Author: tilman
Date: Wed Jan 14 12:30:12 2026
New Revision: 1931311

Log:
PDFBOX-6145: revert last change because it breaks tika with pages that have no 
contents but have annotations

Modified:
   
pdfbox/branches/2.0/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java

Modified: 
pdfbox/branches/2.0/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java
==============================================================================
--- 
pdfbox/branches/2.0/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java
        Wed Jan 14 10:30:56 2026        (r1931310)
+++ 
pdfbox/branches/2.0/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java
        Wed Jan 14 12:30:12 2026        (r1931311)
@@ -302,7 +302,10 @@ public class PDFTextStripper extends Leg
 
         for (PDPage page : pages)
         {
-            processPage(page);
+            if (page.hasContents())
+            {
+                processPage(page);
+            }
             currentPageNo++;
         }
     }
@@ -344,10 +347,6 @@ public class PDFTextStripper extends Leg
                 && (startBookmarkPageNumber == -1 || currentPageNo >= 
startBookmarkPageNumber)
                 && (endBookmarkPageNumber == -1 || currentPageNo <= 
endBookmarkPageNumber))
         {
-            if (!page.hasContents())
-            {
-                return;
-            }
             startPage(page);
 
             int numberOfArticleSections = 1;

Reply via email to