You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@pdfbox.apache.org by ti...@apache.org on 2026/01/13 11:46:41 UTC

svn commit: r1931287 - pdfbox/branches/2.0/pdfbox/src/main/java/org/apache/pdfbox/text

Author: tilman
Date: Tue Jan 13 11:46:41 2026
New Revision: 1931287

Log:
PDFBOX-6145: move content check after page number check so that not all pages get checked

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	Tue Jan 13 10:04:11 2026	(r1931286)
+++ pdfbox/branches/2.0/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java	Tue Jan 13 11:46:41 2026	(r1931287)
@@ -302,10 +302,7 @@ public class PDFTextStripper extends Leg
 
         for (PDPage page : pages)
         {
-            if (page.hasContents())
-            {
-                processPage(page);
-            }
+            processPage(page);
             currentPageNo++;
         }
     }
@@ -347,6 +344,10 @@ public class PDFTextStripper extends Leg
                 && (startBookmarkPageNumber == -1 || currentPageNo >= startBookmarkPageNumber)
                 && (endBookmarkPageNumber == -1 || currentPageNo <= endBookmarkPageNumber))
         {
+            if (!page.hasContents())
+            {
+                return;
+            }
             startPage(page);
 
             int numberOfArticleSections = 1;