Bug 33845: Headings become cursive in TOC when they contain an image

Fixes the problems with r102179 and r102179, as there are
valid tags which begin the same, which meant they were not removed from
the TOC (the second regex, intended to remove tag parameters, then converted
<img or <blockquote> into <i> / <b>).
The same problem existed in the original regex, but as there are no valid
tags which begin with sup or sub, it never happened).

Added comment explaining the tocline regex, and added a bunch of parser tests.

diff --git a/includes/parser/Parser.php b/includes/parser/Parser.php
index 51751aa..761149d 100644 (file)
--- a/includes/parser/Parser.php
+++ b/includes/parser/Parser.php
@@ -4048,9 +4048,11 @@ class Parser {
                        #     link text with suffix
                        $safeHeadline = $this->replaceLinkHoldersText( $safeHeadline );
 
-                       # Strip out HTML (other than plain <sup> and <sub>: bug 8393, or <i>: bug 26375)
+                       # Strip out HTML (first regex removes any tag not allowed)
+                       # Allowed tags are <sup> and <sub> (bug 8393), <i> (bug 26375) and <b> (r105284)
+                       # We strip any parameter from accepted tags (second regex)
                        $tocline = preg_replace(
-                               array( '#<(?!/?(sup|sub|i|b)).*?'.'>#', '#<(/?(sup|sub|i|b)).*?'.'>#' ),
+                               array( '#<(?!/?(sup|sub|i|b)(?: [^>]*)?>).*?'.'>#', '#<(/?(sup|sub|i|b))(?: .*?)?'.'>#' ),
                                array( '',                          '<$1>' ),
                                $safeHeadline
                        );

diff --git a/tests/parser/parserTests.txt b/tests/parser/parserTests.txt
index 9c276e0..6f5702d 100644 (file)
--- a/tests/parser/parserTests.txt
+++ b/tests/parser/parserTests.txt
@@ -8976,6 +8976,99 @@ __TOC__
 
 !! end
 
+!! test
+Bug 33845: Headings become cursive in TOC when they contain an image
+!! options
+title=[[Main Page]]
+!! input
+__TOC__
+== Image [[Image:foobar.jpg]] ==
+!! result
+<table id="toc" class="toc"><tr><td><div id="toctitle"><h2>Contents</h2></div>
+<ul>
+<li class="toclevel-1 tocsection-1"><a href="#Image"><span class="tocnumber">1</span> <span class="toctext">Image</span></a></li>
+</ul>
+</td></tr></table>
+<h2><span class="editsection">[<a href="/index.php?title=Main_Page&amp;action=edit&amp;section=1" title="Edit section: Image">edit</a>]</span> <span class="mw-headline" id="Image"> Image <a href="/wiki/File:Foobar.jpg" class="image"><img alt="Foobar.jpg" src="http://example.com/images/3/3a/Foobar.jpg" width="1941" height="220" /></a> </span></h2>
+
+!! end
+
+!! test
+Bug 33845 (2): Headings become bold in TOC when they contain a blockquote
+!! options
+title=[[Main Page]]
+!! input
+__TOC__
+== <blockquote>Quote</blockquote> ==
+!! result
+<table id="toc" class="toc"><tr><td><div id="toctitle"><h2>Contents</h2></div>
+<ul>
+<li class="toclevel-1 tocsection-1"><a href="#Quote"><span class="tocnumber">1</span> <span class="toctext">Quote</span></a></li>
+</ul>
+</td></tr></table>
+<h2><span class="editsection">[<a href="/index.php?title=Main_Page&amp;action=edit&amp;section=1" title="Edit section: Quote">edit</a>]</span> <span class="mw-headline" id="Quote"> <blockquote>Quote</blockquote> </span></h2>
+
+!! end
+
+!! test
+Unclosed tags in TOC
+!! options
+title=[[Main Page]]
+!! input
+__TOC__
+== Proof: 2 < 3 ==
+<small>Hanc marginis exiguitas non caperet.</small>
+QED
+!! result
+<table id="toc" class="toc"><tr><td><div id="toctitle"><h2>Contents</h2></div>
+<ul>
+<li class="toclevel-1 tocsection-1"><a href="#Proof:_2_.3C_3"><span class="tocnumber">1</span> <span class="toctext">Proof: 2 &lt; 3</span></a></li>
+</ul>
+</td></tr></table>
+<h2><span class="editsection">[<a href="/index.php?title=Main_Page&amp;action=edit&amp;section=1" title="Edit section: Proof: 2 &lt; 3">edit</a>]</span> <span class="mw-headline" id="Proof:_2_.3C_3"> Proof: 2 &lt; 3 </span></h2>
+<p><small>Hanc marginis exiguitas non caperet.</small>
+QED
+</p>
+!! end
+
+!! test
+Multiple tags in TOC
+!! input
+__TOC__
+== <i>Foo</i> <b>Bar</b> ==
+
+== <i>Foo</i> <blockquote>Bar</blockquote> ==
+!! result
+<table id="toc" class="toc"><tr><td><div id="toctitle"><h2>Contents</h2></div>
+<ul>
+<li class="toclevel-1 tocsection-1"><a href="#Foo_Bar"><span class="tocnumber">1</span> <span class="toctext"><i>Foo</i> <b>Bar</b></span></a></li>
+<li class="toclevel-1 tocsection-2"><a href="#Foo_Bar_2"><span class="tocnumber">2</span> <span class="toctext"><i>Foo</i> Bar</span></a></li>
+</ul>
+</td></tr></table>
+<h2><span class="editsection">[<a href="/index.php?title=Parser_test&amp;action=edit&amp;section=1" title="Edit section: Foo Bar">edit</a>]</span> <span class="mw-headline" id="Foo_Bar"> <i>Foo</i> <b>Bar</b> </span></h2>
+<h2><span class="editsection">[<a href="/index.php?title=Parser_test&amp;action=edit&amp;section=2" title="Edit section: Foo Bar">edit</a>]</span> <span class="mw-headline" id="Foo_Bar_2"> <i>Foo</i> <blockquote>Bar</blockquote> </span></h2>
+
+!! end
+
+!! test
+Tags with parameters in TOC
+!! input
+__TOC__
+== <sup class="in-h2">Hello</sup> ==
+
+== <sup class="a > b">Evilbye</sup> ==
+!! result
+<table id="toc" class="toc"><tr><td><div id="toctitle"><h2>Contents</h2></div>
+<ul>
+<li class="toclevel-1 tocsection-1"><a href="#Hello"><span class="tocnumber">1</span> <span class="toctext"><sup>Hello</sup></span></a></li>
+<li class="toclevel-1 tocsection-2"><a href="#b.22.3EEvilbye"><span class="tocnumber">2</span> <span class="toctext"><sup> b"&gt;Evilbye</sup></span></a></li>
+</ul>
+</td></tr></table>
+<h2><span class="editsection">[<a href="/index.php?title=Parser_test&amp;action=edit&amp;section=1" title="Edit section: Hello">edit</a>]</span> <span class="mw-headline" id="Hello"> <sup class="in-h2">Hello</sup> </span></h2>
+<h2><span class="editsection">[<a href="/index.php?title=Parser_test&amp;action=edit&amp;section=2" title="Edit section: b&quot;>Evilbye">edit</a>]</span> <span class="mw-headline" id="b.22.3EEvilbye"> <sup> b"&gt;Evilbye</sup> </span></h2>
+
+!! end
+
 !! article
 MediaWiki:Bug32057
 !! text