arsvendg/Stirling-PDF
1
0
Fork 0
mirror of https://github.com/arsvendg/Stirling-PDF.git synced 2026-07-15 02:54:06 +02:00
Code Issues Actions 6 Packages Projects Releases 1 Wiki Activity

formattingand autowired constructors (#2557)

Browse Source 
# Description
This pull request includes several changes aimed at improving the code
structure and removing redundant code. The most significant changes
involve reordering methods, removing unnecessary annotations, and
refactoring constructors to use dependency injection.
Autowired now comes via constructor (which also doesn't need autowired
annotation as its done by default for configuration)



## Checklist

- [ ] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have performed a self-review of my own code
- [ ] I have attached images of the change if it is UI based
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] If my code has heavily changed functionality I have updated
relevant docs on [Stirling-PDFs doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
- [ ] My changes generate no new warnings
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)
This commit is contained in:
Anthony Stirling
2024-12-24 09:52:53 +00:00
committed by GitHub
parent 2abfe599ed
commit 9884c65b10
92 changed files with 1256 additions and 1535 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/main/java/stirling/software/SPDF/controller/api/misc/AutoRenameController.java
+10 -10
View File
@@ -46,16 +46,6 @@ public class AutoRenameController {
PDDocument document = Loader.loadPDF(file.getBytes());
PDFTextStripper reader =
new PDFTextStripper() {
class LineInfo {
String text;
float fontSize;
LineInfo(String text, float fontSize) {
this.text = text;
this.fontSize = fontSize;
}
}
List<LineInfo> lineInfos = new ArrayList<>();
StringBuilder lineBuilder = new StringBuilder();
float lastY = -1;
@@ -122,6 +112,16 @@ public class AutoRenameController {
.text)
: null);
}
class LineInfo {
String text;
float fontSize;
LineInfo(String text, float fontSize) {
this.text = text;
this.fontSize = fontSize;
}
}
};
String header = reader.getText(document);
src/main/java/stirling/software/SPDF/controller/api/misc/AutoSplitPdfController.java
+47 -52
View File
@@ -23,12 +23,7 @@ import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;
import org.springframework.web.multipart.MultipartFile;
import com.google.zxing.BinaryBitmap;
import com.google.zxing.LuminanceSource;
import com.google.zxing.MultiFormatReader;
import com.google.zxing.NotFoundException;
import com.google.zxing.PlanarYUVLuminanceSource;
import com.google.zxing.Result;
import com.google.zxing.*;
import com.google.zxing.common.HybridBinarizer;
import io.github.pixee.security.Filenames;
@@ -56,6 +51,52 @@ public class AutoSplitPdfController {
this.pdfDocumentFactory = pdfDocumentFactory;
}
private static String decodeQRCode(BufferedImage bufferedImage) {
LuminanceSource source;
if (bufferedImage.getRaster().getDataBuffer() instanceof DataBufferByte) {
byte[] pixels = ((DataBufferByte) bufferedImage.getRaster().getDataBuffer()).getData();
source =
new PlanarYUVLuminanceSource(
pixels,
bufferedImage.getWidth(),
bufferedImage.getHeight(),
0,
0,
bufferedImage.getWidth(),
bufferedImage.getHeight(),
false);
} else if (bufferedImage.getRaster().getDataBuffer() instanceof DataBufferInt) {
int[] pixels = ((DataBufferInt) bufferedImage.getRaster().getDataBuffer()).getData();
byte[] newPixels = new byte[pixels.length];
for (int i = 0; i < pixels.length; i++) {
newPixels[i] = (byte) (pixels[i] & 0xff);
}
source =
new PlanarYUVLuminanceSource(
newPixels,
bufferedImage.getWidth(),
bufferedImage.getHeight(),
0,
0,
bufferedImage.getWidth(),
bufferedImage.getHeight(),
false);
} else {
throw new IllegalArgumentException(
"BufferedImage must have 8-bit gray scale, 24-bit RGB, 32-bit ARGB (packed int), byte gray, or 3-byte/4-byte RGB image data");
}
BinaryBitmap bitmap = new BinaryBitmap(new HybridBinarizer(source));
try {
Result result = new MultiFormatReader().decode(bitmap);
return result.getText();
} catch (NotFoundException e) {
return null; // there is no QR code in the image
}
}
@PostMapping(value = "/auto-split-pdf", consumes = "multipart/form-data")
@Operation(
summary = "Auto split PDF pages into separate documents",
@@ -154,50 +195,4 @@ public class AutoSplitPdfController {
}
}
}
private static String decodeQRCode(BufferedImage bufferedImage) {
LuminanceSource source;
if (bufferedImage.getRaster().getDataBuffer() instanceof DataBufferByte) {
byte[] pixels = ((DataBufferByte) bufferedImage.getRaster().getDataBuffer()).getData();
source =
new PlanarYUVLuminanceSource(
pixels,
bufferedImage.getWidth(),
bufferedImage.getHeight(),
0,
0,
bufferedImage.getWidth(),
bufferedImage.getHeight(),
false);
} else if (bufferedImage.getRaster().getDataBuffer() instanceof DataBufferInt) {
int[] pixels = ((DataBufferInt) bufferedImage.getRaster().getDataBuffer()).getData();
byte[] newPixels = new byte[pixels.length];
for (int i = 0; i < pixels.length; i++) {
newPixels[i] = (byte) (pixels[i] & 0xff);
}
source =
new PlanarYUVLuminanceSource(
newPixels,
bufferedImage.getWidth(),
bufferedImage.getHeight(),
0,
0,
bufferedImage.getWidth(),
bufferedImage.getHeight(),
false);
} else {
throw new IllegalArgumentException(
"BufferedImage must have 8-bit gray scale, 24-bit RGB, 32-bit ARGB (packed int), byte gray, or 3-byte/4-byte RGB image data");
}
BinaryBitmap bitmap = new BinaryBitmap(new HybridBinarizer(source));
try {
Result result = new MultiFormatReader().decode(bitmap);
return result.getText();
} catch (NotFoundException e) {
return null; // there is no QR code in the image
}
}
}
src/main/java/stirling/software/SPDF/controller/api/misc/BlankPageController.java
+26 -26
View File
@@ -47,6 +47,32 @@ public class BlankPageController {
this.pdfDocumentFactory = pdfDocumentFactory;
}
public static boolean isBlankImage(
BufferedImage image, int threshold, double whitePercent, int blurSize) {
if (image == null) {
log.info("Error: Image is null");
return false;
}
// Convert to binary image based on the threshold
int whitePixels = 0;
int totalPixels = image.getWidth() * image.getHeight();
for (int i = 0; i < image.getHeight(); i++) {
for (int j = 0; j < image.getWidth(); j++) {
int color = image.getRGB(j, i) & 0xFF;
if (color >= 255 - threshold) {
whitePixels++;
}
}
}
double whitePixelPercentage = (whitePixels / (double) totalPixels) * 100;
log.info(String.format("Page has white pixel percent of %.2f%%", whitePixelPercentage));
return whitePixelPercentage >= whitePercent;
}
@PostMapping(consumes = "multipart/form-data", value = "/remove-blanks")
@Operation(
summary = "Remove blank pages from a PDF file",
@@ -143,30 +169,4 @@ public class BlankPageController {
zos.closeEntry();
}
}
public static boolean isBlankImage(
BufferedImage image, int threshold, double whitePercent, int blurSize) {
if (image == null) {
log.info("Error: Image is null");
return false;
}
// Convert to binary image based on the threshold
int whitePixels = 0;
int totalPixels = image.getWidth() * image.getHeight();
for (int i = 0; i < image.getHeight(); i++) {
for (int j = 0; j < image.getWidth(); j++) {
int color = image.getRGB(j, i) & 0xFF;
if (color >= 255 - threshold) {
whitePixels++;
}
}
}
double whitePixelPercentage = (whitePixels / (double) totalPixels) * 100;
log.info(String.format("Page has white pixel percent of %.2f%%", whitePixelPercentage));
return whitePixelPercentage >= whitePercent;
}
}
src/main/java/stirling/software/SPDF/controller/api/misc/CompressController.java
+1 -1
View File
@@ -1,6 +1,6 @@
package stirling.software.SPDF.controller.api.misc;
import java.awt.Image;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.ByteArrayOutputStream;
import java.nio.file.Files;
src/main/java/stirling/software/SPDF/controller/api/misc/ExtractImageScansController.java
+2 -2
View File
@@ -42,6 +42,8 @@ import stirling.software.SPDF.utils.WebResponseUtils;
@Tag(name = "Misc", description = "Miscellaneous APIs")
public class ExtractImageScansController {
private static final String REPLACEFIRST = "[.][^.]+$";
@PostMapping(consumes = "multipart/form-data", value = "/extract-image-scans")
@Operation(
summary = "Extract image scans from an input file",
@@ -221,6 +223,4 @@ public class ExtractImageScansController {
});
}
}
private static final String REPLACEFIRST = "[.][^.]+$";
}
src/main/java/stirling/software/SPDF/controller/api/misc/FakeScanControllerWIP.java
+2 -11
View File
@@ -1,19 +1,10 @@
package stirling.software.SPDF.controller.api.misc;
import java.awt.AlphaComposite;
import java.awt.BasicStroke;
import java.awt.Color;
import java.awt.GradientPaint;
import java.awt.Graphics2D;
import java.awt.RenderingHints;
import java.awt.*;
import java.awt.geom.AffineTransform;
import java.awt.geom.Ellipse2D;
import java.awt.geom.Path2D;
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.*;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.security.SecureRandom;
src/main/java/stirling/software/SPDF/controller/api/misc/MetadataController.java
+1 -5
View File
@@ -13,11 +13,7 @@ import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDDocumentInformation;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.WebDataBinder;
import org.springframework.web.bind.annotation.InitBinder;
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.bind.annotation.*;
import org.springframework.web.multipart.MultipartFile;
import io.github.pixee.security.Filenames;
src/main/java/stirling/software/SPDF/controller/api/misc/OCRController.java
+9 -36
View File
@@ -1,18 +1,10 @@
package stirling.software.SPDF.controller.api.misc;
import java.awt.image.BufferedImage;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.*;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.Comparator;
import java.util.List;
import java.util.*;
import java.util.stream.Collectors;
import java.util.zip.ZipEntry;
import java.util.zip.ZipOutputStream;
@@ -24,7 +16,6 @@ import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.pdfbox.text.PDFTextStripper;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.ModelAttribute;
@@ -48,12 +39,14 @@ import stirling.software.SPDF.service.CustomPDDocumentFactory;
@Slf4j
public class OCRController {
@Autowired private ApplicationProperties applicationProperties;
private final ApplicationProperties applicationProperties;
private final CustomPDDocumentFactory pdfDocumentFactory;
@Autowired
public OCRController(CustomPDDocumentFactory pdfDocumentFactory) {
public OCRController(
ApplicationProperties applicationProperties,
CustomPDDocumentFactory pdfDocumentFactory) {
this.applicationProperties = applicationProperties;
this.pdfDocumentFactory = pdfDocumentFactory;
}
@@ -78,13 +71,11 @@ public class OCRController {
MultipartFile inputFile = request.getFileInput();
List<String> languages = request.getLanguages();
String ocrType = request.getOcrType();
Path tempDir = Files.createTempDirectory("ocr_process");
Path tempInputFile = tempDir.resolve("input.pdf");
Path tempOutputDir = tempDir.resolve("output");
Path tempImagesDir = tempDir.resolve("images");
Path finalOutputFile = tempDir.resolve("final_output.pdf");
Files.createDirectories(tempOutputDir);
Files.createDirectories(tempImagesDir);
Process process = null;
@@ -93,39 +84,32 @@ public class OCRController {
inputFile.transferTo(tempInputFile.toFile());
PDFMergerUtility merger = new PDFMergerUtility();
merger.setDestinationFileName(finalOutputFile.toString());
try (PDDocument document = pdfDocumentFactory.load(tempInputFile.toFile())) {
PDFRenderer pdfRenderer = new PDFRenderer(document);
int pageCount = document.getNumberOfPages();
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();
hasText = !stripper.getText(tempDoc).trim().isEmpty();
}
boolean shouldOcr =
switch (ocrType) {
case "skip-text" -> !hasText;
case "force-ocr" -> true;
default -> true;
};
Path pageOutputPath =
tempOutputDir.resolve(String.format("page_%d.pdf", pageNum));
if (shouldOcr) {
// 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");
@@ -136,11 +120,10 @@ public class OCRController {
.toString());
command.add("-l");
command.add(String.join("+", languages));
command.add("pdf"); // Always output PDF
// Always output PDF
command.add("pdf");
ProcessBuilder pb = new ProcessBuilder(command);
process = pb.start();
// Capture any error output
try (BufferedReader reader =
new BufferedReader(
@@ -150,13 +133,11 @@ public class OCRController {
log.debug("Tesseract: {}", line);
}
}
int exitCode = process.waitFor();
if (exitCode != 0) {
throw new RuntimeException(
"Tesseract failed with exit code: " + exitCode);
}
// Add OCR'd PDF to merger
merger.addSource(pageOutputPath.toFile());
} else {
@@ -169,29 +150,24 @@ public class OCRController {
}
}
}
// Merge all pages into final PDF
merger.mergeDocuments(null);
// Read the final PDF file
byte[] pdfContent = Files.readAllBytes(finalOutputFile);
String outputFilename =
Filenames.toSimpleFileName(inputFile.getOriginalFilename())
.replaceFirst("[.][^.]+$", "")
+ "_OCR.pdf";
return ResponseEntity.ok()
.header(
"Content-Disposition",
"attachment; filename=\"" + outputFilename + "\"")
.contentType(MediaType.APPLICATION_PDF)
.body(pdfContent);
} finally {
if (process != null) {
process.destroy();
}
// Clean up temporary files
deleteDirectory(tempDir);
}
@@ -203,17 +179,14 @@ public class OCRController {
log.warn("File {} does not exist, skipping", file);
return;
}
try (FileInputStream fis = new FileInputStream(file)) {
ZipEntry zipEntry = new ZipEntry(filename);
zipOut.putNextEntry(zipEntry);
byte[] buffer = new byte[1024];
int length;
while ((length = fis.read(buffer)) >= 0) {
zipOut.write(buffer, 0, length);
}
zipOut.closeEntry();
}
}
src/main/java/stirling/software/SPDF/controller/api/misc/PrintFileController.java
+1 -2
View File
@@ -1,7 +1,6 @@
package stirling.software.SPDF.controller.api.misc;
import java.awt.Graphics;
import java.awt.Graphics2D;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.awt.print.PageFormat;
import java.awt.print.Printable;
src/main/java/stirling/software/SPDF/controller/api/misc/StampController.java
+1 -1
View File
@@ -1,6 +1,6 @@
package stirling.software.SPDF.controller.api.misc;
import java.awt.Color;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.FileOutputStream;