"""broader_vtable_sweep.py <larsson.dmp> <time.dmp>

Find vtables in the acclient image range that have very high count
in larsson and low count in time, EXCLUDING the already-tracked ones.
Aim: surface previously-untracked leak classes.
"""
import struct, sys
from collections import Counter
from minidump.minidumpfile import MinidumpFile

# Known/already-investigated vtables
KNOWN = {
    0x007c0498: "UIElement_UIItem",
    0x007caa08: "Palette",
    0x007c78ec: "CPhysicsObj",
    0x0079a67c: "RenderSurface",
    0x00801a94: "RenderSurfaceD3D",
    0x00801a18: "RenderTextureD3D",
    0x007ca4dc: "CSurface",
    0x007cab04: "ImgTex",
    0x007ca418: "CGfxObj",
    0x007ed3b0: "D3DXMesh",
    0x0079bf64: "GraphicsResource",
    0x007ccb60: "NoticeHandler_subvt",
    0x007c98e8: "CObjCell_primary",
    0x007c9a60: "CEnvCell_primary",
    0x0079385c: "CObjCell_subvt",
    0x00400c08: "CPhys_data_sentinel",
    0x007c9b58: "CPhys_inner",  # speculative
    0x0079c198: "RenderTexture",
}

# Acclient image VA range (32-bit)
IMG_LO = 0x00400000
IMG_HI = 0x00880000

def _ei(v):
    if v is None: return 0
    if hasattr(v, 'value'): return int(v.value)
    return int(v)

def scan(dmp_path):
    md = MinidumpFile.parse(dmp_path)
    reader = md.get_reader().get_buffered_reader()
    counts = Counter()
    for r in md.memory_info.infos:
        st, ty, pr = _ei(r.State), _ei(r.Type), _ei(r.Protect) & 0xff
        if st != 0x1000 or ty == 0x1000000 or pr not in (0x04, 0x40):
            continue
        try:
            reader.move(r.BaseAddress)
            buf = reader.read(r.RegionSize)
        except Exception:
            continue
        if not buf: continue
        end = (len(buf) // 4) * 4
        for off in range(0, end, 4):
            v = struct.unpack_from("<I", buf, off)[0]
            if IMG_LO <= v < IMG_HI:
                # filter UTF-16 noise: low byte 0x00 of every other byte
                # rough check: byte 1 is 0 and byte 3 is 0 with letters in bytes 0,2
                b0, b1, b2, b3 = v & 0xff, (v >> 8) & 0xff, (v >> 16) & 0xff, (v >> 24) & 0xff
                if b1 == 0 and b3 == 0 and 0x20 <= b0 <= 0x7e and 0x20 <= b2 <= 0x7e:
                    continue  # UTF-16 string fragment
                counts[v] += 1
    return counts


def main():
    larsson = sys.argv[1]
    time_path = sys.argv[2]
    print(f"scanning larsson: {larsson}")
    lc = scan(larsson)
    print(f"  unique vtables: {len(lc)}")
    print(f"scanning time: {time_path}")
    tc = scan(time_path)
    print(f"  unique vtables: {len(tc)}")
    # Compute diff
    rows = []
    for vt, c in lc.items():
        if vt in KNOWN: continue
        if c < 20: continue
        t = tc.get(vt, 0)
        ratio = c / max(t, 0.5)
        delta = c - t
        rows.append((vt, t, c, ratio, delta))
    rows.sort(key=lambda x: -x[4])
    print()
    print("UN-tracked acclient vtables, sorted by absolute delta (larsson - time):")
    print(f"{'vtable':12} {'time':>6} {'larsson':>8} {'ratio':>7} {'delta':>7}")
    for vt, t, c, ratio, delta in rows[:40]:
        print(f"0x{vt:08x} {t:>6} {c:>8} {ratio:>7.1f} {delta:>7}")


if __name__ == "__main__":
    main()