2 // $Id: spam.php,v 1.208 2008/12/28 14:17:18 henoheno Exp $
3 // Copyright (C) 2006-2007 PukiWiki Developers Team
4 // License: GPL v2 or (at your option) any later version
6 // Functions for Concept-work of spam-uri metrics
8 // (PHP 4 >= 4.3.0): preg_match_all(PREG_OFFSET_CAPTURE): $method['uri_XXX'] related feature
10 if (! defined('SPAM_INI_FILE')) define('SPAM_INI_FILE', 'spam.ini.php');
11 if (! defined('DOMAIN_INI_FILE')) define('DOMAIN_INI_FILE', 'domain.ini.php');
13 // ---------------------
16 // (PHP 4 >= 4.2.0): var_export(): mail-reporting and dump related
17 if (! function_exists('var_export')) {
18 function var_export() {
19 return 'var_export() is not found on this server' . "\n";
23 // (PHP 4 >= 4.2.0): preg_grep() enables invert option
24 function preg_grep_invert($pattern = '//', $input = array())
27 if (! isset($invert)) $invert = defined('PREG_GREP_INVERT');
30 return preg_grep($pattern, $input, PREG_GREP_INVERT);
32 $result = preg_grep($pattern, $input);
34 return array_diff($input, preg_grep($pattern, $input));
42 // ---------------------
45 // Very roughly, shrink the lines of var_export()
46 // NOTE: If the same data exists, it must be corrupted.
47 function var_export_shrink($expression, $return = FALSE, $ignore_numeric_keys = FALSE)
49 $result = var_export($expression, TRUE);
51 $result = preg_replace(
52 // Remove a newline and spaces
53 '# => \n *array \(#', ' => array (',
57 if ($ignore_numeric_keys) {
58 $result =preg_replace(
59 // Remove numeric keys
60 '#^( *)[0-9]+ => #m', '$1',
73 // Data structure: Create an array they _refer_only_one_ value
74 function one_value_array($num = 0, $value = NULL)
76 $num = max(0, intval($num));
79 for ($i = 0; $i < $num; $i++) {
86 // Reverse $string with specified delimiter
87 function delimiter_reverse($string = 'foo.bar.example.com', $from_delim = '.', $to_delim = NULL)
89 $to_null = ($to_delim === NULL);
91 if (! is_string($from_delim) || (! $to_null && ! is_string($to_delim))) {
94 if (is_array($string)) {
96 $count = count($string);
97 $from = one_value_array($count, $from_delim);
99 // Note: array_map() vanishes all keys
100 return array_map('delimiter_reverse', $string, $from);
102 $to = one_value_array($count, $to_delim);
103 // Note: array_map() vanishes all keys
104 return array_map('delimiter_reverse', $string, $from, $to);
107 if (! is_string($string)) {
111 // Returns com.example.bar.foo
112 if ($to_null) $to_delim = & $from_delim;
113 return implode($to_delim, array_reverse(explode($from_delim, $string)));
117 function ksort_by_domain(& $array)
120 foreach(array_keys($array) as $key) {
121 $reversed = delimiter_reverse($key);
122 if ($reversed !== FALSE) {
123 $sort[$reversed] = $key;
126 ksort($sort, SORT_STRING);
129 foreach($sort as $key) {
130 $result[$key] = & $array[$key];
136 // Roughly strings(1) using PCRE
137 // This function is useful to:
138 // * Reduce the size of data, from removing unprintable binary data
139 // * Detect _bare_strings_ from binary data
141 // http://www.freebsd.org/cgi/man.cgi?query=strings (Man-page of GNU strings)
142 // http://www.pcre.org/pcre.txt
143 // Note: mb_ereg_replace() is one of mbstring extension's functions
144 // and need to init its encoding.
145 function strings($binary = '', $min_len = 4, $ignore_space = FALSE, $multibyte = FALSE)
148 $binary = (is_array($binary) || $binary === TRUE) ? '' : strval($binary);
150 $regex = $ignore_space ?
151 '[^[:graph:] \t\n]+' : // Remove "\0" etc, and readable spaces
152 '[^[:graph:][:space:]]+'; // Preserve readable spaces if possible
154 $binary = $multibyte ?
155 mb_ereg_replace($regex, "\n", $binary) :
156 preg_replace('/' . $regex . '/s', "\n", $binary);
159 $binary = preg_replace(
174 // The last character seems "\n" or not
175 $br = (! empty($binary) && $binary[strlen($binary) - 1] == "\n") ? "\n" : '';
177 $min_len = min(1024, intval($min_len));
178 $regex = '/^.{' . $min_len . ',}/S';
179 $binary = implode("\n", preg_grep($regex, explode("\n", $binary))) . $br;
186 // ---------------------
189 // Count leaves (A leaf = value that is not an array, or an empty array)
190 function array_count_leaves($array = array(), $count_empty = FALSE)
192 if (! is_array($array) || (empty($array) && $count_empty)) return 1;
196 foreach ($array as $part) {
197 $count += array_count_leaves($part, $count_empty);
203 // Similar to PHP array_merge_leaves(), except strictly preserving keys as string
204 function array_merge_leaves($array1, $array2, $sort_keys = TRUE)
207 $is_array1 = is_array($array1);
208 $is_array2 = is_array($array2);
215 } else if ($is_array2) {
218 return $array2; // Not array ($array1 is overwritten)
221 $keys_all = array_merge(array_keys($array1), array_keys($array2));
222 if ($sort_keys) sort($keys_all, SORT_STRING);
225 foreach($keys_all as $key) {
226 $isset1 = isset($array1[$key]);
227 $isset2 = isset($array2[$key]);
228 if ($isset1 && $isset2) {
230 $result[$key] = array_merge_leaves($array1[$key], $array2[$key], $sort_keys);
231 } else if ($isset1) {
232 $result[$key] = & $array1[$key];
234 $result[$key] = & $array2[$key];
240 // An array-leaves to a flat array
241 function array_flat_leaves($array, $unique = TRUE)
243 if (! is_array($array)) return $array;
246 foreach(array_keys($array) as $key) {
247 if (is_array($array[$key])) {
249 foreach(array_flat_leaves($array[$key]) as $_value) {
253 $tmp[] = & $array[$key];
257 return $unique ? array_values(array_unique($tmp)) : $tmp;
260 // $array['something'] => $array['wanted']
261 function array_rename_keys(& $array, $keys = array('from' => 'to'), $force = FALSE, $default = '')
263 if (! is_array($array) || ! is_array($keys)) return FALSE;
265 // Nondestructive test
267 foreach(array_keys($keys) as $from) {
268 if (! isset($array[$from])) {
274 foreach($keys as $from => $to) {
275 if ($from === $to) continue;
276 if (! $force || isset($array[$from])) {
277 $array[$to] = & $array[$from];
278 unset($array[$from]);
280 $array[$to] = $default;
287 // Remove redundant values from array()
288 function array_unique_recursive($array = array())
290 if (! is_array($array)) return $array;
293 foreach($array as $key => $value){
294 if (is_array($value)) {
295 $array[$key] = array_unique_recursive($value);
297 if (isset($tmp[$value])) {
309 // ---------------------
310 // Part One : Checker
312 // Rough implementation of globbing
314 // USAGE: $regex = '/^' . generate_glob_regex('*.txt', '/') . '$/i';
316 function generate_glob_regex($string = '', $divider = '/')
318 static $from = array(
321 // 22 => '[', // Maybe cause regex compilation error (e.g. '[]')
337 if (! is_string($string)) return '';
339 $string = str_replace($from, $mid, $string); // Hide
340 $string = preg_quote($string, $divider);
341 $string = str_replace($mid, $to, $string); // Unhide
346 // Generate host (FQDN, IPv4, ...) regex
347 // 'localhost' : Matches with 'localhost' only
348 // 'example.org' : Matches with 'example.org' only (See host_normalize() about 'www')
349 // '.example.org' : Matches with ALL FQDN ended with '.example.org'
350 // '*.example.org' : Almost the same of '.example.org' except 'www.example.org'
351 // '10.20.30.40' : Matches with IPv4 address '10.20.30.40' only
352 // [TODO] '192.' : Matches with all IPv4 hosts started with '192.'
353 // TODO: IPv4, CIDR?, IPv6
354 function generate_host_regex($string = '', $divider = '/')
356 if (! is_string($string)) return '';
358 if (mb_strpos($string, '.') === FALSE) {
360 return generate_glob_regex($string, $divider);
363 if (is_ip($string)) {
365 return generate_glob_regex($string, $divider);
368 $part = explode('.', $string, 2);
369 if ($part[0] == '') {
371 $part[0] = '(?:.*\.)?';
372 } else if ($part[0] == '*') {
377 return generate_glob_regex($string, $divider);
379 $part[1] = generate_glob_regex($part[1], $divider);
380 return implode('', $part);
384 // Rough hostname checker
385 // TODO: Strict digit, 0x, CIDR, '999.999.999.999', ':', '::G'
386 function is_ip($string = '')
388 if (! is_string($string)) return FALSE;
390 if (strpos($string, ':') !== FALSE) {
391 return 6; // Seems IPv6
394 if (preg_match('/^' .
395 '(?:[0-9]{1,3}\.){3}[0-9]{1,3}' . '|' .
396 '(?:[0-9]{1,3}\.){1,3}' . '$/',
398 return 4; // Seems IPv4(dot-decimal)
401 return FALSE; // Seems not IP
404 // Load SPAM_INI_FILE and return parsed one
405 function get_blocklist($list = '')
409 if ($list === NULL) {
410 $regexes = NULL; // Unset
414 if (! isset($regexes)) {
416 if (file_exists(SPAM_INI_FILE)) {
417 $blocklist = array();
419 include(SPAM_INI_FILE);
420 // $blocklist['list'] = array(
421 // //'goodhost' => FALSE;
422 // 'badhost' => TRUE;
424 // $blocklist['badhost'] = array(
425 // '*.blogspot.com', // Blog services's subdomains (only)
426 // 'IANA-examples' => '#^(?:.*\.)?example\.(?:com|net|org)$#',
434 if (! isset($blocklist[$special])) continue;
436 $regexes[$special] = $blocklist[$special];
438 foreach(array_keys($blocklist[$special]) as $_list) {
439 if (! isset($blocklist[$_list])) continue;
441 foreach ($blocklist[$_list] as $key => $value) {
442 if (is_array($value)) {
443 $regexes[$_list][$key] = array();
444 foreach($value as $_key => $_value) {
445 get_blocklist_add($regexes[$_list][$key], $_key, $_value);
448 get_blocklist_add($regexes[$_list], $key, $value);
452 unset($blocklist[$_list]);
459 return $regexes; // ALL of
460 } else if (isset($regexes[$list])) {
461 return $regexes[$list]; // A part of
463 return array(); // Found nothing
467 // Subroutine of get_blocklist(): Add new regex to the $array
468 function get_blocklist_add(& $array, $key = 0, $value = '*.example.org/path/to/file.html')
470 if (is_string($key)) {
471 $array[$key] = & $value; // Treat $value as a regex for FQDN(host)s
473 $array[$value] = '#^' . generate_host_regex($value, '#') . '$#i';
477 // Blocklist metrics: Separate $host, to $blocked and not blocked
478 function blocklist_distiller(& $hosts, $keys = array('goodhost', 'badhost'), $asap = FALSE)
480 if (! is_array($hosts)) $hosts = array($hosts);
481 if (! is_array($keys)) $keys = array($keys);
483 $list = get_blocklist('list');
486 foreach($keys as $key){
487 foreach (get_blocklist($key) as $label => $regex) {
488 if (is_array($regex)) {
489 foreach($regex as $_label => $_regex) {
490 $group = preg_grep($_regex, $hosts);
492 $hosts = array_diff($hosts, $group);
493 $blocked[$key][$label][$_label] = $group;
494 if ($asap && $list[$key]) break;
498 $group = preg_grep($regex, $hosts);
500 $hosts = array_diff($hosts, $group);
501 $blocked[$key][$label] = $group;
502 if ($asap && $list[$key]) break;
512 // ---------------------
515 // Default (enabled) methods and thresholds (for content insertion)
516 function check_uri_spam_method($times = 1, $t_area = 0, $rule = TRUE)
518 $times = intval($times);
519 $t_area = intval($t_area);
523 'quantity' => 8 * $times, // Allow N URIs
524 'non_uniqhost' => 3 * $times, // Allow N duped (and normalized) Hosts
525 //'non_uniquri'=> 3 * $times, // Allow N duped (and normalized) URIs
528 'area_anchor' => $t_area, // Using <a href> HTML tag
529 'area_bbcode' => $t_area, // Using [url] or [link] BBCode
530 //'uri_anchor' => $t_area, // URI inside <a href> HTML tag
531 //'uri_bbcode' => $t_area, // URI inside [url] or [link] BBCode
536 //'asap' => TRUE, // Quit or return As Soon As Possible
537 'uniqhost' => TRUE, // Show uniq host (at block notification mail)
538 'badhost' => TRUE, // Check badhost
544 // Remove non-$positive values
545 foreach (array_keys($positive) as $key) {
546 if ($positive[$key] < 0) unset($positive[$key]);
549 return $positive + $bool;
552 // Simple/fast spam check
553 function check_uri_spam($target = '', $method = array())
558 // Theme to do => Dummy, optional value, or optional array()
560 //'uniqhost' => TRUE,
561 //'non_uniqhost'=> 3,
562 //'non_uniquri' => 3,
564 //'area_anchor' => 0,
565 //'area_bbcode' => 0,
570 // Theme => Volume found (int)
573 // Flag. If someting defined here,
574 // one or more spam will be included
579 //'category' => array(
588 // ----------------------------------------
591 $sum = & $progress['sum'];
592 $is_spam = & $progress['is_spam'];
593 $progress['method'] = & $method; // Argument
594 $blocked = & $progress['blocked'];
595 $hosts = & $progress['hosts'];
596 $asap = isset($method['asap']);
598 // ----------------------------------------
601 if (! is_array($method) || empty($method)) {
602 $method = check_uri_spam_method();
604 foreach(array_keys($method) as $key) {
605 if (! isset($sum[$key])) $sum[$key] = 0;
607 if (! isset($sum['quantity'])) $sum['quantity'] = 0;
609 // ----------------------------------------
612 if (is_array($target)) {
613 foreach($target as $str) {
614 if (! is_string($str)) continue;
616 $_progress = check_uri_spam($str, $method); // Recurse
619 $_sum = & $_progress['sum'];
620 foreach (array_keys($_sum) as $key) {
621 if (! isset($sum[$key])) {
622 $sum[$key] = & $_sum[$key];
624 $sum[$key] += $_sum[$key];
629 $_is_spam = & $_progress['is_spam'];
630 foreach (array_keys($_is_spam) as $key) {
631 $is_spam[$key] = TRUE;
634 if ($asap && $is_spam) break;
637 $blocked = array_merge_leaves($blocked, $_progress['blocked'], FALSE);
638 $hosts = array_merge_leaves($hosts, $_progress['hosts'], FALSE);
642 $blocked = array_unique_recursive($blocked);
643 $hosts = array_unique_recursive($hosts);
645 // Recount $sum['badhost']
646 $sum['badhost'] = array_count_leaves($blocked);
651 // ----------------------------------------
654 // Area: There's HTML anchor tag
655 if ((! $asap || ! $is_spam) && isset($method['area_anchor'])) {
656 $key = 'area_anchor';
657 $_asap = isset($method['asap']) ? array('asap' => TRUE) : array();
658 $result = area_pickup($target, array($key => TRUE) + $_asap);
660 $sum[$key] = $result[$key];
661 if (isset($method[$key]) && $sum[$key] > $method[$key]) {
662 $is_spam[$key] = TRUE;
667 // Area: There's 'BBCode' linking tag
668 if ((! $asap || ! $is_spam) && isset($method['area_bbcode'])) {
669 $key = 'area_bbcode';
670 $_asap = isset($method['asap']) ? array('asap' => TRUE) : array();
671 $result = area_pickup($target, array($key => TRUE) + $_asap);
673 $sum[$key] = $result[$key];
674 if (isset($method[$key]) && $sum[$key] > $method[$key]) {
675 $is_spam[$key] = TRUE;
681 if ($asap && $is_spam) return $progress;
683 // ----------------------------------------
686 $pickups = uri_pickup_normalize(spam_uri_pickup($target, $method));
688 foreach ($pickups as $key => $pickup) {
689 $hosts[$key] = & $pickup['host'];
693 if (empty($pickups)) return $progress;
695 // ----------------------------------------
696 // URI: Bad host <pre-filter> (Separate good/bad hosts from $hosts)
698 if ((! $asap || ! $is_spam) && isset($method['badhost'])) {
699 $list = get_blocklist('pre');
700 $blocked = blocklist_distiller($hosts, array_keys($list), $asap);
701 foreach($list as $key=>$type){
702 if (! $type) unset($blocked[$key]); // Ignore goodhost etc
705 if (! empty($blocked)) $is_spam['badhost'] = TRUE;
709 if ($asap && $is_spam) return $progress;
711 // Remove blocked from $pickups
712 foreach(array_keys($pickups) as $key) {
713 if (! isset($hosts[$key])) {
714 unset($pickups[$key]);
718 // ----------------------------------------
719 // URI: Check quantity
721 $sum['quantity'] += count($pickups);
723 if ((! $asap || ! $is_spam) && isset($method['quantity']) &&
724 $sum['quantity'] > $method['quantity']) {
725 $is_spam['quantity'] = TRUE;
728 // ----------------------------------------
729 // URI: used inside HTML anchor tag pair
731 if ((! $asap || ! $is_spam) && isset($method['uri_anchor'])) {
733 foreach($pickups as $pickup) {
734 if (isset($pickup['area'][$key])) {
735 $sum[$key] += $pickup['area'][$key];
736 if(isset($method[$key]) &&
737 $sum[$key] > $method[$key]) {
738 $is_spam[$key] = TRUE;
739 if ($asap && $is_spam) break;
741 if ($asap && $is_spam) break;
746 // ----------------------------------------
747 // URI: used inside 'BBCode' pair
749 if ((! $asap || ! $is_spam) && isset($method['uri_bbcode'])) {
751 foreach($pickups as $pickup) {
752 if (isset($pickup['area'][$key])) {
753 $sum[$key] += $pickup['area'][$key];
754 if(isset($method[$key]) &&
755 $sum[$key] > $method[$key]) {
756 $is_spam[$key] = TRUE;
757 if ($asap && $is_spam) break;
759 if ($asap && $is_spam) break;
764 // ----------------------------------------
765 // URI: Uniqueness (and removing non-uniques)
767 if ((! $asap || ! $is_spam) && isset($method['non_uniquri'])) {
770 foreach (array_keys($pickups) as $key) {
771 $uris[$key] = uri_pickup_implode($pickups[$key]);
773 $count = count($uris);
774 $uris = array_unique($uris);
775 $sum['non_uniquri'] += $count - count($uris);
776 if ($sum['non_uniquri'] > $method['non_uniquri']) {
777 $is_spam['non_uniquri'] = TRUE;
779 if (! $asap || ! $is_spam) {
780 foreach (array_diff(array_keys($pickups),
781 array_keys($uris)) as $remove) {
782 unset($pickups[$remove]);
789 if ($asap && $is_spam) return $progress;
791 // ----------------------------------------
792 // Host: Uniqueness (uniq / non-uniq)
794 $hosts = array_unique($hosts);
796 if (isset($sum['uniqhost'])) $sum['uniqhost'] += count($hosts);
797 if ((! $asap || ! $is_spam) && isset($method['non_uniqhost'])) {
798 $sum['non_uniqhost'] = $sum['quantity'] - $sum['uniqhost'];
799 if ($sum['non_uniqhost'] > $method['non_uniqhost']) {
800 $is_spam['non_uniqhost'] = TRUE;
805 if ($asap && $is_spam) return $progress;
807 // ----------------------------------------
808 // URI: Bad host (Separate good/bad hosts from $hosts)
810 if ((! $asap || ! $is_spam) && isset($method['badhost'])) {
811 $list = get_blocklist('list');
812 $blocked = array_merge_leaves(
814 blocklist_distiller($hosts, array_keys($list), $asap),
817 foreach($list as $key=>$type){
818 if (! $type) unset($blocked[$key]); // Ignore goodhost etc
821 if (! empty($blocked)) $is_spam['badhost'] = TRUE;
825 //if ($asap && $is_spam) return $progress;
827 // ----------------------------------------
833 // ---------------------
836 // Summarize $progress (blocked only)
837 function summarize_spam_progress($progress = array(), $blockedonly = FALSE)
840 $tmp = array_keys($progress['is_spam']);
843 $method = & $progress['method'];
844 if (isset($progress['sum'])) {
845 foreach ($progress['sum'] as $key => $value) {
846 if (isset($method[$key]) && $value) {
847 $tmp[] = $key . '(' . $value . ')';
853 return implode(', ', $tmp);
856 function summarize_detail_badhost($progress = array())
858 if (! isset($progress['blocked']) || empty($progress['blocked'])) return '';
862 foreach($progress['blocked'] as $list => $lvalue) {
863 foreach($lvalue as $group => $gvalue) {
864 $flat = implode(', ', array_flat_leaves($gvalue));
865 if ($flat === $group) {
866 $blocked[$list][] = $flat;
868 $blocked[$list][$group] = $flat;
874 // From: 'A-1' => array('ie.to')
875 // To: 'A-1' => 'ie.to'
876 foreach($blocked as $list => $lvalue) {
877 if (is_array($lvalue) &&
878 count($lvalue) == 1 &&
879 is_numeric(key($lvalue))) {
880 $blocked[$list] = current($lvalue);
884 return var_export_shrink($blocked, TRUE, TRUE);
887 function summarize_detail_newtral($progress = array())
889 if (! isset($progress['hosts']) ||
890 ! is_array($progress['hosts']) ||
891 empty($progress['hosts'])) return '';
893 // Generate a responsible $trie
895 foreach($progress['hosts'] as $value) {
896 // 'A.foo.bar.example.com'
897 $resp = whois_responsibility($value); // 'example.com'
899 // One or more test, or do nothing here
900 $resp = strval($value);
903 $rest = rtrim(substr($value, 0, - strlen($resp)), '.'); // 'A.foo.bar'
905 $trie = array_merge_leaves($trie, array($resp => array($rest => NULL)), FALSE);
908 // Format: var_export_shrink() -like output
910 ksort_by_domain($trie);
911 foreach(array_keys($trie) as $key) {
912 ksort_by_domain($trie[$key]);
913 if (count($trie[$key]) == 1 && key($trie[$key]) == '') {
914 // Just one 'responsibility.example.com'
915 $result[] = ' \'' . $key . '\',';
917 // One subdomain-or-host, or several ones
919 foreach(array_keys($trie[$key]) as $sub) {
921 $subs[] = $key; // 'example.com'
923 $subs[] = $sub . '...'; // 'A.foo.bar...'
926 $result[] = ' \'' . $key . '\' => \'' . implode(', ', $subs) . '\',';
932 implode("\n", $result) . "\n" .
937 // Check responsibility-root of the FQDN
938 // 'foo.bar.example.com' => 'example.com' (.com has the last whois for it)
939 // 'foo.bar.example.au' => 'example.au' (.au has the last whois for it)
940 // 'foo.bar.example.edu.au' => 'example.edu.au' (.edu.au has the last whois for it)
941 // 'foo.bar.example.act.edu.au' => 'example.act.edu.au' (.act.edu.au has the last whois for it)
942 function whois_responsibility($fqdn = 'foo.bar.example.com', $parent = FALSE, $implicit = TRUE)
946 if ($fqdn === NULL) {
947 $domain = NULL; // Unset
950 if (! is_string($fqdn)) return '';
952 if (is_ip($fqdn)) return $fqdn;
954 if (! isset($domain)) {
956 if (file_exists(DOMAIN_INI_FILE)) {
957 include(DOMAIN_INI_FILE); // Set
962 $dcursor = & $domain;
963 $array = array_reverse(explode('.', $fqdn));
966 if (! isset($array[$i])) break;
967 $acursor = $array[$i];
968 if (is_array($dcursor) && isset($dcursor[$acursor])) {
969 $result[] = & $array[$i];
970 $dcursor = & $dcursor[$acursor];
972 if (! $parent && isset($acursor)) {
973 $result[] = & $array[$i]; // Whois servers must know this subdomain
980 // Implicit responsibility: Top-Level-Domains must not be yours
981 // 'bar.foo.something' => 'foo.something'
982 if ($implicit && count($result) == 1 && count($array) > 1) {
983 $result[] = & $array[1];
986 return $result ? implode('.', array_reverse($result)) : '';
990 // ---------------------
994 function spam_dispose()
997 whois_responsibility(NULL);
1000 // Common bahavior for blocking
1001 // NOTE: Call this function from various blocking feature, to disgueise the reason 'why blocked'
1002 function spam_exit($mode = '', $data = array())
1011 echo('<pre>' . "\n");
1012 echo htmlspecialchars(var_export($data, TRUE));
1013 echo('</pre>' . "\n");
1017 if ($exit) exit; // Force exit
1021 // ---------------------
1024 // TODO: Record them
1025 // Simple/fast spam filter ($target: 'a string' or an array())
1026 function pkwk_spamfilter($action, $page, $target = array('title' => ''), $method = array(), $exitmode = '')
1028 $progress = check_uri_spam($target, $method);
1030 if (empty($progress['is_spam'])) {
1034 // TODO: detect encoding from $target for mbstring functions
1036 // foreach(array_keys($target) as $key) {
1037 // $tmp[strings($key, 0, FALSE, TRUE)] = strings($target[$key], 0, FALSE, TRUE); // Removing "\0" etc
1039 // $target = & $tmp;
1041 pkwk_spamnotify($action, $page, $target, $progress, $method);
1042 spam_exit($exitmode, $progress);
1046 // ---------------------
1047 // PukiWiki original
1049 // Mail to administrator(s)
1050 function pkwk_spamnotify($action, $page, $target = array('title' => ''), $progress = array(), $method = array())
1052 global $notify, $notify_subject;
1054 if (! $notify) return;
1056 $asap = isset($method['asap']);
1058 $summary['ACTION'] = 'Blocked by: ' . summarize_spam_progress($progress, TRUE);
1060 $summary['METRICS'] = summarize_spam_progress($progress);
1063 $tmp = summarize_detail_badhost($progress);
1064 if ($tmp != '') $summary['DETAIL_BADHOST'] = $tmp;
1066 $tmp = summarize_detail_newtral($progress);
1067 if (! $asap && $tmp != '') $summary['DETAIL_NEUTRAL_HOST'] = $tmp;
1069 $summary['COMMENT'] = $action;
1070 $summary['PAGE'] = '[blocked] ' . (is_pagename($page) ? $page : '');
1071 $summary['URI'] = get_script_uri() . '?' . rawurlencode($page);
1072 $summary['USER_AGENT'] = TRUE;
1073 $summary['REMOTE_ADDR'] = TRUE;
1074 pkwk_mail_notify($notify_subject, var_export($target, TRUE), $summary, TRUE);