code-backups/perl/unicode.pl

#!/usr/bin/env perl

# unicode.pl

# Shows how to enable support for utf-8
# License: CC0

# Must read for troubleshooting or adapting:
# https://newbedev.com/why-does-modern-perl-avoid-utf-8-by-default

# To use decode_utf8
require Encode;
# For DATA file handles
# Ref:
#   - https://users.cs.cf.ac.uk/Dave.Marshall/PERL/node105.html
#   - https://www.perl.com/article/24/2013/5/11/Perl-tokens-you-should-know/
binmode DATA, ":utf8";
# Allow wide character outputs without warning
binmode STDOUT, ":utf8";
# To enable the use of unicode throughout perl functions
use feature 'unicode_strings';
# Since this script is UTF-8 encoded
use utf8;
# To handle CLI parameters
use Getopt::Long;

# Shows up when --help or -h is passed
sub help_text {
	print("usage: unicode.pl [-h] [TEXT]

Prints the text that is passed to it.

optional arguments:
  -h, --help            show this help message and exit

usage:
  Simple example:
    ./unicode.pl 'some ইউনিকোড test'
  Also supports piping the TEXT:
    echo 'some ইউনিকোড test' | ./unicode.pl -\n");
	exit;
}

my $stdio;

# An example subroutine that just prints whatever is passed to it.
sub printit {
	print(Encode::decode_utf8(shift, 1) . "\n");
}

# Process CLI parameters and update config values as necessary
GetOptions (# This is for parameter that isn't a parameter (e.g.
			# starting with -- or - or the value of them.)
			'<>'             => \&printit,
			# This has the value of "1" when being piped something.
			''               => \$stdio,
			# To show help text when -h or --help is passed.
			"h|help"         => \&help_text)
or die("Error in command line arguments. Please review and try again.\n");

# Process stdin
if ($stdio) {
	# Get the piped string
	my $input = <>;
	# Get rid of extra empty line at the end
	chomp $input;
	# Send it to printit function
	printit($input);
}