Update app.py

app.py

@@ -6,6 +6,7 @@ from huggingface_hub import hf_hub_download
 import tempfile
 import os, re
 from collections import defaultdict
+from datetime import datetime
 
 HF_DATASET_REPO = "leadingbridge/ammu"
 TEMPLATE_FILENAME = "AMMU-order-form-template.xlsx"
@@ -63,6 +64,17 @@ def _download_template():
         repo_id=HF_DATASET_REPO, filename=TEMPLATE_FILENAME, repo_type="dataset"
     )
 
+def _auto_fit_columns(ws: Worksheet, max_col: int, max_row: int):
+    # Width = longest string in column + small padding
+    for c in range(1, max_col + 1):
+        max_len = 0
+        col_letter = get_column_letter(c)
+        for r in range(1, max_row + 1):
+            val = ws.cell(row=r, column=c).value
+            if val is not None:
+                max_len = max(max_len, len(str(val)))
+        ws.column_dimensions[col_letter].width = max(10, max_len + 2)
+
 def process(input_file):
     try:
         if input_file is None:
@@ -71,6 +83,11 @@ def process(input_file):
         # --- INPUT: detect headers by name ---
         wb_in = load_workbook(input_file.name, data_only=True)
         ws_in = wb_in.active
+
+        # Copy ALL input (for "raw data" sheet later)
+        in_max_row = ws_in.max_row
+        in_max_col = ws_in.max_column
+
         header_row_idx, header_map = _find_header_row(
             ws_in, {"SKU", "Product Option Value", "Quantity"}
         )
@@ -78,7 +95,6 @@ def process(input_file):
         col_pov = header_map["product option value"]
         col_qty = header_map["quantity"]
 
-        in_max_col = ws_in.max_column
         header_values = [ws_in.cell(row=header_row_idx, column=c).value for c in range(1, in_max_col + 1)]
 
         entries = []
@@ -123,10 +139,12 @@ def process(input_file):
 
         for r in range(1, 11):
             row_vals = [ws_out.cell(row=r, column=c).value for c in range(1, ws_out.max_column + 1)]
+            # "MY SKU" header
             for c, v in enumerate(row_vals, start=1):
                 if isinstance(v, str) and v.strip().lower() == "my sku":
                     mysku_header_row = r
                     mysku_col_idx = c
+            # textual power labels
             labels = {}
             for c, v in enumerate(row_vals, start=1):
                 if isinstance(v, str):
@@ -136,6 +154,7 @@ def process(input_file):
             if len(labels) >= 5 and power_label_row is None:
                 power_label_row = r
                 power_col_map = labels
+            # numeric triplets
             trip = {}
             for c, v in enumerate(row_vals, start=1):
                 if isinstance(v, str) and re.fullmatch(r"\d{2,3}", v.strip()):
@@ -145,10 +164,11 @@ def process(input_file):
                 triplet_col_map = trip
 
         if mysku_header_row is None or mysku_col_idx is None:
-            raise ValueError("Could not find the 'MY SKU' header in the template.")
+            raise ValueError("Could not find the 'MY SKU' header in the template (rows 1–10).")
         if not (power_label_row or triplet_row):
-            raise ValueError("Could not find power-column headers in the template.")
+            raise ValueError("Could not find power-column headers in the template (rows 1–10).")
 
+        # Build SKU -> row map
         sku_to_row = {}
         for r in range(mysku_header_row + 1, ws_out.max_row + 1):
             val = ws_out.cell(row=r, column=mysku_col_idx).value
@@ -156,6 +176,7 @@ def process(input_file):
                 continue
             sku_to_row[str(val).strip()] = r
 
+        # Classify entries and aggregate matches
         agg = defaultdict(int)
         unmatched_rows = []
 
@@ -177,6 +198,7 @@ def process(input_file):
                 continue
             agg[(sku, power)] += qty
 
+        # Write aggregated matches
         written_count = 0
         for (sku, power), qty in agg.items():
             row_idx = sku_to_row.get(sku)
@@ -199,40 +221,49 @@ def process(input_file):
             ws_out.cell(row=row_idx, column=col_idx).value = current_val + int(qty)
             written_count += 1
 
-        # --- Create the "additional order" tab ---
-        sheet_name = "additional order"
-        if sheet_name in wb_out.sheetnames:
-            wb_out.remove(wb_out[sheet_name])
-        ws_extra = wb_out.create_sheet(title=sheet_name)
+        # --- "additional order" tab with unmatched rows ---
+        add_name = "additional order"
+        if add_name in wb_out.sheetnames:
+            wb_out.remove(wb_out[add_name])
+        ws_add = wb_out.create_sheet(title=add_name)
 
-        # Write header
+        # header + rows
         for c, val in enumerate(header_values, start=1):
-            ws_extra.cell(row=1, column=c).value = val
-        # Write unmatched rows
+            ws_add.cell(row=1, column=c).value = val
         for i, row_vals in enumerate(unmatched_rows, start=2):
             for c, val in enumerate(row_vals, start=1):
-                ws_extra.cell(row=i, column=c).value = val
-
-        # --- Auto adjust column widths ---
-        for c in range(1, in_max_col + 1):
-            max_len = 0
-            col_letter = get_column_letter(c)
-            for r in range(1, len(unmatched_rows) + 2):  # +1 header
-                val = ws_extra.cell(row=r, column=c).value
-                if val is not None:
-                    max_len = max(max_len, len(str(val)))
-            ws_extra.column_dimensions[col_letter].width = max_len + 2  # padding
-
-        # Save output
+                ws_add.cell(row=i, column=c).value = val
+
+        # Auto-fit additional order
+        _auto_fit_columns(ws_add, max_col=in_max_col, max_row=len(unmatched_rows) + 1)
+
+        # --- "raw data" tab with ALL input copied verbatim ---
+        raw_name = "raw data"
+        if raw_name in wb_out.sheetnames:
+            wb_out.remove(wb_out[raw_name])
+        ws_raw = wb_out.create_sheet(title=raw_name)
+
+        for r in range(1, in_max_row + 1):
+            for c in range(1, in_max_col + 1):
+                ws_raw.cell(row=r, column=c).value = ws_in.cell(row=r, column=c).value
+
+        # Auto-fit raw data
+        _auto_fit_columns(ws_raw, max_col=in_max_col, max_row=in_max_row)
+
+        # --- Save output with date-based filename ---
+        yymmdd = datetime.now().strftime("%y%m%d")
         tmpdir = tempfile.mkdtemp()
-        out_path = os.path.join(tmpdir, "AMMU-order-form-FILLED.xlsx")
+        out_filename = f"AMMU-Order-Form-Leading-Bridge-{yymmdd}.xlsx"
+        out_path = os.path.join(tmpdir, out_filename)
         wb_out.save(out_path)
 
         log_lines = [
             f"Rows scanned in input: {rows_scanned}",
             f"Unique matched (SKU, power) pairs aggregated: {len(agg)}",
             f"Entries written into template: {written_count}",
-            f"Unmatched rows copied to '{sheet_name}': {len(unmatched_rows)}",
+            f"Unmatched rows copied to 'additional order': {len(unmatched_rows)}",
+            f"Raw data sheet rows x cols: {in_max_row} x {in_max_col}",
+            f"Output file: {out_filename}",
         ]
         log = "\n".join(log_lines)
         return out_path, log
@@ -246,7 +277,9 @@ with gr.Blocks(title="AMMU Order Form Filler") as demo:
         "• Uses **MY SKU** column to map rows\n"
         "• Matches power columns (text like `-1.25` or fallback triplets like `125`)\n"
         "• Aggregates quantities for matched lines\n"
-        "• Copies **unmatched lines** to new sheet **`additional order`**, with auto column width"
+        "• Copies **unmatched lines** to **`additional order`** (auto-fit columns)\n"
+        "• Copies **entire input** to **`raw data`** (auto-fit columns)\n"
+        "• Exports as **AMMU-Order-Form-Leading-Bridge-YYMMDD.xlsx**"
     )
     with gr.Row():
         in_file = gr.File(label="Upload input Excel (.xlsx)", file_types=[".xlsx"])
@@ -254,7 +287,7 @@ with gr.Blocks(title="AMMU Order Form Filler") as demo:
         run_btn = gr.Button("Process")
     with gr.Row():
         out_file = gr.File(label="Download filled template (.xlsx)")
-    log_box = gr.Textbox(label="Log", lines=10)
+    log_box = gr.Textbox(label="Log", lines=12)
 
     run_btn.click(fn=process, inputs=in_file, outputs=[out_file, log_box])