From 0aba1faa0803af6013c9ac2071e87f117e9c4835 Mon Sep 17 00:00:00 2001
From: Marc Alexander <admin@m-a-styles.de>
Date: Wed, 26 Jul 2017 21:14:05 +0200
Subject: [PATCH] [ticket/security/211] Do not match javascript URIs with URL
 regexes

SECURITY-211
---
 phpBB/develop/regex_idn.php             | 2 +-
 phpBB/includes/functions.php            | 4 ++--
 tests/functions/make_clickable_test.php | 8 ++++++++
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/phpBB/develop/regex_idn.php b/phpBB/develop/regex_idn.php
index d871695c50..30373f8de3 100644
--- a/phpBB/develop/regex_idn.php
+++ b/phpBB/develop/regex_idn.php
@@ -120,7 +120,7 @@ do
 	$pct_encoded = "%[\dA-F]{2}";
 	$unreserved = "$add_chars\pL0-9\-._~";
 	$sub_delims = ($inline) ? '!$&\'(*+,;=' : '!$&\'()*+,;=';
-	$scheme = ($inline) ? '[a-z][a-z\d+]*': '[a-z][a-z\d+\-.]*' ; // avoid automatic parsing of "word" in "last word.http://..."
+	$scheme = ($inline) ? '[a-z][a-z\d+]*(?<!javascript)': '[a-z][a-z\d+\-.]*(?<!javascript)' ; // avoid automatic parsing of "word" in "last word.http://..."
 	$pchar = "(?:[^$remove_chars]*[$unreserved$sub_delims:@|]+|$pct_encoded)"; // rfc: no "|"
 
 	$reg_name = "(?:[^$remove_chars]*[$unreserved$sub_delims:@|]+|$pct_encoded)+"; // rfc: * instead of + and no "|" and no "@" and no ":" (included instead of userinfo)
diff --git a/phpBB/includes/functions.php b/phpBB/includes/functions.php
index 7aa63f2e0c..29abadfcaf 100644
--- a/phpBB/includes/functions.php
+++ b/phpBB/includes/functions.php
@@ -3406,7 +3406,7 @@ function get_preg_expression($mode)
 
 		case 'url':
 			// generated with regex_idn.php file in the develop folder
-			return "[a-z][a-z\d+\-.]*:/{2}(?:(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'()*+,;=:@|]+|%[\dA-F]{2})+|[0-9.]+|\[[a-z0-9.]+:[a-z0-9.]+:[a-z0-9.:]+\])(?::\d*)?(?:/(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'()*+,;=:@|]+|%[\dA-F]{2})*)*(?:\?(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'()*+,;=:@/?|]+|%[\dA-F]{2})*)?(?:\#(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'()*+,;=:@/?|]+|%[\dA-F]{2})*)?";
+			return "[a-z][a-z\d+\-.]*(?<!javascript):/{2}(?:(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'()*+,;=:@|]+|%[\dA-F]{2})+|[0-9.]+|\[[a-z0-9.]+:[a-z0-9.]+:[a-z0-9.:]+\])(?::\d*)?(?:/(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'()*+,;=:@|]+|%[\dA-F]{2})*)*(?:\?(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'()*+,;=:@/?|]+|%[\dA-F]{2})*)?(?:\#(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'()*+,;=:@/?|]+|%[\dA-F]{2})*)?";
 		break;
 
 		case 'url_http':
@@ -3416,7 +3416,7 @@ function get_preg_expression($mode)
 
 		case 'url_inline':
 			// generated with regex_idn.php file in the develop folder
-			return "[a-z][a-z\d+]*:/{2}(?:(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'(*+,;=:@|]+|%[\dA-F]{2})+|[0-9.]+|\[[a-z0-9.]+:[a-z0-9.]+:[a-z0-9.:]+\])(?::\d*)?(?:/(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'(*+,;=:@|]+|%[\dA-F]{2})*)*(?:\?(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'(*+,;=:@/?|]+|%[\dA-F]{2})*)?(?:\#(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'(*+,;=:@/?|]+|%[\dA-F]{2})*)?";
+			return "[a-z][a-z\d+]*(?<!javascript):/{2}(?:(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'(*+,;=:@|]+|%[\dA-F]{2})+|[0-9.]+|\[[a-z0-9.]+:[a-z0-9.]+:[a-z0-9.:]+\])(?::\d*)?(?:/(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'(*+,;=:@|]+|%[\dA-F]{2})*)*(?:\?(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'(*+,;=:@/?|]+|%[\dA-F]{2})*)?(?:\#(?:[^\p{C}\p{Z}\p{S}\p{P}\p{Nl}\p{No}\p{Me}\x{1100}-\x{115F}\x{A960}-\x{A97C}\x{1160}-\x{11A7}\x{D7B0}-\x{D7C6}\x{20D0}-\x{20FF}\x{1D100}-\x{1D1FF}\x{1D200}-\x{1D24F}\x{0640}\x{07FA}\x{302E}\x{302F}\x{3031}-\x{3035}\x{303B}]*[\x{00B7}\x{0375}\x{05F3}\x{05F4}\x{30FB}\x{002D}\x{06FD}\x{06FE}\x{0F0B}\x{3007}\x{00DF}\x{03C2}\x{200C}\x{200D}\pL0-9\-._~!$&'(*+,;=:@/?|]+|%[\dA-F]{2})*)?";
 		break;
 
 		case 'www_url':
diff --git a/tests/functions/make_clickable_test.php b/tests/functions/make_clickable_test.php
index 63beeb06b2..2cdefe689d 100644
--- a/tests/functions/make_clickable_test.php
+++ b/tests/functions/make_clickable_test.php
@@ -55,6 +55,10 @@ class phpbb_functions_make_clickable_test extends phpbb_test_case
 				'http://testhost/viewtopic.php?t=1',
 				'<!-- l --><a class="postlink-local" href="http://testhost/viewtopic.php?t=1">viewtopic.php?t=1</a><!-- l -->'
 			),
+			array(
+				'javascript://testhost/viewtopic.php?t=1',
+				'javascript://testhost/viewtopic.php?t=1'
+			),
 			array(
 				'email@domain.com',
 				'<!-- e --><a href="mailto:email@domain.com">email@domain.com</a><!-- e -->'
@@ -92,6 +96,10 @@ class phpbb_functions_make_clickable_test extends phpbb_test_case
 				'ftp://ftp.täst.de/',
 				'<!-- m --><a class="postlink" href="ftp://ftp.täst.de/">ftp://ftp.täst.de/</a><!-- m -->'
 			),
+			array(
+				'javascript://täst.de/',
+				'javascript://täst.de/'
+			),
 			array(
 				'sip://bantu@täst.de',
 				'<!-- m --><a class="postlink" href="sip://bantu@täst.de">sip://bantu@täst.de</a><!-- m -->'