This is an automated email from the ASF dual-hosted git repository.
THausherr pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new 1a8b2efd59 TIKA-4853: DWGReadParser emits the drawing thumbnail as
THUMBNAIL (#3092)
1a8b2efd59 is described below
commit 1a8b2efd59f5322671c9b922fd23b932b7af46eb
Author: Dominik Schmidt <[email protected]>
AuthorDate: Sat Aug 29 18:05:44 2026 +0200
TIKA-4853: DWGReadParser emits the drawing thumbnail as THUMBNAIL (#3092)
* TIKA-4853 - the DWG thumbnail is a THUMBNAIL embedded document
The THUMBNAILIMAGE section is the drawing's preview image, not a picture
placed in the drawing, so mark it THUMBNAIL like the preview image of the
other container formats.
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI
<[email protected]>
---------
Co-authored-by: Tilman Hausherr <[email protected]>
Co-authored-by: Copilot Autofix powered by AI
<[email protected]>
---
CHANGES.txt | 3 +++
.../src/main/java/org/apache/tika/parser/dwg/DWGReadParser.java | 3 ++-
.../src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java | 7 ++++---
3 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/CHANGES.txt b/CHANGES.txt
index fdb00f6e76..0f1671eea3 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -1,5 +1,8 @@
Release 4.1.0 - unreleased
+ * DWGReadParser emits the drawing's THUMBNAILIMAGE as a THUMBNAIL embedded
+ document instead of INLINE (TIKA-4853).
+
* EpubParser emits the cover image named by the OPF (the EPUB 3
cover-image manifest property, or the EPUB 2 cover meta) as a THUMBNAIL
embedded document (TIKA-4852).
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/main/java/org/apache/tika/parser/dwg/DWGReadParser.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/main/java/org/apache/tika/parser/dwg/DWGReadParser.java
index ec048699a1..dd14afcad1 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/main/java/org/apache/tika/parser/dwg/DWGReadParser.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/main/java/org/apache/tika/parser/dwg/DWGReadParser.java
@@ -416,8 +416,9 @@ public class DWGReadParser extends AbstractDWGParser {
EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
Metadata embeddedMetadata = new Metadata();
embeddedMetadata.set(TikaCoreProperties.RESOURCE_NAME_KEY,
"thumbnail");
+ // The drawing's preview image, not a picture placed in the drawing
embeddedMetadata.set(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE,
- TikaCoreProperties.EmbeddedResourceType.INLINE.toString());
+ TikaCoreProperties.EmbeddedResourceType.THUMBNAIL.toString());
if (!embeddedDocumentExtractor.shouldParseEmbedded(embeddedMetadata,
context)) {
return;
}
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java
index 479292c903..bf8cbd7452 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/test/java/org/apache/tika/parser/dwg/DWGParserTest.java
@@ -276,16 +276,17 @@ public class DWGParserTest extends TikaTest {
assertNotNull(root.get(DWG.APPLICATION_COMMENT));
assertContains("AutoCAD", root.get(DWG.PRODUCT_INFO));
- // Thumbnail embedded as INLINE
+ // the THUMBNAILIMAGE section is the drawing's THUMBNAIL embedded
document
Metadata thumb = null;
for (int i = 1; i < metadataList.size(); i++) {
String type =
metadataList.get(i).get(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE);
- if
(TikaCoreProperties.EmbeddedResourceType.INLINE.name().equals(type)) {
+ if
(TikaCoreProperties.EmbeddedResourceType.THUMBNAIL.name().equals(type)) {
thumb = metadataList.get(i);
break;
}
}
- assertNotNull(thumb, "Expected an INLINE thumbnail attachment");
+ assertNotNull(thumb, "Expected a THUMBNAIL embedded document");
+ assertEquals("thumbnail",
thumb.get(TikaCoreProperties.RESOURCE_NAME_KEY));
}
@Test