#!/usr/bin/env python3
"""audit_data.py — 数据存储碎片化审计：三个数据目录 + 遗留JSON + 旧库"""
import os, json, sqlite3
from datetime import datetime

DATA_DIRS = [
    '/home/hmo/MoFin/data',
    '/home/hmo/web-dashboard/data',
    '/home/hmo/.hermes/profiles/position-analyst/scripts/data',
    '/home/hmo/.hermes/profiles/position-analyst/data',
    '/home/hmo/.hermes/data',
]

now = datetime.now()

print("=== 1. 各数据目录内容与时效 ===")
for dd in DATA_DIRS:
    if not os.path.isdir(dd):
        print(f"\n{dd}: 不存在")
        continue
    print(f"\n{dd}:")
    try:
        entries = []
        for f in sorted(os.listdir(dd)):
            p = os.path.join(dd, f)
            if os.path.isfile(p):
                mt = datetime.fromtimestamp(os.path.getmtime(p))
                age_h = (now - mt).total_seconds() / 3600
                entries.append((f, os.path.getsize(p), mt, age_h))
        # 只显示 >7天 或 >100KB 的
        for f, size, mt, age_h in entries:
            flag = '🔴' if age_h > 24*14 else ('🟡' if age_h > 24*3 else '🟢')
            print(f"  {flag} {f:45s} {size//1024:6d}KB  {mt.strftime('%m-%d %H:%M')} ({age_h/24:.0f}d)")
    except Exception as e:
        print(f"  ERR: {e}")

print("\n=== 2. 三个 mofin.db 对比 ===")
for label, path in [('canonical', '/home/hmo/MoFin/data/mofin.db'),
                    ('profile-local', '/home/hmo/.hermes/profiles/position-analyst/scripts/data/mofin.db'),
                    ('profile-data', '/home/hmo/.hermes/profiles/position-analyst/data/mofin.db')]:
    if not os.path.exists(path):
        print(f"  {label}: 不存在")
        continue
    c = sqlite3.connect(path, timeout=5)
    tables = {r[0]: r[1] for r in c.execute(
        "SELECT name, (SELECT COUNT(*) FROM sqlite_master m2 WHERE m2.name=m1.name) FROM sqlite_master m1 WHERE type='table'")}
    cnts = {}
    for t in tables:
        try:
            cnts[t] = c.execute(f"SELECT COUNT(*) FROM {t}").fetchone()[0]
        except Exception:
            cnts[t] = -1
    nonempty = {k: v for k, v in cnts.items() if v > 0}
    print(f"  {label} ({os.path.getsize(path)//1024}KB): {len(nonempty)} 张非空表")
    for t, n in sorted(nonempty.items(), key=lambda x: -x[1])[:8]:
        print(f"    {t}: {n}")
    c.close()

print("\n=== 3. 遗留 JSON 文件（web-dashboard/data，按最后修改排序）===")
wd = '/home/hmo/web-dashboard/data'
jfiles = []
for f in os.listdir(wd):
    if f.endswith('.json') and os.path.isfile(os.path.join(wd, f)):
        p = os.path.join(wd, f)
        mt = datetime.fromtimestamp(os.path.getmtime(p))
        jfiles.append((f, os.path.getsize(p), mt))
jfiles.sort(key=lambda x: x[2])
for f, size, mt in jfiles:
    age_d = (now - mt).total_seconds() / 86400
    flag = '🔴' if age_d > 14 else ('🟡' if age_d > 3 else '🟢')
    print(f"  {flag} {f:45s} {size//1024:5d}KB  {mt.strftime('%m-%d')} ({age_d:.0f}d前)")

print("\n=== 4. trashbox / archive / 旧日志 ===")
for d in ['/home/hmo/trashbox', '/home/hmo/MoFin/archive', '/home/hmo/MoFin/data/archive']:
    if os.path.isdir(d):
        total = sum(os.path.getsize(os.path.join(r, f)) for r, _, fs in os.walk(d) for f in fs if os.path.isfile(os.path.join(r, f)))
        cnt = sum(len(fs) for _, _, fs in os.walk(d))
        print(f"  {d}: {cnt} 个文件, {total//1024//1024}MB")
logs = [f for f in os.listdir('/home/hmo') if f.endswith('.log') and os.path.isfile(f'/home/hmo/{f}')]
print(f"\n  /home/hmo 根目录 .log 文件: {len(logs)} 个")
for f in sorted(logs):
    p = f'/home/hmo/{f}'
    mt = datetime.fromtimestamp(os.path.getmtime(p))
    print(f"    {f} {os.path.getsize(p)//1024}KB {mt.strftime('%m-%d')}")