1 | #!/usr/bin/perl -w
|
---|
2 |
|
---|
3 | ###########################################################################
|
---|
4 | #
|
---|
5 | # anonymiselog.pl -- anonymise a log file by MD5 hashing all IP addresses
|
---|
6 | #
|
---|
7 | # A component of the Greenstone digital library software
|
---|
8 | # from the New Zealand Digital Library Project at the
|
---|
9 | # University of Waikato, New Zealand.
|
---|
10 | #
|
---|
11 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
12 | #
|
---|
13 | # This program is free software; you can redistribute it and/or modify
|
---|
14 | # it under the terms of the GNU General Public License as published by
|
---|
15 | # the Free Software Foundation; either version 2 of the License, or
|
---|
16 | # (at your option) any later version.
|
---|
17 | #
|
---|
18 | # This program is distributed in the hope that it will be useful,
|
---|
19 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
20 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
21 | # GNU General Public License for more details.
|
---|
22 | #
|
---|
23 | # You should have received a copy of the GNU General Public License
|
---|
24 | # along with this program; if not, write to the Free Software
|
---|
25 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
26 | #
|
---|
27 | ###########################################################################
|
---|
28 |
|
---|
29 |
|
---|
30 | use MD5;
|
---|
31 |
|
---|
32 |
|
---|
33 | sub main
|
---|
34 | {
|
---|
35 | # Get the name of the log file to process
|
---|
36 | local $logfilename = shift(@_);
|
---|
37 |
|
---|
38 | # Check that the necessary arguments were supplied
|
---|
39 | if (!$logfilename) {
|
---|
40 | print STDERR "Usage: anonymiselog.pl <logfile-name>\n";
|
---|
41 | die "Error: Required argument missing.\n";
|
---|
42 | }
|
---|
43 |
|
---|
44 | # Open the log file
|
---|
45 | open(LOG_FILE, "<$logfilename") or die "Error: Could not open log file $logfilename.\n";
|
---|
46 |
|
---|
47 | # Open the output file
|
---|
48 | local $outfilename = $logfilename . ".anon";
|
---|
49 | open(OUT_FILE, ">$outfilename") or die "Error: Could not write file $outfilename.\n";
|
---|
50 |
|
---|
51 | # Create a new MD5 (RSA Data Security Inc. MD5 Message Digest) object
|
---|
52 | local $md5 = new MD5;
|
---|
53 |
|
---|
54 | # Process the log, one line at a time
|
---|
55 | local $entry = "";
|
---|
56 | while (<LOG_FILE>) {
|
---|
57 | local $line = $_;
|
---|
58 | # print "Line: $line";
|
---|
59 |
|
---|
60 | # If this line starts a new entry, process the previous one
|
---|
61 | if ($line =~ /^\//) {
|
---|
62 | print OUT_FILE &anonymise_log_entry($entry);
|
---|
63 | $entry = "";
|
---|
64 | }
|
---|
65 |
|
---|
66 | # Remove trailing whitespace, and skip blank lines
|
---|
67 | $line =~ s/(\s*)$//;
|
---|
68 | next if ($line =~ /^$/);
|
---|
69 |
|
---|
70 | $entry = $entry . $line;
|
---|
71 | }
|
---|
72 |
|
---|
73 | # Process the last entry
|
---|
74 | print OUT_FILE &anonymise_log_entry($entry);
|
---|
75 |
|
---|
76 | # All done
|
---|
77 | close(LOG_FILE);
|
---|
78 | close(OUT_FILE);
|
---|
79 | }
|
---|
80 |
|
---|
81 |
|
---|
82 | sub anonymise_log_entry
|
---|
83 | {
|
---|
84 | local $entry = shift(@_);
|
---|
85 | return "" if ($entry eq "");
|
---|
86 |
|
---|
87 | # Parse the IP address from the entry
|
---|
88 | $entry =~ /^\S+\s((\w|-|\.)+)\s\[/;
|
---|
89 | if (!defined($1)) {
|
---|
90 | print STDERR "Could not extract IP address from entry: $entry\n";
|
---|
91 | return "";
|
---|
92 | }
|
---|
93 |
|
---|
94 | # Casefold the IP address, hash using MD5, and take the last 16 characters
|
---|
95 | local $ipaddress = $1;
|
---|
96 | $ipaddress =~ tr/A-Z/a-z/;
|
---|
97 | local $hashedaddress = substr($md5->hexhash($ipaddress), -16);
|
---|
98 |
|
---|
99 | # Replace the IP address with the hashed value
|
---|
100 | $entry =~ s/$ipaddress/$hashedaddress/ig;
|
---|
101 |
|
---|
102 | # Parse the Greenstone user identifier (z variable) from the entry
|
---|
103 | $entry =~ /\sz=((\w|-|\.)+)/;
|
---|
104 | if (!defined($1)) {
|
---|
105 | print STDERR "No z variable in entry: $entry\n";
|
---|
106 | return "";
|
---|
107 | }
|
---|
108 |
|
---|
109 | # Casefold the Greenstone user ID, hash using MD5, and take the last 16 characters
|
---|
110 | local $gsuserid = $1;
|
---|
111 | $gsuserid =~ tr/A-Z/a-z/;
|
---|
112 | local $hasheduserid = substr($md5->hexhash($gsuserid), -16);
|
---|
113 |
|
---|
114 | # Replace the Greenstone user ID with the hashed value
|
---|
115 | $entry =~ s/$gsuserid/$hasheduserid/ig;
|
---|
116 | return $entry . "\n";
|
---|
117 | }
|
---|
118 |
|
---|
119 |
|
---|
120 | &main(@ARGV);
|
---|