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

Lots of changes (#70)

Browse Source 
Image extraction and conversion to formats 

Multi parallel file execution for all forms so you can input multiple files quickly 

Any file at all pdf using libreoffice, super powerful
Sadly makes docker image larger but worth it 

OCR PDF using ocr my pdf
Works awesomely for adding text to a image

Improved compression using ocr my pdf app

Settings page with custom download options such as 
- open in same window
- open in new window
- download
- download as zip

Update detection in settings page it should show notification if there is a update (very hidden)

UI cleanups

Add other image formats to PDF to Image

Various fies to icons, and pdf.js usage
This commit is contained in:
Anthony Stirling
2023-03-20 21:55:11 +00:00
committed by GitHub
parent 54abb53842
commit a9145fe84c
54 changed files with 82327 additions and 8300 deletions
Download Patch File Download Diff File Expand all files Collapse all files

109
src/main/java/stirling/software/SPDF/controller/CompressController.java
View File

@@ -1,9 +1,23 @@
package stirling.software.SPDF.controller;
import java.awt.Graphics2D;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import javax.imageio.ImageIO;
import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDResources;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.http.HttpStatus;
import org.springframework.http.ResponseEntity;
import org.springframework.stereotype.Controller;
import org.springframework.ui.Model;
@@ -12,16 +26,31 @@ import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestParam;
import org.springframework.web.multipart.MultipartFile;
import com.spire.pdf.PdfCompressionLevel;
import com.spire.pdf.PdfDocument;
import com.spire.pdf.PdfPageBase;
import com.spire.pdf.exporting.PdfImageInfo;
import com.spire.pdf.graphics.PdfBitmap;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.PdfStamper;
import stirling.software.SPDF.utils.ErrorUtils;
import stirling.software.SPDF.utils.PdfUtils;
import stirling.software.SPDF.utils.ProcessExecutor;
import org.springframework.http.HttpHeaders;
import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestParam;
import org.springframework.web.multipart.MultipartFile;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
//import com.spire.pdf.*;
@Controller
public class CompressController {
@@ -33,36 +62,56 @@ public class CompressController {
return "compress-pdf";
}
@PostMapping("/compress-pdf")
public ResponseEntity<byte[]> compressPDF(@RequestParam("fileInput") MultipartFile pdfFile, @RequestParam("imageCompressionLevel") String imageCompressionLevel)
throws IOException {
// Load a sample PDF document
PdfDocument document = new PdfDocument();
document.loadFromBytes(pdfFile.getBytes());
public ResponseEntity<byte[]> optimizePdf(
@RequestParam("fileInput") MultipartFile inputFile,
@RequestParam("optimizeLevel") int optimizeLevel,
@RequestParam(name = "fastWebView", required = false) Boolean fastWebView,
@RequestParam(name = "jbig2Lossy", required = false) Boolean jbig2Lossy) throws IOException, InterruptedException {
// Compress PDF
document.getFileInfo().setIncrementalUpdate(false);
document.setCompressionLevel(PdfCompressionLevel.Best);
// Save the uploaded file to a temporary location
Path tempInputFile = Files.createTempFile("input_", ".pdf");
inputFile.transferTo(tempInputFile.toFile());
// compress PDF Images
for (int i = 0; i < document.getPages().getCount(); i++) {
// Prepare the output file path
Path tempOutputFile = Files.createTempFile("output_", ".pdf");
PdfPageBase page = document.getPages().get(i);
PdfImageInfo[] images = page.getImagesInfo();
if (images != null && images.length > 0)
for (int j = 0; j < images.length; j++) {
PdfImageInfo image = images[j];
PdfBitmap bp = new PdfBitmap(image.getImage());
// bp.setPngDirectToJpeg(true);
bp.setQuality(Integer.valueOf(imageCompressionLevel));
// Prepare the OCRmyPDF command
List<String> command = new ArrayList<>();
command.add("ocrmypdf");
command.add("--optimize");
command.add(String.valueOf(optimizeLevel));
page.replaceImage(j, bp);
}
if (fastWebView != null && fastWebView) {
long fileSize = inputFile.getSize();
long fastWebViewSize = (long) (fileSize * 1.25); // 25% higher than file size
command.add("--fast-web-view");
command.add(String.valueOf(fastWebViewSize));
}
return PdfUtils.pdfDocToWebResponse(document, pdfFile.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_compressed.pdf");
if (jbig2Lossy != null && jbig2Lossy) {
command.add("--jbig2-lossy");
}
}
command.add(tempInputFile.toString());
command.add(tempOutputFile.toString());
int returnCode = ProcessExecutor.runCommandWithOutputHandling(command);
// Read the optimized PDF file
byte[] pdfBytes = Files.readAllBytes(tempOutputFile);
// Clean up the temporary files
Files.delete(tempInputFile);
Files.delete(tempOutputFile);
// Return the optimized PDF as a response
String outputFilename = inputFile.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_Optimized.pdf";
HttpHeaders headers = new HttpHeaders();
headers.setContentType(MediaType.APPLICATION_PDF);
headers.setContentDispositionFormData("attachment", outputFilename);
return ResponseEntity.ok().headers(headers).body(pdfBytes);
}
}