-#-----------------------------------------------------------------------
-
-=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
-
-#-----------------------------------------------------------------------
+#
+# Locale::Script - ISO codes for script identification (ISO 15924)
+#
+# $Id: Script.pm,v 2.7 2004/06/10 21:19:34 neilb Exp $
+#
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+)/);
+$VERSION = sprintf("%d.%02d", q$Revision: 2.7 $ =~ /(\d+)\.(\d+)/);
@ISA = qw(Exporter);
@EXPORT = qw(code2script script2code
all_script_codes all_script_names
#=======================================================================
-
-=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
-
+#
+# code2script ( CODE [, CODESET ] )
+#
#=======================================================================
sub code2script
{
}
}
+
+#=======================================================================
+#
+# script2code ( SCRIPT [, CODESET ] )
+#
+#=======================================================================
sub script2code
{
my $script = shift;
}
}
+
+#=======================================================================
+#
+# script_code2code ( CODE, IN-CODESET, OUT-CODESET )
+#
+#=======================================================================
sub script_code2code
{
(@_ == 3) or croak "script_code2code() takes 3 arguments!";
my $code = shift;
my $inset = shift;
my $outset = shift;
- my $outcode = shift;
+ my $outcode;
my $script;
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
#=======================================================================
+#
+# all_script_codes()
+#
+#=======================================================================
sub all_script_codes
{
my $codeset = @_ > 0 ? shift : LOCALE_CODE_DEFAULT;
return keys %{ $CODES->[$codeset] };
}
+
+#=======================================================================
+#
+# all_script_names()
+#
+#=======================================================================
sub all_script_names
{
my $codeset = @_ > 0 ? shift : LOCALE_CODE_DEFAULT;
}
-#-----------------------------------------------------------------------
-
-=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 $script;
+ my ($alpha2, $alpha3, $numeric);
+ my $script;
+ local $_;
while (<DATA>)
}
}
+
+ close(DATA);
}
1;
projects / p5sagit/p5-mst-13.2.git / blobdiff