firestorm/MW4COMPARE/tools/decompile/constants.py

#!/usr/bin/env python3
"""
constants.py - reverse tables for the `.data` keys authored as symbolic names.

Four `[GameData]` keys are written in the source as a symbol rather than a
literal, and the record stores only the resolved integer. Emitting a faithful
`.data` therefore needs the int -> symbol direction:

    MechID       $(M_Annihilator)     MechLabHeaders.h    #define M_Annihilator 0
    TechType     $(Tech_IS)           MechLabHeaders.h    #define Tech_IS 0
    NameIndex    $(IDS_Annihilator)   MissionLang.defines #define IDS_ANNIHILATOR 576
    MoveTypeFlag LEGJUMPMOVETYPE      MWObject.hpp enum + MWObject_Tool.cpp:20

MoveTypeFlag is the odd one out: a bare token, not `$(...)`, matched by the
`stricmp` chain in `MWObject__GameModel::ConvertStringToMoveType`. Its values
come from the anonymous enum at MWObject.hpp:136, where LEG is 0 and the order
is NOT the same as the stricmp chain, so the enum is the authority.

The `.defines` and `.h` files spell symbols in mixed case while sources
reference them in any case, so lookups here are case-insensitive.
"""
import re

REPO = "/home/rich/Repositories/firestorm/Gameleap"
MECHLAB_HEADERS = REPO + "/mw4/Content/ShellScripts/MechLabHeaders.h"
MISSIONLANG_DEFINES = REPO + "/mw4/Content/Defines/MissionLang.defines"

# MWObject.hpp:136. Declaration order is the value order.
MOVE_TYPE = [
    "LEGMOVETYPE", "LEGJUMPMOVETYPE", "TRACKMOVETYPE", "WHEELMOVETYPE",
    "FLYERMOVETYPE", "HOVERMOVETYPE", "HELIMOVETYPE", "NONEMOVETYPE",
    "DROPSHIPMOVETYPE", "WATERMOVETYPE",
]

_DEFINE = re.compile(r'^\s*#define\s+(\w+)\s+(-?\d+)\s*$', re.M)


def defines(path, prefix):
    """-> {value: [symbols]} for every `#define <prefix>NAME <int>` in a file.

    Values are not unique: IDS_FIRSTSKIN and IDS_WOLFHOUND are both 501, so a
    single winner cannot be picked here without knowing which mech is being
    emitted.
    """
    txt = open(path, encoding="latin-1", errors="replace").read()
    out = {}
    for name, val in _DEFINE.findall(txt):
        if name.lower().startswith(prefix.lower()):
            out.setdefault(int(val), []).append(name)
    return out


def tables():
    """-> {sourceKey: {intValue: [sourceToken]}} for the four symbolic keys."""
    wrap = lambda d: {v: [f"$({s})" for s in syms] for v, syms in d.items()}
    return {
        "MechID": wrap(defines(MECHLAB_HEADERS, "M_")),
        "TechType": wrap(defines(MECHLAB_HEADERS, "Tech_")),
        "NameIndex": wrap(defines(MISSIONLANG_DEFINES, "IDS_")),
        "MoveTypeFlag": {i: [s] for i, s in enumerate(MOVE_TYPE)},
    }


def symbol(tbl, key, value, hint=None):
    """Pick the source token for a value, preferring one naming the chassis."""
    syms = tbl.get(key, {}).get(value)
    if not syms:
        return None
    if hint and len(syms) > 1:
        h = norm(hint)
        for s in syms:
            if h and h in norm(s):
                return s
    return syms[0]


def norm(tok):
    """Compare symbols ignoring case and $() wrapping."""
    return re.sub(r'[^a-z0-9_]', '', tok.lower())


if __name__ == "__main__":
    for key, tbl in tables().items():
        print(f"{key:14s} {len(tbl):5d} values   e.g. {list(tbl.items())[:2]}")