#!/usr/bin/perl

use strict;

# Berkeley DBMs are my fav.
use DB_File;

my %Index;

# remove the old index and start fresh
unlink("/home/maverick/tmp/index_dbm");
tie (%Index,'DB_File',"/home/maverick/tmp/index_dbm",O_RDWR|O_CREAT,0640,$DB_BTREE) || die "Tie Failed: $!";

foreach my $file (glob("/home/maverick/tmp/*.txt")) {

        open(F,$file) || die "Can't open $file: $!";

        # slirp up the file and make a list of words
        my @words = map { split(/\W+/,$_) } <F>;

        # add this file to the list of matches for this word
        my %uniq;
        foreach (@words) {
                if (!defined($uniq{$_})) {
                        # we've not seen this word before, so we add it.
                        # I'm also assuming that ~ is safe to use as a seperator.
                        if (!defined($Index{$_})) {
                                # it's the first additon of this word, so I don't need to prepend a '~'
                                $Index{$_} = $file;
                        }
                        else {
                                $Index{$_} .= "~$file";
                        }
                        $uniq{$_} = 1;
                }
        }
	close(F);
}
untie %Index;