From 0acd50b75d0f9d96cd1e93f81cabc956738ac7fc Mon Sep 17 00:00:00 2001
From: pablonyx <pablo@danswer.ai>
Date: Fri, 4 Apr 2025 18:20:31 -0700
Subject: [PATCH] docx bugfix

---
 backend/onyx/file_processing/extract_file_text.py | 8 ++++----
 backend/onyx/server/documents/connector.py        | 3 +--
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/backend/onyx/file_processing/extract_file_text.py b/backend/onyx/file_processing/extract_file_text.py
index bab357aca..0905ada98 100644
--- a/backend/onyx/file_processing/extract_file_text.py
+++ b/backend/onyx/file_processing/extract_file_text.py
@@ -2,6 +2,7 @@ import io
 import json
 import os
 import re
+import uuid
 import zipfile
 from collections.abc import Callable
 from collections.abc import Iterator
@@ -567,9 +568,7 @@ def extract_text_and_images(
         return ExtractionResult(text_content="", embedded_images=[], metadata={})
 
 
-def convert_docx_to_txt(
-    file: UploadFile, file_store: FileStore, file_path: str
-) -> None:
+def convert_docx_to_txt(file: UploadFile, file_store: FileStore) -> str:
     """
     Helper to convert docx to a .txt file in the same filestore.
     """
@@ -581,7 +580,7 @@ def convert_docx_to_txt(
     all_paras = [p.text for p in doc.paragraphs]
     text_content = "\n".join(all_paras)
 
-    text_file_name = docx_to_txt_filename(file_path)
+    text_file_name = docx_to_txt_filename(file.filename or f"docx_{uuid.uuid4()}")
     file_store.save_file(
         file_name=text_file_name,
         content=BytesIO(text_content.encode("utf-8")),
@@ -589,6 +588,7 @@ def convert_docx_to_txt(
         file_origin=FileOrigin.CONNECTOR,
         file_type="text/plain",
     )
+    return text_file_name
 
 
 def docx_to_txt_filename(file_path: str) -> str:
diff --git a/backend/onyx/server/documents/connector.py b/backend/onyx/server/documents/connector.py
index c2da0d7aa..fa8078457 100644
--- a/backend/onyx/server/documents/connector.py
+++ b/backend/onyx/server/documents/connector.py
@@ -435,8 +435,7 @@ def upload_files(files: list[UploadFile], db_session: Session) -> FileUploadResp
             if file.content_type and file.content_type.startswith(
                 "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
             ):
-                file_path = os.path.join(str(uuid.uuid4()), cast(str, file.filename))
-                convert_docx_to_txt(file, file_store, file_path)
+                file_path = convert_docx_to_txt(file, file_store)
                 deduped_file_paths.append(file_path)
                 continue