"""classify_0x0079385c_v2.py <pid>

V2 of the classifier. Two new approaches:

1. Test the "CObjCell shell at +0x30 and +0x54" hypothesis: for each hit,
   check if there's ALSO a 0x0079385c marker exactly 0x24 (36) bytes away
   (i.e. the OTHER offset of the same CObjCell). If yes → likely a real
   CObjCell shell pair. Count those.

2. Check immediate-neighborhood context. A "real leaked object" looks like:
   - Object head at some 8/16-byte-aligned address
   - First DWORD is a vtable pointer in .rdata range
   - Most of object is zeros or sensible field values
   A "compiler-baked constant" looks like:
   - Surrounded by code/anim data, not separable as an object
   - May appear right after a function pointer (in a vtable construction)
   or in a const-data array

Approach: for each hit, look at the 16 bytes BEFORE the hit. If the
preceding DWORDs contain ANY value in the executable-range
0x00400000-0x00700000 (which would be CODE pointer), this is likely an
embedded constant in compiled data, not a runtime object field.
Real heap object fields would not have code-range pointers RIGHT
before the marker.
"""
import argparse, ctypes, ctypes.wintypes as wt, struct, sys
from collections import Counter

PROCESS_VM_READ = 0x10
PROCESS_QUERY_INFORMATION = 0x400
MEM_COMMIT = 0x1000
MEM_PRIVATE = 0x20000

TARGET = 0x0079385c

# Code is in .text typically 0x00401000 - 0x006xxxxx
CODE_LO = 0x00401000
CODE_HI = 0x006d0000
# Read-only data (.rdata) typically follows .text
RDATA_LO = 0x006d0000
RDATA_HI = 0x008c0000


class MBI(ctypes.Structure):
    _fields_ = [('BaseAddress', ctypes.c_void_p),
                ('AllocationBase', ctypes.c_void_p),
                ('AllocationProtect', wt.DWORD),
                ('PartitionId', wt.WORD),
                ('RegionSize', ctypes.c_size_t),
                ('State', wt.DWORD),
                ('Protect', wt.DWORD),
                ('Type', wt.DWORD)]


k = ctypes.windll.kernel32
k.OpenProcess.argtypes = [wt.DWORD, wt.BOOL, wt.DWORD]; k.OpenProcess.restype = wt.HANDLE
k.ReadProcessMemory.argtypes = [wt.HANDLE, wt.LPCVOID, wt.LPVOID, ctypes.c_size_t,
                                ctypes.POINTER(ctypes.c_size_t)]
k.ReadProcessMemory.restype = wt.BOOL
k.VirtualQueryEx.argtypes = [wt.HANDLE, ctypes.c_void_p, ctypes.POINTER(MBI), ctypes.c_size_t]
k.VirtualQueryEx.restype = ctypes.c_size_t


ap = argparse.ArgumentParser()
ap.add_argument("pid", type=int)
args = ap.parse_args()

h = k.OpenProcess(PROCESS_VM_READ | PROCESS_QUERY_INFORMATION, False, args.pid)
if not h:
    print(f"OpenProcess({args.pid}) failed err={ctypes.get_last_error()}"); sys.exit(2)

regions = []
mbi = MBI()
addr = 0
while k.VirtualQueryEx(h, addr, ctypes.byref(mbi), ctypes.sizeof(mbi)):
    pr = mbi.Protect & 0xff
    if (mbi.State == MEM_COMMIT and mbi.Type == MEM_PRIVATE
            and pr in (0x04, 0x40)):
        buf = (ctypes.c_ubyte * mbi.RegionSize)()
        sz = ctypes.c_size_t(0)
        if k.ReadProcessMemory(h, mbi.BaseAddress, buf, mbi.RegionSize, ctypes.byref(sz)):
            regions.append((int(mbi.BaseAddress), bytes(buf[:sz.value]), int(mbi.RegionSize)))
    addr = (mbi.BaseAddress or 0) + mbi.RegionSize
    if addr >= 0x80000000:
        break

target_bytes = struct.pack("<I", TARGET)

# Stats
total_hits = 0
n_pair_at_24 = 0          # has a paired 0x0079385c at +/- 0x24 (CObjCell layout hint)
n_solo = 0                # alone
prev_dword_kind = Counter()  # what's the DWORD immediately before the hit
prev16_has_code = 0        # has a code-range pointer in the prior 16 bytes (suggests baked-in)
prev16_all_zero = 0        # surrounded by zeros (suggests cleared-but-not-freed object field)

# Per-region density: hits-per-region
region_hit_counter = []

for base, data, rsize in regions:
    hits_here = []
    pos = 0
    while True:
        idx = data.find(target_bytes, pos)
        if idx < 0: break
        if idx % 4 != 0:
            pos = idx + 1
            continue
        hits_here.append(idx)
        pos = idx + 4
    if not hits_here:
        continue
    region_hit_counter.append((base, rsize, len(hits_here)))

    hits_set = set(hits_here)
    for idx in hits_here:
        total_hits += 1
        # CObjCell pair check
        if (idx + 0x24) in hits_set or (idx - 0x24) in hits_set:
            n_pair_at_24 += 1
        else:
            n_solo += 1

        # Immediate prior DWORD class
        if idx >= 4:
            prev = struct.unpack_from("<I", data, idx - 4)[0]
            if prev == 0:
                prev_dword_kind["zero"] += 1
            elif CODE_LO <= prev < CODE_HI:
                prev_dword_kind["code_ptr"] += 1
            elif RDATA_LO <= prev < RDATA_HI:
                prev_dword_kind["rdata_ptr"] += 1
            elif 0x01000000 <= prev < 0x80000000:
                prev_dword_kind["heap_ptr"] += 1
            elif prev == TARGET:
                prev_dword_kind["self_marker"] += 1
            else:
                prev_dword_kind["scalar/other"] += 1

        # 16-byte window before
        if idx >= 16:
            window = data[idx-16:idx]
            wd = struct.unpack("<IIII", window)
            if all(d == 0 for d in wd):
                prev16_all_zero += 1
            if any(CODE_LO <= d < CODE_HI for d in wd):
                prev16_has_code += 1

print(f"Total 0x{TARGET:08x} hits: {total_hits}")
print(f"  Paired at +/-0x24 (CObjCell layout candidate): {n_pair_at_24}")
print(f"  Solo:                                          {n_solo}")
print()
print("Immediate prior DWORD classification:")
for k_, v in prev_dword_kind.most_common():
    print(f"  {k_:<15} {v:>7}")
print()
print(f"Prior 16 bytes all zero  (likely object field): {prev16_all_zero}")
print(f"Prior 16 bytes has code-ptr (likely baked data): {prev16_has_code}")
print()
print("=== Top 15 regions by hit count ===")
region_hit_counter.sort(key=lambda x: -x[2])
for base, rsize, c in region_hit_counter[:15]:
    print(f"  base=0x{base:08x}  size={rsize/1024:>8.1f}KB  hits={c:>5}  hits/KB={c*1024/rsize:.2f}")