#!/usr/bin/env perl
use warnings;
use strict;
use open qw/:std :utf8/;
use Text::Unidecode;
use Encode;

print "# Text::Unidecode demo:\n";
my $test = "\N{U+201C}test\N{U+201D} \N{U+2013} test\N{U+2026}";
print " original: ", $test, "\n";
print "asciified: ", unidecode($test), "\n";

# set up some test data
my $str = "\N{U+CF} spent 20\N{U+20AC} \N{U+C3}t the c\N{U+AA}f\N{U+E9}\n";
{
	open my $fh1, '>:raw:encoding(CP-1252)', 'one.txt' or die $!;
	print $fh1 $str;
	close $fh1;
	open my $fh2, '>:raw:encoding(Latin-9)', 'two.txt' or die $!;
	print $fh2 $str;
	close $fh2;
	open my $fh3, '>:raw:encoding(UTF-8)', 'three.txt' or die $!;
	print $fh3 $str;
	close $fh3;
}

my $expected_chars = qr/[\N{U+20AC}]/u; # heuristic
my $unexpected_chars = qr/[\N{U+80}]/u; # heuristic
for my $file (qw/ one.txt two.txt three.txt /) {
	# slurp the raw file as undecoded bytes
	open my $fh, '<:raw', $file or die "$file: $!";
	my $bytes = do { local $/; <$fh> };
	close $fh;
	my $string;
	# try different encodings
	for my $enc (qw/ UTF-8 Latin-9 CP-1252 /) {
		$string = eval { decode($enc, $bytes,
			Encode::FB_CROAK|Encode::LEAVE_SRC) };
		if ( defined $string && $string =~ $expected_chars
			&& $string !~ $unexpected_chars )
				{ print "### $file looks like $enc\n"; last }
		else { print "### $file is NOT $enc\n" }
	}
	die "Failed to decode $file" unless defined $string;
	print $string;
	print unidecode($string);
}