🧮 fix: XLSX/XLS Upload-as-Text via Buffer-Based SheetJS Parsing (#12098)

* 🔧 fix: Update Excel sheet parsing to use fs.promises.readFile and correct import for xlsx

- Modified the excelSheetToText function to read the file using fs.promises.readFile instead of directly accessing the file path.
- Updated the import statement for the xlsx library to use the correct read method, ensuring proper functionality in parsing Excel sheets.

* 🔧 fix: Update document parsing methods to use buffer for file reading

- Modified the wordDocToText function to read the file as a buffer using fs.promises.readFile, ensuring compatibility with the mammoth library.
- Updated the excelSheetToText function to read the Excel file as a buffer, addressing issues with the xlsx library's handling of dynamic imports and file access.

* feat: Add tests for empty xlsx document parsing and validate xlsx imports

- Introduced a new test case to verify that the `parseDocument` function correctly handles an empty xlsx file with only a sheet name, ensuring it returns the expected document structure.
- Added a test to confirm that the `xlsx` library exports `read` and `utils` as named imports, validating the functionality of the library integration.
- Included a new empty xlsx file to support the test cases.

packages/api/src/files/documents/crud.spec.ts

@@ -121,4 +121,28 @@ describe('Document Parser', () => {
 
     await expect(parseDocument({ file })).rejects.toThrow('No text found in document');
   });
+
+  test('parseDocument() parses empty xlsx with only sheet name', async () => {
+    const file = {
+      originalname: 'empty.xlsx',
+      path: path.join(__dirname, 'empty.xlsx'),
+      mimetype: 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
+    } as Express.Multer.File;
+
+    const document = await parseDocument({ file });
+
+    expect(document).toEqual({
+      bytes: 8,
+      filename: 'empty.xlsx',
+      filepath: 'document_parser',
+      images: [],
+      text: 'Empty:\n\n',
+    });
+  });
+
+  test('xlsx exports read and utils as named imports', async () => {
+    const { read, utils } = await import('xlsx');
+    expect(typeof read).toBe('function');
+    expect(typeof utils?.sheet_to_csv).toBe('function');
+  });
 });

packages/api/src/files/documents/crud.ts

@@ -68,14 +68,17 @@ async function pdfToText(file: Express.Multer.File): Promise<string> {
 /** Parses Word document, returns text inside. */
 async function wordDocToText(file: Express.Multer.File): Promise<string> {
   const { extractRawText } = await import('mammoth');
-  const rawText = await extractRawText({ path: file.path });
+  const rawText = await extractRawText({ buffer: await fs.promises.readFile(file.path) });
   return rawText.value;
 }
 
 /** Parses Excel sheet, returns text inside. */
 async function excelSheetToText(file: Express.Multer.File): Promise<string> {
-  const { readFile, utils } = await import('xlsx');
-  const workbook = readFile(file.path);
+  // xlsx CDN build (0.20.x) does not bind fs internally when dynamically imported;
+  // readFile() fails with "Cannot access file". read() takes a pre-loaded Buffer instead.
+  const { read, utils } = await import('xlsx');
+  const data = await fs.promises.readFile(file.path);
+  const workbook = read(data, { type: 'buffer' });
 
   let text = '';
   for (const sheetName of workbook.SheetNames) {