Compare commits

...
21 Commits
Author SHA1 Message Date
Jérémy BenoistandGitHub 9632c4df8c Merge pull request #61 from j0k3r/github-actions
Ditch Travis to use GitHub Actions
2020-11-30 14:34:46 +01:00
Jeremy Benoist bd9ca1b2cd Ditch Travis to use GitHub Actions 2020-11-30 14:18:40 +01:00
Jérémy BenoistandGitHub 6c917794a7 Merge pull request #60 from jtojnar/patch-1
readability: stop tidy from wrapping noscript text
2020-11-16 12:02:02 +01:00
Jan TojnarandGitHub 7cea79c23a readability: stop tidy from wrapping noscript text
HTML 4.01 Strict only allows block-level elements within noscript, form and
blockquote. The `enclose-block-text` option fixes the instances when those
elements contain inline elements or text by wrapping the children in paragraphs.

HTML 5 has looser content model and allows noscript elements basically anywhere,
including paragraphs, making the noscript elements inherit the parent element’s
content model. This means that tidy will produce invalid HTML nesting paragraphs
for `p > noscript > text`, a structure that would be invalid on two counts
in HTML 4 Strict profile but is completely valid in HTML 5.

Popular WordPress image lazy-loading code produces precisely that structure
so tidy “corrects” it to invalid code. In a proper HTML parser, the produced
code would force close the outer paragraph, making the noscript element
its sibling instead of a child. The only reason this does not break Graby’s code
for stripping the lazy-loading HTML is that libxml2 contains a bug
counteracting this:

https://gitlab.gnome.org/GNOME/libxml2/-/issues/205

Since all three elements allow flow content in HTML 5, it does not make much
sense to enable this option any more. The only possible issues that could occur
is producing HTML code not conforming to 4.01 Strict but that was never guaranteed,
as our example shows, and having blockquotes contain text nodes not wrapped
in paragraphs, which might be expected by some ancient stylesheets
but that is only minor and easily fixable visual backwards incompatibility.
2020-11-14 22:13:53 +01:00
Jérémy BenoistandGitHub c6425cc28b Merge pull request #58 from j0k3r/fix/test-php8
Enable tests for PHP 8
2020-06-08 09:58:28 +02:00
Jeremy Benoist e6ad806460 Enable tests on PHP 8 2020-06-08 09:24:50 +02:00
Jérémy BenoistandGitHub 3fa88461a0 Merge pull request #57 from j0k3r/fix/html5-parser
Use a new deps for HTML5 parser
2020-06-08 07:59:42 +02:00
Jeremy Benoist 6a8ecf232f Use a new deps for HTML5 parser
`electrolinux/php-html5lib` was quite old and incompatible with the upcoming Composer 2.0.
Jumping to `masterminds/html5` for the same result. Also the lib is maintained.

Also:
- keep README in vendors
- use new Scrutinizer engine
- test with lower deps
- remove php-coveralls dev deps and download the phar during the CI build
2020-06-08 07:04:00 +02:00
Jérémy BenoistandGitHub 52b1ddba57 Merge pull request #55 from j0k3r/fix/cleanup-travis
Cleanup travis
2020-04-12 16:38:09 +02:00
Jeremy Benoist 90c625bb57 Cleanup travis 2020-04-12 16:30:02 +02:00
Jérémy BenoistandGitHub 4d1c3b1777 Merge pull request #54 from j0k3r/fix/phpstan
Fix PHPStan (again)
2020-01-06 14:26:41 +01:00
Jeremy Benoist d649b59414 Fixing PHPUnit versions 2020-01-06 14:22:15 +01:00
Jeremy Benoist 44bebfc3d6 Only install PHPStan when we need it
This is to avoid error when installing it on PHP < 7.1
2020-01-06 14:03:30 +01:00
Jeremy Benoist b1acc9ed73 Fix PHPStan (again)
Also cleanup
2019-11-19 14:09:29 +01:00
Jérémy BenoistandGitHub 9306996b47 Merge pull request #53 from j0k3r/openload.co
Add openload.co to media detection
2019-06-25 17:15:37 +02:00
Jeremy Benoist bb75b4f089 Fix PHPStan 2019-06-25 17:06:49 +02:00
Jeremy Benoist 11d2946904 Add openload.co to media detection 2019-06-25 16:54:38 +02:00
Jérémy BenoistandGitHub f808c1b0a2 Merge pull request #50 from j0k3r/fix/non-well-formed-numeric-value
Fix “A non well formed numeric value encountered”
2019-05-11 22:07:19 +02:00
Jeremy Benoist bb65caf864 Fix “A non well formed numeric value encountered” 2019-05-11 21:58:11 +02:00
Jérémy BenoistandGitHub de1b1d9775 Merge pull request #48 from Simounet/feature/out-removed-from-negative
\bout removed from negative content
2019-04-23 10:45:13 +02:00
Simounet 2e20f76195 \bout removed from negative content 2019-04-19 12:12:41 +02:00
13 changed files with 313 additions and 73 deletions
+3 -2
View File
@@ -4,9 +4,10 @@ root = true
; Unix-style newlines
[*]
end_of_line = LF
[*.php]
indent_style = space
indent_size = 4
trim_trailing_whitespace = true
insert_final_newline = true
[.github/**.yml]
indent_size = 2
+2 -2
View File
@@ -4,7 +4,7 @@
/.scrutinizer.yml export-ignore
/.travis.yml export-ignore
/.php_cs export-ignore
/README.md export-ignore
/phpunit.xml.dist export-ignore
/tests export-ignore
/phpstan.neon export-ignore
/.github export-ignore
/tests export-ignore
+53
View File
@@ -0,0 +1,53 @@
name: "CS"
on:
pull_request:
branches:
- master
push:
branches:
- master
env:
SYMFONY_PHPUNIT_VERSION: 7.5
jobs:
coding-standards:
name: "CS Fixer & PHPStan"
runs-on: "ubuntu-18.04"
strategy:
matrix:
php:
- "7.3"
steps:
- name: "Checkout"
uses: "actions/checkout@v2"
- name: "Install PHP"
uses: "shivammathur/setup-php@v2"
with:
coverage: "none"
php-version: "${{ matrix.php }}"
tools: cs2pr, composer:v1
ini-values: "date.timezone=Europe/Paris"
env:
COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: "Add PHPStan"
run: "composer require phpstan/phpstan phpstan/phpstan-phpunit --dev --no-progress --no-suggest"
- name: "Install dependencies with Composer"
uses: "ramsey/composer-install@v1"
with:
composer-options: "--optimize-autoloader --prefer-dist"
- name: "Run PHP CS Fixer"
run: "php vendor/bin/php-cs-fixer fix --verbose --dry-run --format=checkstyle | cs2pr"
- name: "Install PHPUnit for PHPStan"
run: "php vendor/bin/simple-phpunit install"
- name: "Run PHPStan"
run: "php vendor/bin/phpstan analyse --error-format=checkstyle | cs2pr"
@@ -0,0 +1,202 @@
name: "CI"
on:
pull_request:
branches:
- "master"
push:
branches:
- "master"
env:
fail-fast: true
jobs:
phpunit:
name: "PHPUnit (PHP ${{ matrix.php }})"
runs-on: "ubuntu-18.04"
strategy:
matrix:
php:
- "5.6"
- "7.0"
- "7.1"
- "7.2"
- "7.3"
- "7.4"
steps:
- name: "Checkout"
uses: "actions/checkout@v2"
with:
fetch-depth: 2
- name: "Install PHP"
uses: "shivammathur/setup-php@v2"
with:
php-version: "${{ matrix.php }}"
coverage: "none"
tools: composer:v1
extensions: tidy
ini-values: "date.timezone=Europe/Paris"
env:
COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: "Force PHPUnit version"
if: matrix.php >= '7.2'
run: "echo $SYMFONY_PHPUNIT_VERSION"
env:
SYMFONY_PHPUNIT_VERSION: 7.5
- name: "Remove useless deps"
run: "composer remove friendsofphp/php-cs-fixer --dev --no-progress --no-update"
- name: "Install dependencies with Composer"
uses: "ramsey/composer-install@v1"
with:
composer-options: "--optimize-autoloader --prefer-dist"
- name: "Setup logs"
run: "mkdir -p build/logs"
- name: "Run PHPUnit"
run: "php vendor/bin/simple-phpunit -v"
phpunit-coverage:
name: "PHPUnit coverage (PHP ${{ matrix.php }})"
runs-on: "ubuntu-18.04"
strategy:
matrix:
php:
- "7.4"
steps:
- name: "Checkout"
uses: "actions/checkout@v2"
with:
fetch-depth: 2
- name: "Install PHP with Xdebug"
uses: "shivammathur/setup-php@v2"
with:
php-version: "${{ matrix.php }}"
coverage: "xdebug"
tools: composer:v1
extensions: tidy
ini-values: "date.timezone=Europe/Paris"
env:
COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: "Remove useless deps"
run: "composer remove friendsofphp/php-cs-fixer --dev --no-progress --no-update"
- name: "Install dependencies with Composer"
uses: "ramsey/composer-install@v1"
with:
composer-options: "--optimize-autoloader --prefer-dist"
- name: "Setup logs"
run: "mkdir -p build/logs"
- name: "Run PHPUnit (with coverage)"
run: "php vendor/bin/simple-phpunit -v --coverage-clover build/logs/clover.xml"
env:
SYMFONY_PHPUNIT_VERSION: 7.5
- name: "Retrieve Coveralls phar"
run: "wget https://github.com/php-coveralls/php-coveralls/releases/download/v2.4.2/php-coveralls.phar"
- name: "Enable Coveralls phar"
run: "chmod +x php-coveralls.phar"
- name: "Upload to Coveralls"
run: "php php-coveralls.phar -v -x build/logs/clover.xml"
env:
COVERALLS_REPO_TOKEN: ${{ secrets.GITHUB_TOKEN }}
phpunit-lowest:
name: "PHPUnit lowest deps (PHP ${{ matrix.php }})"
runs-on: "ubuntu-18.04"
strategy:
matrix:
php:
- "7.2"
steps:
- name: "Checkout"
uses: "actions/checkout@v2"
with:
fetch-depth: 2
- name: "Install PHP"
uses: "shivammathur/setup-php@v2"
with:
php-version: "${{ matrix.php }}"
coverage: "none"
tools: composer:v1
extensions: tidy
ini-values: "date.timezone=Europe/Paris"
env:
COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: "Remove useless deps"
run: "composer remove friendsofphp/php-cs-fixer --dev --no-progress --no-update"
- name: "Install dependencies with Composer"
uses: "ramsey/composer-install@v1"
with:
composer-options: "--optimize-autoloader --prefer-dist"
dependency-versions: "lowest"
- name: "Setup logs"
run: "mkdir -p build/logs"
- name: "Run PHPUnit"
run: "php vendor/bin/simple-phpunit -v"
env:
SYMFONY_PHPUNIT_VERSION: 7.5
phpunit-composerv2:
name: "PHPUnit with Composer v2 (PHP ${{ matrix.php }})"
runs-on: "ubuntu-18.04"
strategy:
matrix:
php:
- "7.4"
steps:
- name: "Checkout"
uses: "actions/checkout@v2"
with:
fetch-depth: 2
- name: "Install PHP"
uses: "shivammathur/setup-php@v2"
with:
php-version: "${{ matrix.php }}"
coverage: "none"
tools: composer:v2
extensions: tidy
ini-values: "date.timezone=Europe/Paris"
env:
COMPOSER_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: "Remove useless deps"
run: "composer remove friendsofphp/php-cs-fixer --dev --no-progress --no-update"
- name: "Install dependencies with Composer"
uses: "ramsey/composer-install@v1"
with:
composer-options: "--optimize-autoloader --prefer-dist"
- name: "Setup logs"
run: "mkdir -p build/logs"
- name: "Run PHPUnit"
run: "php vendor/bin/simple-phpunit -v"
env:
SYMFONY_PHPUNIT_VERSION: 7.5
+1
View File
@@ -2,3 +2,4 @@ vendor/
coverage/
composer.lock
.php_cs.cache
.phpunit.result.cache
+10
View File
@@ -1,2 +1,12 @@
tools:
external_code_coverage: false
build:
nodes:
analysis:
tests:
override:
- php-scrutinizer-run
environment:
php:
version: 7.2
+16 -24
View File
@@ -1,42 +1,34 @@
dist: xenial
os: linux
language: php
php:
- 5.6
- 7.0
- 7.1
- 7.2
- 7.3
- nightly
# avoid double Travis build when the PR is created on upstream
if: |
type = pull_request OR \
branch = master
matrix:
jobs:
include:
- php: 7.2
env: CS_FIXER=run
- php: 8.0
env: SYMFONY_PHPUNIT_VERSION=7.5
fast_finish: true
allow_failures:
- php: nightly
- php: 8.0
# cache vendor dirs
cache:
directories:
- vendor
- $HOME/.composer/cache
- $HOME/.composer/cache/files
before_install:
- if [ -n "$GH_TOKEN" ]; then composer config github-oauth.github.com ${GH_TOKEN}; fi;
install:
- composer self-update
- if [ "$CS_FIXER" != "run" ]; then composer remove friendsofphp/php-cs-fixer --dev --no-progress --no-update ; fi;
- composer update --prefer-dist --no-progress --no-suggest -o $
- php vendor/bin/simple-phpunit install
before_script:
- if [ "$CS_FIXER" = "run" ]; then composer require phpstan/phpstan phpstan/phpstan-phpunit --dev -n ; fi;
- composer install -o --prefer-dist --no-interaction
- mkdir -p build/logs
script:
- mkdir -p build/logs
- php vendor/bin/simple-phpunit -v --coverage-clover build/logs/clover.xml
- if [ "$CS_FIXER" = "run" ]; then php vendor/bin/php-cs-fixer fix --verbose --dry-run ; fi;
- if [ "$CS_FIXER" = "run" ]; then php vendor/bin/phpstan analyse src tests --no-progress --level 1 ; fi;
after_script:
- php vendor/bin/php-coveralls -v -x build/logs/clover.xml
- php vendor/bin/simple-phpunit -v
+1
View File
@@ -1,5 +1,6 @@
# Readability
![CI](https://github.com/j0k3r/php-readability/workflows/CI/badge.svg)
[![Build Status](https://travis-ci.org/j0k3r/php-readability.svg?branch=master)](https://travis-ci.org/j0k3r/php-readability)
[![Coverage Status](https://coveralls.io/repos/j0k3r/php-readability/badge.svg?branch=master&service=github)](https://coveralls.io/github/j0k3r/php-readability/?branch=master)
[![Total Downloads](https://poser.pugx.org/j0k3r/php-readability/downloads)](https://packagist.org/packages/j0k3r/php-readability)
+2 -3
View File
@@ -27,12 +27,11 @@
"php": ">=5.6.0",
"ext-mbstring": "*",
"psr/log": "^1.0",
"electrolinux/php-html5lib": "^0.1.0"
"masterminds/html5": "^2.7"
},
"require-dev": {
"php-coveralls/php-coveralls": "^2.1",
"friendsofphp/php-cs-fixer": "^2.14",
"monolog/monolog": "^1.24",
"monolog/monolog": "^1.24|^2.1",
"symfony/phpunit-bridge": "^4.2.3"
},
"suggest": {
+10 -5
View File
@@ -1,8 +1,13 @@
parameters:
level: 1
paths:
- src
- tests
# https://github.com/phpstan/phpstan/issues/694#issuecomment-350724288
bootstrapFiles:
- vendor/bin/.phpunit/phpunit-7.5-0/vendor/autoload.php
includes:
- vendor/phpstan/phpstan-phpunit/extension.neon
- vendor/phpstan/phpstan-phpunit/rules.neon
parameters:
# https://github.com/phpstan/phpstan/issues/694#issuecomment-350724288
autoload_files:
- vendor/bin/.phpunit/phpunit-6.5/vendor/autoload.php
+1 -2
View File
@@ -7,7 +7,6 @@
convertWarningsToExceptions="true"
processIsolation="false"
stopOnFailure="false"
syntaxCheck="false"
bootstrap="vendor/autoload.php"
>
@@ -27,6 +26,6 @@
</filter>
<!-- <logging>
<log type="coverage-html" target="coverage" title="Readability" charset="UTF-8" yui="true" highlight="true" lowUpperBound="35" highLowerBound="70"/>
<log type="coverage-html" target="coverage" lowUpperBound="35" highLowerBound="70"/>
</logging> -->
</phpunit>
+7 -30
View File
@@ -2,7 +2,7 @@
namespace Readability;
use HTML5Lib\Parser;
use Masterminds\HTML5;
use Psr\Log\LoggerAwareInterface;
use Psr\Log\LoggerInterface;
use Psr\Log\NullLogger;
@@ -61,7 +61,7 @@ class Readability implements LoggerAwareInterface
// constants
const SCORE_CHARS_IN_PARAGRAPH = 100;
const SCORE_WORDS_IN_PARAGRAPH = 20;
const GRANDPARENT_SCORE_DIVISOR = 2.2;
const GRANDPARENT_SCORE_DIVISOR = 2;
const MIN_PARAGRAPH_LENGTH = 20;
const MIN_COMMAS_IN_PARAGRAPH = 6;
const MIN_ARTICLE_LENGTH = 200;
@@ -92,10 +92,10 @@ class Readability implements LoggerAwareInterface
'unlikelyCandidates' => '/display\s*:\s*none|ignore|\binfos?\b|annoy|clock|date|time|author|intro|hidd?e|about|archive|\bprint|bookmark|tags|tag-list|share|search|social|robot|published|combx|comment|mast(?:head)|subscri|community|category|disqus|extra|head|head(?:er|note)|floor|foot(?:er|note)|menu|tool\b|function|nav|remark|rss|shoutbox|widget|meta|banner|sponsor|adsense|inner-?ad|ad-|sponsor|\badv\b|\bads\b|agr?egate?|pager|sidebar|popup|tweet|twitter/i',
'okMaybeItsACandidate' => '/article\b|contain|\bcontent|column|general|detail|shadow|lightbox|blog|body|entry|main|page|footnote/i',
'positive' => '/read|full|article|body|\bcontent|contain|entry|main|markdown|media|page|attach|pagination|post|text|blog|story/i',
'negative' => '/bottom|stat|info|discuss|e[\-]?mail|comment|reply|log.{2}(n|ed)|sign|single|combx|com-|contact|_nav|link|media|\bout|promo|\bad-|related|scroll|shoutbox|sidebar|sponsor|shopping|teaser|recommend/i',
'negative' => '/bottom|stat|info|discuss|e[\-]?mail|comment|reply|log.{2}(n|ed)|sign|single|combx|com-|contact|_nav|link|media|promo|\bad-|related|scroll|shoutbox|sidebar|sponsor|shopping|teaser|recommend/i',
'divToPElements' => '/<(?:blockquote|header|section|code|div|article|footer|aside|img|p|pre|dl|ol|ul)/mi',
'killBreaks' => '/(<br\s*\/?>([ \r\n\s]|&nbsp;?)*)+/',
'media' => '!//(?:[^\.\?/]+\.)?(?:youtu(?:be)?|giphy|soundcloud|dailymotion|vimeo|pornhub|xvideos|twitvid|rutube|viddler)\.(?:com|be|org|net)/!i',
'media' => '!//(?:[^\.\?/]+\.)?(?:youtu(?:be)?|giphy|soundcloud|dailymotion|vimeo|pornhub|xvideos|twitvid|rutube|openload\.co|viddler)\.(?:com|be|org|net)/!i',
'skipFootnoteLink' => '/^\s*(\[?[a-z0-9]{1,2}\]?|^|edit|citation needed)\s*$/i',
];
public $tidy_config = [
@@ -116,7 +116,6 @@ class Readability implements LoggerAwareInterface
'drop-empty-paras' => true,
'drop-proprietary-attributes' => false,
'enclose-text' => true,
'enclose-block-text' => true,
'merge-divs' => true,
// 'merge-spans' => true,
'input-encoding' => '????',
@@ -307,8 +306,6 @@ class Readability implements LoggerAwareInterface
/**
* Run any post-process modifications to article content as necessary.
*
* @param \DOMElement $articleContent
*/
public function postProcessContent(\DOMElement $articleContent)
{
@@ -321,8 +318,6 @@ class Readability implements LoggerAwareInterface
* For easier reading, convert this document to have footnotes at the bottom rather than inline links.
*
* @see http://www.roughtype.com/archives/2010/05/experiments_in.php
*
* @param \DOMElement $articleContent
*/
public function addFootnotes(\DOMElement $articleContent)
{
@@ -385,8 +380,6 @@ class Readability implements LoggerAwareInterface
/**
* Prepare the article node for display. Clean out any inline styles,
* iframes, forms, strip extraneous <p> tags, etc.
*
* @param \DOMNode $articleContent
*/
public function prepArticle(\DOMNode $articleContent)
{
@@ -558,7 +551,6 @@ class Readability implements LoggerAwareInterface
* This is the amount of text that is inside a link divided by the total text in the node.
* Can exclude external references to differentiate between simple text and menus/infoblocks.
*
* @param \DOMElement $e
* @param bool $excludeExternal
*
* @return int
@@ -586,8 +578,6 @@ class Readability implements LoggerAwareInterface
/**
* Get an element relative weight.
*
* @param \DOMElement $e
*
* @return int
*/
public function getWeight(\DOMElement $e)
@@ -607,8 +597,6 @@ class Readability implements LoggerAwareInterface
/**
* Remove extraneous break tags from a node.
*
* @param \DOMElement $node
*/
public function killBreaks(\DOMElement $node)
{
@@ -623,12 +611,10 @@ class Readability implements LoggerAwareInterface
*
* Updated 2012-09-18 to preserve youtube/vimeo iframes
*
* @param \DOMElement $e
* @param string $tag
*/
public function clean(\DOMElement $e, $tag)
{
$currentItem = null;
$targetList = $e->getElementsByTagName($tag);
$isEmbed = ('audio' === $tag || 'video' === $tag || 'iframe' === $tag || 'object' === $tag || 'embed' === $tag);
@@ -659,7 +645,6 @@ class Readability implements LoggerAwareInterface
* "Fishy" is an algorithm based on content length, classnames,
* link density, number of images & embeds, etc.
*
* @param \DOMElement $e
* @param string $tag
*/
public function cleanConditionally(\DOMElement $e, $tag)
@@ -670,7 +655,6 @@ class Readability implements LoggerAwareInterface
$tagsList = $e->getElementsByTagName($tag);
$curTagsLength = $tagsList->length;
$node = null;
/*
* Gather counts for other typical elements embedded within.
@@ -772,8 +756,6 @@ class Readability implements LoggerAwareInterface
/**
* Clean out spurious headers from an Element. Checks things like classnames and link density.
*
* @param \DOMElement $e
*/
public function cleanHeaders(\DOMElement $e)
{
@@ -915,8 +897,6 @@ class Readability implements LoggerAwareInterface
/**
* Initialize a node with the readability object. Also checks the
* className/id for special names to add to its score.
*
* @param \DOMElement $node
*/
protected function initializeNode(\DOMElement $node)
{
@@ -1115,7 +1095,7 @@ class Readability implements LoggerAwareInterface
// Add the score to the parent. The grandparent gets half.
$parentNode->getAttributeNode('readability')->value += $contentScore;
if ($grandParentNode) {
$grandParentNode->getAttributeNode('readability')->value += $contentScore / self::GRANDPARENT_SCORE_DIVISOR;
$grandParentNode->getAttributeNode('readability')->value += round($contentScore / self::GRANDPARENT_SCORE_DIVISOR);
}
}
@@ -1125,7 +1105,6 @@ class Readability implements LoggerAwareInterface
*/
if ($this->flagIsActive(self::FLAG_STRIP_UNLIKELYS) && $xpath) {
$candidates = $xpath->query('.//*[(self::footer and count(//footer)<2) or (self::aside and count(//aside)<2)]', $page->documentElement);
$node = null;
for ($c = $candidates->length - 1; $c >= 0; --$c) {
$node = $candidates->item($c);
@@ -1137,7 +1116,6 @@ class Readability implements LoggerAwareInterface
}
$candidates = $xpath->query('.//*[not(self::body) and (@class or @id or @style) and ((number(@readability) < 40) or not(@readability))]', $page->documentElement);
$node = null;
for ($c = $candidates->length - 1; $c >= 0; --$c) {
$node = $candidates->item($c);
@@ -1346,7 +1324,6 @@ class Readability implements LoggerAwareInterface
* Get an element weight by attribute.
* Uses regular expressions to tell if this element looks good or bad.
*
* @param \DOMElement $element
* @param string $attribute
*
* @return int
@@ -1442,8 +1419,8 @@ class Readability implements LoggerAwareInterface
$this->html = mb_convert_encoding($this->html, 'HTML-ENTITIES', 'UTF-8');
if ('html5lib' === $this->parser) {
$this->dom = Parser::parse($this->html);
if ('html5lib' === $this->parser || 'html5' === $this->parser) {
$this->dom = (new HTML5())->loadHTML($this->html);
}
if ('libxml' === $this->parser) {
+1 -1
View File
@@ -193,7 +193,7 @@ class ReadabilityTest extends \PHPUnit\Framework\TestCase
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertNotContains('<aside>', $readability->getContent()->getInnerHtml());
$this->assertContains('<footer readability="4"/>', $readability->getContent()->getInnerHtml());
$this->assertContains('<footer readability="5"/>', $readability->getContent()->getInnerHtml());
}
public function testWithClasses()