Merge "Revert "Preprocessor: Don't allow unclosed extension tags (matching until...

diff --combined tests/parser/parserTests.txt
index d866ed8,cd2b769..d4e7119
--- 1/tests/parser/parserTests.txt
--- 2/tests/parser/parserTests.txt
+++ b/tests/parser/parserTests.txt
@@@ -2520,6 -2520,7 +2520,7 @@@ Barack Obama <President> of the United 
  </p>
  !! end
  
+ ## PHP parser discards the "<pre " string
  !! test
  Handle broken pre-like tags (bug 64025)
  !! options
@@@ -2530,13 -2531,8 +2531,8 @@@ parsoid=wt2htm
  <table><pre </table>
  !! html/php
  <pre>x</pre>
- <table>&lt;pre </table>
+ <table><pre></pre></table>
  
- !! html/php+tidy
- <pre>
- x
- </pre>
- <p>&lt;pre</p>
  !! html/parsoid
  <pre about="#mwt1" typeof="mw:Transclusion" data-parsoid='{"a":{"&lt;pre":null},"sa":{"&lt;pre":""},"stx":"html","pi":[[{"k":"1","spc":["","","",""]}]]}' data-mw='{"parts":[{"template":{"target":{"wt":"echo","href":"./Template:Echo"},"params":{"1":{"wt":"&lt;pre &lt;pre>x&lt;/pre>"}},"i":0}}]}'>x</pre>
  
@@@ -6334,24 -6330,6 +6330,24 @@@ parsoid=wt2html,html2htm
  <td data-parsoid='{"startTagSrc":"| ","attrSepSrc":"|","autoInsertedEnd":true}'><a rel="mw:ExtLink" href="ftp://|x||"></a>" onmouseover="alert(document.cookie)">test</td></tr></tbody></table>
  !! end
  
 +!! test
 +! and || in element attributes should not be parsed as <th>/<td>
 +!! wikitext
 +{|
 +| <div style="color: red !important;" data-contrived="put this here ||">hi</div>
 +|}
 +!! html/php
 +<table>
 +<tr>
 +<td> <div style="color: red !important;" data-contrived="put this here &#124;&#124;">hi</div>
 +</td></tr></table>
 +
 +!! html/parsoid
 +<table>
 +<tbody><tr><td> <div style="color: red !important;" data-contrived="put this here ||" data-parsoid='{"stx":"html"}'>hi</div></td></tr>
 +</tbody></table>
 +!! end
 +
  # FIXME: The output seems broken. Filed as T110268.
  !! test
  ! and || in td attributes should not be parsed as <th>/<td>
@@@ -8805,40 -8783,6 +8801,40 @@@ Mixed lis
  
  !! end
  
 +!! test
 +1. Nested mixed wikitext and html list
 +!! wikitext
 +* hi
 +* <ul><li>ho</li></ul>
 +* hi
 +** ho
 +!! html/php
 +<ul><li> hi</li>
 +<li> <ul><li>ho</li></ul></li>
 +<li> hi
 +<ul><li> ho</li></ul></li></ul>
 +
 +!! html/parsoid
 +<ul><li> hi</li>
 +<li> <ul data-parsoid='{"stx":"html"}'><li data-parsoid='{"stx":"html"}'>ho</li></ul></li>
 +<li> hi
 +<ul><li> ho</li></ul></li></ul>
 +!! end
 +
 +!! test
 +2. Nested mixed wikitext and html list (incompatible)
 +!! wikitext
 +; hi
 +: {{echo|<li>ho</li>}}
 +!! html/php
 +<dl><dt> hi</dt>
 +<dd> <li>ho</li></dd></dl>
 +
 +!! html/parsoid
 +<dl><dt> hi</dt>
 +<dd> <li about="#mwt1" typeof="mw:Transclusion" data-parsoid='{"stx":"html","pi":[[{"k":"1","spc":["","","",""]}]]}' data-mw='{"parts":[{"template":{"target":{"wt":"echo","href":"./Template:Echo"},"params":{"1":{"wt":"&lt;li>ho&lt;/li>"}},"i":0}}]}'>ho</li></dd></dl>
 +!! end
 +
  !! test
  Nested lists 1
  !! wikitext
@@@ -10709,43 -10653,6 +10705,43 @@@ foo {{''}} ba
  </p>
  !! end
  
 +## This test is about making sure Parsoid's data-mw is well formed in the
 +## face of multiple templates with intersecting and overlapping ranges.  The
 +## wikitext itself is wretched.
 +!! test
 +Templates with intersecting and overlapping ranges
 +!! wikitext
 +{|{{echo|
 +<p>ha</p>}}
 +{|{{echo|
 +<p>ho</p>}}
 +{{echo|{{!}}hi}}
 +|}
 +!! html/php+tidy
 +<p>ha</p>
 +<p>ho</p>
 +<table>
 +<tr>
 +<td></td>
 +</tr>
 +<tr>
 +<td>hi</td>
 +</tr>
 +</table>
 +<table>
 +<tr>
 +<td></td>
 +</tr>
 +</table>
 +!! html/parsoid
 +<p about="#mwt1" typeof="mw:Transclusion" data-parsoid='{"stx":"html","autoInsertedEnd":true,"pi":[[{"k":"1","spc":["","","",""]}],[{"k":"1","spc":["","","",""]}],[{"k":"1","spc":["","","",""]}]],"firstWikitextNode":"table"}' data-mw='{"parts":["{|",{"template":{"target":{"wt":"echo","href":"./Template:Echo"},"params":{"1":{"wt":"\n&lt;p>ha&lt;/p>"}},"i":0}},"\n","{|",{"template":{"target":{"wt":"echo","href":"./Template:Echo"},"params":{"1":{"wt":"\n&lt;p>ho&lt;/p>"}},"i":1}},"\n",{"template":{"target":{"wt":"echo","href":"./Template:Echo"},"params":{"1":{"wt":"{{!}}hi"}},"i":2}},"\n|}"]}'>ha</p><table about="#mwt1" typeof="mw:ExpandedAttrs" data-mw='{"attribs":[[{"txt":"","html":""},{"html":""}]]}'>
 +
 +</table><p about="#mwt1">ho</p><table about="#mwt1" typeof="mw:ExpandedAttrs" data-mw='{"attribs":[[{"txt":"","html":""},{"html":""}]]}'>
 +
 +<tbody><tr><td>hi</td></tr>
 +</tbody></table>
 +!! end
 +
  !! article
  Template:MSGNW test
  !! text
@@@ -10969,8 -10876,6 +10965,6 @@@ Un-closed <includeonly
  !! wikitext
  <includeonly>
  !! html
- <p>&lt;includeonly&gt;
- </p>
  !! end
  
  ## We used to, but no longer wt2wt this test since the default serializer
@@@ -18389,6 -18294,8 +18383,6 @@@ image4    |300px| centr
                <li class="gallerybox" style="width: 155px"><div style="width: 155px">
                        <div class="thumb" style="height: 150px;">Image2.gif</div>
                        <div class="gallerytext">
 -<p>||||
 -</p>
                        </div>
                </div></li>
                <li class="gallerybox" style="width: 155px"><div style="width: 155px">
@@@ -18399,8 -18306,8 +18393,8 @@@
                <li class="gallerybox" style="width: 155px"><div style="width: 155px">
                        <div class="thumb" style="height: 150px;">Image4</div>
                        <div class="gallerytext">
 -<p>300px| centre
 -</p>
 +<pre>centre
 +</pre>
                        </div>
                </div></li>
                <li class="gallerybox" style="width: 155px"><div style="width: 155px">
@@@ -18459,7 -18366,7 +18453,7 @@@ image:foobar.jpg|Blabla|alt=This is a f
                <li class="gallerybox" style="width: 105px"><div style="width: 105px">
                        <div class="thumb" style="width: 100px;"><div style="margin:31px auto;"><a href="/wiki/File:Foobar.jpg" class="image"><img alt="This is a foo-bar." src="http://example.com/images/thumb/3/3a/Foobar.jpg/70px-Foobar.jpg" width="70" height="8" srcset="http://example.com/images/thumb/3/3a/Foobar.jpg/105px-Foobar.jpg 1.5x, http://example.com/images/thumb/3/3a/Foobar.jpg/140px-Foobar.jpg 2x" /></a></div></div>
                        <div class="gallerytext">
 -<p>Blabla|blabla.
 +<p>blabla.
  </p>
                        </div>
                </div></li>
@@@ -20778,11 -20685,9 +20772,11 @@@ HTML5 data attribute
  Strip reserved data attributes
  !! wikitext
  <div data-mw="foo" data-parsoid="bar" data-mw-someext="baz" data-ok="fred" data-ooui="xyzzy" data-bad:ns="ns">d</div>
 -!! html
 +!! html/php
  <div data-ok="fred">d</div>
  
 +!! html/parsoid
 +<div data-x-data-mw="foo" data-x-data-parsoid="bar" data-x-data-mw-someext="baz" data-ok="fred" data-parsoid='{"stx":"html","a":{"data-ooui":null,"data-bad:ns":null},"sa":{"data-ooui":"xyzzy","data-bad:ns":"ns"}}'>d</div>
  !! end
  
  !! test