0
  1   oˆl–Ãa¾”êh¥8 ]¸î¥1hß×…ži¦_‹uÐb&=LV[(ÃÛ ?÷     opackage Unicode::UCD;

use strict;
use warnings;
no warnings 'surrogate';    # surrogates can be inputs to this
use charnames ();
use Unicode::Normalize qw(getCombinClass NFD);

our $VERSION = '0.43';

use Storable qw(dclone);

require Exporter;

our @ISA = qw(Exporter);

our @EXPORT_OK = qw(charinfo
		    charblock charscript
		    charblocks charscripts
		    charinrange
		    general_categories bidi_types
		    compexcl
		    casefold casespec
		    namedseq
                    num
                    prop_aliases
                    prop_value_aliases
                    prop_invlist
                    prop_invmap
                    MAX_CP
                );

use Carp;

=head1 NAME

Unicode::UCD - Unicode character database

=head1 SYNOPSIS

    use Unicode::UCD 'charinfo';
    my $charinfo   = charinfo($codepoint);

    use Unicode::UCD 'casefold';
    my $casefold = casefold(0xFB00);

    use Unicode::UCD 'casespec';
    my $casespec = casespec(0xFB00);

    use Unicode::UCD 'charblock';
    my $charblock  = charblock($codepoint);

    use Unicode::UCD 'charscript';
    my $charscript = charscript($codepoint);

    use Unicode::UCD 'charblocks';
    my $charblocks = charblocks();

    use Unicode::UCD 'charscripts';
    my $charscripts = charscripts();

    use Unicode::UCD qw(charscript charinrange);
    my $range = charscript($script);
    print "looks like $script\n" if charinrange($range, $codepoint);

    use Unicode::UCD qw(general_categories bidi_types);
    my $categories = general_categories();
    my $types = bidi_types();

    use Unicode::UCD 'prop_aliases';
    my @space_names = prop_aliases("space");

    use Unicode::UCD 'prop_value_aliases';
    my @gc_punct_names = prop_value_aliases("Gc", "Punct");

    use Unicode::UCD 'prop_invlist';
    my @puncts = prop_invlist("gc=punctuation");

    use Unicode::UCD 'prop_invmap';
    my ($list_ref, $map_ref, $format, $missing)
                                      = prop_invmap("General Category");

    use Unicode::UCD 'compexcl';
    my $compexcl = compexcl($codepoint);

    use Unicode::UCD 'namedseq';
    my $namedseq = namedseq($named_sequence_name);

    my $unicode_version = Unicode::UCD::UnicodeVersion();

    my $convert_to_numeric =
              Unicode::UCD::num("\N{RUMI DIGIT ONE}\N{RUMI DIGIT TWO}");

=head1 DESCRIPTION

The Unicode::UCD module offers a series of functions that
provide a simple interface to the Unicode
Character Database.

=head2 code point argument

Some of the functions are called with a I<code point argument>, which is either
a decimal or a hexadecimal scalar designating a Unicode code point, or C<U+>
followed by hexadecimals designating a Unicode code point.  In other words, if
you want a code point to be interpreted as a hexadecimal number, you must
prefix it with either C<0x> or C<U+>, because a string like e.g. C<123> will be
interpreted as a decimal code point.  Note that the largest code point in
Unicode is U+10FFFF.

=cut

my $BLOCKSFH;
my $VERSIONFH;
my $CASEFOLDFH;
my $CASESPECFH;
my $NAMEDSEQFH;

sub openunicode {
    my ($rfh, @path) = @_;
    my $f;
    unless (defined $$rfh) {
	for my $d (@INC) {
	    use File::Spec;
	    $f = File::Spec->catfile($d, "unicore", @path);
	    last if open($$rfh, $f);
	    undef $f;
	}
	croak __PACKAGE__, ": failed to find ",
              File::Spec->catfile(@path), " in @INC"
	    unless defined $f;
    }
    return $f;
}

=head2 B<charinfo()>

    use Unicode::UCD 'charinfo';

    my $charinfo = charinfo(0x41);

This returns information about the input L</code point argument>
as a reference to a hash of fields as defined by the Unicode
standard.  If the L</code point argument> is not assigned in the standard
(i.e., has the general category C<Cn> meaning C<Unassigned>)
or is a non-character (meaning it is guaranteed to never be assigned in
the standard),
C<undef> is returned.

Fields that aren't applicable to the particular code point argument exist in the
returned hash, and are empty. 

The keys in the hash