[core] Use Parsedown for Markdown parsing (#1783)

This commit is contained in:
Corentin Garcia 2020-10-09 20:29:02 +02:00 committed by GitHub
parent fe166d0216
commit ff98efe8dc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 1744 additions and 45 deletions

View file

@ -243,6 +243,7 @@ The source code for RSS-Bridge is [Public Domain](UNLICENSE).
RSS-Bridge uses third party libraries with their own license: RSS-Bridge uses third party libraries with their own license:
* [`Parsedown`](https://github.com/erusev/parsedown) licensed under the [MIT License](http://opensource.org/licenses/MIT)
* [`PHP Simple HTML DOM Parser`](http://simplehtmldom.sourceforge.net/) licensed under the [MIT License](http://opensource.org/licenses/MIT) * [`PHP Simple HTML DOM Parser`](http://simplehtmldom.sourceforge.net/) licensed under the [MIT License](http://opensource.org/licenses/MIT)
* [`php-urljoin`](https://github.com/fluffy-critter/php-urljoin) licensed under the [MIT License](http://opensource.org/licenses/MIT) * [`php-urljoin`](https://github.com/fluffy-critter/php-urljoin) licensed under the [MIT License](http://opensource.org/licenses/MIT)

View file

@ -100,7 +100,9 @@ class NyaaTorrentsBridge extends BridgeAbstract {
//Retrieve data from page contents //Retrieve data from page contents
$item_title = str_replace(' :: Nyaa', '', $item_html->find('title', 0)->plaintext); $item_title = str_replace(' :: Nyaa', '', $item_html->find('title', 0)->plaintext);
$item_desc = str_get_html(markdownToHtml($item_html->find('#torrent-description', 0)->innertext)); $item_desc = str_get_html(
markdownToHtml(html_entity_decode($item_html->find('#torrent-description', 0)->innertext))
);
$item_author = extractFromDelimiters($item_html->outertext, 'href="/user/', '"'); $item_author = extractFromDelimiters($item_html->outertext, 'href="/user/', '"');
$item_date = intval(extractFromDelimiters($item_html->outertext, 'data-timestamp="', '"')); $item_date = intval(extractFromDelimiters($item_html->outertext, 'data-timestamp="', '"'));

View file

@ -27,16 +27,13 @@ class RainbowSixSiegeBridge extends BridgeAbstract {
$uri = $uri . $jsonItem['button']['buttonUrl']; $uri = $uri . $jsonItem['button']['buttonUrl'];
$thumbnail = '<img src="' . $jsonItem['thumbnail']['url'] . '" alt="Thumbnail">'; $thumbnail = '<img src="' . $jsonItem['thumbnail']['url'] . '" alt="Thumbnail">';
$content = $thumbnail . '<br />' . $jsonItem['content']; $content = $thumbnail . '<br />' . markdownToHtml($jsonItem['content']);
// Line breaks
$content = preg_replace("/\r\n|\r|\n/", '<br/>', $content);
$item = array(); $item = array();
$item['uri'] = $uri; $item['uri'] = $uri;
$item['id'] = $jsonItem['id']; $item['id'] = $jsonItem['id'];
$item['title'] = $jsonItem['title']; $item['title'] = $jsonItem['title'];
$item['content'] = markdownToHtml($content); $item['content'] = $content;
$item['timestamp'] = strtotime($jsonItem['date']); $item['timestamp'] = strtotime($jsonItem['date']);
$this->items[] = $item; $this->items[] = $item;

View file

@ -195,7 +195,7 @@ function stripRecursiveHTMLSection($string, $tag_name, $tag_start){
} }
/** /**
* Convert Markdown into HTML. Only a subset of the Markdown syntax is implemented. * Convert Markdown into HTML with Parsedown.
* *
* @link https://daringfireball.net/projects/markdown/ Markdown * @link https://daringfireball.net/projects/markdown/ Markdown
* @link https://github.github.com/gfm/ GitHub Flavored Markdown Spec * @link https://github.github.com/gfm/ GitHub Flavored Markdown Spec
@ -205,40 +205,6 @@ function stripRecursiveHTMLSection($string, $tag_name, $tag_start){
*/ */
function markdownToHtml($string) { function markdownToHtml($string) {
//For more details about how these regex work: $Parsedown = new Parsedown();
// https://github.com/RSS-Bridge/rss-bridge/pull/802#discussion_r216138702 return $Parsedown->text($string);
// Images: https://regex101.com/r/JW9Evr/2
// Links: https://regex101.com/r/eRGVe7/1
// Bold: https://regex101.com/r/2p40Y0/1
// Italic: https://regex101.com/r/xJkET9/1
// Separator: https://regex101.com/r/ZBEqFP/1
// Plain URL: https://regex101.com/r/2JHYwb/1
// Site name: https://regex101.com/r/qIuKYE/1
$string = preg_replace('/\!\[([^\]]*)\]\(([^\) ]+)(?: [^\)]+)?\)/', '<img src="$2" alt="$1" />', $string);
$string = preg_replace('/\[([^\]]+)\]\(([^\)]+)\)/', '<a href="$2">$1</a>', $string);
$string = preg_replace('/\*\*(.*)\*\*/U', '<b>$1</b>', $string);
$string = preg_replace('/\*(.*)\*/U', '<i>$1</i>', $string);
$string = preg_replace('/__(.*)__/U', '<b>$1</b>', $string);
$string = preg_replace('/_(.*)_/U', '<i>$1</i>', $string);
$string = preg_replace('/[-]{6,99}/', '<hr />', $string);
$string = str_replace('&#10;', '<br />', $string);
$string = preg_replace('/([^"])(https?:\/\/[^ "<]+)([^"])/', '$1<a href="$2">$2</a>$3', $string . ' ');
$string = preg_replace('/([^"\/])(www\.[^ "<]+)([^"])/', '$1<a href="http://$2">$2</a>$3', $string . ' ');
//As the regex are not perfect, we need to fix <i> and </i> that are introduced in URLs
// Fixup regex <i>: https://regex101.com/r/NTRPf6/1
// Fixup regex </i>: https://regex101.com/r/aNklRp/1
$count = 1;
while($count > 0) {
$string = preg_replace('/ (src|href)="([^"]+)<i>([^"]+)"/U', ' $1="$2_$3"', $string, -1, $count);
}
$count = 1;
while($count > 0) {
$string = preg_replace('/ (src|href)="([^"]+)<\/i>([^"]+)"/U', ' $1="$2_$3"', $string, -1, $count);
}
return '<div>' . trim($string) . '</div>';
} }

View file

@ -82,5 +82,6 @@ require_once PATH_LIB . 'contents.php';
// Vendor // Vendor
define('MAX_FILE_SIZE', 10000000); /* Allow larger files for simple_html_dom */ define('MAX_FILE_SIZE', 10000000); /* Allow larger files for simple_html_dom */
require_once PATH_LIB_VENDOR . 'simplehtmldom/simple_html_dom.php'; require_once PATH_LIB_VENDOR . 'parsedown/Parsedown.php';
require_once PATH_LIB_VENDOR . 'php-urljoin/src/urljoin.php'; require_once PATH_LIB_VENDOR . 'php-urljoin/src/urljoin.php';
require_once PATH_LIB_VENDOR . 'simplehtmldom/simple_html_dom.php';

20
vendor/parsedown/LICENSE.txt vendored Normal file
View file

@ -0,0 +1,20 @@
The MIT License (MIT)
Copyright (c) 2013-2018 Emanuil Rusev, erusev.com
Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in
the Software without restriction, including without limitation the rights to
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
the Software, and to permit persons to whom the Software is furnished to do so,
subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

1712
vendor/parsedown/Parsedown.php vendored Normal file

File diff suppressed because it is too large Load diff