Update test.py

test.py

@@ -27,7 +27,6 @@ oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
 GOOGLE_CLIENT_ID = "485753721652-5uta3e18va2g6cnkldib2d68q39t4vod.apps.googleusercontent.com"
 GOOGLE_CLIENT_SECRET = "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"
 GOOGLE_REDIRECT_URI = "https://omkar008-receipt-radar-test.hf.space/auth/google"
-GOOGLE_REDIRECT_URI_hr = "https://receiptradar-0bb387d81174.herokuapp.com/auth/google"
 # Configure the logger
 logging.basicConfig(level=logging.DEBUG)
 logger = logging.getLogger(__name__)
@@ -54,18 +53,6 @@ async def auth_google(request: Request):
     print(code)
     if not code:
         raise HTTPException(status_code=400, detail="Authorization code not provided")
-
-    # token_url = "https://accounts.google.com/o/oauth2/token"
-    # print(code)
-    # data = {
-    #     "code": code,
-    #     "client_id": GOOGLE_CLIENT_ID,
-    #     "client_secret": GOOGLE_CLIENT_SECRET,
-    #     "redirect_uri": GOOGLE_REDIRECT_URI,
-    #     "grant_type": "authorization_code",
-    # }
-    # response = requests.post(token_url, data=data)
-    # access_token = response.json().get("access_token")
     access_token_new = code
 
     user_info = requests.get("https://www.googleapis.com/oauth2/v1/userinfo", headers={"Authorization": f"Bearer {access_token_new}"})
@@ -123,17 +110,6 @@ async def auth_google(request: Request):
                                 attachment_content = base64.urlsafe_b64decode(data.encode("UTF-8"))
                                 attachment_no+=1
 
-                            # if data:
-                            #     # Decode base64-encoded attachment data
-                            #     attachment_content = base64.urlsafe_b64decode(data.encode("UTF-8"))
-
-                            #     # Save the attachment to a file
-                            #     save_path = f"/Users/omkarmalpure/Documents/Gmail_API/attachments/{filename}"
-                            #     with open(save_path, "wb") as file:
-                            #         file.write(attachment_content)
-
-                            #     attachments.append(save_path)
-    print(data_new)
     return {"attachment_count":attachment_no,"attachment_content":data_new}
 
 
@@ -141,66 +117,49 @@ async def send_chunked_data(websocket: WebSocket, filename: str, data: str):
     chunk_size = 1024  # Set an appropriate chunk size
     for i in range(0, len(data), chunk_size):
         await websocket.send_json({"filename": filename, "data_chunk": data[i:i + chunk_size]})
-        await asyncio.sleep(0.1)
+        await asyncio.sleep(0.4)
     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_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_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"
+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 .
-    #We require the gmail.readonly scopes that requires verification of our application and all.
-    # raw_body = await request.body()
-    # return {"data":Yo Yo"}
-    # data = await request.json()
-    # code = data.get("access_token")
     await websocket.accept()
-    # await print(sucess)
-    # await print("Hi hi working")
     logger.info("Hi hi succefull in connecting !!")
-    # await websocket.send_json({"message":"Yes Websockets successfull"})
-    # await print("working after line 163")
-    logger.info("Now receiving json!!")
 
     data = await websocket.receive_text()
     logger.info("Received JSON data: %s", data)
-    # print(data)
-    # code = data.get("message")
-    # print(code)
-    # code = raw_body.decode()
-    # sent=event_generator(data)
-    for i in range(1, 11):
-        logging.info(f"printing value {i}")
+
+
     
     def get_messages(code:str):
-        print()
-        # print(code)
+  
         logging.info("entered into the get_messages")
         access_token = code
         print("printing access_token")
@@ -242,12 +201,7 @@ async def test_websocket(websocket: WebSocket):
             if thread_id not in unique_thread_ids:
                 unique_thread_ids.add(thread_id)
                 filtered_data_list.append(entry)
-
-
-        print(messages)
         
-        print(filtered_data_list)
-        logging.info(f"{filtered_data_list}")
 
         return filtered_data_list
     
@@ -255,14 +209,9 @@ async def test_websocket(websocket: WebSocket):
         
         logging.info("entered into the event_generator")
 
-        print(code)
         access_token = code
         messages=get_messages(access_token)
         print(len(messages))
-        # await websocket.send_json({"message 1":0})
-        # time.sleep(1)
-        # await websocket.send_text("message 2")
-        # time.sleep(1)
 
         attachments = []
         prev_data=""
@@ -299,36 +248,15 @@ async def test_websocket(websocket: WebSocket):
                                 attachment_data = attachment_response.json()
                                 data = attachment_data.get("data",{})
                                 filename = part.get("filename", "untitled.txt")
-
-                                # print("Print the data json response for that gmail")
-                                print(filename)
-                                
-                                
-                                # print(attachment_data)
-                                # json_str = json.dumps(attachment_data, indent=2)
-
-                                # with subprocess.Popen(["less"], stdin=subprocess.PIPE) as less_process:
-                                #     less_process.communicate(input=json_str.encode("utf-8"))
                                 if data:
                                     data_new[filename]=str(data[:10])
                                     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)
+                                    logging.info(filename)
+                                    extracted_text = await extract_text_from_attachment(filename, data
+                                    logging.info(extracted_text)
                                     await send_chunked_data(websocket, filename, data)
 
                                     attachment_no+=1
-                                    # time.sleep(2)
-                                    # await websocket.send_json({filename:data})
-
-                                    # yield f"data: {str(data_new)}\n\n"
-                                    
-                                    # data_new={}
-
-
-                                
-
-
 
         await websocket.send_text("CompletedFetchingMessages")