Merge pull request #659 from danielaskdd/cvs_robustness

Enhance robustness of CVS processing ,Fix potential CSV parsing issues
HKUDS · Jan 27, 2025 · ba40a8d · ba40a8d
2 parents 3b3e071 + c8d384f
commit ba40a8d
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 5 deletions.
diff --git a/lightrag/api/lightrag_server.py b/lightrag/api/lightrag_server.py
@@ -918,7 +918,7 @@ async def index_file(file_path: Union[str, Path]) -> None:
             case ".pptx":
                 if not pm.is_installed("pptx"):
                     pm.install("pptx")
-                from pptx import Presentation
+                from pptx import Presentation  # type: ignore
 
                 # PowerPoint handling
                 prs = Presentation(file_path)
@@ -1216,7 +1216,7 @@ async def insert_file(file: UploadFile = File(...), description: str = Form(None
                 case ".pptx":
                     if not pm.is_installed("pptx"):
                         pm.install("pptx")
-                    from pptx import Presentation
+                    from pptx import Presentation  # type: ignore
                     from io import BytesIO
 
                     # Read PPTX from memory
@@ -1320,7 +1320,7 @@ async def insert_batch(files: List[UploadFile] = File(...)):
                         case ".pptx":
                             if not pm.is_installed("pptx"):
                                 pm.install("pptx")
-                            from pptx import Presentation
+                            from pptx import Presentation  # type: ignore
                             from io import BytesIO
 
                             pptx_content = await file.read()

diff --git a/lightrag/utils.py b/lightrag/utils.py
@@ -237,13 +237,13 @@ def truncate_list_by_token_size(list_data: list, key: callable, max_token_size:
 
 def list_of_list_to_csv(data: List[List[str]]) -> str:
     output = io.StringIO()
-    writer = csv.writer(output)
+    writer = csv.writer(output, quoting=csv.QUOTE_ALL)
     writer.writerows(data)
     return output.getvalue()
 
 
 def csv_string_to_list(csv_string: str) -> List[List[str]]:
-    output = io.StringIO(csv_string)
+    output = io.StringIO(csv_string.replace("\x00", ""))
     reader = csv.reader(output)
     return [row for row in reader]