Add % and ~ as valid characters in the path, querystring, and fragment parts of URLs

diff --git a/lib/util.php b/lib/util.php
index 8a56be55d514489460d48d84b55205828fab0aca..edc08d4c127b96df29bffd3d8c65cfc934104c21 100644 (file)
--- a/lib/util.php
+++ b/lib/util.php
@@ -421,7 +421,7 @@ function common_replace_urls_callback($text, $callback, $notice_id = null) {
                     '|'.
                     '(?:(?:mailto|aim|tel|xmpp):)'.
                 ')'.
-                '(?:[\pN\pL\-\_\+]+(?::[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
+                '(?:[\pN\pL\-\_\+\%\~]+(?::[\pN\pL\-\_\+\%\~]+)?\@)?'. //user:pass@
                 '(?:'.
                     '(?:'.
                         '\[[\pN\pL\-\_\:\.]+(?<![\.\:])\]'. //[dns]
@@ -434,7 +434,7 @@ function common_replace_urls_callback($text, $callback, $notice_id = null) {
             '|(?:'. //IPv6
                 '\[?(?:(?:(?:[0-9A-Fa-f]{1,4}:){7}(?:(?:[0-9A-Fa-f]{1,4})|:))|(?:(?:[0-9A-Fa-f]{1,4}:){6}(?::|(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})|(?::[0-9A-Fa-f]{1,4})))|(?:(?:[0-9A-Fa-f]{1,4}:){5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){4}(?::[0-9A-Fa-f]{1,4}){0,1}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){3}(?::[0-9A-Fa-f]{1,4}){0,2}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){2}(?::[0-9A-Fa-f]{1,4}){0,3}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:)(?::[0-9A-Fa-f]{1,4}){0,4}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?::(?::[0-9A-Fa-f]{1,4}){0,5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})))\]?'.
             ')|(?:'. //DNS
-                '(?:[\pN\pL\-\_\+]+(?:\:[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
+                '(?:[\pN\pL\-\_\+\%\~]+(?:\:[\pN\pL\-\_\+\%\~]+)?\@)?'. //user:pass@
                 '[\pN\pL\-\_]+(?:\.[\pN\pL\-\_]+)*\.'.
                 //tld list from http://data.iana.org/TLD/tlds-alpha-by-domain.txt, also added local, loc, and onion
                 '(?:AC|AD|AE|AERO|AF|AG|AI|AL|AM|AN|AO|AQ|AR|ARPA|AS|ASIA|AT|AU|AW|AX|AZ|BA|BB|BD|BE|BF|BG|BH|BI|BIZ|BJ|BM|BN|BO|BR|BS|BT|BV|BW|BY|BZ|CA|CAT|CC|CD|CF|CG|CH|CI|CK|CL|CM|CN|CO|COM|COOP|CR|CU|CV|CX|CY|CZ|DE|DJ|DK|DM|DO|DZ|EC|EDU|EE|EG|ER|ES|ET|EU|FI|FJ|FK|FM|FO|FR|GA|GB|GD|GE|GF|GG|GH|GI|GL|GM|GN|GOV|GP|GQ|GR|GS|GT|GU|GW|GY|HK|HM|HN|HR|HT|HU|ID|IE|IL|IM|IN|INFO|INT|IO|IQ|IR|IS|IT|JE|JM|JO|JOBS|JP|KE|KG|KH|KI|KM|KN|KP|KR|KW|KY|KZ|LA|LB|LC|LI|LK|LR|LS|LT|LU|LV|LY|MA|MC|MD|ME|MG|MH|MIL|MK|ML|MM|MN|MO|MOBI|MP|MQ|MR|MS|MT|MU|MUSEUM|MV|MW|MX|MY|MZ|NA|NAME|NC|NE|NET|NF|NG|NI|NL|NO|NP|NR|NU|NZ|OM|ORG|PA|PE|PF|PG|PH|PK|PL|PM|PN|PR|PRO|PS|PT|PW|PY|QA|RE|RO|RS|RU|RW|SA|SB|SC|SD|SE|SG|SH|SI|SJ|SK|SL|SM|SN|SO|SR|ST|SU|SV|SY|SZ|TC|TD|TEL|TF|TG|TH|TJ|TK|TL|TM|TN|TO|TP|TR|TRAVEL|TT|TV|TW|TZ|UA|UG|UK|US|UY|UZ|VA|VC|VE|VG|VI|VN|VU|WF|WS|XN--0ZWM56D|测试|XN--11B5BS3A9AJ6G|परीक्षा|XN--80AKHBYKNJ4F|испытание|XN--9T4B11YI5A|테스트|XN--DEBA0AD|טעסט|XN--G6W251D|測試|XN--HGBK6AJ7F53BBA|آزمایشی|XN--HLCJ6AYA9ESC7A|பரிட்சை|XN--JXALPDLP|δοκιμή|XN--KGBECHTV|إختبار|XN--ZCKZAH|テスト|YE|YT|YU|ZA|ZM|ZW|local|loc|onion)'.
@@ -442,9 +442,9 @@ function common_replace_urls_callback($text, $callback, $notice_id = null) {
         ')'.
         '(?:'.
             '(?:\:\d+)?'. //:port
-            '(?:/[\pN\pL$\[\]\,\!\(\)\.\-\_\+\/\=\&\;]*)?'. // /path
-            '(?:\?[\pN\pL\$\[\]\,\!\(\)\.\-\_\+\/\=\&\;\/]*)?'. // ?query string
-            '(?:\#[\pN\pL$\[\]\,\!\(\)\.\-\_\+\/\=\&\;\/\?\#]*)?'. // #fragment
+            '(?:/[\pN\pL$\[\]\,\!\(\)\.\-\_\+\/\=\&\;\%\~]*)?'. // /path
+            '(?:\?[\pN\pL\$\[\]\,\!\(\)\.\-\_\+\/\=\&\;\%\~\/]*)?'. // ?query string
+            '(?:\#[\pN\pL$\[\]\,\!\(\)\.\-\_\+\/\=\&\;\%\~\/\?\#]*)?'. // #fragment
         ')(?<![\?\.\,\#\,])'.
     ')'.
     '#ixu';

diff --git a/tests/URLDetectionTest.php b/tests/URLDetectionTest.php
index 767f895bbae4c3c1ec8d7af169a19b95910d4066..fd697c2189062bd52812d2d84e78f07b001bdc10 100644 (file)
--- a/tests/URLDetectionTest.php
+++ b/tests/URLDetectionTest.php
@@ -33,6 +33,10 @@ class URLDetectionTest extends PHPUnit_Framework_TestCase
                            '<a href="http://127.0.0.1:99/" rel="external">127.0.0.1:99</a>'),
                      array('127.0.0.1/test.php',
                            '<a href="http://127.0.0.1/test.php" rel="external">127.0.0.1/test.php</a>'),
+                     array('127.0.0.1/~test',
+                           '<a href="http://127.0.0.1/~test" rel="external">127.0.0.1/~test</a>'),
+                     array('127.0.0.1/test%20stuff',
+                           '<a href="http://127.0.0.1/test%20stuff" rel="external">127.0.0.1/test%20stuff</a>'),
                      array('http://[::1]:99/test.php',
                            '<a href="http://[::1]:99/test.php" rel="external">http://[::1]:99/test.php</a>'),
                      array('http://::1/test.php',