blob: 3aa5183b4145596d943db83098e20378e0efcb64 (
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
58
59
|
#!/usr/bin/perl
#===============================================================================
#
# FILE: ch-2.pl
#
# USAGE: ./ch-2.pl
#
# DESCRIPTION: https://perlweeklychallenge.org/blog/perl-weekly-challenge-024/
#
#
# Create a script to implement full text search functionality using Inverted Index. According to wikipedia:
#
# In computer science, an inverted index (also referred to as a postings file or inverted file) is a database index storing a mapping from content, such as words or numbers, to its locations in a table, or in a document or a set of documents (named in contrast to a forward index, which maps from documents to content). The purpose of an inverted index is to allow fast full-text searches, at a cost of increased processing when a document is added to the database.
#
#
#
# OPTIONS: ---
# REQUIREMENTS: ---
# BUGS: ---
# NOTES: ---
# AUTHOR: Lubos Kolouch
# ORGANIZATION:
# VERSION: 1.0
# CREATED: 09/08/2019 12:32:53 PM
# REVISION: ---
#===============================================================================
use strict;
use warnings;
use Carp;
use Data::Dumper;
my @files = glob "*";
my %words;
for my $file (@files) {
open my $what, '<', $file or croak "Cannot open $file $!";
while (my $line = <$what>) {
for (split /\s+/msx, $line) {
s/\W//gmsx;
$words{lc($_)}{$file} = 1;
}
}
close $what;
}
warn Dumper \%words;
# ------ TESTS -----------
use Test::More;
is ($words{'using'}{'ch-2.pl'}, 1);
is ($words{'using'}{'ch-1.pl'}, undef);
done_testing;
|
