blob: e86e04a7f299eb4be899de91e7023dd76c9a3cff (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
#!/usr/bin/perl
# USAGE: generate_distribution.pl word_list > character_list
use warnings;
use strict;
use Getopt::Long;
use Pod::Usage;
my $help = 0;
GetOptions(
'help|?' => \$help) or pod2usage(2);
pod2usage(1) if $help;
=pod
=head1 NAME
generate_distribution.pl - Generate letter distribution data
=head1 SYNOPSIS
One argument: the output of generate_words.pl.
=cut
binmode STDOUT, ':utf8';
my %characters;
sub read_characters {
for my $arg (@ARGV) {
open (my $input, "<:encoding(utf8)", $arg);
while (<$input>) {
chomp;
my ($word, $count) = split(/\s/, $_);
for my $character (split(/;/, $word)) {
$characters{$character} += $count;
}
}
}
}
sub spit_characters {
my @sorted_characters = sort { $characters{$b} <=> $characters{$a} } keys %characters;
for my $character (@sorted_characters) {
print "$character $characters{$character}\n";
}
}
read_characters();
spit_characters();
|
