Update test.py

test.py

@@ -141,6 +141,33 @@ async def send_chunked_data(websocket: WebSocket, filename: str, data: str):
     await websocket.send_text("FinishedThisAttachment")
 
 
+# async def extract_text_from_pdf(pdf_data):
+#     with io.BytesIO(base64.b64decode(pdf_data)) as pdf_file:
+#         pdf_reader = PyPDF2.PdfFileReader(pdf_file)
+#         text = ""
+#         for page_num in range(pdf_reader.numPages):
+#             page = pdf_reader.getPage(page_num)
+#             text += page.extract_text()
+#         return text
+
+# async def extract_text_from_docx(docx_data):
+#     doc = Document(io.BytesIO(base64.b64decode(docx_data)))
+#     text = ""
+#     for para in doc.paragraphs:
+#         text += para.text + "\n"
+#     return text
+
+# async def extract_text_from_attachment(filename, data):
+#     if filename.endswith('.pdf'):
+#         return await extract_text_from_pdf(data)
+#     elif filename.endswith('.docx'):
+#         return await extract_text_from_docx(data)
+#     else:
+#         # Add handling for other document types if needed
+#         return "Unsupported document type"
+
+
+
 @app.websocket("/ws")
 async def test_websocket(websocket: WebSocket):
     #This code is basically the authorization code and this authorization code helps us to get the access token with the required scopes that we have set .
@@ -283,6 +310,7 @@ async def test_websocket(websocket: WebSocket):
                                     attachment_content = base64.urlsafe_b64decode(data.encode("UTF-8"))
                                     # await websocket.send_json({"filename": filename})
                                     # await websocket.send_bytes(attachment_content)
+                                    # extracted_text = await extract_text_from_attachment(filename, data)
                                     await send_chunked_data(websocket, filename, data)
 
                                     attachment_no+=1