public function fetchTestBinaries($groupname, $numarticles, $clearexistingbins)
{
$db = new DB();
$nntp = new Nntp();
$binaries = new Binaries();
$groups = new Groups();
$ret = array();
if ($clearexistingbins == true) {
$db->exec('truncate releaseregextesting');
}
$nntp->doConnect();
$groupsToFetch = array();
if (preg_match('/^[a-z]{2,3}(\\.[a-z0-9\\-]+)+$/', $groupname)) {
$groupsToFetch[] = array('name' => $groupname);
} elseif ($groupname === 0) {
$groupsToFetch = $groups->getAll();
} else {
$newsgroups = $nntp->getGroups();
foreach ($newsgroups as $ngroup) {
if (preg_match('/' . $groupname . '/', $ngroup['group'])) {
$groupsToFetch[] = array('name' => $ngroup['group']);
}
}
}
foreach ($groupsToFetch as $groupArr) {
$group = $groupArr['name'];
$data = $nntp->selectGroup($group);
if ($nntp->isError($data)) {
$ret[] = "Could not select group (doesnt exist on USP): {$group}";
continue;
} else {
$rangeStart = $data['last'] - $numarticles;
$rangeEnd = $groupEnd = $data['last'];
$rangeTotal = $rangeEnd - $rangeStart;
$done = false;
while ($done === false) {
if ($rangeTotal > $binaries->messagebuffer) {
if ($rangeStart + $binaries->messagebuffer > $groupEnd) {
$rangeEnd = $groupEnd;
} else {
$rangeEnd = $rangeStart + $binaries->messagebuffer;
}
}
if ($binaries->compressedHeaders) {
$msgs = $nntp->getXOverview($rangeStart . "-" . $rangeEnd, true, false);
} else {
$msgs = $nntp->getOverview($rangeStart . "-" . $rangeEnd, true, false);
}
if ($nntp->isError($msgs)) {
$ret[] = "Error {$msgs->code}: {$msgs->message} on " . $group;
continue 2;
}
$headers = array();
if (is_array($msgs)) {
//loop headers, figure out parts
foreach ($msgs as $msg) {
if (!isset($msg['Number'])) {
continue;
}
$msgPart = $msgTotalParts = 0;
$pattern = '|\\((\\d+)[\\/](\\d+)\\)|i';
preg_match_all($pattern, $msg['Subject'], $matches, PREG_PATTERN_ORDER);
$matchcnt = sizeof($matches[0]);
for ($i = 0; $i < $matchcnt; $i++) {
//not (int)'d here because of the preg_replace later on
$msgPart = $matches[1][$i];
$msgTotalParts = $matches[2][$i];
}
if (!isset($msg['Subject']) || $matchcnt == 0) {
// not a binary post most likely.. continue
continue;
}
if ((int) $msgPart > 0 && (int) $msgTotalParts > 0) {
$subject = utf8_encode(trim(preg_replace('|\\(' . $msgPart . '[\\/]' . $msgTotalParts . '\\)|i', '', $msg['Subject'])));
if (!isset($headers[$subject])) {
$headers[$subject]['Subject'] = $subject;
$headers[$subject]['From'] = $msg['From'];
$headers[$subject]['Date'] = strtotime($msg['Date']);
$headers[$subject]['Message-ID'] = $msg['Message-ID'];
$headers[$subject]['Size'] = $msg['Bytes'];
} else {
$headers[$subject]['Size'] += $msg['Bytes'];
}
}
}
unset($msgs);
if (isset($headers) && count($headers)) {
$groupRegexes = $this->getForGroup($group);
$binSetData = array();
foreach ($headers as $subject => $data) {
$binData = array('name' => $subject, 'fromname' => $data['From'], 'date' => $data['Date'], 'binaryhash' => md5($subject . $data['From'] . $group), 'groupname' => $group, 'regexID' => "null", 'categoryID' => "null", 'reqID' => "null", 'blacklistID' => 0, 'size' => $data['Size'], 'relname' => "null", 'relpart' => "null", 'reltotalpart' => "null");
//Filter binaries based on black/white list
if ($binaries->isBlackListed($data, $group)) {
//binary is blacklisted
$binData['blacklistID'] = 1;
}
//Apply Regexes
$regexMatches = array();
foreach ($groupRegexes as $groupRegex) {
$regexCheck = $this->performMatch($groupRegex, $subject, $data['From']);
if ($regexCheck !== false) {
$regexMatches = $regexCheck;
$binData['regexID'] = $regexCheck['regexID'];
$binData['categoryID'] = $regexCheck['regcatid'];
$binData['reqID'] = empty($regexCheck['reqID']) ? "null" : $regexCheck['reqID'];
$binData['relname'] = $regexCheck['name'];
break;
}
}
$binSetData[] = $binData;
}
//insert 500 bins at a time
$binChunks = array_chunk($binSetData, 500);
foreach ($binChunks as $binChunk) {
foreach ($binChunk as $chunk) {
$binParams[] = sprintf("(%s, %s, FROM_UNIXTIME(%s), %s, %s, %s, %s, %s, %d, %d, now())", $db->escapeString($chunk['name']), $db->escapeString($chunk['fromname']), $db->escapeString($chunk['date']), $db->escapeString($chunk['binaryhash']), $db->escapeString($chunk['groupname']), $chunk['regexID'], $chunk['categoryID'], $chunk['reqID'], $chunk['blacklistID'], $chunk['size']);
}
$binSql = "INSERT IGNORE INTO releaseregextesting (name, fromname, date, binaryhash, groupname, regexID, categoryID, reqID, blacklistID, size, dateadded) VALUES " . implode(', ', $binParams);
//echo $binSql;
$db->exec($binSql);
}
$ret[] = "Fetched " . number_format($numarticles) . " articles from " . $group;
} else {
$ret[] = "No headers found on " . $group;
continue;
}
} else {
$ret[] = "Can't get parts from server (msgs not array) on " . $group;
continue;
}
if ($rangeEnd == $groupEnd) {
$done = true;
}
$rangeStart = $rangeEnd + 1;
}
}
}
$nntp->doQuit();
return $ret;
}
/**
* Download a range of usenet messages. Store binaries with subjects matching a
* specific pattern in the database.
*/
function scan($nntp, $groupArr, $first, $last, $type = 'update')
{
$db = new Db();
$releaseRegex = new ReleaseRegex();
$n = $this->n;
$this->startHeaders = microtime(true);
if ($this->compressedHeaders) {
$nntpn = new Nntp();
$nntpn->doConnect(5, false, true);
$response = $nntpn->_sendCommand('XFEATURE COMPRESS GZIP');
if ($nntpn->isError($response) || $response != 290) {
$response2 = $nntpn->_sendCommand('XZVER');
if ($nntpn->isError($response2) || $response2 != 412) {
$msgs = $nntp->getOverview($first . "-" . $last, true, false);
$nntpn->doQuit();
} else {
$msgs = $nntp->getXOverview($first . "-" . $last, true, false);
$nntpn->doQuit();
}
} else {
$msgs = $nntp->getOverview($first . "-" . $last, true, false);
$nntpn->doQuit();
}
} else {
$msgs = $nntp->getOverview($first . "-" . $last, true, false);
}
if ($nntp->isError($msgs) && ($msgs->code == 400 || $msgs->code == 503)) {
echo "NNTP connection timed out. Reconnecting...{$n}";
if (!$nntp->doConnect()) {
// TODO: What now?
echo "Failed to get NNTP connection.{$n}";
return;
}
$nntp->selectGroup($groupArr['name']);
if ($this->compressedHeaders) {
$nntpn = new Nntp();
$nntpn->doConnect(5, false, true);
$response = $nntpn->_sendCommand('XFEATURE COMPRESS GZIP');
if ($nntpn->isError($response) || $response != 290) {
$response2 = $nntpn->_sendCommand('XZVER');
if ($nntpn->isError($response2) || $response2 != 412) {
$msgs = $nntp->getOverview($first . "-" . $last, true, false);
$nntpn->doQuit();
} else {
$msgs = $nntp->getXOverview($first . "-" . $last, true, false);
$nntpn->doQuit();
}
} else {
$msgs = $nntp->getOverview($first . "-" . $last, true, false);
$nntpn->doQuit();
}
} else {
$msgs = $nntp->getOverview($first . "-" . $last, true, false);
}
}
$rangerequested = range($first, $last);
$msgsreceived = array();
$msgsblacklisted = array();
$msgsignored = array();
$msgsinserted = array();
$msgsnotinserted = array();
$timeHeaders = number_format(microtime(true) - $this->startHeaders, 2);
if ($nntp->isError($msgs)) {
echo "Error {$msgs->code}: {$msgs->message}{$n}";
echo "Skipping group{$n}";
return false;
}
$this->startUpdate = microtime(true);
if (is_array($msgs)) {
//loop headers, figure out parts
foreach ($msgs as $msg) {
if (!isset($msg['Number'])) {
continue;
}
$msgsreceived[] = $msg['Number'];
$msgPart = $msgTotalParts = 0;
$pattern = '|\\((\\d+)[\\/](\\d+)\\)|i';
preg_match_all($pattern, $msg['Subject'], $matches, PREG_PATTERN_ORDER);
$matchcnt = sizeof($matches[0]);
for ($i = 0; $i < $matchcnt; $i++) {
$msgPart = $matches[1][$i];
$msgTotalParts = $matches[2][$i];
}
if (!isset($msg['Subject']) || $matchcnt == 0) {
$msgsignored[] = $msg['Number'];
continue;
}
if ((int) $msgPart > 0 && (int) $msgTotalParts > 0) {
$subject = utf8_encode(trim(preg_replace('|\\(' . $msgPart . '[\\/]' . $msgTotalParts . '\\)|i', '', $msg['Subject'])));
if (!isset($this->message[$subject])) {
$this->message[$subject] = $msg;
$this->message[$subject]['MaxParts'] = (int) $msgTotalParts;
$this->message[$subject]['Date'] = strtotime($this->message[$subject]['Date']);
}
if ((int) $msgPart > 0) {
$this->message[$subject]['Parts'][(int) $msgPart] = array('Message-ID' => substr($msg['Message-ID'], 1, -1), 'number' => $msg['Number'], 'part' => (int) $msgPart, 'size' => $msg['Bytes']);
$this->message[$subject]['PartNumbers'][(int) $msgPart] = $msg['Number'];
}
}
}
unset($msg);
unset($msgs);
$count = 0;
$updatecount = 0;
$partcount = 0;
$rangenotreceived = array_diff($rangerequested, $msgsreceived);
if ($type != 'partrepair') {
echo "Received " . sizeof($msgsreceived) . " articles of " . ($last - $first + 1) . " requested, " . sizeof($msgsignored) . " not binaries {$n}";
}
if ($type == 'update' && sizeof($msgsreceived) == 0) {
echo "Error: Server did not return any articles.{$n}";
echo "Skipping group{$n}";
return false;
}
if (sizeof($rangenotreceived) > 0) {
switch ($type) {
case 'backfill':
//don't add missing articles
break;
case 'partrepair':
case 'update':
default:
$this->addMissingParts($rangenotreceived, $groupArr['ID']);
break;
}
echo "Server did not return " . count($rangenotreceived) . " article(s).{$n}";
}
if (isset($this->message) && count($this->message)) {
$groupRegexes = $releaseRegex->getForGroup($groupArr['name']);
//insert binaries and parts into database. when binary already exists; only insert new parts
foreach ($this->message as $subject => $data) {
//Filter binaries based on black/white list
if ($this->isBlackListed($data, $groupArr['name'])) {
$msgsblacklisted[] = count($data['Parts']);
if ($type == 'partrepair') {
$partIds = array();
foreach ($data['Parts'] as $partdata) {
$partIds[] = $partdata['number'];
}
$db->exec(sprintf("DELETE FROM partrepair WHERE numberID IN (%s) AND groupID=%d", implode(',', $partIds), $groupArr['ID']));
}
continue;
}
if (isset($data['Parts']) && count($data['Parts']) > 0 && $subject != '') {
//Check for existing binary
$binaryID = 0;
$binaryHash = md5($subject . $data['From'] . $groupArr['ID']);
$res = $db->queryOneRow(sprintf("SELECT ID FROM binaries WHERE binaryhash = %s", $db->escapeString($binaryHash)));
if (!$res) {
//Apply Regexes
$regexMatches = array();
foreach ($groupRegexes as $groupRegex) {
$regexCheck = $releaseRegex->performMatch($groupRegex, $subject);
if ($regexCheck !== false) {
$regexMatches = $regexCheck;
break;
}
}
$sql = '';
if (!empty($regexMatches)) {
$relparts = explode("/", $regexMatches['parts']);
$sql = sprintf("INSERT INTO binaries (name, fromname, date, xref, totalparts, groupID, procstat, categoryID, regexID, reqID, relpart, reltotalpart, binaryhash, relname, dateadded) VALUES (%s, %s, FROM_UNIXTIME(%s), %s, %s, %d, %d, %s, %d, %s, %d, %d, %s, %s, now())", $db->escapeString($subject), $db->escapeString(utf8_encode($data['From'])), $db->escapeString($data['Date']), $db->escapeString($data['Xref']), $db->escapeString($data['MaxParts']), $groupArr['ID'], Releases::PROCSTAT_TITLEMATCHED, $regexMatches['regcatid'], $regexMatches['regexID'], $db->escapeString($regexMatches['reqID']), $relparts[0], $relparts[1], $db->escapeString($binaryHash), $db->escapeString(str_replace('_', ' ', $regexMatches['name'])));
} elseif ($this->onlyProcessRegexBinaries === false) {
$sql = sprintf("INSERT INTO binaries (name, fromname, date, xref, totalparts, groupID, binaryhash, dateadded) VALUES (%s, %s, FROM_UNIXTIME(%s), %s, %s, %d, %s, now())", $db->escapeString($subject), $db->escapeString(utf8_encode($data['From'])), $db->escapeString($data['Date']), $db->escapeString($data['Xref']), $db->escapeString($data['MaxParts']), $groupArr['ID'], $db->escapeString($binaryHash));
} elseif ($type == 'partrepair') {
$partIds = array();
foreach ($data['Parts'] as $partdata) {
$partIds[] = $partdata['number'];
}
$db->exec(sprintf("DELETE FROM partrepair WHERE numberID IN (%s) AND groupID=%d", implode(',', $partIds), $groupArr['ID']));
continue;
}
if ($sql != '') {
$binaryID = $db->queryInsert($sql);
$count++;
if ($count % 500 == 0) {
echo "{$count} bin adds...";
}
}
} else {
$binaryID = $res["ID"];
$updatecount++;
if ($updatecount % 500 == 0) {
echo "{$updatecount} bin updates...";
}
}
if ($binaryID != 0) {
$partParams = array();
$partNumbers = array();
$totsize = 0;
foreach ($data['Parts'] as $partdata) {
$partcount++;
$totsize += $partdata['size'];
$partParams[] = sprintf("(%d, %s, %s, %s, %s)", $binaryID, $db->escapeString($partdata['Message-ID']), $db->escapeString($partdata['number']), $db->escapeString(round($partdata['part'])), $db->escapeString($partdata['size']));
$partNumbers[] = $partdata['number'];
}
$partSql = "INSERT INTO parts (binaryID, messageID, number, partnumber, size) VALUES " . implode(', ', $partParams);
$pidata = $db->queryInsert($partSql, false);
if (!$pidata) {
$msgsnotinserted = array_merge($msgsnotinserted, $partNumbers);
} else {
$msgsinserted = array_merge($msgsinserted, $partNumbers);
}
// update bin size
$upsql = sprintf("update binaries set size = size + %d where ID = %d", $totsize, $binaryID);
$db->exec($upsql);
}
}
}
//TODO: determine whether to add to missing articles if insert failed
if (sizeof($msgsnotinserted) > 0) {
echo 'WARNING: ' . count($msgsnotinserted) . ' Parts failed to insert' . $n;
$this->addMissingParts($msgsnotinserted, $groupArr['ID']);
}
if ($count >= 500 || $updatecount >= 500) {
echo $n;
}
//line break for bin adds output
}
$timeUpdate = number_format(microtime(true) - $this->startUpdate, 2);
$timeLoop = number_format(microtime(true) - $this->startLoop, 2);
if (sizeof($msgsblacklisted) > 0) {
echo "Blacklisted " . array_sum($msgsblacklisted) . " parts in " . sizeof($msgsblacklisted) . " binaries" . $n;
}
if ($type != 'partrepair') {
echo number_format($count) . ' new, ' . number_format($updatecount) . ' updated, ' . number_format($partcount) . ' parts.';
echo " {$timeHeaders} headers, {$timeUpdate} update, {$timeLoop} range.{$n}";
}
unset($this->message);
unset($data);
return $last;
} else {
echo "Error: Can't get parts from server (msgs not array) {$n}";
echo "Skipping group{$n}";
return false;
}
}
/**
* Update a group back to a specified date.
*/
function backfillGroup($groupArr, $backfillDate = null, $regexOnly = false)
{
$db = new DB();
$binaries = new Binaries();
$n = $this->n;
if ($regexOnly === true) {
echo "Only inserting binaries which match regex{$n}";
$binaries->onlyProcessRegexBinaries = true;
}
$this->startGroup = microtime(true);
$nntp = new Nntp();
$nntpc = new Nntp();
//Make sure we actually have a connection going before doing anything.
if ($nntp->doConnect(5, false, true)) {
echo 'Processing ' . $groupArr['name'] . $n;
$data = $nntp->selectGroup($groupArr['name']);
if ($nntp->isError($data)) {
echo "Could not select group (bad name?): {$groupArr['name']}{$n}";
return;
}
if ($backfillDate) {
$targetpost = $this->daytopost($nntp, $groupArr['name'], $this->dateToDays($backfillDate), TRUE);
} else {
$targetpost = $this->daytopost($nntp, $groupArr['name'], $groupArr['backfill_target'], TRUE);
}
//get targetpost based on days target
if ($groupArr['first_record'] == 0 || $groupArr['backfill_target'] == 0 && !$backfillDate) {
echo "Group " . $groupArr['name'] . " has invalid numbers. Have you run update on it? Have you set the backfill days amount?{$n}";
return;
}
echo "Group " . $data["group"] . ": server has " . $data['first'] . " - " . $data['last'] . ", or ~";
echo (int) (($this->postdate($nntp, $data['last'], FALSE) - $this->postdate($nntp, $data['first'], FALSE)) / 86400);
echo " days." . $n . "Local first = " . $groupArr['first_record'] . " (";
echo (int) ((date('U') - $this->postdate($nntp, $groupArr['first_record'], FALSE)) / 86400);
echo " days). Backfill target of " . ($backfillDate ? date('Y-m-d', $backfillDate) : $groupArr['backfill_target'] . " days") . " is post {$targetpost}.{$n}";
if ($targetpost >= $groupArr['first_record']) {
echo "Nothing to do, we already have the target post.{$n} {$n}";
return "";
}
//get first and last part numbers from newsgroup
if ($targetpost < $data['first']) {
echo "WARNING: Backfill came back as before server's first. Setting targetpost to server first.{$n}";
echo "Skipping Group {$n}";
return "";
}
echo $binaries->onlyProcessRegexBinaries === true ? "Note: Discarding parts that do not match a regex" . $n : "";
//Done with $nntp for now, close it to avoid timeouts.
$nntp->doQuit();
$nntpc->doConnect();
$datac = $nntpc->selectGroup($groupArr['name']);
if ($nntpc->isError($datac)) {
echo "Could not select group (bad name?): {$groupArr['name']}{$n}";
return;
}
//calculate total number of parts
$total = $groupArr['first_record'] - $targetpost;
$done = false;
//set first and last, moving the window by maxxMssgs
$last = $groupArr['first_record'] - 1;
$first = $last - $binaries->messagebuffer + 1;
//set initial "chunk"
if ($targetpost > $first) {
//just in case this is the last chunk we needed
$first = $targetpost;
}
while ($done === false) {
$binaries->startLoop = microtime(true);
echo "Getting " . ($last - $first + 1) . " parts (" . number_format($first - $targetpost) . " in queue)" . $n;
flush();
$success = $binaries->scan($nntpc, $groupArr, $first, $last, 'backfill');
if (!$success) {
return "";
}
$db->exec(sprintf("update groups SET first_record = %s, last_updated = now() WHERE ID = %d", $db->escapeString($first), $groupArr['ID']));
if ($first == $targetpost) {
$done = true;
} else {
//Keep going: set new last, new first, check for last chunk.
$last = $first - 1;
$first = $last - $binaries->messagebuffer + 1;
if ($targetpost > $first) {
$first = $targetpost;
}
}
}
//Done with $nntpc
$nntpc->doQuit();
//Just need $nntp for a quick check on the first_record_postdate
$nntp->doConnect();
//$nntp->selectGroup($groupArr['name']); // some users report having this in keeps backfill working
$first_record_postdate = $this->postdate($nntp, $first, false);
//All done with NNTP.
$nntp->doQuit();
if ($first_record_postdate != "") {
$db->exec(sprintf("update groups SET first_record_postdate = FROM_UNIXTIME(" . $first_record_postdate . "), last_updated = now() WHERE ID = %d", $groupArr['ID']));
}
//Set group's first postdate
$timeGroup = number_format(microtime(true) - $this->startGroup, 2);
echo "Group processed in {$timeGroup} seconds {$n}";
} else {
echo "Failed to get NNTP connection.{$n}";
}
}
/**
* Get nzpre data from usenet and parse.
*/
public function nzpreUpdate()
{
require_once WWW_DIR . "/lib/nntp.php";
$s = new Sites();
$site = $s->get();
if (empty($site->nzpregroup) || empty($site->nzpresubject) || empty($site->nzpreposter) || empty($site->nzprefield) || empty($site->nzprekey)) {
return false;
}
if ($this->echooutput) {
echo "Predb : Checking for new pre data ";
}
$db = new DB();
$nntp = new Nntp();
if (!$nntp->doConnect()) {
echo "Failed to get NNTP connection\n";
return false;
}
$ret = $groupData = $nntp->selectGroup($site->nzpregroup);
if ($nntp->isError($ret)) {
echo "Predb : Error " . $ret->getMessage() . "\n";
return false;
}
$ret = $groupMsgs = $nntp->getOverview($groupData['last'] - (!empty($site->nzprearticles) ? $site->nzprearticles : 500) . '-' . $groupData['last']);
if ($nntp->isError($ret)) {
echo "Predb : Error " . $ret->getMessage() . "\n";
return false;
}
$added_updated = 0;
$nzprekey = $site->nzprekey;
while (strlen($nzprekey) < 1024) {
$nzprekey = $nzprekey . $nzprekey;
}
$cnt = !empty($site->nzprearticles) ? $site->nzprearticles : 500;
foreach ($groupMsgs as $groupMsg) {
if ($cnt % 50 == 0 && $cnt != 0 && $this->echooutput) {
echo $cnt . "..";
}
$cnt--;
if (preg_match('/^' . $site->nzpresubject . '$/', $groupMsg['Subject']) && preg_match('/^' . $site->nzpreposter . '$/', $groupMsg['From'])) {
$ret = $msgHeader = $nntp->getHeader($groupMsg['Message-ID']);
if ($nntp->isError($ret)) {
continue;
}
for ($i = 0; $i < count($msgHeader); $i++) {
if (preg_match('/^' . $site->nzprefield . ': /', $msgHeader[$i])) {
if ($nzpreParse = $this->nzpreParse(str_replace($site->nzprefield . ': ', '', $msgHeader[$i]), $nzprekey)) {
if ($this->updatePreDB($db, $nzpreParse)) {
$added_updated++;
}
}
break;
}
}
}
}
$nntp->disconnect();
if ($this->echooutput) {
echo "\nPredb : Added/Updated " . $added_updated . " records\n";
}
}
