mirror of
https://gerrit.wikimedia.org/r/mediawiki/extensions/RSS
synced 2024-09-25 03:09:26 +00:00
* Use [[Template:RSSPost]] (and [[Mediawiki:Rss-item]]) (or another
specified template) to display the feeds and remove hard-coded HTML. * Add check to make sure the cache dir is writable and put an error in the debug log if not. * Remove Snoopy.class.php — replace with use of the Http class. * Remove RSSParse.php — which was a copy of MagpieRSS and use plain XML parsing. MagpieRSS looks unmaintained and has security problems. http://www.madirish.net/?article=253 * Remove references to Magpie RSS * Remove (over?) use of wf{Supress,Restore}Warnings * Construct simple RSSData class for normalizing (some of) the feed data.
This commit is contained in:
Mark A. Hershberger
parent
d06c97258b
commit
e14f1ce5f2
|
|
@ -15,8 +15,14 @@ $messages['en'] = array(
|
|||
'rss-desc' => 'Displays an RSS feed on a wiki page',
|
||||
'rss-error' => 'Failed to load RSS feed from $1: $2',
|
||||
'rss-empty' => 'Failed to load RSS feed from $1!',
|
||||
'rss-item' => '{{RSSPost | title = {{{title}}} | link = {{{link}}} | date = {{{date}}} | author = {{{author}}} }}',
|
||||
);
|
||||
|
||||
$messages['qqq'] = array(
|
||||
'rss-item' => 'Do not translate',
|
||||
);
|
||||
|
||||
|
||||
/** Afrikaans (Afrikaans)
|
||||
* @author Naudefj
|
||||
*/
|
||||
|
|
|
|||
246
RSS.php
246
RSS.php
|
|
@ -42,7 +42,7 @@ $wgExtensionCredits['parserhook'][] = array(
|
|||
// Internationalization file and autoloadable classes
|
||||
$dir = dirname( __FILE__ ) . '/';
|
||||
$wgExtensionMessagesFiles['RSS'] = $dir . 'RSS.i18n.php';
|
||||
$wgAutoloadClasses['MagpieRSS'] = $dir . 'RSSParse.php';
|
||||
$wgAutoloadClasses['RSSData'] = $dir . 'RSSData.php';
|
||||
$wgAutoloadClasses['RSSCache'] = $dir . 'RSSCache.php';
|
||||
|
||||
$wgHooks['ParserFirstCallInit'][] = 'wfRssExtension';
|
||||
|
|
@ -55,51 +55,32 @@ function wfRssExtension( &$parser ) {
|
|||
}
|
||||
|
||||
# Parser hook callback function
|
||||
function renderRss( $input ) {
|
||||
global $wgOutputEncoding, $wgParser;
|
||||
function renderRss( $input, $args, $parser, $frame ) {
|
||||
global $wgOutputEncoding;
|
||||
|
||||
// Kill parser cache
|
||||
$wgParser->disableCache();
|
||||
$parser->disableCache();
|
||||
|
||||
if ( !$input ) {
|
||||
return ''; # if <rss>-section is empty, return nothing
|
||||
}
|
||||
|
||||
# Parse fields in rss section
|
||||
$fields = explode( '|', $input );
|
||||
wfSuppressWarnings();
|
||||
$url = $fields[0];
|
||||
wfRestoreWarnings();
|
||||
|
||||
$args = array();
|
||||
for ( $i = 1; $i < sizeof( $fields ); $i++ ) {
|
||||
$f = $fields[$i];
|
||||
|
||||
if ( strpos( $f, '=' ) === false ) {
|
||||
$args[strtolower( trim( $f ) )] = false;
|
||||
} else {
|
||||
list( $k, $v ) = explode( '=', $f, 2 );
|
||||
if ( trim( $v ) == false ) {
|
||||
$args[strtolower( trim( $k ) )] = false;
|
||||
} else {
|
||||
$args[strtolower( trim( $k ) )] = trim( $v );
|
||||
}
|
||||
}
|
||||
}
|
||||
$url = $input;
|
||||
|
||||
# Get charset from argument array
|
||||
wfSuppressWarnings();
|
||||
$charset = $args['charset'];
|
||||
wfRestoreWarnings();
|
||||
if( !$charset ) {
|
||||
if( isset( $args['charset'] ) ) {
|
||||
$charset = $args['charset'];
|
||||
} else {
|
||||
$charset = $wgOutputEncoding;
|
||||
}
|
||||
|
||||
# Get max number of headlines from argument-array
|
||||
wfSuppressWarnings();
|
||||
$maxheads = $args['max'];
|
||||
wfRestoreWarnings();
|
||||
$headcnt = 0;
|
||||
if( isset( $args['max'] ) ) {
|
||||
$maxheads = $args['max'];
|
||||
} else {
|
||||
$maxheads = 32;
|
||||
}
|
||||
|
||||
# Get short flag from argument array
|
||||
# If short is set, no description text is printed
|
||||
|
|
@ -111,52 +92,57 @@ function renderRss( $input ) {
|
|||
|
||||
# Get reverse flag from argument array
|
||||
if( isset( $args['reverse'] ) ) {
|
||||
$reverse = true;
|
||||
} else {
|
||||
$reverse = false;
|
||||
$rss->items = array_reverse( $rss->items );
|
||||
}
|
||||
|
||||
# Get date format from argument array
|
||||
if ( isset( $args['date'] ) ) {
|
||||
wfSuppressWarnings();
|
||||
$date = $args['date'];
|
||||
wfRestoreWarnings();
|
||||
if ( $date == '' ) {
|
||||
$date = 'd M Y H:i';
|
||||
}
|
||||
} else {
|
||||
$date = false;
|
||||
$date = 'd M Y H:i';
|
||||
}
|
||||
|
||||
# Get highlight terms from argument array
|
||||
wfSuppressWarnings();
|
||||
$rssHighlight = $args['highlight'];
|
||||
wfRestoreWarnings();
|
||||
$rssHighlight = str_replace( ' ', ' ', $rssHighlight );
|
||||
$rssHighlight = explode( ' ', trim( $rssHighlight ) );
|
||||
if( isset( $args['highlight'] ) ) {
|
||||
$rssHighlight = $args['highlight'];
|
||||
$rssHighlight = str_replace( ' ', ' ', $rssHighlight );
|
||||
$rssHighlight = explode( ' ', trim( $rssHighlight ) );
|
||||
} else {
|
||||
$rssHighlight = false;
|
||||
}
|
||||
|
||||
# Get filter terms from argument array
|
||||
wfSuppressWarnings();
|
||||
$rssFilter = $args['filter'];
|
||||
wfRestoreWarnings();
|
||||
$rssFilter = str_replace( ' ', ' ', $rssFilter );
|
||||
$rssFilter = explode( ' ', trim( $rssFilter ) );
|
||||
if( isset( $args['filter'] ) ) {
|
||||
$rssFilter = $args['filter'];
|
||||
$rssFilter = str_replace( ' ', ' ', $rssFilter );
|
||||
$rssFilter = explode( ' ', trim( $rssFilter ) );
|
||||
} else {
|
||||
$rssFilter = false;
|
||||
}
|
||||
|
||||
# Filterout terms
|
||||
wfSuppressWarnings();
|
||||
$rssFilterout = $args['filterout'];
|
||||
wfRestoreWarnings();
|
||||
$rssFilterout = str_replace( ' ', ' ', $rssFilterout );
|
||||
$rssFilterout = explode( ' ', trim( $rssFilterout ) );
|
||||
if( isset( $args['filterout'] ) ) {
|
||||
$rssFilterout = $args['filterout'];
|
||||
$rssFilterout = str_replace( ' ', ' ', $rssFilterout );
|
||||
$rssFilterout = explode( ' ', trim( $rssFilterout ) );
|
||||
} else {
|
||||
$rssFilterout = false;
|
||||
}
|
||||
|
||||
if( isset( $args['template'] ) ) {
|
||||
$template = 'Template:'.$args['template'];
|
||||
} else {
|
||||
$template = wfMsgNoTrans("rss-item");
|
||||
}
|
||||
|
||||
$headcnt = 0;
|
||||
|
||||
# Fetch RSS. May be cached locally.
|
||||
# Refer to the documentation of MagpieRSS for details.
|
||||
if ( !function_exists( 'fetch_rss' ) ) {
|
||||
include( dirname( __FILE__ ) . '/RSSFetch.php' ); // provides fetch_rss() function
|
||||
}
|
||||
wfSuppressWarnings();
|
||||
$rss = fetch_rss( $url );
|
||||
wfRestoreWarnings();
|
||||
|
||||
# Check for errors.
|
||||
if ( empty( $rss ) ) {
|
||||
|
|
@ -171,110 +157,50 @@ function renderRss( $input ) {
|
|||
return '<div>' . wfMsg( 'rss-empty', $url ) . '</div>';
|
||||
}
|
||||
|
||||
# Build title line
|
||||
#$title = iconv( $charset, $wgOutputEncoding, $rss->channel['title'] );
|
||||
#if( $rss->channel['link'] ) $title = "<a href='" . $rss->channel['link'] . "'>$title</a>";
|
||||
|
||||
$output = '';
|
||||
if( $reverse ) {
|
||||
$rss->items = array_reverse( $rss->items );
|
||||
}
|
||||
$description = false;
|
||||
foreach ( $rss->items as $item ) {
|
||||
if ( isset( $item['description'] ) && $item['description'] ) {
|
||||
$description = true;
|
||||
break;
|
||||
|
||||
/* This would be better served by preg_replace_callback, but
|
||||
* I can't create a callback that carries $item in PHP < 5.3
|
||||
*/
|
||||
if ( $template ) {
|
||||
$headcnt = 0;
|
||||
foreach( $rss->items as $item ) {
|
||||
if($maxheads > 0 && $headcnt >= $maxheads) continue;
|
||||
|
||||
$decision = true;
|
||||
foreach(array('title', 'author', 'description', 'category') as $check) {
|
||||
if( isset( $item[$check] ) ) {
|
||||
$decision &= wfRssFilter($item[$check], $rssFilter) & wfRssFilterout($item[$check], $rssFilterout);
|
||||
if( !$decision ) continue 2;
|
||||
|
||||
$item[$check] = wfRssHighlight( $item[$check], $rssHighlight );
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
$rssTemp = "";
|
||||
|
||||
foreach(explode("|", $template) as $bit) {
|
||||
$bits = explode("=", $bit);
|
||||
if( count($bits) == 2 ) {
|
||||
$left = trim($bits[0]);
|
||||
|
||||
if( isset( $item[$left] ) ) {
|
||||
$right = $item[$left];
|
||||
}
|
||||
|
||||
$rssTemp .= implode( " = ", array($left, $right) );
|
||||
} else {
|
||||
$rssTemp .= $bit;
|
||||
}
|
||||
$rssTemp .= "|";
|
||||
}
|
||||
$rssTemp .= "}}";
|
||||
|
||||
$output .= $parser->recursiveTagParse( $rssTemp, $frame );
|
||||
$headcnt++;
|
||||
}
|
||||
}
|
||||
|
||||
# Build items
|
||||
if ( !$short && $description ) { # full item list
|
||||
$output .= '<dl>';
|
||||
|
||||
foreach ( $rss->items as $item ) {
|
||||
$d_text = true;
|
||||
$d_title = true;
|
||||
|
||||
$href = htmlspecialchars( trim( iconv( $charset, $wgOutputEncoding, $item['link'] ) ) );
|
||||
$title = htmlspecialchars( trim( iconv( $charset, $wgOutputEncoding, $item['title'] ) ) );
|
||||
|
||||
if ( $date ) {
|
||||
$pubdate = trim( iconv( $charset, $wgOutputEncoding, $item['pubdate'] ) );
|
||||
$pubdate = date( $date, strtotime( $pubdate ) );
|
||||
}
|
||||
|
||||
$d_title = wfRssFilter( $title, $rssFilter );
|
||||
$d_title = wfRssFilterout( $title, $rssFilterout );
|
||||
$title = wfRssHighlight( $title, $rssHighlight );
|
||||
|
||||
# Build description text if desired
|
||||
if ( $item['description'] ) {
|
||||
$text = trim( iconv( $charset, $wgOutputEncoding, $item['description'] ) );
|
||||
# Avoid <pre> tags
|
||||
$text = str_replace( "\r", ' ', $text );
|
||||
$text = str_replace( "\n", ' ', $text );
|
||||
$text = str_replace( "\t", ' ', $text );
|
||||
$text = str_replace( '<br>', '', $text );
|
||||
|
||||
$d_text = wfRssFilter( $text, $rssFilter );
|
||||
$d_text = wfRssFilterout( $text, $rssFilterout );
|
||||
$text = wfRssHighlight( $text, $rssHighlight );
|
||||
$display = $d_text || $d_title;
|
||||
} else {
|
||||
$text = '';
|
||||
$display = $d_title;
|
||||
}
|
||||
if ( $display ) {
|
||||
$output.= "<dt><a href='$href'><b>$title</b></a></dt>";
|
||||
if ( $date ) {
|
||||
$output .= " ($pubdate)";
|
||||
}
|
||||
if ( $text ) {
|
||||
$output .= "<dd>$text <b>[<a href='$href'>?</a>]</b></dd>";
|
||||
}
|
||||
}
|
||||
# Cut off output when maxheads is reached:
|
||||
if ( ++$headcnt == $maxheads ) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
$output .= '</dl>';
|
||||
} else { # short item list
|
||||
## HACKY HACKY HACKY
|
||||
$output .= '<ul>';
|
||||
$displayed = array();
|
||||
foreach ( $rss->items as $item ) {
|
||||
$href = htmlspecialchars( trim( iconv( $charset, $wgOutputEncoding, $item['link'] ) ) );
|
||||
$title = htmlspecialchars( trim( iconv( $charset, $wgOutputEncoding, $item['title'] ) ) );
|
||||
$d_title = wfRssFilter( $title, $rssFilter ) && wfRssFilterout( $title, $rssFilterout );
|
||||
$title = wfRssHighlight( $title, $rssHighlight );
|
||||
if ( $date ) {
|
||||
$pubdate = isset( $item['pubdate'] ) ? trim( iconv( $charset, $wgOutputEncoding, $item['pubdate'] ) ) : '';
|
||||
if ( $pubdate == '' ) {
|
||||
$pubdate = trim( iconv( $charset, $wgOutputEncoding, $item['dc']['date'] ) );
|
||||
}
|
||||
$pubdate = date( $date, strtotime( $pubdate ) );
|
||||
}
|
||||
|
||||
if ( $d_title && !in_array( $title, $displayed ) ) {
|
||||
// Add date to ouput if specified
|
||||
$output .= '<li><a href="' . $href . '" title="' . $title . '">' . $title . '</a>';
|
||||
if( $date ) {
|
||||
$output .= " ($pubdate)";
|
||||
}
|
||||
$output .= '</li>';
|
||||
|
||||
$displayed[] = $title;
|
||||
# Cut off output when maxheads is reached:
|
||||
if ( ++$headcnt == $maxheads ) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
$output.= '</ul>';
|
||||
}
|
||||
|
||||
return $output;
|
||||
}
|
||||
|
||||
|
|
@ -343,4 +269,4 @@ function wfRssHighlight( $text, $rssHighlight ) {
|
|||
}
|
||||
|
||||
return $text;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -30,6 +30,14 @@ class RSSCache {
|
|||
);
|
||||
}
|
||||
}
|
||||
|
||||
// check if it is writable.
|
||||
if ( !is_writable( $this->BASE_CACHE ) ) {
|
||||
wfDebugLog(
|
||||
'RSS',
|
||||
"Cache dir '" . $this->BASE_CACHE . "' is not writable."
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
|
|||
61
RSSData.php
Normal file
61
RSSData.php
Normal file
|
|
@ -0,0 +1,61 @@
|
|||
<?php
|
||||
class RSSData {
|
||||
public $etag;
|
||||
public $last_modified;
|
||||
public $ERROR;
|
||||
public $xml;
|
||||
public $items;
|
||||
|
||||
function __construct( $resp ) {
|
||||
$this->xml = new DOMDocument;
|
||||
$this->xml->loadXML($resp->getContent());
|
||||
$h = $resp->getResponseHeader('ETag');
|
||||
$this->etag = $h;
|
||||
$h = $resp->getResponseHeader('Last-Modified');
|
||||
$this->last_modified = $h;
|
||||
|
||||
$xpath = new DOMXPath($this->xml);
|
||||
$items = $xpath->evaluate("/rss/channel/item");
|
||||
|
||||
foreach($items as $item) {
|
||||
$bit = array();
|
||||
foreach($item->childNodes as $n) {
|
||||
$name = $this->rssTokenToName($n->nodeName);
|
||||
if($name != null)
|
||||
$bit[$name] = $n->nodeValue;
|
||||
}
|
||||
var_dump(implode(":: ", array_keys($bit)));
|
||||
$this->items[] = $bit;
|
||||
}
|
||||
}
|
||||
|
||||
function rssTokenToName($n) {
|
||||
switch($n) {
|
||||
case "dc:date":
|
||||
return "date";
|
||||
# parse "2010-10-18T18:07:00Z"
|
||||
case "pubDate":
|
||||
return "date";
|
||||
# parse RFC date
|
||||
case "dc:creator":
|
||||
return "author";
|
||||
case "title":
|
||||
return "title";
|
||||
case "content:encoded":
|
||||
return "encodedContent";
|
||||
|
||||
case "slash:comments":
|
||||
case "slash:department":
|
||||
case "slash:section":
|
||||
case "slash:hit_parade":
|
||||
case "feedburner:origLink":
|
||||
case "wfw:commentRss":
|
||||
case "comments":
|
||||
case "category":
|
||||
return null;
|
||||
|
||||
default:
|
||||
return $n;
|
||||
}
|
||||
}
|
||||
}
|
||||
151
RSSFetch.php
151
RSSFetch.php
|
|
@ -10,26 +10,26 @@
|
|||
* Globals - redefine these in your script to change the
|
||||
* behaviour of fetch_rss() currently, most options effect the cache
|
||||
*
|
||||
* $wgMagpieRSSCache - Should Magpie cache parsed RSS objects?
|
||||
* $wgRSSCache - Should we cache parsed RSS objects?
|
||||
*
|
||||
* $wgMagpieRSSCacheDirectory - Where should Magpie cache parsed RSS objects?
|
||||
* $wgRSSCacheDirectory - Where should we cache parsed RSS objects?
|
||||
* This should be a location that the webserver can write to. If this
|
||||
* directory does not already exist, Magpie will try to be smart and create it.
|
||||
* directory does not already exist, We will try to be smart and create it.
|
||||
* This will often fail for permissions reasons.
|
||||
*
|
||||
* $wgMagpieRSSCacheAge - How long to store cached RSS objects (in seconds)?.
|
||||
* $wgRSSCacheAge - How long to store cached RSS objects (in seconds)?.
|
||||
*
|
||||
* $wgMagpieRSSCacheFreshOnly - If remote fetch fails, throw an error
|
||||
* $wgRSSCacheFreshOnly - If remote fetch fails, throw an error
|
||||
* instead of returning stale object?
|
||||
*/
|
||||
|
||||
$MAGPIE_ERROR = '';
|
||||
$RSS_FETCH_ERROR = '';
|
||||
|
||||
/**
|
||||
* Return RSS object for the given URL, maintaining caching.
|
||||
*
|
||||
* NOTES ON CACHING:
|
||||
* If caching is on ($wgMagpieRSSCache) fetch_rss will first check the cache.
|
||||
* If caching is on ($wgRSSCache) fetch_rss will first check the cache.
|
||||
*
|
||||
* NOTES ON RETRIEVING REMOTE FILES:
|
||||
* If conditional gets are on (MAGPIE_CONDITIONAL_GET_ON) fetch_rss will
|
||||
|
|
@ -37,29 +37,32 @@ $MAGPIE_ERROR = '';
|
|||
*
|
||||
* NOTES ON FAILED REQUESTS:
|
||||
* If there is an HTTP error while fetching an RSS object, the cached version
|
||||
* will be returned, if it exists (and if $wgMagpieRSSCacheFreshOnly is off)
|
||||
* will be returned, if it exists (and if $wgRSSCacheFreshOnly is off)
|
||||
*
|
||||
* @param $url String: URL of RSS file
|
||||
* @return parsed RSS object (see RSSParse)
|
||||
*/
|
||||
function fetch_rss( $url ) {
|
||||
global $wgMagpieRSSCache, $wgMagpieRSSCacheAge, $wgMagpieRSSCacheFreshOnly;
|
||||
global $wgMagpieRSSCacheDirectory, $wgMagpieRSSFetchTimeout;
|
||||
global $wgMagpieRSSOutputEncoding, $wgMagpieRSSInputEncoding;
|
||||
global $wgMagpieRSSDetectEncoding, $wgMagpieRSSUseGzip;
|
||||
global $wgRSSCache, $wgRSSCacheAge, $wgRSSCacheFreshOnly;
|
||||
global $wgRSSCacheDirectory, $wgRSSFetchTimeout;
|
||||
global $wgRSSOutputEncoding, $wgRSSInputEncoding;
|
||||
global $wgRSSDetectEncoding, $wgRSSUseGzip;
|
||||
|
||||
$wgMagpieRSSCache = true;
|
||||
$wgMagpieRSSCacheAge = 60 * 60; // one hour
|
||||
$wgMagpieRSSCacheFreshOnly = false;
|
||||
$wgMagpieRSSCacheDirectory = '/extensions/RSS/cache';
|
||||
$wgMagpieRSSOutputEncoding = 'ISO-8859-1';
|
||||
$wgMagpieRSSInputEncoding = null;
|
||||
$wgMagpieRSSDetectEncoding = true;
|
||||
$nameValue = array('wgRSSCache' => true,
|
||||
'wgRSSCacheAge' => 60 * 60, // one hour
|
||||
'wgRSSCacheFreshOnly' => false,
|
||||
'wgRSSCacheDirectory' => '/extensions/RSS/cache',
|
||||
'wgRSSOutputEncoding' => 'ISO-8859-1',
|
||||
'wgRSSInputEncoding' => null,
|
||||
'wgRSSDetectEncoding' => true,
|
||||
'wgRSSFetchTimeout' => 5, // 5 second timeout
|
||||
'wgRSSUseGzip' => true);
|
||||
|
||||
$wgMagpieRSSFetchTimeout = 5; // 5 second timeout
|
||||
|
||||
// use gzip encoding to fetch RSS files if supported?
|
||||
$wgMagpieRSSUseGzip = true;
|
||||
foreach($nameValue as $n => $v) {
|
||||
if( !isset( $GLOBALS[$n] ) ) {
|
||||
$GLOBALS[$n] = $v;
|
||||
}
|
||||
}
|
||||
|
||||
if ( !isset( $url ) ) {
|
||||
wfDebugLog( 'RSS', 'fetch_rss (RSSFetch.php) called without a URL!' );
|
||||
|
|
@ -67,10 +70,11 @@ function fetch_rss( $url ) {
|
|||
}
|
||||
|
||||
// if cache is disabled
|
||||
if ( !$wgMagpieRSSCache ) {
|
||||
if ( !$wgRSSCache ) {
|
||||
// fetch file, and parse it
|
||||
$resp = _fetch_remote_file( $url );
|
||||
if ( $resp->status >= 200 && $resp->status < 300 ) {
|
||||
$errs = $resp->getErrorsArray();
|
||||
if ( count( $errs ) == 0 ) {
|
||||
return _response_to_rss( $resp );
|
||||
} else {
|
||||
wfDebugLog( 'RSS', "Failed to fetch $url and cache is off" );
|
||||
|
|
@ -82,12 +86,12 @@ function fetch_rss( $url ) {
|
|||
// 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( $wgMagpieRSSCacheDirectory, $wgMagpieRSSCacheAge );
|
||||
$cache = new RSSCache( $wgRSSCacheDirectory, $wgRSSCacheAge );
|
||||
|
||||
if ( $cache->ERROR ) {
|
||||
wfDebugLog(
|
||||
'RSS',
|
||||
'MagpieRSS: cache error on RSSFetch.php! Error msg: ' .
|
||||
'cache error on RSSFetch.php! Error msg: ' .
|
||||
$cache->ERROR
|
||||
);
|
||||
}
|
||||
|
|
@ -99,7 +103,7 @@ function fetch_rss( $url ) {
|
|||
|
||||
// store parsed XML by desired output encoding
|
||||
// as character munging happens at parse time
|
||||
$cache_key = $url . $wgMagpieRSSOutputEncoding;
|
||||
$cache_key = $url . $wgRSSOutputEncoding;
|
||||
|
||||
if ( !$cache->ERROR ) {
|
||||
// return cache HIT, MISS, or STALE
|
||||
|
|
@ -112,7 +116,7 @@ function fetch_rss( $url ) {
|
|||
if ( isset( $rss ) && $rss ) {
|
||||
// should be cache age
|
||||
$rss->from_cache = 1;
|
||||
wfDebugLog( 'RSS', 'MagpieRSS: Cache HIT' );
|
||||
wfDebugLog( 'RSS', 'Cache HIT' );
|
||||
return $rss;
|
||||
}
|
||||
}
|
||||
|
|
@ -128,16 +132,17 @@ function fetch_rss( $url ) {
|
|||
}
|
||||
}
|
||||
|
||||
var_dump($request_headers);
|
||||
$resp = _fetch_remote_file( $url, $request_headers );
|
||||
|
||||
if ( isset( $resp ) && $resp ) {
|
||||
if ( $resp->status == '304' ) {
|
||||
if ( $resp->getStatus() === 304 ) {
|
||||
// we have the most current copy
|
||||
wfDebugLog( 'RSS', "Got 304 for $url" );
|
||||
// reset cache on 304 (at minutillo insistent prodding)
|
||||
$cache->set( $cache_key, $rss );
|
||||
return $rss;
|
||||
} elseif ( $resp->status >= 200 && $resp->status < 300 ) {
|
||||
} elseif ( $resp->getStatus() >= 200 && $resp->getStatus() < 300 ) {
|
||||
$rss = _response_to_rss( $resp );
|
||||
if ( $rss ) {
|
||||
wfDebugLog( 'RSS', 'Fetch successful' );
|
||||
|
|
@ -147,12 +152,10 @@ function fetch_rss( $url ) {
|
|||
}
|
||||
} else {
|
||||
$errormsg = "Failed to fetch $url ";
|
||||
if ( $resp->status == '-100' ) {
|
||||
global $wgMagpieRSSFetchTimeout;
|
||||
$errormsg .= '(Request timed out after ' . $wgMagpieRSSFetchTimeout . ' seconds)';
|
||||
if ( $resp->getStatus() === -100 ) {
|
||||
global $wgRSSFetchTimeout;
|
||||
$errormsg .= '(Request timed out after ' . $wgRSSFetchTimeout . ' 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 {
|
||||
|
|
@ -172,38 +175,47 @@ function fetch_rss( $url ) {
|
|||
}
|
||||
|
||||
// else we totally failed
|
||||
$MAGPIE_ERROR = $errormsg;
|
||||
$RSS_FETCH_ERROR = $errormsg;
|
||||
wfDebugLog(
|
||||
'MagpieRSS (RSSFetch): we totally failed :-( Error message:' .
|
||||
'RSSFetch: we totally failed :-( Error message:' .
|
||||
$errormsg
|
||||
);
|
||||
|
||||
return false;
|
||||
} // end if ( !$wgMagpieRSSCache ) {
|
||||
} // end if ( !$wgRSSCache ) {
|
||||
} // end fetch_rss()
|
||||
|
||||
/**
|
||||
* Retrieve an arbitrary remote file.
|
||||
* @param $url String: URL of the remote file
|
||||
* @param $headers Array: headers to send along with the request
|
||||
* @return an HTTP response object (see Snoopy.class.php)
|
||||
* @return an HTTP response object
|
||||
*/
|
||||
function _fetch_remote_file( $url, $headers = '' ) {
|
||||
global $wgMagpieRSSFetchTimeout, $wgMagpieRSSUseGzip;
|
||||
// Snoopy is an HTTP client in PHP
|
||||
if ( !class_exists( 'Snoopy', false ) ) {
|
||||
require_once( dirname( __FILE__ ) . '/Snoopy.class.php' );
|
||||
}
|
||||
$client = new Snoopy();
|
||||
$client->agent = 'MagpieRSS/0.72 (+http://magpierss.sourceforge.net) / MediaWiki RSS extension';
|
||||
$client->read_timeout = $wgMagpieRSSFetchTimeout;
|
||||
$client->use_gzip = $wgMagpieRSSUseGzip;
|
||||
if ( is_array( $headers ) ) {
|
||||
$client->rawheaders = $headers;
|
||||
global $wgRSSFetchTimeout, $wgRSSUseGzip;
|
||||
|
||||
$client =
|
||||
HttpRequest::factory($url, array('timeout' => $wgRSSFetchTimeout));
|
||||
$client->setUserAgent('MediawikiRSS/0.01 (+http://www.mediawiki.org/wiki/Extension:RSS) / MediaWiki RSS extension');
|
||||
/* $client->use_gzip = $wgRSSUseGzip; */
|
||||
if ( is_array( $headers ) && count( $headers ) > 0 ) {
|
||||
foreach($headers as $h) {
|
||||
if( count( $h ) > 1 ) {
|
||||
$client->setHeader($h[0], $h[1]);
|
||||
} else {
|
||||
var_dump($h);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@$client->fetch( $url );
|
||||
return $client;
|
||||
$fetch = $client->execute();
|
||||
|
||||
/* @$client->fetch( $url ); */
|
||||
if( $fetch->isGood() ) {
|
||||
return $client;
|
||||
} else {
|
||||
wfDebugLog( 'RSS', 'error fetching $url: ' . $fetch->getMessage() );
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
@ -212,45 +224,24 @@ function _fetch_remote_file( $url, $headers = '' ) {
|
|||
* @return parsed RSS object (see RSSParse) or false
|
||||
*/
|
||||
function _response_to_rss( $resp ) {
|
||||
global $wgMagpieRSSOutputEncoding, $wgMagpieRSSInputEncoding, $wgMagpieRSSDetectEncoding;
|
||||
$rss = new MagpieRSS(
|
||||
$resp->results,
|
||||
$wgMagpieRSSOutputEncoding,
|
||||
$wgMagpieRSSInputEncoding,
|
||||
$wgMagpieRSSDetectEncoding
|
||||
);
|
||||
global $wgRSSOutputEncoding, $wgRSSInputEncoding, $wgRSSDetectEncoding;
|
||||
$rss = new RSSData($resp);
|
||||
|
||||
// if RSS parsed successfully
|
||||
if ( $rss && !$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 { // else construct error message
|
||||
$errormsg = 'Failed to parse RSS file.';
|
||||
$errormsg = 'Failed to parsex RSS file.';
|
||||
|
||||
if ( $rss ) {
|
||||
$errormsg .= ' (' . $rss->ERROR . ')';
|
||||
}
|
||||
$MAGPIE_ERROR = $errormsg;
|
||||
$RSS_FETCH_ERROR = $errormsg;
|
||||
wfDebugLog( 'RSS', 'error!' . $errormsg );
|
||||
|
||||
return false;
|
||||
} // end if ( $rss && !$rss->ERROR )
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
494
RSSParse.php
494
RSSParse.php
|
|
@ -1,494 +0,0 @@
|
|||
<?php
|
||||
/**
|
||||
* Hybrid parser, and object, takes RSS or Atom feed as a string and returns a
|
||||
* simple object.
|
||||
* Handles RSS 0.9x, RSS 2.0, RSS 1.0, and Atom 0.3
|
||||
*
|
||||
* @file
|
||||
* @see RSSFetch.php for a simpler interface with integrated caching support
|
||||
*/
|
||||
class MagpieRSS {
|
||||
public $parser;
|
||||
|
||||
public $current_item = array(); // item currently being parsed
|
||||
public $items = array(); // collection of parsed items
|
||||
public $channel = array(); // hash of channel fields
|
||||
public $textinput = array();
|
||||
public $image = array();
|
||||
public $feed_type;
|
||||
public $feed_version;
|
||||
public $encoding = ''; // output encoding of parsed rss
|
||||
|
||||
public $_source_encoding = ''; // only set if we have to parse xml prolog
|
||||
|
||||
public $ERROR = '';
|
||||
public $WARNING = '';
|
||||
|
||||
// define some constants
|
||||
public $_CONTENT_CONSTRUCTS = array( 'content', 'summary', 'info', 'title', 'tagline', 'copyright' );
|
||||
public $_KNOWN_ENCODINGS = array( 'UTF-8', 'US-ASCII', 'ISO-8859-1' );
|
||||
|
||||
// parser variables, useless if you're not a parser, treat as private
|
||||
public $stack = array(); // parser stack
|
||||
public $inchannel = false;
|
||||
public $initem = false;
|
||||
public $incontent = false; // if in Atom <content mode="xml"> field
|
||||
public $intextinput = false;
|
||||
public $inimage = false;
|
||||
public $current_namespace = false;
|
||||
|
||||
/**
|
||||
* Set up XML parser, parse source, and return populated RSS object..
|
||||
*
|
||||
* @param $source String: 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 $output_encoding String: 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 $input_encoding String: the character set of the incoming RSS source.
|
||||
* Leave blank and Magpie will try to figure it
|
||||
* out.
|
||||
*
|
||||
* @param $detect_encoding Boolean: if false, Magpie won't attempt to
|
||||
* detect source encoding. (caveat emptor)
|
||||
*/
|
||||
function __construct( $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 && $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' || $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' &&
|
||||
$this->current_namespace == '' &&
|
||||
$el == 'textinput' )
|
||||
{
|
||||
$this->intextinput = true;
|
||||
} elseif (
|
||||
$this->feed_type == 'RSS' &&
|
||||
$this->current_namespace == '' &&
|
||||
$el == 'image' )
|
||||
{
|
||||
$this->inimage = true;
|
||||
}
|
||||
|
||||
// handle Atom content constructs
|
||||
elseif ( $this->feed_type == 'Atom' && 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' && $this->incontent ) {
|
||||
// if tags are inlined, then flatten
|
||||
$attrs_str = join(
|
||||
' ',
|
||||
array_map(
|
||||
array( 'MagpieRSS', 'mapAttributes' ),
|
||||
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' && $el == 'link' ) {
|
||||
if ( isset( $attrs['rel'] ) && $attrs['rel'] == 'alternate' ) {
|
||||
$link_el = 'link';
|
||||
} else {
|
||||
$link_el = 'link_' . $attrs['rel'];
|
||||
}
|
||||
|
||||
$this->append( $link_el, $attrs['href'] );
|
||||
} else { // set stack[0] to current element
|
||||
array_unshift( $this->stack, $el );
|
||||
}
|
||||
}
|
||||
|
||||
function feed_cdata( $p, $text ) {
|
||||
if ( $this->feed_type == 'Atom' && $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' || $el == 'entry' ) {
|
||||
$this->items[] = $this->current_item;
|
||||
$this->current_item = array();
|
||||
$this->initem = false;
|
||||
} elseif ( $this->feed_type == 'RSS' && $this->current_namespace == '' && $el == 'textinput' ) {
|
||||
$this->intextinput = false;
|
||||
} elseif ( $this->feed_type == 'RSS' && $this->current_namespace == '' && $el == 'image' ) {
|
||||
$this->inimage = false;
|
||||
} elseif ( $this->feed_type == 'Atom' && in_array( $el, $this->_CONTENT_CONSTRUCTS ) ) {
|
||||
$this->incontent = false;
|
||||
} elseif ( $el == 'channel' || $el == 'feed' ) {
|
||||
$this->inchannel = false;
|
||||
} elseif ( $this->feed_type == 'Atom' && $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 ) {
|
||||
$epoch = @$this->parse_w3cdtf( $atom_date );
|
||||
if ( $epoch && $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' && isset( $item['dc']['date'] ) ) {
|
||||
$epoch = @$this->parse_w3cdtf( $item['dc']['date'] );
|
||||
if ( $epoch && $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;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Instantiate an XML parser.
|
||||
* @return XML parser, and possibly re-encoded source
|
||||
*/
|
||||
function create_parser( $source, $out_enc, $in_enc, $detect ) {
|
||||
// by default PHP5 does a fine job of detecting input encodings
|
||||
if( !$detect && $in_enc ) {
|
||||
$parser = xml_parser_create( $in_enc );
|
||||
} else {
|
||||
$parser = xml_parser_create( '' );
|
||||
}
|
||||
if ( $out_enc ) {
|
||||
$this->encoding = $out_enc;
|
||||
xml_parser_set_option(
|
||||
$parser,
|
||||
XML_OPTION_TARGET_ENCODING,
|
||||
$out_enc
|
||||
);
|
||||
}
|
||||
|
||||
return array( $parser, $source );
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if $enc is an encoding type supported by MagpieRSS.
|
||||
* @param $enc String: encoding name
|
||||
* @return String or false
|
||||
*/
|
||||
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 is enabled
|
||||
if ( isset( $php_errormsg ) ) {
|
||||
$errormsg .= " ($php_errormsg)";
|
||||
}
|
||||
|
||||
$notices = E_USER_NOTICE|E_NOTICE;
|
||||
if ( $lvl&$notices ) {
|
||||
$this->WARNING = $errormsg;
|
||||
} else {
|
||||
$this->ERROR = $errormsg;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Parse a W3CDTF date into unix epoch.
|
||||
* This used to be in its own file.
|
||||
* @note http://www.w3.org/TR/NOTE-datetime
|
||||
* @param $date_str String: date string to parse
|
||||
* @return Integer
|
||||
*/
|
||||
public static 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] );
|
||||
|
||||
// calculate 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;
|
||||
}
|
||||
}
|
||||
|
||||
public static function mapAttributes( $k, $v ) {
|
||||
return "$k=\"$v\"";
|
||||
}
|
||||
|
||||
} // end class MagpieRSS
|
||||
1241
Snoopy.class.php
1241
Snoopy.class.php
File diff suppressed because it is too large
Load diff
Loading…
Reference in a new issue