javier/Stirling-PDF
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

dummy lang changes

Browse Source
This commit is contained in:
Anthony Stirling
2023-06-04 22:40:14 +01:00
parent b8fa278173
commit 4f851156b7
19 changed files with 585 additions and 173 deletions
Download Patch File Download Diff File Expand all files Collapse all files

312
src/main/java/stirling/software/SPDF/controller/api/ScalePagesController.java
View File

@@ -35,10 +35,12 @@ import com.itextpdf.kernel.pdf.canvas.parser.data.TextRenderInfo;
import com.itextpdf.kernel.pdf.canvas.parser.listener.IEventListener;
import com.itextpdf.kernel.pdf.xobject.PdfFormXObject;
import io.swagger.v3.oas.annotations.Hidden;
import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.Parameter;
import io.swagger.v3.oas.annotations.media.Schema;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
public class ScalePagesController {
@@ -47,48 +49,51 @@ public class ScalePagesController {
@PostMapping(value = "/scale-pages", consumes = "multipart/form-data")
@Operation(summary = "Change the size of a PDF page/document", description = "This operation takes an input PDF file and the size to scale the pages to in the output PDF file.")
public ResponseEntity<byte[]> scalePages(
@Parameter(description = "The input PDF file", required = true) @RequestParam("fileInput") MultipartFile file,
@Parameter(description = "The scale of pages in the output PDF. Acceptable values are A0-A10, B0-B9, LETTER, TABLOID, LEDGER, LEGAL, EXECUTIVE.", required = true, schema = @Schema(type = "String", allowableValues = { "A0", "A1", "A2", "A3", "A4", "A5", "A6", "A7", "A8", "A9", "A10", "B0", "B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8", "B9", "LETTER", "TABLOID", "LEDGER", "LEGAL", "EXECUTIVE" })) @RequestParam("pageSize") String targetPageSize,
@Parameter(description = "The scale of the content on the pages of the output PDF. Acceptable values are floats.", required = true, schema = @Schema(type = "float")) @RequestParam("scaleFactor") float scaleFactor)
throws IOException {
@Parameter(description = "The input PDF file", required = true) @RequestParam("fileInput") MultipartFile file,
@Parameter(description = "The scale of pages in the output PDF. Acceptable values are A0-A10, B0-B9, LETTER, TABLOID, LEDGER, LEGAL, EXECUTIVE.", required = true, schema = @Schema(type = "String", allowableValues = {
"A0", "A1", "A2", "A3", "A4", "A5", "A6", "A7", "A8", "A9", "A10", "B0", "B1", "B2", "B3", "B4",
"B5", "B6", "B7", "B8", "B9", "LETTER", "TABLOID", "LEDGER", "LEGAL",
"EXECUTIVE" })) @RequestParam("pageSize") String targetPageSize,
@Parameter(description = "The scale of the content on the pages of the output PDF. Acceptable values are floats.", required = true, schema = @Schema(type = "float")) @RequestParam("scaleFactor") float scaleFactor)
throws IOException {
Map<String, PageSize> sizeMap = new HashMap<>();
// Add A0 - A10
sizeMap.put("A0", PageSize.A0);
sizeMap.put("A1", PageSize.A1);
sizeMap.put("A2", PageSize.A2);
sizeMap.put("A3", PageSize.A3);
sizeMap.put("A4", PageSize.A4);
sizeMap.put("A5", PageSize.A5);
sizeMap.put("A6", PageSize.A6);
sizeMap.put("A7", PageSize.A7);
sizeMap.put("A8", PageSize.A8);
sizeMap.put("A9", PageSize.A9);
sizeMap.put("A10", PageSize.A10);
// Add B0 - B9
sizeMap.put("B0", PageSize.B0);
sizeMap.put("B1", PageSize.B1);
sizeMap.put("B2", PageSize.B2);
sizeMap.put("B3", PageSize.B3);
sizeMap.put("B4", PageSize.B4);
sizeMap.put("B5", PageSize.B5);
sizeMap.put("B6", PageSize.B6);
sizeMap.put("B7", PageSize.B7);
sizeMap.put("B8", PageSize.B8);
sizeMap.put("B9", PageSize.B9);
// Add other sizes
sizeMap.put("LETTER", PageSize.LETTER);
sizeMap.put("TABLOID", PageSize.TABLOID);
sizeMap.put("LEDGER", PageSize.LEDGER);
sizeMap.put("LEGAL", PageSize.LEGAL);
sizeMap.put("EXECUTIVE", PageSize.EXECUTIVE);
if (!sizeMap.containsKey(targetPageSize)) {
throw new IllegalArgumentException("Invalid pageSize. It must be one of the following: A0, A1, A2, A3, A4, A5, A6, A7, A8, A9, A10");
}
// Add A0 - A10
sizeMap.put("A0", PageSize.A0);
sizeMap.put("A1", PageSize.A1);
sizeMap.put("A2", PageSize.A2);
sizeMap.put("A3", PageSize.A3);
sizeMap.put("A4", PageSize.A4);
sizeMap.put("A5", PageSize.A5);
sizeMap.put("A6", PageSize.A6);
sizeMap.put("A7", PageSize.A7);
sizeMap.put("A8", PageSize.A8);
sizeMap.put("A9", PageSize.A9);
sizeMap.put("A10", PageSize.A10);
// Add B0 - B9
sizeMap.put("B0", PageSize.B0);
sizeMap.put("B1", PageSize.B1);
sizeMap.put("B2", PageSize.B2);
sizeMap.put("B3", PageSize.B3);
sizeMap.put("B4", PageSize.B4);
sizeMap.put("B5", PageSize.B5);
sizeMap.put("B6", PageSize.B6);
sizeMap.put("B7", PageSize.B7);
sizeMap.put("B8", PageSize.B8);
sizeMap.put("B9", PageSize.B9);
// Add other sizes
sizeMap.put("LETTER", PageSize.LETTER);
sizeMap.put("TABLOID", PageSize.TABLOID);
sizeMap.put("LEDGER", PageSize.LEDGER);
sizeMap.put("LEGAL", PageSize.LEGAL);
sizeMap.put("EXECUTIVE", PageSize.EXECUTIVE);
if (!sizeMap.containsKey(targetPageSize)) {
throw new IllegalArgumentException(
"Invalid pageSize. It must be one of the following: A0, A1, A2, A3, A4, A5, A6, A7, A8, A9, A10");
}
PageSize pageSize = sizeMap.get(targetPageSize);
byte[] bytes = file.getBytes();
PdfReader reader = new PdfReader(new ByteArrayInputStream(bytes));
@@ -97,9 +102,7 @@ public class ScalePagesController {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
PdfWriter writer = new PdfWriter(baos);
PdfDocument outputPdf = new PdfDocument(writer);
int totalPages = pdfDoc.getNumberOfPages();
for (int i = 1; i <= totalPages; i++) {
@@ -111,7 +114,7 @@ public class ScalePagesController {
float scaleWidth = pageSize.getWidth() / rect.getWidth();
float scaleHeight = pageSize.getHeight() / rect.getHeight();
float scale = Math.min(scaleWidth, scaleHeight) * scaleFactor;
System.out.println("Scale: " + scale);
System.out.println("Scale: " + scale);
PdfFormXObject formXObject = pdfDoc.getPage(i).copyAsFormXObject(outputPdf);
float x = (pageSize.getWidth() - rect.getWidth() * scale) / 2; // Center Page
@@ -128,130 +131,111 @@ public class ScalePagesController {
outputPdf.close();
byte[] pdfContent = baos.toByteArray();
pdfDoc.close();
return WebResponseUtils.bytesToWebResponse(pdfContent, file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_scaled.pdf");
return WebResponseUtils.bytesToWebResponse(pdfContent,
file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_scaled.pdf");
}
@PostMapping(value = "/auto-crop", consumes = "multipart/form-data")
public ResponseEntity<byte[]> cropPdf(@RequestParam("fileInput") MultipartFile file) throws IOException {
byte[] bytes = file.getBytes();
PdfReader reader = new PdfReader(new ByteArrayInputStream(bytes));
PdfDocument pdfDoc = new PdfDocument(reader);
//TODO
@Hidden
@PostMapping(value = "/auto-crop", consumes = "multipart/form-data")
public ResponseEntity<byte[]> cropPdf(@RequestParam("fileInput") MultipartFile file) throws IOException {
byte[] bytes = file.getBytes();
PdfReader reader = new PdfReader(new ByteArrayInputStream(bytes));
PdfDocument pdfDoc = new PdfDocument(reader);
ByteArrayOutputStream baos = new ByteArrayOutputStream();
PdfWriter writer = new PdfWriter(baos);
PdfDocument outputPdf = new PdfDocument(writer);
int totalPages = pdfDoc.getNumberOfPages();
for (int i = 1; i <= totalPages; i++) {
PdfPage page = pdfDoc.getPage(i);
Rectangle originalMediaBox = page.getMediaBox();
Rectangle contentBox = determineContentBox(page);
// Make sure we don't go outside the original media box.
Rectangle intersection = originalMediaBox.getIntersection(contentBox);
page.setCropBox(intersection);
ByteArrayOutputStream baos = new ByteArrayOutputStream();
PdfWriter writer = new PdfWriter(baos);
PdfDocument outputPdf = new PdfDocument(writer);
// Copy page to the new document
outputPdf.addPage(page.copyTo(outputPdf));
}
int totalPages = pdfDoc.getNumberOfPages();
for (int i = 1; i <= totalPages; i++) {
PdfPage page = pdfDoc.getPage(i);
Rectangle originalMediaBox = page.getMediaBox();
Rectangle contentBox = determineContentBox(page);
// Make sure we don't go outside the original media box.
Rectangle intersection = originalMediaBox.getIntersection(contentBox);
page.setCropBox(intersection);
// Copy page to the new document
outputPdf.addPage(page.copyTo(outputPdf));
}
outputPdf.close();
byte[] pdfContent = baos.toByteArray();
pdfDoc.close();
return ResponseEntity.ok()
.header(HttpHeaders.CONTENT_DISPOSITION, "attachment; filename=\""
+ file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_cropped.pdf\"")
.contentType(MediaType.APPLICATION_PDF).body(pdfContent);
}
private Rectangle determineContentBox(PdfPage page) {
// Extract the text from the page and find the bounding box.
TextBoundingRectangleFinder finder = new TextBoundingRectangleFinder();
PdfCanvasProcessor processor = new PdfCanvasProcessor(finder);
processor.processPageContent(page);
return finder.getBoundingBox();
}
private static class TextBoundingRectangleFinder implements IEventListener {
private List<Rectangle> allTextBoxes = new ArrayList<>();
public Rectangle getBoundingBox() {
// Sort the text boxes based on their vertical position
allTextBoxes.sort(Comparator.comparingDouble(Rectangle::getTop));
// Consider a box an outlier if its top is more than 1.5 times the IQR above the
// third quartile.
int q1Index = allTextBoxes.size() / 4;
int q3Index = 3 * allTextBoxes.size() / 4;
double iqr = allTextBoxes.get(q3Index).getTop() - allTextBoxes.get(q1Index).getTop();
double threshold = allTextBoxes.get(q3Index).getTop() + 1.5 * iqr;
// Initialize boundingBox to the first non-outlier box
int i = 0;
while (i < allTextBoxes.size() && allTextBoxes.get(i).getTop() > threshold) {
i++;
}
if (i == allTextBoxes.size()) {
// If all boxes are outliers, just return the first one
return allTextBoxes.get(0);
}
Rectangle boundingBox = allTextBoxes.get(i);
// Extend the bounding box to include all non-outlier boxes
for (; i < allTextBoxes.size(); i++) {
Rectangle textBoundingBox = allTextBoxes.get(i);
if (textBoundingBox.getTop() > threshold) {
// This box is an outlier, skip it
continue;
}
float left = Math.min(boundingBox.getLeft(), textBoundingBox.getLeft());
float bottom = Math.min(boundingBox.getBottom(), textBoundingBox.getBottom());
float right = Math.max(boundingBox.getRight(), textBoundingBox.getRight());
float top = Math.max(boundingBox.getTop(), textBoundingBox.getTop());
// Add a small padding around the bounding box
float padding = 10;
boundingBox = new Rectangle(left - padding, bottom - padding, right - left + 2 * padding,
top - bottom + 2 * padding);
}
return boundingBox;
}
@Override
public void eventOccurred(IEventData data, EventType type) {
if (type == EventType.RENDER_TEXT) {
TextRenderInfo renderInfo = (TextRenderInfo) data;
allTextBoxes.add(renderInfo.getBaseline().getBoundingRectangle());
}
}
@Override
public Set<EventType> getSupportedEvents() {
return Collections.singleton(EventType.RENDER_TEXT);
}
}
outputPdf.close();
byte[] pdfContent = baos.toByteArray();
pdfDoc.close();
return ResponseEntity.ok()
.header(HttpHeaders.CONTENT_DISPOSITION, "attachment; filename=\"" + file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_cropped.pdf\"")
.contentType(MediaType.APPLICATION_PDF)
.body(pdfContent);
}
private Rectangle determineContentBox(PdfPage page) {
// Extract the text from the page and find the bounding box.
TextBoundingRectangleFinder finder = new TextBoundingRectangleFinder();
PdfCanvasProcessor processor = new PdfCanvasProcessor(finder);
processor.processPageContent(page);
return finder.getBoundingBox();
}
private static class TextBoundingRectangleFinder implements IEventListener {
private List<Rectangle> allTextBoxes = new ArrayList<>();
public Rectangle getBoundingBox() {
// Sort the text boxes based on their vertical position
allTextBoxes.sort(Comparator.comparingDouble(Rectangle::getTop));
// Consider a box an outlier if its top is more than 1.5 times the IQR above the third quartile.
int q1Index = allTextBoxes.size() / 4;
int q3Index = 3 * allTextBoxes.size() / 4;
double iqr = allTextBoxes.get(q3Index).getTop() - allTextBoxes.get(q1Index).getTop();
double threshold = allTextBoxes.get(q3Index).getTop() + 1.5 * iqr;
// Initialize boundingBox to the first non-outlier box
int i = 0;
while (i < allTextBoxes.size() && allTextBoxes.get(i).getTop() > threshold) {
i++;
}
if (i == allTextBoxes.size()) {
// If all boxes are outliers, just return the first one
return allTextBoxes.get(0);
}
Rectangle boundingBox = allTextBoxes.get(i);
// Extend the bounding box to include all non-outlier boxes
for (; i < allTextBoxes.size(); i++) {
Rectangle textBoundingBox = allTextBoxes.get(i);
if (textBoundingBox.getTop() > threshold) {
// This box is an outlier, skip it
continue;
}
float left = Math.min(boundingBox.getLeft(), textBoundingBox.getLeft());
float bottom = Math.min(boundingBox.getBottom(), textBoundingBox.getBottom());
float right = Math.max(boundingBox.getRight(), textBoundingBox.getRight());
float top = Math.max(boundingBox.getTop(), textBoundingBox.getTop());
// Add a small padding around the bounding box
float padding = 10;
boundingBox = new Rectangle(left - padding, bottom - padding, right - left + 2 * padding, top - bottom + 2 * padding);
}
return boundingBox;
}
@Override
public void eventOccurred(IEventData data, EventType type) {
if (type == EventType.RENDER_TEXT) {
TextRenderInfo renderInfo = (TextRenderInfo) data;
allTextBoxes.add(renderInfo.getBaseline().getBoundingRectangle());
}
}
@Override
public Set<EventType> getSupportedEvents() {
return Collections.singleton(EventType.RENDER_TEXT);
}
}
}

161
src/main/java/stirling/software/SPDF/controller/api/other/FakeScanController.java Normal file
View File

@@ -0,0 +1,161 @@
package stirling.software.SPDF.controller.api.other;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.List;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestPart;
import org.springframework.web.bind.annotation.RestController;
import org.springframework.web.multipart.MultipartFile;
import com.itextpdf.io.source.ByteArrayOutputStream;
import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.Parameter;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.WebResponseUtils;
//Required for PDF manipulation
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.PDImageXObject;
import org.apache.pdfbox.pdmodel.graphics.image.LosslessFactory;
import org.apache.pdfbox.rendering.ImageType;
import org.apache.pdfbox.rendering.PDFRenderer;
//Required for image manipulation
import java.awt.image.BufferedImage;
import java.awt.image.BufferedImageOp;
import java.awt.image.RescaleOp;
import java.awt.image.AffineTransformOp;
import java.awt.image.ConvolveOp;
import java.awt.image.Kernel;
import java.awt.Color;
import java.awt.geom.AffineTransform;
//Required for image input/output
import javax.imageio.ImageIO;
//Required for file input/output
import java.io.File;
//Other required classes
import java.util.Random;
import io.swagger.v3.oas.annotations.Hidden;
@RestController
public class FakeScanController {
private static final Logger logger = LoggerFactory.getLogger(FakeScanController.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(
@RequestPart(required = true, value = "fileInput")
@Parameter(description = "The input PDF file to be repaired", required = true)
MultipartFile inputFile) throws IOException, InterruptedException {
PDDocument document = PDDocument.load(inputFile.getBytes());
PDFRenderer pdfRenderer = new PDFRenderer(document);
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"));
}
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 Random().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 Random();
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();
}
ByteArrayOutputStream baos = new ByteArrayOutputStream();
documentOut.save(baos);
documentOut.close();
// Return the optimized PDF as a response
String outputFilename = inputFile.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_scanned.pdf";
return WebResponseUtils.boasToWebResponse(baos, outputFilename);
}
}