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 2026/04/03 21:22:41 UTC

(tika) 03/03: refactor xlsx - WIP

This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch TIKA-4708-refactor-xlsx
in repository https://gitbox.apache.org/repos/asf/tika.git

commit 9daaacf7785fa4d05de18c59ab1328881b55553b
Author: tallison <ta...@apache.org>
AuthorDate: Fri Apr 3 07:57:53 2026 -0400

    refactor xlsx - WIP
---
 .../parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java    | 5 +++++
 .../tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java     | 5 +++++
 2 files changed, 10 insertions(+)

diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java
index c16b75fd8c..d6f5b9759d 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/SXSLFPowerPointExtractorDecorator.java
@@ -93,6 +93,11 @@ public class SXSLFPowerPointExtractorDecorator extends AbstractOOXMLExtractor {
         //if mainDocument == null, throw exception
     }
 
+    @Override
+    public MetadataExtractor getMetadataExtractor() {
+        return new SAXBasedMetadataExtractor(opcPackage, context);
+    }
+
     /**
      * @see org.apache.poi.xslf.extractor.XSLFPowerPointExtractor#getText()
      */
diff --git a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
index 3ebccba8e5..899016caf8 100644
--- a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
+++ b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
@@ -132,6 +132,11 @@ public class XSSFExcelExtractorDecorator extends AbstractOOXMLExtractor {
         //does no good here.
     }
 
+    @Override
+    public MetadataExtractor getMetadataExtractor() {
+        return new SAXBasedMetadataExtractor(extractor.getPackage(), parseContext);
+    }
+
     @Override
     public void getXHTML(ContentHandler handler, Metadata metadata, ParseContext context)
             throws SAXException, IOException, TikaException {