mirror of
https://github.com/Frooodle/Stirling-PDF.git
synced 2025-09-03 17:52:30 +02:00
pdfa
This commit is contained in:
parent
7bac488ca4
commit
80820e75c9
@ -53,9 +53,10 @@ public class CompressController {
|
||||
command.add("--skip-text");
|
||||
command.add("--tesseract-timeout=0");
|
||||
command.add("--optimize");
|
||||
command.add(String.valueOf(optimizeLevel));
|
||||
command.add("--output-type");
|
||||
command.add("pdf");
|
||||
command.add(String.valueOf(optimizeLevel));
|
||||
|
||||
|
||||
if (fastWebView != null && fastWebView) {
|
||||
long fileSize = inputFile.getSize();
|
||||
|
@ -1,5 +1,6 @@
|
||||
package stirling.software.SPDF.controller.converters;
|
||||
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Path;
|
||||
@ -7,6 +8,8 @@ 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;
|
||||
@ -15,10 +18,58 @@ 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 "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("[.][^.]+$", "") + "_PDFA.pdf";
|
||||
HttpHeaders headers = new HttpHeaders();
|
||||
headers.setContentType(MediaType.APPLICATION_PDF);
|
||||
headers.setContentDispositionFormData("attachment", outputFilename);
|
||||
return ResponseEntity.ok().headers(headers).body(pdfBytes);
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
@ -82,6 +82,9 @@ home.ocr.desc=Scans and detects text from images within a PDF and re-adds it as
|
||||
home.extractImages.title=Extract Images
|
||||
home.extractImages.desc=Extracts all images from a PDF and saves them to zip
|
||||
|
||||
home.pdfToPDFA.title=Convert PDF to PDF/A
|
||||
home.pdfToPDFA.desc=Convert PDF to PDF/A for long-term storage
|
||||
|
||||
|
||||
navbar.settings=Settings
|
||||
settings.title=Settings
|
||||
@ -113,6 +116,12 @@ ocr.help=Please read this documentation on how to use this for other languages a
|
||||
ocr.credit=This service uses OCRmyPDF and Tesseract for OCR.
|
||||
ocr.submit=Process PDF with OCR
|
||||
|
||||
|
||||
pdfToPDFA.title=PDF To PDF/A
|
||||
pdfToPDFA.header=PDF To PDF/A
|
||||
pdfToPDFA.credit=This service uses OCRmyPDF for PDF/A conversion
|
||||
pdfToPDFA.submit=Convert
|
||||
|
||||
extractImages.title=Extract Images
|
||||
extractImages.header=Extract Images
|
||||
extractImages.selectText=Select image format to convert extracted images to
|
||||
|
30
src/main/resources/templates/convert/pdf-to-pdfa.html
Normal file
30
src/main/resources/templates/convert/pdf-to-pdfa.html
Normal file
@ -0,0 +1,30 @@
|
||||
<!DOCTYPE html>
|
||||
<html th:lang="${#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>
|
||||
<form method="post" enctype="multipart/form-data" th:action="@{file-to-pdf}">
|
||||
<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>
|
@ -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>
|
||||
|
||||
|
@ -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>
|
||||
|
||||
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user