User:ClueBot/Source - Knowledge (XXG)

63:<?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,&$ matches = null) { $ ret = 0; foreach ($ list as $ preg => $ pts) { if ($ x = preg_match_all($ preg.'S',$ data,$ m)) { // echo $ x.'*'.$ pts.' ('.$ preg.')'."\n"; $ matches = $ x; $ ret += $ pts * $ x; } } // echo 'Score: '.$ ret."\n"; return $ ret; } function myfnmatch ($ pattern,$ string) { if (strlen($ string) < 4000) { return fnmatch($ pattern,$ string); } else { $ pattern = strtr(preg_quote($ pattern, '#'), array('\*' => '.*', '\?' => '.', '\' => ']')); if (preg_match('#^'.$ pattern.'$ #',$ string)) return true; return false; } } 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; var_export($ 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); } } $ ircchannel = $ tmp; $ ircdebugchannel = $ tmp; $ ircreportchannel = $ tmp; $ ircvandalismchannel = $ tmp; $ ircaivchannel = $ tmp; $ irctechchannel = $ tmp; $ ircproxychannels = $ tmp; $ ircunrevertedchannels = $ tmp; $ ircbagtrialchannels = $ tmp; $ ircotherchannels = $ tmp; unset($ tmp,$ tmpline); $ stalkbots = array(); $ trialbots = explode("\n",$ wpq->getpage('Knowledge (XXG):Bots/Requests for approval')); foreach ($ trialbots as $ trialbot) if (preg_match('/\{\{BRFA\|(.*)\|.*\|Trial\}\}/',str_replace(array("\n","\r"),'',$ trialbot),$ m)) $ stalkbots] = 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 Knowledge (XXG) 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) == 'ping') { fwrite($ irc,'PONG '.$ d."\n"); } elseif (($ d == '376') or ($ d == '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) == 'privmsg') { if (substr($ d,0,2) == ':!') { if (strtolower($ d) == '#wikipedia-en') { $ tmp = explode('!',substr($ d,1)); $ cmd = 'NOTICE '.$ tmp; } elseif (strtolower($ d) == strtolower($ user)) { $ tmp = explode('!',substr($ d,1)); $ cmd = 'NOTICE '.$ tmp; } else { $ cmd = 'PRIVMSG '.$ d; } switch (substr(strtolower($ d),2)) { case 'edit': if (preg_match("/\\]/",$ data,$ m)) { $ rv = $ wpapi->revisions($ m,1,'older'); fwrite($ irc,$ cmd.' :.']] http://en.wikipedia.org/search/?title='.urlencode($ m).'&diff=prev' . '&oldid='.urlencode($ rv).' * '.$ rv.' * '.$ rv."\n"); } else { fwrite($ irc,$ cmd.' :Couldn\'t find link.'."\n"); } break; case 'stalk': if (preg_match("/\\]/",$ data,$ m)) { $ uc = $ wpapi->usercontribs($ m,1); fwrite($ irc,$ cmd.' :.']] http://en.wikipedia.org/search/?title='.urlencode($ uc).'&diff=prev' . '&oldid='.urlencode($ uc).' * '.$ m.' * '.$ uc."\n"); } else { fwrite($ irc,$ cmd.' :Couldn\'t find link.'."\n"); } break; case 'beaten': if (preg_match("/\\]/",$ 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).'\' 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).'\' LIMIT 1')); $ z = mysql_fetch_assoc(mysql_query('SELECT FOUND_ROWS() as `ahead`')); fwrite($ irc,$ cmd.' :.']] has beaten me '.(($ x != '')?$ x:'0').' times. There are '.$ z.' 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])) { fwrite($ irc,$ cmd.' :.']] has been vandalized '.count($ tmp]).' time(s) in the last 48 hours.'."\n"); } else { fwrite($ irc,$ cmd.' :.']] 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); } 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); } } file_put_contents('titles.txt',serialize($ titles)); $ tcount = count($ titles); foreach ($ ov as $ x => $ y) { $ ocount = count($ y); } arsort($ ocount); foreach ($ ocount as $ x => $ y) { $ mova = $ x; $ movacount = $ y; break; } preg_match('/$\'\'\'\*)\|more...\]\]\'\'\'$/iU',$ wpq->getpage('Knowledge (XXG):Today\'s featured article/'.date('F j, Y')),$ tfa); $ tfa = $ tfa; 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.' ('.$ x.')'; } 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.' :] is the most vandalized page with a total of '.$ movacount.' vandalisms in the last 48 hours. ' . 'Today\'s featured article is: ].'."\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.'.'."\n"); unset($ x,$ y,$ count,$ ov,$ tcount,$ ocount,$ mova,$ movacount,$ tfa,$ run,$ title,$ titles,$ time,$ top5beat); break; case 'warninglevel': if (preg_match("/\\]/",$ data,$ n)) { $ warning = 0; if (preg_match_all('/.*(\d{2}):(\d{2}), (\d+) (+) (\d{4}) $UTC$/iU', $ wpq->getpage('User talk:'.$ n), $ 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 == 'Blatantvandal (serious warning)') $ m = 4; if ((time() - gmmktime($ m,$ m,0,$ month],$ m,$ m)) <= (2*24*60*60)) { if ($ m > $ warning) { $ warning = $ m; } } } } fwrite($ irc,$ cmd.' :.']] is at warning level '.$ warning.".\n"); } else { fwrite($ irc,$ cmd.' :Couldn\'t find link.'."\n"); } break; case 'count': if (preg_match("/\\]/",$ data,$ n)) { fwrite($ irc,$ cmd.' :.']] has '.$ wpq->contribcount($ n)." contributions.\n"); } else { fwrite($ irc,$ cmd.' :Couldn\'t find link.'."\n"); } break; case 'help': fwrite($ irc,$ cmd.' :Please see ].'."\n"); break; case 'eval': $ tmp = explode(' ',$ data,6); $ tmp1 = explode('!',substr($ d,1)); if ($ d == md5($ thesecret.$ tmp1.$ tmp)) { eval($ tmp); } else { fwrite($ irc,$ cmd.' :Code incorrect.'."\n"); } break; case 'cbproxy': $ tmp = explode(' ',$ data,6); $ tmp1 = explode('!',substr($ d,1)); if ($ tmp1 == 'ClueBot-Bopm') { foreach (explode(',',$ ircproxychannels) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :!admin '.$ tmp."\n"); } $ data = $ wpq->getpage('Knowledge (XXG):WikiProject on open proxies'); if (strpos($ data,$ tmp) === false) { $ header = explode('{{proxyip2|127.0.0.1}} || Example',$ data,2); $ header .= '{{proxyip2|127.0.0.1}} || Example '; $ footer = $ header; $ header = $ header; $ data = "\n".'{{proxyip2|'.$ tmp.'}} || '.$ tmp.' ~~~~'."\n"; $ data = $ header.$ data.$ footer; unset($ header,$ footer); $ wpapi->edit('Knowledge (XXG):WikiProject on open proxies',$ data,'Adding '.$ tmp.'.'); 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); $ wpapi->edit('User:'.$ user.'/Source', 'The following is automatically generated by ].\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~~~~", 'Automated source upload.'); /* Our source code, we force post this because this is *our* page, and it triggers the nobots. */ unset($ heuristics); $ wpapi->edit('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] = trim($ tmp3); } } $ tmp = explode("\n",$ wpq->getpage('User:'.$ owner.'/CBAutoedit.js')); foreach ($ tmp as $ tmp2) { if (substr($ tmp2,0,1) != '#') { $ tmp3 = explode('|',$ tmp2,2); $ edit] = trim($ tmp3); } } 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 Knowledge (XXG) Bot.'."\n"); fwrite($ feed,'NICK '.$ user."\n"); while (!feof($ feed)) { $ rawline = fgets($ feed,1024); $ line = str_replace(array("\n","\r","\002"),'',$ rawline); $ 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) == 'ping') { fwrite($ feed,'PONG '.$ linea."\n"); } elseif (($ linea == '376') or ($ linea == '422')) { fwrite($ feed,'JOIN '.$ feedchannel."\n"); } elseif ((strtolower($ linea) == 'privmsg') and (strtolower($ linea) == strtolower($ feedchannel))) { $ message = substr($ linea,1); if (preg_match('/^\*)\]\] (\S*) (http:\/\/en\.wikipedia\.org\/w\/index\.php\?diff=(\d*)&oldid=(\d*).*|http:\/\/en\.wikipedia\.org\/wiki\/\S+)? \* (*) \* ($(*)$)? (.*)$ /S',$ message,$ m)) { $ messagereceived = microtime(1); $ change = $ m; $ change = $ m; $ change = $ m; $ change = $ m; $ change = $ m; $ change = $ m; $ change = $ m; $ change = $ m; $ change = $ m; // include 'cluebot.stalk.config.php'; $ stalkchannel = array(); foreach ($ stalk as $ key => $ value) if (myfnmatch(str_replace('_',' ',$ key),str_replace('_',' ',$ change))) $ stalkchannel = array_merge($ stalkchannel,explode(',',$ value)); foreach ($ stalkbots as $ key => $ value) if (myfnmatch(str_replace('_',' ',$ key),str_replace('_',' ',$ change))) $ stalkchannel = array_merge($ stalkchannel,explode(',',$ ircbagtrialchannels)); foreach ($ edit as $ key => $ value) if (myfnmatch(str_replace('_',' ',$ key),str_replace('_',' ',$ change.$ change))) $ stalkchannel = array_merge($ stalkchannel,explode(',',$ value)); // if ($ change == $ owner) $ stalkchannel = $ ircchannel; $ stalkchannel = array_unique($ stalkchannel); foreach ($ stalkchannel as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :New edit: .$ change.']] http://en.wikipedia.org/search/?title=' . urlencode($ change.$ change).'&diff=prev'.'&oldid='.urlencode($ change).' * '.$ change . ' * '.$ change."\n"); } if (($ change == 'User:') or ($ change == 'User talk:')) { if (strtolower($ change) == strtolower($ user.'/Run')) { $ run = $ wpq->getpage('User:'.$ user.'/Run'); } if (strtolower($ change) == strtolower($ user.'/Whitelist')) { $ wl = $ wpq->getpage('User:'.$ user.'/Whitelist'); } if (strtolower($ change) == strtolower($ user.'/Optin')) { $ optin = $ wpq->getpage('User:'.$ user.'/Optin'); } if (strtolower($ change) == strtolower($ user.'/AngryOptin')) { $ aoptin = $ wpq->getpage('User:'.$ user.'/AngryOptin'); } if (strtolower($ change) == 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] = trim($ tmp3); } } unset($ tmp,$ tmp2,$ tmp3); print_r($ stalk); } if (strtolower($ change) == 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] = trim($ tmp3); } } unset($ tmp,$ tmp2,$ tmp3); print_r($ edit); } if (strtolower($ change) == 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); } } print_r($ tmp); $ tmpold = array(); $ tmpnew = array(); foreach ($ tmp as $ tmp2) foreach (explode(',',$ tmp2) as $ tmp3) $ tmpnew = 1; foreach (explode(',',$ ircchannel.','.$ ircdebugchannel.','.$ ircreportchannel.','.$ ircvandalismchannel.','.$ ircaivchannel.','.$ irctechchannel.','.$ ircproxychannels.','.$ ircunrevertedchannels.','.$ ircbagtrialchannels.','.$ ircotherchannels) as $ tmp3) $ tmpold = 1; foreach ($ tmpold as $ tmp2 => $ tmp3) if (isset($ tmpnew)) unset($ tmpold,$ tmpnew); 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; $ ircdebugchannel = $ tmp; $ ircreportchannel = $ tmp; $ ircvandalismchannel = $ tmp; $ ircaivchannel = $ tmp; $ irctechchannel = $ tmp; $ ircproxychannels = $ tmp; $ ircunrevertedchannels = $ tmp; $ ircbagtrialchannels = $ tmp; $ ircotherchannels = $ tmp; unset($ tmp,$ tmpline,$ tmpold,$ tmpnew,$ tmp2,$ tmp3); } } if ($ change.$ change == 'Knowledge (XXG):Bots/Requests for approval') { $ stalkbots = array(); $ trialbots = explode("\n",$ wpq->getpage('Knowledge (XXG):Bots/Requests for approval')); foreach ($ trialbots as $ trialbot) if (preg_match('/\{\{BRFA\|(.*)\|.*\|Trial\}\}/',str_replace(array("\n","\r"),'',$ trialbot),$ m)) $ stalkbots] = 1; } if (($ change != '') and ((!preg_match('/\* \.$ change,'/').')\]\] \- .*/i',$ optin))) and ($ change != 'move') and ($ change != 'Template:')) continue; $ change = $ change; $ change = $ change.$ change; if ($ change == 'move') { if (preg_match('/moved \\] to \\]( over redirect)?: (.*)$ /',$ change,$ m)) { $ change = $ m; $ change = $ m; $ change = $ change; $ change = $ m; echo "\n\n\n".'Move!'."\n\n\n"; print_r($ change); echo "\n\n\n".'Move!'."\n\n\n"; } } if ( ((time() - $ tfas) >= 1800) and (preg_match('/$\'\'\'\*)\|more...\]\]\'\'\'$/iU',$ wpq->getpage('Knowledge (XXG):Today\'s featured article/'.date('F j, Y')),$ tfam)) ) { $ tfas = time(); $ tfa = $ tfam; //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++; print_r($ log); file_put_contents('cluebot.heuristics.stats.txt',serialize($ stats)); unset($ stats); break; } } if ($ heuristicret == true) { echo 'Heuristics time: '.(microtime(1) - $ hutime)."\n"; /*file_put_contents('trainingdata.txt',$ change."\0".$ change."\0".'1'."\n",FILE_APPEND);*/ } else { $ tmp = explode(' ',$ rawline,4); $ tmp = $ tmp; $ udp = fsockopen('udp://localhost',3333); fwrite($ udp,substr(str_replace(array("\n","\r"),'',$ tmp),1)."\n"); fclose($ udp); unset($ tmp,$ udp); $ d = $ wpi->diff($ change,$ change,$ change); $ s = score($ obscenelist,$ d,$ log); $ s -= score($ obscenelist,$ d,$ log); // if ($ s > 15) file_put_contents('trainingdata.txt',$ change."\0".$ change."\0".'0'."\n",FILE_APPEND); } unset($ hutime); if ( ($ heuristicret == true) ) { if ( ( ( /* IP users with 250 contributions are fine .. */ (long2ip(ip2long($ change)) == $ change) /* and ($ uc = $ wpapi->usercontribs($ change,250)) and (!isset($ uc)) */ ) or ( /* Users with 50 contributions are fine .. */ (long2ip(ip2long($ change)) != $ change) and ($ wpq->contribcount($ change) < 50) ) ) and ( /* Whitelisted users are ok. */ /* ($ wl = $ wpq->getpage('User:'.$ user.'/Whitelist')) and */ (!preg_match('/^\* \,'/').')|\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,$ m,$ m,$ m,$ m,$ m)) > (5*60*60)) { // unset($ x); // } // } // } // $ vandalpage = implode("\n\n",$ x); $ diff = 'http://en.wikipedia.org/search/' . '?title='.urlencode($ change) . '&diff='.urlencode($ change) . '&oldid='.urlencode($ change); $ report = ').']] was ' . (($ change != 'move')?' by ':'moved to ).']] by ') . '.'|'.$ change.']] ' . '.'|(u)]] ' . '.'|(t)]] ' . $ reason.' on '.gmdate('c'); // $ datatopost = $ vandalpage."\n\n".'Possible ]: '.$ report." ~~~~\n"; if ($ s == null) { // $ rv = $ wpapi->revisions($ change,2,'older',true,$ change); // $ s = score($ scorelist,diff($ rv,$ rv)); // $ s += (score($ scorelist,diff($ rv,$ rv,false))) * -1; $ s = 'N/A'; } $ tmp = unserialize(file_get_contents('oftenvandalized.txt')); if (rand(1,50) == 2) { foreach ($ tmp as $ key1 => $ tmp2) { foreach ($ tmp2 as $ key2 => $ time) { if ((time() - $ time) > (2*24*60*60)) { unset($ tmp); } } } } $ tmp] = time(); if (count($ tmp]) >= 30) { foreach (explode(',',$ ircreportchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :!admin .']] has been vandalized '.(count($ tmp])).' times in the last 2 days.'."\n"); } } file_put_contents('oftenvandalized.txt',serialize($ tmp)); if ( ( ($ rv1 = $ wpapi->revisions($ change,1,'older')) and ($ rv1 == $ change) ) or ($ change == 'move') ) { /* No need to continue further if it has been reverted */ echo 'Possible vandalism: '.$ change.' changed by '.$ change.' '.$ reason.' on '.$ rv.'('.$ s.").\n"; foreach (explode(',',$ ircdebugchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :Possible vandalism: '.$ change.' changed by '.$ change.' '.$ reason.' on '.$ rv.'('.$ s.").\n"); fwrite($ irc,'PRIVMSG '.$ y.' :( http://en.wikipedia.org/search/?title='.urlencode($ change).'&action=history | '.$ change.' )'."\n"); } fwrite($ pipe,'http://en.wikipedia.org/search/?title='.urlencode($ change).'&action=history'."\n"); /* Tell owner */ $ mqtime = microtime(1); if (is_array($ log)) { $ logt = ''; foreach ($ log as $ k => $ v) { $ logt .= '* '.$ v.' * "'.$ k.'"'."\n"; } } $ query = 'INSERT INTO `vandalism` ' . '(`id`,`user`,`article`,`heuristic`'.((is_array($ log))?',`regex`':'').',`reason`,`diff`,`old_id`,`new_id`,`reverted`) ' . 'VALUES ' . '(NULL,\''.mysql_real_escape_string($ change).'\',' . '\''.mysql_real_escape_string($ change).'\',' . '\''.mysql_real_escape_string($ heuristic).'\',' . ((is_array($ log))?'\''.mysql_real_escape_string($ logt).'\',':'') . '\''.mysql_real_escape_string($ reason).'\',' . '\''.mysql_real_escape_string($ change).'\',' . '\''.mysql_real_escape_string($ change).'\',' . '\''.mysql_real_escape_string($ change).'\',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)/iS',$ status)) and (print('Revert ? ')) and (strtolower(substr(fgets($ stdin,3),0,1)) == 'y') ) or ( (preg_match('/(read-write|rw|go|approved|trial)/iS',$ status)) ) ) and ( /*ANGRY MODE*/ false or ( ( ((time() - $ tfas) < 1800) or ( (preg_match('/$\'\'\'\*)\|more...\]\]\'\'\'$/iU',$ wpq->getpage('Knowledge (XXG):Today\'s featured article/'.date('F j, Y')),$ tfam)) and ($ tfas = time()) and ($ tfa = $ tfam) and ((print("TFA: ".$ tfa."\n")) or (true)) ) ) and ($ tfa == $ change) ) or ( (preg_match('/\* \,'/').')\]\] \- .*/i',$ aoptin)) and ((fwrite($ irc,'PRIVMSG '.$ ircdebugchannel.' :Angry-reverting .']].'."\n")) or (true)) ) or ( (($ tmp = unserialize(file_get_contents('titles.txt'))) or true) and ((!isset($ tmp.$ change])) or ((time() - $ tmp.$ change]) > (24*60*60))) and ($ tmp.$ change] = time()) and ((file_put_contents('titles.txt',serialize($ tmp))) or true) ) ) ) { echo 'Reverting ...'."\n"; if ($ change != 'move') { $ rev = $ wpapi->revisions($ change,5,'older',false,null,true,true); $ revid = 0; $ rbtok = $ rev; foreach ($ rev as $ revdata) { if ($ revdata != $ change) { $ revid = $ revdata; break; } } if (($ revdata == $ user) or (in_array($ revdata,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,1,'older',true,$ revid); // if (!$ revisiondata) die(); // if (!$ rv1) $ rv1 = $ rv; // $ wpi->post( // $ change, // $ revisiondata, // 'Reverting possible vandalism by .'|'.$ change.']] ' . // 'to version by '.$ revisiondata.'. ' . // 'False positive? ]. '. // 'Thanks, ]. ('.$ mysqlid.') (Bot)', // false, // $ rv1 // ); /* Revert the page */ if ($ change != 'move') { if (!$ rbtok) { $ d = $ wpi->diff($ change,$ change,$ change); $ rbtok = $ d; } $ rbret = $ wpapi->rollback( $ change, $ change, 'Reverting possible vandalism by .'|'.$ change.']] ' . 'to '.(($ revid == 0)?'older version':'version by '.$ revdata).'. ' . 'False positive? ]. '. 'Thanks, ]. ('.$ mysqlid.') (Bot)', $ rbtok ); } else { $ rbret = $ wpapi->move( $ change, $ change, 'Reverting possible vandalism by .'|'.$ change.']] ' . 'to '.(($ revid == 0)?'older version':'version by '.$ revdata).'. ' . 'False positive? ]. '. 'Thanks, ]. ('.$ mysqlid.') (Bot)' ); } // // $ rv2 = $ wpapi->revisions($ change,1); // if ($ rv2 == $ user) { if ($ rbret !== false) { foreach (explode(',',$ ircdebugchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :Reverted. ('.(microtime(1) - $ messagereceived).' s)'."\n"); } $ warning = 0; $ tpcontent = $ wpq->getpage('User talk:'.$ change); if (preg_match_all('/.*(\d{2}):(\d{2}), (\d+) (+) (\d{4}) $UTC$/iU', $ tpcontent, $ 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 == 'Blatantvandal (serious warning)') $ m = 4; if ((time() - gmmktime($ m,$ m,0,$ month],$ m,$ m)) <= (2*24*60*60)) { if ($ m > $ warning) { $ warning = $ m; } } } } $ warning++; if ($ warning == 5) { /* Report them if they have been warned 4 times. */ $ aivdata = $ wpq->getpage('Knowledge (XXG):Administrator_intervention_against_vandalism/TB2'); if (!preg_match('/'.preg_quote($ change,'/').'/i',$ aivdata)) { foreach(explode(',',$ ircaivchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :!admin Reporting .']] to ]. Contributions: .']] Block: .']]'."\n"); } foreach (explode(',',$ ircvandalismchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :rcbot bl add '.$ change.' x='.(24*$ warning).' r=Vandalism to .']] (#'.$ warning.").\n"); } $ wpapi->edit( 'Knowledge (XXG):Administrator_intervention_against_vandalism/TB2', $ aivdata . "\n\n* {{".((long2ip(ip2long($ change)) == $ change)?'IPvandal':'Vandal').'|'.$ change.'}}' . ' - '.$ report." (Automated) ~~~~\n", 'Automatically reporting .']]. (bot)', false, false ); } else { foreach (explode(',',$ ircreportchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :!admin .']] has vandalized at least one time while being listed on ]. Contributions: .']] Block: .']]'."\n"); } } } elseif ($ warning < 5) { /* Warn them if they haven't been warned 4 times. */ foreach (explode(',',$ ircvandalismchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :rcbot bl add '.$ change.' x='.(24*$ warning).' r=Vandalism to .']] (#'.$ warning.').'."\n"); } $ wpapi->edit( 'User talk:'.$ change, $ tpcontent."\n\n" . '{{subst:User:'.$ user.'/Warnings/Warning|1='.$ warning.'|2='.str_replace('File:',':File:',$ change).'|3='.$ report.' <!{{subst:ns:0}}-- MySQL ID: '.$ mysqlid.' --{{subst:ns:0}}>}} ~~~~'."\n", 'Warning .'|'.$ change.']] - #'.$ warning, false, false ); /* 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 { $ rv2 = $ wpapi->revisions($ change,1); if ($ change != $ rv2) { echo 'Grr! Beaten by '.$ rv2.".\n"; foreach(explode(',',$ ircdebugchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :Grr! Beaten by '.$ rv2.".\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).'\',\''.mysql_real_escape_string($ change).'\',\''.mysql_real_escape_string($ rv2).'\')'); } } } else { foreach (explode(',',$ ircunrevertedchannels) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :'."\002\00304Possible ignored vandalism: \002\003."\003]]\00304 changed by \003."\003]] \00303".$ reason."\00304 on \00307".$ rv."\003(\002\00313".$ s."\003).\n"); fwrite($ irc,'PRIVMSG '.$ y.' :'."\002(\002\00312 http://en.wikipedia.org/search/?title=".urlencode($ change)."&action=history \003\002|\002\00312 ".$ change." \003\002)\002"."\n"); } $ 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+)Z',$ y,$ m)) { if ((gmtime() - gmmktime($ m,$ m,$ m,$ m,$ m,$ m)) > (5*60*60)) { unset($ x); } } } $ vandalpage = implode("\n\n",$ vandalpage); $ wpapi->edit('User:'.$ user.'/PossibleVandalism',$ vandalpage."\n\n".'Possible ignored vandalism: .']] changed by .']] '.$ reason.' on '.$ rv.' ('.$ s.')'.' ).'&action=history hist] .' diff] ~~~~','Adding possible vandalism',true,true); } } else { $ rev = $ wpapi->revisions($ change,1); $ rev = $ rev; echo 'Possible corrected vandalism: '.$ change.' changed by '.$ change.' '.$ reason.'('.$ s.")\n\tReverted by ".$ rev." before I saw it.\n"; foreach (explode(',',$ ircdebugchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :Possible corrected vandalism: '.$ change.' changed by '.$ change.' '.$ reason.'('.$ s.")\n"); fwrite($ irc,'PRIVMSG '.$ y.' :Reverted by '.$ rev." before I saw it.\n"); } if (($ rev != $ user) and ($ rev != $ change)) { 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).'\',\''.mysql_real_escape_string($ change).'\',\''.mysql_real_escape_string($ rev).'\')'); } } } } die(); } } } } ?> 41:<?PHP /** * @author Cobi Carter **/ /** * This class is designed to provide a simplified interface to cURL which maintains cookies. * @author Cobi **/ class http { private $ ch; private $ uid; public $ postfollowredirs; public $ getfollowredirs; /** * Our constructor function. This just does basic cURL initialization. * @return void **/ function __construct () { global $ proxyhost, $ proxyport, $ proxytype; $ 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); curl_setopt($ this->ch,CURLOPT_USERAGENT,'ClueBot/1.1'); if (isset($ proxyhost) and isset($ proxyport) and ($ proxyport != null) and ($ proxyhost != null)) { curl_setopt($ this->ch,CURLOPT_PROXYTYPE,isset( $ proxytype ) ? $ proxytype : CURLPROXY_HTTP); curl_setopt($ this->ch,CURLOPT_PROXY,$ proxyhost); curl_setopt($ this->ch,CURLOPT_PROXYPORT,$ proxyport); } $ this->postfollowredirs = 0; $ this->getfollowredirs = 1; } /** * Post to a URL. * @param $ url The URL to post to. * @param $ data The post-data to post, should be an array of key => value pairs. * @return Data retrieved from the POST request. **/ function post ($ url,$ data) { $ time = microtime(1); curl_setopt($ this->ch,CURLOPT_URL,$ url); curl_setopt($ this->ch,CURLOPT_FOLLOWLOCATION,$ this->postfollowredirs); 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, $ data); curl_setopt($ this->ch,CURLOPT_HTTPHEADER, array('Expect:')); $ data = curl_exec($ this->ch); global $ logfd; if (!is_resource($ logfd)) $ logfd = fopen('php://stderr','w'); fwrite($ logfd,'POST: '.$ url.' ('.(microtime(1) - $ time).' s) ('.strlen($ data)." b)\n"); return $ data; } /** * Get a URL. * @param $ url The URL to get. * @return Data retrieved from the GET request. **/ function get ($ url) { $ time = microtime(1); curl_setopt($ this->ch,CURLOPT_URL,$ url); curl_setopt($ this->ch,CURLOPT_FOLLOWLOCATION,$ this->getfollowredirs); 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); global $ logfd; if (!is_resource($ logfd)) $ logfd = fopen('php://stderr','w'); fwrite($ logfd,'GET: '.$ url.' ('.(microtime(1) - $ time).' s) ('.strlen($ data)." b)\n"); return $ data; } /** * Our destructor. Cleans up cURL and unlinks temporary files. **/ function __destruct () { curl_close($ this->ch); @unlink('/tmp/cluewikibot.cookies.'.$ this->uid.'.dat'); } } /** * This class is a deprecated wrapper class which allows legacy code written for Knowledge (XXG)'s query.php API to still work with wikipediaapi::. **/ class wikipediaquery { private $ http; private $ api; public $ queryurl = 'http://en.wikipedia.org/w/query.php'; //Obsolete, but kept for compatibility purposes. /** * This is our constructor. * @return void **/ function __construct () { global $ __wp__http; if (!isset($ __wp__http)) { $ __wp__http = new http; } $ this->http = &$ __wp__http; $ this->api = new wikipediaapi; } /** * Reinitializes the queryurl. * @private * @return void **/ private function checkurl() { $ this->api->apiurl = str_replace('query.php','api.php',$ this->queryurl); } /** * Gets the content of a page. * @param $ page The wikipedia page to fetch. * @return The wikitext for the page. **/ function getpage ($ page) { $ this->checkurl(); $ ret = $ this->api->revisions($ page,1,'older',true,null,true,false,false,false); return $ ret; } /** * Gets the page id for a page. * @param $ page The wikipedia page to get the id for. * @return The page id of the page. **/ function getpageid ($ page) { $ this->checkurl(); $ ret = $ this->api->revisions($ page,1,'older',false,null,true,false,false,false); return $ ret; } /** * Gets the number of contributions a user has. * @param $ user The username for which to get the edit count. * @return The number of contributions the user has. **/ function contribcount ($ user) { $ this->checkurl(); $ ret = $ this->api->users($ user,1,null,true); if ($ ret !== false) return $ ret; return false; } } /** * This class is for interacting with Knowledge (XXG)'s api.php API. **/ class wikipediaapi { private $ http; private $ edittoken; private $ tokencache; private $ user, $ pass; public $ apiurl = 'http://en.wikipedia.org/w/api.php'; /** * This is our constructor. * @return void **/ function __construct () { global $ __wp__http; if (!isset($ __wp__http)) { $ __wp__http = new http; } $ this->http = &$ __wp__http; } /** * This function takes a username and password and logs you into wikipedia. * @param $ user Username to login as. * @param $ pass Password that corrisponds to the username. * @return void **/ function login ($ user,$ pass) { $ this->user = $ user; $ this->pass = $ pass; $ x = unserialize($ this->http->post($ this->apiurl.'?action=login&format=php',array('lgname' => $ user, 'lgpassword' => $ pass))); if($ x == 'Success') return true; if($ x == 'NeedToken') { $ x = unserialize($ this->http->post($ this->apiurl.'?action=login&format=php',array('lgname' => $ user, 'lgpassword' => $ pass, 'lgtoken' => $ x))); if($ x == 'Success') return true; } return false; } /** * This function returns the edit token. * @return Edit token. **/ function getedittoken () { $ tokens = $ this->gettokens('Main Page'); if ($ tokens == '') $ tokens = $ this->gettokens('Main Page',true); $ this->edittoken = $ tokens; return $ tokens; } /** * This function returns the various tokens for a certain page. * @param $ title Page to get the tokens for. * @param $ flush Optional - internal use only. Flushes the token cache. * @return An associative array of tokens for the page. **/ function gettokens ($ title,$ flush = false) { if (!is_array($ this->tokencache)) $ this->tokencache = array(); foreach ($ this->tokencache as $ t => $ data) if (time() - $ data > 6*60*60) unset($ this->tokencache); if (isset($ this->tokencache) && (!$ flush)) { return $ this->tokencache; } else { $ tokens = array(); $ x = $ this->http->get($ this->apiurl.'?action=query&format=php&prop=info&intoken=edit|delete|protect|move|block|unblock|email&titles='.urlencode($ title)); $ x = unserialize($ x); foreach ($ x as $ y) { $ tokens = $ y; $ tokens = $ y; $ tokens = $ y; $ tokens = $ y; $ tokens = $ y; $ tokens = $ y; $ tokens = $ y; $ this->tokencache = array( 'timestamp' => time(), 'tokens' => $ tokens ); return $ tokens; } } } /** * This function returns the recent changes for the wiki. * @param $ count The number of items to return. (Default 10) * @param $ namespace The namespace ID to filter items on. Null for no filtering. (Default null) * @param $ dir The direction to pull items. "older" or "newer". (Default 'older') * @param $ ts The timestamp to start at. Null for the beginning/end (depending on direction). (Default null) * @return Associative array of recent changes metadata. **/ 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; } /** * This function returns search results from Knowledge (XXG)'s internal search engine. * @param $ search The query string to search for. * @param $ limit The number of results to return. (Default 10) * @param $ offset The number to start at. (Default 0) * @param $ namespace The namespace ID to filter by. Null means no filtering. (Default 0) * @param $ what What to search, 'text' or 'title'. (Default 'text') * @param $ redirs Whether or not to list redirects. (Default false) * @return Associative array of search result metadata. **/ function search ($ search,$ limit = 10,$ offset = 0,$ namespace = 0,$ what = 'text',$ redirs = false) { $ append = ''; if ($ limit != null) $ append .= '&srlimit='.urlencode($ limit); if ($ offset != null) $ append .= '&sroffset='.urlencode($ offset); if ($ namespace != null) $ append .= '&srnamespace='.urlencode($ namespace); if ($ what != null) $ append .= '&srwhat='.urlencode($ what); if ($ redirs == true) $ append .= '&srredirects=1'; else $ append .= '&srredirects=0'; $ x = $ this->http->get($ this->apiurl.'?action=query&list=search&format=php&srsearch='.urlencode($ search).$ append); $ x = unserialize($ x); return $ x; } /** * Retrieve entries from the WikiLog. * @param $ user Username who caused the entry. Null means anyone. (Default null) * @param $ title Object to which the entry refers. Null means anything. (Default null) * @param $ limit Number of entries to return. (Default 50) * @param $ type Type of logs. Null means any type. (Default null) * @param $ start Date to start enumerating logs. Null means beginning/end depending on $ dir. (Default null) * @param $ end Where to stop enumerating logs. Null means whenever limit is satisfied or there are no more logs. (Default null) * @param $ dir Direction to enumerate logs. "older" or "newer". (Default 'older') * @return Associative array of logs metadata. **/ function logs ($ user = null,$ title = null,$ limit = 50,$ type = null,$ start = null,$ end = null,$ dir = 'older') { $ append = ''; if ($ user != null) $ append.= '&leuser='.urlencode($ user); if ($ title != null) $ append.= '&letitle='.urlencode($ title); if ($ limit != null) $ append.= '&lelimit='.urlencode($ limit); if ($ type != null) $ append.= '&letype='.urlencode($ type); if ($ start != null) $ append.= '&lestart='.urlencode($ start); if ($ end != null) $ append.= '&leend='.urlencode($ end); if ($ dir != null) $ append.= '&ledir='.urlencode($ dir); $ x = $ this->http->get($ this->apiurl.'?action=query&format=php&list=logevents&leprop=ids|title|type|user|timestamp|comment|details'.$ append); $ x = unserialize($ x); return $ x; } /** * Retrieves metadata about a user's contributions. * @param $ user Username whose contributions we want to retrieve. * @param $ count Number of entries to return. (Default 50) * @param $ continue Where to continue enumerating if part of a larger, split request. This is filled with the next logical continuation value. (Default null) * @param $ dir Which direction to enumerate from, "older" or "newer". (Default 'older') * @return Associative array of contributions metadata. **/ 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); $ continue = $ x; return $ x; } /** * Returns revision data (meta and/or actual). * @param $ page Page for which to return revision data for. * @param $ count Number of revisions to return. (Default 1) * @param $ dir Direction to start enumerating multiple revisions from, "older" or "newer". (Default 'older') * @param $ content Whether to return actual revision content, true or false. (Default false) * @param $ revid Revision ID to start at. (Default null) * @param $ wait Whether or not to wait a few seconds for the specific revision to become available. (Default true) * @param $ getrbtok Whether or not to retrieve a rollback token for the revision. (Default false) * @param $ dieonerror Whether or not to kill the process with an error if an error occurs. (Default false) * @param $ redirects Whether or not to follow redirects. (Default false) * @return Associative array of revision data. **/ function revisions ($ page,$ count = 1,$ dir = 'older',$ content = false,$ revid = null,$ wait = true,$ getrbtok = false,$ dieonerror = true,$ redirects = false) { $ 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&meta=userinfo&rvdir='.urlencode($ dir).(($ revid !== null)?'&rvstartid='.urlencode($ revid):'').(($ getrbtok == true)?'&rvtoken=rollback':'').(($ redirects == true)?'&redirects':'')); $ x = unserialize($ x); if ($ revid !== null) { $ found = false; if (!isset($ x) or !is_array($ x)) { if ($ dieonerror == true) die('No such page.'."\n"); else return false; } foreach ($ x as $ data) { if (!isset($ data) or !is_array($ data)) { if ($ dieonerror == true) die('No such page.'."\n"); else return false; } foreach ($ data as $ data2) if ($ data2 == $ revid) $ found = true; unset($ data,$ data2); break; } if ($ found == false) { if ($ wait == true) { sleep(1); return $ this->revisions($ page,$ count,$ dir,$ content,$ revid,false,$ getrbtok,$ dieonerror); } else { if ($ dieonerror == true) die('Revision error.'."\n"); } } } foreach ($ x as $ key => $ data) { $ data = $ data; $ data = $ data; $ data = $ x; // $ data = $ x; $ data = $ x; $ data = $ key; return $ data; } } /** * Enumerates user metadata. * @param $ start The username to start enumerating from. Null means from the beginning. (Default null) * @param $ limit The number of users to enumerate. (Default 1) * @param $ group The usergroup to filter by. Null means no filtering. (Default null) * @param $ requirestart Whether or not to require that $ start be a valid username. (Default false) * @param $ continue This is filled with the name to continue from next query. (Default null) * @return Associative array of user metadata. **/ function users ($ start = null,$ limit = 1,$ group = null,$ requirestart = false,&$ continue = null) { $ append = ''; if ($ start != null) $ append .= '&aufrom='.urlencode($ start); if ($ group != null) $ append .= '&augroup='.urlencode($ group); $ x = $ this->http->get($ this->apiurl.'?action=query&list=allusers&format=php&auprop=blockinfo|editcount|registration|groups&aulimit='.urlencode($ limit).$ append); $ x = unserialize($ x); $ continue = $ x; if (($ requirestart == true) and ($ x != $ start)) return false; return $ x; } /** * Get members of a category. * @param $ category Category to enumerate from. * @param $ count Number of members to enumerate. (Default 500) * @param $ continue Where to continue enumerating from. This is automatically filled in when run. (Default null) * @return Associative array of category member metadata. **/ function categorymembers ($ category,$ count = 500,&$ continue = null) { if ($ continue != null) { $ append = '&cmcontinue='.urlencode($ continue); } else { $ append = ''; } $ category = 'Category:'.str_ireplace('category:','',$ category); $ x = $ this->http->get($ this->apiurl.'?action=query&list=categorymembers&cmtitle='.urlencode($ category).'&format=php&cmlimit='.$ count.$ append); $ x = unserialize($ x); $ continue = $ x; return $ x; } /** * Enumerate all categories. * @param $ start Where to start enumerating. This is updated automatically with the value to continue from. (Default null) * @param $ limit Number of categories to enumerate. (Default 50) * @param $ dir Direction to enumerate in. 'ascending' or 'descending'. (Default 'ascending') * @param $ prefix Only enumerate categories with this prefix. (Default null) * @return Associative array of category list metadata. **/ function listcategories (&$ start = null,$ limit = 50,$ dir = 'ascending',$ prefix = null) { $ append = ''; if ($ start != null) $ append .= '&acfrom='.urlencode($ start); if ($ limit != null) $ append .= '&aclimit='.urlencode($ limit); if ($ dir != null) $ append .= '&acdir='.urlencode($ dir); if ($ prefix != null) $ append .= '&acprefix='.urlencode($ prefix); $ x = $ this->http->get($ this->apiurl.'?action=query&list=allcategories&acprop=size&format=php'.$ append); $ x = unserialize($ x); $ start = $ x; return $ x; } /** * Enumerate all backlinks to a page. * @param $ page Page to search for backlinks to. * @param $ count Number of backlinks to list. (Default 500) * @param $ continue Where to start enumerating from. This is automatically filled in. (Default null) * @param $ filter Whether or not to include redirects. Acceptible values are 'all', 'redirects', and 'nonredirects'. (Default null) * @return Associative array of backlink metadata. **/ function backlinks ($ page,$ count = 500,&$ continue = null,$ filter = null) { if ($ continue != null) { $ append = '&blcontinue='.urlencode($ continue); } else { $ append = ''; } if ($ filter != null) { $ append .= '&blfilterredir='.urlencode($ filter); } $ x = $ this->http->get($ this->apiurl.'?action=query&list=backlinks&bltitle='.urlencode($ page).'&format=php&bllimit='.$ count.$ append); $ x = unserialize($ x); $ continue = $ x; return $ x; } /** * Gets a list of transcludes embedded in a page. * @param $ page Page to look for transcludes in. * @param $ count Number of transcludes to list. (Default 500) * @param $ continue Where to start enumerating from. This is automatically filled in. (Default null) * @return Associative array of transclude metadata. **/ 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; return $ x; } /** * Gets a list of pages with a common prefix. * @param $ prefix Common prefix to search for. * @param $ namespace Numeric namespace to filter on. (Default 0) * @param $ count Number of pages to list. (Default 500) * @param $ continue Where to start enumerating from. This is automatically filled in. (Default null) * @return Associative array of page metadata. **/ 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); $ continue = $ x; return $ x; } /** * Edits a page. * @param $ page Page name to edit. * @param $ data Data to post to page. * @param $ summary Edit summary to use. * @param $ minor Whether or not to mark edit as minor. (Default false) * @param $ bot Whether or not to mark edit as a bot edit. (Default true) * @param $ wpStarttime Time in MW TS format of beginning of edit. (Default now) * @param $ wpEdittime Time in MW TS format of last edit to that page. (Default correct) * @return boolean True on success, false on failure. **/ function edit ($ page,$ data,$ summary = '',$ minor = false,$ bot = true,$ wpStarttime = null,$ wpEdittime = null,$ checkrun = true) { global $ run, $ user; $ wpq = new wikipediaquery; $ wpq->queryurl = str_replace('api.php','query.php',$ this->apiurl); if ($ checkrun == true) if (!preg_match('/(yes|enable|true)/iS',((isset($ run))?$ run:$ wpq->getpage('User:'.$ user.'/Run')))) return false; /* Check /Run page */ $ params = Array( 'action' => 'edit', 'format' => 'php', 'assert' => 'bot', 'title' => $ page, 'text' => $ data, 'token' => $ this->getedittoken(), 'summary' => $ summary, ($ minor?'minor':'notminor') => '1', ($ bot?'bot':'notbot') => '1' ); if ($ wpStarttime !== null) $ params = $ wpStarttime; if ($ wpEdittime !== null) $ params = $ wpEdittime; $ x = $ this->http->post($ this->apiurl,$ params); $ x = unserialize($ x); var_export($ x); if ($ x == 'Success') return true; if ($ x == 'badtoken') { if($ this->login($ this->user,$ this->pass)) { $ this->gettokens('Main Page',true); return $ this->edit($ page,$ data,$ summary,$ minor,$ bot,$ wpStarttime,$ wpEdittime,$ checkrun); } else return false; } else return false; } /** * Moves a page. * @param $ old Name of page to move. * @param $ new New page title. * @param $ reason Move summary to use. * @return void **/ function move ($ old,$ new,$ reason) { $ tokens = $ this->gettokens($ old); $ params = array( 'action' => 'move', 'format' => 'php', 'from' => $ old, 'to' => $ new, 'token' => $ tokens, 'reason' => $ reason ); $ x = $ this->http->post($ this->apiurl,$ params); $ x = unserialize($ x); var_export($ x); } /** * Rollback an edit. * @param $ title Title of page to rollback. * @param $ user Username of last edit to the page to rollback. * @param $ reason Edit summary to use for rollback. * @param $ token Rollback token. If not given, it will be fetched. (Default null) * @return void **/ function rollback ($ title,$ user,$ reason,$ token = null) { if (($ token == null) or ($ token == '')) { $ token = $ this->revisions($ title,1,'older',false,null,true,true); print_r($ token); if ($ token == $ user) { $ token = $ token; } else { return false; } } $ params = array( 'action' => 'rollback', 'format' => 'php', 'title' => $ title, 'user' => $ user, 'summary' => $ reason, 'token' => $ token, 'markbot' => 0 ); echo 'Posting to API: '; var_export($ params); $ x = $ this->http->post($ this->apiurl,$ params); $ x = unserialize($ x); var_export($ x); return ( isset($ x) and isset( $ x ) and $ x ) ? true : false; } } /** * This class is for interacting with Knowledge (XXG)'s browser interface, index.php. * Many of these functions are deprecated. **/ class wikipediaindex { private $ http; public $ indexurl = 'http://en.wikipedia.org/search/'; private $ postinterval = 0; private $ lastpost; private $ edittoken; /** * This is our constructor. * @return void **/ function __construct () { global $ __wp__http; if (!isset($ __wp__http)) { $ __wp__http = new http; } $ this->http = &$ __wp__http; } /** * Post data to a page, nicely. * @param $ page Page title. * @param $ data Data to post to page. * @param $ summery Edit summary. (Default '') * @param $ minor Whether to mark edit as minor. (Default false) * @param $ rv Revision data. If not given, it will be fetched. (Default null) * @param $ bot Whether to mark edit as bot. (Default true) * @return HTML data from the page. * @deprecated * @see wikipediaapi::edit **/ function post ($ page,$ data,$ summery = '',$ minor = false,$ rv = null,$ bot = true) { global $ user; global $ maxlag; global $ irc; global $ irctechchannel; global $ run; global $ maxlagkeepgoing; $ wpq = new wikipediaquery; $ wpq->queryurl = str_replace('index.php','query.php',$ this->indexurl); $ wpapi = new wikipediaapi; $ wpapi->apiurl = str_replace('index.php','api.php',$ this->indexurl); if ((!$ this->edittoken) or ($ this->edittoken == '')) $ this->edittoken = $ wpapi->getedittoken(); if ($ rv == null) $ rv = $ wpapi->revisions($ page,1,'older',true); if (!$ rv) $ rv = $ wpq->getpage($ page); //Fake the edit form. $ now = gmdate('YmdHis', time()); $ token = htmlspecialchars($ this->edittoken); $ tmp = date_parse($ rv); $ edittime = gmdate('YmdHis', gmmktime($ tmp,$ tmp,$ tmp,$ tmp,$ tmp,$ tmp)); $ html = "<input type='hidden' value=\"{$ now}\" name=\"wpStarttime\" />\n"; $ html.= "<input type='hidden' value=\"{$ edittime}\" name=\"wpEdittime\" />\n"; $ html.= "<input type='hidden' value=\"{$ token}\" name=\"wpEditToken\" />\n"; $ html.= '<input name="wpAutoSummary" type="hidden" value="'.md5('').'" />'."\n"; if (preg_match('/'.preg_quote('{{nobots}}','/').'/iS',$ rv)) { return false; } /* Honor the bots flags */ if (preg_match('/'.preg_quote('{{bots|allow=none}}','/').'/iS',$ rv)) { return false; } if (preg_match('/'.preg_quote('{{bots|deny=all}}','/').'/iS',$ rv)) { return false; } if (preg_match('/'.preg_quote('{{bots|deny=','/').'(.*)'.preg_quote('}}','/').'/iS',$ rv,$ m)) { if (in_array(explode(',',$ m),$ user)) { return false; } } /* /Honor the bots flags */ if (!preg_match('/'.preg_quote($ user,'/').'/iS',$ rv)) { return false; } /* We need to be logged in */ // if (preg_match('/'.preg_quote('You have new messages','/').'/iS',$ rv)) { return false; } /* Check talk page */ if (!preg_match('/(yes|enable|true)/iS',((isset($ run))?$ run:$ wpq->getpage('User:'.$ user.'/Run')))) { return false; } /* Check /Run page */ $ x = $ this->forcepost($ page,$ data,$ summery,$ minor,$ html,$ maxlag,$ maxlagkeepgoing,$ bot); /* Go ahead and post. */ $ this->lastpost = time(); return $ x; } /** * Post data to a page. * @param $ page Page title. * @param $ data Data to post to page. * @param $ summery Edit summary. (Default '') * @param $ minor Whether to mark edit as minor. (Default false) * @param $ edithtml HTML from the edit form. If not given, it will be fetched. (Default null) * @param $ maxlag Maxlag for posting. (Default null) * @param $ mlkg Whether to keep going after encountering a maxlag error and sleeping or not. (Default null) * @param $ bot Whether to mark edit as bot. (Default true) * @return HTML data from the page. * @deprecated * @see wikipediaapi::edit **/ function forcepost ($ page,$ data,$ summery = '',$ minor = false,$ edithtml = null,$ maxlag = null,$ mlkg = null,$ bot = true) { $ post = ''; $ post = ''; if ($ minor == true) { $ post = 1; } $ post = $ data; $ post = $ 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 = $ m; preg_match('|\<input type\=\\\'hidden\\\' value\=\"(.*)\" name\=\"wpEdittime\" /\>|U',$ html,$ m); $ post = $ m; preg_match('|\<input type\=\\\'hidden\\\' value\=\"(.*)\" name\=\"wpEditToken\" /\>|U',$ html,$ m); $ post = $ m; preg_match('|\<input name\=\"wpAutoSummary\" type\=\"hidden\" value\=\"(.*)\" /\>|U',$ html,$ m); $ post = $ m; if ($ maxlag != null) { $ x = $ this->http->post($ this->indexurl.'?title='.urlencode($ page).'&action=submit&maxlag='.urlencode($ maxlag).'&bot='.(($ bot == true)?'1':'0'),$ post); if (preg_match('/Waiting for (*): (+) seconds lagged/S',$ x,$ lagged)) { global $ irc; if (is_resource($ irc)) { global $ irctechchannel; foreach(explode(',',$ irctechchannel) as $ y) { fwrite($ irc,'PRIVMSG '.$ y.' :'.$ lagged.' is lagged out by '.$ lagged.' seconds. ('.$ lagged.')'."\n"); } } sleep(10); if ($ mlkg != true) { return false; } else { $ x = $ this->http->post($ this->indexurl.'?title='.urlencode($ page).'&action=submit&bot='.(($ bot == true)?'1':'0'),$ post); } } return $ x; } else { return $ this->http->post($ this->indexurl.'?title='.urlencode($ page).'&action=submit&bot='.(($ bot == true)?'1':'0'),$ post); } } /** * Get a diff. * @param $ title Page title to get the diff of. * @param $ oldid Old revision ID. * @param $ id New revision ID. * @param $ wait Whether or not to wait for the diff to become available. (Default true) * @return Array of added data, removed data, and a rollback token if one was fetchable. **/ function diff ($ title,$ oldid,$ id,$ wait = true) { $ deleted = ''; $ added = ''; $ html = $ this->http->get($ this->indexurl.'?title='.urlencode($ title).'&action=render&diff='.urlencode($ id).'&oldid='.urlencode($ oldid).'&diffonly=1'); if (preg_match_all('/\&amp\;(oldid\=)(\d*)\\\'\>(Revision as of|Current revision as of)/USs', $ html, $ m, PREG_SET_ORDER)) { //print_r($ m); if ((($ oldid != $ m) and (is_numeric($ oldid))) or (($ id != $ m) and (is_numeric($ id)))) { if ($ wait == true) { sleep(1); return $ this->diff($ title,$ oldid,$ id,false); } else { echo 'OLDID as detected: '.$ m.' Wanted: '.$ oldid."\n"; echo 'NEWID as detected: '.$ m.' Wanted: '.$ id."\n"; echo $ html; die('Revision error.'."\n"); } } } if (preg_match_all('/\<td class\=(\"|\\\')diff-addedline\1\>\<div\>(.*)\<\/div\>\<\/td\>/USs', $ html, $ m, PREG_SET_ORDER)) { //print_r($ m); foreach ($ m as $ x) { $ added .= htmlspecialchars_decode(strip_tags($ x))."\n"; } } if (preg_match_all('/\<td class\=(\"|\\\')diff-deletedline\1\>\<div\>(.*)\<\/div\>\<\/td\>/USs', $ html, $ m, PREG_SET_ORDER)) { //print_r($ m); foreach ($ m as $ x) { $ deleted .= htmlspecialchars_decode(strip_tags($ x))."\n"; } } //echo $ added."\n".$ deleted."\n"; if (preg_match('/action\=rollback\&amp\;from\=.*\&amp\;token\=(.*)\"/US', $ html, $ m)) { $ rbtoken = $ m; $ rbtoken = urldecode($ rbtoken); // echo 'rbtoken: '.$ rbtoken.' -- '; print_r($ m); echo "\n\n"; return array($ added,$ deleted,$ rbtoken); } return array($ added,$ deleted); } /** * Rollback an edit. * @param $ title Page title to rollback. * @param $ user Username of last edit to the page to rollback. * @param $ reason Reason to rollback. If null, default is generated. (Default null) * @param $ token Rollback token to use. If null, it is fetched. (Default null) * @param $ bot Whether or not to mark as bot. (Default true) * @return HTML or false if failure. * @deprecated * @see wikipediaapi::rollback **/ function rollback ($ title,$ user,$ reason = null,$ token = null,$ bot = true) { if (($ token == null) or (!$ token)) { $ wpapi = new wikipediaapi; $ wpapi->apiurl = str_replace('index.php','api.php',$ this->indexurl); $ token = $ wpapi->revisions($ title,1,'older',false,null,true,true); if ($ token == $ user) { // echo 'Token: '; print_r($ token); echo "\n\n"; $ token = $ token; } else { return false; } } $ x = $ this->http->get($ this->indexurl.'?title='.urlencode($ title).'&action=rollback&from='.urlencode($ user).'&token='.urlencode($ token).(($ reason != null)?'&summary='.urlencode($ reason):'').'&bot='.(($ bot == true)?'1':'0')); global $ logfd; if (!is_resource($ logfd)) $ logfd = fopen('php://stderr','w'); fwrite($ logfd,'Rollback return: '.$ x."\n"); if (!preg_match('/action complete/iS',$ x)) return false; return $ x; } /** * Move a page. * @param $ old Page title to move. * @param $ new New title to move to. * @param $ reason Move page summary. * @return HTML page. * @deprecated * @see wikipediaapi::move **/ function move ($ old,$ new,$ reason) { $ wpapi = new wikipediaapi; $ wpapi->apiurl = str_replace('index.php','api.php',$ this->indexurl); if ((!$ this->edittoken) or ($ this->edittoken == '')) $ this->edittoken = $ wpapi->getedittoken(); $ token = htmlspecialchars($ this->edittoken); $ post = array ( 'wpOldTitle' => $ old, 'wpNewTitle' => $ new, 'wpReason' => $ reason, 'wpWatch' => '0', 'wpEditToken' => $ token, 'wpMove' => 'Move page' ); return $ this->http->post($ this->indexurl.'?title=Special:Movepage&action=submit',$ post); } /** * Uploads a file. * @param $ page Name of page on the wiki to upload as. * @param $ file Name of local file to upload. * @param $ desc Content of the file description page. * @return HTML content. **/ function upload ($ page,$ file,$ desc) { $ post = array ( 'wpUploadFile' => '@'.$ file, 'wpSourceType' => 'file', 'wpDestFile' => $ page, 'wpUploadDescription' => $ desc, 'wpLicense' => '', 'wpWatchthis' => '0', 'wpIgnoreWarning' => '1', 'wpUpload' => 'Upload file' ); return $ this->http->post($ this->indexurl.'?title=Special:Upload&action=submit',$ post); } /** * Check if a user has email enabled. * @param $ user Username to check whether or not the user has email enabled. * @return True or false depending on whether or not the user has email enabled. **/ function hasemail ($ user) { $ tmp = $ this->http->get($ this->indexurl.'?title=Special:EmailUser&target='.urlencode($ user)); if (stripos($ tmp,"No e-mail address") !== false) return false; return true; } /** * Sends an email to a user. * @param $ user Username to send email to. * @param $ subject Subject of email to send. * @param $ body Body of email to send. * @return HTML content. **/ function email ($ user,$ subject,$ body) { $ wpapi = new wikipediaapi; $ wpapi->apiurl = str_replace('index.php','api.php',$ this->indexurl); if ((!$ this->edittoken) or ($ this->edittoken == '')) $ this->edittoken = $ wpapi->getedittoken(); $ post = array ( 'wpSubject' => $ subject, 'wpText' => $ body, 'wpCCMe' => 0, 'wpSend' => 'Send', 'wpEditToken' => $ this->edittoken ); return $ this->http->post($ this->indexurl.'?title=Special:EmailUser&target='.urlencode($ user).'&action=submit',$ post); } } ?> 191:<?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 */ '/\\]/' => +20, /* This one is a false positive */ '/bitch/i' => -20, '/\bpussy\b/i' => -20, '/penis/i' => -20, '/Penisula/' => +20, /* False Positive */ '/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.*\b/U' => +2, /* This looks to be a correct sentence */ '/\b{30,}\b/U' => -10, /* All capitals? Looks like vandal activity */ '/\b{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. */ '/\{\{nfobox .*\}\}/U' => +20, /* Wiki infoboxes are good. */ '/\\]/iU' => +3 /* Wiki categories are good. */ ); $ scorelist = array_merge($ obscenelist,$ grammarlist); ?> 175:<?PHP unset($ log,$ log2); if ( /* Small changes with obscenities. */ (($ change >= -200) and ($ change <= 200)) and (($ d = $ wpi->diff($ change,$ change,$ change)) or true) and ((($ change == 'User:ClueBot/Sandbox') and print_r($ rv)) or true) and (($ s = score($ obscenelist,$ d,$ log)) or true) and (($ s -= score($ obscenelist,$ d,$ log2)) or true) and ( ( ($ s < -5) /* There are times when small changes are ok. */ and (($ rv = $ wpapi->revisions($ change,2,'older',true,$ change)) or true) and (!fnmatch('*#REDIRECT*',strtoupper(substr($ rv,0,9)))) and (!fnmatch('*SEX*',strtoupper($ rv))) and (!fnmatch('*BDSM*',strtoupper($ rv))) and (score($ obscenelist,$ change) >= 0) and (score($ obscenelist,$ rv) >= 0) and (!preg_match('/(^|\s)({1,2}(\*+|\-{3,}){0,2}|\*{4}|\-{4}|(\<|$)?censored(\>|$)?)(ing?|ed)?(\s|$ )/iS',$ rv)) and ($ heuristic .= '/obscenities') and ($ reason = 'making a minor change with obscenities') ) or ( ($ s > 5) and (($ rv = $ wpapi->revisions($ change,2,'older',true,$ change)) or true) and (!fnmatch('*#REDIRECT*',strtoupper(substr($ rv,0,9)))) and (!preg_match('/(^|\s)({1,2}(\*+|\-{3,}){0,2}|\*{4}|\-{4}|(\<|$)?censored(\>|$)?)(ing?|ed)?(\s|$ )/iS',$ rv)) and (preg_match('/(^|\s)({1,2}(\*+|\-{3,}){0,2}|\*{4}|\-{4}|(\<|$)?censored(\>|$)?)(ing?|ed)?(\s|$ )/iS',$ rv)) and ($ heuristic .= '/censor') and ($ reason = 'making a minor change censoring content (])') ) or ( (preg_match('/\!\!\!/S',$ d)) and (($ rv = $ wpapi->revisions($ change,2,'older',true,$ change)) or true) and (!preg_match('/\!\!\!/S',$ rv)) and (!fnmatch('*#REDIRECT*',strtoupper(substr($ rv,0,9)))) and ($ heuristic .= '/exclamation') and ($ reason = 'making a minor change adding "!!!"') ) ) ) { $ heuristicret = true; if (isset($ log2) and is_array($ log2)) foreach ($ log2 as $ k => $ v) $ log -= $ v; if (isset($ log) and is_array($ log)) foreach ($ log as $ k => $ v) if ($ v == 0) unset($ log); unset($ log2); /* fwrite($ irc,'PRIVMSG #wikipedia-BAG/ClueBot :Would revert http://en.wikipedia.org/search/?title='.urlencode($ change.$ change).'&diff=prev'.'&oldid='.urlencode($ change)." .\n"); */ } ?> 167:<?PHP unset($ log,$ log2); if ( /* Small changes with obscenities. */ (($ change >= -200) and ($ change <= 200)) and (($ d = $ wpi->diff($ change,$ change,$ change)) or true) and ((($ change == 'User:ClueBot/Sandbox') and print_r($ rv)) or true) and (($ s = score($ obscenelist,$ d,$ log)) or true) and (($ s -= score($ obscenelist,$ d,$ log2)) or true) and ( ( ($ s < -5) /* There are times when small changes are ok. */ and (($ rv = $ wpapi->revisions($ change,2,'older',true,$ change)) or true) and (!fnmatch('*#REDIRECT*',strtoupper(substr($ rv,0,9)))) and (!fnmatch('*SEX*',strtoupper($ rv))) and (!fnmatch('*BDSM*',strtoupper($ rv))) and (score($ obscenelist,$ change) >= 0) and (score($ obscenelist,$ rv) >= 0) and (!preg_match('/(^|\s)({1,2}(\*+|\-{3,}){0,2}|\*{4}|\-{4}|(\<|$)?censored(\>|$)?)(ing?|ed)?(\s|$ )/iS',$ rv)) and ($ heuristic .= '/obscenities') and ($ reason = 'making a minor change with obscenities') ) or ( ($ s > 5) and (($ rv = $ wpapi->revisions($ change,2,'older',true,$ change)) or true) and (!fnmatch('*#REDIRECT*',strtoupper(substr($ rv,0,9)))) and (!preg_match('/(^|\s)({1,2}(\*+|\-{3,}){0,2}|\*{4}|\-{4}|(\<|$)?censored(\>|$)?)(ing?|ed)?(\s|$ )/iS',$ rv)) and (preg_match('/(^|\s)({1,2}(\*+|\-{3,}){0,2}|\*{4}|\-{4}|(\<|$)?censored(\>|$)?)(ing?|ed)?(\s|$ )/iS',$ rv)) and ($ heuristic .= '/censor') and ($ reason = 'making a minor change censoring content (])') ) or ( (preg_match('/\!\!\!/S',$ d)) and (($ rv = $ wpapi->revisions($ change,2,'older',true,$ change)) or true) and (!preg_match('/\!\!\!/S',$ rv)) and (!fnmatch('*#REDIRECT*',strtoupper(substr($ rv,0,9)))) and ($ heuristic .= '/exclamation') and ($ reason = 'making a minor change adding "!!!"') ) ) ) { $ heuristicret = true; if (isset($ log2) and is_array($ log2)) foreach ($ log2 as $ k => $ v) $ log -= $ v; if (isset($ log) and is_array($ log)) foreach ($ log as $ k => $ v) if ($ v == 0) unset($ log); unset($ log2); /* fwrite($ irc,'PRIVMSG #wikipedia-BAG/ClueBot :Would revert http://en.wikipedia.org/search/?title='.urlencode($ change.$ change).'&diff=prev'.'&oldid='.urlencode($ change)." .\n"); */ } ?> 52:<?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); elseif ($ nret) $ out = '> '.$ line; else $ out = '< '.$ 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); } ?> 119:<?PHP if ( /* The Grawp vandal */ ( (fnmatch('*epic*lulz*on*nimp*org*',strtolower($ change))) or (fnmatch('*on*nimp*org*epic*lulz*',strtolower($ change))) or (fnmatch('*punishing*wikipedia*',strtolower($ change))) or (fnmatch('*anti*avril*hate*campaign*',strtolower($ change))) or (fnmatch('*HAGGER*',$ change)) or (fnmatch('*H?A?G?G?E?R*',$ change)) or (fnmatch('*h??a??g??g??e??r*',strtolower($ change))) or (fnmatch('*grawp*cock*',strtolower($ change))) or (fnmatch('*massive*cock*',strtolower($ change))) or (fnmatch('*grawp*dick*',strtolower($ change))) or (fnmatch('*massive*dick*',strtolower($ change))) or (fnmatch('*H?A?G?E?R*',$ change)) or (fnmatch('*hgger*',strtolower($ change))) ) and ($ reason = 'Grawp?') ) { $ heuristicret = true; foreach (explode(',',$ ircreportchannel) as $ y) fwrite($ irc,'PRIVMSG '.$ y.' :!admin Grawp vandal? ."]] .\n"); } ?> 95:<?PHP if ( /* The ClaimJumperPete vandal */ (($ change >= 100) and ($ change <= 400)) and ( ($ change <= 200) or ($ d = $ wpi->diff($ change,$ change,$ change)) ) and ( (fnmatch("*",trim(strtolower($ d)))) or (fnmatch("*",trim(strtolower($ d)))) or (fnmatch("*",trim(strtolower($ d)))) ) and ($ reason = 'ClaimJumperPete?') ) { $ heuristicret = true; foreach (explode(',',$ ircreportchannel) as $ y) fwrite($ irc,'PRIVMSG '.$ y.' :!admin ClaimJumperPete vandal? http://en.wikipedia.org/search/?title='.urlencode($ change).'&diff=prev'.'&oldid='.urlencode($ change)." .\n"); } ?> 159:<?PHP if ( /* The Redirect vandals */ ( ($ tfa == $ change) and (fnmatch('*#redirect *',strtolower($ wpq->getpage($ change)))) and ($ reason = 'redirecting featured article to new title') ) or ( ($ pagedata = $ wpq->getpage($ change)) and (substr(trim(strtolower($ pagedata)),0,10) == '#redirect ') and (preg_match('/\\]/',$ pagedata,$ m)) and (!$ wpq->getpage($ m)) and ($ reason = 'redirecting article to non-existant page') ) ) { $ heuristicret = true; // fwrite($ irc,'PRIVMSG #cvn-wp-en :!admin Grawp vandal? http://en.wikipedia.org/Special:Contributions/'.$ change." .\n"); } ?> 87:<?PHP if ( /* The Avril Lavigne vandal */ ( (preg_match('/avril\s*lavigne\s*roc*k**\s*my\s*soc*k**/i',$ change)) or (preg_match('/she\s*(is\s*)*(so\s*)*.*hot\!.*using.*TW/i',$ change)) // or ( // ($ change == 'Template:') // and (preg_match('/\{\{user((\s|_)talk)?:/i',$ wpq->getpage($ change))) // ) ) and ($ reason = 'Avril Lavigne vandal?') ) { $ heuristicret = true; foreach (explode(',',$ ircreportchannel) as $ y) fwrite($ irc,'PRIVMSG '.$ y.' :!admin Avril Lavigne vandal? ."]] .\n"); } ?> 111:<?PHP if ( /* The Evolution vandal */ ($ change == 'Evolution') and (($ pagedata = $ wpq->getpage($ change)) or true) and (fnmatch('*Genesis 1*The beginning*',$ pagedata)) and ($ reason = 'replacing article with the Bible') ) { $ heuristicret = true; foreach (explode(',',$ ircreportchannel) as $ y) fwrite($ irc,'PRIVMSG '.$ y.' :!admin Evolution vandal? http://en.wikipedia.org/search/?title='.urlencode($ change).'&diff=prev'.'&oldid='.urlencode($ change)." .\n"); } ?> 135:<?PHP if ( /* Massive deletes */ ($ change <= -7500) and ($ pagedata = $ wpq->getpage($ change)) and (!fnmatch('*#REDIRECT*',strtoupper(substr($ pagedata,0,9)))) and ($ rv = $ wpapi->revisions($ change,2,'older',true,$ change)) and ($ s = score($ scorelist,$ rv)) and ($ s += (score($ scorelist,$ rv)) * -1) and ($ s < -50) /* There are times when massive deletes are ok. */ and ($ reason = 'deleting '.($ change * -1).' characters') ) $ heuristicret = true; ?> 79:<?PHP $ heuristics = 'grawp'; $ heuristics = 'evolution'; $ heuristics = 'avrillavigne'; $ heuristics = 'editsummary'; $ heuristics = 'pagereplace'; $ heuristics = 'pageblank'; $ heuristics = 'massdelete'; $ heuristics = 'massadd'; $ heuristics = 'tables'; $ heuristics = 'smallchange'; $ heuristics = 'claimjumperpete'; $ heuristics = 'sneaky'; $ heuristics = 'redirect'; ?> 151:<?PHP if ( /* Page replaces */ (preg_match('/\\]Replaced page with (.*)$ /',$ change,$ m)) and ($ pagedata = $ wpq->getpage($ change)) and ($ fc = $ wpapi->revisions($ change,1,'newer')) and ($ fc != $ change) /* The creator is allowed to replace the page. */ and ($ reason = 'replacing entire content with something else') ) $ heuristicret = true; ?> 127:<?PHP if ( /* Massive additions */ ($ change >= 7500) and ($ rv = $ wpapi->revisions($ change,2,'older',true,$ change)) and ($ pagedata = $ wpq->getpage($ change)) and ($ s = score($ scorelist,$ rv)) and ($ s += (score($ scorelist,$ rv)) * -1) and ($ s < -1000) and ($ reason = 'score equals '.$ s) ) $ heuristicret = true; ?> 143:<?PHP if ( /* Page blanks */ (preg_match('/\,$ m)) and (($ pagedata = $ wpq->getpage($ change)) or true) and ($ fc = $ wpapi->revisions($ change,1,'newer')) and ($ fc != $ change) /* The creator is allowed to blank the page. */ and ($ reason = 'blanking the page') ) $ heuristicret = true; ?> 183:<?PHP if ( /* Massive tables */ ($ change >= 7500) and ($ rv = $ wpapi->revisions($ change,2,'older',true,$ change)) and (substr_count(strtolower($ rv),'<td') > 300) and ($ reason = 'adding huge, browser-crashing tables') ) $ heuristicret = true; ?> 103:<?PHP if ( ( (fnmatch('*nimp*org*',strtolower($ change))) ) and ($ reason = 'obscenities in edit summary') ) { $ heuristicret = true; } ?> 201: 197: 27: 17: 91:heuristics/cluebot.claimjumperpete.heuristic.php 83:heuristics/cluebot.avrillavigne.heuristic.php 8: 163:heuristics/cluebot.smallchange.heuristic.php 147:heuristics/cluebot.pagereplace.heuristic.php 99:heuristics/cluebot.editsummary.heuristic.php 26:The following is automatically generated by 131:heuristics/cluebot.massdelete.heuristic.php 139:heuristics/cluebot.pageblank.heuristic.php 107:heuristics/cluebot.evolution.heuristic.php 155:heuristics/cluebot.redirect.heuristic.php 123:heuristics/cluebot.massadd.heuristic.php 179:heuristics/cluebot.tables.heuristic.php 171:heuristics/cluebot.sneaky.heuristic.php 115:heuristics/cluebot.grawp.heuristic.php 75:Config (cluebot.heuristics.config.php) 7: 24: 48:Diff function (diff.function.php) 204:) 13:01, 27 November 2010 (UTC) 1: 37:Classes (wikibot.classes.php) 218: 59:Source to ClueBot 209: 217: 216: 212: 211: 210: 208: 207: 206: 194: 192: 189: 184: 181: 176: 173: 168: 165: 160: 157: 152: 149: 144: 141: 136: 133: 128: 125: 120: 117: 112: 109: 104: 101: 96: 93: 88: 85: 80: 77: 72: 66: 64: 61: 55: 53: 50: 44: 42: 39: 33: 22: 21: 20: 12: 11: 5: 215: 213: 190: 188: 185: 182: 180: 177: 174: 172: 169: 166: 164: 161: 158: 156: 153: 150: 148: 145: 142: 140: 137: 134: 132: 129: 126: 124: 121: 118: 116: 113: 110: 108: 105: 102: 100: 97: 94: 92: 89: 86: 84: 81: 78: 76: 73: 71: 68: 62: 60: 57: 51: 49: 46: 40: 38: 35: 23: 15: 14: 13: 10: 9: 6: 4: 3: 2: 214: 205: 203: 199: 195: 186: 178: 170: 162: 154: 146: 138: 130: 122: 114: 106: 98: 90: 82: 74: 69: 67: 58: 56: 47: 45: 36: 34: 31: 29: 19: 196: 193: 65: 54: 43: 32: 25: 18:User:ClueBot 187:Score list 70:Heuristics 198:ClueBot 28:ClueBot 16:< 202:talk 30:. 200:(

Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.

Index