Files
fil/docs/snippets/java/ocr/ocr_elements.md
Henrik Jess Nielsen b4c07d3693
All checks were successful
Deploy fil (kreuzberg) / deploy (push) Successful in 49s
Nomad changes
2026-06-01 23:40:55 +02:00

39 lines
1.4 KiB
Markdown

```java title="Java"
import dev.kreuzberg.Kreuzberg;
import dev.kreuzberg.ExtractionResult;
import dev.kreuzberg.KreuzbergException;
import dev.kreuzberg.ExtractionConfig;
import dev.kreuzberg.OcrConfig;
import dev.kreuzberg.types.OcrElement;
import java.io.IOException;
public class Main {
public static void main(String[] args) {
try {
ExtractionConfig config = ExtractionConfig.builder()
.ocr(OcrConfig.builder()
.backend("paddle-ocr")
.language("en")
.build())
.build();
ExtractionResult result = Kreuzberg.extractFile("scanned.pdf", config);
if (result.getOcrElements() != null) {
for (OcrElement element : result.getOcrElements()) {
System.out.printf("Text: %s%n", element.getText());
System.out.printf("Confidence: %.2f%n", element.getConfidence().getRecognition());
System.out.printf("Geometry: %s%n", element.getGeometry());
if (element.getRotation() != null) {
System.out.printf("Rotation: %.1f°%n", element.getRotation().getAngle());
}
System.out.println();
}
}
} catch (IOException | KreuzbergException e) {
System.err.println("Extraction failed: " + e.getMessage());
}
}
}
```