"""classify_0x0079385c_hits.py <pid>

For each occurrence of the DWORD 0x0079385c in private RW memory of <pid>:
  - Record the absolute address of the hit
  - Walk BACKWARDS 16-byte aligned, looking for a plausible vtable pointer
    in the 0x00400000-0x00900000 (acclient .rdata) range with a small
    nonzero offset distance (<= 0x400 bytes). That's the object's start
    and offset-of-the-marker.
  - Group hits by:
      * offset-of-marker (e.g. +0x30, +0x54 confirms CObjCell)
      * the head vtable found (what class the object actually is)
  - Then independently bucket by REGION size of the containing
    VirtualAlloc region (informational, not allocation size).

Output:
  * Total hits
  * Offset histogram (top 10)
  * Head-vtable histogram (top 10) — includes vtable address + count
  * Sample hex dumps (first 64 bytes) for top 3 head-vtable groups
"""
import argparse, ctypes, ctypes.wintypes as wt, struct, sys, time
from collections import Counter, defaultdict

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

TARGET = 0x0079385c

# acclient.exe is loaded around 0x00400000 with .rdata vtables typically
# in the 0x00700000-0x00880000 range. Accept slightly wider for safety.
VTABLE_LO = 0x00400000
VTABLE_HI = 0x00900000


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)

# Pass 1: enumerate all readable private RW regions; remember snapshots in memory
# so we can back-scan WITHOUT extra remote reads.
regions = []   # list of (base, data:bytes, region_size)
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

total_hits = 0
offset_hist = Counter()             # offset from inferred object head
head_vt_hist = Counter()            # vtable found at inferred object head
region_size_hist = Counter()
head_vt_samples = defaultdict(list) # vt -> list of (addr, first 64 bytes)

# Bucket region sizes for histogram
def bucket(sz):
    if sz < 1024:        return "<1KB"
    if sz < 4*1024:      return "1-4KB"
    if sz < 64*1024:     return "4-64KB"
    if sz < 256*1024:    return "64-256KB"
    if sz < 512*1024:    return "256-512KB"
    if sz < 1024*1024:   return "512KB-1MB"
    return ">=1MB"

# For each hit, search backward for a vtable head.
# Walk back up to 0x400 bytes (CObjCell-class size guess), aligned to 4.
MAX_BACKSCAN = 0x400

for base, data, rsize in regions:
    end = (len(data) // 4) * 4
    # Find all DWORD positions equal to TARGET
    # struct.iter_unpack is fast enough
    pos = 0
    target_bytes = struct.pack("<I", TARGET)
    while True:
        idx = data.find(target_bytes, pos)
        if idx < 0: break
        if idx % 4 != 0:
            pos = idx + 1
            continue
        total_hits += 1
        region_size_hist[bucket(rsize)] += 1
        hit_addr = base + idx

        # Back-scan: try each 4-byte aligned offset 0, -4, -8, ... up to MAX_BACKSCAN
        found_vt = None
        found_off = None
        for back in range(0, MAX_BACKSCAN + 4, 4):
            probe = idx - back
            if probe < 0: break
            v = struct.unpack_from("<I", data, probe)[0]
            if VTABLE_LO <= v < VTABLE_HI and v != TARGET:
                # Heuristic: this is likely the head vtable.
                # The first plausible one we find (smallest back-distance) wins.
                found_vt = v
                found_off = back
                break
        if found_vt is not None:
            offset_hist[found_off] += 1
            head_vt_hist[found_vt] += 1
            if len(head_vt_samples[found_vt]) < 3:
                head_addr = hit_addr - found_off
                head_idx = idx - found_off
                snippet = data[head_idx:head_idx + 64]
                head_vt_samples[found_vt].append((head_addr, snippet))
        else:
            offset_hist[-1] += 1   # marker for "no head found"
        pos = idx + 4

print(f"PID={args.pid}  scanned {len(regions)} private RW regions")
print(f"Total 0x{TARGET:08x} hits: {total_hits}\n")

print("=== Region-size histogram (where the hit lives) ===")
for b, c in region_size_hist.most_common():
    print(f"  {b:>10}  {c:>7}")
print()

print("=== Offset of marker from inferred object head (top 15) ===")
for off, c in offset_hist.most_common(15):
    if off == -1:
        print(f"  (no head found)  {c:>7}")
    else:
        print(f"  +0x{off:04x}        {c:>7}")
print()

print("=== Head vtable histogram (top 15) ===")
for vt, c in head_vt_hist.most_common(15):
    print(f"  0x{vt:08x}    {c:>7}")
print()

print("=== Sample first-64-byte dumps for top 3 head vtables ===")
for vt, _c in head_vt_hist.most_common(3):
    print(f"\n--- head vtable 0x{vt:08x} ---")
    for ha, snip in head_vt_samples[vt]:
        hexs = " ".join(f"{b:02x}" for b in snip)
        print(f"  at 0x{ha:08x}: {hexs}")