Update app.py

app.py

@@ -24,7 +24,7 @@ import altair as alt
 import spacy
 import spacy.cli
 import PyPDF2
-import io  # For handling in-memory files for Excel
+import io  # For handling in-memory files (Excel, etc.)
 
 # Ensure spaCy model is downloaded
 try:
@@ -131,7 +131,7 @@ def parse_pubmed_xml(xml_data: str) -> List[Dict[str, Any]]:
         })
     return articles
 
-### Asynchronous Functions for Europe PMC ###
+### Async Functions for Europe PMC ###
 async def fetch_articles_by_nct_id(nct_id: str) -> Dict[str, Any]:
     params = {"query": nct_id, "format": "json"}
     async with httpx.AsyncClient() as client_http:
@@ -381,7 +381,6 @@ def perform_enhanced_eda(df: pd.DataFrame) -> Tuple[str, Optional[alt.Chart], Op
         return f"Enhanced EDA failed: {e}", None, None
 
 ### File Handling ###
-
 def read_uploaded_file(uploaded_file: Optional[gr.File]) -> str:
     """
     Reads the content of an uploaded file (txt, csv, xls, xlsx, pdf).
@@ -405,7 +404,6 @@ def read_uploaded_file(uploaded_file: Optional[gr.File]) -> str:
 
         # Excel
         elif file_ext in [".xls", ".xlsx"]:
-            # We won't parse here; we'll parse in parse_excel_file(...)
             # Return a placeholder so we know an Excel file was uploaded
             return "EXCEL_FILE_PLACEHOLDER"
 
@@ -425,13 +423,21 @@ def read_uploaded_file(uploaded_file: Optional[gr.File]) -> str:
 
 def parse_excel_file(uploaded_file: gr.File) -> pd.DataFrame:
     """
-    Parse an Excel file into a pandas DataFrame using raw bytes.
-    This avoids the NamedString error from calling .read() on a Gradio file.
+    Parse an Excel file into a pandas DataFrame.
+    1) Try using the local file path, if it exists.
+    2) Otherwise, read from the in-memory object using uploaded_file.file.read().
     """
+    import pandas as pd
+
+    # If we have a valid local file path (common in some Gradio versions)
+    if os.path.exists(uploaded_file.name):
+        # Directly read from the file path
+        return pd.read_excel(uploaded_file.name, engine="openpyxl")
+
+    # Otherwise, we read the file from memory
     try:
-        excel_bytes = uploaded_file.data  # raw file content in bytes
-        df = pd.read_excel(io.BytesIO(excel_bytes), engine="openpyxl")
-        return df
+        excel_bytes = uploaded_file.file.read()
+        return pd.read_excel(io.BytesIO(excel_bytes), engine="openpyxl")
     except Exception as e:
         logger.error(f"Excel parsing error: {e}")
         raise ValueError(f"Excel parsing error: {e}")