Update app.py

app.py

@@ -3,7 +3,8 @@ import pandas as pd
 from datetime import datetime
 import pytz
 
-# Updated Gradio app for YunExpress with new header mappings and hyperlinks
+# Updated Gradio app for YunExpress with new header mappings, hyperlinks,
+# ZIP padding bug fix, and RoutingCode change (US/NO -> HK-ASS-PF; others -> HKTHZXR)
 
 def process_file(file):
     file_name = file.name.lower()
@@ -16,7 +17,7 @@ def process_file(file):
     except Exception as e:
         return f"Error reading file: {e}", None
 
-    # New output headers as requested
+    # New output headers as requested (kept as in original)
     output_headers = [
         "CustomerOrderNo.", "RoutingCode", "Trackingnumber", "AdditionalServices",
         "ShipmentProtectionPlusService", "SignatureService", "VatNumber", "EoriNumber",
@@ -46,12 +47,12 @@ def process_file(file):
         first = df["Shipping First Name"].fillna("").astype(str).str.strip()
         last  = df["Shipping Last Name"].fillna("").astype(str).str.strip()
         comp  = df["Shipping Company"].fillna("").astype(str).str.strip()
-        output_df["Name"] = (first + " " + last + " " + comp).str.strip()
+        output_df["Name"] = (first + " " + last + " " + comp).str.replace(r"\s+", " ", regex=True).str.strip()
 
     # 3. Street: Address 1 + Address 2 → Street
-    addr1 = df.get("Shipping Address 1", pd.Series([""] * len(df))).fillna("").astype(str).str.strip()
-    addr2 = df.get("Shipping Address 2", pd.Series([""] * len(df))).fillna("").astype(str).str.strip()
-    output_df["Street"] = (addr1 + " " + addr2).str.strip()
+    addr1 = df.get("Shipping Address 1", pd.Series([""] * len(df), index=df.index)).fillna("").astype(str).str.strip()
+    addr2 = df.get("Shipping Address 2", pd.Series([""] * len(df), index=df.index)).fillna("").astype(str).str.strip()
+    output_df["Street"] = (addr1 + " " + addr2).str.replace(r"\s+", " ", regex=True).str.strip()
 
     # 4. City
     if "Shipping City" in df.columns:
@@ -61,21 +62,23 @@ def process_file(file):
     if "Shipping Province" in df.columns:
         output_df["Province/State"] = df["Shipping Province"]
 
-    # 6. ZipCode (pad 4-digit US zips with a leading zero + apostrophe for text)
-    if "Shipping ZIP" in df.columns:
-        zip_raw = df["Shipping ZIP"].astype(str).str.strip()
-        mask_us = output_df["CountryCode"] == "US"
-        mask_4  = zip_raw.str.len() == 4
-        # pad to 5 digits
-        zip_padded = zip_raw.where(~(mask_us & mask_4), "0" + zip_raw)
-        # prefix apostrophe so Excel treats it as text and preserves leading zero
-        zip_final  = zip_padded.where(~(mask_us & mask_4), "'" + zip_padded)
-        output_df["ZipCode"] = zip_final
-
-    # 7. CountryCode
+    # 7. CountryCode (moved BEFORE ZIP handling to fix the bug)
     if "Shipping Country Code" in df.columns:
         output_df["CountryCode"] = df["Shipping Country Code"]
 
+    # 6. ZipCode (pad 4-digit US zips to 5 with leading zero; prefix apostrophe so Excel keeps it)
+    if "Shipping ZIP" in df.columns:
+        zip_raw = (
+            df["Shipping ZIP"]
+            .astype(str)
+            .str.strip()
+            .str.replace(r"\.0$", "", regex=True)  # clean "1234.0"
+        )
+        mask_us = output_df["CountryCode"].eq("US")
+        mask_4  = zip_raw.str.fullmatch(r"\d{4}")
+        zip_padded = zip_raw.where(~(mask_us & mask_4), "0" + zip_raw)
+        output_df["ZipCode"] = zip_padded.where(~(mask_us & mask_4), "'" + zip_padded)
+
     # 8. phone
     if "Shipping Address Phone" in df.columns:
         output_df["phone"] = df["Shipping Address Phone"]
@@ -89,18 +92,19 @@ def process_file(file):
         output_df["DeclaredQuantity1"] = df.groupby("Order Number")["Quantity"].transform("sum")
 
     # 11. Fixed defaults and conditional RoutingCode
-    mask = output_df["CustomerOrderNo."].notna() & (output_df["CustomerOrderNo."] != "")
-    mask_norway = mask & (output_df["CountryCode"] == "NO")
-    mask_other  = mask & (output_df["CountryCode"] != "NO")
+    mask = output_df["CustomerOrderNo."].astype(str).str.len() > 0
 
-    output_df.loc[mask_other, "RoutingCode"] = "HKTHZXR"
-    output_df.loc[mask_norway, "RoutingCode"] = "HK-ASS-PF"
+    # RoutingCode: HK-ASS-PF if CountryCode ∈ {NO, US}; otherwise HKTHZXR
+    mask_us_or_no = mask & output_df["CountryCode"].isin(["US", "NO"])
+    mask_other    = mask & ~output_df["CountryCode"].isin(["US", "NO"])
+    output_df.loc[mask_us_or_no, "RoutingCode"] = "HK-ASS-PF"
+    output_df.loc[mask_other,    "RoutingCode"] = "HKTHZXR"
 
     output_df.loc[mask, "UnitPrice1"]              = 2
     output_df.loc[mask, "CurrencyCode"]            = "USD"
     output_df.loc[mask, "ItemDescription1"]        = "Eye Cosmetic Accessories"
-    output_df.loc[mask, "UnitWeight1"]             = 0.02
     output_df.loc[mask, "ForeignItemDescription1"] = "Eye Cosmetic Accessories"
+    output_df.loc[mask, "UnitWeight1"]             = 0.02
 
     EU_COUNTRIES = {"AT","BE","BG","CY","CZ","DE","DK","EE","ES","FI",
                     "FR","HR","HU","IE","IT","LT","LU","LV","MT","NL",
@@ -121,6 +125,7 @@ def process_file(file):
 
     return output_df, output_file_name
 
+
 # Gradio interface
 with gr.Blocks(title="Shipping - YunExpress") as demo:
     gr.Markdown("# Shipping - YunExpress")
@@ -146,10 +151,10 @@ with gr.Blocks(title="Shipping - YunExpress") as demo:
         <div style="text-align: center; font-size: 16px; margin-top: 20px;">
             <h3>Administration Tools</h3>
             <a href="https://huggingface.co/spaces/leadingbridge/email-template">Email Template</a> | 
-            <a href="https://huggingface.co/spaces/leadingbridge/product-feed">Google Merchant</a> | 
-            <a href="https://huggingface.co/spaces/leadingbridge/tss-order">Order Processing</a>
+            <a href="https://huggingface.co/spaces/leadingbridge/product-feeding">Google Merchant</a> | 
+            <a href="https://huggingface.co/spaces/leadingbridge/tss">Order Processing</a>
         </div>
         """
     )
 
-demo.launch()
+demo.launch()