mythes/mythes-1.2.0-vanilla-th-gen-idx.patch

   1 --- misc/mythes-1.2.0.orig/th_gen_idx.pl
   2 +++ misc/build/mythes-1.2.0/th_gen_idx.pl
   3 @@ -1,11 +1,32 @@
   4 -#!/usr/bin/perl
   5 -
   6 -# perl program to take a thesaurus structured text data file
   7 -# and create the proper sorted index file (.idx)
   8 +:
   9 +eval 'exec perl -wS $0 ${1+"$@"}'
  10 +    if 0;
  11 +#*************************************************************************
  12 +#
  13 +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
  14 +#
  15 +# Copyright 2000, 2010 Oracle and/or its affiliates.
  16 +#
  17 +# OpenOffice.org - a multi-platform office productivity suite
  18 +#
  19 +# This file is part of OpenOffice.org.
  20 +#
  21 +# OpenOffice.org is free software: you can redistribute it and/or modify
  22 +# it under the terms of the GNU Lesser General Public License version 3
  23 +# only, as published by the Free Software Foundation.
  24 +#
  25 +# OpenOffice.org is distributed in the hope that it will be useful,
  26 +# but WITHOUT ANY WARRANTY; without even the implied warranty of
  27 +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  28 +# GNU Lesser General Public License version 3 for more details
  29 +# (a copy is included in the LICENSE file that accompanied this code).
  30  #
  31 -# typcially invoked as follows:
  32 -# cat th_en_US_new.dat | ./th_gen_idx.pl > th_en_US_new.idx
  33 +# You should have received a copy of the GNU Lesser General Public License
  34 +# version 3 along with OpenOffice.org.  If not, see
  35 +# <http://www.openoffice.org/license.html>
  36 +# for a copy of the LGPLv3 License.
  37  #
  38 +#*************************************************************************
  39
  40  sub by_entry {
  41      my ($aent, $aoff) = split('\|',$a);
  42 @@ -13,6 +34,27 @@ sub by_entry {
  43      $aent cmp $bent;
  44  }
  45
  46 +#FIXME: someone may want "infile" or even parameter parsing
  47 +sub get_outfile {
  48 +       my $next_is_file = 0;
  49 +       foreach ( @ARGV ) {
  50 +               if ( $next_is_file ) {
  51 +                       return $_
  52 +               }
  53 +               if ( $_ eq "-o" ) {
  54 +                       $next_is_file = 1;
  55 +               }
  56 +       }
  57 +       return "";
  58 +}
  59 +
  60 +sub usage {
  61 +       print "usage:\n";
  62 +       print "$0 -o outfile < input\n";
  63 +
  64 +       exit 99;
  65 +}
  66 +
  67  # main routine
  68  my $ne = 0;       # number of entries in index
  69  my @tindex=();    # the index itself
  70 @@ -24,6 +66,10 @@ my $nm=0;         # number of meaning fo
  71  my $meaning="";   # current meaning and synonyms
  72  my $p;            # misc uses
  73  my $encoding;     # encoding used by text file
  74 +my $outfile = "";
  75 +
  76 +$outfile = get_outfile();
  77 +usage() if ( $outfile eq "" );
  78
  79  # top line of thesaurus provides encoding
  80  $encoding=<STDIN>;
  81 @@ -51,9 +97,13 @@ while ($rec=<STDIN>){
  82  # now we have all of the information
  83  # so sort it and then output the encoding, count and index data
  84  @tindex = sort by_entry @tindex;
  85 -print STDOUT "$encoding\n";
  86 -print STDOUT "$ne\n";
  87 +
  88 +print "$outfile\n";
  89 +open OUTFILE, ">$outfile" or die "ERROR: Can't open $outfile for writing!";
  90 +print OUTFILE "$encoding\n";
  91 +print OUTFILE "$ne\n";
  92  foreach $one (@tindex) {
  93 -    print STDOUT "$one\n";
  94 +    print OUTFILE "$one\n";
  95  }
  96 +close OUTFILE;
  97