import os, shutil, glob
from datetime import datetime

ARCHIVE = f'/home/hmo/MoFin/archive/json-legacy-20260720'
os.makedirs(ARCHIVE, exist_ok=True)

# 保留的活文件（在用，不动）
KEEP = {
    'evaluation.json',           # evaluator 在读
    'accuracy_stats.json',       # strategy_feedback 在读
    'format_error_library.json', # 在用 (9d)
    'candidate_pool.json',       # 在用 (3d)
    'pipeline_registry.json',    # 在用 (3d)
    # 今天还在写的
    'growth_registry.json', 'hardcode_audit.json', 'health_checklist.json',
    'macro_divergence_state.json', 'macro_risk_state.json', 'market.json',
    'mofin_health.json', 'portfolio.json', 'preflight_result.json',
    'price_history.json', 'scanner_state.json', 'state.db',
    'strategy_staleness_report.json', 'system_audit_report.json',
    'mofin.db', 'mofin.db-shm', 'mofin.db-wal',
    'analyst-knowledge-log.md', 'mofin_health.html', 'evaluation_input.json',
    'push_cooldown.json', 'system_audit.json', 'system_inventory.json',
    'watchlist.json.bak2',
}

DATA = '/home/hmo/web-dashboard/data'  # = MoFin/data 硬链接
moved = 0
for f in sorted(os.listdir(DATA)):
    p = os.path.join(DATA, f)
    if not os.path.isfile(p):
        continue
    if f in KEEP:
        continue
    if f.startswith('.'):
        continue
    # 只归档 json/db/txt/log/md 类数据文件，别的不动
    if not any(f.endswith(ext) for ext in ('.json', '.db', '.txt')):
        continue
    # 归档目标明确为遗留：>7天未修改
    age_d = (datetime.now().timestamp() - os.path.getmtime(p)) / 86400
    if age_d < 7:
        continue
    shutil.move(p, os.path.join(ARCHIVE, f))
    moved += 1
    print(f'  archived: {f} ({age_d:.0f}d)')

print(f'\narchived {moved} files -> {ARCHIVE}')

# 废弃小库
print('\n=== 废弃小库 ===')
for f in ['market.db', 'market_data.db', 'stock_analysis.db']:
    p = os.path.join(DATA, f)
    if os.path.exists(p):
        print(f'  {f}: 已在归档中' if not os.path.exists(p) else '')
# 上面已经按 >7d 规则归档了（27d/21d 的 db 文件），确认：
for f in ['market.db', 'market_data.db', 'stock_analysis.db']:
    archived = os.path.join(ARCHIVE, f)
    print(f'  {f}: {"ARCHIVED" if os.path.exists(archived) else "still present!"}')