#!/usr/bin/perl

#  POD can be found at the bottom of this script

use strict;
use warnings;
use Compress::Zlib;
use Getopt::Long;
use Pod::Usage;

my $VERSION = 0.81;
my $dictfile = 'dict.gz';

#  Process command-line options

my %cl_options = (
    help             =>     '',
    version         =>     '',
    token_debug         =>     '',
    glossary_output     =>     '',
    dictionary_output     =>     ''
);

GetOptions(
        'help|?'      => \$cl_options{help},
        'version'     => \$cl_options{version},
        'man'         => \$cl_options{man},
        'token-debug' => \$cl_options{token_debug}, 
        'glossary'    => \$cl_options{glossary_output},
        'dictionary'  => \$cl_options{dictionary_output}    
);

print "This is version $VERSION of $0.\n" if $cl_options{version};
exit(0) if ($cl_options{version});
pod2usage(-exitstatus => 0, -verbose => 1, -msg => "Help for $0") if $cl_options{help};
pod2usage(-exitstatus => 0, -verbose => 2, -msg => "Man page for $0") if $cl_options{man};

my $file = shift;
my %dictionary = readdict(\$dictfile);
my %glossary;

findwords();

printlexicon(\%dictionary) if $cl_options{dictionary_output};
printlexicon(\%glossary) if $cl_options{glossary_output};


#  Readdict reads in the dictionary file defined above using
#  the Compress:Zlib CPAN module.  It returns a hash that is
#  used for all further dictionary operations.
#
sub readdict {
    my $dict = shift;
    my %dicthash;

    my $gz = gzopen($$dict, "rb") or die "Cannot open $$dict: $gzerrno\n" ;
    while ($gz->gzreadline($_) > 0) {
        chomp;
        $dicthash{lc($_)} = 0;
		print "Dictionary $_\n";
    }
    die "Error reading from $$dict: $gzerrno\n" if $gzerrno != Z_STREAM_END ;
    return %dicthash;
}

#  findwords() reads in a file and compares words found in the file
#  with the contents of the dictionary read in by the readdict
#  function.  It assigns counts to the elements of %dictionary and
#  creates %glossary elements and increases its values according to
#  the number of matches.

sub findwords {
    open my $if, "<", $file || die "Could not open $file: $!";
    while (<$if>) {
        chomp;
    my @elements = split(/[ '-]/,$_); # split on hyphens, too
        foreach my $element (@elements) {
            next if $element =~ /\d/; #  Don't need digits
            print "[$element]->" if $cl_options{token_debug};
            $element = lc($element);
            $element =~ s/[\s,!?._;«»)("'-]//g; 
            print "[$element]\n" if $cl_options{token_debug};
            next if $element eq '';
            if ( exists $dictionary{$element} ) {
                $dictionary{$element}++;
            } else {
                $glossary{$element}++;
				print "Text: @elements\n"; 
            }
        }
    }
}

#  Showmatches reads in a lexicon hash via a reference and prints all words out 
#  that have been seen in the findwords() function along with a frequency count.
#
sub  printlexicon {
    my $lexicon = shift;
    my $counter = 0;
    foreach my $key (sort keys %$lexicon) {
        if ( $$lexicon{$key} > 0 ) {
            print $key . " : " . $$lexicon{$key} . "\n";
            $counter++;
        }
    }
    print "\n$counter entries total\n";
}

__END__