print (WIP), fake scan (WIP) and text conversion for ultra-lite (#1098)

* Changes!

* lang

* fake scan init, print init and pdf to text for exe

* Hardening suggestions for Stirling-PDF / changes (#1099)

* Switch order of literals to prevent NullPointerException

* Introduced protections against predictable RNG abuse

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>

* Update README.md

* install custom fonts

* Formats etc

* version bump

* disable WIP work

* remove chinese font

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
Co-authored-by: systo <systo@host.docker.internal>

src/main/java/stirling/software/SPDF/SPdfApplication.java

@@ -62,6 +62,7 @@ public class SPdfApplication {
     }
 
     public static void main(String[] args) throws IOException, InterruptedException {
+
         SpringApplication app = new SpringApplication(SPdfApplication.class);
         app.addInitializers(new ConfigInitializer());
         if (Files.exists(Paths.get("configs/settings.yml"))) {

src/main/java/stirling/software/SPDF/config/EndpointConfiguration.java

@@ -146,7 +146,6 @@ public class EndpointConfiguration {
         addEndpointToGroup("CLI", "xlsx-to-pdf");
         addEndpointToGroup("CLI", "pdf-to-word");
         addEndpointToGroup("CLI", "pdf-to-presentation");
-        addEndpointToGroup("CLI", "pdf-to-text");
         addEndpointToGroup("CLI", "pdf-to-html");
         addEndpointToGroup("CLI", "pdf-to-xml");
         addEndpointToGroup("CLI", "ocr-pdf");
@@ -154,6 +153,7 @@ public class EndpointConfiguration {
         addEndpointToGroup("CLI", "url-to-pdf");
         addEndpointToGroup("CLI", "book-to-pdf");
         addEndpointToGroup("CLI", "pdf-to-book");
+        addEndpointToGroup("CLI", "pdf-to-rtf");
 
         // Calibre
         addEndpointToGroup("Calibre", "book-to-pdf");
@@ -175,7 +175,7 @@ public class EndpointConfiguration {
         addEndpointToGroup("LibreOffice", "xlsx-to-pdf");
         addEndpointToGroup("LibreOffice", "pdf-to-word");
         addEndpointToGroup("LibreOffice", "pdf-to-presentation");
-        addEndpointToGroup("LibreOffice", "pdf-to-text");
+        addEndpointToGroup("LibreOffice", "pdf-to-rtf");
         addEndpointToGroup("LibreOffice", "pdf-to-html");
         addEndpointToGroup("LibreOffice", "pdf-to-xml");
 
@@ -218,6 +218,7 @@ public class EndpointConfiguration {
         addEndpointToGroup("Java", "overlay-pdf");
         addEndpointToGroup("Java", "split-pdf-by-sections");
         addEndpointToGroup("Java", REMOVE_BLANKS);
+        addEndpointToGroup("Java", "pdf-to-text");
 
         // Javascript
         addEndpointToGroup("Javascript", "pdf-organizer");

src/main/java/stirling/software/SPDF/controller/api/converters/ConvertPDFToPDFA.java

@@ -31,7 +31,8 @@ public class ConvertPDFToPDFA {
             summary = "Convert a PDF to a PDF/A",
             description =
                     "This endpoint converts a PDF file to a PDF/A file. PDF/A is a format designed for long-term archiving of digital documents. Input:PDF Output:PDF Type:SISO")
-    public ResponseEntity<byte[]> pdfToPdfA(@ModelAttribute PdfToPdfARequest request) throws Exception {
+    public ResponseEntity<byte[]> pdfToPdfA(@ModelAttribute PdfToPdfARequest request)
+            throws Exception {
         MultipartFile inputFile = request.getFileInput();
         String outputFormat = request.getOutputFormat();
 

src/main/java/stirling/software/SPDF/controller/api/misc/FakeScanControllerWIP.java

@@ -1,27 +1,25 @@
 package stirling.software.SPDF.controller.api.misc;
 
+import java.awt.AlphaComposite;
 import java.awt.Color;
+import java.awt.GradientPaint;
+import java.awt.Graphics2D;
 import java.awt.geom.AffineTransform;
 import java.awt.image.AffineTransformOp;
 import java.awt.image.BufferedImage;
 import java.awt.image.BufferedImageOp;
 import java.awt.image.ConvolveOp;
 import java.awt.image.Kernel;
-import java.awt.image.RescaleOp;
 import java.io.ByteArrayOutputStream;
-import java.io.File;
 import java.io.IOException;
 import java.security.SecureRandom;
+import java.util.ArrayList;
+import java.util.List;
 import java.util.Random;
 
-import javax.imageio.ImageIO;
-
 import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
-import org.apache.pdfbox.pdmodel.PDPage;
-import org.apache.pdfbox.pdmodel.PDPageContentStream;
-import org.apache.pdfbox.pdmodel.common.PDRectangle;
-import org.apache.pdfbox.pdmodel.graphics.image.LosslessFactory;
+import org.apache.pdfbox.pdmodel.graphics.image.JPEGFactory;
 import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
 import org.apache.pdfbox.rendering.ImageType;
 import org.apache.pdfbox.rendering.PDFRenderer;
@@ -29,16 +27,17 @@ import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 import org.springframework.http.ResponseEntity;
 import org.springframework.web.bind.annotation.ModelAttribute;
+import org.springframework.web.bind.annotation.PostMapping;
 import org.springframework.web.bind.annotation.RequestMapping;
 import org.springframework.web.bind.annotation.RestController;
 import org.springframework.web.multipart.MultipartFile;
 
 import io.github.pixee.security.Filenames;
-import io.swagger.v3.oas.annotations.Hidden;
 import io.swagger.v3.oas.annotations.Operation;
 import io.swagger.v3.oas.annotations.tags.Tag;
 
 import stirling.software.SPDF.model.api.PDFFile;
+import stirling.software.SPDF.utils.PdfUtils;
 import stirling.software.SPDF.utils.WebResponseUtils;
 
 @RestController
@@ -48,98 +47,38 @@ public class FakeScanControllerWIP {
 
     private static final Logger logger = LoggerFactory.getLogger(FakeScanControllerWIP.class);
 
-    // TODO
-    @Hidden
-    // @PostMapping(consumes = "multipart/form-data", value = "/fakeScan")
-    @Operation(
-            summary = "Repair a PDF file",
-            description =
-                    "This endpoint repairs a given PDF file by running Ghostscript command. The PDF is first saved to a temporary location, repaired, read back, and then returned as a response.")
-    public ResponseEntity<byte[]> repairPdf(@ModelAttribute PDFFile request) throws IOException {
+    //TODO
+    //@PostMapping(consumes = "multipart/form-data", value = "/fake-scan")
+    //@Operation(
+    //        summary = "Repair a PDF file",
+    //        description =
+    //                "This endpoint repairs a given PDF file by running Ghostscript command. The PDF is first saved to a temporary location, repaired, read back, and then returned as a response.")
+    public ResponseEntity<byte[]> fakeScan(@ModelAttribute PDFFile request) throws IOException {
         MultipartFile inputFile = request.getFileInput();
 
+        // Load the PDF document
         PDDocument document = Loader.loadPDF(inputFile.getBytes());
-        PDFRenderer pdfRenderer = new PDFRenderer(document);
-        pdfRenderer.setSubsamplingAllowed(true);
-        for (int page = 0; page < document.getNumberOfPages(); ++page) {
-            BufferedImage image = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB);
-            ImageIO.write(image, "png", new File("scanned-" + (page + 1) + ".png"));
+        PDFRenderer renderer = new PDFRenderer(document);
+        List<BufferedImage> images = new ArrayList<>();
+        // Convert each page to an image
+        for (int i = 0; i < document.getNumberOfPages(); i++) {
+            BufferedImage image = renderer.renderImageWithDPI(i, 150, ImageType.GRAY);
+            images.add(processImage(image));
         }
         document.close();
 
-        // Constants
-        int scannedness = 90; // Value between 0 and 100
-        int dirtiness = 0; // Value between 0 and 100
-
-        // Load the source image
-        BufferedImage sourceImage = ImageIO.read(new File("scanned-1.png"));
-
-        // Create the destination image
-        BufferedImage destinationImage =
-                new BufferedImage(
-                        sourceImage.getWidth(), sourceImage.getHeight(), sourceImage.getType());
-
-        // Apply a brightness and contrast effect based on the "scanned-ness"
-        float scaleFactor = 1.0f + (scannedness / 100.0f) * 0.5f; // Between 1.0 and 1.5
-        float offset = scannedness * 1.5f; // Between 0 and 150
-        BufferedImageOp op = new RescaleOp(scaleFactor, offset, null);
-        op.filter(sourceImage, destinationImage);
-
-        // Apply a rotation effect
-        double rotationRequired =
-                Math.toRadians(
-                        (new SecureRandom().nextInt(3 - 1)
-                                + 1)); // Random angle between 1 and 3 degrees
-        double locationX = destinationImage.getWidth() / 2;
-        double locationY = destinationImage.getHeight() / 2;
-        AffineTransform tx =
-                AffineTransform.getRotateInstance(rotationRequired, locationX, locationY);
-        AffineTransformOp rotateOp = new AffineTransformOp(tx, AffineTransformOp.TYPE_BILINEAR);
-        destinationImage = rotateOp.filter(destinationImage, null);
-
-        // Apply a blur effect based on the "scanned-ness"
-        float blurIntensity = scannedness / 100.0f * 0.2f; // Between 0.0 and 0.2
-        float[] matrix = {
-            blurIntensity, blurIntensity, blurIntensity,
-            blurIntensity, blurIntensity, blurIntensity,
-            blurIntensity, blurIntensity, blurIntensity
-        };
-        BufferedImageOp blurOp =
-                new ConvolveOp(new Kernel(3, 3, matrix), ConvolveOp.EDGE_NO_OP, null);
-        destinationImage = blurOp.filter(destinationImage, null);
-
-        // Add noise to the image based on the "dirtiness"
-        Random random = new SecureRandom();
-        for (int y = 0; y < destinationImage.getHeight(); y++) {
-            for (int x = 0; x < destinationImage.getWidth(); x++) {
-                if (random.nextInt(100) < dirtiness) {
-                    // Change the pixel color to black randomly based on the "dirtiness"
-                    destinationImage.setRGB(x, y, Color.BLACK.getRGB());
-                }
-            }
-        }
-
-        // Save the image
-        ImageIO.write(destinationImage, "PNG", new File("scanned-1.png"));
-
-        PDDocument documentOut = new PDDocument();
-        for (int page = 1; page <= document.getNumberOfPages(); ++page) {
-            BufferedImage bim = ImageIO.read(new File("scanned-" + page + ".png"));
-
-            // Adjust the dimensions of the page
-            PDPage pdPage = new PDPage(new PDRectangle(bim.getWidth() - 1, bim.getHeight() - 1));
-            documentOut.addPage(pdPage);
-
-            PDImageXObject pdImage = LosslessFactory.createFromImage(documentOut, bim);
-            PDPageContentStream contentStream = new PDPageContentStream(documentOut, pdPage);
-
-            // Draw the image with a slight offset and enlarged dimensions
-            contentStream.drawImage(pdImage, -1, -1, bim.getWidth() + 2, bim.getHeight() + 2);
-            contentStream.close();
-        }
+        // Create a new PDF document with the processed images
         ByteArrayOutputStream baos = new ByteArrayOutputStream();
-        documentOut.save(baos);
-        documentOut.close();
+        PDDocument newDocument = new PDDocument();
+        for (BufferedImage img : images) {
+            // PDPageContentStream contentStream = new PDPageContentStream(newDocument, new
+            // PDPage());
+            PDImageXObject pdImage = JPEGFactory.createFromImage(newDocument, img);
+            PdfUtils.addImageToDocument(newDocument, pdImage, "maintainAspectRatio", false);
+        }
+
+        newDocument.save(baos);
+        newDocument.close();
 
         // Return the optimized PDF as a response
         String outputFilename =
@@ -148,4 +87,164 @@ public class FakeScanControllerWIP {
                         + "_scanned.pdf";
         return WebResponseUtils.boasToWebResponse(baos, outputFilename);
     }
+
+    public BufferedImage processImage(BufferedImage image) {
+        // Rotation
+
+        image = rotate(image);
+        // image = softenEdges(image, 5);
+        image = applyGaussianBlur(image, 0.5);
+        addGaussianNoise(image, 0.25);
+        image = linearStretch(image);
+
+        return image;
+    }
+
+    private BufferedImage rotate(BufferedImage image) {
+
+        double rotationRequired = Math.toRadians(1.0);
+        double locationX = image.getWidth() / 2;
+        double locationY = image.getHeight() / 2;
+        AffineTransform tx =
+                AffineTransform.getRotateInstance(rotationRequired, locationX, locationY);
+        AffineTransformOp op = new AffineTransformOp(tx, AffineTransformOp.TYPE_BICUBIC);
+        return op.filter(image, null);
+    }
+
+    private BufferedImage applyGaussianBlur(BufferedImage image, double sigma) {
+        int radius = 3; // Fixed radius size for simplicity
+
+        int size = 2 * radius + 1;
+        float[] data = new float[size * size];
+        double sum = 0.0;
+
+        for (int i = -radius; i <= radius; i++) {
+            for (int j = -radius; j <= radius; j++) {
+                double xDistance = i * i;
+                double yDistance = j * j;
+                double g = Math.exp(-(xDistance + yDistance) / (2 * sigma * sigma));
+                data[(i + radius) * size + j + radius] = (float) g;
+                sum += g;
+            }
+        }
+
+        // Normalize the kernel
+        for (int i = 0; i < data.length; i++) {
+            data[i] /= sum;
+        }
+
+        Kernel kernel = new Kernel(size, size, data);
+        BufferedImageOp op = new ConvolveOp(kernel, ConvolveOp.EDGE_NO_OP, null);
+        return op.filter(image, null);
+    }
+
+    public BufferedImage softenEdges(BufferedImage image, int featherRadius) {
+        int width = image.getWidth();
+        int height = image.getHeight();
+        BufferedImage output = new BufferedImage(width, height, BufferedImage.TYPE_INT_ARGB);
+
+        Graphics2D g2 = output.createGraphics();
+        g2.drawImage(image, 0, 0, null);
+        g2.setComposite(AlphaComposite.DstIn);
+        g2.setPaint(
+                new GradientPaint(
+                        0, 0, new Color(0, 0, 0, 1f), 0, featherRadius, new Color(0, 0, 0, 0f)));
+        g2.fillRect(0, 0, width, featherRadius); // top edge
+        g2.setPaint(
+                new GradientPaint(
+                        0,
+                        height - featherRadius,
+                        new Color(0, 0, 0, 0f),
+                        0,
+                        height,
+                        new Color(0, 0, 0, 1f)));
+        g2.fillRect(0, height - featherRadius, width, featherRadius); // bottom edge
+        g2.setPaint(
+                new GradientPaint(
+                        0, 0, new Color(0, 0, 0, 1f), featherRadius, 0, new Color(0, 0, 0, 0f)));
+        g2.fillRect(0, 0, featherRadius, height); // left edge
+        g2.setPaint(
+                new GradientPaint(
+                        width - featherRadius,
+                        0,
+                        new Color(0, 0, 0, 0f),
+                        width,
+                        0,
+                        new Color(0, 0, 0, 1f)));
+        g2.fillRect(width - featherRadius, 0, featherRadius, height); // right edge
+        g2.dispose();
+
+        return output;
+    }
+
+    private void addGaussianNoise(BufferedImage image, double strength) {
+        Random rand = new SecureRandom();
+        int width = image.getWidth();
+        int height = image.getHeight();
+
+        for (int i = 0; i < width; i++) {
+            for (int j = 0; j < height; j++) {
+                int rgba = image.getRGB(i, j);
+                int alpha = (rgba >> 24) & 0xff;
+                int red = (rgba >> 16) & 0xff;
+                int green = (rgba >> 8) & 0xff;
+                int blue = rgba & 0xff;
+
+                // Apply Gaussian noise
+                red = (int) (red + rand.nextGaussian() * strength);
+                green = (int) (green + rand.nextGaussian() * strength);
+                blue = (int) (blue + rand.nextGaussian() * strength);
+
+                // Clamping values to the 0-255 range
+                red = Math.min(Math.max(0, red), 255);
+                green = Math.min(Math.max(0, green), 255);
+                blue = Math.min(Math.max(0, blue), 255);
+
+                image.setRGB(i, j, (alpha << 24) | (red << 16) | (green << 8) | blue);
+            }
+        }
+    }
+
+    public BufferedImage linearStretch(BufferedImage image) {
+        int width = image.getWidth();
+        int height = image.getHeight();
+        int min = 255;
+        int max = 0;
+
+        // First pass: find the min and max grayscale values
+        for (int y = 0; y < height; y++) {
+            for (int x = 0; x < width; x++) {
+                int rgb = image.getRGB(x, y);
+                int gray =
+                        (int)
+                                (((rgb >> 16) & 0xff) * 0.299
+                                        + ((rgb >> 8) & 0xff) * 0.587
+                                        + (rgb & 0xff) * 0.114); // Convert to grayscale
+                if (gray < min) min = gray;
+                if (gray > max) max = gray;
+            }
+        }
+
+        // Second pass: stretch the histogram
+        for (int y = 0; y < height; y++) {
+            for (int x = 0; x < width; x++) {
+                int rgb = image.getRGB(x, y);
+                int alpha = (rgb >> 24) & 0xff;
+                int red = (rgb >> 16) & 0xff;
+                int green = (rgb >> 8) & 0xff;
+                int blue = rgb & 0xff;
+
+                // Apply linear stretch to each channel
+                red = (int) (((red - min) / (float) (max - min)) * 255);
+                green = (int) (((green - min) / (float) (max - min)) * 255);
+                blue = (int) (((blue - min) / (float) (max - min)) * 255);
+
+                // Set new RGB value maintaining the alpha channel
+                rgb = (alpha << 24) | (red << 16) | (green << 8) | blue;
+                image.setRGB(x, y, rgb);
+            }
+        }
+
+        return image;
+    }
 }

src/main/java/stirling/software/SPDF/controller/api/misc/PrintFileController.java

@@ -0,0 +1,106 @@
+package stirling.software.SPDF.controller.api.misc;
+
+import java.awt.Graphics;
+import java.awt.Graphics2D;
+import java.awt.image.BufferedImage;
+import java.awt.print.PageFormat;
+import java.awt.print.Printable;
+import java.awt.print.PrinterException;
+import java.awt.print.PrinterJob;
+import java.io.IOException;
+import java.util.Arrays;
+
+import javax.imageio.ImageIO;
+import javax.print.PrintService;
+import javax.print.PrintServiceLookup;
+
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.printing.PDFPageable;
+import org.springframework.http.HttpStatus;
+import org.springframework.http.ResponseEntity;
+import org.springframework.web.bind.annotation.ModelAttribute;
+import org.springframework.web.bind.annotation.PostMapping;
+import org.springframework.web.bind.annotation.RequestMapping;
+import org.springframework.web.bind.annotation.RestController;
+import org.springframework.web.multipart.MultipartFile;
+
+import io.swagger.v3.oas.annotations.Operation;
+import io.swagger.v3.oas.annotations.tags.Tag;
+
+import stirling.software.SPDF.model.api.misc.PrintFileRequest;
+
+@RestController
+@RequestMapping("/api/v1/misc")
+@Tag(name = "Misc", description = "Miscellaneous APIs")
+public class PrintFileController {
+
+	//TODO
+    //@PostMapping(value = "/print-file", consumes = "multipart/form-data")
+    //@Operation(
+    //        summary = "Prints PDF/Image file to a set printer",
+    //        description =
+    //                "Input of PDF or Image along with a printer name/URL/IP to match against to send it to (Fire and forget) Input:Any Output:N/A Type:SISO")
+    public ResponseEntity<String> printFile(@ModelAttribute PrintFileRequest request)
+            throws IOException {
+        MultipartFile file = request.getFileInput();
+        String printerName = request.getPrinterName();
+        String contentType = file.getContentType();
+        try {
+            // Find matching printer
+            PrintService[] services = PrintServiceLookup.lookupPrintServices(null, null);
+            PrintService selectedService =
+                    Arrays.stream(services)
+                            .filter(
+                                    service ->
+                                            service.getName().toLowerCase().contains(printerName))
+                            .findFirst()
+                            .orElseThrow(
+                                    () ->
+                                            new IllegalArgumentException(
+                                                    "No matching printer found"));
+
+            System.out.println("Selected Printer: " + selectedService.getName());
+
+            if ("application/pdf".equals(contentType)) {
+                PDDocument document = Loader.loadPDF(file.getBytes());
+                PrinterJob job = PrinterJob.getPrinterJob();
+                job.setPrintService(selectedService);
+                job.setPageable(new PDFPageable(document));
+                job.print();
+                document.close();
+            } else if (contentType.startsWith("image/")) {
+                BufferedImage image = ImageIO.read(file.getInputStream());
+                PrinterJob job = PrinterJob.getPrinterJob();
+                job.setPrintService(selectedService);
+                job.setPrintable(
+                        new Printable() {
+                            public int print(
+                                    Graphics graphics, PageFormat pageFormat, int pageIndex)
+                                    throws PrinterException {
+                                if (pageIndex != 0) {
+                                    return NO_SUCH_PAGE;
+                                }
+                                Graphics2D g2d = (Graphics2D) graphics;
+                                g2d.translate(
+                                        pageFormat.getImageableX(), pageFormat.getImageableY());
+                                g2d.drawImage(
+                                        image,
+                                        0,
+                                        0,
+                                        (int) pageFormat.getImageableWidth(),
+                                        (int) pageFormat.getImageableHeight(),
+                                        null);
+                                return PAGE_EXISTS;
+                            }
+                        });
+                job.print();
+            }
+            return new ResponseEntity<>(
+                    "File printed successfully to " + selectedService.getName(), HttpStatus.OK);
+        } catch (Exception e) {
+            System.err.println("Failed to print: " + e.getMessage());
+            return new ResponseEntity<>(e.getMessage(), HttpStatus.BAD_REQUEST);
+        }
+    }
+}

src/main/java/stirling/software/SPDF/controller/web/OtherWebController.java

@@ -54,6 +54,13 @@ public class OtherWebController {
         return "misc/add-page-numbers";
     }
 
+    @GetMapping("/fake-scan")
+    @Hidden
+    public String fakeScanForm(Model model) {
+        model.addAttribute("currentPage", "fake-scan");
+        return "misc/fake-scan";
+    }
+
     @GetMapping("/extract-images")
     @Hidden
     public String extractImagesForm(Model model) {
@@ -82,6 +89,13 @@ public class OtherWebController {
         return "misc/compare";
     }
 
+    @GetMapping("/print-file")
+    @Hidden
+    public String printFileForm(Model model) {
+        model.addAttribute("currentPage", "print-file");
+        return "misc/print-file";
+    }
+
     public List<String> getAvailableTesseractLanguages() {
         String tessdataDir = "/usr/share/tessdata";
         File[] files = new File(tessdataDir).listFiles();

src/main/java/stirling/software/SPDF/model/api/misc/PrintFileRequest.java

@@ -0,0 +1,15 @@
+package stirling.software.SPDF.model.api.misc;
+
+import io.swagger.v3.oas.annotations.media.Schema;
+
+import lombok.Data;
+import lombok.EqualsAndHashCode;
+import stirling.software.SPDF.model.api.PDFFile;
+
+@Data
+@EqualsAndHashCode(callSuper = true)
+public class PrintFileRequest extends PDFFile {
+
+    @Schema(description = "Name of printer to match against", required = true)
+    private String printerName;
+}

src/main/java/stirling/software/SPDF/utils/PdfUtils.java

@@ -336,7 +336,7 @@ public class PdfUtils {
         }
     }
 
-    private static void addImageToDocument(
+    public static void addImageToDocument(
             PDDocument doc, PDImageXObject image, String fitOption, boolean autoRotate)
             throws IOException {
         boolean imageIsLandscape = image.getWidth() > image.getHeight();