cuqmbr/rss-bridge
1
0
Fork 0
mirror of https://github.com/RSS-Bridge/rss-bridge.git synced 2025-04-04 16:49:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

FeedExpander: Remove tailing content in XML

Browse Source 
- Move preprocessing code into overridable preprocessXml()
- Auto-remove trailing data after root xml node
This commit is contained in:
ORelio 2025-03-20 15:11:32 +01:00
parent dee734d360
commit c7b5a3f5b3
1 changed files with 37 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
lib/FeedExpander.php
View File

@ -22,14 +22,7 @@ abstract class FeedExpander extends BridgeAbstract
if ($xmlString === '') {
throw new \Exception(sprintf('Unable to parse xml from `%s` because we got the empty string', $url), 10);
}
// prepare/massage the xml to make it more acceptable
$problematicStrings = [
' ',
'»',
'’',
];
$xmlString = str_replace($problematicStrings, '', $xmlString);
$xmlString = $this->prepareXml($xmlString);
$feedParser = new FeedParser();
try {
$this->feed = $feedParser->parseFeed($xmlString);
@ -59,6 +52,42 @@ abstract class FeedExpander extends BridgeAbstract
return $item;
}
/**
* Prepare XML document to make it more acceptable by the parser
* This method can be overriden by bridges to change this behavior
*
* @return string
*/
protected function prepareXml($xmlString)
{
// Remove problematic escape sequences
$problematicStrings = [
' ',
'»',
'’',
];
$xmlString = str_replace($problematicStrings, '', $xmlString);
// Remove extra content at the end of the document, if any.
// First retrieve tag name of root node, which is the first node following <?xml prolog,
// Then find the last matching </tag> in xml string and strip anything beyond that.
if (preg_match('/(?:<\?xml[^>]*\?>[^<]*<)([^ "\'>]+)/i', $xmlString, $matches) === 1)
{
$root_node_tag = $matches[1];
$last_closing_occurrence = strripos($xmlString, '</' . $root_node_tag);
if ($last_closing_occurrence !== false)
{
$closing_node_end = strpos($xmlString, '>', $last_closing_occurrence);
if ($closing_node_end !== false)
{
$xmlString = substr($xmlString, 0, $closing_node_end + 1);
}
}
}
return $xmlString;
}
public function getURI()
{
return $this->feed['uri'] ?? parent::getURI();