(nifi) branch main updated: NIFI-15098 Disabled OCR for ExtractMediaMetadata Processor (#10426)

[exceptionfactory]

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

exceptionfactory pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/nifi.git


The following commit(s) were added to refs/heads/main by this push:
     new 931ed06729 NIFI-15098 Disabled OCR for ExtractMediaMetadata Processor 
(#10426)
931ed06729 is described below

commit 931ed06729800b9d8727184812a156d53d8e5ea5
Author: Lars Francke <lars.fran...@stackable.tech>
AuthorDate: Fri Oct 17 05:42:29 2025 +0200

    NIFI-15098 Disabled OCR for ExtractMediaMetadata Processor (#10426)
    
    Signed-off-by: David Handermann <exceptionfact...@apache.org>
---
 .../apache/nifi/processors/media/ExtractMediaMetadata.java   | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git 
a/nifi-extension-bundles/nifi-media-bundle/nifi-media-processors/src/main/java/org/apache/nifi/processors/media/ExtractMediaMetadata.java
 
b/nifi-extension-bundles/nifi-media-bundle/nifi-media-processors/src/main/java/org/apache/nifi/processors/media/ExtractMediaMetadata.java
index 7bed9edc0e..7453c94663 100644
--- 
a/nifi-extension-bundles/nifi-media-bundle/nifi-media-processors/src/main/java/org/apache/nifi/processors/media/ExtractMediaMetadata.java
+++ 
b/nifi-extension-bundles/nifi-media-bundle/nifi-media-processors/src/main/java/org/apache/nifi/processors/media/ExtractMediaMetadata.java
@@ -48,6 +48,8 @@ import org.apache.tika.exception.TikaException;
 import org.apache.tika.io.TikaInputStream;
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.parser.AutoDetectParser;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.ocr.TesseractOCRConfig;
 import org.xml.sax.SAXException;
 import org.xml.sax.helpers.DefaultHandler;
 
@@ -196,8 +198,16 @@ public class ExtractMediaMetadata extends 
AbstractProcessor {
                                            Integer maxAttribLen) throws 
IOException, TikaException, SAXException {
         final Metadata metadata = new Metadata();
         final TikaInputStream tikaInputStream = 
TikaInputStream.get(sourceStream);
+
+        // Configure ParseContext to disable OCR - metadata extraction does 
not require OCR
+        // https://issues.apache.org/jira/browse/NIFI-15098
+        final TesseractOCRConfig ocrConfig = new TesseractOCRConfig();
+        ocrConfig.setSkipOcr(true);
+        final ParseContext parseContext = new ParseContext();
+        parseContext.set(TesseractOCRConfig.class, ocrConfig);
+
         try {
-            autoDetectParser.parse(tikaInputStream, new DefaultHandler(), 
metadata);
+            autoDetectParser.parse(tikaInputStream, new DefaultHandler(), 
metadata, parseContext);
         } finally {
             tikaInputStream.close();
         }