mirror/parsedown
1
0
Fork 0
mirror of https://github.com/erusev/parsedown.git synced 2023-08-10 21:13:06 +03:00
Code Releases Activity

Better autolinks

Browse Source 
This doesn't follow gfm spec yet, work lifted from my code over
at
8505e2737e/src/Parsers/GitHubFlavor/Inlines/AutoLink.php

Fixes #505
Fixes #717
This commit is contained in:
Aidan Woods 2021-10-11 20:09:57 +01:00
parent cc5614bc5c
commit 7d1b9ca562
No known key found for this signature in database
GPG Key ID: 9A6A8EFAA512BBB9
3 changed files with 47 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
src/Components/Inlines/Url.php
View File

@ -14,6 +14,9 @@ final class Url implements BacktrackingInline
{
use WidthTrait;
private const ABSOLUTE_URI = '[a-z][a-z0-9+.-]{1,31}:[^\s[:cntrl:]<>]*';
private const NO_TRAILING_PUNCT = '(?<![?!.,:*_~])';
/** @var string */
private $url;
@ -38,14 +41,31 @@ final class Url implements BacktrackingInline
*/
public static function build(Excerpt $Excerpt, State $State)
{
if (\preg_match(
'/(?<=^|\s|[*_~(])https?+:[\/]{2}[^\s<]+\b\/*+/ui',
$Excerpt->context(),
$matches,
\PREG_OFFSET_CAPTURE
)) {
// this needs some work to follow spec
if (
\preg_match(
'/'.self::ABSOLUTE_URI.self::NO_TRAILING_PUNCT.'/iu',
$Excerpt->context(),
$matches,
\PREG_OFFSET_CAPTURE
)
) {
/** @var array{0: array{string, int}} $matches */
return new self($matches[0][0], \intval($matches[0][1]));
$url = $matches[0][0];
$position = \intval($matches[0][1]);
if (\preg_match('/[)]++$/', $url, $matches)) {
$trailingParens = \strlen($matches[0]);
$openingParens = \substr_count($url, '(');
$closingParens = \substr_count($url, ')');
if ($closingParens > $openingParens) {
$url = \substr($url, 0, -\min($trailingParens, $closingParens - $openingParens));
}
}
return new self($url, $position);
}
return null;

8
tests/data/url_autolinking.html
View File

@ -1,3 +1,9 @@
<p>an autolink <a href="http://example.com">http://example.com</a></p>
<p>inside of parentheses (<a href="http://example.com">http://example.com</a>)</p>
<p>trailing slash <a href="http://example.com/">http://example.com/</a> and <a href="http://example.com/path/">http://example.com/path/</a></p>
<p><a href="http://www.google.com/search?q=Markup+(business)">http://www.google.com/search?q=Markup+(business)</a></p>
<p><a href="http://www.google.com/search?q=Markup+(business)">http://www.google.com/search?q=Markup+(business)</a>))</p>
<p>(<a href="http://www.google.com/search?q=Markup+(business)">http://www.google.com/search?q=Markup+(business)</a>)</p>
<p>(<a href="http://www.google.com/search?q=Markup+(business)">http://www.google.com/search?q=Markup+(business)</a></p>
<p>trailing slash <a href="http://example.com/">http://example.com/</a> and <a href="http://example.com/path/">http://example.com/path/</a></p>
<p>trailing paren <a href="https://www.owasp.org/index.php/Cross-site_Scripting_(XSS)">https://www.owasp.org/index.php/Cross-site_Scripting_(XSS)</a></p>
<p>complex link <a href="http://elk.canda.biz/app/kibana#/discover?_g=()&amp;_a=(columns:!(_source),index:&#039;deve-*&#039;,interval:auto,query:(query_string:(analyze_wildcard:!t,query:&#039;*&#039;)),sort:!(&#039;@timestamp&#039;,desc))">http://elk.canda.biz/app/kibana#/discover?_g=()&amp;_a=(columns:!(_source),index:'deve-*',interval:auto,query:(query_string:(analyze_wildcard:!t,query:'*')),sort:!('@timestamp',desc))</a></p>

14
tests/data/url_autolinking.md
View File

@ -2,4 +2,16 @@ an autolink http://example.com
inside of parentheses (http://example.com)
trailing slash http://example.com/ and http://example.com/path/
http://www.google.com/search?q=Markup+(business)
http://www.google.com/search?q=Markup+(business)))
(http://www.google.com/search?q=Markup+(business))
(http://www.google.com/search?q=Markup+(business)
trailing slash http://example.com/ and http://example.com/path/
trailing paren https://www.owasp.org/index.php/Cross-site_Scripting_(XSS)
complex link http://elk.canda.biz/app/kibana#/discover?_g=()&_a=(columns:!(_source),index:'deve-*',interval:auto,query:(query_string:(analyze_wildcard:!t,query:'*')),sort:!('@timestamp',desc))