Syplheed-Reborn/tools/re-capture/miscbin_names.py

#!/usr/bin/env python3
"""Resolve every `hidden/MiscBin.pak` entry to its on-disc name.

The names are not in `MiscBin` itself -- they are the values of the `MapPath`,
`MapMesh` and `CollisionMeshes` fields of the per-stage `StageResource` objects
(IDXD schema `3c9ae32e`, in every `dat/GP_MAIN_GAME_<lang>.pak`), and each one
hashes with the ordinary pak `name_hash` to a `MiscBin` TOC entry.

    ./miscbin_names.py <extract root>          # the table
    ./miscbin_names.py <extract root> --pairs  # check each .rgn/.col pair

`MapPath` names the `REGN` navigation mesh and `MapMesh` the `MCOL` collision
mesh of one *phase* of one stage, so the pair is what links the two formats --
an object-to-object link, not the matching-header-distributions argument that
`structures/mcol-collision.md` had to settle for before.
"""

import collections
import glob
import os
import struct
import sys

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from regn_decode import pak_entries
from unitgroup import name_hash, tag_hash

SCHEMA = 0x3C9AE32E
KEYS = ("MapPath", "MapMesh", "CollisionMeshes")
TAGS = {tag_hash(k): k for k in KEYS}


def be32(b, o):
    return struct.unpack_from(">I", b, o)[0]


def parse_idxd(b):
    """Records and fields of an IDXD object; None if it is not one."""
    if b[:4] != b"IDXD" or len(b) < 0x10:
        return None
    n = be32(b, 4)
    if not 0 < n <= 200_000:
        return None
    recs = [(None,) + struct.unpack_from(">III", b, 0x0C)]
    o = 0x18
    if o + 16 * (n - 1) + 4 > len(b):
        return None
    for _ in range(n - 1):
        recs.append(struct.unpack_from(">IIII", b, o))
        o += 16
    m = be32(b, o)
    o += 4
    if o + 12 * m + 4 > len(b):
        return None
    fields = [struct.unpack_from(">III", b, o + 12 * i) for i in range(m)]
    return dict(schema=be32(b, 8), recs=recs, fields=fields,
                pool=o + 12 * m + 4, raw=b)


def pool_str(p, off):
    b, base = p["raw"], p["pool"]
    if base + off >= len(b):
        return None
    return b[base + off:b.index(b"\0", base + off)].decode("latin-1")


def stage_phases(root):
    """(phase record name, {key: value}) for every stage-resource phase."""
    out = []
    for pak in sorted(glob.glob(os.path.join(root, "dat", "GP_MAIN_GAME_*.pak"))):
        for _, blob in pak_entries(pak):
            p = parse_idxd(blob)
            if not p or p["schema"] != SCHEMA:
                continue
            for _, noff, fb, fe in p["recs"]:
                d = {TAGS[k]: pool_str(p, vo)
                     for k, _, vo in p["fields"][fb:fe] if k in TAGS}
                if d:
                    out.append((pool_str(p, noff) if noff is not None else None, d))
    return out


def resolve(root):
    misc = dict(pak_entries(os.path.join(root, "hidden", "MiscBin.pak")))
    seen = collections.OrderedDict()
    for _, d in stage_phases(root):
        for k in KEYS:
            if d.get(k):
                seen.setdefault(d[k], k)
    table = []
    for nm, kind in seen.items():
        h = name_hash(nm)
        blob = misc.get(h)
        table.append((nm, h, kind, blob[:4].decode("latin-1") if blob else None))
    return misc, table


def cmd_table(root):
    misc, table = resolve(root)
    print(f"{'name':>30} {'name_hash':>10}  {'magic':>5}  {'field':>15}")
    for nm, h, kind, magic in sorted(table, key=lambda r: (r[3] or "", r[0])):
        print(f"{nm:>30} {h:10x}  {magic or '  --':>5}  {kind:>15}")
    got = {h for _, h, _, m in table if m}
    print(f"\nMiscBin entries {len(misc)}   resolved {len(got)}   "
          f"unresolved {len(set(misc) - got)}")
    return len(set(misc) - got) == 0


def cmd_pairs(root):
    """Each phase names a .rgn and a .col; check they describe the same volume."""
    misc, _ = resolve(root)
    f32 = lambda b, o: struct.unpack_from(">f", b, o)[0]
    u16 = lambda b, o: struct.unpack_from(">H", b, o)[0]
    pairs = collections.OrderedDict()
    for _, d in stage_phases(root):
        if d.get("MapPath") and d.get("MapMesh"):
            pairs.setdefault((d["MapPath"], d["MapMesh"]), 0)
            pairs[(d["MapPath"], d["MapMesh"])] += 1
    ok = 0
    print(f"{'stem':>30} {'phases':>7} {'bbox':>6} {'cell':>6}  verts/tris")
    for (rgn, col), n in pairs.items():
        R, C = misc[name_hash(rgn)], misc[name_hash(col)]
        stem = rgn.rsplit(".", 1)[0] == col.rsplit(".", 1)[0]
        bb = all(f32(R, 0x10 + 4 * i) == f32(C, 0x10 + 4 * i)
                 and f32(R, 0x20 + 4 * i) == f32(C, 0x20 + 4 * i) for i in range(3))
        cc = all(f32(R, 0x40 + 4 * i) == f32(C, 0x40 + 4 * i) for i in range(3))
        ok += stem and bb and cc
        print(f"{rgn.rsplit('.', 1)[0]:>30} {n:7d} {'yes' if bb else 'NO':>6} "
              f"{'yes' if cc else 'NO':>6}  {u16(C, 0x50)}/{u16(C, 0x52)}")
    print(f"\npairs agreeing on stem, bbox and cell size: {ok}/{len(pairs)}")
    return ok == len(pairs)


if __name__ == "__main__":
    if len(sys.argv) < 2:
        raise SystemExit(__doc__)
    root = sys.argv[1]
    good = cmd_pairs(root) if "--pairs" in sys.argv else cmd_table(root)
    print("\nPASS" if good else "\nFAIL")
    sys.exit(0 if good else 1)