hello_js_reverse_skill/scripts/verify/audit_names.py

# -*- coding: utf-8 -*-
"""audit_names.py —— 把「语义名 / 模块结构 / 明文槽值」放在一张表里逐个核对。

为什么需要（2026-10-12 实测）:
  对齐是**按位置**做的（require 序 == 槽位序），所以一旦某个语义名识别错了，
  它对应的**真值就会被记到错误的名字下**。tdc_profile 之前就把「轨迹」的
  空数组记成了 trajectory，而真正的轨迹（含 mousemove/touchmove 的大模块）
  却在另一个名字下。名字错 = 生成器错，必须逐个核对。

本脚本给出 4 条独立证据并排显示:
  1. 指纹命中的字符串（tdc_modules 的规则）
  2. 结构签名（entry/get 指令数、closure 种类）
  3. 该模块**自身代码里**是否出现鼠标/触摸/时钟等关键串
  4. 同会话明文里该槽的**真值**

用法:
    .venv/bin/python scripts/verify/audit_names.py \
        --build /tmp/1ms_bridge/session_build.js \
        --collect /tmp/1ms_bridge/session_collect.json
"""
import argparse
import base64
import json
import re
import sys
from pathlib import Path
from urllib.parse import unquote

ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT))
sys.path.insert(0, str(ROOT / "tools"))

import tdc_modules as tm          # noqa: E402
import tdc_program as tp          # noqa: E402
from tcaptcha.crypto import xtea_decrypt_bytes          # noqa: E402
from tcaptcha.tdc_key import extract_xtea_key_pure      # noqa: E402

# 用于「这个模块到底像在采什么」的旁证关键词
HINTS = {
    "鼠标/触摸轨迹": ["mousemove", "mouseMoveEvent", "touchmove", "touchStartEvent",
                 "mousedown", "pointermove", "clientX", "pageX"],
    "时钟": ["getTime", "Date", "performance"],
    "屏幕": ["screen", "colorDepth", "availHeight"],
    "WebGL": ["UNMASKED", "getExtension", "getParameter"],
    "Canvas": ["toDataURL", "getImageData", "fillText"],
    "UA/平台": ["userAgent", "platform"],
    "时区/语言": ["getTimezoneOffset", "languages"],
    "自动化检测": ["webdriver", "$cdc_", "__webdriver_script_fn"],
    "存储": ["cookie", "localStorage", "sessionStorage"],
    "iframe/DOM": ["contentWindow", "createElement", "appendChild"],
}


def parse_cd(plain: str):
    """把明文切成 (cd 元素列表带跨度, 顶层对象)。pad（>=2 空格）先移除。"""
    logical = re.sub(r" {2,}", "", plain)
    dec = json.JSONDecoder()
    i = logical.index("[", logical.index('"cd"'))
    spans, j = [], i + 1
    while True:
        while logical[j] in " \t\r\n,":
            j += 1
        if logical[j] == "]":
            break
        val, end = dec.raw_decode(logical, j)
        spans.append((val, j, end))
        j = end
    return spans, json.loads(logical)


def slot_names(rows):
    """把 37 个清单项展开成 38 个槽的语义名（itoken 占 2 槽）。"""
    out = []
    for i, r in enumerate(rows):
        n = 2 if r["name"].startswith("itoken") else 1
        out.extend([r["name"]] * n)
    return out


def main() -> int:
    ap = argparse.ArgumentParser(description="语义名 / 结构 / 槽值 联合审计")
    ap.add_argument("--build", default="/tmp/1ms_bridge/session_build.js")
    ap.add_argument("--collect", default="/tmp/1ms_bridge/session_collect.json")
    ap.add_argument("--json", default="/tmp/1ms_bridge/audit.json")
    args = ap.parse_args()

    js = open(args.build, encoding="utf-8", errors="replace").read()
    key = extract_xtea_key_pure(js)["key"]
    sess = json.load(open(args.collect, encoding="utf-8"))
    if "collect" not in sess and isinstance(sess.get("data"), dict):
        sess = sess["data"]
    plain = xtea_decrypt_bytes(base64.b64decode(unquote(sess["collect"])), key) \
        .decode("latin1").rstrip("\x00")

    spans, _obj = parse_cd(plain)
    pads = [m.span() for m in re.finditer(r" {2,}", plain)]

    p = tp.load(args.build)
    rows = tm.analyze_prog(p)
    names = slot_names(rows)

    print("构建 %s (%d 字节)  明文 %d 字节  cd %d 槽  清单 %d 项"
          % (Path(args.build).name, len(js), len(plain), len(spans), len(rows)))
    print("pad 段边界:", [(a, b, b - a) for a, b in pads])
    pad_ends = {a for a, _b in pads}
    print()

    out = []
    print("%-3s %-5s %-36s %-9s %-22s %s"
          % ("项", "模块", "语义名", "结构", "槽值", "旁证"))
    print("-" * 132)
    for i, r in enumerate(rows):
        n = 2 if r["name"].startswith("itoken") else 1
        k = sum(2 if x["name"].startswith("itoken") else 1 for x in rows[:i])
        vals = [spans[k + t][0] for t in range(n)]
        val = vals[0] if n == 1 else vals
        st = r["struct"]
        tag = "e%s/g%s%s" % (st["entry_instr"], st["get_instr"],
                             "_call" if st["call_func"] else "")
        s = set(r["strings"])
        hints = [k2 for k2, ks in HINTS.items() if any(x in s for x in ks)]
        # 该槽的结束位置是否正好是 pad 边界？
        end = spans[k + n - 1][2]
        mark = " <<< 段边界" if end in pad_ends else ""
        print("%-3d %-5d %-36s %-9s %-22s %s%s"
              % (r["item"], r["module"], r["name"], tag,
                 json.dumps(val, ensure_ascii=False)[:20], ",".join(hints), mark))
        out.append({
            "item": r["item"], "module": r["module"], "name": r["name"],
            "struct": st, "tag": tag, "delegate": r["delegate"],
            "strings": r["strings"], "value": val,
            "span": [spans[k][1], end], "segment_boundary": end in pad_ends,
        })
    Path(args.json).write_text(json.dumps(out, ensure_ascii=False, indent=1),
                              encoding="utf-8")
    print()
    print(">>> %s" % args.json)
    return 0


if __name__ == "__main__":
    raise SystemExit(main())