Marmelator/redaction-service
1
0
Fork 0
Code Issues Pull Requests 14 Actions Packages Projects Releases 622 Wiki Activity

DM-307: Fixed applyWithLineBreaks

Browse Source
This commit is contained in:
deiflaender 2023-07-06 15:24:51 +02:00
parent a1ebcc2abf
commit 210186bfd7
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/layoutparsing/document/graph/textblock/AtomicTextBlock.java
View File

@ -7,7 +7,6 @@ import java.util.Arrays;
import java.util.Collection;
import java.util.Collections;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;
@ -210,14 +209,16 @@ public class AtomicTextBlock implements TextBlock {
return "";
}
CharSequence subSequence = subSequence(boundary);
Set<Integer> lbInBoundary = new HashSet<>(lineBreaks);
Set<Integer> lbInBoundary = lineBreaks.stream()
.map(i -> i+ boundary.start())
.filter(boundary::contains)
.collect(Collectors.toSet());
if (boundary.end() == getBoundary().end()) {
lbInBoundary.add(getBoundary().length());
}
StringBuilder sb = new StringBuilder();
for (int i = 0; i < subSequence.length(); i++) {
char character = subSequence.charAt(i);
for (int i = boundary.start(); i < boundary.end(); i++) {
char character = this.charAt(i);
if (lbInBoundary.contains(i + 1)) {
// always plus one, due to the linebreaks being an exclusive end index
if (!Character.isWhitespace(character)) {