From fb125de072338f56dfd2ba08bab3c08c19ebdc6e Mon Sep 17 00:00:00 2001
From: "C. Scott Ananian" <cscott@cscott.net>
Date: Tue, 24 Jun 2014 14:15:25 -0400
Subject: [PATCH] Allow HTML5 <rtc> tag (ruby support for East Asian
 typography).

We currently allow <ruby>, <rt>, <rb>, and <rp> but not the W3C HTML5
<rtc> element.  Fix that.

(Note that <rb> and <rtc> are new additions to HTML5 which currently
appear in the W3C but not the WHATWG version of the HTML5 spec.
Support for these has already been merged in gecko and webkit and
the editor plans to update the WHATWG spec.)

Bug: 67042
Change-Id: I8c0e65d782b6d23057a9723b87323b28e8bf8852
---
 includes/Sanitizer.php                  |  6 ++--
 includes/parser/CoreParserFunctions.php |  2 +-
 tests/parser/parserTests.txt            | 46 +++++++++++++++++++++++--
 3 files changed, 47 insertions(+), 7 deletions(-)

diff --git a/includes/Sanitizer.php b/includes/Sanitizer.php
index 6a568c2d0cd..ec17a0895cf 100644
--- a/includes/Sanitizer.php
+++ b/includes/Sanitizer.php
@@ -383,7 +383,7 @@ class Sanitizer {
 				'h2', 'h3', 'h4', 'h5', 'h6', 'cite', 'code', 'em', 's',
 				'strike', 'strong', 'tt', 'var', 'div', 'center',
 				'blockquote', 'ol', 'ul', 'dl', 'table', 'caption', 'pre',
-				'ruby', 'rt', 'rb', 'rp', 'p', 'span', 'abbr', 'dfn',
+				'ruby', 'rb', 'rp', 'rt', 'rtc', 'p', 'span', 'abbr', 'dfn',
 				'kbd', 'samp', 'data', 'time', 'mark'
 			);
 			$htmlsingle = array(
@@ -1685,10 +1685,10 @@ class Sanitizer {
 			# http://www.whatwg.org/html/text-level-semantics.html#the-ruby-element
 			'ruby'       => $common,
 			# rbc
-			# rtc
 			'rb'         => $common,
-			'rt'         => $common, #array_merge( $common, array( 'rbspan' ) ),
 			'rp'         => $common,
+			'rt'         => $common, #array_merge( $common, array( 'rbspan' ) ),
+			'rtc'         => $common,
 
 			# MathML root element, where used for extensions
 			# 'title' may not be 100% valid here; it's XHTML
diff --git a/includes/parser/CoreParserFunctions.php b/includes/parser/CoreParserFunctions.php
index cde7a2d83ee..79c8ade65e8 100644
--- a/includes/parser/CoreParserFunctions.php
+++ b/includes/parser/CoreParserFunctions.php
@@ -378,7 +378,7 @@ class CoreParserFunctions {
 		// list of disallowed tags for DISPLAYTITLE
 		// these will be escaped even though they are allowed in normal wiki text
 		$bad = array( 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'div', 'blockquote', 'ol', 'ul', 'li', 'hr',
-			'table', 'tr', 'th', 'td', 'dl', 'dd', 'caption', 'p', 'ruby', 'rb', 'rt', 'rp', 'br' );
+			'table', 'tr', 'th', 'td', 'dl', 'dd', 'caption', 'p', 'ruby', 'rb', 'rt', 'rtc', 'rp', 'br' );
 
 		// disallow some styles that could be used to bypass $wgRestrictDisplayTitle
 		if ( $wgRestrictDisplayTitle ) {
diff --git a/tests/parser/parserTests.txt b/tests/parser/parserTests.txt
index e4d93242e4b..6097370612b 100644
--- a/tests/parser/parserTests.txt
+++ b/tests/parser/parserTests.txt
@@ -1087,7 +1087,7 @@ Non-html5 tags should be accepted
 </p>
 !! end
 
-## a,rtc not permitted
+## a not permitted
 ## i,b,br omitted
 !! test
 Text-level semantic html elements in wikitext
@@ -1109,7 +1109,7 @@ Text-level semantic html elements in wikitext
 <sub>text</sub>
 <u>text</u>
 <mark>text</mark>
-<ruby><rb>明日<rp>(</rp><rt>Ashita</rt><rp>)</rp></rb></ruby>
+<ruby><rb>明日</rb><rp>(</rp><rt>Ashita</rt><rp> </rp><rtc>あした</rtc><rp>)</rp></ruby>
 <bdi>text</bdi>
 <bdo>text</bdo>
 <span>text</span>
@@ -1132,7 +1132,7 @@ Text-level semantic html elements in wikitext
 <sub>text</sub>
 <u>text</u>
 <mark>text</mark>
-<ruby><rb>明日<rp>(</rp><rt>Ashita</rt><rp>)</rp></rb></ruby>
+<ruby><rb>明日</rb><rp>(</rp><rt>Ashita</rt><rp> </rp><rtc>あした</rtc><rp>)</rp></ruby>
 <bdi>text</bdi>
 <bdo>text</bdo>
 <span>text</span>
@@ -1140,6 +1140,46 @@ Text-level semantic html elements in wikitext
 </p>
 !! end
 
+# test cases taken from
+# http://www.w3.org/TR/html5/text-level-semantics.html#the-ruby-element
+!! test
+Ruby markup (W3C-style)
+!! wikitext
+; Mono-ruby for individual base characters
+: <ruby>日<rt>に</rt>本<rt>ほん</rt>語<rt>ご</rt></ruby>
+; Group ruby
+: <ruby>今日<rt>きょう</rt></ruby>
+; Jukugo ruby
+: <ruby>法<rb>華</rb><rb>経</rb><rt>ほ</rt><rt>け</rt><rt>きょう</rt></ruby>
+; Inline ruby
+: <ruby>東<rb>京</rb><rp>(</rp><rt>とう</rt><rt>きょう</rt><rp>)</rp></ruby>
+; Double-sided ruby
+: <ruby><rb>旧</rb><rb>金</rb><rb>山</rb><rt>jiù</rt><rt>jīn</rt><rt>shān</rt><rtc>San Francisco</rtc></ruby>
+
+<ruby>
+<rb>♥</rb><rtc><rt>Heart</rt></rtc><rtc lang=fr><rt>Cœur</rt></rtc>
+<rb>☘</rb><rtc><rt>Shamrock</rt></rtc><rtc lang=fr><rt>Trèfle</rt></rtc>
+<rb>✶</rb><rtc><rt>Star</rt></rtc><rtc lang=fr><rt>Étoile</rt></rtc>
+</ruby>
+!! html
+<dl><dt> Mono-ruby for individual base characters</dt>
+<dd> <ruby>日<rt>に</rt>本<rt>ほん</rt>語<rt>ご</rt></ruby></dd>
+<dt> Group ruby</dt>
+<dd> <ruby>今日<rt>きょう</rt></ruby></dd>
+<dt> Jukugo ruby</dt>
+<dd> <ruby>法<rb>華</rb><rb>経</rb><rt>ほ</rt><rt>け</rt><rt>きょう</rt></ruby></dd>
+<dt> Inline ruby</dt>
+<dd> <ruby>東<rb>京</rb><rp>(</rp><rt>とう</rt><rt>きょう</rt><rp>)</rp></ruby></dd>
+<dt> Double-sided ruby</dt>
+<dd> <ruby><rb>旧</rb><rb>金</rb><rb>山</rb><rt>jiù</rt><rt>jīn</rt><rt>shān</rt><rtc>San Francisco</rtc></ruby></dd></dl>
+<p><ruby>
+<rb>♥</rb><rtc><rt>Heart</rt></rtc><rtc lang="fr"><rt>Cœur</rt></rtc>
+<rb>☘</rb><rtc><rt>Shamrock</rt></rtc><rtc lang="fr"><rt>Trèfle</rt></rtc>
+<rb>✶</rb><rtc><rt>Star</rt></rtc><rtc lang="fr"><rt>Étoile</rt></rtc>
+</ruby>
+</p>
+!! end
+
 !! test
 Non-word characters don't terminate tag names (bug 17663, 40670, 52022)
 !! wikitext