Update autolinker regular expression in Text\BBCode

- Thanks to https://daringfireball.net/2010/07/improved_regex_for_matching_urls
This commit is contained in:
Hypolite Petovan 2019-03-08 23:39:21 -05:00
parent 75d144aee7
commit 379f4d18c3
1 changed files with 23 additions and 5 deletions

View File

@ -1268,11 +1268,29 @@ class BBCode extends BaseObject
// if the HTML is used to generate plain text, then don't do this search, but replace all URL of that kind to text
if (!$for_plaintext) {
// Autolink feature (thanks to http://code.seebz.net/p/autolink-php/)
// Currently disabled, since the function is too greedy
// $autolink_regex = "`([^\]\=\"']|^)(https?\://[^\s<]+[^\s<\.\)])`ism";
$autolink_regex = "/([^\]\='".'"'."]|^)(https?\:\/\/[a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\%\$\!\+\,]+)/ism";
$text = preg_replace($autolink_regex, '$1[url]$2[/url]', $text);
// Autolink feature (thanks to https://daringfireball.net/2010/07/improved_regex_for_matching_urls)
$autolink_regex = '@(?xi)
(?<![=\'\]"/]) # Not preceded by =, \', ], ", /
\b
( # Capture 1: entire matched URL
https?:// # http or https protocol
(?:
www\d{0,3}[.] # "www.", "www1.", "www2." … "www999."
| # or
[a-z0-9.\-]+[.][a-z]{2,4}/ # looks like domain name followed by a slash
)
(?: # One or more:
[^\s()<>]+ # Run of non-space, non-()<>
| # or
\(([^\s()<>]+|(\([^\s()<>]+\)))*\) # balanced parens, up to 2 levels
)+
(?: # End with:
\(([^\s()<>]+|(\([^\s()<>]+\)))*\) # balanced parens, up to 2 levels
| # or
[^\s`!()\[\]{};:\'".,<>?«»“”‘’] # not a space or one of these punct chars
)
)@';
$text = preg_replace($autolink_regex, '[url]$1[/url]', $text);
if ($simple_html == 7) {
$text = preg_replace_callback("/\[url\]([$URLSearchString]*)\[\/url\]/ism", 'self::convertUrlForOStatusCallback', $text);
$text = preg_replace_callback("/\[url\=([$URLSearchString]*)\]([$URLSearchString]*)\[\/url\]/ism", 'self::convertUrlForOStatusCallback', $text);