Blame view

tools/scripts/MergeLexicon.pl 3.64 KB
e6be5137b   Jean-François Rey   reinitialized pro...
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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
  #!/usr/bin/perl -w
  
  use strict;
  use Getopt::Long;
  use Pod::Usage;
  
  #-------------------------------------------
  # MAIN
  #-------------------------------------------
  
  # options variables
  my $help = 0;
  my $level = 2;
  my $lexSep = "\t";
  my $report = "";
  my $pause=1;
  my $desactlc = 0;
  # usefull variables
  my %MergeLexicon;
  my %HomoPhon;
  my $homoPhonFile ="";
  my $polyPhonFile = "";
  my @polyPhonTab = ();
  
  GetOptions('help|?' => \$help,
  	   'dlc' => \$desactlc,
  	   'report=s' => \$report,
  	   'level=s' => \$level);
   
  pod2usage(1) if($help);
  pod2usage({-msg => "BAD USAGE - you must specify a level value greater than 0
  ", -exitval => 1, -verbose => 0, -output => \*STDERR}) if($report && $level <= 0);
  
  if($report){
  	$homoPhonFile= $report.".homophon.lst";
  	$polyPhonFile= $report.".polyphon.lst";
  }
  
  for(my $i = 0; $i<=$#ARGV; $i++){
  	my $file;
  	open($file, "$ARGV[$i]") or die ("Cannot open : $ARGV[$i]
  ");
  	while(<$file>){
  		chomp($_);
  		#split 0: word 1: phon spelling
  		my @splittedLine = split($lexSep, $_);
  		if($#splittedLine != 1){
  			die("BAD FORMAT : $_
  ");
  		}
  		my $word = $splittedLine[0];
  		my $phonSpelling = $splittedLine[1];
  		my $lcword;
  		if(!$desactlc){
  			$lcword = lc($word);
  		} else{
  			$lcword = $word;
  		}
  		if(exists $MergeLexicon{$lcword}){
  			${$MergeLexicon{$lcword}}{$phonSpelling}++;
  		} else{
  			$MergeLexicon{$lcword} = { $phonSpelling => 1};
  		}
  		# no count duplicate value with pause
  		if($phonSpelling !~ /pause/){
  			if(exists $HomoPhon{$phonSpelling}){
  				${$HomoPhon{$phonSpelling}}{$word}++;
  			} else{
  				$HomoPhon{$phonSpelling} = { $word => 1 };
  			}
  		}
  	}
  	close($file);	
  }
  
  my @lcwords = keys %MergeLexicon;
  @lcwords = sort @lcwords;
  for(my $idx=0; $idx<=$#lcwords; $idx++){
  	my $lcword = $lcwords[$idx];
  	my $refPhonHash = $MergeLexicon{$lcword};
  	my @diffPhonTab = keys %{$refPhonHash};
  	@diffPhonTab = sort @diffPhonTab;
  	if($#diffPhonTab >= $level - 1){
  		my $nbDiff;
  		if($pause){
  			$nbDiff = (($#diffPhonTab + 1)/2);
  		} else{
  			$nbDiff = ($#diffPhonTab +1);
  		}
  		push(@polyPhonTab, "$lcword\t$nbDiff");
  	}
  	for (my $i=0; $i <= $#diffPhonTab; $i++){
  	 	print "$lcword\t$diffPhonTab[$i]
  ";
  	}
  }
  
  
  if($polyPhonFile){
  	my $file;
  	if($#polyPhonTab >= 0){
  		open($file, ">$polyPhonFile") or die("Cannot open: $polyPhonFile
  ");
  		@polyPhonTab = sort sort_polyphon_homophon @polyPhonTab;
  		for(my $i = 0; $i <= $#polyPhonTab; $i++){
  			print $file "$polyPhonTab[$i]
  ";
  		}
  		close($file);
  	}
  }
  
  if($homoPhonFile){
  	my @homoPhonTab=();
  	while(my ($phon, $wordHash) = each %HomoPhon){
  		my @diffWordTab = keys %{$wordHash};
  		if($#diffWordTab >= $level -1){
  			my $nbDiff = $#diffWordTab + 1;
  			push(@homoPhonTab, "$phon\t$nbDiff");
  		}
  	}
  	if($#homoPhonTab >= 0){
  		my $file;
  		open($file, ">$homoPhonFile") or die("Cannot open : $homoPhonFile
  ");
  		@homoPhonTab = sort sort_polyphon_homophon @homoPhonTab;
  		for(my $i = 0; $i <= $#homoPhonTab; $i++){
  			my @splittedLine = split(/\t/, $homoPhonTab[$i]);
  			my $phon = $splittedLine[0];
  			my $nbDiff = $splittedLine[1];
  			print $file "### $nbDiff FOR $phon :
  ";
  			my @diffWordTab = keys %{$HomoPhon{$phon}};
  			@diffWordTab = sort @diffWordTab;
  			for(my $i=0; $i <= $#diffWordTab; $i++){
  				print $file "$diffWordTab[$i]
  ";
  			}
  		}
  		close($file);
  	}
  }
  
  sub sort_polyphon_homophon{
  	my @splita = split(/\t/, $a);
  	my @splitb = split(/\t/, $b);
  	return $splitb[1] <=> $splita[1];
  }
  
  __END__
  
  =head1 NAME
  
  MergeLexicon.pl - merge phonetized lexicon (upper case to lower case)
  
  =head1 SYNOPSIS
  
  MergeLexicon.pl [options] <lexicon.phon> ...
  
  Options :
  
  	-help|? 	display this help
  
  	-report		produce report
  
  	-dlc		desactivate lower case transformation
  
  	-level 	 	choose a level of report consideration (default 2)