[jbossws-commits] JBossWS SVN: r13187 - in projects: magnolia2docbook and 5 other directories.

Author: alessio.soldano(a)jboss.com Date: 2010-10-25 13:29:29 -0400 (Mon, 25 Oct 2010) New Revision: 13187 Added: projects/magnolia2docbook/ projects/magnolia2docbook/README projects/magnolia2docbook/src/ projects/magnolia2docbook/src/org/ projects/magnolia2docbook/src/org/jboss/ projects/magnolia2docbook/src/org/jboss/util/ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Converter.java projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/DocBookPage.java projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/FilteredURLException.java projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/JBossWSLinkFilter.java projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/LinkFilter.java projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Magnolia2DocBook.java projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Page.java projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Registry.java projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/XHTMLPage.java projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/xhtml2docbook.xsl Log: Adding prototype application for automatically generating docbook files from JBoss.org Magnolia "wiki" Added: projects/magnolia2docbook/README =================================================================== --- projects/magnolia2docbook/README (rev 0) +++ projects/magnolia2docbook/README 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,15 @@ +For now, you can simply compile the app classes with JDK6 +> javac org/jboss/util/magnolia2docbook/* + +then run the app with +> java org.jboss.util.magnolia2docbook.Magnolia2DocBook <url> + +By default the app filters urls not starting with "JBossWS", "wsconsume" or "wsprovide". +Custom filters can be provided, still need to become configurable. + +Once the docbook xml files are generated (currently in output_docbook), a simple +frontend page can be manually created importing all files as preferred (each file +defines a chapter). + +All links referencing object/section/chapter in the generated files use <link> for +resolving without going over the network. Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Converter.java =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Converter.java (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Converter.java 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,94 @@ +/* + * JBoss, Home of Professional Open Source. + * Copyright 2010, Red Hat Middleware LLC, and individual contributors + * as indicated by the @author tags. See the copyright.txt file in the + * distribution for a full listing of individual contributors. + * + * This is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as + * published by the Free Software Foundation; either version 2.1 of + * the License, or (at your option) any later version. + * + * This software is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.jboss.util.magnolia2docbook; + +import java.io.ByteArrayInputStream; +import java.io.File; +import java.io.FileInputStream; +import java.io.FileOutputStream; +import java.io.InputStream; +import java.io.OutputStream; +import java.net.URL; +import java.util.HashMap; +import java.util.Map; + +import javax.xml.parsers.SAXParserFactory; +import javax.xml.transform.Transformer; +import javax.xml.transform.TransformerFactory; +import javax.xml.transform.sax.SAXSource; +import javax.xml.transform.stream.StreamResult; +import javax.xml.transform.stream.StreamSource; + +import org.xml.sax.InputSource; +import org.xml.sax.XMLReader; + +public class Converter +{ + private static TransformerFactory tFactory = TransformerFactory.newInstance(); + private static URL xhtml2docbookXsl = Converter.class.getResource("xhtml2docbook.xsl"); + + public static synchronized DocBookPage convert(XHTMLPage page, String outputDir) throws Exception + { + page.update(); + String content = page.getContent(); + + Map<String, String> params = new HashMap<String, String>(); + params.put("filename", page.getName()); //consumed by the xsl for generating chapter ids + + DocBookPage docBookPage = new DocBookPage(page.getName(), page.getOutgoingLinks(), outputDir); + applyTransformation(xhtml2docbookXsl, new ByteArrayInputStream(content.getBytes()), docBookPage.getOutputStream(), params); + + return docBookPage; + } + + public static synchronized void applyTransformation(URL xsl, InputStream content, OutputStream result) throws Exception + { + applyTransformation(xsl, content, result, null); + } + + public static synchronized void applyTransformation(URL xsl, InputStream content, OutputStream result, Map<String, String> params) throws Exception + { + SAXParserFactory spf = SAXParserFactory.newInstance(); + spf.setNamespaceAware(true); spf.setValidating(false); // Turn off validation + spf.setFeature("http://apache.org/xml/features/nonvalidating/load-ex...;, false); + XMLReader rdr = spf.newSAXParser().getXMLReader(); + + Transformer trans = tFactory.newTransformer(new StreamSource(new File(xsl.toURI()))); + if (params != null) + { + for (String k : params.keySet()) + { + trans.setParameter(k, params.get(k)); + } + } + trans.transform(new SAXSource(rdr, new InputSource(content)), new StreamResult(result)); + } + + public static void main(String[] args) throws Exception + { + FileInputStream is = new FileInputStream(args[1]); + FileOutputStream os = new FileOutputStream(args[2]); + applyTransformation(new File(args[0]).toURI().toURL(), is, os); + os.close(); + is.close(); + } +} Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/DocBookPage.java =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/DocBookPage.java (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/DocBookPage.java 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,77 @@ +/* + * JBoss, Home of Professional Open Source. + * Copyright 2010, Red Hat Middleware LLC, and individual contributors + * as indicated by the @author tags. See the copyright.txt file in the + * distribution for a full listing of individual contributors. + * + * This is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as + * published by the Free Software Foundation; either version 2.1 of + * the License, or (at your option) any later version. + * + * This software is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.jboss.util.magnolia2docbook; + +import java.io.File; +import java.io.FileOutputStream; +import java.io.IOException; +import java.io.OutputStream; +import java.net.URL; +import java.util.Set; + +public class DocBookPage implements Page +{ + private OutputStream os; + private String name; + private Set<URL> links; + private String outputDir; + + public DocBookPage(String name, Set<URL> links, String outputDir) + { + this.name = name; + this.links = links; + this.outputDir = outputDir; + } + + @Override + public Set<URL> getOutgoingLinks() + { + return links; + } + + @Override + public void write() throws IOException + { + os.flush(); + os.close(); + os = null; + } + + public OutputStream getOutputStream() throws Exception + { + if (os == null) + { + File dir = new File(outputDir); + if (!dir.exists()) + { + dir.mkdir(); + } + os = new FileOutputStream(new File(dir, getFilename())); + } + return os; + } + + private String getFilename() + { + return name + ".xml"; + } +} Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/FilteredURLException.java =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/FilteredURLException.java (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/FilteredURLException.java 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,32 @@ +/* + * JBoss, Home of Professional Open Source. + * Copyright 2010, Red Hat Middleware LLC, and individual contributors + * as indicated by the @author tags. See the copyright.txt file in the + * distribution for a full listing of individual contributors. + * + * This is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as + * published by the Free Software Foundation; either version 2.1 of + * the License, or (at your option) any later version. + * + * This software is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.jboss.util.magnolia2docbook; + +public class FilteredURLException extends Exception +{ + private static final long serialVersionUID = 5181162966146479113L; + + public FilteredURLException() + { + super(); + } +} Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/JBossWSLinkFilter.java =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/JBossWSLinkFilter.java (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/JBossWSLinkFilter.java 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,36 @@ +/* + * JBoss, Home of Professional Open Source. + * Copyright 2010, Red Hat Middleware LLC, and individual contributors + * as indicated by the @author tags. See the copyright.txt file in the + * distribution for a full listing of individual contributors. + * + * This is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as + * published by the Free Software Foundation; either version 2.1 of + * the License, or (at your option) any later version. + * + * This software is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.jboss.util.magnolia2docbook; + +import java.net.URL; + +public class JBossWSLinkFilter implements LinkFilter +{ + + @Override + public boolean accept(URL url) + { + String path = url.getPath() != null ? url.getPath().toLowerCase() : ""; + return (path.contains("jbossws") || path.contains("jbws") || path.contains("wsconsume") || path.contains("wsprovide")); + } + +} Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/LinkFilter.java =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/LinkFilter.java (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/LinkFilter.java 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,29 @@ +/* + * JBoss, Home of Professional Open Source. + * Copyright 2010, Red Hat Middleware LLC, and individual contributors + * as indicated by the @author tags. See the copyright.txt file in the + * distribution for a full listing of individual contributors. + * + * This is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as + * published by the Free Software Foundation; either version 2.1 of + * the License, or (at your option) any later version. + * + * This software is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.jboss.util.magnolia2docbook; + +import java.net.URL; + +public interface LinkFilter +{ + public boolean accept(URL url); +} Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Magnolia2DocBook.java =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Magnolia2DocBook.java (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Magnolia2DocBook.java 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,113 @@ +/* + * JBoss, Home of Professional Open Source. + * Copyright 2010, Red Hat Middleware LLC, and individual contributors + * as indicated by the @author tags. See the copyright.txt file in the + * distribution for a full listing of individual contributors. + * + * This is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as + * published by the Free Software Foundation; either version 2.1 of + * the License, or (at your option) any later version. + * + * This software is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.jboss.util.magnolia2docbook; + +import java.net.URL; +import java.util.Collection; +import java.util.HashSet; +import java.util.LinkedList; +import java.util.List; +import java.util.Set; + +public class Magnolia2DocBook +{ + + /** + * @param args + */ + public static void main(String[] args) throws Exception + { + String startPage = args[0]; + LinkFilter filter = new JBossWSLinkFilter(); //TODO read from args + Magnolia2DocBook m2d = new Magnolia2DocBook(); + m2d.run(new URL(startPage), false, "output", filter); + + } + + public void run(URL pageUrl, boolean recursive, String outputDir, LinkFilter filter) throws Exception + { + List<XHTMLPage> xhtmlPages = new LinkedList<XHTMLPage>(); + Registry registry = new Registry(); + xhtmlPages.add(XHTMLPage.newInstance(pageUrl, registry, outputDir)); + Set<URL> todo = getTodo(xhtmlPages, registry); + System.out.println("-> Outgoing links to process: " + todo.size()); + while (!todo.isEmpty()) + { + List<XHTMLPage> addedPages = new LinkedList<XHTMLPage>(); + for (URL url : todo) + { + try + { + addedPages.add(XHTMLPage.newInstance(url, registry, outputDir, filter)); + } + catch (FilteredURLException e) + { + System.out.println("* Skipped filtered page: " + url); + } + catch (Exception e) + { + e.printStackTrace(); + } + } + xhtmlPages.addAll(addedPages); + todo = getTodo(addedPages, registry); + System.out.println("-> Outgoing links to process: " + todo.size()); + } + //Convert + System.out.println("*** Convert Phase ***"); + for (XHTMLPage xhtmlPage : xhtmlPages) + { +// xhtmlPage.update(); +// xhtmlPage.write(); + + try + { + DocBookPage docBookPage = Converter.convert(xhtmlPage, outputDir + "_docbook"); + xhtmlPage.write(); + docBookPage.write(); + System.out.println("Conversion of " + xhtmlPage.getName() + " OK"); + } + catch (Throwable t) + { + System.out.println("Conversion of " + xhtmlPage.getName() + " FAILED!"); + t.printStackTrace(); + } + } + } + + private <T extends Page> Set<URL> getTodo(Collection<T> pages, Registry registry) + { + Set<URL> result = new HashSet<URL>(); + for (Page page : pages) + { + for (URL link : page.getOutgoingLinks()) + { + if (!registry.hasReference(link)) + { + result.add(link); + } + } + } + return result; + } + +} Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Page.java =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Page.java (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Page.java 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,34 @@ +/* + * JBoss, Home of Professional Open Source. + * Copyright 2010, Red Hat Middleware LLC, and individual contributors + * as indicated by the @author tags. See the copyright.txt file in the + * distribution for a full listing of individual contributors. + * + * This is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as + * published by the Free Software Foundation; either version 2.1 of + * the License, or (at your option) any later version. + * + * This software is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.jboss.util.magnolia2docbook; + +import java.io.IOException; +import java.net.URL; +import java.util.Set; + +public interface Page +{ + public Set<URL> getOutgoingLinks(); + + public void write() throws IOException; + +} Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Registry.java =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Registry.java (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/Registry.java 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,83 @@ +/* + * JBoss, Home of Professional Open Source. + * Copyright 2010, Red Hat Middleware LLC, and individual contributors + * as indicated by the @author tags. See the copyright.txt file in the + * distribution for a full listing of individual contributors. + * + * This is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as + * published by the Free Software Foundation; either version 2.1 of + * the License, or (at your option) any later version. + * + * This software is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this software; if not, write to the Free + * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA, or see the FSF site: http://www.fsf.org. + */ +package org.jboss.util.magnolia2docbook; + +import java.net.URL; +import java.util.HashMap; +import java.util.HashSet; +import java.util.Map; +import java.util.Set; + +public class Registry +{ + private Map<String, String> locations; + private Set<String> names; + + public Registry() + { + locations = new HashMap<String, String>(); + names = new HashSet<String>(); + } + + public void addReference(URL reference, String name) + { + String key = getKey(reference); +// System.out.println("Mapping " + key + " to " + name); + locations.put(key, name); + names.add(name); + } + + public boolean hasReference(URL reference) + { + return getReference(reference) != null; + } + + public String getReference(URL reference) + { + String key = getKey(reference); + return locations.get(key); + } + + public boolean isReferenced(String name) + { + return names.contains(name); + } + + private String getKey(URL url) + { + String protocol = url.getProtocol(); + if (!protocol.toLowerCase().startsWith("http")) + { + throw new RuntimeException("Unsupported protocol for url " + url); + } + String path = url.getPath(); + if (path.endsWith("/")) + { + path = path.substring(0, path.length() - 1); + } + return path; + +// String query = url.getQuery(); +// return path != null ? path : "" + query != null ? query : ""; + } + +} Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/XHTMLPage.java =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/XHTMLPage.java (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/XHTMLPage.java 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,536 @@ +package org.jboss.util.magnolia2docbook; + +import java.io.BufferedReader; +import java.io.ByteArrayInputStream; +import java.io.ByteArrayOutputStream; +import java.io.File; +import java.io.FileWriter; +import java.io.IOException; +import java.io.InputStreamReader; +import java.net.HttpURLConnection; +import java.net.MalformedURLException; +import java.net.URL; +import java.net.URLEncoder; +import java.util.Arrays; +import java.util.HashSet; +import java.util.List; +import java.util.Set; + +import javax.xml.namespace.QName; +import javax.xml.stream.XMLInputFactory; +import javax.xml.stream.XMLOutputFactory; +import javax.xml.stream.XMLStreamException; +import javax.xml.stream.XMLStreamReader; +import javax.xml.stream.XMLStreamWriter; +import javax.xml.stream.events.XMLEvent; + +public class XHTMLPage implements Page +{ + private static final String WIKI_LINK_CLASS = "jive-link-wiki"; + private static final String DOCUMENT_BODY_START = "[DocumentBodyStart:"; + private static final String DOCUMENT_BODY_END = "[DocumentBodyEnd:"; + + private static final String XHTML_NS = "http://www.w3.org/1999/xhtml"; + private static final QName A = new QName(XHTML_NS, "a"); + private static final QName BODY = new QName(XHTML_NS, "body"); + private static final QName BR = new QName(XHTML_NS, "br"); + private static final QName CODE = new QName(XHTML_NS, "code"); + private static final QName DIV = new QName(XHTML_NS, "div"); + private static final QName TBODY = new QName(XHTML_NS, "tbody"); + private static final QName THEAD = new QName(XHTML_NS, "thead"); + private static final QName TFOOT = new QName(XHTML_NS, "tfoot"); + private static final QName HTML = new QName(XHTML_NS, "html"); + private static final String CLASS = "class"; + private static final String HREF = "href"; + private static final String ID = "id"; + private static final String SECTION = "section"; + private static final String LOCATION_HEADER = "Location"; + private static final int BASE_H_LEVEL = 0; + + private URL url; + private URL actualUrl; + private String name; + private String content; + private Set<URL> links; + private Registry registry; + private String outputDir; + + public static XHTMLPage newInstance(URL url, Registry registry, String outputDir, LinkFilter filter) throws IOException, MalformedURLException, FilteredURLException + { + return new XHTMLPage(url, registry, outputDir, filter); + } + + public static XHTMLPage newInstance(URL url, Registry registry, String outputDir) throws IOException, MalformedURLException, FilteredURLException + { + return new XHTMLPage(url, registry, outputDir, null); + } + + private XHTMLPage(URL url, Registry registry, String outputDir, LinkFilter filter) throws IOException, MalformedURLException, FilteredURLException + { + this.url = url; + this.links = new HashSet<URL>(); + this.registry = registry; + this.outputDir = outputDir; + processContent(filter); + processLinks(); + } + + public URL getUrl() + { + return url; + } + public String getName() + { + return name; + } + + private void setName(URL url) + { + name = getNameFromUrl(url); + } + + @SuppressWarnings("deprecation") + private static String getNameFromUrl(URL url) + { + String path = url.getPath(); + if (path.endsWith("/")) + { + path = path.substring(0, path.length() - 1); + } + String result = path.substring(path.lastIndexOf("/") + 1); +// if (url.getQuery() != null) +// { +// result = result + url.getQuery(); +// } + result = URLEncoder.encode(result); + return result; + } + + private void processContent(LinkFilter filter) throws IOException, MalformedURLException, FilteredURLException + { + this.actualUrl = this.url; + HttpURLConnection con = (HttpURLConnection)appendDecoratorQuery(actualUrl).openConnection(); + + con.setInstanceFollowRedirects(false); + con.connect(); + boolean passFilter = filter == null || filter.accept(actualUrl); + int responseCode = con.getResponseCode(); +// System.out.println("pass="+passFilter+" code="+responseCode); + while (responseCode == HttpURLConnection.HTTP_MOVED_TEMP || responseCode == HttpURLConnection.HTTP_MOVED_PERM) + { + String location = con.getHeaderField(LOCATION_HEADER); + actualUrl = location.startsWith("http") ? new URL(location) : new URL(actualUrl.getProtocol(), actualUrl.getHost(), actualUrl.getPort(), location); + passFilter = passFilter || filter.accept(actualUrl); +// System.out.println("actualUrl="+actualUrl+" pass="+passFilter); + con.disconnect(); + con = (HttpURLConnection)actualUrl.openConnection(); + con.setInstanceFollowRedirects(false); + con.connect(); + responseCode = con.getResponseCode(); + } + if (responseCode != HttpURLConnection.HTTP_OK) + { + con.disconnect(); + throw new IOException("Response code " + responseCode + " received connecting to URL " + actualUrl); + } + if (!passFilter) + { + con.disconnect(); + throw new FilteredURLException(); + } + setName(actualUrl); + System.out.println("** Creating XHTMLPage '" + name + "' from URL: " + url); + registry.addReference(url, name); + if (!((Object)actualUrl).equals((Object)url)) + { + registry.addReference(actualUrl, name); + } + + BufferedReader in = new BufferedReader(new InputStreamReader(con.getInputStream())); + StringBuilder sb = new StringBuilder(); + sb.append("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n"); + sb.append("<" + HTML.getLocalPart() + " xmlns=\"" + HTML.getNamespaceURI() + "\" xml:lang=\"en\" lang=\"en\">\n"); + sb.append("<head><title>"); + sb.append(name); + sb.append("</title></head>\n"); + sb.append("<body>"); + String line; + boolean startReached = false; + boolean stopReached = false; + while ((line = in.readLine()) != null) + { + if (!stopReached) + { + if (!startReached) + { + if (line.contains(DOCUMENT_BODY_START)) + { + startReached = true; + } + } + if (startReached) + { + if (line.contains(DOCUMENT_BODY_END)) + { + stopReached = true; + } + sb.append(line); + sb.append("\n"); + } + + } + } + sb.append("</body>\n"); + sb.append("</html>"); + content = sb.toString(); + + con.disconnect(); + } + + private void processLinks() + { + try + { + XMLInputFactory xmlif = null; + xmlif = XMLInputFactory.newInstance(); + xmlif.setProperty(XMLInputFactory.IS_REPLACING_ENTITY_REFERENCES, Boolean.TRUE); + xmlif.setProperty(XMLInputFactory.IS_SUPPORTING_EXTERNAL_ENTITIES, Boolean.FALSE); + xmlif.setProperty(XMLInputFactory.IS_NAMESPACE_AWARE, Boolean.TRUE); + xmlif.setProperty(XMLInputFactory.IS_VALIDATING, Boolean.FALSE); + xmlif.setProperty(XMLInputFactory.IS_COALESCING, Boolean.TRUE); + XMLStreamReader xmlr = xmlif.createXMLStreamReader(new ByteArrayInputStream(content.getBytes())); + int eventType = xmlr.getEventType(); + while (xmlr.hasNext()) + { + eventType = xmlr.next(); + switch (eventType) + { + case XMLEvent.START_ELEMENT: + if (A.equals(xmlr.getName())) + { + String clazz = xmlr.getAttributeValue(null, CLASS); + if (clazz != null && clazz.startsWith(WIKI_LINK_CLASS)) + { + String value = xmlr.getAttributeValue(null, HREF); + //links.add(value.startsWith("http") ? new URL(value) : new URL(actualUrl, value)); + links.add(value.startsWith("http") ? new URL(value) : composeURL(actualUrl, value)); + } + } + break; + } + } + } + catch (Exception e) + { + throw new RuntimeException(e); + } + } + + private static URL composeURL(URL base, String location) throws MalformedURLException + { + URL url = new URL(base, location); + String path = url.getPath(); +// System.out.println("path ->> "+path); + while (path.startsWith("/..")) //swallow trailing .. in the path, as that's not possible + { + path = path.substring(3); + url = new URL(url.getProtocol(), url.getHost(), url.getPort(), path); + } + return url; + } + + public void update() + { + try + { + ByteArrayOutputStream bos = new ByteArrayOutputStream(); //TODO evaluate streaming for performance reasons... + XMLOutputFactory xof = XMLOutputFactory.newInstance(); + XMLStreamWriter xtw = xof.createXMLStreamWriter(bos); + + XMLInputFactory xmlif = null; + xmlif = XMLInputFactory.newInstance(); + xmlif.setProperty(XMLInputFactory.IS_REPLACING_ENTITY_REFERENCES, Boolean.TRUE); + xmlif.setProperty(XMLInputFactory.IS_SUPPORTING_EXTERNAL_ENTITIES, Boolean.FALSE); + xmlif.setProperty(XMLInputFactory.IS_NAMESPACE_AWARE, Boolean.TRUE); + xmlif.setProperty(XMLInputFactory.IS_VALIDATING, Boolean.FALSE); + xmlif.setProperty(XMLInputFactory.IS_COALESCING, Boolean.TRUE); + XMLStreamReader xmlr = xmlif.createXMLStreamReader(new ByteArrayInputStream(content.getBytes())); + int eventType = xmlr.getEventType(); + + boolean insideCode = false; + int nestedSectionLevel = BASE_H_LEVEL; + int lowerNestedSectionLevel = BASE_H_LEVEL; + + while (xmlr.hasNext()) + { + eventType = xmlr.next(); + switch (eventType) + { + case XMLEvent.START_ELEMENT : { + QName elName = xmlr.getName(); + if (TBODY.equals(elName) || THEAD.equals(elName) || TFOOT.equals(elName)) + { + //completely ignore and flatten the table joining head, body and foot + //(as tbody / thead / tfoot tags break the xhtml2docbook xsl conversion) + break; + } + else if (A.equals(elName)) + { + String clazz = xmlr.getAttributeValue(null, CLASS); + if (clazz != null && clazz.startsWith(WIKI_LINK_CLASS)) + { + updateLink(xmlr, xtw); + break; + } + else + { + xtw.writeStartElement(xmlr.getPrefix(), xmlr.getLocalName(), xmlr.getNamespaceURI()); + } + } + else if (insideCode && BR.equals(elName)) + { + //replace with new line to prevent messing up with java code blocks + xtw.writeCharacters("\n"); + } + else if (CODE.equals(elName)) + { + insideCode = true; + break; + } + else if (elName.getLocalPart().startsWith("h") && elName.getLocalPart().length() == 2 && XHTML_NS.equals(elName.getNamespaceURI())) + { + int hLevel = Integer.valueOf(elName.getLocalPart().substring(1)); +// System.out.println("cur lev: " + nestedSectionLevel + ", found h"+hLevel); + if (hLevel == nestedSectionLevel + 1) + { + nestedSectionLevel++; + startSection(xmlr, xtw); + break; + } + else if (hLevel == nestedSectionLevel) + { + xtw.writeEndElement(); + xtw.writeCharacters("\n"); + startSection(xmlr, xtw); + break; + } + else if (hLevel < nestedSectionLevel) + { + int nestDiff = nestedSectionLevel - hLevel; + for (int i = 0; i < nestDiff + 1; i++) + { + xtw.writeEndElement(); + xtw.writeCharacters("\n"); + } + nestedSectionLevel = hLevel; + startSection(xmlr, xtw); + break; + } + else if (hLevel > nestedSectionLevel && nestedSectionLevel == lowerNestedSectionLevel && lowerNestedSectionLevel == BASE_H_LEVEL) + { + //when -for instance- the page does not use anything below h4 + nestedSectionLevel = hLevel; + lowerNestedSectionLevel = hLevel - 1; + startSection(xmlr, xtw); + break; + } + else + { + System.out.println("WARNING: unsupported Hx tags sequence found"); + xtw.writeStartElement(xmlr.getPrefix(), xmlr.getLocalName(), xmlr.getNamespaceURI()); + } + } + else + { + xtw.writeStartElement(xmlr.getPrefix(), xmlr.getLocalName(), xmlr.getNamespaceURI()); + if (HTML.equals(elName)) + { + xtw.writeNamespace(xmlr.getPrefix(), xmlr.getNamespaceURI()); + } + } + copyElementAttributes(xmlr, xtw); + break; + } + case XMLEvent.END_ELEMENT: { + QName elName = xmlr.getName(); + if (TBODY.equals(elName) || THEAD.equals(elName) || TFOOT.equals(elName)) + { + //ignore + } + else if (CODE.equals(elName)) + { + insideCode = false; + } + else if (insideCode && BR.equals(elName)) + { + //ignore + } + else + { + if (BODY.equals(elName) && nestedSectionLevel > lowerNestedSectionLevel) + { + for (int i = 0; i < nestedSectionLevel - lowerNestedSectionLevel; i++) + { + xtw.writeEndElement(); + } + nestedSectionLevel = 0; + } + xtw.writeEndElement(); + } + break; + } + case XMLEvent.ATTRIBUTE: { + //ignore + break; + } + case XMLEvent.PROCESSING_INSTRUCTION: { + xtw.writeProcessingInstruction(xmlr.getPITarget(), xmlr.getPIData()); + break; + } + case XMLEvent.CHARACTERS: { + xtw.writeCharacters(xmlr.getText()); + break; + } + case XMLEvent.COMMENT: { + xtw.writeComment(xmlr.getText()); + break; + } + case XMLEvent.START_DOCUMENT: { + xtw.writeStartDocument(xmlr.getEncoding(), xmlr.getVersion()); + break; + } + case XMLEvent.END_DOCUMENT: { + xtw.writeEndDocument(); + break; + } + case XMLEvent.ENTITY_REFERENCE: { + String t = xmlr.getText(); + if (t == null) + { + System.out.println("WARNING: Unable to copy entity reference: " + xmlr.getLocalName()); + } + else + { + xtw.writeEntityRef(t); + } + break; + } + case XMLEvent.DTD: { + xtw.writeDTD("<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">"); + break; + } + case XMLEvent.SPACE: { + xtw.writeCharacters(xmlr.getText()); + break; + } + case XMLEvent.CDATA: { + xtw.writeCData(xmlr.getText()); + break; + } + } + } + xtw.flush(); + xtw.close(); + content = bos.toString(); + } + catch (Exception e) + { + throw new RuntimeException(e); + } + } + + private static void startSection(XMLStreamReader xmlr, XMLStreamWriter xtw) throws XMLStreamException + { + xtw.writeStartElement("", DIV.getLocalPart(), DIV.getNamespaceURI()); + xtw.writeAttribute(CLASS, SECTION); + String id = xmlr.getAttributeValue(null, ID); + if (id != null) + { + xtw.writeAttribute(ID, id); + } + xtw.writeStartElement(xmlr.getPrefix(), xmlr.getLocalName(), xmlr.getNamespaceURI()); + copyElementAttributes(xmlr, xtw, ID); + } + + private void updateLink(XMLStreamReader xmlr, XMLStreamWriter xtw) throws XMLStreamException, MalformedURLException + { + xtw.writeStartElement(xmlr.getPrefix(), xmlr.getLocalName(), xmlr.getNamespaceURI()); + String linkString = xmlr.getAttributeValue(null, HREF); + URL link = linkString.startsWith("http") ? new URL(linkString) : composeURL(actualUrl, linkString); + String newLink = registry.getReference(link); + if (newLink != null) + { + xtw.writeAttribute(HREF, newLink); + copyElementAttributes(xmlr, xtw, HREF); +// System.out.println("Rewritten link to: " + link + "(" + newLink + ")"); + } + else + { + System.out.println("Failed to rewrite link to: " + link); + copyElementAttributes(xmlr, xtw); + } + } + + private static void copyElementAttributes(XMLStreamReader xmlr, XMLStreamWriter xtw, String... localNameExclusions) throws XMLStreamException + { + List<String> ex = Arrays.asList(localNameExclusions); + int attrCount = xmlr.getAttributeCount(); + for (int i = 0; i < attrCount; i++) + { + if (xmlr.getAttributeNamespace(i) == null) + { + String n = xmlr.getAttributeLocalName(i); + if (!ex.contains(n)) + { + xtw.writeAttribute(n, xmlr.getAttributeValue(i)); + } + } + else + { + String n = xmlr.getAttributeLocalName(i); + if (!ex.contains(n)) + { + xtw.writeAttribute(xmlr.getAttributePrefix(i), xmlr.getAttributeNamespace(i), n, + xmlr.getAttributeValue(i)); + } + } + } + } + + private URL appendDecoratorQuery(URL url) throws MalformedURLException + { + URL u = new URL(url.toString() + (url.getQuery() == null ? "?" : "&") + "decorator=print"); +// System.out.println("trying with... " + u); + return u; + } + + public String getContent() + { + return content; + } + + @Override + public Set<URL> getOutgoingLinks() + { + return links; + } + + @Override + public void write() throws IOException + { + File dir = new File(outputDir); + if (!dir.exists()) + { + dir.mkdir(); + } + FileWriter fw = new FileWriter(new File(dir, getFilename())); + fw.write(content); + fw.close(); + } + + private String getFilename() + { + return name + ".xhtml"; + } + +} Added: projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/xhtml2docbook.xsl =================================================================== --- projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/xhtml2docbook.xsl (rev 0) +++ projects/magnolia2docbook/src/org/jboss/util/magnolia2docbook/xhtml2docbook.xsl 2010-10-25 17:29:29 UTC (rev 13187) @@ -0,0 +1,615 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + This is a modified version of the style sheet available at http://wiki.docbook.org/topic/Html2DocBook. + It basically comes with some customizations for getting docbook files similar to what's used for + nowadays for JBoss AS documentation, as well as for coping with minor details due to the conversion + from Magnolia-generated XHTML. +--> +<xsl:stylesheet version="1.0" + xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + xmlns:fo="http://www.w3.org/1999/XSL/Format" + xmlns:html="http://www.w3.org/1999/xhtml" + xmlns:saxon="http://icl.com/saxon" + exclude-result-prefixes="xsl fo html saxon"> + +<xsl:output method="xml" indent="no"/> +<xsl:param name="filename"></xsl:param> +<xsl:param name="prefix">wb</xsl:param> +<xsl:param name="graphics_location">images/</xsl:param> + +<!-- Main block-level conversions --> +<xsl:template match="html:html"> + <xsl:apply-templates select="html:body"/> +</xsl:template> + +<!-- This template converts each HTML file encountered into a DocBook + section. For a title, it selects the first h1 element --> +<xsl:template match="html:body"> + <chapter> + <xsl:if test="$filename != ''"> + <xsl:attribute name="id"> + <xsl:value-of select="$prefix"/> + <xsl:text>_</xsl:text> + <xsl:value-of select="translate($filename,' ()','__')"/> + </xsl:attribute> + </xsl:if> + <title> + <!-- <xsl:value-of select=".//html:h1[1] + |.//html:h2[1] + |.//html:h3[1]"/> --> + <xsl:value-of select="parent::node()/html:head/html:title"/> + </title> + <xsl:apply-templates select="*"/> + </chapter> +</xsl:template> + +<!-- This template matches on all HTML header items and makes them into + bridgeheads. It attempts to assign an ID to each bridgehead by looking + for an id attribute or for a named anchor as a child of the header or + as the immediate preceding or following sibling --> +<xsl:template match="html:h1 + |html:h2 + |html:h3 + |html:h4 + |html:h5 + |html:h6"> + <bridgehead> + <xsl:choose> + <xsl:when test="@id"> + <xsl:attribute name="id"> + <xsl:value-of select="@id"/> + </xsl:attribute> + </xsl:when> + <xsl:when test="count(html:a/@name)"> + <xsl:attribute name="id"> + <xsl:value-of select="html:a/@name"/> + </xsl:attribute> + </xsl:when> + <xsl:when test="preceding-sibling::* = preceding-sibling::html:a[@name != '']"> + <xsl:attribute name="id"> + <xsl:value-of select="concat($prefix,preceding-sibling::html:a[1]/@name)"/> + </xsl:attribute> + </xsl:when> + <xsl:when test="following-sibling::* = following-sibling::html:a[@name != '']"> + <xsl:attribute name="id"> + <xsl:value-of select="concat($prefix,following-sibling::html:a[1]/@name)"/> + </xsl:attribute> + </xsl:when> + </xsl:choose> + <xsl:apply-templates/> + </bridgehead> +</xsl:template> + +<!-- These templates perform one-to-one conversions of HTML elements into + DocBook elements --> +<xsl:template match="html:p"> +<!-- if the paragraph has no text (perhaps only a child <img>), don't + make it a para --> + <xsl:choose> + <xsl:when test="normalize-space(.) = ''"> + <xsl:apply-templates/> + </xsl:when> + <xsl:otherwise> + <para> + <xsl:apply-templates/> + </para> + </xsl:otherwise> + </xsl:choose> +</xsl:template> +<xsl:template match="html:pre"> + <screen xml:space="preserve"><xsl:apply-templates/></screen> +</xsl:template> +<xsl:template match="html:tt"> + <computeroutput><xsl:apply-templates/></computeroutput> +</xsl:template> + +<!-- Hyperlinks --> +<xsl:template match="html:a[contains(@href,'http://')]" priority="1.5"> + <ulink> + <xsl:attribute name="url"> + <xsl:value-of select="normalize-space(@href)"/> + </xsl:attribute> + <xsl:apply-templates/> + </ulink> +</xsl:template> +<xsl:template match="html:a[contains(@href,'https://')]" priority="1.5"> + <ulink> + <xsl:attribute name="url"> + <xsl:value-of select="normalize-space(@href)"/> + </xsl:attribute> + <xsl:apply-templates/> + </ulink> +</xsl:template> +<xsl:template match="html:a[contains(@href,'ftp://')]" priority="1.5"> + <ulink> + <xsl:attribute name="url"> + <xsl:value-of select="normalize-space(@href)"/> + </xsl:attribute> + <xsl:apply-templates/> + </ulink> +</xsl:template> +<xsl:template match="html:a[contains(@href,'mailto:')]" priority="1.5"> + <ulink> + <xsl:attribute name="url"> + <xsl:value-of select="normalize-space(@href)"/> + </xsl:attribute> + <xsl:apply-templates/> + </ulink> +</xsl:template> + +<xsl:template match="html:a[contains(@href,'#')]" priority="0.6"> + <link> + <xsl:attribute name="linkend"> + <xsl:call-template name="make_id"> + <xsl:with-param name="string" select="substring-after(@href,'#')"/> + </xsl:call-template> + </xsl:attribute> + <xsl:apply-templates/> + </link> +</xsl:template> +<xsl:template match="html:a[@name != '']" priority="0.6"> + <anchor> + <xsl:attribute name="id"> + <xsl:call-template name="make_id"> + <xsl:with-param name="string" select="@name"/> + </xsl:call-template> + </xsl:attribute> + <xsl:apply-templates/> + </anchor> +</xsl:template> + +<xsl:template match="html:a[@href != '']"> + <link> + <xsl:attribute name="linkend"> + <xsl:value-of select="$prefix"/> + <xsl:text>_</xsl:text> + <xsl:call-template name="make_id"> + <xsl:with-param name="string" select="@href"/> + </xsl:call-template> + </xsl:attribute> + <xsl:apply-templates/> + </link> +</xsl:template> + +<!-- Need to come up with good template for converting filenames into ID's --> +<xsl:template name="make_id"> + <xsl:param name="string" select="''"/> + <xsl:variable name="fixedname"> + <xsl:call-template name="get_filename"> + <xsl:with-param name="path" select="translate($string,' \()','_/_')"/> + </xsl:call-template> + </xsl:variable> + <xsl:choose> + <xsl:when test="contains($fixedname,'.htm')"> + <xsl:value-of select="substring-before($fixedname,'.htm')"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="$fixedname"/> + </xsl:otherwise> + </xsl:choose> +</xsl:template> + +<xsl:template name="string.subst"> + <xsl:param name="string" select="''"/> + <xsl:param name="substitute" select="''"/> + <xsl:param name="with" select="''"/> + <xsl:choose> + <xsl:when test="contains($string,$substitute)"> + <xsl:variable name="pre" select="substring-before($string,$substitute)"/> + <xsl:variable name="post" select="substring-after($string,$substitute)"/> + <xsl:call-template name="string.subst"> + <xsl:with-param name="string" select="concat($pre,$with,$post)"/> + <xsl:with-param name="substitute" select="$substitute"/> + <xsl:with-param name="with" select="$with"/> + </xsl:call-template> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="$string"/> + </xsl:otherwise> + </xsl:choose> +</xsl:template> + +<!-- Images --> +<!-- Images and image maps --> +<xsl:template match="html:img"> + <xsl:variable name="tag_name"> + <xsl:choose> + <xsl:when test="boolean(parent::html:p) and + boolean(normalize-space(parent::html:p/text()))"> + <xsl:text>inlinemediaobject</xsl:text> + </xsl:when> + <xsl:otherwise>mediaobject</xsl:otherwise> + </xsl:choose> + </xsl:variable> + <xsl:element name="{$tag_name}"> + <imageobject> + <xsl:call-template name="process.image"/> + </imageobject> + </xsl:element> +</xsl:template> + +<xsl:template name="process.image"> + <imagedata> +<xsl:attribute name="fileref"> + <xsl:call-template name="make_absolute"> + <xsl:with-param name="filename" select="@src"/> + </xsl:call-template> +</xsl:attribute> +<xsl:if test="@height != ''"> + <xsl:attribute name="depth"> + <xsl:value-of select="@height"/> + </xsl:attribute> +</xsl:if> +<xsl:if test="@width != ''"> + <xsl:attribute name="width"> + <xsl:value-of select="@width"/> + </xsl:attribute> +</xsl:if> + </imagedata> +</xsl:template> + +<xsl:template name="make_absolute"> + <xsl:param name="filename"/> + <xsl:variable name="name_only"> + <xsl:call-template name="get_filename"> + <xsl:with-param name="path" select="$filename"/> + </xsl:call-template> + </xsl:variable> + <xsl:value-of select="$graphics_location"/><xsl:value-of select="$name_only"/> +</xsl:template> + +<xsl:template match="html:ul[count(*) = 0]"> + <xsl:message>Matched</xsl:message> + <blockquote> + <xsl:apply-templates/> + </blockquote> +</xsl:template> + +<xsl:template name="get_filename"> + <xsl:param name="path"/> + <xsl:choose> + <xsl:when test="contains($path,'/')"> + <xsl:call-template name="get_filename"> + <xsl:with-param name="path" select="substring-after($path,'/')"/> + </xsl:call-template> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="$path"/> + </xsl:otherwise> + </xsl:choose> +</xsl:template> + +<!-- LIST ELEMENTS --> +<xsl:template match="html:ul"> + <itemizedlist> + <xsl:apply-templates/> + </itemizedlist> +</xsl:template> + +<xsl:template match="html:ol"> + <orderedlist> + <xsl:apply-templates/> + </orderedlist> +</xsl:template> + +<!-- This template makes a DocBook variablelist out of an HTML definition list --> +<xsl:template match="html:dl"> + <variablelist> + <xsl:for-each select="html:dt"> + <varlistentry> + <term> + <xsl:apply-templates/> + </term> + <listitem> + <xsl:apply-templates select="following-sibling::html:dd[1]"/> + </listitem> + </varlistentry> + </xsl:for-each> + </variablelist> +</xsl:template> + +<xsl:template match="html:dd"> + <xsl:choose> + <xsl:when test="boolean(html:p)"> + <xsl:apply-templates/> + </xsl:when> + <xsl:otherwise> + <para> + <xsl:apply-templates/> + </para> + </xsl:otherwise> + </xsl:choose> +</xsl:template> + +<xsl:template match="html:li"> + <listitem> + <xsl:choose> + <xsl:when test="count(html:p) = 0"> + <para> + <xsl:apply-templates/> + </para> + </xsl:when> + <xsl:otherwise> + <xsl:apply-templates/> + </xsl:otherwise> + </xsl:choose> + </listitem> +</xsl:template> + +<xsl:template match="*"> + <xsl:message>No template for <xsl:value-of select="name()"/> + </xsl:message> + <xsl:apply-templates/> +</xsl:template> + +<xsl:template match="@*"> + <xsl:message>No template for <xsl:value-of select="name()"/> + </xsl:message> + <xsl:apply-templates/> +</xsl:template> +<!-- unsupported tags --> +<xsl:template match="html:code"> + <xsl:apply-templates/> +</xsl:template> +<xsl:template match="html:font"> + <xsl:apply-templates/> +</xsl:template> +<xsl:template match="html:span"> + <xsl:apply-templates/> +</xsl:template> +<xsl:template match="html:div" priority="0.1"> + <xsl:apply-templates/> +</xsl:template> + +<!-- inline formatting --> +<xsl:template match="html:b"> + <emphasis role="bold"> + <xsl:apply-templates/> + </emphasis> +</xsl:template> +<xsl:template match="html:strong"> + <emphasis role="bold"> + <xsl:apply-templates/> + </emphasis> +</xsl:template> +<xsl:template match="html:i"> + <emphasis> + <xsl:apply-templates/> + </emphasis> +</xsl:template> +<xsl:template match="html:em"> + <emphasis> + <xsl:apply-templates/> + </emphasis> +</xsl:template> +<xsl:template match="html:u"> + <citetitle> + <xsl:apply-templates/> + </citetitle> +</xsl:template> + +<!-- JBossWS customizations --> +<xsl:template match="html:div[@class = 'section']"> + <section> + <xsl:attribute name="id"> + <xsl:value-of select="@id"/> + </xsl:attribute> + <title><xsl:value-of select="child::node()[1]"/></title> + <xsl:apply-templates select="child::node()[position() != 1]"/> + </section> +</xsl:template> +<xsl:template match="html:div[@class = 'note']"> + <note> + <para> + <xsl:apply-templates/> + </para> + </note> +</xsl:template> +<xsl:template match="html:div[@class = 'toc']"/> + +<!-- Ignored elements --> +<xsl:template match="html:hr"/> +<xsl:template match="html:h1[1]|html:h2[1]|html:h3[1]" priority="1"/> +<xsl:template match="html:br"/> +<xsl:template match="html:p[normalize-space(.) = '' and count(*) = 0]"/> +<xsl:template match="text()"> + <xsl:choose> + <xsl:when test="normalize-space(.) = '' and string-length() > 1"></xsl:when> + <xsl:otherwise><xsl:copy/></xsl:otherwise> + </xsl:choose> +</xsl:template> + +<!-- Workbench Hacks --> +<xsl:template match="html:div[contains(@style,'margin-left: 2em')]"> + <blockquote><para> + <xsl:apply-templates/></para> + </blockquote> +</xsl:template> + +<xsl:template match="html:a[@href != '' + and not(boolean(ancestor::html:p|ancestor::html:li))]" + priority="1"> + <para> + <link> + <xsl:attribute name="linkend"> + <xsl:value-of select="$prefix"/> + <xsl:text>_</xsl:text> + <xsl:call-template name="make_id"> + <xsl:with-param name="string" select="@href"/> + </xsl:call-template> + </xsl:attribute> + <xsl:apply-templates/> + </link> + </para> +</xsl:template> + +<xsl:template match="html:a[contains(@href,'#') + and not(boolean(ancestor::html:p|ancestor::html:li))]" + priority="1.1"> + <para> + <link> + <xsl:attribute name="linkend"> + <xsl:value-of select="$prefix"/> + <xsl:text>_</xsl:text> + <xsl:call-template name="make_id"> + <xsl:with-param name="string" select="substring-after(@href,'#')"/> + </xsl:call-template> + </xsl:attribute> + <xsl:apply-templates/> + </link> + </para> +</xsl:template> + +<!-- Table conversion --> +<xsl:template match="html:table"> +<!-- <xsl:variable name="column_count" + select="saxon:max(.//html:tr,saxon:expression('count(html:td)'))"/> --> + <xsl:variable name="column_count"> + <xsl:call-template name="count_columns"> + <xsl:with-param name="table" select="."/> + </xsl:call-template> + </xsl:variable> + <informaltable> + <tgroup> + <xsl:attribute name="cols"> + <xsl:value-of select="$column_count"/> + </xsl:attribute> + <xsl:call-template name="generate-colspecs"> + <xsl:with-param name="count" select="$column_count"/> + </xsl:call-template> + <thead> + <xsl:apply-templates select="html:tr[1]"/> + </thead> + <tbody> + <xsl:apply-templates select="html:tr[position() != 1]"/> + </tbody> + </tgroup> + </informaltable> +</xsl:template> + +<xsl:template name="generate-colspecs"> + <xsl:param name="count" select="0"/> + <xsl:param name="number" select="1"/> + <xsl:choose> + <xsl:when test="$count &lt; $number"/> + <xsl:otherwise> + <colspec> + <xsl:attribute name="colnum"> + <xsl:value-of select="$number"/> + </xsl:attribute> + <xsl:attribute name="colname"> + <xsl:value-of select="concat('col',$number)"/> + </xsl:attribute> + </colspec> + <xsl:call-template name="generate-colspecs"> + <xsl:with-param name="count" select="$count"/> + <xsl:with-param name="number" select="$number + 1"/> + </xsl:call-template> + </xsl:otherwise> + </xsl:choose> +</xsl:template> + +<xsl:template match="html:tr"> + <row> + <xsl:apply-templates/> + </row> +</xsl:template> + +<xsl:template match="html:th|html:td"> + <xsl:variable name="position" select="count(preceding-sibling::*) + 1"/> + <entry> + <xsl:if test="@colspan &gt; 1"> + <xsl:attribute name="namest"> + <xsl:value-of select="concat('col',$position)"/> + </xsl:attribute> + <xsl:attribute name="nameend"> + <xsl:value-of select="concat('col',$position + number(@colspan) - 1)"/> + </xsl:attribute> + </xsl:if> + <xsl:if test="@rowspan &gt; 1"> + <xsl:attribute name="morerows"> + <xsl:value-of select="number(@rowspan) - 1"/> + </xsl:attribute> + </xsl:if> + <xsl:apply-templates/> + </entry> +</xsl:template> + +<xsl:template match="html:td_null"> + <xsl:apply-templates/> +</xsl:template> + +<xsl:template name="count_columns"> + <xsl:param name="table" select="."/> + <xsl:param name="row" select="$table/html:tr[1]"/> + <xsl:param name="max" select="0"/> + <xsl:choose> + <xsl:when test="local-name($table) != 'table'"> + <xsl:message>Attempting to count columns on a non-table element</xsl:message> + </xsl:when> + <xsl:when test="local-name($row) != 'tr'"> + <xsl:message>Row parameter is not a valid row</xsl:message> + </xsl:when> + <xsl:otherwise> + <!-- Count cells in the current row --> + <xsl:variable name="current_count"> + <xsl:call-template name="count_cells"> + <xsl:with-param name="cell" select="$row/html:td[1]|$row/html:th[1]"/> + </xsl:call-template> + </xsl:variable> + <!-- Check for the maximum value of $current_count and $max --> + <xsl:variable name="new_max"> + <xsl:choose> + <xsl:when test="$current_count &gt; $max"> + <xsl:value-of select="number($current_count)"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="number($max)"/> + </xsl:otherwise> + </xsl:choose> + </xsl:variable> + <!-- If this is the last row, return $max, otherwise continue --> + <xsl:choose> + <xsl:when test="count($row/following-sibling::html:tr) = 0"> + <xsl:value-of select="$new_max"/> + </xsl:when> + <xsl:otherwise> + <xsl:call-template name="count_columns"> + <xsl:with-param name="table" select="$table"/> + <xsl:with-param name="row" select="$row/following-sibling::html:tr"/> + <xsl:with-param name="max" select="$new_max"/> + </xsl:call-template> + </xsl:otherwise> + </xsl:choose> + </xsl:otherwise> + </xsl:choose> +</xsl:template> + +<xsl:template name="count_cells"> + <xsl:param name="cell"/> + <xsl:param name="count" select="0"/> + <xsl:variable name="new_count"> + <xsl:choose> + <xsl:when test="$cell/@colspan &gt; 1"> + <xsl:value-of select="number($cell/@colspan) + number($count)"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="number('1') + number($count)"/> + </xsl:otherwise> + </xsl:choose> + </xsl:variable> + <xsl:choose> + <xsl:when test="count($cell/following-sibling::*) &gt; 0"> + <xsl:call-template name="count_cells"> + <xsl:with-param name="cell" + select="$cell/following-sibling::*[1]"/> + <xsl:with-param name="count" select="$new_count"/> + </xsl:call-template> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="$new_count"/> + </xsl:otherwise> + </xsl:choose> +</xsl:template> + +</xsl:stylesheet>