import json
d = json.load(open(r'F:\seismic_webapp\inventory.json'))

# Verifier quelques fichiers
print("=== EXEMPLES DE FICHIERS ===")
for f in d[:5]:
    print(f"File: {f['filename']}")
    print(f"  Bumper: {f['bumper_id']}, Channel: {f['channel']}")
    print(f"  Samples: {f['samples']}, Epoch: {f['epoch_time']}")
    print()

# Compter les bumpers uniques
bumpers = set(f['bumper_id'] for f in d if f['bumper_id'])
print(f"Bumpers uniques: {len(bumpers)}")
print(f"Liste: {sorted(bumpers, key=lambda x: int(x) if x and x.isdigit() else 999)[:30]}")

# Verifier le probleme des samples
print("\n=== FICHIERS AVEC GROS SAMPLES ===")
big_files = [f for f in d if f['samples'] > 100000000]
for f in big_files[:5]:
    print(f"  {f['filename']}: {f['samples']} samples = {f['samples']/200/3600:.1f}h")

# Stats par bumper
from collections import defaultdict
by_bumper = defaultdict(lambda: {'files': 0, 'channels': set()})
for f in d:
    if f['bumper_id']:
        by_bumper[f['bumper_id']]['files'] += 1
        if f['channel']:
            by_bumper[f['bumper_id']]['channels'].add(f['channel'])

print(f"\n=== PAR BUMPER (premiers 20) ===")
for b in sorted(by_bumper.keys(), key=lambda x: int(x) if x.isdigit() else 999)[:20]:
    s = by_bumper[b]
    print(f"  b{b}: {s['files']} files, channels: {sorted(s['channels'])}")