Skip to content

Fix: Analysis of relative links (Node.php) #13

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
Grotax merged 3 commits into from
Aug 13, 2025
Merged

Fix: Analysis of relative links (Node.php) #13

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
65842dc
Fix: Analysis of relative links (Node.php)
IgorA100 Dec 23, 2024
29601f3
add changelog entry
Grotax Jul 5, 2025
33ba99f
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. (#12)


### Fixed

- Fix: Analysis of relative links for the Atom feed (#13)
61 changes: 45 additions & 16 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 All @@ -152,29 +167,43 @@ protected function setHost(string $link = null): void

protected function setHostInContent(string $host = null): void
{
if (property_exists($this, 'content')){
if (!is_null($host) && !is_null($this->content)) {
$this->content = preg_replace('!(<*\s*[^>]*)(href=)(.?)(\/[^\/])!','\1 href=\3'.$host.'\4', $this->content );
$this->content = preg_replace('!(<*\s*[^>]*)(src=)(.?)(\/[^\/])!','\1 src=\3'.$host.'\4', $this->content );
}
if (is_null($host)) {
return;
}
if (property_exists($this, 'description')){
if (!is_null($host) && !is_null($this->description)) {
$this->description = preg_replace('!(<*\s*[^>]*)(href=)(.?)(\/[^\/])!','\1 href=\3'.$host.'\4', $this->description );
$this->description = preg_replace('!(<*\s*[^>]*)(src=)(.?)(\/[^\/])!','\1 src=\3'.$host.'\4', $this->description );
}
// Replaced links like href="/aaa/bbb.xxx"
$pattern = '(<\s*[^>]*)(href=|src=)(.?)(\/[^\/])(?!(.(?!<code))*<\/code>)';
$this->pregReplaceInProperty('content', $pattern, '\1\2\3'.$host.'\4');
$this->pregReplaceInProperty('description', $pattern, '\1\2\3'.$host.'\4');

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

// Replaced links like href="#aaa/bbb.xxx"
$pattern = '(<\s*[^>]*)(href=|src=)(.?)(#)(?!(.(?!<code))*<\/code>)';
$this->pregReplaceInProperty('content', $pattern, '\1\2\3'.$itemFullLink.'\4');
$this->pregReplaceInProperty('description', $pattern, '\1\2\3'.$itemFullLink.'\4');

// Replaced links like href="aaa/bbb.xxx"
$pattern = '(<\s*[^>]*)(href=|src=)(.?)(\w+\b)(?![:])(?!(.(?!<code))*<\/code>)';
$this->pregReplaceInProperty('content', $pattern, '\1\2\3'.$itemLink.'\4');
$this->pregReplaceInProperty('description', $pattern, '\1\2\3'.$itemLink.'\4');
}

public function pregReplaceInProperty(string $property, string $pattern, string $replacement): void
{
if (property_exists($this, $property) && !is_null($this->{$property})) {
$this->{$property} = preg_replace('~'.$pattern.'~', $replacement, $this->{$property}) ?? $this->{$property};
}
}

public function getHostFromLink(): ?string
{
if (!is_null($this->getLink())) {
$partsUrl = parse_url($this->getLink());
$result = $partsUrl['scheme']."://".$partsUrl['host'];
} else
$result = null;
if (is_null($this->getLinkForAnalysis())) {
return null;
}
$partsUrl = parse_url($this->getLinkForAnalysis());

return $result;
return $partsUrl['scheme']."://".$partsUrl['host'];
}

public function getValue(string $name): ?string
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());
}
}