Author: nick
Date: Wed May 15 00:30:12 2013
New Revision: 1482648
URL: http://svn.apache.org/r1482648
Log:
New code to help for TIKA-1118, currently disabled pending a POI upgrade
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java?rev=1482648&r1=1482647&r2=1482648&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
Wed May 15 00:30:12 2013
@@ -173,6 +173,14 @@ public abstract class AbstractOOXMLExtra
*/
private void handleEmbeddedOLE(PackagePart part, ContentHandler handler,
String rel)
throws IOException, SAXException {
+ // A POIFSFileSystem needs to be at least 3 blocks big to be valid
+ // TODO: TIKA-1118 Upgrade to POI 4.0 then enable this block of code
+// if (part.getSize() >= 0 && part.getSize() < 512*3) {
+// // Too small, skip
+// return;
+// }
+
+ // Open the POIFS (OLE2) structure and process
POIFSFileSystem fs = new POIFSFileSystem(part.getInputStream());
try {
Metadata metadata = new Metadata();