#!/usr/bin/perl

# http://perlmonks.org/?node_id=1084067

# Script by Jim

#use v5.10;

use strict;

use warnings;

use utf8;

use Encode qw( encode_utf8 );

use Unicode::UCD qw( charblock );

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

while (my $word = <DATA>) {

    chomp $word;

    my $length_in_bytes       = length_in_bytes($word);

    my $length_in_code_points = length_in_code_points($word);

    my $length_in_graphemes   = length_in_graphemes($word);

    my $code_points_in_blocks = code_points_in_blocks($word);

    printf "%-12s | Bytes: %2d | Code Points: %2d | Graphemes: %2d | Blocks: %s\n",

        $word,

        $length_in_bytes,

        $length_in_code_points,

        $length_in_graphemes,

        $code_points_in_blocks;

}

exit 0;

sub length_in_bytes {

    my $word = shift;

    my $length = length encode_utf8($word);

    return $length;

}

sub length_in_code_points {

    my $word = shift;

    my $length = length $word;

    return $length;

}

sub length_in_graphemes {

    my $word = shift;

    my $length = () = $word =~ m/\X/g;

    return $length;

}

sub code_points_in_blocks {

    my $word = shift;

    my %total_code_points_by;

    my $blocks = '';

    for my $character (split m//, $word) {

        my $block = charblock(ord $character);

        $total_code_points_by{$block}++;

    }

    for my $block (sort keys %total_code_points_by) {

        my $total = $total_code_points_by{$block};

        $blocks .= sprintf "%s%s (%d)",

                   (length $blocks ? ', ' : ''), $block, $total;

    }

    return $blocks;

}

__DATA__

æ

æð

æða

æðaber

æðahnútur

æðakölkun

æðardúnn

æðarfugl

æðarkolla

æðarkóngur

æðarvarp

æði

æðimargur

æðisgenginn

æðiskast

æðislegur

æðrast

æðri

æðrulaus

æðruleysi

æðruorð

æðrutónn

æðstur

æður

æfa