Update app.py

app.py

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 
 """
-*NetCom → WooCommerce CSV Processor*
+*NetCom → WooCommerce CSV/Excel Processor*
 Robust edition – catches and logs every recoverable error so one failure never
 brings the whole pipeline down.  Only small, surgical changes were made.
 """
@@ -81,7 +81,6 @@ async def process_text_batch_async(client, prompts):
         else:
             tasks.append(asyncio.create_task(_call_openai(client, p)))
 
-    # Wait for *all* tasks, collecting exceptions too
     for prompt, task in zip([p for p in prompts if p not in results], tasks):
         try:
             res = await task
@@ -104,7 +103,7 @@ async def process_text_with_ai_async(texts, instruction):
 
 # ──────────────────────────────  MAIN TRANSFORM  ──────────────────────────────
 def process_woocommerce_data_in_memory(upload):
-    """Convert NetCom → Woo CSV; every stage guarded."""
+    """Convert NetCom → Woo CSV/XLSX; every stage guarded."""
     try:
         # brand → logo mapping
         brand_logo = {
@@ -127,30 +126,69 @@ def process_woocommerce_data_in_memory(upload):
         )
 
         # ---------------- I/O ----------------
+        ext = Path(upload.name).suffix.lower()
         try:
-            df = pd.read_csv(upload.name, encoding="latin1")
+            if ext in {".xlsx", ".xls"}:
+                try:
+                    df = pd.read_excel(upload.name, sheet_name="Active Schedules")
+                except Exception as e:
+                    _log(e, "Excel read failed (falling back to first sheet)")
+                    df = pd.read_excel(upload.name, sheet_name=0)
+            else:  # CSV
+                try:
+                    df = pd.read_csv(upload.name, encoding="latin1")
+                except Exception as e:
+                    _log(e, "CSV read failed (trying utf-8)")
+                    df = pd.read_csv(upload.name, encoding="utf-8", errors="ignore")
         except Exception as e:
-            _log(e, "CSV read failed (trying utf-8)")
-            df = pd.read_csv(upload.name, encoding="utf-8", errors="ignore")
+            _log(e, "file read totally failed")
+            raise
+
         df.columns = df.columns.str.strip()
 
+        # --------- column harmonisation (new vs old formats) ----------
+        rename_map = {
+            "Decription": "Description",
+            "description": "Description",
+            "Objectives": "Objectives",
+            "objectives": "Objectives",
+            "RequiredPrerequisite": "Required Prerequisite",
+            "Required Pre-requisite": "Required Prerequisite",
+            "RequiredPre-requisite": "Required Prerequisite",
+        }
+        df.rename(columns={k: v for k, v in rename_map.items() if k in df.columns}, inplace=True)
+
+        # duration if missing
+        if "Duration" not in df.columns:
+            try:
+                df["Duration"] = (
+                    pd.to_datetime(df["Course End Date"]) - pd.to_datetime(df["Course Start Date"])
+                ).dt.days.add(1)
+            except Exception as e:
+                _log(e, "duration calc failed")
+                df["Duration"] = ""
+
         # ---------------- ASYNC AI ----------------
         loop = asyncio.new_event_loop()
         asyncio.set_event_loop(loop)
 
+        col_desc = "Description"
+        col_obj = "Objectives"
+        col_prereq = "Required Prerequisite"
+
         try:
             res = loop.run_until_complete(
                 asyncio.gather(
                     process_text_with_ai_async(
-                        df["Decription"].fillna("").tolist(),
+                        df[col_desc].fillna("").tolist(),
                         "Create a concise 250-character summary of this course description:",
                     ),
                     process_text_with_ai_async(
-                        df["Decription"].fillna("").tolist(),
+                        df[col_desc].fillna("").tolist(),
                         "Condense this description to maximum 750 characters in paragraph format, with clean formatting:",
                     ),
                     process_text_with_ai_async(
-                        df["Objectives"].fillna("").tolist(),
+                        df[col_obj].fillna("").tolist(),
                         "Format these objectives into a bullet list format with clean formatting. Start each bullet with '• ':",
                     ),
                     process_text_with_ai_async(
@@ -161,7 +199,7 @@ def process_woocommerce_data_in_memory(upload):
             )
         except Exception as e:
             _log(e, "async AI gather failed")
-            res = [[""] * len(df)] * 4  # fallback blank columns
+            res = [[""] * len(df)] * 4
         finally:
             loop.close()
 
@@ -169,7 +207,7 @@ def process_woocommerce_data_in_memory(upload):
 
         # prerequisites handled synchronously (tiny)
         prereq_out = []
-        for p in df["RequiredPrerequisite"].fillna("").tolist():
+        for p in df[col_prereq].fillna("").tolist():
             if not p.strip():
                 prereq_out.append(default_prereq)
             else:
@@ -196,7 +234,6 @@ def process_woocommerce_data_in_memory(upload):
         except Exception as e:
             _log(e, "adding AI columns")
 
-        # … (rest identical to original script – only guarded sections changed) …
         # 2. aggregate date/time
         df = df.sort_values(["Course ID", "Course Start Date"])
         date_agg = (
@@ -220,7 +257,6 @@ def process_woocommerce_data_in_memory(upload):
         parent = df.drop_duplicates(subset=["Course ID"]).merge(date_agg).merge(time_agg)
         woo_parent_df = pd.DataFrame(
             {
-                # unchanged fields ...
                 "Type": "variable",
                 "SKU": parent["Course ID"],
                 "Name": parent["Course Name"],
@@ -344,7 +380,6 @@ def process_woocommerce_data_in_memory(upload):
         return buf
     except Exception as e:
         _log(e, "fatal transformation error")
-        # Return a tiny CSV explaining the failure instead of crashing
         err_buf = BytesIO()
         pd.DataFrame({"error": [str(e)]}).to_csv(err_buf, index=False)
         err_buf.seek(0)
@@ -365,14 +400,14 @@ def process_file(file):
 
 interface = gr.Interface(
     fn=process_file,
-    inputs=gr.File(label="Upload NetCom CSV", file_types=[".csv"]),
+    inputs=gr.File(label="Upload NetCom Schedule", file_types=[".csv", ".xlsx", ".xls"]),
     outputs=gr.File(label="Download WooCommerce CSV"),
-    title="NetCom → WooCommerce CSV Processor",
-    description="Upload a NetCom Reseller Schedule CSV to generate a WooCommerce-ready CSV.",
+    title="NetCom → WooCommerce CSV/Excel Processor",
+    description="Upload a NetCom Reseller Schedule CSV or XLSX to generate a WooCommerce-ready CSV.",
     analytics_enabled=False,
 )
 
 if __name__ == "__main__":  # run
     if not os.getenv("OPENAI_API_KEY"):
         print("[WARN] OPENAI_API_KEY not set; AI steps will error out.")
-    interface.launch()  # robust interface launch
+    interface.launch()