(tika) branch main updated: TIKA-4311: replace getItem() where possible

[tilman]

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 e9f1c8264 TIKA-4311: replace getItem() where possible
e9f1c8264 is described below

commit e9f1c8264aa3629c0a3c743a2540e9bc8d20ce82
Author: Tilman Hausherr <til...@apache.org>
AuthorDate: Tue Sep 17 18:06:29 2024 +0200

    TIKA-4311: replace getItem() where possible
---
 .../org/apache/tika/parser/pdf/PDFMarkedContent2XHTML.java   | 12 ++++++------
 1 file changed, 6 insertions(+), 6 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 bb65d294c..1c670f866 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
@@ -185,7 +185,7 @@ public class PDFMarkedContent2XHTML extends PDF2XHTML {
                             continue;
                         }
                         if (((COSDictionary) 
kidbase).containsKey(COSName.KIDS)) {
-                            findPages(((COSDictionary) 
kidbase).getItem(COSName.KIDS), pageRefs);
+                            findPages(((COSDictionary) 
kidbase).getDictionaryObject(COSName.KIDS), pageRefs);
                         }
                     }
                 }
@@ -202,7 +202,7 @@ public class PDFMarkedContent2XHTML extends PDF2XHTML {
 
         List<ObjectRef> pageRefs = new ArrayList<>();
         //STEP 1: get the page refs
-        findPages(pdDocument.getPages().getCOSObject().getItem(COSName.KIDS), 
pageRefs);
+        
findPages(pdDocument.getPages().getCOSObject().getDictionaryObject(COSName.KIDS),
 pageRefs);
         //confirm the right number of pages was found
         if (pageRefs.size() != pdDocument.getNumberOfPages()) {
             throw new IOException(new TikaException(
@@ -288,9 +288,9 @@ public class PDFMarkedContent2XHTML extends PDF2XHTML {
                         roleMap);
             }
 
-            COSBase n = dict.getItem(COSName.S);
+            COSName n = dict.getCOSName(COSName.S);
             String name = "";
-            if (n instanceof COSName) {
+            if (n != null) {
                 name = ((COSName) n).getName();
             }
             COSBase grandkids = dict.getItem(COSName.K);
@@ -300,8 +300,8 @@ public class PDFMarkedContent2XHTML extends PDF2XHTML {
             COSBase pageBase = dict.getItem(COSName.PG);
 
             if (pageBase instanceof COSObject) {
-                currentPageRef = new ObjectRef(((COSObject) 
pageBase).getObjectNumber(),
-                        ((COSObject) pageBase).getGenerationNumber());
+                currentPageRef = new ObjectRef(((COSObject) 
pageBase).getKey().getNumber(),
+                        ((COSObject) pageBase).getKey().getGeneration());
             }
 
             HtmlTag tag = getTag(name, roleMap);