firestorm/MW4COMPARE/tools/decompile/contents.py

#!/usr/bin/env python3
"""
contents.py - decompiler for a mech `<chassis>.contents` file.

`.contents` is the thin half of the pair `armature.py` already handles. It
`!include`s `<chassis>.armature` and then gives every joint and site exactly two
entries:

    [joint_torso]
    Model=basic.data
    ExecutionState=AlwaysExecuteState

Both values ride in the same CreateMessages `armature.py` walks -- the `.armature`
source contributes a page's geometry, the `.contents` source contributes its
Model and ExecutionState, and the packer merges them into one message per page.
So nothing new has to be located: `Model` is `dataListID` (record id in the HIGH
word) and `ExecutionState` is the enum at offset 76.

Site pages are the exception. `{sites}` records store only name, rotation and
translation, so a site's Model and ExecutionState are not in the package at all.
They do not need to be: all **2926** site pages across the 89 mech `.contents`
files carry the identical pair `basic.data` / `AlwaysExecuteState`, so they are
emitted as constants rather than guessed per mech.

    python3 contents.py <chassis-record-dir> [-o out.contents]
    python3 contents.py --verify
"""
import argparse, collections, glob, os, re, struct, subprocess, sys

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import mw4msg, subsystems

MANIFEST = "/home/rich/Repositories/FS_Ours_extracted/_manifest.tsv"
REC_RE = re.compile(r'^(?P<chassis>.+?)\.contents\[(?P<parent>[^\]]+)\]\{(?P<kind>armature|sites)\}$',
                    re.I)
EXEC_STATE = {1: "NeverExecuteState", 2: "AlwaysExecuteState", 6: "ActiveState"}
SITE_DEFAULTS = [("Model", "basic.data"), ("ExecutionState", "AlwaysExecuteState")]

EXEC_OFF = 76
DATALIST_OFF = 84


def relative(path, chassis, folder=None):
    """Model= is written relative to the mech folder, not from the package root.

    The package path uses the FOLDER name, which need not match the record stem
    (V4H's jenner2c/ holds jenner_2c.* records), so both are tried.
    """
    if not path:
        return path
    for name in (chassis, folder):
        if name:
            path = re.sub(rf'^mechs[\\/]{re.escape(name)}[\\/]', '', path, flags=re.I)
    return path


def decompile(mech_dir, manifest=None):
    """-> (chassis, [(pageName, [(key, value)])])"""
    manifest = manifest if manifest is not None else subsystems.load_manifest(MANIFEST)
    chassis = None
    folder = os.path.basename(mech_dir.rstrip("/"))
    pages = collections.OrderedDict()

    root = [p for p in glob.glob(os.path.join(mech_dir, "*.contents"))
            if not re.search(r'[\[\{]', os.path.basename(p))]
    for path in sorted(glob.glob(os.path.join(mech_dir, "*{armature}"))) + root:
        base = os.path.basename(path)
        m = REC_RE.match(base)
        if m:
            chassis = chassis or m.group("chassis")
        else:
            chassis = chassis or base[:-len(".contents")]
        with open(path, "rb") as fh:
            data = fh.read()
        for _off, msg in mw4msg.walk(data):
            name = mw4msg.joint_name(msg)
            if not name:
                continue
            model = manifest.get(mw4msg.record_id(msg, DATALIST_OFF))
            state = EXEC_STATE.get(struct.unpack_from("<i", msg, EXEC_OFF)[0])
            pages.setdefault(name, [("Model", relative(model, chassis, folder)),
                                    ("ExecutionState", state)])

    for path in sorted(glob.glob(os.path.join(mech_dir, "*{sites}"))):
        with open(path, "rb") as fh:
            for name, _rot, _trans in mw4msg.read_sites(fh.read()):
                pages.setdefault(name, list(SITE_DEFAULTS))

    return chassis, list(pages.items())


def emit(chassis, pages):
    lines = ["[includes]", f"!include={chassis}.armature", ""]
    for name, kv in pages:
        lines.append(f"[{name}]")
        lines.extend(f"{k}={v}" for k, v in kv)
        lines.append("")
    return "\r\n".join(lines)


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("mech_dir", nargs="?")
    ap.add_argument("-o", "--output")
    ap.add_argument("-m", "--manifest", default=MANIFEST)
    ap.add_argument("--verify", action="store_true")
    args = ap.parse_args()
    if args.verify:
        here = os.path.dirname(os.path.abspath(__file__))
        raise SystemExit(subprocess.call([sys.executable,
                                          os.path.join(here, "verify_contents.py")]))
    if not args.mech_dir:
        ap.error("mech_dir required")
    chassis, pages = decompile(args.mech_dir, subsystems.load_manifest(args.manifest))
    text = emit(chassis, pages)
    if args.output:
        with open(args.output, "wb") as fh:
            fh.write(text.encode("latin-1"))
        print(f"wrote {args.output}")
    else:
        sys.stdout.write(text)


if __name__ == "__main__":
    main()