Skip to content

Iterate node lists with foreach #90

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 4 commits into from
Oct 11, 2024
Merged

Iterate node lists with foreach #90

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5885dbb
Remove pointless `stdClass`
jtojnar Mar 16, 2024
8b1ef07
Extract `for`-iterated items into variables
jtojnar Mar 17, 2024
d454c3a
Remove dead iteration code
jtojnar Mar 17, 2024
9a9373d
Iterate node lists with `foreach`
jtojnar Mar 16, 2024
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
51 changes: 22 additions & 29 deletions src/Readability.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -302,8 +302,7 @@ public function addFootnotes(\DOMElement $articleContent): void
$articleLinks = $articleContent->getElementsByTagName('a');
$linkCount = 0;

for ($i = 0; $i < $articleLinks->length; ++$i) {
$articleLink = $articleLinks->item($i);
foreach ($articleLinks as $articleLink) {
$footnoteLink = $articleLink->cloneNode(true);
$refLink = $this->dom->createElement('a');
$footnote = $this->dom->createElement('li');
Expand Down Expand Up @@ -383,8 +382,8 @@ public function prepArticle(\DOMNode $articleContent): void

// Remove service data-candidate attribute.
$elems = $xpath->query('.//*[@data-candidate]', $articleContent);
for ($i = $elems->length - 1; $i >= 0; --$i) {
$elems->item($i)->removeAttribute('data-candidate');
foreach ($elems as $elem) {
$elem->removeAttribute('data-candidate');
}

// Clean out junk from the article content.
Expand Down Expand Up @@ -520,11 +519,12 @@ public function getLinkDensity(\DOMElement $e, bool $excludeExternal = false): f
$textLength = mb_strlen($this->getInnerText($e, true, true));
$linkLength = 0;

for ($dRe = $this->domainRegExp, $i = 0, $il = $links->length; $i < $il; ++$i) {
if ($excludeExternal && $dRe && !preg_match($dRe, $links->item($i)->getAttribute('href'))) {
$dRe = $this->domainRegExp;
foreach ($links as $link) {
if ($excludeExternal && $dRe && !preg_match($dRe, $link->getAttribute('href'))) {
continue;
}
$linkLength += mb_strlen($this->getInnerText($links->item($i)));
$linkLength += mb_strlen($this->getInnerText($link));
}

if ($textLength > 0 && $linkLength > 0) {
Expand Down Expand Up @@ -586,7 +586,7 @@ public function clean(\DOMElement $e, string $tag): void
}

// Then check the elements inside this element for the same.
if (preg_match($this->regexps['media'], $targetList->item($y)->getInnerHTML())) {
if (preg_match($this->regexps['media'], $currentItem->getInnerHTML())) {
continue;
}
}
Expand Down Expand Up @@ -640,15 +640,15 @@ public function cleanConditionally(\DOMElement $e, string $tag): void
$embedCount = 0;
$embeds = $node->getElementsByTagName('embed');

for ($ei = 0, $il = $embeds->length; $ei < $il; ++$ei) {
if (preg_match($this->regexps['media'], $embeds->item($ei)->getAttribute('src'))) {
foreach ($embeds as $embed) {
if (preg_match($this->regexps['media'], $embed->getAttribute('src'))) {
++$embedCount;
}
}

$embeds = $node->getElementsByTagName('iframe');
for ($ei = 0, $il = $embeds->length; $ei < $il; ++$ei) {
if (preg_match($this->regexps['media'], $embeds->item($ei)->getAttribute('src'))) {
foreach ($embeds as $embed) {
if (preg_match($this->regexps['media'], $embed->getAttribute('src'))) {
++$embedCount;
}
}
Expand Down Expand Up @@ -719,8 +719,9 @@ public function cleanHeaders(\DOMElement $e): void
$headers = $e->getElementsByTagName('h' . $headerIndex);

for ($i = $headers->length - 1; $i >= 0; --$i) {
if ($this->getWeight($headers->item($i)) < 0 || $this->getLinkDensity($headers->item($i)) > 0.33) {
$headers->item($i)->parentNode->removeChild($headers->item($i));
$header = $headers->item($i);
if ($this->getWeight($header) < 0 || $this->getLinkDensity($header) > 0.33) {
$header->parentNode->removeChild($header);
}
}
}
Expand Down Expand Up @@ -812,12 +813,14 @@ protected function prepDocument(): void
// Remove all style tags in head.
$styleTags = $this->dom->getElementsByTagName('style');
for ($i = $styleTags->length - 1; $i >= 0; --$i) {
$styleTags->item($i)->parentNode->removeChild($styleTags->item($i));
$styleTag = $styleTags->item($i);
$styleTag->parentNode->removeChild($styleTag);
}

$linkTags = $this->dom->getElementsByTagName('link');
for ($i = $linkTags->length - 1; $i >= 0; --$i) {
$linkTags->item($i)->parentNode->removeChild($linkTags->item($i));
$linkTag = $linkTags->item($i);
$linkTag->parentNode->removeChild($linkTag);
}
}

Expand Down Expand Up @@ -1015,15 +1018,15 @@ protected function grabArticle(?\DOMElement $page = null)
* A score is determined by things like number of commas, class names, etc.
* Maybe eventually link density.
*/
for ($pt = 0, $scored = \count($nodesToScore); $pt < $scored; ++$pt) {
$ancestors = $this->getAncestors($nodesToScore[$pt], 5);
foreach ($nodesToScore as $nodeToScore) {
$ancestors = $this->getAncestors($nodeToScore, 5);

// No parent node? Move on...
if (0 === \count($ancestors)) {
continue;
}

$innerText = $this->getInnerText($nodesToScore[$pt]);
$innerText = $this->getInnerText($nodeToScore);

// If this paragraph is less than MIN_PARAGRAPH_LENGTH (default:20) characters, don't even count it.
if (mb_strlen($innerText) < self::MIN_PARAGRAPH_LENGTH) {
Expand Down Expand Up @@ -1076,11 +1079,6 @@ protected function grabArticle(?\DOMElement $page = null)
}
}

$candidates = $xpath->query('.//*[not(self::body) and (@class or @id or @style) and ((number(@readability) < 40) or not(@readability))]', $page->documentElement);

for ($c = $candidates->length - 1; $c >= 0; --$c) {
$node = $candidates->item($c);
}
unset($candidates);
}

Expand Down Expand Up @@ -1231,11 +1229,6 @@ protected function grabArticle(?\DOMElement $page = null)
$parentOfTopCandidate = $topCandidate->parentNode;
$siblingNodes = $parentOfTopCandidate->childNodes;

if (0 === $siblingNodes->length) {
$siblingNodes = new \stdClass();
$siblingNodes->length = 0;
}

for ($s = 0, $sl = $siblingNodes->length; $s < $sl; ++$s) {
$siblingNode = $siblingNodes->item($s);
$siblingNodeName = $siblingNode->nodeName;
Expand Down