You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lenya.apache.org by so...@apache.org on 2008/01/31 08:44:36 UTC

svn commit: r617035 [19/22] - in /lenya/branches/revolution/1.3.x: ./ src/java/org/apache/lenya/ac/ src/java/org/apache/lenya/ac/cache/ src/java/org/apache/lenya/ac/cifs/ src/java/org/apache/lenya/ac/file/ src/java/org/apache/lenya/ac/impl/ src/java/or...

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/search/crawler/IterativeHTMLCrawler.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/search/crawler/IterativeHTMLCrawler.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/search/crawler/IterativeHTMLCrawler.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/search/crawler/IterativeHTMLCrawler.java Wed Jan 30 23:44:03 2008
@@ -14,550 +14,458 @@
  *  limitations under the License.
  *
  */
-
 /* $Id$  */
-
 package org.apache.lenya.search.crawler;
-
 import java.io.File;
 import java.io.FileOutputStream;
 import java.net.HttpURLConnection;
 import java.net.MalformedURLException;
 import java.net.URL;
 import java.util.StringTokenizer;
-
+import org.apache.log4j.Logger;
 import websphinx.RobotExclusion;
-
-import org.apache.log4j.Category;
-
-
 /**
  * Crawl iteratively
  */
 public class IterativeHTMLCrawler {
-    static Category log = Category.getInstance(IterativeHTMLCrawler.class);
-
-    java.util.Vector urlsToCrawl;
-    java.util.TreeSet urlsToCrawlLowerCase;
-    String url_list_file = "url_file.txt";
-    String html_dump_directory = "html_dump";
-    private String rootURL;
-    private String[] scopeURL;
-    private RobotExclusion robot;
-
-    /**
-     * Command line interface
-     *
-     * @param args Configuration file crawler.xconf
-     */
-    public static void main(String[] args) {
-        if (args.length == 0) {
+   private static Logger log = Logger.getLogger(IterativeHTMLCrawler.class);
+   java.util.Vector urlsToCrawl;
+   java.util.TreeSet urlsToCrawlLowerCase;
+   String url_list_file = "url_file.txt";
+   String html_dump_directory = "html_dump";
+   private String rootURL;
+   private String[] scopeURL;
+   private RobotExclusion robot;
+   /**
+    * Command line interface
+    * 
+    * @param args
+    *           Configuration file crawler.xconf
+    */
+   public static void main(String[] args) {
+      if(args.length == 0){
+         System.err.println("Usage: IterativeHTMLCrawler crawler.xconf");
+         return;
+      }
+      try{
+         if(args.length == 1){
+            CrawlerConfiguration ce = new CrawlerConfiguration(args[0]);
+            new IterativeHTMLCrawler(new File(args[0])).crawl(new URL(ce.getBaseURL()), ce.getScopeURL());
+         }else{
             System.err.println("Usage: IterativeHTMLCrawler crawler.xconf");
-
-            return;
-        }
-
-        try {
-            if (args.length == 1) {
-                CrawlerConfiguration ce = new CrawlerConfiguration(args[0]);
-                new IterativeHTMLCrawler(new File(args[0])).crawl(new URL(ce.getBaseURL()), ce.getScopeURL());
-	    } else {
-                System.err.println("Usage: IterativeHTMLCrawler crawler.xconf");
-            }
-        } catch (MalformedURLException e) {
-            log.error("" + e);
-        }
-    }
-
-    /**
-     * Creates a new IterativeHTMLCrawler object.
-     *
-     * @param url_list_file File where all dumped files will be listed
-     * @param html_dump_directory Directory where htdocs should be dumped
-     * @param userAgent User-agent for robots.txt
-     */
-    public IterativeHTMLCrawler(String url_list_file, String html_dump_directory, String userAgent) {
-        this.url_list_file = url_list_file;
-        this.html_dump_directory = html_dump_directory;
-
-        robot = new RobotExclusion(userAgent);
-    }
-
-    /**
-     * Creates a new IterativeHTMLCrawler object.
-     * @param config Configuration File
-     */
-    public IterativeHTMLCrawler(File config) {
-        CrawlerConfiguration ce = new CrawlerConfiguration(config.getAbsolutePath());
-
-
-        this.url_list_file = ce.getURIListResolved();
-        log.debug("URI list file: " + this.url_list_file);
-
-        this.html_dump_directory = ce.getHTDocsDumpDirResolved();
-        log.debug("HTDocs Dump Dir: " + this.html_dump_directory);
-
-        robot = new RobotExclusion(ce.getUserAgent());
-
-        String robots_file = ce.getRobotsFileResolved();
-        log.debug("Robots File: " + robots_file);
-        String robots_domain = ce.getRobotsDomain();
-        if (robots_file != null && robots_domain != null) {
-            log.debug(robots_file + " " + robots_domain);
-            robot.addLocalEntries(robots_domain, new File(robots_file));
-        }
-    }
-
-    /**
-     * Crawl
-     *
-     * @param start Start crawling at this URL
-     * @param scope Limit crawling to this scope
-     */
-    public void crawl(URL start, String scope) {
-        scopeURL = new String[1];
-        scopeURL[0] = scope;
-
-        String seedURL = start.toString();
-        this.rootURL = seedURL.substring(0, seedURL.indexOf("/", 8));
-
-        urlsToCrawl = new java.util.Vector();
-        urlsToCrawlLowerCase = new java.util.TreeSet();
-
-        String currentURLPath = start.toString().substring(0, start.toString().lastIndexOf("/"));
-
-        try {
-            log.info("Start crawling at: " + start);
-
-            if (addURL(start.getFile(), currentURLPath) != null) {
-                dumpHTDoc(start);
-            } else {
-                log.warn("Start URL has not been dumped: " + start);
-            }
-        } catch (MalformedURLException e) {
-            log.error("" + e);
-        }
-
-        int currentPosition = 0;
-
-        while (currentPosition < urlsToCrawl.size()) {
-            URL currentURL = (URL) urlsToCrawl.elementAt(currentPosition);
-            currentURLPath = currentURL.toString().substring(0, currentURL.toString().lastIndexOf("/"));
-
-            log.info("INFO: Current Array Size: " + urlsToCrawl.size() + ", Current Position: " + currentPosition + ", Current URL: " + currentURL.toString());
-
-
-            java.util.List urlsWithinPage = parsePage(currentURL.toString());
-
-            if (urlsWithinPage != null) {
-                java.util.Iterator iterator = urlsWithinPage.iterator();
-
-                while (iterator.hasNext()) {
-                    String urlCandidate = (String) iterator.next();
-
-                    try {
-                        URL urlToCrawl = null;
-
-                        if ((urlToCrawl = addURL(urlCandidate, currentURLPath)) != null) {
-                            dumpHTDoc(urlToCrawl);
-                        }
-                    } catch (MalformedURLException e) {
-                        log.warn("" + e + " " + urlCandidate);
-                    }
-                }
-            }
-
-            currentPosition = currentPosition + 1;
-        }
-
-        log.info("Stop crawling at: " + urlsToCrawl.elementAt(urlsToCrawl.size()-1));
-
-
-
-        // Write all crawled URLs into file
-        try {
-            File parent = new File(new File(url_list_file).getParent());
-            if (!parent.isDirectory()) {
-                parent.mkdirs();
-                log.warn("Directory has been created: " + parent);
-            }
-            java.io.PrintWriter out = new java.io.PrintWriter(new FileOutputStream(url_list_file));
-
-            for (int i = 0; i < urlsToCrawl.size(); i++) {
-                out.println("" + urlsToCrawl.elementAt(i));
-            }
-
-            out.close();
-        } catch (java.io.FileNotFoundException e) {
-            log.error("" + e);
-        }
-    }
-
-    /**
-     * Add URLs to crawl
-     *
-     * @param urlCandidate DOCUMENT ME!
-     * @param currentURLPath DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     *
-     * @throws MalformedURLException DOCUMENT ME!
-     */
-    public URL addURL(String urlCandidate, String currentURLPath)
-        throws MalformedURLException {
-        URL url = new URL(parseHREF(urlCandidate, urlCandidate.toLowerCase(), currentURLPath));
-        //completeURL(currentURL,urlCandidate)  new URL(currentURLPath+"/"+urlCandidate);
-
-        if (filterURL(urlCandidate, currentURLPath, urlsToCrawlLowerCase)) {
-            if (!robot.disallowed(url)) {
-                if (url.getQuery() == null) {
-                    urlsToCrawl.add(url);
-                    urlsToCrawlLowerCase.add(url.toString().toLowerCase());
-                    log.debug("URL added: " + url);
-                } else {
-                    log.info("Don't crawl URLs with query string: " + url);
-                }
-
-                return url;
-            } else {
-                log.info("Disallowed by robots.txt: " + urlCandidate);
-            }
-        }
-
-        return null;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param urlString DOCUMENT ME!
-     *
-     * @return ok, 404
-     */
-    public java.util.List parsePage(String urlString) {
-        String status = "ok";
-
-        try {
-            URL currentURL = new java.net.URL(urlString);
-            String currentURLPath = urlString.substring(0, urlString.lastIndexOf("/"));
-            HttpURLConnection httpCon = (HttpURLConnection) currentURL.openConnection();
-
-            httpCon.setRequestProperty("User-Agent", "Lenya Lucene Crawler");
-
-            httpCon.connect();
-
-            long lastModified = httpCon.getLastModified();
-
-            if (httpCon.getResponseCode() == HttpURLConnection.HTTP_OK) {
-                String contentType = httpCon.getContentType();
-
-                if (contentType.indexOf("text/html") != -1) {
-                    return handleHTML(httpCon);
-                } else if (contentType.indexOf("application/pdf") != -1) {
-                    handlePDF(httpCon);
-                } else {
-                    status = "Not an excepted content type : " + contentType;
-                }
-            } else {
-                status = "bad";
-            }
-
-            httpCon.disconnect();
-        } catch (java.net.MalformedURLException mue) {
-            status = mue.toString();
-        } catch (java.net.UnknownHostException uh) {
-            status = uh.toString(); // Mark as a bad URL
-        } catch (java.io.IOException ioe) {
-            status = ioe.toString(); // Mark as a bad URL
-        } catch (Exception e) {
-            status = e.toString(); // Mark as a bad URL
-        }
-
-        //return status;
-        return null;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param httpCon DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     *
-     * @throws java.io.IOException DOCUMENT ME!
-     */
-    public static java.util.List handleHTML(HttpURLConnection httpCon)
-        throws java.io.IOException {
-        ContentHandler handler = new HTMLHandler();
-        handler.parse(httpCon.getInputStream());
-
-        if (handler.getRobotFollow()) {
-            java.util.List links = handler.getLinks();
-
-            return links;
-        }
-
-        return null;
-    }
-
-    /**
-     * Parse PDF for links
-     *
-     * @param httpCon DOCUMENT ME!
-     */
-    public void handlePDF(HttpURLConnection httpCon) {
-        log.debug(".handlePDF(): Not handled yet!");
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param url DOCUMENT ME!
-     * @param currentURLPath DOCUMENT ME!
-     * @param links DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public boolean filterURL(String url, String currentURLPath, java.util.TreeSet links) {
-        String urlLowCase = url.toLowerCase();
-
-        if (!(urlLowCase.startsWith("http://") || urlLowCase.startsWith("https://"))) {
-            url = parseHREF(url, urlLowCase, currentURLPath);
-
-            if (url != null) {
-                urlLowCase = url.toLowerCase();
-            }
-        }
-
-        if ((url != null) && inScope(url)) {
-            if (!links.contains(urlLowCase)) {
-                return true;
+         }
+      }catch(MalformedURLException e){
+         log.error("" + e);
+      }
+   }
+   /**
+    * Creates a new IterativeHTMLCrawler object.
+    * 
+    * @param url_list_file
+    *           File where all dumped files will be listed
+    * @param html_dump_directory
+    *           Directory where htdocs should be dumped
+    * @param userAgent
+    *           User-agent for robots.txt
+    */
+   public IterativeHTMLCrawler(String url_list_file, String html_dump_directory, String userAgent) {
+      this.url_list_file = url_list_file;
+      this.html_dump_directory = html_dump_directory;
+      robot = new RobotExclusion(userAgent);
+   }
+   /**
+    * Creates a new IterativeHTMLCrawler object.
+    * 
+    * @param config
+    *           Configuration File
+    */
+   public IterativeHTMLCrawler(File config) {
+      CrawlerConfiguration ce = new CrawlerConfiguration(config.getAbsolutePath());
+      this.url_list_file = ce.getURIListResolved();
+      log.debug("URI list file: " + this.url_list_file);
+      this.html_dump_directory = ce.getHTDocsDumpDirResolved();
+      log.debug("HTDocs Dump Dir: " + this.html_dump_directory);
+      robot = new RobotExclusion(ce.getUserAgent());
+      String robots_file = ce.getRobotsFileResolved();
+      log.debug("Robots File: " + robots_file);
+      String robots_domain = ce.getRobotsDomain();
+      if(robots_file != null && robots_domain != null){
+         log.debug(robots_file + " " + robots_domain);
+         robot.addLocalEntries(robots_domain, new File(robots_file));
+      }
+   }
+   /**
+    * Crawl
+    * 
+    * @param start
+    *           Start crawling at this URL
+    * @param scope
+    *           Limit crawling to this scope
+    */
+   public void crawl(URL start, String scope) {
+      scopeURL = new String[1];
+      scopeURL[0] = scope;
+      String seedURL = start.toString();
+      this.rootURL = seedURL.substring(0, seedURL.indexOf("/", 8));
+      urlsToCrawl = new java.util.Vector();
+      urlsToCrawlLowerCase = new java.util.TreeSet();
+      String currentURLPath = start.toString().substring(0, start.toString().lastIndexOf("/"));
+      try{
+         log.info("Start crawling at: " + start);
+         if(addURL(start.getFile(), currentURLPath) != null){
+            dumpHTDoc(start);
+         }else{
+            log.warn("Start URL has not been dumped: " + start);
+         }
+      }catch(MalformedURLException e){
+         log.error("" + e);
+      }
+      int currentPosition = 0;
+      while(currentPosition < urlsToCrawl.size()){
+         URL currentURL = (URL) urlsToCrawl.elementAt(currentPosition);
+         currentURLPath = currentURL.toString().substring(0, currentURL.toString().lastIndexOf("/"));
+         log.info("INFO: Current Array Size: " + urlsToCrawl.size() + ", Current Position: " + currentPosition + ", Current URL: " + currentURL.toString());
+         java.util.List urlsWithinPage = parsePage(currentURL.toString());
+         if(urlsWithinPage != null){
+            java.util.Iterator iterator = urlsWithinPage.iterator();
+            while(iterator.hasNext()){
+               String urlCandidate = (String) iterator.next();
+               try{
+                  URL urlToCrawl = null;
+                  if((urlToCrawl = addURL(urlCandidate, currentURLPath)) != null){
+                     dumpHTDoc(urlToCrawl);
+                  }
+               }catch(MalformedURLException e){
+                  log.warn("" + e + " " + urlCandidate);
+               }
+            }
+         }
+         currentPosition = currentPosition + 1;
+      }
+      log.info("Stop crawling at: " + urlsToCrawl.elementAt(urlsToCrawl.size() - 1));
+      // Write all crawled URLs into file
+      try{
+         File parent = new File(new File(url_list_file).getParent());
+         if(!parent.isDirectory()){
+            parent.mkdirs();
+            log.warn("Directory has been created: " + parent);
+         }
+         java.io.PrintWriter out = new java.io.PrintWriter(new FileOutputStream(url_list_file));
+         for(int i = 0; i < urlsToCrawl.size(); i++){
+            out.println("" + urlsToCrawl.elementAt(i));
+         }
+         out.close();
+      }catch(java.io.FileNotFoundException e){
+         log.error("" + e);
+      }
+   }
+   /**
+    * Add URLs to crawl
+    * 
+    * @param urlCandidate
+    *           DOCUMENT ME!
+    * @param currentURLPath
+    *           DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    * 
+    * @throws MalformedURLException
+    *            DOCUMENT ME!
+    */
+   public URL addURL(String urlCandidate, String currentURLPath) throws MalformedURLException {
+      URL url = new URL(parseHREF(urlCandidate, urlCandidate.toLowerCase(), currentURLPath));
+      // completeURL(currentURL,urlCandidate) new URL(currentURLPath+"/"+urlCandidate);
+      if(filterURL(urlCandidate, currentURLPath, urlsToCrawlLowerCase)){
+         if(!robot.disallowed(url)){
+            if(url.getQuery() == null){
+               urlsToCrawl.add(url);
+               urlsToCrawlLowerCase.add(url.toString().toLowerCase());
+               log.debug("URL added: " + url);
+            }else{
+               log.info("Don't crawl URLs with query string: " + url);
             }
-        } else {
-            log.debug("Not in scope: " + url);
-        }
-
-        return false;
-    }
-
-    /**
-     * Parse URL and complete if necessary
-     *
-     * @param url URL from href
-     * @param urlLowCase url is lower case
-     * @param currentURLPath URL of current page
-     *
-     * @return Completed URL
-     */
-    public String parseHREF(String url, String urlLowCase, String currentURLPath) {
-        if (urlLowCase.startsWith("http://") || urlLowCase.startsWith("https://")) {
             return url;
-        }
-
-        // Looks for incomplete URL and completes them
-        if (urlLowCase.startsWith("/")) {
-            url = rootURL + url;
-        } else if (urlLowCase.startsWith("./")) {
-            url = currentURLPath + url.substring(1, url.length());
-        } else if (urlLowCase.startsWith("../")) {
-            int back = 1;
-
-            // Count number of "../"s
-            while (urlLowCase.indexOf("../", back * 3) != -1)
-                back++;
-
-            int pos = currentURLPath.length();
-            int count = back;
-
-            while (count-- > 0) {
-                pos = currentURLPath.lastIndexOf("/", pos) - 1;
-            }
-
-            String dotsRemoved = url.substring(3 * back, url.length());
-            if (dotsRemoved.length() > 0 && dotsRemoved.charAt(0) == '.') {
-                log.error("Parsing failed: " + url + " (" + currentURLPath + ")");
-                url = null;
-            } else {
-                url = currentURLPath.substring(0, pos + 2) + dotsRemoved;
-            }
-        } else if (urlLowCase.startsWith("javascript:")) {
-            // handle javascript:...
-            log.debug("\"javascript:\" is not implemented yet!");
-            url = null;
-        } else if (urlLowCase.startsWith("#")) {
-            log.debug("\"#\" (anchor) will be ignored!");
-
-            // internal anchor... ignore.
-            url = null;
-        } else if (urlLowCase.startsWith("mailto:")) {
-            log.debug("\"mailto:\" is not a URL to be followed!");
-
-            // handle mailto:...
+         }else{
+            log.info("Disallowed by robots.txt: " + urlCandidate);
+         }
+      }
+      return null;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param urlString
+    *           DOCUMENT ME!
+    * 
+    * @return ok, 404
+    */
+   public java.util.List parsePage(String urlString) {
+      // String status = "ok";
+      String status = "";
+      try{
+         URL currentURL = new java.net.URL(urlString);
+         // String currentURLPath = urlString.substring(0, urlString.lastIndexOf("/"));
+         HttpURLConnection httpCon = (HttpURLConnection) currentURL.openConnection();
+         httpCon.setRequestProperty("User-Agent", "Lenya Lucene Crawler");
+         httpCon.connect();
+         // long lastModified = httpCon.getLastModified();
+         if(httpCon.getResponseCode() == HttpURLConnection.HTTP_OK){
+            String contentType = httpCon.getContentType();
+            if(contentType.indexOf("text/html") != -1){
+               return handleHTML(httpCon);
+            }else if(contentType.indexOf("application/pdf") != -1){
+               handlePDF(httpCon);
+            }else{
+               status = "Not an excepted content type : " + contentType;
+            }
+         }else{
+            status = "bad";
+         }
+         httpCon.disconnect();
+      }catch(java.net.MalformedURLException mue){
+         status = mue.toString();
+      }catch(java.net.UnknownHostException uh){
+         status = uh.toString(); // Mark as a bad URL
+      }catch(java.io.IOException ioe){
+         status = ioe.toString(); // Mark as a bad URL
+      }catch(Exception e){
+         status = e.toString(); // Mark as a bad URL
+      }
+      if(status.length() > 0){
+         System.out.println("IterativeHTMLCrawler parsePage() status=" + status);
+      }
+      // return status;
+      return null;
+   }
+   public static java.util.List handleHTML(HttpURLConnection httpCon) throws java.io.IOException {
+      ContentHandler handler = new HTMLHandler();
+      handler.parse(httpCon.getInputStream());
+      if(handler.getRobotFollow()){
+         return handler.getLinks();
+      }
+      return null;
+   }
+   /**
+    * Parse PDF for links
+    */
+   public void handlePDF(HttpURLConnection httpCon) {
+      log.debug(".handlePDF(): Not handled yet!");
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param url
+    *           DOCUMENT ME!
+    * @param currentURLPath
+    *           DOCUMENT ME!
+    * @param links
+    *           DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public boolean filterURL(String url, String currentURLPath, java.util.TreeSet links) {
+      String urlLowCase = url.toLowerCase();
+      if(!(urlLowCase.startsWith("http://") || urlLowCase.startsWith("https://"))){
+         url = parseHREF(url, urlLowCase, currentURLPath);
+         if(url != null){
+            urlLowCase = url.toLowerCase();
+         }
+      }
+      if((url != null) && inScope(url)){
+         if(!links.contains(urlLowCase)){
+            return true;
+         }
+      }else{
+         log.debug("Not in scope: " + url);
+      }
+      return false;
+   }
+   /**
+    * Parse URL and complete if necessary
+    * 
+    * @param url
+    *           URL from href
+    * @param urlLowCase
+    *           url is lower case
+    * @param currentURLPath
+    *           URL of current page
+    * 
+    * @return Completed URL
+    */
+   public String parseHREF(String url, String urlLowCase, String currentURLPath) {
+      if(urlLowCase.startsWith("http://") || urlLowCase.startsWith("https://")){
+         return url;
+      }
+      // Looks for incomplete URL and completes them
+      if(urlLowCase.startsWith("/")){
+         url = rootURL + url;
+      }else if(urlLowCase.startsWith("./")){
+         url = currentURLPath + url.substring(1, url.length());
+      }else if(urlLowCase.startsWith("../")){
+         int back = 1;
+         // Count number of "../"s
+         while(urlLowCase.indexOf("../", back * 3) != -1)
+            back++;
+         int pos = currentURLPath.length();
+         int count = back;
+         while(count-- > 0){
+            pos = currentURLPath.lastIndexOf("/", pos) - 1;
+         }
+         String dotsRemoved = url.substring(3 * back, url.length());
+         if(dotsRemoved.length() > 0 && dotsRemoved.charAt(0) == '.'){
+            log.error("Parsing failed: " + url + " (" + currentURLPath + ")");
             url = null;
-        } else {
-            url = currentURLPath + "/" + url;
-        }
-
-        // strip anchor if exists otherwise crawler may index content multiple times
-        // links to the same url but with unique anchors would be considered unique
-        // by the crawler when they should not be
-        if (url != null) {
-            int i;
-
-            if ((i = url.indexOf("#")) != -1) {
-                url = url.substring(0, i);
+         }else{
+            url = currentURLPath.substring(0, pos + 2) + dotsRemoved;
+         }
+      }else if(urlLowCase.startsWith("javascript:")){
+         // handle javascript:...
+         log.debug("\"javascript:\" is not implemented yet!");
+         url = null;
+      }else if(urlLowCase.startsWith("#")){
+         log.debug("\"#\" (anchor) will be ignored!");
+         // internal anchor... ignore.
+         url = null;
+      }else if(urlLowCase.startsWith("mailto:")){
+         log.debug("\"mailto:\" is not a URL to be followed!");
+         // handle mailto:...
+         url = null;
+      }else{
+         url = currentURLPath + "/" + url;
+      }
+      // strip anchor if exists otherwise crawler may index content multiple times
+      // links to the same url but with unique anchors would be considered unique
+      // by the crawler when they should not be
+      if(url != null){
+         int i;
+         if((i = url.indexOf("#")) != -1){
+            url = url.substring(0, i);
+         }
+      }
+      return url;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param url
+    *           DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public boolean inScope(String url) {
+      for(int i = 0; i < scopeURL.length; i++){
+         if(url.startsWith(scopeURL[i])){
+            return true;
+         }
+      }
+      return false;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param parent
+    *           DOCUMENT ME!
+    * @param child
+    *           DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    * 
+    * @throws MalformedURLException
+    *            DOCUMENT ME!
+    */
+   public URL completeURL(URL parent, String child) throws MalformedURLException {
+      return parent;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param url
+    *           DOCUMENT ME!
+    */
+   public void dumpHTDoc(URL url) {
+      String ext = getExtension(url);
+      String filename = html_dump_directory + url.getFile();
+      File file = new File(filename);
+      if(filename.charAt(filename.length() - 1) == '/'){
+         file = new File(filename + "index.html");
+         ext = getExtension(file);
+      }
+      if(ext.equals("html") || ext.equals("htm") || ext.equals("txt") || ext.equals("pdf")){
+         try{
+            File parent = new File(file.getParent());
+            if(!parent.exists()){
+               parent.mkdirs();
+            }
+            HttpURLConnection httpConnection = (HttpURLConnection) url.openConnection();
+            java.io.InputStream in = httpConnection.getInputStream();
+            FileOutputStream out = new FileOutputStream(file);
+            byte[] buffer = new byte[1024];
+            int bytesRead = -1;
+            while((bytesRead = in.read(buffer)) >= 0){
+               out.write(buffer, 0, bytesRead);
             }
-        }
-
-
-        return url;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param url DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public boolean inScope(String url) {
-        for (int i = 0; i < scopeURL.length; i++) {
-            if (url.startsWith(scopeURL[i])) {
-                return true;
-            }
-        }
-
-        return false;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param parent DOCUMENT ME!
-     * @param child DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     *
-     * @throws MalformedURLException DOCUMENT ME!
-     */
-    public URL completeURL(URL parent, String child) throws MalformedURLException {
-        return parent;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param url DOCUMENT ME!
-     */
-    public void dumpHTDoc(URL url) {
-        String ext = getExtension(url);
-
-        String filename = html_dump_directory + url.getFile();
-        File file = new File(filename);
-
-        if (filename.charAt(filename.length() - 1) == '/') {
-            file = new File(filename + "index.html");
-            ext = getExtension(file);
-        }
-
-        if (ext.equals("html") || ext.equals("htm") || ext.equals("txt") || ext.equals("pdf")) {
-            try {
-                File parent = new File(file.getParent());
-
-                if (!parent.exists()) {
-                    parent.mkdirs();
-                }
-
-                HttpURLConnection httpConnection = (HttpURLConnection) url.openConnection();
-                java.io.InputStream in = httpConnection.getInputStream();
-
-		FileOutputStream out = new FileOutputStream(file);
-                byte[] buffer = new byte[1024];
-                int bytesRead = -1;
-                while ((bytesRead = in.read(buffer)) >= 0) {
-                    out.write(buffer, 0, bytesRead);
-                }
-                out.close();
-
-/*
-                BufferedInputStream bin = new BufferedInputStream(in);
-                BufferedReader reader = new BufferedReader(new InputStreamReader(bin));
-
-                java.io.FileWriter fw = new java.io.FileWriter(file);
-                int i;
-
-                while ((i = reader.read()) != -1) {
-                    fw.write(i);
-                }
-
-                fw.close();
-
-                bin.close();
-*/
-                in.close();
-                httpConnection.disconnect();
-
-                log.info("URL dumped: " + url + " (" + file + ")");
-            } catch (Exception e) {
-                log.error("" + e);
-                log.error("URL not dumped: " + url);
-            }
-        } else {
-            log.info("URL not dumped: " + url);
-        }
-    }
-
-    /**
-     *
-     */
-/*
-    public void saveToFile(String filename, byte[] bytes)
-        throws FileNotFoundException, IOException {
-        File file = new File(filename);
-
-        if (filename.charAt(filename.length() - 1) == '/') {
-            file = new File(filename + "index.html");
-        }
-
-        File parent = new File(file.getParent());
-
-        if (!parent.exists()) {
-            log.warn("Directory will be created: " + parent.getAbsolutePath());
-            parent.mkdirs();
-        }
-
-        FileOutputStream out = new FileOutputStream(file.getAbsolutePath());
-        out.write(bytes);
-        out.close();
-    }
-*/
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param url DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public String getExtension(URL url) {
-        return getExtension(new File(url.getPath()));
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param file DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public String getExtension(File file) {
-        StringTokenizer st = new StringTokenizer(file.getPath(), ".");
-        String extension = null;
-
-        while (st.hasMoreElements()) {
-            extension = st.nextToken();
-        }
-
-        return extension;
-    }
+            out.close();
+            /*
+             * BufferedInputStream bin = new BufferedInputStream(in); BufferedReader reader = new BufferedReader(new InputStreamReader(bin));
+             * 
+             * java.io.FileWriter fw = new java.io.FileWriter(file); int i;
+             * 
+             * while ((i = reader.read()) != -1) { fw.write(i); }
+             * 
+             * fw.close();
+             * 
+             * bin.close();
+             */
+            in.close();
+            httpConnection.disconnect();
+            log.info("URL dumped: " + url + " (" + file + ")");
+         }catch(Exception e){
+            log.error("" + e);
+            log.error("URL not dumped: " + url);
+         }
+      }else{
+         log.info("URL not dumped: " + url);
+      }
+   }
+   /**
+    * 
+    */
+   /*
+    * public void saveToFile(String filename, byte[] bytes) throws FileNotFoundException, IOException { File file = new File(filename);
+    * 
+    * if (filename.charAt(filename.length() - 1) == '/') { file = new File(filename + "index.html"); }
+    * 
+    * File parent = new File(file.getParent());
+    * 
+    * if (!parent.exists()) { log.warn("Directory will be created: " + parent.getAbsolutePath()); parent.mkdirs(); }
+    * 
+    * FileOutputStream out = new FileOutputStream(file.getAbsolutePath()); out.write(bytes); out.close(); }
+    */
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param url
+    *           DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public String getExtension(URL url) {
+      return getExtension(new File(url.getPath()));
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param file
+    *           DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public String getExtension(File file) {
+      StringTokenizer st = new StringTokenizer(file.getPath(), ".");
+      String extension = null;
+      while(st.hasMoreElements()){
+         extension = st.nextToken();
+      }
+      return extension;
+   }
 }

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/CacheMap.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/CacheMap.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/CacheMap.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/CacheMap.java Wed Jan 30 23:44:03 2008
@@ -14,69 +14,57 @@
  *  limitations under the License.
  *
  */
-
 /* $Id$  */
-
 package org.apache.lenya.util;
-
 import java.util.Date;
 import java.util.HashMap;
 import java.util.SortedMap;
 import java.util.TreeMap;
-
-import org.apache.log4j.Category;
-
+import org.apache.log4j.Logger;
 /**
  * A map with a maximum capacity. When the map is full, the oldest entry is removed.
  */
 public class CacheMap extends HashMap {
-    
-    private static final Category log = Category.getInstance(CacheMap.class);
-    
-    /**
-     * Ctor.
-     * @param capacity The maximum number of entries.
-     */
-    public CacheMap(int capacity) {
-//        assert capacity > -1;
-        this.capacity = capacity;
-    }
-    
-    private int capacity;
-    private SortedMap timeToKey = new TreeMap();
-    
-    /**
-     * @see java.util.Map#put(Object, Object)
-     */
-    public Object put(Object key, Object value) {
-        
-        if (size() == capacity) {
-            Object oldestKey = timeToKey.get(timeToKey.firstKey());
-            remove(oldestKey);
-            if (log.isDebugEnabled()) {
-                log.debug("Clearing cache");
-            }
-        }
-        timeToKey.put(new Date(), key);
-        return super.put(key, value);
-    }
-    
-    
-    
-    /**
-     * @see java.util.Map#get(java.lang.Object)
-     */
-    public Object get(Object key) {
-        Object result = super.get(key);
-        if (log.isDebugEnabled()) {
-            if (result != null) {
-                log.debug("Using cached object for key [" + key + "]");
-            }
-            else {
-                log.debug("No cached object for key [" + key + "]");
-            }
-        }
-        return result;
-    }
-
+   private static final long serialVersionUID = 1L;
+   private static Logger log = Logger.getLogger(CacheMap.class);
+   /**
+    * Ctor.
+    * 
+    * @param capacity
+    *           The maximum number of entries.
+    */
+   public CacheMap(int capacity) {
+      // assert capacity > -1;
+      this.capacity = capacity;
+   }
+   private int capacity;
+   private SortedMap timeToKey = new TreeMap();
+   /**
+    * @see java.util.Map#put(Object, Object)
+    */
+   public Object put(Object key, Object value) {
+      if(size() == capacity){
+         Object oldestKey = timeToKey.get(timeToKey.firstKey());
+         remove(oldestKey);
+         if(log.isDebugEnabled()){
+            log.debug("Clearing cache");
+         }
+      }
+      timeToKey.put(new Date(), key);
+      return super.put(key, value);
+   }
+   /**
+    * @see java.util.Map#get(java.lang.Object)
+    */
+   public Object get(Object key) {
+      Object result = super.get(key);
+      if(log.isDebugEnabled()){
+         if(result != null){
+            log.debug("Using cached object for key [" + key + "]");
+         }else{
+            log.debug("No cached object for key [" + key + "]");
+         }
+      }
+      return result;
+   }
 }

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/FileUtil.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/FileUtil.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/FileUtil.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/FileUtil.java Wed Jan 30 23:44:03 2008
@@ -14,9 +14,7 @@
  *  limitations under the License.
  *
  */
-
 package org.apache.lenya.util;
-
 import java.io.File;
 import java.io.FileInputStream;
 import java.io.FileNotFoundException;
@@ -25,223 +23,200 @@
 import java.io.InputStream;
 import java.io.OutputStream;
 import java.util.StringTokenizer;
-
-import org.apache.log4j.Category;
-
+import org.apache.log4j.Logger;
 /**
  * @version $Id$
  */
 public final class FileUtil {
-    private static Category log = Category.getInstance(FileUtil.class);
-
-    /**
-     * DOCUMENT ME!
-     * 
-     * @param args DOCUMENT ME!
-     */
-    public static void main(String[] args) {
-        if (args.length == 0) {
-            System.err.println("Usage: java " + new FileUtil().getClass().getName());
-
+   private static Logger log = Logger.getLogger(FileUtil.class);
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param args
+    *           DOCUMENT ME!
+    */
+   public static void main(String[] args) {
+      if(args.length == 0){
+         System.err.println("Usage: java " + new FileUtil().getClass().getName());
+         return;
+      }
+      if(args[0].equals("--copy")){
+         if(args.length != 3){
+            System.err.println("Usage: --copy source destination");
             return;
-        }
-
-        if (args[0].equals("--copy")) {
-            if (args.length != 3) {
-                System.err.println("Usage: --copy source destination");
-
-                return;
-            }
-
-            try {
-                System.err.println("cp " + args[1] + " " + args[2]);
-                copy(args[1], args[2]);
-            } catch (FileNotFoundException e) {
-                System.err.println(e);
-            } catch (IOException e) {
-                System.err.println(e);
-            }
-
+         }
+         try{
+            System.err.println("cp " + args[1] + " " + args[2]);
+            copy(args[1], args[2]);
+         }catch(FileNotFoundException e){
+            System.err.println(e);
+         }catch(IOException e){
+            System.err.println(e);
+         }
+         return;
+      }
+      if(args[0].equals("--concatPath")){
+         // FIXME:
+         File file = org.apache.lenya.util.FileUtil.file("/root/temp/jpf-1.9/java/lenya/x/xps/samples/invoices/invoices", "../addresses/lenya.xml");
+         System.out.println(file.getAbsolutePath());
+      }else{
+      }
+   }
+   /**
+    * Copying a file
+    * 
+    * @param source_name
+    *           DOCUMENT ME!
+    * @param destination_name
+    *           DOCUMENT ME!
+    * 
+    * @throws FileNotFoundException
+    *            DOCUMENT ME!
+    * @throws IOException
+    *            DOCUMENT ME!
+    */
+   public static void copy(String source_name, String destination_name) throws FileNotFoundException, IOException {
+      InputStream source = new FileInputStream(source_name);
+      File destination_file = new File(destination_name);
+      File parent = new File(destination_file.getParent());
+      if(!parent.exists()){
+         parent.mkdirs();
+         log.debug("Directory has been created: " + parent.getAbsolutePath());
+      }
+      OutputStream destination = new FileOutputStream(destination_name);
+      byte[] bytes_buffer = new byte[1024];
+      int bytes_read;
+      while((bytes_read = source.read(bytes_buffer)) >= 0){
+         destination.write(bytes_buffer, 0, bytes_read);
+      }
+   }
+   /**
+    * Copy a single File or a complete Directory including its Contents.
+    * 
+    * @param src
+    *           the source File.
+    * @param dest
+    *           the destiantion File.
+    * 
+    * @throws FileNotFoundException
+    *            if the source File does not exists.
+    * @throws IOException
+    *            if an error occures in the io system.
+    */
+   public static void copy(File src, File dest) throws FileNotFoundException, IOException {
+      if(src.isFile()){
+         copySingleFile(src, dest);
+      }else{
+         File[] contents = src.listFiles();
+         if(contents == null)
             return;
-        }
-
-        if (args[0].equals("--concatPath")) {
-            // FIXME:
-            File file = org.apache.lenya.util.FileUtil.file(
-                    "/root/temp/jpf-1.9/java/lenya/x/xps/samples/invoices/invoices",
-                    "../addresses/lenya.xml");
-            System.out.println(file.getAbsolutePath());
-        } else {
-        }
-    }
-
-    /**
-     * Copying a file
-     * 
-     * @param source_name DOCUMENT ME!
-     * @param destination_name DOCUMENT ME!
-     * 
-     * @throws FileNotFoundException DOCUMENT ME!
-     * @throws IOException DOCUMENT ME!
-     */
-    public static void copy(String source_name, String destination_name)
-            throws FileNotFoundException, IOException {
-        InputStream source = new FileInputStream(source_name);
-        File destination_file = new File(destination_name);
-        File parent = new File(destination_file.getParent());
-
-        if (!parent.exists()) {
-            parent.mkdirs();
-            log.debug("Directory has been created: " + parent.getAbsolutePath());
-        }
-
-        OutputStream destination = new FileOutputStream(destination_name);
-        byte[] bytes_buffer = new byte[1024];
-        int bytes_read;
-
-        while ((bytes_read = source.read(bytes_buffer)) >= 0) {
-            destination.write(bytes_buffer, 0, bytes_read);
-        }
-    }
-
-    /**
-     * Copy a single File or a complete Directory including its Contents.
-     * 
-     * @param src the source File.
-     * @param dest the destiantion File.
-     * 
-     * @throws FileNotFoundException if the source File does not exists.
-     * @throws IOException if an error occures in the io system.
-     */
-    public static void copy(File src, File dest) throws FileNotFoundException, IOException {
-
-        if (src.isFile()) {
-            copySingleFile(src, dest);
-        } else {
-            File[] contents = src.listFiles();
-
-            if (contents == null)
-                return;
-
-            dest.mkdirs();
-
-            for (int i = 0; i < contents.length; i++) {
-                String destPath = dest.getAbsolutePath() + File.separator + contents[i].getName();
-                copy(contents[i], new File(destPath));
-            }
-        }
-    }
-
-    /**
-     * Copy a single File.
-     * 
-     * @param src the source File.
-     * @param dest the destiantion File.
-     * 
-     * @throws FileNotFoundException if the source File does not exists.
-     * @throws IOException if an error occures in the io system.
-     */
-    protected static void copySingleFile(File src, File dest) throws FileNotFoundException,
-            IOException {
-
-        dest.getParentFile().mkdirs();
-        dest.createNewFile();
-        org.apache.commons.io.FileUtils.copyFile(src, dest);
-    }
-
-    /**
-     * Returns a file by specifying an absolute directory name and a relative file name
-     * 
-     * @param absoluteDir DOCUMENT ME!
-     * @param relativeFile DOCUMENT ME!
-     * 
-     * @return DOCUMENT ME!
-     */
-    public static File file(String absoluteDir, String relativeFile) {
-        File file = new File(fileName(absoluteDir, relativeFile));
-
-        return file;
-    }
-
-    /**
-     * Returns an absolute file name by specifying an absolute directory name and a relative file
-     * name
-     * 
-     * @param absoluteDir DOCUMENT ME!
-     * @param relativeFile DOCUMENT ME!
-     * 
-     * @return DOCUMENT ME!
-     */
-    public static String fileName(String absoluteDir, String relativeFile) {
-        String fileName = null;
-        String newAbsoluteDir = null;
-
-        if (!(absoluteDir.charAt(absoluteDir.length() - 1) == '/')) {
-            newAbsoluteDir = absoluteDir + "/";
-        } else {
-            newAbsoluteDir = absoluteDir;
-        }
-
-        if (relativeFile.indexOf("../") == 0) {
-            StringTokenizer token = new StringTokenizer(newAbsoluteDir, "/");
-            newAbsoluteDir = "/";
-
-            int numberOfTokens = token.countTokens();
-
-            for (int i = 0; i < (numberOfTokens - 1); i++) {
-                newAbsoluteDir = newAbsoluteDir + token.nextToken() + "/";
-            }
-
-            String newRelativeFile = relativeFile.substring(3, relativeFile.length());
-            fileName = fileName(newAbsoluteDir, newRelativeFile);
-        } else if (relativeFile.indexOf("./") == 0) {
-            fileName = newAbsoluteDir + relativeFile.substring(2, relativeFile.length());
-        } else {
-            fileName = newAbsoluteDir + relativeFile;
-        }
-
-        return fileName;
-    }
-
-    /**
-     * Returns an absolute file name by specifying an absolute directory name and a relative file
-     * name
-     * 
-     * @param absoluteFile DOCUMENT ME!
-     * @param relativeFile DOCUMENT ME!
-     * 
-     * @return DOCUMENT ME!
-     */
-    public static String concat(String absoluteFile, String relativeFile) {
-        File file = new File(absoluteFile);
-
-        if (file.isFile()) {
-            return fileName(file.getParent(), relativeFile);
-        }
-
-        return fileName(absoluteFile, relativeFile);
-    }
-
-    /**
-     * Deletes all dirs up to stop dir or if dirs in hirachy are not empty.
-     * 
-     * @param start File to delete the parents of. The File itself is not deleted.
-     * @param stop Stop deleting at this dir. This dir is not deleted.
-     * @throws IllegalArgumentException If stop is not a dir or start is not a descending sibling of
-     *                   stop dir.
-     */
-    public static void deleteParentDirs(File start, File stop) throws IllegalArgumentException {
-        if (!stop.isDirectory())
-            throw new IllegalArgumentException("Stop dir '" + stop.getAbsolutePath()
-                    + "' is not a directory");
-        if (!start.getAbsolutePath().startsWith(stop.getAbsolutePath()))
-            throw new IllegalArgumentException("Start dir '" + start.getAbsolutePath()
-                    + "' is not a descending sibling of stop directory '" + stop.getAbsolutePath()
-                    + "'.");
-
-        File parent = start.getParentFile();
-
-        while (!parent.equals(stop) && parent.delete())
-            parent = parent.getParentFile();
-    }
+         dest.mkdirs();
+         for(int i = 0; i < contents.length; i++){
+            String destPath = dest.getAbsolutePath() + File.separator + contents[i].getName();
+            copy(contents[i], new File(destPath));
+         }
+      }
+   }
+   /**
+    * Copy a single File.
+    * 
+    * @param src
+    *           the source File.
+    * @param dest
+    *           the destiantion File.
+    * 
+    * @throws FileNotFoundException
+    *            if the source File does not exists.
+    * @throws IOException
+    *            if an error occures in the io system.
+    */
+   protected static void copySingleFile(File src, File dest) throws FileNotFoundException, IOException {
+      dest.getParentFile().mkdirs();
+      dest.createNewFile();
+      org.apache.commons.io.FileUtils.copyFile(src, dest);
+   }
+   /**
+    * Returns a file by specifying an absolute directory name and a relative file name
+    * 
+    * @param absoluteDir
+    *           DOCUMENT ME!
+    * @param relativeFile
+    *           DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public static File file(String absoluteDir, String relativeFile) {
+      File file = new File(fileName(absoluteDir, relativeFile));
+      return file;
+   }
+   /**
+    * Returns an absolute file name by specifying an absolute directory name and a relative file name
+    * 
+    * @param absoluteDir
+    *           DOCUMENT ME!
+    * @param relativeFile
+    *           DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public static String fileName(String absoluteDir, String relativeFile) {
+      String fileName = null;
+      String newAbsoluteDir = null;
+      if(!(absoluteDir.charAt(absoluteDir.length() - 1) == '/')){
+         newAbsoluteDir = absoluteDir + "/";
+      }else{
+         newAbsoluteDir = absoluteDir;
+      }
+      if(relativeFile.indexOf("../") == 0){
+         StringTokenizer token = new StringTokenizer(newAbsoluteDir, "/");
+         newAbsoluteDir = "/";
+         int numberOfTokens = token.countTokens();
+         for(int i = 0; i < (numberOfTokens - 1); i++){
+            newAbsoluteDir = newAbsoluteDir + token.nextToken() + "/";
+         }
+         String newRelativeFile = relativeFile.substring(3, relativeFile.length());
+         fileName = fileName(newAbsoluteDir, newRelativeFile);
+      }else if(relativeFile.indexOf("./") == 0){
+         fileName = newAbsoluteDir + relativeFile.substring(2, relativeFile.length());
+      }else{
+         fileName = newAbsoluteDir + relativeFile;
+      }
+      return fileName;
+   }
+   /**
+    * Returns an absolute file name by specifying an absolute directory name and a relative file name
+    * 
+    * @param absoluteFile
+    *           DOCUMENT ME!
+    * @param relativeFile
+    *           DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public static String concat(String absoluteFile, String relativeFile) {
+      File file = new File(absoluteFile);
+      if(file.isFile()){
+         return fileName(file.getParent(), relativeFile);
+      }
+      return fileName(absoluteFile, relativeFile);
+   }
+   /**
+    * Deletes all dirs up to stop dir or if dirs in hirachy are not empty.
+    * 
+    * @param start
+    *           File to delete the parents of. The File itself is not deleted.
+    * @param stop
+    *           Stop deleting at this dir. This dir is not deleted.
+    * @throws IllegalArgumentException
+    *            If stop is not a dir or start is not a descending sibling of stop dir.
+    */
+   public static void deleteParentDirs(File start, File stop) throws IllegalArgumentException {
+      if(!stop.isDirectory())
+         throw new IllegalArgumentException("Stop dir '" + stop.getAbsolutePath() + "' is not a directory");
+      if(!start.getAbsolutePath().startsWith(stop.getAbsolutePath()))
+         throw new IllegalArgumentException("Start dir '" + start.getAbsolutePath() + "' is not a descending sibling of stop directory '" + stop.getAbsolutePath() + "'.");
+      File parent = start.getParentFile();
+      while(!parent.equals(stop) && parent.delete())
+         parent = parent.getParentFile();
+   }
 }

Added: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Globals.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Globals.java?rev=617035&view=auto
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Globals.java (added)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Globals.java Wed Jan 30 23:44:03 2008
@@ -0,0 +1,140 @@
+package org.apache.lenya.util;
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.util.Map;
+import org.apache.cocoon.environment.http.HttpContext;
+import org.apache.cocoon.environment.http.HttpEnvironment;
+import org.apache.excalibur.source.Source;
+import org.apache.excalibur.source.SourceException;
+import org.apache.log.ContextMap;
+/**
+ * Static functions for accessing global and thread-based constants.
+ * 
+ * @author solprovider
+ * @since 1.3
+ * 
+ */
+public final class Globals {
+   private Globals() {
+   }
+   // null
+   static public String getAction() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpEnvironment he = (HttpEnvironment) map.get("source-resolver");
+      return he.getAction();
+   }
+   // null
+   static public String getContentType() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpEnvironment he = (HttpEnvironment) map.get("source-resolver");
+      return he.getContentType();
+   }
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/authoring/
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/cache/module.xmap
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/edit/
+   // ?? Last use of map:mount
+   static public String getContext() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpEnvironment he = (HttpEnvironment) map.get("source-resolver");
+      return he.getContext();
+  }
+   static public String getModule() {
+      Source source = getSource();
+      if(null == source)
+         return "";
+      String ret = "";
+      String[] strings = source.getURI().split("^(.*)modules");
+      if(1 < strings.length){
+         strings = strings[1].split("[/\\\\]");
+         if(1 < strings.length){
+            ret = strings[1];
+         }
+      }
+      return ret;
+   }
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/
+   // ??? servletContextPath with protocol
+   static public String getRootContext() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpEnvironment he = (HttpEnvironment) map.get("source-resolver");
+      return he.getRootContext();
+   }
+   // Jetty/4.2
+   static public String getServerName() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpContext hc = (HttpContext) map.get("context");
+      return hc.getServerInfo();
+   }
+   // F:\eclipseWS\Lenya13x\build\lenya\webapp
+   // servletContextPath in OS' native format
+   static public String getServletContextPath() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpContext hc = (HttpContext) map.get("context");
+      return hc.getRealPath("");
+   }
+   // Source.getURI() =
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/navigation/
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/nav/
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/authoring/
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/cache/module.xmap
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/edit/
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/live/
+   // file:///F:/eclipseWS/Lenya13x/build/lenya/webapp/lenya/modules/xhtml/
+   // ??? The current XMAP (Lenya 1.3 defaults directories to "module.xmap")
+   /**
+    * FileSource
+    */
+   static public Source getSource() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpEnvironment he = (HttpEnvironment) map.get("source-resolver");
+      try{
+         return he.resolveURI("");
+      }catch(MalformedURLException e){
+         System.out.println("Globals.getSource MalformedURLException");
+      }catch(SourceException e){
+         System.out.println("Globals.getSource SourceException");
+      }catch(IOException e){
+         System.out.println("Globals.getSource IOException");
+      }
+      return null;
+   }
+   // C:\DOCUME~1\solprovider\LOCALS~1\Temp\Jetty__8888__
+   static public String getTempDir() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpContext hc = (HttpContext) map.get("context");
+      return (String) hc.getAttribute("javax.servlet.context.tempdir");
+   }
+   // authoring/index.html
+   // edit
+   // live/features_en.html
+   // live/index.html
+   // ??? The current match string for the XMAP.
+   static public String getURI() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpEnvironment he = (HttpEnvironment) map.get("source-resolver");
+      return he.getURI();
+   }
+   // default13/
+   static public String getURIPrefix() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpEnvironment he = (HttpEnvironment) map.get("source-resolver");
+      return he.getURIPrefix();
+   }
+   // null
+   static public String getView() {
+      ContextMap contextMap = ContextMap.getCurrentContext();
+      Map map = (Map) contextMap.get("objectModel");
+      HttpEnvironment he = (HttpEnvironment) map.get("source-resolver");
+      return he.getView();
+   }
+}

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/HTMLHandler.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/HTMLHandler.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/HTMLHandler.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/HTMLHandler.java Wed Jan 30 23:44:03 2008
@@ -14,150 +14,128 @@
  *  limitations under the License.
  *
  */
-
 /* $Id$  */
-
 package org.apache.lenya.util;
-
 import java.util.ArrayList;
-
 import javax.swing.text.MutableAttributeSet;
 import javax.swing.text.html.HTML;
 import javax.swing.text.html.HTML.Tag;
 import javax.swing.text.html.HTMLEditorKit.ParserCallback;
-
-import org.apache.log4j.Category;
-
-
-/**
- * DOCUMENT ME!
- */
 public class HTMLHandler extends ParserCallback {
-    Category log = Category.getInstance(HTMLHandler.class);
-    private ArrayList img_src;
-    private ArrayList img_src_all;
-    private ArrayList a_href;
-    private ArrayList a_href_all;
-    private ArrayList link_href;
-    private ArrayList link_href_all;
-
-    /**
-     * Creates a new HTMLHandler object.
-     */
-    public HTMLHandler() {
-        img_src_all = new ArrayList();
-        img_src = new ArrayList();
-        a_href_all = new ArrayList();
-        a_href = new ArrayList();
-        link_href_all = new ArrayList();
-        link_href = new ArrayList();
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param tag DOCUMENT ME!
-     * @param attributes DOCUMENT ME!
-     * @param pos DOCUMENT ME!
-     */
-    public void handleStartTag(Tag tag, MutableAttributeSet attributes, int pos) {
-        if (tag.equals(HTML.Tag.A)) {
-            String href = (String) attributes.getAttribute(HTML.Attribute.HREF);
-
-            if (href != null) {
-                a_href_all.add(href);
-
-                if (!a_href.contains(href)) {
-                    a_href.add(href);
-                }
+   private ArrayList img_src;
+   private ArrayList img_src_all;
+   private ArrayList a_href;
+   private ArrayList a_href_all;
+   private ArrayList link_href;
+   private ArrayList link_href_all;
+   /**
+    * Creates a new HTMLHandler object.
+    */
+   public HTMLHandler() {
+      img_src_all = new ArrayList();
+      img_src = new ArrayList();
+      a_href_all = new ArrayList();
+      a_href = new ArrayList();
+      link_href_all = new ArrayList();
+      link_href = new ArrayList();
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param tag
+    *           DOCUMENT ME!
+    * @param attributes
+    *           DOCUMENT ME!
+    * @param pos
+    *           DOCUMENT ME!
+    */
+   public void handleStartTag(Tag tag, MutableAttributeSet attributes, int pos) {
+      if(tag.equals(HTML.Tag.A)){
+         String href = (String) attributes.getAttribute(HTML.Attribute.HREF);
+         if(href != null){
+            a_href_all.add(href);
+            if(!a_href.contains(href)){
+               a_href.add(href);
             }
-        }
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param tag DOCUMENT ME!
-     * @param attributes DOCUMENT ME!
-     * @param pos DOCUMENT ME!
-     */
-    public void handleSimpleTag(Tag tag, MutableAttributeSet attributes, int pos) {
-        if (tag.equals(HTML.Tag.IMG)) {
-            String src = (String) attributes.getAttribute(HTML.Attribute.SRC);
-
-            if (src != null) {
-                img_src_all.add(src);
-
-                if (!img_src.contains(src)) {
-                    img_src.add(src);
-                }
+         }
+      }
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param tag
+    *           DOCUMENT ME!
+    * @param attributes
+    *           DOCUMENT ME!
+    * @param pos
+    *           DOCUMENT ME!
+    */
+   public void handleSimpleTag(Tag tag, MutableAttributeSet attributes, int pos) {
+      if(tag.equals(HTML.Tag.IMG)){
+         String src = (String) attributes.getAttribute(HTML.Attribute.SRC);
+         if(src != null){
+            img_src_all.add(src);
+            if(!img_src.contains(src)){
+               img_src.add(src);
             }
-        }
-
-        if (tag.equals(HTML.Tag.LINK)) {
-            String href = (String) attributes.getAttribute(HTML.Attribute.HREF);
-
-            if (href != null) {
-                link_href_all.add(href);
-
-                if (!link_href.contains(href)) {
-                    link_href.add(href);
-                }
+         }
+      }
+      if(tag.equals(HTML.Tag.LINK)){
+         String href = (String) attributes.getAttribute(HTML.Attribute.HREF);
+         if(href != null){
+            link_href_all.add(href);
+            if(!link_href.contains(href)){
+               link_href.add(href);
             }
-        }
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public ArrayList getImageSrcs() {
-        return img_src;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public ArrayList getAllImageSrcs() {
-        return img_src_all;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public ArrayList getLinkHRefs() {
-        return link_href;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public ArrayList getAllLinkHRefs() {
-        return link_href_all;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public ArrayList getAHRefs() {
-        return a_href;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @return DOCUMENT ME!
-     */
-    public ArrayList getAllAHRefs() {
-        return a_href_all;
-    }
+         }
+      }
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public ArrayList getImageSrcs() {
+      return img_src;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public ArrayList getAllImageSrcs() {
+      return img_src_all;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public ArrayList getLinkHRefs() {
+      return link_href;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public ArrayList getAllLinkHRefs() {
+      return link_href_all;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public ArrayList getAHRefs() {
+      return a_href;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @return DOCUMENT ME!
+    */
+   public ArrayList getAllAHRefs() {
+      return a_href_all;
+   }
 }

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Log4Echo.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Log4Echo.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Log4Echo.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Log4Echo.java Wed Jan 30 23:44:03 2008
@@ -14,45 +14,39 @@
  *  limitations under the License.
  *
  */
-
 /* $Id$  */
-
 package org.apache.lenya.util;
-
-import org.apache.log4j.Category;
-
-
+import org.apache.log4j.Logger;
 /**
  * Can be used within shell scripts resp. batch files
  */
 public class Log4Echo {
-    private static Category log = Category.getInstance(Log4Echo.class);
-    
-    /**
-     * main
-     *
-     * @param args DOCUMENT ME!
-     */
-    public static void main(String[] args) {
-        if (args.length != 2) {
-            System.err.println("Usage: java " + new Log4Echo().getClass().getName() + "log-level log-message");
-            return;
-        }
-
-        String level = args[0].toLowerCase();
-        String message = args[1];
-        if (level.equals("debug")) {
-            log.debug(message);
-        } else if (level.equals("info")) {
-            log.info(message);
-        } else if (level.equals("warn")) {
-            log.warn(message);
-        } else if (level.equals("error")) {
-            log.error(message);
-        } else if (level.equals("fatal")) {
-            log.fatal(message);
-        } else {
-            log.error("No such log level: " + level + " " + message);
-        }
-    }
+   private static Logger log = Logger.getLogger(Log4Echo.class);
+   /**
+    * main
+    * 
+    * @param args
+    *           DOCUMENT ME!
+    */
+   public static void main(String[] args) {
+      if(args.length != 2){
+         System.err.println("Usage: java " + new Log4Echo().getClass().getName() + "log-level log-message");
+         return;
+      }
+      String level = args[0].toLowerCase();
+      String message = args[1];
+      if(level.equals("debug")){
+         log.debug(message);
+      }else if(level.equals("info")){
+         log.info(message);
+      }else if(level.equals("warn")){
+         log.warn(message);
+      }else if(level.equals("error")){
+         log.error(message);
+      }else if(level.equals("fatal")){
+         log.fatal(message);
+      }else{
+         log.error("No such log level: " + level + " " + message);
+      }
+   }
 }

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/SED.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/SED.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/SED.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/SED.java Wed Jan 30 23:44:03 2008
@@ -14,11 +14,8 @@
  *  limitations under the License.
  *
  */
-
 /* $Id$  */
-
 package org.apache.lenya.util;
-
 import java.io.File;
 import java.io.FileInputStream;
 import java.io.FileOutputStream;
@@ -31,64 +28,58 @@
 import java.nio.charset.CharsetDecoder;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
-
-import org.apache.log4j.Category;
-
+import org.apache.log4j.Logger;
 /**
  * Similar to the UNIX sed
  */
 public class SED {
-    static Category log = Category.getInstance(SED.class);
-
-    /**
-     * Command Line Interface
-     *
-     * @param args DOCUMENT ME!
-     */
-    public static void main(String[] args) {
-        if (args.length == 0) {
-            System.out.println("Usage: org.apache.lenya.util.SED");
-            return;
-        }
-    }
-
-    /**
-     * Substitute prefix, e.g. ".*world.*" by "universe"
-     *
-     * @param file File which sed shall be applied
-     * @param prefixSubstitute Prefix which shall be replaced
-     * @param substituteReplacement Prefix which is going to replace the original
-     *
-     * @throws IOException DOCUMENT ME!
-     */
-    public static void replaceAll(File file, String substitute, String substituteReplacement) throws IOException {
-        log.debug("Replace " + substitute + " by " + substituteReplacement);
-
-        Pattern pattern = Pattern.compile(substitute);
-
-        // Open the file and then get a channel from the stream
-        FileInputStream fis = new FileInputStream(file);
-        FileChannel fc = fis.getChannel();
-
-        // Get the file's size and then map it into memory
-        int sz = (int)fc.size();
-        MappedByteBuffer bb = fc.map(FileChannel.MapMode.READ_ONLY, 0, sz);
-
-	// Decode the file into a char buffer
-        // Charset and decoder for ISO-8859-15
-        Charset charset = Charset.forName("ISO-8859-15");
-        CharsetDecoder decoder = charset.newDecoder();
-	CharBuffer cb = decoder.decode(bb);
-
-        Matcher matcher = pattern.matcher(cb);
-        String outString = matcher.replaceAll(substituteReplacement);
-        log.debug(outString);
-
-
-        FileOutputStream fos = new FileOutputStream(file.getAbsolutePath());
-        PrintStream ps =new PrintStream(fos);
-        ps.print(outString);
-        ps.close();
-        fos.close();
-    }
+   private static Logger log = Logger.getLogger(SED.class);
+   /**
+    * Command Line Interface
+    * 
+    * @param args
+    *           DOCUMENT ME!
+    */
+   public static void main(String[] args) {
+      if(args.length == 0){
+         System.out.println("Usage: org.apache.lenya.util.SED");
+         return;
+      }
+   }
+   /**
+    * Substitute prefix, e.g. ".*world.*" by "universe"
+    * 
+    * @param file
+    *           File which sed shall be applied
+    * @param prefixSubstitute
+    *           Prefix which shall be replaced
+    * @param substituteReplacement
+    *           Prefix which is going to replace the original
+    * 
+    * @throws IOException
+    *            DOCUMENT ME!
+    */
+   public static void replaceAll(File file, String substitute, String substituteReplacement) throws IOException {
+      log.debug("Replace " + substitute + " by " + substituteReplacement);
+      Pattern pattern = Pattern.compile(substitute);
+      // Open the file and then get a channel from the stream
+      FileInputStream fis = new FileInputStream(file);
+      FileChannel fc = fis.getChannel();
+      // Get the file's size and then map it into memory
+      int sz = (int) fc.size();
+      MappedByteBuffer bb = fc.map(FileChannel.MapMode.READ_ONLY, 0, sz);
+      // Decode the file into a char buffer
+      // Charset and decoder for ISO-8859-15
+      Charset charset = Charset.forName("ISO-8859-15");
+      CharsetDecoder decoder = charset.newDecoder();
+      CharBuffer cb = decoder.decode(bb);
+      Matcher matcher = pattern.matcher(cb);
+      String outString = matcher.replaceAll(substituteReplacement);
+      log.debug(outString);
+      FileOutputStream fos = new FileOutputStream(file.getAbsolutePath());
+      PrintStream ps = new PrintStream(fos);
+      ps.print(outString);
+      ps.close();
+      fos.close();
+   }
 }

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/ServletHelper.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/ServletHelper.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/ServletHelper.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/ServletHelper.java Wed Jan 30 23:44:03 2008
@@ -14,85 +14,76 @@
  *  limitations under the License.
  *
  */
-
 /* $Id$  */
-
 package org.apache.lenya.util;
-
 import java.util.Enumeration;
 import java.util.HashMap;
 import java.util.Map;
-
 import org.apache.cocoon.environment.Request;
-import org.apache.log4j.Category;
-
+import org.apache.log4j.Logger;
 /**
  * Servlet utility class.
  */
 public final class ServletHelper {
-	
-	private static Category log = Category.getInstance(ServletHelper.class);
-
-    /**
-     * Ctor.
-     */
-    private ServletHelper() {
-
-    }
-
-    /**
-     * Returns the URL inside the web application (without the context prefix). 
-     * @param request The request.
-     * @return A string.
-     */
-    public static String getWebappURI(Request request) {
-        String context = request.getContextPath();
-        String requestUri = request.getRequestURI();
-        return getWebappURI(context, requestUri);
-    }
-
-    /**
-     * Returns the URL inside the web application (without the context prefix). 
-     * @param context The context prefix.
-     * @param requestUri The complete request URI.
-     * @return A string.
-     */
-    public static String getWebappURI(String context, String requestUri) {
-        if (context == null) {
-            context = "";
-        }
-        String url = requestUri.substring(context.length());
-		if (url.length() > 0 && !url.startsWith("/")) {
-			url = "/" + url;
-		}
-		
-		log.debug("    Context prefix:   [" + context + "]");
-		log.debug("    Webapp URL:       [" + url + "]");
-		
-        return url;
-    }
-
-    /**
-     * Converts the request parameters to a map.
-     * If a key is mapped to multiple parameters, a string array is used as the value.
-     * @param request The request.
-     * @return A map.
-     */
-    public static Map getParameterMap(Request request) {
-        Map requestParameters = new HashMap();
-        for (Enumeration e = request.getParameterNames(); e.hasMoreElements();) {
-            String key = (String) e.nextElement();
-            String[] values = request.getParameterValues(key);
-            Object value;
-            if (values.length == 1) {
-                value = values[0];
-            }
-            else {
-                value = values;
-            }
-            requestParameters.put(key, value);
-        }
-        return requestParameters;
-    }
-
+   private static Logger log = Logger.getLogger(ServletHelper.class);
+   /**
+    * Ctor.
+    */
+   private ServletHelper() {
+   }
+   /**
+    * Returns the URL inside the web application (without the context prefix).
+    * 
+    * @param request
+    *           The request.
+    * @return A string.
+    */
+   public static String getWebappURI(Request request) {
+      String context = request.getContextPath();
+      String requestUri = request.getRequestURI();
+      return getWebappURI(context, requestUri);
+   }
+   /**
+    * Returns the URL inside the web application (without the context prefix).
+    * 
+    * @param context
+    *           The context prefix.
+    * @param requestUri
+    *           The complete request URI.
+    * @return A string.
+    */
+   public static String getWebappURI(String context, String requestUri) {
+      if(context == null){
+         context = "";
+      }
+      String url = requestUri.substring(context.length());
+      if(url.length() > 0 && !url.startsWith("/")){
+         url = "/" + url;
+      }
+      log.debug("    Context prefix:   [" + context + "]");
+      log.debug("    Webapp URL:       [" + url + "]");
+      return url;
+   }
+   /**
+    * Converts the request parameters to a map. If a key is mapped to multiple parameters, a string array is used as the value.
+    * 
+    * @param request
+    *           The request.
+    * @return A map.
+    */
+   public static Map getParameterMap(Request request) {
+      Map requestParameters = new HashMap();
+      for(Enumeration e = request.getParameterNames(); e.hasMoreElements();){
+         String key = (String) e.nextElement();
+         String[] values = request.getParameterValues(key);
+         Object value;
+         if(values.length == 1){
+            value = values[0];
+         }else{
+            value = values;
+         }
+         requestParameters.put(key, value);
+      }
+      return requestParameters;
+   }
 }

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Stack.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Stack.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Stack.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/Stack.java Wed Jan 30 23:44:03 2008
@@ -14,49 +14,43 @@
  *  limitations under the License.
  *
  */
-
 /* $Id$  */
-
 package org.apache.lenya.util;
-
 import java.util.Vector;
-
-
 /**
  * DOCUMENT ME!
  */
-
 // FIXME: this class seems pretty useless. Why not remove it?
 public class Stack extends Vector {
-    int maxsize = 0;
-
-    /**
-     * Creates a new Stack object.
-     *
-     * @param maxsize DOCUMENT ME!
-     */
-    public Stack(int maxsize) {
-        this.maxsize = maxsize;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param args DOCUMENT ME!
-     */
-    public static void main(String[] args) {
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @param object DOCUMENT ME!
-     */
-    public void push(Object object) {
-        insertElementAt(object, 0);
-
-        if (size() == (maxsize + 1)) {
-            removeElementAt(maxsize);
-        }
-    }
+   private static final long serialVersionUID = 1L;
+   int maxsize = 0;
+   /**
+    * Creates a new Stack object.
+    * 
+    * @param maxsize
+    *           DOCUMENT ME!
+    */
+   public Stack(int maxsize) {
+      this.maxsize = maxsize;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param args
+    *           DOCUMENT ME!
+    */
+   public static void main(String[] args) {
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @param object
+    *           DOCUMENT ME!
+    */
+   public void push(Object object) {
+      insertElementAt(object, 0);
+      if(size() == (maxsize + 1)){
+         removeElementAt(maxsize);
+      }
+   }
 }

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/XPSFileOutputStream.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/XPSFileOutputStream.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/XPSFileOutputStream.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/util/XPSFileOutputStream.java Wed Jan 30 23:44:03 2008
@@ -14,130 +14,124 @@
  *  limitations under the License.
  *
  */
-
 /* $Id$  */
-
 package org.apache.lenya.util;
-
 import java.io.File;
 import java.io.FileDescriptor;
 import java.io.FileOutputStream;
 import java.io.IOException;
-
 import org.apache.commons.io.FileUtils;
-import org.apache.log4j.Category;
-
-
+import org.apache.log4j.Logger;
 /**
  * DOCUMENT ME!
  */
 public class XPSFileOutputStream extends FileOutputStream {
-    static Category log = Category.getInstance(XPSFileOutputStream.class);
-    private static final String suffixBase = ".xpstemp";
-    protected String realFilename = null;
-    protected String suffix = null;
-
-    /**
-     * Creates a new XPSFileOutputStream object.
-     *
-     * @param name DOCUMENT ME!
-     *
-     * @throws IOException DOCUMENT ME!
-     */
-    public XPSFileOutputStream(String name) throws IOException {
-        super(getTempFilename(name));
-        setRealFilename(name);
-    }
-
-    /**
-     * Creates a new XPSFileOutputStream object.
-     *
-     * @param file DOCUMENT ME!
-     *
-     * @throws IOException DOCUMENT ME!
-     */
-    public XPSFileOutputStream(File file) throws IOException {
-        super(getTempFilename(file.getAbsolutePath()));
-        setRealFilename(file.getAbsolutePath());
-    }
-
-    /**
-     * Creates a new XPSFileOutputStream object.
-     *
-     * @param filename DOCUMENT ME!
-     * @param append DOCUMENT ME!
-     *
-     * @throws IOException DOCUMENT ME!
-     */
-    public XPSFileOutputStream(String filename, boolean append)
-        throws IOException {
-        super(getTempFilename(filename), append);
-        setRealFilename(filename);
-    }
-
-    /**
-     * We cannot support this version of the constructer because we need to play tricks with the
-     * filename. There is no filename available when starting with a FileDescriptor.
-     *
-     * @param fdObj DOCUMENT ME!
-     *
-     * @throws IOException DOCUMENT ME!
-     */
-    public XPSFileOutputStream(FileDescriptor fdObj) throws IOException {
-        super(fdObj);
-        throw new IOException(
-            "Constructing an XPSFileOutputStream using a FileDescriptor is not suported because we depend on a filename");
-    }
-
-    /**
-	 * @param realname DOCUMENT ME!
-	 * @return DOCUMENT ME!
-	 */
-	// FIXME: the hashCode() is probably not good enough
-    //        We need to find a better source of a random
-    //        string that is available to a static method.
-    //
-    protected static String getTempFilename(String realname) {
-        return realname + XPSFileOutputStream.suffixBase + "." + Runtime.getRuntime().hashCode();
-    }
-
-    /**
-	 * @return DOCUMENT ME!
-	 */
-	protected String getRealFilename() {
-        return this.realFilename;
-    }
-
-    /**
-	 * @param filename DOCUMENT ME!
-	 */
-	protected void setRealFilename(String filename) {
-        this.realFilename = filename;
-    }
-
-    /**
-     * DOCUMENT ME!
-     *
-     * @throws IOException DOCUMENT ME!
-     */
-    public void close() throws IOException {
-        super.close();
-        File temp =  new File(getTempFilename(getRealFilename()));
-		File file =  new File(getRealFilename());
-        FileUtils.copyFile(temp, file);
-        boolean deleted = temp.delete();
-        if (deleted) {
-        	log.debug("The temporary file "+temp.getAbsolutePath() +"is deleted");
-        } else {
-			log.debug("The temporary file "+temp.getAbsolutePath() +" couldn't be deleted");
-        }
-        log.debug(".close(): mv " + getTempFilename(getRealFilename()) + " " + getRealFilename());
-    }
-
-    /**
-     * DOCUMENT ME!
-     */
-    public void flush() {
-        log.debug("flush() called");
-    }
+   private static Logger log = Logger.getLogger(XPSFileOutputStream.class);
+   private static final String suffixBase = ".xpstemp";
+   protected String realFilename = null;
+   protected String suffix = null;
+   /**
+    * Creates a new XPSFileOutputStream object.
+    * 
+    * @param name
+    *           DOCUMENT ME!
+    * 
+    * @throws IOException
+    *            DOCUMENT ME!
+    */
+   public XPSFileOutputStream(String name) throws IOException {
+      super(getTempFilename(name));
+      setRealFilename(name);
+   }
+   /**
+    * Creates a new XPSFileOutputStream object.
+    * 
+    * @param file
+    *           DOCUMENT ME!
+    * 
+    * @throws IOException
+    *            DOCUMENT ME!
+    */
+   public XPSFileOutputStream(File file) throws IOException {
+      super(getTempFilename(file.getAbsolutePath()));
+      setRealFilename(file.getAbsolutePath());
+   }
+   /**
+    * Creates a new XPSFileOutputStream object.
+    * 
+    * @param filename
+    *           DOCUMENT ME!
+    * @param append
+    *           DOCUMENT ME!
+    * 
+    * @throws IOException
+    *            DOCUMENT ME!
+    */
+   public XPSFileOutputStream(String filename, boolean append) throws IOException {
+      super(getTempFilename(filename), append);
+      setRealFilename(filename);
+   }
+   /**
+    * We cannot support this version of the constructer because we need to play tricks with the filename. There is no filename available when starting with a FileDescriptor.
+    * 
+    * @param fdObj
+    *           DOCUMENT ME!
+    * 
+    * @throws IOException
+    *            DOCUMENT ME!
+    */
+   public XPSFileOutputStream(FileDescriptor fdObj) throws IOException {
+      super(fdObj);
+      throw new IOException("Constructing an XPSFileOutputStream using a FileDescriptor is not suported because we depend on a filename");
+   }
+   /**
+    * @param realname
+    *           DOCUMENT ME!
+    * @return DOCUMENT ME!
+    */
+   // FIXME: the hashCode() is probably not good enough
+   // We need to find a better source of a random
+   // string that is available to a static method.
+   //
+   protected static String getTempFilename(String realname) {
+      return realname + XPSFileOutputStream.suffixBase + "." + Runtime.getRuntime().hashCode();
+   }
+   /**
+    * @return DOCUMENT ME!
+    */
+   protected String getRealFilename() {
+      return this.realFilename;
+   }
+   /**
+    * @param filename
+    *           DOCUMENT ME!
+    */
+   protected void setRealFilename(String filename) {
+      this.realFilename = filename;
+   }
+   /**
+    * DOCUMENT ME!
+    * 
+    * @throws IOException
+    *            DOCUMENT ME!
+    */
+   public void close() throws IOException {
+      super.close();
+      File temp = new File(getTempFilename(getRealFilename()));
+      File file = new File(getRealFilename());
+      FileUtils.copyFile(temp, file);
+      boolean deleted = temp.delete();
+      if(deleted){
+         log.debug("The temporary file " + temp.getAbsolutePath() + "is deleted");
+      }else{
+         log.debug("The temporary file " + temp.getAbsolutePath() + " couldn't be deleted");
+      }
+      log.debug(".close(): mv " + getTempFilename(getRealFilename()) + " " + getRealFilename());
+   }
+   /**
+    * DOCUMENT ME!
+    */
+   public void flush() {
+      log.debug("flush() called");
+   }
 }

Modified: lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/workflow/WorkflowException.java
URL: http://svn.apache.org/viewvc/lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/workflow/WorkflowException.java?rev=617035&r1=617034&r2=617035&view=diff
==============================================================================
--- lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/workflow/WorkflowException.java (original)
+++ lenya/branches/revolution/1.3.x/src/java/org/apache/lenya/workflow/WorkflowException.java Wed Jan 30 23:44:03 2008
@@ -14,48 +14,43 @@
  *  limitations under the License.
  *
  */
-
 /* $Id$  */
-
 package org.apache.lenya.workflow;
-
-
 /**
  * Workflow exception.
  */
 public class WorkflowException extends Exception {
-    /**
-     *
-     */
-    public WorkflowException() {
-        super();
-    }
-
-    /**
-     * Create a WorkflowException.
-     * 
-     * @param message The message.
-     */
-    public WorkflowException(String message) {
-        super(message);
-    }
-
-    /**
-     * Create a WorkflowException.
-     * 
-     * @param message The message.
-     * @param cause The cause.
-     */
-    public WorkflowException(String message, Throwable cause) {
-        super(message, cause);
-    }
-
-    /**
-     * Create a WorkflowException.
-     * 
-     * @param cause The cause.
-     */
-    public WorkflowException(Throwable cause) {
-        super(cause);
-    }
+   private static final long serialVersionUID = 1L;
+   public WorkflowException() {
+      super();
+   }
+   /**
+    * Create a WorkflowException.
+    * 
+    * @param message
+    *           The message.
+    */
+   public WorkflowException(String message) {
+      super(message);
+   }
+   /**
+    * Create a WorkflowException.
+    * 
+    * @param message
+    *           The message.
+    * @param cause
+    *           The cause.
+    */
+   public WorkflowException(String message, Throwable cause) {
+      super(message, cause);
+   }
+   /**
+    * Create a WorkflowException.
+    * 
+    * @param cause
+    *           The cause.
+    */
+   public WorkflowException(Throwable cause) {
+      super(cause);
+   }
 }



---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@lenya.apache.org
For additional commands, e-mail: commits-help@lenya.apache.org