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
|
--- misc/mythes-1.2.3.orig/th_gen_idx.pl
+++ misc/build/mythes-1.2.3/th_gen_idx.pl
@@ -1,11 +1,32 @@
-#!/usr/bin/perl
-
-# perl program to take a thesaurus structured text data file
-# and create the proper sorted index file (.idx)
+:
+eval 'exec perl -wS $0 ${1+"$@"}'
+ if 0;
+#*************************************************************************
+#
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# Copyright 2000, 2010 Oracle and/or its affiliates.
+#
+# OpenOffice.org - a multi-platform office productivity suite
+#
+# This file is part of OpenOffice.org.
+#
+# OpenOffice.org is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Lesser General Public License version 3
+# only, as published by the Free Software Foundation.
+#
+# OpenOffice.org is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU Lesser General Public License version 3 for more details
+# (a copy is included in the LICENSE file that accompanied this code).
#
-# typically invoked as follows:
-# cat th_en_US_new.dat | ./th_gen_idx.pl > th_en_US_new.idx
+# You should have received a copy of the GNU Lesser General Public License
+# version 3 along with OpenOffice.org. If not, see
+# <http://www.openoffice.org/license.html>
+# for a copy of the LGPLv3 License.
#
+#*************************************************************************
sub by_entry {
my ($aent, $aoff) = split('\|',$a);
@@ -13,6 +34,27 @@ sub by_entry {
$aent cmp $bent;
}
+#FIXME: someone may want "infile" or even parameter parsing
+sub get_outfile {
+ my $next_is_file = 0;
+ foreach ( @ARGV ) {
+ if ( $next_is_file ) {
+ return $_
+ }
+ if ( $_ eq "-o" ) {
+ $next_is_file = 1;
+ }
+ }
+ return "";
+}
+
+sub usage {
+ print "usage:\n";
+ print "$0 -o outfile < input\n";
+
+ exit 99;
+}
+
# main routine
my $ne = 0; # number of entries in index
my @tindex=(); # the index itself
@@ -24,6 +66,10 @@ my $nm=0; # number of meaning fo
my $meaning=""; # current meaning and synonyms
my $p; # misc uses
my $encoding; # encoding used by text file
+my $outfile = "";
+
+$outfile = get_outfile();
+usage() if ( $outfile eq "" );
# top line of thesaurus provides encoding
$encoding=<STDIN>;
@@ -51,9 +97,13 @@ while ($rec=<STDIN>){
# now we have all of the information
# so sort it and then output the encoding, count and index data
@tindex = sort by_entry @tindex;
-print STDOUT "$encoding\n";
-print STDOUT "$ne\n";
+
+print "$outfile\n";
+open OUTFILE, ">$outfile" or die "ERROR: Can't open $outfile for writing!";
+print OUTFILE "$encoding\n";
+print OUTFILE "$ne\n";
foreach $one (@tindex) {
- print STDOUT "$one\n";
+ print OUTFILE "$one\n";
}
+close OUTFILE;
|