From e13cb1943939c94118f10f469e59908710c522ca Mon Sep 17 00:00:00 2001
From: Anthony Stirling <77850077+Frooodle@users.noreply.github.com.>
Date: Tue, 25 Mar 2025 13:35:34 +0000
Subject: [PATCH] revert OCR

---
 .../controller/api/misc/OCRController.java    | 51 ++++---------------
 1 file changed, 10 insertions(+), 41 deletions(-)

diff --git a/src/main/java/stirling/software/SPDF/controller/api/misc/OCRController.java b/src/main/java/stirling/software/SPDF/controller/api/misc/OCRController.java
index c69d328c3..059e1f011 100644
--- a/src/main/java/stirling/software/SPDF/controller/api/misc/OCRController.java
+++ b/src/main/java/stirling/software/SPDF/controller/api/misc/OCRController.java
@@ -9,11 +9,7 @@ import java.util.stream.Collectors;
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipOutputStream;
 
-import javax.imageio.IIOImage;
 import javax.imageio.ImageIO;
-import javax.imageio.ImageWriteParam;
-import javax.imageio.ImageWriter;
-import javax.imageio.stream.FileImageOutputStream;
 
 import org.apache.pdfbox.multipdf.PDFMergerUtility;
 import org.apache.pdfbox.pdmodel.PDDocument;
@@ -92,6 +88,7 @@ public class OCRController {
         Files.createDirectories(tempImagesDir);
         Process process = null;
         try {
+            // Save input file
             inputFile.transferTo(tempInputFile.toFile());
             PDFMergerUtility merger = new PDFMergerUtility();
             merger.setDestinationFileName(finalOutputFile.toString());
@@ -101,6 +98,7 @@ public class OCRController {
                 for (int pageNum = 0; pageNum < pageCount; pageNum++) {
                     PDPage page = document.getPage(pageNum);
                     boolean hasText = false;
+                    // Check for existing text
                     try (PDDocument tempDoc = new PDDocument()) {
                         tempDoc.addPage(page);
                         PDFTextStripper stripper = new PDFTextStripper();
@@ -115,42 +113,12 @@ public class OCRController {
                     Path pageOutputPath =
                             tempOutputDir.resolve(String.format("page_%d.pdf", pageNum));
                     if (shouldOcr) {
-                        // Render with lower DPI (200 instead of 300)
-                        BufferedImage image = pdfRenderer.renderImageWithDPI(pageNum, 200);
-
-                        // Convert to RGB to remove alpha channel if present
-                        if (image.getType() != BufferedImage.TYPE_INT_RGB) {
-                            BufferedImage rgbImage =
-                                    new BufferedImage(
-                                            image.getWidth(),
-                                            image.getHeight(),
-                                            BufferedImage.TYPE_INT_RGB);
-                            rgbImage.getGraphics().drawImage(image, 0, 0, null);
-                            image = rgbImage;
-                        }
-
-                        // Save as JPEG with compression
-                        String imageName = String.format("page_%d.jpg", pageNum);
-                        Path imagePath = tempImagesDir.resolve(imageName);
-
-                        Iterator<ImageWriter> writers = ImageIO.getImageWritersByFormatName("jpg");
-                        if (!writers.hasNext()) {
-                            throw new IllegalStateException("No JPG ImageWriter found");
-                        }
-                        ImageWriter writer = writers.next();
-                        ImageWriteParam params = writer.getDefaultWriteParam();
-                        params.setCompressionMode(ImageWriteParam.MODE_EXPLICIT);
-                        params.setCompressionQuality(0.7f); // Adjust quality here (0.7 = 70%)
-
-                        try (FileImageOutputStream output =
-                                new FileImageOutputStream(imagePath.toFile())) {
-                            writer.setOutput(output);
-                            writer.write(null, new IIOImage(image, null, null), params);
-                        } finally {
-                            writer.dispose();
-                        }
-
-                        // Build OCR command with JPG image
+                        // Convert page to image
+                        BufferedImage image = pdfRenderer.renderImageWithDPI(pageNum, 300);
+                        Path imagePath =
+                                tempImagesDir.resolve(String.format("page_%d.png", pageNum));
+                        ImageIO.write(image, "png", imagePath.toFile());
+                        // Build OCR command
                         List<String> command = new ArrayList<>();
                         command.add("tesseract");
                         command.add(imagePath.toString());
@@ -160,6 +128,7 @@ public class OCRController {
                                         .toString());
                         command.add("-l");
                         command.add(String.join("+", languages));
+                        // Always output PDF
                         command.add("pdf");
                         ProcessBuilder pb = new ProcessBuilder(command);
                         process = pb.start();
@@ -246,4 +215,4 @@ public class OCRController {
             log.error("Error walking directory {}: {}", directory, e.getMessage());
         }
     }
-}
+}
\ No newline at end of file