line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
# |
2
|
|
|
|
|
|
|
# TestifiedTermParser.yp |
3
|
|
|
|
|
|
|
# |
4
|
|
|
|
|
|
|
# used to generate Lingua::YaTeA::TestifiedTermParser.pm |
5
|
|
|
|
|
|
|
# |
6
|
|
|
|
|
|
|
# Use: yapp -m 'Lingua::YaTeA::TestifiedTermParser' -o lib/Lingua/YaTeA/TestifiedTermParser.pm lib/Lingua/YaTeA/TestifiedTermParser.yp |
7
|
|
|
|
|
|
|
# |
8
|
|
|
|
|
|
|
# Parse::Yapp input grammar for parsing the yatea testified terms |
9
|
|
|
|
|
|
|
# |
10
|
|
|
|
|
|
|
# |
11
|
|
|
|
|
|
|
# |
12
|
|
|
|
|
|
|
%{ |
13
|
5
|
|
|
5
|
|
1442
|
use Lingua::YaTeA; |
|
5
|
|
|
|
|
10
|
|
|
5
|
|
|
|
|
84
|
|
14
|
5
|
|
|
5
|
|
149
|
use Data::Dumper; |
|
5
|
|
|
|
|
14
|
|
|
5
|
|
|
|
|
225
|
|
15
|
5
|
|
|
5
|
|
28
|
use warnings; |
|
5
|
|
|
|
|
10
|
|
|
5
|
|
|
|
|
115
|
|
16
|
5
|
|
|
5
|
|
23
|
use UNIVERSAL; |
|
5
|
|
|
|
|
10
|
|
|
5
|
|
|
|
|
27
|
|
17
|
5
|
|
|
5
|
|
171
|
use Scalar::Util qw(blessed); |
|
5
|
|
|
|
|
9
|
|
|
5
|
|
|
|
|
10263
|
|
18
|
|
|
|
|
|
|
my @words; |
19
|
|
|
|
|
|
|
my $word; |
20
|
|
|
|
|
|
|
my $item; |
21
|
|
|
|
|
|
|
my @infos; |
22
|
|
|
|
|
|
|
my @IF; |
23
|
|
|
|
|
|
|
my @POS; |
24
|
|
|
|
|
|
|
my @LF; |
25
|
|
|
|
|
|
|
my $src; |
26
|
|
|
|
|
|
|
my @lex_items; |
27
|
|
|
|
|
|
|
my $testified; |
28
|
|
|
|
|
|
|
my $i; |
29
|
|
|
|
|
|
|
my $tree; |
30
|
|
|
|
|
|
|
my $node_set; |
31
|
|
|
|
|
|
|
my $node; |
32
|
|
|
|
|
|
|
my $edge; |
33
|
|
|
|
|
|
|
my $index = 0; |
34
|
|
|
|
|
|
|
my @uncomplete; |
35
|
|
|
|
|
|
|
my $level = 0; |
36
|
|
|
|
|
|
|
my $num_line =1; |
37
|
|
|
|
|
|
|
%} |
38
|
|
|
|
|
|
|
%% |
39
|
|
|
|
|
|
|
input: #empty |
40
|
0
|
|
|
0
|
0
|
|
| input line { #print STDERR "\n INPUT \n"; |
|
|
|
|
0
|
|
|
|
41
|
0
|
0
|
|
|
|
|
} |
42
|
|
|
|
|
|
|
; |
43
|
|
|
|
|
|
|
|
44
|
|
|
|
|
|
|
line: '\n' { # print "VIDE: " . $_[1] |
45
|
0
|
|
|
0
|
|
|
$num_line++; |
46
|
|
|
|
|
|
|
} |
47
|
|
|
|
|
|
|
| testified { |
48
|
0
|
|
|
0
|
|
|
$num_line++; |
49
|
0
|
|
|
|
|
|
@lex_items = (); |
50
|
0
|
|
|
|
|
|
@words= (); |
51
|
0
|
|
|
|
|
|
my $testified; |
52
|
|
|
|
|
|
|
# print STDERR "=>$_[1]\n"; |
53
|
|
|
|
|
|
|
my $testified_infos; |
54
|
0
|
0
|
|
|
|
|
if($_[0]->YYData->{TTS}->getTestifiedInfos(\$testified_infos,\@IF,\@POS,\@LF,$src,\@lex_items,$_[0]->YYData->{MATCH},$_[0]->YYData->{FILTERING_LEXICON},$_[0]->YYData->{TAGSET}) == 1) { |
55
|
0
|
0
|
|
|
|
|
if(scalar @lex_items > 1) { |
56
|
0
|
|
|
|
|
|
$testified = Lingua::YaTeA::MultiWordTestifiedTerm->new($testified_infos->{"NUM_CONTENT_WORDS"},\@lex_items,$_[0]->YYData->{TAGSET},$src,$_[0]->YYData->{MATCH}); |
57
|
|
|
|
|
|
|
} |
58
|
|
|
|
|
|
|
} |
59
|
0
|
0
|
0
|
|
|
|
if ((blessed($testified)) && ($testified->isa('Lingua::YaTeA::TestifiedTerm'))) { |
60
|
|
|
|
|
|
|
#print STDERR "ajout tt: " . $testified->getIF . "\n"; |
61
|
0
|
|
|
|
|
|
$_[0]->YYData->{TTS}->addTestified($testified); |
62
|
|
|
|
|
|
|
|
63
|
0
|
0
|
0
|
|
|
|
if ((blessed($testified)) && ($testified->isa('Lingua::YaTeA::MultiWordTestifiedTerm'))) { |
64
|
0
|
|
|
|
|
|
$tree = Lingua::YaTeA::Tree->new; |
65
|
0
|
|
|
|
|
|
$tree->setNodeSet($node_set); |
66
|
|
|
|
|
|
|
# $tree->print($testified_infos->{"WORDS"}); |
67
|
0
|
|
|
|
|
|
$tree->setIndexSet($testified->getIndexSet); |
68
|
0
|
|
|
|
|
|
$tree->setHead; |
69
|
0
|
|
|
|
|
|
$testified->addTree($tree); |
70
|
0
|
|
|
|
|
|
$testified->setParsingMethod("USER"); |
71
|
|
|
|
|
|
|
} |
72
|
|
|
|
|
|
|
} |
73
|
|
|
|
|
|
|
# print "fin creation :" . $testified->getIF . "\n"; |
74
|
0
|
|
|
|
|
|
$level = 0; |
75
|
0
|
|
|
|
|
|
$index = 0; |
76
|
|
|
|
|
|
|
} |
77
|
|
|
|
|
|
|
; |
78
|
|
|
|
|
|
|
|
79
|
|
|
|
|
|
|
|
80
|
|
|
|
|
|
|
testified: { |
81
|
0
|
|
|
0
|
|
|
$node_set = Lingua::YaTeA::NodeSet->new; |
82
|
|
|
|
|
|
|
} |
83
|
|
|
|
0
|
|
|
OPEN parsing END infos { #print "trouve testified2 $_[1]\n"; |
84
|
|
|
|
|
|
|
} |
85
|
0
|
|
|
0
|
|
|
| error '\nTESTIFIED: ' { $_[0]->YYErrok } |
86
|
|
|
|
|
|
|
; |
87
|
|
|
|
|
|
|
|
88
|
|
|
|
|
|
|
infos: INFOS { |
89
|
|
|
|
|
|
|
# print "infos $_[1]\n"; |
90
|
0
|
|
|
0
|
|
|
@infos = split /\t/, $_[1]; |
91
|
0
|
|
|
|
|
|
@IF = split / /, $infos[0]; |
92
|
0
|
|
|
|
|
|
@POS = split / /, $infos[1]; |
93
|
0
|
|
|
|
|
|
@LF = split / /, $infos[2]; |
94
|
0
|
|
|
|
|
|
$src = $infos[3]; |
95
|
|
|
|
|
|
|
} |
96
|
|
|
|
|
|
|
; |
97
|
|
|
|
|
|
|
|
98
|
|
|
|
|
|
|
|
99
|
|
|
|
|
|
|
|
100
|
|
|
|
|
|
|
parsing: CANDIDATE PREP DET CANDIDATE |
101
|
|
|
|
|
|
|
| CANDIDATE PREP CANDIDATE |
102
|
|
|
|
|
|
|
| CANDIDATE PREP PREP CANDIDATE |
103
|
|
|
|
|
|
|
| CANDIDATE DET CANDIDATE |
104
|
|
|
|
0
|
|
|
| CANDIDATE CANDIDATE { |
105
|
|
|
|
|
|
|
# print STDERR "PARSING $_[1]\n" |
106
|
|
|
|
|
|
|
} |
107
|
|
|
|
|
|
|
| |
108
|
0
|
|
|
0
|
|
|
| error '\nPARSING: ' { $_[0]->YYErrok } |
109
|
|
|
|
|
|
|
; |
110
|
|
|
|
|
|
|
|
111
|
|
|
|
|
|
|
|
112
|
|
|
|
|
|
|
PREP: WORD P_STATUS { |
113
|
|
|
|
|
|
|
# print STDERR "PREP $_[1] $_[2]\n"; |
114
|
0
|
|
|
0
|
|
|
$node->{"PREP"} = Lingua::YaTeA::TermLeaf->new($index); |
115
|
0
|
|
|
|
|
|
$index++; |
116
|
|
|
|
|
|
|
}; |
117
|
|
|
|
|
|
|
|
118
|
|
|
|
|
|
|
DET: WORD D_STATUS { |
119
|
|
|
|
|
|
|
# print STDERR "DET $_[1] $_[2]\n"; |
120
|
0
|
|
|
0
|
|
|
$node->{"DET"} = Lingua::YaTeA::TermLeaf->new($index); |
121
|
0
|
|
|
|
|
|
$index++; |
122
|
|
|
|
|
|
|
}; |
123
|
|
|
|
|
|
|
|
124
|
|
|
|
|
|
|
CANDIDATE: WORD C_STATUS{ |
125
|
|
|
|
|
|
|
# print STDERR "CANDIDATE1 $_[1] $_[2]\n"; |
126
|
0
|
|
|
0
|
|
|
$edge = Lingua::YaTeA::TermLeaf->new($index); |
127
|
0
|
|
|
|
|
|
$node->addEdge($edge,$_[2]); |
128
|
|
|
|
|
|
|
# print "ajout du edge :" ; |
129
|
|
|
|
|
|
|
# print Dumper($edge) . "\n"; |
130
|
0
|
|
|
|
|
|
$index++; |
131
|
|
|
|
|
|
|
} |
132
|
|
|
|
0
|
|
|
| OPEN parsing CLOSE { |
133
|
|
|
|
|
|
|
#print STDERR "CANDIDATE2 $_[1]\n"; |
134
|
|
|
|
|
|
|
} |
135
|
0
|
|
|
0
|
|
|
| error '\nCANDIDATE: ' { $_[0]->YYErrok } |
136
|
|
|
|
|
|
|
; |
137
|
|
|
|
|
|
|
|
138
|
|
|
|
|
|
|
OPEN: OPEN_TAG { |
139
|
|
|
|
|
|
|
# print STDERR "OPEN $_[1]\n"; |
140
|
0
|
0
|
|
0
|
|
|
if ($level == 0) |
141
|
|
|
|
|
|
|
{ |
142
|
0
|
|
|
|
|
|
$node = Lingua::YaTeA::RootNode->new($level); |
143
|
|
|
|
|
|
|
} |
144
|
|
|
|
|
|
|
else |
145
|
|
|
|
|
|
|
{ |
146
|
0
|
|
|
|
|
|
$node = Lingua::YaTeA::InternalNode->new($level); |
147
|
|
|
|
|
|
|
} |
148
|
0
|
|
|
|
|
|
$node_set->addNode($node); |
149
|
0
|
|
|
|
|
|
push @uncomplete, $node; |
150
|
0
|
|
|
|
|
|
$level++; |
151
|
|
|
|
|
|
|
} |
152
|
0
|
|
|
0
|
|
|
| error '\nOPEN: ' { $_[0]->YYErrok } |
153
|
|
|
|
|
|
|
; |
154
|
|
|
|
|
|
|
|
155
|
|
|
|
|
|
|
|
156
|
|
|
|
0
|
|
|
END: END_TAG { |
157
|
|
|
|
|
|
|
# print STDERR "END $_[1]\n"; |
158
|
|
|
|
|
|
|
} |
159
|
0
|
|
|
0
|
|
|
| error '\nEND: ' { $_[0]->YYErrok } |
160
|
|
|
|
|
|
|
; |
161
|
|
|
|
|
|
|
|
162
|
|
|
|
|
|
|
CLOSE: END_TAG C_STATUS { |
163
|
|
|
|
|
|
|
# print STDERR "CLOSE_TAG $_[1] $_[2]\n"; |
164
|
0
|
|
|
0
|
|
|
pop @uncomplete; |
165
|
0
|
|
|
|
|
|
$node->linkToFather(\@uncomplete,$_[2]); |
166
|
0
|
|
|
|
|
|
$node = $uncomplete[$#uncomplete]; |
167
|
0
|
|
|
|
|
|
$level--; |
168
|
|
|
|
|
|
|
} |
169
|
0
|
|
|
0
|
|
|
| error '\nCLOSE: ' { $_[0]->YYErrok } |
170
|
0
|
|
|
|
|
|
; |
171
|
|
|
|
|
|
|
|
172
|
|
|
|
|
|
|
|
173
|
0
|
|
|
|
|
|
%% |
174
|
|
|
|
|
|
|
|
175
|
|
|
|
|
|
|
sub _Error { |
176
|
|
|
|
|
|
|
exists $_[0]->YYData->{ERRMSG} |
177
|
0
|
0
|
|
0
|
|
|
and do { |
178
|
0
|
|
|
|
|
|
print $_[0]->YYData->{ERRMSG}; |
179
|
0
|
|
|
|
|
|
delete $_[0]->YYData->{ERRMSG}; |
180
|
0
|
|
|
|
|
|
return; |
181
|
|
|
|
|
|
|
}; |
182
|
0
|
|
|
|
|
|
print "EXPECT: "; |
183
|
0
|
|
|
|
|
|
print $_[0]->YYExpect . "\n"; |
184
|
0
|
|
|
|
|
|
print "CURTOK: "; |
185
|
0
|
|
|
|
|
|
print "-" . $_[0]->YYCurtok . "-\n"; |
186
|
0
|
|
|
|
|
|
print "CURVAL: "; |
187
|
0
|
|
|
|
|
|
print $_[0]->YYCurval . "\n"; |
188
|
0
|
|
|
|
|
|
print "Lexer: "; |
189
|
0
|
|
|
|
|
|
print Dumper($_[0]->YYLexer) . "\n"; |
190
|
0
|
|
|
|
|
|
print "Syntax error.\n"; |
191
|
|
|
|
|
|
|
} |
192
|
|
|
|
|
|
|
|
193
|
|
|
|
|
|
|
sub _Lexer { |
194
|
0
|
|
|
0
|
|
|
my($parser)=shift; |
195
|
0
|
|
|
|
|
|
my $fh = $parser->YYData->{FH}; |
196
|
|
|
|
|
|
|
|
197
|
|
|
|
|
|
|
|
198
|
0
|
|
|
|
|
|
my $open = '(\()'; |
199
|
0
|
|
|
|
|
|
my $word = $parser->YYData->{WORD};; |
200
|
0
|
|
|
|
|
|
my $close = '(\)<=[MH]>)'; |
201
|
0
|
|
|
|
|
|
my $end = '(\))'; |
202
|
0
|
|
|
|
|
|
my $d_status = '<=(D)>'; |
203
|
0
|
|
|
|
|
|
my $p_status = '<=(P)>'; |
204
|
0
|
|
|
|
|
|
my $c_status = '<=([MH])>'; |
205
|
0
|
|
|
|
|
|
my $infos = '\t(.+)'; |
206
|
|
|
|
|
|
|
|
207
|
|
|
|
|
|
|
|
208
|
|
|
|
|
|
|
$parser->YYData->{INPUT} |
209
|
|
|
|
|
|
|
or $parser->YYData->{INPUT} = <$fh> |
210
|
0
|
0
|
0
|
|
|
|
or return('',undef); |
211
|
|
|
|
|
|
|
|
212
|
0
|
|
|
|
|
|
$parser->YYData->{INPUT}=~s/^[ \t]*#.*//; |
213
|
|
|
|
|
|
|
|
214
|
|
|
|
|
|
|
|
215
|
0
|
|
|
|
|
|
for ($parser->YYData->{INPUT}) { |
216
|
|
|
|
|
|
|
#print "TEST-" .$parser->YYData->{INPUT}. "-\n"; |
217
|
0
|
0
|
|
|
|
|
s/^$open\s*// and return ('OPEN_TAG', $1); |
218
|
0
|
0
|
|
|
|
|
s/^$end// and return('END_TAG', $1); |
219
|
0
|
0
|
|
|
|
|
s/^$word\s*// and return ('WORD', $1); |
220
|
0
|
0
|
|
|
|
|
s/^$c_status\s*// and return ('C_STATUS', $1); |
221
|
0
|
0
|
|
|
|
|
s/^$d_status\s*// and return ('D_STATUS', $1); |
222
|
0
|
0
|
|
|
|
|
s/^$p_status\s*// and return ('P_STATUS', $1); |
223
|
0
|
0
|
|
|
|
|
s/^$close\s*// and return('CLOSE_TAG', $1); |
224
|
0
|
0
|
|
|
|
|
s/^$infos\s*// and return('INFOS', $1, $2); |
225
|
0
|
0
|
|
|
|
|
s/^.+//s and return($1,$1); |
226
|
|
|
|
|
|
|
} |
227
|
|
|
|
|
|
|
} |
228
|
|
|
|
|
|
|
|
229
|
|
|
|
|
|
|
=head1 NAME |
230
|
|
|
|
|
|
|
|
231
|
|
|
|
|
|
|
Lingua::YaTeA::TestifiedTermParser - Perl extension for the parser of testified term file (based on Parse::Yapp) |
232
|
|
|
|
|
|
|
|
233
|
|
|
|
|
|
|
=head1 SYNOPSIS |
234
|
|
|
|
|
|
|
|
235
|
|
|
|
|
|
|
use Lingua::YaTeA::TestifiedTermParser; |
236
|
|
|
|
|
|
|
|
237
|
|
|
|
|
|
|
my $fh = FileHandle->new("<$file_path"); |
238
|
|
|
|
|
|
|
|
239
|
|
|
|
|
|
|
my $parser = Lingua::YaTeA::TestifiedTermParser->new(); |
240
|
|
|
|
|
|
|
|
241
|
|
|
|
|
|
|
$parser->YYData->{TTS} = $this; |
242
|
|
|
|
|
|
|
$parser->YYData->{WORD} = $word_characters_regexp; |
243
|
|
|
|
|
|
|
$parser->YYData->{TAGSET} = $tag_set; |
244
|
|
|
|
|
|
|
$parser->YYData->{MATCH} = $match_type; |
245
|
|
|
|
|
|
|
$parser->YYData->{FH} = $fh; |
246
|
|
|
|
|
|
|
$parser->YYData->{FILTERING_LEXICON} = $filtering_lexicon_h; |
247
|
|
|
|
|
|
|
|
248
|
|
|
|
|
|
|
$parser->YYParse(yylex => \&Lingua::YaTeA::ParsingPatternParser::_Lexer, yyerror => \&Lingua::YaTeA::ParsingPatternParser::_Error); |
249
|
|
|
|
|
|
|
|
250
|
|
|
|
|
|
|
|
251
|
|
|
|
|
|
|
=head1 DESCRIPTION |
252
|
|
|
|
|
|
|
|
253
|
|
|
|
|
|
|
The module implements a parser for analysing testified term file. |
254
|
|
|
|
|
|
|
|
255
|
|
|
|
|
|
|
The parser takes into account several information: the word character |
256
|
|
|
|
|
|
|
list (field C) i.e. all the possible characters in a word, the |
257
|
|
|
|
|
|
|
Part-of-Speech tagset (field C), the type of matching (field |
258
|
|
|
|
|
|
|
C), the file handler to read (field C), and the lexicon of |
259
|
|
|
|
|
|
|
the corpus (field C). |
260
|
|
|
|
|
|
|
|
261
|
|
|
|
|
|
|
=head1 METHODS |
262
|
|
|
|
|
|
|
|
263
|
|
|
|
|
|
|
=head2 _Error() |
264
|
|
|
|
|
|
|
|
265
|
|
|
|
|
|
|
_Error($error_objet); |
266
|
|
|
|
|
|
|
|
267
|
|
|
|
|
|
|
The method is used to manage the parsing error and prints a message |
268
|
|
|
|
|
|
|
explaining the error. |
269
|
|
|
|
|
|
|
|
270
|
|
|
|
|
|
|
=head2 _Lexer() |
271
|
|
|
|
|
|
|
|
272
|
|
|
|
|
|
|
_Lexer($parser_info); |
273
|
|
|
|
|
|
|
|
274
|
|
|
|
|
|
|
The method applies the parser on the data contains in the structure |
275
|
|
|
|
|
|
|
C<$parser_info> (field C). |
276
|
|
|
|
|
|
|
|
277
|
|
|
|
|
|
|
=head1 SEE ALSO |
278
|
|
|
|
|
|
|
|
279
|
|
|
|
|
|
|
Sophie Aubin and Thierry Hamon. Improving Term Extraction with |
280
|
|
|
|
|
|
|
Terminological Resources. In Advances in Natural Language Processing |
281
|
|
|
|
|
|
|
(5th International Conference on NLP, FinTAL 2006). pages |
282
|
|
|
|
|
|
|
380-387. Tapio Salakoski, Filip Ginter, Sampo Pyysalo, Tapio Pahikkala |
283
|
|
|
|
|
|
|
(Eds). August 2006. LNAI 4139. |
284
|
|
|
|
|
|
|
|
285
|
|
|
|
|
|
|
|
286
|
|
|
|
|
|
|
=head1 AUTHOR |
287
|
|
|
|
|
|
|
|
288
|
|
|
|
|
|
|
Thierry Hamon and Sophie Aubin |
289
|
|
|
|
|
|
|
|
290
|
|
|
|
|
|
|
=head1 COPYRIGHT AND LICENSE |
291
|
|
|
|
|
|
|
|
292
|
|
|
|
|
|
|
Copyright (C) 2005 by Thierry Hamon and Sophie Aubin |
293
|
|
|
|
|
|
|
|
294
|
|
|
|
|
|
|
This library is free software; you can redistribute it and/or modify |
295
|
|
|
|
|
|
|
it under the same terms as Perl itself, either Perl version 5.8.6 or, |
296
|
|
|
|
|
|
|
at your option, any later version of Perl 5 you may have available. |
297
|
|
|
|
|
|
|
|
298
|
|
|
|
|
|
|
=cut |