fangke/server/tracker/services/validation.py

import json
import re
from datetime import datetime
from urllib.parse import parse_qsl, urlencode, urlparse
from django.utils import timezone
from tracker import constants as C

_SENSITIVE = re.compile("|".join(C.SENSITIVE_KEY_PATTERNS), re.I)
_URL_DROP_KEY = re.compile("|".join(C.URL_PARAM_DROP_PATTERNS), re.I)

def _utf8_ok(s: str) -> bool:
    """孤代理（如 "\ud800"）在下游 encode/JSON 序列化时必然 500，入口处即拒。"""
    try:
        s.encode("utf-8")
        return True
    except UnicodeEncodeError:
        return False

def sanitize_url(url: str) -> str:
    """按参数名整键删除（fullmatch 防止误伤 monkey 这类含 key 子串的参数）。"""
    p = urlparse(url)
    kept = [(k, v) for k, v in parse_qsl(p.query, keep_blank_values=True)
            if not _URL_DROP_KEY.fullmatch(k)]
    return p._replace(query=urlencode(kept)).geturl()

def _walk_props(v, depth=0):
    """单次递归同时做深度检查、敏感键扫描与字符串超长检查。
    dict 所有层级的键都过 _SENSITIVE，所有层级的字符串都受 MAX_STR_LEN 约束。
    返回 (depth_ok, sensitive_hit, str_too_long)。深度超限即停止下探，防恶意深嵌套递归爆栈。"""
    if depth > C.MAX_PROP_DEPTH:
        return False, False, False
    if isinstance(v, dict):
        depth_ok, sens, too_long = True, False, False
        for k, x in v.items():
            if _SENSITIVE.search(str(k)):
                sens = True
            d, s, l = _walk_props(x, depth + 1)
            depth_ok = depth_ok and d
            sens = sens or s
            too_long = too_long or l
        return depth_ok, sens, too_long
    if isinstance(v, list):
        depth_ok, sens, too_long = True, False, False
        for x in v:
            d, s, l = _walk_props(x, depth + 1)
            depth_ok = depth_ok and d
            sens = sens or s
            too_long = too_long or l
        return depth_ok, sens, too_long
    if isinstance(v, str) and len(v) > C.MAX_STR_LEN:
        return True, False, True
    return True, False, False

def sanitize_payload(obj):
    """原始批次快照脱敏：递归遍历 dict/list，键名命中 SENSITIVE_KEY_PATTERNS（大小写不敏感）
    → 值替换为字符串 "[FILTERED]"（结构保留，便于排查时仍看清字段形态）。
    返回新对象（容器全部重建，叶值原样共享）——调用方在 ingest 之前对 payload 深拷贝后传入，
    与 ingest/validate_event 的就地改写互不影响。"""
    if isinstance(obj, dict):
        return {k: ("[FILTERED]" if _SENSITIVE.search(str(k)) else sanitize_payload(v))
                for k, v in obj.items()}
    if isinstance(obj, list):
        return [sanitize_payload(x) for x in obj]
    return obj


def validate_event(ev) -> str | None:
    """返回 None 表示通过；否则返回拒绝原因码。类型/白名单/体积/深度全在此守门。
    通过时会就地截断/清洗并写回 ev（path 先 sanitize_url 再截 MAX_PATH_LEN，title 截
    MAX_TITLE_LEN）——Task 6 的 ingest 依赖此写回契约。"""
    if not isinstance(ev, dict):
        return "event_invalid_shape"
    if ev.get("event_name") not in C.EVENT_NAMES:
        return "event_name_not_allowed"
    eid = ev.get("event_id")
    if not isinstance(eid, str) or not eid or len(eid) > 64 or not _utf8_ok(eid):
        return "invalid_event_id"
    for k in ("path", "title"):
        v = ev.get(k)
        if v is not None and (not isinstance(v, str) or not _utf8_ok(v)):
            return "invalid_field_type"
    occ = ev.get("occurred_at")
    if not isinstance(occ, datetime):
        return "invalid_occurred_at"
    if timezone.is_naive(occ):
        return "invalid_occurred_at"
    skew = (timezone.now() - occ).total_seconds()
    if abs(skew) > C.CLOCK_SKEW_REJECT_SEC:
        return "occurred_at_out_of_window"
    props = ev.get("properties", {})
    if not isinstance(props, dict) or len(props) > C.MAX_PROP_KEYS:
        return "properties_invalid"          # 传了但非 dict（[]/""/0/None）一律拒
    # 敏感键扫描（含嵌套层级）先于属性白名单：白名单内无任何键命中敏感模式，
    # 若放在白名单之后，sensitive_field 将不可达（见 test_sensitive_property_rejected）。
    depth_ok, sensitive_hit, str_too_long = _walk_props(props)
    if sensitive_hit:
        return "sensitive_field"
    if not set(props) <= C.EVENT_PROP_WHITELIST.get(ev["event_name"], set()):
        return "property_not_allowed"
    if not depth_ok:
        return "properties_depth"
    # 体积按 UTF-8 字节数守门（汉字多字节，按字符数会被绕过）；孤代理 encode 必炸，按 invalid 拒
    try:
        prop_bytes = len(json.dumps(props, ensure_ascii=False, default=str).encode("utf-8"))
    except UnicodeEncodeError:
        return "properties_invalid"
    if prop_bytes > C.MAX_PROP_JSON_BYTES:
        return "properties_too_large"
    if str_too_long:
        return "properties_too_long"
    # 先清洗后截断：urlencode 对中文查询参数最多膨胀 3 倍，先截后洗会破坏"出门 ≤MAX_PATH_LEN"不变量
    if ev.get("path"):
        ev["path"] = sanitize_url(ev["path"])
    if len(ev.get("path") or "") > C.MAX_PATH_LEN:
        ev["path"] = ev["path"][:C.MAX_PATH_LEN]
    # referrer 是完整 URL：同样过参数清洗（email/token 等整键剔除）再截 MAX_STR_LEN。
    # 放在 str_too_long 检查之后——超长 referrer 仍按 properties_too_long 拒，不静默截半。
    if ev["event_name"] == "page_view" and isinstance(props.get("referrer"), str) and props["referrer"]:
        props["referrer"] = sanitize_url(props["referrer"])[:C.MAX_STR_LEN]
    if len(ev.get("title") or "") > C.MAX_TITLE_LEN:
        ev["title"] = ev["title"][:C.MAX_TITLE_LEN]
    return None