From 25d35fc65c54a787ea91c5326bbb2a8de486a773 Mon Sep 17 00:00:00 2001
From: "C. Scott Ananian" <cscott@cscott.net>
Date: Thu, 15 May 2014 17:19:10 -0700
Subject: [PATCH] Enforce spaces around magic links (RFC, PMID, and ISBN).

Ensure that there is a \b boundary before and after RFC, PMID, and ISBN
links.  (Previously we enforced \b boundaries only before free external
links and after ISBN links.)  Consistency is a good thing!

In addition:
* \b is not a PHP escape sequence, so you don't need to write \\b inside
  a string.
* \b before the numeric part of an ISBN is pointless: by the structure
  of the regexp there will always be a space on the left and a word
  character (a digit) on the right.

Bug: 65278
Change-Id: Ic315b988091a5c7530a8285b9249804db72e55db
---
 RELEASE-NOTES-1.25           |  2 ++
 includes/parser/Parser.php   |  8 +++----
 tests/parser/parserTests.txt | 42 ++++++++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/RELEASE-NOTES-1.25 b/RELEASE-NOTES-1.25
index 06d2d6619d..339e677f1b 100644
--- a/RELEASE-NOTES-1.25
+++ b/RELEASE-NOTES-1.25
@@ -271,6 +271,8 @@ changes to languages because of Bugzilla reports.
 ** In source text of the form '{$A}'{$B}' or `{$A}`{$B}`, where variable A
    does not exist yet variable B does, the latter may not be replaced.
    However, this difference is unlikely to arise in practice.
+* (T67278) RFC, PMID, and ISBN "magic links" must be surrounded by non-word
+  characters on both sides.
 
 == Compatibility ==
 
diff --git a/includes/parser/Parser.php b/includes/parser/Parser.php
index 91d8a81ad4..5c8253a0c3 100644
--- a/includes/parser/Parser.php
+++ b/includes/parser/Parser.php
@@ -1393,13 +1393,13 @@ class Parser {
 			'!(?:                           # Start cases
 				(<a[ \t\r\n>].*?</a>) |     # m[1]: Skip link text
 				(<.*?>) |                   # m[2]: Skip stuff inside HTML elements' . "
-				(\\b(?i:$prots)$urlChar+) |  # m[3]: Free external links" . '
-				(?:RFC|PMID)\s+([0-9]+) |   # m[4]: RFC or PMID, capture number
-				ISBN\s+(\b                  # m[5]: ISBN, capture number
+				(\b(?i:$prots)$urlChar+) |  # m[3]: Free external links" . '
+				\b(?:RFC|PMID)\s+([0-9]+)\b |# m[4]: RFC or PMID, capture number
+				\bISBN\s+(                  # m[5]: ISBN, capture number
 					(?: 97[89] [\ \-]? )?   # optional 13-digit ISBN prefix
 					(?: [0-9]  [\ \-]? ){9} # 9 digits with opt. delimiters
 					[0-9Xx]                 # check digit
-					\b)
+					)\b
 			)!xu', array( &$this, 'magicLinkCallback' ), $text );
 		wfProfileOut( __METHOD__ );
 		return $text;
diff --git a/tests/parser/parserTests.txt b/tests/parser/parserTests.txt
index 78e1387a61..5f19e8b4ff 100644
--- a/tests/parser/parserTests.txt
+++ b/tests/parser/parserTests.txt
@@ -4184,6 +4184,21 @@ http://example.com/url_with_(brackets)
 </p>
 !! end
 
+!! test
+External links: No preceding word characters allowed (bug 65278)
+!! wikitext
+NOPEhttp://example.com
+N0http://example.com
+ok:http://example.com
+ok-http://example.com
+!! html
+<p>NOPEhttp://example.com
+N0http://example.com
+ok:<a rel="nofollow" class="external free" href="http://example.com">http://example.com</a>
+ok-<a rel="nofollow" class="external free" href="http://example.com">http://example.com</a>
+</p>
+!! end
+
 !! test
 External image
 !! wikitext
@@ -8886,6 +8901,15 @@ RFC 822
 </p>
 !! end
 
+!! test
+Magic links: RFC (bug 65278)
+!! wikitext
+This is RFC 822 but thisRFC 822 is not RFC 822linked.
+!! html
+<p>This is <a class="external mw-magiclink-rfc" rel="nofollow" href="//tools.ietf.org/html/rfc822">RFC 822</a> but thisRFC 822 is not RFC 822linked.
+</p>
+!! end
+
 !! test
 Magic links: ISBN (bug 1937)
 !! wikitext
@@ -8895,6 +8919,15 @@ ISBN 0-306-40615-2
 </p>
 !! end
 
+!! test
+Magic links: ISBN (bug 65278)
+!! wikitext
+This is ISBN 978-0-316-09811-3 but thisISBN 978-0-316-09811-3 is not ISBN 978-0-316-09811-3linked.
+!! html
+<p>This is <a href="/wiki/Special:BookSources/9780316098113" class="internal mw-magiclink-isbn">ISBN 978-0-316-09811-3</a> but thisISBN 978-0-316-09811-3 is not ISBN 978-0-316-09811-3linked.
+</p>
+!! end
+
 !! test
 Magic links: PMID incorrectly converts space to underscore
 !! wikitext
@@ -8904,6 +8937,15 @@ PMID 1234
 </p>
 !! end
 
+!! test
+Magic links: PMID (bug 65278)
+!! wikitext
+This is PMID 1234 but thisPMID 1234 is not PMID 1234linked.
+!! html
+<p>This is <a class="external mw-magiclink-pmid" rel="nofollow" href="//www.ncbi.nlm.nih.gov/pubmed/1234?dopt=Abstract">PMID 1234</a> but thisPMID 1234 is not PMID 1234linked.
+</p>
+!! end
+
 ###
 ### Templates
 ####
-- 
2.20.1