feat: implement PDF attachment extraction functionality with web worker support

- Added a new worker script to handle extraction of embedded attachments from PDF files.
- Created TypeScript definitions for the message structure and response types.
- Updated the main extraction logic to utilize the worker for improved performance and responsiveness.
- Integrated the extraction feature into the UI, allowing users to extract attachments as a ZIP file.
- Enhanced error handling and user feedback during the extraction process.

public/workers/extract-attachments.worker.d.ts

@@ -0,0 +1,19 @@
+declare const coherentpdf: typeof import('../../src/types/coherentpdf.global').coherentpdf;
+
+interface ExtractAttachmentsMessage {
+  command: 'extract-attachments';
+  fileBuffers: ArrayBuffer[];
+  fileNames: string[];
+}
+
+interface ExtractAttachmentSuccessResponse {
+  status: 'success';
+  attachments: Array<{ name: string; data: ArrayBuffer }>;
+}
+
+interface ExtractAttachmentErrorResponse {
+  status: 'error';
+  message: string;
+}
+
+type ExtractAttachmentResponse = ExtractAttachmentSuccessResponse | ExtractAttachmentErrorResponse;

public/workers/extract-attachments.worker.js

@@ -0,0 +1,106 @@
+self.importScripts('/coherentpdf.browser.min.js');
+
+function extractAttachmentsFromPDFsInWorker(fileBuffers, fileNames) {
+  try {
+    const allAttachments = [];
+    const totalFiles = fileBuffers.length;
+    
+    for (let i = 0; i < totalFiles; i++) {
+      const buffer = fileBuffers[i];
+      const fileName = fileNames[i];
+      const uint8Array = new Uint8Array(buffer);
+      
+      let pdf;
+      try {
+        pdf = coherentpdf.fromMemory(uint8Array, '');
+      } catch (error) {
+        console.warn(`Failed to load PDF: ${fileName}`, error);
+        continue;
+      }
+
+      coherentpdf.startGetAttachments(pdf);
+      const attachmentCount = coherentpdf.numberGetAttachments();
+
+      if (attachmentCount === 0) {
+        console.warn(`No attachments found in ${fileName}`);
+        coherentpdf.deletePdf(pdf);
+        continue;
+      }
+
+      const baseName = fileName.replace(/\.pdf$/i, '');
+      for (let j = 0; j < attachmentCount; j++) {
+        try {
+          const attachmentName = coherentpdf.getAttachmentName(j);
+          const attachmentPage = coherentpdf.getAttachmentPage(j);
+          const attachmentData = coherentpdf.getAttachmentData(j);
+
+          let uniqueName = attachmentName;
+          let counter = 1;
+          while (allAttachments.some(att => att.name === uniqueName)) {
+            const nameParts = attachmentName.split('.');
+            if (nameParts.length > 1) {
+              const extension = nameParts.pop();
+              uniqueName = `${nameParts.join('.')}_${counter}.${extension}`;
+            } else {
+              uniqueName = `${attachmentName}_${counter}`;
+            }
+            counter++;
+          }
+
+          if (attachmentPage > 0) {
+            uniqueName = `${baseName}_page${attachmentPage}_${uniqueName}`;
+          } else {
+            uniqueName = `${baseName}_${uniqueName}`;
+          }
+
+          allAttachments.push({
+            name: uniqueName,
+            data: attachmentData.buffer.slice(0)
+          });
+        } catch (error) {
+          console.warn(`Failed to extract attachment ${j} from ${fileName}:`, error);
+        }
+      }
+
+      coherentpdf.endGetAttachments();
+      coherentpdf.deletePdf(pdf);
+    }
+
+    if (allAttachments.length === 0) {
+      self.postMessage({
+        status: 'error',
+        message: 'No attachments were found in the selected PDF(s).'
+      });
+      return;
+    }
+    
+    const response = {
+      status: 'success',
+      attachments: []
+    };
+
+    const transferBuffers = [];
+    for (const attachment of allAttachments) {
+      response.attachments.push({
+        name: attachment.name,
+        data: attachment.data
+      });
+      transferBuffers.push(attachment.data);
+    }
+
+    self.postMessage(response, transferBuffers);
+  } catch (error) {
+    self.postMessage({
+      status: 'error',
+      message: error instanceof Error
+        ? error.message
+        : 'Unknown error occurred during attachment extraction.'
+    });
+  }
+}
+
+self.onmessage = (e) => {
+  if (e.data.command === 'extract-attachments') {
+    extractAttachmentsFromPDFsInWorker(e.data.fileBuffers, e.data.fileNames);
+  }
+};

src/js/config/tools.ts

@@ -318,13 +318,12 @@ export const categories = [
         icon: 'paperclip',
         subtitle: 'Embed one or more files into your PDF.',
       },
-      // TODO@ALAM - MAKE THIS LATER, ONCE INTEGERATED WITH CPDF
+      {
-      // {
+        id: 'extract-attachments',
-      //   id: 'extract-attachments',
+        name: 'Extract Attachments',
-      //   name: 'Extract Attachments',
+        icon: 'download',
-      //   icon: 'download',
+        subtitle: 'Extract all embedded files from PDF(s) as a ZIP.',
-      //   subtitle: 'Extract all embedded files from PDF(s) as a ZIP.',
+      },
-      // },
       // {
       //   id: 'edit-attachments',
       //   name: 'Edit Attachments',

src/js/logic/extract-attachments.ts

@@ -1,88 +1,130 @@
-// TODO@ALAM - USE CPDF HERE
+import { downloadFile, formatBytes } from '../utils/helpers.js';
+import { state } from '../state.js';
+import JSZip from 'jszip';
 
-// import { showLoader, hideLoader, showAlert } from '../ui.js';
+const worker = new Worker('/workers/extract-attachments.worker.js');
-// import { downloadFile, readFileAsArrayBuffer } from '../utils/helpers.js';
-// import { state } from '../state.js';
-// import { PDFDocument as PDFLibDocument } from 'pdf-lib';
-// import JSZip from 'jszip';
 
-// export async function extractAttachments() {
+interface ExtractAttachmentSuccessResponse {
-//   if (state.files.length === 0) {
+  status: 'success';
-//     showAlert('No Files', 'Please select at least one PDF file.');
+  attachments: Array<{ name: string; data: ArrayBuffer }>;
-//     return;
+}
-//   }
 
-//   showLoader('Extracting attachments...');
+interface ExtractAttachmentErrorResponse {
-//   try {
+  status: 'error';
-//     const zip = new JSZip();
+  message: string;
-//     let totalAttachments = 0;
+}
 
-//     for (const file of state.files) {
+type ExtractAttachmentResponse = ExtractAttachmentSuccessResponse | ExtractAttachmentErrorResponse;
-//       const pdfBytes = await readFileAsArrayBuffer(file);
-//       const pdfDoc = await PDFLibDocument.load(pdfBytes as ArrayBuffer, {
-//         ignoreEncryption: true,
-//       });
 
-//       const embeddedFiles = pdfDoc.context.enumerateIndirectObjects()
+export async function extractAttachments() {
-//         .filter(([ref, obj]: any) => {
+  if (state.files.length === 0) {
-//           // obj must be a PDFDict
+    showStatus('No Files', 'error');
-//           if (obj && typeof obj.get === 'function') {
+    return;
-//             const type = obj.get('Type');
+  }
-//             return type && type.toString() === '/Filespec';
-//           }
-//           return false;
-//         });
 
-//       if (embeddedFiles.length === 0) {
+  document.getElementById('process-btn')?.classList.add('opacity-50', 'cursor-not-allowed');
-//         console.warn(`No attachments found in ${file.name}`);
+  document.getElementById('process-btn')?.setAttribute('disabled', 'true');
-//         continue;
-//       }
   
-//       // Extract attachments
+  showStatus('Reading files (Main Thread)...', 'info');
-//       const baseName = file.name.replace(/\.pdf$/i, '');
-//       for (let i = 0; i < embeddedFiles.length; i++) {
-//         try {
-//           const [ref, fileSpec] = embeddedFiles[i];
-//           const fileSpecDict = fileSpec as any;
 
-//           // Get attachment name
+  try {
-//           const fileName = fileSpecDict.get('UF')?.decodeText() || 
+    const fileBuffers: ArrayBuffer[] = [];
-//                          fileSpecDict.get('F')?.decodeText() || 
+    const fileNames: string[] = [];
-//                          `attachment-${i + 1}`;
 
-//           // Get embedded file stream
+    for (const file of state.files) {
-//           const ef = fileSpecDict.get('EF');
+      const buffer = await file.arrayBuffer();
-//           if (ef) {
+      fileBuffers.push(buffer);
-//             const fRef = ef.get('F') || ef.get('UF');
+      fileNames.push(file.name);
-//             if (fRef) {
+    }
-//               const fileStream = pdfDoc.context.lookup(fRef);
-//               if (fileStream) {
-//                 const fileData = (fileStream as any).getContents();
-//                 zip.file(`${baseName}_${fileName}`, fileData);
-//                 totalAttachments++;
-//               }
-//             }
-//           }
-//         } catch (e) {
-//           console.warn(`Failed to extract attachment ${i} from ${file.name}:`, e);
-//         }
-//       }
-//     }
 
-//     if (totalAttachments === 0) {
+    showStatus(`Extracting attachments from ${state.files.length} file(s)...`, 'info');
-//       showAlert('No Attachments', 'No attachments were found in the selected PDF(s).');
-//       hideLoader();
-//       return;
-//     }
 
-//     const zipBlob = await zip.generateAsync({ type: 'blob' });
+    const message: ExtractAttachmentsMessage = {
-//     downloadFile(zipBlob, 'extracted-attachments.zip');
+      command: 'extract-attachments',
-//     showAlert('Success', `Extracted ${totalAttachments} attachment(s) successfully!`);
+      fileBuffers,
-//   } catch (e) {
+      fileNames,
-//     console.error(e);
+    };
-//     showAlert('Error', 'Failed to extract attachments. The PDF may not contain attachments or may be corrupted.');
-//   } finally {
-//     hideLoader();
-//   }
-// }
 
+    const transferables = fileBuffers.map(buf => buf);
+    worker.postMessage(message, transferables);
+
+  } catch (error) {
+    console.error('Error reading files:', error);
+    showStatus(
+      `Error reading files: ${error instanceof Error ? error.message : 'Unknown error occurred'}`,
+      'error'
+    );
+    document.getElementById('process-btn')?.classList.remove('opacity-50', 'cursor-not-allowed');
+    document.getElementById('process-btn')?.removeAttribute('disabled');
+  }
+}
+
+worker.onmessage = (e: MessageEvent<ExtractAttachmentResponse>) => {
+  document.getElementById('process-btn')?.classList.remove('opacity-50', 'cursor-not-allowed');
+  document.getElementById('process-btn')?.removeAttribute('disabled');
+
+  if (e.data.status === 'success') {
+    const attachments = e.data.attachments;
+
+    const zip = new JSZip();
+    let totalSize = 0;
+    
+    for (const attachment of attachments) {
+      zip.file(attachment.name, new Uint8Array(attachment.data));
+      totalSize += attachment.data.byteLength;
+    }
+
+    zip.generateAsync({ type: 'blob' }).then((zipBlob) => {
+      downloadFile(zipBlob, 'extracted-attachments.zip');
+      showStatus(
+        `Extraction completed! ${attachments.length} attachment(s) in zip file (${formatBytes(totalSize)}). Download started.`,
+        'success'
+      );
+
+      state.files = [];
+      const fileDisplayArea = document.getElementById('file-display-area');
+      if (fileDisplayArea) {
+        fileDisplayArea.innerHTML = '';
+        fileDisplayArea.classList.add('hidden');
+      }
+      const fileInput = document.getElementById('file-input') as HTMLInputElement;
+      if (fileInput) {
+        fileInput.value = '';
+      }
+      document.getElementById('process-btn')?.classList.add('opacity-50', 'cursor-not-allowed');
+      document.getElementById('process-btn')?.setAttribute('disabled', 'true');
+    });
+  } else if (e.data.status === 'error') {
+    const errorMessage = e.data.message || 'Unknown error occurred in worker.';
+    console.error('Worker Error:', errorMessage);
+    showStatus(`Error: ${errorMessage}`, 'error');
+  }
+};
+
+worker.onerror = (error) => {
+  console.error('Worker error:', error);
+  showStatus('Worker error occurred. Check console for details.', 'error');
+  document.getElementById('process-btn')?.classList.remove('opacity-50', 'cursor-not-allowed');
+  document.getElementById('process-btn')?.removeAttribute('disabled');
+};
+
+function showStatus(message: string, type: 'success' | 'error' | 'info' = 'info') {
+  const statusMessage = document.getElementById('status-message') as HTMLElement;
+  if (!statusMessage) return;
+  
+  statusMessage.textContent = message;
+  statusMessage.className = `mt-4 p-3 rounded-lg text-sm ${
+    type === 'success'
+      ? 'bg-green-900 text-green-200'
+      : type === 'error'
+        ? 'bg-red-900 text-red-200'
+        : 'bg-blue-900 text-blue-200'
+  }`;
+  statusMessage.classList.remove('hidden');
+}
+
+interface ExtractAttachmentsMessage {
+  command: 'extract-attachments';
+  fileBuffers: ArrayBuffer[];
+  fileNames: string[];
+}

src/js/logic/index.ts

@@ -63,7 +63,7 @@ import {
 import { alternateMerge, setupAlternateMergeTool } from './alternate-merge.js';
 import { linearizePdf } from './linearize.js';
 import { addAttachments, setupAddAttachmentsTool } from './add-attachments.js';
-// import { extractAttachments } from './extract-attachments.js';
+import { extractAttachments } from './extract-attachments.js';
 // import { editAttachments, setupEditAttachmentsTool } from './edit-attachments.js';
 import { sanitizePdf } from './sanitize-pdf.js';
 import { removeRestrictions } from './remove-restrictions.js';
@@ -140,7 +140,7 @@ export const toolLogic = {
     process: addAttachments,
     setup: setupAddAttachmentsTool,
   },
-  // 'extract-attachments': extractAttachments,
+  'extract-attachments': extractAttachments,
   // 'edit-attachments': {
   //   process: editAttachments,
   //   setup: setupEditAttachmentsTool,