[pLog-svn] r2554 - in
plog/branches/plog-1.0.2/class/xml/rssparser/magpierss: . extlib
oscar at devel.plogworld.net
oscar at devel.plogworld.net
Thu Nov 10 17:03:03 GMT 2005
Author: oscar
Date: 2005-11-10 17:03:03 +0000 (Thu, 10 Nov 2005)
New Revision: 2554
Modified:
plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/extlib/Snoopy.class.inc
plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_cache.inc
plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_fetch.inc
plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_parse.inc
plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_utils.inc
Log:
Updated to MagpieRSS 0.72 because of a security issue: http://www.sec-consult.com/216.html
Modified: plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/extlib/Snoopy.class.inc
===================================================================
--- plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/extlib/Snoopy.class.inc 2005-11-10 16:51:39 UTC (rev 2553)
+++ plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/extlib/Snoopy.class.inc 2005-11-10 17:03:03 UTC (rev 2554)
@@ -81,7 +81,7 @@
var $timed_out = false; // if a read operation timed out
var $status = 0; // http request status
- var $curl_path = "/usr/local/bin/curl";
+ 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.
@@ -93,6 +93,9 @@
// 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)
@@ -144,7 +147,7 @@
}
else
{
- $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
+ $path = $URI_PARTS["path"].(isset($URI_PARTS["query"]) ? "?".$URI_PARTS["query"] : "");
// no proxy, send only the path
$this->_httprequest($path, $fp, $URI, $this->_httpmethod);
}
@@ -191,8 +194,10 @@
return true;
break;
case "https":
- if(!$this->curl_path || (!is_executable($this->curl_path)))
+ if(!$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"];
@@ -251,328 +256,9 @@
return true;
}
-/*======================================================================*\
- Function: submit
- Purpose: submit an http form
- Input: $URI the location to post the data
- $formvars the formvars to use.
- format: $formvars["var"] = "val";
- Output: $this->results the text output from the post
-\*======================================================================*/
- function submit($URI, $formvars="", $formfiles="")
- {
- unset($postdata);
-
- $postdata = $this->_prepare_post_body($formvars, $formfiles);
-
- $URI_PARTS = parse_url($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 = $URI_PARTS["port"];
- if($this->_connect($fp))
- {
- if($this->_isproxy)
- {
- // using proxy, send entire URI
- $this->_httprequest($URI,$fp,$URI,$this->_submit_method,$this->_submit_type,$postdata);
- }
- else
- {
- $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
- // no proxy, send only the path
- $this->_httprequest($path, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata);
- }
-
- $this->_disconnect($fp);
- if($this->_redirectaddr)
- {
- /* url was redirected, check if we've hit the max depth */
- if($this->maxredirs > $this->_redirectdepth)
- {
- if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr))
- $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]);
-
- // 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;
- $this->submit($this->_redirectaddr,$formvars, $formfiles);
- }
- }
- }
-
- if($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)))
- 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->_submit_method, $this->_submit_type, $postdata);
- }
- else
- {
- $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
- // no proxy, send only the path
- $this->_httpsrequest($path, $URI, $this->_submit_method, $this->_submit_type, $postdata);
- }
-
- if($this->_redirectaddr)
- {
- /* url was redirected, check if we've hit the max depth */
- if($this->maxredirs > $this->_redirectdepth)
- {
- if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr))
- $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]);
-
- // 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;
- $this->submit($this->_redirectaddr,$formvars, $formfiles);
- }
- }
- }
-
- if($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;
- }
-
/*======================================================================*\
- Function: fetchlinks
- Purpose: fetch the links from a web page
- Input: $URI where you are fetching from
- Output: $this->results an array of the URLs
-\*======================================================================*/
-
- function fetchlinks($URI)
- {
- if ($this->fetch($URI))
- {
-
- if(is_array($this->results))
- {
- for($x=0;$x<count($this->results);$x++)
- $this->results[$x] = $this->_striplinks($this->results[$x]);
- }
- else
- $this->results = $this->_striplinks($this->results);
-
- if($this->expandlinks)
- $this->results = $this->_expandlinks($this->results, $URI);
- return true;
- }
- else
- return false;
- }
-
-/*======================================================================*\
- Function: fetchform
- Purpose: fetch the form elements from a web page
- Input: $URI where you are fetching from
- Output: $this->results the resulting html form
-\*======================================================================*/
-
- function fetchform($URI)
- {
-
- if ($this->fetch($URI))
- {
-
- if(is_array($this->results))
- {
- for($x=0;$x<count($this->results);$x++)
- $this->results[$x] = $this->_stripform($this->results[$x]);
- }
- else
- $this->results = $this->_stripform($this->results);
-
- return true;
- }
- else
- return false;
- }
-
-
-/*======================================================================*\
- Function: fetchtext
- Purpose: fetch the text from a web page, stripping the links
- Input: $URI where you are fetching from
- Output: $this->results the text from the web page
-\*======================================================================*/
-
- function fetchtext($URI)
- {
- if($this->fetch($URI))
- {
- if(is_array($this->results))
- {
- for($x=0;$x<count($this->results);$x++)
- $this->results[$x] = $this->_striptext($this->results[$x]);
- }
- else
- $this->results = $this->_striptext($this->results);
- return true;
- }
- else
- return false;
- }
-
-/*======================================================================*\
- Function: submitlinks
- Purpose: grab links from a form submission
- Input: $URI where you are submitting from
- Output: $this->results an array of the links from the post
-\*======================================================================*/
-
- function submitlinks($URI, $formvars="", $formfiles="")
- {
- if($this->submit($URI,$formvars, $formfiles))
- {
- if(is_array($this->results))
- {
- for($x=0;$x<count($this->results);$x++)
- {
- $this->results[$x] = $this->_striplinks($this->results[$x]);
- if($this->expandlinks)
- $this->results[$x] = $this->_expandlinks($this->results[$x],$URI);
- }
- }
- else
- {
- $this->results = $this->_striplinks($this->results);
- if($this->expandlinks)
- $this->results = $this->_expandlinks($this->results,$URI);
- }
- return true;
- }
- else
- return false;
- }
-
-/*======================================================================*\
- Function: submittext
- Purpose: grab text from a form submission
- Input: $URI where you are submitting from
- Output: $this->results the text from the web page
-\*======================================================================*/
-
- function submittext($URI, $formvars = "", $formfiles = "")
- {
- if($this->submit($URI,$formvars, $formfiles))
- {
- if(is_array($this->results))
- {
- for($x=0;$x<count($this->results);$x++)
- {
- $this->results[$x] = $this->_striptext($this->results[$x]);
- if($this->expandlinks)
- $this->results[$x] = $this->_expandlinks($this->results[$x],$URI);
- }
- }
- else
- {
- $this->results = $this->_striptext($this->results);
- if($this->expandlinks)
- $this->results = $this->_expandlinks($this->results,$URI);
- }
- return true;
- }
- else
- return false;
- }
-
-
-
-/*======================================================================*\
- Function: set_submit_multipart
- Purpose: Set the form submission content type to
- multipart/form-data
-\*======================================================================*/
- function set_submit_multipart()
- {
- $this->_submit_type = "multipart/form-data";
- }
-
-
-/*======================================================================*\
- Function: set_submit_normal
- Purpose: Set the form submission content type to
- application/x-www-form-urlencoded
-\*======================================================================*/
- function set_submit_normal()
- {
- $this->_submit_type = "application/x-www-form-urlencoded";
- }
-
-
-
-
-/*======================================================================*\
Private functions
\*======================================================================*/
@@ -733,6 +419,21 @@
$headers .= "Host: ".$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))
@@ -778,6 +479,9 @@
$this->_redirectaddr = false;
unset($this->headers);
+
+ // content was returned gzip encoded?
+ $is_gzipped = false;
while($currentHeader = fgets($fp,$this->_maxlinelen))
{
@@ -787,8 +491,9 @@
return false;
}
- if($currentHeader == "\r\n")
- break;
+ // if($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))
@@ -818,20 +523,31 @@
}
$this->response_code = $currentHeader;
}
-
+
+ if (preg_match("/Content-Encoding: gzip/", $currentHeader) ) {
+ $is_gzipped = true;
+ }
+
$this->headers[] = $currentHeader;
}
- //$results = fread($fp, $this->maxlength);
- while(!feof($fp)) {
- $results .= fgets($fp, 128);
+ # $results = fread($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))
{
$this->status=-100;
@@ -923,9 +639,10 @@
if(!empty($this->user) || !empty($this->pass))
$headers[] = "Authorization: BASIC ".base64_encode($this->user.":".$this->pass);
- for($curr_header = 0; $curr_header < count($headers); $curr_header++)
+ for($curr_header = 0; $curr_header < count($headers); $curr_header++) {
$cmdline_params .= " -H \"".$headers[$curr_header]."\"";
-
+ }
+
if(!empty($body))
$cmdline_params .= " -d \"$body\"";
@@ -933,9 +650,11 @@
$cmdline_params .= " -m ".$this->read_timeout;
$headerfile = uniqid(time());
-
- exec($this->curl_path." -D \"/tmp/$headerfile\"".$cmdline_params." ".$URI,$results,$return);
+ # 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 $return.";
@@ -974,8 +693,13 @@
}
if(preg_match("|^HTTP/|",$result_headers[$currentHeader]))
- $this->response_code = $result_headers[$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];
}
Modified: plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_cache.inc
===================================================================
--- plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_cache.inc 2005-11-10 16:51:39 UTC (rev 2553)
+++ plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_cache.inc 2005-11-10 17:03:03 UTC (rev 2554)
@@ -1,185 +1,200 @@
-<?php
-/**
- * \ingroup XML
- *
- * Project: MagpieRSS: a simple RSS integration tool
- * File: rss_cache.inc, a simple, rolling(no GC), cache
- * for RSS objects, keyed on URL.
- * Author: Kellan Elliott-McCrea <kellan at protest.net>
- * 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;
- }
-
- $data = fread( $fp, filesize($cache_file) );
- $rss = $this->unserialize( $data );
-
- return $rss;
- }
-
-/*=======================================================================*\
- 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: 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);
- }
- }
-
-}
-
-?>
+<?php
+/*
+ * Project: MagpieRSS: a simple RSS integration tool
+ * File: rss_cache.inc, a simple, rolling(no GC), cache
+ * for RSS objects, keyed on URL.
+ * Author: Kellan Elliott-McCrea <kellan at protest.net>
+ * 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 );
+
+ 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);
+ }
+ }
+
+}
+
+?>
Modified: plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_fetch.inc
===================================================================
--- plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_fetch.inc 2005-11-10 16:51:39 UTC (rev 2553)
+++ plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_fetch.inc 2005-11-10 17:03:03 UTC (rev 2554)
@@ -1,460 +1,458 @@
-<?php
-/**
- * \ingroup XML
- *
- * Project: MagpieRSS: a simple RSS integration tool
- * File: rss_fetch.inc, a simple functional interface
- to fetching and parsing RSS files, via the
- function fetch_rss()
- * Author: Kellan Elliott-McCrea <kellan at protest.net>
- * 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 at 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', '0.7');
-
-$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 .')';
- }
- }
- }
- 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;
- trigger_error( $errormsg, $lvl);
- }
-}
-
-function debug ($debugmsg, $lvl=E_USER_NOTICE) {
- 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;
-}
-
-?>
+<?php
+/*
+ * Project: MagpieRSS: a simple RSS integration tool
+ * File: rss_fetch.inc, a simple functional interface
+ to fetching and parsing RSS files, via the
+ function fetch_rss()
+ * Author: Kellan Elliott-McCrea <kellan at protest.net>
+ * 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 at 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 .')';
+ }
+ }
+ }
+ 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;
+ trigger_error( $errormsg, $lvl);
+ }
+}
+
+function debug ($debugmsg, $lvl=E_USER_NOTICE) {
+ 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;
+}
+
+?>
Modified: plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_parse.inc
===================================================================
--- plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_parse.inc 2005-11-10 16:51:39 UTC (rev 2553)
+++ plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_parse.inc 2005-11-10 17:03:03 UTC (rev 2554)
@@ -1,592 +1,605 @@
-<?php
-
-define('RSS', 'RSS');
-define('ATOM', 'Atom');
-
-require_once (MAGPIE_DIR . 'rss_utils.inc');
-
+<?php
+
/**
-* \ingroup XML
-*
-* Project: MagpieRSS: a simple RSS integration tool
-* File: rss_parse.inc - parse an RSS or Atom feed
-* return as a simple object.
-*
-* Handles RSS 0.9x, RSS 2.0, RSS 1.0, and Atom 0.3
-*
-* 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 at lists.sourceforge.net
-*
-* @author Kellan Elliott-McCrea <kellan at protest.net>
-* @version 0.7a (with enclosures)
-* @license GPL
-*
-*/
-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 <content mode="xml"> field
- var $intextinput = false;
- var $inimage = false;
- var $current_field = '';
- 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) = split( ':', $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;
- }
- elseif (
- $this->feed_type == RSS and
- $el == 'enclosure' )
- {
- $this->current_item[$el][] = $attrs;
- $this->incontent = $el;
- }
-
- # 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 )
- {
- $this->append_content("</$el>");
- }
- 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 ) {
- $epoch = @parse_w3cdtf($item['modified']);
- 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('/<?xml.*encoding=[\'"](.*?)[\'"].*?>/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);
- return array(xml_parser_create(''), $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 ( $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\"";
-}
-
-
-?>
+* Project: MagpieRSS: a simple RSS integration tool
+* File: rss_parse.inc - parse an RSS or Atom feed
+* return as a simple object.
+*
+* Handles RSS 0.9x, RSS 2.0, RSS 1.0, and Atom 0.3
+*
+* 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 at lists.sourceforge.net
+*
+* @author Kellan Elliott-McCrea <kellan at protest.net>
+* @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 <content mode="xml"> 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) = split( ':', $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 )
+ {
+ $this->append_content("</$el>");
+ }
+ 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('/<?xml.*encoding=[\'"](.*?)[\'"].*?>/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=\"$v\"";
+}
+
+// patch to support medieval versions of PHP4.1.x,
+// courtesy, Ryan Currie, ryan at digibliss.com
+
+if (!function_exists('array_change_key_case')) {
+ define("CASE_UPPER",1);
+ define("CASE_LOWER",0);
+
+
+ function array_change_key_case($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;
+ }
+
+}
+
+?>
Modified: plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_utils.inc
===================================================================
--- plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_utils.inc 2005-11-10 16:51:39 UTC (rev 2553)
+++ plog/branches/plog-1.0.2/class/xml/rssparser/magpierss/rss_utils.inc 2005-11-10 17:03:03 UTC (rev 2554)
@@ -1,69 +1,67 @@
-<?php
-/**
- * \ingroup XML
- *
- * Project: MagpieRSS: a simple RSS integration tool
- * File: rss_utils.inc, utility methods for working with RSS
- * Author: Kellan Elliott-McCrea <kellan at protest.net>
- * 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 at 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;
- }
-}
-
-?>
+<?php
+/*
+ * Project: MagpieRSS: a simple RSS integration tool
+ * File: rss_utils.inc, utility methods for working with RSS
+ * Author: Kellan Elliott-McCrea <kellan at protest.net>
+ * 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 at 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;
+ }
+}
+
+?>
More information about the pLog-svn
mailing list