RELEASE_2_1_13/src/blocks/html/samples/htmltransformer/input.xml

<?xml version="1.0"?>
<!--
  Licensed to the Apache Software Foundation (ASF) under one or more
  contributor license agreements.  See the NOTICE file distributed with
  this work for additional information regarding copyright ownership.
  The ASF licenses this file to You under the Apache License, Version 2.0
  (the "License"); you may not use this file except in compliance with
  the License.  You may obtain a copy of the License at

      http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License.
-->

<!-- CVS $Id: samples.xml 158439 2005-03-21 10:17:23Z cziegeler $ -->

<html-transformer-test>
  <div id="explain">
    <p>
      This XML file contains HTML code with escaped markup: tags are written
      like &amp;lt;body/&amp;gt; with escaped &lt; and &gt; signs. This is
      often the case with RSS feeds.
    </p>
    <p>
      In this example, the HTMLTransformer is configured to parse the contents
      of the &lt;description&gt; and &lt;escaped-html&gt;, elements, creating
      well-formed content from this escaped markup.
    </p>
    <p>
      A downstream transform is used to filter the result, as the HTMLTransformer
      writes full HTML documents as &lt;html&gt; elements, for each input element
      that it parses.
    </p>
    <p>
      For more info search "HTMLTransformer" in the sitemap that drives this sample.
    </p>
  </div>
  <div id="content-with-escaped-html">
    <div id="example-1">
      <description>
        <!-- this element does not contain markup, only text with escaped &lt; and &gt; signs -->
        &lt;div style="background: #FFFFCC; color: black; margin: 1em;"&gt;
        &lt;h1&gt;Here's some escaped HTML&lt;/h1&gt;
        This test document contains escaped HTML code in the description elements,
        as is customary in RSS documents for example.
        &lt;p&gt;

        &lt;img align="right" src="http://cocoon.apache.org/2.1/images/cocoon.gif"/&gt;

        This description element contains escaped html markup, which should be
        converted to proper html by the HTMLTransformer. If the Cocoon logo is shown
        properly, it means that the parsing worked.
        &lt;blockquote&gt;
        This should be a blockquote and &lt;b&gt;here's some bold&lt;/b&gt;.
        &lt;/blockquote&gt;
        Note that the HTMLTransformer generates a complete HTML document for each element that
        is parsed - here this is filtered downstream to keep only the contents of the &amp;lt;body&amp;gt;
        of the parsed documents.
        &lt;/div&gt;
      </description>
    </div>

    <div id="example-2">
      <escaped-html>
        &lt;div style="background: #FFFFCC; color: black; margin: 1em;"&gt;
        &lt;h1&gt;More escaped HTML&lt;/h1&gt;

         &lt;img align="right" src="http://cocoon.apache.org/2.1/images/cocoon.gif"/&gt;

         Another description element with escaped html markup, including a Cocoon logo.
         &lt;p&gt;
         Here's some &lt;i&gt;italic&lt;/i&gt; and a &lt;a href="http://cocoon.apache.org"&gt;
         link to the Cocoon site&lt;/a&gt;.

         &lt;/div&gt;
      </escaped-html>
    </div>
  </div>
</html-transformer-test>