A PAC file is a Javascript file evaluated by web browsers to determine which proxy server to use for certain URL's.
Here's a working example of using the php_spidermonkey extension to run a proxy auto config script (javascript) in PHP.
All you need is a PAC file to test it. You can write your own following instructions across the web, here is a guide: http://www.ee.ed.ac.uk/%7Emfg/work/proxy-live.html
There is more information and Windows builds of php_spidermonkey in this article: Javascript in PHP on Windows with php_spidermonkey. Install the extension dll in PHP in the usual way.
Here is a snippet of code that uses the class 'CProxy' (defined underneath) which executes the Javascript PAC function FindProxyForURL:
Code formatted by http://hilite.me/
use DEMO\PAC\CProxy; // namespace, if required.
$proxy = new CProxy();
$proxy->LoadPAC('C:\proxy.pac'); // pac file is usually a URL
$test = $proxy->FindProxyForAddress('http://www.google.com/', true);
echo $test;
/*
Assuming your PAC file contained something like this:
function FindProxyForURL(url, host)
{
if ( shExpMatch(host, "*.google.*") )
{
return "PROXY 10.20.30.40:8000; DIRECT";
}
return "DIRECT";
}
this snippet would print:
PROXY 10.20.30.40:8000; DIRECT
*/
Definition of class CProxy - it utilises and demonstrates some of the following:
- PHP 5.4 - uses namespaces to show how they work in this scenario, and traits.
- php_spidermonkey javascript interpreter
- PAC (proxy-auto-config) functions
<?php
/* This example uses a namespace, just to show how it works inside namespaces.
Namespace can be removed. */
namespace DEMO\PAC;
use \JSContext, \Exception;
if ( !defined('JSVERSION_DEFAULT') )
{
error_log(__FILE__ . 'CProxy not loaded, php_spidermonkey extension not detected!');
return;
}
// global function to escape javascript strings: function js($str, $quotes = '\'"')
{
return addcslashes($str,"\\$quotes\n\r<>");
}
class CProxy
{
use PACFunctions; // include traits in this class, defined below.
private $pac, $js, $proxyconfig;
function __construct($pacfile=NULL, $strictJavascript=false)
{
// requires php_spidermonkey.dll extension.
$js = new JSContext();
if ( $strictJavascript )
{
$opts = $js->getOptions() | JSOPTION_STRICT | JSOPTION_WERROR;
$prev = $js->setOptions($opts);
}
$js->registerFunction(__NAMESPACE__.'\CProxy::myIpAddress', 'myIpAddress');
$js->registerFunction(__NAMESPACE__.'\CProxy::isPlainHostName', 'isPlainHostName');
$js->registerFunction(__NAMESPACE__.'\CProxy::dnsDomainIs', 'dnsDomainIs');
$js->registerFunction(__NAMESPACE__.'\CProxy::localHostOrDomainIs', 'localHostOrDomainIs');
$js->registerFunction(__NAMESPACE__.'\CProxy::isResolvable', 'isResolvable');
$js->registerFunction(__NAMESPACE__.'\CProxy::isInNet', 'isInNet');
$js->registerFunction(__NAMESPACE__.'\CProxy::dnsResolve', 'dnsResolve');
$js->registerFunction(__NAMESPACE__.'\CProxy::dnsDomainLevels', 'dnsDomainLevels');
$js->registerFunction(__NAMESPACE__.'\CProxy::shExpMatch', 'shExpMatch');
$js->registerFunction(__NAMESPACE__.'\CProxy::weekdayRange', 'weekdayRange');
$js->registerFunction(__NAMESPACE__.'\CProxy::dateRange', 'dateRange');
$js->registerFunction(__NAMESPACE__.'\CProxy::timeRange', 'timeRange');
// I don't know what ProxyConfig is used for:
$this->proxyconfig = new \stdClass();
$this->proxyconfig->bindings = array();
$js->assign('ProxyConfig', $this->proxyconfig);
$this->js = $js;
$this->LoadPAC($pacfile);
}
function FindProxyForAddress($address, $raw=false)
{
/* returns an array of proxy servers
(from preg_match_all),
or, if $raw is true, returns
the original string returned by
FindProxyForURL function. */
if ( !$this->pac )
return false;
$parts = parse_url($address);
$url = $address;
if ( !isset($parts['port']) )
{
$port = '';
}
else if ( ($port=$parts['port']) )
{
$port = ':' . $port;
}
if ( !isset($parts['host']) )
{
/* $address is badly formed, not sure if this is right, but
* return it from the beginning to the first slash. */
if ( !isset($parts['path']) )
return false;
$parts['host'] = preg_replace('/(.*?)(?>\/.*$|$)/', '$1', $parts['path']);
}
$host = $parts['host'] . $port;
try
{
if ( !($rv=$this->js->evaluateScript('FindProxyForURL(\'' . js($url) . '\', \'' . js($host) . '\');', 'FindProxyForURL')) || $raw )
{
return $rv;
}
}
catch ( Exception $ex )
{
return false;
}
return self::ReadPacResult($rv);
}
function LoadPAC($pac)
{
if ( $this->pac )
{
return NULL; // already loaded
}
if ( $pac === NULL || !$this->js )
{
return false; // param error or not initialised properly
}
if ( !($script = file_get_contents($pac)) )
{
return false; // cannot read PAC file
}
try
{
$rv = $this->js->evaluateScript($script, $pac);
}
catch ( Exception $ex )
{
return false;
}
$this->pac = $script;
return true;
}
public static function ReadPacResult($pacres)
{
if ( !$pacres )
return false;
// $pacres should be something like
// PROXY 1.2.3.4:8080; PROXY 1.2.3.5:8080; DIRECT
if ( !preg_match_all('/(PROXY|SOCKS|DIRECT)\s*([^;]*|.*?$)/ui', $pacres, $matches, PREG_SET_ORDER) )
{
return false;
}
return $matches;
}
}
?>
Code formatted by http://hilite.me/
<?php
/* Define the PAC traits used in class CProxy, above. */
namespace DEMO\PAC;
use \DateTime, \DateTimeZone, \Exception;
trait PACFunctions
{
private static $s_myIP;
/*
* PAC functions:
* 'global' functions to replicate javascript PAC environment...
*/
static function myIpAddress()
{
if ( self::$s_myIP )
{
return self::$s_myIP;
}
$vars = array('SERVER_ADDR', 'LOCAL_ADDR');
$ip = NULL;
$bestip = '0.0.0.0';
foreach ( $vars as $var )
{
if ( isset($_SERVER[$var]) )
{
$ip = $_SERVER[$var];
if ( !empty($ip) )
{
if ( $ip != '127.0.0.1' )
{
return (self::$s_myIP = $ip);
}
$bestip = $ip;
}
}
}
if ( ($hn = gethostname()) && ($ip = gethostbyname($hn)) && $ip !== $hn )
{
return (self::$s_myIP=$ip);
}
return (self::$s_myIP=$bestip);
}
static function isPlainHostName( $host )
{
return strpos($host, '.')===false;
}
static function shExpMatch($host, $pattern)
{
$parts = explode('*', $pattern);
$pattern = '';
foreach( $parts as $part )
{
if ( $part === '' )
{
$pattern .= '.*?';
}
else
{
$pattern .= preg_quote($part, '/');
}
}
return preg_match('/^'.$pattern.'$/ui', $host)===1;
}
static function isResolvable($host)
{
if ( ip2long($host) !== false )
{
return true;
}
$test = gethostbyname($host);
return $test && ip2long($test) !== false;
}
static function isInNet($host, $ip, $subnet)
{
if ( ($longhost = ip2long($host)) === false )
{
$host = gethostbyname($host);
if ( ($longhost = ip2long($host))===false )
{
return false;
}
}
$longip = ip2long($ip);
$longsub = ip2long($subnet);
return ($longhost&$longsub) == $longip;
}
static function dnsDomainIs($host, $domain)
{
$len = strlen($domain);
return $len <= strlen($host) && substr($host, -$len)==$domain;
}
static function localHostOrDomainIs($host, $domain)
{
return strcasecmp($domain, substr($host, 0, strlen($domain)))===0;
}
static function dnsResolve($host)
{
return gethostbyname($host);
}
static function dnsDomainLevels($host)
{
return substr_count($host, '.');
}
static function weekdayRange($fr, $to=NULL, $gmt=NULL)
{
$days = array('mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun');
$fr = strtolower(substr($fr,0,3));
if ( $gmt )
$gmt = strtoupper($gmt);
if ( $to === NULL )
$to = $fr;
else if ( strcasecmp($to, 'GMT')==0 )
{
$to = $fr;
$gmt = 'GMT';
}
else
$to = strtolower(substr($to,0,3));
if ( $gmt == 'GMT' )
{
$tzn = 'UTC';
}
else if ( !($tzn = ini_get('date.timezone')) )
{
$tzn = 'Europe/London';
}
$tz = new DateTimeZone($tzn);
$today = strtolower( (new DateTime('now',$tz))->format('D') );
foreach ( $days as $wd=>$day )
{
if ( $fr == $day )
$fr = $wd+1;
if ( $to == $day )
$to = $wd+1;
if ( $today == $day )
$today = $wd+1;
}
if ( !(int)$today || !(int)$fr || !(int)$to )
return false;
// FRI = 5
// MON = 1
// THU = 4
// is THU in FRI - MON ??
if ( $fr > $to )
{
return $today >= $fr || $today <= $to;
}
return $today >= $fr && $today <= $to;
}
static function dateRange($day1, $month1=NULL, $year1=NULL, $day2=NULL, $month2=NULL, $year2=NULL, $gmt=NULL)
{
$args = array($day1, $month1, $year1, $day2, $month2, $year2, $gmt);
$RationaliseArgs = function(&$arg)
{
$isgmt = 0;
for ( $ct=0 ; $ct < 6 ; $ct += 3 )
{
if ( (int)$arg[$ct] > 31 )
{
// 1st arg is a year, insert blank day and month
array_splice($arg, $ct, 0, array(0,''));
}
else if ( (int)$arg[$ct] )
{
// 1st arg is day
if ( (int)$arg[$ct+1] )
{
// 2nd arg must be a day. 2nd arg can't be year if 1st arg is a day.
array_splice($arg, $ct+1, 0, array('',0)); // insert blank month and year
}
else if ( $arg[$ct+1]===NULL || strcasecmp($arg[$ct+1], 'GMT')==0 )
{
// nothing else after the day.
array_splice($arg, $ct+1, 0, array('',0)); // insert blank month and year.
}
else if ( (int)$arg[$ct+2] && (int)$arg[$ct+2] <= 31 ) // month supplied, test what's after month
{
// month followed by day... insert blank year...
array_splice($arg, $ct+2, 0, array(0)); // insert empty year1 and shift arg2 to 2nd date.
}
}
else if ( is_string($arg[$ct]) )
{
if ( strcasecmp($arg[$ct], 'GMT')==0 )
{
if ( !$ct )
{
return false; // error, 1st arg cannot be 'GMT'.
}
break;
}
// 1st arg is month
array_splice($arg, $ct, 0, array(0)); // insert a blank day.
if ( (int)$arg[$ct+2] <= 31 ) // month not followed by a year
{
// insert a blank year...
array_splice($arg, $ct+2, 0, array(0));
}
}
else
{
if ( $ct && $arg[$ct] === NULL ) // only 1 date supplied. ok.
return 1;
return false; // error
}
}
if ( strcasecmp($arg[$ct], 'GMT')==0 )
{
$isgmt = 1;
$arg[$ct] = 'GMT';
}
array_splice($arg, 7);
return $ct/3;
};
if ( !($cd = $RationaliseArgs($args, $gmt)) )
{
return false;
}
list($day1, $month1, $year1, $day2, $month2, $year2, $gmt) = $args;
if ( $gmt == 'GMT' )
{
$tzn = 'UTC';
}
else if ( !($tzn = ini_get('date.timezone')) )
{
$tzn = 'Europe/London';
}
$tz = new DateTimeZone($tzn);
$now = new DateTime('now',$tz);
$thisyear = $now->format('Y');
$thismonth = 'Jan'; // a month with 31 days.
$thisday = $now->format('d');
try
{
$from = new \DateTime(($year1 ? $year1 : $thisyear) . '-' . ($month1 ? $month1 : $thismonth) . '-' . ($day1 ? $day1 : $thisday), $tz);
if ( !$day1 )
$day2 = 0;
if ( !$month1 )
$month2 = '';
if ( !$year1 )
$year2 = 0;
if ( $day2 || $month2 || $year2 )
{
$to = new \DateTime(($year2 ? $year2 : $thisyear) . '-' . ($month2 ? $month2 : $thismonth) . '-' . ($day2 ? $day2 : $thisday), $tz);
}
else
$to = NULL;
}
catch ( Exception $ex )
{
return false; // data error, an arg is incorrect
}
$dateformat = ($year1 ? 'Y' : '') . ($month1 ? 'm' : '') . ($day1 ? 'd' : '');
$test = $now->format($dateformat);
$lhs = $from->format($dateformat);
if ( !$to )
{
return $test == $lhs;
}
$rhs = $to->format($dateformat);
if ( $rhs < $lhs && $dateformat{0} != 'Y' )
{
return $test >= $lhs || $test <= $rhs;
}
return $test >= $lhs && $test <= $rhs;
}
static function timeRange($hour1, $min1=NULL, $sec1=NULL, $hour2=NULL, $min2=NULL, $sec2=NULL, $gmt=NULL)
{
$args = array($hour1, $min1, $sec1, $hour2, $min2, $sec2, $gmt);
for ( $ct=0 ; $ct < count($args) && $args[$ct] !== NULL && strcasecmp($args[$ct], 'GMT') ; ++$ct ) ;
if ( !$ct )
return false; // arg error
if ( ($gmt = (strcasecmp($args[$ct], 'GMT')==0)) )
{
$tzn = 'UTC';
}
else if ( !($tzn = ini_get('date.timezone')) )
{
$tzn = 'Europe/London';
}
$tz = new DateTimeZone($tzn);
$now = new DateTime('now',$tz);
/* $ct is the number of args (excluding any 'GMT' value).
* if 6 args supplied, full time specified, else... */
if ( $ct == 4 ) // range of hours+minutes
{
// hour and minute supplied
$min2 = $hour2;
$hour2 = $sec1;
$sec1 = $sec2 = 0;
$fmt = 'Hi';
}
else if ( $ct < 3 ) // range of hours (1 or 2)
{
$hour2 = ($ct==2 ? $min1 : $hour1);
$min1 = $sec1 = $min2 = $sec2 = 0;
$fmt = 'H';
}
else if ( $ct == 6 )
{
$fmt = 'His';
}
else
{
return false; // parameters not specified properly
}
try
{
$lhs = new \DateTime( ($dt=$now->format('Y-m-d')) . ' ' . (int)$hour1 . ':' . (int)$min1 . ':' . $sec1, $tz);
$rhs = (( $ct == 1 ) ? NULL : new \DateTime( $dt . ' ' . (int)$hour2 . ':' . (int)$min2 . ':' . $sec2, $tz));
}
catch ( Exception $ex )
{
// datetime not recognised, so parameter probably out of range
return false;
}
$nowtime = $now->format($fmt);
$ltime = $lhs->format($fmt);
if ( $rhs === NULL )
{
return $nowtime == $ltime;
}
$rtime = $rhs->format($fmt);
if ( $ltime > $rtime )
{
return $nowtime >= $ltime || $nowtime <= $rtime;
}
return $nowtime >= $ltime && $nowtime <= $rtime;
}
}
?>