Skip to content

[5.3] Fix: Analysis of relative links for the Atom feed #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jul 12, 2025
+187 −7
Merged

[5.3] Fix: Analysis of relative links for the Atom feed #10

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c7a47a9
Cannot use the "Link" object to analyze relative links
IgorA100 Dec 22, 2024
5583866
add changelog entry
Grotax Jul 5, 2025
d182689
make sure href starts with /
Grotax Jul 5, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,5 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed
- Add logic to set the node's link from the <guid> element when isPermaLink="true" and no link is present. (#8)


### Fixed

- Fix: Analysis of relative links for the Atom feed (#10)
22 changes: 19 additions & 3 deletions src/FeedIo/Feed/Node.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,8 @@ class Node implements NodeInterface, ElementsAwareInterface, ArrayableInterface

protected ?string $host = null;

protected ?string $linkForAnalysis = null;

public function __construct()
{
$this->initElements();
Expand Down Expand Up @@ -135,10 +137,23 @@ public function getLink(): ?string
return $this->link;
}

public function getLinkForAnalysis(): ?string
{
return $this->linkForAnalysis;
}

public function setLink(string $link = null): NodeInterface
{
$this->link = $link;
$this->setHost($link);
$this->setLinkForAnalysis($link);

return $this;
}

public function setLinkForAnalysis(string $link = null): NodeInterface
{
$this->linkForAnalysis = $link;

return $this;
}
Expand Down Expand Up @@ -168,7 +183,8 @@ protected function setHostInContent(string $host = null): void
return;
}

$itemLink = implode("/", array_slice(explode("/", $itemFullLink), 0, -1))."/";
$itemFullLink = $this->getLinkForAnalysis();
Copy link

Copilot AI Jul 5, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If linkForAnalysis is null, calling explode() on it below will raise a warning. Add an explicit null check before using it, or coerce to an empty string.

Suggested change
$itemFullLink = $this->getLinkForAnalysis();
$itemFullLink = $this->getLinkForAnalysis();
if (is_null($itemFullLink)) {
$itemFullLink = ''; // Coerce to an empty string to avoid runtime errors
}

Copilot uses AI. Check for mistakes.
$itemLink = implode("/", array_slice(explode("/", $itemFullLink ?? ''), 0, -1))."/";

// Replaced links like href="#aaa/bbb.xxx"
$pattern = '(<\s*[^>]*)(href=|src=)(.?)(#)(?!(.(?!<code))*<\/code>)';
Expand All @@ -190,10 +206,10 @@ public function pregReplaceInProperty(string $property, string $pattern, string

public function getHostFromLink(): ?string
{
if (is_null($this->getLink())) {
if (is_null($this->getLinkForAnalysis())) {
return null;
}
$partsUrl = parse_url($this->getLink());
$partsUrl = parse_url($this->getLinkForAnalysis());

return $partsUrl['scheme']."://".$partsUrl['host'];
}
Expand Down
3 changes: 2 additions & 1 deletion src/FeedIo/Parser/XmlParser.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,8 @@ protected function handleNode(NodeInterface $item, DOMElement $node, RuleSet $ru
{
if ($this->isItem($node->tagName) && $item instanceof FeedInterface) {
$linkItem = $item->getLink();
$newItem = $this->parseNode($item->newItem()->setLink($linkItem), $node, $this->getItemRuleSet());
$newItem = $this->parseNode($item->newItem()->setLinkForAnalysis($linkItem), $node, $this->getItemRuleSet());

$this->addValidItem($item, $newItem);
} else {
$rule = $ruleSet->get($node->tagName);
Expand Down
13 changes: 12 additions & 1 deletion src/FeedIo/Rule/Atom/Link.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,18 @@ protected function selectAlternateLink(NodeInterface $node, \DOMElement $element
($element->hasAttribute('rel') && $element->getAttribute('rel') == 'alternate')
|| is_null($node->getLink())
) {
$node->setLink($element->getAttribute('href'));
$href = $element->getAttribute('href');
if (parse_url($href, PHP_URL_HOST) == null) {
$baseUrl = $node->getHostFromLink();
if ($baseUrl !== null) {
// Add slash if href doesn't start with one
if (!str_starts_with($href, '/')) {
$href = '/' . $href;
}
$href = $baseUrl . $href;
}
}
$node->setLink($href);
}
}

Expand Down
153 changes: 153 additions & 0 deletions tests/FeedIo/Rule/Atom/LinkTest.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,4 +60,157 @@ public function testCreateElement()
$document->saveXML()
);
}

public function testRelativeHrefWithoutLeadingSlash()
{
$item = new Item();
$item->setLink('https://example.com/some/path.html');
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', 'page.html');
$link->setAttribute('rel', 'alternate');
$this->object->setProperty($item, $link);

$this->assertEquals('https://example.com/page.html', $item->getLink());
}

public function testRelativeHrefWithLeadingSlash()
{
$item = new Item();
$item->setLink('https://example.com/some/path.html');
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', '/absolute/path.html');
$link->setAttribute('rel', 'alternate');
$this->object->setProperty($item, $link);

$this->assertEquals('https://example.com/absolute/path.html', $item->getLink());
}

public function testAbsoluteHrefIsNotModified()
{
$item = new Item();
$item->setLink('https://example.com/some/path.html');
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', 'https://other.com/page.html');
$link->setAttribute('rel', 'alternate');
$this->object->setProperty($item, $link);

$this->assertEquals('https://other.com/page.html', $item->getLink());
}

public function testNonAlternateLinkIsIgnored()
{
$item = new Item();
$item->setLink('https://example.com/original.html');
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', '/new/path.html');
$link->setAttribute('rel', 'stylesheet');
$this->object->setProperty($item, $link);

$this->assertEquals('https://example.com/original.html', $item->getLink());
}

public function testLinkWithoutRelAttributeWhenNodeLinkIsNull()
{
$item = new Item();
$item->setLink(null);
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', '/path.html');
$this->object->setProperty($item, $link);

$this->assertEquals('/path.html', $item->getLink());
}

public function testLinkWithNullBaseUrl()
{
$item = new Item();
$item->setLink(null);
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', 'relative.html');
$link->setAttribute('rel', 'alternate');
$this->object->setProperty($item, $link);

$this->assertEquals('relative.html', $item->getLink());
}

public function testProtocolRelativeUrl()
{
$item = new Item();
$item->setLink('https://example.com/path.html');
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', '//cdn.example.com/resource.css');
$link->setAttribute('rel', 'alternate');
$this->object->setProperty($item, $link);

$this->assertEquals('//cdn.example.com/resource.css', $item->getLink());
}

public function testFragmentUrl()
{
$item = new Item();
$item->setLink('https://example.com/page.html');
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', '#section1');
$link->setAttribute('rel', 'alternate');
$this->object->setProperty($item, $link);

$this->assertEquals('https://example.com/#section1', $item->getLink());
}

public function testQueryParameterUrl()
{
$item = new Item();
$item->setLink('https://example.com/page.html');
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', '?param=value');
$link->setAttribute('rel', 'alternate');
$this->object->setProperty($item, $link);

$this->assertEquals('https://example.com/?param=value', $item->getLink());
}

public function testHttpScheme()
{
$item = new Item();
$item->setLink('http://example.com/path.html');
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', '/secure/path.html');
$link->setAttribute('rel', 'alternate');
$this->object->setProperty($item, $link);

$this->assertEquals('http://example.com/secure/path.html', $item->getLink());
}

public function testEmptyHref()
{
$item = new Item();
$item->setLink('https://example.com/original.html');
$document = new \DOMDocument();

$link = $document->createElement('link');
$link->setAttribute('href', '');
$link->setAttribute('rel', 'alternate');
$this->object->setProperty($item, $link);

$this->assertEquals('https://example.com/', $item->getLink());
}
}