Split grml-scripts into grml-scripts and grml-scripts-core

[grml-scripts-core.git] / usr_bin / find-hidden-word-text

diff --git a/usr_bin/find-hidden-word-text b/usr_bin/find-hidden-word-text
deleted file mode 100755 (executable)
index 7612e5e..0000000
--- a/usr_bin/find-hidden-word-text
+++ /dev/null
@@ -1,94 +0,0 @@
-#!/usr/bin/perl -w
-=head1 NAME
-
-find-hidden-word-text - find hidden text in MS Word documents
-
-=head1 SYNOPSIS
-
-find-hidden-word-text word.doc > hidden.txt
-
-=head1 DESCRIPTION
-
-This is a command-line UNIX tool to ease the task of discovering hidden text
-in MS Word documents. 
-
-More specifically, it is an implementation of Method 2 from Simon Byers'
-paper, _Scalable Exploitation of, and Responses to Information Leakage
-Through Hidden Data in Published Documents_, at
-<URL:http://www.user-agent.org/word_docs.pdf>.
-
-This goes a little further in that it removes some common 'noise' strings,
-like 'Word.Document.8', 'Title', 'PAGE', 'Microsoft Word Document' and
-the like.  It will also remove any strings that do not contain at least
-1 whitespace character.
-
-=head1 PREREQUISITES
-
-This tool requires antiword be installed.
-
-=head1 AUTHOR
-
-Justin Mason, C<jm dash wordtext at jmason dot org>
-
-=head1 VERSION
-
-1.0 Aug 15 2003 jm
-
-=cut
-
-my $print_names = 0;
-if (scalar @ARGV > 1) { $print_names = 1; }
-
-foreach my $file (@ARGV) {
-  if ($print_names) {
-    print "\n$file\n\n";
-  }
-
-  open (IN, "antiword -t $file |") or die "cannot run antiword";
-  my $aw = join ('', <IN>);
-  close IN or die "cannot run antiword -t $file";
-
-  open (IN, "strings $file |") or die "cannot run strings";
-  my $str = join ('', <IN>);
-  close IN;
-
-  # normalize the antiword version
-  $aw =~ s/\s+/ /gs;
-
-  # get each string from strings, and see if we can find it in the "visible"
-  # text from antiword
-  my %count = ();
-  foreach (split (/\n/, $str)) {
-    s/\s+/ /g; s/^ //gs; s/ $//gs;
-    next if ($aw =~ /\Q$_\E/);
-
-    # killfile.
-    # skip almost-entirely non-alpha 4-byte snippets
-    #next if /^(?:\W\w\W\W|\W\W\w\W|\w\W{3,3}|\W{4,4}|\W{3,3}\w)$/;
-
-    next if (!/ /);    # no spaces!
-
-    # skip 4-to-6-byte snippets with 1 nonalpha and no spaces
-    #next if (/^\S{4,6}$/ && /\W/);
-
-    # common word droppings
-    next if /^\s*PAGE\s*$/;
-    #next if /^Word.Document.\d$/;
-    next if /^Microsoft Word 9.0$/;
-    next if /^Microsoft Word Document$/;
-    #next if /^Normal$/;
-    #next if /^Title$/;
-    #next if /^MSWordDoc$/;
-    next if /^Click to edit Master text styles$/;
-    next if /^Click to edit Master title style$/;
-    next if /^Embedded OLE Servers$/;
-
-    $count{$_}++;
-  }
-
-# output the strings and their counts
-  foreach (sort keys %count) {
-    my $cnt = $count{$_};
-    print "$cnt|$_\n";
-  }
-}