Brancheneinstufung2/duplicate_checker.py

import os
import sys
import logging
import pandas as pd
from thefuzz import fuzz
from helpers import normalize_company_name, simple_normalize_url
from google_sheet_handler import GoogleSheetHandler

# duplicate_checker.py v2.7 (Logging-Setup Fix)
# Version: 2025-08-06_17-30

# --- Konfiguration ---
CRM_SHEET_NAME      = "CRM_Accounts"
MATCHING_SHEET_NAME = "Matching_Accounts"
SCORE_THRESHOLD     = 80
LOG_DIR             = "Log"
LOG_FILE            = "duplicate_check_v2.7.log"

# --- Logging Setup ---
if not os.path.exists(LOG_DIR):
    os.makedirs(LOG_DIR, exist_ok=True)
log_path = os.path.join(LOG_DIR, LOG_FILE)

# Clear existing handlers
root_logger = logging.getLogger()
root_logger.setLevel(logging.DEBUG)
for h in list(root_logger.handlers):
    root_logger.removeHandler(h)

# Formatter
formatter = logging.Formatter("%(asctime)s - %(levelname)-8s - %(message)s")

# Console Handler - INFO+
ch = logging.StreamHandler(sys.stdout)
ch.setLevel(logging.INFO)
ch.setFormatter(formatter)
root_logger.addHandler(ch)

# File Handler - DEBUG+
fh = logging.FileHandler(log_path, mode='a', encoding='utf-8')
fh.setLevel(logging.DEBUG)
fh.setFormatter(formatter)
root_logger.addHandler(fh)

logger = logging.getLogger(__name__)
logger.info(f"Logging to console and file: {log_path}")
logger.info("Starting duplicate_checker.py v2.7 | Version: 2025-08-06_17-30")


def calculate_similarity(record1, record2):
    total_score = 0
    dom1 = record1.get('normalized_domain', '')
    dom2 = record2.get('normalized_domain', '')
    if dom1 and dom1 == dom2:
        total_score += 100
    name1 = record1.get('normalized_name', '')
    name2 = record2.get('normalized_name', '')
    if name1 and name2:
        total_score += fuzz.token_set_ratio(name1, name2) * 0.7
    if record1.get('CRM Ort') == record2.get('CRM Ort') and record1.get('CRM Land') == record2.get('CRM Land'):
        total_score += 20
    return round(total_score)


def main():
    logger.info("Starte Duplikats-Check v2.7")
    try:
        sheet_handler = GoogleSheetHandler()
        logger.info("GoogleSheetHandler initialisiert")
    except Exception as e:
        logger.critical(f"Init GoogleSheetHandler fehlgeschlagen: {e}")
        sys.exit(1)

    # Load data
    logger.info(f"Lade CRM-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:
        logger.critical("CRM-Tab leer. Abbruch.")
        return
    logger.info(f"{len(crm_df)} CRM-Datensätze geladen")

    logger.info(f"Lade Matching-Daten aus '{MATCHING_SHEET_NAME}'...")
    match_df = sheet_handler.get_sheet_as_dataframe(MATCHING_SHEET_NAME)
    if match_df is None or match_df.empty:
        logger.critical("Matching-Tab leer. Abbruch.")
        return
    logger.info(f"{len(match_df)} Matching-Datensätze geladen")

    # Normalize & blocking key
    for df, label in [(crm_df, 'CRM'), (match_df, 'Matching')]:
        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 else None)
        logger.debug(f"{label}-Sample: {df.iloc[0][['normalized_name','normalized_domain','block_key']].to_dict()}")

    # Build blocking index
    logger.info("Erstelle Blocking-Index...")
    crm_index = {}
    for idx, row in crm_df.iterrows():
        key = row['block_key']
        if key:
            crm_index.setdefault(key, []).append(row)
    logger.info(f"Blocking-Index mit {len(crm_index)} Keys erstellt")

    # Matching
    logger.info("Starte Matching...")
    results = []
    total = len(match_df)
    for i, mrow in match_df.iterrows():
        key = mrow['block_key']
        candidates = crm_index.get(key, [])
        logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' -> {len(candidates)} Kandidaten")
        if not candidates:
            results.append({'Potenzieller Treffer im CRM': '', 'Ähnlichkeits-Score': 0})
            continue
        scored = [(crow['CRM Name'], calculate_similarity(mrow, crow)) for crow in candidates]
        top3 = sorted(scored, key=lambda x: x[1], reverse=True)[:3]
        logger.debug(f" Top3 Kandidaten: {top3}")
        best_name, best_score = max(scored, key=lambda x: x[1])
        if best_score >= SCORE_THRESHOLD:
            results.append({'Potenzieller Treffer im CRM': best_name, 'Ähnlichkeits-Score': best_score})
            logger.info(f" --> Match: '{best_name}' Score={best_score}")
        else:
            results.append({'Potenzieller Treffer im CRM': best_name or '', 'Ähnlichkeits-Score': best_score})
            logger.info(f" --> Kein Match (Score {best_score})")

    # Write back
    logger.info("Schreibe Ergebnisse zurück ins Sheet...")
    out_df = pd.DataFrame(results)
    output = match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].copy()
    output = pd.concat([output.reset_index(drop=True), out_df], axis=1)
    data = [output.columns.tolist()] + output.values.tolist()
    success = sheet_handler.clear_and_write_data(MATCHING_SHEET_NAME, data)
    if success:
        logger.info("Ergebnisse erfolgreich geschrieben")
    else:
        logger.error("Fehler beim Schreiben ins Google Sheet")

if __name__ == '__main__':
    main()