diff --git a/build/deb/dolibarr.lintian-overrides b/build/deb/dolibarr.lintian-overrides index 6cab21c0ffc..a8b77a06a71 100755 --- a/build/deb/dolibarr.lintian-overrides +++ b/build/deb/dolibarr.lintian-overrides @@ -1,7 +1,5 @@ -# embedded libraries, which don't seem to be available in Debian in correct version +# Embedded libraries, which don't seem to be available in Debian in correct version # or because they were modified and are specific dolibarr code embedded-javascript-library usr/share/dolibarr/htdocs/includes/ckeditor/adapters/jquery.js embedded-javascript-library usr/share/dolibarr/htdocs/includes/ckeditor/ckeditor.js -embedded-php-library usr/share/dolibarr/htdocs/includes/magpierss/extlib/Snoopy.class.inc -embedded-php-library usr/share/dolibarr/htdocs/includes/magpierss/rss_parse.inc embedded-php-library usr/share/dolibarr/htdocs/includes/nusoap/lib/nusoap.php \ No newline at end of file diff --git a/build/doxygen/dolibarr-doxygen.doxyfile b/build/doxygen/dolibarr-doxygen.doxyfile index 37796e233de..1c058f49c9f 100644 --- a/build/doxygen/dolibarr-doxygen.doxyfile +++ b/build/doxygen/dolibarr-doxygen.doxyfile @@ -611,7 +611,7 @@ RECURSIVE = YES # excluded from the INPUT source files. This way you can easily exclude a # subdirectory from a directory tree whose root is specified with the INPUT tag. -EXCLUDE = ../../mssql ../../mysql ../../pgsql ../../CVS ../../build ../../dev ../../doc ../../documents ../../htdocs/conf/conf.php ../../htdocs/includes/adodbtime ../../htdocs/includes/artichow ../../htdocs/includes/barcode ../../htdocs/includes/ckeditor ../../htdocs/includes/fckeditor ../../htdocs/includes/fpdi ../../htdocs/includes/geoip ../../htdocs/includes/jquery ../../htdocs/includes/magpierss ../../htdocs/includes/nusoap ../../htdocs/includes/odtphp ../../htdocs/includes/pear ../../htdocs/includes/phpexcel ../../htdocs/includes/smtps ../../htdocs/includes/tcpdf ../../htdocs/includes/vcard ../../htdocs/cashdesk/include/jscalendar ../../htdocs/avoir ../../htdocs/document ../../htdocs/documents ../../htdocs/lolix ../../htdocs/postnuke ../../htdocs/rapport ../../htdocs/telephonie ../../htdocs/voyage ../../htdocs/oscommerce_ws/ws_client_demo ../../htdocs/oscommerce_ws/ws_server ../../scripts/addons ../../scripts/courrier ../../scripts/lolix ../../scripts/energie +EXCLUDE = ../../mssql ../../mysql ../../pgsql ../../CVS ../../build ../../dev ../../doc ../../documents ../../htdocs/conf/conf.php ../../htdocs/includes/adodbtime ../../htdocs/includes/artichow ../../htdocs/includes/barcode ../../htdocs/includes/ckeditor ../../htdocs/includes/fckeditor ../../htdocs/includes/fpdi ../../htdocs/includes/geoip ../../htdocs/includes/jquery ../../htdocs/includes/nusoap ../../htdocs/includes/odtphp ../../htdocs/includes/pear ../../htdocs/includes/phpexcel ../../htdocs/includes/smtps ../../htdocs/includes/tcpdf ../../htdocs/includes/vcard ../../htdocs/cashdesk/include/jscalendar ../../htdocs/avoir ../../htdocs/document ../../htdocs/documents ../../htdocs/lolix ../../htdocs/postnuke ../../htdocs/rapport ../../htdocs/telephonie ../../htdocs/voyage ../../htdocs/oscommerce_ws/ws_client_demo ../../htdocs/oscommerce_ws/ws_server ../../scripts/addons ../../scripts/courrier ../../scripts/lolix ../../scripts/energie # The EXCLUDE_SYMLINKS tag can be used select whether or not files or # directories that are symbolic links (a Unix filesystem feature) are excluded diff --git a/htdocs/admin/external_rss.php b/htdocs/admin/external_rss.php index 4177432bf2f..8f8813033ce 100644 --- a/htdocs/admin/external_rss.php +++ b/htdocs/admin/external_rss.php @@ -1,7 +1,7 @@ * Copyright (C) 2003,2005 Rodolphe Quiedeville - * Copyright (C) 2004-2008 Laurent Destailleur + * Copyright (C) 2004-2011 Laurent Destailleur * Copyright (C) 2004 Sebastien Di Cintio * Copyright (C) 2004 Benoit Mortier * Copyright (C) 2005-2011 Regis Houssin @@ -23,21 +23,27 @@ /** * \file htdocs/admin/external_rss.php * \ingroup external_rss - * \brief Page d'administration/configuration du module ExternalRss - * \version $Id: external_rss.php,v 1.48 2011/07/31 22:23:21 eldy Exp $ + * \brief Page to setupe module ExternalRss + * \version $Id: external_rss.php,v 1.49 2011/08/17 13:44:16 eldy Exp $ */ require("../main.inc.php"); require_once(DOL_DOCUMENT_ROOT."/lib/admin.lib.php"); -include_once(MAGPIERSS_PATH."rss_fetch.inc"); - +require_once(DOL_DOCUMENT_ROOT."/core/class/rssparser.class.php"); $langs->load("admin"); +// Security check if (!$user->admin) accessforbidden(); $def = array(); $lastexternalrss=0; +$action=GETPOST('action'); + + +/* + * Actions + */ // positionne la variable pour le nombre de rss externes $sql ="SELECT MAX(".$db->decrypt('name').") as name FROM ".MAIN_DB_PREFIX."const"; @@ -54,14 +60,14 @@ else dol_print_error($db); } -if ($_POST["action"] == 'add' || $_POST["modify"]) +if ($action == 'add' || $_POST["modify"]) { + $external_rss_title = "external_rss_title_" . $_POST["norss"]; $external_rss_urlrss = "external_rss_urlrss_" . $_POST["norss"]; - if(isset($_POST[$external_rss_urlrss])) + if (! empty($_POST[$external_rss_urlrss])) { $boxlabel='(ExternalRSSInformations)'; - $external_rss_title = "external_rss_title_" . $_POST["norss"]; //$external_rss_url = "external_rss_url_" . $_POST["norss"]; $db->begin(); @@ -141,7 +147,7 @@ if ($_POST["delete"]) if (! $resql) { $db->rollback(); - dol_print_error($db,"sql=$sql"); + dol_print_error($db,"sql=".$sql); exit; } @@ -153,7 +159,7 @@ if ($_POST["delete"]) else { $db->rollback(); - dol_print_error($db,"sql=$sql"); + dol_print_error($db,"sql=".$sql); exit; } @@ -178,10 +184,10 @@ if ($_POST["delete"]) /* - * Affichage page + * View */ -llxHeader(); +llxHeader('',$langs->trans("ExternalRSSSetup")); $linkback=''.$langs->trans("BackToModuleList").''; print_fiche_titre($langs->trans("ExternalRSSSetup"), $linkback, 'setup'); @@ -191,7 +197,7 @@ print '
'; print '
'; print ''; -print ''; +print '
'; print ''; print ''; print ''; @@ -205,25 +211,24 @@ print ''; print ''; print ''; print ''; -print ''; +print ''; print ''; -print '
'.$langs->trans("NewRSS").''.$langs->trans("Example").'
URL du RSShttp://wiki.april.org/RecentChanges?format=rss
http://linuxfr.org/backend/news/rss20.rss
http://back.fr.lolix.org/jobs.rss.php3		http://news.google.com/news?ned=us&topic=h&output=rss
http://linuxfr.org/backend/news/rss20.rss
'; +print '
'; + +print '

'; print ''; print ''; print ''; -print ''; -print ''; +print '

'; + print ''; -print '
'; - -print ''; $sql ="SELECT rowid, file, note FROM ".MAIN_DB_PREFIX."boxes_def"; $sql.=" WHERE file = 'box_external_rss.php'"; $sql.=" ORDER BY note"; -dol_syslog("external_rss select rss boxes sql=".$sql,LOG_DEBUG); +dol_syslog("select rss boxes sql=".$sql,LOG_DEBUG); $resql=$db->query($sql); if ($resql) { @@ -238,24 +243,30 @@ if ($resql) $idrss = $reg[1]; //print "x".$idrss; + $rssparser=new RssParser($db); + $result = $rssparser->parser(@constant("EXTERNAL_RSS_URLRSS_".$idrss), 5, 300, $conf->externalrss->dir_temp); + $var=true; - $rss = fetch_rss( @constant("EXTERNAL_RSS_URLRSS_".$idrss) ); - // fetch_rss initialise les objets suivant: - // print_r($rss->channel); - // print_r($rss->image); - // print_r($rss->items); - + print "
"; print ""; + + print '
'; print ''; print ""; - print ""; + print ""; + print ''; print ""; $var=!$var; print ""; - print ""; + print ""; print ""; print ""; @@ -269,7 +280,7 @@ if ($resql) print ""; print ""; print ""; // Logo - if (! $rss->ERROR && $rss->image['url']) + if ($result > 0 && empty($rss->error)) { $var=!$var; print ""; print ""; print ''; print ""; } - print ""; - print ""; - print ""; + print '
".$langs->trans("RSS")." ".($i+1)."".$langs->trans("RSS")." ".($i+1)."'; + print "trans("Modify")."\">"; + print "   "; + print "trans("Delete")."\">"; + print ""; + print '
".$langs->trans("Title")."".$langs->trans("Title")."
".$langs->trans("Status").""; - if (! $rss->ERROR) + if ($result > 0 && empty($rss->error)) { print ''.$langs->trans("Online").''; } @@ -281,25 +292,20 @@ if ($resql) print "
".$langs->trans("Logo")."'; - print ''; + $imageurl=$rssparser->getImageUrl(); + if ($imageurl) print ''; + else print $langs->trans("None"); print '
"; - print "trans("Modify")."\">"; - print "   "; - print "trans("Delete")."\">"; - print ""; - print "
'; print ""; @@ -311,10 +317,8 @@ else dol_print_error($db); } -print ''."\n"; - $db->close(); -llxFooter('$Date: 2011/07/31 22:23:21 $ - $Revision: 1.48 $'); +llxFooter('$Date: 2011/08/17 13:44:16 $ - $Revision: 1.49 $'); ?> diff --git a/htdocs/comm/action/class/actioncomm.class.php b/htdocs/comm/action/class/actioncomm.class.php index 96ac4bd24ac..a47c5451692 100644 --- a/htdocs/comm/action/class/actioncomm.class.php +++ b/htdocs/comm/action/class/actioncomm.class.php @@ -22,7 +22,7 @@ * \file htdocs/comm/action/class/actioncomm.class.php * \ingroup commercial * \brief File of class to manage agenda events (actions) - * \version $Id: actioncomm.class.php,v 1.43 2011/08/03 00:46:20 eldy Exp $ + * \version $Id: actioncomm.class.php,v 1.44 2011/08/17 13:44:16 eldy Exp $ */ require_once(DOL_DOCUMENT_ROOT.'/comm/action/class/cactioncomm.class.php'); require_once(DOL_DOCUMENT_ROOT.'/core/class/commonobject.class.php'); @@ -674,7 +674,7 @@ class ActionComm extends CommonObject } // Create dir and define output file (definitive and temporary) - $result=create_exdir($conf->agenda->dir_temp); + $result=dol_mkdir($conf->agenda->dir_temp); $outputfile=$conf->agenda->dir_temp.'/'.$filename; $result=0; diff --git a/htdocs/core/class/rssparser.class.php b/htdocs/core/class/rssparser.class.php new file mode 100755 index 00000000000..1b018b5073d --- /dev/null +++ b/htdocs/core/class/rssparser.class.php @@ -0,0 +1,187 @@ + + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +/** + * \file htdocs/core/class/rssparser.class.php + * \ingroup core + * \brief File of class to parse rss feeds + * \version $Id: rssparser.class.php,v 1.1 2011/08/17 13:44:13 eldy Exp $ + */ +class RssParser +{ + var $db; + var $error; + + protected $_format='rss'; + protected $_urlRSS; + protected $_language; + protected $_generator; + protected $_copyright; + protected $_lastbuilddate; + protected $_imageurl; + protected $_link; + protected $_title; + protected $_description; + protected $_lastfetchdate; // Last successful fetch + protected $_rssarray=array(); + + // Accessors + public function getFormat() { return $this->_format; } + public function getUrlRss() { return $this->_urlRSS; } + public function getLanguage() { return $this->_language; } + public function getGenerator() { return $this->_generator; } + public function getCopyright() { return $this->_copyright; } + public function getLastBuildDate() { return $this->_lastbuilddate; } + public function getImageUrl() { return $this->_imageurl; } + public function getLink() { return $this->_link; } + public function getTitle() { return $this->_title; } + public function getDescription() { return $this->_description; } + public function getLastFetchDate() { return $this->_lastfetchdate; } + public function getItems() { return $this->_rssarray; } + + /** + * Constructor + */ + public function RssParser($db) + { + $this->db=$db; + } + + + /** + * Parse rss URL + * + * @param urlRSS Url to parse + * @param maxNb Max nb of records to get (0 for no limit) + * @param cachedelay 0=No cache, nb of seconds we accept cache files (cachedir must also be defined) + * @param cachedir Directory where to save cache file + * @return int <0 if KO, >0 if OK + */ + public function parser($urlRSS, $maxNb=0, $cachedelay=60, $cachedir='') + { + include_once(DOL_DOCUMENT_ROOT.'/lib/files.lib.php'); + + $this->_urlRSS = $urlRSS; + $newpathofdestfile=$cachedir.'/'.md5($this->_urlRSS); + $newmask=octdec('0644'); + + //dol_syslog("RssPArser::parser parse url=".$urlRSS." => cache file=".$newpathofdestfile); + $nowgmt = dol_now(); + + // Search into cache + $foundintocache=0; + if ($cachedelay > 0 && $cachedir) + { + $filedate=dol_filemtime($newpathofdestfile); + if ($filedate >= ($nowgmt - $cachedelay)) + { + //dol_syslog("RssParser::parser cache file ".$newpathofdestfile." is not older than now - cachedelay (".$nowgmt." - ".$cachedelay.") so we use it."); + $foundintocache=1; + + $this->_lastfetchdate=$filedate; + } + else + { + dol_syslog("RssParser::parser cache file ".$newpathofdestfile." is not found or older than now - cachedelay (".$nowgmt." - ".$cachedelay.") so we can't use it."); + } + } + + // Load file into $rss + if ($foundintocache) // Cache file found and is not too old + { + $str = file_get_contents($newpathofdestfile); + $rss = simplexml_load_string(unserialize($str)); + } + else + { + try { + $rss = @simplexml_load_file($this->_urlRSS); + } + catch (Exception $e) { + print 'Error retrieving URL '.$this->urlRSS.' - '.$e->getMessage(); + } + } + + // If $rss loaded + if ($rss) + { + // Save file into cache + if (empty($foundintocache) && $cachedir) + { + dol_syslog("RssParser::parser cache file ".$newpathofdestfile." is saved onto disk."); + if (! dol_is_dir($cachedir)) dol_mkdir($cachedir); + $fp = fopen($newpathofdestfile, 'w'); + fwrite($fp, serialize($rss->asXML())); + fclose($fp); + if (! empty($conf->global->MAIN_UMASK)) $newmask=$conf->global->MAIN_UMASK; + @chmod($newpathofdestfile, octdec($newmask)); + + $this->_lastfetchdate=$nowgmt; + } + + // Save description entries + if (!empty($rss->channel->language)) $this->_language = (string) $rss->channel->language; + if (!empty($rss->channel->generator)) $this->_generator = (string) $rss->channel->generator; + if (!empty($rss->channel->copyright)) $this->_copyright = (string) $rss->channel->copyright; + if (!empty($rss->channel->lastbuilddate)) $this->_lastbuilddate = (string) $rss->channel->lastbuilddate; + if (!empty($rss->channel->image->url[0])) $this->_imageurl = (string) $rss->channel->image->url[0]; + if (!empty($rss->channel->link)) $this->_link = (string) $rss->channel->link; + if (!empty($rss->channel->title)) $this->_title = (string) $rss->channel->title; + if (!empty($rss->channel->description)) $this->_description = (string) $rss->channel->description; + // TODO imageurl + + $i = 0; + + // Loop on each record + foreach($rss->channel->item as $item) + { + $itemLink = (string) $item->link; + $itemTitle = (string) $item->title; + $itemDescription = (string) $item->description; + $itemPubDate = (string) $item->pubDate; + + // Loop on each category + $itemCategory=array(); + foreach ($item->category as $cat) + { + $itemCategory[] = (string) $cat; + } + + // Add record to result array + $this->_rssarray[$i] = array( + 'link'=>$itemLink, + 'title'=>$itemTitle, + 'description'=>$itemDescription, + 'pubDate'=>$itemPubDate, + 'category'=>$itemCategory); + + $i++; + + if ($i > $maxNb) break; // We get all records we want + } + + return 1; + } + else + { + $this->error='ErrorFailedToLoadRSSFile'; + return -1; + } + } + +} +?> \ No newline at end of file diff --git a/htdocs/includes/boxes/box_external_rss.php b/htdocs/includes/boxes/box_external_rss.php index 0859f336cb4..cdcec1cffd0 100644 --- a/htdocs/includes/boxes/box_external_rss.php +++ b/htdocs/includes/boxes/box_external_rss.php @@ -22,10 +22,10 @@ * \file htdocs/includes/boxes/box_external_rss.php * \ingroup external_rss * \brief Fichier de gestion d'une box pour le module external_rss - * \version $Id: box_external_rss.php,v 1.34 2011/07/31 23:29:10 eldy Exp $ + * \version $Id: box_external_rss.php,v 1.35 2011/08/17 13:44:16 eldy Exp $ */ -include_once(MAGPIERSS_PATH."rss_fetch.inc"); +include_once(DOL_DOCUMENT_ROOT."/core/class/rssparser.class.php"); include_once(DOL_DOCUMENT_ROOT."/includes/boxes/modules_boxes.php"); @@ -57,10 +57,12 @@ class box_external_rss extends ModeleBoxes { } /** - * Charge les donnees en memoire pour affichage ulterieur - * @param $max Nombre maximum d'enregistrements a charger + * Load information for box into memory to show them later with this->showBox method. + * + * @param $max Max numbe rof records to load + * @param $cachedelay Delay we accept for cache file */ - function loadBox($max=5) + function loadBox($max=5, $cachdelay=300) { global $user, $langs, $conf; $langs->load("boxes"); @@ -71,56 +73,52 @@ class box_external_rss extends ModeleBoxes { preg_match('/^([0-9]+) /',$this->param,$reg); $site=$reg[1]; - // Creation rep (pas besoin, on le cree apres recup flux) - // documents/rss is created by module activation - // documents/rss/tmp is created by magpie - //$result=create_exdir($conf->externalrss->dir_temp); + // Create dir nor required + // documents/externalrss is created by module activation + // documents/externalrss/tmp is created by rssparser - // Recupere flux RSS definie dans EXTERNAL_RSS_URLRSS_$site + // Get RSS feed $url=@constant("EXTERNAL_RSS_URLRSS_".$site); - //define('MAGPIE_DEBUG',1); - $rss=fetch_rss($url); - if (! is_object($rss)) - { - dol_syslog("FETCH_RSS site=".$site); - dol_syslog("FETCH_RSS url=".$url); - return -1; - } - // INFO sur le channel - $description=$rss->channel['tagline']; - $link=$rss->channel['link']; + $rssparser=new RssParser($db); + $result = $rssparser->parser($url, $this->max, $cachdelay, $conf->externalrss->dir_temp); + + // INFO on channel + $description=$rssparser->getDescription(); + $link=$rssparser->getLink(); $title=$langs->trans("BoxTitleLastRssInfos",$max, @constant("EXTERNAL_RSS_TITLE_". $site)); - if ($rss->ERROR) + if ($result < 0 || ! empty($rssparser->error)) { - // Affiche warning car il y a eu une erreur - $title.=" ".img_error($langs->trans("FailedToRefreshDataInfoNotUpToDate",(isset($rss->date)?dol_print_date($rss->date,"dayhourtext"):$langs->trans("Unknown")))); + // Show warning + $title.=" ".img_error($langs->trans("FailedToRefreshDataInfoNotUpToDate",($rssparser->getLastFetchDate()?dol_print_date($rssparser->getLastFetchDate(),"dayhourtext"):$langs->trans("Unknown")))); $this->info_box_head = array('text' => $title,'limit' => 0); } else { $this->info_box_head = array('text' => $title, - 'sublink' => $link, 'subtext'=>$langs->trans("LastRefreshDate").': '.(isset($rss->date)?dol_print_date($rss->date,"dayhourtext"):$langs->trans("Unknown")), 'subpicto'=>'object_bookmark'); + 'sublink' => $link, 'subtext'=>$langs->trans("LastRefreshDate").': '.($rssparser->getLastFetchDate()?dol_print_date($rssparser->getLastFetchDate(),"dayhourtext"):$langs->trans("Unknown")), 'subpicto'=>'object_bookmark'); } - // INFO sur le elements - for($i = 0; $i < $max && $i < sizeof($rss->items); $i++) + // INFO on items + $items=$rssparser->getItems(); + $nbitems=sizeof($items); + for($i = 0; $i < $max && $i < $nbitems; $i++) { - $item = $rss->items[$i]; + $item = $items[$i]; - // Magpierss common fields + // Feed common fields $href = $item['link']; $title = urldecode($item['title']); $date = $item['date_timestamp']; // date will be empty if conversion into timestamp failed - if ($rss->is_rss()) // If RSS + if ($rssparser->getFormat() == 'rss') // If RSS { if (! $date && isset($item['pubdate'])) $date=$item['pubdate']; if (! $date && isset($item['dc']['date'])) $date=$item['dc']['date']; //$item['dc']['language'] //$item['dc']['publisher'] } - if ($rss->is_atom()) // If Atom + if ($rssparser->getFormat() == 'atom') // If Atom { if (! $date && isset($item['issued'])) $date=$item['issued']; if (! $date && isset($item['modified'])) $date=$item['modified']; diff --git a/htdocs/includes/magpierss/README b/htdocs/includes/magpierss/README deleted file mode 100644 index 6af7edb07c8..00000000000 --- a/htdocs/includes/magpierss/README +++ /dev/null @@ -1,48 +0,0 @@ -NAME - - MagpieRSS - a simple RSS integration tool - -SYNOPSIS - - require_once(rss_fetch.inc); - $url = $_GET['url']; - $rss = fetch_rss( $url ); - - echo "Channel Title: " . $rss->channel['title'] . "

"; - echo "

    "; - foreach ($rss->items as $item) { - $href = $item['link']; - $title = $item['title']; - echo "
  • $title
    • "; - } - echo "
"; - -DESCRIPTION - - MapieRSS is an XML-based RSS parser in PHP. It attempts to be "PHP-like", - and simple to use. - - Some features include: - - * supports RSS 0.9 - 1.0, with limited RSS 2.0 support - * supports namespaces, and modules, including mod_content and mod_event - * open minded [1] - * simple, functional interface, to object oriented backend parser - * automatic caching of parsed RSS objects makes its easy to integrate - * supports conditional GET with Last-Modified, and ETag - * uses constants for easy override of default behaviour - * heavily commented - - -1. By open minded I mean Magpie will accept any tag it finds in good faith that - it was supposed to be here. For strict validation, look elsewhere. - - -GETTING STARTED - - - -COPYRIGHT: - Copyright(c) 2002 kellan@protest.net. All rights reserved. - This software is released under the GNU General Public License. - Please read the disclaimer at the top of the Snoopy.class.inc file. diff --git a/htdocs/includes/magpierss/extlib/Snoopy.class.inc b/htdocs/includes/magpierss/extlib/Snoopy.class.inc deleted file mode 100644 index 13c87e666b0..00000000000 --- a/htdocs/includes/magpierss/extlib/Snoopy.class.inc +++ /dev/null @@ -1,905 +0,0 @@ - -Modification: Laurent Destailleur (See LDR mark to find bug fix) -Copyright (c): 1999-2000 ispi, all rights reserved -Version: 1.0 - - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - -You may contact the author of Snoopy by e-mail at: -monte@ispi.net - -Or, write to: -Monte Ohrt -CTO, ispi -237 S. 70th suite 220 -Lincoln, NE 68510 - -The latest version of Snoopy can be obtained from: -http://snoopy.sourceforge.com - -*************************************************/ - -class Snoopy -{ - /**** Public variables ****/ - - /* user definable vars */ - - var $host = "www.php.net"; // host name we are connecting to - var $port = 80; // port we are connecting to - var $proxy_host = ""; // proxy host to use - var $proxy_port = ""; // proxy port to use - var $agent = "Snoopy v1.0"; // agent we masquerade as - var $referer = ""; // referer info to pass - var $cookies = array(); // array of cookies to pass - // $cookies["username"]="joe"; - var $rawheaders = array(); // array of raw headers to send - // $rawheaders["Content-type"]="text/html"; - - var $maxredirs = 5; // http redirection depth maximum. 0 = disallow - var $lastredirectaddr = ""; // contains address of last redirected address - var $offsiteok = true; // allows redirection off-site - var $maxframes = 0; // frame content depth maximum. 0 = disallow - var $expandlinks = true; // expand links to fully qualified URLs. - // this only applies to fetchlinks() - // or submitlinks() - var $passcookies = true; // pass set cookies back through redirects - // NOTE: this currently does not respect - // dates, domains or paths. - - var $user = ""; // user for http authentication - var $pass = ""; // password for http authentication - - // http accept types - var $accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*"; - - var $results = ""; // where the content is put - - var $error = ""; // error messages sent here - var $response_code = ""; // response code returned from server - var $headers = array(); // headers returned from server sent here - var $maxlength = 500000; // max return data length (body) - var $read_timeout = 0; // timeout on read operations, in seconds - // supported only since PHP 4 Beta 4 - // set to 0 to disallow timeouts - var $timed_out = false; // if a read operation timed out - var $status = 0; // http request status - - var $curl_path = "/usr/bin/curl"; - // Snoopy will use cURL for fetching - // SSL content if a full system path to - // the cURL binary is supplied here. - // set to false if you do not have - // cURL installed. See http://curl.haxx.se - // for details on installing cURL. - // Snoopy does *not* use the cURL - // library functions built into php, - // as these functions are not stable - // as of this Snoopy release. - - // send Accept-encoding: gzip? - var $use_gzip = true; - - /**** Private variables ****/ - - var $_maxlinelen = 4096; // max line length (headers) - - var $_httpmethod = "GET"; // default http request method - var $_httpversion = "HTTP/1.0"; // default http request version - var $_submit_method = "POST"; // default submit method - var $_submit_type = "application/x-www-form-urlencoded"; // default submit type - var $_mime_boundary = ""; // MIME boundary for multipart/form-data submit type - var $_redirectaddr = false; // will be set if page fetched is a redirect - var $_redirectdepth = 0; // increments on an http redirect - var $_frameurls = array(); // frame src urls - var $_framedepth = 0; // increments on frame depth - - var $_isproxy = false; // set if using a proxy server - var $_fp_timeout = 30; // timeout for socket connection - -/*======================================================================*\ - Function: fetch - Purpose: fetch the contents of a web page - (and possibly other protocols in the - future like ftp, nntp, gopher, etc.) - Input: $URI the location of the page to fetch - Output: $this->results the output text from the fetch -\*======================================================================*/ - - function fetch($URI) - { - - //preg_match("|^([^:]+)://([^:/]+)(:[\d]+)*(.*)|",$URI,$URI_PARTS); - $URI_PARTS = parse_url($URI); - if (!empty($URI_PARTS["user"])) - $this->user = $URI_PARTS["user"]; - if (!empty($URI_PARTS["pass"])) - $this->pass = $URI_PARTS["pass"]; - - switch($URI_PARTS["scheme"]) - { - case "http": - $this->host = $URI_PARTS["host"]; - if(!empty($URI_PARTS["port"])) - $this->port = $URI_PARTS["port"]; - - // LDR FIX BUG syncronized connect timeout to read timeout, otherwise, read timeout is useless - if ($this->read_timeout) $this->_fp_timeout=$this->read_timeout; - - if($this->_connect($fp)) - { - if($this->_isproxy) - { - // using proxy, send entire URI - $this->_httprequest($URI,$fp,$URI,$this->_httpmethod); - } - else - { - $path = $URI_PARTS["path"].(isset($URI_PARTS["query"]) ? "?".$URI_PARTS["query"] : ""); - // no proxy, send only the path - $this->_httprequest($path, $fp, $URI, $this->_httpmethod); - } - - $this->_disconnect($fp); - - if($this->_redirectaddr) - { - /* url was redirected, check if we've hit the max depth */ - if($this->maxredirs > $this->_redirectdepth) - { - // only follow redirect if it's on this site, or offsiteok is true - if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) - { - /* follow the redirect */ - $this->_redirectdepth++; - $this->lastredirectaddr=$this->_redirectaddr; - $this->fetch($this->_redirectaddr); - } - } - } - - if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) - { - $frameurls = $this->_frameurls; - $this->_frameurls = array(); - - while(list(,$frameurl) = each($frameurls)) - { - if($this->_framedepth < $this->maxframes) - { - $this->fetch($frameurl); - $this->_framedepth++; - } - else - break; - } - } - } - else - { - return false; - } - return true; - break; - case "https": - if(!$this->curl_path || (!is_executable($this->curl_path))) { - $this->error = "Bad curl ($this->curl_path), can't fetch HTTPS \n"; - return false; - } - $this->host = $URI_PARTS["host"]; - if(!empty($URI_PARTS["port"])) - $this->port = $URI_PARTS["port"]; - if($this->_isproxy) - { - // using proxy, send entire URI - $this->_httpsrequest($URI,$URI,$this->_httpmethod); - } - else - { - $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); - // no proxy, send only the path - $this->_httpsrequest($path, $URI, $this->_httpmethod); - } - - if($this->_redirectaddr) - { - /* url was redirected, check if we've hit the max depth */ - if($this->maxredirs > $this->_redirectdepth) - { - // only follow redirect if it's on this site, or offsiteok is true - if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) - { - /* follow the redirect */ - $this->_redirectdepth++; - $this->lastredirectaddr=$this->_redirectaddr; - $this->fetch($this->_redirectaddr); - } - } - } - - if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) - { - $frameurls = $this->_frameurls; - $this->_frameurls = array(); - - while(list(,$frameurl) = each($frameurls)) - { - if($this->_framedepth < $this->maxframes) - { - $this->fetch($frameurl); - $this->_framedepth++; - } - else - break; - } - } - return true; - break; - default: - // not a valid protocol - $this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n'; - return false; - break; - } - return true; - } - - - -/*======================================================================*\ - Private functions -\*======================================================================*/ - - -/*======================================================================*\ - Function: _striplinks - Purpose: strip the hyperlinks from an html document - Input: $document document to strip. - Output: $match an array of the links -\*======================================================================*/ - - function _striplinks($document) - { - preg_match_all("'<\s*a\s+.*href\s*=\s* # find ]+)) # if quote found, match up to next matching - # quote, otherwise match up to next space - 'isx",$document,$links); - - - // catenate the non-empty matches from the conditional subpattern - - while(list($key,$val) = each($links[2])) - { - if(!empty($val)) - $match[] = $val; - } - - while(list($key,$val) = each($links[3])) - { - if(!empty($val)) - $match[] = $val; - } - - // return the links - return $match; - } - -/*======================================================================*\ - Function: _stripform - Purpose: strip the form elements from an html document - Input: $document document to strip. - Output: $match an array of the links -\*======================================================================*/ - - function _stripform($document) - { - preg_match_all("'<\/?(FORM|INPUT|SELECT|TEXTAREA|(OPTION))[^<>]*>(?(2)(.*(?=<\/?(option|select)[^<>]*>[\r\n]*)|(?=[\r\n]*))|(?=[\r\n]*))'Usi",$document,$elements); - - // catenate the matches - $match = implode("\r\n",$elements[0]); - - // return the links - return $match; - } - - - -/*======================================================================*\ - Function: _striptext - Purpose: strip the text from an html document - Input: $document document to strip. - Output: $text the resulting text -\*======================================================================*/ - - function _striptext($document) - { - - // I didn't use preg eval (//e) since that is only available in PHP 4.0. - // so, list your entities one by one here. I included some of the - // more common ones. - - $search = array("']*?>.*?'si", // strip out javascript - "'<[\/\!]*?[^<>]*?>'si", // strip out html tags - "'([\r\n])[\s]+'", // strip out white space - "'&(quote|#34);'i", // replace html entities - "'&(amp|#38);'i", - "'&(lt|#60);'i", - "'&(gt|#62);'i", - "'&(nbsp|#160);'i", - "'&(iexcl|#161);'i", - "'&(cent|#162);'i", - "'&(pound|#163);'i", - "'&(copy|#169);'i" - ); - $replace = array( "", - "", - "\\1", - "\"", - "&", - "<", - ">", - " ", - chr(161), - chr(162), - chr(163), - chr(169)); - - $text = preg_replace($search,$replace,$document); - - return $text; - } - -/*======================================================================*\ - Function: _expandlinks - Purpose: expand each link into a fully qualified URL - Input: $links the links to qualify - $URI the full URI to get the base from - Output: $expandedLinks the expanded links -\*======================================================================*/ - - function _expandlinks($links,$URI) - { - - preg_match("/^[^\?]+/",$URI,$match); - - $match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|","",$match[0]); - - $search = array( "|^http://".preg_quote($this->host)."|i", - "|^(?!http://)(\/)?(?!mailto:)|i", - "|/\./|", - "|/[^\/]+/\.\./|" - ); - - $replace = array( "", - $match."/", - "/", - "/" - ); - - $expandedLinks = preg_replace($search,$replace,$links); - - return $expandedLinks; - } - -/*======================================================================*\ - Function: _httprequest - Purpose: go get the http data from the server - Input: $url the url to fetch - $fp the current open file pointer - $URI the full URI - $body body contents to send if any (POST) - Output: -\*======================================================================*/ - - function _httprequest($url,$fp,$URI,$http_method,$content_type="",$body="") - { - if($this->passcookies && $this->_redirectaddr) - $this->setcookies(); - - $URI_PARTS = parse_url($URI); - if(empty($url)) - $url = "/"; - $headers = $http_method." ".$url." ".$this->_httpversion."\r\n"; - if(!empty($this->agent)) - $headers .= "User-Agent: ".$this->agent."\r\n"; - if(!empty($this->host) && !isset($this->rawheaders['Host'])) - $headers .= "Host: ".$this->host."\r\n"; - if(!empty($this->accept)) - $headers .= "Accept: ".$this->accept."\r\n"; - - if($this->use_gzip) { - // make sure PHP was built with --with-zlib - // and we can handle gzipp'ed data - if ( function_exists(gzinflate) ) { - $headers .= "Accept-encoding: gzip\r\n"; - } - else { - trigger_error( - "use_gzip is on, but PHP was built without zlib support.". - " Requesting file(s) without gzip encoding.", - E_USER_NOTICE); - } - } - - if(!empty($this->referer)) - $headers .= "Referer: ".$this->referer."\r\n"; - if(!empty($this->cookies)) - { - if(!is_array($this->cookies)) - $this->cookies = (array)$this->cookies; - - reset($this->cookies); - if ( count($this->cookies) > 0 ) { - $cookie_headers .= 'Cookie: '; - foreach ( $this->cookies as $cookieKey => $cookieVal ) { - $cookie_headers .= $cookieKey."=".urlencode($cookieVal)."; "; - } - $headers .= substr($cookie_headers,0,-2) . "\r\n"; - } - } - if(!empty($this->rawheaders)) - { - if(!is_array($this->rawheaders)) - $this->rawheaders = (array)$this->rawheaders; - while(list($headerKey,$headerVal) = each($this->rawheaders)) - $headers .= $headerKey.": ".$headerVal."\r\n"; - } - if(!empty($content_type)) { - $headers .= "Content-type: $content_type"; - if ($content_type == "multipart/form-data") - $headers .= "; boundary=".$this->_mime_boundary; - $headers .= "\r\n"; - } - if(!empty($body)) - $headers .= "Content-length: ".strlen($body)."\r\n"; - if(!empty($this->user) || !empty($this->pass)) - $headers .= "Authorization: BASIC ".base64_encode($this->user.":".$this->pass)."\r\n"; - - $headers .= "\r\n"; - - // set the read timeout if needed - if ($this->read_timeout > 0) - socket_set_timeout($fp, $this->read_timeout); - $this->timed_out = false; - - fwrite($fp,$headers.$body,strlen($headers.$body)); - - $this->_redirectaddr = false; - unset($this->headers); - - // content was returned gzip encoded? - $is_gzipped = false; - - while($currentHeader = fgets($fp,$this->_maxlinelen)) - { - if ($this->read_timeout > 0 && $this->_check_timeout($fp)) - { - $this->status=-100; - return false; - } - - // if($currentHeader == "\r\n") - if(preg_match("/^\r?\n$/", $currentHeader) ) - break; - - // if a header begins with Location: or URI:, set the redirect - if(preg_match("/^(Location:|URI:)/i",$currentHeader)) - { - // get URL portion of the redirect - preg_match("/^(Location:|URI:)\s+(.*)/",chop($currentHeader),$matches); - // look for :// in the Location header to see if hostname is included - if(!preg_match("|\:\/\/|",$matches[2])) - { - // no host in the path, so prepend - $this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port; - // eliminate double slash - if(!preg_match("|^/|",$matches[2])) - $this->_redirectaddr .= "/".$matches[2]; - else - $this->_redirectaddr .= $matches[2]; - } - else - $this->_redirectaddr = $matches[2]; - } - - if(preg_match("|^HTTP/|",$currentHeader)) - { - if(preg_match("|^HTTP/[^\s]*\s(.*?)\s|",$currentHeader, $status)) - { - $this->status= $status[1]; - } - $this->response_code = $currentHeader; - } - - if (preg_match("/Content-Encoding: gzip/", $currentHeader) ) { - $is_gzipped = true; - } - - $this->headers[] = $currentHeader; - } - - # $results = fread($fp, $this->maxlength); - $results = ""; - while ( $data = fread($fp, $this->maxlength) ) { - $results .= $data; - if ( - strlen($results) > $this->maxlength ) { - break; - } - } - - // gunzip - if ( $is_gzipped ) { - // per http://www.php.net/manual/en/function.gzencode.php - $results = substr($results, 10); - $results = gzinflate($results); - } - - if ($this->read_timeout > 0 && $this->_check_timeout($fp)) - { - $this->status=-100; - return false; - } - - // check if there is a a redirect meta tag - - if(preg_match("']*?content[\s]*=[\s]*[\"\']?\d+;[\s]+URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) - { - $this->_redirectaddr = $this->_expandlinks($match[1],$URI); - } - - // have we hit our frame depth and is there frame src to fetch? - if(($this->_framedepth < $this->maxframes) && preg_match_all("']+)'i",$results,$match)) - { - $this->results[] = $results; - for($x=0; $x_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host); - } - // have we already fetched framed content? - elseif(is_array($this->results)) - $this->results[] = $results; - // no framed content - else - $this->results = $results; - - return true; - } - -/*======================================================================*\ - Function: _httpsrequest - Purpose: go get the https data from the server using curl - Input: $url the url to fetch - $URI the full URI - $body body contents to send if any (POST) - Output: -\*======================================================================*/ - - function _httpsrequest($url,$URI,$http_method,$content_type="",$body="") - { - if($this->passcookies && $this->_redirectaddr) - $this->setcookies(); - - $headers = array(); - - $URI_PARTS = parse_url($URI); - if(empty($url)) - $url = "/"; - // GET ... header not needed for curl - //$headers[] = $http_method." ".$url." ".$this->_httpversion; - if(!empty($this->agent)) - $headers[] = "User-Agent: ".$this->agent; - if(!empty($this->host)) - $headers[] = "Host: ".$this->host; - if(!empty($this->accept)) - $headers[] = "Accept: ".$this->accept; - if(!empty($this->referer)) - $headers[] = "Referer: ".$this->referer; - if(!empty($this->cookies)) - { - if(!is_array($this->cookies)) - $this->cookies = (array)$this->cookies; - - reset($this->cookies); - if ( count($this->cookies) > 0 ) { - $cookie_str = 'Cookie: '; - foreach ( $this->cookies as $cookieKey => $cookieVal ) { - $cookie_str .= $cookieKey."=".urlencode($cookieVal)."; "; - } - $headers[] = substr($cookie_str,0,-2); - } - } - if(!empty($this->rawheaders)) - { - if(!is_array($this->rawheaders)) - $this->rawheaders = (array)$this->rawheaders; - while(list($headerKey,$headerVal) = each($this->rawheaders)) - $headers[] = $headerKey.": ".$headerVal; - } - if(!empty($content_type)) { - if ($content_type == "multipart/form-data") - $headers[] = "Content-type: $content_type; boundary=".$this->_mime_boundary; - else - $headers[] = "Content-type: $content_type"; - } - if(!empty($body)) - $headers[] = "Content-length: ".strlen($body); - if(!empty($this->user) || !empty($this->pass)) - $headers[] = "Authorization: BASIC ".base64_encode($this->user.":".$this->pass); - - for($curr_header = 0; $curr_header < count($headers); $curr_header++) { - $cmdline_params .= " -H \"".$headers[$curr_header]."\""; - } - - if(!empty($body)) - $cmdline_params .= " -d \"$body\""; - - if($this->read_timeout > 0) - $cmdline_params .= " -m ".$this->read_timeout; - - $headerfile = uniqid(time()); - - # accept self-signed certs - $cmdline_params .= " -k"; - exec($this->curl_path." -D \"/tmp/$headerfile\"".escapeshellcmd($cmdline_params)." ".escapeshellcmd($URI),$results,$return); - - if($return) - { - $this->error = "Error: cURL could not retrieve the document, error $return."; - return false; - } - - - $results = implode("\r\n",$results); - - $result_headers = file("/tmp/$headerfile"); - - $this->_redirectaddr = false; - unset($this->headers); - - for($currentHeader = 0; $currentHeader < count($result_headers); $currentHeader++) - { - - // if a header begins with Location: or URI:, set the redirect - if(preg_match("/^(Location: |URI: )/i",$result_headers[$currentHeader])) - { - // get URL portion of the redirect - preg_match("/^(Location: |URI:)(.*)/",chop($result_headers[$currentHeader]),$matches); - // look for :// in the Location header to see if hostname is included - if(!preg_match("|\:\/\/|",$matches[2])) - { - // no host in the path, so prepend - $this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port; - // eliminate double slash - if(!preg_match("|^/|",$matches[2])) - $this->_redirectaddr .= "/".$matches[2]; - else - $this->_redirectaddr .= $matches[2]; - } - else - $this->_redirectaddr = $matches[2]; - } - - if(preg_match("|^HTTP/|",$result_headers[$currentHeader])) - { - $this->response_code = $result_headers[$currentHeader]; - if(preg_match("|^HTTP/[^\s]*\s(.*?)\s|",$this->response_code, $match)) - { - $this->status= $match[1]; - } - } - $this->headers[] = $result_headers[$currentHeader]; - } - - // check if there is a a redirect meta tag - - if(preg_match("']*?content[\s]*=[\s]*[\"\']?\d+;[\s]+URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) - { - $this->_redirectaddr = $this->_expandlinks($match[1],$URI); - } - - // have we hit our frame depth and is there frame src to fetch? - if(($this->_framedepth < $this->maxframes) && preg_match_all("']+)'i",$results,$match)) - { - $this->results[] = $results; - for($x=0; $x_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host); - } - // have we already fetched framed content? - elseif(is_array($this->results)) - $this->results[] = $results; - // no framed content - else - $this->results = $results; - - unlink("/tmp/$headerfile"); - - return true; - } - -/*======================================================================*\ - Function: setcookies() - Purpose: set cookies for a redirection -\*======================================================================*/ - - function setcookies() - { - for($x=0; $xheaders); $x++) - { - if(preg_match("/^set-cookie:[\s]+([^=]+)=([^;]+)/i", $this->headers[$x],$match)) - $this->cookies[$match[1]] = $match[2]; - } - } - - -/*======================================================================*\ - Function: _check_timeout - Purpose: checks whether timeout has occurred - Input: $fp file pointer -\*======================================================================*/ - - function _check_timeout($fp) - { - if ($this->read_timeout > 0) { - $fp_status = socket_get_status($fp); - if ($fp_status["timed_out"]) { - $this->timed_out = true; - return true; - } - } - return false; - } - -/*======================================================================*\ - Function: _connect - Purpose: make a socket connection - Input: $fp file pointer -\*======================================================================*/ - - function _connect(&$fp) - { - if(!empty($this->proxy_host) && !empty($this->proxy_port)) - { - $this->_isproxy = true; - $host = $this->proxy_host; - $port = $this->proxy_port; - } - else - { - $host = $this->host; - $port = $this->port; - } - - $this->status = 0; - - if($fp = fsockopen( - $host, - $port, - $errno, - $errstr, - $this->_fp_timeout - )) - { - // socket connection succeeded - - return true; - } - else - { - // socket connection failed - $this->status = $errno; - switch($errno) - { - case -3: - $this->error="socket creation failed (-3)"; - case -4: - $this->error="dns lookup failure (-4)"; - case -5: - $this->error="connection refused or timed out (-5)"; - default: - $this->error="connection failed (".$errno.")"; - } - return false; - } - } -/*======================================================================*\ - Function: _disconnect - Purpose: disconnect a socket connection - Input: $fp file pointer -\*======================================================================*/ - - function _disconnect($fp) - { - return(fclose($fp)); - } - - -/*======================================================================*\ - Function: _prepare_post_body - Purpose: Prepare post body according to encoding type - Input: $formvars - form variables - $formfiles - form upload files - Output: post body -\*======================================================================*/ - - function _prepare_post_body($formvars, $formfiles) - { - settype($formvars, "array"); - settype($formfiles, "array"); - - if (count($formvars) == 0 && count($formfiles) == 0) - return; - - switch ($this->_submit_type) { - case "application/x-www-form-urlencoded": - reset($formvars); - while(list($key,$val) = each($formvars)) { - if (is_array($val) || is_object($val)) { - while (list($cur_key, $cur_val) = each($val)) { - $postdata .= urlencode($key)."[]=".urlencode($cur_val)."&"; - } - } else - $postdata .= urlencode($key)."=".urlencode($val)."&"; - } - break; - - case "multipart/form-data": - $this->_mime_boundary = "Snoopy".md5(uniqid(microtime())); - - reset($formvars); - while(list($key,$val) = each($formvars)) { - if (is_array($val) || is_object($val)) { - while (list($cur_key, $cur_val) = each($val)) { - $postdata .= "--".$this->_mime_boundary."\r\n"; - $postdata .= "Content-Disposition: form-data; name=\"$key\[\]\"\r\n\r\n"; - $postdata .= "$cur_val\r\n"; - } - } else { - $postdata .= "--".$this->_mime_boundary."\r\n"; - $postdata .= "Content-Disposition: form-data; name=\"$key\"\r\n\r\n"; - $postdata .= "$val\r\n"; - } - } - - reset($formfiles); - while (list($field_name, $file_names) = each($formfiles)) { - settype($file_names, "array"); - while (list(, $file_name) = each($file_names)) { - if (!is_readable($file_name)) continue; - - $fp = fopen($file_name, "r"); - $file_content = fread($fp, filesize($file_name)); - fclose($fp); - $base_name = basename($file_name); - - $postdata .= "--".$this->_mime_boundary."\r\n"; - $postdata .= "Content-Disposition: form-data; name=\"$field_name\"; filename=\"$base_name\"\r\n\r\n"; - $postdata .= "$file_content\r\n"; - } - } - $postdata .= "--".$this->_mime_boundary."--\r\n"; - break; - } - - return $postdata; - } -} - -?> diff --git a/htdocs/includes/magpierss/rss_cache.inc b/htdocs/includes/magpierss/rss_cache.inc deleted file mode 100644 index ae134a80072..00000000000 --- a/htdocs/includes/magpierss/rss_cache.inc +++ /dev/null @@ -1,203 +0,0 @@ - - * Version: 0.51 - * License: GPL - * - * The lastest version of MagpieRSS can be obtained from: - * http://magpierss.sourceforge.net - * - * For questions, help, comments, discussion, etc., please join the - * Magpie mailing list: - * http://lists.sourceforge.net/lists/listinfo/magpierss-general - * - */ - -class RSSCache { - var $BASE_CACHE = './cache'; // where the cache files are stored - var $MAX_AGE = 3600; // when are files stale, default one hour - var $ERROR = ""; // accumulate error messages - - function RSSCache ($base='', $age='') { - if ( $base ) { - $this->BASE_CACHE = $base; - } - if ( $age ) { - $this->MAX_AGE = $age; - } - - // attempt to make the cache directory - if ( ! file_exists( $this->BASE_CACHE ) ) { - $status = @mkdir( $this->BASE_CACHE, 0755 ); - - // if make failed - if ( ! $status ) { - $this->error( - "Cache couldn't make dir '" . $this->BASE_CACHE . "'." - ); - } - } - } - -/*=======================================================================*\ - Function: set - Purpose: add an item to the cache, keyed on url - Input: url from wich the rss file was fetched - Output: true on sucess -\*=======================================================================*/ - function set ($url, $rss) { - $this->ERROR = ""; - $cache_file = $this->file_name( $url ); - $fp = @fopen( $cache_file, 'w' ); - - if ( ! $fp ) { - $this->error( - "Cache unable to open file for writing: $cache_file" - ); - return 0; - } - - - $data = $this->serialize( $rss ); - fwrite( $fp, $data ); - fclose( $fp ); - - return $cache_file; - } - -/*=======================================================================*\ - Function: get - Purpose: fetch an item from the cache - Input: url from wich the rss file was fetched - Output: cached object on HIT, false on MISS -\*=======================================================================*/ - function get ($url) { - $this->ERROR = ""; - $cache_file = $this->file_name( $url ); - - if ( ! file_exists( $cache_file ) ) { - $this->debug( - "Cache doesn't contain: $url (cache file: $cache_file)" - ); - return 0; - } - - $fp = @fopen($cache_file, 'r'); - if ( ! $fp ) { - $this->error( - "Failed to open cache file for reading: $cache_file" - ); - return 0; - } - - if ($filesize = filesize($cache_file) ) { - $data = fread( $fp, filesize($cache_file) ); - $rss = $this->unserialize( $data ); - - // LDR - $rss->date=filemtime($cache_file); - - return $rss; - } - - return 0; - } - -/*=======================================================================*\ - Function: check_cache - Purpose: check a url for membership in the cache - and whether the object is older then MAX_AGE (ie. STALE) - Input: url from wich the rss file was fetched - Output: cached object on HIT, false on MISS -\*=======================================================================*/ - function check_cache ( $url ) { - $this->ERROR = ""; - $filename = $this->file_name( $url ); - - if ( file_exists( $filename ) ) { - // find how long ago the file was added to the cache - // and whether that is longer then MAX_AGE - $mtime = filemtime( $filename ); - $age = time() - $mtime; - if ( $this->MAX_AGE > $age ) { - // object exists and is current - return 'HIT'; - } - else { - // object exists but is old - return 'STALE'; - } - } - else { - // object does not exist - return 'MISS'; - } - } - - function cache_age( $cache_key ) { - $filename = $this->file_name( $url ); - if ( file_exists( $filename ) ) { - $mtime = filemtime( $filename ); - $age = time() - $mtime; - return $age; - } - else { - return -1; - } - } - -/*=======================================================================*\ - Function: serialize -\*=======================================================================*/ - function serialize ( $rss ) { - return serialize( $rss ); - } - -/*=======================================================================*\ - Function: unserialize -\*=======================================================================*/ - function unserialize ( $data ) { - return unserialize( $data ); - } - -/*=======================================================================*\ - Function: file_name - Purpose: map url to location in cache - Input: url from wich the rss file was fetched - Output: a file name -\*=======================================================================*/ - function file_name ($url) { - $filename = md5( $url ); - return join( DIRECTORY_SEPARATOR, array( $this->BASE_CACHE, $filename ) ); - } - -/*=======================================================================*\ - Function: error - Purpose: register error -\*=======================================================================*/ - function error ($errormsg, $lvl=E_USER_WARNING) { - // append PHP's error message if track_errors enabled - if ( isset($php_errormsg) ) { - $errormsg .= " ($php_errormsg)"; - } - $this->ERROR = $errormsg; - if ( MAGPIE_DEBUG ) { - trigger_error( $errormsg, $lvl); - } - else { - error_log( $errormsg, 0); - } - } - - function debug ($debugmsg, $lvl=E_USER_NOTICE) { - if ( MAGPIE_DEBUG ) { - $this->error("MagpieRSS [debug] $debugmsg", $lvl); - } - } - -} - -?> diff --git a/htdocs/includes/magpierss/rss_fetch.inc b/htdocs/includes/magpierss/rss_fetch.inc deleted file mode 100644 index 2c2d00dcf25..00000000000 --- a/htdocs/includes/magpierss/rss_fetch.inc +++ /dev/null @@ -1,479 +0,0 @@ - - * Modified by: Laurent Destailleur (See LDR mark to find bug fix) - * License: GPL - * - * The lastest version of MagpieRSS can be obtained from: - * http://magpierss.sourceforge.net - * - * For questions, help, comments, discussion, etc., please join the - * Magpie mailing list: - * magpierss-general@lists.sourceforge.net - * - */ - -// Setup MAGPIE_DIR for use on hosts that don't include -// the current path in include_path. -// with thanks to rajiv and smarty -if (!defined('DIR_SEP')) { - define('DIR_SEP', DIRECTORY_SEPARATOR); -} - -if (!defined('MAGPIE_DIR')) { - define('MAGPIE_DIR', dirname(__FILE__) . DIR_SEP); -} - -require_once( MAGPIE_DIR . 'rss_parse.inc' ); -require_once( MAGPIE_DIR . 'rss_cache.inc' ); - -// for including 3rd party libraries -define('MAGPIE_EXTLIB', MAGPIE_DIR . 'extlib' . DIR_SEP); -require_once( MAGPIE_EXTLIB . 'Snoopy.class.inc'); - - -/* - * CONSTANTS - redefine these in your script to change the - * behaviour of fetch_rss() currently, most options effect the cache - * - * MAGPIE_CACHE_ON - Should Magpie cache parsed RSS objects? - * For me a built in cache was essential to creating a "PHP-like" - * feel to Magpie, see rss_cache.inc for rationale - * - * - * MAGPIE_CACHE_DIR - Where should Magpie cache parsed RSS objects? - * This should be a location that the webserver can write to. If this - * directory does not already exist Mapie will try to be smart and create - * it. This will often fail for permissions reasons. - * - * - * MAGPIE_CACHE_AGE - How long to store cached RSS objects? In seconds. - * - * - * MAGPIE_CACHE_FRESH_ONLY - If remote fetch fails, throw error - * instead of returning stale object? - * - * MAGPIE_DEBUG - Display debugging notices? - * -*/ - - -/*=======================================================================*\ - Function: fetch_rss: - Purpose: return RSS object for the give url - maintain the cache - Input: url of RSS file - Output: parsed RSS object (see rss_parse.inc) - - NOTES ON CACHEING: - If caching is on (MAGPIE_CACHE_ON) fetch_rss will first check the cache. - - NOTES ON RETRIEVING REMOTE FILES: - If conditional gets are on (MAGPIE_CONDITIONAL_GET_ON) fetch_rss will - return a cached object, and touch the cache object upon recieving a - 304. - - NOTES ON FAILED REQUESTS: - If there is an HTTP error while fetching an RSS object, the cached - version will be return, if it exists (and if MAGPIE_CACHE_FRESH_ONLY is off) -\*=======================================================================*/ - -define('MAGPIE_VERSION', '0.72'); - -$MAGPIE_ERROR = ""; - -function fetch_rss ($url) { - // initialize constants - init(); - - if ( !isset($url) ) { - error("fetch_rss called without a url"); - return false; - } - - // if cache is disabled - if ( !MAGPIE_CACHE_ON ) { - // fetch file, and parse it - $resp = _fetch_remote_file( $url ); - if ( is_success( $resp->status ) ) { - return _response_to_rss( $resp ); - } - else { - error("Failed to fetch $url and cache is off"); - return false; - } - } - // else cache is ON - else { - // Flow - // 1. check cache - // 2. if there is a hit, make sure its fresh - // 3. if cached obj fails freshness check, fetch remote - // 4. if remote fails, return stale object, or error - - $cache = new RSSCache( MAGPIE_CACHE_DIR, MAGPIE_CACHE_AGE ); - - if (MAGPIE_DEBUG and $cache->ERROR) { - debug($cache->ERROR, E_USER_WARNING); - } - - - $cache_status = 0; // response of check_cache - $request_headers = array(); // HTTP headers to send with fetch - $rss = 0; // parsed RSS object - $errormsg = 0; // errors, if any - - // store parsed XML by desired output encoding - // as character munging happens at parse time - $cache_key = $url . MAGPIE_OUTPUT_ENCODING; - - if (!$cache->ERROR) { - // return cache HIT, MISS, or STALE - $cache_status = $cache->check_cache( $cache_key); - } - - // if object cached, and cache is fresh, return cached obj - if ( $cache_status == 'HIT' ) { - $rss = $cache->get( $cache_key ); - if ( isset($rss) and $rss ) { - // should be cache age - $rss->from_cache = 1; - if ( MAGPIE_DEBUG > 1) { - debug("MagpieRSS: Cache HIT", E_USER_NOTICE); - } - return $rss; - } - } - - // else attempt a conditional get - - // setup headers - if ( $cache_status == 'STALE' ) { - $rss = $cache->get( $cache_key ); - if ( $rss and $rss->etag and $rss->last_modified ) { - $request_headers['If-None-Match'] = $rss->etag; - $request_headers['If-Last-Modified'] = $rss->last_modified; - } - } - - $resp = _fetch_remote_file( $url, $request_headers ); - - if (isset($resp) and $resp) { - if ($resp->status == '304' ) { - // we have the most current copy - if ( MAGPIE_DEBUG > 1) { - debug("Got 304 for $url"); - } - // reset cache on 304 (at minutillo insistent prodding) - $cache->set($cache_key, $rss); - return $rss; - } - elseif ( is_success( $resp->status ) ) { - $rss = _response_to_rss( $resp ); - if ( $rss ) { - if (MAGPIE_DEBUG > 1) { - debug("Fetch successful"); - } - // add object to cache - $cache->set( $cache_key, $rss ); - return $rss; - } - } - else { - $errormsg = "Failed to fetch $url "; - if ( $resp->status == '-100' ) { - $errormsg .= "(Request timed out after " . MAGPIE_FETCH_TIME_OUT . " seconds)"; - } - elseif ( $resp->error ) { - # compensate for Snoopy's annoying habbit to tacking - # on '\n' - $http_error = substr($resp->error, 0, -2); - $errormsg .= "(HTTP Error: $http_error)"; - } - else { - $errormsg .= "(HTTP Response: " . $resp->response_code .')'; - } - - // LDR FIX BUG If fails to get http url but cache file is read successfuly, - // we store error as a property of $rss->ERROR and date of last successful - // http access in $rss->date property. - // This allows caller to trap error reasons and manage itself networks errors. - if ($rss) - { - if ($cache && $cache_key) $rss->date=filemtime($cache->file_name($cache_key)); - } - else - { - $rss=$cache; - } - $rss->ERROR=$errormsg; - } - } - else { - $errormsg = "Unable to retrieve RSS file for unknown reasons."; - } - - // else fetch failed - - // attempt to return cached object - if ($rss) { - if ( MAGPIE_DEBUG ) { - debug("Returning STALE object for $url"); - } - return $rss; - } - - // else we totally failed - error( $errormsg ); - - return false; - - } // end if ( !MAGPIE_CACHE_ON ) { -} // end fetch_rss() - -/*=======================================================================*\ - Function: error - Purpose: set MAGPIE_ERROR, and trigger error -\*=======================================================================*/ - -function error ($errormsg, $lvl=E_USER_WARNING) { - global $MAGPIE_ERROR; - - // append PHP's error message if track_errors enabled - if ( isset($php_errormsg) ) { - $errormsg .= " ($php_errormsg)"; - } - if ( $errormsg ) { - $errormsg = "MagpieRSS: $errormsg"; - $MAGPIE_ERROR = $errormsg; - // LDR BUG FIX On affiche erreur que si en mode debug - if ( MAGPIE_DEBUG ) { - trigger_error( $errormsg, $lvl); - } - } -} - -function debug ($debugmsg, $lvl=E_USER_NOTICE) { - // LDR BUG FIX On affiche erreur que si en mode debug - if ( MAGPIE_DEBUG ) { - trigger_error("MagpieRSS [debug] $debugmsg", $lvl); - } -} - -/*=======================================================================*\ - Function: magpie_error - Purpose: accessor for the magpie error variable -\*=======================================================================*/ -function magpie_error ($errormsg="") { - global $MAGPIE_ERROR; - - if ( isset($errormsg) and $errormsg ) { - $MAGPIE_ERROR = $errormsg; - } - - return $MAGPIE_ERROR; -} - -/*=======================================================================*\ - Function: _fetch_remote_file - Purpose: retrieve an arbitrary remote file - Input: url of the remote file - headers to send along with the request (optional) - Output: an HTTP response object (see Snoopy.class.inc) -\*=======================================================================*/ -function _fetch_remote_file ($url, $headers = "" ) { - // Snoopy is an HTTP client in PHP - $client = new Snoopy(); - $client->agent = MAGPIE_USER_AGENT; - $client->read_timeout = MAGPIE_FETCH_TIME_OUT; - $client->use_gzip = MAGPIE_USE_GZIP; - if (is_array($headers) ) { - $client->rawheaders = $headers; - } - - @$client->fetch($url); - return $client; - -} - -/*=======================================================================*\ - Function: _response_to_rss - Purpose: parse an HTTP response object into an RSS object - Input: an HTTP response object (see Snoopy) - Output: parsed RSS object (see rss_parse) -\*=======================================================================*/ -function _response_to_rss ($resp) { - $rss = new MagpieRSS( $resp->results, MAGPIE_OUTPUT_ENCODING, MAGPIE_INPUT_ENCODING, MAGPIE_DETECT_ENCODING ); - - // if RSS parsed successfully - if ( $rss and !$rss->ERROR) { - - // find Etag, and Last-Modified - foreach($resp->headers as $h) { - // 2003-03-02 - Nicola Asuni (www.tecnick.com) - fixed bug "Undefined offset: 1" - if (strpos($h, ": ")) { - list($field, $val) = explode(": ", $h, 2); - } - else { - $field = $h; - $val = ""; - } - - if ( $field == 'ETag' ) { - $rss->etag = $val; - } - - if ( $field == 'Last-Modified' ) { - $rss->last_modified = $val; - } - } - - return $rss; - } // else construct error message - else { - $errormsg = "Failed to parse RSS file."; - - if ($rss) { - $errormsg .= " (" . $rss->ERROR . ")"; - } - error($errormsg); - - return false; - } // end if ($rss and !$rss->error) -} - -/*=======================================================================*\ - Function: init - Purpose: setup constants with default values - check for user overrides -\*=======================================================================*/ -function init () { - if ( defined('MAGPIE_INITALIZED') ) { - return; - } - else { - define('MAGPIE_INITALIZED', true); - } - - if ( !defined('MAGPIE_CACHE_ON') ) { - define('MAGPIE_CACHE_ON', true); - } - - if ( !defined('MAGPIE_CACHE_DIR') ) { - define('MAGPIE_CACHE_DIR', './cache'); - } - - if ( !defined('MAGPIE_CACHE_AGE') ) { - define('MAGPIE_CACHE_AGE', 60*60); // one hour - } - - if ( !defined('MAGPIE_CACHE_FRESH_ONLY') ) { - define('MAGPIE_CACHE_FRESH_ONLY', false); - } - - if ( !defined('MAGPIE_OUTPUT_ENCODING') ) { - define('MAGPIE_OUTPUT_ENCODING', 'ISO-8859-1'); - } - - if ( !defined('MAGPIE_INPUT_ENCODING') ) { - define('MAGPIE_INPUT_ENCODING', null); - } - - if ( !defined('MAGPIE_DETECT_ENCODING') ) { - define('MAGPIE_DETECT_ENCODING', true); - } - - if ( !defined('MAGPIE_DEBUG') ) { - define('MAGPIE_DEBUG', 0); - } - - if ( !defined('MAGPIE_USER_AGENT') ) { - $ua = 'MagpieRSS/'. MAGPIE_VERSION . ' (+http://magpierss.sf.net'; - - if ( MAGPIE_CACHE_ON ) { - $ua = $ua . ')'; - } - else { - $ua = $ua . '; No cache)'; - } - - define('MAGPIE_USER_AGENT', $ua); - } - - if ( !defined('MAGPIE_FETCH_TIME_OUT') ) { - define('MAGPIE_FETCH_TIME_OUT', 5); // 5 second timeout - } - - // use gzip encoding to fetch rss files if supported? - if ( !defined('MAGPIE_USE_GZIP') ) { - define('MAGPIE_USE_GZIP', true); - } -} - -// NOTE: the following code should really be in Snoopy, or at least -// somewhere other then rss_fetch! - -/*=======================================================================*\ - HTTP STATUS CODE PREDICATES - These functions attempt to classify an HTTP status code - based on RFC 2616 and RFC 2518. - - All of them take an HTTP status code as input, and return true or false - - All this code is adapted from LWP's HTTP::Status. -\*=======================================================================*/ - - -/*=======================================================================*\ - Function: is_info - Purpose: return true if Informational status code -\*=======================================================================*/ -function is_info ($sc) { - return $sc >= 100 && $sc < 200; -} - -/*=======================================================================*\ - Function: is_success - Purpose: return true if Successful status code -\*=======================================================================*/ -function is_success ($sc) { - return $sc >= 200 && $sc < 300; -} - -/*=======================================================================*\ - Function: is_redirect - Purpose: return true if Redirection status code -\*=======================================================================*/ -function is_redirect ($sc) { - return $sc >= 300 && $sc < 400; -} - -/*=======================================================================*\ - Function: is_error - Purpose: return true if Error status code -\*=======================================================================*/ -function is_error ($sc) { - return $sc >= 400 && $sc < 600; -} - -/*=======================================================================*\ - Function: is_client_error - Purpose: return true if Error status code, and its a client error -\*=======================================================================*/ -function is_client_error ($sc) { - return $sc >= 400 && $sc < 500; -} - -/*=======================================================================*\ - Function: is_client_error - Purpose: return true if Error status code, and its a server error -\*=======================================================================*/ -function is_server_error ($sc) { - return $sc >= 500 && $sc < 600; -} - -?> diff --git a/htdocs/includes/magpierss/rss_parse.inc b/htdocs/includes/magpierss/rss_parse.inc deleted file mode 100644 index e39d3971d2c..00000000000 --- a/htdocs/includes/magpierss/rss_parse.inc +++ /dev/null @@ -1,605 +0,0 @@ - -* @version 0.7a -* @license GPL -* -*/ - -define('RSS', 'RSS'); -define('ATOM', 'Atom'); - -require_once (MAGPIE_DIR . 'rss_utils.inc'); - -/** -* Hybrid parser, and object, takes RSS as a string and returns a simple object. -* -* see: rss_fetch.inc for a simpler interface with integrated caching support -* -*/ -class MagpieRSS { - var $parser; - - var $current_item = array(); // item currently being parsed - var $items = array(); // collection of parsed items - var $channel = array(); // hash of channel fields - var $textinput = array(); - var $image = array(); - var $feed_type; - var $feed_version; - var $encoding = ''; // output encoding of parsed rss - - var $_source_encoding = ''; // only set if we have to parse xml prolog - - var $ERROR = ""; - var $WARNING = ""; - - // define some constants - - var $_CONTENT_CONSTRUCTS = array('content', 'summary', 'info', 'title', 'tagline', 'copyright'); - var $_KNOWN_ENCODINGS = array('UTF-8', 'US-ASCII', 'ISO-8859-1'); - - // parser variables, useless if you're not a parser, treat as private - var $stack = array(); // parser stack - var $inchannel = false; - var $initem = false; - var $incontent = false; // if in Atom field - var $intextinput = false; - var $inimage = false; - var $current_namespace = false; - - - /** - * Set up XML parser, parse source, and return populated RSS object.. - * - * @param string $source string containing the RSS to be parsed - * - * NOTE: Probably a good idea to leave the encoding options alone unless - * you know what you're doing as PHP's character set support is - * a little weird. - * - * NOTE: A lot of this is unnecessary but harmless with PHP5 - * - * - * @param string $output_encoding output the parsed RSS in this character - * set defaults to ISO-8859-1 as this is PHP's - * default. - * - * NOTE: might be changed to UTF-8 in future - * versions. - * - * @param string $input_encoding the character set of the incoming RSS source. - * Leave blank and Magpie will try to figure it - * out. - * - * - * @param bool $detect_encoding if false Magpie won't attempt to detect - * source encoding. (caveat emptor) - * - */ - function MagpieRSS ($source, $output_encoding='ISO-8859-1', - $input_encoding=null, $detect_encoding=true) - { - # if PHP xml isn't compiled in, die - # - if (!function_exists('xml_parser_create')) { - $this->error( "Failed to load PHP's XML Extension. " . - "http://www.php.net/manual/en/ref.xml.php", - E_USER_ERROR ); - } - - list($parser, $source) = $this->create_parser($source, - $output_encoding, $input_encoding, $detect_encoding); - - - if (!is_resource($parser)) { - $this->error( "Failed to create an instance of PHP's XML parser. " . - "http://www.php.net/manual/en/ref.xml.php", - E_USER_ERROR ); - } - - - $this->parser = $parser; - - # pass in parser, and a reference to this object - # setup handlers - # - xml_set_object( $this->parser, $this ); - xml_set_element_handler($this->parser, - 'feed_start_element', 'feed_end_element' ); - - xml_set_character_data_handler( $this->parser, 'feed_cdata' ); - - $status = xml_parse( $this->parser, $source ); - - if (! $status ) { - $errorcode = xml_get_error_code( $this->parser ); - if ( $errorcode != XML_ERROR_NONE ) { - $xml_error = xml_error_string( $errorcode ); - $error_line = xml_get_current_line_number($this->parser); - $error_col = xml_get_current_column_number($this->parser); - $errormsg = "$xml_error at line $error_line, column $error_col"; - - $this->error( $errormsg ); - } - } - - xml_parser_free( $this->parser ); - - $this->normalize(); - } - - function feed_start_element($p, $element, &$attrs) { - $el = $element = strtolower($element); - $attrs = array_change_key_case($attrs, CASE_LOWER); - - // check for a namespace, and split if found - $ns = false; - if ( strpos( $element, ':' ) ) { - list($ns, $el) = explode( ':', $element, 2); - } - if ( $ns and $ns != 'rdf' ) { - $this->current_namespace = $ns; - } - - # if feed type isn't set, then this is first element of feed - # identify feed from root element - # - if (!isset($this->feed_type) ) { - if ( $el == 'rdf' ) { - $this->feed_type = RSS; - $this->feed_version = '1.0'; - } - elseif ( $el == 'rss' ) { - $this->feed_type = RSS; - $this->feed_version = $attrs['version']; - } - elseif ( $el == 'feed' ) { - $this->feed_type = ATOM; - $this->feed_version = $attrs['version']; - $this->inchannel = true; - } - return; - } - - if ( $el == 'channel' ) - { - $this->inchannel = true; - } - elseif ($el == 'item' or $el == 'entry' ) - { - $this->initem = true; - if ( isset($attrs['rdf:about']) ) { - $this->current_item['about'] = $attrs['rdf:about']; - } - } - - // if we're in the default namespace of an RSS feed, - // record textinput or image fields - elseif ( - $this->feed_type == RSS and - $this->current_namespace == '' and - $el == 'textinput' ) - { - $this->intextinput = true; - } - - elseif ( - $this->feed_type == RSS and - $this->current_namespace == '' and - $el == 'image' ) - { - $this->inimage = true; - } - - # handle atom content constructs - elseif ( $this->feed_type == ATOM and in_array($el, $this->_CONTENT_CONSTRUCTS) ) - { - // avoid clashing w/ RSS mod_content - if ($el == 'content' ) { - $el = 'atom_content'; - } - - $this->incontent = $el; - - - } - - // if inside an Atom content construct (e.g. content or summary) field treat tags as text - elseif ($this->feed_type == ATOM and $this->incontent ) - { - // if tags are inlined, then flatten - $attrs_str = join(' ', - array_map('map_attrs', - array_keys($attrs), - array_values($attrs) ) ); - - $this->append_content( "<$element $attrs_str>" ); - - array_unshift( $this->stack, $el ); - } - - // Atom support many links per containging element. - // Magpie treats link elements of type rel='alternate' - // as being equivalent to RSS's simple link element. - // - elseif ($this->feed_type == ATOM and $el == 'link' ) - { - if ( isset($attrs['rel']) and $attrs['rel'] == 'alternate' ) - { - $link_el = 'link'; - } - else { - $link_el = 'link_' . $attrs['rel']; - } - - $this->append($link_el, $attrs['href']); - } - // set stack[0] to current element - else { - array_unshift($this->stack, $el); - } - } - - - - function feed_cdata ($p, $text) { - if ($this->feed_type == ATOM and $this->incontent) - { - $this->append_content( $text ); - } - else { - $current_el = join('_', array_reverse($this->stack)); - $this->append($current_el, $text); - } - } - - function feed_end_element ($p, $el) { - $el = strtolower($el); - - if ( $el == 'item' or $el == 'entry' ) - { - $this->items[] = $this->current_item; - $this->current_item = array(); - $this->initem = false; - } - elseif ($this->feed_type == RSS and $this->current_namespace == '' and $el == 'textinput' ) - { - $this->intextinput = false; - } - elseif ($this->feed_type == RSS and $this->current_namespace == '' and $el == 'image' ) - { - $this->inimage = false; - } - elseif ($this->feed_type == ATOM and in_array($el, $this->_CONTENT_CONSTRUCTS) ) - { - $this->incontent = false; - } - elseif ($el == 'channel' or $el == 'feed' ) - { - $this->inchannel = false; - } - elseif ($this->feed_type == ATOM and $this->incontent ) { - // balance tags properly - // note: i don't think this is actually neccessary - if ( $this->stack[0] == $el ) - { - $this->append_content(""); - } - else { - $this->append_content("<$el />"); - } - - array_shift( $this->stack ); - } - else { - array_shift( $this->stack ); - } - - $this->current_namespace = false; - } - - function concat (&$str1, $str2="") { - if (!isset($str1) ) { - $str1=""; - } - $str1 .= $str2; - } - - - - function append_content($text) { - if ( $this->initem ) { - $this->concat( $this->current_item[ $this->incontent ], $text ); - } - elseif ( $this->inchannel ) { - $this->concat( $this->channel[ $this->incontent ], $text ); - } - } - - // smart append - field and namespace aware - function append($el, $text) { - if (!$el) { - return; - } - if ( $this->current_namespace ) - { - if ( $this->initem ) { - $this->concat( - $this->current_item[ $this->current_namespace ][ $el ], $text); - } - elseif ($this->inchannel) { - $this->concat( - $this->channel[ $this->current_namespace][ $el ], $text ); - } - elseif ($this->intextinput) { - $this->concat( - $this->textinput[ $this->current_namespace][ $el ], $text ); - } - elseif ($this->inimage) { - $this->concat( - $this->image[ $this->current_namespace ][ $el ], $text ); - } - } - else { - if ( $this->initem ) { - $this->concat( - $this->current_item[ $el ], $text); - } - elseif ($this->intextinput) { - $this->concat( - $this->textinput[ $el ], $text ); - } - elseif ($this->inimage) { - $this->concat( - $this->image[ $el ], $text ); - } - elseif ($this->inchannel) { - $this->concat( - $this->channel[ $el ], $text ); - } - - } - } - - function normalize () { - // if atom populate rss fields - if ( $this->is_atom() ) { - $this->channel['description'] = $this->channel['tagline']; - for ( $i = 0; $i < count($this->items); $i++) { - $item = $this->items[$i]; - if ( isset($item['summary']) ) - $item['description'] = $item['summary']; - if ( isset($item['atom_content'])) - $item['content']['encoded'] = $item['atom_content']; - - $atom_date = (isset($item['issued']) ) ? $item['issued'] : $item['modified']; - if ( $atom_date ) { - $epoch = @parse_w3cdtf($atom_date); - if ($epoch and $epoch > 0) { - $item['date_timestamp'] = $epoch; - } - } - - $this->items[$i] = $item; - } - } - elseif ( $this->is_rss() ) { - $this->channel['tagline'] = $this->channel['description']; - for ( $i = 0; $i < count($this->items); $i++) { - $item = $this->items[$i]; - if ( isset($item['description'])) - $item['summary'] = $item['description']; - if ( isset($item['content']['encoded'] ) ) - $item['atom_content'] = $item['content']['encoded']; - - if ( $this->is_rss() == '1.0' and isset($item['dc']['date']) ) { - $epoch = @parse_w3cdtf($item['dc']['date']); - if ($epoch and $epoch > 0) { - $item['date_timestamp'] = $epoch; - } - } - elseif ( isset($item['pubdate']) ) { - $epoch = @strtotime($item['pubdate']); - if ($epoch > 0) { - $item['date_timestamp'] = $epoch; - } - } - - $this->items[$i] = $item; - } - } - } - - - function is_rss () { - if ( $this->feed_type == RSS ) { - return $this->feed_version; - } - else { - return false; - } - } - - function is_atom() { - if ( $this->feed_type == ATOM ) { - return $this->feed_version; - } - else { - return false; - } - } - - /** - * return XML parser, and possibly re-encoded source - * - */ - function create_parser($source, $out_enc, $in_enc, $detect) { - if ( substr(phpversion(),0,1) == 5) { - $parser = $this->php5_create_parser($in_enc, $detect); - } - else { - list($parser, $source) = $this->php4_create_parser($source, $in_enc, $detect); - } - if ($out_enc) { - $this->encoding = $out_enc; - xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, $out_enc); - } - - return array($parser, $source); - } - - /** - * Instantiate an XML parser under PHP5 - * - * PHP5 will do a fine job of detecting input encoding - * if passed an empty string as the encoding. - * - * All hail libxml2! - * - */ - function php5_create_parser($in_enc, $detect) { - // by default php5 does a fine job of detecting input encodings - if(!$detect && $in_enc) { - return xml_parser_create($in_enc); - } - else { - return xml_parser_create(''); - } - } - - /** - * Instaniate an XML parser under PHP4 - * - * Unfortunately PHP4's support for character encodings - * and especially XML and character encodings sucks. As - * long as the documents you parse only contain characters - * from the ISO-8859-1 character set (a superset of ASCII, - * and a subset of UTF-8) you're fine. However once you - * step out of that comfy little world things get mad, bad, - * and dangerous to know. - * - * The following code is based on SJM's work with FoF - * @see http://minutillo.com/steve/weblog/2004/6/17/php-xml-and-character-encodings-a-tale-of-sadness-rage-and-data-loss - * - */ - function php4_create_parser($source, $in_enc, $detect) { - if ( !$detect ) { - return array(xml_parser_create($in_enc), $source); - } - - if (!$in_enc) { - if (preg_match('//m', $source, $m)) { - $in_enc = strtoupper($m[1]); - $this->source_encoding = $in_enc; - } - else { - $in_enc = 'UTF-8'; - } - } - - if ($this->known_encoding($in_enc)) { - return array(xml_parser_create($in_enc), $source); - } - - // the dectected encoding is not one of the simple encodings PHP knows - - // attempt to use the iconv extension to - // cast the XML to a known encoding - // @see http://php.net/iconv - - if (function_exists('iconv')) { - $encoded_source = iconv($in_enc,'UTF-8', $source); - if ($encoded_source) { - return array(xml_parser_create('UTF-8'), $encoded_source); - } - } - - // iconv didn't work, try mb_convert_encoding - // @see http://php.net/mbstring - if(function_exists('mb_convert_encoding')) { - $encoded_source = mb_convert_encoding($source, 'UTF-8', $in_enc ); - if ($encoded_source) { - return array(xml_parser_create('UTF-8'), $encoded_source); - } - } - - // else - $this->error("Feed is in an unsupported character encoding. ($in_enc) " . - "You may see strange artifacts, and mangled characters.", - E_USER_NOTICE); - - return array(xml_parser_create(), $source); - } - - function known_encoding($enc) { - $enc = strtoupper($enc); - if ( in_array($enc, $this->_KNOWN_ENCODINGS) ) { - return $enc; - } - else { - return false; - } - } - - function error ($errormsg, $lvl=E_USER_WARNING) { - // append PHP's error message if track_errors enabled - if ( isset($php_errormsg) ) { - $errormsg .= " ($php_errormsg)"; - } - if ( MAGPIE_DEBUG ) { - trigger_error( $errormsg, $lvl); - } - else { - error_log( $errormsg, 0); - } - - $notices = E_USER_NOTICE|E_NOTICE; - if ( $lvl&$notices ) { - $this->WARNING = $errormsg; - } else { - $this->ERROR = $errormsg; - } - } - - -} // end class RSS - -function map_attrs($k, $v) { - return "$k=\"$v\""; -} - -// patch to support medieval versions of PHP4.1.x, -// courtesy, Ryan Currie, ryan@digibliss.com - -if (!function_exists('array_change_key_case')) { - define("CASE_UPPER",1); - define("CASE_LOWER",0); - - - function array_change_key_case($array,$case=CASE_LOWER) { - if ($case=CASE_LOWER) $cmd=strtolower; - elseif ($case=CASE_UPPER) $cmd=strtoupper; - foreach($array as $key=>$value) { - $output[$cmd($key)]=$value; - } - return $output; - } - -} - -?> diff --git a/htdocs/includes/magpierss/rss_utils.inc b/htdocs/includes/magpierss/rss_utils.inc deleted file mode 100644 index 2a29e72a969..00000000000 --- a/htdocs/includes/magpierss/rss_utils.inc +++ /dev/null @@ -1,67 +0,0 @@ - - * Version: 0.51 - * License: GPL - * - * The lastest version of MagpieRSS can be obtained from: - * http://magpierss.sourceforge.net - * - * For questions, help, comments, discussion, etc., please join the - * Magpie mailing list: - * magpierss-general@lists.sourceforge.net - */ - - -/*======================================================================*\ - Function: parse_w3cdtf - Purpose: parse a W3CDTF date into unix epoch - - NOTE: http://www.w3.org/TR/NOTE-datetime -\*======================================================================*/ - -function parse_w3cdtf ( $date_str ) { - - # regex to match wc3dtf - $pat = "/(\d{4})-(\d{2})-(\d{2})T(\d{2}):(\d{2})(:(\d{2}))?(?:([-+])(\d{2}):?(\d{2})|(Z))?/"; - - if ( preg_match( $pat, $date_str, $match ) ) { - list( $year, $month, $day, $hours, $minutes, $seconds) = - array( $match[1], $match[2], $match[3], $match[4], $match[5], $match[6]); - - # calc epoch for current date assuming GMT - $epoch = gmmktime( $hours, $minutes, $seconds, $month, $day, $year); - - $offset = 0; - if ( $match[10] == 'Z' ) { - # zulu time, aka GMT - } - else { - list( $tz_mod, $tz_hour, $tz_min ) = - array( $match[8], $match[9], $match[10]); - - # zero out the variables - if ( ! $tz_hour ) { $tz_hour = 0; } - if ( ! $tz_min ) { $tz_min = 0; } - - $offset_secs = (($tz_hour*60)+$tz_min)*60; - - # is timezone ahead of GMT? then subtract offset - # - if ( $tz_mod == '+' ) { - $offset_secs = $offset_secs * -1; - } - - $offset = $offset_secs; - } - $epoch = $epoch + $offset; - return $epoch; - } - else { - return -1; - } -} - -?> diff --git a/htdocs/master.inc.php b/htdocs/master.inc.php index 66599852176..2959f22c6b2 100644 --- a/htdocs/master.inc.php +++ b/htdocs/master.inc.php @@ -29,7 +29,7 @@ * \ingroup core * \brief File that defines environment for all Dolibarr process (pages or scripts) * This script reads the conf file, init $lang, $db and and empty $user - * \version $Id: master.inc.php,v 1.356 2011/08/14 18:26:15 eldy Exp $ + * \version $Id: master.inc.php,v 1.357 2011/08/17 13:44:15 eldy Exp $ */ @@ -296,7 +296,6 @@ if (! defined('MAIN_LABEL_MENTION_NPR') ) define('MAIN_LABEL_MENTION_NPR','NPR') // Path to root libraries if (! defined('TCPDF_PATH')) { define('TCPDF_PATH', DOL_DOCUMENT_ROOT .'/includes/tcpdf/'); } if (! defined('FPDFI_PATH')) { define('FPDFI_PATH', DOL_DOCUMENT_ROOT .'/includes/fpdfi/'); } -if (! defined('MAGPIERSS_PATH')) { define('MAGPIERSS_PATH', DOL_DOCUMENT_ROOT .'/includes/magpierss/'); } if (! defined('NUSOAP_PATH')) { define('NUSOAP_PATH', DOL_DOCUMENT_ROOT .'/includes/nusoap/lib/'); } if (! defined('PHPEXCEL_PATH')) { define('PHPEXCEL_PATH', DOL_DOCUMENT_ROOT .'/includes/phpexcel/'); } if (! defined('ODTPHP_PATH')) { define('ODTPHP_PATH', empty($dolibarr_lib_ODTPHP_PATH)?DOL_DOCUMENT_ROOT.'/includes/odtphp/':$dolibarr_lib_ODTPHP_PATH.'/'); } @@ -306,8 +305,6 @@ if (! defined('ARTICHOW_FONT')) { define('ARTICHOW_FONT', empty($d if (! defined('ARTICHOW_FONT_NAMES')) { define('ARTICHOW_FONT_NAMES', empty($dolibarr_font_DOL_DEFAULT_TTF_BOLD)?'Tuffy,TuffyBold,TuffyBoldItalic,TuffyItalic':'DejaVuSans,DejaVuSans-Bold,DejaVuSans-BoldOblique,DejaVuSans-Oblique'); } if (! defined('DOL_DEFAULT_TTF')) { define('DOL_DEFAULT_TTF', empty($dolibarr_font_DOL_DEFAULT_TTF)?DOL_DOCUMENT_ROOT.'/includes/barcode/php-barcode/fonts/Aerial.ttf':$dolibarr_font_DOL_DEFAULT_TTF); } if (! defined('DOL_DEFAULT_TTF_BOLD')) { define('DOL_DEFAULT_TTF_BOLD', empty($dolibarr_font_DOL_DEFAULT_TTF_BOLD)?DOL_DOCUMENT_ROOT.'/includes/barcode/php-barcode/fonts/AerialBd.ttf':$dolibarr_font_DOL_DEFAULT_TTF_BOLD); } -if (! defined('MAGPIE_DIR')) { define('MAGPIE_DIR', MAGPIERSS_PATH); } -if (! defined('MAGPIE_CACHE_DIR')) { define('MAGPIE_CACHE_DIR', $conf->externalrss->dir_temp); } // Old path to root deprecated (not used). Kept for extensions. if (! defined('FPDF_PATH')) { define('FPDF_PATH', DOL_DOCUMENT_ROOT .'/includes/fpdf/fpdf/'); } if (! defined('PHP_WRITEEXCEL_PATH')) { define('PHP_WRITEEXCEL_PATH',DOL_DOCUMENT_ROOT .'/includes/php_writeexcel/'); } diff --git a/test/phpunit/phpunittest.xml b/test/phpunit/phpunittest.xml index f06a12890e5..8d445e7b9fb 100644 --- a/test/phpunit/phpunittest.xml +++ b/test/phpunit/phpunittest.xml @@ -22,7 +22,6 @@ ../../htdocs/includes/geoip/ ../../htdocs/includes/jquery/ ../../htdocs/includes/jsgantt/ - ../../htdocs/includes/magpierss/ ../../htdocs/includes/menus/smartphone/ ../../htdocs/includes/nusoap/ ../../htdocs/includes/odtphp/ @@ -63,7 +62,6 @@ ../../htdocs/includes/geoip/ ../../htdocs/includes/jquery/ ../../htdocs/includes/jsgantt/ - ../../htdocs/includes/magpierss/ ../../htdocs/includes/menus/smartphone ../../htdocs/includes/nusoap/ ../../htdocs/includes/odtphp/