Unicode Normalization test using Unicode::Normalize

unicode-normalize-test.pl

#! /usr/bin/perl

use strict;
use local::lib;
use Unicode::Normalize;
use bytes;
no bytes;
use utf8;
use Encode qw(encode_utf8);

binmode STDOIUT, ':raw';

our $str_list = [
    "漢字",          "パンダ",
    "ABC",             "ﾄﾝﾄｶｲﾓ",
    "ﾊﾟﾝﾀﾞ", "＃♯１",
    "⓵\x{20DD}１",  "①⑳",
    "﹡",             "ゔヴ",
    "⒙",
];

main();

exit(0);

sub main {
    my $first = 1;
    foreach my $str (@$str_list) {
        print "\n" unless $first;
        foreach my $n (qw(NFD NFC NFKD NFKC)) {
            my $cstr       = eval "$n(\$str)";
            my $cstr_bytes = bytes::length($cstr);
            my $cstr_len   = length($cstr);
            printf " %s: '%s' (%d bytes, %d chars)\n", $n, encode_utf8($cstr),
                $cstr_bytes, $cstr_len;
        }
        $first = 0;
    }
}

## end of script