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

Fix pdfa conversion (#1907)

Browse Source 
* fix: use gs to convert to pdfa and return output by reading file as bytes

* feat: update translation files for pdfToPDFA.credit

* Hardening suggestions for Stirling-PDF / fix_pdfa_conversion (#1908)

Switch order of literals to prevent NullPointerException

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
This commit is contained in:
Eric
2024-09-15 10:01:33 -07:00
committed by GitHub
parent c6c33d611a
commit b13b925bf0
38 changed files with 67 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
src/main/java/stirling/software/SPDF/controller/api/converters/ConvertPDFToPDFA.java
View File

@@ -1,22 +1,15 @@
package stirling.software.SPDF.controller.api.converters;
import java.io.ByteArrayOutputStream;
import java.io.FileOutputStream;
import java.io.OutputStream;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.List;
import java.util.stream.Collectors;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDDocumentCatalog;
import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
import org.apache.pdfbox.pdmodel.interactive.form.PDField;
import org.apache.pdfbox.pdmodel.interactive.form.PDSignatureField;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.ModelAttribute;
import org.springframework.web.bind.annotation.PostMapping;
@@ -29,7 +22,6 @@ import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.model.api.converters.PdfToPdfARequest;
import stirling.software.SPDF.service.CustomPDDocumentFactory;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@@ -41,13 +33,6 @@ public class ConvertPDFToPDFA {
private static final Logger logger = LoggerFactory.getLogger(ConvertPDFToPDFA.class);
private final CustomPDDocumentFactory pdfDocumentFactory;
@Autowired
public ConvertPDFToPDFA(CustomPDDocumentFactory pdfDocumentFactory) {
this.pdfDocumentFactory = pdfDocumentFactory;
}
@PostMapping(consumes = "multipart/form-data", value = "/pdf/pdfa")
@Operation(
summary = "Convert a PDF to a PDF/A",
@@ -61,32 +46,7 @@ public class ConvertPDFToPDFA {
// Convert MultipartFile to byte[]
byte[] pdfBytes = inputFile.getBytes();
// Load the PDF document
PDDocument document = pdfDocumentFactory.load(pdfBytes);
// Get the document catalog
PDDocumentCatalog catalog = document.getDocumentCatalog();
// Get the AcroForm
PDAcroForm acroForm = catalog.getAcroForm();
if (acroForm != null) {
// Remove signature fields safely
List<PDField> fieldsToRemove =
acroForm.getFields().stream()
.filter(field -> field instanceof PDSignatureField)
.collect(Collectors.toList());
if (!fieldsToRemove.isEmpty()) {
acroForm.flatten(fieldsToRemove, false);
ByteArrayOutputStream baos = new ByteArrayOutputStream();
document.save(baos);
pdfBytes = baos.toByteArray();
}
}
document.close();
// Save the uploaded (and possibly modified) file to a temporary location
// Save the uploaded file to a temporary location
Path tempInputFile = Files.createTempFile("input_", ".pdf");
try (OutputStream outputStream = new FileOutputStream(tempInputFile.toFile())) {
outputStream.write(pdfBytes);
@@ -95,28 +55,37 @@ public class ConvertPDFToPDFA {
// Prepare the output file path
Path tempOutputFile = Files.createTempFile("output_", ".pdf");
// Prepare the OCRmyPDF command
// Prepare the ghostscript command
List<String> command = new ArrayList<>();
command.add("ocrmypdf");
command.add("--skip-text");
command.add("--tesseract-timeout=0");
command.add("--output-type");
command.add(outputFormat.toString());
command.add(tempInputFile.toString());
command.add("gs");
command.add("-dPDFA=" + ("pdfa".equals(outputFormat) ? "2" : "1"));
command.add("-dNOPAUSE");
command.add("-dBATCH");
command.add("-sColorConversionStrategy=UseDeviceIndependentColor");
command.add("-sDEVICE=pdfwrite");
command.add("-dPDFACompatibilityPolicy=2");
command.add("-o");
command.add(tempOutputFile.toString());
command.add(tempInputFile.toString());
ProcessExecutorResult returnCode =
ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF)
ProcessExecutor.getInstance(ProcessExecutor.Processes.GHOSTSCRIPT)
.runCommandWithOutputHandling(command);
if (returnCode.getRc() != 0) {
logger.info(
outputFormat + " conversion failed with return code: " + returnCode.getRc());
}
try {
PDDocument doc = pdfDocumentFactory.load(tempOutputFile.toFile());
byte[] pdfBytesOutput = Files.readAllBytes(tempOutputFile);
// Return the optimized PDF as a response
String outputFilename =
Filenames.toSimpleFileName(inputFile.getOriginalFilename())
.replaceFirst("[.][^.]+$", "")
+ "_PDFA.pdf";
return WebResponseUtils.pdfDocToWebResponse(doc, outputFilename);
return WebResponseUtils.bytesToWebResponse(
pdfBytesOutput, outputFilename, MediaType.APPLICATION_PDF);
} finally {
// Clean up the temporary files
Files.deleteIfExists(tempInputFile);