line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Lingua::Identifier::Feature::Trigrams; |
2
|
|
|
|
|
|
|
$Lingua::Identifier::Feature::Trigrams::VERSION = '0.01'; |
3
|
2
|
|
|
2
|
|
33
|
use 5.006; |
|
2
|
|
|
|
|
6
|
|
|
2
|
|
|
|
|
75
|
|
4
|
2
|
|
|
2
|
|
12
|
use strict; |
|
2
|
|
|
|
|
4
|
|
|
2
|
|
|
|
|
72
|
|
5
|
|
|
|
|
|
|
|
6
|
2
|
|
|
2
|
|
2005
|
use Text::Ngram 'ngram_counts'; |
|
2
|
|
|
|
|
6724
|
|
|
2
|
|
|
|
|
291
|
|
7
|
|
|
|
|
|
|
|
8
|
|
|
|
|
|
|
sub features { |
9
|
1
|
|
|
1
|
0
|
3
|
my $n = 3; |
10
|
|
|
|
|
|
|
|
11
|
1
|
|
|
|
|
3
|
my ($txt) = @_; |
12
|
1
|
|
|
|
|
8
|
my $hash = ngram_counts $txt, $n; |
13
|
|
|
|
|
|
|
|
14
|
1
|
|
|
|
|
23873
|
my $total = 0; |
15
|
1
|
|
|
|
|
449
|
$total += $hash->{$_} for keys %$hash; |
16
|
|
|
|
|
|
|
|
17
|
1
|
|
|
|
|
182
|
for my $k (keys %$hash) { |
18
|
781
|
|
|
|
|
1559
|
$hash->{$k} = $hash->{$k} / $total; |
19
|
|
|
|
|
|
|
} |
20
|
|
|
|
|
|
|
|
21
|
1
|
|
|
|
|
67
|
return $hash; |
22
|
|
|
|
|
|
|
} |
23
|
|
|
|
|
|
|
|
24
|
|
|
|
|
|
|
=for Pod::Coverage features |
25
|
|
|
|
|
|
|
|
26
|
|
|
|
|
|
|
=cut |
27
|
|
|
|
|
|
|
|
28
|
|
|
|
|
|
|
|
29
|
|
|
|
|
|
|
1; |