diff --git a/html2xdoc/.cvsignore b/html2xdoc/.cvsignore
new file mode 100644
index 00000000..5d21c883
--- /dev/null
+++ b/html2xdoc/.cvsignore
@@ -0,0 +1,2 @@
+target
+maven.log
diff --git a/html2xdoc/maven.xml b/html2xdoc/maven.xml
new file mode 100644
index 00000000..14295e0a
--- /dev/null
+++ b/html2xdoc/maven.xml
@@ -0,0 +1,12 @@
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/html2xdoc/plugin.jelly b/html2xdoc/plugin.jelly
new file mode 100644
index 00000000..bda37432
--- /dev/null
+++ b/html2xdoc/plugin.jelly
@@ -0,0 +1,87 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Generating ${outFile} from ${file}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/html2xdoc/project.xml b/html2xdoc/project.xml
new file mode 100644
index 00000000..13228c6a
--- /dev/null
+++ b/html2xdoc/project.xml
@@ -0,0 +1,106 @@
+
+
+
+ ${basedir}/../project.xml
+ 3
+ maven-html2xdoc-plugin
+ Maven Html2XDoc Plug-in
+ 1.0
+
+
+ jakarta
+ Creates XDoc documentation from normal HTML documentation.
+
+ http://jakarta.apache.org/turbine/maven/reference/plugins/html2xdoc/
+
+ /www/jakarta.apache.org/turbine/maven/reference/plugins/html2xdoc/
+
+
+ scm:cvs:pserver:anoncvs@cvs.apache.org:/home/cvspublic:jakarta-turbine-maven/src/plugins-build/html2xdoc/
+ http://cvs.apache.org/viewcvs/jakarta-turbine-maven/src/plugins-build/html2xdoc/
+
+
+
+
+ James Strachan
+ jstrachan
+ jstrachan@apache.org
+ SpiritSoft, Inc.
+
+ Java Developer
+
+
+
+
+
+
+ commons-jelly
+ commons-jelly-tags-xml
+ 20030211.142705
+ http://jakarta.apache.org/commons/jelly/tags/xml/
+
+ root.maven
+
+
+
+ commons-jelly
+ commons-jelly-tags-html
+ SNAPSHOT
+ http://jakarta.apache.org/commons/jelly/tags/html/
+
+ root.maven
+
+
+
+ nekohtml
+ 0.7.1
+
+ root.maven
+
+
+
+
+
+ commons-logging
+ 1.0.1
+
+ root.maven
+
+
+
+ dom4j
+ 1.4-dev-8
+ http://www.dom4j.org/
+
+
+ xml-apis
+ 1.0.b2
+ http://xml.apache.org/xerces2-j/
+
+
+ xerces
+ 2.2.1
+ http://xml.apache.org/xerces2-j/
+
+
+
+
+ src/main
+ src/test
+
+
+ **/Test*.java
+
+
+
+ src/test
+
+ *.xml
+ *.html
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/html2xdoc/src/main/org/apache/maven/html2xdoc/Html2XdocBean.java b/html2xdoc/src/main/org/apache/maven/html2xdoc/Html2XdocBean.java
new file mode 100644
index 00000000..89d8a4f6
--- /dev/null
+++ b/html2xdoc/src/main/org/apache/maven/html2xdoc/Html2XdocBean.java
@@ -0,0 +1,271 @@
+/*
+ * /home/cvs/jakarta-turbine-maven/src/plugins-build/jellydoc/src/main/org/apache/maven/jellydoc/TagXMLDoclet.java,v 1.1 2003/02/07 12:10:44 jstrachan Exp
+ * 1.1
+ * 2003/02/07 12:10:44
+ *
+ * ====================================================================
+ *
+ * The Apache Software License, Version 1.1
+ *
+ * Copyright (c) 2002 The Apache Software Foundation. All rights
+ * reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * 3. The end-user documentation included with the redistribution, if
+ * any, must include the following acknowlegement:
+ * "This product includes software developed by the
+ * Apache Software Foundation (http://www.apache.org/)."
+ * Alternately, this acknowlegement may appear in the software itself,
+ * if and wherever such third-party acknowlegements normally appear.
+ *
+ * 4. The names "The Jakarta Project", "Commons", and "Apache Software
+ * Foundation" must not be used to endorse or promote products derived
+ * from this software without prior written permission. For written
+ * permission, please contact apache@apache.org.
+ *
+ * 5. Products derived from this software may not be called "Apache"
+ * nor may "Apache" appear in their names without prior written
+ * permission of the Apache Group.
+ *
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
+ * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
+ * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+ * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
+ * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ * ====================================================================
+ *
+ * This software consists of voluntary contributions made by many
+ * individuals on behalf of the Apache Software Foundation. For more
+ * information on the Apache Software Foundation, please see
+ * .
+ *
+ * TagXMLDoclet.java,v 1.1 2003/02/07 12:10:44 jstrachan Exp
+ */
+
+package org.apache.maven.html2xdoc;
+
+import java.util.ArrayList;
+import java.util.Iterator;
+import java.util.LinkedList;
+import java.util.List;
+
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.dom4j.CharacterData;
+import org.dom4j.Document;
+import org.dom4j.DocumentFactory;
+import org.dom4j.Element;
+import org.dom4j.Node;
+
+/**
+ * A simple bean for converting a HTML document into an XDoc compliant XML document.
+ * This could be done via XSLT but is a little more complex than it might first
+ * appear so its done via Java code instead.
+ *
+ * @author James Strachan
+ */
+public class Html2XdocBean {
+
+ /** The Log to which logging calls will be made. */
+ private static final Log log = LogFactory.getLog(Html2XdocBean.class);
+
+ private DocumentFactory factory = new DocumentFactory();
+
+ /**
+ * Converts the given HTML document into the corresponding XDoc format
+ * of XML
+ *
+ * @param html
+ * @return Document
+ */
+ public Document convert(Document html) {
+ Document doc = factory.createDocument();
+ Element root = doc.addElement("document");
+ Element properties = root.addElement("properties");
+ Element title = properties.addElement("title");
+ title.setText(html.valueOf("/html/head/title"));
+
+ Element body = root.addElement("body");
+
+ Element htmlContent = (Element) html.selectSingleNode("/html/body");
+ if (htmlContent == null) {
+ log.info("No body element found for HTML document: " + html.asXML());
+ }
+ else {
+ addSections(body, htmlContent);
+ }
+ return doc;
+ }
+
+ /**
+ * Iterates thorugh the given body looking for h1, h2, h3 nodes and
+ * creating the associated section elements. Any text nodes
+ * contained inside the body are wrapped in a <p> element
+ *
+ * @param output the output destination
+ * @param body the block of HTML markup to convert
+ */
+ protected void addSections(Element output, Element body) {
+ List content = getBodyContent(body.content());
+ Element section = null;
+ Element p = null;
+
+ for (Iterator iter = content.iterator(); iter.hasNext(); ) {
+ Node node = (Node) iter.next();
+
+ String name = node.getName();
+ if (name != null && name.startsWith("h")) {
+ /** @todo we should handle child headings as a nested section */
+ section = output.addElement("section");
+ section.addAttribute("name", node.getText());
+ p = null;
+ }
+ else {
+ if (section == null ) {
+ // we have a section with no name
+ // should we default it to be the same as the document title?
+ section = output.addElement("section");
+ }
+
+ if (node instanceof CharacterData) {
+ // lets add a
+ if (p == null) {
+ p = section.addElement("p");
+ }
+ p.addText( node.getText() );
+ }
+ else {
+ section.add(cloneNode(node));
+ p = null;
+ }
+ }
+ }
+ }
+
+ /**
+ * @param node
+ * @return true if the given node is a heading element (h1, h2, h3 etc)
+ */
+ protected boolean isHeading(Node node) {
+ String name = node.getName();
+ return name != null && name.startsWith("h");
+ }
+
+ /**
+ * Returns a copy of the body content, removing any whitespace from the beginning and end
+ * @param body
+ * @return List
+ */
+ protected List getBodyContent(List content) {
+ // lets turn
into and concatenate consective entries
+ Element lastPre = null;
+ LinkedList list = new LinkedList();
+ boolean lastWasElement = true;
+ for (Iterator iter = content.iterator(); iter.hasNext(); ) {
+ Node node = (Node) iter.next();
+
+ if (isPre(node)) {
+ if (lastPre == null) {
+ lastPre = factory.createElement("source");
+ list.add(lastPre);
+ }
+ lastPre.addText(node.getText());
+ }
+ else {
+ if (isWhitespace(node) && lastWasElement) {
+ if (lastPre != null) {
+ lastPre.addText(node.getText());
+ }
+ }
+ else {
+ lastWasElement = node instanceof Element;
+ if (lastWasElement) {
+ lastPre = null;
+ }
+ list.add(node);
+ }
+ }
+ }
+
+ // now lets remove any whitespace text nodes at the beginning and end
+ while (true) {
+ Node node = (Node) list.getFirst();
+ if (isWhitespace(node)) {
+ list.removeFirst();
+ continue;
+ }
+ break;
+ }
+ while (true) {
+ Node node = (Node) list.getLast();
+ if (isWhitespace(node)) {
+ list.removeLast();
+ continue;
+ }
+ break;
+ }
+ return list;
+ }
+
+ protected boolean isPre(Node node) {
+ if (node instanceof Element) {
+ Element element = (Element) node;
+ return element.getName().equals("pre");
+ }
+ return false;
+ }
+
+ /**
+ * @return true if the given node is a whitespace text node
+ */
+ protected boolean isWhitespace(Node node) {
+ if (node instanceof CharacterData) {
+ String text = node.getText();
+ return text.trim().length() <= 0;
+ }
+ if (node instanceof Element) {
+ String name = node.getName();
+ if (name.equals("p")) {
+ String text = node.getText();
+ return text.trim().length() <= 0;
+ }
+ if (name.equals("br")) {
+ return true;
+ }
+ }
+ return false;
+ }
+
+ /**
+ * Normalizes the whitespace of any Elements
+ * @param node
+ * @return Node
+ */
+ protected Node cloneNode(Node node) {
+ Node answer = (Node) node.clone();
+ if (answer instanceof Element) {
+ Element element = (Element) answer;
+ element.normalize();
+ }
+ return answer;
+ }
+
+}
diff --git a/html2xdoc/src/test/org/apache/maven/html2xdoc/TestHtml2Xdoc.java b/html2xdoc/src/test/org/apache/maven/html2xdoc/TestHtml2Xdoc.java
new file mode 100644
index 00000000..53387fcd
--- /dev/null
+++ b/html2xdoc/src/test/org/apache/maven/html2xdoc/TestHtml2Xdoc.java
@@ -0,0 +1,203 @@
+/*
+ * /home/cvs/jakarta-turbine-maven/src/plugins-build/jellydoc/src/main/org/apache/maven/jellydoc/TagXMLDoclet.java,v 1.1 2003/02/07 12:10:44 jstrachan Exp
+ * 1.1
+ * 2003/02/07 12:10:44
+ *
+ * ====================================================================
+ *
+ * The Apache Software License, Version 1.1
+ *
+ * Copyright (c) 2002 The Apache Software Foundation. All rights
+ * reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * 3. The end-user documentation included with the redistribution, if
+ * any, must include the following acknowlegement:
+ * "This product includes software developed by the
+ * Apache Software Foundation (http://www.apache.org/)."
+ * Alternately, this acknowlegement may appear in the software itself,
+ * if and wherever such third-party acknowlegements normally appear.
+ *
+ * 4. The names "The Jakarta Project", "Commons", and "Apache Software
+ * Foundation" must not be used to endorse or promote products derived
+ * from this software without prior written permission. For written
+ * permission, please contact apache@apache.org.
+ *
+ * 5. Products derived from this software may not be called "Apache"
+ * nor may "Apache" appear in their names without prior written
+ * permission of the Apache Group.
+ *
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+ * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
+ * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
+ * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+ * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
+ * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ * ====================================================================
+ *
+ * This software consists of voluntary contributions made by many
+ * individuals on behalf of the Apache Software Foundation. For more
+ * information on the Apache Software Foundation, please see
+ * .
+ *
+ * TagXMLDoclet.java,v 1.1 2003/02/07 12:10:44 jstrachan Exp
+ */
+
+package org.apache.maven.html2xdoc;
+
+import java.io.IOException;
+import java.io.StringWriter;
+import java.net.URL;
+import java.util.Iterator;
+import java.util.LinkedList;
+import java.util.List;
+
+import org.dom4j.CharacterData;
+import org.dom4j.Document;
+import org.dom4j.DocumentFactory;
+import org.dom4j.Element;
+import org.dom4j.Node;
+import org.dom4j.io.OutputFormat;
+import org.dom4j.io.SAXReader;
+import org.dom4j.io.XMLWriter;
+
+import org.cyberneko.html.parsers.SAXParser;
+
+import junit.framework.Test;
+import junit.framework.TestCase;
+import junit.framework.TestSuite;
+import junit.textui.TestRunner;
+
+/**
+ * A test harness for the HTML to XDOC converter
+ *
+ * @author James Strachan
+ */
+public class TestHtml2Xdoc extends TestCase {
+
+ public static void main( String[] args ) {
+ TestRunner.run( suite() );
+ }
+
+ public static Test suite() {
+ return new TestSuite( TestHtml2Xdoc.class );
+ }
+
+ public TestHtml2Xdoc(String testName) {
+ super(testName);
+ }
+
+ // Test cases
+ //-------------------------------------------------------------------------
+ public void testOne() throws Exception {
+ assertConversion("input1.html", "output1.xml");
+ }
+
+ // Implementation methods
+ //-------------------------------------------------------------------------
+ protected void assertConversion(String input, String output) throws Exception {
+ Html2XdocBean converter = createConverter();
+ Document inputDoc = parseHtml(input);
+ Document expectedDoc = parse(output);
+
+ Document actualDoc = converter.convert(inputDoc);
+
+ assertEqual("Output for: " + input + " does not match: " + output, expectedDoc, actualDoc);
+ }
+
+ /**
+ * Asserts that the given two documents are equal
+ *
+ * @param string
+ * @param expectedDoc
+ * @param actualDoc
+ */
+ protected void assertEqual(
+ String message,
+ Document expectedDoc,
+ Document actualDoc) throws IOException {
+
+ String expectedText = getPrettyPrintText(expectedDoc);
+ String actualText = getPrettyPrintText(actualDoc);
+
+ if (!expectedText.equals(actualText)) {
+ System.out.println("Expected: " + expectedText);
+ System.out.println("Actual: " + actualText);
+ }
+ assertEquals(message, expectedText, actualText);
+ }
+
+ /**
+ * @param expectedDoc
+ * @return Object
+ */
+ protected String getPrettyPrintText(Document doc) throws IOException {
+ OutputFormat format = OutputFormat.createPrettyPrint();
+ StringWriter buffer = new StringWriter();
+ XMLWriter writer = new XMLWriter(buffer, format);
+ writer.write(doc);
+ writer.close();
+ return buffer.toString();
+ }
+
+ /**
+ * Parses the given String URI on the classpath and returns the docuemnt
+ *
+ * @param input
+ * @return Document
+ */
+ protected Document parse(String input) throws Exception {
+ URL url = getClassURL(input);
+ SAXReader saxReader = new SAXReader();
+ return saxReader.read(url);
+ }
+
+ /**
+ * Parses the given HTML using a String URI on the classpath
+ * and returns the docuemnt
+ *
+ * @param input
+ * @return Document
+ */
+ protected Document parseHtml(String input) throws Exception {
+ URL url = getClassURL(input);
+ SAXParser htmlParser = new SAXParser();
+ htmlParser.setProperty(
+ "http://cyberneko.org/html/properties/names/elems",
+ "lower"
+ );
+ htmlParser.setProperty(
+ "http://cyberneko.org/html/properties/names/attrs",
+ "lower"
+ );
+ SAXReader saxReader = new SAXReader(htmlParser);
+ return saxReader.read(url);
+ }
+
+ protected URL getClassURL(String input) throws Exception {
+ URL url = getClass().getResource(input);
+ assertTrue("Could not find resource on classpath for: " + input, url != null);
+ return url;
+ }
+
+ protected Html2XdocBean createConverter() {
+ return new Html2XdocBean();
+ }
+}
diff --git a/html2xdoc/src/test/org/apache/maven/html2xdoc/input1.html b/html2xdoc/src/test/org/apache/maven/html2xdoc/input1.html
new file mode 100644
index 00000000..7258110e
--- /dev/null
+++ b/html2xdoc/src/test/org/apache/maven/html2xdoc/input1.html
@@ -0,0 +1,19 @@
+
+
+
+
+ A title
+
+
+
+
A H1
+
+Some text
+
+More text
+
+
Some consective pres
+
hi
+
there
+
+
diff --git a/html2xdoc/src/test/org/apache/maven/html2xdoc/output1.xml b/html2xdoc/src/test/org/apache/maven/html2xdoc/output1.xml
new file mode 100644
index 00000000..14a18e13
--- /dev/null
+++ b/html2xdoc/src/test/org/apache/maven/html2xdoc/output1.xml
@@ -0,0 +1,16 @@
+
+
+ A title
+
+
+
+
Some text
+
+
+
More text
+
+
Some consective pres
+ hi there
+
+
+
\ No newline at end of file
diff --git a/html2xdoc/xdocs/.cvsignore b/html2xdoc/xdocs/.cvsignore
new file mode 100644
index 00000000..cb6131bb
--- /dev/null
+++ b/html2xdoc/xdocs/.cvsignore
@@ -0,0 +1 @@
+stylesheets
diff --git a/html2xdoc/xdocs/goals.xml b/html2xdoc/xdocs/goals.xml
new file mode 100644
index 00000000..1595769c
--- /dev/null
+++ b/html2xdoc/xdocs/goals.xml
@@ -0,0 +1,34 @@
+
+
+
+
+ Html2XDoc Plugin Goals
+ James Strachan
+
+
+
+
+
+
Goal
Description
+
+
+
+
html2xdoc
+
+ The default goal. This goal generates xdoc documents from some basic
+ HTML documentation which can then be styled by the xdoc goal to use
+ a uniform CSS style and add the common navigation links etc.
+
+ This goal means that normal vanilla HTML can be used to create documentation
+ using a WYSIWYG editing tool like Mozilla or MS FrontPage.
+
+ Most end user documentation
+ only requires basic formatting (bold, italic, bullets) along with headings and images and
+ links so using normal HTML for docuemntation with a WYSIWYG tool seems like a good idea.
+
+ This plugin generates xdoc documents from some basic
+ HTML documentation which can then be styled by the xdoc goal to use
+ a uniform CSS style and add the common navigation links etc.
+
+
+ This goal means that normal vanilla HTML can be used to create documentation
+ using a WYSIWYG editing tool like Mozilla or MS FrontPage.
+
+
+ Most end user documentation
+ only requires basic formatting (bold, italic, bullets) along with headings and images and
+ links so using normal HTML for documentation with a WYSIWYG tool is a good idea.
+
+
+ The properties that allow you to customize the execution
+ are documented here.
+
+
+ To enable HTML to xdoc conversion add the following to your maven.xml
+
+ Specifies the directory containing HTML documents which will be
+ turned into xdoc XML documents in the
+ target/generated-xdoc directory
+ ready for use by the xdoc plugin.
+
+
+
+
maven.html2xdoc.jsl
+
Yes
+
+ Allows the JSL stylesheet to be specified to perform some custom
+ HTML to XDoc transformation.
+