added zip code fixer

app.py

@@ -1,22 +1,15 @@
-
 import os
 import pandas as pd
+import re
 import gradio as gr
 from datetime import datetime
 
-# ------------------------------------------------------------------
-# 1️⃣  EDITABLE SETTINGS
-# ------------------------------------------------------------------
-EXTRA_MODS = []    # optional suffixes
+# ------------------------ SETTINGS ------------------------
+EXTRA_MODS = []
 CITY_TEMPLATES = [
     "{keyword} {city}",
-    # "{keyword} {city} ca",
-    # "{keyword} {city} new jersey",
     "{keyword} in {city}",
-    # "{keyword} in {city} california",
     "{city} {keyword}",
-    # "{city} ca {keyword}",
-    # "{city} california {keyword}",
 ]
 ZIP_TEMPLATES = [
     "{keyword} {zip}",
@@ -26,32 +19,24 @@ ZIP_TEMPLATES = [
 def has_any_mod(phrase: str, mods) -> bool:
     return any(phrase.endswith(" " + m) for m in mods)
 
-# ------------------------------------------------------------------
-# 2️⃣  CORE LOGIC  (unchanged except for reading keywords from Excel)
-# ------------------------------------------------------------------
+# ------------------------ CORE LOGIC ------------------------
 def build_keywords(city_df: pd.DataFrame, kw_df: pd.DataFrame):
-    primary_zip_col = city_df.columns[0]  # A
-    city_col        = city_df.columns[1]  # B
-    # state_col       = city_df.columns[2]  # C
-
-    # Check if ZIP list column (F) exists
-    zip_list_col = city_df.columns[5] if len(city_df.columns) > 5 else None
+    primary_zip_col = city_df.columns[0]
+    city_col        = city_df.columns[1]
+    zip_list_col    = city_df.columns[5] if len(city_df.columns) > 5 else None
 
     city_kw_records, zip_kw_records = [], []
 
     for _, row in city_df.iterrows():
         city        = str(row[city_col]).strip().lower()
-        # state       = str(row[state_col]).strip().upper()
         primary_zip = str(row[primary_zip_col]).strip()
-
-        zip_raw = str(row[zip_list_col]) if zip_list_col and pd.notna(row[zip_list_col]) else ""
-        zip_list = [z.strip() for z in zip_raw.split(",") if z.strip().isdigit()] or (
+        zip_raw     = str(row[zip_list_col]) if zip_list_col and pd.notna(row[zip_list_col]) else ""
+        zip_list    = [z.strip() for z in zip_raw.split(",") if z.strip().isdigit()] or (
             [primary_zip] if primary_zip.isdigit() else []
         )
 
         for kw in kw_df.iloc[:, 0].astype(str):
             kw = kw.lower().strip()
-
             kw_variants = [kw]
             if not has_any_mod(kw, EXTRA_MODS):
                 kw_variants += [f"{kw} {m}" for m in EXTRA_MODS]
@@ -59,78 +44,82 @@ def build_keywords(city_df: pd.DataFrame, kw_df: pd.DataFrame):
             for v in kw_variants:
                 for tpl in CITY_TEMPLATES:
                     candidate = tpl.format(keyword=v, city=city).replace("  ", " ").strip()
-                    city_kw_records.append({
-                        "City": city.title(),
-                        # "State": state,
-                        "Keyword": candidate,
-                    })
+                    city_kw_records.append({"City": city.title(), "Keyword": candidate})
 
             for z in zip_list:
                 for tpl in ZIP_TEMPLATES:
                     candidate = tpl.format(keyword=kw, zip=z).strip()
-                    zip_kw_records.append({
-                        "ZIP": z,
-                        "Keyword": candidate,
-                    })
+                    zip_kw_records.append({"ZIP": z, "Keyword": candidate})
 
     city_out = pd.DataFrame(city_kw_records).drop_duplicates(subset=["Keyword"])
     zip_out  = pd.DataFrame(zip_kw_records).drop_duplicates(subset=["Keyword"])
     return city_out, zip_out
 
-
-# ------------------------------------------------------------------
-# 3️⃣  UTIL – create tidy output file names
-# ------------------------------------------------------------------
 def make_name(prefix: str, city_file: str, kw_file: str):
     a = os.path.splitext(os.path.basename(city_file))[0]
     b = os.path.splitext(os.path.basename(kw_file))[0]
-    today = datetime.now().strftime("%Y%m%d")   # makes name unique & sortable
+    today = datetime.now().strftime("%Y%m%d")
     return f"{prefix}_{a}__{b}_{today}.csv"
 
-
-# ------------------------------------------------------------------
-# 4️⃣  MAIN callable for Gradio
-# ------------------------------------------------------------------
 def run_builder(city_excel, keyword_excel):
-    # read excels
     city_df = pd.read_excel(city_excel.name)
     kw_df   = pd.read_excel(keyword_excel.name)
 
     city_out, zip_out = build_keywords(city_df, kw_df)
 
-    # write to CSVs with combined names
     city_csv = make_name("locksmith_city_keywords", city_excel.name, keyword_excel.name)
     zip_csv  = make_name("locksmith_zip_keywords",  city_excel.name, keyword_excel.name)
     city_out.to_csv(city_csv, index=False)
     zip_out.to_csv(zip_csv,  index=False)
 
-    # return paths so Gradio presents download buttons
     return city_csv, zip_csv
 
+# ------------------------ ZIP COMBINER TAB ------------------------
+def combine_zips(file):
+    df = pd.read_excel(file.name)
+    col_a = df.iloc[:, 0].dropna().astype(str).str.strip()
+    col_f_raw = df.iloc[:, 5].dropna().astype(str)
+    flat_col_f = []
 
-# ------------------------------------------------------------------
-# 5️⃣  GRADIO FRONT-END
-# ------------------------------------------------------------------
-title = "Locksmith Keyword Generator"
-description = (
-    "Upload:\n"
-    "  1️⃣  *City-ZIP Excel* (columns: ZIP Code, City, State, … ZIP List in col F)\n"
-    "  2️⃣  *Keywords Excel* (first column contains the base keywords)\n\n"
-    "Click **Generate** and download the two CSVs."
-)
+    for row in col_f_raw:
+        zip_codes = re.split(r'[\n,]+', row)
+        flat_col_f.extend([z.strip() for z in zip_codes if z.strip()])
 
-demo = gr.Interface(
+    all_zips = pd.Series(list(col_a) + flat_col_f).drop_duplicates().reset_index(drop=True)
+
+    base_name = os.path.splitext(os.path.basename(file.name))[0]
+    output_path = f"{base_name}_zips_combined.xlsx"
+    all_zips.to_excel(output_path, index=False, header=['ZIP'])
+
+    return output_path
+
+# ------------------------ INTERFACES ------------------------
+locksmith_demo = gr.Interface(
     fn=run_builder,
     inputs=[
-        gr.File(label="City & ZIP Excel (e.g. Orange County.xlsx)",    file_types=[".xls", ".xlsx"]),
-        gr.File(label="Keyword Excel (one keyword per row)",            file_types=[".xls", ".xlsx"]),
+        gr.File(label="City & ZIP Excel",    file_types=[".xls", ".xlsx"]),
+        gr.File(label="Keyword Excel",       file_types=[".xls", ".xlsx"]),
     ],
     outputs=[
         gr.File(label="City-level keyword CSV"),
         gr.File(label="ZIP-level keyword CSV"),
     ],
-    title=title,
-    description=description,
+    title="Locksmith Keyword Generator",
+    description="Upload 1️⃣ City-ZIP Excel and 2️⃣ Keyword Excel. Generate city & ZIP-based keyword CSVs.",
+)
+
+zip_demo = gr.Interface(
+    fn=combine_zips,
+    inputs=gr.File(label="Excel with ZIPs in Column A & F", file_types=[".xls", ".xlsx"]),
+    outputs=gr.File(label="Combined ZIP Excel"),
+    title="ZIP Code Combiner",
+    description="Upload an Excel file with ZIPs in Column A and ZIP Lists in Column F (comma/newline separated). Get a clean, deduplicated ZIP list.",
+)
+
+# ------------------------ MULTI-TAB APP ------------------------
+demo = gr.TabbedInterface(
+    interface_list=[locksmith_demo, zip_demo],
+    tab_names=["🔐 Keyword Builder", "📬 ZIP Combiner"]
 )
 
 if __name__ == "__main__":