You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@pdfbox.apache.org by le...@apache.org on 2020/02/05 16:37:01 UTC
svn commit: r1873652 -
/pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java
Author: lehmi
Date: Wed Feb 5 16:37:01 2020
New Revision: 1873652
URL: http://svn.apache.org/viewvc?rev=1873652&view=rev
Log:
PDFBOX-4760: don't replace word separator as proposed by John Gesimondo
Modified:
pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java
Modified: pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java
URL: http://svn.apache.org/viewvc/pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java?rev=1873652&r1=1873651&r2=1873652&view=diff
==============================================================================
--- pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java (original)
+++ pdfbox/trunk/pdfbox/src/main/java/org/apache/pdfbox/text/PDFTextStripper.java Wed Feb 5 16:37:01 2020
@@ -633,10 +633,10 @@ public class PDFTextStripper extends Leg
}
// test if our TextPosition starts after a new word would be expected to start
if (Float.compare(expectedStartOfNextWordX, EXPECTED_START_OF_NEXT_WORD_X_RESET_VALUE) != 0
- && expectedStartOfNextWordX < positionX &&
- // only bother adding a space if the last character was not a space
- lastPosition.getTextPosition().getUnicode() != null
- && !lastPosition.getTextPosition().getUnicode().endsWith(" "))
+ && expectedStartOfNextWordX < positionX
+ // only bother adding a word separator if the last character was not a word separator
+ && lastPosition.getTextPosition().getUnicode() != null
+ && !lastPosition.getTextPosition().getUnicode().endsWith(wordSeparator))
{
line.add(LineItem.getWordSeparator());
}