Author: lehmi
Date: Mon Apr 21 10:53:42 2025
New Revision: 1925195
URL: http://svn.apache.org/viewvc?rev=1925195&view=rev
Log:
PDFBOX-4668: avoid NPE due to a missing font name
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
URL:
http://svn.apache.org/viewvc/pdfbox/branches/2.0/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java?rev=1925195&r1=1925194&r2=1925195&view=diff
==============================================================================
---
pdfbox/branches/2.0/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java
(original)
+++
pdfbox/branches/2.0/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java
Mon Apr 21 10:53:42 2025
@@ -564,17 +564,10 @@ public class PDFTextStripper extends Leg
// Resets the average character width when we see a change in
font
// or a change in the font size
- if (lastPosition != null)
+ if (lastPosition != null
+ && hasFontOrSizeChanged(position,
lastPosition.getTextPosition()))
{
- TextPosition lastTextPosition =
lastPosition.getTextPosition();
- boolean fontHasChanged = !position.getFont().getName()
- .equals(lastTextPosition.getFont().getName());
- boolean fontSizeChanged =
Float.compare(position.getFontSize(),
- lastTextPosition.getFontSize()) != 0;
- if (fontHasChanged || fontSizeChanged)
- {
- previousAveCharWidth = -1;
- }
+ previousAveCharWidth = -1;
}
float positionX;
float positionY;
@@ -735,6 +728,38 @@ public class PDFTextStripper extends Leg
writePageEnd();
}
+ private boolean hasFontOrSizeChanged(TextPosition current, TextPosition
last)
+ {
+ if (last == null)
+ {
+ return false;
+ }
+ // compare font sizes
+ if (Float.compare(current.getFontSize(), last.getFontSize()) != 0)
+ {
+ return true;
+ }
+ // compare font instances, may not work if the resource cache is
disabled
+ if (current.getFont() == last.getFont())
+ {
+ return false;
+ }
+ String currentFontName = current.getFont().getName();
+ String lastFontName = last.getFont().getName();
+ if (currentFontName != null)
+ {
+ // compare font names
+ return !currentFontName.equals(lastFontName);
+ }
+ if (lastFontName != null)
+ {
+ // currentFontName is null but lastFontName isn't -> font changes
+ return true;
+ }
+ // both fonts don't have a name -> compare hashes
+ return current.getFont().hashCode() != last.getFont().hashCode();
+ }
+
private boolean overlap(float y1, float height1, float y2, float height2)
{
return within(y1, y2, .1f) || y2 <= y1 && y2 >= y1 - height1
