line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Lingua::StopWords::EN; |
2
|
|
|
|
|
|
|
|
3
|
2
|
|
|
2
|
|
1203
|
use strict; |
|
2
|
|
|
|
|
6
|
|
|
2
|
|
|
|
|
68
|
|
4
|
2
|
|
|
2
|
|
10
|
use warnings; |
|
2
|
|
|
|
|
5
|
|
|
2
|
|
|
|
|
62
|
|
5
|
|
|
|
|
|
|
|
6
|
2
|
|
|
2
|
|
687
|
use utf8; |
|
2
|
|
|
|
|
18
|
|
|
2
|
|
|
|
|
17
|
|
7
|
|
|
|
|
|
|
|
8
|
2
|
|
|
2
|
|
670
|
use Encode qw(encode); |
|
2
|
|
|
|
|
11466
|
|
|
2
|
|
|
|
|
175
|
|
9
|
|
|
|
|
|
|
|
10
|
2
|
|
|
2
|
|
16
|
use Exporter; |
|
2
|
|
|
|
|
4
|
|
|
2
|
|
|
|
|
748
|
|
11
|
|
|
|
|
|
|
our @ISA = qw(Exporter); |
12
|
|
|
|
|
|
|
|
13
|
|
|
|
|
|
|
our %EXPORT_TAGS = ( 'all' => [ qw( getStopWords ) ] ); |
14
|
|
|
|
|
|
|
our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } ); |
15
|
|
|
|
|
|
|
our $VERSION = 0.10; |
16
|
|
|
|
|
|
|
|
17
|
|
|
|
|
|
|
sub getStopWords { |
18
|
3
|
100
|
66
|
3
|
0
|
17
|
if ( @_ and $_[0] eq 'UTF-8' ) { |
19
|
1
|
|
|
|
|
3
|
my %stoplist = map { ( $_, 1 ) } _stopwords(); |
|
174
|
|
|
|
|
321
|
|
20
|
1
|
|
|
|
|
17
|
return \%stoplist; |
21
|
|
|
|
|
|
|
} |
22
|
|
|
|
|
|
|
else { |
23
|
2
|
|
|
|
|
9
|
my %stoplist = map { ( encode("iso-8859-1", $_), 1 ) } _stopwords(); |
|
348
|
|
|
|
|
9184
|
|
24
|
2
|
|
|
|
|
367
|
return \%stoplist; |
25
|
|
|
|
|
|
|
} |
26
|
|
|
|
|
|
|
} |
27
|
|
|
|
|
|
|
|
28
|
|
|
|
|
|
|
sub _stopwords { |
29
|
3
|
|
|
3
|
|
70
|
return qw( |
30
|
|
|
|
|
|
|
i me my myself we our ours ourselves you your yours yourself |
31
|
|
|
|
|
|
|
yourselves he him his himself she her hers herself it its |
32
|
|
|
|
|
|
|
itself they them their theirs themselves what which who whom |
33
|
|
|
|
|
|
|
this that these those am is are was were be been being have has |
34
|
|
|
|
|
|
|
had having do does did doing would should could ought i'm |
35
|
|
|
|
|
|
|
you're he's she's it's we're they're i've you've we've they've |
36
|
|
|
|
|
|
|
i'd you'd he'd she'd we'd they'd i'll you'll he'll she'll we'll |
37
|
|
|
|
|
|
|
they'll isn't aren't wasn't weren't hasn't haven't hadn't |
38
|
|
|
|
|
|
|
doesn't don't didn't won't wouldn't shan't shouldn't can't |
39
|
|
|
|
|
|
|
cannot couldn't mustn't let's that's who's what's here's |
40
|
|
|
|
|
|
|
there's when's where's why's how's a an the and but if or |
41
|
|
|
|
|
|
|
because as until while of at by for with about against between |
42
|
|
|
|
|
|
|
into through during before after above below to from up down in |
43
|
|
|
|
|
|
|
out on off over under again further then once here there when |
44
|
|
|
|
|
|
|
where why how all any both each few more most other some such |
45
|
|
|
|
|
|
|
no nor not only own same so than too very |
46
|
|
|
|
|
|
|
); |
47
|
|
|
|
|
|
|
} |
48
|
|
|
|
|
|
|
|
49
|
|
|
|
|
|
|
1; |