|  line  | 
 stmt  | 
 bran  | 
 cond  | 
 sub  | 
 pod  | 
 time  | 
 code  | 
| 
1
 | 
  
 
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 package Lingua::YaTeA::TermCandidate;  | 
| 
2
 | 
5
 | 
 
 | 
 
 | 
  
5
  
 | 
 
 | 
32
 | 
 use strict;  | 
| 
 
 | 
5
 | 
 
 | 
 
 | 
 
 | 
 
 | 
10
 | 
    | 
| 
 
 | 
5
 | 
 
 | 
 
 | 
 
 | 
 
 | 
135
 | 
    | 
| 
3
 | 
5
 | 
 
 | 
 
 | 
  
5
  
 | 
 
 | 
27
 | 
 use warnings;  | 
| 
 
 | 
5
 | 
 
 | 
 
 | 
 
 | 
 
 | 
22
 | 
    | 
| 
 
 | 
5
 | 
 
 | 
 
 | 
 
 | 
 
 | 
7793
 | 
    | 
| 
4
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 # use UNIVERSAL;  | 
| 
5
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 # use Scalar::Util qw(blessed);  | 
| 
6
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
7
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $id = 0;  | 
| 
8
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 our $VERSION=$Lingua::YaTeA::VERSION;  | 
| 
9
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
10
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub new  | 
| 
11
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
12
 | 
306
 | 
 
 | 
 
 | 
  
306
  
 | 
  
1
  
 | 
537
 | 
     my ($class) = @_;  | 
| 
13
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
463
 | 
     my $this;  | 
| 
14
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
751
 | 
     $this->{ID} = $id++;  | 
| 
15
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
550
 | 
     $this->{KEY} = "";  | 
| 
16
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
518
 | 
     $this->{HEAD} = ();  | 
| 
17
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
622
 | 
     $this->{WORDS} = [];  | 
| 
18
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
609
 | 
     $this->{OCCURRENCES} = [];  | 
| 
19
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
501
 | 
     $this->{RELIABILITY} = ();  | 
| 
20
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
467
 | 
     $this->{TERM_STATUS} = 1;  | 
| 
21
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
643
 | 
     $this->{ORIGINAL_PHRASE} = ();  | 
| 
22
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #     $this->{WEIGHT} = 0;  | 
| 
23
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
633
 | 
     $this->{WEIGHTS} = {};  | 
| 
24
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
492
 | 
     $this->{ROOT} = ();  | 
| 
25
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
531
 | 
     $this->{MNP_STATUS} = 0;  # added by SA 13/02/2009  | 
| 
26
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
515
 | 
     bless ($this,$class);  | 
| 
27
 | 
306
 | 
 
 | 
 
 | 
 
 | 
 
 | 
706
 | 
     return $this;  | 
| 
28
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
29
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
30
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub setROOT {  | 
| 
31
 | 
301
 | 
 
 | 
 
 | 
  
301
  
 | 
  
0
  
 | 
489
 | 
     my ($this, $ROOT) = @_;  | 
| 
32
 | 
301
 | 
 
 | 
 
 | 
 
 | 
 
 | 
415
 | 
     push @{$this->{ROOT}}, $ROOT;  | 
| 
 
 | 
301
 | 
 
 | 
 
 | 
 
 | 
 
 | 
661
 | 
    | 
| 
33
 | 
301
 | 
 
 | 
 
 | 
 
 | 
 
 | 
611
 | 
     return($this->{ROOT});  | 
| 
34
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
35
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
36
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getROOT {  | 
| 
37
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
0
  
 | 
0
 | 
     my ($this) = @_;  | 
| 
38
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     return($this->{ROOT});  | 
| 
39
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
40
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
41
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub setTermStatus {  | 
| 
42
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
1
  
 | 
0
 | 
     my ($this, $status) = @_;  | 
| 
43
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     $this->{TERM_STATUS} = $status;  | 
| 
44
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     return($this->{TERM_STATUS});  | 
| 
45
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
46
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
47
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getTermStatus {  | 
| 
48
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
1
  
 | 
0
 | 
     my ($this) = @_;  | 
| 
49
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     return($this->{TERM_STATUS});  | 
| 
50
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
51
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
52
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub isTerm {  | 
| 
53
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
1
  
 | 
0
 | 
     my ($this) = @_;  | 
| 
54
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
55
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     return($this->getTermStatus != 0);  | 
| 
56
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
57
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
58
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getLength  | 
| 
59
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
60
 | 
1210
 | 
 
 | 
 
 | 
  
1210
  
 | 
  
1
  
 | 
1870
 | 
     my ($this) = @_;  | 
| 
61
 | 
1210
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1515
 | 
     return scalar @{$this->getWords};  | 
| 
 
 | 
1210
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1983
 | 
    | 
| 
62
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
63
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
64
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub addWord  | 
| 
65
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
66
 | 
408
 | 
 
 | 
 
 | 
  
408
  
 | 
  
1
  
 | 
748
 | 
     my ($this,$leaf,$words_a) = @_;  | 
| 
67
 | 
408
 | 
 
 | 
 
 | 
 
 | 
 
 | 
562
 | 
     push @{$this->{WORDS}}, $words_a->[$leaf->getIndex];  | 
| 
 
 | 
408
 | 
 
 | 
 
 | 
 
 | 
 
 | 
911
 | 
    | 
| 
68
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
69
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
70
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub addOccurrence  | 
| 
71
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
72
 | 
319
 | 
 
 | 
 
 | 
  
319
  
 | 
  
1
  
 | 
547
 | 
     my ($this,$occurrence) = @_;  | 
| 
73
 | 
319
 | 
  
100
  
 | 
 
 | 
 
 | 
 
 | 
697
 | 
     if($occurrence->isMaximal)  | 
| 
74
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     {  | 
| 
75
 | 
1
 | 
 
 | 
 
 | 
 
 | 
 
 | 
4
 | 
 	$this->{MNP_STATUS} = 1;  # added by SA 13/02/2009:: if at least one occurrence is a MNP, TC is a MNP  | 
| 
76
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
77
 | 
319
 | 
 
 | 
 
 | 
 
 | 
 
 | 
496
 | 
     push @{$this->{OCCURRENCES}}, $occurrence;  | 
| 
 
 | 
319
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1069
 | 
    | 
| 
78
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
79
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
80
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub addOccurrences  | 
| 
81
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
82
 | 
66
 | 
 
 | 
 
 | 
  
66
  
 | 
  
1
  
 | 
115
 | 
     my ($this,$occurrences_a) = @_;  | 
| 
83
 | 
66
 | 
 
 | 
 
 | 
 
 | 
 
 | 
90
 | 
     my $occurrence;  | 
| 
84
 | 
66
 | 
 
 | 
 
 | 
 
 | 
 
 | 
122
 | 
     foreach $occurrence (@$occurrences_a)  | 
| 
85
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     {  | 
| 
86
 | 
67
 | 
 
 | 
 
 | 
 
 | 
 
 | 
133
 | 
 	$this->addOccurrence($occurrence);  | 
| 
87
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
88
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
89
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
90
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getKey  | 
| 
91
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
92
 | 
1140
 | 
 
 | 
 
 | 
  
1140
  
 | 
  
1
  
 | 
1880
 | 
     my ($this) = @_;  | 
| 
93
 | 
1140
 | 
 
 | 
 
 | 
 
 | 
 
 | 
4114
 | 
     return $this->{KEY};  | 
| 
94
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
95
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
96
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getID  | 
| 
97
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
98
 | 
2291
 | 
 
 | 
 
 | 
  
2291
  
 | 
  
1
  
 | 
3650
 | 
     my ($this) = @_;  | 
| 
99
 | 
2291
 | 
 
 | 
 
 | 
 
 | 
 
 | 
5679
 | 
     return $this->{ID};  | 
| 
100
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
101
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
102
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getMNPStatus  | 
| 
103
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
104
 | 
240
 | 
 
 | 
 
 | 
  
240
  
 | 
  
1
  
 | 
405
 | 
     my ($this) = @_;  | 
| 
105
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
936
 | 
     return $this->{MNP_STATUS};  | 
| 
106
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
107
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
108
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub editKey  | 
| 
109
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
110
 | 
692
 | 
 
 | 
 
 | 
  
692
  
 | 
  
1
  
 | 
1228
 | 
     my ($this,$string) = @_;  | 
| 
111
 | 
692
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1828
 | 
     $this->{KEY} .= $string;  | 
| 
112
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
113
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
114
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub setHead  | 
| 
115
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
116
 | 
240
 | 
 
 | 
 
 | 
  
240
  
 | 
  
1
  
 | 
392
 | 
     my ($this) = @_;  | 
| 
117
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
528
 | 
     $this->{HEAD} = $this->searchHead(0);  | 
| 
118
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
119
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
120
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getHead  | 
| 
121
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
122
 | 
352
 | 
 
 | 
 
 | 
  
352
  
 | 
  
1
  
 | 
600
 | 
     my ($this) = @_;  | 
| 
123
 | 
352
 | 
 
 | 
 
 | 
 
 | 
 
 | 
776
 | 
     return $this->{HEAD};  | 
| 
124
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
125
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
126
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub setWeight  | 
| 
127
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
128
 | 
240
 | 
 
 | 
 
 | 
  
240
  
 | 
  
1
  
 | 
343
 | 
     my $this = shift;  | 
| 
129
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
312
 | 
     my $weight;  | 
| 
130
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     my $weight_name;  | 
| 
131
 | 
240
 | 
  
 50
  
 | 
 
 | 
 
 | 
 
 | 
420
 | 
     if (scalar(@_) == 2) {  | 
| 
132
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
 	$weight_name = shift;  | 
| 
133
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     } else {  | 
| 
134
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 	# default weight because it's the first   | 
| 
135
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
328
 | 
 	$weight_name = "DDW";	  | 
| 
136
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
137
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
332
 | 
     $weight = shift;  | 
| 
138
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
374
 | 
     $this->getWeights->{$weight_name} = $weight;  | 
| 
139
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
140
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #     $this->{WEIGHT} = $weight;  | 
| 
141
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
142
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
143
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getWeight  | 
| 
144
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
145
 | 
1316
 | 
 
 | 
 
 | 
  
1316
  
 | 
  
1
  
 | 
1873
 | 
     my $this = shift;  | 
| 
146
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
147
 | 
1316
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1694
 | 
     my $weight_name;  | 
| 
148
 | 
1316
 | 
  
 50
  
 | 
 
 | 
 
 | 
 
 | 
2177
 | 
     if (@_) {  | 
| 
149
 | 
1316
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1816
 | 
 	$weight_name = shift;  | 
| 
150
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     } else {  | 
| 
151
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 	# default wieght because it's the first   | 
| 
152
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
 	$weight_name = "DDW";	  | 
| 
153
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
154
 | 
1316
 | 
 
 | 
 
 | 
 
 | 
 
 | 
2150
 | 
     return($this->getWeights->{$weight_name});  | 
| 
155
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
156
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 #     return $this->{WEIGHT};  | 
| 
157
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
158
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
159
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub setWeights  | 
| 
160
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
161
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
1
  
 | 
0
 | 
     my ($this,$weight) = @_;  | 
| 
162
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     $this->{WEIGHTS} = $weight;  | 
| 
163
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
164
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
165
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getWeights  | 
| 
166
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
167
 | 
1558
 | 
 
 | 
 
 | 
  
1558
  
 | 
  
1
  
 | 
2389
 | 
     my ($this) = @_;  | 
| 
168
 | 
1558
 | 
 
 | 
 
 | 
 
 | 
 
 | 
4779
 | 
     return($this->{WEIGHTS});  | 
| 
169
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
170
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
171
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getWeightNames  | 
| 
172
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
173
 | 
240
 | 
 
 | 
 
 | 
  
240
  
 | 
  
1
  
 | 
444
 | 
     my ($this) = @_;  | 
| 
174
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
328
 | 
     return(keys %{$this->{WEIGHTS}});  | 
| 
 
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1011
 | 
    | 
| 
175
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
176
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
177
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getWords  | 
| 
178
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
179
 | 
1893
 | 
 
 | 
 
 | 
  
1893
  
 | 
  
1
  
 | 
3271
 | 
     my ($this) = @_;  | 
| 
180
 | 
1893
 | 
 
 | 
 
 | 
 
 | 
 
 | 
4779
 | 
     return $this->{WORDS};  | 
| 
181
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
182
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
183
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getWord  | 
| 
184
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
185
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
0
  
 | 
0
 | 
     my ($this,$index) = @_;  | 
| 
186
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     return $this->getWords->[$index];  | 
| 
187
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
188
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
189
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getOccurrences  | 
| 
190
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
191
 | 
2960
 | 
 
 | 
 
 | 
  
2960
  
 | 
  
1
  
 | 
4459
 | 
     my ($this) = @_;  | 
| 
192
 | 
2960
 | 
 
 | 
 
 | 
 
 | 
 
 | 
7805
 | 
     return $this->{OCCURRENCES};  | 
| 
193
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
194
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
195
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getOccurrencesNumber  | 
| 
196
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
197
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
0
  
 | 
0
 | 
     my ($this) = @_;  | 
| 
198
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     return scalar @{$this->getOccurrences};  | 
| 
 
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
    | 
| 
199
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
200
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
201
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub buildLinguisticInfos  | 
| 
202
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
203
 | 
240
 | 
 
 | 
 
 | 
  
240
  
 | 
  
1
  
 | 
506
 | 
     my ($this,$tagset) = @_;  | 
| 
204
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
649
 | 
     my $if;  | 
| 
205
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     my $pos;  | 
| 
206
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     my $lf;  | 
| 
207
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     my $word;  | 
| 
208
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
       | 
| 
209
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
355
 | 
     foreach $word (@{$this->getWords})  | 
| 
 
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
466
 | 
    | 
| 
210
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     {  | 
| 
211
 | 
489
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1194
 | 
 	$if .= $word->getIF . " " ;  | 
| 
212
 | 
489
 | 
  
100
  
 | 
 
 | 
 
 | 
 
 | 
1100
 | 
 	if ($tagset->existTag('PREPOSITIONS',$word->getIF))  | 
| 
213
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 	{  | 
| 
214
 | 
45
 | 
 
 | 
 
 | 
 
 | 
 
 | 
123
 | 
 	    $pos .= $word->getLF . " ";  | 
| 
215
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 	}  | 
| 
216
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 	else  | 
| 
217
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 	{  | 
| 
218
 | 
444
 | 
 
 | 
 
 | 
 
 | 
 
 | 
933
 | 
 	    $pos .= $word->getPOS . " ";  | 
| 
219
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 	}  | 
| 
220
 | 
489
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1147
 | 
 	$lf .= $word->getLF . " " ;  | 
| 
221
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
222
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1426
 | 
     $if =~ s/\s+$//;  | 
| 
223
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
905
 | 
     $pos =~ s/\s+$//;  | 
| 
224
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
848
 | 
     $lf =~ s/\s+$//;  | 
| 
225
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
892
 | 
     return ($if,$pos,$lf);  | 
| 
226
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
227
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
228
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
229
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getIF  | 
| 
230
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
231
 | 
123
 | 
 
 | 
 
 | 
  
123
  
 | 
  
1
  
 | 
224
 | 
     my ($this) = @_;  | 
| 
232
 | 
123
 | 
 
 | 
 
 | 
 
 | 
 
 | 
189
 | 
     my $word;  | 
| 
233
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     my $if;  | 
| 
234
 | 
123
 | 
 
 | 
 
 | 
 
 | 
 
 | 
164
 | 
     foreach $word (@{$this->getWords})  | 
| 
 
 | 
123
 | 
 
 | 
 
 | 
 
 | 
 
 | 
218
 | 
    | 
| 
235
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     {  | 
| 
236
 | 
386
 | 
 
 | 
 
 | 
 
 | 
 
 | 
884
 | 
 	$if .= $word->getIF . " " ;  | 
| 
237
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
238
 | 
123
 | 
 
 | 
 
 | 
 
 | 
 
 | 
696
 | 
     $if =~ s/\s+$//;  | 
| 
239
 | 
123
 | 
 
 | 
 
 | 
 
 | 
 
 | 
454
 | 
     return $if;  | 
| 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
241
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
242
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getLF  | 
| 
243
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
244
 | 
112
 | 
 
 | 
 
 | 
  
112
  
 | 
  
1
  
 | 
203
 | 
     my ($this) = @_;  | 
| 
245
 | 
112
 | 
 
 | 
 
 | 
 
 | 
 
 | 
162
 | 
     my $word;  | 
| 
246
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     my $lf;  | 
| 
247
 | 
112
 | 
 
 | 
 
 | 
 
 | 
 
 | 
160
 | 
     foreach $word (@{$this->getWords})  | 
| 
 
 | 
112
 | 
 
 | 
 
 | 
 
 | 
 
 | 
173
 | 
    | 
| 
248
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     {  | 
| 
249
 | 
361
 | 
 
 | 
 
 | 
 
 | 
 
 | 
737
 | 
 	$lf .= $word->getLF . " " ;  | 
| 
250
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
251
 | 
112
 | 
 
 | 
 
 | 
 
 | 
 
 | 
494
 | 
     $lf =~ s/\s+$//;  | 
| 
252
 | 
112
 | 
 
 | 
 
 | 
 
 | 
 
 | 
372
 | 
     return $lf;  | 
| 
253
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
254
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
255
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getPOS  | 
| 
256
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
257
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
1
  
 | 
0
 | 
     my ($this) = @_;  | 
| 
258
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     my $word;  | 
| 
259
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     my $pos;  | 
| 
260
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     foreach $word (@{$this->getWords})  | 
| 
 
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
    | 
| 
261
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     {  | 
| 
262
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
 	$pos .= $word->getPOS . " " ;  | 
| 
263
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     }  | 
| 
264
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     $pos =~ s/\s+$//;  | 
| 
265
 | 
  
0
  
 | 
 
 | 
 
 | 
 
 | 
 
 | 
0
 | 
     return $pos;  | 
| 
266
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
267
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
268
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getFrequency  | 
| 
269
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
270
 | 
2296
 | 
 
 | 
 
 | 
  
2296
  
 | 
  
1
  
 | 
3742
 | 
     my ($this) = @_;  | 
| 
271
 | 
2296
 | 
 
 | 
 
 | 
 
 | 
 
 | 
2848
 | 
     return scalar @{$this->getOccurrences};  | 
| 
 
 | 
2296
 | 
 
 | 
 
 | 
 
 | 
 
 | 
3523
 | 
    | 
| 
272
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
273
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
274
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub setReliability  | 
| 
275
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
276
 | 
240
 | 
 
 | 
 
 | 
  
240
  
 | 
  
1
  
 | 
416
 | 
     my ($this,$reliability) = @_;  | 
| 
277
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
501
 | 
     $this->{RELIABILITY} = $reliability;  | 
| 
278
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
279
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
280
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getReliability  | 
| 
281
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
282
 | 
240
 | 
 
 | 
 
 | 
  
240
  
 | 
  
1
  
 | 
400
 | 
     my ($this) = @_;  | 
| 
283
 | 
240
 | 
 
 | 
 
 | 
 
 | 
 
 | 
1425
 | 
     return $this->{RELIABILITY};  | 
| 
284
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
285
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
286
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 sub getOriginalPhrase  | 
| 
287
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 {  | 
| 
288
 | 
  
0
  
 | 
 
 | 
 
 | 
  
0
  
 | 
  
1
  
 | 
 
 | 
     my ($this) = @_;  | 
| 
289
 | 
0
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
     return $this->{ORIGINAL_PHRASE};  | 
| 
290
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 }  | 
| 
291
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
292
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
293
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
294
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 1;  | 
| 
295
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
    | 
| 
296
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 
 | 
 __END__  |