[cgiowt] (2) Update the fragment parsing algorithm to handle <script>…

… more theoretically properly. And mention a quicker implementation strategy.

Fixing http://www.w3.org/Bugs/Public/show_bug.cgi?id=8099

git-svn-id: http://svn.whatwg.org/webapps@4457 340c8d12-0b0e-0410-8428-c7bf67bfef74

complete.html

@@ -108,7 +108,7 @@
 
   <header class=head id=head><p><a class=logo href=http://www.whatwg.org/ rel=home><img alt=WHATWG src=/images/logo></a></p>
    <hgroup><h1>Web Applications 1.0</h1>
-    <h2 class="no-num no-toc">Draft Standard &mdash; 21 December 2009</h2>
+    <h2 class="no-num no-toc">Draft Standard &mdash; 4 January 2010</h2>
    </hgroup><p>You can take part in this work. <a href=http://www.whatwg.org/mailing-list>Join the working group's discussion list.</a></p>
    <p><strong>Web designers!</strong> We have a <a href=http://blog.whatwg.org/faq/>FAQ</a>, a <a href=http://forums.whatwg.org/>forum</a>, and a <a href=http://www.whatwg.org/mailing-list#help>help mailing list</a> for you!</p>
    <!--<p class="impl"><strong>Implementors!</strong> We have a <a href="http://www.whatwg.org/mailing-list#implementors">mailing list</a> for you too!</p>-->
@@ -76711,13 +76711,18 @@ <h3 id=parsing-html-fragments><span class=secno>11.5 </span>Parsing HTML fragmen
        <dd>Switch the tokenizer to the <a href=#rcdata-state>RCDATA state</a>.</dd>
 
 
-       <dt>If it is a <code><a href=#the-style-element>style</a></code>, <code><a href=#script>script</a></code>,
-       <code><a href=#xmp>xmp</a></code>, <code><a href=#the-iframe-element>iframe</a></code>, <code><a href=#noembed>noembed</a></code>, or
+       <dt>If it is a <code><a href=#the-style-element>style</a></code>, <code><a href=#xmp>xmp</a></code>,
+       <code><a href=#the-iframe-element>iframe</a></code>, <code><a href=#noembed>noembed</a></code>, or
        <code><a href=#noframes>noframes</a></code> element</dt>
 
        <dd>Switch the tokenizer to the <a href=#rawtext-state>RAWTEXT state</a>.</dd>
 
 
+       <dt>If it is a <code><a href=#script>script</a></code> element</dt>
+
+       <dd>Switch the tokenizer to the <a href=#script-data-state>script data state</a>.</dd>
+
+
        <dt>If it is a <code><a href=#the-noscript-element>noscript</a></code> element</dt>
 
        <dd>If the <a href=#scripting-flag>scripting flag</a> is enabled, switch the
@@ -76735,7 +76740,15 @@ <h3 id=parsing-html-fragments><span class=secno>11.5 </span>Parsing HTML fragmen
 
        <dd>Leave the tokenizer in the <a href=#data-state>data state</a>.</dd>
 
-      </dl></li>
+      </dl><p class=note>For performance reasons, an implementation that
+      uses the actual state machine described in this specification
+      directly could use the PLAINTEXT state instead of the RAWTEXT
+      and script data states where those are mentioned in the list
+      above. They are equivalent, since there is no <a href=#appropriate-end-tag-token>appropriate
+      end tag token</a> in the fragment case, but involve far fewer
+      state transitions.</p>
+
+     </li>
 
      <li>
 

index

@@ -110,7 +110,7 @@
 
   <header class=head id=head><p><a class=logo href=http://www.whatwg.org/ rel=home><img alt=WHATWG src=/images/logo></a></p>
    <hgroup><h1>WHATWG HTML (Including HTML5)</h1>
-    <h2 class="no-num no-toc">Draft Standard &mdash; 21 December 2009</h2>
+    <h2 class="no-num no-toc">Draft Standard &mdash; 4 January 2010</h2>
    </hgroup><p>You can take part in this work. <a href=http://www.whatwg.org/mailing-list>Join the working group's discussion list.</a></p>
    <p><strong>Web designers!</strong> We have a <a href=http://blog.whatwg.org/faq/>FAQ</a>, a <a href=http://forums.whatwg.org/>forum</a>, and a <a href=http://www.whatwg.org/mailing-list#help>help mailing list</a> for you!</p>
    <!--<p class="impl"><strong>Implementors!</strong> We have a <a href="http://www.whatwg.org/mailing-list#implementors">mailing list</a> for you too!</p>-->
@@ -68338,13 +68338,18 @@ document.body.appendChild(text);
        <dd>Switch the tokenizer to the <a href=#rcdata-state>RCDATA state</a>.</dd>
 
 
-       <dt>If it is a <code><a href=#the-style-element>style</a></code>, <code><a href=#script>script</a></code>,
-       <code><a href=#xmp>xmp</a></code>, <code><a href=#the-iframe-element>iframe</a></code>, <code><a href=#noembed>noembed</a></code>, or
+       <dt>If it is a <code><a href=#the-style-element>style</a></code>, <code><a href=#xmp>xmp</a></code>,
+       <code><a href=#the-iframe-element>iframe</a></code>, <code><a href=#noembed>noembed</a></code>, or
        <code><a href=#noframes>noframes</a></code> element</dt>
 
        <dd>Switch the tokenizer to the <a href=#rawtext-state>RAWTEXT state</a>.</dd>
 
 
+       <dt>If it is a <code><a href=#script>script</a></code> element</dt>
+
+       <dd>Switch the tokenizer to the <a href=#script-data-state>script data state</a>.</dd>
+
+
        <dt>If it is a <code><a href=#the-noscript-element>noscript</a></code> element</dt>
 
        <dd>If the <a href=#scripting-flag>scripting flag</a> is enabled, switch the
@@ -68362,7 +68367,15 @@ document.body.appendChild(text);
 
        <dd>Leave the tokenizer in the <a href=#data-state>data state</a>.</dd>
 
-      </dl></li>
+      </dl><p class=note>For performance reasons, an implementation that
+      uses the actual state machine described in this specification
+      directly could use the PLAINTEXT state instead of the RAWTEXT
+      and script data states where those are mentioned in the list
+      above. They are equivalent, since there is no <a href=#appropriate-end-tag-token>appropriate
+      end tag token</a> in the fragment case, but involve far fewer
+      state transitions.</p>
+
+     </li>
 
      <li>
 

source

@@ -87469,13 +87469,18 @@ document.body.appendChild(text);
        <dd>Switch the tokenizer to the <span>RCDATA state</span>.</dd>
 
 
-       <dt>If it is a <code>style</code>, <code>script</code>,
-       <code>xmp</code>, <code>iframe</code>, <code>noembed</code>, or
+       <dt>If it is a <code>style</code>, <code>xmp</code>,
+       <code>iframe</code>, <code>noembed</code>, or
        <code>noframes</code> element</dt>
 
        <dd>Switch the tokenizer to the <span>RAWTEXT state</span>.</dd>
 
 
+       <dt>If it is a <code>script</code> element</dt>
+
+       <dd>Switch the tokenizer to the <span>script data state</span>.</dd>
+
+
        <dt>If it is a <code>noscript</code> element</dt>
 
        <dd>If the <span>scripting flag</span> is enabled, switch the
@@ -87495,6 +87500,14 @@ document.body.appendChild(text);
 
       </dl>
 
+      <p class="note">For performance reasons, an implementation that
+      uses the actual state machine described in this specification
+      directly could use the PLAINTEXT state instead of the RAWTEXT
+      and script data states where those are mentioned in the list
+      above. They are equivalent, since there is no <span>appropriate
+      end tag token</span> in the fragment case, but involve far fewer
+      state transitions.</p>
+
      </li>
 
      <li>