This commit is contained in:
Anthony Stirling
2024-05-05 13:33:17 +01:00
committed by GitHub
parent d6b1fec69d
commit ac5273244c
33 changed files with 145 additions and 38 deletions

View File

@@ -0,0 +1,84 @@
package stirling.software.SPDF.controller.api.misc;
import java.awt.image.BufferedImage;
import java.io.IOException;
import org.apache.pdfbox.Loader;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.graphics.image.JPEGFactory;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
import org.apache.pdfbox.rendering.ImageType;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.springframework.http.ResponseEntity;
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.multipart.MultipartFile;
import io.github.pixee.security.Filenames;
import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.model.PdfMetadata;
import stirling.software.SPDF.model.api.misc.FlattenRequest;
import stirling.software.SPDF.utils.PdfUtils;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@RequestMapping("/api/v1/misc")
@Tag(name = "Misc", description = "Miscellaneous APIs")
public class FlattenController {
@PostMapping(consumes = "multipart/form-data", value = "/flatten")
@Operation(
summary = "Flatten PDF form fields or full page",
description =
"Flattening just PDF form fields or converting each page to images to make text unselectable. Input: PDF, Output: PDF. Type: SISO")
public ResponseEntity<byte[]> flatten(@ModelAttribute FlattenRequest request) throws Exception {
MultipartFile file = request.getFileInput();
PDDocument document = Loader.loadPDF(file.getBytes());
PdfMetadata metadata = PdfUtils.extractMetadataFromPdf(document);
Boolean flattenOnlyForms = request.getFlattenOnlyForms();
if (Boolean.TRUE.equals(flattenOnlyForms)) {
PDAcroForm acroForm = document.getDocumentCatalog().getAcroForm();
if (acroForm != null) {
acroForm.flatten();
}
return WebResponseUtils.pdfDocToWebResponse(
document, Filenames.toSimpleFileName(file.getOriginalFilename()));
} else {
// flatten whole page aka convert each page to image and readd it (making text
// unselectable)
PDFRenderer pdfRenderer = new PDFRenderer(document);
PDDocument newDocument = new PDDocument();
int numPages = document.getNumberOfPages();
for (int i = 0; i < numPages; i++) {
try {
BufferedImage image = pdfRenderer.renderImageWithDPI(i, 300, ImageType.RGB);
PDPage page = new PDPage();
page.setMediaBox(document.getPage(i).getMediaBox());
newDocument.addPage(page);
try (PDPageContentStream contentStream =
new PDPageContentStream(newDocument, page)) {
PDImageXObject pdImage = JPEGFactory.createFromImage(newDocument, image);
float pageWidth = page.getMediaBox().getWidth();
float pageHeight = page.getMediaBox().getHeight();
contentStream.drawImage(pdImage, 0, 0, pageWidth, pageHeight);
}
} catch (IOException e) {
e.printStackTrace();
}
}
PdfUtils.setMetadataToPdf(newDocument, metadata);
return WebResponseUtils.pdfDocToWebResponse(
newDocument, Filenames.toSimpleFileName(file.getOriginalFilename()));
}
}
}