<?php
-// $Id: spam.php,v 1.175 2007/06/11 14:28:07 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
//
// NOTE: If the same data exists, it must be corrupted.
function var_export_shrink($expression, $return = FALSE, $ignore_numeric_keys = FALSE)
{
- $result =preg_replace(
+ $result = var_export($expression, TRUE);
+
+ $result = preg_replace(
// Remove a newline and spaces
'# => \n *array \(#', ' => array (',
- var_export($expression, TRUE)
+ $result
);
if ($ignore_numeric_keys) {
// 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 {
- // Remove "\0" etc. Preserve readable spaces if possible.
- $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));
$regex = '/^.{' . $min_len . ',}/S';
- if (is_array($binary)) {
- foreach(array_keys($binary) as $key) {
- $binary[$key] = implode("\n", preg_grep($regex, explode("\n", $binary[$key])));
- }
- } else {
- $binary = implode("\n", preg_grep($regex, explode("\n", $binary)));
- }
+ $binary = implode("\n", preg_grep($regex, explode("\n", $binary))) . $br;
}
return $binary;
// 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][a-z0-9.-]+[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
$method = check_uri_spam_method();
}
- $string = spam_uri_pickup_preprocess($string);
+ $string = spam_uri_pickup_preprocess($string, $method);
$array = uri_pickup($string);
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 $str) {
! is_array($progress['hosts']) ||
empty($progress['hosts'])) return '';
- $result = '';
- if (FALSE) {
- // Sort by domain
- $tmp = array();
- foreach($progress['hosts'] as $value) {
- $tmp[delimiter_reverse($value)] = $value;
- }
- ksort($tmp, SORT_STRING);
- $result = count($tmp) . ' (' .implode(', ', $tmp) . ')';
- } else {
- $tmp = array();
- foreach($progress['hosts'] as $value) {
- $tmp = array_merge_recursive(
- $tmp,
- array_leaf(explode('.', delimiter_reverse($value)), TRUE, $value)
- );
- }
-
-//var_dump($tmp);
-// TODO: IP address 1.2.3.4 => "0"-3-2-1 by array_shrinkbranch_leaves()
-
- array_shrinkbranch_leaves($tmp, '.', TRUE); // "domain.tld"
- array_joinbranch_leaf($tmp, '.', 0, TRUE);
- foreach($tmp as $key => $value) {
- if (is_array($value)) {
- ksort($tmp[$key], SORT_STRING);
- $tmp[$key] = implode(', ', array_flat_leaves($value));
- }
+ // Generate a responsible $trie
+ $trie = array();
+ foreach($progress['hosts'] as $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($resp)), '.'); // 'A.foo.bar'
}
- ksort($tmp, SORT_STRING);
-
- $result = var_export_shrink($tmp, TRUE, TRUE);
+ $trie = array_merge_recursive($trie, array($resp => array($rest => NULL)));
}
- return $result;
-}
-
-// array('F' => array('B' => array('C' => array('d' => array('' => 'foobar')))))
-// to
-// array('F.B.C.d.' => 'foobar')
-function array_joinbranch_leaf(& $array, $delim = '.', $limit = 0, $reverse = FALSE)
-{
+ // Format: var_export_shrink() -like output
$result = array();
- if (! is_array($array)) return $result; // Nothing to do
-
- $limit = max(0, intval($limit));
- $cstack = array();
-
- foreach(array_keys($array) as $key) {
- $kstack = array();
- $k = -1;
-
- $single = array($key => & $array[$key]); // Keep it single
- $cursor = & $single;
- while(is_array($cursor) && count($cursor) == 1) { // Once
- ++$k;
- $kstack[] = key($cursor);
- $cursor = & $cursor[$kstack[$k]];
- if ($limit != 0 && $k == $limit) break;
- }
-
- // Relink
- if ($k != 0) {
- if ($reverse) $kstack = array_reverse($kstack);
- $joinkey = implode($delim, $kstack);
-
- unset($array[$key]);
- $array[$joinkey] = & $cursor;
- $result[$joinkey] = $k + 1; // Key seems not an single array => joined length
+ ksort_by_domain($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 $result;
+ return
+ 'array (' . "\n" .
+ implode("\n", $result) . "\n" .
+ ')';
}
-
-// array('A' => array('B' => 'C')) to
-// array('A.B' => 'C')
-// array(
-// 'A' => array(
-// 'B' => array(
-// 'C' => array(
-// 'D' => '1'
-// ),
-// ),
-// ),
-// 'G' => array(
-// 'H' => '2'
-// ),
-// )
-// to
-// array (
-// 'G.H' => '2',
-// 'A.B.C.D' => '1',
-// )
-function array_shrinkbranch_leaves(& $array, $delim = '.', $reverse = FALSE, $recurse = FALSE)
+// ksort() by domain
+function ksort_by_domain(& $array)
{
- $result = 0;
- if (! is_array($array) || empty($array)) return $result;
-
+ $sort = array();
foreach(array_keys($array) as $key) {
- $branch = & $array[$key];
- if (! is_array($branch) || empty($branch)) continue;
-
- foreach(array_keys($branch) as $bkey) {
- $joinkey = $reverse ?
- $bkey . $delim . $key :
- $key . $delim . $bkey;
- $array[$joinkey] = & $branch[$bkey];
- unset($array[$key]);
- ++$result;
- }
+ $sort[delimiter_reverse($key)] = $key;
}
-
- // Rescan (Recurse)
- if ($recurse && $result) {
- $result = array_shrinkbranch_leaves($array, $delim, $reverse, $recurse);
+ ksort($sort, SORT_STRING);
+ $result = array();
+ foreach($sort as $key) {
+ $result[$key] = & $array[$key];
}
-
- return $result; // Tell me how many
+ $array = $result;
}
-//$a = array (
-// 'edu' => array (
-// 'berkeley' => array (
-// 'polisci' => array (
-// '' => 'polisci.berkeley.edu',
-// ),
-// ),
-// 'cmich' => array (
-// 'rso' => array (
-// '' => 'rso.cmich.edu',
-// ),
-// ),
-// ),
-//);
-//array_shrinkbranch_leaves($a, '.', TRUE);
-//var_export($a);
-
-//$a = array (
-// '4' => array (
-// '5' => array (
-// '6' => array (
-// '' => '7.8.9',
-// ),
-// ),
-// ),
-//);
-//array_shrinkbranch_leaves($a, '.', TRUE);
-//var_export($a);
-
-
// Check responsibility-root of the FQDN
-// 'foobar.example.co.jp' => 'example.co.jp' (.co.jp seems public)
-// 'foobar.example.act.edu.au' => 'example.act.edu.au' (.act.edu.au seems public)
-// 'foobar.example.com' => 'example.com' (.com seems public)
-function domain_responsibility($fqdn = 'fqdn.foo.bar.example.com', $implicit = TRUE)
+// 'foo.bar.example.com' => 'example.com' (.com has the last whois for it)
+// 'foo.bar.example.au' => 'example.au' (.au has the last whois for it)
+// 'foo.bar.example.edu.au' => 'example.edu.au' (.edu.au has the last whois for it)
+// 'foo.bar.example.act.edu.au' => 'example.act.edu.au' (.act.edu.au has the last whois for it)
+function whois_responsibility($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/ http://www.aunic.net/ http://www.ausregistry.com.au/
+ // 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/
+ // .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,
'wa' => TRUE,
),
'gov' => array(
+ // Geographic
'act' => TRUE, // Australian Capital Territory
'nt' => TRUE, // Northern Territory
'nsw' => TRUE, // New South Wales
'info' => TRUE,
),
- // ccTLD: Japan http://jprs.co.jp/en/ http://whois.jprs.jp/en/
+ // 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,
'yokohama' => TRUE,
),
- // ccTLD: Ukraine http://www.nic.net.ua/ http://whois.com.ua/
+ // 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(
- 'cherkassy' => TRUE, // www.cherkassy.ua
- 'chernigov' => TRUE,
+ // 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,
'zt' => TRUE,
),
- // ccTLD: United Kingdom http://www.nic.uk/
+ // ccTLD: United Kingdom
+ // NIC : http://www.nic.uk/
'uk' => array(
- // http://www.nominet.org.uk/registrants/faq/#available
+ // Second Level Domains
+ // http://www.nic.uk/registrants/aboutdomainnames/sld/
'co' => TRUE,
'ltd' => TRUE,
'me' => TRUE,
'plc' => TRUE,
'sch' => TRUE,
- // "Delegated Second Level Domains" http://www.nominet.org.uk/registrants/aboutdomainnames/sld/delegated/
+ // Delegated Second Level Domains
+ // http://www.nic.uk/registrants/aboutdomainnames/sld/delegated/
'ac' => TRUE,
'gov' => TRUE,
'mil' => TRUE,
'police' => TRUE,
),
- // ccTLD: United States of America http://nic.us/ http://whois.us/
- 'us' => array( // RFC1480
+ // ccTLD: United States of America
+ // NIC : http://nic.us/
+ // Whois: http://whois.us/
+ 'us' => array(
+ // See RFC1480
+
+ // Organizational
+ 'dni',
+ 'fed',
+ 'isa',
+ 'kids',
+ 'nsn',
- // State abbreviations for postal codes http://www.usps.com/ncsc/lookups/abbreviations.html
+ // 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
'wi' => TRUE, // Wisconsin
'wv' => TRUE, // West Virginia
'wy' => TRUE, // Wyoming
+ ),
- // Others
- 'dni',
- 'fed',
- 'isa',
- 'kids',
- 'nsn',
+ // 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 (isset($acursor)) {
+ if (! $parent && isset($acursor)) {
$result[] = & $array[$i]; // Whois servers must know this subdomain
}
break;
// 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");
if (empty($progress['is_spam'])) {
spam_dispose();
} else {
- $target = string($target, 0); // Removing "\0" etc
+
+// 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);
}