line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Plucene::Analysis::LowerCaseTokenizer; |
2
|
|
|
|
|
|
|
|
3
|
|
|
|
|
|
|
=head1 NAME |
4
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
Plucene::Analysis::LowerCaseTokenizer - tokenizer which also lower cases text |
6
|
|
|
|
|
|
|
|
7
|
|
|
|
|
|
|
=head1 SYNOPSIS |
8
|
|
|
|
|
|
|
|
9
|
|
|
|
|
|
|
# isa Plucene::Analysis::LetterTokenizer |
10
|
|
|
|
|
|
|
|
11
|
|
|
|
|
|
|
=head1 DESCRIPTION |
12
|
|
|
|
|
|
|
|
13
|
|
|
|
|
|
|
This tokenizer divides text at non letters, and also lower cases them. |
14
|
|
|
|
|
|
|
|
15
|
|
|
|
|
|
|
=head1 METHODS |
16
|
|
|
|
|
|
|
|
17
|
|
|
|
|
|
|
=cut |
18
|
|
|
|
|
|
|
|
19
|
19
|
|
|
19
|
|
102
|
use strict; |
|
19
|
|
|
|
|
44
|
|
|
19
|
|
|
|
|
656
|
|
20
|
19
|
|
|
19
|
|
132
|
use warnings; |
|
19
|
|
|
|
|
40
|
|
|
19
|
|
|
|
|
720
|
|
21
|
|
|
|
|
|
|
|
22
|
19
|
|
|
19
|
|
106
|
use base 'Plucene::Analysis::LetterTokenizer'; |
|
19
|
|
|
|
|
49
|
|
|
19
|
|
|
|
|
11055
|
|
23
|
|
|
|
|
|
|
|
24
|
143610
|
|
|
143610
|
1
|
462723
|
sub normalize { lc $_[1] } |
25
|
|
|
|
|
|
|
|
26
|
|
|
|
|
|
|
1; |