Bug 266649 – [Help] htmlparser doesn't tell filename when complaning about parsing error

4 files changed, 77 insertions, 20 deletions

diff --git a/org.eclipse.help.base/src/org/eclipse/help/internal/search/HTMLDocParser.java b/org.eclipse.help.base/src/org/eclipse/help/internal/search/HTMLDocParser.java
index 136bb579f..a80ba976d 100644
--- a/org.eclipse.help.base/src/org/eclipse/help/internal/search/HTMLDocParser.java
+++ b/org.eclipse.help.base/src/org/eclipse/help/internal/search/HTMLDocParser.java
@@ -1,5 +1,5 @@
 /*******************************************************************************
- * Copyright (c) 2000, 2007 IBM Corporation and others.
+ * Copyright (c) 2000, 2009 IBM Corporation and others.
  * All rights reserved. This program and the accompanying materials
  * are made available under the terms of the Eclipse Public License v1.0
  * which accompanies this distribution, and is available at
@@ -361,4 +361,11 @@ public class HTMLDocParser {
 		}
 		return null;
 	}
+	
+	public Exception getException() {
+		if (htmlParser != null) {
+			return htmlParser.getException();
+		}
+		return null;
+	}
 }
diff --git a/org.eclipse.help.base/src/org/eclipse/help/internal/search/HTMLSearchParticipant.java b/org.eclipse.help.base/src/org/eclipse/help/internal/search/HTMLSearchParticipant.java
index d83c11ce4..128bb57e7 100644
--- a/org.eclipse.help.base/src/org/eclipse/help/internal/search/HTMLSearchParticipant.java
+++ b/org.eclipse.help.base/src/org/eclipse/help/internal/search/HTMLSearchParticipant.java
@@ -1,5 +1,5 @@
 /*******************************************************************************
- * Copyright (c) 2005, 2007 IBM Corporation and others.
+ * Copyright (c) 2005, 2009 IBM Corporation and others.
  * All rights reserved. This program and the accompanying materials
  * are made available under the terms of the Eclipse Public License v1.0
  * which accompanies this distribution, and is available at
@@ -60,7 +60,7 @@ public class HTMLSearchParticipant extends LuceneSearchParticipant {
 						return new Status(IStatus.ERROR, HelpBasePlugin.PLUGIN_ID, IStatus.ERROR,
 								"Help document " //$NON-NLS-1$
 										+ name + " cannot be opened.", //$NON-NLS-1$
-								null);
+								ioe);
 					}
 					ParsedDocument parsed = new ParsedDocument(parser.getContentReader());
 					doc.add(new Field("contents", parsed.newContentReader())); //$NON-NLS-1$
@@ -70,13 +70,19 @@ public class HTMLSearchParticipant extends LuceneSearchParticipant {
 					doc.add(new Field("exact_title", title, Field.Store.NO, Field.Index.TOKENIZED)); //$NON-NLS-1$
 					doc.add(new Field("raw_title", title, Field.Store.YES, Field.Index.NO)); //$NON-NLS-1$
 					doc.add(new Field("summary", parser.getSummary(title), Field.Store.YES, Field.Index.NO)); //$NON-NLS-1$
+					if (parser.getException() != null) {
+						return new Status(IStatus.ERROR, HelpBasePlugin.PLUGIN_ID, IStatus.ERROR,
+								"Parse error occurred while adding document " + name //$NON-NLS-1$
+										+ " to search index " + indexPath + ".", //$NON-NLS-1$ //$NON-NLS-2$
+								parser.getException());
+					}
 				} finally {
 					parser.closeDocument();
 				}
 			} catch (IOException e) {
 				return new Status(IStatus.ERROR, HelpBasePlugin.PLUGIN_ID, IStatus.ERROR,
 						"IO exception occurred while adding document " + name //$NON-NLS-1$
-								+ " to index " + indexPath + ".", //$NON-NLS-1$ //$NON-NLS-2$
+								+ " to search index " + indexPath + ".", //$NON-NLS-1$ //$NON-NLS-2$
 						e);
 			}
 			return Status.OK_STATUS;
diff --git a/org.eclipse.help.base/src_demo/org/apache/lucene/demo/html/HTMLParser.java b/org.eclipse.help.base/src_demo/org/apache/lucene/demo/html/HTMLParser.java
index 7d71b39cc..7d65fc835 100644
--- a/org.eclipse.help.base/src_demo/org/apache/lucene/demo/html/HTMLParser.java
+++ b/org.eclipse.help.base/src_demo/org/apache/lucene/demo/html/HTMLParser.java
@@ -1,4 +1,33 @@
+/**
+ * Copyright 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.
+ *
+ *     Copyright (c) 2003, 2009 IBM Corp.
+ *     All rights reserved.
+ *
+ * Contributors:
+ *     Apache Software Foundation - Initial contribution
+ *     Konrad Kolosowski, IBM - skipping XML decl, merging meta keywords
+ *       content with main text, encoding read and write to piped stream,
+ *       returning summary if starts with title.
+ *     Curtis d'Entremont, IBM - added missing serialVersionUIDs, removed
+ *       unused imports, labels, variables, methods from javacc *generated*
+ *       code, strip title off summary.
+ *     Chris Goldthorpe, IBM - Bugs 223860, 210991, 246095, 245411, 269380, 266649
+
 /* Generated By:JavaCC: Do not edit this line. HTMLParser.java */
+
 package org.apache.lucene.demo.html;
 
 import java.io.*;
@@ -25,6 +54,7 @@ public class HTMLParser implements HTMLParserConstants {
   Writer pipeOut;
   private MyPipedInputStream pipeInStream = null;
   private PipedOutputStream pipeOutStream = null;
+  private Exception exception = null;
 
   private class MyPipedInputStream extends PipedInputStream{
 
@@ -737,7 +767,15 @@ null)
     p.gen = jj_gen + xla - jj_la; p.first = token; p.arg = xla;
   }
 
-  static final class JJCalls {
+  public void setException(Exception exception) {
+	this.exception = exception;
+  }
+
+  public Exception getException() {
+	return exception;
+  }
+
+static final class JJCalls {
     int gen;
     Token first;
     int arg;
diff --git a/org.eclipse.help.base/src_demo/org/apache/lucene/demo/html/ParserThread.java b/org.eclipse.help.base/src_demo/org/apache/lucene/demo/html/ParserThread.java
index 8d7cdb408..bdbb2e287 100644
--- a/org.eclipse.help.base/src_demo/org/apache/lucene/demo/html/ParserThread.java
+++ b/org.eclipse.help.base/src_demo/org/apache/lucene/demo/html/ParserThread.java
@@ -1,7 +1,7 @@
 package org.apache.lucene.demo.html;
 
 /**
- * Copyright 2004 The Apache Software Foundation
+ * Copyright 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.
@@ -14,7 +14,16 @@ package org.apache.lucene.demo.html;
  * 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.
+ * 
+ *     Copyright (c) 2009 IBM Corp.
+ *     All rights reserved.
  */
+ 
+/**
+* History
+* 2004 Initial contribution The Apache Software Foundation
+* 2009 Chris Goldthorpe, IBM Corporation, fix for bug 266649
+*/
 
 import java.io.*;
 
@@ -26,23 +35,20 @@ class ParserThread extends Thread {
   }
 
   public void run() {				  // convert pipeOut to pipeIn
-    try {
+
       try {					  // parse document to pipeOut
         parser.HTMLDocument();
-      } catch (ParseException e) {
-        System.out.println("Parse Aborted: " + e.getMessage()); //$NON-NLS-1$
-      } catch (TokenMgrError e) {
-        System.out.println("Parse Aborted: " + e.getMessage()); //$NON-NLS-1$
-      } finally {
-        parser.pipeOut.close();
-        synchronized (parser) {
-	      parser.summary.setLength(HTMLParser.SUMMARY_LENGTH);
-	      parser.titleComplete = true;
-	      parser.notifyAll();
-	    }
+      } catch (Exception e) {
+    	  parser.setException(e);
       }
-    } catch (IOException e) {
-	  e.printStackTrace();
+
+      try {
+	    parser.summary.setLength(HTMLParser.SUMMARY_LENGTH);
+	    parser.titleComplete = true;
+        parser.pipeOut.close();
+      } catch (IOException e) {
+	       e.printStackTrace();
     }
+	parser.notifyAll();
   }
 }