line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Wiktionary::Parser::Section::PartofSpeech; |
2
|
|
|
|
|
|
|
|
3
|
3
|
|
|
3
|
|
22
|
use Wiktionary::Parser::Section; |
|
3
|
|
|
|
|
7
|
|
|
3
|
|
|
|
|
94
|
|
4
|
|
|
|
|
|
|
|
5
|
3
|
|
|
3
|
|
17
|
use base qw(Wiktionary::Parser::Section); |
|
3
|
|
|
|
|
7
|
|
|
3
|
|
|
|
|
2155
|
|
6
|
|
|
|
|
|
|
|
7
|
|
|
|
|
|
|
sub new { |
8
|
12
|
|
|
12
|
0
|
99
|
my $class = shift; |
9
|
12
|
|
|
|
|
69
|
my %args = @_; |
10
|
12
|
|
|
|
|
74
|
my $self = bless Wiktionary::Parser::Section->new(%args), $class; |
11
|
|
|
|
|
|
|
|
12
|
|
|
|
|
|
|
# in some poorly formatted sections, |
13
|
|
|
|
|
|
|
# we can still get the part of speech and language from section headers |
14
|
|
|
|
|
|
|
# if they are not defined in markup |
15
|
12
|
|
|
|
|
54
|
$self->set_part_of_speech($self->get_header()); |
16
|
12
|
|
|
|
|
44
|
$self->set_language_code($self->get_language()); |
17
|
12
|
|
|
|
|
49
|
return $self; |
18
|
|
|
|
|
|
|
} |
19
|
|
|
|
|
|
|
|
20
|
|
|
|
|
|
|
# add a line of content to this section and parse it into its component parts |
21
|
|
|
|
|
|
|
sub add_content { |
22
|
58
|
|
|
58
|
0
|
74
|
my $self = shift; |
23
|
58
|
|
|
|
|
69
|
my $line = shift; |
24
|
|
|
|
|
|
|
|
25
|
58
|
100
|
|
|
|
163
|
if ($line =~ m/^\{\{([^\}]+)\}\}/) { |
26
|
11
|
|
|
|
|
25
|
my $header_meta = $1; |
27
|
11
|
|
|
|
|
38
|
my @meta_parts = split(/\|/,$header_meta); |
28
|
|
|
|
|
|
|
|
29
|
|
|
|
|
|
|
# e.g. {{head|en|noun}} |
30
|
11
|
100
|
|
|
|
74
|
if ($meta_parts[0] eq 'head') { |
|
|
100
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
31
|
2
|
|
|
|
|
7
|
$self->set_language_code($meta_parts[1]); |
32
|
2
|
|
|
|
|
7
|
$self->set_part_of_speech($meta_parts[2]) |
33
|
|
|
|
|
|
|
|
34
|
|
|
|
|
|
|
|
35
|
|
|
|
|
|
|
} elsif ($meta_parts[0] =~ m/^(\w+)\-(\w+)-(\w+)\|?/) { |
36
|
|
|
|
|
|
|
# {{roa-jer-noun|... |
37
|
2
|
|
|
|
|
7
|
$self->set_language_code($1); |
38
|
2
|
|
|
|
|
6
|
$self->set_part_of_speech($3); |
39
|
2
|
|
|
|
|
9
|
$self->set_inflection([@meta_parts[1..-1]]); |
40
|
|
|
|
|
|
|
|
41
|
|
|
|
|
|
|
} elsif ($meta_parts[0] =~ m/^(\w+)\-(\w+)/) { |
42
|
|
|
|
|
|
|
# e.g. {{en-noun|...}} |
43
|
6
|
|
|
|
|
38
|
$self->set_language_code($1); |
44
|
6
|
|
|
|
|
12
|
$self->set_part_of_speech($2); |
45
|
6
|
|
|
|
|
22
|
$self->set_inflection([@meta_parts[1..-1]]); |
46
|
|
|
|
|
|
|
} |
47
|
|
|
|
|
|
|
} |
48
|
|
|
|
|
|
|
|
49
|
58
|
|
|
|
|
62
|
push @{$self->{content}}, $line; |
|
58
|
|
|
|
|
254
|
|
50
|
|
|
|
|
|
|
} |
51
|
|
|
|
|
|
|
|
52
|
|
|
|
|
|
|
sub set_part_of_speech { |
53
|
22
|
|
|
22
|
0
|
28
|
my $self = shift; |
54
|
22
|
|
|
|
|
54
|
$self->{part_of_speech} = shift; |
55
|
|
|
|
|
|
|
} |
56
|
|
|
|
|
|
|
|
57
|
|
|
|
|
|
|
sub get_part_of_speech { |
58
|
0
|
|
|
0
|
0
|
0
|
my $self = shift; |
59
|
0
|
|
|
|
|
0
|
return $self->{part_of_speech}; |
60
|
|
|
|
|
|
|
} |
61
|
|
|
|
|
|
|
|
62
|
|
|
|
|
|
|
|
63
|
|
|
|
|
|
|
sub set_language_code { |
64
|
22
|
|
|
22
|
0
|
33
|
my $self = shift; |
65
|
22
|
|
|
|
|
53
|
$self->{language_code} = shift; |
66
|
|
|
|
|
|
|
} |
67
|
|
|
|
|
|
|
|
68
|
|
|
|
|
|
|
sub get_language_code { |
69
|
0
|
|
|
0
|
0
|
0
|
my $self = shift; |
70
|
0
|
|
|
|
|
0
|
return $self->{language_code}; |
71
|
|
|
|
|
|
|
} |
72
|
|
|
|
|
|
|
|
73
|
|
|
|
|
|
|
sub set_inflection { |
74
|
8
|
|
|
8
|
0
|
10
|
my $self = shift; |
75
|
8
|
|
|
|
|
24
|
$self->{inflection} = shift; |
76
|
|
|
|
|
|
|
} |
77
|
|
|
|
|
|
|
|
78
|
|
|
|
|
|
|
sub get_inflection { |
79
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
80
|
0
|
|
|
|
|
|
return $self->{inflection}; |
81
|
|
|
|
|
|
|
} |
82
|
|
|
|
|
|
|
|
83
|
|
|
|
|
|
|
|
84
|
|
|
|
|
|
|
|
85
|
|
|
|
|
|
|
1; |