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>
191 lines
6.8 KiB
Python
191 lines
6.8 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
prune-identical.py - delete everything from an extracted tree that we already have,
|
|
leaving only genuine differences and additions.
|
|
|
|
python3 prune-identical.py <extractedDir> [--apply]
|
|
|
|
Dry-run by default; nothing is deleted without --apply.
|
|
|
|
Why two baselines
|
|
-----------------
|
|
A .mw4 is not a zip of the source tree. Our own packer rewrites ~7,400 files on
|
|
the way in (.data .video .instance .contents .audio .damage .torso .subsystems
|
|
.engine .lights) and generates a further ~17,700 qualified records that have no
|
|
source file at all ('foo.data{gamemodel}', 'foo.contents[joint_hip]{armature}',
|
|
'bar.tga{hint}'). Comparing only against Content/ would therefore "keep" about
|
|
24,000 files we in fact already have.
|
|
|
|
So each candidate is tested, in order:
|
|
|
|
1. same package + same entry path in OUR extracted packages, identical bytes
|
|
2. same entry path anywhere in OUR extracted packages, identical bytes
|
|
3. unqualified name + same path in our Content/ source tree, identical bytes
|
|
|
|
Any hit means we have that exact asset -> delete. Rule 3 is what recognises
|
|
raw pass-through assets (.tga, .wav, .erf, scripts); rules 1-2 are what
|
|
recognise the packer-generated forms.
|
|
|
|
Afterwards _merged/ is rebuilt from the survivors and empty directories removed.
|
|
"""
|
|
import sys, os, hashlib, collections, shutil
|
|
|
|
OURS_EXTRACTED = "/home/rich/Repositories/FS_Ours_extracted"
|
|
OUR_SOURCE = "/home/rich/Repositories/firestorm/Gameleap/mw4/Content"
|
|
|
|
PRECEDENCE = {"props": 50, "core": 40, "textures": 30, "maps": 20, "missions": 10}
|
|
MERGE_EXCLUDE = ("variants/", "pilots/")
|
|
|
|
|
|
def digest(path, cache={}):
|
|
key = (path, os.path.getsize(path))
|
|
if key not in cache:
|
|
with open(path, "rb") as fh:
|
|
cache[key] = hashlib.md5(fh.read()).hexdigest()
|
|
return cache[key]
|
|
|
|
|
|
def index_paths(root, skip_top=()):
|
|
"""relative-lowercased-path -> absolute path. No hashing (lazy)."""
|
|
out = {}
|
|
for dp, dirs, fs in os.walk(root):
|
|
if dp == root:
|
|
dirs[:] = [d for d in dirs if d.lower() not in skip_top]
|
|
for f in fs:
|
|
p = os.path.join(dp, f)
|
|
out[os.path.relpath(p, root).replace("\\", "/").lower()] = p
|
|
return out
|
|
|
|
|
|
def package_of(rel):
|
|
"""Split '<pkgdir>/<entryPath>' for an extracted file.
|
|
|
|
Package directories are: core, props, textures, maps/<x>, Missions/<x>,
|
|
Variants/<x>, Pilots/Tesla/options
|
|
"""
|
|
parts = rel.split("/")
|
|
head = parts[0].lower()
|
|
if head in ("core", "props", "textures"):
|
|
return parts[0], "/".join(parts[1:])
|
|
if head in ("maps", "missions", "variants") and len(parts) > 2:
|
|
return "/".join(parts[:2]), "/".join(parts[2:])
|
|
if head == "pilots" and len(parts) > 3:
|
|
return "/".join(parts[:3]), "/".join(parts[3:])
|
|
return parts[0], "/".join(parts[1:])
|
|
|
|
|
|
def merged_precedence(pkg):
|
|
return PRECEDENCE.get(pkg.split("/")[0].lower(), 0)
|
|
|
|
|
|
def main():
|
|
if len(sys.argv) < 2:
|
|
sys.exit(__doc__)
|
|
root = sys.argv[1]
|
|
apply_ = "--apply" in sys.argv
|
|
merged_root = os.path.join(root, "_merged")
|
|
|
|
print("indexing our extracted packages ...", flush=True)
|
|
ours_pkg = index_paths(OURS_EXTRACTED, skip_top={"_merged"})
|
|
ours_by_entry = {}
|
|
for rel, p in ours_pkg.items():
|
|
if rel.startswith("_"):
|
|
continue
|
|
_pkg, entry = package_of(rel)
|
|
ours_by_entry.setdefault(entry, []).append(p)
|
|
print(f" {len(ours_pkg)} files, {len(ours_by_entry)} distinct entry paths")
|
|
|
|
print("indexing our Content source tree ...", flush=True)
|
|
src = index_paths(OUR_SOURCE)
|
|
print(f" {len(src)} files")
|
|
|
|
stats = collections.Counter()
|
|
doomed, kept = [], []
|
|
|
|
for dp, _dirs, fs in os.walk(root):
|
|
if dp == merged_root or dp.startswith(merged_root + os.sep):
|
|
continue
|
|
for f in fs:
|
|
p = os.path.join(dp, f)
|
|
rel = os.path.relpath(p, root).replace("\\", "/")
|
|
if rel.startswith("_"):
|
|
continue
|
|
pkg, entry = package_of(rel)
|
|
h = digest(p)
|
|
reason = None
|
|
|
|
cand = ours_pkg.get(rel.lower())
|
|
if cand and digest(cand) == h:
|
|
reason = "same-package"
|
|
if reason is None:
|
|
for c in ours_by_entry.get(entry.lower(), ()):
|
|
if digest(c) == h:
|
|
reason = "other-package"
|
|
break
|
|
if reason is None and "{" not in f and "[" not in f:
|
|
c = src.get(entry.lower())
|
|
if c and digest(c) == h:
|
|
reason = "our-source"
|
|
|
|
if reason:
|
|
stats["deleted:" + reason] += 1
|
|
doomed.append((rel, reason))
|
|
else:
|
|
stats["kept"] += 1
|
|
kept.append((rel, pkg, entry, h))
|
|
|
|
total = len(doomed) + len(kept)
|
|
print(f"\nexamined {total} files")
|
|
for k, v in sorted(stats.items()):
|
|
print(f" {v:7d} {k}")
|
|
print(f"\n -> would delete {len(doomed)}, keep {len(kept)}")
|
|
|
|
with open(os.path.join(root, "_survivors.tsv"), "w", encoding="utf-8") as fh:
|
|
fh.write("path\tpackage\tentry\tmd5\n")
|
|
for rel, pkg, entry, h in sorted(kept):
|
|
fh.write(f"{rel}\t{pkg}\t{entry}\t{h}\n")
|
|
|
|
if not apply_:
|
|
print(f"\nDRY RUN - nothing changed. Survivor list written to "
|
|
f"{os.path.join(root, '_survivors.tsv')}. Re-run with --apply.")
|
|
return
|
|
|
|
for rel, _reason in doomed:
|
|
os.remove(os.path.join(root, rel))
|
|
|
|
with open(os.path.join(root, "_pruned.tsv"), "w", encoding="utf-8") as fh:
|
|
fh.write("deletedPath\tmatchedVia\n")
|
|
for rel, reason in sorted(doomed):
|
|
fh.write(f"{rel}\t{reason}\n")
|
|
|
|
# rebuild _merged from survivors
|
|
shutil.rmtree(merged_root, ignore_errors=True)
|
|
best = {}
|
|
for rel, pkg, entry, h in kept:
|
|
if pkg.lower().startswith(MERGE_EXCLUDE):
|
|
continue
|
|
pr = merged_precedence(pkg)
|
|
cur = best.get(entry.lower())
|
|
if cur is None or pr > cur[0]:
|
|
best[entry.lower()] = (pr, entry, os.path.join(root, rel))
|
|
for _pr, entry, srcfile in best.values():
|
|
dest = os.path.join(merged_root, entry)
|
|
os.makedirs(os.path.dirname(dest), exist_ok=True)
|
|
os.link(srcfile, dest)
|
|
|
|
removed = 0
|
|
for dp, dirs, fs in os.walk(root, topdown=False):
|
|
if dp == root or not os.path.isdir(dp):
|
|
continue
|
|
if not os.listdir(dp):
|
|
os.rmdir(dp)
|
|
removed += 1
|
|
|
|
print(f"\ndeleted {len(doomed)} files, removed {removed} empty directories")
|
|
print(f"_merged rebuilt with {len(best)} paths")
|
|
print(f"log: {os.path.join(root, '_pruned.tsv')}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|