line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package Wiktionary::Parser::Section::Pronunciation; |
2
|
|
|
|
|
|
|
|
3
|
3
|
|
|
3
|
|
23
|
use Wiktionary::Parser::Section; |
|
3
|
|
|
|
|
6
|
|
|
3
|
|
|
|
|
135
|
|
4
|
3
|
|
|
3
|
|
2101
|
use Wiktionary::Parser::Section::Pronunciation::Audio; |
|
3
|
|
|
|
|
9
|
|
|
3
|
|
|
|
|
95
|
|
5
|
3
|
|
|
3
|
|
2810
|
use Wiktionary::Parser::Section::Pronunciation::Representation; |
|
3
|
|
|
|
|
12
|
|
|
3
|
|
|
|
|
113
|
|
6
|
|
|
|
|
|
|
|
7
|
3
|
|
|
3
|
|
20
|
use base qw(Wiktionary::Parser::Section); |
|
3
|
|
|
|
|
9
|
|
|
3
|
|
|
|
|
5966
|
|
8
|
|
|
|
|
|
|
|
9
|
|
|
|
|
|
|
sub new { |
10
|
4
|
|
|
4
|
0
|
6
|
my $class = shift; |
11
|
4
|
|
|
|
|
16
|
my %args = @_; |
12
|
4
|
|
|
|
|
19
|
my $self = bless Wiktionary::Parser::Section->new(%args), $class; |
13
|
4
|
|
|
|
|
17
|
return $self; |
14
|
|
|
|
|
|
|
} |
15
|
|
|
|
|
|
|
|
16
|
|
|
|
|
|
|
|
17
|
|
|
|
|
|
|
# add a line of content to this section and parse it into its component parts |
18
|
|
|
|
|
|
|
sub add_content { |
19
|
14
|
|
|
14
|
0
|
22
|
my $self = shift; |
20
|
14
|
|
|
|
|
21
|
my $line = shift; |
21
|
|
|
|
|
|
|
|
22
|
14
|
|
|
|
|
16
|
push @{$self->{content}}, $line; |
|
14
|
|
|
|
|
36
|
|
23
|
|
|
|
|
|
|
|
24
|
14
|
50
|
|
|
|
28
|
return unless $line; |
25
|
14
|
|
|
|
|
56
|
$line =~ s/^[\*\s]+//i; |
26
|
14
|
|
|
|
|
94
|
my @meta = $line =~ m/\{\{([^\}]+)\}\}/g; |
27
|
14
|
50
|
|
|
|
39
|
if (@meta) { |
28
|
14
|
|
|
|
|
16
|
my @context; |
29
|
|
|
|
|
|
|
my @senses; |
30
|
14
|
|
|
|
|
20
|
for my $meta (@meta) { |
31
|
22
|
|
|
|
|
74
|
my @parts = split(/\|/,$meta); |
32
|
|
|
|
|
|
|
|
33
|
22
|
50
|
|
|
|
136
|
if ($parts[0] eq 'sense') { |
|
|
100
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
34
|
0
|
0
|
|
|
|
0
|
if (@parts > 1) { |
35
|
0
|
0
|
|
|
|
0
|
push @senses, grep {$_ && $_ ne 'sense'} @parts |
|
0
|
|
|
|
|
0
|
|
36
|
|
|
|
|
|
|
} |
37
|
|
|
|
|
|
|
} elsif ($parts[0] eq 'a') { |
38
|
3
|
50
|
|
|
|
9
|
if (@parts > 1) { |
39
|
3
|
50
|
|
|
|
7
|
push @context, grep {$_ && $_ ne 'a'} @parts |
|
6
|
|
|
|
|
35
|
|
40
|
|
|
|
|
|
|
} |
41
|
|
|
|
|
|
|
} elsif ($parts[0] eq 'audio') { |
42
|
5
|
|
|
|
|
18
|
my $lang = $self->get_language(); |
43
|
|
|
|
|
|
|
|
44
|
5
|
|
|
|
|
23
|
$self->add_audio( |
45
|
|
|
|
|
|
|
language => $lang, |
46
|
|
|
|
|
|
|
file => $parts[1], |
47
|
|
|
|
|
|
|
text => $parts[2], |
48
|
|
|
|
|
|
|
context => \@context, |
49
|
|
|
|
|
|
|
senses => \@senses, |
50
|
|
|
|
|
|
|
); |
51
|
|
|
|
|
|
|
} elsif ($parts[0] =~ m/(rhyme|homophone|hyphenation)/) { |
52
|
|
|
|
|
|
|
|
53
|
4
|
|
|
|
|
10
|
my $meta = $self->parse_template(@parts); |
54
|
4
|
|
66
|
|
|
18
|
$meta->{lang} ||= $self->get_language(); |
55
|
|
|
|
|
|
|
|
56
|
4
|
|
|
|
|
23
|
$self->add_category( |
57
|
|
|
|
|
|
|
category => $1, |
58
|
|
|
|
|
|
|
language => $meta->{lang}, |
59
|
|
|
|
|
|
|
representation => $meta->{representation}, |
60
|
|
|
|
|
|
|
pronunciation => $meta->{pronunciation}, |
61
|
|
|
|
|
|
|
context => \@context, |
62
|
|
|
|
|
|
|
senses => \@senses, |
63
|
|
|
|
|
|
|
); |
64
|
|
|
|
|
|
|
|
65
|
|
|
|
|
|
|
} else { |
66
|
10
|
|
|
|
|
31
|
my $meta = $self->parse_template(@parts); |
67
|
10
|
|
66
|
|
|
60
|
$meta->{lang} ||= $self->get_language(); |
68
|
|
|
|
|
|
|
|
69
|
10
|
|
|
|
|
45
|
$self->add_pronunciation( |
70
|
|
|
|
|
|
|
language => $meta->{lang}, |
71
|
|
|
|
|
|
|
representation => $meta->{representation}, |
72
|
|
|
|
|
|
|
pronunciation => $meta->{pronunciation}, |
73
|
|
|
|
|
|
|
context => \@context, |
74
|
|
|
|
|
|
|
senses => \@senses, |
75
|
|
|
|
|
|
|
); |
76
|
|
|
|
|
|
|
} |
77
|
|
|
|
|
|
|
} |
78
|
|
|
|
|
|
|
} |
79
|
|
|
|
|
|
|
} |
80
|
|
|
|
|
|
|
|
81
|
|
|
|
|
|
|
sub parse_template { |
82
|
14
|
|
|
14
|
0
|
20
|
my $self = shift; |
83
|
14
|
|
|
|
|
29
|
my @parts = @_; |
84
|
|
|
|
|
|
|
|
85
|
14
|
|
|
|
|
17
|
my %meta; |
86
|
|
|
|
|
|
|
my $representation; |
87
|
0
|
|
|
|
|
0
|
my $lang; |
88
|
14
|
|
|
|
|
27
|
my @pronunciation = []; |
89
|
14
|
|
|
|
|
35
|
for my $i (0..$#parts) { |
90
|
37
|
100
|
|
|
|
236
|
if ($parts[$i] =~ m/rhyme|homophone|hyphenation/) { |
|
|
100
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
91
|
|
|
|
|
|
|
|
92
|
|
|
|
|
|
|
} elsif ($parts[$i] =~ m/(IPA|enPR|AHD|SAMPA)/) { |
93
|
10
|
|
|
|
|
25
|
$meta{representation} = $parts[$i]; |
94
|
|
|
|
|
|
|
} elsif ($parts[$i] =~ m/lang=(.+)/) { |
95
|
4
|
|
|
|
|
17
|
$meta{lang} = $1; |
96
|
|
|
|
|
|
|
} else { |
97
|
19
|
|
|
|
|
20
|
push @{$meta{pronunciation}}, $parts[$i]; |
|
19
|
|
|
|
|
70
|
|
98
|
|
|
|
|
|
|
} |
99
|
|
|
|
|
|
|
} |
100
|
14
|
|
|
|
|
49
|
return \%meta; |
101
|
|
|
|
|
|
|
} |
102
|
|
|
|
|
|
|
|
103
|
|
|
|
|
|
|
sub add_pronunciation { |
104
|
10
|
|
|
10
|
0
|
16
|
my $self = shift; |
105
|
10
|
|
|
|
|
40
|
my %args = @_; |
106
|
|
|
|
|
|
|
|
107
|
10
|
|
|
|
|
19
|
my $meta = {}; |
108
|
10
|
|
50
|
|
|
29
|
my $lang = $args{language} || '__language_undefined__'; |
109
|
|
|
|
|
|
|
|
110
|
10
|
|
|
|
|
65
|
my $pronunciation = Wiktionary::Parser::Section::Pronunciation::Representation->new( |
111
|
|
|
|
|
|
|
representation => $args{representation}, |
112
|
|
|
|
|
|
|
pronunciation => $args{pronunciation}, |
113
|
|
|
|
|
|
|
context => $args{context}, |
114
|
|
|
|
|
|
|
); |
115
|
10
|
|
|
|
|
15
|
push @{$self->{pronunciation}{$lang}},$pronunciation; |
|
10
|
|
|
|
|
90
|
|
116
|
|
|
|
|
|
|
} |
117
|
|
|
|
|
|
|
|
118
|
|
|
|
|
|
|
|
119
|
|
|
|
|
|
|
# rhyme, homophone, hyphenation entries |
120
|
|
|
|
|
|
|
sub add_category { |
121
|
4
|
|
|
4
|
0
|
17
|
my $self = shift; |
122
|
4
|
|
|
|
|
30
|
my %args = @_; |
123
|
4
|
50
|
|
|
|
14
|
my $category = $args{category} or die 'category not defined'; |
124
|
|
|
|
|
|
|
|
125
|
4
|
|
50
|
|
|
11
|
my $lang = $args{language} || '__language_undefined__'; |
126
|
4
|
|
|
|
|
8
|
my $meta = {}; |
127
|
4
|
|
|
|
|
19
|
my $item = Wiktionary::Parser::Section::Pronunciation::Representation->new( |
128
|
|
|
|
|
|
|
representation => $args{representation}, |
129
|
|
|
|
|
|
|
pronunciation => $args{pronunciation}, |
130
|
|
|
|
|
|
|
context => $args{context}, |
131
|
|
|
|
|
|
|
senses => $args{senses}, |
132
|
|
|
|
|
|
|
); |
133
|
4
|
|
|
|
|
6
|
push @{$self->{$category}{$lang}},$item; |
|
4
|
|
|
|
|
54
|
|
134
|
|
|
|
|
|
|
} |
135
|
|
|
|
|
|
|
|
136
|
|
|
|
|
|
|
|
137
|
|
|
|
|
|
|
sub add_audio { |
138
|
5
|
|
|
5
|
0
|
9
|
my $self = shift; |
139
|
5
|
|
|
|
|
25
|
my %args = @_; |
140
|
5
|
|
50
|
|
|
16
|
my $lang = $args{language} || '__language_undefined__'; |
141
|
|
|
|
|
|
|
|
142
|
5
|
|
|
|
|
38
|
my $audio = Wiktionary::Parser::Section::Pronunciation::Audio->new( |
143
|
|
|
|
|
|
|
file => $args{file}, |
144
|
|
|
|
|
|
|
text => $args{text}, |
145
|
|
|
|
|
|
|
context => $args{context}, |
146
|
|
|
|
|
|
|
); |
147
|
|
|
|
|
|
|
|
148
|
5
|
|
|
|
|
8
|
push @{$self->{audio}{$lang}}, $audio; |
|
5
|
|
|
|
|
49
|
|
149
|
|
|
|
|
|
|
} |
150
|
|
|
|
|
|
|
|
151
|
|
|
|
|
|
|
sub get_pronunciations { |
152
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
153
|
0
|
|
|
|
|
|
return $self->{pronunciation}; |
154
|
|
|
|
|
|
|
} |
155
|
|
|
|
|
|
|
|
156
|
|
|
|
|
|
|
sub get_audio { |
157
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
158
|
0
|
|
|
|
|
|
return $self->{audio}; |
159
|
|
|
|
|
|
|
} |
160
|
|
|
|
|
|
|
|
161
|
|
|
|
|
|
|
sub get_rhymes { |
162
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
163
|
0
|
|
|
|
|
|
return $self->{rhyme} |
164
|
|
|
|
|
|
|
} |
165
|
|
|
|
|
|
|
|
166
|
|
|
|
|
|
|
sub get_homophones{ |
167
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
168
|
0
|
|
|
|
|
|
return $self->{homophone} |
169
|
|
|
|
|
|
|
} |
170
|
|
|
|
|
|
|
|
171
|
|
|
|
|
|
|
sub get_hyphenations{ |
172
|
0
|
|
|
0
|
0
|
|
my $self = shift; |
173
|
0
|
|
|
|
|
|
return $self->{hyphenation} |
174
|
|
|
|
|
|
|
} |
175
|
|
|
|
|
|
|
|
176
|
|
|
|
|
|
|
1; |