Sanataize PDF improvements (#3251)

# Description of Changes Please provide a summary of the changes, including: - Make distinction between metadata removal and XMP metadata removal - Change file loaders to only edit metadata for certain ops Closes #(issue_number) --- ## Checklist ### General - [ ] I have read the [Contribution Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md) - [ ] I have read the [Stirling-PDF Developer Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md) (if applicable) - [ ] I have read the [How to add new languages to Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md) (if applicable) - [ ] I have performed a self-review of my own code - [ ] My changes generate no new warnings ### Documentation - [ ] I have updated relevant docs on [Stirling-PDF's doc repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/) (if functionality has heavily changed) - [ ] I have read the section [Add New Translation Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags) (for new translation tags only) ### UI Changes (if applicable) - [ ] Screenshots or videos demonstrating the UI changes are attached (e.g., as comments or direct attachments in the PR) ### Testing (if applicable) - [ ] I have tested my changes locally. Refer to the [Testing Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/DeveloperGuide.md#6-testing) for more details.
2025-06-03 15:52:01 +00:00 · 2025-03-26 10:53:22 +00:00 · 2025-03-26 10:53:22 +00:00 · 5ce941dda0
commit 5ce941dda0
parent e2ba296320
45 changed files with 175 additions and 83 deletions
--- a/src/main/java/stirling/software/SPDF/controller/api/misc/MetadataController.java
+++ b/src/main/java/stirling/software/SPDF/controller/api/misc/MetadataController.java
@ -86,7 +86,7 @@ public class MetadataController {
            allRequestParams = new java.util.HashMap<String, String>();
        }
        // Load the PDF file into a PDDocument
-        PDDocument document = pdfDocumentFactory.load(pdfFile);
+        PDDocument document = pdfDocumentFactory.load(pdfFile, true);

        // Get the document information from the PDF
        PDDocumentInformation info = document.getDocumentInformation();
--- a/src/main/java/stirling/software/SPDF/controller/api/security/SanitizeController.java
+++ b/src/main/java/stirling/software/SPDF/controller/api/security/SanitizeController.java
@ -51,11 +51,12 @@ public class SanitizeController {
        MultipartFile inputFile = request.getFileInput();
        boolean removeJavaScript = request.isRemoveJavaScript();
        boolean removeEmbeddedFiles = request.isRemoveEmbeddedFiles();
+        boolean removeXMPMetadata = request.isRemoveXMPMetadata();
        boolean removeMetadata = request.isRemoveMetadata();
        boolean removeLinks = request.isRemoveLinks();
        boolean removeFonts = request.isRemoveFonts();

-        PDDocument document = pdfDocumentFactory.load(inputFile);
+        PDDocument document = pdfDocumentFactory.load(inputFile, true);
        if (removeJavaScript) {
            sanitizeJavaScript(document);
        }
@ -64,10 +65,14 @@ public class SanitizeController {
            sanitizeEmbeddedFiles(document);
        }

-        if (removeMetadata) {
-            sanitizeMetadata(document);
+        if (removeXMPMetadata) {
+        	sanitizeXMPMetadata(document);
        }

+        if (removeMetadata) {
+        	sanitizeDocumentInfoMetadata(document);
+        }
+      
        if (removeLinks) {
            sanitizeLinks(document);
        }
@ -145,7 +150,7 @@ public class SanitizeController {
        }
    }

-    private void sanitizeMetadata(PDDocument document) {
+    private void sanitizeXMPMetadata(PDDocument document) {
        if (document.getDocumentCatalog() != null) {
            PDMetadata metadata = document.getDocumentCatalog().getMetadata();
            if (metadata != null) {
@ -153,6 +158,16 @@ public class SanitizeController {
            }
        }
    }
+    
+    private void sanitizeDocumentInfoMetadata(PDDocument document) {
+        PDDocumentInformation docInfo = document.getDocumentInformation();
+        if (docInfo != null) {
+            PDDocumentInformation newInfo = new PDDocumentInformation();
+            document.setDocumentInformation(newInfo);
+        }
+    }
+
+

    private void sanitizeLinks(PDDocument document) throws IOException {
        for (PDPage page : document.getPages()) {
--- a/src/main/java/stirling/software/SPDF/model/api/security/SanitizePdfRequest.java
+++ b/src/main/java/stirling/software/SPDF/model/api/security/SanitizePdfRequest.java
@ -17,9 +17,12 @@ public class SanitizePdfRequest extends PDFFile {
    @Schema(description = "Remove embedded files from the PDF", defaultValue = "false")
    private boolean removeEmbeddedFiles;

-    @Schema(description = "Remove metadata from the PDF", defaultValue = "false")
-    private boolean removeMetadata;
+    @Schema(description = "Remove XMP metadata from the PDF", defaultValue = "false")
+    private boolean removeXMPMetadata;

+    @Schema(description = "Remove document info metadata from the PDF", defaultValue = "false")
+    private boolean removeMetadata;
+    
    @Schema(description = "Remove links from the PDF", defaultValue = "false")
    private boolean removeLinks;

--- a/src/main/java/stirling/software/SPDF/service/CustomPDFDocumentFactory.java
+++ b/src/main/java/stirling/software/SPDF/service/CustomPDFDocumentFactory.java
@ -68,10 +68,18 @@ public class CustomPDFDocumentFactory {
    }

    /**
-     * Main entry point for loading a PDF document from a file. Automatically selects the most
-     * appropriate loading strategy.
-     */
+    * Main entry point for loading a PDF document from a file. Automatically selects the most
+    * appropriate loading strategy.
+    */
    public PDDocument load(File file) throws IOException {
+        return load(file, false);
+    }
+
+    /**
+    * Main entry point for loading a PDF document from a file with read-only option.
+    * Automatically selects the most appropriate loading strategy.
+    */
+    public PDDocument load(File file, boolean readOnly) throws IOException {
        if (file == null) {
            throw new IllegalArgumentException("File cannot be null");
        }
@ -79,14 +87,26 @@ public class CustomPDFDocumentFactory {
        long fileSize = file.length();
        log.debug("Loading PDF from file, size: {}MB", fileSize / (1024 * 1024));

-        return loadAdaptively(file, fileSize);
+        PDDocument doc = loadAdaptively(file, fileSize);
+        if (!readOnly) {
+            postProcessDocument(doc);
+        }
+        return doc;
    }

    /**
-     * Main entry point for loading a PDF document from a Path. Automatically selects the most
-     * appropriate loading strategy.
-     */
+    * Main entry point for loading a PDF document from a Path. Automatically selects the most
+    * appropriate loading strategy.
+    */
    public PDDocument load(Path path) throws IOException {
+        return load(path, false);
+    }
+
+    /**
+    * Main entry point for loading a PDF document from a Path with read-only option.
+    * Automatically selects the most appropriate loading strategy.
+    */
+    public PDDocument load(Path path, boolean readOnly) throws IOException {
        if (path == null) {
            throw new IllegalArgumentException("File cannot be null");
        }
@ -94,11 +114,20 @@ public class CustomPDFDocumentFactory {
        long fileSize = Files.size(path);
        log.debug("Loading PDF from file, size: {}MB", fileSize / (1024 * 1024));

-        return loadAdaptively(path.toFile(), fileSize);
+        PDDocument doc = loadAdaptively(path.toFile(), fileSize);
+        if (!readOnly) {
+            postProcessDocument(doc);
+        }
+        return doc;
    }

    /** Load a PDF from byte array with automatic optimization. */
    public PDDocument load(byte[] input) throws IOException {
+        return load(input, false);
+    }
+
+    /** Load a PDF from byte array with automatic optimization and read-only option. */
+    public PDDocument load(byte[] input, boolean readOnly) throws IOException {
        if (input == null) {
            throw new IllegalArgumentException("Input bytes cannot be null");
        }
@ -106,11 +135,20 @@ public class CustomPDFDocumentFactory {
        long dataSize = input.length;
        log.debug("Loading PDF from byte array, size: {}MB", dataSize / (1024 * 1024));

-        return loadAdaptively(input, dataSize);
+        PDDocument doc = loadAdaptively(input, dataSize);
+        if (!readOnly) {
+            postProcessDocument(doc);
+        }
+        return doc;
    }

    /** Load a PDF from InputStream with automatic optimization. */
    public PDDocument load(InputStream input) throws IOException {
+        return load(input, false);
+    }
+
+    /** Load a PDF from InputStream with automatic optimization and read-only option. */
+    public PDDocument load(InputStream input, boolean readOnly) throws IOException {
        if (input == null) {
            throw new IllegalArgumentException("InputStream cannot be null");
        }
@ -119,11 +157,20 @@ public class CustomPDFDocumentFactory {
        Path tempFile = createTempFile("pdf-stream-");

        Files.copy(input, tempFile, StandardCopyOption.REPLACE_EXISTING);
-        return loadAdaptively(tempFile.toFile(), Files.size(tempFile));
+        PDDocument doc = loadAdaptively(tempFile.toFile(), Files.size(tempFile));
+        if (!readOnly) {
+            postProcessDocument(doc);
+        }
+        return doc;
    }

    /** Load with password from InputStream */
    public PDDocument load(InputStream input, String password) throws IOException {
+        return load(input, password, false);
+    }
+
+    /** Load with password from InputStream and read-only option */
+    public PDDocument load(InputStream input, String password, boolean readOnly) throws IOException {
        if (input == null) {
            throw new IllegalArgumentException("InputStream cannot be null");
        }
@ -132,9 +179,54 @@ public class CustomPDFDocumentFactory {
        Path tempFile = createTempFile("pdf-stream-");

        Files.copy(input, tempFile, StandardCopyOption.REPLACE_EXISTING);
-        return loadAdaptivelyWithPassword(tempFile.toFile(), Files.size(tempFile), password);
+        PDDocument doc = loadAdaptivelyWithPassword(tempFile.toFile(), Files.size(tempFile), password);
+        if (!readOnly) {
+            postProcessDocument(doc);
+        }
+        return doc;
    }

+    /** Load from a file path string */
+    public PDDocument load(String path) throws IOException {
+        return load(path, false);
+    }
+
+    /** Load from a file path string with read-only option */
+    public PDDocument load(String path, boolean readOnly) throws IOException {
+        return load(new File(path), readOnly);
+    }
+
+    /** Load from a PDFFile object */
+    public PDDocument load(PDFFile pdfFile) throws IOException {
+        return load(pdfFile, false);
+    }
+
+    /** Load from a PDFFile object with read-only option */
+    public PDDocument load(PDFFile pdfFile, boolean readOnly) throws IOException {
+    	return load(pdfFile.getFileInput(), readOnly);
+    }
+
+    /** Load from a MultipartFile */
+    public PDDocument load(MultipartFile pdfFile) throws IOException {
+        return load(pdfFile, false);
+    }
+
+    /** Load from a MultipartFile with read-only option */
+    public PDDocument load(MultipartFile pdfFile, boolean readOnly) throws IOException {
+       return  load(pdfFile.getInputStream(), readOnly);
+
+    }
+
+    /** Load with password from MultipartFile */
+    public PDDocument load(MultipartFile fileInput, String password) throws IOException {
+        return load(fileInput, password, false);
+    }
+
+    /** Load with password from MultipartFile with read-only option */
+    public PDDocument load(MultipartFile fileInput, String password, boolean readOnly) throws IOException {
+    	return load(fileInput.getInputStream(), password, readOnly);
+    }
+    
    /**
     * Determine the appropriate caching strategy based on file size and available memory. This
     * common method is used by both password and non-password loading paths.
@ -197,8 +289,6 @@ public class CustomPDFDocumentFactory {
        } else {
            throw new IllegalArgumentException("Unsupported source type: " + source.getClass());
        }
-
-        postProcessDocument(document);
        return document;
    }

@ -220,8 +310,6 @@ public class CustomPDFDocumentFactory {
        } else {
            throw new IllegalArgumentException("Unsupported source type: " + source.getClass());
        }
-
-        postProcessDocument(document);
        return document;
    }

@ -384,23 +472,4 @@ public class CustomPDFDocumentFactory {
        }
    }

-    /** Load from a file path string */
-    public PDDocument load(String path) throws IOException {
-        return load(new File(path));
-    }
-
-    /** Load from a PDFFile object */
-    public PDDocument load(PDFFile pdfFile) throws IOException {
-        return load(pdfFile.getFileInput());
-    }
-
-    /** Load from a MultipartFile */
-    public PDDocument load(MultipartFile pdfFile) throws IOException {
-        return load(pdfFile.getInputStream());
-    }
-
-    /** Load with password from MultipartFile */
-    public PDDocument load(MultipartFile fileInput, String password) throws IOException {
-        return load(fileInput.getInputStream(), password);
-    }
 }
--- a/src/main/resources/messages_ar_AR.properties
+++ b/src/main/resources/messages_ar_AR.properties
@ -733,7 +733,7 @@ sanitizePDF.title=تنظيف PDF
 sanitizePDF.header=تنظيف ملف PDF
 sanitizePDF.selectText.1=إزالة إجراءات جافا سكريبت
 sanitizePDF.selectText.2=إزالة الملفات المضمنة
-sanitizePDF.selectText.3=إزالة البيانات الوصفية
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=إزالة الروابط
 sanitizePDF.selectText.5=إزالة الخطوط
 sanitizePDF.submit=تنظيف PDF
--- a/src/main/resources/messages_az_AZ.properties
+++ b/src/main/resources/messages_az_AZ.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF-i Təmizlə
 sanitizePDF.header=PDF Faylını Təmizlə
 sanitizePDF.selectText.1=JavaScript Fəaliyyətlərini Sil
 sanitizePDF.selectText.2=Daxil Edilmiş Faylları Sil
-sanitizePDF.selectText.3=Metadatanı Sil
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Linkləri Sil
 sanitizePDF.selectText.5=Şriftləri Sil
 sanitizePDF.submit=PDF-i Təmizlə
--- a/src/main/resources/messages_bg_BG.properties
+++ b/src/main/resources/messages_bg_BG.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Дезинфектирай PDF
 sanitizePDF.header=Дезинфектира PDF файл
 sanitizePDF.selectText.1=Премахва JavaScript действия
 sanitizePDF.selectText.2=Премахва вградени файлове
-sanitizePDF.selectText.3=Премахва метаданни
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Премахва линкове
 sanitizePDF.selectText.5=Премахва шрифтове
 sanitizePDF.submit=Дезинфектирай PDF
--- a/src/main/resources/messages_ca_CA.properties
+++ b/src/main/resources/messages_ca_CA.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Neteja PDF
 sanitizePDF.header=Neteja un fitxer PDF
 sanitizePDF.selectText.1=Elimina accions JavaScript
 sanitizePDF.selectText.2=Elimina fitxers incrustats
-sanitizePDF.selectText.3=Elimina metadades
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Elimina enllaços
 sanitizePDF.selectText.5=Elimina fonts
 sanitizePDF.submit=Neteja PDF
--- a/src/main/resources/messages_cs_CZ.properties
+++ b/src/main/resources/messages_cs_CZ.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Sanitizovat PDF
 sanitizePDF.header=Sanitizovat PDF soubor
 sanitizePDF.selectText.1=Odstranit JavaScript akce
 sanitizePDF.selectText.2=Odstranit vložené soubory
-sanitizePDF.selectText.3=Odstranit metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Odstranit odkazy
 sanitizePDF.selectText.5=Odstranit písma
 sanitizePDF.submit=Sanitizovat PDF
--- a/src/main/resources/messages_da_DK.properties
+++ b/src/main/resources/messages_da_DK.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Rens PDF
 sanitizePDF.header=Rens en PDF-fil
 sanitizePDF.selectText.1=Fjern JavaScript-handlinger
 sanitizePDF.selectText.2=Fjern indlejrede filer
-sanitizePDF.selectText.3=Fjern metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Fjern links
 sanitizePDF.selectText.5=Fjern skrifttyper
 sanitizePDF.submit=Rens PDF
--- a/src/main/resources/messages_de_DE.properties
+++ b/src/main/resources/messages_de_DE.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF Bereinigen
 sanitizePDF.header=PDF Bereinigen
 sanitizePDF.selectText.1=Javascript-Aktionen entfernen
 sanitizePDF.selectText.2=Eingebettete Dateien entfernen
-sanitizePDF.selectText.3=Metadaten entfernen
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Links entfernen
 sanitizePDF.selectText.5=Schriftarten entfernen
 sanitizePDF.submit=Bereinigen
--- a/src/main/resources/messages_el_GR.properties
+++ b/src/main/resources/messages_el_GR.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Εξυγίανση PDF
 sanitizePDF.header=Εξυγίανση αρχείου PDF
 sanitizePDF.selectText.1=Αφαίρεση ενεργειών JavaScript
 sanitizePDF.selectText.2=Αφαίρεση ενσωματωμένων αρχείων
-sanitizePDF.selectText.3=Αφαίρεση μεταδεδομένων
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Αφαίρεση συνδέσμων
 sanitizePDF.selectText.5=Αφαίρεση γραμματοσειρών
 sanitizePDF.submit=Εξυγίανση PDF
--- a/src/main/resources/messages_en_GB.properties
+++ b/src/main/resources/messages_en_GB.properties
@ -733,9 +733,10 @@ sanitizePDF.title=Sanitize PDF
 sanitizePDF.header=Sanitize a PDF file
 sanitizePDF.selectText.1=Remove JavaScript actions
 sanitizePDF.selectText.2=Remove embedded files
-sanitizePDF.selectText.3=Remove metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Remove links
 sanitizePDF.selectText.5=Remove fonts
+sanitizePDF.selectText.6=Remove Document Info Metadata
 sanitizePDF.submit=Sanitize PDF


--- a/src/main/resources/messages_en_US.properties
+++ b/src/main/resources/messages_en_US.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Sanitize PDF
 sanitizePDF.header=Sanitize a PDF file
 sanitizePDF.selectText.1=Remove JavaScript actions
 sanitizePDF.selectText.2=Remove embedded files
-sanitizePDF.selectText.3=Remove metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Remove links
 sanitizePDF.selectText.5=Remove fonts
 sanitizePDF.submit=Sanitize PDF
--- a/src/main/resources/messages_es_ES.properties
+++ b/src/main/resources/messages_es_ES.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Limpiar archivo PDF
 sanitizePDF.header=Limpiar un archivo PDF
 sanitizePDF.selectText.1=Eliminar código JavaScript
 sanitizePDF.selectText.2=Eliminar archivos incrustados
-sanitizePDF.selectText.3=Eliminar metadatos
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Eliminar enlaces
 sanitizePDF.selectText.5=Eliminar fuentes
 sanitizePDF.submit=Limpiar PDF
--- a/src/main/resources/messages_eu_ES.properties
+++ b/src/main/resources/messages_eu_ES.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF-a desinfektatu
 sanitizePDF.header=PDF fitxategi bat desinfektatu
 sanitizePDF.selectText.1=Ezabatu JavaScript akzioak
 sanitizePDF.selectText.2=Ezabatu embedded fitxategiak
-sanitizePDF.selectText.3=Ezabatu metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Ezabatu esketak
 sanitizePDF.selectText.5=Ezabatu iturri letrak
 sanitizePDF.submit=Desinfektatu PDF
--- a/src/main/resources/messages_fa_IR.properties
+++ b/src/main/resources/messages_fa_IR.properties
@ -733,7 +733,7 @@ sanitizePDF.title=پاکسازی PDF
 sanitizePDF.header=پاکسازی یک فایل PDF
 sanitizePDF.selectText.1=حذف عملیات جاوااسکریپت
 sanitizePDF.selectText.2=حذف فایل‌های جاسازی شده
-sanitizePDF.selectText.3=حذف متاداده‌ها
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=حذف لینک‌ها
 sanitizePDF.selectText.5=حذف فونت‌ها
 sanitizePDF.submit=پاکسازی PDF
--- a/src/main/resources/messages_fr_FR.properties
+++ b/src/main/resources/messages_fr_FR.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Assainir
 sanitizePDF.header=Assainir
 sanitizePDF.selectText.1=Supprimer les actions JavaScript
 sanitizePDF.selectText.2=Supprimer les fichiers intégrés
-sanitizePDF.selectText.3=Supprimer les métadonnées
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Supprimer les liens
 sanitizePDF.selectText.5=Supprimer les polices
 sanitizePDF.submit=Assainir
--- a/src/main/resources/messages_ga_IE.properties
+++ b/src/main/resources/messages_ga_IE.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF sláintíocht
 sanitizePDF.header=Glanadh comhad PDF
 sanitizePDF.selectText.1=Bain gníomhartha JavaScript
 sanitizePDF.selectText.2=Bain comhaid leabaithe
-sanitizePDF.selectText.3=Bain meiteashonraí
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Bain naisc
 sanitizePDF.selectText.5=Bain clónna
 sanitizePDF.submit=PDF sláintíocht
--- a/src/main/resources/messages_hi_IN.properties
+++ b/src/main/resources/messages_hi_IN.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF सैनिटाइज़ करें
 sanitizePDF.header=PDF फ़ाइल सैनिटाइज़ करें
 sanitizePDF.selectText.1=जावास्क्रिप्ट क्रियाएं हटाएं
 sanitizePDF.selectText.2=एम्बेडेड फ़ाइलें हटाएं
-sanitizePDF.selectText.3=मेटाडेटा हटाएं
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=लिंक हटाएं
 sanitizePDF.selectText.5=फ़ॉन्ट्स हटाएं
 sanitizePDF.submit=PDF सैनिटाइज़ करें
--- a/src/main/resources/messages_hr_HR.properties
+++ b/src/main/resources/messages_hr_HR.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Sanirajte PDF
 sanitizePDF.header=Sanirajte PDF datoteku
 sanitizePDF.selectText.1=Ukloni JavaScript akcije
 sanitizePDF.selectText.2=Ukloni ugrađene datoteke
-sanitizePDF.selectText.3=Ukloni metapodatke
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Ukloni poveznice
 sanitizePDF.selectText.5=Uklonite fontove
 sanitizePDF.submit=Sanirajte PDF
--- a/src/main/resources/messages_hu_HU.properties
+++ b/src/main/resources/messages_hu_HU.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF tisztítása
 sanitizePDF.header=PDF fájl tisztítása
 sanitizePDF.selectText.1=JavaScript műveletek eltávolítása
 sanitizePDF.selectText.2=Beágyazott fájlok eltávolítása
-sanitizePDF.selectText.3=Metaadatok eltávolítása
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Hivatkozások eltávolítása
 sanitizePDF.selectText.5=Betűtípusok eltávolítása
 sanitizePDF.submit=PDF tisztítása
--- a/src/main/resources/messages_id_ID.properties
+++ b/src/main/resources/messages_id_ID.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Bersihkan PDF
 sanitizePDF.header=Membersihkan berkas PDF
 sanitizePDF.selectText.1=Hapus tindakan JavaScript
 sanitizePDF.selectText.2=Hapus berkas yang disematkan
-sanitizePDF.selectText.3=Hapus metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Hapus tautan
 sanitizePDF.selectText.5=Hapus font
 sanitizePDF.submit=Membersihkan PDF
--- a/src/main/resources/messages_it_IT.properties
+++ b/src/main/resources/messages_it_IT.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Pulire PDF
 sanitizePDF.header=Pulisci un file PDF
 sanitizePDF.selectText.1=Rimuovi le azioni JavaScript
 sanitizePDF.selectText.2=Rimuovi i file incorporati
-sanitizePDF.selectText.3=Rimuovi i metadati
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Rimuovi collegamenti
 sanitizePDF.selectText.5=Rimuovi i font
 sanitizePDF.submit=Pulisci PDF
--- a/src/main/resources/messages_ja_JP.properties
+++ b/src/main/resources/messages_ja_JP.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDFをサニタイズ
 sanitizePDF.header=PDFファイルをサニタイズ
 sanitizePDF.selectText.1=JavaScriptアクションを削除
 sanitizePDF.selectText.2=埋め込みファイルを削除
-sanitizePDF.selectText.3=メタデータを削除
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=リンクを削除
 sanitizePDF.selectText.5=フォントを削除
 sanitizePDF.submit=PDFをサニタイズする
--- a/src/main/resources/messages_ko_KR.properties
+++ b/src/main/resources/messages_ko_KR.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF 정리
 sanitizePDF.header=PDF 파일 정리
 sanitizePDF.selectText.1=JavaScript 작업 제거
 sanitizePDF.selectText.2=임베디드 파일 제거
-sanitizePDF.selectText.3=메타데이터 제거
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=링크 제거
 sanitizePDF.selectText.5=글꼴 제거
 sanitizePDF.submit=PDF 정리
--- a/src/main/resources/messages_nl_NL.properties
+++ b/src/main/resources/messages_nl_NL.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF opschonen
 sanitizePDF.header=Een PDF-bestand opschonen
 sanitizePDF.selectText.1=Verwijder Javascript-acties
 sanitizePDF.selectText.2=Verwijder ingebedde bestanden
-sanitizePDF.selectText.3=Verwijder metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Verwijder links
 sanitizePDF.selectText.5=Verwijder lettertypen
 sanitizePDF.submit=PDF opschonen
--- a/src/main/resources/messages_no_NB.properties
+++ b/src/main/resources/messages_no_NB.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Rensker PDF
 sanitizePDF.header=Rensker en PDF fil
 sanitizePDF.selectText.1=Fjern JavaScript-handlinger
 sanitizePDF.selectText.2=Fjern innebygde filer
-sanitizePDF.selectText.3=Fjern metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Fjern lenker
 sanitizePDF.selectText.5=Fjern skrifter
 sanitizePDF.submit=Rensk PDF
--- a/src/main/resources/messages_pl_PL.properties
+++ b/src/main/resources/messages_pl_PL.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Dezynfekuj PDF
 sanitizePDF.header=Dezynfekuj dokument PDF
 sanitizePDF.selectText.1=Usuń elementy JavaScript
 sanitizePDF.selectText.2=Usuń załączone pliki
-sanitizePDF.selectText.3=Usuń metadane
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Usuń linki
 sanitizePDF.selectText.5=Usuń czcionki
 sanitizePDF.submit=Dezynfekuj PDF
--- a/src/main/resources/messages_pt_BR.properties
+++ b/src/main/resources/messages_pt_BR.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Higienizar
 sanitizePDF.header=Higienizar
 sanitizePDF.selectText.1=Remover scripts de JavaScript.
 sanitizePDF.selectText.2=Remover arquivos embutidos.
-sanitizePDF.selectText.3=Remover metadados.
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Remover links.
 sanitizePDF.selectText.5=Remover fontes.
 sanitizePDF.submit=Higienizar PDF
--- a/src/main/resources/messages_pt_PT.properties
+++ b/src/main/resources/messages_pt_PT.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Sanitizar PDF
 sanitizePDF.header=Sanitizar um ficheiro PDF
 sanitizePDF.selectText.1=Remover ações JavaScript
 sanitizePDF.selectText.2=Remover ficheiros incorporados
-sanitizePDF.selectText.3=Remover metadados
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Remover ligações
 sanitizePDF.selectText.5=Remover tipos de letra
 sanitizePDF.submit=Sanitizar PDF
--- a/src/main/resources/messages_ro_RO.properties
+++ b/src/main/resources/messages_ro_RO.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Igienizează PDF
 sanitizePDF.header=Igienizează un fișier PDF
 sanitizePDF.selectText.1=Elimină acțiunile JavaScript
 sanitizePDF.selectText.2=Elimină fișierele încorporate
-sanitizePDF.selectText.3=Elimină metadatele
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Elimină link-urile
 sanitizePDF.selectText.5=Elimină fonturile
 sanitizePDF.submit=Igienizează PDF
--- a/src/main/resources/messages_ru_RU.properties
+++ b/src/main/resources/messages_ru_RU.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Очистить PDF
 sanitizePDF.header=Очистить PDF-файл
 sanitizePDF.selectText.1=Удалить JavaScript-действия
 sanitizePDF.selectText.2=Удалить встроенные файлы
-sanitizePDF.selectText.3=Удалить метаданные
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Удалить ссылки
 sanitizePDF.selectText.5=Удалить шрифты
 sanitizePDF.submit=Очистить PDF
--- a/src/main/resources/messages_sk_SK.properties
+++ b/src/main/resources/messages_sk_SK.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Vyčistiť PDF
 sanitizePDF.header=Vyčistiť PDF súbor
 sanitizePDF.selectText.1=Odstrániť JavaScript akcie
 sanitizePDF.selectText.2=Odstrániť vložené súbory
-sanitizePDF.selectText.3=Odstrániť metadáta
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Odstrániť odkazy
 sanitizePDF.selectText.5=Odstrániť fonty
 sanitizePDF.submit=Vyčistiť PDF
--- a/src/main/resources/messages_sl_SI.properties
+++ b/src/main/resources/messages_sl_SI.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Prečisti PDF
 sanitizePDF.header=Prečisti datoteko PDF
 sanitizePDF.selectText.1=Odstrani dejanja JavaScript
 sanitizePDF.selectText.2=Odstrani vdelane datoteke
-sanitizePDF.selectText.3=Odstrani metapodatke
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Odstrani povezave
 sanitizePDF.selectText.5=Odstrani pisave
 sanitizePDF.submit=Prečisti PDF
--- a/src/main/resources/messages_sr_LATN_RS.properties
+++ b/src/main/resources/messages_sr_LATN_RS.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Sanitizacija PDF-a
 sanitizePDF.header=Sanitizacija PDF fajla
 sanitizePDF.selectText.1=Ukloni JavaScript akcije
 sanitizePDF.selectText.2=Ukloni ugrađene fajlove
-sanitizePDF.selectText.3=Ukloni metapodatke
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Ukloni linkove
 sanitizePDF.selectText.5=Ukloni fontove
 sanitizePDF.submit=Sanitizuj PDF
--- a/src/main/resources/messages_sv_SE.properties
+++ b/src/main/resources/messages_sv_SE.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Sanera PDF
 sanitizePDF.header=Sanera en PDF-fil
 sanitizePDF.selectText.1=Ta bort JavaScript-åtgärder
 sanitizePDF.selectText.2=Ta bort inbäddade filer
-sanitizePDF.selectText.3=Ta bort metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Ta bort länkar
 sanitizePDF.selectText.5=Ta bort typsnitt
 sanitizePDF.submit=Sanera PDF
--- a/src/main/resources/messages_th_TH.properties
+++ b/src/main/resources/messages_th_TH.properties
@ -733,7 +733,7 @@ sanitizePDF.title=ทำความสะอาด PDF
 sanitizePDF.header=ทำความสะอาดไฟล์ PDF
 sanitizePDF.selectText.1=ลบการกระทำ JavaScript
 sanitizePDF.selectText.2=ลบไฟล์ฝังตัว
-sanitizePDF.selectText.3=ลบข้อมูลเมตา
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=ลบลิงก์
 sanitizePDF.selectText.5=ลบฟอนต์
 sanitizePDF.submit=ทำความสะอาด PDF
--- a/src/main/resources/messages_tr_TR.properties
+++ b/src/main/resources/messages_tr_TR.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF'i Temizle
 sanitizePDF.header=PDF dosyasını temizle
 sanitizePDF.selectText.1=JavaScript işlemlerini kaldır
 sanitizePDF.selectText.2=Gömülü dosyaları kaldır
-sanitizePDF.selectText.3=Üst veriyi kaldır
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Linkleri kaldır
 sanitizePDF.selectText.5=Fontları kaldır
 sanitizePDF.submit=PDF'i Temizle
--- a/src/main/resources/messages_uk_UA.properties
+++ b/src/main/resources/messages_uk_UA.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Дезінфекція PDF
 sanitizePDF.header=Дезінфекція PDF файлу
 sanitizePDF.selectText.1=Видалити JavaScript
 sanitizePDF.selectText.2=Видалити вбудовані файли
-sanitizePDF.selectText.3=Видалити метадані
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Видалити посилання
 sanitizePDF.selectText.5=Видалити шрифти
 sanitizePDF.submit=Дезінфекція
--- a/src/main/resources/messages_vi_VN.properties
+++ b/src/main/resources/messages_vi_VN.properties
@ -733,7 +733,7 @@ sanitizePDF.title=Làm sạch PDF
 sanitizePDF.header=Làm sạch tệp PDF
 sanitizePDF.selectText.1=Xóa các hành động JavaScript
 sanitizePDF.selectText.2=Xóa các tệp nhúng
-sanitizePDF.selectText.3=Xóa metadata
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=Xóa liên kết
 sanitizePDF.selectText.5=Xóa phông chữ
 sanitizePDF.submit=Làm sạch PDF
--- a/src/main/resources/messages_zh_BO.properties
+++ b/src/main/resources/messages_zh_BO.properties
@ -733,7 +733,7 @@ sanitizePDF.title=PDF གཙང་སེལ།
 sanitizePDF.header=PDF ཡིག་ཆ་གཙང་སེལ།
 sanitizePDF.selectText.1=Javascript བྱ་འགུལ་སུབ་པ།
 sanitizePDF.selectText.2=ནང་འཇུག་ཡིག་ཆ་སུབ་པ།
-sanitizePDF.selectText.3=གནས་ཆ་སུབ་པ།
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=འབྲེལ་ཐག་སུབ་པ།
 sanitizePDF.selectText.5=ཡིག་གཟུགས་སུབ་པ།
 sanitizePDF.submit=PDF གཙང་སེལ།
--- a/src/main/resources/messages_zh_CN.properties
+++ b/src/main/resources/messages_zh_CN.properties
@ -733,7 +733,7 @@ sanitizePDF.title=清理 PDF
 sanitizePDF.header=清理 PDF 文件
 sanitizePDF.selectText.1=移除 JavaScript 操作
 sanitizePDF.selectText.2=移除嵌入的文件
-sanitizePDF.selectText.3=移除元数据
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=移除链接
 sanitizePDF.selectText.5=移除字体
 sanitizePDF.submit=清理PDF
--- a/src/main/resources/messages_zh_TW.properties
+++ b/src/main/resources/messages_zh_TW.properties
@ -733,7 +733,7 @@ sanitizePDF.title=清理 PDF
 sanitizePDF.header=清理 PDF 檔案
 sanitizePDF.selectText.1=移除 JavaScript 操作
 sanitizePDF.selectText.2=移除內嵌文件
-sanitizePDF.selectText.3=移除中繼資料
+sanitizePDF.selectText.3=Remove XMP metadata
 sanitizePDF.selectText.4=移除連結
 sanitizePDF.selectText.5=移除字型
 sanitizePDF.submit=清理 PDF
--- a/src/main/resources/templates/security/sanitize-pdf.html
+++ b/src/main/resources/templates/security/sanitize-pdf.html
@ -29,8 +29,12 @@
                  <label for="removeEmbeddedFiles" th:text="#{sanitizePDF.selectText.2}"></label>
                </div>
                <div class="form-check ms-3">
-                  <input type="checkbox" id="removeMetadata" name="removeMetadata" checked>
-                  <label for="removeMetadata" th:text="#{sanitizePDF.selectText.3}"></label>
+                  <input type="checkbox" id="removeXMPMetadata" name="removeXMPMetadata">
+                  <label for="removeXMPMetadata" th:text="#{sanitizePDF.selectText.3}"></label>
+                </div>
+                <div class="form-check ms-3">
+                  <input type="checkbox" id="removeMetadata" name="removeMetadata">
+                  <label for="removeMetadata" th:text="#{sanitizePDF.selectText.6}"></label>
                </div>
                <div class="form-check ms-3">
                  <input type="checkbox" id="removeLinks" name="removeLinks">