Space Time Stories

#! /usr/bin/perl

my %word_list; # this hash will have an entry for every distinct word
my $count = 0; # count of distinct words
my $total_words =0; # total # of words used
my $file = shift; # name of text file to parse

open FILE, “<$file”;

while (<FILE>){ #for each line in the file

my @words = split; # split each line into separate words

foreach my $word (@words) { # for each word on that line

$word =~ s/[.]//g;  # strip any periods
$word =~ s/”//g;  # strip any quotes
$word =~ s/,//g;  # strip any commas
$word =~ s/’//g;  # strip any apostrophes

# unless ($word =~ /ly/) {next;} # remove the first # sign if you want to look for adverbs

if ($word_list{$word}) { # if the word has already been seen increment the count
$word_list{$word}++;
}
else {
$word_list{$word} = 1; # else it’s a new word, start with 1
}
$total_words++; # increment counter for total # of words
}

print “\nWord usage in $file\n\n\n”;

foreach $key (sort sort_values (keys(%word_list))) { # get the keys, sort them by value, for each one
print “$word_list{$key} \t $key\n”;
$count ++; # increment counter for distinct # of words
}

print “\n\nTotal of $total_words words, $count distinct words used\n”;
}

sub sort_values { # sort a hash by value
$word_list{$a} <=> $word_list{$b};
}