#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ P1-④ 实例级细粒度分级:敏感实例加 object_markings 覆盖层(自愈/幂等)。 两层分级模型(server/classification.go + handlers_objects.go): 1) objects.classification 列 = 类型默认级(recompute 物化),由 classificationCond 强制。 2) object_markings 表 = 实例级「额外覆盖层」,由 visibilityCond(CanRead) 强制。 两者都要过:实例 marking 要求主体 clearance 包含其全部 marking。 -> 给实例打 ["L4"] 即在列值之上再叠加一层「仅 L4+ 可见」限制。 规则: - Standard (列默认 L0/公开) 正向命中敏感词 -> ["L3"] (员工可见, 公开/connector 不可见) - PolicyDocument (列默认 L3) 正向命中敏感词 -> ["L4"] (仅 manager/ingest 可见) - UsageControlPolicy(列默认 L3) 全部 -> ["L4"] (访问控制策略, 默认受限) 敏感词排除「非」前缀否定语境(如「非涉密」不计为正向命中)。 自愈: - 正向命中 -> 确保 object_markings = [目标级](已是则跳过)。 - 未命中 -> 若当前有 object_markings(上一轮误标),PUT [] 移除覆盖层,回落到列默认级; 当前本就无标记(由列默认级治理)则不动。 """ import sys, json, argparse sys.path.insert(0, "scripts") import raise_employee_clearance as r SENSITIVE = ["涉密", "机密", "秘密", "保密", "内部", "受限", "敏感", "军事", "国防", "绝密", "商密", "密级", "secret", "internal", "confidential", "restricted", "classified", "sensitive"] CONFIG = { "Standard": {"scan": True, "level": "L3", "reason": "内部/涉密标准(实际扫描0命中, 保持L0公开)"}, "PolicyDocument": {"scan": True, "level": "L4", "reason": "仅国家秘密等真涉密文件升L4; 含'非涉密'否定语境的不升"}, # UsageControlPolicy 不在此处处理:用户确认降到 L3(经理以上也可治理), # 由 scripts/revert_ucp_level.py 维护(实例级移除L4覆盖层, 回落类型默认L3)。 } def list_instances(typ): out, offset = [], 0 while True: code, data = r.api("GET", f"/objects?type={typ}&limit=1000&offset={offset}") if code != 200 or not data: break arr = data.get("items", data) if isinstance(data, dict) else data if not arr: break out.extend(arr) if len(arr) < 1000: break offset += 1000 return out def text_of(o): parts = [str(o.get(k, "") or "") for k in ("name", "title", "title_cn", "title_en", "standard_code", "doc_no", "publisher", "issuer", "scope", "classification")] pj = o.get("properties_json") or o.get("properties") if isinstance(pj, dict): parts += [str(v) for v in pj.values()] elif isinstance(pj, str): parts.append(pj) return " ".join(parts).lower() def positive_hit(txt): hits = [] for kw in SENSITIVE: k = kw.lower() start = 0 found = False while True: i = txt.find(k, start) if i < 0: break if i > 0 and txt[i - 1] == "非": # 否定语境,不算正向命中 start = i + len(k) continue found = True start = i + len(k) if found: hits.append(kw) return hits def get_current_markings(typ, pk): code, data = r.api("GET", f"/access/objects/{typ}/{pk}/markings") if code == 200 and isinstance(data, dict): return data.get("markings", []) or [] return [] def main(): ap = argparse.ArgumentParser() ap.add_argument("--dry-run", action="store_true", help="只盘点不写入") args = ap.parse_args() plan, applied, reverted = [], 0, 0 for typ, cfg in CONFIG.items(): insts = list_instances(typ) for o in insts: pk = o.get("pk") name = o.get("name") or o.get("title_cn") or o.get("title") or pk txt = text_of(o) cur = get_current_markings(typ, pk) hits = positive_hit(txt) if cfg["scan"] else ["(全部)"] if hits: desired = [cfg["level"]] note = "升" + str(hits) else: # 未命中:仅当本就被误升到目标级(覆盖层)时才回落移除; # 其余(如 recompute 物化的列默认级标记)保持原样不动。 desired = [] if cur == [cfg["level"]] else cur note = "回落(移除误标)" if desired == [] else "保持" if cur == desired: continue plan.append((typ, pk, name, desired, cur, note)) if args.dry_run: continue code, _ = r.api("PUT", f"/access/objects/{typ}/{pk}/markings", {"markings": desired}) if code == 200: if desired: applied += 1 else: reverted += 1 else: print(f" ✗ 写入失败 {typ}/{pk}: HTTP {code}", file=sys.stderr) print(f"[{typ}] 实例总数={len(insts)} 目标级={cfg['level']} ({cfg['reason']})") print(f"\n=== 待处理 {len(plan)} 条(升={sum(1 for p in plan if p[3])} 移除误标={sum(1 for p in plan if not p[3])})===") for typ, pk, name, desired, cur, note in plan[:60]: print(f" {typ}/{pk} {cur} -> {desired or '[]'} {note} {name!r}") if len(plan) > 60: print(f" ... 其余 {len(plan)-60} 条省略") if args.dry_run: print("\n[DRY-RUN] 未写入。去掉 --dry-run 执行。") else: print(f"\n已写入:加覆盖层 {applied} 条,移除误标 {reverted} 条(幂等)。") if __name__ == "__main__": main()