<?PHP
class http {
private $ch;
private $uid;
function data_encode ($data, $keyprefix = "", $keypostfix = "") {
assert( is_array($data) );
$vars=null;
foreach($data as $key=>$value) {
if(is_array($value)) $vars .= $this->data_encode($value, $keyprefix.$key.$keypostfix.urlencode("["), urlencode("]"));
else $vars .= $keyprefix.$key.$keypostfix."=".urlencode($value)."&";
}
return $vars;
}
function __construct () {
$this->ch = curl_init();
$this->uid = dechex(rand(0,99999999));
curl_setopt($this->ch,CURLOPT_COOKIEJAR,'/tmp/cluewikibot.cookies.'.$this->uid.'.dat');
curl_setopt($this->ch,CURLOPT_COOKIEFILE,'/tmp/cluewikibot.cookies.'.$this->uid.'.dat');
curl_setopt($this->ch,CURLOPT_MAXCONNECTS,100);
curl_setopt($this->ch,CURLOPT_CLOSEPOLICY,CURLCLOSEPOLICY_LEAST_RECENTLY_USED);
}
function post ($url,$data) {
// echo 'POST: '.$url."\n";
$time = microtime(1);
curl_setopt($this->ch,CURLOPT_URL,$url);
curl_setopt($this->ch,CURLOPT_FOLLOWLOCATION,1);
curl_setopt($this->ch,CURLOPT_MAXREDIRS,10);
curl_setopt($this->ch,CURLOPT_HEADER,0);
curl_setopt($this->ch,CURLOPT_RETURNTRANSFER,1);
curl_setopt($this->ch,CURLOPT_TIMEOUT,30);
curl_setopt($this->ch,CURLOPT_CONNECTTIMEOUT,10);
curl_setopt($this->ch,CURLOPT_POST,1);
curl_setopt($this->ch,CURLOPT_POSTFIELDS, substr($this->data_encode($data), 0, -1) );
$data = curl_exec($this->ch);
echo 'POST: '.$url.' ('.(microtime(1) - $time)." s)\n";
return $data;
}
function get ($url) {
//echo 'GET: '.$url."\n";
$time = microtime(1);
curl_setopt($this->ch,CURLOPT_URL,$url);
curl_setopt($this->ch,CURLOPT_FOLLOWLOCATION,1);
curl_setopt($this->ch,CURLOPT_MAXREDIRS,10);
curl_setopt($this->ch,CURLOPT_HEADER,0);
curl_setopt($this->ch,CURLOPT_RETURNTRANSFER,1);
curl_setopt($this->ch,CURLOPT_TIMEOUT,30);
curl_setopt($this->ch,CURLOPT_CONNECTTIMEOUT,10);
curl_setopt($this->ch,CURLOPT_HTTPGET,1);
$data = curl_exec($this->ch);
echo 'GET: '.$url.' ('.(microtime(1) - $time).' s)'."\n";
return $data;
}
function __destruct () {
curl_close($this->ch);
@unlink('/tmp/cluewikibot.cookies.'.$this->uid.'.dat');
}
}
class wikipediaquery {
private $http;
public $queryurl = 'http://en.wikipedia.org/w/query.php';
function __construct () {
global $__wp__http;
if (!isset($__wp__http)) {
$__wp__http = new http;
}
$this->http = &$__wp__http;
}
function getpage ($page) {
$ret = unserialize($this->http->get($this->queryurl.'?what=content&format=php&titles='.urlencode($page)));
foreach ($ret['pages'] as $page) {
return $page['content']['*'];
}
}
function getpageid ($page) {
$ret = unserialize($this->http->get($this->queryurl.'?what=content&format=php&titles='.urlencode($page)));
foreach ($ret['pages'] as $page) {
return $page['id'];
}
}
function contribcount ($user) {
$ret = unserialize($this->http->get($this->queryurl.'?what=contribcounter&format=php&titles=User:'.urlencode($user)));
foreach ($ret['pages'] as $page) {
return $page['contribcounter']['count'];
}
}
}
class wikipediaapi {
private $http;
public $apiurl = 'http://en.wikipedia.org/w/api.php';
function __construct () {
global $__wp__http;
if (!isset($__wp__http)) {
$__wp__http = new http;
}
$this->http = &$__wp__http;
}
function login ($user,$pass) {
$this->http->post($this->apiurl.'?action=login',array('lgname' => $user, 'lgpassword' => $pass));
}
function recentchanges ($count = 10,$namespace = null,$dir = 'older',$ts = null) {
$append = '';
if ($ts !== null) { $append .= '&rcstart='.urlencode($ts); }
$append .= '&rcdir='.urlencode($dir);
if ($namespace !== null) { $append .= '&rcnamespace='.urlencode($namespace); }
$x = $this->http->get($this->apiurl.'?action=query&list=recentchanges&rcprop=user|comment|flags|timestamp|title|ids|sizes&format=php&rclimit='.$count.$append);
$x = unserialize($x);
return $x['query']['recentchanges'];
}
function usercontribs ($user,$count = 50,$continue = null,$dir = 'older') {
if ($continue != null) {
$append = '&ucstart='.urlencode($continue);
} else {
$append = '';
}
$x = $this->http->get($this->apiurl.'?action=query&format=php&list=usercontribs&ucuser='.urlencode($user).'&uclimit='.urlencode($count).'&ucdir='.urlencode($dir).$append);
$x = unserialize($x);
return $x['query']['usercontribs'];
}
function revisions ($page,$count = 1,$dir = 'older',$content = false,$revid = null,$wait = true) {
$x = $this->http->get($this->apiurl.'?action=query&prop=revisions&titles='.urlencode($page).'&rvlimit='.urlencode($count).'&rvprop=timestamp|ids|user|comment'.(($content)?'|content':'').'&format=php&rvdir='.urlencode($dir).(($revid !== null)?'&rvstartid='.urlencode($revid):''));
$x = unserialize($x);
if ($revid !== null) {
$found = false;
if (!isset($x['query']['pages']) or !is_array($x['query']['pages'])) die();
foreach ($x['query']['pages'] as $data) {
if (!isset($data['revisions']) or !is_array($data['revisions'])) die();
foreach ($data['revisions'] as $data2) if ($data2['revid'] == $revid) $found = true;
unset($data,$data2);
break;
}
if ($found == false) {
if ($wait == true) {
sleep(1);
return $this->revisions($page,$count,$dir,$content,$revid,false);
} else {
die('Revision error.'."\n");
}
}
}
foreach ($x['query']['pages'] as $data) {
return $data['revisions'];
}
}
function categorymembers ($category,$count = 500,$continue = null) {
if ($continue != null) {
$append = '&cmcontinue='.urlencode($continue);
} else {
$append = '';
}
$x = $this->http->get($this->apiurl.'?action=query&list=categorymembers&cmcategory='.urlencode($category).'&format=php&cmlimit='.$count.$append);
$x = unserialize($x);
return $x['query']['categorymembers'];
}
function backlinks ($page,$count = 500,&$continue = null) {
if ($continue != null) {
$append = '&blcontinue='.urlencode($continue);
} else {
$append = '';
}
$x = $this->http->get($this->apiurl.'?action=query&list=backlinks&bltitle='.urlencode($page).'&format=php&bllimit='.$count.$append);
$x = unserialize($x);
$continue = $x['query-continue']['backlinks']['blcontinue'];
return $x['query']['backlinks'];
}
function embeddedin ($page,$count = 500,&$continue = null) {
if ($continue != null) {
$append = '&eicontinue='.urlencode($continue);
} else {
$append = '';
}
$x = $this->http->get($this->apiurl.'?action=query&list=embeddedin&eititle='.urlencode($page).'&format=php&eilimit='.$count.$append);
$x = unserialize($x);
$continue = $x['query-continue']['embeddedin']['eicontinue'];
return $x['query']['embeddedin'];
}
function listprefix ($prefix,$namespace = 0,$count = 500,$continue = null) {
$append = '&apnamespace='.urlencode($namespace);
if ($continue != null) {
$append .= '&apfrom='.urlencode($continue);
}
$x = $this->http->get($this->apiurl.'?action=query&list=allpages&apprefix='.urlencode($prefix).'&format=php&aplimit='.$count.$append);
$x = unserialize($x);
return $x['query']['allpages'];
}
}
class wikipediaindex {
private $http;
public $indexurl = 'http://en.wikipedia.org/w/index.php';
private $postinterval = 0;
private $lastpost;
function __construct () {
global $__wp__http;
if (!isset($__wp__http)) {
$__wp__http = new http;
}
$this->http = &$__wp__http;
}
function post ($page,$data,$summery = '',$minor = false) {
global $user;
global $maxlag;
global $irc;
global $irctechchannel;
global $run;
global $maxlagkeepgoing;
// if ((time() - $this->lastpost) < $this->postinterval) {
// sleep($this->postinterval - (time() - $this->lastpost));
// } /* Slightly more effecient than sleeping 30 seconds after each post. */
$html = $this->http->get($this->indexurl.'?title='.urlencode($page).'&action=edit&maxlag='.urlencode($maxlag));
if (preg_match('/Waiting for ([^ ]*): ([0-9.-]+) seconds lagged/',$html,$lagged)) {
if (is_resource($irc)) {
foreach(explode(',',$irctechchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :'.$lagged[1].' is lagged out by '.$lagged[2].' seconds. ('.$lagged[0].')'."\n");
}
}
sleep(10);
if ($maxlagkeepgoing != true) { return false; }
else { $html = $this->http->get($this->indexurl.'?title='.urlencode($page).'&action=edit'); }
} /* If server is lagged, wait 10 seconds, then return false. */
if (preg_match('/'.preg_quote('{{nobots}}','/').'/i',$html)) { return false; } /* Honor the bots flags */
if (preg_match('/'.preg_quote('{{bots|allow=none}}','/').'/i',$html)) { return false; }
if (preg_match('/'.preg_quote('{{bots|deny=all}}','/').'/i',$html)) { return false; }
if (preg_match('/'.preg_quote('{{bots|deny=','/').'(.*)'.preg_quote('}}','/').'/i',$html,$m)) { if (in_array(explode(',',$m[1]),$user)) { return false; } } /* /Honor the bots flags */
if (!preg_match('/'.preg_quote($user,'/').'/i',$html)) { return false; } /* We need to be logged in */
// if (preg_match('/'.preg_quote('You have new messages','/').'/i',$html)) { return false; } /* Check talk page */
$wpq = new wikipediaquery; $wpq->queryurl = str_replace('index.php','query.php',$this->indexurl);
// preg_match('/([0-9a-f]{32})/i',$wpq->getpage('User:'.$user.'/FalsePositives/md5'),$m); /* Check the false positives page */
// if (strtolower($m[1]) == strtolower(md5($wpq->getpage('User:'.$user.'/FalsePositives')))) { return false; }
if (!preg_match('/(yes|enable|true)/i',((isset($run))?$run:$wpq->getpage('User:'.$user.'/Run')))) { return false; } /* Check /Run page */
$x = $this->forcepost($page,$data,$summery,$minor,$html); /* Go ahead and post. */
$this->lastpost = time();
return $x;
}
function forcepost ($page,$data,$summery = '',$minor = false,$edithtml = null) {
$post['wpSection'] = '';
$post['wpScrolltop'] = '';
if ($minor == true) { $post['wpMinoredit'] = 1; }
$post['wpTextbox1'] = $data;
$post['wpSummary'] = $summery;
if ($edithtml == null) {
$html = $this->http->get($this->indexurl.'?title='.urlencode($page).'&action=edit');
} else {
$html = $edithtml;
}
preg_match('|\<input type\=\\\'hidden\\\' value\=\"(.*)\" name\=\"wpStarttime\" /\>|U',$html,$m);
$post['wpStarttime'] = $m[1];
preg_match('|\<input type\=\\\'hidden\\\' value\=\"(.*)\" name\=\"wpEdittime\" /\>|U',$html,$m);
$post['wpEdittime'] = $m[1];
preg_match('|\<input type\=\\\'hidden\\\' value\=\"(.*)\" name\=\"wpEditToken\" /\>|U',$html,$m);
$post['wpEditToken'] = $m[1];
preg_match('|\<input name\=\"wpAutoSummary\" type\=\"hidden\" value\=\"(.*)\" /\>|U',$html,$m);
$post['wpAutoSummary'] = $m[1];
return $this->http->post($this->indexurl.'?title='.urlencode($page).'&action=submit',$post);
}
}
?>
[edit] Diff function (diff.function.php)
<?PHP
function diff ($old,$new,$nret = true,$inline = false) {
// if ($inline) {
// return str_replace(array("\n",chr(92).chr(92),'\n'),array(' ',chr(92),"\n"),diff(implode("\n",explode(' ',str_replace(array(chr(92),"\n"),array(chr(92).chr(92),'\n'),$old))),implode("\n",explode(' ',str_replace(array(chr(92),"\n"),array(chr(92).chr(92),'\n'),$new))),$nret,false));
// }
$file1 = tempnam('/tmp','diff_');
$file2 = tempnam('/tmp','diff_');
file_put_contents($file1,$old);
file_put_contents($file2,$new);
$out = array();
if ($inline) {
// echo 'EXEC: wdiff -3'.(($nret)?'1':'2').' '.escapeshellarg($file1).' '.escapeshellarg($file2)."\n";
@exec('wdiff -3'.(($nret)?'1':'2').' '.escapeshellarg($file1).' '.escapeshellarg($file2),$out);
foreach ($out as $key => $line) {
if ($line == '======================================================================') unset($out[$key]);
elseif ($nret) $out[$key] = '> '.$line;
else $out[$key] = '< '.$line;
}
} else {
@exec('diff -d --suppress-common-lines '.escapeshellarg($file1).' '.escapeshellarg($file2),$out);
}
$out2 = array();
foreach ($out as $line) {
if (
(
($nret)
and (preg_match('/^\> .*$/',$line))
)
or (
(!$nret)
and (preg_match('/^\< .*$/',$line))
)
) {
$out2[] = substr($line,2);
}
}
$out = $out2;
unset($out2);
unlink($file1);
unlink($file2);
return implode("\n",$out);
}
?>
[edit] Source to ClueBot
<?PHP
declare(ticks = 1);
function sig_handler($signo) {
switch ($signo) {
case SIGCHLD:
while (($x = pcntl_waitpid(0, $status, WNOHANG)) != -1) {
if ($x == 0) break;
$status = pcntl_wexitstatus($status);
}
break;
}
}
pcntl_signal(SIGCHLD, "sig_handler");
function score ($list,$data) {
$ret = 0;
foreach ($list as $preg => $pts) {
if ($x = preg_match_all($preg,$data,$m)) {
// echo $x.'*'.$pts.' ('.$preg.')'."\n";
$ret += $pts * $x;
}
}
// echo 'Score: '.$ret."\n";
return $ret;
}
include '../diff.function.php'; /* The diff function. */
include '../wikibot.classes.php'; /* The wikipedia classes. */
include 'cluebot.config.php'; /* This file is very simple, but it contains sensitive information, we just define $user, $ircserver, $ircport, $ircchannel, $pass, $owner, and $status. */
include 'cluebot.scorelist.php'; /* This file is uploaded as well as the main file. */
$wpapi = new wikipediaapi;
$wpq = new wikipediaquery;
$wpi = new wikipediaindex;
$wpapi->login($user,$pass);
$mysql = mysql_pconnect($mysqlhost.':'.$mysqlport,$mysqluser,$mysqlpass);
if (!$mysql) { die('Could not connect: ' . mysql_error()); }
if (!mysql_select_db($mysqldb, $mysql)) { die ('Can\'t use database : ' . mysql_error()); }
$ircconfig = explode("\n",$wpq->getpage('User:'.$owner.'/CBChannels.js'));
$tmp = array();
foreach($ircconfig as $tmpline) { if (substr($tmpline,0,1) != '#') { $tmpline = explode('=',$tmpline,2); $tmp[trim($tmpline[0])] = trim($tmpline[1]); } }
$ircchannel = $tmp['ircchannel'];
$ircdebugchannel = $tmp['ircdebugchannel'];
$ircreportchannel = $tmp['ircreportchannel'];
$ircvandalismchannel = $tmp['ircvandalismchannel'];
$ircaivchannel = $tmp['ircaivchannel'];
$irctechchannel = $tmp['irctechchannel'];
$ircproxychannels = $tmp['ircproxychannels'];
$ircunrevertedchannels = $tmp['ircunrevertedchannels'];
$ircbagtrialchannels = $tmp['ircbagtrialchannels'];
$ircotherchannels = $tmp['ircotherchannels'];
unset($tmp,$tmpline);
$stalkbots = array();
$trialbots = explode("\n",$wpq->getpage('Wikipedia:Bots/Requests for approval'));
foreach ($trialbots as $trialbot) if (preg_match('/\{\{BRFA\|(.*)\|.*\|Trial\}\}/',str_replace(array("\n","\r"),'',$trialbot),$m)) $stalkbots[$m[1]] = 1;
$irc = fsockopen($ircserver,$ircport,$ircerrno,$ircerrstr,15);
$ircpid = pcntl_fork();
if ($ircpid == 0) {
fwrite($irc,'PASS '.$ircpass."\n");
fwrite($irc,'USER '.$user.' "1" "1" :ClueBot Wikipedia Bot.'."\n");
fwrite($irc,'NICK '.$user."\n");
while (!feof($irc)) {
$data = str_replace(array("\n","\r"),'',fgets($irc,1024));
// echo 'IRC: '.$data."\n";
$d = explode(' ',$data);
if (strtolower($d[0]) == 'ping') {
fwrite($irc,'PONG '.$d[1]."\n");
} elseif (($d[1] == '376') or ($d[1] == '422')) {
// fwrite($irc,'PRIVMSG NickServ :identify '.$pass."\n");
// sleep(2);
fwrite($irc,'JOIN '.$ircchannel.','.$ircdebugchannel.','.$ircreportchannel.','.$ircvandalismchannel.','.$ircaivchannel.','.$irctechchannel.','.$ircproxychannels.','.$ircunrevertedchannels.','.$ircbagtrialchannels.','.$ircotherchannels."\n");
foreach (explode(',',$ircchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :IRC logging enabled.'."\n");
}
} elseif (strtolower($d[1]) == 'privmsg') {
if (substr($d[3],0,2) == ':!') {
if (strtolower($d[2]) == '#wikipedia-en') { $tmp = explode('!',substr($d[0],1)); $cmd = 'NOTICE '.$tmp[0]; }
elseif (strtolower($d[2]) == strtolower($user)) { $tmp = explode('!',substr($d[0],1)); $cmd = 'NOTICE '.$tmp[0]; }
else { $cmd = 'PRIVMSG '.$d[2]; }
switch (substr(strtolower($d[3]),2)) {
case 'edit':
if (preg_match("/\[\[(.*)\]\]/",$data,$m)) {
$rv = $wpapi->revisions($m[1],1,'older');
fwrite($irc,$cmd.' :[['.$m[1].']] http://en.wikipedia.org/w/index.php?title='.urlencode($m[1]).'&;diff=prev' .
'&oldid='.urlencode($rv[0]['revid']).' * '.$rv[0]['user'].' * '.$rv[0]['comment']."\n");
} else {
fwrite($irc,$cmd.' :Couldn\'t find link.'."\n");
}
break;
case 'stalk':
if (preg_match("/\[\[User:(.*)\]\]/",$data,$m)) {
$uc = $wpapi->usercontribs($m[1],1);
fwrite($irc,$cmd.' :[['.$uc[0]['title'].']] http://en.wikipedia.org/w/index.php?title='.urlencode($uc[0]['title']).'&;diff=prev' .
'&oldid='.urlencode($uc[0]['revid']).' * '.$m[1].' * '.$uc[0]['comment']."\n");
} else {
fwrite($irc,$cmd.' :Couldn\'t find link.'."\n");
}
break;
case 'beaten':
if (preg_match("/\[\[User:(.*)\]\]/",$data,$m)) {
if (!mysql_ping($mysql)) { $mysql = mysql_pconnect($mysqlhost.':'.$mysqlport,$mysqluser,$mysqlpass); mysql_select_db($mysqldb, $mysql); }
$x = mysql_fetch_assoc(mysql_query('SELECT COUNT(`id`) AS `count` FROM `beaten` WHERE `user` = \''.mysql_real_escape_string($m[1]).'\' GROUP BY `user`'));
$y = mysql_fetch_assoc(mysql_query('SELECT SQL_CALC_FOUND_ROWS COUNT(`id`) AS `count2` FROM `beaten` GROUP BY `user` HAVING `count2` > \''.mysql_real_escape_string($x['count']).'\' LIMIT 1'));
$z = mysql_fetch_assoc(mysql_query('SELECT FOUND_ROWS() as `ahead`'));
fwrite($irc,$cmd.' :[[User:'.$m[1].']] has beaten me '.(($x['count'] != '')?$x['count']:'0').' times. There are '.$z['ahead'].' users who have beaten me more times.'."\n");
unset($x,$y);
} else {
fwrite($irc,$cmd.' :Couldn\'t find link.'."\n");
}
break;
case 'vandalcount':
if (preg_match("/\[\[(.*)\]\]/",$data,$m)) {
$tmp = unserialize(file_get_contents('oftenvandalized.txt'));
if (isset($tmp[$m[1]])) {
fwrite($irc,$cmd.' :[['.$m[1].']] has been vandalized '.count($tmp[$m[1]]).' time(s) in the last 48 hours.'."\n");
} else {
fwrite($irc,$cmd.' :[['.$m[1].']] has not been vandalized in the last 48 hours.'."\n");
}
} else {
fwrite($irc,$cmd.' :Couldn\'t find link.'."\n");
}
break;
case 'heuristics':
include 'cluebot.heuristics.config.php';
$stats = unserialize(file_get_contents('cluebot.heuristics.stats.txt'));
fwrite($irc,$cmd.' :I have the following heuristics enabled: '.implode(', ',$heuristics).".\n");
foreach ($stats as $heuristic => $count) {
fwrite($irc,$cmd.' :The '.$heuristic.' heuristic has been matched '.$count.' times.'."\n");
}
unset($count,$heuristic,$stats,$heuristics);
break;
case 'status':
$ov = unserialize(file_get_contents('oftenvandalized.txt'));
foreach ($ov as $title => $array) {
if (count($array) == 0) unset($ov[$title]);
}
file_put_contents('oftenvandalized.txt',serialize($ov));
$count = count($ov);
$titles = unserialize(file_get_contents('titles.txt'));
foreach ($titles as $title => $time) {
if ((time() - $time) > (24*60*60)) {
unset($titles[$title]);
}
}
file_put_contents('titles.txt',serialize($titles));
$tcount = count($titles);
foreach ($ov as $x => $y) {
$ocount[$x] = count($y);
}
arsort($ocount);
foreach ($ocount as $x => $y) {
$mova = $x;
$movacount = $y;
break;
}
preg_match('/\(\'\'\'\[\[([^|]*)\|more...\]\]\'\'\'\)/iU',$wpq->getpage('Wikipedia:Today\'s featured article/'.date('F j, Y')),$tfa);
$tfa = $tfa[1];
if (!preg_match('/(yes|enable|true)/i',$wpq->getpage('User:'.$user.'/Run'))) {
$run = false;
} else {
$run = true;
}
$top5beat = array();
if (!mysql_ping($mysql)) { $mysql = mysql_pconnect($mysqlhost.':'.$mysqlport,$mysqluser,$mysqlpass); mysql_select_db($mysqldb, $mysql); }
$q = mysql_query('SELECT `user`,COUNT(`id`) AS `count` FROM `cluebot_enwiki`.`beaten` WHERE `user` != \'\' GROUP BY `user` HAVING `count` > 1 ORDER BY `count` DESC LIMIT 5');
while ($x = mysql_fetch_assoc($q)) {
$top5beat[] = $x['user'].' ('.$x['count'].')';
}
unset($x,$q);
$top5beat = implode(' - ',$top5beat);
fwrite($irc,$cmd.' :I am '.$user.'. I am currently '.($run?'enabled':'disabled').'. I currently have '.$wpq->contribcount($user).' contributions.'."\n");
fwrite($irc,$cmd.' :I have attempted to revert '.$tcount.' unique article/user combinations in the last 24 hours. ' .
'I know of '.$count.' different articles that have been vandalized in the last 48 hours.'."\n"
);
fwrite($irc,$cmd.' :[['.$mova.']] is the most vandalized page with a total of '.$movacount.' vandalisms in the last 48 hours. ' .
'Today\'s featured article is: [['.$tfa.']].'."\n"
);
fwrite($irc,$cmd.' :The following users have beat me to the revert the most: '.$top5beat."\n");
fwrite($irc,$cmd.' :I log all information to '.$ircchannel.'. This channel is '.$d[2].'.'."\n");
unset($x,$y,$count,$ov,$tcount,$ocount,$mova,$movacount,$tfa,$run,$title,$titles,$time,$top5beat);
break;
case 'warninglevel':
if (preg_match("/\[\[User:(.*)\]\]/",$data,$n)) {
$warning = 0;
if (preg_match_all('/<!-- Template:(uw-[a-z]*(\d)(im)?|Blatantvandal \(serious warning\)) -->;.*(\d{2}):(\d{2}), (\d+) ([a-zA-Z]+) (\d{4}) \(UTC\)/iU',
$wpq->getpage('User talk:'.$n[1]),
$match,PREG_SET_ORDER)
) {
foreach ($match as $m) {
$month = array('January' => 1, 'February' => 2, 'March' => 3,
'April' => 4, 'May' => 5, 'June' => 6, 'July' => 7,
'August' => 8, 'September' => 9, 'October' => 10,
'November' => 11, 'December' => 12
);
if ($m[1] == 'Blatantvandal (serious warning)') $m[2] = 4;
if ((time() - gmmktime($m[4],$m[5],0,$month[$m[7]],$m[6],$m[8])) <= (2*24*60*60)) {
if ($m[2] > $warning) { $warning = $m[2]; }
}
}
}
fwrite($irc,$cmd.' :[[User:'.$n[1].']] is at warning level '.$warning.".\n");
} else {
fwrite($irc,$cmd.' :Couldn\'t find link.'."\n");
}
break;
case 'count':
if (preg_match("/\[\[User:(.*)\]\]/",$data,$n)) {
fwrite($irc,$cmd.' :[[User:'.$n[1].']] has '.$wpq->;contribcount($n[1])." contributions.\n");
} else {
fwrite($irc,$cmd.' :Couldn\'t find link.'."\n");
}
break;
case 'help':
fwrite($irc,$cmd.' :Please see [[User:'.$user.']].'."\n");
break;
case 'eval':
$tmp = explode(' ',$data,6);
$tmp1 = explode('!',substr($d[0],1));
if ($d[4] == md5($thesecret.$tmp1[0].$tmp[5])) {
eval($tmp[5]);
} else {
fwrite($irc,$cmd.' :Code incorrect.'."\n");
}
break;
case 'cbproxy':
$tmp = explode(' ',$data,6);
$tmp1 = explode('!',substr($d[0],1));
if ($tmp1[0] == 'ClueBot-Bopm') {
foreach (explode(',',$ircproxychannels) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :!admin '.$tmp[5]."\n");
}
$data = $wpq->getpage('Wikipedia:WikiProject on open proxies');
if (strpos($data,$tmp[4]) === false) {
$header = explode('{{proxyip2|127.0.0.1}} || Example',$data,2);
$header[0] .= '{{proxyip2|127.0.0.1}} || Example ';
$footer = $header[1];
$header = $header[0];
$data = "\n".'{{proxyip2|'.$tmp[4].'}} || '.$tmp[5].' <font face="Copperplate Gothic">[[User:Gp75motorsports|<font color="#FF0000">Gp</font><font color="#000000">75</font><font color="#FF0000">motorsports</font>]] <sup><font color="#800000">[[User talk:Gp75motorsports|REV LIMITER]]</font></sup></font> 22:39, 2 January 2008 (UTC)'."\n";
$data = $header.$data.$footer;
unset($header,$footer);
$wpi->post('Wikipedia:WikiProject on open proxies',$data,'Adding '.$tmp[4].'.');
unset($data);
}
}
break;
}
}
}
}
die();
}
$heuristics = "==Heuristics==\n\n===Config (cluebot.heuristics.config.php)===\n\n<pre>".htmlentities(file_get_contents('cluebot.heuristics.config.php'))."</pre>\n\n";
foreach (glob('heuristics/cluebot.*.heuristic.php') as $heuristic) $heuristics .= '==='.$heuristic."===\n\n<pre>".htmlentities(file_get_contents($heuristic))."</pre>\n\n";
unset($heuristic);
$wpi->forcepost('User:'.$user.'/Source',
'The following is automatically generated by [[User:'.$user.'|'.$user."]].\n\n\n\n==Classes (wikibot.classes.php)==\n\n<pre>" .
htmlentities(file_get_contents('../wikibot.classes.php'))."</pre>\n\n\n\n==Diff function (diff.function.php)==\n\n<pre>" .
htmlentities(file_get_contents('../diff.function.php'))."</pre>\n\n\n\n==Source to ".$user .
"==\n\n".'<pre>'.htmlentities(file_get_contents(__FILE__))."</pre>\n\n\n\n" .
$heuristics .
"==Score list==\n\n".'<pre>'.htmlentities(file_get_contents('cluebot.scorelist.php'))."</pre>\n\n\n\n<font face="Copperplate Gothic">[[User:Gp75motorsports|<font color="#FF0000">Gp</font><font color="#000000">75</font><font color="#FF0000">motorsports</font>]] <sup><font color="#800000">[[User talk:Gp75motorsports|REV LIMITER]]</font></sup></font> 22:39, 2 January 2008 (UTC)",
'Automated source upload.'); /* Our source code, we force post this because this is *our* page, and it triggers the nobots. */
unset($heuristics);
$wpi->forcepost('User:'.$user,
"{{User:ClueBot Commons/Userpage}}\n",
'Automated bot userpage set.'); /* Our page, we force post this because this is *our* page. */
$tfas = 0;
$pipe = fopen('thepipe','w');
$stdin = fopen('php://stdin','r');
$run = $wpq->getpage('User:'.$user.'/Run');
$wl = $wpq->getpage('User:'.$user.'/Whitelist');
$optin = $wpq->getpage('User:'.$user.'/Optin');
$aoptin = $wpq->getpage('User:'.$user.'/AngryOptin');
unset($tmp,$tmp2,$tmp3);
$tmp = explode("\n",$wpq->getpage('User:'.$owner.'/CBAutostalk.js'));
foreach ($tmp as $tmp2) { if (substr($tmp2,0,1) != '#') { $tmp3 = explode('|',$tmp2,2); $stalk[$tmp3[0]] = trim($tmp3[1]); } }
$tmp = explode("\n",$wpq->getpage('User:'.$owner.'/CBAutoedit.js'));
foreach ($tmp as $tmp2) { if (substr($tmp2,0,1) != '#') { $tmp3 = explode('|',$tmp2,2); $edit[$tmp3[0]] = trim($tmp3[1]); } }
unset($tmp,$tmp2,$tmp3);
print_r($stalk); print_r($edit);
while (1) {
$feed = fsockopen($feedhost,$feedport,$feederrno,$feederrstr,30);
if (!$feed) {
sleep(10);
$feed = fsockopen($feedhost,$feedport,$feederrno,$feederrstr,30);
if (!$feed) die($feederrstr.' ('.$feederrno.')');
}
fwrite($feed,'USER '.$user.' "1" "1" :ClueBot Wikipedia Bot.'."\n");
fwrite($feed,'NICK '.$user."\n");
while (!feof($feed)) {
$line = str_replace(array("\n","\r","\002"),'',fgets($feed,1024));
$line = preg_replace('/\003(\d\d?(,\d\d?)?)?/','',$line);
// echo 'FEED: '.$line."\n";
if (!$line) { fclose($feed); break; }
$linea= explode(' ',$line,4);
if (strtolower($linea[0]) == 'ping') {
fwrite($feed,'PONG '.$linea[1]."\n");
} elseif (($linea[1] == '376') or ($linea[1] == '422')) {
fwrite($feed,'JOIN '.$feedchannel."\n");
} elseif ((strtolower($linea[1]) == 'privmsg') and (strtolower($linea[2]) == strtolower($feedchannel))) {
$message = substr($linea[3],1);
if (preg_match('/^\[\[((Talk|User|Wikipedia|Image|MediaWiki|Template|Help|Category|Portal|Special)(( |_)talk)?:)?([^\x5d]*)\]\] (\S*) (http:\/\/en\.wikipedia\.org\/w\/index\.php\?title=[^&;]*&diff=(\d*)&oldid=(\d*)|http:\/\/en\.wikipedia\.org\/wiki\/\S+)? \* ([^*]*) \* (\(([^)]*)\))? (.*)$/',$message,$m)) {
$change['namespace'] = $m[1];
$change['title'] = $m[5];
$change['flags'] = $m[6];
$change['url'] = $m[7];
$change['revid'] = $m[8];
$change['old_revid'] = $m[9];
$change['user'] = $m[10];
$change['length'] = $m[12];
$change['comment'] = $m[13];
// include 'cluebot.stalk.config.php';
$stalkchannel = array();
foreach ($stalk as $key => $value) if (fnmatch(str_replace('_',' ',$key),str_replace('_',' ',$change['user']))) $stalkchannel = array_merge($stalkchannel,explode(',',$value));
foreach ($stalkbots as $key => $value) if (fnmatch(str_replace('_',' ',$key),str_replace('_',' ',$change['user']))) $stalkchannel = array_merge($stalkchannel,explode(',',$ircbagtrialchannels));
foreach ($edit as $key => $value) if (fnmatch(str_replace('_',' ',$key),str_replace('_',' ',$change['namespace'].$change['title']))) $stalkchannel = array_merge($stalkchannel,explode(',',$value));
// if ($change['user'] == $owner) $stalkchannel[] = $ircchannel;
$stalkchannel = array_unique($stalkchannel);
foreach ($stalkchannel as $y) {
fwrite($irc,'PRIVMSG '.$y.' :New edit: [['.$change['namespace'].$change['title'].']] http://en.wikipedia.org/w/index.php?title=' .
urlencode($change['namespace'].$change['title']).'&;diff=prev'.'&oldid='.urlencode($change['revid']).' * '.$change['user'] .
' * '.$change['comment']."\n");
}
if (($change['namespace'] == 'User:') or ($change['namespace'] == 'User talk:')) {
if (strtolower($change['title']) == strtolower($user.'/Run')) { $run = $wpq->getpage('User:'.$user.'/Run'); }
if (strtolower($change['title']) == strtolower($user.'/Whitelist')) { $wl = $wpq->getpage('User:'.$user.'/Whitelist'); }
if (strtolower($change['title']) == strtolower($user.'/Optin')) { $optin = $wpq->getpage('User:'.$user.'/Optin'); }
if (strtolower($change['title']) == strtolower($user.'/AngryOptin')) { $aoptin = $wpq->getpage('User:'.$user.'/AngryOptin'); }
if (strtolower($change['title']) == strtolower($owner.'/CBAutostalk.js')) {
unset($stalk);
$tmp = explode("\n",$wpq->getpage('User:'.$owner.'/CBAutostalk.js'));
foreach ($tmp as $tmp2) { if (substr($tmp2,0,1) != '#') { $tmp3 = explode('|',$tmp2,2); $stalk[$tmp3[0]] = trim($tmp3[1]); } }
unset($tmp,$tmp2,$tmp3);
print_r($stalk);
}
if (strtolower($change['title']) == strtolower($owner.'/CBAutoedit.js')) {
unset($edit);
$tmp = explode("\n",$wpq->getpage('User:'.$owner.'/CBAutoedit.js'));
foreach ($tmp as $tmp2) { if (substr($tmp2,0,1) != '#') { $tmp3 = explode('|',$tmp2,2); $edit[$tmp3[0]] = trim($tmp3[1]); } }
unset($tmp,$tmp2,$tmp3);
print_r($edit);
}
if (strtolower($change['title']) == strtolower($owner.'/CBChannels.js')) {
$ircconfig = explode("\n",$wpq->getpage('User:'.$owner.'/CBChannels.js'));
$tmp = array();
foreach($ircconfig as $tmpline) { if (substr($tmpline,0,1) != '#') { $tmpline = explode('=',$tmpline,2); $tmp[trim($tmpline[0])] = trim($tmpline[1]); } }
print_r($tmp);
$tmpold = array();
$tmpnew = array();
foreach ($tmp as $tmp2) foreach (explode(',',$tmp2) as $tmp3) $tmpnew[$tmp3] = 1;
foreach (explode(',',$ircchannel.','.$ircdebugchannel.','.$ircreportchannel.','.$ircvandalismchannel.','.$ircaivchannel.','.$irctechchannel.','.$ircproxychannels.','.$ircunrevertedchannels.','.$ircbagtrialchannels.','.$ircotherchannels) as $tmp3) $tmpold[$tmp3] = 1;
foreach ($tmpold as $tmp2 => $tmp3) if (isset($tmpnew[$tmp2])) unset($tmpold[$tmp2],$tmpnew[$tmp2]);
foreach ($tmpnew as $tmp2 => $tmp3) $tmpnew1[] = $tmp2;
foreach ($tmpold as $tmp2 => $tmp3) $tmpold1[] = $tmp2;
$tmpold = $tmpold1; $tmpnew = $tmpnew1; unset($tmpold1,$tmpnew1);
fwrite($irc,'JOIN '.implode(',',$tmpnew)."\n");
fwrite($irc,'PART '.implode(',',$tmpold)."\n");
$ircchannel = $tmp['ircchannel'];
$ircdebugchannel = $tmp['ircdebugchannel'];
$ircreportchannel = $tmp['ircreportchannel'];
$ircvandalismchannel = $tmp['ircvandalismchannel'];
$ircaivchannel = $tmp['ircaivchannel'];
$irctechchannel = $tmp['irctechchannel'];
$ircproxychannels = $tmp['ircproxychannels'];
$ircunrevertedchannels = $tmp['ircunrevertedchannels'];
$ircbagtrialchannels = $tmp['ircbagtrialchannels'];
$ircotherchannels = $tmp['ircotherchannels'];
unset($tmp,$tmpline,$tmpold,$tmpnew,$tmp2,$tmp3);
}
}
if ($change['namespace'].$change['title'] == 'Wikipedia:Bots/Requests for approval') {
$stalkbots = array();
$trialbots = explode("\n",$wpq->getpage('Wikipedia:Bots/Requests for approval'));
foreach ($trialbots as $trialbot) if (preg_match('/\{\{BRFA\|(.*)\|.*\|Trial\}\}/',str_replace(array("\n","\r"),'',$trialbot),$m)) $stalkbots[$m[1]] = 1;
}
if (($change['namespace'] != '') and ((!preg_match('/\* \[\[('.preg_quote($change['namespace'].$change['title'],'/').')\]\] \- .*/i',$optin)))) { /* echo 'Continuing ...'."\n"; */ continue; }
$change['justtitle'] = $change['title'];
$change['title'] = $change['namespace'].$change['title'];
if (
((time() - $tfas) >= 1800)
and (preg_match('/\(\'\'\'\[\[([^|]*)\|more...\]\]\'\'\'\)/iU',$wpq->getpage('Wikipedia:Today\'s featured article/'.date('F j, Y')),$tfam))
) {
$tfas = time();
$tfa = $tfam[1];
//echo "TFA: ".$tfa."\n";
}
$s = null;
$pid = @pcntl_fork();
if ($pid != 0) continue;
$hutime = microtime(1);
include 'cluebot.heuristics.config.php';
foreach ($heuristics as $heuristic) {
$heuristicret = false;
include 'heuristics/cluebot.'.$heuristic.'.heuristic.php';
if ($heuristicret == true) {
$stats = unserialize(file_get_contents('cluebot.heuristics.stats.txt'));
$stats[$heuristic]++;
file_put_contents('cluebot.heuristics.stats.txt',serialize($stats));
unset($stats);
break;
}
}
if ($heuristicret == true) echo 'Heuristics time: '.(microtime(1) - $hutime)."\n";
unset($hutime);
if (
($heuristicret == true)
) {
if (
(
( /* IP users with 250 contributions are fine .. */
(long2ip(ip2long($change['user'])) == $change['user'])
/* and ($uc = $wpapi->usercontribs($change['user'],250))
and (!isset($uc[249])) */
)
or ( /* Users with 50 contributions are fine .. */
(long2ip(ip2long($change['user'])) != $change['user'])
and ($wpq->contribcount($change['user']) < 50)
)
)
and ( /* Whitelisted users are ok. */
/* ($wl = $wpq->getpage('User:'.$user.'/Whitelist'))
and */ (!preg_match('/^\* \[\[User:('.preg_quote($change['user'],'/').')|\1\]\] \- .*/',$wl))
)
) {
// $vandalpage = $wpq->;getpage('User:'.$user.'/PossibleVandalism');
// $x = explode("\n\n",$vandalpage);
// foreach ($x as $k => $y) {
// if (preg_match('/(\d+)\-(\d+)\-(\d+)T(\d+):(\d+):(\d+)/',$y,$m)) {
// if ((time() - gmmktime($m[4],$m[5],$m[6],$m[2],$m[3],$m[1])) > (5*60*60)) {
// unset($x[$k]);
// }
// }
// }
// $vandalpage = implode("\n\n",$x);
$diff = 'http://en.wikipedia.org/w/index.php' .
'?title='.urlencode($change['title']) .
'&diff='.urlencode($change['revid']) .
'&oldid='.urlencode($change['old_revid']);
$report = '[['.$change['title'].']] was ' .
'['.$diff.' changed] by ' .
'[[User:'.$change['user'].'|'.$change['user'].']] ' .
'[[Special:Contributions/'.$change['user'].'|(c)]] ' .
'[[User talk:'.$change['user'].'|(t)]] ' .
$reason.' on '.gmdate('c');
// $datatopost = $vandalpage."\n\n".'Possible [[WP:VAN|vandalism]]: '.$report." <font face="Copperplate Gothic">[[User:Gp75motorsports|<font color="#FF0000">Gp</font><font color="#000000">75</font><font color="#FF0000">motorsports</font>]] <sup><font color="#800000">[[User talk:Gp75motorsports|REV LIMITER]]</font></sup></font> 22:39, 2 January 2008 (UTC)\n";
if ($s == null) {
// $rv = $wpapi->revisions($change['title'],2,'older',true,$change['revid']);
// $s = score($scorelist,diff($rv[1]['*'],$rv[0]['*']));
// $s += (score($scorelist,diff($rv[1]['*'],$rv[0]['*'],false))) * -1;
$s = 'N/A';
}
$tmp = unserialize(file_get_contents('oftenvandalized.txt'));
foreach ($tmp as $key1 => $tmp2) {
foreach ($tmp2 as $key2 => $time) {
if ((time() - $time) > (2*24*60*60)) { unset($tmp[$key1][$key2]); }
}
}
$tmp[$change['title']][] = time();
if (count($tmp[$change['title']]) >= 30) {
foreach (explode(',',$ircreportchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :!admin [['.$change['title'].']] has been vandalized '.(count($tmp[$change['title']])).' times in the last 2 days.'."\n");
}
}
file_put_contents('oftenvandalized.txt',serialize($tmp));
if (
($rv = $wpapi->revisions($change['title'],1,'older'))
and ($rv[0]['revid'] == $change['revid'])
) { /* No need to continue further if it has been reverted */
echo 'Possible vandalism: '.$change['title'].' changed by '.$change['user'].' '.$reason.' on '.$rv[0]['timestamp'].'('.$s.").\n";
foreach (explode(',',$ircdebugchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :Possible vandalism: '.$change['title'].' changed by '.$change['user'].' '.$reason.' on '.$rv[0]['timestamp'].'('.$s.").\n");
fwrite($irc,'PRIVMSG '.$y.' :( http://en.wikipedia.org/w/index.php?title='.urlencode($change['title']).'&;action=history | '.$change['url'].' )'."\n");
}
fwrite($pipe,'http://en.wikipedia.org/w/index.php?title='.urlencode($change['title']).'&action=history'."\n"); /* Tell owner */
$mqtime = microtime(1);
$query = 'INSERT INTO `vandalism` ' .
'(`id`,`user`,`article`,`heuristic`,`reason`,`diff`,`old_id`,`new_id`,`reverted`) ' .
'VALUES ' .
'(NULL,\''.mysql_real_escape_string($change['user']).'\',' .
'\''.mysql_real_escape_string($change['title']).'\',' .
'\''.mysql_real_escape_string($heuristic).'\',' .
'\''.mysql_real_escape_string($reason).'\',' .
'\''.mysql_real_escape_string($change['url']).'\',' .
'\''.mysql_real_escape_string($change['old_revid']).'\',' .
'\''.mysql_real_escape_string($change['revid']).'\',0)';
//echo 'Mysql query: '.$query."\n";
if (!mysql_ping($mysql)) {
$mysql = mysql_pconnect($mysqlhost.':'.$mysqlport,$mysqluser,$mysqlpass);
if (!$mysql) { die('Could not connect: ' . mysql_error()); }
if (!mysql_select_db($mysqldb, $mysql)) { die ('Can\'t use database : ' . mysql_error()); }
}
mysql_query($query);
//echo 'Mysql error: '.mysql_error()."\n";
$mysqlid = mysql_insert_id();
echo 'MySQL time: '.(microtime(1) - $mqtime).' MySQL id: '.$mysqlid."\n";
unset($mqtime);
if (
(
(
(preg_match('/(assisted|manual)/i',$status))
and (print('Revert [y/N]? '))
and (strtolower(substr(fgets($stdin,3),0,1)) == 'y')
)
or (
(preg_match('/(read-write|rw|go|approved|trial)/i',$status))
)
)
and (
(
(
((time() - $tfas) < 1800)
or (
(preg_match('/\(\'\'\'\[\[([^|]*)\|more...\]\]\'\'\'\)/iU',$wpq->getpage('Wikipedia:Today\'s featured article/'.date('F j, Y')),$tfam))
and ($tfas = time())
and ($tfa = $tfam[1])
and ((print("TFA: ".$tfa."\n")) or (true))
)
)
and ($tfa == $change['title'])
)
or (
(preg_match('/\* \[\[('.preg_quote($change['title'],'/').')\]\] \- .*/i',$aoptin))
and ((fwrite($irc,'PRIVMSG '.$ircdebugchannel.' :Angry-reverting [['.$change['title'].']].'."\n")) or (true))
)
or (
(($tmp = unserialize(file_get_contents('titles.txt'))) !== false)
and ((!isset($tmp[$change['title'].$change['user']])) or ((time() - $tmp[$change['title'].$change['user']]) > (24*60*60)))
and ($tmp[$change['title'].$change['user']] = time())
and ((file_put_contents('titles.txt',serialize($tmp))) !== false)
)
)
) {
echo 'Reverting ...'."\n";
$rev = $wpapi->revisions($change['title'],5,'older',false,$change['old_revid']);
$revid = 0;
foreach ($rev as $revdata) {
if ($revdata['user'] != $change['user']) {
$revid = $revdata['revid'];
break;
}
}
if (($revdata['user'] == $user) or (in_array($revdata['user'],explode(',',$botfriends)))) { die(); /* Do not revert to us. */ }
if ($revid == 0) { die(); }
foreach (explode(',',$ircdebugchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :Reverting ...'."\n");
}
$revisiondata = $wpapi->revisions($change['title'],1,'older',true,$revid);
if (!$revisiondata[0]['*']) die();
$wpi->post(
$change['title'],
$revisiondata[0]['*'],
'Reverting possible vandalism by [[Special:Contributions/'.$change['user'].']] ' .
'to version by '.$revisiondata[0]['user'].'. ' .
'False positive? [[User:'.$user.'/FalsePositives|report it]]. '.
'Thanks, [[User:'.$user.'|'.$user.']]. ('.$mysqlid.') (Bot)'
); /* Revert the page */
$rv2 = $wpapi->revisions($change['title'],1);
if ($rv2[0]['user'] == $user) {
$warning = 0;
if (preg_match_all('/<!-- Template:(uw-[a-z]*(\d)(im)?|Blatantvandal \(serious warning\)) -->;.*(\d{2}):(\d{2}), (\d+) ([a-zA-Z]+) (\d{4}) \(UTC\)/iU',
$wpq->getpage('User talk:'.$change['user']),
$match,PREG_SET_ORDER)
) {
foreach ($match as $m) {
$month = array('January' => 1, 'February' => 2, 'March' => 3,
'April' => 4, 'May' => 5, 'June' => 6, 'July' => 7,
'August' => 8, 'September' => 9, 'October' => 10,
'November' => 11, 'December' => 12
);
if ($m[1] == 'Blatantvandal (serious warning)') $m[2] = 4;
if ((time() - gmmktime($m[4],$m[5],0,$month[$m[7]],$m[6],$m[8])) <= (2*24*60*60)) {
if ($m[2] > $warning) { $warning = $m[2]; }
}
}
}
$warning++;
if ($warning == 5) { /* Report them if they have been warned 4 times. */
$aivdata = $wpq->getpage('Wikipedia:Administrator_intervention_against_vandalism/TB2');
if (!preg_match('/'.preg_quote($change['user'],'/').'/i',$aivdata)) {
foreach(explode(',',$ircaivchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :!admin Reporting [[User:'.$change['user'].']] to [[WP:AIV]]. Contributions: [[Special:Contributions/'.$change['user'].']] Block: [[Special:Blockip/'.$change['user'].']]'."\n");
}
foreach (explode(',',$ircvandalismchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :computer bl add '.$change['user'].' x='.(24*$warning).' r=Vandalism to [['.$change['title'].']] (#'.$warning.").\n");
}
$wpi->post(
'Wikipedia:Administrator_intervention_against_vandalism/TB2',
$aivdata .
"\n\n* {{".((long2ip(ip2long($change['user'])) == $change['user'])?'IPvandal':'Vandal').'|'.$change['user'].'}}' .
' - '.$report." (Automated) <font face="Copperplate Gothic">[[User:Gp75motorsports|<font color="#FF0000">Gp</font><font color="#000000">75</font><font color="#FF0000">motorsports</font>]] <sup><font color="#800000">[[User talk:Gp75motorsports|REV LIMITER]]</font></sup></font> 22:39, 2 January 2008 (UTC)\n",
'Automatically reporting [[Special:Contributions/'.$change['user'].']]. (bot)'
);
} else {
foreach (explode(',',$ircreportchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :!admin [[User:'.$change['user'].']] has vandalized at least one time while being listed on [[WP:AIV]]. Contributions: [[Special:Contributions/'.$change['user'].']] Block: [[Special:Blockip/'.$change['user'].']]'."\n");
}
}
} elseif ($warning < 5) { /* Warn them if they haven't been warned 4 times. */
foreach (explode(',',$ircvandalismchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :computer bl add '.$change['user'].' x='.(24*$warning).' r=Vandalism to [['.$change['title'].']] (#'.$warning.').'."\n");
}
$wpi->post(
'User talk:'.$change['user'],
$wpq->getpage('User talk:'.$change['user'])."\n\n" .
'{{subst:User:'.$user.'/Warnings/Warning|1='.$warning.'|2='.$change['title'].'|3='.$report.' <;!-- MySQL ID: '.$mysqlid.' -->;}} <font face="Copperplate Gothic">[[User:Gp75motorsports|<font color="#FF0000">Gp</font><font color="#000000">75</font><font color="#FF0000">motorsports</font>]] <sup><font color="#800000">[[User talk:Gp75motorsports|REV LIMITER]]</font></sup></font> 22:39, 2 January 2008 (UTC)'."\n",
'Warning [[User:'.$change['user'].']] - #'.$warning
); /* Warn the user */
} else { /* They have already been reported ... do nothing */
}
if (!mysql_ping($mysql)) {
$mysql = mysql_pconnect($mysqlhost.':'.$mysqlport,$mysqluser,$mysqlpass);
if (!$mysql) { die('Could not connect: ' . mysql_error()); }
if (!mysql_select_db($mysqldb, $mysql)) { die ('Can\'t use database : ' . mysql_error()); }
}
mysql_query('UPDATE `vandalism` SET `reverted` = 1 WHERE `id` = \''.mysql_real_escape_string($mysqlid).'\'');
} else {
if ($change['user'] != $rv2[0]['user']) {
echo 'Grr! Beaten by '.$rv2[0]['user'].".\n";
foreach(explode(',',$ircdebugchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :Grr! Beaten by '.$rv2[0]['user'].".\n");
}
if (!mysql_ping($mysql)) { $mysql = mysql_pconnect($mysqlhost.':'.$mysqlport,$mysqluser,$mysqlpass); mysql_select_db($mysqldb, $mysql); }
mysql_query('INSERT INTO `beaten` (`id`,`article`,`diff`,`user`) VALUES (NULL,\''.mysql_real_escape_string($change['title']).'\',\''.mysql_real_escape_string($change['url']).'\',\''.mysql_real_escape_string($rv2[0]['user']).'\')');
}
}
} else {
foreach (explode(',',$ircunrevertedchannels) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :'."\002\00304Possible ignored vandalism: \002\003[[\00312".$change['title']."\003]]\00304 changed by \003[[\00312User:".$change['user']."\003]] \00303".$reason."\00304 on \00307".$rv[0]['timestamp']."\003(\002\00313".$s."\003).\n");
fwrite($irc,'PRIVMSG '.$y.' :'."\002(\002\00312 http://en.wikipedia.org/w/index.php?title=".urlencode($change['title'])."&;action=history \003\002|\002\00312 ".$change['url']." \003\002)\002"."\n");
}
}
} else {
$rev = $wpapi->revisions($change['title'],1);
$rev = $rev[0];
echo 'Possible corrected vandalism: '.$change['title'].' changed by '.$change['user'].' '.$reason.'('.$s.")\n\tReverted by ".$rev['user']." before I saw it.\n";
foreach (explode(',',$ircdebugchannel) as $y) {
fwrite($irc,'PRIVMSG '.$y.' :Possible corrected vandalism: '.$change['title'].' changed by '.$change['user'].' '.$reason.'('.$s.")\n");
fwrite($irc,'PRIVMSG '.$y.' :Reverted by '.$rev['user']." before I saw it.\n");
}
if (($rev['user'] != $user) and ($rev['user'] != $change['user'])) {
if (!mysql_ping($mysql)) { $mysql = mysql_pconnect($mysqlhost.':'.$mysqlport,$mysqluser,$mysqlpass); mysql_select_db($mysqldb, $mysql); }
mysql_query('INSERT INTO `beaten` (`id`,`article`,`diff`,`user`) VALUES (NULL,\''.mysql_real_escape_string($change['title']).'\',\''.mysql_real_escape_string($change['url']).'\',\''.mysql_real_escape_string($rev['user']).'\')');
}
}
}
}
die();
}
}
}
}
?>
[edit] Heuristics
[edit] Config (cluebot.heuristics.config.php)
<?PHP
$heuristics[] = 'pagereplace';
$heuristics[] = 'pageblank';
$heuristics[] = 'massdelete';
$heuristics[] = 'massadd';
$heuristics[] = 'smallchange';
?>
[edit] heuristics/cluebot.massadd.heuristic.php
<?PHP
if ( /* Massive additions */
($change['length'] >= 7500)
and ($rv = $wpapi->revisions($change['title'],2,'older',true,$change['revid']))
and ($pagedata = $wpq->getpage($change['title']))
and ($s = score($scorelist,diff($rv[1]['*'],$rv[0]['*'])))
and ($s += (score($scorelist,diff($rv[1]['*'],$rv[0]['*'],false))) * -1)
and ($s < -1000)
and ($reason = 'score equals '.$s)
) $heuristicret = true;
?>
[edit] heuristics/cluebot.massdelete.heuristic.php
<?PHP
if ( /* Massive deletes */
($change['length'] <= -7500)
and ($pagedata = $wpq->getpage($change['title']))
and (!fnmatch('*#REDIRECT*',strtoupper(substr($pagedata,0,9))))
and ($rv = $wpapi->revisions($change['title'],2,'older',true,$change['revid']))
and ($s = score($scorelist,diff($rv[1]['*'],$rv[0]['*'])))
and ($s += (score($scorelist,diff($rv[1]['*'],$rv[0]['*'],false))) * -1)
and ($s < -50) /* There are times when massive deletes are ok. */
and ($reason = 'deleting '.($change['length'] * -1).' characters')
) $heuristicret = true;
?>
[edit] heuristics/cluebot.pageblank.heuristic.php
<?PHP
if ( /* Page blanks */
(preg_match('/\[\[WP:AES.*Blanked.*page/',$change['comment'],$m))
and (($pagedata = $wpq->getpage($change['title'])) or true)
and ($fc = $wpapi->revisions($change['title'],1,'newer'))
and ($fc[0]['user'] != $change['user']) /* The creator is allowed to blank the page. */
and ($reason = 'blanking the page')
) $heuristicret = true;
?>
[edit] heuristics/cluebot.pagereplace.heuristic.php
<?PHP
if ( /* Page replaces */
(preg_match('/\[\[WP:AES\|.*\]\]Replaced page with (.*)$/',$change['comment'],$m))
and ($pagedata = $wpq->getpage($change['title']))
and ($fc = $wpapi->revisions($change['title'],1,'newer'))
and ($fc[0]['user'] != $change['user']) /* The creator is allowed to replace the page. */
and ($reason = 'replacing entire content with something else')
) $heuristicret = true;
?>
[edit] heuristics/cluebot.smallchange.heuristic.php
<?PHP
if ( /* Small changes with obscenities. */
(($change['length'] >= -200) and ($change['length'] <= 200))
and (($rv = $wpapi->revisions($change['title'],2,'older',true,$change['revid'])) or true)
and (!fnmatch('*#REDIRECT*',strtoupper(substr($rv[0]['*'],0,9))))
and ((($change['title'] == 'User:ClueBot/Sandbox') and print_r($rv)) or true)
and (($d1 = diff($rv[1]['*'],$rv[0]['*'],true,true)) or true)
and (($s = score($obscenelist,$d1)) or true)
and (($s -= score($obscenelist,diff($rv[1]['*'],$rv[0]['*'],false,true))) or true)
// and ((print($change['title'].' Score = '.$s."\n")) or true)
and (
(
($s < -5) /* There are times when small changes are ok. */
and (!fnmatch('*SEX*',strtoupper($rv[1]['*'])))
and (!fnmatch('*BDSM*',strtoupper($rv[1]['*'])))
and (score($obscenelist,$change['title']) >= 0)
and (score($obscenelist,$rv[1]['*']) >= 0)
and (!preg_match('/(^|\s)([a-z]{1,2}(\*+|\-{3,})[a-z]{0,2}|\*{4}|\-{4}|(\<|\()?censored(\>|\))?)(ing?|ed)?(\s|$)/i',$rv[1]['*']))
and ($heuristic .= '/obscenities')
and ($reason = 'making a minor change with obscenities')
)
or (
($s > 5)
and (!preg_match('/(^|\s)([a-z]{1,2}(\*+|\-{3,})[a-z]{0,2}|\*{4}|\-{4}|(\<|\()?censored(\>|\))?)(ing?|ed)?(\s|$)/i',$rv[1]['*']))
and (preg_match('/(^|\s)([a-z]{1,2}(\*+|\-{3,})[a-z]{0,2}|\*{4}|\-{4}|(\<|\()?censored(\>|\))?)(ing?|ed)?(\s|$)/i',$d1))
and ($heuristic .= '/censor')
and ($reason = 'making a minor change censoring content ([[WP:CENSOR|Wikipedia is not censored]])')
)
or (
(preg_match('/\!\!\!/',$d1))
and (!preg_match('/\!\!\!/',$rv[1]['*']))
and ($heuristic .= '/exclamation')
and ($reason = 'making a minor change adding "!!!"')
)
)
) { $heuristicret = true; /* fwrite($irc,'PRIVMSG #wikipedia-BAG/ClueBot :Would revert http://en.wikipedia.org/w/index.php?title='.urlencode($change['namespace'].$change['title']).'&;diff=prev'.'&oldid='.urlencode($change['revid'])." .\n"); */ }
?>
[edit] Score list
<?PHP
/*
* This page contains bad words out of necessity.
* Here is 50 lines of whitespace before the actual list:
* (scroll down to see the list)
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
* Here is the list:
*/
$obscenelist = Array
(
/* 'preg' => points, */
'/suck/i' => -5, /* Usually bad words */
'/stupid/i' => -3,
'/haha/i' => -5,
'/\bomg/i' => -3,
'/\bpimp\b/i' => -7,
'/1337/i' => -5,
'/leet/i' => -5,
'/dumb/i' => -5,
'/\bputa\b/i' => -7,
'/\bhomo\b/i' => -7,
'/\bGAY\b/' => -10,
'/\bslut/i' => -5,
'/damn/i' => -5,
'/\bass\b/i' => -10,
'/\brape\b/i' => -7,
'/\bpoop\b/i' => -10,
'/\bcock\b/i' => -10,
'/\blol\b/i' => -7,
'/\bcrap\b/i' => -5,
'/\bsex\b/i' => -5,
'/noob/i' => -5,
'/\bnazi\b/i' => -3,
'/\bneo-nazi\b/i' => +3, /* False-positive */
'/fuck/i' => -20, /* Stronger bad words */
'/\[\[Fucked\ Up\]\]/' => +20, /* This one is a false positive */
'/bitch/i' => -20,
'/\bpussy\b/i' => -20,
'/penis/i' => -20,
'/vagina/i' => -20,
'/whore/i' => -15,
'/\bshit\b/i' => -20,
'/nigger/i' => -20,
'/\bnigga\b/i' => -20,
'/cocksucker/i' => -20,
'/assrape/i' => -15,
'/motherfucker/i' => -20,
'/wanker/i' => -20,
'/\bcunt\b/i' => -20,
'/faggot/i' => -20,
'/fags/i' => -20,
'/asshole/i' => -15,
'/fuck ((yo)?u|h(er|im)|them|it)/i' => -100, /* This looks like a personal attack */
'/((yo)?u|s?he|we|they|it) sucks?/i' => -100, /* This looks like a personal attack */
'/666+\b/i' => -50 /* Though this has uses, it is commonly used by vandals */
);
$grammarlist = Array
(
'/(.{1,4})\1{30}/' => -10, /* Ugg .. the same letter(s) several times in a row. */
'/\b[A-Z].*[.!?]\b/U' => +2, /* This looks to be a correct sentence */
'/\b[A-Z][^a-z]{30,}\b/U' => -10, /* All capitals? Looks like vandal activity */
'/\b[^A-Z]{1500,}\b/U' => -10, /* No capitals? Looks like vandal activity */
'/!{5,}/i' => -10, /* No wikipedia article needs '!!!!!' in it */
'/!!+1+(one)*/i' => -30, /* No wikipedia article needs '!!!11one' in it */
'/\[\[.*\]\]/U' => +1, /* Wiki links are good. */
'/\{\{.*\}\}/U' => +5, /* Wiki transcludes are good. */
'/\{\{[iI]nfobox .*\}\}/U' => +20, /* Wiki infoboxes are good. */
'/\[\[Category\:.*\]\]/iU' => +3 /* Wiki categories are good. */
);
$scorelist = array_merge($obscenelist,$grammarlist);
?>