Update app.py

app.py

@@ -31,7 +31,6 @@ def convert_ci(by_line_item_file, combined_file, password, max_rows):
         description = re.sub(r"\d+", "", description)
         return re.sub(r"[^\w\s]", "", description)
 
-    # by_line_item_df["Part"] = by_line_item_df.iloc[:, 0].astype(str)
     by_line_item_df["Part"] = ""
     by_line_item_df["Tariff_Number"] = by_line_item_df.iloc[:, 1].apply(lambda x: str(x).replace('.0', '') if isinstance(x, float) and str(x).endswith('.0') else str(x))
     by_line_item_df["Commercial_Description"] = by_line_item_df.apply(clean_desc, axis=1)
@@ -138,37 +137,35 @@ def convert_ci(by_line_item_file, combined_file, password, max_rows):
         'CVD_Case_Number', 'AD_Non_Reimbursement_Statement',
         'AD-CVD_Certification_Designation'
     ]
-
-    # Update SHEIN Incorrect MID:
-    MID_mapping_df = pd.read_csv("MID_replace.csv")
-    mid_map = dict(zip(MID_mapping_df["SHEIN_MID_Code"], MID_mapping_df["Replacement"]))
-    merged_df["MID_Code"] = merged_df["MID_Code"].map(mid_map).fillna(merged_df["MID_Code"])
-
     for col in column_order:
         if col not in merged_df.columns:
             merged_df[col] = ""
     merged_df = merged_df[column_order]
 
-    # Save merged output partitioned into 998-row chunks 
+    # Save merged output partitioned by user-defined max_rows
     outputs = []
-
-    for i, start in enumerate(range(0, len(merged_df), max_rows)):
-        chunk = merged_df.iloc[start : start + max_rows]
-        suffix = chr(65 + i) if i < 26 else f"part{i + 1}"  # A, B, C... then part27+
+    for i, start in enumerate(range(0, len(merged_df), int(max_rows))):
+        chunk = merged_df.iloc[start : start + int(max_rows)]
+        suffix = chr(65 + i) if i < 26 else f"part{i + 1}"
         filename = f"{mawb} T01 Manifest - {suffix}.xlsx"
-        with pd.ExcelWriter(filename, engine='openpyxl') as writer:
+        with pd.ExcelWriter(filename, engine='xlsxwriter') as writer:
             chunk.to_excel(writer, sheet_name="Converted", index=False)
+            workbook = writer.book
             worksheet = writer.sheets['Converted']
-        for column_cells in worksheet.columns:
-            max_length = max(len(str(cell.value)) if cell.value is not None else 0 for cell in column_cells)
-            col_letter = column_cells[0].column_letter
-            worksheet.column_dimensions[col_letter].width = max_length + 2
-            for cell in column_cells:
-                cell.number_format = "@"
+            # Format all cells as text
+            text_format = workbook.add_format({'num_format': '@'})
+            worksheet.set_column(0, len(chunk.columns) - 1, None, text_format)
+
         outputs.append(filename)
 
-    return outputs
+    import zipfile
+    zip_name = f"{mawb} T01 Manifest.zip"
+    with zipfile.ZipFile(zip_name, 'w') as zipf:
+        for file in outputs:
+            zipf.write(file, arcname=file)
+    return zip_name
 
+# Gradio Interface
 # Gradio Interface
 iface = gr.Interface(
     fn=convert_ci,
@@ -176,9 +173,9 @@ iface = gr.Interface(
         gr.File(label="Upload 'By Line Item' File (.xlsx)", type="filepath"),
         gr.File(label="Upload 'Combined' File (.xlsx)", type="filepath"),
         gr.Textbox(label="Password for 'By Line Item' File", type="password"),
-        gr.Number(label="Max Rows per Output File", value=350, precision=0)
+        gr.Number(label="Max Rows per Output File", value=700, precision=0)
     ],
-    outputs=gr.File(label="Download Partitioned Files", file_types=[".xlsx"], file_count="multiple"),
+    outputs=gr.File(label="Download Zipped Excel Output", file_types=[".zip"]),
     title="SHEIN CI to Magaya Format Conversion Tool",
     description="Upload both 'By Line Item' (with password) and 'Combined' Excel files to merge and generate the Manifest in Magaya T01 Format."
 )