#!/usr/bin/perl

=head1 NAME

space-hist  -- tabulate histogram of whitespace patterns

=head1 SYNOPSIS

space-hist file.name

=head1 DESCRIPTION

This will read the full content of the given text file into memory,
tokenize the data on whitespace, and then count how many times each
distinct whitespace string occurs.  The various whitespace string
patterns are listed on STDOUT as strings of hex codes, with the
frequency of occurrence for each, in descending order of frequency.

=cut

use strict;

die "Usage: $0 file.txt\n" unless ( @ARGV == 1 and -f $ARGV[0] );

$/ = undef; # slurp mode
open( IN, "<", $ARGV[0] ) or die "open failed for $ARGV[0]: $!";
$_ = <IN>;

@_ = split /(\s+)/;

my %whitespace;
for my $tkn ( @_ ) {
    next unless ( $tkn =~ /^\s+$/ );
    my $wshex = join " ", map { sprintf "%02x", ord($_) } split //, $tkn;
    $whitespace{$wshex}++;
}

print "Whitespace tokens found in $ARGV[0]:\n";
for ( sort {$whitespace{$b} <=> $whitespace{$a}} keys %whitespace ) {
    printf "%4d %s\n", $whitespace{$_}, $_;
}