#!/usr/bin/perl -w -s

our ($ori,$ablt,$rblt,$protcom) ;

my ($bl,$langpat,%l);
$bl = $ablt if (defined $ablt) && ($ablt =~ /[A-Za-z]+/);
$bl = $rblt if (defined $rblt) && ($rblt =~ /[A-Za-z]+/);

$/='';

my $s;
while(<>){
  chomp;
  if(/^\%/){
    if (/\%baselang(?:uage)?\s+(\S+)/) { $bl ||= $1; }
    while( m/\%lang(?:uage)?\s+(\S+.*)/g)     { 
      my $ls = $1;
      for ($ls =~ m/(\S+)/g){ $l{$_} = 1}; 
      $langpat=join('|',keys %l)}
  }
  elsif(/^[#]/)                        {   }
  elsif(/^(.*)/) { 
      if($protcom){
        while( s/^(.*?)\s*,\s*/$1 _and / ){} 
        if($langpat){while( s/(\n(?:$langpat))(.*?)\s*,\s*/$1$2 _and / ){} }
      }  
      $_ .= "\nFROM $ori"   if $ori;
      $_ = "$bl $_"         if $ablt;
      $_ =~ s/^$bl\s+//i    if $rblt;
  }
  print "$_\n\n";
}

__END__

=head1 NAME

thesaurusSC - Make thesaurus changes (simple changes)

=head1 SYNOPSIS

 thesaurusSC -ori=Natura file.the    (adds  "FROM Natura" to each entry)
 thesaurusSC -ablt[=PT]  file.the    (adds  "baselang tag" to each entry)
 thesaurusSC -rblt[=PT]  file.the    (removes "baselang tag" from each entry)
 thesaurusSC -protcom  file.the      (protect commas  "," --> "_and ")

=head1 DESCRIPTION

Make simple changes in Thesaurus files.

 1 add origin
 2 add baselang tag
 3 removes baselang tag
 4 protcom            protect commas in term and language
 5 cat               (not yet implemented)

=head1 AUTHOR

J.Joao Almeida, jj@di.uminho.pt

=head1 SEE ALSO

perl(1).

=cut