|
|
|
@ -1,6 +1,6 @@
|
|
|
|
#!/usr/bin/perl -w
|
|
|
|
#!/usr/bin/perl -w
|
|
|
|
# $Id: extract.pl 490579 2005-12-22 12:32:17Z scripty $
|
|
|
|
# $Id: extract.pl 490579 2005-12-22 12:32:17Z scripty $
|
|
|
|
# This file is part of the KDE project
|
|
|
|
# This file is part of the TDE project
|
|
|
|
# Copyright (C) 2001 Daniel Naber <daniel.naber@t-online.de>
|
|
|
|
# Copyright (C) 2001 Daniel Naber <daniel.naber@t-online.de>
|
|
|
|
|
|
|
|
|
|
|
|
# This program is free software; you can redistribute it and/or
|
|
|
|
# This program is free software; you can redistribute it and/or
|
|
|
|
@ -20,7 +20,7 @@
|
|
|
|
# Extract information from WordNet data files - only useful for development.
|
|
|
|
# Extract information from WordNet data files - only useful for development.
|
|
|
|
# cat together all of WordNet's data.* files and call this script. As a second
|
|
|
|
# cat together all of WordNet's data.* files and call this script. As a second
|
|
|
|
# argument you can use a word frequency list as "Alphabetical frequency list of
|
|
|
|
# argument you can use a word frequency list as "Alphabetical frequency list of
|
|
|
|
# the whole corpus (lemmatized)" on http://www.comp.lancs.ac.uk/ucrel/bncfreq/flists.html
|
|
|
|
# the whole corpus (lemmatized)" on http://ucrel.lancs.ac.uk/bncfreq/flists.html
|
|
|
|
# This will remove all words whcih are not in the list, i.e. words that are rare.
|
|
|
|
# This will remove all words whcih are not in the list, i.e. words that are rare.
|
|
|
|
#
|
|
|
|
#
|
|
|
|
# Output of this script is:
|
|
|
|
# Output of this script is:
|
|
|
|
@ -93,35 +93,32 @@ sub prg()
|
|
|
|
close(IN);
|
|
|
|
close(IN);
|
|
|
|
|
|
|
|
|
|
|
|
print <<__EOF;
|
|
|
|
print <<__EOF;
|
|
|
|
1 This software and database is being provided to you, the LICENSEE, by
|
|
|
|
1 This software and database is being provided to you, the LICENSEE,
|
|
|
|
2 Princeton University under the following license. By obtaining, using
|
|
|
|
2 Princeton University under the following license. By obtaining, using
|
|
|
|
3 and/or copying this software and database, you agree that you have
|
|
|
|
2 and/or copying this software and database, you agree that you have read,
|
|
|
|
4 read, understood, and will comply with these terms and conditions.:
|
|
|
|
3 understood, and will comply with these terms and conditions.:
|
|
|
|
5
|
|
|
|
4
|
|
|
|
6 Permission to use, copy, modify and distribute this software and
|
|
|
|
5 Permission to use, copy, modify and distribute this software and database
|
|
|
|
7 database and its documentation for any purpose and without fee or
|
|
|
|
6 and its documentation for any purpose and without fee or royalty is hereby
|
|
|
|
8 royalty is hereby granted, provided that you agree to comply with
|
|
|
|
7 granted, provided that you agree to comply with the following copyright
|
|
|
|
9 the following copyright notice and statements, including the disclaimer,
|
|
|
|
8 notice and statements, including the disclaimer, and that the same appear
|
|
|
|
10 and that the same appear on ALL copies of the software, database and
|
|
|
|
9 on ALL copies of the software, database and documentation, including
|
|
|
|
11 documentation, including modifications that you make for internal
|
|
|
|
10 modifications that youmake for internal use or for distribution.
|
|
|
|
12 use or for distribution.
|
|
|
|
11
|
|
|
|
13
|
|
|
|
12 WordNet 3.0 Copyright 2006 by Princeton University. All rights reserved.
|
|
|
|
14 WordNet 1.7 Copyright 2001 by Princeton University. All rights reserved.
|
|
|
|
13
|
|
|
|
15
|
|
|
|
14 THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON UNIVERSITY
|
|
|
|
16 THIS SOFTWARE AND DATABASE IS PROVIDED "AS IS" AND PRINCETON
|
|
|
|
15 MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR IMPLIED. BY WAY OF
|
|
|
|
17 UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
|
|
|
|
16 EXAMPLE, BUT NOT LIMITATION, PRINCETON UNIVERSITY MAKES NO REPRESENTATIONS
|
|
|
|
18 IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PRINCETON
|
|
|
|
17 OR WARRANTIES OF MERCHANT- ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE
|
|
|
|
19 UNIVERSITY MAKES NO REPRESENTATIONS OR WARRANTIES OF MERCHANT-
|
|
|
|
18 OR THAT THE USE OF THE LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL
|
|
|
|
20 ABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE
|
|
|
|
19 NOT INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS.
|
|
|
|
21 OF THE LICENSED SOFTWARE, DATABASE OR DOCUMENTATION WILL NOT
|
|
|
|
20
|
|
|
|
22 INFRINGE ANY THIRD PARTY PATENTS, COPYRIGHTS, TRADEMARKS OR
|
|
|
|
21 The name of Princeton University or Princeton may not be used in advertising
|
|
|
|
23 OTHER RIGHTS.
|
|
|
|
22 or publicity pertaining to distribution of the software and/or database.
|
|
|
|
24
|
|
|
|
23 Title to copyright in this software, database and any associated documentation
|
|
|
|
25 The name of Princeton University or Princeton may not be used in
|
|
|
|
24 shall at all times remain with Princeton University and LICENSEE agrees to
|
|
|
|
26 advertising or publicity pertaining to distribution of the software
|
|
|
|
25 preserve same.
|
|
|
|
28 and/or database. Title to copyright in this software, database and
|
|
|
|
|
|
|
|
29 any associated documentation shall at all times remain with
|
|
|
|
|
|
|
|
30 Princeton University and LICENSEE agrees to preserve same.
|
|
|
|
|
|
|
|
__EOF
|
|
|
|
__EOF
|
|
|
|
# for each synset, find its hypernyms:
|
|
|
|
# for each synset, find its hypernyms:
|
|
|
|
open(IN, "<$filename") || die "Cannot open '$filename': $!";
|
|
|
|
open(IN, "<$filename") || die "Cannot open '$filename': $!";
|
|
|
|
|
Darrell Anderson
10 years ago