#!perl

use strict;
use warnings;
use v5.12;

use Encode qw( encode );
use English qw( -no_match_vars );
use Unicode::UCD qw( charinfo );

binmode STDOUT, ':encoding(UTF-8)';

# Include the Unicode byte order mark...
print "\x{FEFF}";

local $OUTPUT_AUTOFLUSH        = 1;
local $OUTPUT_RECORD_SEPARATOR = "\n";
local $OUTPUT_FIELD_SEPARATOR  = "\t";

CODE:
for my $code (0x0000 .. 0x10FFFF) {
    # Don't complain about surrogate codes...
    no warnings qw( utf8 );

    my $charinfo = charinfo($code);

    # Skip unassigned code points and non-characters...
    next CODE unless defined $charinfo;

    my $codepoint = sprintf 'U+%06X', $code;
    my $character = chr $code;
    my $name      = $charinfo->{'name'};
    my $category  = $charinfo->{'category'};
    my $block     = $charinfo->{'block'};
    my $script    = $charinfo->{'script'};

    my @utf8_octets
        = map { ord }
          split m//, encode('UTF-8', $character);

    my $utf8_hexstring
        = join ' ',
          map { sprintf '%02X', $_ }
          @utf8_octets;

    my $utf8_binstring
        = join ' ',
          map { sprintf '%08b', $_ }
          @utf8_octets;

    # Don't try to print unprintable or private use characters...
    $character = '' if $category eq 'Cc'
                    || $category eq 'Co'
                    || $category eq 'Cs';

    print $character,
          $code,
          $codepoint,
          $utf8_hexstring,
          $utf8_binstring,
          $name,
          $category,
          $block,
          $script;
}

exit 0;

##</code><code>##

#!perl

use strict;
use warnings;
use v5.12;

use Encode qw( encode_utf8 );
use English qw( -no_match_vars );
use Unicode::UCD qw( charinfo );

binmode STDOUT, ':encoding(UTF-8)';

# Include a Unicode byte order mark in the output...
print "\x{FEFF}";

local $OUTPUT_AUTOFLUSH        = 1;
local $OUTPUT_RECORD_SEPARATOR = "\n";
local $OUTPUT_FIELD_SEPARATOR  = "\t";

CODE:
for my $code (0x000000 .. 0x10FFFF) {
    # Look up the code point in the Unicode Character Database...
    my $charinfo = charinfo($code);

    # Skip unassigned code points and non-characters...
    next CODE unless defined $charinfo;

    my $codepoint = sprintf 'U+%06X', $code;
    my $character = chr $code;
    my $name      = $charinfo->{'name'};
    my $category  = $charinfo->{'category'};
    my $block     = $charinfo->{'block'};
    my $script    = $charinfo->{'script'};

    my @utf8_octets
        = unpack 'C*', encode_utf8($character);

    my $utf8_hex_string
        = join ' ', map { sprintf '%02X', $ARG } @utf8_octets;

    my $utf8_bin_string
        = join ' ', map { sprintf '%08b', $ARG } @utf8_octets;

   # Don't try to print unprintable or private use characters...
   if ($category =~ m/^C[cfos]$/) {
         $character = '';

        # Don't falsely represent surrogates as valid UTF-8...
        if ($category eq 'Cs') {
            $utf8_hex_string = $utf8_bin_string = '';
        }
    }

    print $character,
          $code,
          $codepoint,
          $utf8_hex_string,
          $utf8_bin_string,
          $name,
          $category,
          $block,
          $script;
}

exit 0;

##</code><code>##

    # Don't complain about surrogates...
    no warnings qw( surrogate );