#!/usr/bin/perl -wT

# script brodé à partir d'un exemple
# trouvé en ligne sur le forum CPAN
# http://cpanforum.com/posts/1304

# à utiliser sous la forme :
# logs_anonymes.pl fichier.log > sortie_anonyme.log

use strict;
$|=1;

use IP::Anonymous;
use Digest::MD5;

# 32 integers entre 0 et 255 (jot -r 32 0 255)
my @key = (135,229,13,26,29,84,46,37,231,95,211,
           196,243,11,87,5,23,217,173,214,66,241,
           164,67,132,149,161,151,114,137,238,75);

my $obj = new IP::Anonymous(@key);
my $md5 = Digest::MD5->new;

# seed pour le md5 
my $seed = '766326241f69b1244792587f556d02b8';

while(defined(my $line=<>)) {
    chomp $line;
    # les IP
    if($line =~ /\d{1,3}(?:\.\d{1,3}){3}/) {
        $line =~
            s/(\d{1,3}(?:\.\d{1,3}){3})/$obj->anonymize($1)/eg;
    }
    # les adresses email et messageID
    if($line =~ /[=< ][^@ ]*@/) {
        $line =~
            s/([=< ])([^@=< ]*@)/$1.$md5->add($seed)->add($2)->hexdigest."@"/eg;
    }
    # les hostnames
    if($line =~ /([=< @])(([a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9\-]*[a-zA-Z0-9])\.)*([a-zA-Z0-9][a-zA-Z0-9\-]*[a-zA-Z0-9])\.(AC|AD|AE|AERO|AF|AG|AI|AL|AM|AN|AO|AQ|AR|ARPA|AS|ASIA|AT|AU|AW|AX|AZ|BA|BB|BD|BE|BF|BG|BH|BI|BIZ|BJ|BM|BN|BO|BR|BS|BT|BV|BW|BY|BZ|CA|CAT|CC|CD|CF|CG|CH|CI|CK|CL|CM|CN|CO|COM|COOP|CR|CU|CV|CX|CY|CZ|DE|DJ|DK|DM|DO|DZ|EC|EDU|EE|EG|ER|ES|ET|EU|FI|FJ|FK|FM|FO|FR|GA|GB|GD|GE|GF|GG|GH|GI|GL|GM|GN|GOV|GP|GQ|GR|GS|GT|GU|GW|GY|HK|HM|HN|HR|HT|HU|ID|IE|IL|IM|IN|INFO|INT|IO|IQ|IR|IS|IT|JE|JM|JO|JOBS|JP|KE|KG|KH|KI|KM|KN|KP|KR|KW|KY|KZ|LA|LB|LC|LI|LK|LR|LS|LT|LU|LV|LY|MA|MC|MD|ME|MG|MH|MIL|MK|ML|MM|MN|MO|MOBI|MP|MQ|MR|MS|MT|MU|MUSEUM|MV|MW|MX|MY|MZ|NA|NAME|NC|NE|NET|NF|NG|NI|NL|NO|NP|NR|NU|NZ|OM|ORG|PA|PE|PF|PG|PH|PK|PL|PM|PN|PR|PRO|PS|PT|PW|PY|QA|RE|RO|RS|RU|RW|SA|SB|SC|SD|SE|SG|SH|SI|SJ|SK|SL|SM|SN|SO|SR|ST|SU|SV|SY|SZ|TC|TD|TEL|TF|TG|TH|TJ|TK|TL|TM|TN|TO|TP|TR|TRAVEL|TT|TV|TW|TZ|UA|UG|UK|US|UY|UZ|VA|VC|VE|VG|VI|VN|VU|WF|WS|XXX|YE|YT|ZA|ZM|ZW)/i ) {
        $line =~
            s/([=< @])((?:(?:[a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9\-]*[a-zA-Z0-9])\.)*)([a-zA-Z0-9][a-zA-Z0-9\-]*[a-zA-Z0-9])\.(AC|AD|AE|AERO|AF|AG|AI|AL|AM|AN|AO|AQ|AR|ARPA|AS|ASIA|AT|AU|AW|AX|AZ|BA|BB|BD|BE|BF|BG|BH|BI|BIZ|BJ|BM|BN|BO|BR|BS|BT|BV|BW|BY|BZ|CA|CAT|CC|CD|CF|CG|CH|CI|CK|CL|CM|CN|CO|COM|COOP|CR|CU|CV|CX|CY|CZ|DE|DJ|DK|DM|DO|DZ|EC|EDU|EE|EG|ER|ES|ET|EU|FI|FJ|FK|FM|FO|FR|GA|GB|GD|GE|GF|GG|GH|GI|GL|GM|GN|GOV|GP|GQ|GR|GS|GT|GU|GW|GY|HK|HM|HN|HR|HT|HU|ID|IE|IL|IM|IN|INFO|INT|IO|IQ|IR|IS|IT|JE|JM|JO|JOBS|JP|KE|KG|KH|KI|KM|KN|KP|KR|KW|KY|KZ|LA|LB|LC|LI|LK|LR|LS|LT|LU|LV|LY|MA|MC|MD|ME|MG|MH|MIL|MK|ML|MM|MN|MO|MOBI|MP|MQ|MR|MS|MT|MU|MUSEUM|MV|MW|MX|MY|MZ|NA|NAME|NC|NE|NET|NF|NG|NI|NL|NO|NP|NR|NU|NZ|OM|ORG|PA|PE|PF|PG|PH|PK|PL|PM|PN|PR|PRO|PS|PT|PW|PY|QA|RE|RO|RS|RU|RW|SA|SB|SC|SD|SE|SG|SH|SI|SJ|SK|SL|SM|SN|SO|SR|ST|SU|SV|SY|SZ|TC|TD|TEL|TF|TG|TH|TJ|TK|TL|TM|TN|TO|TP|TR|TRAVEL|TT|TV|TW|TZ|UA|UG|UK|US|UY|UZ|VA|VC|VE|VG|VI|VN|VU|WF|WS|XXX|YE|YT|ZA|ZM|ZW)/$1.$md5->add($seed)->add($2)->hexdigest.".".$3.".".$4/egi;
    }
    # suppression des HELO
    if($line =~ /(helo=<[^>]*>)/i ) {
        $line =~
            s/(helo=<[^>]*>)//gi;
    }
    
    print $line."\n";
}