Author: jukka
Date: Thu Mar 5 21:14:37 2009
New Revision: 750589
URL: http://svn.apache.org/viewvc?rev=750589&view=rev
Log:
TIKA-152: Support for Office XML files
Upgraded POI dependency to 3.5-beta5
Modified:
lucene/tika/trunk/pom.xml
lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java
lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
Modified: lucene/tika/trunk/pom.xml
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/pom.xml?rev=750589&r1=750588&r2=750589&view=diff
==============================================================================
--- lucene/tika/trunk/pom.xml (original)
+++ lucene/tika/trunk/pom.xml Thu Mar 5 21:14:37 2009
@@ -203,17 +203,17 @@
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
- <version>3.5-beta4</version>
+ <version>3.5-beta5</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
- <version>3.5-beta4</version>
+ <version>3.5-beta5</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
- <version>3.5-beta4</version>
+ <version>3.5-beta5</version>
</dependency>
<dependency>
<groupId>net.sourceforge.nekohtml</groupId>
Modified:
lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java?rev=750589&r1=750588&r2=750589&view=diff
==============================================================================
---
lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java
(original)
+++
lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java
Thu Mar 5 21:14:37 2009
@@ -21,12 +21,12 @@
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.POIXMLProperties.CoreProperties;
import org.apache.poi.POIXMLProperties.ExtendedProperties;
+import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
+import org.apache.poi.openxml4j.opc.internal.PackagePropertiesPart;
+import org.apache.poi.openxml4j.util.Nullable;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.xmlbeans.XmlException;
-import org.openxml4j.exceptions.OpenXML4JException;
-import org.openxml4j.opc.internal.PackagePropertiesPart;
-import org.openxml4j.util.Nullable;
import
org.openxmlformats.schemas.officeDocument.x2006.extendedProperties.CTProperties;
/**
Modified:
lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java?rev=750589&r1=750588&r2=750589&view=diff
==============================================================================
---
lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
(original)
+++
lucene/tika/trunk/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
Thu Mar 5 21:14:37 2009
@@ -21,12 +21,12 @@
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.extractor.ExtractorFactory;
+import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
+import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.Parser;
import org.apache.xmlbeans.XmlException;
-import org.openxml4j.exceptions.InvalidFormatException;
-import org.openxml4j.exceptions.OpenXML4JException;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;