duplicate_checker.py aktualisiert

duplicate_checker.py

@@ -172,13 +172,29 @@ def main():
             results.append({'Match':'','Score':best_score})
             logger.info(f" --> Kein Match (Score={best_score}) [Dom={dm},Name={ns},Ort={lm},Bonus={bf}]")
 
-    # Ergebnisse zurückschreiben (inkl. Gefundene Website)
-    logger.info("Schreibe Ergebnisse ins Sheet...")
-    out = pd.DataFrame(results)
-    output = match_df[['CRM Name','CRM Website','Gefundene Website','CRM Ort','CRM Land']].copy()
-    output = pd.concat([output.reset_index(drop=True), out], axis=1)
-    data = [output.columns.tolist()] + output.values.tolist()
-    if sheet.clear_and_write_data(MATCHING_SHEET_NAME, data):
+    # Ergebnisse zurückschreiben (SAFE: alle Originalspalten + neue, ohne interne Normalisierungsfelder)
+    logger.info("Schreibe Ergebnisse ins Sheet (SAFE in-place, keine Spaltenverluste)...")
+    res_df = pd.DataFrame(results, index=match_df.index)
+    write_df = match_df.copy()
+    # Ergebnisse anfügen
+    write_df['Match'] = res_df['Match']
+    write_df['Score'] = res_df['Score']
+    # Interne Arbeitsfelder entfernen
+    drop_cols = ['normalized_name', 'normalized_domain', 'block_key', 'Effektive Website']
+    for c in drop_cols:
+        if c in write_df.columns:
+            write_df.drop(columns=[c], inplace=True)
+    # Lokales Backup der originalen Matching-Daten inkl. neuer Spalten
+    backup_path = os.path.join(LOG_DIR, f"{now}_backup_{MATCHING_SHEET_NAME}.csv")
+    try:
+        write_df.to_csv(backup_path, index=False, encoding='utf-8')
+        logger.info(f"Lokales Backup geschrieben: {backup_path}")
+    except Exception as e:
+        logger.warning(f"Backup fehlgeschlagen: {e}")
+    # Schreiben
+    data = [write_df.columns.tolist()] + write_df.fillna('').values.tolist()
+    ok = sheet.clear_and_write_data(MATCHING_SHEET_NAME, data)
+    if ok:
         logger.info("Ergebnisse erfolgreich geschrieben")
     else:
         logger.error("Fehler beim Schreiben ins Google Sheet")