# -*- coding: utf-8 -*-
"""全量配平：37 个语义名 <-> 真机明文的 38 个槽。

约束（这些是硬证据，不是猜）:
  1. 值内容唯一确定语义名（MacIntel/UTF-8/ANGLE/GgoA.../98k/iframe...）
  2. screen_fingerprint `"1440-2560-2530-24-*-*-|-*"` 反解出
     screen_height=1440 / screen_width=2560 / screen_color_depth=24
  3. itoken 有 `^\\d+:\\d+$` 特征 -> 占 **2 槽**（`641547489,1791732001`）
  4. 37 项 -> 38 槽（仅 itoken 多占 1 槽），可与明文槽数对账

输出: 每个语义名的取值 + 置信度，供人工核对。
"""
import json
import re
import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parents[2]
sys.path.insert(0, str(ROOT / "tools"))
import tdc_modules as tm  # noqa: E402

RAW = "/tmp/1ms_bridge/real_collect_plain.txt"
raw = open(RAW, encoding="latin1").read().rstrip("\x00")
cd = json.loads(re.sub(r" {2,}", "", raw))["cd"]
print("明文 38 槽:")
for i, v in enumerate(cd):
    print("  %2d %s" % (i, json.dumps(v, ensure_ascii=False)[:78]))
print()

rows = tm.analyze("har/1ms_dianxuan/tdc.js")
names = [r["name"] for r in rows]
print("语义名 %d 个" % len(names))
print()

# ---- 按内容给每个槽打标签（不依赖位置）----
def tags(v):
    t = []
    if isinstance(v, str):
        if "Mozilla" in v: t.append("user_agent")
        if v == "MacIntel": t.append("platform")
        if re.fullmatch(r"[+-]\d\d", v): t.append("timezone_offset")
        if v.upper() == "UTF-8": t.append("charset")
        if "ANGLE" in v: t.append("webgl_renderer")
        if "Inc." in v: t.append("webgl_vendor")
        if v.startswith("GgoA"): t.append("canvas_fingerprint")
        if "rand=" in v and "captcha" in v: t.append("template_url")
        if v == "98k": t.append("constant_98k")
        if v == "iframe": t.append("iframe_detect")
        if "*" in v and "-" in v: t.append("screen_fingerprint")
        if v.startswith("http") and "1ms.run" in v: t.append("location_href")
    elif isinstance(v, list):
        if v and all(isinstance(x, list) and len(x) == 3 for x in v): t.append("trajectory")
        if v and all(isinstance(x, str) for x in v): t.append("languages")
    elif isinstance(v, int) and not isinstance(v, bool):
        if 1_600_000_000 <= v <= 2_100_000_000: t.append("timestamp?")
        elif v > 1_000_000: t.append("bigint?")
        else: t.append("smallint?")
    elif isinstance(v, str) and v == "":
        t.append("emptystr?")
    return t

print("逐槽标签:")
for i, v in enumerate(cd):
    print("  %2d %-22s %s" % (i, ",".join(tags(v)), json.dumps(v, ensure_ascii=False)[:50]))
print()

# ---- 反解 screen_fingerprint 的约束 ----
fp = next((v for v in cd if isinstance(v, str) and "*" in v and "-" in v), None)
if fp:
    p = fp.split("-")
    print("screen_fingerprint = %r -> 高%s 宽%s 色深%s" % (fp, p[0], p[1], p[3]))
    for target, want in (("screen_height", int(p[0])), ("screen_width", int(p[1])),
                         ("screen_color_depth", int(p[3]))):
        idxs = [i for i, v in enumerate(cd) if v == want]
        print("   %-20s 期望 %s -> 明文里出现在槽 %s" % (target, want, idxs))