<?php
-// $Id: spam.php,v 1.154 2007/05/05 08:49:10 henoheno Exp $
+// $Id: spam.php,v 1.160 2007/05/12 09:19:49 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, $return = FALSE)
+function var_export_shrink($expression, $return = FALSE, $ignore_numeric_keys = FALSE)
{
$result =preg_replace(
// Remove a newline and spaces
var_export($expression, TRUE)
);
+ if ($ignore_numeric_keys) {
+ $result =preg_replace(
+ // Remove numeric keys
+ '#^( *)[0-9]+ => #m', '$1',
+ $result
+ );
+ }
+
if ($return) {
return $result;
} else {
// 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(
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, $rule = TRUE)
{
if ($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)
-{
- $array = array_merge_recursive($array1, $array2);
-
- // Redundant values (and keys) are vanished
- if ($unique_values) $array = array_unique_recursive($array);
-
- // All NUMERIC keys are always renumbered from 0
- if ($renumber_numeric) array_renumber_numeric_keys($array);
-
- return $array;
-}
-
-// Shrink array('key' => array('key')) to array('key')
-function array_shrink_leaves(& $array)
+// An array-leaves to a flat array
+function array_flat_leaves($array, $unique = TRUE)
{
if (! is_array($array)) return $array;
- foreach($array as $key => $value){
- // Recurse. Removing more leaves beforehand
- if (is_array($value)) array_shrink_leaves($array[$key]);
- }
-
$tmp = array();
- foreach($array as $key => $value){
- if (is_array($value)) {
- $count = count($value);
- if ($count == 1 && current($value) == $key) {
- unset($array[$key]);
- $array[] = $key;
+ foreach(array_keys($array) as $key) {
+ if (is_array($array[$key])) {
+ // Recurse
+ foreach(array_flat_leaves($array[$key]) as $_value) {
+ $tmp[] = $_value;
}
+ } else {
+ $tmp[] = & $array[$key];
}
}
- return $array;
+ return $unique ? array_values(array_unique($tmp)) : $tmp;
+}
+
+// An array() to an array leaf
+function array_leaf($array = array('A', 'B', 'C.D'), $stem = FALSE, $edge = 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(), $blockedonly = FALSE)
{
function summarize_detail_badhost($progress = array())
{
- if (! isset($progress['is_spam']['badhost'])) return '';
+ if (! isset($progress['blocked']) || empty($progress['blocked'])) return '';
+
+ // 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] = $flat;
+ }
+ }
+ }
+
+ // Shrink per list
+ // From: 'A-1' => array('ie.to')
+ // To: 'A-1' => 'ie.to'
+ foreach($blocked as $list => $lvalue) {
+ if (is_array($lvalue) &&
+ count($lvalue) == 1 &&
+ is_numeric(key($lvalue))) {
+ $blocked[$list] = current($lvalue);
+ }
+ }
- return var_export_shrink(array_shrink_leaves($progress['blocked']), TRUE);
+ return var_export_shrink($blocked, TRUE, TRUE);
}
function summarize_detail_newtral($progress = array())
! is_array($progress['hosts']) ||
empty($progress['hosts'])) return '';
- // Sort by domain
- $tmp = array();
- foreach($progress['hosts'] as $value) {
- $tmp[delimiter_reverse($value)] = $value;
+ $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, $value)
+ );
+ }
+ ksort($tmp);
+ foreach($tmp as $key => $value) {
+ ksort($tmp[$key]);
+ foreach($value as $_key => $_value) {
+ ksort($tmp[$key][$_key]);
+ $tmp[$key][$_key] = implode(', ', array_flat_leaves($_value));
+ }
+ }
+
+ //$tmp = array_unique_recursive($tmp); // Buggy?
+ $result = var_export_shrink($tmp, TRUE, TRUE);
}
- ksort($tmp);
- return count($tmp) . ' (' .implode(', ', $tmp) . ')';
+ return $result;
}