Author: tallison
Date: Thu Jul 23 17:26:58 2015
New Revision: 1692422
URL: http://svn.apache.org/r1692422
Log:
TIKA-1667: upgrade to POI 3.13-beta1
Modified:
tika/trunk/CHANGES.txt
tika/trunk/tika-parsers/pom.xml
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFListManager.java
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
Modified: tika/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/tika/trunk/CHANGES.txt?rev=1692422&r1=1692421&r2=1692422&view=diff
==============================================================================
--- tika/trunk/CHANGES.txt (original)
+++ tika/trunk/CHANGES.txt Thu Jul 23 17:26:58 2015
@@ -1,5 +1,7 @@
Release 1.10 - Current Development
+ * Upgrade to POI 3.13-beta1 (TIKA-1667).
+
* Upgrade to PDFBox 1.8.10 (TIKA-1588).
* MimeTypes now tries to find a registered type with and
Modified: tika/trunk/tika-parsers/pom.xml
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/pom.xml?rev=1692422&r1=1692421&r2=1692422&view=diff
==============================================================================
--- tika/trunk/tika-parsers/pom.xml (original)
+++ tika/trunk/tika-parsers/pom.xml Thu Jul 23 17:26:58 2015
@@ -35,7 +35,7 @@
<url>http://tika.apache.org/</url>
<properties>
- <poi.version>3.12</poi.version>
+ <poi.version>3.13-beta1</poi.version>
<codec.version>1.9</codec.version>
<!-- NOTE: sync with POI -->
<compress.version>1.9</compress.version>
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java?rev=1692422&r1=1692421&r2=1692422&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
Thu Jul 23 17:26:58 2015
@@ -23,6 +23,7 @@ import java.util.Collections;
import java.util.HashSet;
import java.util.Set;
+import org.apache.poi.openxml4j.util.ZipSecureFile;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
@@ -35,6 +36,10 @@ import org.xml.sax.SAXException;
* Office Open XML (OOXML) parser.
*/
public class OOXMLParser extends AbstractParser {
+ static {
+ //turn off POI's zip bomb detection because we have our own
+ ZipSecureFile.setMinInflateRatio(-1.0d);
+ }
protected static final Set<MediaType> SUPPORTED_TYPES =
Collections.unmodifiableSet(new HashSet<MediaType>(Arrays.asList(
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFListManager.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFListManager.java?rev=1692422&r1=1692421&r2=1692422&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFListManager.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFListManager.java
Thu Jul 23 17:26:58 2015
@@ -16,8 +16,6 @@
*/
package org.apache.tika.parser.microsoft.ooxml;
-import java.math.BigInteger;
-
import org.apache.poi.xwpf.usermodel.XWPFAbstractNum;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFNum;
@@ -28,6 +26,7 @@ import org.openxmlformats.schemas.wordpr
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTDecimalNumber;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTLvl;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTNum;
+import org.openxmlformats.schemas.wordprocessingml.x2006.main.CTNumLvl;
public class XWPFListManager extends AbstractListManager {
@@ -83,19 +82,9 @@ public class XWPFListManager extends Abs
return formattedString;
}
-
- /**
- * WARNING: currently always returns null.
- * TODO: Once CTNumLvl is available to Tika,
- * we can turn this back on.
- *
- * @param ctNum number on which to build the overrides
- * @param length length of intended array
- * @return null or an array of override tuples of length {@param length}
- */
+
private LevelTuple[] loadOverrideTuples(CTNum ctNum, int length) {
- return null;
-/* LevelTuple[] levelTuples = new LevelTuple[length];
+ LevelTuple[] levelTuples = new LevelTuple[length];
int overrideLength = ctNum.sizeOfLvlOverrideArray();
if (overrideLength == 0) {
return null;
@@ -114,7 +103,7 @@ public class XWPFListManager extends Abs
}
levelTuples[i] = tuple;
}
- return levelTuples;*/
+ return levelTuples;
}
Modified:
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java?rev=1692422&r1=1692421&r2=1692422&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
(original)
+++
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
Thu Jul 23 17:26:58 2015
@@ -1238,8 +1238,8 @@ public class OOXMLParserTest extends Tik
assertContains("<p>1 1</p>", xml);
assertContains("<p>A A</p>", xml);
assertContains("<p>B B</p>", xml);
- //TODO: add this back in once overrides are available via CTNumLvl
- //assertContains("<p>C C</p>", xml);
+ //this tests overrides
+ assertContains("<p>C C</p>", xml);
assertContains("<p>4 4</p>", xml);
//Test5