You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2017/07/03 11:22:55 UTC
[tika] 01/03: TIKA-2336: Upgrade to POI 3.17-beta1
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/tika.git
commit b9825c608b0553ba780e1f3a92d6f67bb57aadae
Author: tballison <ta...@mitre.org>
AuthorDate: Wed Jun 28 14:53:19 2017 -0400
TIKA-2336: Upgrade to POI 3.17-beta1
---
CHANGES.txt | 2 ++
tika-parsers/pom.xml | 2 +-
.../parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java | 11 -----------
3 files changed, 3 insertions(+), 12 deletions(-)
diff --git a/CHANGES.txt b/CHANGES.txt
index e8a4a74..a377e35 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -1,5 +1,7 @@
Release 1.15.1 - ??/??/????
+ * Upgrade to POI 3.17-beta1 (TIKA-2336).
+
* Remove non-ASL 2.0 compatible org.json (TIKA-1804).
* Allow extraction of scripts as embedded "MACRO". Users
diff --git a/tika-parsers/pom.xml b/tika-parsers/pom.xml
index 218f03f..1bf079d 100644
--- a/tika-parsers/pom.xml
+++ b/tika-parsers/pom.xml
@@ -35,7 +35,7 @@
<url>http://tika.apache.org/</url>
<properties>
- <poi.version>3.16</poi.version>
+ <poi.version>3.17-beta1</poi.version>
<!-- NOTE: sync codec version with POI -->
<codec.version>1.10</codec.version>
<!-- NOTE: sync tukaani version with commons-compress in tika-parent-->
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
index 55df80c..28435de 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
@@ -20,11 +20,9 @@ import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.HashMap;
-import java.util.HashSet;
import java.util.List;
import java.util.Locale;
import java.util.Map;
-import java.util.Set;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hssf.extractor.ExcelExtractor;
@@ -137,21 +135,12 @@ public class XSSFExcelExtractorDecorator extends AbstractOOXMLExtractor {
throw new XmlException(oe);
}
- //temporary workaround for POI-61034
- //remove once POI 3.17-beta1 is released
- Set<String> seen = new HashSet<>();
-
while (iter.hasNext()) {
SheetTextAsHTML sheetExtractor = new SheetTextAsHTML(config.getIncludeHeadersAndFooters(), xhtml);
PackagePart sheetPart = null;
try (InputStream stream = iter.next()) {
sheetPart = iter.getSheetPart();
- final String partName = sheetPart.getPartName().toString();
- if (seen.contains(partName)) {
- continue;
- }
- seen.add(partName);
addDrawingHyperLinks(sheetPart);
sheetParts.add(sheetPart);
--
To stop receiving notification emails like this one, please contact
"commits@tika.apache.org" <co...@tika.apache.org>.