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

THausherr · THausherr · commit ac86541fa943 · 2026-01-13T11:46:49.000Z
git-svn-id: https://svn.apache.org/repos/asf/pdfbox/trunk@1931289 13f79535-47bb-0310-9956-ffa450edef68
diff --git a/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java b/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java
@@ -298,10 +298,7 @@ protected void processPages(PDPageTree pages) throws IOException
 
         for (PDPage page : pages)
         {
-            if (page.hasContents())
-            {
-                processPage(page);
-            }
+            processPage(page);
             currentPageNo++;
         }
     }
@@ -343,6 +340,10 @@ public void processPage(PDPage page) throws IOException
                 && (startBookmarkPageNumber == -1 || currentPageNo >= startBookmarkPageNumber)
                 && (endBookmarkPageNumber == -1 || currentPageNo <= endBookmarkPageNumber))
         {
+            if (!page.hasContents())
+            {
+                return;
+            }
             startPage(page);
 
             int numberOfArticleSections = 1;

Original file line number	Diff line number	Diff line change
`@@ -298,10 +298,7 @@ protected void processPages(PDPageTree pages) throws IOException`
`298`	`298`
`299`	`299`	`for (PDPage page : pages)`
`300`	`300`	`{`
`301`		`- if (page.hasContents())`
`302`		`- {`
`303`		`- processPage(page);`
`304`		`- }`
	`301`	`+ processPage(page);`
`305`	`302`	`currentPageNo++;`
`306`	`303`	`}`
`307`	`304`	`}`
`@@ -343,6 +340,10 @@ public void processPage(PDPage page) throws IOException`
`343`	`340`	`&& (startBookmarkPageNumber == -1 \|\| currentPageNo >= startBookmarkPageNumber)`
`344`	`341`	`&& (endBookmarkPageNumber == -1 \|\| currentPageNo <= endBookmarkPageNumber))`
`345`	`342`	`{`
	`343`	`+ if (!page.hasContents())`
	`344`	`+ {`
	`345`	`+ return;`
	`346`	`+ }`
`346`	`347`	`startPage(page);`
`347`	`348`
`348`	`349`	`int numberOfArticleSections = 1;`