tools/re-capture/struct_layout_control.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+"""Type-plausibility control for a published record layout.
+
+🔴 WHY THIS EXISTS. I published the dialog table as `{handler, id, name_ptr}`.
+It is `{id, name_ptr, handler}` -- the same three fields shifted one word, so every
+record was credited with the PREVIOUS record's handler. sylpheed-port had copied it
+into their authored data before either of us noticed.
+
+Their rule -- "the claims that go unchecked are the ones that carry no weight" --
+did NOT protect them here, and they named the gap precisely: a wrong FIELD ORDER
+looks like a fact rather than an aside, and a later reader builds on it. It carried
+no weight only by luck.
+
+So a structural claim needs a control that FAILS when the alignment is wrong. Every
+field has a type, and a wrong alignment breaks the types: an id stops being small,
+a string pointer stops pointing at a string, a code pointer stops looking like code.
+
+⚠️ TWO-SIDED BY CONSTRUCTION: it checks the published layout passes AND that the
+shifted alignments fail. A layout check that only confirms the current reading is
+the same defect one level up.
+
+    struct_layout_control.py
+"""
+import struct
+import sys
+
+PE = open("/image/sylpheed.pe", "rb").read()
+BASE = 0x82000000
+CODE_LO, CODE_HI = 0x82000000, 0x82600000
+
+
+def rd(va):
+    o = va - BASE
+    return struct.unpack_from(">I", PE, o)[0] if 0 <= o < len(PE) - 4 else None
+
+
+def is_id(v):
+    return v is not None and v < 100_000
+
+
+def is_dlg_name(v):
+    if v is None or not (BASE <= v < BASE + len(PE)):
+        return False
+    o = v - BASE
+    e = PE.find(b"\x00", o)
+    return e > o and PE[o:e].startswith(b"DLG_")
+
+
+def is_code(v):
+    """A code pointer whose target opens with a real PowerPC prologue."""
+    if v is None or not (CODE_LO <= v < CODE_HI) or v % 4:
+        return False
+    w = rd(v)
+    return w is not None and (w == 0x7D8802A6 or (w >> 26) == 37)  # mflr r12 / stwu
+
+
+def check(first_field_va, order, n=70):
+    """order: sequence of predicates, one per 4-byte field."""
+    ok = 0
+    for k in range(n):
+        b = first_field_va + 12 * k
+        vals = [rd(b + 4 * i) for i in range(len(order))]
+        if all(p(v) for p, v in zip(order, vals)):
+            ok += 1
+    return ok
+
+
+ID_NAME_HANDLER = (is_id, is_dlg_name, is_code)
+HANDLER_ID_NAME = (is_code, is_id, is_dlg_name)
+NAME_HANDLER_ID = (is_dlg_name, is_code, is_id)
+
+TABLE = 0x820A0A30   # first record under the published layout
+N = 70
+
+# 🔴 THE OBVIOUS CONTROL DOES NOT WORK, AND THAT IS THE POINT.
+# Checking "are all records type-plausible" passes on the SHIFTED alignments too:
+# 69/70 in both directions. A homogeneous repeated table has the same field types
+# in sequence -- id, name, handler, id, name, handler -- so ANY window starting on
+# a field boundary type-checks. The interior carries no information about phase.
+#
+# ✅ ONLY THE BOUNDARIES DO. A shifted reading must consume a word from OUTSIDE the
+# table at one end, and that word does not obey the field's type. That is exactly
+# how the original error surfaced: under the shifted alignment record 0's "handler"
+# was 0x10000000, the word sitting before the table.
+print("── dialog table: alignment control (boundaries, not interior) ──")
+print("   interior is UNINFORMATIVE, shown so nobody rebuilds it:")
+for label, base, order in (("published ", TABLE, ID_NAME_HANDLER),
+                           ("shifted -1", TABLE - 4, HANDLER_ID_NAME),
+                           ("shifted +1", TABLE + 4, NAME_HANDLER_ID)):
+    print(f"      {label}  {check(base, order, N)}/{N} records type-plausible")
+
+def edges_ok(base, order):
+    """Both terminal records must type-check under this alignment."""
+    for k in (0, N - 1):
+        b = base + 12 * k
+        if not all(p(rd(b + 4 * i)) for i, p in enumerate(order)):
+            return False
+    return True
+
+print("\n   boundaries -- the discriminating test:")
+res = [("PUBLISHED  {id, name_ptr, handler}", edges_ok(TABLE, ID_NAME_HANDLER), True),
+       ("shifted -1 {handler, id, name_ptr}", edges_ok(TABLE - 4, HANDLER_ID_NAME), False),
+       ("shifted +1 {name_ptr, handler, id}", edges_ok(TABLE + 4, NAME_HANDLER_ID), False)]
+bad = 0
+for label, got, want in res:
+    good = (got == want)
+    bad += not good
+    print(f"      {'✅' if good else '🔴'} {label}  edges type-check: {got} (want {want})")
+if bad:
+    print("🔴 LAYOUT CONTROL FAILED"); sys.exit(2)
+print("\n   ✅ only the published alignment survives at both boundaries")