Compare commits

...
38 Commits
Author SHA1 Message Date
Jérémy BenoistandGitHub 38870cdff1 Merge pull request #80 from jtojnar/stricter
Fix some CI issues
2023-04-03 14:47:32 +02:00
Jan Tojnar 9bdd3b6b2e ci: Add PHP 8.2 and 8.3 2023-03-31 05:26:07 +02:00
Jan Tojnar f14428e4c0 Do not use mb_convert_encoding with HTML-ENTITIES as target encoding
This is deprecated since PHP 8.2:

    Deprecated: mb_convert_encoding(): Handling HTML entities via mbstring is deprecated; use htmlspecialchars, htmlentities, or mb_encode_numericentity/mb_decode_numericentity instead

It was used because `DOMDocument`, which uses libxml2 internally, will parse the HTML as ISO-8859-1, unless the document contains an XML encoding declaration or HTML meta tag setting character set.
Since first such element wins, putting the `meta[charset]` up front will ensure the parser uses the correct encoding, even if the document contains incorrect meta tag (e.g. when the document is converted to UTF-8 without also updating the metadata by the software passing it to Readability).

https://stackoverflow.com/a/39148511/160386
2023-03-31 05:26:07 +02:00
Jan Tojnar 23f824a1ce tests: Fix “THE ERROR HANDLER HAS CHANGED!” 2023-03-31 03:19:22 +02:00
Jan Tojnar 2a57124528 composer: upgrade rector 2023-03-31 03:19:22 +02:00
Jan Tojnar 0975574bdb Rector: Upgrade configuration 2023-03-31 03:19:22 +02:00
Jan Tojnar 9ed89bde92 Fix PHP-Cs-Fixer changes
1) src/Readability.php (braces, no_unneeded_control_parentheses, single_line_comment_spacing, global_namespace_import, no_unused_imports, phpdoc_align)
   2) src/JSLikeHTMLElement.php (phpdoc_separation)

Switch code blocks to Markdown syntax to work around `phpdoc_separation`, ApiGen uses Markdown these days anyway.
2023-03-31 03:14:00 +02:00
Jan Tojnar 2c6c6d5987 PHPStan: Use stable PHPUnit path
phpunit-bridge will create a symlink.
2023-03-31 03:14:00 +02:00
Jan Tojnar c5407ec07c composer: Add scripts for development 2023-03-31 03:14:00 +02:00
Jérémy BenoistandGitHub 7cd8476d38 Merge pull request #79 from j0k3r/fix/psr-log-2-3
Allow `psr/log` 2.0 & 3.0
2022-10-17 22:44:36 +02:00
Jeremy Benoist 82083c872b Allow psr/log 2.0 & 3.0 2022-10-17 22:42:47 +02:00
Kevin DecherfandJeremy Benoist 6689f19956 Strip script and style tags through ::clean() method instead of preg_replace
Huge tags can lead to a failure of preg_replace, thus erasing the whole
fetched content.

Fixes https://github.com/wallabag/wallabag/issues/5847

Signed-off-by: Kevin Decherf <kevin@kdecherf.com>
2022-06-13 09:13:23 +02:00
Jérémy BenoistandGitHub 0c0653dad6 Merge pull request #73 from Kdecherf/fix/impr
Fix `isPhrasingContent` conditions, text node replacement
2022-02-16 00:03:37 +01:00
Kevin Decherf 2ab87d7445 Fix isPhrasingContent conditions, text node replacement
It also disables reverting forced paragraph elements as it can break
layouts or corrupt content.

Signed-off-by: Kevin Decherf <kevin@kdecherf.com>
2022-02-15 20:53:28 +01:00
Jérémy BenoistandGitHub 8af69ad68c Merge pull request #71 from j0k3r/feature/enable-rector
Add Rector
2022-02-04 12:15:57 +01:00
Jeremy Benoist c2a1639b34 Add Rector 2022-02-04 12:13:37 +01:00
Jérémy BenoistandGitHub ccf1b336c5 Merge pull request #64 from Kdecherf/improvements 2022-02-04 05:27:57 +01:00
Kevin Decherf a44c4e5482 Add routine to remove invisible nodes
Readability was previously removing (was trying to actually, see next
section) invisible nodes using a pattern from `unlikelyCandidates`. This
was quite hacky and was removed during a backport of logics from
mozilla/readability. There is still a need to remove them so here we
are. We still use a pattern but specifically against the style
attribute. We also remove nodes with the attribute `hidden`.

The clean feature of tidy actually replaces inline style attributes
with css classes thus preventing readability to detect invisible nodes,
see https://github.com/htacg/tidy-html5/blob/5.6.0/src/clean.c#L1488
We therefore set clean configuration to false.

Signed-off-by: Kevin Decherf <kevin@kdecherf.com>
2022-02-04 01:23:11 +01:00
Kevin Decherf b580cf216d Backport some logics from mozilla/readability
This change backports several things from mozilla/readability:

- Add child score to all ancestors instead of the first parent only
- Check 5 top candidates and try to find alternative candidates within
  ancestors, this can help to find a better parent and grab more content
- Reduce patterns from `unlikelyCandidates` to the one used by Mozilla
  as ours tend to remove useful nodes
- Score headers (h2 to h6) by default in addition to div, p, td and
  section

Signed-off-by: Kevin Decherf <kevin@kdecherf.com>
2022-02-04 01:05:13 +01:00
Jérémy BenoistandGitHub 2e9349f076 Merge pull request #69 from j0k3r/feature/php-7.2
Require PHP >= 7.2
2022-02-02 12:53:28 +01:00
Jeremy Benoist c4bba53dbe Remove Scrutinizer 2022-02-02 12:52:12 +01:00
Jeremy Benoist 66215a6c80 Require PHP >= 7.2
- remove test on Composer v1
- remove deprecated function
- move `loadHtml()` into `init()` instead of `__construct`

Kinda prepare 2.0 version :)
2022-02-02 12:44:24 +01:00
Jérémy BenoistandGitHub b1a20a9575 Merge pull request #68 from open-source-contributions/master
Using assertSame to make assertion equal strict
2021-12-17 12:17:44 +01:00
peter279k 97c02e8ad4 Using assertSame to make assertion equal strict 2021-12-17 19:09:36 +08:00
Jérémy BenoistandGitHub c506b7ebd7 Merge pull request #67 from j0k3r/fix/psr-log-void
Fix deprecated message
2021-11-29 21:06:47 +01:00
Jeremy Benoist d0af21814a Ditch assertContains & assertNotContains 2021-11-29 21:04:56 +01:00
Jeremy Benoist 5b1eba79bd Test on PHP 8 & drop Travis 2021-11-29 21:00:36 +01:00
Jérémy BenoistandGitHub fabf096ce6 Fix deprecated message
> Method "Psr\Log\LoggerAwareInterface::setLogger()" might add "void" as a native return type declaration in the future. Do the same in implementation "Readability\Readability" now to avoid errors or add an explicit @return annotation to suppress this message.
2021-11-29 20:50:10 +01:00
Jérémy BenoistandGitHub 8ce1663238 Merge pull request #66 from Kdecherf/fix/figure 2021-10-29 16:24:41 +02:00
Kevin Decherf eb72a315c4 Clean empty figure tags without ending
See 'Tag omission' https://developer.mozilla.org/en-US/docs/Web/HTML/Element/figure

Signed-off-by: Kevin Decherf <kevin@kdecherf.com>
2021-10-29 15:36:19 +02:00
Jérémy BenoistandGitHub d5330a9c28 Merge pull request #65 from j0k3r/fix/php-cs
Fix PHPCS config file
2021-10-04 11:42:34 +02:00
Jeremy Benoist 635f8963dc Fix Travis & PHPStan 2021-10-04 11:37:33 +02:00
Jeremy Benoist 19b2a25d96 Fix PHPCS config file 2021-10-04 11:32:34 +02:00
Jérémy BenoistandGitHub 9a490fac07 Merge pull request #52 from nicofrand/master
Skip empty (empty innerHTML) nodes when grabbing article
2021-03-09 11:14:29 +01:00
Jérémy BenoistandGitHub 6f6b1f9e2b Merge pull request #62 from j0k3r/fix/avoid-wiped-body
Body can be wiped without tidy
2021-03-09 10:49:54 +01:00
Jeremy Benoist ea1368fac0 Body can be wiped without tidy
Re-create it in that case.

Also run CS-Fixer.
2021-03-08 11:59:24 +01:00
Jérémy BenoistandGitHub be81eb2a4f Create FUNDING.yml 2020-12-08 09:47:38 +01:00
nicofrand ff78c63e6d Skip empty (empty innerHTML) nodes when grabbing article 2019-05-25 16:12:52 +02:00
17 changed files with 815 additions and 675 deletions
+1
View File
@@ -6,5 +6,6 @@
/.php_cs export-ignore
/phpunit.xml.dist export-ignore
/phpstan.neon export-ignore
/rector.php export-ignore
/.github export-ignore
/tests export-ignore
+1
View File
@@ -0,0 +1 @@
github: j0k3r
+5 -11
View File
@@ -8,38 +8,32 @@ on:
branches:
- master
env:
SYMFONY_PHPUNIT_VERSION: 7.5
jobs:
coding-standards:
name: "CS Fixer & PHPStan"
runs-on: "ubuntu-18.04"
runs-on: "ubuntu-20.04"
strategy:
matrix:
php:
- "7.3"
- "7.2"
steps:
- name: "Checkout"
uses: "actions/checkout@v2"
uses: "actions/checkout@v3"
- name: "Install PHP"
uses: "shivammathur/setup-php@v2"
with:
coverage: "none"
php-version: "${{ matrix.php }}"
tools: cs2pr, composer:v1
tools: cs2pr, composer:v2
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"
uses: "ramsey/composer-install@v2"
with:
composer-options: "--optimize-autoloader --prefer-dist"
+98 -149
View File
@@ -14,163 +14,22 @@ env:
jobs:
phpunit:
name: "PHPUnit (PHP ${{ matrix.php }})"
runs-on: "ubuntu-18.04"
runs-on: "ubuntu-20.04"
strategy:
matrix:
php:
- "5.6"
- "7.0"
- "7.1"
- "7.2"
- "7.3"
- "7.4"
- "8.0"
- "8.1"
- "8.2"
- "8.3"
steps:
- name: "Checkout"
uses: "actions/checkout@v2"
with:
fetch-depth: 2
- name: "Install PHP"
uses: "shivammathur/setup-php@v2"
with:
php-version: "${{ 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"
uses: "actions/checkout@v3"
with:
fetch-depth: 2
@@ -189,7 +48,7 @@ jobs:
run: "composer remove friendsofphp/php-cs-fixer --dev --no-progress --no-update"
- name: "Install dependencies with Composer"
uses: "ramsey/composer-install@v1"
uses: "ramsey/composer-install@v2"
with:
composer-options: "--optimize-autoloader --prefer-dist"
@@ -198,5 +57,95 @@ jobs:
- name: "Run PHPUnit"
run: "php vendor/bin/simple-phpunit -v"
phpunit-coverage:
name: "PHPUnit coverage (PHP ${{ matrix.php }})"
runs-on: "ubuntu-20.04"
strategy:
matrix:
php:
- "7.4"
steps:
- name: "Checkout"
uses: "actions/checkout@v3"
with:
fetch-depth: 2
- name: "Install PHP with Xdebug"
uses: "shivammathur/setup-php@v2"
with:
php-version: "${{ matrix.php }}"
coverage: "xdebug"
tools: composer:v2
extensions: tidy
ini-values: "date.timezone=Europe/Paris"
env:
SYMFONY_PHPUNIT_VERSION: 7.5
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@v2"
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"
- 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 ${{ matrix.php }})"
runs-on: "ubuntu-20.04"
strategy:
matrix:
php:
- "7.2"
steps:
- name: "Checkout"
uses: "actions/checkout@v3"
with:
fetch-depth: 2
- name: "Install PHP"
uses: "shivammathur/setup-php@v2"
with:
php-version: "${{ 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@v2"
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"
+1
View File
@@ -2,4 +2,5 @@ vendor/
coverage/
composer.lock
.php_cs.cache
.php-cs-fixer.cache
.phpunit.result.cache
+8 -7
View File
@@ -1,6 +1,11 @@
<?php
return PhpCsFixer\Config::create()
$finder = (new PhpCsFixer\Finder())
->in(__DIR__)
->exclude(['vendor', 'var', 'web'])
;
return (new PhpCsFixer\Config())
->setUsingCache(true)
->setRiskyAllowed(true)
->setRules([
@@ -9,7 +14,7 @@ return PhpCsFixer\Config::create()
'array_syntax' => ['syntax' => 'short'],
'combine_consecutive_unsets' => true,
'heredoc_to_nowdoc' => true,
'no_extra_consecutive_blank_lines' => ['break', 'continue', 'extra', 'return', 'throw', 'use', 'parenthesis_brace_block', 'square_brace_block', 'curly_brace_block'],
'no_extra_blank_lines' => ['tokens' => ['break', 'continue', 'extra', 'return', 'throw', 'use', 'parenthesis_brace_block', 'square_brace_block', 'curly_brace_block']],
'no_unreachable_default_argument_value' => true,
'no_useless_else' => true,
'no_useless_return' => true,
@@ -22,9 +27,5 @@ return PhpCsFixer\Config::create()
'strict_param' => true,
'concat_space' => ['spacing' => 'one'],
])
->setFinder(
PhpCsFixer\Finder::create()
->exclude(['vendor'])
->in(__DIR__)
)
->setFinder($finder)
;
-12
View File
@@ -1,12 +0,0 @@
tools:
external_code_coverage: false
build:
nodes:
analysis:
tests:
override:
- php-scrutinizer-run
environment:
php:
version: 7.2
-34
View File
@@ -1,34 +0,0 @@
dist: xenial
os: linux
language: php
# avoid double Travis build when the PR is created on upstream
if: |
type = pull_request OR \
branch = master
jobs:
include:
- php: 8.0
env: SYMFONY_PHPUNIT_VERSION=7.5
fast_finish: true
allow_failures:
- php: 8.0
cache:
directories:
- $HOME/.composer/cache/files
before_install:
- if [ -n "$GH_TOKEN" ]; then composer config github-oauth.github.com ${GH_TOKEN}; fi;
install:
- if [ "$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:
- mkdir -p build/logs
script:
- php vendor/bin/simple-phpunit -v
+1 -2
View File
@@ -1,12 +1,11 @@
# 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)
[![License](https://poser.pugx.org/j0k3r/php-readability/license)](https://packagist.org/packages/j0k3r/php-readability)
This is an extract of the Readability class from this [full-text-rss](https://github.com/Dither/full-text-rss) fork. It can be defined as a better version of the original [php-readability](https://bitbucket.org/fivefilters/php-readability/overview).
This is an extract of the Readability class from this [full-text-rss](https://github.com/Dither/full-text-rss) fork. It can be defined as a better version of the original [php-readability](https://bitbucket.org/fivefilters/php-readability).
## Differences
+13 -4
View File
@@ -24,15 +24,18 @@
"role": "Developer (original JS version)"
}],
"require": {
"php": ">=5.6.0",
"php": ">=7.2.0",
"ext-mbstring": "*",
"psr/log": "^1.0",
"psr/log": "^1.0.1 || ^2.0 || ^3.0",
"masterminds/html5": "^2.7"
},
"require-dev": {
"friendsofphp/php-cs-fixer": "^2.14",
"friendsofphp/php-cs-fixer": "^3.0",
"monolog/monolog": "^1.24|^2.1",
"symfony/phpunit-bridge": "^4.2.3"
"symfony/phpunit-bridge": "^4.4|^5.3|^6.0",
"phpstan/phpstan": "^1.3",
"phpstan/phpstan-phpunit": "^1.0",
"rector/rector": "^0.15.0"
},
"suggest": {
"ext-tidy": "Used to clean up given HTML and to avoid problems with bad HTML structure."
@@ -42,5 +45,11 @@
},
"autoload-dev": {
"psr-4": { "Tests\\Readability\\": "tests/" }
},
"scripts": {
"fix": "php-cs-fixer fix --verbose --diff",
"phpstan": "phpstan analyze --memory-limit 512M",
"rector": "rector process",
"test": "simple-phpunit -v"
}
}
+3 -1
View File
@@ -6,7 +6,9 @@ parameters:
# https://github.com/phpstan/phpstan/issues/694#issuecomment-350724288
bootstrapFiles:
- vendor/bin/.phpunit/phpunit-7.5-0/vendor/autoload.php
- vendor/bin/.phpunit/phpunit/vendor/autoload.php
checkMissingIterableValueType: false
includes:
- vendor/phpstan/phpstan-phpunit/extension.neon
+1 -1
View File
@@ -11,7 +11,7 @@
>
<testsuites>
<testsuite name="Readability Test Suite">
<testsuite name="Readability">
<directory>./tests/</directory>
</testsuite>
</testsuites>
+31
View File
@@ -0,0 +1,31 @@
<?php
declare(strict_types=1);
use Rector\Config\RectorConfig;
use Rector\Core\ValueObject\PhpVersion;
use Rector\Set\ValueObject\LevelSetList;
return static function (RectorConfig $rectorConfig): void {
// paths to refactor; solid alternative to CLI arguments
$rectorConfig->paths([
__DIR__ . '/src',
__DIR__ . '/tests',
]);
// Path to phpstan with extensions, that PHPSTan in Rector uses to determine types
$rectorConfig->phpstanConfig(__DIR__ . '/phpstan.neon');
$rectorConfig->bootstrapFiles([
__DIR__ . '/vendor/bin/.phpunit/phpunit/vendor/autoload.php',
__DIR__ . '/vendor/autoload.php',
]);
// Define what rule sets will be applied
$rectorConfig->sets([
LevelSetList::UP_TO_PHP_72,
]);
// is your PHP version different from the one your refactor to?
$rectorConfig->phpVersion(PhpVersion::PHP_72);
};
+11 -8
View File
@@ -39,23 +39,25 @@ class JSLikeHTMLElement extends \DOMElement
/**
* Used for setting innerHTML like it's done in JavaScript:.
*
* @code
* ```php
* $div->innerHTML = '<h2>Chapter 2</h2><p>The story begins...</p>';
* @endcode
* ```
*/
public function __set($name, $value)
{
if ('innerHTML' !== $name) {
$trace = debug_backtrace();
trigger_error('Undefined property via __set(): ' . $name . ' in ' . $trace[0]['file'] . ' on line ' . $trace[0]['line'], E_USER_NOTICE);
trigger_error('Undefined property via __set(): ' . $name . ' in ' . $trace[0]['file'] . ' on line ' . $trace[0]['line'], \E_USER_NOTICE);
return;
}
// first, empty the element
if (isset($this->childNodes)) {
for ($x = $this->childNodes->length - 1; $x >= 0; --$x) {
$this->removeChild($this->childNodes->item($x));
}
}
// $value holds our new inner HTML
$value = trim($value);
@@ -77,14 +79,13 @@ class JSLikeHTMLElement extends \DOMElement
} else {
// $value is probably ill-formed
$f = new \DOMDocument();
$value = mb_convert_encoding($value, 'HTML-ENTITIES', 'UTF-8');
// Using <htmlfragment> will generate a warning, but so will bad HTML
// (and by this point, bad HTML is what we've got).
// We use it (and suppress the warning) because an HTML fragment will
// be wrapped around <html><body> tags which we don't really want to keep.
// Note: despite the warning, if loadHTML succeeds it will return true.
$result = $f->loadHTML('<htmlfragment>' . $value . '</htmlfragment>');
$result = $f->loadHTML('<meta charset="utf-8"><htmlfragment>' . $value . '</htmlfragment>');
if ($result) {
$import = $f->getElementsByTagName('htmlfragment')->item(0);
@@ -103,24 +104,26 @@ class JSLikeHTMLElement extends \DOMElement
/**
* Used for getting innerHTML like it's done in JavaScript:.
*
* @code
* ```php
* $string = $div->innerHTML;
* @endcode
* ```
*/
public function __get($name)
{
if ('innerHTML' === $name) {
$inner = '';
if (isset($this->childNodes)) {
foreach ($this->childNodes as $child) {
$inner .= $this->ownerDocument->saveXML($child);
}
}
return $inner;
}
$trace = debug_backtrace();
trigger_error('Undefined property via __get(): ' . $name . ' in ' . $trace[0]['file'] . ' on line ' . $trace[0]['line'], E_USER_NOTICE);
trigger_error('Undefined property via __get(): ' . $name . ' in ' . $trace[0]['file'] . ' on line ' . $trace[0]['line'], \E_USER_NOTICE);
}
public function __toString()
+315 -254
View File
@@ -7,68 +7,25 @@ use Psr\Log\LoggerAwareInterface;
use Psr\Log\LoggerInterface;
use Psr\Log\NullLogger;
/**
* Arc90's Readability ported to PHP for FiveFilters.org
* Based on readability.js version 1.7.1 (without multi-page support)
* ------------------------------------------------------
* Original URL: http://lab.arc90.com/experiments/readability/js/readability.js
* Arc90's project URL: http://lab.arc90.com/experiments/readability/
* JS Source: http://code.google.com/p/arc90labs-readability
* Ported by: Keyvan Minoukadeh, http://www.keyvan.net
* Modded by: Dither, https://dithersky.wordpress.com
* More information: http://fivefilters.org/content-only/
* License: Apache License, Version 2.0
* Requires: PHP version 5.2.0+
* Date: 2013-08-02.
*
* Differences between the PHP port and the original
* ------------------------------------------------------
* Arc90's Readability is designed to run in the browser. It works on the DOM
* tree (the parsed HTML) after the page's CSS styles have been applied and
* Javascript code executed. This PHP port does not run inside a browser.
* We use PHP's ability to parse HTML to build our DOM tree, but we cannot
* rely on CSS or Javascript support. As such, the results will not always
* match Arc90's Readability. (For example, if a web page contains CSS style
* rules or Javascript code which hide certain HTML elements from display,
* Arc90's Readability will dismiss those from consideration but our PHP port,
* unable to understand CSS or Javascript, will not know any better.)
*
* Another significant difference is that the aim of Arc90's Readability is
* to re-present the main content block of a given web page so users can
* read it more easily in their browsers. Correct identification, clean up,
* and separation of the content block is only a part of this process.
* This PHP port is only concerned with this part, it does not include code
* that relates to presentation in the browser - Arc90 already do
* that extremely well, and for PDF output there's FiveFilters.org's
* PDF Newspaper: http://fivefilters.org/pdf-newspaper/.
*
* Finally, this class contains methods that might be useful for developers
* working on HTML document fragments. So without deviating too much from
* the original code (which I don't want to do because it makes debugging
* and updating more difficult), I've tried to make it a little more
* developer friendly. You should be able to use the methods here on
* existing DOMElement objects without passing an entire HTML document to
* be parsed.
*/
class Readability implements LoggerAwareInterface
{
// flags
const FLAG_STRIP_UNLIKELYS = 1;
const FLAG_WEIGHT_ATTRIBUTES = 2;
const FLAG_CLEAN_CONDITIONALLY = 4;
const FLAG_DISABLE_PREFILTER = 8;
const FLAG_DISABLE_POSTFILTER = 16;
public const FLAG_STRIP_UNLIKELYS = 1;
public const FLAG_WEIGHT_ATTRIBUTES = 2;
public const FLAG_CLEAN_CONDITIONALLY = 4;
public const FLAG_DISABLE_PREFILTER = 8;
public const FLAG_DISABLE_POSTFILTER = 16;
// constants
const SCORE_CHARS_IN_PARAGRAPH = 100;
const SCORE_WORDS_IN_PARAGRAPH = 20;
const GRANDPARENT_SCORE_DIVISOR = 2;
const MIN_PARAGRAPH_LENGTH = 20;
const MIN_COMMAS_IN_PARAGRAPH = 6;
const MIN_ARTICLE_LENGTH = 200;
const MIN_NODE_LENGTH = 80;
const MAX_LINK_DENSITY = 0.25;
public const SCORE_CHARS_IN_PARAGRAPH = 100;
public const SCORE_WORDS_IN_PARAGRAPH = 20;
public const GRANDPARENT_SCORE_DIVISOR = 2;
public const MIN_PARAGRAPH_LENGTH = 20;
public const MIN_COMMAS_IN_PARAGRAPH = 6;
public const MIN_ARTICLE_LENGTH = 200;
public const MIN_NODE_LENGTH = 80;
public const MAX_LINK_DENSITY = 0.25;
public $convertLinksToFootnotes = false;
public $revertForcedParagraphElements = true;
public $revertForcedParagraphElements = false;
public $articleTitle;
public $articleContent;
public $original_html;
@@ -89,14 +46,27 @@ class Readability implements LoggerAwareInterface
* Defined up here so we don't instantiate them repeatedly in loops.
*/
public $regexps = [
'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',
'unlikelyCandidates' => '/-ad-|ai2html|banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|footer|gdpr|header|legends|menu|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote/i',
'okMaybeItsACandidate' => '/article\b|contain|\bcontent|column|general|detail|shadow|lightbox|blog|body|entry|main|page|footnote|element/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|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|openload\.co|viddler)\.(?:com|be|org|net)/!i',
'skipFootnoteLink' => '/^\s*(\[?[a-z0-9]{1,2}\]?|^|edit|citation needed)\s*$/i',
'hasContent' => '/\S$/',
'isNotVisible' => '/display\s*:\s*none/',
];
public $defaultTagsToScore = ['section', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'td', 'pre'];
// The commented out elements qualify as phrasing content but tend to be
// removed by readability when put into paragraphs, so we ignore them here.
public $phrasingElements = [
// "CANVAS", "IFRAME", "SVG", "VIDEO",
'ABBR', 'AUDIO', 'B', 'BDO', 'BR', 'BUTTON', 'CITE', 'CODE', 'DATA',
'DATALIST', 'DFN', 'EM', 'EMBED', 'I', 'IMG', 'INPUT', 'KBD', 'LABEL',
'MARK', 'MATH', 'METER', 'NOSCRIPT', 'OBJECT', 'OUTPUT', 'PROGRESS', 'Q',
'RUBY', 'SAMP', 'SCRIPT', 'SELECT', 'SMALL', 'SPAN', 'STRONG', 'SUB',
'SUP', 'TEXTAREA', 'TIME', 'VAR', 'WBR',
];
public $tidy_config = [
'tidy-mark' => false,
@@ -105,7 +75,7 @@ class Readability implements LoggerAwareInterface
'numeric-entities' => false,
// 'preserve-entities' => true,
'break-before-br' => false,
'clean' => true,
'clean' => false,
'output-xhtml' => true,
'logical-emphasis' => true,
'show-body-only' => false,
@@ -137,10 +107,6 @@ class Readability implements LoggerAwareInterface
protected $useTidy;
// raw HTML filters
protected $pre_filters = [
// remove obvious scripts
'!<script[^>]*>(.*?)</script>!is' => '',
// remove obvious styles
'!<style[^>]*>(.*?)</style>!is' => '',
// remove spans as we redefine styles and they're probably special-styled
'!</?span[^>]*>!is' => '',
// HACK: firewall-filtered content
@@ -157,7 +123,7 @@ class Readability implements LoggerAwareInterface
// replace excessive br's
'/<br\s*\/?>\s*<p/i' => '<p',
// replace empty tags that break layouts
'!<(?:a|div|p)[^>]+/>!is' => '',
'!<(?: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
@@ -174,20 +140,19 @@ class Readability implements LoggerAwareInterface
* @param string $html UTF-8 encoded string
* @param string $url URL associated with HTML (for footnotes)
* @param string $parser Which parser to use for turning raw HTML into a DOMDocument
* @param bool $use_tidy Use tidy
* @param bool $useTidy Use tidy
*/
public function __construct($html, $url = null, $parser = 'libxml', $use_tidy = true)
public function __construct(string $html, string $url = null, string $parser = 'libxml', bool $useTidy = true)
{
$this->url = $url;
$this->html = $html;
$this->parser = $parser;
$this->useTidy = $use_tidy && \function_exists('tidy_parse_string');
$this->useTidy = $useTidy && \function_exists('tidy_parse_string');
$this->logger = new NullLogger();
$this->loadHtml();
}
public function setLogger(LoggerInterface $logger)
public function setLogger(LoggerInterface $logger): void
{
$this->logger = $logger;
}
@@ -218,7 +183,7 @@ class Readability implements LoggerAwareInterface
* @param string $filter RegExp for replace
* @param string $replacer Replacer
*/
public function addPreFilter($filter, $replacer = '')
public function addPreFilter(string $filter, string $replacer = ''): void
{
$this->pre_filters[$filter] = $replacer;
}
@@ -229,7 +194,7 @@ class Readability implements LoggerAwareInterface
* @param string $filter RegExp for replace
* @param string $replacer Replacer
*/
public function addPostFilter($filter, $replacer = '')
public function addPostFilter(string $filter, string $replacer = ''): void
{
$this->post_filters[$filter] = $replacer;
}
@@ -246,8 +211,10 @@ class Readability implements LoggerAwareInterface
*
* @return bool true if we found content, false otherwise
*/
public function init()
public function init(): bool
{
$this->loadHtml();
if (!isset($this->dom->documentElement)) {
return false;
}
@@ -291,6 +258,11 @@ class Readability implements LoggerAwareInterface
$innerDiv->appendChild($articleContent);
$overlay->appendChild($innerDiv);
// without tidy the body can (sometimes) be wiped, so re-create it
if (false === isset($this->body->childNodes)) {
$this->body = $this->dom->createElement('body');
}
// Clear the old HTML, insert the new content.
$this->body->setInnerHtml('');
$this->body->appendChild($overlay);
@@ -307,7 +279,7 @@ class Readability implements LoggerAwareInterface
/**
* Run any post-process modifications to article content as necessary.
*/
public function postProcessContent(\DOMElement $articleContent)
public function postProcessContent(\DOMElement $articleContent): void
{
if ($this->convertLinksToFootnotes && !preg_match('/\bwiki/', $this->url)) {
$this->addFootnotes($articleContent);
@@ -319,7 +291,7 @@ class Readability implements LoggerAwareInterface
*
* @see http://www.roughtype.com/archives/2010/05/experiments_in.php
*/
public function addFootnotes(\DOMElement $articleContent)
public function addFootnotes(\DOMElement $articleContent): void
{
$footnotesWrapper = $this->dom->createElement('footer');
$footnotesWrapper->setAttribute('class', 'readability-footnotes');
@@ -335,9 +307,9 @@ class Readability implements LoggerAwareInterface
$footnoteLink = $articleLink->cloneNode(true);
$refLink = $this->dom->createElement('a');
$footnote = $this->dom->createElement('li');
$linkDomain = @parse_url($footnoteLink->getAttribute('href'), PHP_URL_HOST);
$linkDomain = @parse_url($footnoteLink->getAttribute('href'), \PHP_URL_HOST);
if (!$linkDomain && isset($this->url)) {
$linkDomain = @parse_url($this->url, PHP_URL_HOST);
$linkDomain = @parse_url($this->url, \PHP_URL_HOST);
}
$linkText = $this->getInnerText($articleLink);
@@ -362,7 +334,7 @@ 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);
@@ -381,7 +353,7 @@ class Readability implements LoggerAwareInterface
* Prepare the article node for display. Clean out any inline styles,
* iframes, forms, strip extraneous <p> tags, etc.
*/
public function prepArticle(\DOMNode $articleContent)
public function prepArticle(\DOMNode $articleContent): void
{
if (!$articleContent instanceof \DOMElement) {
return;
@@ -389,6 +361,9 @@ class Readability implements LoggerAwareInterface
$this->logger->debug($this->lightClean ? 'Light clean enabled.' : 'Standard clean enabled.');
$this->clean($articleContent, 'style');
$this->clean($articleContent, 'script');
$this->cleanStyles($articleContent);
$this->killBreaks($articleContent);
@@ -483,10 +458,8 @@ class Readability implements LoggerAwareInterface
* @param \DOMElement $e
* @param bool $normalizeSpaces (default: true)
* @param bool $flattenLines (default: false)
*
* @return string
*/
public function getInnerText($e, $normalizeSpaces = true, $flattenLines = false)
public function getInnerText($e, bool $normalizeSpaces = true, bool $flattenLines = false): string
{
if (null === $e || !isset($e->textContent) || '' === $e->textContent) {
return '';
@@ -495,9 +468,11 @@ class Readability implements LoggerAwareInterface
$textContent = trim($e->textContent);
if ($flattenLines) {
$textContent = mb_ereg_replace('(?:[\r\n](?:\s|&nbsp;)*)+', '', $textContent);
} elseif ($normalizeSpaces) {
$textContent = mb_ereg_replace('\s\s+', ' ', $textContent);
return (string) mb_ereg_replace('(?:[\r\n](?:\s|&nbsp;)*)+', '', $textContent);
}
if ($normalizeSpaces) {
return (string) mb_ereg_replace('\s\s+', ' ', $textContent);
}
return $textContent;
@@ -505,43 +480,31 @@ class Readability implements LoggerAwareInterface
/**
* Remove the style attribute on every $e and under.
*
* @param \DOMElement $e
*/
public function cleanStyles($e)
public function cleanStyles(\DOMElement $e): void
{
if (!\is_object($e)) {
return;
}
if (\is_object($e)) {
$elems = $e->getElementsByTagName('*');
foreach ($elems as $elem) {
$elem->removeAttribute('style');
}
}
}
/**
* Get comma number for a given text.
*
* @param string $text
*
* @return int
*/
public function getCommaCount($text)
public function getCommaCount(string $text): int
{
return substr_count($text, ',');
return \count(explode(',', $text));
}
/**
* Get words number for a given text if words separated by a space.
* Input string should be normalized.
*
* @param string $text
*
* @return int
*/
public function getWordCount($text)
public function getWordCount(string $text): int
{
return substr_count($text, ' ');
}
@@ -550,12 +513,8 @@ class Readability implements LoggerAwareInterface
* Get the density of links as a percentage of the content
* 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 bool $excludeExternal
*
* @return int
*/
public function getLinkDensity(\DOMElement $e, $excludeExternal = false)
public function getLinkDensity(\DOMElement $e, bool $excludeExternal = false): float
{
$links = $e->getElementsByTagName('a');
$textLength = mb_strlen($this->getInnerText($e, true, true));
@@ -577,10 +536,8 @@ class Readability implements LoggerAwareInterface
/**
* Get an element relative weight.
*
* @return int
*/
public function getWeight(\DOMElement $e)
public function getWeight(\DOMElement $e): int
{
if (!$this->flagIsActive(self::FLAG_WEIGHT_ATTRIBUTES)) {
return 0;
@@ -598,7 +555,7 @@ class Readability implements LoggerAwareInterface
/**
* Remove extraneous break tags from a node.
*/
public function killBreaks(\DOMElement $node)
public function killBreaks(\DOMElement $node): void
{
$html = $node->getInnerHTML();
$html = preg_replace($this->regexps['killBreaks'], '<br />', $html);
@@ -610,10 +567,8 @@ class Readability implements LoggerAwareInterface
* (Unless it's a youtube/vimeo video. People love movies.).
*
* Updated 2012-09-18 to preserve youtube/vimeo iframes
*
* @param string $tag
*/
public function clean(\DOMElement $e, $tag)
public function clean(\DOMElement $e, string $tag): void
{
$targetList = $e->getElementsByTagName($tag);
$isEmbed = ('audio' === $tag || 'video' === $tag || 'iframe' === $tag || 'object' === $tag || 'embed' === $tag);
@@ -644,10 +599,8 @@ class Readability implements LoggerAwareInterface
* Clean an element of all tags of type "tag" if they look fishy.
* "Fishy" is an algorithm based on content length, classnames,
* link density, number of images & embeds, etc.
*
* @param string $tag
*/
public function cleanConditionally(\DOMElement $e, $tag)
public function cleanConditionally(\DOMElement $e, string $tag): void
{
if (!$this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) {
return;
@@ -668,6 +621,9 @@ class Readability implements LoggerAwareInterface
$contentScore = ($node->hasAttribute('readability')) ? (int) $node->getAttribute('readability') : 0;
$this->logger->debug('Start conditional cleaning of ' . $node->getNodePath() . ' (class=' . $node->getAttribute('class') . '; id=' . $node->getAttribute('id') . ')' . (($node->hasAttribute('readability')) ? (' with score ' . $node->getAttribute('readability')) : ''));
// XXX Incomplete implementation
$isList = \in_array($node->tagName, ['ul', 'ol'], true);
if ($weight + $contentScore < 0) {
$this->logger->debug('Removing...');
$node->parentNode->removeChild($node);
@@ -702,16 +658,16 @@ class Readability implements LoggerAwareInterface
$toRemove = false;
if ($this->lightClean) {
if ($li > $p && 'ul' !== $tag && 'ol' !== $tag) {
if (!$isList && $li > $p) {
$this->logger->debug(' too many <li> elements, and parent is not <ul> or <ol>');
$toRemove = true;
} elseif ($input > floor($p / 3)) {
$this->logger->debug(' too many <input> elements');
$toRemove = true;
} elseif ($contentLength < 6 && (0 === $embedCount && (0 === $img || $img > 2))) {
} elseif (!$isList && $contentLength < 6 && (0 === $embedCount && (0 === $img || $img > 2))) {
$this->logger->debug(' content length less than 6 chars, 0 embeds and either 0 images or more than 2 images');
$toRemove = true;
} elseif ($weight < 25 && $linkDensity > 0.25) {
} elseif (!$isList && $weight < 25 && $linkDensity > 0.25) {
$this->logger->debug(' weight is ' . $weight . ' < 25 and link density is ' . sprintf('%.2f', $linkDensity) . ' > 0.25');
$toRemove = true;
} elseif ($a > 2 && ($weight >= 25 && $linkDensity > 0.5)) {
@@ -725,16 +681,16 @@ class Readability implements LoggerAwareInterface
if ($img > $p) {
$this->logger->debug(' more image elements than paragraph elements');
$toRemove = true;
} elseif ($li > $p && 'ul' !== $tag && 'ol' !== $tag) {
} elseif (!$isList && $li > $p) {
$this->logger->debug(' too many <li> elements, and parent is not <ul> or <ol>');
$toRemove = true;
} elseif ($input > floor($p / 3)) {
$this->logger->debug(' too many <input> elements');
$toRemove = true;
} elseif ($contentLength < 10 && (0 === $img || $img > 2)) {
} elseif (!$isList && $contentLength < 10 && (0 === $img || $img > 2)) {
$this->logger->debug(' content length less than 10 chars and 0 images, or more than 2 images');
$toRemove = true;
} elseif ($weight < 25 && $linkDensity > 0.2) {
} elseif (!$isList && $weight < 25 && $linkDensity > 0.2) {
$this->logger->debug(' weight is ' . $weight . ' lower than 0 and link density is ' . sprintf('%.2f', $linkDensity) . ' > 0.2');
$toRemove = true;
} elseif ($weight >= 25 && $linkDensity > 0.5) {
@@ -757,7 +713,7 @@ class Readability implements LoggerAwareInterface
/**
* Clean out spurious headers from an Element. Checks things like classnames and link density.
*/
public function cleanHeaders(\DOMElement $e)
public function cleanHeaders(\DOMElement $e): void
{
for ($headerIndex = 1; $headerIndex < 3; ++$headerIndex) {
$headers = $e->getElementsByTagName('h' . $headerIndex);
@@ -772,57 +728,28 @@ class Readability implements LoggerAwareInterface
/**
* Check if the given flag is active.
*
* @param int $flag
*
* @return bool
*/
public function flagIsActive($flag)
public function flagIsActive(int $flag): bool
{
return ($this->flags & $flag) > 0;
}
/**
* Add a flag.
*
* @param int $flag
*/
public function addFlag($flag)
public function addFlag(int $flag): void
{
$this->flags = $this->flags | $flag;
}
/**
* Remove a flag.
*
* @param int $flag
*/
public function removeFlag($flag)
public function removeFlag(int $flag): void
{
$this->flags = $this->flags & ~$flag;
}
/**
* Debug.
*
* @deprecated use $this->logger->debug() instead
* @codeCoverageIgnore
*/
protected function dbg($msg)
{
$this->logger->debug($msg);
}
/**
* Dump debug info.
*
* @deprecated since Monolog gather log, we don't need it
* @codeCoverageIgnore
*/
protected function dump_dbg()
{
}
/**
* Get the article title as an H1.
*
@@ -869,7 +796,7 @@ class Readability implements LoggerAwareInterface
* Prepare the HTML document for readability to scrape it.
* This includes things like stripping javascript, CSS, and handling terrible markup.
*/
protected function prepDocument()
protected function prepDocument(): void
{
/*
* In some cases a body element can't be found (if the HTML is totally hosed for example)
@@ -898,7 +825,7 @@ class Readability implements LoggerAwareInterface
* Initialize a node with the readability object. Also checks the
* className/id for special names to add to its score.
*/
protected function initializeNode(\DOMElement $node)
protected function initializeNode(\DOMElement $node): void
{
if (!isset($node->tagName)) {
return;
@@ -934,7 +861,7 @@ class Readability implements LoggerAwareInterface
case 'DD':
case 'DT':
case 'LI':
$readability->value -= 2 * round($this->getLinkDensity($node), 0, PHP_ROUND_HALF_UP);
$readability->value -= 3;
break;
case 'ASIDE':
case 'FOOTER':
@@ -985,22 +912,50 @@ class Readability implements LoggerAwareInterface
$allElements = $page->getElementsByTagName('*');
for ($nodeIndex = 0; ($node = $allElements->item($nodeIndex)); ++$nodeIndex) {
for ($nodeIndex = 0; $allElements->item($nodeIndex); ++$nodeIndex) {
$node = $allElements->item($nodeIndex);
$tagName = $node->tagName;
$nodeContent = $node->getInnerHTML();
if (empty($nodeContent)) {
$this->logger->debug('Skipping empty node');
continue;
}
// Remove invisible nodes
if (!$this->isNodeVisible($node)) {
$this->logger->debug('Removing invisible node ' . $node->getNodePath());
$node->parentNode->removeChild($node);
--$nodeIndex;
continue;
}
// 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)
) {
$this->logger->debug('Removing unlikely candidate (using conf) ' . $node->getNodePath() . ' by "' . $unlikelyMatchString . '"');
$node->parentNode->removeChild($node);
--$nodeIndex;
continue;
}
// Some well known site uses sections as paragraphs.
if (0 === strcasecmp($tagName, 'p') || 0 === strcasecmp($tagName, 'td') || 0 === strcasecmp($tagName, 'pre') || 0 === strcasecmp($tagName, 'section')) {
if (\in_array($tagName, $this->defaultTagsToScore, true)) {
$nodesToScore[] = $node;
}
// Turn divs into P tags where they have been used inappropriately
// (as in, where they contain no other block level elements).
if (0 === strcasecmp($tagName, 'div') || 0 === strcasecmp($tagName, 'article') || 0 === strcasecmp($tagName, 'section')) {
if (!preg_match($this->regexps['divToPElements'], $node->getInnerHTML())) {
if ('div' === $tagName) {
if (!preg_match($this->regexps['divToPElements'], $nodeContent)) {
$newNode = $this->dom->createElement('p');
try {
$newNode->setInnerHtml($node->getInnerHTML());
$newNode->setInnerHtml($nodeContent);
$node->parentNode->replaceChild($newNode, $node);
--$nodeIndex;
@@ -1010,27 +965,46 @@ class Readability implements LoggerAwareInterface
}
} else {
// Will change these P elements back to text nodes after processing.
for ($i = 0, $il = $node->childNodes->length; $i < $il; ++$i) {
$childNode = $node->childNodes->item($i);
// it looks like sometimes the loop is going too far and we are retrieving a non-existant child
if (null === $childNode) {
continue;
}
$p = null;
// foreach does not handle removeChild very well
// See https://www.php.net/manual/en/domnode.removechild.php#90292
$childs = iterator_to_array($node->childNodes);
foreach ($childs as $childNode) {
// executable tags (<?php or <?xml) warning
if (\is_object($childNode) && 'DOMProcessingInstruction' === \get_class($childNode)) {
if ($childNode instanceof \DOMProcessingInstruction) {
$childNode->parentNode->removeChild($childNode);
continue;
}
if (XML_TEXT_NODE === $childNode->nodeType) {
$p = $this->dom->createElement('p');
$p->setInnerHtml($childNode->nodeValue);
$p->setAttribute('data-readability-styled', 'true');
$childNode->parentNode->replaceChild($p, $childNode);
if ($childNode instanceof \DOMText && '' === $this->getInnerText($childNode, true, true)) {
/* $this->logger->debug('Remove empty text node'); */
$childNode->parentNode->removeChild($childNode);
continue;
}
if ($this->isPhrasingContent($childNode)) {
if (null !== $p) {
$p->appendChild($childNode);
} elseif ('' !== $this->getInnerText($childNode, true, true)) {
$p = $this->dom->createElement('p');
$p->setAttribute('data-readability-styled', 'true');
$node->replaceChild($p, $childNode);
$p->appendChild($childNode);
}
} elseif (null !== $p) {
while ($p->lastChild && '' === $this->getInnerText($p->lastChild, true, true)) {
$p->removeChild($p->lastChild);
}
$p = null;
}
}
if ($this->hasSingleTagInsideElement($node, 'p') && $this->getLinkDensity($node) < 0.25) {
$newNode = $node->childNodes->item(0);
$node->parentNode->replaceChild($newNode, $node);
$nodesToScore[] = $newNode;
}
}
}
@@ -1044,14 +1018,13 @@ class Readability implements LoggerAwareInterface
* Maybe eventually link density.
*/
for ($pt = 0, $scored = \count($nodesToScore); $pt < $scored; ++$pt) {
$parentNode = $nodesToScore[$pt]->parentNode;
$ancestors = $this->getAncestors($nodesToScore[$pt], 5);
// No parent node? Move on...
if (!$parentNode) {
if (0 === \count($ancestors)) {
continue;
}
$grandParentNode = $parentNode->parentNode instanceof \DOMElement ? $parentNode->parentNode : null;
$innerText = $this->getInnerText($nodesToScore[$pt]);
// If this paragraph is less than MIN_PARAGRAPH_LENGTH (default:20) characters, don't even count it.
@@ -1059,17 +1032,6 @@ class Readability implements LoggerAwareInterface
continue;
}
// Initialize readability data for the parent.
if (!$parentNode->hasAttribute('readability')) {
$this->initializeNode($parentNode);
$parentNode->setAttribute('data-candidate', 'true');
}
// Initialize readability data for the grandparent.
if ($grandParentNode && !$grandParentNode->hasAttribute('readability') && isset($grandParentNode->tagName)) {
$this->initializeNode($grandParentNode);
$grandParentNode->setAttribute('data-candidate', 'true');
}
// Add a point for the paragraph itself as a base.
$contentScore = 1;
// Add points for any commas within this paragraph.
@@ -1077,25 +1039,26 @@ class Readability implements LoggerAwareInterface
// For every SCORE_CHARS_IN_PARAGRAPH (default:100) characters in this paragraph, add another point. Up to 3 points.
$contentScore += min(floor(mb_strlen($innerText) / self::SCORE_CHARS_IN_PARAGRAPH), 3);
// For every SCORE_WORDS_IN_PARAGRAPH (default:20) words in this paragraph, add another point. Up to 3 points.
$contentScore += min(floor($this->getWordCount($innerText) / self::SCORE_WORDS_IN_PARAGRAPH), 3);
/* TEST: For every positive/negative parent tag, add/substract half point. Up to 3 points. *\/
$up = $nodesToScore[$pt];
$score = 0;
while ($up->parentNode instanceof \DOMElement) {
$up = $up->parentNode;
if (preg_match($this->regexps['positive'], $up->getAttribute('class') . ' ' . $up->getAttribute('id'))) {
$score += 0.5;
} elseif (preg_match($this->regexps['negative'], $up->getAttribute('class') . ' ' . $up->getAttribute('id'))) {
$score -= 0.5;
}
}
$score = floor($score);
$contentScore += max(min($score, 3), -3);/**/
// $contentScore += min(floor($this->getWordCount($innerText) / self::SCORE_WORDS_IN_PARAGRAPH), 3);
// Add the score to the parent. The grandparent gets half.
$parentNode->getAttributeNode('readability')->value += $contentScore;
if ($grandParentNode) {
$grandParentNode->getAttributeNode('readability')->value += round($contentScore / self::GRANDPARENT_SCORE_DIVISOR);
foreach ($ancestors as $level => $ancestor) {
if (!$ancestor->nodeName || !$ancestor->parentNode) {
return;
}
if (!$ancestor->hasAttribute('readability')) {
$this->initializeNode($ancestor);
$ancestor->setAttribute('data-candidate', 'true');
}
if (0 === $level) {
$scoreDivider = 1;
} elseif (1 === $level) {
$scoreDivider = 2;
} else {
$scoreDivider = $level * 3;
}
$ancestor->getAttributeNode('readability')->value += $contentScore / $scoreDivider;
}
}
@@ -1119,18 +1082,6 @@ class Readability implements LoggerAwareInterface
for ($c = $candidates->length - 1; $c >= 0; --$c) {
$node = $candidates->item($c);
// 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)
) {
$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);
--$nodeIndex;
}
}
unset($candidates);
}
@@ -1139,10 +1090,11 @@ class Readability implements LoggerAwareInterface
* After we've calculated scores, loop through all of the possible candidate nodes we found
* and find the one with the highest score.
*/
$topCandidate = null;
$topCandidates = array_fill(0, 5, null);
if ($xpath) {
// Using array of DOMElements after deletion is a path to DOOMElement.
$candidates = $xpath->query('.//*[@data-candidate]', $page->documentElement);
$this->logger->debug('Candidates: ' . $candidates->length);
for ($c = $candidates->length - 1; $c >= 0; --$c) {
$item = $candidates->item($c);
@@ -1151,16 +1103,27 @@ class Readability implements LoggerAwareInterface
// relatively small link density (5% or less) and be mostly unaffected by this operation.
// If not for this we would have used XPath to find maximum @readability.
$readability = $item->getAttributeNode('readability');
$readability->value = round($readability->value * (1 - $this->getLinkDensity($item)), 0, PHP_ROUND_HALF_UP);
$readability->value = round($readability->value * (1 - $this->getLinkDensity($item)), 0, \PHP_ROUND_HALF_UP);
if (!$topCandidate || $readability->value > (int) $topCandidate->getAttribute('readability')) {
for ($t = 0; $t < 5; ++$t) {
$aTopCandidate = $topCandidates[$t];
if (!$aTopCandidate || $readability->value > (int) $aTopCandidate->getAttribute('readability')) {
$this->logger->debug('Candidate: ' . $item->getNodePath() . ' (' . $item->getAttribute('class') . ':' . $item->getAttribute('id') . ') with score ' . $readability->value);
$topCandidate = $item;
array_splice($topCandidates, $t, 0, [$item]);
if (\count($topCandidates) > 5) {
array_pop($topCandidates);
}
break;
}
}
}
}
unset($candidates);
}
$topCandidates = array_filter($topCandidates, function ($v, $idx) {
return 0 === $idx || null !== $v;
}, \ARRAY_FILTER_USE_BOTH);
$topCandidate = $topCandidates[0];
/*
* If we still have no top candidate, just use the body as a last resort.
@@ -1187,6 +1150,59 @@ class Readability implements LoggerAwareInterface
}
$this->initializeNode($topCandidate);
} elseif ($topCandidate) {
$alternativeCandidateAncestors = [];
foreach ($topCandidates as $candidate) {
if ((int) $candidate->getAttribute('readability') / (int) $topCandidate->getAttribute('readability') >= 0.75) {
$ancestors = $this->getAncestors($candidate);
$this->logger->debug('Adding ' . \count($ancestors) . ' alternative ancestors for ' . $candidate->getNodePath());
$alternativeCandidateAncestors[] = $ancestors;
}
}
if (\count($alternativeCandidateAncestors) >= 3) {
$parentOfTopCandidate = $topCandidate->parentNode;
while ('body' !== $parentOfTopCandidate->nodeName) {
$listsContainingThisAncestor = 0;
for ($ancestorIndex = 0; $ancestorIndex < \count($alternativeCandidateAncestors) && $listsContainingThisAncestor < 3; ++$ancestorIndex) {
$listsContainingThisAncestor += (int) \in_array($parentOfTopCandidate, $alternativeCandidateAncestors[$ancestorIndex], true);
}
if ($listsContainingThisAncestor >= 3) {
$topCandidate = $parentOfTopCandidate;
break;
}
$parentOfTopCandidate = $parentOfTopCandidate->parentNode;
}
}
if (!$topCandidate->hasAttribute('readability')) {
$this->initializeNode($topCandidate);
}
$parentOfTopCandidate = $topCandidate->parentNode;
$lastScore = (int) $topCandidate->getAttribute('readability');
$scoreThreshold = $lastScore / 3;
while ('body' !== $parentOfTopCandidate->nodeName) {
if (!$parentOfTopCandidate->hasAttribute('readability')) {
$parentOfTopCandidate = $parentOfTopCandidate->parentNode;
continue;
}
$parentScore = (int) $parentOfTopCandidate->getAttribute('readability');
if ($parentScore < $scoreThreshold) {
break;
}
if ($parentScore > $lastScore) {
$topCandidate = $parentOfTopCandidate;
break;
}
$lastScore = (int) $parentOfTopCandidate->getAttribute('readability');
$parentOfTopCandidate = $parentOfTopCandidate->parentNode;
}
$parentOfTopCandidate = $topCandidate->parentNode;
while ('body' !== $parentOfTopCandidate->nodeName && 1 === $parentOfTopCandidate->childNodes->length) {
$topCandidate = $parentOfTopCandidate;
$parentOfTopCandidate = $topCandidate->parentNode;
}
if (!$topCandidate->hasAttribute('readability')) {
$this->initializeNode($topCandidate);
}
}
// Set table as the main node if resulted data is table element.
@@ -1212,9 +1228,10 @@ class Readability implements LoggerAwareInterface
$articleContent = $this->dom->createElement('div');
$articleContent->setAttribute('class', 'readability-content');
$siblingScoreThreshold = max(10, ((int) $topCandidate->getAttribute('readability')) * 0.2);
$siblingNodes = $topCandidate->parentNode->childNodes;
$parentOfTopCandidate = $topCandidate->parentNode;
$siblingNodes = $parentOfTopCandidate->childNodes;
if (null === $siblingNodes) {
if (0 === $siblingNodes->length) {
$siblingNodes = new \stdClass();
$siblingNodes->length = 0;
}
@@ -1223,33 +1240,31 @@ class Readability implements LoggerAwareInterface
$siblingNode = $siblingNodes->item($s);
$siblingNodeName = $siblingNode->nodeName;
$append = false;
$this->logger->debug('Looking at sibling node: ' . $siblingNode->getNodePath() . ((XML_ELEMENT_NODE === $siblingNode->nodeType && $siblingNode->hasAttribute('readability')) ? (' with score ' . $siblingNode->getAttribute('readability')) : ''));
$this->logger->debug('Looking at sibling node: ' . $siblingNode->getNodePath() . ((\XML_ELEMENT_NODE === $siblingNode->nodeType && $siblingNode->hasAttribute('readability')) ? (' with score ' . $siblingNode->getAttribute('readability')) : ''));
if ($siblingNode->isSameNode($topCandidate)) {
$append = true;
}
} else {
$contentBonus = 0;
// Give a bonus if sibling nodes and top candidates have the same classname.
if (XML_ELEMENT_NODE === $siblingNode->nodeType && $siblingNode->getAttribute('class') === $topCandidate->getAttribute('class') && '' !== $topCandidate->getAttribute('class')) {
if (\XML_ELEMENT_NODE === $siblingNode->nodeType && $siblingNode->getAttribute('class') === $topCandidate->getAttribute('class') && '' !== $topCandidate->getAttribute('class')) {
$contentBonus += ((int) $topCandidate->getAttribute('readability')) * 0.2;
}
if (XML_ELEMENT_NODE === $siblingNode->nodeType && $siblingNode->hasAttribute('readability') && (((int) $siblingNode->getAttribute('readability')) + $contentBonus) >= $siblingScoreThreshold) {
if (\XML_ELEMENT_NODE === $siblingNode->nodeType && $siblingNode->hasAttribute('readability') && (((int) $siblingNode->getAttribute('readability')) + $contentBonus) >= $siblingScoreThreshold) {
$append = true;
}
if (0 === strcasecmp($siblingNodeName, 'p')) {
$linkDensity = $this->getLinkDensity($siblingNode);
} elseif (0 === strcasecmp($siblingNodeName, 'p')) {
$linkDensity = (int) $this->getLinkDensity($siblingNode);
$nodeContent = $this->getInnerText($siblingNode, true, true);
$nodeLength = mb_strlen($nodeContent);
if (($nodeLength > self::MIN_NODE_LENGTH && $linkDensity < self::MAX_LINK_DENSITY)
|| ($nodeLength < self::MIN_NODE_LENGTH && 0 === $linkDensity && preg_match('/\.( |$)/', $nodeContent))) {
|| ($nodeLength < self::MIN_NODE_LENGTH && 0 === $nodeLength && 0 === $linkDensity && preg_match('/\.( |$)/', $nodeContent))) {
$append = true;
}
}
}
if ($append) {
$this->logger->debug('Appending node: ' . $siblingNode->getNodePath());
@@ -1323,12 +1338,8 @@ class Readability implements LoggerAwareInterface
/**
* Get an element weight by attribute.
* Uses regular expressions to tell if this element looks good or bad.
*
* @param string $attribute
*
* @return int
*/
protected function weightAttribute(\DOMElement $element, $attribute)
protected function weightAttribute(\DOMElement $element, string $attribute): int
{
if (!$element->hasAttribute($attribute)) {
return 0;
@@ -1359,7 +1370,7 @@ class Readability implements LoggerAwareInterface
/**
* Will recreate previously deleted body property.
*/
protected function reinitBody()
protected function reinitBody(): void
{
if (!isset($this->body->childNodes)) {
$this->body = $this->dom->createElement('body');
@@ -1371,17 +1382,15 @@ class Readability implements LoggerAwareInterface
* Load HTML in a DOMDocument.
* Apply Pre filters
* Cleanup HTML using Tidy (or not).
*
* @todo This should be called in init() instead of from __construct
*/
private function loadHtml()
private function loadHtml(): void
{
$this->original_html = $this->html;
$this->logger->debug('Parsing URL: ' . $this->url);
if ($this->url) {
$this->domainRegExp = '/' . strtr(preg_replace('/www\d*\./', '', parse_url($this->url, PHP_URL_HOST)), ['.' => '\.']) . '/';
$this->domainRegExp = '/' . strtr((string) preg_replace('/www\d*\./', '', (string) parse_url($this->url, \PHP_URL_HOST)), ['.' => '\.']) . '/';
}
mb_internal_encoding('UTF-8');
@@ -1417,7 +1426,7 @@ class Readability implements LoggerAwareInterface
unset($tidy);
}
$this->html = mb_convert_encoding($this->html, 'HTML-ENTITIES', 'UTF-8');
$this->html = '<meta charset="utf-8">' . (string) $this->html;
if ('html5lib' === $this->parser || 'html5' === $this->parser) {
$this->dom = (new HTML5())->loadHTML($this->html);
@@ -1428,11 +1437,63 @@ class Readability implements LoggerAwareInterface
$this->dom = new \DOMDocument();
$this->dom->preserveWhiteSpace = false;
$this->dom->loadHTML($this->html, LIBXML_NOBLANKS | LIBXML_COMPACT | LIBXML_NOERROR);
$this->dom->loadHTML($this->html, \LIBXML_NOBLANKS | \LIBXML_COMPACT | \LIBXML_NOERROR);
libxml_use_internal_errors(false);
}
$this->dom->registerNodeClass('DOMElement', 'Readability\JSLikeHTMLElement');
$this->dom->registerNodeClass(\DOMElement::class, \Readability\JSLikeHTMLElement::class);
}
private function getAncestors(\DOMElement $node, int $maxDepth = 0): array
{
$ancestors = [];
$i = 0;
while ($node->parentNode instanceof \DOMElement) {
$ancestors[] = $node->parentNode;
if (++$i === $maxDepth) {
break;
}
$node = $node->parentNode;
}
return $ancestors;
}
private function isPhrasingContent($node): bool
{
return \XML_TEXT_NODE === $node->nodeType
|| \in_array(strtoupper($node->nodeName), $this->phrasingElements, true)
|| (\in_array(strtoupper($node->nodeName), ['A', 'DEL', 'INS'], true) && !\in_array(false, array_map(function ($c) {
return $this->isPhrasingContent($c);
}, iterator_to_array($node->childNodes)), true));
}
private function hasSingleTagInsideElement(\DOMElement $node, string $tag): bool
{
if (1 !== $node->childNodes->length || $node->childNodes->item(0)->nodeName !== $tag) {
return false;
}
$a = array_filter(iterator_to_array($node->childNodes), function ($childNode) {
return $childNode instanceof \DOMText &&
preg_match($this->regexps['hasContent'], $this->getInnerText($childNode));
});
return 0 === \count($a);
}
/**
* Return whether a given node is visible or not.
*
* Tidy must be configured to not clean the input for this function to
* work as expected, see $this->tidy_config['clean']
*/
private function isNodeVisible(\DOMElement $node): bool
{
return !($node->hasAttribute('style')
&& preg_match($this->regexps['isNotVisible'], $node->getAttribute('style'))
)
&& !$node->hasAttribute('hidden');
}
}
+210 -143
View File
@@ -4,120 +4,129 @@ namespace Tests\Readability;
use Monolog\Handler\TestHandler;
use Monolog\Logger;
use Psr\Log\LoggerInterface;
use Readability\JSLikeHTMLElement;
use Readability\Readability;
class ReadabilityTest extends \PHPUnit\Framework\TestCase
{
/** @var TestHandler */
public $logHandler;
/** @var LoggerInterface */
public $logger;
/**
* @requires extension tidy
*/
public function testConstructDefault()
public function testConstructDefault(): void
{
$readability = $this->getReadability('');
$readability->init();
$this->assertNull($readability->url);
$this->assertInstanceOf('DomDocument', $readability->dom);
}
public function testConstructHtml5Parser()
public function testConstructHtml5Parser(): void
{
$readability = $this->getReadability('<html/>', 'http://0.0.0.0', 'html5lib');
$readability->init();
$this->assertEquals('http://0.0.0.0', $readability->url);
$this->assertSame('http://0.0.0.0', $readability->url);
$this->assertInstanceOf('DomDocument', $readability->dom);
$this->assertEquals('<html/>', $readability->original_html);
$this->assertSame('<html/>', $readability->original_html);
}
/**
* @requires extension tidy
*/
public function testConstructSimple()
public function testConstructSimple(): void
{
$readability = $this->getReadability('<html/>', 'http://0.0.0.0');
$readability->init();
$this->assertEquals('http://0.0.0.0', $readability->url);
$this->assertSame('http://0.0.0.0', $readability->url);
$this->assertInstanceOf('DomDocument', $readability->dom);
$this->assertEquals('<html/>', $readability->original_html);
$this->assertSame('<html/>', $readability->original_html);
$this->assertTrue($readability->tidied);
}
public function testConstructDefaultWithoutTidy()
public function testConstructDefaultWithoutTidy(): void
{
$readability = $this->getReadability('', null, 'libxml', false);
$readability->init();
$this->assertNull($readability->url);
$this->assertEquals('', $readability->original_html);
$this->assertSame('', $readability->original_html);
$this->assertFalse($readability->tidied);
$this->assertInstanceOf('DomDocument', $readability->dom);
}
public function testConstructSimpleWithoutTidy()
public function testConstructSimpleWithoutTidy(): void
{
$readability = $this->getReadability('<html/>', 'http://0.0.0.0', 'libxml', false);
$readability->init();
$this->assertEquals('http://0.0.0.0', $readability->url);
$this->assertSame('http://0.0.0.0', $readability->url);
$this->assertInstanceOf('DomDocument', $readability->dom);
$this->assertEquals('<html/>', $readability->original_html);
$this->assertSame('<html/>', $readability->original_html);
$this->assertFalse($readability->tidied);
}
public function testInitNoContent()
public function testInitNoContent(): void
{
$readability = $this->getReadability('<html/>', 'http://0.0.0.0');
$res = $readability->init();
$this->assertFalse($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('Sorry, Readability was unable to parse this page for content.', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('Sorry, Readability was unable to parse this page for content.', $readability->getContent()->getInnerHtml());
}
public function testInitP()
public function testInitP(): void
{
$readability = $this->getReadability(str_repeat('<p>This is the awesome content :)</p>', 7), 'http://0.0.0.0');
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is the awesome content :)', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is the awesome content :)', $readability->getContent()->getInnerHtml());
}
public function testInitDivP()
public function testInitDivP(): void
{
$readability = $this->getReadability('<div>' . str_repeat('<p>This is the awesome content :)</p>', 7) . '</div>', 'http://0.0.0.0');
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is the awesome content :)', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is the awesome content :)', $readability->getContent()->getInnerHtml());
}
public function testInitDiv()
public function testInitDiv(): void
{
$readability = $this->getReadability('<div>' . str_repeat('This is the awesome content :)', 7) . '</div>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is the awesome content :)', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is the awesome content :)', $readability->getContent()->getInnerHtml());
}
public function testWithFootnotes()
public function testWithFootnotes(): void
{
$readability = $this->getReadability('<div>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '</div>', 'http://0.0.0.0');
$readability->debug = true;
@@ -125,16 +134,16 @@ class ReadabilityTest extends \PHPUnit\Framework\TestCase
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertContains('readabilityFootnoteLink', $readability->getContent()->getInnerHtml());
$this->assertContains('readabilityLink-3', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('readabilityFootnoteLink', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('readabilityLink-3', $readability->getContent()->getInnerHtml());
}
public function testStandardClean()
public function testStandardClean(): void
{
$readability = $this->getReadability('<div><h2>Title</h2>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<a href="#nofollow" rel="nofollow">will NOT be removed</a></div>', 'http://0.0.0.0');
$readability->debug = true;
@@ -142,76 +151,76 @@ class ReadabilityTest extends \PHPUnit\Framework\TestCase
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertContains('will NOT be removed', $readability->getContent()->getInnerHtml());
$this->assertNotContains('<h2>', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('will NOT be removed', $readability->getContent()->getInnerHtml());
$this->assertStringNotContainsString('<h2>', $readability->getContent()->getInnerHtml());
}
public function testWithIframe()
public function testWithIframe(): void
{
$readability = $this->getReadability('<div><h2>Title</h2>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<p>This is an awesome text with some links, here there are <iframe src="http://youtube.com/test" href="#nofollow" rel="nofollow"></iframe><iframe>http://soundcloud.com/test</iframe></p></div>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('<div readability=', $readability->getContent()->getInnerHtml());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertContains('nofollow', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('nofollow', $readability->getContent()->getInnerHtml());
}
public function testWithArticle()
public function testWithArticle(): void
{
$readability = $this->getReadability('<article><p>' . str_repeat('This is an awesome text with some links, here there are: the awesome', 20) . '</p><p>This is an awesome text with some links, here there are <iframe src="http://youtube.com/test" href="#nofollow" rel="nofollow"></iframe></p></article>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('alt="article"', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('alt="article"', $readability->getContent()->getInnerHtml());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertContains('nofollow', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('nofollow', $readability->getContent()->getInnerHtml());
}
public function testWithAside()
public function testWithAside(): void
{
$readability = $this->getReadability('<article>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<footer><aside>' . str_repeat('<p>This is an awesome text with some links, here there are</p>', 8) . '</aside></footer></article>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertEmpty($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="5"/>', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringNotContainsString('<aside>', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('<footer readability="9"/>', $readability->getContent()->getInnerHtml());
}
public function testWithClasses()
public function testWithClasses(): void
{
$readability = $this->getReadability('<article>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<div style="display:none">' . str_repeat('<p class="clock">This text should be removed</p>', 10) . '</div></article>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('alt="article"', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('alt="article"', $readability->getContent()->getInnerHtml());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertNotContains('This text should be removed', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringNotContainsString('This text should be removed', $readability->getContent()->getInnerHtml());
}
public function testWithClassesWithoutLightClean()
public function testWithClassesWithoutLightClean(): void
{
$readability = $this->getReadability('<article>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<div style="display:none">' . str_repeat('<p class="clock">This text should be removed</p>', 10) . '</div></article>', 'http://0.0.0.0');
$readability->debug = true;
@@ -219,123 +228,121 @@ class ReadabilityTest extends \PHPUnit\Framework\TestCase
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('alt="article"', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('alt="article"', $readability->getContent()->getInnerHtml());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertNotContains('This text should be removed', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringNotContainsString('This text should be removed', $readability->getContent()->getInnerHtml());
}
public function testWithTd()
public function testWithTd(): void
{
$readability = $this->getReadability('<table><tr>' . str_repeat('<td><p>This is an awesome text with some links, here there are the awesome</td>', 7) . '</tr></table>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
}
public function testWithSameClasses()
public function testWithSameClasses(): void
{
$readability = $this->getReadability('<article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<div class="awesomecontent">This text is also an awesome text and you should know that !</div></article>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertContains('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
}
public function testWithScript()
public function testWithScript(): void
{
$readability = $this->getReadability('<article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p><script>This text is also an awesome text and you should know that !</script></p></article>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertEmpty($readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringNotContainsString('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
}
public function testTitle()
public function testTitle(): void
{
$readability = $this->getReadability('<title>this is my title</title><article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p></p></article>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertEquals('this is my title', $readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertSame('this is my title', $readability->getTitle()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringNotContainsString('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
}
public function testTitleWithDash()
public function testTitleWithDash(): void
{
$readability = $this->getReadability('<title> title2 - title3 </title><article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p></p></article>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertEquals('title2 - title3', $readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertSame('title2 - title3', $readability->getTitle()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringNotContainsString('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
}
public function testTitleWithDoubleDot()
public function testTitleWithDoubleDot(): void
{
$readability = $this->getReadability('<title> title2 : title3 </title><article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p></p></article>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertEquals('title2 : title3', $readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertSame('title2 : title3', $readability->getTitle()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringNotContainsString('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
}
public function testTitleTooShortUseH1()
public function testTitleTooShortUseH1(): void
{
$readability = $this->getReadability('<title>too short</title><h1>this is my h1 title !</h1><article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p></p></article>', 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertEquals('this is my h1 title !', $readability->getTitle()->getInnerHtml());
$this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertSame('this is my h1 title !', $readability->getTitle()->getInnerHtml());
$this->assertStringContainsString('This is an awesome text with some links, here there are', $readability->getContent()->getInnerHtml());
$this->assertStringNotContainsString('This text is also an awesome text and you should know that', $readability->getContent()->getInnerHtml());
}
public function testAutoClosingIframeNotThrowingException(): void
{
$oldErrorReporting = error_reporting(\E_ALL | \E_STRICT);
$oldDisplayErrors = ini_set('display_errors', '1');
// dummy function to be used to the next test
public function error2Exception($code, $string, $file, $line, $context)
{
throw new \Exception($string, $code);
}
public function testAutoClosingIframeNotThrowingException()
{
error_reporting(E_ALL | E_STRICT);
ini_set('display_errors', true);
set_error_handler([$this, 'error2Exception'], E_ALL | E_STRICT);
set_error_handler(function (int $errno, string $errstr, string $errfile, int $errline, array $errcontext) {
throw new \Exception($errstr, $errno);
}, \E_ALL | \E_STRICT);
try {
$data = '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" lang="ru-RU" prefix="og: http://ogp.me/ns#">
@@ -367,16 +374,23 @@ class ReadabilityTest extends \PHPUnit\Framework\TestCase
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertContains('<iframe src="https://www.youtube.com/embed/PUep6xNeKjA" width="560" height="315" frameborder="0" allowfullscreen="allowfullscreen"> </iframe>', $readability->getContent()->getInnerHtml());
$this->assertContains('3D Touch', $readability->getTitle()->getInnerHtml());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
$this->assertStringContainsString('<iframe src="https://www.youtube.com/embed/PUep6xNeKjA" width="560" height="315" frameborder="0" allowfullscreen="allowfullscreen"> </iframe>', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('3D Touch', $readability->getTitle()->getInnerHtml());
} finally {
restore_error_handler();
if (false !== $oldDisplayErrors) {
ini_set('display_errors', $oldDisplayErrors);
}
error_reporting($oldErrorReporting);
}
}
/**
* This should generate an Exception "DOMElement::setAttribute(): ID post-60 already defined".
*/
public function testAppendIdAlreadyHere()
public function testAppendIdAlreadyHere(): void
{
$data = '<!DOCTYPE html>
<html lang="fr">
@@ -428,11 +442,11 @@ class ReadabilityTest extends \PHPUnit\Framework\TestCase
$res = $readability->init();
$this->assertTrue($res);
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
$this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getContent());
$this->assertInstanceOf(JSLikeHTMLElement::class, $readability->getTitle());
}
public function testPostFilters()
public function testPostFilters(): void
{
$readability = $this->getReadability('<div>' . str_repeat('<p>This <strong>is</strong> the awesome content :)</p>', 10) . '</div>', 'http://0.0.0.0');
$readability->addPostFilter('!<strong[^>]*>(.*?)</strong>!is', '');
@@ -440,26 +454,24 @@ class ReadabilityTest extends \PHPUnit\Framework\TestCase
$res = $readability->init();
$this->assertTrue($res);
$this->assertContains('This the awesome content :)', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This the awesome content :)', $readability->getContent()->getInnerHtml());
}
public function testPreFilters()
public function testPreFilters(): void
{
$this->markTestSkipped('Won\'t work until loadHtml() is moved in init() instead of __construct()');
$readability = $this->getReadability('<div>' . str_repeat('<p>This <b>is</b> the awesome and WONDERFUL content :)</p>', 7) . '</div>', 'http://0.0.0.0');
$readability->addPreFilter('!<b[^>]*>(.*?)</b>!is', '');
$res = $readability->init();
$this->assertTrue($res);
$this->assertContains('This the awesome and WONDERFUL content :)', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('This the awesome and WONDERFUL content :)', $readability->getContent()->getInnerHtml());
}
public function testChildNodeGoneNull()
public function testChildNodeGoneNull(): void
{
// from http://www.ayyaantuu.net/ethiopia-targets-opposition-lawmakers/
$html = file_get_contents('tests/fixtures/childNodeGoesNull.html');
$html = (string) file_get_contents('tests/fixtures/childNodeGoesNull.html');
$readability = $this->getReadability($html, 'http://0.0.0.0');
$readability->debug = true;
@@ -469,21 +481,76 @@ class ReadabilityTest extends \PHPUnit\Framework\TestCase
$this->assertTrue($res);
}
public function testKeepFootnotes()
public function testKeepFootnotes(): void
{
// from https://www.schreibdichte.de/blog/feed-aggregator-und-spaeter-lesen-dienst-im-team
$html = file_get_contents('tests/fixtures/keepFootnotes.html');
$html = (string) file_get_contents('tests/fixtures/keepFootnotes.html');
$readability = $this->getReadability($html, 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertContains('<sup id="fnref1:fnfeed_2"><a href="#fn:fnfeed_2" class="footnote-ref">2</a></sup>', $readability->getContent()->getInnerHtml());
$this->assertContains('<a href="#fnref1:fnfeed_2" rev="footnote"', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('<sup id="fnref1:fnfeed_2"><a href="#fn:fnfeed_2" class="footnote-ref">2</a></sup>', $readability->getContent()->getInnerHtml());
$this->assertStringContainsString('<a href="#fnref1:fnfeed_2" rev="footnote"', $readability->getContent()->getInnerHtml());
}
private function getReadability($html, $url = null, $parser = 'libxml', $useTidy = true)
public function testWithWipedBody(): void
{
// from https://www.cs.cmu.edu/~rgs/alice-table.html
$html = (string) file_get_contents('tests/fixtures/wipedBody.html');
$readability = $this->getReadability($html, 'http://0.0.0.0', 'libxml', false);
$readability->debug = true;
$res = $readability->init();
$this->assertTrue($res);
$this->assertStringContainsString('<a href="alice-I.html">Down the Rabbit-Hole</a>', $readability->getContent()->getInnerHtml());
}
public function dataForVisibleNode(): array
{
return [
'visible node' => [
'<div>' . str_repeat('<p>This <b>is</b> the awesome and WONDERFUL content :)</p>', 7) . '</div>',
true,
],
'display=none' => [
'<div style="display:none;">' . str_repeat('<p>This <b>is</b> the awesome and WONDERFUL content :)</p>', 7) . '</div>',
false,
],
'display=inline' => [
'<div style="display:inline;">' . str_repeat('<p>This <b>is</b> the awesome and WONDERFUL content :)</p>', 7) . '</div>',
true,
],
'hidden attribute' => [
'<div hidden>' . str_repeat('<p>This <b>is</b> the awesome and WONDERFUL content :)</p>', 7) . '</div>',
false,
],
'missing display' => [
'<div style="color:#ccc;">' . str_repeat('<p>This <b>is</b> the awesome and WONDERFUL content :)</p>', 7) . '</div>',
true,
],
];
}
/**
* @dataProvider dataForVisibleNode
*/
public function testVisibleNode(string $content, bool $shouldBeVisible): void
{
$readability = $this->getReadability($content, 'http://0.0.0.0');
$readability->debug = true;
$res = $readability->init();
if ($shouldBeVisible) {
$this->assertStringContainsString('WONDERFUL content', $readability->getContent()->getInnerHtml());
} else {
$this->assertStringNotContainsString('WONDERFUL content', $readability->getContent()->getInnerHtml());
}
}
private function getReadability(string $html, string $url = null, string $parser = 'libxml', bool $useTidy = true): Readability
{
$readability = new Readability($html, $url, $parser, $useTidy);
+67
View File
@@ -0,0 +1,67 @@
<HTML>
<HEAD>
<TITLE>Alice's Adventures in Wonderland (Project Gutenberg)</TITLE>
</HEAD>
<frameset Rows="50, *">
<frame src="alice-finfo.html">
<frame src="alice-ftitle.html" name="alice-main">
</frameset>
<noframes>
<BODY>
<H1>Alice's Adventures in Wonderland</H1>
<H1>Lewis Carroll</H1>
<H1>The Millennium Fulcrum Edition 3.0</H1>
NOTE: This is a hypertext formatted version of the Project Gutenberg edition.
For more information, check the
<A HREF="alice-small.txt">small print</A>
or check out the
<A HREF="ftp://uiarchive.cso.uiuc.edu/pub/etext/gutenberg/etext91/alice30.txt">
full ascii text</A>. The original Tenniel illustrations are also available
due to the efforts of Project Gutenberg. You can if you like, grab them as a
<A HREF="ftp://uiarchive.cso.uiuc.edu/pub/etext/gutenberg/etext94/algif10.zip">
"zip file"</A> or read the <A HREF="algif-small.txt">small print</A>
that comes with them.
This document is part of a small, but growing collection of html formatted
etexts. (Others may be found in either my <A
HREF="http://www.cs.cmu.edu/Web/People/rgs/rgs-home.html">home page</A> or
John Ockerbloom's indexes by <A
HREF="http://www.cs.cmu.edu/Web/bookauthors.html">author</A> and <A
HREF="http://www.cs.cmu.edu/Web/booktitles.html">title</A>.)
I am still trying to figure out whether anyone else is interested in these
on-line readable documents. If you appreciate this document or would like to
see more such, send me mail at "rgs@cs.cmu.edu".
<P>
<A HREF="alice01a.gif"><IMG SRC="alice01th.gif"></A>
<P>
<H2>CONTENTS</H2>
<PRE>
CHAPTER I: <A HREF="alice-I.html">Down the Rabbit-Hole</A>
CHAPTER II: <A HREF="alice-II.html">The Pool of Tears</A>
CHAPTER III: <A HREF="alice-III.html">A Caucus-Race and a Long Tale</A>
CHAPTER IV: <A HREF="alice-IV.html">The Rabbit Sends in a Little Bill</A>
CHAPTER V: <A HREF="alice-V.html">Advice from a Caterpillar</A>
CHAPTER VI: <A HREF="alice-VI.html">Pig and Pepper</A>
CHAPTER VII: <A HREF="alice-VII.html">A Mad Tea-Party</A>
CHAPTER VIII: <A HREF="alice-VIII.html">The Queen's Croquet-Ground</A>
CHAPTER IX: <A HREF="alice-IX.html">The Mock Turtle's Story</A>
CHAPTER X: <A HREF="alice-X.html">The Lobster Quadrille</A>
CHAPTER XI: <A HREF="alice-XI.html">Who Stole the Tarts?</A>
CHAPTER XII: <A HREF="alice-XII.html">Alice's Evidence</A>
</PRE>
<ADDRESS><A HREF="mailto:rgs@cs.cmu.edu">Robert Stockton</A></ADDRESS>
<P>
<!- Access counter added 5/25 1:49am ->
<A href="http://www.dbasics.com/cgi-bin/pages.cgi?143205747"><IMG SRC="http://www.dbasics.com/cgi-bin/counter.cgi?143205747.2&(none)"></A> Access statistics from htmlZine
<!- This page has been visited
A HREF="http://counter.digits.com/wc?--info=yes&--name=rgsalice"
IMG SRC="http://counter.digits.com/wc/-d/4/-r/-z/rgsalice"
ALIGN=absmiddle WIDTH=60 HEIGHT=20 BORDER=0 HSPACE=4 ALT="????"/A
times since March 2, 1996. ->
</BODY>
</noframes>
</HTML>