line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Plucene::Analysis::Analyzer; |
2
|
|
|
|
|
|
|
|
3
|
|
|
|
|
|
|
=head1 NAME |
4
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
Plucene::Analysis::Analyzer - base class for Analyzers |
6
|
|
|
|
|
|
|
|
7
|
|
|
|
|
|
|
=head1 SYNOPSIS |
8
|
|
|
|
|
|
|
|
9
|
|
|
|
|
|
|
my $analyzer = Plucene::Analysis::Analyzer::Subclass->new; |
10
|
|
|
|
|
|
|
|
11
|
|
|
|
|
|
|
=head1 DESCRIPTION |
12
|
|
|
|
|
|
|
|
13
|
|
|
|
|
|
|
This is an abstract base class of Analyzers. |
14
|
|
|
|
|
|
|
|
15
|
|
|
|
|
|
|
An Analyzer builds TokenStreams, which analyze text. It thus represents |
16
|
|
|
|
|
|
|
a policy for extracting index terms from text. |
17
|
|
|
|
|
|
|
|
18
|
|
|
|
|
|
|
Typical implementations first build a Tokenizer, which breaks the stream |
19
|
|
|
|
|
|
|
of characters from the Reader into raw Tokens. One or more TokenFilters |
20
|
|
|
|
|
|
|
may then be applied to the output of the Tokenizer. |
21
|
|
|
|
|
|
|
|
22
|
|
|
|
|
|
|
=head1 METHODS |
23
|
|
|
|
|
|
|
|
24
|
|
|
|
|
|
|
=cut |
25
|
|
|
|
|
|
|
|
26
|
19
|
|
|
19
|
|
112
|
use strict; |
|
19
|
|
|
|
|
37
|
|
|
19
|
|
|
|
|
607
|
|
27
|
19
|
|
|
19
|
|
97
|
use warnings; |
|
19
|
|
|
|
|
39
|
|
|
19
|
|
|
|
|
1240
|
|
28
|
|
|
|
|
|
|
|
29
|
|
|
|
|
|
|
=head2 new |
30
|
|
|
|
|
|
|
|
31
|
|
|
|
|
|
|
my $analyzer = Plucene::Analysis::Analyzer::Subclass->new; |
32
|
|
|
|
|
|
|
|
33
|
|
|
|
|
|
|
=cut |
34
|
|
|
|
|
|
|
|
35
|
197
|
|
|
197
|
1
|
4025
|
sub new { bless {}, shift } |
36
|
|
|
|
|
|
|
|
37
|
|
|
|
|
|
|
=head2 tokenstream |
38
|
|
|
|
|
|
|
|
39
|
|
|
|
|
|
|
This must be defined in a subclass |
40
|
|
|
|
|
|
|
|
41
|
|
|
|
|
|
|
=cut |
42
|
|
|
|
|
|
|
|
43
|
0
|
|
|
0
|
1
|
|
sub tokenstream { die "tokenstream must be defined in a subclass" } |
44
|
|
|
|
|
|
|
|
45
|
|
|
|
|
|
|
1; |