ÿþIndex: D:/eclipse/apache-workspace/linkcheck/project.xml =================================================================== --- D:/eclipse/apache-workspace/linkcheck/project.xml (revision 264764) +++ D:/eclipse/apache-workspace/linkcheck/project.xml (working copy) @@ -151,25 +151,9 @@ <version>1.2.8</version> </dependency> <dependency> - <groupId>dom4j</groupId> - <artifactId>dom4j</artifactId> - <version>1.4-dev-8</version> - </dependency> - <dependency> - <groupId>jtidy</groupId> - <artifactId>jtidy</artifactId> - <version>4aug2000r7-dev</version> - </dependency> - <dependency> <groupId>maven</groupId> <artifactId>maven</artifactId> <version>1.0.2</version> </dependency> - <dependency> - <jar>js-1.5R4-RC3.jar</jar> - <groupId>rhino</groupId> - <artifactId>rhino</artifactId> - <version>1.5R4-RC3</version> - </dependency> </dependencies> </project> Index: D:/eclipse/apache-workspace/linkcheck/src/main/org/apache/maven/linkcheck/FileToCheck.java =================================================================== --- D:/eclipse/apache-workspace/linkcheck/src/main/org/apache/maven/linkcheck/FileToCheck.java (revision 264741) +++ D:/eclipse/apache-workspace/linkcheck/src/main/org/apache/maven/linkcheck/FileToCheck.java (working copy) @@ -17,29 +17,19 @@ * ==================================================================== */ -import java.io.BufferedInputStream; -import java.io.ByteArrayOutputStream; import java.io.File; -import java.io.FileInputStream; -import java.io.FileNotFoundException; import java.io.InputStream; import java.io.OutputStream; -import java.io.PrintWriter; import java.util.Iterator; import java.util.LinkedList; import java.util.List; import java.util.Set; -import java.util.TreeSet; import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; import org.apache.maven.linkcheck.validation.LinkValidationItem; import org.apache.maven.linkcheck.validation.LinkValidationResult; import org.apache.maven.linkcheck.validation.LinkValidatorManager; -import org.dom4j.Document; -import org.dom4j.Node; -import org.dom4j.io.DOMReader; -import org.w3c.tidy.Tidy; /** * @author <a href="mailto:bwalding@apache.org">Ben Walding</a> @@ -88,7 +78,7 @@ final Set hrefs; try { - hrefs = getLinks(); + hrefs = LinkMatcher.match(fileToCheck); } catch (Throwable e) { @@ -143,34 +133,6 @@ } } - private Set getLinks() throws FileNotFoundException - { - ByteArrayOutputStream baos = new ByteArrayOutputStream(); - PrintWriter errOut = new PrintWriter(baos); - BufferedInputStream bin = new BufferedInputStream(new FileInputStream(fileToCheck)); - try - { - Tidy tidy = getTidy(); - tidy.setErrout(errOut); - LOG.debug("Processing:" + fileToCheck); - org.w3c.dom.Document domDocument = tidy.parseDOM(bin, null); - - // now read a dom4j document from - // JTidy's W3C DOM object - final DOMReader domReader = new DOMReader(); - final Document doc = domReader.read(domDocument); - - LOG.debug(baos.toString()); - - return findUniqueLinks(doc); - } - finally - { - close(bin); - close(baos); - } - } - private void close(InputStream is) { try @@ -179,7 +141,7 @@ } catch (Exception e) { - //Don't really care. + // Don't really care. } } @@ -195,43 +157,6 @@ } } - private Set findUniqueLinks(Document doc) - { - List xpathResults = new LinkedList(); - - xpathResults.addAll(doc.selectNodes("//a/@href")); - xpathResults.addAll(doc.selectNodes("//img/@src")); - - //<link rel="stylesheet" href="..."> - xpathResults.addAll(doc.selectNodes("//link/@href")); - - //<script src="http://ar.atwola.com/file/adsWrapper.js"> - xpathResults.addAll(doc.selectNodes("//script/@src")); - - Set results = new TreeSet(); - Iterator linkIter = xpathResults.iterator(); - while (linkIter.hasNext()) - { - Node node = (Node) linkIter.next(); - String href = node.getText(); - results.add(href); - } - - return results; - } - - private Tidy getTidy() - { - Tidy tidy = new Tidy(); - tidy.setMakeClean(true); - tidy.setXmlTags(true); - tidy.setXmlOut(true); - tidy.setXHTML(true); - tidy.setQuiet(true); - tidy.setShowWarnings(false); - return tidy; - } - /** * Returns the message. * @return String Index: D:/eclipse/apache-workspace/linkcheck/src/main/org/apache/maven/linkcheck/LinkMatcher.java =================================================================== --- D:/eclipse/apache-workspace/linkcheck/src/main/org/apache/maven/linkcheck/LinkMatcher.java (revision 0) +++ D:/eclipse/apache-workspace/linkcheck/src/main/org/apache/maven/linkcheck/LinkMatcher.java (revision 0) @@ -0,0 +1,111 @@ +package org.apache.maven.linkcheck; + +/* ==================================================================== + * Copyright 2001-2004 The Apache Software Foundation. + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + * ==================================================================== + */ + +import java.io.BufferedReader; +import java.io.File; +import java.io.FileReader; +import java.io.IOException; +import java.util.Set; +import java.util.TreeSet; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +/** + * Link matcher. Reads the contents of a file and tries to match the following: + * <code> + * <a href="".... + * <link href="".... + * <img src="".... + * <script src="".... + * </code> + * + * @author <a href="mailto:mac@apache.org">Ignacio G. Mac Dowell </a> + */ +class LinkMatcher { + + /** + * Regexp for link matching. + */ + private final static Pattern p = Pattern + .compile( + "<(?>link|a|img|script)[^>]*?(?>href|src)\\s*?=\\s*?[\\\"'](.*?)[\\\"'][^>]*?", + Pattern.CASE_INSENSITIVE); + + /** + * No need to create a new object each time a file is processed. Just clear + * it. + */ + private final static Set linkList = new TreeSet(); + + /** + * Reads a file and returns a StringBuffer with its contents. + * + * TODO: Check for encoding issues + * + * TODO: Better exception handling? + * + * @param file + * the file we are reading + * @return a StringBuffer with file's contents. + * @throws IOException + */ + private static StringBuffer fileToStringBuffer(File file) + throws IOException { + BufferedReader reader = null; + final StringBuffer pageBuffer = new StringBuffer(); + try { + reader = new BufferedReader(new FileReader(file)); + String line; + while ((line = reader.readLine()) != null) { + pageBuffer.append(line); + } + } finally { + reader.close(); + } + return pageBuffer; + } + + /** + * Performs the actual matching. + * + * @param file + * the file to check + * @return a set with all links to check + * @throws IOException + */ + static Set match(File file) throws IOException { + linkList.clear(); + final Matcher m = p.matcher(fileToStringBuffer(file)); + String link; + while (m.find()) { + link = m.group(1).trim(); + if (link.length() < 1) { + continue; + } else if (link.toLowerCase().indexOf("javascript") != -1) { + continue; + } + // else if (link.toLowerCase().indexOf("mailto:") != -1) { + // continue; + // } + linkList.add(link); + } + return linkList; + } + +}