duplicate_checker.py aktualisiert

duplicate_checker.py

@@ -267,12 +267,12 @@ def main():
     metrics = Counter()
     total = len(match_df)
     logger.info("Starte Matching-Prozess…")
-    for i, mrow in match_df.to_dict('records'):
-        pass
+    processed = 0
 
     # iterate safely with index
     for idx, mrow in match_df.to_dict('index').items():
         name_disp = mrow.get('CRM Name','')
+        processed += 1
         # Kandidatenwahl
         candidates = []
         used_block = ''
@@ -299,7 +299,7 @@ def main():
             candidates = [r for _, r in pf[:PREFILTER_LIMIT]]
             used_block = f"prefilter:{PREFILTER_MIN_PARTIAL}/{len(pf)}"
 
-        logger.info(f"Prüfe {idx+1}/{total}: '{name_disp}' -> {len(candidates)} Kandidaten (Block={used_block})")
+        logger.info(f"Prüfe {processed}/{total}: '{name_disp}' -> {len(candidates)} Kandidaten (Block={used_block})")
         if not candidates:
             results.append({'Match':'', 'Score':0, 'Match_Grund':'keine Kandidaten'})
             continue