If we have a document with a hpsf stream that exists, but is of the wrong type, then...

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@620582 13f79535-47bb-0310-9956-ffa450edef68

diff --git a/src/java/org/apache/poi/POIDocument.java b/src/java/org/apache/poi/POIDocument.java
index ece7a3f13dbf5bbd315860d4cf003cc059f94b8d..8d91c06e79a9e4e7dc14ebd52ec679b745301733 100644 (file)
--- a/src/java/org/apache/poi/POIDocument.java
+++ b/src/java/org/apache/poi/POIDocument.java
@@ -67,14 +67,28 @@ public abstract class POIDocument {
 
        /**
         * Find, and create objects for, the standard
-        *  Documment Information Properties (HPSF)
+        *  Documment Information Properties (HPSF).
+        * If a given property set is missing or corrupt,
+        *  it will remain null;
         */
        protected void readProperties() {
+               PropertySet ps;
+               
                // DocumentSummaryInformation
-               dsInf = (DocumentSummaryInformation)getPropertySet(DocumentSummaryInformation.DEFAULT_STREAM_NAME);
+               ps = getPropertySet(DocumentSummaryInformation.DEFAULT_STREAM_NAME);
+               if(ps != null && ps instanceof DocumentSummaryInformation) {
+                       dsInf = (DocumentSummaryInformation)ps;
+               } else if(ps != null) {
+                       logger.log(POILogger.WARN, "DocumentSummaryInformation property set came back with wrong class - ", ps.getClass());
+               }
 
                // SummaryInformation
-               sInf = (SummaryInformation)getPropertySet(SummaryInformation.DEFAULT_STREAM_NAME);
+               ps = getPropertySet(SummaryInformation.DEFAULT_STREAM_NAME);
+               if(ps instanceof SummaryInformation) {
+                       sInf = (SummaryInformation)ps;
+               } else if(ps != null) {
+                       logger.log(POILogger.WARN, "SummaryInformation property set came back with wrong class - ", ps.getClass());
+               }
        }
 
        /** 

diff --git a/src/scratchpad/testcases/org/apache/poi/hwpf/data/ProblemExtracting.doc b/src/scratchpad/testcases/org/apache/poi/hwpf/data/ProblemExtracting.doc
new file mode 100644 (file)
index 0000000..b980089
Binary files /dev/null and b/src/scratchpad/testcases/org/apache/poi/hwpf/data/ProblemExtracting.doc differ

diff --git a/src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestWordExtractorBugs.java b/src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestWordExtractorBugs.java
new file mode 100644 (file)
index 0000000..b87f586
--- /dev/null
+++ b/src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestWordExtractorBugs.java
@@ -0,0 +1,45 @@
+/*
+* Licensed to the Apache Software Foundation (ASF) under one or more
+* contributor license agreements.  See the NOTICE file distributed with
+* this work for additional information regarding copyright ownership.
+* The ASF licenses this file to You 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.
+*/
+package org.apache.poi.hwpf.extractor;
+
+import java.io.FileInputStream;
+
+import junit.framework.TestCase;
+
+/**
+ * Tests for bugs with the WordExtractor
+ *
+ * @author Nick Burch (nick at torchbox dot com)
+ */
+public class TestWordExtractorBugs extends TestCase {
+       private String dirname;
+    protected void setUp() throws Exception {
+               dirname = System.getProperty("HWPF.testdata.path");
+    }
+    
+    public void testProblemMetadata() throws Exception {
+               String filename = dirname + "/ProblemExtracting.doc";
+               WordExtractor extractor = 
+                       new WordExtractor(new FileInputStream(filename));
+               
+               // Check it gives text without error
+               extractor.getText();
+               extractor.getParagraphText();
+               extractor.getTextFromPieces();
+    }                  
+    
+}