dims 01/07/13 13:01:06
Modified: src/org/apache/cocoon/generation Tag: cocoon_20_branch
HTMLGenerator.java
webapp Tag: cocoon_20_branch sitemap.xmap
webapp/docs/samples Tag: cocoon_20_branch samples.xml
Log:
Added a sample for HTML Generator - It also shows how to get a subset of the HTML
page using XPath.
Revision Changes Path
No revision
No revision
1.4.2.3 +38 -3 xml-cocoon2/src/org/apache/cocoon/generation/HTMLGenerator.java
Index: HTMLGenerator.java
===================================================================
RCS file: /home/cvs/xml-cocoon2/src/org/apache/cocoon/generation/HTMLGenerator.java,v
retrieving revision 1.4.2.2
retrieving revision 1.4.2.3
diff -u -r1.4.2.2 -r1.4.2.3
--- HTMLGenerator.java 2001/07/07 19:08:16 1.4.2.2
+++ HTMLGenerator.java 2001/07/13 20:00:52 1.4.2.3
@@ -18,9 +18,11 @@
import org.apache.avalon.excalibur.pool.Recyclable;
import org.apache.avalon.framework.component.Component;
import org.apache.avalon.framework.parameters.Parameters;
+import org.apache.cocoon.environment.Request;
import org.apache.avalon.excalibur.pool.Poolable;
import org.apache.cocoon.ProcessingException;
import org.apache.cocoon.ResourceNotFoundException;
+import org.apache.cocoon.Constants;
import org.apache.cocoon.caching.Cacheable;
import org.apache.cocoon.caching.CacheValidity;
import org.apache.cocoon.caching.TimeStampCacheValidity;
@@ -30,17 +32,29 @@
import org.apache.cocoon.xml.dom.DOMStreamer;
import org.w3c.tidy.Tidy;
import org.xml.sax.SAXException;
+import javax.xml.transform.Transformer;
+import javax.xml.transform.TransformerFactory;
+import javax.xml.transform.dom.DOMSource;
+import javax.xml.transform.sax.SAXResult;
+import org.apache.xpath.XPathAPI;
+import org.w3c.dom.Node;
+import org.w3c.dom.traversal.NodeIterator;
+import org.xml.sax.InputSource;
+import javax.xml.transform.OutputKeys;
/**
* @author <a href="mailto:[EMAIL PROTECTED]";>Davanum Srinivas</a>
* @author <a href="mailto:[EMAIL PROTECTED]";>Carsten Ziegeler</a>
- * @version CVS $Revision: 1.4.2.2 $ $Date: 2001/07/07 19:08:16 $
+ * @version CVS $Revision: 1.4.2.3 $ $Date: 2001/07/13 20:00:52 $
*/
public class HTMLGenerator extends ComposerGenerator implements Cacheable,
Recyclable {
/** The source */
private Source inputSource;
+ /** XPATH expression */
+ private String xpath = null;
+
/**
* Recycle this component.
* All instance variables are set to <code>null</code>.
@@ -48,6 +62,7 @@
public void recycle() {
super.recycle();
this.inputSource = null;
+ this.xpath = null;
}
/**
@@ -58,6 +73,11 @@
throws ProcessingException, SAXException, IOException {
super.setup(resolver, objectModel, src, par);
this.inputSource = resolver.resolve(super.source);
+
+ Request request = (Request) objectModel.get(Constants.REQUEST_OBJECT);
+ xpath = request.getParameter("xpath");
+ if(xpath == null)
+ xpath = par.getParameter("xpath",null);
}
/**
@@ -104,8 +124,23 @@
// Extract the document using JTidy and stream it.
org.w3c.dom.Document doc = tidy.parseDOM(new
BufferedInputStream(this.inputSource.getInputStream()), null);
- DOMStreamer streamer = new
DOMStreamer(this.contentHandler,this.lexicalHandler);
- streamer.stream(doc);
+ if(xpath != null)
+ {
+ Transformer serializer =
TransformerFactory.newInstance().newTransformer();
+ serializer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION,
"yes");
+
+ NodeIterator nl = XPathAPI.selectNodeIterator(doc, xpath);
+ Node n;
+ while ((n = nl.nextNode())!= null)
+ {
+ SAXResult result = new SAXResult(this.contentHandler);
+ result.setLexicalHandler(this.lexicalHandler);
+ serializer.transform(new DOMSource(n), result);
+ }
+ } else {
+ DOMStreamer streamer = new
DOMStreamer(this.contentHandler,this.lexicalHandler);
+ streamer.stream(doc);
+ }
} catch (IOException e){
getLogger().warn("HTMLGenerator.generate()", e);
throw new ResourceNotFoundException("Could not get Resource for
HTMLGenerator", e);
No revision
No revision
1.11.2.18 +10 -0 xml-cocoon2/webapp/sitemap.xmap
Index: sitemap.xmap
===================================================================
RCS file: /home/cvs/xml-cocoon2/webapp/sitemap.xmap,v
retrieving revision 1.11.2.17
retrieving revision 1.11.2.18
diff -u -r1.11.2.17 -r1.11.2.18
--- sitemap.xmap 2001/07/13 15:16:09 1.11.2.17
+++ sitemap.xmap 2001/07/13 20:00:57 1.11.2.18
@@ -570,6 +570,16 @@
<map:serialize/>
</map:match>
+ <!-- ========================== Tidy Samples ============================== -->
+
+ <map:match pattern="yahoo">
+ <map:generate type="html" src="http://www.yahoo.com";>
+ <map:parameter name="xpath" value="//form/table[3]/tr/td/table[2]"/>
+ </map:generate>
+ <map:transform src="stylesheets/news/news.xsl"/>
+ <map:serialize type="html"/>
+ </map:match>
+
<!-- ========================= Server ================================ -->
<map:match pattern="generror">
<map:generate src="docs/samples/error-giving-page.xml"/>
No revision
No revision
1.3.2.5 +3 -0 xml-cocoon2/webapp/docs/samples/samples.xml
Index: samples.xml
===================================================================
RCS file: /home/cvs/xml-cocoon2/webapp/docs/samples/samples.xml,v
retrieving revision 1.3.2.4
retrieving revision 1.3.2.5
diff -u -r1.3.2.4 -r1.3.2.5
--- samples.xml 2001/07/13 13:40:19 1.3.2.4
+++ samples.xml 2001/07/13 20:01:04 1.3.2.5
@@ -121,6 +121,9 @@
<sample name="Parameterised Redirect"
href="redirect?dest=http://xml.apache.org/";>
An example of redirecting a client based on a request parameter.
</sample>
+ <sample name="Yahoo Screen Scrape" href="yahoo">
+ An example of HTML Generator scraping a part of the Yahoo main page.
+ </sample>
</group>
<group name="Web Applications">
----------------------------------------------------------------------
In case of troubles, e-mail: [EMAIL PROTECTED]
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
