o MAVEN-313: Catch files that don't parse properly and throw Throwable exceptions rather than Exception exceptions!

git-svn-id: https://svn.apache.org/repos/asf/maven/maven-1/plugins/trunk@113079 13f79535-47bb-0310-9956-ffa450edef68

linkcheck/src/main/org/apache/maven/linkcheck/FileToCheck.java

@@ -59,7 +59,6 @@ package org.apache.maven.linkcheck;
 import java.io.ByteArrayOutputStream;
 import java.io.File;
 import java.io.FileInputStream;
-import java.io.IOException;
 import java.io.PrintWriter;
 import java.util.ArrayList;
 import java.util.HashMap;
@@ -79,7 +78,7 @@ import org.w3c.tidy.Tidy;
 
 /**
  * @author <a href="mailto:bwalding@apache.org">Ben Walding</a>
- * @version $Id: FileToCheck.java,v 1.9 2003/03/07 22:09:56 bwalding Exp $
+ * @version $Id: FileToCheck.java,v 1.10 2003/03/07 22:44:54 bwalding Exp $
  *
  */
 public class FileToCheck
@@ -131,34 +130,41 @@ public class FileToCheck
                 ByteArrayOutputStream baos = new ByteArrayOutputStream();
                 PrintWriter errOut = new PrintWriter(baos);
                 tidy.setErrout(errOut);
-                
+                System.out.println("Processing:" + fileToCheck);
                 tidy.setXHTML(true);
                 org.w3c.dom.Document domDocument = tidy.parseDOM(in, null);
 
                 // now read a dom4j document from
                 // JTidy's W3C DOM object
+
                 DOMReader domReader = new DOMReader();
                 doc = domReader.read(domDocument);
-                
+
                 LOG.debug(baos.toString());
             }
-            catch (IOException e)
+            catch (Throwable e)
             {
-                System.out.println("While processing " + fileToCheck + " : " + e.toString());
+                //We catch Throwable, because there is a chance that the domReader will throw
+                //a stack overflow exception for some files
+                if (!(e instanceof Exception)) {
+                    LOG.info("Caught " + e.toString());
+                }
+                LinkCheckResult lcr = new LinkCheckResult();
+                lcr.setStatus("PARSE FAILURE");
+                lcr.setTarget("N/A");
+                this.links.add(lcr);
+                return;
             }
-            
-            
+
             List xpathResults = new ArrayList();
-            
+
             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"));
-            
 
-            
             Map uniqueLinks = new HashMap();
             Iterator linkIter = xpathResults.iterator();
             while (linkIter.hasNext())

linkcheck/src/test/org/apache/maven/linkcheck/LinkCheckTest.java

@@ -95,7 +95,7 @@ public class LinkCheckTest extends TestCase
       map.put(ftc.getName(), ftc);
     }
 
-    assertEquals("files.size()", 6, lc.getFiles().size());
+    assertEquals("files.size()", 7, lc.getFiles().size());
 
     check(map, "nolink.html", 0);
     check(map, "test-resources/nolink.html", 0);
@@ -103,6 +103,9 @@ public class LinkCheckTest extends TestCase
     check(map, "test-resources/test1/test2.html", 0);
     check(map, "test1/test1.html", 1);
     check(map, "testA.html", 3);
+    
+    //index-all.html should get parsed, but is currently having problems.
+    //check(map, "index-all.html", 1);
 
   }