1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
|
open(fid_doc,"corpus.txt") || die ("couldn't open corpus.txt!");
while (<fid_doc>)
{
push(@file_doc,$_); #Files constituting the corpus
}
close(fid_doc);
$N_doc = $#file_doc + 1;
foreach $i (0..$#file_doc)
{
&occurrence($file_doc[$i]);
#print $file_doc[$i]. "\n";
}
open(fid_req,"requete.txt") || die ("couldn't open requete.txt!");
while (<fid_req>)
{
push(@file_req,$_); #Files constituting the queries
}
close(fid_req);
$N_req = $#file_req + 1;
foreach $i (0..$#file_req)
{
&occurrence_req($file_req[$i],$i);
#print $file_req[$i]. "\n";
}
#**************************************************************
display(corpus_traited_word,terms_traited_word,graphe_word,\%occurrence_matrix);
#**************************************************************
#
#**************************************************************
# occurrence procedure
#**************************************************************
sub occurrence
{
my @word_list;
open(fid,$_[0]) || die ("couldn't open file.txt!");
while (<fid>)
{
@word_list = (@word_list,split(/[\n\*]/,$_));
}
close(fid);
#**************************************************************
foreach $word (@word_list)
{
@{$occurrence_matrix{$word}}[$_[1]]++;
#print $word;
}
delete $occurrence_matrix{""};
}
#**************************************************************
#**************************************************************
# occurrence_req procedure
#**************************************************************
sub occurrence_req
{
my @word_list;
open(fid,$_[0]) || die ("couldn't open file.txt!");
while (<fid>)
{
@word_list = (@word_list,split(/[\*\n]/,$_));
}
close(fid);
$i = 0;
while ($i<$#word_list)
{
if(@{$occurrence_matrix{$word_list[$i]}} != undef)
{
@{$occurrence_matrix{$word_list[$i]}}[$_[1]]= $word_list[$i+1] ;
print $word_list[0];
}
$i=$i+2
}
delete $occurrence_matrix{""};
}
#**************************************************************
# Displaying the Results
#**************************************************************
sub display
{
open(fid,">$_[0].txt") || die ("couldn't open corpus_traited.txt!");
open(fid_t,">$_[1].txt") || die ("couldn't open terms_traited.txt!");
open(fid_g,">$_[2].txt") || die ("couldn't open graphe.txt!");
my $ref_occurrence_matrix;
$ref_occurrence_matrix = $_[3];
@key = keys(%{$ref_occurrence_matrix});
foreach $i (0..$#key)
{
if (length(@key[$i]) == 2)
{
delete $$ref_occurrence_matrix{@key[$i]};
}
}
@key = sort(keys(%{$ref_occurrence_matrix}));
$N_mot = $#key + 1;
print fid "nombre de documents: $N_doc", "\n";
print fid "nombre de requetes: $N_req", "\n";
print fid "nombre de mots: $N_mot", "\n";
print fid_g "$N_doc $N_req $N_mot", "\n";
foreach $i (0..$#key)
{
print fid @key[$i];
print fid_t @key[$i];
for($j = 0;$j <= ($#file_doc + $N_req);$j ++)
{
print fid "\t";
if(${$$ref_occurrence_matrix{@key[$i]}}[$j] == undef)
{
print fid "0";
print fid_g "0 ";
}
else
{
print fid ${$$ref_occurrence_matrix{@key[$i]}}[$j];
print fid_g "${$$ref_occurrence_matrix{@key[$i]}}[$j] ";
}
}
print fid "\n";
print fid_t "\n";
print fid_g "\n";
}
close(fid);
close(fid_t);
close(fid_g);
} |
