This is an automated email from the ASF dual-hosted git repository.
tilman 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 eea624dd4 TIKA-4311: simplify
eea624dd4 is described below
commit eea624dd4aff7dd0261c4975fa30ee73a06e36ba
Author: Tilman Hausherr <[email protected]>
AuthorDate: Wed Sep 18 08:48:08 2024 +0200
TIKA-4311: simplify
---
.../java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTML.java | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTML.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTML.java
index e5627911c..d12e18c81 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTML.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFMarkedContent2XHTML.java
@@ -37,7 +37,6 @@ import org.apache.pdfbox.cos.COSObject;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageTree;
-import
org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDObjectReference;
import
org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDStructureTreeRoot;
import
org.apache.pdfbox.pdmodel.documentinterchange.markedcontent.PDMarkedContent;
import org.apache.pdfbox.text.PDFMarkedContentExtractor;
@@ -281,9 +280,8 @@ public class PDFMarkedContent2XHTML extends PDF2XHTML {
// and maybe dereference COSObject first, i.e. before the first
"if"?
COSDictionary dict = (COSDictionary) ((COSObject)
kids).getObject();
COSName type = dict.getCOSName(COSName.TYPE);
- if (COSName.getPDFName(PDObjectReference.TYPE).equals(type)) //
OBJR
- {
- recurse(dict.getDictionaryObject(COSName.OBJ),
currentPageRef,depth + 1, paragraphs,
+ if (COSName.OBJR.equals(type)) {
+ recurse(dict.getDictionaryObject(COSName.OBJ), currentPageRef,
depth + 1, paragraphs,
roleMap);
}