# duplicate_checker.py (v2.0 + Transparenz) import logging import pandas as pd from thefuzz import fuzz from config import Config from helpers import normalize_company_name, simple_normalize_url, create_log_filename from google_sheet_handler import GoogleSheetHandler import time # --- Konfiguration --- CRM_SHEET_NAME = "CRM_Accounts" MATCHING_SHEET_NAME = "Matching_Accounts" SCORE_THRESHOLD = 80 # --- VOLLSTÄNDIGES LOGGING SETUP --- LOG_LEVEL = logging.DEBUG if Config.DEBUG else logging.INFO LOG_FORMAT = '%(asctime)s - %(levelname)-8s - %(name)s - %(message)s' root_logger = logging.getLogger() root_logger.setLevel(LOG_LEVEL) # Handler nur hinzufügen, wenn noch keine konfiguriert sind, um Dopplung zu vermeiden if not root_logger.handlers: stream_handler = logging.StreamHandler() stream_handler.setFormatter(logging.Formatter(LOG_FORMAT)) root_logger.addHandler(stream_handler) log_file_path = create_log_filename("duplicate_check_v2_final") if log_file_path: file_handler = logging.FileHandler(log_file_path, mode='a', encoding='utf-8') file_handler.setFormatter(logging.Formatter(LOG_FORMAT)) root_logger.addHandler(file_handler) else: log_file_path = next((h.baseFilename for h in root_logger.handlers if isinstance(h, logging.FileHandler)), None) logger = logging.getLogger(__name__) def calculate_similarity_with_details(record1, record2): """ Berechnet einen gewichteten Ähnlichkeits-Score und gibt den Score und den Grund zurück. Basierend auf der v2.0 Scoring-Logik. """ scores = {'name': 0, 'location': 0, 'domain': 0} domain1 = record1.get('normalized_domain') domain2 = record2.get('normalized_domain') if domain1 and domain1 != 'k.a.' and domain1 == domain2: scores['domain'] = 100 name1 = record1.get('normalized_name') name2 = record2.get('normalized_name') if name1 and name2: name_similarity = fuzz.token_set_ratio(name1, name2) scores['name'] = round(name_similarity * 0.7) ort1 = record1.get('CRM Ort') ort2 = record2.get('CRM Ort') land1 = record1.get('CRM Land') land2 = record2.get('CRM Land') if ort1 and ort1 == ort2 and land1 and land1 == land2: scores['location'] = 20 total_score = sum(scores.values()) reasons = [] if scores['domain'] > 0: reasons.append(f"Domain({scores['domain']})") if scores['name'] > 0: reasons.append(f"Name({scores['name']})") if scores['location'] > 0: reasons.append(f"Ort({scores['location']})") reason_text = " + ".join(reasons) if reasons else "Keine Übereinstimmung" return round(total_score), reason_text def main(): """Hauptfunktion zum Laden, Vergleichen und Schreiben der Daten.""" start_time = time.time() logger.info("Starte den Duplikats-Check (v2.0 mit Blocking und Maximum Logging)...") logger.info(f"Logdatei: {log_file_path}") try: sheet_handler = GoogleSheetHandler() except Exception as e: logger.critical(f"FEHLER bei Initialisierung des GoogleSheetHandler: {e}") return logger.info(f"Lade Master-Daten aus '{CRM_SHEET_NAME}'...") crm_df = sheet_handler.get_sheet_as_dataframe(CRM_SHEET_NAME) if crm_df is None or crm_df.empty: return logger.info(f"Lade zu prüfende Daten aus '{MATCHING_SHEET_NAME}'...") matching_df = sheet_handler.get_sheet_as_dataframe(MATCHING_SHEET_NAME) if matching_df is None or matching_df.empty: return original_matching_df = matching_df.copy() logger.info("Normalisiere Daten für den Vergleich...") for df in [crm_df, matching_df]: df['normalized_name'] = df['CRM Name'].astype(str).apply(normalize_company_name) df['normalized_domain'] = df['CRM Website'].astype(str).apply(simple_normalize_url) df['CRM Ort'] = df['CRM Ort'].astype(str).str.lower().str.strip() df['CRM Land'] = df['CRM Land'].astype(str).str.lower().str.strip() df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x and x.split() else None) logger.info("Erstelle Index für CRM-Daten zur Beschleunigung...") crm_index = {} crm_records = crm_df.to_dict('records') for record in crm_records: key = record['block_key'] if key: if key not in crm_index: crm_index[key] = [] crm_index[key].append(record) logger.info("Starte Matching-Prozess...") results = [] for match_record in matching_df.to_dict('records'): best_score = -1 best_match_name = "" best_reason = "" logger.info(f"--- Prüfe: '{match_record.get('CRM Name', 'N/A')}' ---") logger.debug(f" [Normalisiert: '{match_record.get('normalized_name')}', Domain: '{match_record.get('normalized_domain')}', Key: '{match_record.get('block_key')}']") block_key = match_record.get('block_key') candidates = crm_index.get(block_key, []) if not candidates: logger.debug(" -> Keine Kandidaten im Index gefunden. Überspringe Vergleich.") results.append({ 'Potenzieller Treffer im CRM': "", 'Ähnlichkeits-Score': 0, 'Matching-Grund': "Keine Kandidaten" }) continue logger.debug(f" -> Vergleiche mit {len(candidates)} Kandidaten aus Block '{block_key}'.") for crm_row in candidates: score, reason = calculate_similarity_with_details(match_record, crm_row) if score > 0: logger.debug(f" - Kandidat: '{crm_row.get('CRM Name', 'N/A')}' -> Score: {score} (Grund: {reason})") if score > best_score: best_score = score best_match_name = crm_row.get('CRM Name', 'N/A') best_reason = reason logger.info(f" --> Bester Treffer: '{best_match_name}' mit Score {best_score} (Grund: {best_reason})") results.append({ 'Potenzieller Treffer im CRM': best_match_name if best_score >= SCORE_THRESHOLD else "", 'Ähnlichkeits-Score': best_score, 'Matching-Grund': best_reason }) logging.info("Matching abgeschlossen. Schreibe Ergebnisse zurück ins Sheet...") result_df = pd.DataFrame(results) output_df = pd.concat([original_matching_df.reset_index(drop=True), result_df], axis=1) data_to_write = [output_df.columns.values.tolist()] + output_df.values.tolist() success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data_to_write) if success: logger.info(f"Ergebnisse erfolgreich in das Tabellenblatt '{MATCHING_SHEET_NAME}' geschrieben.") else: logger.error("FEHLER beim Schreiben der Ergebnisse ins Google Sheet.") end_time = time.time() logger.info(f"Gesamtdauer des Duplikats-Checks: {end_time - start_time:.2f} Sekunden.") logger.info(f"===== Skript beendet =====") if __name__ == "__main__": main()