feat(VM): cd 槽位表可静态导出 + 槽位语义还原（符号求值）

tdc_program 新增 symbolic_assignments(): 对小程序做线性符号求值, 把字节码还原成 `r6 = c.navigator.userAgent` 这样的可读表达式（覆盖字面串/BIND_THIS/MAKE_(REG_)PROP_REF/ GET_GLOBAL_PROP/NEW_FUNC/CALL_*/STORE_REG/LOAD_REG_IMM/REVERSE_TOP2/DUP/算术）。 tdc_layout 新增: * slot_value_expr(): 精确规则 —— 采集器模块把值存进某寄存器, `get` 闭包只返回它（caps 的父寄存器就是取值寄存器）; 含"模块里唯一闭包"的兜底 * slot_semantics(): 合并"工厂赋值链 + require 委派 + 内部闭包"三条线索 * 输出改成叶子语义 + 真机明文并排核对实测确认（线上构建 + 同会话解出的真机 collect）: * 清单模块 = registry[7], 构造方式是 `r6[r6.length] = require(N)` 追加 -> **require 顺序即 cd 槽位顺序**（37 个 require + 1 个字面量槽 = 38, 与真机完全吻合） * 语义已精确命中: cd[3] <- c.navigator.userAgent, cd[5] <- c.navigator.languages * 仍有若干槽的语义标签未对齐（取值寄存器规则需再收口）, 已在账本记录
2026-10-12 00:17:30 +08:00
parent c4fe365e8c
commit fe1415508a
2 changed files with 217 additions and 7 deletions
@@ -33,6 +33,7 @@ from __future__ import annotations

 import argparse
 import json
+import re
 import sys
 from pathlib import Path
 from typing import Dict, List, Optional, Tuple
@@ -56,6 +57,101 @@ ENV_KEYS = [
 ]


+def _fold_str_before(code: List[dict], end: int, span: int = 40) -> Optional[str]:
+    """从 end 往前折叠一个字面串（PUSH_EMPTY_STR + 连续 PUSH_STR_CHAR）。"""
+    chars: List[str] = []
+    i = end
+    while i >= 0 and i > end - span and code[i]["name"] == "PUSH_STR_CHAR":
+        chars.append(chr(code[i]["operands"][0] & 0xFF))
+        i -= 1
+    if i >= 0 and code[i]["name"] == "PUSH_EMPTY_STR":
+        return "".join(reversed(chars))
+    return None
+
+
+def slot_value_expr(p: tp.Program, entry: int) -> Optional[str]:
+    """**精确**取一个槽位模块"这一槽的值是什么"。
+
+    规则（实测形状）: 采集器模块最后做
+        r3.exports.get = function () { ... return <被捕获的那个寄存器> ... }
+    也就是 `get` 闭包**只返回它捕获的寄存器**。所以:
+        1. 在工厂里找到被赋给属性 `get` 的那个 CREATE_CLOSURE;
+        2. 从它的 caps 里取出**父寄存器号**;
+        3. 该寄存器在工厂里的赋值表达式, 就是这一槽的语义。
+    例: 模块 18 -> caps=[r3=r6], 工厂里 `r6 = c.navigator.userAgent`。
+    """
+    code = p.function_code(entry)
+    assigns = dict(p.symbolic_assignments(entry, limit=60))
+    for k, inst in enumerate(code):
+        if inst["name"] != "CREATE_CLOSURE":
+            continue
+        # 形状: <"get" 字面量>; REVERSE_TOP2; JUMP -> @site; @site: CREATE_CLOSURE
+        j = k - 1
+        if j >= 0 and code[j]["name"] == "JUMP":
+            j -= 1
+        if _fold_str_before(code, j) != "get":
+            continue
+        site = next((c for c in p.closures if c.pc == inst["pc"]), None)
+        if site is None:
+            continue
+        for _child, parent in site.caps:          # caps 是 (子寄存器, 父寄存器)
+            expr = assigns.get(f"r{parent}")
+            if expr:
+                return expr
+    # 兜底（覆盖更广）: 采集器模块里通常**只有一个闭包**，它捕获的那个父寄存器就是取值寄存器
+    for c in p.closures:
+        if p.owner(c.pc) != entry or len(c.caps) != 1:
+            continue
+        _child, parent = c.caps[0]
+        expr = assigns.get(f"r{parent}")
+        if expr:
+            return expr
+    return None
+
+
+def slot_semantics(p: tp.Program, reg: Dict[int, int], mid: int, depth: int = 2) -> List[str]:
+    """还原某个槽位子模块"到底取什么值"。
+
+    三条线索合并（都来自 tdc_program 的符号求值, 不跑 JS）:
+      1. 模块工厂自身的赋值链, 例如 `r6 = c.navigator.userAgent`;
+      2. **委派**: 有些模块只是 `r6 = r5(N)`（require 另一个模块再导出），要跟进去;
+      3. **`get` 闭包内部**: canvas/WebGL 这类是延迟取值, 真正读环境在它内部创建的闭包里。
+    """
+    exprs: List[str] = []
+    seen: set = set()
+
+    def visit(m: int, d: int) -> None:
+        if m in seen or d < 0 or m not in reg:
+            return
+        seen.add(m)
+        entry = reg[m]
+        for _r, v in p.symbolic_assignments(entry, limit=14):
+            v = v.strip()
+            if not v:
+                continue
+            exprs.append(v)
+            mm = re.match(r"r\d+\((\d+)\)$", v)          # 纯委派 r6 = r5(N)
+            if mm:
+                visit(int(mm.group(1)), d - 1)
+        for c in p.closures:                              # 该模块内部创建的闭包（含 get 实现）
+            if p.owner(c.pc) != entry:
+                continue
+            for _r, v in p.symbolic_assignments(c.target, limit=10):
+                if v.strip():
+                    exprs.append(v.strip())
+                    mm = re.match(r"r\d+\((\d+)\)$", v.strip())
+                    if mm:
+                        visit(int(mm.group(1)), d - 1)
+
+    visit(mid, depth)
+    uniq, out = set(), []
+    for e in exprs:
+        if e not in uniq:
+            uniq.add(e)
+            out.append(e)
+    return out
+
+
 def find_manifest_module(p: tp.Program) -> Tuple[int, int, List[int]]:
    """找"清单模块": 体内 `push(require(N))` 次数最多者。

@@ -130,18 +226,28 @@ def main() -> int:
        print(f"真机明文 cd 槽数: {len(plain_cd)}")

    table = []
-    print("\n槽位   模块id  工厂entry  语义线索                            真机值")
-    print("-" * 108)
+    print("\n槽位   模块id  工厂entry  取值语义(静态还原)                       真机值")
+    print("-" * 112)
    for i, m in enumerate(seq):
        tgt = reg.get(m)
-        strs = transitive_strings(p, tgt) if tgt else []
-        hints = env_hints(strs)
+        expr = slot_value_expr(p, tgt) if tgt else None
+        # 有些模块只是"再 require 一层"（r6 = r5(M)），跟进一层
+        mm = re.match(r"r\d+\((\d+)\)$", (expr or "").strip())
+        if mm and int(mm.group(1)) in reg:
+            sub = slot_value_expr(p, reg[int(mm.group(1))])
+            if sub:
+                expr = f"{sub}   [via require({mm.group(1)})]"
+        if not expr:
+            expr = "; ".join(slot_semantics(p, reg, m)[:2]) if tgt else ""
        val = ""
        if plain_cd is not None and i < len(plain_cd):
            v = repr(plain_cd[i])
-            val = v if len(v) <= 34 else v[:34] + "..."
-        table.append({"slot": i, "module": m, "entry": tgt, "hints": hints})
-        print(f"  {i:2d}   {m:4d}    @{tgt:<7} {str(hints)[:34]:<34} {val}")
+            val = v if len(v) <= 30 else v[:30] + "..."
+        sem = expr or ""
+        if len(sem) > 44:
+            sem = sem[:44] + "..."
+        table.append({"slot": i, "module": m, "entry": tgt, "expr": expr})
+        print(f"  {i:2d}   {m:4d}    @{tgt:<7} {sem:<46} {val}")

    if plain_cd is not None:
        print(f"\n(真机 cd 里还有 {len(plain_cd) - len(seq)} 个槽不来自 require —— "
@@ -175,6 +175,110 @@ class Program:
            out.append((mid, tgt))
        return out

+    # ---------------------------------------------------------- 轻量符号求值
+    def symbolic_assignments(self, entry: int, limit: int = 30) -> List[Tuple[str, str]]:
+        """对一个小函数(如采集器模块)做**线性符号求值**, 还原 `rN = <表达式>`。
+
+        只覆盖这类小模块实际用到的形状: 字面串 / BIND_THIS / MAKE_(REG_)PROP_REF /
+        GET_PROP / GET_GLOBAL_PROP / NEW_FUNC / CALL_FUNC / CALL_METHOD / STORE_REG /
+        LOAD_REG_IMM / REVERSE_TOP2 / DUP / 算术。
+
+        目的: 把"这一槽取的是什么值"变成可读路径, 例如 `c.navigator.userAgent`。
+        说明: 遇到分支时按 pc 顺序近似处理, 结果用于**定位语义**, 不作为执行依据。
+        """
+        regs: Dict[int, str] = {}
+        out: List[Tuple[str, str]] = []
+        st: List[Tuple[str, str]] = []          # ("reg", n) | ("sym", text)
+
+        def top() -> Tuple[str, str]:
+            return st[-1] if st else ("sym", "?")
+
+        def popn(n: int) -> List[Tuple[str, str]]:
+            r = st[-n:] if n else []
+            del st[len(st) - n:]
+            return r
+
+        for inst in self.function_code(entry):
+            n, ops = inst["name"], inst["operands"] or []
+            if n == "PUSH_IMM_ARRAY":
+                st.append(("reg", ops[0]))
+            elif n == "PUSH_EMPTY_STR":
+                st.append(("sym", ""))
+            elif n == "PUSH_STR_CHAR":
+                k, v = top()
+                st[-1] = ("sym", v + chr(ops[0] & 0xFF))
+            elif n == "PUSH_IMM":
+                st.append(("sym", str(ops[0])))
+            elif n == "PUSH_UNDEFINED":
+                st.append(("sym", "undefined"))
+            elif n == "PUSH_NULL":
+                st.append(("sym", "null"))
+            elif n == "PUSH_TRUE":
+                st.append(("sym", "true"))
+            elif n == "PUSH_FALSE":
+                st.append(("sym", "false"))
+            elif n == "LOAD_REG_IMM":
+                st.append(("sym", regs.get(ops[0], f"r{ops[0]}")))
+            elif n == "LOAD_REG_INDIRECT":
+                k, v = st.pop() if st else ("sym", "?")
+                st.append(("sym", regs.get(int(v), f"r{v}") if str(v).isdigit() else v))
+            elif n == "BIND_THIS":
+                k, v = st.pop() if st else ("sym", "?")
+                st.append(("sym", f"c.{v}"))
+            elif n == "MAKE_PROP_REF":
+                key = top()[1]
+                popn(1)
+                base = top()[1]
+                popn(1)
+                st.append(("sym", f"{base}.{key}"))
+            elif n == "MAKE_REG_PROP_REF":
+                key = top()[1]
+                popn(1)
+                k, v = st.pop() if st else ("sym", "?")
+                st.append(("sym", f"{regs.get(v, f'r{v}')}.{key}"))
+            elif n == "GET_GLOBAL_PROP":
+                st[-1] = ("sym", f"c.{top()[1]}")
+            elif n in ("GET_PROP", "GET_ELEM"):
+                pass
+            elif n in ("ADD", "SUB", "MUL", "DIV", "MOD", "BIT_AND", "BIT_OR", "BIT_XOR",
+                       "SHL", "SHR", "SHR_U", "EQ", "EQ_STRICT", "GREATER"):
+                if len(st) >= 2:
+                    b = top()[1]
+                    popn(1)
+                    a = top()[1]
+                    popn(1)
+                    st.append(("sym", f"({a} {n} {b})"))
+            elif n in ("NEW_FUNC", "NEW_METHOD"):
+                args = popn(int(ops[0]) if ops else 0)
+                fn = st.pop()[1] if st else "?"
+                st.append(("sym", f"new {fn}({','.join(x[1] for x in args)})"))
+            elif n == "CALL_FUNC":
+                args = popn(int(ops[0]) if ops else 0)
+                fn = st.pop()[1] if st else "?"
+                st.append(("sym", f"{fn}({','.join(x[1] for x in args)})"))
+            elif n == "CALL_METHOD":
+                args = popn(int(ops[0]) if ops else 0)
+                tgt = st.pop() if st else ("sym", "?")
+                st.append(("sym", f"{tgt[1]}({','.join(x[1] for x in args)})"))
+            elif n == "STORE_REG":
+                v = st.pop()[1] if st else "?"
+                k, ref = st.pop() if st else ("sym", "?")
+                if k == "reg":
+                    regs[ref] = v
+                    out.append((f"r{ref}", v))
+            elif n == "DUP":
+                if st:
+                    st.append(st[-1])
+            elif n == "REVERSE_TOP2":
+                if len(st) >= 2:
+                    st[-1], st[-2] = st[-2], st[-1]
+            elif n in ("POP", "SET_PROP", "ALLOC_REG", "SET_STACK_LEN", "REPLACE_TOP_IMM"):
+                if n in ("POP", "SET_PROP") and st:
+                    st.pop()
+            if len(out) >= limit:
+                break
+        return out
+
    def find_strings(self, pattern: str) -> List[Tuple[int, str, int]]:
        """返回 (pc, 串, 所属子程序入口)。"""
        rx = re.compile(pattern, re.I)