| line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
|
1
|
|
|
|
|
|
|
package Lingua::YALI::LanguageIdentifier; |
|
2
|
|
|
|
|
|
|
# ABSTRACT: Module for language identification. |
|
3
|
|
|
|
|
|
|
|
|
4
|
11
|
|
|
11
|
|
455367
|
use strict; |
|
|
11
|
|
|
|
|
28
|
|
|
|
11
|
|
|
|
|
547
|
|
|
5
|
11
|
|
|
11
|
|
66
|
use warnings; |
|
|
11
|
|
|
|
|
24
|
|
|
|
11
|
|
|
|
|
367
|
|
|
6
|
11
|
|
|
11
|
|
36559
|
use File::ShareDir; |
|
|
11
|
|
|
|
|
119762
|
|
|
|
11
|
|
|
|
|
1573
|
|
|
7
|
11
|
|
|
11
|
|
131
|
use File::Glob; |
|
|
11
|
|
|
|
|
27
|
|
|
|
11
|
|
|
|
|
758
|
|
|
8
|
11
|
|
|
11
|
|
69
|
use Carp; |
|
|
11
|
|
|
|
|
24
|
|
|
|
11
|
|
|
|
|
824
|
|
|
9
|
11
|
|
|
11
|
|
24107
|
use Moose; |
|
|
11
|
|
|
|
|
6439098
|
|
|
|
11
|
|
|
|
|
108
|
|
|
10
|
|
|
|
|
|
|
|
|
11
|
|
|
|
|
|
|
our $VERSION = '0.015'; # VERSION |
|
12
|
|
|
|
|
|
|
|
|
13
|
|
|
|
|
|
|
extends 'Lingua::YALI::Identifier'; |
|
14
|
|
|
|
|
|
|
|
|
15
|
|
|
|
|
|
|
has '_languages' => (is => 'rw', isa => 'ArrayRef'); |
|
16
|
|
|
|
|
|
|
has '_language_model' => (is => 'rw', isa => 'HashRef'); |
|
17
|
|
|
|
|
|
|
|
|
18
|
|
|
|
|
|
|
|
|
19
|
|
|
|
|
|
|
|
|
20
|
|
|
|
|
|
|
|
|
21
|
|
|
|
|
|
|
|
|
22
|
|
|
|
|
|
|
sub add_language |
|
23
|
|
|
|
|
|
|
{ |
|
24
|
0
|
|
|
0
|
|
|
my ($self, @languages) = @_; |
|
25
|
|
|
|
|
|
|
|
|
26
|
|
|
|
|
|
|
# lazy loading |
|
27
|
0
|
0
|
|
|
|
|
if ( ! defined($self->_languages) ) { |
|
28
|
0
|
|
|
|
|
|
$self->get_available_languages(); |
|
29
|
|
|
|
|
|
|
} |
|
30
|
|
|
|
|
|
|
|
|
31
|
|
|
|
|
|
|
# register languages |
|
32
|
0
|
|
|
|
|
|
my $added_languages = 0; |
|
33
|
0
|
|
|
|
|
|
for my $lang (@languages) { |
|
34
|
0
|
0
|
|
|
|
|
if ( ! defined($self->{_language_model}->{$lang}) ) { |
|
35
|
0
|
|
|
|
|
|
croak("Unknown language $lang"); |
|
36
|
|
|
|
|
|
|
} |
|
37
|
0
|
|
|
|
|
|
$added_languages += $self->add_class($lang, $self->{_language_model}->{$lang}); |
|
38
|
|
|
|
|
|
|
} |
|
39
|
|
|
|
|
|
|
|
|
40
|
0
|
|
|
|
|
|
return $added_languages; |
|
41
|
|
|
|
|
|
|
} |
|
42
|
|
|
|
|
|
|
|
|
43
|
|
|
|
|
|
|
|
|
44
|
|
|
|
|
|
|
sub remove_language |
|
45
|
|
|
|
|
|
|
{ |
|
46
|
0
|
|
|
0
|
|
|
my ($self, @languages) = @_; |
|
47
|
|
|
|
|
|
|
|
|
48
|
|
|
|
|
|
|
# lazy loading |
|
49
|
0
|
0
|
|
|
|
|
if ( ! defined($self->_languages) ) { |
|
50
|
0
|
|
|
|
|
|
$self->get_available_languages(); |
|
51
|
|
|
|
|
|
|
} |
|
52
|
|
|
|
|
|
|
|
|
53
|
|
|
|
|
|
|
# remove languages |
|
54
|
0
|
|
|
|
|
|
my $removed_languages = 0; |
|
55
|
0
|
|
|
|
|
|
for my $lang (@languages) { |
|
56
|
0
|
0
|
|
|
|
|
if ( ! defined($self->{_language_model}->{$lang}) ) { |
|
57
|
0
|
|
|
|
|
|
croak("Unknown language $lang"); |
|
58
|
|
|
|
|
|
|
} |
|
59
|
0
|
|
|
|
|
|
$removed_languages += $self->remove_class($lang); |
|
60
|
|
|
|
|
|
|
} |
|
61
|
|
|
|
|
|
|
|
|
62
|
0
|
|
|
|
|
|
return $removed_languages; |
|
63
|
|
|
|
|
|
|
} |
|
64
|
|
|
|
|
|
|
|
|
65
|
|
|
|
|
|
|
|
|
66
|
|
|
|
|
|
|
sub get_languages |
|
67
|
|
|
|
|
|
|
{ |
|
68
|
0
|
|
|
0
|
|
|
my $self = shift; |
|
69
|
0
|
|
|
|
|
|
return $self->get_classes(); |
|
70
|
|
|
|
|
|
|
} |
|
71
|
|
|
|
|
|
|
|
|
72
|
|
|
|
|
|
|
|
|
73
|
|
|
|
|
|
|
sub get_available_languages |
|
74
|
|
|
|
|
|
|
{ |
|
75
|
0
|
|
|
0
|
|
|
my $self = shift; |
|
76
|
|
|
|
|
|
|
|
|
77
|
|
|
|
|
|
|
# Get a module's shared files directory |
|
78
|
0
|
0
|
|
|
|
|
if ( ! defined($self->_languages) ) { |
|
79
|
|
|
|
|
|
|
|
|
80
|
0
|
|
|
|
|
|
my $dir = "share/"; |
|
81
|
0
|
|
|
|
|
|
eval { $dir = File::ShareDir::dist_dir('Lingua-YALI'); }; |
|
|
0
|
|
|
|
|
|
|
|
82
|
|
|
|
|
|
|
|
|
83
|
0
|
|
|
|
|
|
my @languages = (); |
|
84
|
|
|
|
|
|
|
|
|
85
|
0
|
|
|
|
|
|
for my $file (File::Glob::bsd_glob($dir . "/*.yali.gz")) { |
|
86
|
0
|
|
|
|
|
|
my $language = $file; |
|
87
|
0
|
|
|
|
|
|
$language =~ s/\Q$dir\E.//; |
|
88
|
0
|
|
|
|
|
|
$language =~ s/.yali.gz//; |
|
89
|
|
|
|
|
|
|
|
|
90
|
0
|
|
|
|
|
|
push(@languages, $language); |
|
91
|
0
|
|
|
|
|
|
$self->{_language_model}->{$language} = $file; |
|
92
|
|
|
|
|
|
|
} |
|
93
|
0
|
|
|
|
|
|
$self->_languages(\@languages); |
|
94
|
|
|
|
|
|
|
# print STDERR join("\t", @languages), "\n"; |
|
95
|
|
|
|
|
|
|
} |
|
96
|
|
|
|
|
|
|
|
|
97
|
0
|
|
|
|
|
|
return $self->_languages; |
|
98
|
|
|
|
|
|
|
} |
|
99
|
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
|
|
101
|
|
|
|
|
|
|
|
|
102
|
|
|
|
|
|
|
|
|
103
|
|
|
|
|
|
|
# for lang in `ls lib/auto/Lingua/YALI/ | cut -f1 -d.`; do name=`webAPI.sh GET $lang name | cut -f3-`; echo -e "=item * $lang - $name\n"; done |
|
104
|
|
|
|
|
|
|
|
|
105
|
|
|
|
|
|
|
|
|
106
|
|
|
|
|
|
|
|
|
107
|
|
|
|
|
|
|
|
|
108
|
|
|
|
|
|
|
1; |
|
109
|
|
|
|
|
|
|
|
|
110
|
|
|
|
|
|
|
__END__ |
|
111
|
|
|
|
|
|
|
|
|
112
|
|
|
|
|
|
|
=pod |
|
113
|
|
|
|
|
|
|
|
|
114
|
|
|
|
|
|
|
=encoding UTF-8 |
|
115
|
|
|
|
|
|
|
|
|
116
|
|
|
|
|
|
|
=head1 NAME |
|
117
|
|
|
|
|
|
|
|
|
118
|
|
|
|
|
|
|
Lingua::YALI::LanguageIdentifier - Module for language identification. |
|
119
|
|
|
|
|
|
|
|
|
120
|
|
|
|
|
|
|
=head1 VERSION |
|
121
|
|
|
|
|
|
|
|
|
122
|
|
|
|
|
|
|
version 0.015 |
|
123
|
|
|
|
|
|
|
|
|
124
|
|
|
|
|
|
|
=head1 SYNOPSIS |
|
125
|
|
|
|
|
|
|
|
|
126
|
|
|
|
|
|
|
This modul is for language identification and can identify 122 languages. |
|
127
|
|
|
|
|
|
|
|
|
128
|
|
|
|
|
|
|
use Lingua::YALI::LanguageIdentifier; |
|
129
|
|
|
|
|
|
|
|
|
130
|
|
|
|
|
|
|
# create identifier and register languages |
|
131
|
|
|
|
|
|
|
my $identifier = Lingua::YALI::LanguageIdentifier->new(); |
|
132
|
|
|
|
|
|
|
$identifier->add_language("ces", "eng") |
|
133
|
|
|
|
|
|
|
|
|
134
|
|
|
|
|
|
|
# identify string |
|
135
|
|
|
|
|
|
|
my $result = $identifier->identify_string("CPAN, the Comprehensive Perl Archive Network, is an archive of modules written in Perl."); |
|
136
|
|
|
|
|
|
|
print "The most probable language is " . $result->[0]->[0] . ".\n"; |
|
137
|
|
|
|
|
|
|
# prints out The most probable language is eng. |
|
138
|
|
|
|
|
|
|
|
|
139
|
|
|
|
|
|
|
More examples is presented in L<Lingua::YALI::Examples|Lingua::YALI::Examples>. |
|
140
|
|
|
|
|
|
|
|
|
141
|
|
|
|
|
|
|
=head1 METHODS |
|
142
|
|
|
|
|
|
|
|
|
143
|
|
|
|
|
|
|
=head2 add_language |
|
144
|
|
|
|
|
|
|
|
|
145
|
|
|
|
|
|
|
my $added_languages = $identifier->add_languages(@languages) |
|
146
|
|
|
|
|
|
|
|
|
147
|
|
|
|
|
|
|
Registers new languages C<@languages> for identification and returns |
|
148
|
|
|
|
|
|
|
the amount of newly added languages. Languages are identified by their |
|
149
|
|
|
|
|
|
|
ISO 639-3 code. |
|
150
|
|
|
|
|
|
|
|
|
151
|
|
|
|
|
|
|
It croaks when unsupported language is used. |
|
152
|
|
|
|
|
|
|
|
|
153
|
|
|
|
|
|
|
print $identifier->add_languages("ces", "deu", "eng") . "\n"; |
|
154
|
|
|
|
|
|
|
# prints out 3 |
|
155
|
|
|
|
|
|
|
print $identifier->add_languages("ces", "slk") . "\n"; |
|
156
|
|
|
|
|
|
|
# prints out 1 |
|
157
|
|
|
|
|
|
|
|
|
158
|
|
|
|
|
|
|
=head2 remove_language |
|
159
|
|
|
|
|
|
|
|
|
160
|
|
|
|
|
|
|
my $removed_languages = $identifier->remove_languages(@languages) |
|
161
|
|
|
|
|
|
|
|
|
162
|
|
|
|
|
|
|
Remove languages C<@languages> and returns the amount of removed languages. |
|
163
|
|
|
|
|
|
|
|
|
164
|
|
|
|
|
|
|
It croaks when unsupported language is used. |
|
165
|
|
|
|
|
|
|
|
|
166
|
|
|
|
|
|
|
print $identifier->add_languages("ces", "deu", "eng") |
|
167
|
|
|
|
|
|
|
# prints out 3 |
|
168
|
|
|
|
|
|
|
print $identifier->remove_languages("ces", "slk") . "\n"; |
|
169
|
|
|
|
|
|
|
# prints out 1 |
|
170
|
|
|
|
|
|
|
print $identifier->remove_languages("ces", "slk") . "\n"; |
|
171
|
|
|
|
|
|
|
# prints out 0 |
|
172
|
|
|
|
|
|
|
|
|
173
|
|
|
|
|
|
|
=head2 get_languages |
|
174
|
|
|
|
|
|
|
|
|
175
|
|
|
|
|
|
|
my \@languages = $identifier->get_languages(); |
|
176
|
|
|
|
|
|
|
|
|
177
|
|
|
|
|
|
|
Returns all registered languages. |
|
178
|
|
|
|
|
|
|
|
|
179
|
|
|
|
|
|
|
=head2 get_available_languages |
|
180
|
|
|
|
|
|
|
|
|
181
|
|
|
|
|
|
|
my \@languages = $identifier->get_available_languages(); |
|
182
|
|
|
|
|
|
|
|
|
183
|
|
|
|
|
|
|
Returns all available languages. Currently there is 122 languages (L</LANGUAGES>). |
|
184
|
|
|
|
|
|
|
|
|
185
|
|
|
|
|
|
|
=head2 identify_file |
|
186
|
|
|
|
|
|
|
|
|
187
|
|
|
|
|
|
|
my $result = $identifier->identify_file($file) |
|
188
|
|
|
|
|
|
|
|
|
189
|
|
|
|
|
|
|
Identifies language for file C<$file>. |
|
190
|
|
|
|
|
|
|
|
|
191
|
|
|
|
|
|
|
For more details look at method L<Lingua::YALI::Identifier/identify_file>. |
|
192
|
|
|
|
|
|
|
|
|
193
|
|
|
|
|
|
|
=head2 identify_string |
|
194
|
|
|
|
|
|
|
|
|
195
|
|
|
|
|
|
|
my $result = $identifier->identify_string($string) |
|
196
|
|
|
|
|
|
|
|
|
197
|
|
|
|
|
|
|
Identifies language for string C<$string>. |
|
198
|
|
|
|
|
|
|
|
|
199
|
|
|
|
|
|
|
For more details look at method L<Lingua::YALI::Identifier/identify_string>. |
|
200
|
|
|
|
|
|
|
|
|
201
|
|
|
|
|
|
|
=head2 identify_handle |
|
202
|
|
|
|
|
|
|
|
|
203
|
|
|
|
|
|
|
my $result = $identifier->identify_handle($fh) |
|
204
|
|
|
|
|
|
|
|
|
205
|
|
|
|
|
|
|
Identifies language for handle C<$fh>. |
|
206
|
|
|
|
|
|
|
|
|
207
|
|
|
|
|
|
|
For more details look at method L<Lingua::YALI::Identifier/identify_handle>. |
|
208
|
|
|
|
|
|
|
|
|
209
|
|
|
|
|
|
|
=head1 LANGUAGES |
|
210
|
|
|
|
|
|
|
|
|
211
|
|
|
|
|
|
|
More details about supported languages may be found at L<http://ufal.mff.cuni.cz/~majlis/w2c/download.html>. |
|
212
|
|
|
|
|
|
|
|
|
213
|
|
|
|
|
|
|
=over |
|
214
|
|
|
|
|
|
|
|
|
215
|
|
|
|
|
|
|
=item * afr - Afrikaans |
|
216
|
|
|
|
|
|
|
|
|
217
|
|
|
|
|
|
|
=item * als - Tosk Albanian |
|
218
|
|
|
|
|
|
|
|
|
219
|
|
|
|
|
|
|
=item * amh - Amharic |
|
220
|
|
|
|
|
|
|
|
|
221
|
|
|
|
|
|
|
=item * ara - Arabic |
|
222
|
|
|
|
|
|
|
|
|
223
|
|
|
|
|
|
|
=item * arg - Aragonese |
|
224
|
|
|
|
|
|
|
|
|
225
|
|
|
|
|
|
|
=item * arz - Egyptian Arabic |
|
226
|
|
|
|
|
|
|
|
|
227
|
|
|
|
|
|
|
=item * ast - Asturian |
|
228
|
|
|
|
|
|
|
|
|
229
|
|
|
|
|
|
|
=item * aze - Azerbaijani |
|
230
|
|
|
|
|
|
|
|
|
231
|
|
|
|
|
|
|
=item * bcl - Central Bicolano |
|
232
|
|
|
|
|
|
|
|
|
233
|
|
|
|
|
|
|
=item * bel - Belarusian |
|
234
|
|
|
|
|
|
|
|
|
235
|
|
|
|
|
|
|
=item * ben - Bengali |
|
236
|
|
|
|
|
|
|
|
|
237
|
|
|
|
|
|
|
=item * bos - Bosnian |
|
238
|
|
|
|
|
|
|
|
|
239
|
|
|
|
|
|
|
=item * bpy - Bishnupriya |
|
240
|
|
|
|
|
|
|
|
|
241
|
|
|
|
|
|
|
=item * bre - Breton |
|
242
|
|
|
|
|
|
|
|
|
243
|
|
|
|
|
|
|
=item * bug - Buginese |
|
244
|
|
|
|
|
|
|
|
|
245
|
|
|
|
|
|
|
=item * bul - Bulgarian |
|
246
|
|
|
|
|
|
|
|
|
247
|
|
|
|
|
|
|
=item * cat - Catalan |
|
248
|
|
|
|
|
|
|
|
|
249
|
|
|
|
|
|
|
=item * ceb - Cebuano |
|
250
|
|
|
|
|
|
|
|
|
251
|
|
|
|
|
|
|
=item * ces - Czech |
|
252
|
|
|
|
|
|
|
|
|
253
|
|
|
|
|
|
|
=item * chv - Chuvash |
|
254
|
|
|
|
|
|
|
|
|
255
|
|
|
|
|
|
|
=item * cos - Corsican |
|
256
|
|
|
|
|
|
|
|
|
257
|
|
|
|
|
|
|
=item * cym - Welsh |
|
258
|
|
|
|
|
|
|
|
|
259
|
|
|
|
|
|
|
=item * dan - Danish |
|
260
|
|
|
|
|
|
|
|
|
261
|
|
|
|
|
|
|
=item * deu - German |
|
262
|
|
|
|
|
|
|
|
|
263
|
|
|
|
|
|
|
=item * diq - Dimli (individual language) |
|
264
|
|
|
|
|
|
|
|
|
265
|
|
|
|
|
|
|
=item * ell - Modern Greek (1453-) |
|
266
|
|
|
|
|
|
|
|
|
267
|
|
|
|
|
|
|
=item * eng - English |
|
268
|
|
|
|
|
|
|
|
|
269
|
|
|
|
|
|
|
=item * epo - Esperanto |
|
270
|
|
|
|
|
|
|
|
|
271
|
|
|
|
|
|
|
=item * est - Estonian |
|
272
|
|
|
|
|
|
|
|
|
273
|
|
|
|
|
|
|
=item * eus - Basque |
|
274
|
|
|
|
|
|
|
|
|
275
|
|
|
|
|
|
|
=item * fao - Faroese |
|
276
|
|
|
|
|
|
|
|
|
277
|
|
|
|
|
|
|
=item * fas - Persian |
|
278
|
|
|
|
|
|
|
|
|
279
|
|
|
|
|
|
|
=item * fin - Finnish |
|
280
|
|
|
|
|
|
|
|
|
281
|
|
|
|
|
|
|
=item * fra - French |
|
282
|
|
|
|
|
|
|
|
|
283
|
|
|
|
|
|
|
=item * fry - Western Frisian |
|
284
|
|
|
|
|
|
|
|
|
285
|
|
|
|
|
|
|
=item * gan - Gan Chinese |
|
286
|
|
|
|
|
|
|
|
|
287
|
|
|
|
|
|
|
=item * gla - Scottish Gaelic |
|
288
|
|
|
|
|
|
|
|
|
289
|
|
|
|
|
|
|
=item * gle - Irish |
|
290
|
|
|
|
|
|
|
|
|
291
|
|
|
|
|
|
|
=item * glg - Galician |
|
292
|
|
|
|
|
|
|
|
|
293
|
|
|
|
|
|
|
=item * glk - Gilaki |
|
294
|
|
|
|
|
|
|
|
|
295
|
|
|
|
|
|
|
=item * guj - Gujarati |
|
296
|
|
|
|
|
|
|
|
|
297
|
|
|
|
|
|
|
=item * hat - Haitian |
|
298
|
|
|
|
|
|
|
|
|
299
|
|
|
|
|
|
|
=item * hbs - Serbo-Croatian |
|
300
|
|
|
|
|
|
|
|
|
301
|
|
|
|
|
|
|
=item * heb - Hebrew |
|
302
|
|
|
|
|
|
|
|
|
303
|
|
|
|
|
|
|
=item * hif - Fiji Hindi |
|
304
|
|
|
|
|
|
|
|
|
305
|
|
|
|
|
|
|
=item * hin - Hindi |
|
306
|
|
|
|
|
|
|
|
|
307
|
|
|
|
|
|
|
=item * hrv - Croatian |
|
308
|
|
|
|
|
|
|
|
|
309
|
|
|
|
|
|
|
=item * hsb - Upper Sorbian |
|
310
|
|
|
|
|
|
|
|
|
311
|
|
|
|
|
|
|
=item * hun - Hungarian |
|
312
|
|
|
|
|
|
|
|
|
313
|
|
|
|
|
|
|
=item * hye - Armenian |
|
314
|
|
|
|
|
|
|
|
|
315
|
|
|
|
|
|
|
=item * ido - Ido |
|
316
|
|
|
|
|
|
|
|
|
317
|
|
|
|
|
|
|
=item * ina - Interlingua (International Auxiliary Language Association) |
|
318
|
|
|
|
|
|
|
|
|
319
|
|
|
|
|
|
|
=item * ind - Indonesian |
|
320
|
|
|
|
|
|
|
|
|
321
|
|
|
|
|
|
|
=item * isl - Icelandic |
|
322
|
|
|
|
|
|
|
|
|
323
|
|
|
|
|
|
|
=item * ita - Italian |
|
324
|
|
|
|
|
|
|
|
|
325
|
|
|
|
|
|
|
=item * jav - Javanese |
|
326
|
|
|
|
|
|
|
|
|
327
|
|
|
|
|
|
|
=item * jpn - Japanese |
|
328
|
|
|
|
|
|
|
|
|
329
|
|
|
|
|
|
|
=item * kan - Kannada |
|
330
|
|
|
|
|
|
|
|
|
331
|
|
|
|
|
|
|
=item * kat - Georgian |
|
332
|
|
|
|
|
|
|
|
|
333
|
|
|
|
|
|
|
=item * kaz - Kazakh |
|
334
|
|
|
|
|
|
|
|
|
335
|
|
|
|
|
|
|
=item * kor - Korean |
|
336
|
|
|
|
|
|
|
|
|
337
|
|
|
|
|
|
|
=item * kur - Kurdish |
|
338
|
|
|
|
|
|
|
|
|
339
|
|
|
|
|
|
|
=item * lat - Latin |
|
340
|
|
|
|
|
|
|
|
|
341
|
|
|
|
|
|
|
=item * lav - Latvian |
|
342
|
|
|
|
|
|
|
|
|
343
|
|
|
|
|
|
|
=item * lim - Limburgan |
|
344
|
|
|
|
|
|
|
|
|
345
|
|
|
|
|
|
|
=item * lit - Lithuanian |
|
346
|
|
|
|
|
|
|
|
|
347
|
|
|
|
|
|
|
=item * lmo - Lombard |
|
348
|
|
|
|
|
|
|
|
|
349
|
|
|
|
|
|
|
=item * ltz - Luxembourgish |
|
350
|
|
|
|
|
|
|
|
|
351
|
|
|
|
|
|
|
=item * mal - Malayalam |
|
352
|
|
|
|
|
|
|
|
|
353
|
|
|
|
|
|
|
=item * mar - Marathi |
|
354
|
|
|
|
|
|
|
|
|
355
|
|
|
|
|
|
|
=item * mkd - Macedonian |
|
356
|
|
|
|
|
|
|
|
|
357
|
|
|
|
|
|
|
=item * mlg - Malagasy |
|
358
|
|
|
|
|
|
|
|
|
359
|
|
|
|
|
|
|
=item * mon - Mongolian |
|
360
|
|
|
|
|
|
|
|
|
361
|
|
|
|
|
|
|
=item * mri - Maori |
|
362
|
|
|
|
|
|
|
|
|
363
|
|
|
|
|
|
|
=item * msa - Malay (macrolanguage) |
|
364
|
|
|
|
|
|
|
|
|
365
|
|
|
|
|
|
|
=item * mya - Burmese |
|
366
|
|
|
|
|
|
|
|
|
367
|
|
|
|
|
|
|
=item * nap - Neapolitan |
|
368
|
|
|
|
|
|
|
|
|
369
|
|
|
|
|
|
|
=item * nds - Low German |
|
370
|
|
|
|
|
|
|
|
|
371
|
|
|
|
|
|
|
=item * nep - Nepali |
|
372
|
|
|
|
|
|
|
|
|
373
|
|
|
|
|
|
|
=item * new - Newari |
|
374
|
|
|
|
|
|
|
|
|
375
|
|
|
|
|
|
|
=item * nld - Dutch |
|
376
|
|
|
|
|
|
|
|
|
377
|
|
|
|
|
|
|
=item * nno - Norwegian Nynorsk |
|
378
|
|
|
|
|
|
|
|
|
379
|
|
|
|
|
|
|
=item * nor - Norwegian |
|
380
|
|
|
|
|
|
|
|
|
381
|
|
|
|
|
|
|
=item * oci - Occitan (post 1500) |
|
382
|
|
|
|
|
|
|
|
|
383
|
|
|
|
|
|
|
=item * oss - Ossetian |
|
384
|
|
|
|
|
|
|
|
|
385
|
|
|
|
|
|
|
=item * pam - Pampanga |
|
386
|
|
|
|
|
|
|
|
|
387
|
|
|
|
|
|
|
=item * pms - Piemontese |
|
388
|
|
|
|
|
|
|
|
|
389
|
|
|
|
|
|
|
=item * pnb - Western Panjabi |
|
390
|
|
|
|
|
|
|
|
|
391
|
|
|
|
|
|
|
=item * pol - Polish |
|
392
|
|
|
|
|
|
|
|
|
393
|
|
|
|
|
|
|
=item * por - Portuguese |
|
394
|
|
|
|
|
|
|
|
|
395
|
|
|
|
|
|
|
=item * que - Quechua |
|
396
|
|
|
|
|
|
|
|
|
397
|
|
|
|
|
|
|
=item * ron - Romanian |
|
398
|
|
|
|
|
|
|
|
|
399
|
|
|
|
|
|
|
=item * rus - Russian |
|
400
|
|
|
|
|
|
|
|
|
401
|
|
|
|
|
|
|
=item * sah - Yakut |
|
402
|
|
|
|
|
|
|
|
|
403
|
|
|
|
|
|
|
=item * scn - Sicilian |
|
404
|
|
|
|
|
|
|
|
|
405
|
|
|
|
|
|
|
=item * sco - Scots |
|
406
|
|
|
|
|
|
|
|
|
407
|
|
|
|
|
|
|
=item * slk - Slovak |
|
408
|
|
|
|
|
|
|
|
|
409
|
|
|
|
|
|
|
=item * slv - Slovenian |
|
410
|
|
|
|
|
|
|
|
|
411
|
|
|
|
|
|
|
=item * spa - Spanish |
|
412
|
|
|
|
|
|
|
|
|
413
|
|
|
|
|
|
|
=item * sqi - Albanian |
|
414
|
|
|
|
|
|
|
|
|
415
|
|
|
|
|
|
|
=item * srp - Serbian |
|
416
|
|
|
|
|
|
|
|
|
417
|
|
|
|
|
|
|
=item * sun - Sundanese |
|
418
|
|
|
|
|
|
|
|
|
419
|
|
|
|
|
|
|
=item * swa - Swahili (macrolanguage) |
|
420
|
|
|
|
|
|
|
|
|
421
|
|
|
|
|
|
|
=item * swe - Swedish |
|
422
|
|
|
|
|
|
|
|
|
423
|
|
|
|
|
|
|
=item * tam - Tamil |
|
424
|
|
|
|
|
|
|
|
|
425
|
|
|
|
|
|
|
=item * tat - Tatar |
|
426
|
|
|
|
|
|
|
|
|
427
|
|
|
|
|
|
|
=item * tel - Telugu |
|
428
|
|
|
|
|
|
|
|
|
429
|
|
|
|
|
|
|
=item * tgk - Tajik |
|
430
|
|
|
|
|
|
|
|
|
431
|
|
|
|
|
|
|
=item * tgl - Tagalog |
|
432
|
|
|
|
|
|
|
|
|
433
|
|
|
|
|
|
|
=item * tha - Thai |
|
434
|
|
|
|
|
|
|
|
|
435
|
|
|
|
|
|
|
=item * tur - Turkish |
|
436
|
|
|
|
|
|
|
|
|
437
|
|
|
|
|
|
|
=item * ukr - Ukrainian |
|
438
|
|
|
|
|
|
|
|
|
439
|
|
|
|
|
|
|
=item * urd - Urdu |
|
440
|
|
|
|
|
|
|
|
|
441
|
|
|
|
|
|
|
=item * uzb - Uzbek |
|
442
|
|
|
|
|
|
|
|
|
443
|
|
|
|
|
|
|
=item * vec - Venetian |
|
444
|
|
|
|
|
|
|
|
|
445
|
|
|
|
|
|
|
=item * vie - Vietnamese |
|
446
|
|
|
|
|
|
|
|
|
447
|
|
|
|
|
|
|
=item * vol - Volapük |
|
448
|
|
|
|
|
|
|
|
|
449
|
|
|
|
|
|
|
=item * war - Waray (Philippines) |
|
450
|
|
|
|
|
|
|
|
|
451
|
|
|
|
|
|
|
=item * wln - Walloon |
|
452
|
|
|
|
|
|
|
|
|
453
|
|
|
|
|
|
|
=item * yid - Yiddish |
|
454
|
|
|
|
|
|
|
|
|
455
|
|
|
|
|
|
|
=item * yor - Yoruba |
|
456
|
|
|
|
|
|
|
|
|
457
|
|
|
|
|
|
|
=item * zho - Chinese |
|
458
|
|
|
|
|
|
|
|
|
459
|
|
|
|
|
|
|
=back |
|
460
|
|
|
|
|
|
|
|
|
461
|
|
|
|
|
|
|
=head1 SEE ALSO |
|
462
|
|
|
|
|
|
|
|
|
463
|
|
|
|
|
|
|
=over |
|
464
|
|
|
|
|
|
|
|
|
465
|
|
|
|
|
|
|
=item * Identifier for own models is L<Lingua::YALI::Identifier|Lingua::YALI::Identifier>. |
|
466
|
|
|
|
|
|
|
|
|
467
|
|
|
|
|
|
|
=item * There is also command line tool L<yali-language-identifier|Lingua::YALI::yali-language-identifier> with similar functionality. |
|
468
|
|
|
|
|
|
|
|
|
469
|
|
|
|
|
|
|
=item * Source codes are available at L<https://github.com/martin-majlis/YALI>. |
|
470
|
|
|
|
|
|
|
|
|
471
|
|
|
|
|
|
|
=back |
|
472
|
|
|
|
|
|
|
|
|
473
|
|
|
|
|
|
|
=head1 AUTHOR |
|
474
|
|
|
|
|
|
|
|
|
475
|
|
|
|
|
|
|
Martin Majlis <martin@majlis.cz> |
|
476
|
|
|
|
|
|
|
|
|
477
|
|
|
|
|
|
|
=head1 COPYRIGHT AND LICENSE |
|
478
|
|
|
|
|
|
|
|
|
479
|
|
|
|
|
|
|
This software is Copyright (c) 2012 by Martin Majlis. |
|
480
|
|
|
|
|
|
|
|
|
481
|
|
|
|
|
|
|
This is free software, licensed under: |
|
482
|
|
|
|
|
|
|
|
|
483
|
|
|
|
|
|
|
The (three-clause) BSD License |
|
484
|
|
|
|
|
|
|
|
|
485
|
|
|
|
|
|
|
=cut |