LOCALE_CODE_ALPHA_3 => 2;
use constant LOCALE_CODE_NUMERIC => 3;
-$VERSION = '1.00';
-
use constant LOCALE_CODE_DEFAULT => LOCALE_CODE_ALPHA_2;
1;
=head1 DESCRIPTION
B<Locale::Constants> defines symbols which are used in
-the three modules from the Locale-Codes distribution:
+the four modules from the Locale-Codes distribution:
Locale::Language
Locale::Country
Locale::Currency
+ Locale::Script
-B<Note:> at the moment only Locale::Country supports
-more than one code set.
+B<Note:> at the moment only Locale::Country and Locale::Script
+support more than one code set.
The symbols defined are used to specify which codes you
want to be used:
Codes for identification of countries.
+=item Locale::Script
+
+Codes for identification of scripts.
+
=item Locale::Currency
Codes for identification of currencies and funds.
=head1 AUTHOR
-Neil Bowers E<lt>neilb@cre.canon.co.ukE<gt>
+Neil Bowers E<lt>neil@bowers.comE<gt>
=head1 COPYRIGHT
+Copyright (C) 2002, Neil Bowers.
+
Copyright (C) 2001, Canon Research Centre Europe (CRE).
This module is free software; you can redistribute it and/or
When a code is returned by one of the functions in
this module, it will always be lower-case.
+As of version 2.00, Locale::Country supports variant
+names for countries. So, for example, the country code for "United States"
+is "us", so country2code('United States') returns 'us'.
+Now the following will also return 'us':
+
+ country2code('United States of America')
+ country2code('USA')
+
=cut
#-----------------------------------------------------------------------
# Public Global Variables
#-----------------------------------------------------------------------
use vars qw($VERSION @ISA @EXPORT @EXPORT_OK);
-$VERSION = sprintf("%d.%02d", q$Revision: 1.7 $ =~ /(\d+)\.(\d+)/);
+$VERSION = sprintf("%d.%02d", q$Revision: 2.0 $ =~ /(\d+)\.(\d+)/);
@ISA = qw(Exporter);
@EXPORT = qw(code2country country2code
all_country_codes all_country_names
=item *
When using C<country2code()>, the country name must currently appear
-exactly as it does in the source of the module. For example,
-
- country2code('United States')
-
-will return B<us>, as expected. But the following will all return C<undef>:
+exactly as it does in the source of the module. The module now supports
+a small number of variants.
- country2code('United States of America')
- country2code('Great Britain')
- country2code('U.S.A.')
-
-If there's need for it, a future version could have variants
-for country names.
+Possible extensions to this are: an interface for getting at the
+list of variant names, and regular expression matches.
=item *
module is loaded, and then held in memory.
A lazy implementation would be more memory friendly.
+=item *
+
+Support for country names in different languages.
+
=back
=head1 SEE ALSO
ISO two letter codes for identification of language (ISO 639).
+=item Locale::Script
+
+ISO codes for identification of scripts (ISO 15924).
+
=item Locale::Currency
ISO three letter codes for identification of currencies
=head1 AUTHOR
-Neil Bowers E<lt>neilb@cre.canon.co.ukE<gt>
+Neil Bowers E<lt>neil@bowers.comE<gt>
=head1 COPYRIGHT
+Copyright (C) 2002, Neil Bowers.
+
Copyright (c) 1997-2001 Canon Research Centre Europe (CRE).
This module is free software; you can redistribute it and/or
#=======================================================================
{
my ($alpha2, $alpha3, $numeric);
- my $country;
+ my ($country, @countries);
while (<DATA>)
{
next unless /\S/;
chop;
- ($alpha2, $alpha3, $numeric, $country) = split(/:/, $_, 4);
+ ($alpha2, $alpha3, $numeric, @countries) = split(/:/, $_);
- $CODES->[LOCALE_CODE_ALPHA_2]->{$alpha2} = $country;
- $COUNTRIES->[LOCALE_CODE_ALPHA_2]->{"\L$country"} = $alpha2;
+ $CODES->[LOCALE_CODE_ALPHA_2]->{$alpha2} = $countries[0];
+ foreach $country (@countries)
+ {
+ $COUNTRIES->[LOCALE_CODE_ALPHA_2]->{"\L$country"} = $alpha2;
+ }
if ($alpha3)
{
- $CODES->[LOCALE_CODE_ALPHA_3]->{$alpha3} = $country;
- $COUNTRIES->[LOCALE_CODE_ALPHA_3]->{"\L$country"} = $alpha3;
+ $CODES->[LOCALE_CODE_ALPHA_3]->{$alpha3} = $countries[0];
+ foreach $country (@countries)
+ {
+ $COUNTRIES->[LOCALE_CODE_ALPHA_3]->{"\L$country"} = $alpha3;
+ }
}
if ($numeric)
{
- $CODES->[LOCALE_CODE_NUMERIC]->{$numeric} = $country;
- $COUNTRIES->[LOCALE_CODE_NUMERIC]->{"\L$country"} = $numeric;
+ $CODES->[LOCALE_CODE_NUMERIC]->{$numeric} = $countries[0];
+ foreach $country (@countries)
+ {
+ $COUNTRIES->[LOCALE_CODE_NUMERIC]->{"\L$country"} = $numeric;
+ }
}
}
bz:blz:084:Belize
ca:can:124:Canada
cc:::Cocos (Keeling) Islands
-cd:cod:180:Congo, The Democratic Republic of the
+cd:cod:180:Congo, The Democratic Republic of the:Congo, Democratic Republic of the
cf:caf:140:Central African Republic
cg:cog:178:Congo
ch:che:756:Switzerland
et:eth:231:Ethiopia
fi:fin:246:Finland
fj:fji:242:Fiji
-fk:flk:238:Falkland Islands (Malvinas)
+fk:flk:238:Falkland Islands (Malvinas):Falkland Islands (Islas Malvinas)
fm:fsm:583:Micronesia, Federated States of
fo:fro:234:Faroe Islands
fr:fra:250:France
fx:::France, Metropolitan
ga:gab:266:Gabon
-gb:gbr:826:United Kingdom
+gb:gbr:826:United Kingdom:Great Britain
gd:grd:308:Grenada
ge:geo:268:Georgia
gf:guf:254:French Guiana
in:ind:356:India
io:::British Indian Ocean Territory
iq:irq:368:Iraq
-ir:irn:364:Iran, Islamic Republic of
+ir:irn:364:Iran, Islamic Republic of:Iran
is:isl:352:Iceland
it:ita:380:Italy
jm:jam:388:Jamaica
ki:kir:296:Kiribati
km:com:174:Comoros
kn:kna:659:Saint Kitts and Nevis
-kp:prk:408:Korea, Democratic People's Republic of
-kr:kor:410:Korea, Republic of
+kp:prk:408:Korea, Democratic People's Republic of:Korea, North:North Korea
+kr:kor:410:Korea, Republic of:Korea, South:South Korea
kw:kwt:414:Kuwait
ky:cym:136:Cayman Islands
kz:kaz:398:Kazakstan
lt:ltu:440:Lithuania
lu:lux:442:Luxembourg
lv:lva:428:Latvia
-ly:lby:434:Libyan Arab Jamahiriya
+ly:lby:434:Libyan Arab Jamahiriya:Libya
ma:mar:504:Morocco
mc:mco:492:Monaco
md:mda:498:Moldova, Republic of
mg:mdg:450:Madagascar
mh:mhl:584:Marshall Islands
-mk:mkd:807:Macedonia, the Former Yugoslav Republic of
+mk:mkd:807:Macedonia, the Former Yugoslav Republic of:Macedonia, Former Yugoslav Republic of:Macedonia
ml:mli:466:Mali
mm:mmr:104:Myanmar
mn:mng:496:Mongolia
pk:pak:586:Pakistan
pl:pol:616:Poland
pm:spm:666:Saint Pierre and Miquelon
-pn:pcn:612:Pitcairn
+pn:pcn:612:Pitcairn:Pitcairn Island
pr:pri:630:Puerto Rico
ps:pse:275:Palestinian Territory, Occupied
pt:prt:620:Portugal
qa:qat:634:Qatar
re:reu:638:Reunion
ro:rom:642:Romania
-ru:rus:643:Russian Federation
+ru:rus:643:Russian Federation:Russia
rw:rwa:646:Rwanda
sa:sau:682:Saudi Arabia
sb:slb:090:Solomon Islands
sg:sgp:702:Singapore
sh:shn:654:Saint Helena
si:svn:705:Slovenia
-sj:sjm:744:Svalbard and Jan Mayen
+sj:sjm:744:Svalbard and Jan Mayen:Jan Mayen:Svalbard
sk:svk:703:Slovakia
sl:sle:694:Sierra Leone
sm:smr:674:San Marino
sr:sur:740:Suriname
st:stp:678:Sao Tome and Principe
sv:slv:222:El Salvador
-sy:syr:760:Syrian Arab Republic
+sy:syr:760:Syrian Arab Republic:Syria
sz:swz:748:Swaziland
tc:tca:796:Turks and Caicos Islands
td:tcd:148:Chad
tr:tur:792:Turkey
tt:tto:780:Trinidad and Tobago
tv:tuv:798:Tuvalu
-tw:twn:158:Taiwan, Province of China
-tz:tza:834:Tanzania, United Republic of
+tw:twn:158:Taiwan, Province of China:Taiwan
+tz:tza:834:Tanzania, United Republic of:Tanzania
ua:ukr:804:Ukraine
ug:uga:800:Uganda
um:::United States Minor Outlying Islands
-us:usa:840:United States
+us:usa:840:United States:USA:United States of America
uy:ury:858:Uruguay
uz:uzb:860:Uzbekistan
-va:vat:336:Holy See (Vatican City State)
+va:vat:336:Holy See (Vatican City State):Hole See (Vatican City)
vc:vct:670:Saint Vincent and the Grenadines
ve:ven:862:Venezuela
-vg:vgb:092:Virgin Islands, British
+vg:vgb:092:Virgin Islands, British:British Virgin Islands
vi:vir:850:Virgin Islands, U.S.
vn:vnm:704:Vietnam
vu:vut:548:Vanuatu
# Public Global Variables
#-----------------------------------------------------------------------
use vars qw($VERSION @ISA @EXPORT);
-$VERSION = sprintf("%d.%02d", q$Revision: 1.3 $ =~ /(\d+)\.(\d+)/);
+$VERSION = sprintf("%d.%02d", q$Revision: 2.0 $ =~ /(\d+)\.(\d+)/);
@ISA = qw(Exporter);
@EXPORT = qw(&code2currency ¤cy2code
&all_currency_codes &all_currency_names );
=item *
ISO 4217 also defines a numeric code for each currency.
-Currency codes are not currently supported by this module.
+Currency codes are not currently supported by this module,
+in the same way Locale::Country supports multiple codesets.
=item *
=item Locale::Country
ISO codes for identification of country (ISO 3166).
-Supports alpha-2, alpha-3, and numeric codes.
-The currency codes use the alpha-2 codeset.
+
+=item Locale::Script
+
+ISO codes for identification of written scripts (ISO 15924).
=item ISO 4217:1995
Michael Hennecke E<lt>hennecke@rz.uni-karlsruhe.deE<gt>
and
-Neil Bowers E<lt>neilb@cre.canon.co.ukE<gt>
+Neil Bowers E<lt>neil@bowers.comE<gt>
=head1 COPYRIGHT
The C<Locale::Language> module provides access to the ISO two-letter
codes for identifying languages, as defined in ISO 639. You can either
access the codes via the L<conversion routines> (described below),
-or with the two functions which return lists of all language codes or
+or via the two functions which return lists of all language codes or
all language names.
=cut
# Public Global Variables
#-----------------------------------------------------------------------
use vars qw($VERSION @ISA @EXPORT);
-$VERSION = sprintf("%d.%02d", q$Revision: 1.6 $ =~ /(\d+)\.(\d+)/);
+$VERSION = sprintf("%d.%02d", q$Revision: 2.0 $ =~ /(\d+)\.(\d+)/);
@ISA = qw(Exporter);
@EXPORT = qw(&code2language &language2code
&all_language_codes &all_language_names );
ISO codes for identification of country (ISO 3166).
Supports 2-letter, 3-letter, and numeric country codes.
+=item Locale::Script
+
+ISO codes for identification of written scripts (ISO 15924).
+
=item Locale::Currency
ISO three letter codes for identification of currencies and funds (ISO 4217).
=item http://lcweb.loc.gov/standards/iso639-2/langhome.html
-Home page for ISO 639-2
+Home page for ISO 639-2.
=back
=head1 AUTHOR
-Neil Bowers E<lt>neilb@cre.canon.co.ukE<gt>
+Neil Bowers E<lt>neil@bowers.comE<gt>
=head1 COPYRIGHT
+Copyright (C) 2002, Neil Bowers.
+
Copyright (c) 1997-2001 Canon Research Centre Europe (CRE).
This module is free software; you can redistribute it and/or
# initialisation code - stuff the DATA into the CODES hash
#=======================================================================
{
- no utf8; # __DATA__ contains Latin-1
-
my $code;
my $language;
while (<DATA>)
{
- next unless /\S/;
+ next unless /\S/;
chop;
($code, $language) = split(/:/, $_, 2);
$CODES{$code} = $language;
--- /dev/null
+#-----------------------------------------------------------------------
+
+=head1 NAME
+
+Locale::Script - ISO codes for script identification (ISO 15924)
+
+=head1 SYNOPSIS
+
+ use Locale::Script;
+ use Locale::Constants;
+
+ $script = code2script('ph'); # 'Phoenician'
+ $code = script2code('Tibetan'); # 'bo'
+ $code3 = script2code('Tibetan',
+ LOCALE_CODE_ALPHA_3); # 'bod'
+ $codeN = script2code('Tibetan',
+ LOCALE_CODE_ALPHA_NUMERIC); # 330
+
+ @codes = all_script_codes();
+ @scripts = all_script_names();
+
+=cut
+
+#-----------------------------------------------------------------------
+
+package Locale::Script;
+use strict;
+require 5.002;
+
+#-----------------------------------------------------------------------
+
+=head1 DESCRIPTION
+
+The C<Locale::Script> module provides access to the ISO
+codes for identifying scripts, as defined in ISO 15924.
+For example, Egyptian hieroglyphs are denoted by the two-letter
+code 'eg', the three-letter code 'egy', and the numeric code 050.
+
+You can either access the codes via the conversion routines
+(described below), or with the two functions which return lists
+of all script codes or all script names.
+
+There are three different code sets you can use for identifying
+scripts:
+
+=over 4
+
+=item B<alpha-2>
+
+Two letter codes, such as 'bo' for Tibetan.
+This code set is identified with the symbol C<LOCALE_CODE_ALPHA_2>.
+
+=item B<alpha-3>
+
+Three letter codes, such as 'ell' for Greek.
+This code set is identified with the symbol C<LOCALE_CODE_ALPHA_3>.
+
+=item B<numeric>
+
+Numeric codes, such as 410 for Hiragana.
+This code set is identified with the symbol C<LOCALE_CODE_NUMERIC>.
+
+=back
+
+All of the routines take an optional additional argument
+which specifies the code set to use.
+If not specified, it defaults to the two-letter codes.
+This is partly for backwards compatibility (previous versions
+of Locale modules only supported the alpha-2 codes), and
+partly because they are the most widely used codes.
+
+The alpha-2 and alpha-3 codes are not case-dependent,
+so you can use 'BO', 'Bo', 'bO' or 'bo' for Tibetan.
+When a code is returned by one of the functions in
+this module, it will always be lower-case.
+
+=head2 SPECIAL CODES
+
+The standard defines various special codes.
+
+=over 4
+
+=item *
+
+The standard reserves codes in the ranges B<qa> - B<qt>,
+B<qaa> - B<qat>, and B<900> - B<919>, for private use.
+
+=item *
+
+B<zx>, B<zxx>, and B<997>, are the codes for unwritten languages.
+
+=item *
+
+B<zy>, B<zyy>, and B<998>, are the codes for an undetermined script.
+
+=item *
+
+B<zz>, B<zzz>, and B<999>, are the codes for an uncoded script.
+
+=back
+
+The private codes are not recognised by Locale::Script,
+but the others are.
+
+=cut
+
+#-----------------------------------------------------------------------
+
+require Exporter;
+use Carp;
+use Locale::Constants;
+
+
+#-----------------------------------------------------------------------
+# Public Global Variables
+#-----------------------------------------------------------------------
+use vars qw($VERSION @ISA @EXPORT @EXPORT_OK);
+$VERSION = sprintf("%d.%02d", q$Revision: 2.0 $ =~ /(\d+)\.(\d+)/);
+@ISA = qw(Exporter);
+@EXPORT = qw(code2script script2code
+ all_script_codes all_script_names
+ script_code2code
+ LOCALE_CODE_ALPHA_2 LOCALE_CODE_ALPHA_3 LOCALE_CODE_NUMERIC);
+
+#-----------------------------------------------------------------------
+# Private Global Variables
+#-----------------------------------------------------------------------
+my $CODES = [];
+my $COUNTRIES = [];
+
+
+#=======================================================================
+
+=head1 CONVERSION ROUTINES
+
+There are three conversion routines: C<code2script()>, C<script2code()>,
+and C<script_code2code()>.
+
+=over 8
+
+=item code2script( CODE, [ CODESET ] )
+
+This function takes a script code and returns a string
+which contains the name of the script identified.
+If the code is not a valid script code, as defined by ISO 15924,
+then C<undef> will be returned:
+
+ $script = code2script('cy'); # Cyrillic
+
+=item script2code( STRING, [ CODESET ] )
+
+This function takes a script name and returns the corresponding
+script code, if such exists.
+If the argument could not be identified as a script name,
+then C<undef> will be returned:
+
+ $code = script2code('Gothic', LOCALE_CODE_ALPHA_3);
+ # $code will now be 'gth'
+
+The case of the script name is not important.
+See the section L<KNOWN BUGS AND LIMITATIONS> below.
+
+=item script_code2code( CODE, CODESET, CODESET )
+
+This function takes a script code from one code set,
+and returns the corresponding code from another code set.
+
+ $alpha2 = script_code2code('jwi',
+ LOCALE_CODE_ALPHA_3 => LOCALE_CODE_ALPHA_2);
+ # $alpha2 will now be 'jw' (Javanese)
+
+If the code passed is not a valid script code in
+the first code set, or if there isn't a code for the
+corresponding script in the second code set,
+then C<undef> will be returned.
+
+=back
+
+=cut
+
+#=======================================================================
+sub code2script
+{
+ my $code = shift;
+ my $codeset = @_ > 0 ? shift : LOCALE_CODE_DEFAULT;
+
+
+ return undef unless defined $code;
+
+ #-------------------------------------------------------------------
+ # Make sure the code is in the right form before we use it
+ # to look up the corresponding script.
+ # We have to sprintf because the codes are given as 3-digits,
+ # with leading 0's. Eg 070 for Egyptian demotic.
+ #-------------------------------------------------------------------
+ if ($codeset == LOCALE_CODE_NUMERIC)
+ {
+ return undef if ($code =~ /\D/);
+ $code = sprintf("%.3d", $code);
+ }
+ else
+ {
+ $code = lc($code);
+ }
+
+ if (exists $CODES->[$codeset]->{$code})
+ {
+ return $CODES->[$codeset]->{$code};
+ }
+ else
+ {
+ #---------------------------------------------------------------
+ # no such script code!
+ #---------------------------------------------------------------
+ return undef;
+ }
+}
+
+sub script2code
+{
+ my $script = shift;
+ my $codeset = @_ > 0 ? shift : LOCALE_CODE_DEFAULT;
+
+
+ return undef unless defined $script;
+ $script = lc($script);
+ if (exists $COUNTRIES->[$codeset]->{$script})
+ {
+ return $COUNTRIES->[$codeset]->{$script};
+ }
+ else
+ {
+ #---------------------------------------------------------------
+ # no such script!
+ #---------------------------------------------------------------
+ return undef;
+ }
+}
+
+sub script_code2code
+{
+ (@_ == 3) or croak "script_code2code() takes 3 arguments!";
+
+ my $code = shift;
+ my $inset = shift;
+ my $outset = shift;
+ my $outcode = shift;
+ my $script;
+
+
+ return undef if $inset == $outset;
+ $script = code2script($code, $inset);
+ return undef if not defined $script;
+ $outcode = script2code($script, $outset);
+ return $outcode;
+}
+
+#=======================================================================
+
+=head1 QUERY ROUTINES
+
+There are two function which can be used to obtain a list of all codes,
+or all script names:
+
+=over 8
+
+=item C<all_script_codes ( [ CODESET ] )>
+
+Returns a list of all two-letter script codes.
+The codes are guaranteed to be all lower-case,
+and not in any particular order.
+
+=item C<all_script_names ( [ CODESET ] )>
+
+Returns a list of all script names for which there is a corresponding
+script code in the specified code set.
+The names are capitalised, and not returned in any particular order.
+
+=back
+
+=cut
+
+#=======================================================================
+sub all_script_codes
+{
+ my $codeset = @_ > 0 ? shift : LOCALE_CODE_DEFAULT;
+
+ return keys %{ $CODES->[$codeset] };
+}
+
+sub all_script_names
+{
+ my $codeset = @_ > 0 ? shift : LOCALE_CODE_DEFAULT;
+
+ return values %{ $CODES->[$codeset] };
+}
+
+
+#-----------------------------------------------------------------------
+
+=head1 EXAMPLES
+
+The following example illustrates use of the C<code2script()> function.
+The user is prompted for a script code, and then told the corresponding
+script name:
+
+ $| = 1; # turn off buffering
+
+ print "Enter script code: ";
+ chop($code = <STDIN>);
+ $script = code2script($code, LOCALE_CODE_ALPHA_2);
+ if (defined $script)
+ {
+ print "$code = $script\n";
+ }
+ else
+ {
+ print "'$code' is not a valid script code!\n";
+ }
+
+
+=head1 KNOWN BUGS AND LIMITATIONS
+
+=over 4
+
+=item *
+
+When using C<script2code()>, the script name must currently appear
+exactly as it does in the source of the module. For example,
+
+ script2code('Egyptian hieroglyphs')
+
+will return B<eg>, as expected. But the following will all return C<undef>:
+
+ script2code('hieroglyphs')
+ script2code('Egyptian Hieroglypics')
+
+If there's need for it, a future version could have variants
+for script names.
+
+=item *
+
+In the current implementation, all data is read in when the
+module is loaded, and then held in memory.
+A lazy implementation would be more memory friendly.
+
+=back
+
+=head1 SEE ALSO
+
+=over 4
+
+=item Locale::Language
+
+ISO two letter codes for identification of language (ISO 639).
+
+=item Locale::Currency
+
+ISO three letter codes for identification of currencies
+and funds (ISO 4217).
+
+=item Locale::Country
+
+ISO three letter codes for identification of countries (ISO 3166)
+
+=item ISO 15924
+
+The ISO standard which defines these codes.
+
+=item http://www.evertype.com/standards/iso15924/
+
+Home page for ISO 15924.
+
+
+=back
+
+
+=head1 AUTHOR
+
+Neil Bowers E<lt>neil@bowers.comE<gt>
+
+=head1 COPYRIGHT
+
+Copyright (c) 2002 Neil Bowers.
+
+This module is free software; you can redistribute it and/or
+modify it under the same terms as Perl itself.
+
+=cut
+
+#-----------------------------------------------------------------------
+
+#=======================================================================
+# initialisation code - stuff the DATA into the ALPHA2 hash
+#=======================================================================
+{
+ my ($alpha2, $alpha3, $numeric);
+ my $script;
+
+
+ while (<DATA>)
+ {
+ next unless /\S/;
+ chop;
+ ($alpha2, $alpha3, $numeric, $script) = split(/:/, $_, 4);
+
+ $CODES->[LOCALE_CODE_ALPHA_2]->{$alpha2} = $script;
+ $COUNTRIES->[LOCALE_CODE_ALPHA_2]->{"\L$script"} = $alpha2;
+
+ if ($alpha3)
+ {
+ $CODES->[LOCALE_CODE_ALPHA_3]->{$alpha3} = $script;
+ $COUNTRIES->[LOCALE_CODE_ALPHA_3]->{"\L$script"} = $alpha3;
+ }
+
+ if ($numeric)
+ {
+ $CODES->[LOCALE_CODE_NUMERIC]->{$numeric} = $script;
+ $COUNTRIES->[LOCALE_CODE_NUMERIC]->{"\L$script"} = $numeric;
+ }
+
+ }
+}
+
+1;
+
+__DATA__
+am:ama:130:Aramaic
+ar:ara:160:Arabic
+av:ave:151:Avestan
+bh:bhm:300:Brahmi (Ashoka)
+bi:bid:372:Buhid
+bn:ben:325:Bengali
+bo:bod:330:Tibetan
+bp:bpm:285:Bopomofo
+br:brl:570:Braille
+bt:btk:365:Batak
+bu:bug:367:Buginese (Makassar)
+by:bys:550:Blissymbols
+ca:cam:358:Cham
+ch:chu:221:Old Church Slavonic
+ci:cir:291:Cirth
+cm:cmn:402:Cypro-Minoan
+co:cop:205:Coptic
+cp:cpr:403:Cypriote syllabary
+cy:cyr:220:Cyrillic
+ds:dsr:250:Deserel (Mormon)
+dv:dvn:315:Devanagari (Nagari)
+ed:egd:070:Egyptian demotic
+eg:egy:050:Egyptian hieroglyphs
+eh:egh:060:Egyptian hieratic
+el:ell:200:Greek
+eo:eos:210:Etruscan and Oscan
+et:eth:430:Ethiopic
+gl:glg:225:Glagolitic
+gm:gmu:310:Gurmukhi
+gt:gth:206:Gothic
+gu:guj:320:Gujarati
+ha:han:500:Han ideographs
+he:heb:125:Hebrew
+hg:hgl:420:Hangul
+hm:hmo:450:Pahawh Hmong
+ho:hoo:371:Hanunoo
+hr:hrg:410:Hiragana
+hu:hun:176:Old Hungarian runic
+hv:hvn:175:Kok Turki runic
+hy:hye:230:Armenian
+iv:ivl:610:Indus Valley
+ja:jap:930:(alias for Han + Hiragana + Katakana)
+jl:jlg:445:Cherokee syllabary
+jw:jwi:360:Javanese
+ka:kam:241:Georgian (Mxedruli)
+kh:khn:931:(alias for Hangul + Han)
+kk:kkn:411:Katakana
+km:khm:354:Khmer
+kn:kan:345:Kannada
+kr:krn:357:Karenni (Kayah Li)
+ks:kst:305:Kharoshthi
+kx:kax:240:Georgian (Xucuri)
+la:lat:217:Latin
+lf:laf:215:Latin (Fraktur variant)
+lg:lag:216:Latin (Gaelic variant)
+lo:lao:356:Lao
+lp:lpc:335:Lepcha (Rong)
+md:mda:140:Mandaean
+me:mer:100:Meroitic
+mh:may:090:Mayan hieroglyphs
+ml:mlm:347:Malayalam
+mn:mon:145:Mongolian
+my:mya:350:Burmese
+na:naa:400:Linear A
+nb:nbb:401:Linear B
+og:ogm:212:Ogham
+or:ory:327:Oriya
+os:osm:260:Osmanya
+ph:phx:115:Phoenician
+ph:pah:150:Pahlavi
+pl:pld:282:Pollard Phonetic
+pq:pqd:295:Klingon plQaD
+pr:prm:227:Old Permic
+ps:pst:600:Phaistos Disk
+rn:rnr:211:Runic (Germanic)
+rr:rro:620:Rongo-rongo
+sa:sar:110:South Arabian
+si:sin:348:Sinhala
+sj:syj:137:Syriac (Jacobite variant)
+sl:slb:440:Unified Canadian Aboriginal Syllabics
+sn:syn:136:Syriac (Nestorian variant)
+sw:sww:281:Shavian (Shaw)
+sy:syr:135:Syriac (Estrangelo)
+ta:tam:346:Tamil
+tb:tbw:373:Tagbanwa
+te:tel:340:Telugu
+tf:tfn:120:Tifnagh
+tg:tag:370:Tagalog
+th:tha:352:Thai
+tn:tna:170:Thaana
+tw:twr:290:Tengwar
+va:vai:470:Vai
+vs:vsp:280:Visible Speech
+xa:xas:000:Cuneiform, Sumero-Akkadian
+xf:xfa:105:Cuneiform, Old Persian
+xk:xkn:412:(alias for Hiragana + Katakana)
+xu:xug:106:Cuneiform, Ugaritic
+yi:yii:460:Yi
+zx:zxx:997:Unwritten language
+zy:zyy:998:Undetermined script
+zz:zzz:999:Uncoded script
projects / platform / upstream / perl.git / commitdiff