mirror of
https://github.com/arsvendg/Stirling-PDF.git
synced 2026-03-18 05:46:49 +01:00
eol
This commit is contained in:
@@ -1,171 +1,171 @@
|
||||
package stirling.software.SPDF.controller.api.security;
|
||||
|
||||
import java.io.IOException;
|
||||
|
||||
import org.apache.pdfbox.cos.COSDictionary;
|
||||
import org.apache.pdfbox.cos.COSName;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDDocumentCatalog;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDPageTree;
|
||||
import org.apache.pdfbox.pdmodel.PDResources;
|
||||
import org.apache.pdfbox.pdmodel.common.PDMetadata;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDAction;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDActionJavaScript;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDActionLaunch;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDActionURI;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDFormFieldAdditionalActions;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationLink;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationWidget;
|
||||
import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
|
||||
import org.apache.pdfbox.pdmodel.interactive.form.PDField;
|
||||
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.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
|
||||
import stirling.software.SPDF.model.api.security.SanitizePdfRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/security")
|
||||
@Tag(name = "Security", description = "Security APIs")
|
||||
public class SanitizeController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/sanitize-pdf")
|
||||
@Operation(
|
||||
summary = "Sanitize a PDF file",
|
||||
description =
|
||||
"This endpoint processes a PDF file and removes specific elements based on the provided options. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> sanitizePDF(@ModelAttribute SanitizePdfRequest request)
|
||||
throws IOException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
boolean removeJavaScript = request.isRemoveJavaScript();
|
||||
boolean removeEmbeddedFiles = request.isRemoveEmbeddedFiles();
|
||||
boolean removeMetadata = request.isRemoveMetadata();
|
||||
boolean removeLinks = request.isRemoveLinks();
|
||||
boolean removeFonts = request.isRemoveFonts();
|
||||
|
||||
try (PDDocument document = PDDocument.load(inputFile.getInputStream())) {
|
||||
if (removeJavaScript) {
|
||||
sanitizeJavaScript(document);
|
||||
}
|
||||
|
||||
if (removeEmbeddedFiles) {
|
||||
sanitizeEmbeddedFiles(document);
|
||||
}
|
||||
|
||||
if (removeMetadata) {
|
||||
sanitizeMetadata(document);
|
||||
}
|
||||
|
||||
if (removeLinks) {
|
||||
sanitizeLinks(document);
|
||||
}
|
||||
|
||||
if (removeFonts) {
|
||||
sanitizeFonts(document);
|
||||
}
|
||||
|
||||
return WebResponseUtils.pdfDocToWebResponse(
|
||||
document,
|
||||
inputFile.getOriginalFilename().replaceFirst("[.][^.]+$", "")
|
||||
+ "_sanitized.pdf");
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeJavaScript(PDDocument document) throws IOException {
|
||||
// Get the root dictionary (catalog) of the PDF
|
||||
PDDocumentCatalog catalog = document.getDocumentCatalog();
|
||||
|
||||
// Get the Names dictionary
|
||||
COSDictionary namesDict =
|
||||
(COSDictionary) catalog.getCOSObject().getDictionaryObject(COSName.NAMES);
|
||||
|
||||
if (namesDict != null) {
|
||||
// Get the JavaScript dictionary
|
||||
COSDictionary javaScriptDict =
|
||||
(COSDictionary) namesDict.getDictionaryObject(COSName.getPDFName("JavaScript"));
|
||||
|
||||
if (javaScriptDict != null) {
|
||||
// Remove the JavaScript dictionary
|
||||
namesDict.removeItem(COSName.getPDFName("JavaScript"));
|
||||
}
|
||||
}
|
||||
|
||||
for (PDPage page : document.getPages()) {
|
||||
for (PDAnnotation annotation : page.getAnnotations()) {
|
||||
if (annotation instanceof PDAnnotationWidget) {
|
||||
PDAnnotationWidget widget = (PDAnnotationWidget) annotation;
|
||||
PDAction action = widget.getAction();
|
||||
if (action instanceof PDActionJavaScript) {
|
||||
widget.setAction(null);
|
||||
}
|
||||
}
|
||||
}
|
||||
PDAcroForm acroForm = document.getDocumentCatalog().getAcroForm();
|
||||
if (acroForm != null) {
|
||||
for (PDField field : acroForm.getFields()) {
|
||||
PDFormFieldAdditionalActions actions = field.getActions();
|
||||
if (actions != null) {
|
||||
if (actions.getC() instanceof PDActionJavaScript) {
|
||||
actions.setC(null);
|
||||
}
|
||||
if (actions.getF() instanceof PDActionJavaScript) {
|
||||
actions.setF(null);
|
||||
}
|
||||
if (actions.getK() instanceof PDActionJavaScript) {
|
||||
actions.setK(null);
|
||||
}
|
||||
if (actions.getV() instanceof PDActionJavaScript) {
|
||||
actions.setV(null);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeEmbeddedFiles(PDDocument document) {
|
||||
PDPageTree allPages = document.getPages();
|
||||
|
||||
for (PDPage page : allPages) {
|
||||
PDResources res = page.getResources();
|
||||
|
||||
// Remove embedded files from the PDF
|
||||
res.getCOSObject().removeItem(COSName.getPDFName("EmbeddedFiles"));
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeMetadata(PDDocument document) {
|
||||
PDMetadata metadata = document.getDocumentCatalog().getMetadata();
|
||||
if (metadata != null) {
|
||||
document.getDocumentCatalog().setMetadata(null);
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeLinks(PDDocument document) throws IOException {
|
||||
for (PDPage page : document.getPages()) {
|
||||
for (PDAnnotation annotation : page.getAnnotations()) {
|
||||
if (annotation instanceof PDAnnotationLink) {
|
||||
PDAction action = ((PDAnnotationLink) annotation).getAction();
|
||||
if (action instanceof PDActionLaunch || action instanceof PDActionURI) {
|
||||
((PDAnnotationLink) annotation).setAction(null);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeFonts(PDDocument document) {
|
||||
for (PDPage page : document.getPages()) {
|
||||
page.getResources().getCOSObject().removeItem(COSName.getPDFName("Font"));
|
||||
}
|
||||
}
|
||||
}
|
||||
package stirling.software.SPDF.controller.api.security;
|
||||
|
||||
import java.io.IOException;
|
||||
|
||||
import org.apache.pdfbox.cos.COSDictionary;
|
||||
import org.apache.pdfbox.cos.COSName;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDDocumentCatalog;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDPageTree;
|
||||
import org.apache.pdfbox.pdmodel.PDResources;
|
||||
import org.apache.pdfbox.pdmodel.common.PDMetadata;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDAction;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDActionJavaScript;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDActionLaunch;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDActionURI;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDFormFieldAdditionalActions;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationLink;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationWidget;
|
||||
import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
|
||||
import org.apache.pdfbox.pdmodel.interactive.form.PDField;
|
||||
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.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
|
||||
import stirling.software.SPDF.model.api.security.SanitizePdfRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/security")
|
||||
@Tag(name = "Security", description = "Security APIs")
|
||||
public class SanitizeController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/sanitize-pdf")
|
||||
@Operation(
|
||||
summary = "Sanitize a PDF file",
|
||||
description =
|
||||
"This endpoint processes a PDF file and removes specific elements based on the provided options. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> sanitizePDF(@ModelAttribute SanitizePdfRequest request)
|
||||
throws IOException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
boolean removeJavaScript = request.isRemoveJavaScript();
|
||||
boolean removeEmbeddedFiles = request.isRemoveEmbeddedFiles();
|
||||
boolean removeMetadata = request.isRemoveMetadata();
|
||||
boolean removeLinks = request.isRemoveLinks();
|
||||
boolean removeFonts = request.isRemoveFonts();
|
||||
|
||||
try (PDDocument document = PDDocument.load(inputFile.getInputStream())) {
|
||||
if (removeJavaScript) {
|
||||
sanitizeJavaScript(document);
|
||||
}
|
||||
|
||||
if (removeEmbeddedFiles) {
|
||||
sanitizeEmbeddedFiles(document);
|
||||
}
|
||||
|
||||
if (removeMetadata) {
|
||||
sanitizeMetadata(document);
|
||||
}
|
||||
|
||||
if (removeLinks) {
|
||||
sanitizeLinks(document);
|
||||
}
|
||||
|
||||
if (removeFonts) {
|
||||
sanitizeFonts(document);
|
||||
}
|
||||
|
||||
return WebResponseUtils.pdfDocToWebResponse(
|
||||
document,
|
||||
inputFile.getOriginalFilename().replaceFirst("[.][^.]+$", "")
|
||||
+ "_sanitized.pdf");
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeJavaScript(PDDocument document) throws IOException {
|
||||
// Get the root dictionary (catalog) of the PDF
|
||||
PDDocumentCatalog catalog = document.getDocumentCatalog();
|
||||
|
||||
// Get the Names dictionary
|
||||
COSDictionary namesDict =
|
||||
(COSDictionary) catalog.getCOSObject().getDictionaryObject(COSName.NAMES);
|
||||
|
||||
if (namesDict != null) {
|
||||
// Get the JavaScript dictionary
|
||||
COSDictionary javaScriptDict =
|
||||
(COSDictionary) namesDict.getDictionaryObject(COSName.getPDFName("JavaScript"));
|
||||
|
||||
if (javaScriptDict != null) {
|
||||
// Remove the JavaScript dictionary
|
||||
namesDict.removeItem(COSName.getPDFName("JavaScript"));
|
||||
}
|
||||
}
|
||||
|
||||
for (PDPage page : document.getPages()) {
|
||||
for (PDAnnotation annotation : page.getAnnotations()) {
|
||||
if (annotation instanceof PDAnnotationWidget) {
|
||||
PDAnnotationWidget widget = (PDAnnotationWidget) annotation;
|
||||
PDAction action = widget.getAction();
|
||||
if (action instanceof PDActionJavaScript) {
|
||||
widget.setAction(null);
|
||||
}
|
||||
}
|
||||
}
|
||||
PDAcroForm acroForm = document.getDocumentCatalog().getAcroForm();
|
||||
if (acroForm != null) {
|
||||
for (PDField field : acroForm.getFields()) {
|
||||
PDFormFieldAdditionalActions actions = field.getActions();
|
||||
if (actions != null) {
|
||||
if (actions.getC() instanceof PDActionJavaScript) {
|
||||
actions.setC(null);
|
||||
}
|
||||
if (actions.getF() instanceof PDActionJavaScript) {
|
||||
actions.setF(null);
|
||||
}
|
||||
if (actions.getK() instanceof PDActionJavaScript) {
|
||||
actions.setK(null);
|
||||
}
|
||||
if (actions.getV() instanceof PDActionJavaScript) {
|
||||
actions.setV(null);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeEmbeddedFiles(PDDocument document) {
|
||||
PDPageTree allPages = document.getPages();
|
||||
|
||||
for (PDPage page : allPages) {
|
||||
PDResources res = page.getResources();
|
||||
|
||||
// Remove embedded files from the PDF
|
||||
res.getCOSObject().removeItem(COSName.getPDFName("EmbeddedFiles"));
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeMetadata(PDDocument document) {
|
||||
PDMetadata metadata = document.getDocumentCatalog().getMetadata();
|
||||
if (metadata != null) {
|
||||
document.getDocumentCatalog().setMetadata(null);
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeLinks(PDDocument document) throws IOException {
|
||||
for (PDPage page : document.getPages()) {
|
||||
for (PDAnnotation annotation : page.getAnnotations()) {
|
||||
if (annotation instanceof PDAnnotationLink) {
|
||||
PDAction action = ((PDAnnotationLink) annotation).getAction();
|
||||
if (action instanceof PDActionLaunch || action instanceof PDActionURI) {
|
||||
((PDAnnotationLink) annotation).setAction(null);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private void sanitizeFonts(PDDocument document) {
|
||||
for (PDPage page : document.getPages()) {
|
||||
page.getResources().getCOSObject().removeItem(COSName.getPDFName("Font"));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user