Blame view

Scripts/utils/find_arpa_oovs.pl 1.99 KB
ec85f8892   bigot benjamin   first commit
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
  #!/usr/bin/perl
  # Copyright 2010-2011 Microsoft Corporation
  
  # Licensed under the Apache License, Version 2.0 (the "License");
  # you may not use this file except in compliance with the License.
  # You may obtain a copy of the License at
  #
  #  http://www.apache.org/licenses/LICENSE-2.0
  #
  # THIS CODE IS PROVIDED *AS IS* BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
  # KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION ANY IMPLIED
  # WARRANTIES OR CONDITIONS OF TITLE, FITNESS FOR A PARTICULAR PURPOSE,
  # MERCHANTABLITY OR NON-INFRINGEMENT.
  # See the Apache 2 License for the specific language governing permissions and
  # limitations under the License.
  
  
  if (  @ARGV < 1 && @ARGV > 2) {
      die "Usage: find_arpa_oovs.pl words.txt [lm.arpa]
  ";
      # This program finds words in the arpa file that are not symbols
      # in the OpenFst-format symbol table words.txt.  It prints them
      # on the standard output, one per line.
  }
  
  $symtab = shift @ARGV;
  open(S, "<$symtab") || die "Failed opening symbol table file $symtab
  ";
  while(<S>){ 
      @A = split(" ", $_);
      @A == 2 || die "Bad line in symbol table file: $_";
      $seen{$A[0]} = 1;
  }
  
  $curgram=0;
  while(<>) { # Find the \data\ marker.
      if(m:^\\data\\$:) { last; }
  }
  while(<>) {
      if(m/^\\(\d+)\-grams:\s*$/) {
          $curgram = $1;
          if($curgram > 1) {
              last; # This is an optimization as we can get the vocab from the 1-grams
          }
      } elsif($curgram > 0) {
          @A = split(" ", $_);
          if(@A > 1) {
              shift @A;
              for($n=0;$n<$curgram;$n++) {
                  $word = $A[$n];
                  if(!defined $word) { print STDERR "Unusual line $_ (line $.) in arpa file.
  "; }
                  $in_arpa{$word} = 1;
              }
          } else {
              if(@A > 0 && $A[0] !~ m:\\end\\:) {
                  print STDERR "Unusual line $_ (line $.) in arpa file
  ";
              }
          }
      }
  }
  
  foreach $w (keys %in_arpa) {
      if(!defined $seen{$w} && $w ne "<s>" && $w ne "</s>") {
          print "$w
  ";
      }
  }