Fixes and others (#83)

Features
-------------
Custom application name via APP_NAME docker env
(These next 3 are done with OCRMyPDF)
Extra features to OCR for scanned page cleanup (tilt/noise fixing)
Adding OCR ability to read and output to text file
Added Dedicated PDF/A conversion page 

Bug fixes
--------------
Fix concurrent calls on Libre and OCRMyPDF
jbig fix for compressions
Fix for compression metadata issues due to forced conversions to PDF/A


Other
--------
Removal of UK US language and just using "English" due to extra development time
Still issue with concurrent files for PDF to image... will fix later sorry

Dockerfile

@@ -36,6 +36,7 @@ RUN apt-get update && \
 		python3-pip \
         unoconv \
 		pngquant \
+		unpaper \
         ocrmypdf && \
 	pip install --user --upgrade ocrmypdf
 
@@ -49,10 +50,10 @@ COPY build/libs/*.jar app.jar
 EXPOSE 8080
 
 # Set environment variables
-ENV LOG_LEVEL=INFO
+ENV APP_NAME="Stirling PDF"
 
 # Run the application
-ENTRYPOINT ["java","-jar","/app.jar","-Dlogging.level=${LOG_LEVEL}"]
+ENTRYPOINT java -jar /app.jar
 
 
 

build.gradle

@@ -19,6 +19,10 @@ dependencies {
 	
 	implementation 'org.apache.logging.log4j:log4j-core:2.20.0'
 	
+	// https://mvnrepository.com/artifact/org.apache.pdfbox/jbig2-imageio
+	implementation group: 'org.apache.pdfbox', name: 'jbig2-imageio', version: '3.0.4'
+	
+		
 	//general PDF
     implementation 'org.apache.pdfbox:pdfbox:2.0.27'
         

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

@@ -5,9 +5,7 @@ import org.springframework.boot.autoconfigure.SpringBootApplication;
 
 @SpringBootApplication
 public class SPdfApplication {
-
     public static void main(String[] args) {
         SpringApplication.run(SPdfApplication.class, args);     
     }
-
 }

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

@@ -11,4 +11,12 @@ public class AppConfig {
         String version = getClass().getPackage().getImplementationVersion();
         return (version != null) ? version : "0.3.3";
     }
+    
+    @Bean(name = "appName")
+    public String appName() {
+        String appName = System.getProperty("AppName");
+        if(appName == null)
+            appName = System.getenv("APP_NAME");
+        return (appName != null) ? appName : "Stirling PDF";
+    }
 }

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

@@ -16,7 +16,7 @@ public class Beans implements WebMvcConfigurer {
     @Bean
     public LocaleResolver localeResolver() {
         SessionLocaleResolver slr = new SessionLocaleResolver();
-        slr.setDefaultLocale(Locale.US);
+        slr.setDefaultLocale(Locale.UK);
         return slr;
     }
 

src/main/java/stirling/software/SPDF/controller/CompressController.java

@@ -54,6 +54,9 @@ public class CompressController {
         command.add("--tesseract-timeout=0");
         command.add("--optimize");
         command.add(String.valueOf(optimizeLevel));
+        command.add("--output-type");
+        command.add("pdf");
+
 
         if (fastWebView != null && fastWebView) {
             long fileSize = inputFile.getSize();
@@ -69,7 +72,7 @@ public class CompressController {
         command.add(tempInputFile.toString());
         command.add(tempOutputFile.toString());
 
-        int returnCode = ProcessExecutor.runCommandWithOutputHandling(command);
+        int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF).runCommandWithOutputHandling(command);
         
         // Read the optimized PDF file
         byte[] pdfBytes = Files.readAllBytes(tempOutputFile);

src/main/java/stirling/software/SPDF/controller/OCRController.java

@@ -28,6 +28,7 @@ import org.springframework.web.servlet.ModelAndView;
 
 import stirling.software.SPDF.utils.ProcessExecutor;
 //import com.spire.pdf.*;
+import java.util.concurrent.Semaphore;
 @Controller
 public class OCRController {
 
@@ -41,10 +42,17 @@ public class OCRController {
 		return modelAndView;
 	}
 
+	private final Semaphore semaphore = new Semaphore(2);
+	
 	@PostMapping("/ocr-pdf")
 	public ResponseEntity<byte[]> processPdfWithOCR(@RequestParam("fileInput") MultipartFile inputFile,
 			@RequestParam("languages") List<String> selectedLanguages,
-			@RequestParam(name = "sidecar", required = false) Boolean sidecar) throws IOException, InterruptedException {
+			@RequestParam(name = "sidecar", required = false) Boolean sidecar,
+			@RequestParam(name = "deskew", required = false) Boolean deskew,
+			@RequestParam(name = "clean", required = false) Boolean clean,
+			@RequestParam(name = "clean-final", required = false) Boolean cleanFinal,
+			@RequestParam(name = "ocrType", required = false) String ocrType) throws IOException, InterruptedException {
+
 	    
 		//--output-type pdfa
 		if (selectedLanguages == null || selectedLanguages.size() < 1) {
@@ -58,20 +66,50 @@ public class OCRController {
 		// Prepare the output file path
 		Path tempOutputFile = Files.createTempFile("output_", ".pdf");
 
+		// Prepare the output file path
+        Path sidecarTextPath = null;
+        
 		// Run OCR Command
 	    String languageOption = String.join("+", selectedLanguages);
-	    List<String> command = new ArrayList<>(Arrays.asList("ocrmypdf","--verbose", "2", "--language", languageOption,
+	    
-	            tempInputFile.toString(), tempOutputFile.toString()));
+	    List<String> command = new ArrayList<>(Arrays.asList("ocrmypdf","--verbose", "2", "--output-type", "pdf"));
-	    String sidecarFile = tempOutputFile.toString().replace(".pdf", ".txt");
+	    		
+	    
 	    if (sidecar != null && sidecar) {
+	        sidecarTextPath = Files.createTempFile("sidecar", ".txt");
 	        command.add("--sidecar");
-	        command.add(sidecarFile);
+	        command.add(sidecarTextPath.toString());
 	    }
-	    int returnCode = ProcessExecutor.runCommandWithOutputHandling(command);
+	    
+	    if (deskew != null && deskew) {
+            command.add("--deskew");
+	    }
+	    if (clean != null && clean) {
+            command.add("--clean");
+        }
+	    if (cleanFinal != null && cleanFinal) {
+            command.add("--clean-final");
+        }
+	    if (ocrType != null && !ocrType.equals("")) {
+            if("skip-text".equals(ocrType)) {
+                command.add("--skip-text");
+            } else if("force-ocr".equals(ocrType)) {
+                command.add("--force-ocr");
+            } else if("Normal".equals(ocrType)) {
+                
+            }
+        }
+
+	    command.addAll(Arrays.asList("--language", languageOption,
+	            tempInputFile.toString(), tempOutputFile.toString()));
+	    
+	    //Run CLI command
+	    int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF).runCommandWithOutputHandling(command);
         
 		// Read the OCR processed PDF file
 		byte[] pdfBytes = Files.readAllBytes(tempOutputFile);
 		
+	    
 		// Clean up the temporary files
 		Files.delete(tempInputFile);
 		// Return the OCR processed PDF as a response
@@ -92,9 +130,9 @@ public class OCRController {
 	            zipOut.closeEntry();
 
 	            // Add text file to the zip
-	            ZipEntry txtEntry = new ZipEntry(sidecarFile);
+	            ZipEntry txtEntry = new ZipEntry(outputFilename.replace(".pdf", ".txt"));
 	            zipOut.putNextEntry(txtEntry);
-	            Files.copy(Paths.get(sidecarFile), zipOut);
+	            Files.copy(sidecarTextPath, zipOut);
 	            zipOut.closeEntry();
 	        }
 
@@ -103,7 +141,7 @@ public class OCRController {
 	        // Clean up the temporary zip file
 	        Files.delete(tempZipFile);
 	        Files.delete(tempOutputFile);
-	        Files.delete(Paths.get(sidecarFile));
+	        Files.delete(sidecarTextPath);
 	        
 	        // Return the zip file containing both the PDF and the text file
 	        headers.setContentType(MediaType.APPLICATION_OCTET_STREAM);

src/main/java/stirling/software/SPDF/controller/converters/ConvertImgPDFController.java

@@ -73,7 +73,6 @@ public class ConvertImgPDFController {
         if (singleImage) {
             HttpHeaders headers = new HttpHeaders();
             headers.setContentType(MediaType.parseMediaType(getMediaType(imageFormat)));
-            headers.setCacheControl("must-revalidate, post-check=0, pre-check=0");
             ResponseEntity<Resource> response = new ResponseEntity<>(new ByteArrayResource(result), headers, HttpStatus.OK);
             return response;
         } else {

src/main/java/stirling/software/SPDF/controller/converters/ConvertOfficeController.java

@@ -53,7 +53,7 @@ public byte[] convertToPdf(MultipartFile inputFile) throws IOException, Interrup
             "-o",
             tempOutputFile.toString(),
             tempInputFile.toString()));
-    int returnCode = ProcessExecutor.runCommandWithOutputHandling(command);
+    int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.LIBRE_OFFICE).runCommandWithOutputHandling(command);
 
     // Read the converted PDF file
     byte[] pdfBytes = Files.readAllBytes(tempOutputFile);

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

@@ -0,0 +1,75 @@
+package stirling.software.SPDF.controller.converters;
+
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.nio.file.Files;
+import java.nio.file.Path;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+
+import org.springframework.http.HttpHeaders;
+import org.springframework.http.MediaType;
+import org.springframework.http.ResponseEntity;
+import org.springframework.stereotype.Controller;
+import org.springframework.ui.Model;
+import org.springframework.web.bind.annotation.GetMapping;
+import org.springframework.web.bind.annotation.PostMapping;
+import org.springframework.web.bind.annotation.RequestParam;
+import org.springframework.web.multipart.MultipartFile;
+
+import com.itextpdf.xmp.XMPException;
+
+import stirling.software.SPDF.utils.PdfUtils;
+import stirling.software.SPDF.utils.ProcessExecutor;
+@Controller
+public class ConvertPDFToPDFA {
+
+	@GetMapping("/pdf-to-pdfa")
+    public String pdfToPdfAForm(Model model) {
+        model.addAttribute("currentPage", "pdf-to-pdfa");
+        return "convert/pdf-to-pdfa";
+    }
+
+    
+    @PostMapping("/pdf-to-pdfa")
+    public ResponseEntity<byte[]> pdfToPdfA(
+            @RequestParam("fileInput") MultipartFile inputFile) throws IOException, InterruptedException {
+
+    	
+        // Save the uploaded file to a temporary location
+        Path tempInputFile = Files.createTempFile("input_", ".pdf");
+        inputFile.transferTo(tempInputFile.toFile());
+
+        // Prepare the output file path
+        Path tempOutputFile = Files.createTempFile("output_", ".pdf");
+
+        // Prepare the OCRmyPDF command
+        List<String> command = new ArrayList<>();
+        command.add("ocrmypdf");
+        command.add("--skip-text");
+        command.add("--tesseract-timeout=0");
+        command.add("--output-type");
+        command.add("pdfa");
+        command.add(tempInputFile.toString());
+        command.add(tempOutputFile.toString());
+
+        int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF).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("[.][^.]+$", "") + "_PDFA.pdf";
+        HttpHeaders headers = new HttpHeaders();
+        headers.setContentType(MediaType.APPLICATION_PDF);
+        headers.setContentDispositionFormData("attachment", outputFilename);
+        return ResponseEntity.ok().headers(headers).body(pdfBytes);
+}
+
+
+}

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

@@ -1,13 +1,46 @@
 package stirling.software.SPDF.utils;
 
 import java.io.BufferedReader;
+import java.util.concurrent.ConcurrentHashMap;
 import java.io.IOException;
 import java.io.InputStreamReader;
 import java.nio.charset.StandardCharsets;
 import java.util.ArrayList;
 import java.util.List;
+import java.util.Map;
+import java.util.concurrent.Semaphore;
 public class ProcessExecutor {
-	public static int runCommandWithOutputHandling(List<String> command) throws IOException, InterruptedException {
+	
+	public enum Processes {
+        LIBRE_OFFICE,
+        OCR_MY_PDF
+    }
+
+	private static final Map<Processes, ProcessExecutor> instances = new ConcurrentHashMap<>();
+
+
+    private final Semaphore semaphore;
+
+    private ProcessExecutor(int semaphoreLimit) {
+        this.semaphore = new Semaphore(semaphoreLimit);
+    }
+
+    public static ProcessExecutor getInstance(Processes processType) {
+        return instances.computeIfAbsent(processType, key -> {
+            int semaphoreLimit = switch (key) {
+                case LIBRE_OFFICE -> 1; 
+                case OCR_MY_PDF -> 2; 
+            };
+            return new ProcessExecutor(semaphoreLimit);
+        });
+    }
+    
+	public int runCommandWithOutputHandling(List<String> command) throws IOException, InterruptedException {
+		int exitCode = 1;
+		semaphore.acquire();
+		try {
+			
+		    System.out.print("Running command: " + String.join(" ", command));
 		    ProcessBuilder processBuilder = new ProcessBuilder(command);
 		    Process process = processBuilder.start();
 	
@@ -41,7 +74,7 @@ public class ProcessExecutor {
 		    outputReaderThread.start();
 	
 		    // Wait for the conversion process to complete
-	    int exitCode = process.waitFor();
+		    exitCode = process.waitFor();
 	
 		    // Wait for the reader threads to finish
 		    errorReaderThread.join();
@@ -59,7 +92,9 @@ public class ProcessExecutor {
 		            throw new IOException("Command process failed with exit code " + exitCode + ". Error message: " + errorMessage);
 		        }
 		    }
-
+		} finally {
+			semaphore.release();
+		}
 	    return exitCode;
 	}
    		

src/main/resources/application.properties

@@ -1,12 +1,12 @@
-spring.http.multipart.max-file-size=1GB
+spring.http.multipart.max-file-size=2GB
-spring.http.multipart.max-request-size=1GB
+spring.http.multipart.max-request-size=2GB
 
 multipart.enabled=true
-multipart.max-file-size=1000MB
+multipart.max-file-size=2000MB
-multipart.max-request-size=1000MB
+multipart.max-request-size=2000MB
 
-spring.servlet.multipart.max-file-size=1000MB
+spring.servlet.multipart.max-file-size=2000MB
-spring.servlet.multipart.max-request-size=1000MB
+spring.servlet.multipart.max-request-size=2000MB
 
 server.forward-headers-strategy=NATIVE
 

src/main/resources/messages_ar_AR.properties

@@ -81,8 +81,8 @@ home.changeMetadata.desc = \u062A\u063A\u064A\u064A\u0631 / \u0625\u0632\u0627\u
 home.fileToPDF.title=\u062A\u062D\u0648\u064A\u0644 \u0627\u0644\u0645\u0644\u0641 \u0625\u0644\u0649 PDF
 home.fileToPDF.desc=\u062A\u062D\u0648\u064A\u0644 \u0623\u064A \u0645\u0644\u0641 \u062A\u0642\u0631\u064A\u0628\u0627 \u0625\u0644\u0649 PDF (DOCX \u0648PNG \u0648XLS \u0648PPT \u0648TXT \u0648\u0627\u0644\u0645\u0632\u064A\u062F)
 
-home.ocr.title=\u062A\u0634\u063A\u064A\u0644 OCR \u0639\u0644\u0649 PDF
+home.ocr.title=\u062A\u0634\u063A\u064A\u0644 OCR \u0639\u0644\u0649 PDF \u0648 / \u0623\u0648 \u0645\u0633\u062D \u0636\u0648\u0626\u064A
-home.ocr.desc=\u0645\u0633\u062D \u0648\u0627\u0643\u062A\u0634\u0627\u0641 \u0627\u0644\u0646\u0635 \u0645\u0646 \u0627\u0644\u0635\u0648\u0631 \u062F\u0627\u062E\u0644 PDF \u0648\u0625\u0639\u0627\u062F\u0629 \u0625\u0636\u0627\u0641\u062A\u0647 \u0643\u0646\u0635.
+home.ocr.desc=\u064A\u0642\u0648\u0645 \u0628\u0631\u0646\u0627\u0645\u062C \u0627\u0644\u062A\u0646\u0638\u064A\u0641 \u0628\u0645\u0633\u062D \u0648\u0627\u0643\u062A\u0634\u0627\u0641 \u0627\u0644\u0646\u0635 \u0645\u0646 \u0627\u0644\u0635\u0648\u0631 \u062F\u0627\u062E\u0644 \u0645\u0644\u0641 PDF \u0648\u064A\u0639\u064A\u062F \u0625\u0636\u0627\u0641\u062A\u0647 \u0643\u0646\u0635
 
 home.extractImages.title=\u0627\u0633\u062A\u062E\u0631\u0627\u062C \u0627\u0644\u0635\u0648\u0631
 home.extractImages.desc=\u064A\u0633\u062A\u062E\u0631\u062C \u062C\u0645\u064A\u0639 \u0627\u0644\u0635\u0648\u0631 \u0645\u0646 \u0645\u0644\u0641 PDF \u0648\u064A\u062D\u0641\u0638\u0647\u0627 \u0641\u064A \u0627\u0644\u0631\u0645\u0632 \u0627\u0644\u0628\u0631\u064A\u062F\u064A
@@ -98,10 +98,18 @@ settings.downloadOption.3=\u062A\u0646\u0632\u064A\u0644 \u0627\u0644\u0645\u064
 settings.zipThreshold=\u0645\u0644\u0641\u0627\u062A \u0645\u0636\u063A\u0648\u0637\u0629 \u0639\u0646\u062F \u062A\u062C\u0627\u0648\u0632 \u0639\u062F\u062F \u0627\u0644\u0645\u0644\u0641\u0627\u062A \u0627\u0644\u062A\u064A \u062A\u0645 \u062A\u0646\u0632\u064A\u0644\u0647\u0627
 
 #OCR
-OCR.title = OCR
+ocr.title=\u0627\u0644\u062A\u0639\u0631\u0641 \u0627\u0644\u0636\u0648\u0626\u064A \u0639\u0644\u0649 \u0627\u0644\u062D\u0631\u0648\u0641 / \u062A\u0646\u0638\u064A\u0641 \u0627\u0644\u0645\u0633\u062D \u0627\u0644\u0636\u0648\u0626\u064A
-ocr.header=OCR (\u0627\u0644\u062A\u0639\u0631\u0641 \u0627\u0644\u0636\u0648\u0626\u064A \u0639\u0644\u0649 \u0627\u0644\u0623\u062D\u0631\u0641)
+ocr.header=\u0645\u0633\u062D \u0627\u0644\u0645\u0633\u062D \u0627\u0644\u0636\u0648\u0626\u064A / \u0627\u0644\u062A\u0639\u0631\u0641 \u0627\u0644\u0636\u0648\u0626\u064A \u0639\u0644\u0649 \u0627\u0644\u062D\u0631\u0648\u0641 (\u0627\u0644\u062A\u0639\u0631\u0641 \u0627\u0644\u0636\u0648\u0626\u064A \u0639\u0644\u0649 \u0627\u0644\u062D\u0631\u0648\u0641)
-ocr.selectText.1=\u062A\u062D\u062F\u064A\u062F \u0627\u0644\u0644\u063A\u0627\u062A \u0627\u0644\u062A\u064A \u0633\u064A\u062A\u0645 \u0627\u0643\u062A\u0634\u0627\u0641\u0647\u0627 \u062F\u0627\u062E\u0644 PDF (\u0627\u0644\u0644\u063A\u0627\u062A \u0627\u0644\u0645\u062F\u0631\u062C\u0629 \u0647\u064A \u062A\u0644\u0643 \u0627\u0644\u0645\u0643\u062A\u0634\u0641\u0629 \u062D\u0627\u0644\u064A\u0627):
+ocr.selectText.1=\u062D\u062F\u062F \u0627\u0644\u0644\u063A\u0627\u062A \u0627\u0644\u062A\u064A \u0633\u064A\u062A\u0645 \u0627\u0643\u062A\u0634\u0627\u0641\u0647\u0627 \u062F\u0627\u062E\u0644 \u0645\u0644\u0641 PDF (\u0627\u0644\u0644\u063A\u0627\u062A \u0627\u0644\u0645\u062F\u0631\u062C\u0629 \u0647\u064A \u062A\u0644\u0643 \u0627\u0644\u062A\u064A \u062A\u0645 \u0627\u0643\u062A\u0634\u0627\u0641\u0647\u0627 \u062D\u0627\u0644\u064A\u064B\u0627):
-ocr.selectText.2=\u0625\u0646\u062A\u0627\u062C \u0645\u0644\u0641 \u0646\u0635\u064A \u064A\u062D\u062A\u0648\u064A \u0639\u0644\u0649 \u0646\u0635 OCR \u062C\u0646\u0628\u0627 \u0625\u0644\u0649 \u062C\u0646\u0628 \u0645\u0639 \u0645\u0644\u0641 PDF OCR'ed
+ocr.selectText.2=\u0625\u0646\u062A\u0627\u062C \u0645\u0644\u0641 \u0646\u0635\u064A \u064A\u062D\u062A\u0648\u064A \u0639\u0644\u0649 \u0646\u0635 OCR \u0628\u062C\u0627\u0646\u0628 \u0645\u0644\u0641 PDF \u0627\u0644\u0630\u064A \u062A\u0645 \u0625\u0639\u062F\u0627\u062F\u0647 \u0628\u0648\u0627\u0633\u0637\u0629 OCR
+ocr.selectText.3=\u062A\u0645 \u0645\u0633\u062D \u0627\u0644\u0635\u0641\u062D\u0627\u062A \u0627\u0644\u0635\u062D\u064A\u062D\u0629 \u0636\u0648\u0626\u064A\u064B\u0627 \u0628\u0632\u0627\u0648\u064A\u0629 \u0645\u0646\u062D\u0631\u0641\u0629 \u0639\u0646 \u0637\u0631\u064A\u0642 \u062A\u062F\u0648\u064A\u0631\u0647\u0627 \u0645\u0631\u0629 \u0623\u062E\u0631\u0649 \u0641\u064A \u0645\u0643\u0627\u0646\u0647\u0627
+ocr.selectText.4=\u0635\u0641\u062D\u0629 \u0646\u0638\u064A\u0641\u0629 \u0644\u0630\u0644\u0643 \u0645\u0646 \u063A\u064A\u0631 \u0627\u0644\u0645\u062D\u062A\u0645\u0644 \u0623\u0646 \u064A\u062C\u062F OCR \u0646\u0635\u064B\u0627 \u0641\u064A \u0636\u0648\u0636\u0627\u0621 \u0627\u0644\u062E\u0644\u0641\u064A\u0629. (\u0644\u0627 \u064A\u0648\u062C\u062F \u062A\u063A\u064A\u064A\u0631 \u0641\u064A \u0627\u0644\u0625\u062E\u0631\u0627\u062C)
+ocr.selectText.5=\u0635\u0641\u062D\u0629 \u0646\u0638\u064A\u0641\u0629 \u060C \u0644\u0630\u0644\u0643 \u0645\u0646 \u063A\u064A\u0631 \u0627\u0644\u0645\u062D\u062A\u0645\u0644 \u0623\u0646 \u064A\u062C\u062F OCR \u0646\u0635\u064B\u0627 \u0641\u064A \u0636\u0648\u0636\u0627\u0621 \u0627\u0644\u062E\u0644\u0641\u064A\u0629 \u060C \u0648\u064A\u062D\u0627\u0641\u0638 \u0639\u0644\u0649 \u0627\u0644\u062A\u0646\u0638\u064A\u0641 \u0641\u064A \u0627\u0644\u0625\u062E\u0631\u0627\u062C.
+ocr.selectText.6=\u064A\u062A\u062C\u0627\u0647\u0644 \u0627\u0644\u0635\u0641\u062D\u0627\u062A \u0627\u0644\u062A\u064A \u062A\u062D\u062A\u0648\u064A \u0639\u0644\u0649 \u0646\u0635 \u062A\u0641\u0627\u0639\u0644\u064A \u060C \u0641\u0642\u0637 \u0635\u0641\u062D\u0627\u062A OCRs \u0627\u0644\u062A\u064A \u0647\u064A \u0635\u0648\u0631
+ocr.selectText.7=\u0641\u0631\u0636 \u0627\u0644\u062A\u0639\u0631\u0641 \u0627\u0644\u0636\u0648\u0626\u064A \u0639\u0644\u0649 \u0627\u0644\u062D\u0631\u0648\u0641 \u060C \u0633\u064A\u0624\u062F\u064A \u0627\u0644\u062A\u0639\u0631\u0641 \u0627\u0644\u0636\u0648\u0626\u064A \u0639\u0644\u0649 \u0627\u0644\u062D\u0631\u0648\u0641 \u0639\u0644\u0649 \u0643\u0644 \u0635\u0641\u062D\u0629 \u0625\u0644\u0649 \u0625\u0632\u0627\u0644\u0629 \u062C\u0645\u064A\u0639 \u0639\u0646\u0627\u0635\u0631 \u0627\u0644\u0646\u0635 \u0627\u0644\u0623\u0635\u0644\u064A
+ocr.selectText.8=\u0639\u0627\u062F\u064A (\u062E\u0637\u0623 \u0625\u0630\u0627 \u0643\u0627\u0646 PDF \u064A\u062D\u062A\u0648\u064A \u0639\u0644\u0649 \u0646\u0635)
+ocr.selectText.9=\u0625\u0639\u062F\u0627\u062F\u0627\u062A \u0625\u0636\u0627\u0641\u064A\u0629
+ocr.selectText.10=\u0648\u0636\u0639 \u0627\u0644\u062A\u0639\u0631\u0641 \u0627\u0644\u0636\u0648\u0626\u064A \u0639\u0644\u0649 \u0627\u0644\u062D\u0631\u0648\u0641
 ocr.help=\u064A\u0631\u062C\u0649 \u0642\u0631\u0627\u0621\u0629 \u0647\u0630\u0647 \u0627\u0644\u0648\u062B\u0627\u0626\u0642 \u062D\u0648\u0644 \u0643\u064A\u0641\u064A\u0629 \u0627\u0633\u062A\u062E\u062F\u0627\u0645 \u0647\u0630\u0627 \u0644\u0644\u063A\u0627\u062A \u0623\u062E\u0631\u0649 \u0648 / \u0623\u0648 \u0627\u0644\u0627\u0633\u062A\u062E\u062F\u0627\u0645 \u0644\u064A\u0633 \u0641\u064A \u0639\u0627\u0645\u0644 \u0627\u0644\u0625\u0631\u0633\u0627\u0621
 ocr.credit=\u062A\u0633\u062A\u062E\u062F\u0645 \u0647\u0630\u0647 \u0627\u0644\u062E\u062F\u0645\u0629 OCRmyPDF \u0648 Tesseract \u0644 OCR.
 ocr.submit=\u0645\u0639\u0627\u0644\u062C\u0629 PDF \u0628\u0627\u0633\u062A\u062E\u062F\u0627\u0645 OCR
@@ -287,3 +295,8 @@ xlsToPdf.title = \u062A\u062D\u0648\u064A\u0644 Excel \u0625\u0644\u0649 PDF
 xlsToPdf.header=\u062A\u062D\u0648\u064A\u0644 Excel \u0625\u0644\u0649 PDF
 xlsToPdf.selectText.1=\u062D\u062F\u062F \u0648\u0631\u0642\u0629 \u0625\u0643\u0633\u0644 XLS \u0623\u0648 XLSX \u0644\u0644\u062A\u062D\u0648\u064A\u0644
 xlsToPdf.convert=\u062A\u062D\u0648\u064A\u0644
+
+pdfToPDFA.title=PDF \u0625\u0644\u0649 PDF / A
+pdfToPDFA.header=PDF \u0625\u0644\u0649 PDF / A
+pdfToPDFA.credit=\u062A\u0633\u062A\u062E\u062F\u0645 \u0647\u0630\u0647 \u0627\u0644\u062E\u062F\u0645\u0629 OCRmyPDF \u0644\u062A\u062D\u0648\u064A\u0644 PDF / A.
+pdfToPDFA.submit=\u062A\u062D\u0648\u064A\u0644

src/main/resources/messages_de_DE.properties

@@ -76,8 +76,8 @@ home.changeMetadata.desc=
 home.fileToPDF.title=Datei in PDF konvertieren
 home.fileToPDF.desc=Konvertieren Sie nahezu jede Datei in PDF (DOCX, PNG, XLS, PPT, TXT und mehr)
 
-home.ocr.title=OCR auf PDF ausführen
+home.ocr.title=Führe OCR auf PDF- und/oder Cleanup-Scans aus
-home.ocr.desc=Scannt und erkennt Text aus Bildern in einer PDF-Datei und fügt ihn erneut als Text hinzu.
+home.ocr.desc=Cleanup scannt und erkennt Text aus Bildern in einer PDF-Datei und fügt ihn erneut als Text hinzu.
 
 home.extractImages.title=Bilder extrahieren
 home.extractImages.desc=Extrahiert alle Bilder aus einer PDF-Datei und speichert sie als Zip-Datei
@@ -93,10 +93,18 @@ settings.downloadOption.3=Datei herunterladen
 settings.zipThreshold=Dateien komprimieren, wenn die Anzahl der heruntergeladenen Dateien überschritten wird
 
 #OCR
-ocr.title=OCR
+ocr.title=OCR / Scan-Bereinigung
-ocr.header=OCR (Optische Zeichenerkennung)
+ocr.header=Scans bereinigen / OCR (Optical Character Recognition)
-ocr.selectText.1=Wählen Sie die Sprachen aus, die in der PDF-Datei erkannt werden sollen (die aufgelisteten sind die aktuell erkannten):
+ocr.selectText.1=Sprachen auswählen, die im PDF erkannt werden sollen (die aufgelisteten sind die aktuell erkannten):
-ocr.selectText.2=Textdatei mit OCR-Text neben der OCR-PDF-Datei erstellen
+ocr.selectText.2=Textdatei erzeugen, die OCR-Text neben dem OCR-bearbeiteten PDF enthält
+ocr.selectText.3=Korrekte Seiten wurden in einem schiefen Winkel gescannt, indem sie wieder an ihren Platz gedreht wurden
+ocr.selectText.4=Seite säubern, daher ist es weniger wahrscheinlich, dass OCR Text im Hintergrundrauschen findet. (Keine Ausgangsänderung)
+ocr.selectText.5=Seite säubern, sodass es weniger wahrscheinlich ist, dass OCR Text im Hintergrundrauschen findet, Bereinigung der Ausgabe wird beibehalten.
+ocr.selectText.6=Ignoriert Seiten mit interaktivem Text, nur OCR-Seiten, die Bilder sind
+ocr.selectText.7=OCR erzwingen, OCR wird jede Seite entfernen und alle ursprünglichen Textelemente entfernen
+ocr.selectText.8=Normal (Fehler, wenn PDF Text enthält)
+ocr.selectText.9=Zusätzliche Einstellungen
+ocr.selectText.10=OCR-Modus
 ocr.help=Bitte lesen Sie diese Dokumentation, um zu erfahren, wie Sie dies für andere Sprachen verwenden und/oder nicht in Docker verwenden können
 ocr.credit=Dieser Dienst verwendet OCRmyPDF und Tesseract für OCR.
 ocr.submit=PDF mit OCR verarbeiten
@@ -289,7 +297,10 @@ xlsToPdf.selectText.1=XLS- oder XLSX-Excel-Tabelle zum Konvertieren ausw
 xlsToPdf.convert=konvertieren
 
 
-
+pdfToPDFA.title=PDF zu PDF/A
+pdfToPDFA.header=PDF zu PDF/A
+pdfToPDFA.credit=Dieser Dienst verwendet OCRmyPDF für die PDF/A-Konvertierung
+pdfToPDFA.submit=Konvertieren
 
 
 

src/main/resources/messages_en_GB.properties

@@ -76,12 +76,15 @@ home.changeMetadata.desc=Change/Remove/Add metadata from a PDF document
 home.fileToPDF.title=Convert file to PDF
 home.fileToPDF.desc=Convert nearly any file to PDF (DOCX, PNG, XLS, PPT, TXT and more)
 
-home.ocr.title=Run OCR on PDF
+home.ocr.title=Run OCR on PDF and/or Cleanup scans
-home.ocr.desc=Scans and detects text from images within a PDF and re-adds it as text.
+home.ocr.desc=Cleanup scans and detects text from images within a PDF and re-adds it as text.
 
 home.extractImages.title=Extract Images
 home.extractImages.desc=Extracts all images from a PDF and saves them to zip
 
+home.pdfToPDFA.title=Convert PDF to PDF/A
+home.pdfToPDFA.desc=Convert PDF to PDF/A for long-term storage
+
 
 navbar.settings=Settings
 settings.title=Settings
@@ -93,15 +96,28 @@ settings.downloadOption.2=Open in new window
 settings.downloadOption.3=Download file
 settings.zipThreshold=Zip files when the number of downloaded files exceeds
 
+
+                            
+                            
 #OCR
-ocr.title=OCR
+ocr.title=OCR / Scan Cleanup
-ocr.header=OCR (Optical Character Recognition)
+ocr.header=Cleanup Scans / OCR (Optical Character Recognition)
 ocr.selectText.1=Select languages that are to be detected within the PDF (Ones listed are the ones currently detected):
 ocr.selectText.2=Produce text file containing OCR text alongside the OCR'ed PDF
+ocr.selectText.3=Correct pages were scanned at a skewed angle by rotating them back into place
+ocr.selectText.4=Clean page so its less likely that OCR will find text in background noise. (No output change)
+ocr.selectText.5=Clean page so its less likely that OCR will find text in background noise, maintains cleanup in output.
+ocr.selectText.6=Ignores pages that have interacive text on them, only OCRs pages that are images
+ocr.selectText.7=Force OCR, will OCR Every page removing all original text elements
+ocr.selectText.8=Normal (Will error if PDF contains text)
+ocr.selectText.9=Additional Settings
+ocr.selectText.10=OCR Mode
 ocr.help=Please read this documentation on how to use this for other languages and/or use not in docker
 ocr.credit=This service uses OCRmyPDF and Tesseract for OCR.
 ocr.submit=Process PDF with OCR
 
+
+
 extractImages.title=Extract Images
 extractImages.header=Extract Images
 extractImages.selectText=Select image format to convert extracted images to
@@ -286,6 +302,10 @@ xlsToPdf.convert=convert
 
 
 
+pdfToPDFA.title=PDF To PDF/A
+pdfToPDFA.header=PDF To PDF/A
+pdfToPDFA.credit=This service uses OCRmyPDF for PDF/A conversion
+pdfToPDFA.submit=Convert
 
 
 

src/main/resources/messages_en_US.properties

@@ -1,298 +0,0 @@
-###########
-# Generic #
-###########
-# the direction that the language is written (ltr = left to right, rtl = right to left)
-language.direction=ltr
-
-pdfPrompt=Select PDF(s)
-multiPdfPrompt=Select PDFs (2+)
-multiPdfDropPrompt=Select (or drag & drop) all PDFs you require
-imgPrompt=Select Image(s)
-genericSubmit=Submit
-processTimeWarning=Warning: This process can take up to a minute depending on file-size
-pageOrderPrompt=Page Order (Enter a comma-separated list of page numbers) :
-goToPage=Go
-true=True
-false=False
-unknown=Unknown
-save=Save
-close=Close
-
-#############
-# HOME-PAGE #
-#############
-home.desc=Your locally hosted one-stop-shop for all your PDF needs.
-
-navbar.convert=Convert
-navbar.security=Security
-navbar.other=Other
-navbar.darkmode=Dark Mode
-
-home.merge.title=Merge PDFs
-home.merge.desc=Easily merge multiple PDFs into one.
-
-home.split.title=Split PDFs
-home.split.desc=Split PDFs into multiple documents
-
-home.rotate.title=Rotate PDFs
-home.rotate.desc=Easily rotate your PDFs.
-
-home.imageToPdf.title=Image to PDF
-home.imageToPdf.desc=Convert a images (PNG, JPEG, GIF) to PDF.
-
-home.pdfToImage.title=PDF to Image
-home.pdfToImage.desc=Convert a PDF to a image. (PNG, JPEG, GIF)
-
-home.pdfOrganiser.title=PDF Organizer
-home.pdfOrganiser.desc=Remove/Rearrange pages in any order
-
-home.addImage.title=Add image onto PDF
-home.addImage.desc=Adds a image onto a set location on the PDF (Work in progress)
-
-home.watermark.title=Add Watermark
-home.watermark.desc=Add a custom watermark to your PDF document.
-
-home.remove-watermark.title=Remove Watermark
-home.remove-watermark.desc=Remove watermarks from your PDF document.
-
-home.permissions.title=Change Permissions
-home.permissions.desc=Change the permissions of your PDF document
-
-home.removePages.title=Remove Pages
-home.removePages.desc=Delete unwanted pages from your PDF document.
-
-home.addPassword.title=Add Password
-home.addPassword.desc=Encrypt your PDF document with a password.
-
-home.removePassword.title=Remove Password
-home.removePassword.desc=Remove password protection from your PDF document.
-
-home.compressPdfs.title=Compress PDFs
-home.compressPdfs.desc=Compress PDFs to reduce their file size.
-
-home.changeMetadata.title=Change Metadata
-home.changeMetadata.desc=Change/Remove/Add metadata from a PDF document
-
-home.fileToPDF.title=Convert file to PDF
-home.fileToPDF.desc=Convert nearly any file to PDF (DOCX, PNG, XLS, PPT, TXT and more)
-
-home.ocr.title=Run OCR on PDF
-home.ocr.desc=Scans and detects text from images within a PDF and re-adds it as text.
-
-home.extractImages.title=Extract Images
-home.extractImages.desc=Extracts all images from a PDF and saves them to zip
-
-
-navbar.settings=Settings
-settings.title=Settings
-settings.update=Update available
-settings.appVersion=App Version:
-settings.downloadOption.title=Choose download option (For single file non zip downloads):
-settings.downloadOption.1=Open in same window
-settings.downloadOption.2=Open in new window
-settings.downloadOption.3=Download file
-settings.zipThreshold=Zip files when the number of downloaded files exceeds
-
-#OCR
-ocr.title=OCR
-ocr.header=OCR (Optical Character Recognition)
-ocr.selectText.1=Select languages that are to be detected within the PDF (Ones listed are the ones currently detected):
-ocr.selectText.2=Produce text file containing OCR text alongside the OCR'ed PDF
-ocr.help=Please read this documentation on how to use this for other languages and/or use not in docker
-ocr.credit=This service uses OCRmyPDF and Tesseract for OCR.
-ocr.submit=Process PDF with OCR
-
-extractImages.title=Extract Images
-extractImages.header=Extract Images
-extractImages.selectText=Select image format to convert extracted images to
-extractImages.submit=Extract
-
-
-#File to PDF
-fileToPDF.title=File to PDF
-fileToPDF.header=Convert any file to PDF
-fileToPDF.credit=This service uses LibreOffice and Unoconv for file conversion.
-fileToPDF.supportedFileTypes=Supported file types should include the below however for a full updated list of supported formats, please refer to the LibreOffice documentation
-fileToPDF.submit=Convert to PDF
-
-
-#Add image
-addImage.title=Add Image
-addImage.header=Add image to PDF (Work in progress)
-addImage.submit=Add image
-
-#compress
-compress.title=Compress
-compress.header=Compress PDF
-compress.credit=This service uses OCRmyPDF for PDF Compress/Optimisation.
-compress.selectText.1=Optimization level:
-compress.selectText.2=0 (No optimization)
-compress.selectText.3=1 (Default, lossless optimization)
-compress.selectText.4=2 (Lossy optimization)
-compress.selectText.5=3 (Lossy optimization, more aggressive)
-compress.selectText.6=Enable fast web view (linearize PDF)
-compress.selectText.7=Enable lossy JBIG2 encoding
-compress.submit=Compress
-
-
-#merge
-merge.title=Merge
-merge.header=Merge multiple PDFs (2+)
-merge.submit=Merge
-
-#pdfOrganiser
-pdfOrganiser.title=Page Organizer
-pdfOrganiser.header=PDF Page Organizer
-pdfOrganiser.submit=Rearrange Pages
-
-
-#pageRemover
-pageRemover.title=Page Remover
-pageRemover.header=PDF Page remover
-pageRemover.pagesToDelete=Pages to delete (Enter a comma-separated list of page numbers) :
-pageRemover.submit=Delete Pages
-
-#rotate
-rotate.title=Rotate PDF
-rotate.header=Rotate PDF
-rotate.selectAngle=Select rotation angle (in multiples of 90 degrees):
-rotate.submit=Rotate
-
-
-
-
-#merge
-split.title=Split PDF
-split.header=Split PDF
-split.desc.1=The numbers you select are the page number you wish to do a split on
-split.desc.2=As such selecting 1,3,7-8 would split a 10 page document into 6 separate PDFS with:
-split.desc.3=Document #1: Page 1
-split.desc.4=Document #2: Page 2 and 3
-split.desc.5=Document #3: Page 4, 5 and 6
-split.desc.6=Document #4: Page 7
-split.desc.7=Document #5: Page 8
-split.desc.8=Document #6: Page 9 and 10
-split.splitPages=Enter pages to split on:
-split.submit=Split
-
-
-#merge
-imageToPDF.title=Image to PDF
-imageToPDF.header=Image to PDF
-imageToPDF.submit=Convert
-imageToPDF.selectText.1=Stretch to fit
-imageToPDF.selectText.2=Auto rotate PDF
-imageToPDF.selectText.3=Multi file logic (Only enabled if working with multiple images)
-imageToPDF.selectText.4=Merge into single PDF
-imageToPDF.selectText.5=Convert to separate PDFs
-
-#pdfToImage
-pdfToImage.title=PDF to Image
-pdfToImage.header=PDF to Image
-pdfToImage.selectText=Image Format
-pdfToImage.singleOrMultiple=Image result type
-pdfToImage.single=Single Big Image
-pdfToImage.multi=Multiple Images
-pdfToImage.colorType=Color type
-pdfToImage.color=Color
-pdfToImage.grey=Grayscale
-pdfToImage.blackwhite=Black and White (May lose data!)
-pdfToImage.submit=Convert
-
-
-#addPassword
-addPassword.title=Add Password
-addPassword.header=Add password (Encrypt)
-addPassword.selectText.1=Select PDF to encrypt
-addPassword.selectText.2=Password
-addPassword.selectText.3=Encryption Key Length
-addPassword.selectText.4=Higher values are stronger, but lower values have better compatibility.
-addPassword.selectText.5=Permissions to set
-addPassword.selectText.6=Prevent assembly of document
-addPassword.selectText.7=Prevent content extraction
-addPassword.selectText.8=Prevent extraction for accessibility
-addPassword.selectText.9=Prevent filling in form
-addPassword.selectText.10=Prevent modification
-addPassword.selectText.11=Prevent annotation modification
-addPassword.selectText.12=Prevent printing
-addPassword.selectText.13=Prevent printing different formats
-addPassword.submit=Encrypt
-
-#watermark
-watermark.title=Add Watermark
-watermark.header=Add Watermark
-watermark.selectText.1=Select PDF to add watermark to:
-watermark.selectText.2=Watermark Text:
-watermark.selectText.3=Font Size:
-watermark.selectText.4=Rotation (0-360):
-watermark.selectText.5=widthSpacer (Space between each watermark horizontally):
-watermark.selectText.6=heightSpacer (Space between each watermark vertically):
-watermark.selectText.7=Opacity (0% - 100%):
-watermark.submit=Add Watermark
-
-#remove-watermark
-remove-watermark.title=Remove Watermark
-remove-watermark.header=Remove Watermark
-remove-watermark.selectText.1=Select PDF to remove watermark from:
-remove-watermark.selectText.2=Watermark Text:
-remove-watermark.submit=Remove Watermark
-
-#Change permissions
-permissions.title=Change Permissions
-permissions.header=Change Permissions
-permissions.warning=Warning to have these permissions be unchangeable it is recommended to set them with a password via the add-password page
-permissions.selectText.1=Select PDF to change permissions
-permissions.selectText.2=Permissions to set
-permissions.selectText.3=Prevent assembly of document
-permissions.selectText.4=Prevent content extraction
-permissions.selectText.5=Prevent extraction for accessibility
-permissions.selectText.6=Prevent filling in form
-permissions.selectText.7=Prevent modification
-permissions.selectText.8=Prevent annotation modification
-permissions.selectText.9=Prevent printing
-permissions.selectText.10=Prevent printing different formats
-permissions.submit=Change
-
-#remove password
-removePassword.title=Remove password
-removePassword.header=Remove password (Decrypt)
-removePassword.selectText.1=Select PDF to Decrypt
-removePassword.selectText.2=Password
-removePassword.submit=Remove
-
-changeMetadata.title=Change Metadata
-changeMetadata.header=Change Metadata
-changeMetadata.selectText.1=Please edit the variables you wish to change
-changeMetadata.selectText.2=Delete all metadata
-changeMetadata.selectText.3=Show Custom Metadata:
-changeMetadata.author=Author:
-changeMetadata.creationDate=Creation Date (yyyy/MM/dd HH:mm:ss):
-changeMetadata.creator=Creator:
-changeMetadata.keywords=Keywords:
-changeMetadata.modDate=Modification Date (yyyy/MM/dd HH:mm:ss):
-changeMetadata.producer=Producer:
-changeMetadata.subject=Subject:
-changeMetadata.title=Title:
-changeMetadata.trapped=Trapped:
-changeMetadata.selectText.4=Other Metadata:
-changeMetadata.selectText.5=Add Custom Metadata Entry
-changeMetadata.submit=Change
-
-
-fileToPDF.credit=This service uses LibreOffice and Unoconv for file conversion.
-fileToPDF.supportedFileTypes=Supported file types should include the below however for a full updated list of supported formats, please refer to the LibreOffice documentation
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-

src/main/resources/messages_fr_FR.properties

@@ -81,8 +81,8 @@ home.changeMetadata.desc=Modifier/Supprimer/Ajouter des m
 home.fileToPDF.title=Convertir un fichier en PDF
 home.fileToPDF.desc=Convertissez presque n\u2019importe quel fichier en PDF (DOCX, PNG, XLS, PPT, TXT et plus)
 
-home.ocr.title=Exécuter OCR sur PDF
+home.ocr.title=Exécuter l'OCR sur les scans PDF et/ou de nettoyage
-home.ocr.desc=Analyse et détecte le texte des images d\u2019un fichier PDF et le rajoute en tant que texte.
+home.ocr.desc=Le nettoyage analyse et détecte le texte des images dans un PDF et le rajoute en tant que texte.
 
 home.extractImages.title=Extraire les images
 home.extractImages.desc=Extrait toutes les images d\u2019un PDF et les enregistre au format zip
@@ -100,10 +100,18 @@ settings.zipThreshold=Zip les fichiers lorsque le nombre de fichiers t
 
 
 #OCR
-ocr.title=OCR
+ocr.title=OCR / Nettoyage de numérisation
-ocr.header=OCR (reconnaissance optique de caractères)
+ocr.header=Nettoyage des scans / OCR (reconnaissance optique des caractères)
-ocr.selectText.1=Sélectionnez les langues à détecter dans le fichier PDF (celles répertoriées sont celles actuellement détectées) :
+ocr.selectText.1=Sélectionnez les langues à détecter dans le PDF (celles répertoriées sont celles actuellement détectées) :
-ocr.selectText.2=Produire un fichier texte contenant du texte OCR à côté du PDF OCR
+ocr.selectText.2=Produire un fichier texte contenant du texte OCR avec le PDF OCR
+ocr.selectText.3=Les pages correctes ont été numérisées à un angle oblique en les remettant en place
+ocr.selectText.4=Nettoyer la page pour qu'il soit moins probable que l'OCR trouve du texte dans le bruit de fond. (Pas de changement de sortie)
+ocr.selectText.5=Nettoyer la page afin qu'il soit moins probable que l'OCR trouve du texte dans le bruit de fond, maintient le nettoyage dans la sortie.
+ocr.selectText.6=Ignore les pages contenant du texte interactif, seulement les pages OCR qui sont des images
+ocr.selectText.7=Forcer l'OCR, OCR chaque page supprimera tous les éléments de texte d'origine
+ocr.selectText.8=Normal (Erreur si le PDF contient du texte)
+ocr.selectText.9=Paramètres supplémentaires
+ocr.selectText.10=Mode ROC
 ocr.help=Veuillez lire cette documentation pour savoir comment l\u2019utiliser pour d\u2019autres langues et/ou une utilisation non dans docker
 ocr.credit=Ce service utilise OCRmyPDF et Tesseract pour l\u2019OCR.
 ocr.submit=Traiter PDF avec OCR
@@ -292,3 +300,7 @@ xlsToPdf.header=Excel en PDF
 xlsToPdf.selectText.1=Sélectionnez une feuille Excel XLS ou XLSX à convertir
 xlsToPdf.convert=convertir
 
+pdfToPDFA.title=PDF vers PDF/A
+pdfToPDFA.header=PDF vers PDF/A
+pdfToPDFA.credit=Ce service utilise OCRmyPDF pour la conversion PDF/A
+pdfToPDFA.submit=Convertir

src/main/resources/templates/convert/pdf-to-pdfa.html

@@ -0,0 +1,31 @@
+<!DOCTYPE html>
+<html th:lang="${#locale.language}" th:lang-direction="#{language.direction}" xmlns:th="http://www.thymeleaf.org">
+
+<th:block th:insert="~{fragments/common :: head(title=#{pdfToPDFA.title})}"></th:block>
+
+
+<body>
+    <div id="page-container">
+        <div id="content-wrap">
+            <div th:insert="~{fragments/navbar.html :: navbar}"></div>
+            <br> <br>
+            <div class="container">
+                <div class="row justify-content-center">
+                    <div class="col-md-6">
+                        <h2 th:text="#{pdfToPDFA.header}"></h2>
+                        <p>Currently doesn't work for multiple inputs at once</p>
+                        <form method="post" enctype="multipart/form-data" th:action="@{pdf-to-pdfa}">
+                            <div th:replace="~{fragments/common :: fileSelector(name='fileInput', multiple=false, accept='application/pdf')}"></div>
+                            <br>
+                            <button type="submit" class="btn btn-primary" th:text="#{pdfToPDFA.submit}"></button>
+                        </form>
+                        <p class="mt-3" th:text="#{pdfToPDFA.credit}"></p>
+                    </div>
+                </div>
+            </div>
+
+        </div>
+        <div th:insert="~{fragments/footer.html :: footer}"></div>
+    </div>
+</body>
+</html>

src/main/resources/templates/fragments/common.html

@@ -3,7 +3,7 @@
 <!-- Metadata -->
 <meta charset="UTF-8">
 
-<title th:text="'S-PDF ' + ${title}"></title>
+<title th:text="${@appName} + (${title} != null and ${title} != '' ? ' - ' + ${title} : '')"></title>
 <link rel="shortcut icon" href="favicon.svg">
 <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
@@ -196,17 +196,17 @@ function toggleDarkMode() {
 
             async function submitMultiPdfForm(event, url) {
                 // Get the selected PDF files
-                var files = $('#fileInput-input')[0].files;
+                let files = $('#fileInput-input')[0].files;
 
                 // Get the existing form data
-                var formData = new FormData($('form')[0]);
+                let formData = new FormData($('form')[0]);
                 formData.delete('fileInput');
 
                 // Show the progress bar
                 $('#progressBarContainer').show();
 
                 // Initialize the progress bar
-                var progressBar = $('#progressBar');
+                let progressBar = $('#progressBar');
                 progressBar.css('width', '0%');
                 progressBar.attr('aria-valuenow', 0);
                 progressBar.attr('aria-valuemax', files.length);
@@ -221,39 +221,51 @@ function toggleDarkMode() {
                     jszip = new JSZip();
                 }
 
-                
                 // Submit each PDF file in parallel
-                var promises = [];
+                let promises = [];
-                for (var i = 0; i < files.length; i++) {
+                for (let i = 0; i < files.length; i++) {
-                    var promise = new Promise(function(resolve, reject) {
+                    let promise = new Promise(async function(resolve, reject) {
-                        var fileFormData = new FormData();
+                        let fileFormData = new FormData();
                         fileFormData.append('fileInput', files[i]);
-                        for (var pair of formData.entries()) {
+                        for (let pair of formData.entries()) {
                             fileFormData.append(pair[0], pair[1]);
                         }
                         console.log(fileFormData);
 
-                        fetch(url, {
+                        try {
+                            let response = await fetch(url, {
                                 method: 'POST',
                                 body: fileFormData
-                        }).then(function(response) {
+                            });
+
                             if (!response) {
                                 throw new Error('Received null response for file ' + i);
                             }
+
+                            if (!response.ok) {
+                                throw new Error(`Error submitting request for file ${i}: ${response.status} ${response.statusText}`);
+                            }
+
+                            let contentDisposition = response.headers.get('content-disposition');
+                            let fileName = "file.pdf"
+                            if (!contentDisposition) {
+                                //throw new Error('Content-Disposition header not found for file ' + i);
+                            } else {
+                            	fileName = contentDisposition.split('filename=')[1].replace(/"/g, '');
+                            }
                             console.log('Received response for file ' + i + ': ' + response);
 
-                            var contentDisposition = response.headers.get('content-disposition');
-                            var fileName = contentDisposition.split('filename=')[1].replace(/"/g, '');
   
-                            response.blob().then(function (blob) {
+
+                            let blob = await response.blob();
                             if (zipFiles) {
                                 // Add the file to the ZIP archive
                                 jszip.file(fileName, blob);
                                 resolve();
                             } else {
                                 // Download the file directly
-                                  var url = window.URL.createObjectURL(blob);
+                                let url = window.URL.createObjectURL(blob);
-                                  var a = document.createElement('a');
+                                let a = document.createElement('a');
                                 a.href = url;
                                 a.download = fileName;
                                 document.body.appendChild(a);
@@ -261,29 +273,25 @@ function toggleDarkMode() {
                                 a.remove();
                                 resolve();
                             }
-                              });
+                        } catch (error) {
-                            
-                        }).catch(function(error) {
                             console.error('Error submitting request for file ' + i + ': ' + error);
 
                             // Set default values or fallbacks for error properties
-                            var status = error && error.status || 500;
+                            let status = error && error.status || 500;
-                            var statusText = error && error.statusText || 'Internal Server Error';
+                            let statusText = error && error.statusText || 'Internal Server Error';
-                            var message = error && error.message || 'An error occurred while processing your request.';
+                            let message = error && error.message || 'An error occurred while processing your request.';
 
                             // Reject the Promise to signal that the request has failed
                             reject();
                             // Redirect to error page with Spring Boot error parameters
-                            var url = '/error?status=' + status + '&error=' + encodeURIComponent(statusText) + '&message=' + encodeURIComponent(message);
+                            let url = '/error?status=' + status + '&error=' + encodeURIComponent(statusText) + '&message=' + encodeURIComponent(message);
                             window.location.href = url;
-                        });
+                        }
                     });
 
                     // Update the progress bar as each request finishes
                     promise.then(function() {
-                        var progress = ((progressBar.attr('aria-valuenow') / files.length) * 100) + (100 / files.length);
+                        updateProgressBar(progressBar, files);
-                        progressBar.css('width', progress + '%');
-                        progressBar.attr('aria-valuenow', parseInt(progressBar.attr('aria-valuenow')) + 1);
                     });
 
                     promises.push(promise);
@@ -302,17 +310,26 @@ function toggleDarkMode() {
 
                 // After all requests are finished, download the ZIP file if needed
                 if (zipFiles) {
-                  jszip.generateAsync({ type: "blob" }).then(function (content) {
+                    try {
-                    var url = window.URL.createObjectURL(content);
+                        let content = await jszip.generateAsync({ type: "blob" });
-                    var a = document.createElement('a');
+                        let url = window.URL.createObjectURL(content);
+                        let a = document.createElement('a');
                         a.href = url;
                         a.download = "files.zip";
                         document.body.appendChild(a);
                         a.click();
                         a.remove();
-                  });
+                    } catch (error) {
+                        console.error('Error generating ZIP file: ' + error);
                     }
                 }
+            }
+            function updateProgressBar(progressBar, files) {
+            	let progress = ((progressBar.attr('aria-valuenow') / files.length) * 100) + (100 / files.length);
+            	progressBar.css('width', progress + '%');
+            	progressBar.attr('aria-valuenow', parseInt(progressBar.attr('aria-valuenow')) + 1);
+        	}
+
             
             
 

src/main/resources/templates/fragments/footer.html

@@ -3,5 +3,6 @@
         <a href="https://github.com/Frooodle/Stirling-PDF" target="_blank" class="mx-1"><img src="images/github.svg"></img></a>
         <a href="https://hub.docker.com/r/frooodle/s-pdf" target="_blank" class="mx-1"><img src="images/docker.svg"></img></a>
         <a href="https://discord.gg/Cn8pWhQRxZ" target="_blank" class="mx-1"><img src="images/discord.svg"></img></a>
+        <div th:if="${@appName} != 'Stirling PDF'" class="mt-2" style="color: grey;">Powered by Stirling PDF</div>
     </footer>
 </div>

src/main/resources/templates/fragments/navbar.html

@@ -109,7 +109,7 @@ function compareVersions(version1, version2) {
     <nav class="navbar navbar-expand-lg navbar-light bg-light">
         <div class="container ">
 
-            <a class="navbar-brand" href="#" th:href="@{/}">Stirling PDF</a>
+            <a class="navbar-brand" href="#" th:href="@{/}" th:text="${@appName}"></a>
 
             <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbarNav" aria-controls="navbarNav" aria-expanded="false" aria-label="Toggle navigation">
                 <span class="navbar-toggler-icon"></span>
@@ -127,12 +127,13 @@ function compareVersions(version1, version2) {
 
                     <li class="nav-item"><a class="nav-link" href="#" th:href="@{rotate-pdf}" th:classappend="${currentPage}=='rotate-pdf' ? 'active' : ''" th:text="#{home.rotate.title}"></a></li>
 
-                    <li class="nav-item dropdown" th:classappend="${currentPage}=='pdf-to-img' OR ${currentPage}=='img-to-pdf' OR ${currentPage}=='file-to-pdf' OR ${currentPage}=='xlsx-to-pdf' ? 'active' : ''"><a class="nav-link dropdown-toggle" href="#" id="navbarDropdown" role="button" data-toggle="dropdown"
+                    <li class="nav-item dropdown" th:classappend="${currentPage}=='pdf-to-img' OR ${currentPage}=='img-to-pdf' OR ${currentPage}=='pdf-to-pdfa' OR ${currentPage}=='file-to-pdf' OR ${currentPage}=='xlsx-to-pdf' ? 'active' : ''"><a class="nav-link dropdown-toggle" href="#" id="navbarDropdown" role="button" data-toggle="dropdown"
                         aria-haspopup="true" aria-expanded="false" th:text="#{navbar.convert}"></a>
                         <div class="dropdown-menu" aria-labelledby="navbarDropdown">
                             <a class="dropdown-item" href="#" th:href="@{pdf-to-img}" th:classappend="${currentPage}=='pdf-to-img' ? 'active' : ''" th:text="#{home.pdfToImage.title}"></a> 
                             <a class="dropdown-item" href="#" th:href="@{img-to-pdf}" th:classappend="${currentPage}=='img-to-pdf' ? 'active' : ''" th:text="#{home.imageToPdf.title}"></a> 
                             <a class="dropdown-item" href="#" th:href="@{file-to-pdf}" th:classappend="${currentPage}=='file-to-pdf' ? 'active' : ''" th:text="#{home.fileToPDF.title}"></a>
+                            <a class="dropdown-item" href="#" th:href="@{pdf-to-pdfa}" th:classappend="${currentPage}=='pdf-to-pdfa' ? 'active' : ''" th:text="#{home.pdfToPDFA.title}"></a>
                         </div>
                     </li>
 
@@ -172,8 +173,7 @@ function compareVersions(version1, version2) {
                         </svg>
                          </a>
                         <div class="dropdown-menu" aria-labelledby="languageDropdown">
-                            <a class="dropdown-item lang_dropdown-item" href="" data-language-code="en_US">English (US)</a> 
+                            <a class="dropdown-item lang_dropdown-item" href="" data-language-code="en_GB">English</a> 
-                            <a class="dropdown-item lang_dropdown-item" href="" data-language-code="en_GB">English (UK)</a> 
                             <a class="dropdown-item lang_dropdown-item" href="" data-language-code="ar_AR">العربية</a>
                             <a class="dropdown-item lang_dropdown-item" href="" data-language-code="de_DE">Deutsch</a> 
                             <a class="dropdown-item lang_dropdown-item" href="" data-language-code="fr_FR">Français</a>

src/main/resources/templates/home.html

@@ -33,7 +33,7 @@
             <!-- Jumbotron -->
             <div class="jumbotron jumbotron-fluid" id="jumbotron">
                 <div class="container">
-                    <h1 class="display-4">Stirling PDF</h1>
+                    <h1 class="display-4" th:text="${@appName}"></h1>
                     <p class="lead" th:text="#{home.desc}"></p>
                 </div>
             </div>
@@ -64,6 +64,7 @@
                 
                 <div th:replace="~{fragments/card :: card(cardTitle=#{home.ocr.title}, cardText=#{home.ocr.desc}, cardLink='ocr-pdf')}"></div>
                 <div th:replace="~{fragments/card :: card(cardTitle=#{home.extractImages.title}, cardText=#{home.extractImages.desc}, cardLink='extract-images')}"></div>
+                <div th:replace="~{fragments/card :: card(cardTitle=#{home.pdfToPDFA.title}, cardText=#{home.pdfToPDFA.desc}, cardLink='pdf-to-pdfa')}"></div>
                 
                 
                 

src/main/resources/templates/ocr-pdf.html

@@ -19,17 +19,42 @@
                             <div th:replace="~{fragments/common :: fileSelector(name='fileInput', multiple=false, accept='application/pdf')}"></div>
                             <div class="form-group">
                                 <label for="languages" class="form-label" th:text="#{ocr.selectText.1}"></label>
+                                <hr>
                                 <div id="languages">
-							        <div th:each="language: ${languages}">
+                                    <div th:each="language, iterStat : ${languages}" >
                                         <input type="checkbox" class="form-check-input" th:name="languages" th:value="${language}" th:id="${'language-' + language}" />
                                         <label class="form-check-label" th:for="${'language-' + language}" th:text="  ${language}"></label>
                                     </div>
                                 </div>
+                                <hr>
                             </div>
-						<!--  	<div class="form-group">
+                            <div class="form-group">
+                                <label th:text="#{ocr.selectText.10}"></label> 
+                                <select class="form-control" name="ocrType">
+                                    <option value="skip-text" th:text="#{ocr.selectText.6}"></option>
+                                    <option value="force-ocr" th:text="#{ocr.selectText.7}"></option>
+                                    <option value="Normal" th:text="#{ocr.selectText.8}"></option>
+                                </select>
+                            </div>
+                            <br>
+                            <label for="languages" class="form-label" th:text="#{ocr.selectText.9}"></label>
+                            <div class="form-check">
                                 <input type="checkbox" class="form-check-input" name="sidecar" id="sidecar" />
                                 <label class="form-check-label" for="sidecar" th:text="#{ocr.selectText.2}"></label>
-						    </div> -->
+                            </div>
+                            <div class="form-check">
+                                <input type="checkbox" class="form-check-input" name="deskew" id="deskew" />
+                                <label class="form-check-label" for="deskew" th:text="#{ocr.selectText.3}"></label>
+                            </div>
+                            <div class="form-check">
+                                <input type="checkbox" class="form-check-input" name="clean" id="clean" />
+                                <label class="form-check-label" for="clean" th:text="#{ocr.selectText.4}"></label>
+                            </div>
+                            <div class="form-check">
+                                <input type="checkbox" class="form-check-input" name="clean-final" id="clean-final" />
+                                <label class="form-check-label" for="clean-final" th:text="#{ocr.selectText.5}"></label>
+                            </div>
+                            <br>
                             <button type="submit" class="btn btn-primary" th:text="#{ocr.submit}"></button>
                         </form>
                         <p th:text="#{ocr.credit}"></p>