infong/php-readability
1
0
Fork 0
mirror of https://github.com/j0k3r/php-readability.git synced 2026-09-27 06:26:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update coding style for upcoming PHP-CS-Fixer changes

Browse Source 
Once we bump minimum PHP version, we will get newer PHP-CS-Fixer,
which will try to apply this cleanups.

(partially cherry picked from commit 648d8c605b)

Though avoid disabling `modernize_strpos` since it was only introduced in PHP-CS-Fixer 3.2.0:
https://github.com/PHP-CS-Fixer/PHP-CS-Fixer/commit/2ca22a27c4ffb8cc46f20e7110b1dfcbb0c8c47c

Also had to disable `visibility_required` for constants since those require PHP ≥ 7.1:
https://cs.symfony.com/doc/rules/class_notation/visibility_required.html

And remove type hint from `grabArticle` since implicitly nullable types were deprecated in PHP 8.4:
https://wiki.php.net/rfc/deprecate-implicitly-nullable-types
But we cannot use explicitly nullable types, which require PHP ≥ 7.1:
https://wiki.php.net/rfc/nullable_types

Also switch code blocks to Markdown syntax to work around `phpdoc_separation`, ApiGen uses Markdown these days anyway.
(partially cherry picked from commit 9ed89bde92)
This commit is contained in:
Jan Tojnar
2025-02-23 02:32:57 +01:00
parent 66864279fd
commit 8421ed5962
3 changed files with 24 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/Readability.php
+16 -14
View File
@@ -144,7 +144,7 @@ class Readability implements LoggerAwareInterface
// HACK: replace linebreaks plus br's with p's
'!(<br[^>]*>[ \r\n\s]*){2,}!i' => '</p><p>',
// replace noscripts
//'!</?noscript>!is' => '',
// '!</?noscript>!is' => '',
// replace fonts to spans
'!<(/?)font[^>]*>!is' => '<\\1span>',
];
@@ -155,8 +155,8 @@ class Readability implements LoggerAwareInterface
// replace empty tags that break layouts
'!<(?:a|div|p|figure)[^>]+/>!is' => '',
// remove all attributes on text tags
//'!<(\s*/?\s*(?:blockquote|br|hr|code|div|article|span|footer|aside|p|pre|dl|li|ul|ol)) [^>]+>!is' => "<\\1>",
//single newlines cleanup
// '!<(\s*/?\s*(?:blockquote|br|hr|code|div|article|span|footer|aside|p|pre|dl|li|ul|ol)) [^>]+>!is' => "<\\1>",
// single newlines cleanup
"/\n+/" => "\n",
// modern web...
'!<pre[^>]*>\s*<code!is' => '<pre',
@@ -366,7 +366,7 @@ class Readability implements LoggerAwareInterface
$articleLink->setAttribute('style', 'color: inherit; text-decoration: none;');
$articleLink->setAttribute('name', 'readabilityLink-' . $linkCount);
$footnote->setInnerHtml('<small><sup><a href="#readabilityLink-' . $linkCount . '" title="Jump to Link in Article">^</a></sup></small> ');
$footnoteLink->setInnerHtml(('' !== $footnoteLink->getAttribute('title') ? $footnoteLink->getAttribute('title') : $linkText));
$footnoteLink->setInnerHtml('' !== $footnoteLink->getAttribute('title') ? $footnoteLink->getAttribute('title') : $linkText);
$footnoteLink->setAttribute('name', 'readabilityFootnoteLink-' . $linkCount);
$footnote->appendChild($footnoteLink);
@@ -796,7 +796,7 @@ class Readability implements LoggerAwareInterface
*/
public function addFlag($flag)
{
$this->flags = $this->flags | $flag;
$this->flags |= $flag;
}
/**
@@ -806,13 +806,14 @@ class Readability implements LoggerAwareInterface
*/
public function removeFlag($flag)
{
$this->flags = $this->flags & ~$flag;
$this->flags &= ~$flag;
}
/**
* Debug.
*
* @deprecated use $this->logger->debug() instead
*
* @codeCoverageIgnore
*/
protected function dbg($msg)
@@ -824,6 +825,7 @@ class Readability implements LoggerAwareInterface
* Dump debug info.
*
* @deprecated since Monolog gather log, we don't need it
*
* @codeCoverageIgnore
*/
protected function dump_dbg()
@@ -973,11 +975,11 @@ class Readability implements LoggerAwareInterface
* Using a variety of metrics (content score, classname, element types), find the content that is
* most likely to be the stuff a user wants to read. Then return it wrapped up in a div.
*
* @param \DOMElement $page
* @param ?\DOMElement $page
*
* @return \DOMElement|false
*/
protected function grabArticle(\DOMElement $page = null)
protected function grabArticle($page = null)
{
if (!$page) {
$page = $this->dom;
@@ -992,7 +994,7 @@ class Readability implements LoggerAwareInterface
$allElements = $page->getElementsByTagName('*');
for ($nodeIndex = 0; ($node = $allElements->item($nodeIndex)); ++$nodeIndex) {
for ($nodeIndex = 0; $node = $allElements->item($nodeIndex); ++$nodeIndex) {
$tagName = $node->tagName;
$nodeContent = $node->getInnerHTML();
@@ -1136,9 +1138,9 @@ class Readability implements LoggerAwareInterface
// Remove unlikely candidates
$unlikelyMatchString = $node->getAttribute('class') . ' ' . $node->getAttribute('id') . ' ' . $node->getAttribute('style');
if (mb_strlen($unlikelyMatchString) > 3 && // don't process "empty" strings
preg_match($this->regexps['unlikelyCandidates'], $unlikelyMatchString) &&
!preg_match($this->regexps['okMaybeItsACandidate'], $unlikelyMatchString)
if (mb_strlen($unlikelyMatchString) > 3 // don't process "empty" strings
&& preg_match($this->regexps['unlikelyCandidates'], $unlikelyMatchString)
&& !preg_match($this->regexps['okMaybeItsACandidate'], $unlikelyMatchString)
) {
$this->logger->debug('Removing unlikely candidate (using conf) ' . $node->getNodePath() . ' by "' . $unlikelyMatchString . '" with readability ' . ($node->hasAttribute('readability') ? (int) $node->getAttributeNode('readability')->value : 0));
$node->parentNode->removeChild($node);
@@ -1289,8 +1291,8 @@ class Readability implements LoggerAwareInterface
// To ensure a node does not interfere with readability styles, remove its classnames & ids.
// Now done via RegExp post_filter.
//$nodeToAppend->removeAttribute('class');
//$nodeToAppend->removeAttribute('id');
// $nodeToAppend->removeAttribute('class');
// $nodeToAppend->removeAttribute('id');
// Append sibling and subtract from our list as appending removes a node.
$articleContent->appendChild($nodeToAppend);
}