Fixed missing whitespaces
This commit is contained in:
parent
42f08194fd
commit
35dec94ccd
@ -46,6 +46,17 @@ public class PDFAreaTextStripper extends PDFTextStripperByArea {
|
|||||||
startIndex = i;
|
startIndex = i;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
if (textPositions.get(i).getRotation() == 0 && i > 0 && textPositions.get(i).getX() > textPositions.get(i - 1).getEndX() + 1) {
|
||||||
|
List<TextPosition> sublist = textPositions.subList(startIndex, i);
|
||||||
|
if (!(sublist.isEmpty() || sublist.size() == 1 && (sublist.get(0)
|
||||||
|
.getUnicode()
|
||||||
|
.equals(" ") || sublist.get(0).getUnicode().equals("\u00A0")))) {
|
||||||
|
textPositionSequences.add(new TextPositionSequence(sublist, pageNumber));
|
||||||
|
}
|
||||||
|
startIndex = i;
|
||||||
|
}
|
||||||
|
|
||||||
if (i > 0 && (textPositions.get(i).getUnicode().equals(" ") || textPositions.get(i)
|
if (i > 0 && (textPositions.get(i).getUnicode().equals(" ") || textPositions.get(i)
|
||||||
.getUnicode()
|
.getUnicode()
|
||||||
.equals("\u00A0")) && i <= textPositions.size() - 2) {
|
.equals("\u00A0")) && i <= textPositions.size() - 2) {
|
||||||
|
|||||||
@ -300,6 +300,18 @@ public class PDFLinesTextStripper extends PDFTextStripper {
|
|||||||
startIndex = i;
|
startIndex = i;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
if (textPositions.get(i).getRotation() == 0 && i > 0 && textPositions.get(i).getX() > textPositions.get(i - 1).getEndX() + 1) {
|
||||||
|
List<TextPosition> sublist = textPositions.subList(startIndex, i);
|
||||||
|
if (!(sublist.isEmpty() || sublist.size() == 1 && (sublist.get(0)
|
||||||
|
.getUnicode()
|
||||||
|
.equals(" ") || sublist.get(0).getUnicode().equals("\u00A0")))) {
|
||||||
|
textPositionSequences.add(new TextPositionSequence(sublist, pageNumber));
|
||||||
|
}
|
||||||
|
startIndex = i;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
if (i > 0 && (textPositions.get(i).getUnicode().equals(" ") || textPositions.get(i)
|
if (i > 0 && (textPositions.get(i).getUnicode().equals(" ") || textPositions.get(i)
|
||||||
.getUnicode()
|
.getUnicode()
|
||||||
.equals("\u00A0")) && i <= textPositions.size() - 2) {
|
.equals("\u00A0")) && i <= textPositions.size() - 2) {
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user