infong/php-readability
1
0
Fork 0
mirror of https://github.com/j0k3r/php-readability.git synced 2026-09-26 22:16:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Iterate node lists with foreach

Browse Source 
`DOMNodeList` implements `Traversable`.

There are some `for` loops left but we cannot simply replace those:
PHP follows the DOM specification, which requires that `NodeList`
objects in the DOM are live. As a result, any operation that removes
a node list member node from its parent (such as `removeChild`,
`replaceChild` or `appendChild`) will cause the next node
in the iterator to be skipped.

We could work around that by converting those node lists to static arrays
using `iterator_to_array` but not sure if it is worth it.
This commit is contained in:
Jan Tojnar
2024-10-10 09:01:45 +02:00
parent d454c3a462
commit 9a9373de4b
1 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/Readability.php
+14 -14
View File
@@ -302,8 +302,7 @@ class Readability implements LoggerAwareInterface
$articleLinks = $articleContent->getElementsByTagName('a'); $articleLinks = $articleContent->getElementsByTagName('a');
$linkCount = 0; $linkCount = 0;
for ($i = 0; $i < $articleLinks->length; ++$i) { foreach ($articleLinks as $articleLink) {
$articleLink = $articleLinks->item($i);
$footnoteLink = $articleLink->cloneNode(true); $footnoteLink = $articleLink->cloneNode(true);
$refLink = $this->dom->createElement('a'); $refLink = $this->dom->createElement('a');
$footnote = $this->dom->createElement('li'); $footnote = $this->dom->createElement('li');
@@ -383,8 +382,8 @@ class Readability implements LoggerAwareInterface
// Remove service data-candidate attribute. // Remove service data-candidate attribute.
$elems = $xpath->query('.//*[@data-candidate]', $articleContent); $elems = $xpath->query('.//*[@data-candidate]', $articleContent);
for ($i = $elems->length - 1; $i >= 0; --$i) { foreach ($elems as $elem) {
$elems->item($i)->removeAttribute('data-candidate'); $elem->removeAttribute('data-candidate');
} }
// Clean out junk from the article content. // Clean out junk from the article content.
@@ -520,11 +519,12 @@ class Readability implements LoggerAwareInterface
$textLength = mb_strlen($this->getInnerText($e, true, true)); $textLength = mb_strlen($this->getInnerText($e, true, true));
$linkLength = 0; $linkLength = 0;
for ($dRe = $this->domainRegExp, $i = 0, $il = $links->length; $i < $il; ++$i) { $dRe = $this->domainRegExp;
if ($excludeExternal && $dRe && !preg_match($dRe, $links->item($i)->getAttribute('href'))) { foreach ($links as $link) {
if ($excludeExternal && $dRe && !preg_match($dRe, $link->getAttribute('href'))) {
continue; continue;
} }
$linkLength += mb_strlen($this->getInnerText($links->item($i))); $linkLength += mb_strlen($this->getInnerText($link));
} }
if ($textLength > 0 && $linkLength > 0) { if ($textLength > 0 && $linkLength > 0) {
@@ -640,15 +640,15 @@ class Readability implements LoggerAwareInterface
$embedCount = 0; $embedCount = 0;
$embeds = $node->getElementsByTagName('embed'); $embeds = $node->getElementsByTagName('embed');
for ($ei = 0, $il = $embeds->length; $ei < $il; ++$ei) { foreach ($embeds as $embed) {
if (preg_match($this->regexps['media'], $embeds->item($ei)->getAttribute('src'))) { if (preg_match($this->regexps['media'], $embed->getAttribute('src'))) {
++$embedCount; ++$embedCount;
} }
} }
$embeds = $node->getElementsByTagName('iframe'); $embeds = $node->getElementsByTagName('iframe');
for ($ei = 0, $il = $embeds->length; $ei < $il; ++$ei) { foreach ($embeds as $embed) {
if (preg_match($this->regexps['media'], $embeds->item($ei)->getAttribute('src'))) { if (preg_match($this->regexps['media'], $embed->getAttribute('src'))) {
++$embedCount; ++$embedCount;
} }
} }
@@ -1018,15 +1018,15 @@ class Readability implements LoggerAwareInterface
* A score is determined by things like number of commas, class names, etc. * A score is determined by things like number of commas, class names, etc.
* Maybe eventually link density. * Maybe eventually link density.
*/ */
for ($pt = 0, $scored = \count($nodesToScore); $pt < $scored; ++$pt) { foreach ($nodesToScore as $nodeToScore) {
$ancestors = $this->getAncestors($nodesToScore[$pt], 5); $ancestors = $this->getAncestors($nodeToScore, 5);
// No parent node? Move on... // No parent node? Move on...
if (0 === \count($ancestors)) { if (0 === \count($ancestors)) {
continue; 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 this paragraph is less than MIN_PARAGRAPH_LENGTH (default:20) characters, don't even count it.
if (mb_strlen($innerText) < self::MIN_PARAGRAPH_LENGTH) { if (mb_strlen($innerText) < self::MIN_PARAGRAPH_LENGTH) {