<?php
-// $Id: spam.php,v 1.153 2007/05/05 08:02:39 henoheno Exp $
+// $Id: spam.php,v 1.191 2007/06/24 03:13:09 henoheno Exp $
// Copyright (C) 2006-2007 PukiWiki Developers Team
// License: GPL v2 or (at your option) any later version
//
}
}
+// ----
+
+// Very roughly, shrink the lines of var_export()
+// NOTE: If the same data exists, it must be corrupted.
+function var_export_shrink($expression, $return = FALSE, $ignore_numeric_keys = FALSE)
+{
+ $result = var_export($expression, TRUE);
+
+ $result = preg_replace(
+ // Remove a newline and spaces
+ '# => \n *array \(#', ' => array (',
+ $result
+ );
+
+ if ($ignore_numeric_keys) {
+ $result =preg_replace(
+ // Remove numeric keys
+ '#^( *)[0-9]+ => #m', '$1',
+ $result
+ );
+ }
+
+ if ($return) {
+ return $result;
+ } else {
+ echo $result;
+ return NULL;
+ }
+}
+
// Remove redundant values from array()
function array_unique_recursive($array = array())
{
// References:
// http://www.freebsd.org/cgi/man.cgi?query=strings (Man-page of GNU strings)
// http://www.pcre.org/pcre.txt
-function strings($binary = '', $min_len = 4, $ignore_space = FALSE)
+// Note: mb_ereg_replace() is one of mbstring extension's functions
+// and need to init its encoding.
+function strings($binary = '', $min_len = 4, $ignore_space = FALSE, $multibyte = FALSE)
{
+ // String only
+ $binary = (is_array($binary) || $binary === TRUE) ? '' : strval($binary);
+
+ $regex = $ignore_space ?
+ '[^[:graph:] \t\n]+' : // Remove "\0" etc, and readable spaces
+ '[^[:graph:][:space:]]+'; // Preserve readable spaces if possible
+
+ $binary = $multibyte ?
+ mb_ereg_replace($regex, "\n", $binary) :
+ preg_replace('/' . $regex . '/s', "\n", $binary);
+
if ($ignore_space) {
$binary = preg_replace(
array(
- '/(?:[^[:graph:] \t\n]|[\r])+/s',
'/[ \t]{2,}/',
'/^[ \t]/m',
'/[ \t]$/m',
),
array(
- "\n",
' ',
'',
''
),
$binary);
- } else {
- $binary = preg_replace('/(?:[^[:graph:][:space:]]|[\r])+/s', "\n", $binary);
}
if ($min_len > 1) {
+ // The last character seems "\n" or not
+ $br = (! empty($binary) && $binary[strlen($binary) - 1] == "\n") ? "\n" : '';
+
$min_len = min(1024, intval($min_len));
- $binary =
- implode("\n",
- preg_grep('/^.{' . $min_len . ',}/S',
- explode("\n", $binary)
- )
- );
+ $regex = '/^.{' . $min_len . ',}/S';
+ $binary = implode("\n", preg_grep($regex, explode("\n", $binary))) . $br;
}
return $binary;
}
+// Reverse $string with specified delimiter
+function delimiter_reverse($string = 'foo.bar.example.com', $from_delim = '.', $to_delim = '.')
+{
+ if (! is_string($string) || ! is_string($from_delim) || ! is_string($to_delim))
+ return $string;
+
+ // com.example.bar.foo
+ return implode($to_delim, array_reverse(explode($from_delim, $string)));
+}
+
// ---------------------
// URI pickup
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)
'@)?' .
// 3: Host
'\[[0-9a-f:.]+\]' . '|' . // IPv6([colon-hex and dot]): RFC2732
'(?:[0-9]{1,3}\.){3}[0-9]{1,3}' . '|' . // IPv4(dot-decimal): 001.22.3.44
- '[a-z0-9.-]+' . // hostname(FQDN) : foo.example.org
+ '[a-z0-9_-][a-z0-9_.-]+[a-z0-9_-]' . // hostname(FQDN) : foo.example.org
')' .
'(?::([0-9]*))?' . // 4: Port
'((?:/+[^\s<>"\'\[\]/\#]+)*/+)?' . // 5: Directory path or path-info
return $result;
}
+// Preprocess: Removing uninterest part for URI detection
+function spam_uri_removing_hocus_pocus($binary = '', $method = array())
+{
+ $length = 4 ; // 'http'(1) and '://'(2) and 'fqdn'(1)
+ if (is_array($method)) {
+ // '<a'(2) or 'href='(5) or '>'(1) or '</a>'(4)
+ // '[uri'(4) or ']'(1) or '[/uri]'(6)
+ if (isset($method['area_anchor']) || isset($method['uri_anchor']) ||
+ isset($method['area_bbcode']) || isset($method['uri_bbcode']))
+ $length = 1; // Seems not effective
+ }
+
+ // Removing sequential spaces and too short lines
+ $binary = strings($binary, $length, TRUE, FALSE); // Multibyte NOT needed
+
+ // Remove words (has no '<>[]:') between spaces
+ $binary = preg_replace('/[ \t][\w.,()\ \t]+[ \t]/', ' ', $binary);
+
+ return $binary;
+}
+
// Preprocess: rawurldecode() and adding space(s) and something
// to detect/count some URIs _if possible_
// NOTE: It's maybe danger to var_dump(result). [e.g. 'javascript:']
// [OK] http://victim.example.org/nasty.example.org
// [OK] http://victim.example.org/go?http%3A%2F%2Fnasty.example.org
// [OK] http://victim.example.org/http://nasty.example.org
-function spam_uri_pickup_preprocess($string = '')
+function spam_uri_pickup_preprocess($string = '', $method = array())
{
if (! is_string($string)) return '';
- $string = rawurldecode($string);
+ $string = spam_uri_removing_hocus_pocus(rawurldecode($string), $method);
+ //var_dump(htmlspecialchars($string));
// Domain exposure (simple)
// http://victim.example.org/nasty.example.org/path#frag
// => http://nasty.example.org/?refer=victim.example.org and original
$string = preg_replace(
- '#http://' .
+ '#h?ttp://' .
'(' .
'ime\.nu' . '|' . // 2ch.net
'ime\.st' . '|' . // 2ch.net
$string
);
+ // Domain exposure (gate-big5)
+ // http://victim.example.org/gate/big5/nasty.example.org/path
+ // => http://nasty.example.org/?refer=victim.example.org and original
+ $string = preg_replace(
+ '#h?ttp://' .
+ '(' .
+ 'big5.51job.com' . '|' .
+ 'big5.china.com' . '|' .
+ 'big5.xinhuanet.com' . '|' .
+ ')' .
+ '/gate/big5' .
+ '/([a-z0-9.%_-]+\.[a-z0-9.%_-]+)' .
+ '#i', // nasty.example.org
+ 'http://$2/?refer=$1 $0', // Preserve $0 or remove?
+ $string
+ );
+
// Domain exposure (See _preg_replace_callback_domain_exposure())
$string = preg_replace_callback(
array(
$method = check_uri_spam_method();
}
- $string = spam_uri_pickup_preprocess($string);
+ $string = spam_uri_pickup_preprocess($string, $method);
$array = uri_pickup($string);
function get_blocklist($list = '')
{
- static $regexs;
+ static $regexes;
+
+ if ($list === NULL) {
+ $regexes = NULL; // Unset
+ return array();
+ }
- if (! isset($regexs)) {
- $regexs = array();
+ if (! isset($regexes)) {
+ $regexes = array();
if (file_exists(SPAM_INI_FILE)) {
$blocklist = array();
include(SPAM_INI_FILE);
// 'IANA-examples' => '#^(?:.*\.)?example\.(?:com|net|org)$#',
// );
if (isset($blocklist['list'])) {
- $regexs['list'] = & $blocklist['list'];
+ $regexes['list'] = & $blocklist['list'];
} else {
// Default
$blocklist['list'] = array(
if (! isset($blocklist[$_list])) continue;
foreach ($blocklist[$_list] as $key => $value) {
if (is_array($value)) {
- $regexs[$_list][$key] = array();
+ $regexes[$_list][$key] = array();
foreach($value as $_key => $_value) {
- get_blocklist_add($regexs[$_list][$key], $_key, $_value);
+ get_blocklist_add($regexes[$_list][$key], $_key, $_value);
}
} else {
- get_blocklist_add($regexs[$_list], $key, $value);
+ get_blocklist_add($regexes[$_list], $key, $value);
}
}
unset($blocklist[$_list]);
}
}
- if ($list == '') {
- return $regexs; // ALL
- } else if (isset($regexs[$list])) {
- return $regexs[$list];
- } else {
+ if ($list === '') {
+ return $regexes; // ALL
+ } else if (isset($regexes[$list])) {
+ return $regexes[$list];
+ } else {
return array();
}
}
return $blocked;
}
-// Simple example for badhost (not used now)
-function is_badhost($hosts = array(), $asap = TRUE, $bool = TRUE)
-{
- $list = get_blocklist('list');
- $blocked = blocklist_distiller($hosts, array_keys($list), $asap);
- foreach($list as $key=>$type){
- if (! $type) unset($blocked[$key]); // Ignore goodhost etc
- }
-
- return $bool ? ! empty($blocked) : $blocked;
-}
-
-
// Default (enabled) methods and thresholds (for content insertion)
function check_uri_spam_method($times = 1, $t_area = 0, $rule = TRUE)
{
foreach(array_keys($method) as $key) {
if (! isset($sum[$key])) $sum[$key] = 0;
}
+ if (! isset($sum['quantity'])) $sum['quantity'] = 0;
if (is_array($target)) {
foreach($target as $str) {
if ($asap && $is_spam) break;
// Merge only
- $blocked = array_merge_leaves($blocked, $_progress['blocked'], FALSE, FALSE);
- $hosts = array_merge_leaves($hosts, $_progress['hosts'], FALSE, FALSE);
+ $blocked = array_merge_recursive($blocked, $_progress['blocked']);
+ $hosts = array_merge_recursive($hosts, $_progress['hosts']);
}
// Unique values
$blocked = array_unique_recursive($blocked);
$hosts = array_unique_recursive($hosts);
- // Renumber numeric keys
- array_renumber_numeric_keys($blocked);
- array_renumber_numeric_keys($hosts);
-
// Recount $sum['badhost']
$sum['badhost'] = array_count_leaves($blocked);
return $count;
}
-// Merge two leaves' value
-function array_merge_leaves(& $array1, & $array2, $unique_values = TRUE, $renumber_numeric = TRUE)
+// An array-leaves to a flat array
+function array_flat_leaves($array, $unique = TRUE)
{
- $array = array_merge_recursive($array1, $array2);
+ if (! is_array($array)) return $array;
- // Redundant values (and keys) are vanished
- if ($unique_values) $array = array_unique_recursive($array);
+ $tmp = array();
+ foreach(array_keys($array) as $key) {
+ if (is_array($array[$key])) {
+ // Recurse
+ foreach(array_flat_leaves($array[$key]) as $_value) {
+ $tmp[] = $_value;
+ }
+ } else {
+ $tmp[] = & $array[$key];
+ }
+ }
- // All NUMERIC keys are always renumbered from 0
- if ($renumber_numeric) array_renumber_numeric_keys($array);
+ return $unique ? array_values(array_unique($tmp)) : $tmp;
+}
- return $array;
+// An array() to an array leaf
+function array_leaf($array = array('A', 'B', 'C.D'), $stem = FALSE, $edge = TRUE)
+{
+ if (! is_array($array)) return $array;
+
+ $leaf = array();
+ $tmp = & $leaf;
+ foreach($array as $arg) {
+ if (! is_string($arg) && ! is_int($arg)) continue;
+ $tmp[$arg] = array();
+ $parent = & $tmp;
+ $tmp = & $tmp[$arg];
+ }
+ if ($stem) {
+ $parent[key($parent)] = & $edge;
+ } else {
+ $parent = key($parent);
+ }
+
+ return $leaf; // array('A' => array('B' => 'C.D'))
}
// ---------------------
// Reporting
-// TODO: Don't show unused $method!
// Summarize $progress (blocked only)
function summarize_spam_progress($progress = array(), $blockedonly = FALSE)
{
return implode(', ', $tmp);
}
-// Very roughly, shrink the lines of var_export()
-// NOTE: If the same data exists, it must be corrupted.
-function var_export_shrink($expression, $return = FALSE)
-{
- $result =preg_replace(
- // Remove a newline and spaces
- '# => \n *array \(#', ' => array (',
- var_export($expression, TRUE)
- );
-
- if ($return) {
- return $result;
- } else {
- echo $result;
- return NULL;
- }
-}
-
function summarize_detail_badhost($progress = array())
{
- if (! isset($progress['is_spam']['badhost'])) return '';
+ if (! isset($progress['blocked']) || empty($progress['blocked'])) return '';
- return var_export_shrink($progress['blocked'], TRUE);
-}
+ // Flat per group
+ $blocked = array();
+ foreach($progress['blocked'] as $list => $lvalue) {
+ foreach($lvalue as $group => $gvalue) {
+ $flat = implode(', ', array_flat_leaves($gvalue));
+ if ($flat === $group) {
+ $blocked[$list][] = $flat;
+ } else {
+ $blocked[$list][$group] = $flat;
+ }
+ }
+ }
-// Reverse $string with specified delimiter
-function delimiter_reverse($string = 'foo.bar.example.com', $from_delim = '.', $to_delim = '.')
-{
- if (! is_string($string) || ! is_string($from_delim) || ! is_string($to_delim))
- return $string;
+ // Shrink per list
+ // From: 'A-1' => array('ie.to')
+ // To: 'A-1' => 'ie.to'
+ foreach($blocked as $list => $lvalue) {
+ if (is_array($lvalue) &&
+ count($lvalue) == 1 &&
+ is_numeric(key($lvalue))) {
+ $blocked[$list] = current($lvalue);
+ }
+ }
- // com.example.bar.foo
- return implode($to_delim, array_reverse(explode($from_delim, $string)));
+ return var_export_shrink($blocked, TRUE, TRUE);
}
function summarize_detail_newtral($progress = array())
! is_array($progress['hosts']) ||
empty($progress['hosts'])) return '';
- // Sort by domain
- $tmp = array();
+ // Generate a responsible $trie
+ $trie = array();
foreach($progress['hosts'] as $value) {
- $tmp[delimiter_reverse($value)] = $value;
+ // 'A.foo.bar.example.com'
+ $resp = whois_responsibility($value); // 'example.com'
+ if (empty($resp)) {
+ // One or more test, or do nothing here
+ $resp = strval($value);
+ $rest = '';
+ } else {
+ $rest = rtrim(substr($value, 0, - strlen($resp)), '.'); // 'A.foo.bar'
+ }
+ $trie = array_merge_recursive($trie, array($resp => array($rest => NULL)));
}
- ksort($tmp);
- return count($tmp) . ' (' .implode(', ', $tmp) . ')';
+ // Format: var_export_shrink() -like output
+ $result = array();
+ ksort_by_domain($trie);
+ foreach(array_keys($trie) as $key) {
+ ksort_by_domain($trie[$key]);
+ if (count($trie[$key]) == 1 && key($trie[$key]) == '') {
+ // Just one 'responsibility.example.com'
+ $result[] = ' \'' . $key . '\',';
+ } else {
+ // One subdomain-or-host, or several ones
+ $subs = array();
+ foreach(array_keys($trie[$key]) as $sub) {
+ if ($sub == '') {
+ $subs[] = $key;
+ } else {
+ $subs[] = $sub . '.' . $key;
+ }
+ }
+ $result[] = ' \'' . $key . '\' => \'' . implode(', ', $subs) . '\',';
+ }
+ unset($trie[$key]);
+ }
+ return
+ 'array (' . "\n" .
+ implode("\n", $result) . "\n" .
+ ')';
+}
+
+// ksort() by domain
+function ksort_by_domain(& $array)
+{
+ $sort = array();
+ foreach(array_keys($array) as $key) {
+ $sort[delimiter_reverse($key)] = $key;
+ }
+ ksort($sort, SORT_STRING);
+ $result = array();
+ foreach($sort as $key) {
+ $result[$key] = & $array[$key];
+ }
+ $array = $result;
+}
+
+// Check responsibility-root of the FQDN
+// 'foo.bar.example.com' => 'example.com' (.com has the last whois for it)
+// 'foo.bar.example.au' => 'example.au' (.au has the last whois for it)
+// 'foo.bar.example.edu.au' => 'example.edu.au' (.edu.au has the last whois for it)
+// 'foo.bar.example.act.edu.au' => 'example.act.edu.au' (.act.edu.au has the last whois for it)
+function whois_responsibility($fqdn = 'foo.bar.example.com', $parent = FALSE, $implicit = TRUE)
+{
+ // Domains who have 2nd and/or 3rd level domains
+ static $domain = array(
+
+ // ccTLD: Australia
+ // http://www.auda.org.au/
+ // NIC : http://www.aunic.net/
+ // Whois: http://www.ausregistry.com.au/
+ 'au' => array(
+ // .au Second Level Domains
+ // http://www.auda.org.au/domains/
+ 'asn' => TRUE,
+ 'com' => TRUE,
+ 'conf' => TRUE,
+ 'csiro' => TRUE,
+ 'edu' => array( // http://www.domainname.edu.au/
+ // Geographic
+ 'act' => TRUE,
+ 'nt' => TRUE,
+ 'nsw' => TRUE,
+ 'qld' => TRUE,
+ 'sa' => TRUE,
+ 'tas' => TRUE,
+ 'vic' => TRUE,
+ 'wa' => TRUE,
+ ),
+ 'gov' => array(
+ // Geographic
+ 'act' => TRUE, // Australian Capital Territory
+ 'nt' => TRUE, // Northern Territory
+ 'nsw' => TRUE, // New South Wales
+ 'qld' => TRUE, // Queensland
+ 'sa' => TRUE, // South Australia
+ 'tas' => TRUE, // Tasmania
+ 'vic' => TRUE, // Victoria
+ 'wa' => TRUE, // Western Australia
+ ),
+ 'id' => TRUE,
+ 'net' => TRUE,
+ 'org' => TRUE,
+ 'info' => TRUE,
+ ),
+
+ // ccTLD: Bahrain
+ // NIC : http://www.inet.com.bh/ (.bh policies not found)
+ // Whois: (Not available) http://www.inet.com.bh/
+ 'bh' => array(
+ // Observed
+ 'com' => TRUE,
+ 'edu' => TRUE,
+ 'gov' => TRUE,
+ 'org' => TRUE,
+ ),
+
+ // ccTLD: China
+ // NIC : http://www.cnnic.net.cn/en/index/
+ // Whois: http://ewhois.cnnic.cn/
+ 'cn' => array(
+ // Provisional Administrative Rules for Registration of Domain Names in China
+ // http://www.cnnic.net.cn/html/Dir/2003/11/27/1520.htm
+
+ // Organizational
+ 'ac' => TRUE,
+ 'com' => TRUE,
+ 'edu' => TRUE,
+ 'gov' => TRUE,
+ 'net' => TRUE,
+ 'org' => TRUE,
+
+ // Geographic
+ 'ah' => TRUE,
+ 'bj' => TRUE,
+ 'cq' => TRUE,
+ 'fj' => TRUE,
+ 'gd' => TRUE,
+ 'gs' => TRUE,
+ 'gx' => TRUE,
+ 'gz' => TRUE,
+ 'ha' => TRUE,
+ 'hb' => TRUE,
+ 'he' => TRUE,
+ 'hi' => TRUE,
+ 'hk' => TRUE,
+ 'hl' => TRUE,
+ 'hn' => TRUE,
+ 'jl' => TRUE,
+ 'js' => TRUE,
+ 'jx' => TRUE,
+ 'ln' => TRUE,
+ 'mo' => TRUE,
+ 'nm' => TRUE,
+ 'nx' => TRUE,
+ 'qh' => TRUE,
+ 'sc' => TRUE,
+ 'sd' => TRUE,
+ 'sh' => TRUE,
+ 'sn' => TRUE,
+ 'sx' => TRUE,
+ 'tj' => TRUE,
+ 'tw' => TRUE,
+ 'xj' => TRUE,
+ 'xz' => TRUE,
+ 'yn' => TRUE,
+ 'zj' => TRUE,
+ ),
+
+ // ccTLD: India
+ // NIC : http://www.inregistry.in/
+ // Whois: http://www.inregistry.in/whois_search/
+ 'in' => array(
+ // Policies http://www.inregistry.in/policies/
+ 'ac' => TRUE,
+ 'co' => TRUE,
+ 'firm' => TRUE,
+ 'gen' => TRUE,
+ 'gov' => TRUE,
+ 'ind' => TRUE,
+ 'mil' => TRUE,
+ 'net' => TRUE,
+ 'org' => TRUE,
+ 'res' => TRUE,
+ // Reserved Names by the government (for the 2nd level)
+ // http://www.inregistry.in/policies/reserved_names
+ ),
+
+ // ccTLD: South Korea
+ // NIC : http://www.nic.or.kr/english/
+ // Whois: http://whois.nida.or.kr/english/
+ 'kr' => array(
+ // .kr domain policy [appendix 1] : Qualifications for Second Level Domains
+ // http://domain.nida.or.kr/eng/policy.jsp
+
+ // Organizational
+ 'co' => TRUE,
+ 'ne ' => TRUE,
+ 'or ' => TRUE,
+ 're ' => TRUE,
+ 'pe' => TRUE,
+ 'go ' => TRUE,
+ 'mil' => TRUE,
+ 'ac' => TRUE,
+ 'hs' => TRUE,
+ 'ms' => TRUE,
+ 'es' => TRUE,
+ 'sc' => TRUE,
+ 'kg' => TRUE,
+
+ // Geographic
+ 'seoul' => TRUE,
+ 'busan' => TRUE,
+ 'daegu' => TRUE,
+ 'incheon' => TRUE,
+ 'gwangju' => TRUE,
+ 'daejeon' => TRUE,
+ 'ulsan' => TRUE,
+ 'gyeonggi' => TRUE,
+ 'gangwon' => TRUE,
+ 'chungbuk' => TRUE,
+ 'chungnam' => TRUE,
+ 'jeonbuk' => TRUE,
+ 'jeonnam' => TRUE,
+ 'gyeongbuk' => TRUE,
+ 'gyeongnam' => TRUE,
+ 'jeju' => TRUE,
+ ),
+
+ // ccTLD: Japan
+ // NIC : http://jprs.co.jp/en/
+ // Whois: http://whois.jprs.jp/en/
+ 'jp' => array(
+ // Guide to JP Domain Name
+ // http://jprs.co.jp/en/jpdomain.html
+
+ // Organizational
+ 'ac' => TRUE,
+ 'ad' => TRUE,
+ 'co' => TRUE,
+ 'ed' => TRUE,
+ 'go' => TRUE,
+ 'gr' => TRUE,
+ 'lg' => TRUE,
+ 'ne' => TRUE,
+ 'or' => TRUE,
+
+ // Geographic
+ //
+ // Examples for 3rd level domains
+ //'kumamoto' => array(
+ // // http://www.pref.kumamoto.jp/link/list.asp#4
+ // 'amakusa' => TRUE,
+ // 'hitoyoshi' => TRUE,
+ // 'jonan' => TRUE,
+ // 'kumamoto' => TRUE,
+ // ...
+ //),
+ 'aichi' => TRUE,
+ 'akita' => TRUE,
+ 'aomori' => TRUE,
+ 'chiba' => TRUE,
+ 'ehime' => TRUE,
+ 'fukui' => TRUE,
+ 'fukuoka' => TRUE,
+ 'fukushima' => TRUE,
+ 'gifu' => TRUE,
+ 'gunma' => TRUE,
+ 'hiroshima' => TRUE,
+ 'hokkaido' => TRUE,
+ 'hyogo' => TRUE,
+ 'ibaraki' => TRUE,
+ 'ishikawa' => TRUE,
+ 'iwate' => TRUE,
+ 'kagawa' => TRUE,
+ 'kagoshima' => TRUE,
+ 'kanagawa' => TRUE,
+ 'kawasaki' => TRUE,
+ 'kitakyushu'=> TRUE,
+ 'kobe' => TRUE,
+ 'kochi' => TRUE,
+ 'kumamoto' => TRUE,
+ 'kyoto' => TRUE,
+ 'mie' => TRUE,
+ 'miyagi' => TRUE,
+ 'miyazaki' => TRUE,
+ 'nagano' => TRUE,
+ 'nagasaki' => TRUE,
+ 'nagoya' => TRUE,
+ 'nara' => TRUE,
+ 'niigata' => TRUE,
+ 'oita' => TRUE,
+ 'okayama' => TRUE,
+ 'okinawa' => TRUE,
+ 'osaka' => TRUE,
+ 'saga' => TRUE,
+ 'saitama' => TRUE,
+ 'sapporo' => TRUE,
+ 'sendai' => TRUE,
+ 'shiga' => TRUE,
+ 'shimane' => TRUE,
+ 'shizuoka' => TRUE,
+ 'tochigi' => TRUE,
+ 'tokushima' => TRUE,
+ 'tokyo' => TRUE,
+ 'tottori' => TRUE,
+ 'toyama' => TRUE,
+ 'wakayama' => TRUE,
+ 'yamagata' => TRUE,
+ 'yamaguchi' => TRUE,
+ 'yamanashi' => TRUE,
+ 'yokohama' => TRUE,
+ ),
+
+ // ccTLD: Mexico
+ // NIC : http://www.nic.mx/
+ // Whois: http://www.nic.mx/es/Busqueda.Who_Is
+ 'mx' => array(
+ // Politicas Generales de Nombres de Dominio
+ // http://www.nic.mx/es/Politicas?CATEGORY=INDICE
+ 'com' => TRUE,
+ 'edu' => TRUE,
+ 'gob' => TRUE,
+ 'net' => TRUE,
+ 'org' => TRUE,
+ ),
+
+ // ccTLD: Russia
+ // NIC : http://www.cctld.ru/en/
+ // Whois: http://www.ripn.net:8080/nic/whois/en/
+ 'ru' => array(
+ // List of Reserved second-level Domain Names
+ // http://www.cctld.ru/en/doc/detail.php?id21=20&i21=2
+
+ // Organizational
+ 'ac' => TRUE,
+ 'com' => TRUE,
+ 'edu' => TRUE,
+ 'gov' => TRUE,
+ 'int' => TRUE,
+ 'mil' => TRUE,
+ 'net' => TRUE,
+ 'org' => TRUE,
+ 'pp' => TRUE,
+ //'test' => TRUE,
+
+ // Geographic
+ 'adygeya' => TRUE,
+ 'altai' => TRUE,
+ 'amur' => TRUE,
+ 'amursk' => TRUE,
+ 'arkhangelsk' => TRUE,
+ 'astrakhan' => TRUE,
+ 'baikal' => TRUE,
+ 'bashkiria' => TRUE,
+ 'belgorod' => TRUE,
+ 'bir' => TRUE,
+ 'bryansk' => TRUE,
+ 'buryatia' => TRUE,
+ 'cbg' => TRUE,
+ 'chel' => TRUE,
+ 'chelyabinsk' => TRUE,
+ 'chita' => TRUE,
+ 'chukotka' => TRUE,
+ 'chuvashia' => TRUE,
+ 'cmw' => TRUE,
+ 'dagestan' => TRUE,
+ 'dudinka' => TRUE,
+ 'e-burg' => TRUE,
+ 'fareast' => TRUE,
+ 'grozny' => TRUE,
+ 'irkutsk' => TRUE,
+ 'ivanovo' => TRUE,
+ 'izhevsk' => TRUE,
+ 'jamal' => TRUE,
+ 'jar' => TRUE,
+ 'joshkar-ola' => TRUE,
+ 'k-uralsk' => TRUE,
+ 'kalmykia' => TRUE,
+ 'kaluga' => TRUE,
+ 'kamchatka' => TRUE,
+ 'karelia' => TRUE,
+ 'kazan' => TRUE,
+ 'kchr' => TRUE,
+ 'kemerovo' => TRUE,
+ 'khabarovsk' => TRUE,
+ 'khakassia' => TRUE,
+ 'khv' => TRUE,
+ 'kirov' => TRUE,
+ 'kms' => TRUE,
+ 'koenig' => TRUE,
+ 'komi' => TRUE,
+ 'kostroma' => TRUE,
+ 'krasnoyarsk' => TRUE,
+ 'kuban' => TRUE,
+ 'kurgan' => TRUE,
+ 'kursk' => TRUE,
+ 'kustanai' => TRUE,
+ 'kuzbass' => TRUE,
+ 'lipetsk' => TRUE,
+ 'magadan' => TRUE,
+ 'magnitka' => TRUE,
+ 'mari-el' => TRUE,
+ 'mari' => TRUE,
+ 'marine' => TRUE,
+ 'mordovia' => TRUE,
+ 'mosreg' => TRUE,
+ 'msk' => TRUE,
+ 'murmansk' => TRUE,
+ 'mytis' => TRUE,
+ 'nakhodka' => TRUE,
+ 'nalchik' => TRUE,
+ 'nkz' => TRUE,
+ 'nnov' => TRUE,
+ 'norilsk' => TRUE,
+ 'nov' => TRUE,
+ 'novosibirsk' => TRUE,
+ 'nsk' => TRUE,
+ 'omsk' => TRUE,
+ 'orenburg' => TRUE,
+ 'oryol' => TRUE,
+ 'oskol' => TRUE,
+ 'palana' => TRUE,
+ 'penza' => TRUE,
+ 'perm' => TRUE,
+ 'pskov' => TRUE,
+ 'ptz' => TRUE,
+ 'pyatigorsk' => TRUE,
+ 'rnd' => TRUE,
+ 'rubtsovsk' => TRUE,
+ 'ryazan' => TRUE,
+ 'sakhalin' => TRUE,
+ 'samara' => TRUE,
+ 'saratov' => TRUE,
+ 'simbirsk' => TRUE,
+ 'smolensk' => TRUE,
+ 'snz' => TRUE,
+ 'spb' => TRUE,
+ 'stavropol' => TRUE,
+ 'stv' => TRUE,
+ 'surgut' => TRUE,
+ 'syzran' => TRUE,
+ 'tambov' => TRUE,
+ 'tatarstan' => TRUE,
+ 'tom' => TRUE,
+ 'tomsk' => TRUE,
+ 'tsaritsyn' => TRUE,
+ 'tsk' => TRUE,
+ 'tula' => TRUE,
+ 'tuva' => TRUE,
+ 'tver' => TRUE,
+ 'tyumen' => TRUE,
+ 'udm' => TRUE,
+ 'udmurtia' => TRUE,
+ 'ulan-ude' => TRUE,
+ 'vdonsk' => TRUE,
+ 'vladikavkaz' => TRUE,
+ 'vladimir' => TRUE,
+ 'vladivostok' => TRUE,
+ 'volgograd' => TRUE,
+ 'vologda' => TRUE,
+ 'voronezh' => TRUE,
+ 'vrn' => TRUE,
+ 'vyatka' => TRUE,
+ 'yakutia' => TRUE,
+ 'yamal' => TRUE,
+ 'yaroslavl' => TRUE,
+ 'yekaterinburg' => TRUE,
+ 'yuzhno-sakhalinsk' => TRUE,
+ 'zgrad' => TRUE,
+ ),
+
+ // ccTLD: Seychelles
+ // NIC : http://www.nic.sc/
+ // Whois: (Not available)
+ 'sc' => array(
+ // http://www.nic.sc/policies.html
+ 'com' => TRUE,
+ 'edu' => TRUE,
+ 'gov' => TRUE,
+ 'net' => TRUE,
+ 'org' => TRUE,
+ ),
+
+ // ccTLD: Taiwan
+ // NIC : http://www.twnic.net.tw/
+ // Whois: http://www.twnic.net.tw/
+ 'tw' => array(
+ // Guidelines for Administration of Domain Name Registration
+ // http://www.twnic.net.tw/english/dn/dn_02.htm
+ // II. Types of TWNIC Domain Names and Application Requirements
+ // http://www.twnic.net.tw/english/dn/dn_02_b.htm
+ 'club' => TRUE,
+ 'com' => TRUE,
+ 'ebiz' => TRUE,
+ 'edu' => TRUE,
+ 'game' => TRUE,
+ 'gov' => TRUE,
+ 'idv' => TRUE,
+ 'mil' => TRUE,
+ 'net' => TRUE,
+ 'org' => TRUE,
+ // Reserved words for the 2nd level
+ // http://mydn.twnic.net.tw/en/dn02/INDEX.htm
+ ),
+
+ // ccTLD: Tanzania
+ // NIC : http://www.psg.com/dns/tz/
+ // Whois: (Not available)
+ 'tz' => array(
+ // TZ DOMAIN NAMING STRUCTURE
+ // http://www.psg.com/dns/tz/tz.txt
+ 'ac' => TRUE,
+ 'co' => TRUE,
+ 'go' => TRUE,
+ 'ne' => TRUE,
+ 'or' => TRUE,
+ ),
+
+ // ccTLD: Ukraine
+ // NIC : http://www.nic.net.ua/
+ // Whois: http://whois.com.ua/
+ 'ua' => array(
+ // policy for alternative 2nd level domain names (a2ld)
+ // http://www.nic.net.ua/doc/a2ld
+ // http://whois.com.ua/
+ 'cherkassy' => TRUE,
+ 'chernigov' => TRUE,
+ 'chernovtsy' => TRUE,
+ 'ck' => TRUE,
+ 'cn' => TRUE,
+ 'com' => TRUE,
+ 'crimea' => TRUE,
+ 'cv' => TRUE,
+ 'dn' => TRUE,
+ 'dnepropetrovsk' => TRUE,
+ 'donetsk' => TRUE,
+ 'dp' => TRUE,
+ 'edu' => TRUE,
+ 'gov' => TRUE,
+ 'if' => TRUE,
+ 'ivano-frankivsk' => TRUE,
+ 'kh' => TRUE,
+ 'kharkov' => TRUE,
+ 'kherson' => TRUE,
+ 'kiev' => TRUE,
+ 'kirovograd' => TRUE,
+ 'km' => TRUE,
+ 'kr' => TRUE,
+ 'ks' => TRUE,
+ 'lg' => TRUE,
+ 'lugansk' => TRUE,
+ 'lutsk' => TRUE,
+ 'lviv' => TRUE,
+ 'mk' => TRUE,
+ 'net' => TRUE,
+ 'nikolaev' => TRUE,
+ 'od' => TRUE,
+ 'odessa' => TRUE,
+ 'org' => TRUE,
+ 'pl' => TRUE,
+ 'poltava' => TRUE,
+ 'rovno' => TRUE,
+ 'rv' => TRUE,
+ 'sebastopol' => TRUE,
+ 'sumy' => TRUE,
+ 'te' => TRUE,
+ 'ternopil' => TRUE,
+ 'uz' => TRUE,
+ 'uzhgorod' => TRUE,
+ 'vinnica' => TRUE,
+ 'vn' => TRUE,
+ 'zaporizhzhe' => TRUE,
+ 'zhitomir' => TRUE,
+ 'zp' => TRUE,
+ 'zt' => TRUE,
+ ),
+
+ // ccTLD: United Kingdom
+ // NIC : http://www.nic.uk/
+ 'uk' => array(
+ // Second Level Domains
+ // http://www.nic.uk/registrants/aboutdomainnames/sld/
+ 'co' => TRUE,
+ 'ltd' => TRUE,
+ 'me' => TRUE,
+ 'net' => TRUE,
+ 'nic' => TRUE,
+ 'org' => TRUE,
+ 'plc' => TRUE,
+ 'sch' => TRUE,
+
+ // Delegated Second Level Domains
+ // http://www.nic.uk/registrants/aboutdomainnames/sld/delegated/
+ 'ac' => TRUE,
+ 'gov' => TRUE,
+ 'mil' => TRUE,
+ 'mod' => TRUE,
+ 'nhs' => TRUE,
+ 'police' => TRUE,
+ ),
+
+ // ccTLD: United States of America
+ // NIC : http://nic.us/
+ // Whois: http://whois.us/
+ 'us' => array(
+ // See RFC1480
+
+ // Organizational
+ 'dni',
+ 'fed',
+ 'isa',
+ 'kids',
+ 'nsn',
+
+ // Geographical
+ // United States Postal Service: State abbreviations (for postal codes)
+ // http://www.usps.com/ncsc/lookups/abbreviations.html
+ 'ak' => TRUE, // Alaska
+ 'al' => TRUE, // Alabama
+ 'ar' => TRUE, // Arkansas
+ 'as' => TRUE, // American samoa
+ 'az' => TRUE, // Arizona
+ 'ca' => TRUE, // California
+ 'co' => TRUE, // Colorado
+ 'ct' => TRUE, // Connecticut
+ 'dc' => TRUE, // District of Columbia
+ 'de' => TRUE, // Delaware
+ 'fl' => TRUE, // Florida
+ 'fm' => TRUE, // Federated states of Micronesia
+ 'ga' => TRUE, // Georgia
+ 'gu' => TRUE, // Guam
+ 'hi' => TRUE, // Hawaii
+ 'ia' => TRUE, // Iowa
+ 'id' => TRUE, // Idaho
+ 'il' => TRUE, // Illinois
+ 'in' => TRUE, // Indiana
+ 'ks' => TRUE, // Kansas
+ 'ky' => TRUE, // Kentucky
+ 'la' => TRUE, // Louisiana
+ 'ma' => TRUE, // Massachusetts
+ 'md' => TRUE, // Maryland
+ 'me' => TRUE, // Maine
+ 'mh' => TRUE, // Marshall Islands
+ 'mi' => TRUE, // Michigan
+ 'mn' => TRUE, // Minnesota
+ 'mo' => TRUE, // Missouri
+ 'mp' => TRUE, // Northern mariana islands
+ 'ms' => TRUE, // Mississippi
+ 'mt' => TRUE, // Montana
+ 'nc' => TRUE, // North Carolina
+ 'nd' => TRUE, // North Dakota
+ 'ne' => TRUE, // Nebraska
+ 'nh' => TRUE, // New Hampshire
+ 'nj' => TRUE, // New Jersey
+ 'nm' => TRUE, // New Mexico
+ 'nv' => TRUE, // Nevada
+ 'ny' => TRUE, // New York
+ 'oh' => TRUE, // Ohio
+ 'ok' => TRUE, // Oklahoma
+ 'or' => TRUE, // Oregon
+ 'pa' => TRUE, // Pennsylvania
+ 'pr' => TRUE, // Puerto Rico
+ 'pw' => TRUE, // Palau
+ 'ri' => TRUE, // Rhode Island
+ 'sc' => TRUE, // South Carolina
+ 'sd' => TRUE, // South Dakota
+ 'tn' => TRUE, // Tennessee
+ 'tx' => TRUE, // Texas
+ 'ut' => TRUE, // Utah
+ 'va' => TRUE, // Virginia
+ 'vi' => TRUE, // Virgin Islands
+ 'vt' => TRUE, // Vermont
+ 'wa' => TRUE, // Washington
+ 'wi' => TRUE, // Wisconsin
+ 'wv' => TRUE, // West Virginia
+ 'wy' => TRUE, // Wyoming
+ ),
+
+ // ccTLD: South Africa
+ // NIC : http://www.zadna.org.za/
+ // Whois:
+ // ac.za http://www.tenet.ac.za/cgi/cgi_domainquery.exe
+ // co.za http://co.za/whois.shtml
+ // gov.za http://dnsadmin.gov.za/
+ // org.za http://www.org.za/
+ 'za' => array(
+ // Second-level subdomains of .ZA
+ // http://www.zadna.org.za/slds.html
+ 'ac' => TRUE,
+ 'city' => TRUE,
+ 'co' => TRUE,
+ 'edu' => TRUE,
+ 'gov' => TRUE,
+ 'law' => TRUE,
+ 'mil' => TRUE,
+ 'nom' => TRUE,
+ 'org' => TRUE,
+ 'school' => array(
+ // Provincial Domains
+ // http://www.esn.org.za/dns/
+ 'ecape' => TRUE,
+ 'fs.' => TRUE,
+ 'gp' => TRUE,
+ 'kzn' => TRUE,
+ 'lp' => TRUE,
+ 'mpm' => TRUE,
+ 'ncape' => TRUE,
+ 'nw' => TRUE,
+ 'wcape' => TRUE,
+ ),
+ ),
+ );
+
+ if (! is_string($fqdn)) return '';
+ if (is_ip($fqdn)) return $fqdn;
+
+ $result = array();
+ $dcursor = & $domain;
+ $array = array_reverse(explode('.', $fqdn));
+ $i = 0;
+ while(TRUE) {
+ if (! isset($array[$i])) break;
+ $acursor = $array[$i];
+ if (is_array($dcursor) && isset($dcursor[$acursor])) {
+ $result[] = & $array[$i];
+ $dcursor = & $dcursor[$acursor];
+ } else {
+ if (! $parent && isset($acursor)) {
+ $result[] = & $array[$i]; // Whois servers must know this subdomain
+ }
+ break;
+ }
+ ++$i;
+ }
+
+ // Implicit responsibility: Top-Level-Domains must not be yours
+ // 'bar.foo.something' => 'foo.something'
+ if ($implicit && count($result) == 1 && count($array) > 1) {
+ $result[] = & $array[1];
+ }
+
+ return $result ? implode('.', array_reverse($result)) : '';
}
// ---------------------
// Exit
+// Freeing memories
+function spam_dispose()
+{
+ get_blocklist(NULL);
+}
+
// Common bahavior for blocking
// NOTE: Call this function from various blocking feature, to disgueise the reason 'why blocked'
function spam_exit($mode = '', $data = array())
{
+ $exit = TRUE;
+
switch ($mode) {
- case '': echo("\n"); break;
+ case '':
+ echo("\n");
+ break;
case 'dump':
echo('<pre>' . "\n");
echo htmlspecialchars(var_export($data, TRUE));
break;
};
- // Force exit
- exit;
+ if ($exit) exit; // Force exit
}
{
$progress = check_uri_spam($target, $method);
- if (! empty($progress['is_spam'])) {
- // Mail to administrator(s)
- pkwk_spamnotify($action, $page, $target, $progress, $method);
+ if (empty($progress['is_spam'])) {
+ spam_dispose();
+ } else {
- // Exit
+// TODO: detect encoding from $target for mbstring functions
+// $tmp = array();
+// foreach(array_keys($target) as $key) {
+// $tmp[strings($key, 0, FALSE, TRUE)] = strings($target[$key], 0, FALSE, TRUE); // Removing "\0" etc
+// }
+// $target = & $tmp;
+
+ pkwk_spamnotify($action, $page, $target, $progress, $method);
spam_exit($exitmode, $progress);
}
}