Update app.py

app.py

@@ -1,5 +1,6 @@
 import pandas as pd
 from openpyxl import load_workbook
+from openpyxl.utils import get_column_letter
 import gradio as gr
 import os
 import warnings
@@ -9,11 +10,8 @@ warnings.filterwarnings("ignore", category=UserWarning, module="openpyxl")
 
 # Load the constant mapping file (embedded in the app)
 def load_mapping():
-    mapping_data = {
-        "PO Output Column": ["Column1", "Column2", "Column3"],  # Replace with actual columns
-        "UVM  MMB  POLY STICKER Column": ["Sheet1.ColumnA", "Sheet1.ColumnB", "Fixed-Value"]  # Replace with mapping logic
-    }
-    return pd.DataFrame(mapping_data)
+    mapping_path = "Levi's Data Mapping.xlsx"
+    return pd.read_excel(mapping_path)
 
 # Function to extract and map data from the input workbook
 def transform_data(input_path, mapping_df):
@@ -21,33 +19,30 @@ def transform_data(input_path, mapping_df):
     input_workbook = pd.ExcelFile(input_path)
 
     # Initialize a dictionary to store data for output
-    output_data = {col: [] for col in mapping_df["PO Output Column"] if not pd.isna(col)}
+    output_data = {}
 
     # Iterate through each mapping rule
     for _, row in mapping_df.iterrows():
         output_column = row["PO Output Column"]
-        input_rule = row["UVM  MMB  POLY STICKER Column"]
+        input_sheet = row["Sheet Name"]
+        input_column = row["Input Column"]
+        start_row = row.get("Start Row", 2)  # Default start row is 2 if not specified
 
-        if pd.isna(output_column) or pd.isna(input_rule):
+        if pd.isna(output_column) or pd.isna(input_sheet) or pd.isna(input_column):
             continue
 
-        # Handle fixed values
-        if "Fixed" in input_rule:
-            fixed_value = input_rule.split("-")[0].strip()
-            output_data[output_column] = [fixed_value] * 10  # Placeholder for rows
+        # Extract data from the specified sheet and column
+        if input_sheet in input_workbook.sheet_names:
+            sheet_data = pd.read_excel(input_path, sheet_name=input_sheet, usecols=[input_column], skiprows=start_row - 1)
+            output_data[output_column] = sheet_data[input_column].tolist()
+        else:
+            output_data[output_column] = []  # If sheet is missing, add empty column
 
-        # Handle column mapping from input workbook
-        elif "." in input_rule:
-            sheet_name, column_name = input_rule.split(".")
-            if sheet_name in input_workbook.sheet_names:
-                sheet_data = pd.read_excel(input_path, sheet_name=sheet_name)
-                if column_name in sheet_data.columns:
-                    output_data[output_column] = sheet_data[column_name].tolist()
-
-    # Fill missing columns with empty lists
+    # Ensure all columns have the same number of rows by filling with blanks
+    max_rows = max(len(col_data) for col_data in output_data.values())
     for key in output_data:
-        if not output_data[key]:
-            output_data[key] = ["" for _ in range(10)]
+        while len(output_data[key]) < max_rows:
+            output_data[key].append("")
 
     return pd.DataFrame(output_data)
 
@@ -61,12 +56,12 @@ def process_files(input_workbook):
         transformed_data = transform_data(input_workbook, mapping_df)
 
         # Load the output template (embedded in the app)
-        output_template_path = "output_template.xlsx"  # Replace with the actual template file path
+        output_template_path = "Generated_Output.xlsx"
         if not os.path.exists(output_template_path):
             return "Output template file is missing."
 
         output_workbook = load_workbook(output_template_path)
-        output_sheet = output_workbook["363040"]
+        output_sheet = output_workbook.active
 
         # Write transformed data to the output sheet
         for row_idx, row_data in enumerate(transformed_data.itertuples(index=False), start=2):
@@ -74,7 +69,7 @@ def process_files(input_workbook):
                 output_sheet.cell(row=row_idx, column=col_idx, value=value)
 
         # Save the generated output file
-        output_file_path = "Generated_Output.xlsx"
+        output_file_path = "Generated_Output_Final.xlsx"
         output_workbook.save(output_file_path)
 
         return output_file_path