wip - fixing embed feature

stirling-pdf/src/main/java/stirling/software/SPDF/config/EndpointConfiguration.java

@@ -173,6 +173,7 @@ public class EndpointConfiguration {
         addEndpointToGroup("Other", "get-info-on-pdf");
         addEndpointToGroup("Other", "show-javascript");
         addEndpointToGroup("Other", "remove-image-pdf");
+        addEndpointToGroup("Other", "add-attachments");
 
         // CLI
         addEndpointToGroup("CLI", "compress-pdf");
@@ -251,6 +252,7 @@ public class EndpointConfiguration {
         addEndpointToGroup("Java", "pdf-to-text");
         addEndpointToGroup("Java", "remove-image-pdf");
         addEndpointToGroup("Java", "pdf-to-markdown");
+        addEndpointToGroup("Java", "add-attachments");
 
         // Javascript
         addEndpointToGroup("Javascript", "pdf-organizer");

stirling-pdf/src/main/java/stirling/software/SPDF/controller/api/misc/AttachmentsController.java

@@ -3,10 +3,7 @@ package stirling.software.SPDF.controller.api.misc;
 import java.io.IOException;
 import java.util.List;
 
-import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.*;
-import org.apache.pdfbox.pdmodel.PDDocumentCatalog;
-import org.apache.pdfbox.pdmodel.PDEmbeddedFilesNameTreeNode;
-import org.apache.pdfbox.pdmodel.PageMode;
 import org.springframework.http.ResponseEntity;
 import org.springframework.web.bind.annotation.*;
 import org.springframework.web.multipart.MultipartFile;
@@ -33,6 +30,7 @@ public class AttachmentsController {
 
     private final PDFAttachmentServiceInterface pdfAttachmentService;
 
+    @SuppressWarnings("DataFlowIssue")
     @PostMapping(consumes = "multipart/form-data", value = "/add-attachments")
     @Operation(
             summary = "Add attachments to PDF",
@@ -50,15 +48,19 @@ public class AttachmentsController {
         PDDocumentCatalog catalog = document.getDocumentCatalog();
 
         // Create embedded files name tree if it doesn't exist
-        PDEmbeddedFilesNameTreeNode efTree = catalog.getNames().getEmbeddedFiles();
+        PDDocumentNameDictionary documentNames = catalog.getNames();
+        PDEmbeddedFilesNameTreeNode embeddedFilesTree = new PDEmbeddedFilesNameTreeNode();
 
-        if (efTree == null) {
+        if (documentNames != null) {
-            efTree = new PDEmbeddedFilesNameTreeNode();
+            embeddedFilesTree = documentNames.getEmbeddedFiles();
-            catalog.getNames().setEmbeddedFiles(efTree);
+        } else {
+            documentNames = new PDDocumentNameDictionary(catalog);
+            documentNames.setEmbeddedFiles(embeddedFilesTree);
         }
 
         // Add attachments
-        pdfAttachmentService.addAttachment(document, efTree, attachments);
+        catalog.setNames(documentNames);
+        pdfAttachmentService.addAttachment(document, embeddedFilesTree, attachments);
 
         // Set PageMode to UseAttachments to show the attachments panel
         catalog.setPageMode(PageMode.USE_ATTACHMENTS);
@@ -79,10 +81,8 @@ public class AttachmentsController {
     public ResponseEntity<byte[]> removeAttachments(
             @RequestParam("fileInput") MultipartFile pdfFile) throws IOException {
 
-        // Load the PDF document
+        // Load the PDF document and document catalog
         PDDocument document = pdfDocumentFactory.load(pdfFile, true);
-
-        // Get the document catalog
         PDDocumentCatalog catalog = document.getDocumentCatalog();
 
         // Remove embedded files

stirling-pdf/src/main/java/stirling/software/SPDF/controller/web/OtherWebController.java

@@ -192,10 +192,10 @@ public class OtherWebController {
         return "misc/auto-rename";
     }
 
-    @GetMapping("/attachments")
+    @GetMapping("/add-attachments")
     @Hidden
     public String attachmentsForm(Model model) {
         model.addAttribute("currentPage", "attachments");
-        return "misc/attachments";
+        return "misc/add-attachments";
     }
 }

stirling-pdf/src/main/java/stirling/software/SPDF/service/PDFAttachmentService.java

@@ -22,18 +22,28 @@ public class PDFAttachmentService implements PDFAttachmentServiceInterface {
     @Override
     public void addAttachment(
             PDDocument document,
-            PDEmbeddedFilesNameTreeNode efTree,
+            PDEmbeddedFilesNameTreeNode embeddedFilesTree,
             List<MultipartFile> attachments)
             throws IOException {
-        // Get existing names or create new map
+//        todo: sanitize attachments first
-        Map<String, PDComplexFileSpecification> existingNames = new java.util.HashMap<>();
+        // todo: find out how to access the embedded files in the PDF
+        Map<String, PDComplexFileSpecification> existingNames;
+
         try {
-            existingNames = efTree.getNames();
+            existingNames = embeddedFilesTree.getNames();
+            if (existingNames == null) {
+                log.info("No existing embedded files found, creating new names map.");
+                // Initialize an empty map if no existing names are found
+                existingNames = new java.util.HashMap<>();
+            }
+
+            log.debug("Existing embedded files: {}", existingNames.keySet());
         } catch (IOException e) {
-            log.warn("Could not retrieve existing embedded files, starting with empty map", e);
+            log.error("Could not retrieve existing embedded files", e);
+            throw e;
         }
 
-        Map<String, PDComplexFileSpecification> finalExistingNames = existingNames;
+        final Map<String, PDComplexFileSpecification> existingEmbeddedFiles = existingNames;
         attachments.forEach(
                 attachment -> {
                     // Create attachments specification
@@ -43,7 +53,6 @@ public class PDFAttachmentService implements PDFAttachmentServiceInterface {
                             "Embedded attachment: " + attachment.getOriginalFilename());
 
                     try {
-                        // Create embedded attachment
                         PDEmbeddedFile embeddedFile =
                                 new PDEmbeddedFile(
                                         document, new ByteArrayInputStream(attachment.getBytes()));
@@ -61,21 +70,20 @@ public class PDFAttachmentService implements PDFAttachmentServiceInterface {
                         fileSpecification.setEmbeddedFile(embeddedFile);
 
                         // Add to the existing names map
-                        finalExistingNames.put(attachment.getOriginalFilename(), fileSpecification);
+                        existingEmbeddedFiles.put(attachment.getOriginalFilename(), fileSpecification);
 
                         log.info(
-                                "Added embedded attachment: {} ({} bytes)",
+                                "Added attachment: {} ({} bytes)",
                                 attachment.getOriginalFilename(),
                                 attachment.getSize());
                     } catch (IOException e) {
-                        log.error(
+                        log.warn(
                                 "Failed to create embedded file for attachment: {}",
                                 attachment.getOriginalFilename(),
                                 e);
                     }
                 });
 
-        // Update the name tree with all names
+        embeddedFilesTree.setNames(existingNames);
-        efTree.setNames(existingNames);
     }
 }

stirling-pdf/src/main/resources/templates/fragments/navElements.html

@@ -238,7 +238,7 @@
         th:replace="~{fragments/navbarEntry :: navbarEntry('unlock-pdf-forms', 'preview_off', 'home.unlockPDFForms.title', 'home.unlockPDFForms.desc', 'unlockPDFForms.tags', 'other')}">
       </div>
       <div
-        th:replace="~{fragments/navbarEntry :: navbarEntry('attachments', 'attachment', 'home.attachments.title', 'home.attachments.desc', 'attachments.tags', 'other')}">
+        th:replace="~{fragments/navbarEntry :: navbarEntry('add-attachments', 'attachment', 'home.attachments.title', 'home.attachments.desc', 'attachments.tags', 'other')}">
       </div>
     </div>
   </div>

stirling-pdf/src/main/resources/templates/home-legacy.html

@@ -290,6 +290,9 @@
               <div
                 th:replace="~{fragments/card :: card(id='unlock-pdf-forms', cardTitle=#{home.unlockPDFForms.title}, cardText=#{home.unlockPDFForms.desc}, cardLink='unlock-pdf-forms', toolIcon='preview_off', tags=#{unlockPDFForms.tags}, toolGroup='other')}">
               </div>
+              <div
+                th:replace="~{fragments/navbarEntry :: navbarEntry('add-attachments', 'attachment', 'home.attachments.title', 'home.attachments.desc', 'attachments.tags', 'other')}">
+              </div>
 
             </div>
           </div>

testing/allEndpointsRemovedSettings.yml

@@ -128,7 +128,7 @@ ui:
   languages: [] # If empty, all languages are enabled. To display only German and Polish ["de_DE", "pl_PL"]. British English is always enabled.
 
 endpoints: # All the possible endpoints are disabled
-  toRemove: [crop, merge-pdfs, multi-page-layout, overlay-pdfs, pdf-to-single-page, rearrange-pages, remove-image-pdf, remove-pages, rotate-pdf, scale-pages, split-by-size-or-count, split-pages, split-pdf-by-chapters, split-pdf-by-sections, add-password, add-watermark, auto-redact, cert-sign, get-info-on-pdf, redact, remove-cert-sign, remove-password, sanitize-pdf, validate-signature, file-to-pdf, html-to-pdf, img-to-pdf, markdown-to-pdf, pdf-to-csv, pdf-to-html, pdf-to-img, pdf-to-markdown, pdf-to-pdfa, pdf-to-presentation, pdf-to-text, pdf-to-word, pdf-to-xml, url-to-pdf, add-image, add-page-numbers, add-stamp, auto-rename, auto-split-pdf, compress-pdf, decompress-pdf, extract-image-scans, extract-images, flatten, ocr-pdf, remove-blanks, repair, replace-invert-pdf, show-javascript, update-metadata, filter-contains-image, filter-contains-text, filter-file-size, filter-page-count, filter-page-rotation, filter-page-size] # list endpoints to disable (e.g. ['img-to-pdf', 'remove-pages'])
+  toRemove: [crop, merge-pdfs, multi-page-layout, overlay-pdfs, pdf-to-single-page, rearrange-pages, remove-image-pdf, remove-pages, rotate-pdf, scale-pages, split-by-size-or-count, split-pages, split-pdf-by-chapters, split-pdf-by-sections, add-password, add-watermark, auto-redact, cert-sign, get-info-on-pdf, redact, remove-cert-sign, remove-password, sanitize-pdf, validate-signature, file-to-pdf, html-to-pdf, img-to-pdf, markdown-to-pdf, pdf-to-csv, pdf-to-html, pdf-to-img, pdf-to-markdown, pdf-to-pdfa, pdf-to-presentation, pdf-to-text, pdf-to-word, pdf-to-xml, url-to-pdf, add-image, add-page-numbers, add-stamp, auto-rename, auto-split-pdf, compress-pdf, decompress-pdf, extract-image-scans, extract-images, flatten, ocr-pdf, remove-blanks, repair, replace-invert-pdf, show-javascript, update-metadata, filter-contains-image, filter-contains-text, filter-file-size, filter-page-count, filter-page-rotation, filter-page-size, add-attachments] # list endpoints to disable (e.g. ['img-to-pdf', 'remove-pages'])
   groupsToRemove: [] # list groups to disable (e.g. ['LibreOffice'])
 
 metrics:

testing/endpoints.txt

@@ -30,6 +30,7 @@
 /api/v1/misc/add-stamp
 /api/v1/misc/add-page-numbers
 /api/v1/misc/add-image
+/api/v1/misc/add-attachments
 /api/v1/convert/url/pdf
 /api/v1/convert/pdf/xml
 /api/v1/convert/pdf/word

testing/webpage_urls.txt

@@ -51,3 +51,4 @@
 /swagger-ui/index.html
 /licenses
 /releases
+/add-attachments