# -*- coding: utf-8 -*-
"""把「同会话 collect 明文」与「同会话 tdc.js 的语义名」按位置精确对齐。

这是"不手工配平"的正解，依据都是已确证的链路：
  * 槽位序 == 清单模块的 require 序（账本 #34/#35，运行时反证过）
  * 语义名 == tdc_modules.analyze(同一份 tdc.js)（账本 #44，37/37 唯一）
  * collect 4 段加密（账本 #41），解密后按空格 pad 切回 cd

输入（全部来自**同一次会话**，无需任何人工假设）:
  /tmp/1ms_bridge/session_build.js    运行时 tdc.js（Debugger 取的）
  /tmp/1ms_bridge/session_collect.json 同会话 TDC.getData(true) + getInfo

用法:
    .venv/bin/python scripts/verify/align_session.py
"""
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"))
from tcaptcha.telemetry import modules as tm  # noqa: E402
from tcaptcha.telemetry.crypto import split_collect_segments, xtea_decrypt_bytes  # noqa: E402
from tcaptcha.telemetry.key import extract_xtea_key_pure  # noqa: E402

BUILD = "/tmp/1ms_bridge/session_build.js"
SESS = "/tmp/1ms_bridge/session_collect.json"

js = open(BUILD, encoding="utf-8", errors="replace").read()
print("运行时 tdc.js: %d 字节" % len(js))
key = extract_xtea_key_pure(js)["key"]
print("本会话密钥 :", key)
print()

sess = json.load(open(SESS, encoding="utf-8"))
if "collect" not in sess and isinstance(sess.get("data"), dict):
    sess = sess["data"]                 # cdp_collect.js 落盘的形状是 {target, ok, data:{...}}
collect = unquote(sess["collect"])      # 浏览器侧返回的是 URL-encoded
print("collect: %d 字符" % len(collect))

# 解密（4 段拼接：整体解一次即可，因为各段独立 XTEA-ECB）
raw = base64.b64decode(collect)
dec = xtea_decrypt_bytes(raw, key).decode("latin1")
plain = dec.rstrip("\x00")
print("解密 %d 字节" % len(dec))
runs = [m.span() for m in re.finditer(r" {2,}", plain)]
print("空格 pad 串:", runs)
print()
if len(runs) == 3:
    c1, traj, c2, sd = split_collect_segments(plain)
    print("段: chunk1=%d traj=%d chunk2=%d sd=%d" % (len(c1), len(traj), len(c2), len(sd)))
else:
    c1 = traj = c2 = sd = None
print()

logical = re.sub(r" {2,}", "", plain)
obj = json.loads(logical)
cd = obj["cd"]
print("cd 槽数:", len(cd))
print()

rows = tm.analyze(BUILD)
names = [r["name"] for r in rows]
mods = [r["module"] for r in rows]
print("清单项 %d, 语义名 %d" % (len(mods), len(names)))
print()

# itoken 占 2 槽（^\\d+:\\d+$），其余 1 槽
multi = [i for i, n in enumerate(names) if n.startswith("itoken")]
slots = 0
print("%-2s %-6s %-34s %s" % ("#", "模块", "语义名", "值"))
print("-" * 110)
out = {}
k = 0
for i, (m, nm) in enumerate(zip(mods, names)):
    n = 2 if i in multi else 1
    if k + n > len(cd):
        break
    vals = cd[k:k + n]
    k += n
    val = vals[0] if n == 1 else vals
    out[nm] = val
    print("%-2d %-6d %-34s %s" % (i, m, nm, json.dumps(val, ensure_ascii=False)[:60]))
print()
print("覆盖槽数 %d / cd %d" % (k, len(cd)))
print()
Path("/tmp/1ms_bridge/name_values.json").write_text(
    json.dumps(out, ensure_ascii=False, indent=1), encoding="utf-8")
print(">>> 语义名 -> 真值 已存 /tmp/1ms_bridge/name_values.json")