AdSpeed.org | Giving it back

With JSONP, you can avoid the "Access is Denied" problem when loading a remote AJAX request. jQuery 1.2.x now supports JSONP, you can use that or this simple code snippet. In this example, let's assume you're on a page with a remote javascript loaded, now you only want this remote script to reload, not the whole page. And the result of getJSON.php:

Labels: ajax, code, javascript

If you need to reload a partial content (not the whole page) with JavaScript, you can easily use AJAX (jQuery is the simplest). But if the content is also from another website (eg: some API), then you can use JSONP (JSON with Padding) to get around the security protection of AJAX requests. And in the server-side javascript.php, you would return:

Labels: javascript

/** grid sorting class
* @since 3/29/2005
* @author Son Nguyen
* @package Scripts
* @subpackage Grid
*/
function CGridSort($pTableID) {
	this.mTable = $($pTableID);
	this.mSortOrder = null; // asc=0, desc=1
	this.mColumnIndex = null; // which is the actively sorted col
	this.mShouldBeOrder = null; // the correct order after sorted
	this.mCurrentOrder = null; // the current row order
	
	this.mBodyOnClass = null; // mouse over row style
	this.mBodyOffClass = null;
	this.mHeaderOnClass = null; // mouse over header style
	this.mHeaderOffClass = null;
	this.mHeaderUpClass = null; // header sorted up 
	this.mHeaderDownClass = null; 
	
	var $vRows = this.mTable.rows;
	for (var $i=1;$i<$vRows.length;$i++) { // assumption: 1st row is header! Skip!
		if ($vRows[$i].nodeName == 'TR') {
			var oThis = this;
			$vRows[$i].onmouseover = function () { oThis.highLiteRow(this) };
			$vRows[$i].onmouseout = function () { oThis.highLiteRow(this) };
		} // fi
	} // rof
}

CGridSort.prototype.setBodyClass = function($pOn,$pOff) {
	this.mBodyOnClass = $pOn;
	this.mBodyOffClass = $pOff;
}

CGridSort.prototype.setHeaderClass = function($pOn,$pOff,$pUp,$pDown) {
	this.mHeaderOnClass = $pOn;
	this.mHeaderOffClass = $pOff;
	this.mHeaderUpClass = $pUp;
	this.mHeaderDownClass = $pDown;
}

CGridSort.prototype.highLiteRow = function($pRowObj) {
	var $vCSS = new CElementCSS($pRowObj);
	if ($vCSS.hasStyle(this.mBodyOnClass)) {
		$vCSS.removeStyle(this.mBodyOnClass);
		$vCSS.appendStyle(this.mBodyOffClass);
	} else {
		$vCSS.removeStyle(this.mBodyOffClass);
		$vCSS.appendStyle(this.mBodyOnClass);
	} // fi
}

CGridSort.prototype.showSrtOrd = function($pHeaderCell,$pIsHeaderOn) {
	this.clearOrders($pHeaderCell);
	var $pPrimary = ($pIsHeaderOn==true)?this.mHeaderOnClass:this.mHeaderOffClass;
	
	if ($pHeaderCell.cellIndex==this.mColumnIndex && this.mSortOrder==0) {
		$pHeaderCell.className = $pPrimary+' '+this.mHeaderUpClass;
	} else if ($pHeaderCell.cellIndex==this.mColumnIndex && this.mSortOrder==1) {
		$pHeaderCell.className = $pPrimary+' '+this.mHeaderDownClass;
	} else {
		$pHeaderCell.className = $pPrimary;
	} // fi
}
/** clear orders for other headers */
CGridSort.prototype.clearOrders = function($pHeaderCell) {
	var $vHeaders = $pHeaderCell.parentNode.childNodes;
	for (var $i=0;$i<$vHeaders.length;$i++) {
		if ($vHeaders[$i].nodeName=='TH' && $i!=this.mColumnIndex && $vHeaders[$i] != $pHeaderCell) {
			$vHeaders[$i].className = this.mHeaderOffClass;
		} // fi
	} // rof
}

/** actually do the sorting */
CGridSort.prototype.sortCol = function($pColumnIndex) {
	this.mSortOrder = (this.mSortOrder!=null && $pColumnIndex==this.mColumnIndex)?(this.mSortOrder+1)%2:0;
	this.mColumnIndex = $pColumnIndex;

this.initSort();

// swap those not in place
	for (var $i=0;$i<this.mCurrentOrder.length;$i++) {
		if (this.mCurrentOrder[$i]!=this.mShouldBeOrder[this.mColumnIndex][$i]) {
			this.swapRow(this.mCurrentOrder[$i],this.mShouldBeOrder[this.mColumnIndex][$i]);	
		} // fi
	} // rof
	
	
	// reverse the order array
	this.mShouldBeOrder[this.mColumnIndex].reverse();
}

/** init the global vars, done for every col for the first time */
CGridSort.prototype.initSort = function() {
	// init gRows for this table if not done outside already
	if (this.mCurrentOrder==null) {
		this.mCurrentOrder = new Array();
		var $vLength = 0;
		var $vCnt = 0;
		var $vRows = this.mTable.rows;
		for (var $i=1;$i<$vRows.length;$i++) { // assumption: 1st row is header! Skip!
			if ($vRows[$i].nodeName == 'TR') {
				this.mCurrentOrder[this.mCurrentOrder.length] = $vRows[$i].id; 
			} // fi
		} // rof
	} // fi

// init order-by array
	if (this.mShouldBeOrder==null) { this.mShouldBeOrder = new Array(); }
	if (typeof(this.mShouldBeOrder[this.mColumnIndex])=='undefined') {
		this.mShouldBeOrder[this.mColumnIndex] = new Array();
		var $vTmpAry = new Array();
		var $vTmpAry2 = new Array();
		var $vCellValue = null;
		var $vKey = null;
		var $vSampleValue = null;
		for (var $i=0;$i<this.mCurrentOrder.length;$i++) {
			$vCellValue = this.processSortValue($(this.mCurrentOrder[$i]).cells[this.mColumnIndex].innerHTML);
			if ($vCellValue!='') {
				$vSampleValue = $vCellValue;
			} // if
			$vTmpAry[$i] = $vCellValue;

$vKey = $vCellValue;
			while (typeof($vTmpAry2[$vKey])!='undefined') {
				$vKey = $vKey+'x';
			} // rof
			$vTmpAry2[$vKey] = this.mCurrentOrder[$i];			
		} // rof

// determine sort algorithm and sorting
		var $vSortFn = null; // this.sortCaseInsen; // default, use the internally supported, the other give IE "Number Expected" err
		if ($vSampleValue.match(/^\d\d[\/-]\d\d[\/-]\d\d\d\d$/)) $vSortFn = this.sortDate;
	    if ($vSampleValue.match(/^\d\d[\/-]\d\d[\/-]\d\d$/)) $vSortFn = this.sortDate;
		if ($vSampleValue.match(/^[£$]/)) $vSortFn = this.sortCur;
	    if ($vSampleValue.match(/^[\d\.\,\%]+$/)) $vSortFn = this.sortNum;
		//alert($vSortFn);
		if ($vSortFn!=null) {
			$vTmpAry.sort($vSortFn);
		} else {
			$vTmpAry.sort();
		} // fi
		
		//alert('pass sorting');

// correct the duplicate rows
		for (var $i=0;$i<$vTmpAry.length;$i++) {
			for (var $j=$i+1;$j<$vTmpAry.length;$j++) {
				if ($vTmpAry[$i]==$vTmpAry[$j]) {
					$vTmpAry[$j] = $vTmpAry[$j]+'x';
				} else { // break out of the first loop now, save some time
					break;
				} // fi
			} // rof
		} // rof

var $vRowID = null;
		for (var $i=0;$i<$vTmpAry.length;$i++) {
			$vRowID = $vTmpAry2[$vTmpAry[$i]];
			this.mShouldBeOrder[this.mColumnIndex][$i] = $vRowID;
		} // rof
	} // fi
}

/** swapping data and index */
CGridSort.prototype.swapRow = function($pRowA,$pRowB) {
	var $vOne = $($pRowA);
	var $vTwo = $($pRowB);
	var $vTmp;

// 1.3 swap the data
	for (var $k=0;$k<$vOne.cells.length;$k++) {
		$vTmp = $vOne.cells[$k].innerHTML;
		$vOne.cells[$k].innerHTML = $vTwo.cells[$k].innerHTML;
		$vTwo.cells[$k].innerHTML = $vTmp;
	} // for

// 2.3 also swap index
	for (var $k=0;$k<this.mCurrentOrder.length;$k++) {
		if (this.mCurrentOrder[$k] == $pRowA) {
			this.mCurrentOrder[$k] = $pRowB;
		} else if (this.mCurrentOrder[$k] == $pRowB) {
			this.mCurrentOrder[$k] = $pRowA;
		} // else
	} // for

// 3.3 also swap id
	$vOne.id = $pRowB;
	$vTwo.id = $pRowA;
}

/** strip tags, process special comment for timestamp/other special cases */
CGridSort.prototype.processSortValue = function($pValue) {
	var $vResult = $pValue.match(//g);
	if ($vResult) { // comment stores the real value, ignore the outside
		$pValue = $vResult[0];
		$pValue = $pValue.substring(4,$pValue.length-4);
		$pValue = $pValue.replace(/ /g,'');
	} else { // strip tags or everything within tags
		var $vBkup = $pValue;
		// first try to strip everything between a pair of tags
		$pValue = $pValue.replace(/<[^>]+>/g,'<>'); // anything in <>
		$pValue = $pValue.replace(/<>.*<>/g,''); 
		$pValue = $pValue.replace(/<>/g,''); 
		if ($pValue=='') { // then only strip tags, leave everything in between
			$pValue = $vBkup.replace(/<[^>]+>/g,''); 
		} // fi
		$pValue = $pValue.replace(/^\s*|\s*$/g,'');	// whitespaces
		$pValue = $pValue.replace(/ /g,'');
		$pValue = $pValue.replace(/ /g,'');
		$pValue = $pValue.replace(/\n/g,'');
	} // fi
	return $pValue;
}

/** HELPER, SORT FUNCTIONS */

/** sort case insensitive */
CGridSort.prototype.sortCaseInsen = function($pValueA,$pValueB) {
	$pValueA = $pValueA.toLowerCase();
	$pValueB = $pValueB.toLowerCase();

if ($pValueA>$pValueB) return 1;
    if ($pValueA<$pValueB) return -1;
    return 0;
}

CGridSort.prototype.sortNum = function($pValueA,$pValueB) { 
	$pValueA = parseFloat($pValueA.replace(/[^0-9.]/g,''));
    $pValueB = parseFloat($pValueB.replace(/[^0-9.]/g,''));

if (isNaN($pValueA)) $pValueA = 0;
	if (isNaN($pValueB)) $pValueB = 0;

return $pValueA-$pValueB;
}

/** sort on date */
CGridSort.prototype.sortDate = function($pValueA,$pValueB) {
    if ($pValueA.length == 10) {
        $dt1 = $pValueA.substr(6,4)+$pValueA.substr(3,2)+$pValueA.substr(0,2);
    } else {
        $yr = $pValueA.substr(6,2);
        if (parseInt($yr) < 50) { $yr = '20'+$yr; } else { $yr = '19'+$yr; }
        $dt1 = $yr+$pValueA.substr(3,2)+$pValueA.substr(0,2);
    } // if

if ($pValueB.length == 10) {
        $dt2 = $pValueB.substr(6,4)+$pValueB.substr(3,2)+$pValueB.substr(0,2);
    } else {
        $yr = $pValueB.substr(6,2);
        if (parseInt($yr) < 50) { $yr = '20'+$yr; } else { $yr = '19'+$yr; }
        $dt2 = $yr+$pValueB.substr(3,2)+$pValueB.substr(0,2);
    }
    if ($dt1==$dt2) return 0;
    if ($dt1<$dt2) return -1;
    return 1;
}

/** sort currency */
CGridSort.prototype.sortCur = function($pValueA,$pValueB) { 
	$pValueA = $pValueA.replace(/[^0-9.]/g,'');
    $pValueB = $pValueB.replace(/[^0-9.]/g,'');
    return parseFloat($pValueA) - parseFloat($pValueB);
}

Given a content string, this class uses Yahoo Term Extraction API to generate a list of keywords/phrases that you can use for things like META tags or other SEO objectives.

<?php
/** 
* @author Son Nguyen
* @since 2/13/2006
* @package Framework
* @subpackage WebServices
*/
class CYahooTermExtraction extends CYahooAPI {
 private $mContext; // string, get main keywords from this text
 /** constructor */
 function __construct($pContext) {
  $this->mServiceURL = 'http://api.search.yahoo.com/ContentAnalysisService/V1/termExtraction';
  $this->mContext = $pContext;
 }

/** get the tags/keywords through Yahoo API */
 function fetchTags() {
  $vReq = new CHTTPRequest($this->mServiceURL);
  $vReq->addQueryString('appid',$this->mAppID);
  $vReq->addQueryString('context',$this->mContext);
  list($vHeader,$vBody) = $vReq->sendPOST();
  //var_dump($vHeader,$vBody);die;
  $vXML = simplexml_load_string($vBody);
  $vTmp = array();
  foreach ($vXML->Result AS $vOne) {
   $vTmp[] = (string)$vOne;
  } // rof
  return $vTmp; // an array of tags
 }

/** comment */
 function display() {
  $vTags = $this->fetchTags();
  return implode(', ',$vTags);
 }
}
?>

<?php
/** 
* @author Son Nguyen
* @since 3/21/2006
* @package Framework
* @subpackage WebServices
*/
class CYahooAPI {
 protected $mAppID = 'YourYahooApplicationID';
 protected $mServiceURL;

/** constructor */
 function __construct() {
  
 }
}
?>

Labels: code

This class parses, fixes and prepares php_browscap.ini into browscap.ini for PHP. It also detects if the latest version needed to download.

<?php
/** from localhost to fetch and prepare the browscap.ini file
* @author Son Nguyen
* @since 8/25/2006
* @package Framework
* @subpackage Lookup
*/
class CBrowsCap {
 private $mTmpFileName = 'php_browscap.ini'; // tmp file before fixing
 private $mDownloadURL = 'http://browsers.garykeith.com/stream.asp?PHP_BrowsCapINI';
 /** constructor */
 function __construct() {}

/** get the version string from the file */
 function getVersion($pFile,$pCheckExisted) {
  $vVersion = NULL;
  if ($pCheckExisted && !file_exists($pFile)) {
   return NULL;
  } // fi

$vContent = file_get_contents($pFile,FALSE,NULL,0,500);
  if (preg_match('/version=(.*)/i',$vContent,$vMatches)) {
   $vVersion = trim($vMatches[1]);
  } // fi
  return $vVersion;
 }

/** comment */
 function getLatestVersion() {
  return $this->getVersion($this->mDownloadURL,FALSE);
 }

/** get the current I'm currently use */
 function getMyVersion() {
  return $this->getVersion($this->mTmpFileName,TRUE);
 }

/** if need to update */
 function checkUpdate() {
  $vMy = $this->getMyVersion();
  $vLatest = $this->getLatestVersion();
  if (!file_exists($this->mTmpFileName) || $vMy<$vLatest) { // should update
   $vContent = file_get_contents($this->mDownloadURL);
   file_put_contents($this->mTmpFileName,$vContent);
   return 'Updated to version #'.$vLatest.' from #'.$vMy; // yes, do update
  } // fi

return 'Already at the latest version #'.$vLatest; // latest, don't update
 }

/** fix the browsecap.ini for php */
 function fix() {
  $vOutput = $this->checkUpdate();

$vContent = file_get_contents($this->mTmpFileName);
  $vContent = preg_replace("/\r/","",$vContent);
  $vContent = preg_replace('/="(.*)"/i','=\\1',$vContent);
  $vContent = preg_replace("/platform=(.*)/i","platform=\"\\1\"",$vContent);
  $vContent = preg_replace("/parent=(.*)/i","parent=\"\\1\"",$vContent);
  $vContent = preg_replace("/minorver=(.*)/i","minorver=\"\\1\"",$vContent);
  $vContent = preg_replace("/majorver=(.*)/i","majorver=\"\\1\"",$vContent);
  $vContent = preg_replace("/version=(.*)/i","version=\"\\1\"",$vContent);
  $vContent = preg_replace("/browser=(.*)/i","browser=\"\\1\"",$vContent);
  $vContent = str_replace("[*]","*",$vContent);
  file_put_contents('browscap.ini',$vContent);

return $vOutput;
 }
}
?>

Labels: code

Developers can use the browscap.ini to detect if the User-Agent is a search engine or data collection spider or not. However, that file is rather large and will be expensive on resources. If you need a faster, simpler (albeit less accurate) method, this class can be useful.

<?php
/** a quick/less resource intensive browser detection
* @author Son Nguyen
* @since 1/29/2007
* @package Framework
* @subpackage Misc
*/
class CBrowserDetect {
 private $mUA;
 /** constructor */
 function __construct($pUA=NULL) {
  $this->setUA($pUA);
 }

/** comment */
 function setUA($pUA=NULL) {
  if (is_null($pUA) && isset($_SERVER['HTTP_USER_AGENT'])) {
   $this->mUA = $_SERVER['HTTP_USER_AGENT'];
  } else {
   $this->mUA = $pUA;
  } // fi
 }

/** if this is a spider/crawler */
 function isSpider($pUA=NULL) {
  $this->setUA($pUA);
  $vBots = array( 
   'AdsBot-Google',
   'alexa',
   'appie',
   'Ask Jeeves',
   'Baiduspider',
   'crawler',
   'FAST',
   'Firefly',
   'froogle',
   'girafabot',
   'Googlebot',
   'ia_archiver',
   'InfoSeek',
   'inktomi',
   'Java/',
   'looksmart',
   'msnbot',
   'NationalDirectory',
   'rabaz',
   'Scooter',
   'Slurp',
   'Spade',
   'TECNOSEEK',
   'Teoma',
   'URL_Spider_SQL',
   'WebBug',
   'WebCapture',
   'WebFindBot',
   'Wget/',
   'ZyBorg',
   'libwww-perl/',
   'httpunit/',
   'WebZIP/',
  );
  foreach ($vBots AS $vPat) {
   if (stripos($this->mUA,$vPat)!==FALSE) {
    return TRUE;
   } // fi
  } // rof
  return FALSE;
 }
}
?>

Labels: code

Lighttpd, fast-cgi & PHP can do quite a wonderful setup that can handle significant load. You can have many layers of load balancing & fail-over. Here is a three-layer approach. A dedicated load balancer directs many web servers. Each web server (lighttpd) delegates the processing of dynamic to multiple application servers (fast-cgi).

Configurations

Check out the lighttpd config for mod_fastcgi. In this case, we want only load-balance a single controller PHP file that is called heavily. We also let the webserver be the appserver itself for the moment and become a dedicated one if it becomes overloaded. All other regular PHP requests are served by the localhost (webserver). Add this into your lighttpd.conf: To start the fast-cgi processes on the application servers:

PowerDNS has a webserver that reports running stats. This code converts the HTML output (which has quite a few syntactic HTML errors) to semi-XML Output

<Section name="Summary">
PowerDNS Operational Monitor
PDNS 2.9.21 Main Page
Uptime: 6.48 hours
Queries/second, 1, 5, 10 minute averages:  0.549, 0.519, 0.532. Max queries/second: 2.57
Cache hitrate, 1, 5, 10 minute averages: 0%, 0%, 0%
Backend query cache hitrate, 1, 5, 10 minute averages: 4.6%, 4.1%, 3.9%
Backend query load, 1, 5, 10 minute averages: 0.845, 0.848, 0.884. Max queries/second: 4.88
Total queries: 13428. Question/answer latency: 0ms
</Section>

<Section name="Top-10 of 0: Log Messages">
 Total:   0   100%
</Section>
<Section name="Top-10 of 0: Queries for existing records, but for type we don't have">
 Total:   0   100%
</Section>
<Section name="Top-10 of 1: Queries for non-existent records within existent domains">
 *.videoserving.com/A   1   1e+02%
 Total:   1   100%
</Section>
<Section name="Top-10 of 21: UDP Queries Received">
 g.videoserving.com/A   5272   53%
 x.videoserving.com/A   2887   29%
 x.videoserving.com/AAAA   785   7.8%
 b.videoserving.com/A   642   6.4%
 g.videoserving.com/AAAA   163   1.6%
 videoserving.com/MX   133   1.3%
 b.videoserving.com/AAAA   69   0.69%
 v.videoserving.com/A   15   0.15%
 y.videoserving.com/MX   9   0.09%
 g.videoserving.com/MX   6   0.06%
 Rest:   19   0.19%
 Total:   10000   100%
</Section>
<Section name="Top-10 of 5323: Remote server IP addresses">
 xx.248.95.194   251   2.5%
 xx.226.48.165   119   1.2%
 xx.24.7.3   89   0.89%
 xx.94.163.100   67   0.67%
 xx.183.64.46   60   0.6%
 xx.29.103.10   58   0.58%
 xx.92.226.9   57   0.57%
 xx.25.5.150   41   0.41%
 xx.96.83.2   29   0.29%
 xx.68.8.4   29   0.29%
 Rest:   9200   92%
 Total:   10000   100%
</Section>
<Section name="Top-10 of 0: Remote hosts sending corrupt packets">
 Total:   0   100%
</Section>
<Section name="Top-10 of 2: Remote hosts querying domains for which we are not auth">
 xx.xx.190.249   2   67%
 xx.xx.245.57   1   33%
 Total:   3   100%
</Section>
<Section name="Top-10 of 0: Queries that could not be answered due to backend errors">
 Total:   0   100%
</Section>
<Section name="Top-10 of 3: Queries for domains that we are not authoritative for">
 irc.xx.com/A   1   33%
 spy.xxx.us/A   1   33%
 www.xxxx.com/A   1   33%
 Total:   3   100%
</Section>
<Section name="Variables">
corrupt-packets   0   Number of corrupt packets received
deferred-cache-inserts   0   Amount of cache inserts that were deferred because of maintenance
deferred-cache-lookup   0   Amount of cache lookups that were deferred because of maintenance
latency   0   Average number of microseconds needed to answer a question
packetcache-hit   0 
packetcache-miss   13428 
packetcache-size   0 
qsize-q   1   Number of questions waiting for database attention
query-cache-hit   925   Number of hits on the query cache
query-cache-miss   22721   Number of misses on the query cache
recursing-answers   0   Number of recursive answers sent out
recursing-questions   0   Number of questions sent to recursor
servfail-packets   0   Number of times a server-failed packet was sent out
tcp-answers   0   Number of answers sent out over TCP
tcp-queries   0   Number of TCP queries received
timedout-packets   0   Number of packets which weren't answered within timeout set
udp-answers   13428   Number of answers sent out over UDP
udp-queries   13428   Number of UDP queries received
udp4-answers   13428   Number of IPv4 answers sent out over UDP
udp4-queries   13428   Number of IPv4UDP queries received
udp6-answers   0   Number of IPv6 answers sent out over UDP
udp6-queries   0   Number of IPv6 UDP queries received
</Section>

Labels: dns

This is the RPM for eAccelerator 0.9.5 for PHP 5.1.6 including source RPM, you can rebuild it by running "rpmbuild --rebuild file.rpm" php-eaccelerator-5.1.6_0.9.5-1.centos4.src.rpm php-eaccelerator-5.1.6_0.9.5-1.centos4.i386.rpm

If you find str_rot13 is limited, this is a more customized string rotation function. It allows you to specify how many characters to shift (positive for moving forward, negative for moving backward) and which characters to shift.

Usage: mysql_tables.sh --optimize MyDatabaseABC

If you have access to the zone files from Verisign (COM/NET/EDU) and want to extract the list of domains from these zone file. This is a one-line extraction command in Linux:

;File start: 95720
; The use of the Data contained in Verisign Inc.' aggregated
; .com, and .net top-level domain zone files (including the checksum
; files) is subject to the restrictions described in the access Agreement
; with Verisign Inc.

$ORIGIN EDU.
@ IN    SOA     L3.NSTLD.COM. NSTLD.VERISIGN-GRS.COM. (
                                  2006040800 ;serial
                                  1800 ;refresh every 30 min
                                  900 ;retry every 15 min
                                  604800 ;expire after a week
                                  86400 ;minimum of a day
                                  )
$TTL 518400
 NS L3.NSTLD.COM.
 NS D3.NSTLD.COM.
 NS A3.NSTLD.COM.
 NS E3.NSTLD.COM.
 NS C3.NSTLD.COM.
 NS G3.NSTLD.COM.
 NS M3.NSTLD.COM.
 NS H3.NSTLD.COM.
L3.NSTLD.COM. A 192.41.162.32
D3.NSTLD.COM. A 192.31.80.32
A3.NSTLD.COM. A 192.5.6.32
E3.NSTLD.COM. A 192.12.94.32
C3.NSTLD.COM. A 192.26.92.32
G3.NSTLD.COM. A 192.42.93.32
M3.NSTLD.COM. A 192.55.83.32
H3.NSTLD.COM. A 192.54.112.32
$TTL 172800
22CF NS DNS1.NAME-SERVICES.COM.
22CF NS DNS2.NAME-SERVICES.COM.
22CF NS DNS3.NAME-SERVICES.COM.
......

The command:

grep '^[a-zA-Z0-9-]\+ NS .*' edu.zone|sed 's/NS .*//'|uniq

The output will be something like this: Timing test (DB as of April 09, 2006, tested on Dual Opteron 244, 4G RAM)

DOT EDU (edu.zone, 7,645 domains)
real    0m0.143s
user    0m0.240s
sys     0m0.010s

DOT NET (net.zone, 7,338,096 domains)
real    3m33.223s
user    4m29.380s
sys     0m3.130s

DOT COM (com.zone, 50,495,462 domains)
real    24m47.369s
user    32m51.330s
sys     0m25.420s

If divide the one-liner command into 3 separate ones, performance decreases

# time grep '^[a-zA-Z0-9]\+ NS .*' net.zone > net.grep
real    2m27.388s
user    2m21.480s
sys     0m2.400s

# time sed 's/NS .*//' net.grep > net.sed
real    1m46.816s
user    1m0.270s
sys     0m1.380s

# time uniq net.sed > net.uniq
real    1m13.276s
user    1m4.180s
sys     0m0.570s

This PHP5 class utilizes the web service provided by Alexa/Amazon to get the traffic information about the site. You'll need to sign up for an account at Alexa to get the pair (access key and secret key). The first 10,000 queries per month are free.

<?php
/** 
* @author Son Nguyen
* @since 3/31/2006
* @package Framework
* @subpackage WebServices
*/
class CAlexaAPI {
  private $mParams;
  private $mSecretKey = 'YOUR SECRET KEY'; 
  /** constructor */
  function __construct() {
    $this->mParams = array(
      'Service'=>'AlexaWebInfoService',
      'AWSAccessKeyId'=>'YOUR ACCESS KEY', // access key id
      'Operation'=>'UrlInfo',
      'ResponseGroup'=>'Rank',
      'Url'=>NULL,
      'Timestamp'=>gmdate('Y-m-d\TH:i:s.000\Z'),
      'Signature'=>NULL,
    );
    $this->prepareSignature();
  }

/** ref: http://developer.amazonwebservices.com/connect/thread.jspa?threadID=9675 */
  private function calculate_RFC2104HMAC ($data, $key) {
    return base64_encode(
      pack("H*", sha1((str_pad($key, 64, chr(0x00))
      ^(str_repeat(chr(0x5c), 64))) .
      pack("H*", sha1((str_pad($key, 64, chr(0x00))
      ^(str_repeat(chr(0x36), 64))) . $data))))
    );
  }

/** have the signature ready */
  private function prepareSignature() {
    $vData = $this->mParams['Service'].$this->mParams['Operation'].$this->mParams['Timestamp'];
    $this->mParams['Signature'] = $this->calculate_RFC2104HMAC($vData,$this->mSecretKey);
  }

/** make the rest call and return result as XML object */
  function call() {
    $vURL = 'http://awis.amazonaws.com/onca/xml?';
    $vTmp = array();
    foreach ($this->mParams AS $vKey=>$vValue) {
      $vTmp[] = $vKey.'='.$vValue;
    } // rof
    $vURL .= implode('&',$vTmp);
    $vFile = file_get_contents($vURL);
    $vXML = simplexml_load_string($vFile);
    return $vXML;
  }

/** get the rank for a domain */
  function getRank($pDomain) {
    $this->mParams['Url'] = $pDomain;
    $vResult = $this->call();
    $vResult = $vResult->UrlInfoResult->Alexa->TrafficData->Rank+0;
    return $vResult;
  }
}
?>

Sample Usage:

This PHP5 class computes the Google PR for any URL. Source code is available online and this is the PHP5 version, can be plugged into any application/software.

<?php
/** source available online in public domain
* @author Son Nguyen
* @since 3/30/2006
* @package Framework
* @subpackage WebServices
*/
class CGooglePR {
  /** constructor */
  function __construct() {
  }

function getRank($pURL) {
    $pURL = 'info:'.$pURL;
    $ch = $this->GoogleCH($this->strord($pURL));
    $vFile = "http://www.google.com/search?client=navclient-auto&ch=6$ch&features=Rank&q=".$pURL;
    $data = file($vFile);
    $rankarray = explode (':', $data[2]);
    $rank = $rankarray[2];
    return intval($rank);
  }

/** unsigned shift right */
  function zeroFill($a,$b) {
    $z = hexdec(80000000);
    if ($z & $a) {
      $a = ($a>>1);
      $a &= (~$z);
      $a |= 0x40000000;
      $a = ($a>>($b-1));
    } else {
      $a = ($a>>$b);
    } // fi
    return $a;
  }

function mix($a,$b,$c) {
    $a -= $b; $a -= $c; $a ^= ($this->zeroFill($c,13));
    $b -= $c; $b -= $a; $b ^= ($a<<8);
    $c -= $a; $c -= $b; $c ^= ($this->zeroFill($b,13));
    $a -= $b; $a -= $c; $a ^= ($this->zeroFill($c,12));
    $b -= $c; $b -= $a; $b ^= ($a<<16);
    $c -= $a; $c -= $b; $c ^= ($this->zeroFill($b,5));
    $a -= $b; $a -= $c; $a ^= ($this->zeroFill($c,3));   
    $b -= $c; $b -= $a; $b ^= ($a<<10);
    $c -= $a; $c -= $b; $c ^= ($this->zeroFill($b,15));
    return array($a,$b,$c);
  }

/** converts a string into an array of integers containing the numeric value of the char */
  function strord($pStr) {
    $vResult = array();
    for($i=0;$i<strlen($pStr);$i++) {
      $vResult[$i] = ord($pStr{$i});
      } // rof
    return $vResult;
  }

function GoogleCH($url,$length=null,$init=0xE6359A60) {
    if(is_null($length)) {
      $length = sizeof($url);
    } // fi

$a = $b = 0x9E3779B9;
    $c = $init;
    $k = 0;
    $len = $length;
    while($len >= 12) {
      $a += ($url[$k+0] +($url[$k+1]<<8) +($url[$k+2]<<16) +($url[$k+3]<<24));
      $b += ($url[$k+4] +($url[$k+5]<<8) +($url[$k+6]<<16) +($url[$k+7]<<24));
      $c += ($url[$k+8] +($url[$k+9]<<8) +($url[$k+10]<<16)+($url[$k+11]<<24));
      $mix = $this->mix($a,$b,$c);
      $a = $mix[0]; $b = $mix[1]; $c = $mix[2];
      $k += 12;
      $len -= 12;
    } // rof

$c += $length;
    switch($len) {
      case 11: $c+=($url[$k+10]<<24);
      case 10: $c+=($url[$k+9]<<16);
      case 9 : $c+=($url[$k+8]<<8);
      case 8 : $b+=($url[$k+7]<<24);
      case 7 : $b+=($url[$k+6]<<16);
      case 6 : $b+=($url[$k+5]<<8);
      case 5 : $b+=($url[$k+4]);
      case 4 : $a+=($url[$k+3]<<24);
      case 3 : $a+=($url[$k+2]<<16);
      case 2 : $a+=($url[$k+1]<<8);
      case 1 : $a+=($url[$k+0]);
      /* case 0: nothing left to add */
    } // esac

$mix = $this->mix($a,$b,$c);
    return $mix[2];
  }
}
?>

AdSpeed.org is an extension of AdSpeed, our popular commercial ad serving solution. We plan to use this site to share our technical and business knowledge about the online advertising industry. We benefit from open-source software every day and we would like to give something back. All the source code contributed on this site are free to the public. It's a way to say Thank You to the developers. We also host a variety of open-source mirrors.

AdSpeed.org | Giving it back

JSON with Padding = JSONP

Reloading partial page content with JavaScript

Javascript table grid sort

PHP5 Class for Yahoo Term Extractor API

Fix php_browscap.ini for PHP

Simple & fast spider detection

fastcgi load balancing with lighttpd

Configurations

Parse stats from PowerDNS webserver

RPM for eAccelerator 0.9.5

PHP - Customize str_rot13 function

MySQL - Shell script to optimize all tables

Parsing Verisign .COM/.NET zone files

Alexa Traffic Rank PHP5 Class

Google PageRank PHP5 Class

Welcome to AdSpeed.org

PHP Classes

Recent Entries