<?php
-// $Id: spam.php,v 1.106 2007/01/11 15:51:12 henoheno Exp $
+// $Id: spam.php,v 1.122 2007/03/04 03:59:37 henoheno Exp $
// Copyright (C) 2006-2007 PukiWiki Developers Team
// License: GPL v2 or (at your option) any later version
+//
// Functions for Concept-work of spam-uri metrics
+//
// (PHP 4 >= 4.3.0): preg_match_all(PREG_OFFSET_CAPTURE): $method['uri_XXX'] related feature
if (! defined('SPAM_INI_FILE')) define('SPAM_INI_FILE', 'spam.ini.php');
preg_match_all(
// scheme://userinfo@host:port/path/or/pathinfo/maybefile.and?query=string#fragment
// Refer RFC3986 (Regex below is not strict)
- '#(\b[a-z][a-z0-9.+-]{1,8})://' . // 1: Scheme
+ '#(\b[a-z][a-z0-9.+-]{1,8}):/+' . // 1: Scheme
'(?:' .
'([^\s<>"\'\[\]/\#?@]*)' . // 2: Userinfo (Username)
'@)?' .
// NOTE: It's maybe danger to var_dump(result). [e.g. 'javascript:']
// [OK] http://victim.example.org/go?http%3A%2F%2Fnasty.example.org
// [OK] http://victim.example.org/http://nasty.example.org
+// TODO: link.toolbot.com, urlx.org
function spam_uri_pickup_preprocess($string = '')
{
if (! is_string($string)) return '';
// Domain exposure (See _preg_replace_callback_domain_exposure())
$string = preg_replace_callback(
array(
- // Something Google: http://www.google.com/supported_domains
- '#(http)://([a-z0-9.]+\.google\.[a-z]{2,3}(?:\.[a-z]{2})?)/' .
- '([ a-z0-9?=&.%_+-]+)' . // ?query=foo+bar hoge
+ '#(http)://' .
+ '(' .
+ // Something Google: http://www.google.com/supported_domains
+ '(?:[a-z0-9.]+\.)?google\.[a-z]{2,3}(?:\.[a-z]{2})?' .
+ '|' .
+ // AltaVista
+ '(?:[a-z0-9.]+\.)?altavista.com' .
+
+ ')' .
+ '/' .
+ '([a-z0-9?=&.%_/\'\\\+-]+)' . // path/?query=foo+bar+
'\bsite:([a-z0-9.%_-]+\.[a-z0-9.%_-]+)' . // site:nasty.example.com
//'()' . // Preserve or remove?
'#i',
// ---------------------
// Part One : Checker
+// Rough implementation of globbing
+//
+// USAGE: $regex = '/^' . generate_glob_regex('*.txt', '/') . '$/i';
+//
function generate_glob_regex($string = '', $divider = '/')
{
static $from = array(
function get_blocklist($list = '')
{
- static $regex;
-
- if (! isset($regex)) {
- $regex = array();
-
- // Sample
- if (FALSE) {
- $blocklist['badhost'] = array(
- //'*', // Deny all uri
- //'10.20.*.*', // 10.20.example.com also matches
- //'*.blogspot.com', // Blog services subdomains
- //array('blogspot.com', '*.blogspot.com')
- );
- foreach ($blocklist['badhost'] as $part) {
- $_part = is_array($part) ? implode('/', $part) : $part;
- $regex['badhost'][$_part] = '/^' . generate_glob_regex($part) . '$/i';
- }
- }
+ static $regexs;
- // Load
+ if (! isset($regexs)) {
+ $regexs = array();
if (file_exists(SPAM_INI_FILE)) {
$blocklist = array();
- require(SPAM_INI_FILE);
- foreach(array('goodhost', 'badhost') as $key) {
- if (! isset($blocklist[$key])) continue;
- foreach ($blocklist[$key] as $part) {
- $_part = is_array($part) ? implode('/', $part) : $part;
- $regex[$key][$_part] = '/^' . generate_glob_regex($part) . '$/i';
+ include(SPAM_INI_FILE);
+ // $blocklist['badhost'] = array(
+ // '*.blogspot.com', // Blog services's subdomains (only)
+ // 'IANA-examples' => '#^(?:.*\.)?example\.(?:com|net|org)$#',
+ // );
+ foreach(array('goodhost', 'badhost') as $_list) {
+ if (! isset($blocklist[$list])) continue;
+ foreach ($blocklist[$_list] as $key => $value) {
+ if (is_string($key)) {
+ $regexs[$_list][$key] = $value;
+ } else {
+ $regexs[$_list][$value] =
+ '/^(?:www\.)?' . generate_glob_regex($value, '/') . '$/i';
+ }
}
}
}
}
if ($list == '') {
- return $regex;
- } else if (isset($regex[$list])) {
- return $regex[$list];
+ return $regexs; // ALL
+ } else if (isset($regexs[$list])) {
+ return $regexs[$list];
} else {
return array();
}
}
if (empty($hosts)) return $result;
- foreach (get_blocklist('goodhost') as $_regex) {
- $hosts = preg_grep_invert($_regex, $hosts);
+ foreach (get_blocklist('goodhost') as $regex) {
+ $hosts = preg_grep_invert($regex, $hosts);
}
if (empty($hosts)) return $result;
$tmp = array();
- foreach (get_blocklist('badhost') as $part => $_regex) {
- $result[$part] = preg_grep($_regex, $hosts);
- if (empty($result[$part])) {
- unset($result[$part]);
+ foreach (get_blocklist('badhost') as $label => $regex) {
+ $result[$label] = preg_grep($regex, $hosts);
+ if (empty($result[$label])) {
+ unset($result[$label]);
} else {
- $hosts = array_diff($hosts, $result[$part]);
+ $hosts = array_diff($hosts, $result[$label]);
if ($asap) break;
}
}
$remains = & $progress['remains'];
$asap = isset($method['asap']);
- // Return if ...
+ // Recurse
if (is_array($target)) {
foreach($target as $str) {
// Recurse
}
foreach ($_remains as $key=>$value) {
foreach ($value as $_key=>$_value) {
- $remains[$key][$_key] = $_value;
+ if (is_int($_key)) {
+ $remains[$key][] = $_value;
+ } else {
+ $remains[$key][$_key] = $_value;
+ }
}
}
if ($asap && $is_spam) break;
}
// Return if ...
- if ($asap && $is_spam) {
- return $progress;
- }
- // URI Init
+ if ($asap && $is_spam) return $progress;
+
+ // URI: Pickup
$pickups = spam_uri_pickup($target, $method);
- if (empty($pickups)) {
- return $progress;
- }
+ //$remains['uri_pickup'] = & $pickups;
+
+ // Return if ...
+ if (empty($pickups)) return $progress;
// URI: Check quantity
$sum['quantity'] += count($pickups);
}
// Return if ...
- if ($asap && $is_spam) {
- return $progress;
- }
+ if ($asap && $is_spam) return $progress;
// Host: Uniqueness (uniq / non-uniq)
$hosts = array();
foreach ($pickups as $pickup) $hosts[] = & $pickup['host'];
$hosts = array_unique($hosts);
+ //$remains['uniqhost'] = & $hosts;
$sum['uniqhost'] += count($hosts);
if ((! $asap || ! $is_spam) && isset($method['non_uniqhost'])) {
$sum['non_uniqhost'] = $sum['quantity'] - $sum['uniqhost'];
}
// Return if ...
- if ($asap && $is_spam) {
- return $progress;
- }
+ if ($asap && $is_spam) return $progress;
// URI: Bad host
if ((! $asap || ! $is_spam) && isset($method['badhost'])) {
} else {
$badhost = is_badhost($hosts, $asap, $__remains);
if ($__remains) {
- $progress['remains']['badhost'] = array();
+ $remains['badhost'] = array();
foreach ($__remains as $value) {
- $progress['remains']['badhost'][$value] = TRUE;
+ $remains['badhost'][$value] = TRUE;
}
}
}
$summary['URI'] = get_script_uri() . '?' . rawurlencode($page);
$summary['USER_AGENT'] = TRUE;
$summary['REMOTE_ADDR'] = TRUE;
- pkwk_mail_notify($notify_subject, var_export($target, TRUE), $summary);
+ pkwk_mail_notify($notify_subject, var_export($target, TRUE), $summary, TRUE);
}
?>