import sys
from detect_overlapping_duplicate_tables import exact_duplicates

sys.stdout.reconfigure(encoding='utf-8')
print(f"Total exact duplicate rows: {len(exact_duplicates)}")

by_file = {}
for d in exact_duplicates:
    by_file.setdefault(d['file'], []).append(d)

for f, dups in sorted(by_file.items()):
    print(f"\n--- {f}: {len(dups)} duplicate rows ---")
    for d in dups[:10]:
        print(f"  L{d['line']} (prev L{d['prev_line']}): {d['row']}")