Tooling built to recover editable source for six 'Mech chassis that exist
in the parallel FS_Build_V4H build but not in this repo. Reverse-engineers
every compiled record type in the .mw4 package format back to the .data /
.instance / .subsystems / .damage / .contents / .torso / .engine /
.armature sources the content pipeline consumes.
Nothing here is wired into the game build. It is a standalone analysis
harness run from Linux.
Package format
--------------
"#VBD" container. Directory records are [len][name][FILETIME][origSize]
[storedSize][offset], payload base at dword 0x0C. A record is stored raw
when storedSize == origSize, otherwise LZW (9->12-bit LSB-first codes,
256=clear, 257=EOF, dict from 258), per Database.cpp:451.
GameModel records are flat /Zp4 structs following the C++ inheritance
chain Entity(0) -> Mover(28) -> MWObject(80) -> Vehicle(664) -> Mech(756),
1636 bytes total. CreateMessage records follow Replicator -> Entity ->
Mover -> MWMover -> MWObject -> Vehicle -> Mech from start=16 (the
undeclared Connection__Message header), ending at 341 and padded to 344.
tools/decompile/
----------------
datamap.py header-driven layout engine; CHAIN + ANCHORS
{Vehicle:664, Mech:756} assert the struct offsets
mw4msg.py CreateMessage reader/walker
data.py .data constants.py define/table symbol resolution
damage.py .damage contents.py .contents
smallmodel.py .torso + .engine instance.py .instance
armature.py / armature_parts.py .armature + armaturedata/armaturevideo
assembly.py joint hierarchy renderer
make_generic_doll.py builds generic MFD/Radar damage dolls
verify_*.py per-type round-trip verifiers
Verified round-trip across all 64 shared chassis:
.armature 2938/2976 pages .subsystems 7579/7585 keys
.data map 6071/6071 values .data trip 8291/8306 keys
.damage 6605/6605 keys .contents 7480/7480 keys
.torso+.engine 1280/1280 keys .instance 896/896 keys, 64/64 pages
armature_parts 1202/1202 .data, 1149/1202 .video
Layout-discovery lessons (documented in DECOMPILING.md)
-------------------------------------------------------
- Never let a field map be discovered by the values that verify it. A
value-matching pass reported 4288/4288 while mis-assigning 34 keys. The
map was rebuilt from header declaration order, anchored on uniquely
resolved fields.
- Read the factory, not the data. 12 .data fields and 5 Torso fields are
declared plain Stuff::Scalar but multiplied by Radians_Per_Degree in
Mech_Tool.cpp:889 / Torso_Tool.cpp.
- Strip typedefs before walking a header. A stray `typedef int AttributeID;`
masked a missing ClassID - two 4-byte errors cancelling out, caught only
by the ANCHORS assertion.
- A verifier that silently narrows its own input reports success. Braced
blocks must be hidden before splitting pages, replacing both CR and LF,
because a `Shadow={...}` block contains a line reading `[shadow]` and
splitlines() also splits on bare CR.
- NSWIZZLE is undefined, so the #else branch is live and orders members
differently. bool is 1 byte; char x[MaxStringLength] is 256.
- V4H carries stale Mech IDs (their Atlas is 5, ours 6), so 64 of 65 shared
chassis are off by one; --retarget-ids emits $(M_<Chassis>)/$(IDS_<Chassis>).
reports/ holds generated diffs. The two ~5 MB manifest-*.tsv intermediates
are gitignored; regenerate everything with run-comparison.sh.
Co-authored-by: Claude Opus 5 (Anthropic) <noreply@anthropic.com>
Co-authored-by: GitHub Copilot <copilot@github.com>
140 lines
4.9 KiB
Python
140 lines
4.9 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
assembly.py - show how a mech's parts bolt together.
|
|
|
|
There is no `.erf` viewer on Linux, but the assembly itself is not hidden: the
|
|
`.armature` gives every joint's parent, offset and rotation, and the `.contents`
|
|
plus `armaturevideo/` say which geometry hangs off each joint. Printing that as
|
|
a tree answers "what are the parts and how do they fit" without a renderer.
|
|
|
|
For actual 3D you need MW4Ed2 on the Windows box (Gameleap/mw4/run-editor.bat) --
|
|
its Game View renders a loaded mech through DDrawCompat.
|
|
|
|
python3 assembly.py <mech-source-dir> [--geometry-only]
|
|
"""
|
|
import argparse, collections, os, re, sys
|
|
|
|
|
|
def pages(path):
|
|
"""-> OrderedDict pageName -> [(key, value)]"""
|
|
txt = re.sub(r'//[^\n]*', '', open(path, "rb").read().decode("latin-1"))
|
|
out, cur = collections.OrderedDict(), None
|
|
for line in txt.splitlines():
|
|
line = line.strip()
|
|
if not line or line.startswith("!"):
|
|
continue
|
|
m = re.match(r'^\[([^\]]+)\]$', line)
|
|
if m:
|
|
cur = m.group(1)
|
|
out.setdefault(cur, [])
|
|
elif "=" in line and cur is not None:
|
|
k, v = line.split("=", 1)
|
|
out[cur].append((k.strip(), v.strip()))
|
|
return out
|
|
|
|
|
|
def find(mech_dir, ext):
|
|
for f in sorted(os.listdir(mech_dir)):
|
|
if f.lower().endswith(ext) and "}" not in f:
|
|
return os.path.join(mech_dir, f)
|
|
return None
|
|
|
|
|
|
def geometry_for(mech_dir, part):
|
|
"""The .erf a joint draws, via armaturevideo/<part>.video.
|
|
|
|
Takes the [lod] block specifically -- a torso's file starts with the
|
|
running-lights block, whose geometry is not the part.
|
|
"""
|
|
vid = os.path.join(mech_dir, "armaturevideo", part + ".video")
|
|
if not os.path.exists(vid):
|
|
return None
|
|
t = open(vid, "rb").read().decode("latin-1")
|
|
m = re.search(r'^\[lod\][^\[]*?Geometry=([^\r\n]+)', t, re.M | re.I | re.S)
|
|
if not m:
|
|
m = re.search(r'Geometry=([^\r\n]+)', t)
|
|
return m.group(1).strip() if m else None
|
|
|
|
|
|
def build(mech_dir):
|
|
arm = find(mech_dir, ".armature")
|
|
con = find(mech_dir, ".contents")
|
|
if not arm:
|
|
raise SystemExit(f"no .armature in {mech_dir}")
|
|
|
|
apages = pages(arm)
|
|
children = collections.defaultdict(list)
|
|
info = {}
|
|
for name, kv in apages.items():
|
|
d = dict(kv)
|
|
info[name] = d
|
|
for k, v in kv:
|
|
if k.lower() == "child":
|
|
children[name].append(v.strip())
|
|
|
|
models = {}
|
|
if con:
|
|
for name, kv in pages(con).items():
|
|
for k, v in kv:
|
|
if k.lower() == "model":
|
|
models[name.lower()] = v.strip()
|
|
|
|
parented = {c for cs in children.values() for c in cs}
|
|
roots = [n for n in apages if n not in parented]
|
|
return apages, children, info, models, roots
|
|
|
|
|
|
def render(mech_dir, geometry_only=False):
|
|
apages, children, info, models, roots = build(mech_dir)
|
|
sizes = {f.lower(): os.path.getsize(os.path.join(mech_dir, f))
|
|
for f in os.listdir(mech_dir) if f.lower().endswith(".erf")}
|
|
lines = []
|
|
|
|
def walk(name, depth, last, prefix):
|
|
d = info.get(name, {})
|
|
model = models.get(name.lower(), "")
|
|
part = None
|
|
m = re.match(r'armaturedata[\\/](.+)\.data', model, re.I)
|
|
if m:
|
|
part = m.group(1)
|
|
geo = geometry_for(mech_dir, part) if part else None
|
|
size = sizes.get((geo or "").lower())
|
|
tag = ""
|
|
if geo:
|
|
tag = f" <- {geo}" + (f" ({size:,} B)" if size else "")
|
|
elif model and model.lower() != "basic.data":
|
|
tag = f" <- {model}"
|
|
trans = d.get("Translation", d.get("translation", ""))
|
|
rot = d.get("Rotation", d.get("rotation", ""))
|
|
pos = f" @[{trans}]" if trans and trans.strip() not in ("0.0 0.0 0.0", "0 0 0") else ""
|
|
if geometry_only and not geo:
|
|
pass
|
|
else:
|
|
branch = "" if depth == 0 else ("`-- " if last else "|-- ")
|
|
lines.append(f"{prefix}{branch}{name}{tag}{pos}")
|
|
kids = children.get(name, [])
|
|
newprefix = prefix + ("" if depth == 0 else (" " if last else "| "))
|
|
for i, k in enumerate(kids):
|
|
walk(k, depth + 1, i == len(kids) - 1, newprefix)
|
|
|
|
for r in roots:
|
|
walk(r, 0, True, "")
|
|
return lines, sizes
|
|
|
|
|
|
def main():
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("mech_dir")
|
|
ap.add_argument("--geometry-only", action="store_true",
|
|
help="hide joints and sites that draw nothing")
|
|
args = ap.parse_args()
|
|
lines, sizes = render(args.mech_dir, args.geometry_only)
|
|
name = os.path.basename(args.mech_dir.rstrip("/"))
|
|
print(f"=== {name}: {len(lines)} nodes, {len(sizes)} .erf, "
|
|
f"{sum(sizes.values()):,} B of geometry ===")
|
|
print("\n".join(lines))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|