336 lines
14 KiB
Python
336 lines
14 KiB
Python
#!/usr/bin/env python3
|
|
"""Extract a *INIT data table to JSON. Auto-detects the table's shape.
|
|
|
|
*INIT scripts populate parallel global arrays with static game data. Three shapes seen:
|
|
|
|
name — records keyed by a name string. Each record: set-string(name), static field writes,
|
|
set-string(desc). Arrays indexed by record id in lockstep (+1/record).
|
|
(SKINIT skills, ITINIT items, EBINIT units)
|
|
numeric— column table with NO names: mov/copy-to-global into parallel int arrays, keyed
|
|
by an incrementing index column. (CGINIT gallery)
|
|
footer — copy-local-array (op 0x64) bulk-loads length-prefixed arrays from the file
|
|
footer into per-record global arrays. The data lives in the footer. (MPINIT maps)
|
|
|
|
Records are {id, name?, desc?, fields:{"0x<col_base>": value}} or, for footer tables,
|
|
{id, global_addr, footer_off, values:[...]}. Column addresses are raw engine globals;
|
|
naming them (attack, cost, …) needs the engine global-var map — later work.
|
|
|
|
Usage: py -3.11 -X utf8 tools/extract_init.py <TABLE> [OUTNAME] [--mode name|numeric|footer]
|
|
"""
|
|
from __future__ import annotations
|
|
import json
|
|
import sys
|
|
from functools import cache
|
|
from pathlib import Path
|
|
|
|
HERE = Path(__file__).resolve().parent
|
|
sys.path.insert(0, str(HERE))
|
|
import paths
|
|
import sys4load
|
|
|
|
SET_STRING = 0x192
|
|
MOV = 0x55
|
|
SUB = 0x51
|
|
COPY_TO_GLOBAL = 0x6C
|
|
COPY_LOCAL_ARRAY = 0x64
|
|
T_GLOBAL_INT = 3
|
|
T_GLOBAL_STRING = 5
|
|
T_IMM = 0
|
|
|
|
|
|
def resolve(name: str) -> Path:
|
|
for cand in (paths.GAME_DIR / f"{name}.BIN", paths.DATA1 / f"{name}.BIN"):
|
|
if cand.exists():
|
|
return cand
|
|
raise SystemExit(f"not found: {name}.BIN")
|
|
|
|
|
|
def _val(arg):
|
|
"""Render an operand as an int (immediate) or a {type,value} ref."""
|
|
t, v = arg
|
|
return v if t == T_IMM else {"type": f"0x{t:x}", "value": f"0x{v:x}"}
|
|
|
|
|
|
def _static_global_write(ins):
|
|
"""Return (destination, value) for statically evaluable global-int writes.
|
|
|
|
The shipped name-mode INIT scripts encode positive values with `mov` and
|
|
negative values with `sub destination, 0, magnitude`. Ignoring the latter
|
|
silently drops costs and penalties from the extracted schema.
|
|
"""
|
|
if not ins.args or ins.args[0][0] != T_GLOBAL_INT:
|
|
return None
|
|
if ins.opcode == MOV and len(ins.args) >= 2:
|
|
return ins.args[0][1], _val(ins.args[1])
|
|
if (ins.opcode == SUB and len(ins.args) >= 3
|
|
and ins.args[1][0] == T_IMM and ins.args[2][0] == T_IMM):
|
|
return ins.args[0][1], ins.args[1][1] - ins.args[2][1]
|
|
return None
|
|
|
|
|
|
def read_footer_array(scr, off):
|
|
"""Read a length-prefixed Data_Array at dword `off`: [length][v0..v_{length-1}]."""
|
|
dw = scr.dwords
|
|
if not (0 <= off < scr.nbody):
|
|
return None
|
|
length = dw[off]
|
|
if length > scr.nbody or off + 1 + length > scr.nbody:
|
|
return None
|
|
return list(dw[off + 1: off + 1 + length])
|
|
|
|
|
|
def detect_mode(scr):
|
|
ops = [ins.opcode for ins in scr.instructions]
|
|
has_str = any(ins.opcode == SET_STRING and ins.args and ins.args[0][0] == T_GLOBAL_STRING
|
|
for ins in scr.instructions)
|
|
if has_str:
|
|
return "name"
|
|
n_footer = ops.count(COPY_LOCAL_ARRAY)
|
|
n_int = ops.count(MOV) + ops.count(COPY_TO_GLOBAL)
|
|
return "footer" if n_footer >= max(4, n_int) else "numeric"
|
|
|
|
|
|
def _infer_record_span(string_addrs):
|
|
"""Infer the reserved width of one parallel string-array column.
|
|
|
|
The shipped INIT tables reserve a fixed number of ids per column (300 for
|
|
SKINIT and 1000 for ITINIT/EBINIT). A populated record commonly writes its
|
|
name and then its description, so that column stride is the dominant large
|
|
positive delta between consecutive string destinations.
|
|
"""
|
|
counts = {}
|
|
for left, right in zip(string_addrs, string_addrs[1:]):
|
|
delta = right - left
|
|
if delta >= 32:
|
|
counts[delta] = counts.get(delta, 0) + 1
|
|
if not counts:
|
|
raise ValueError("cannot infer name-table record span")
|
|
return max(counts, key=lambda delta: (counts[delta], delta))
|
|
|
|
|
|
@cache
|
|
def _known_record_tables():
|
|
"""Return corpus-observed (base, stride) pairs used by lookup-array-2d.
|
|
|
|
INIT scripts often populate linked row-major tables while defining an
|
|
entity. Treating every such write as `destination - entity_id` invents a
|
|
different one-off parallel column for every row. Consumer bytecode gives
|
|
us the unambiguous table base and stride instead.
|
|
"""
|
|
tables = set()
|
|
for path in paths.scripts().values():
|
|
try:
|
|
script = sys4load.load(path)
|
|
except sys4load.Sys4Error:
|
|
continue
|
|
for ins in script.instructions:
|
|
if (sys4load.display_label(ins.opcode) == "lookup-array-2d"
|
|
and len(ins.args) >= 5
|
|
and ins.args[1][0] in (T_GLOBAL_INT, 6)
|
|
and ins.args[3][0] == T_IMM
|
|
and ins.args[3][1] > 0):
|
|
tables.add((ins.args[1][1], ins.args[3][1]))
|
|
return tuple(sorted(tables))
|
|
|
|
|
|
def _record_table_cell(destination, record_id):
|
|
matches = []
|
|
for base, stride in _known_record_tables():
|
|
column = destination - (base + record_id * stride)
|
|
if 0 <= column < stride:
|
|
matches.append((base, stride, column))
|
|
if len(matches) > 1:
|
|
raise ValueError(
|
|
f"ambiguous record-table destination 0x{destination:x} for id {record_id}: {matches}"
|
|
)
|
|
return matches[0] if matches else None
|
|
|
|
|
|
def extract_name(scr):
|
|
string_addrs = [
|
|
ins.args[0][1]
|
|
for ins in scr.instructions
|
|
if ins.opcode == SET_STRING and ins.args and ins.args[0][0] == T_GLOBAL_STRING
|
|
]
|
|
if not string_addrs:
|
|
return [], {}
|
|
name_write_base = string_addrs[0]
|
|
# AGE's shipped entity ids are one-based. Array lookups use the cell just
|
|
# before the first populated destination as their base, then add the id.
|
|
first_record_id = 1
|
|
name_base = name_write_base - first_record_id
|
|
record_span = _infer_record_span(string_addrs)
|
|
records, cur, desc_slot, desc_bases = [], None, 0, {}
|
|
for ins in scr.instructions:
|
|
if ins.opcode == SET_STRING and ins.args and ins.args[0][0] == T_GLOBAL_STRING:
|
|
addr = ins.args[0][1]
|
|
txt = scr.strings.get(ins.args[1][1], (None,))[0] if len(ins.args) > 1 else None
|
|
# Names occupy column zero. Do not use an address decrease as the
|
|
# boundary: ITINIT begins with 101 consecutive name-only records,
|
|
# which the old heuristic collapsed into item zero.
|
|
if name_write_base <= addr < name_write_base + record_span:
|
|
cur = {"id": addr - name_base, "name": txt, "fields": {}, "record_fields": {}}
|
|
records.append(cur); desc_slot = 0
|
|
elif cur is not None:
|
|
key = "desc" if desc_slot == 0 else f"desc{desc_slot}"
|
|
cur[key] = txt; desc_bases.setdefault(key, addr - cur["id"]); desc_slot += 1
|
|
elif cur is not None and (write := _static_global_write(ins)) is not None:
|
|
destination, value = write
|
|
cell = _record_table_cell(destination, cur["id"])
|
|
if cell is None:
|
|
cur["fields"][f"0x{destination - cur['id']:x}"] = value
|
|
else:
|
|
base, stride, column = cell
|
|
cur["record_fields"][f"0x{base:x}/{stride}/{column}"] = value
|
|
for record in records:
|
|
if not record["record_fields"]:
|
|
del record["record_fields"]
|
|
record_columns = sorted(
|
|
{key for record in records for key in record.get("record_fields", {})},
|
|
key=lambda key: tuple(int(part, 0) for part in key.split("/")),
|
|
)
|
|
return records, {"name_array_base": f"0x{name_base:x}",
|
|
"name_write_base": f"0x{name_write_base:x}",
|
|
"first_record_id": first_record_id,
|
|
"record_span": record_span,
|
|
"record_field_columns": record_columns,
|
|
"desc_array_bases": {k: f"0x{v:x}" for k, v in sorted(desc_bases.items())}}
|
|
|
|
|
|
def _int_writes(scr):
|
|
"""Ordered (addr, value_arg) for global-int mov / copy-to-global."""
|
|
out = []
|
|
for ins in scr.instructions:
|
|
if ins.opcode in (MOV, COPY_TO_GLOBAL) and ins.args and ins.args[0][0] == T_GLOBAL_INT:
|
|
out.append((ins.args[0][1], ins.args[1]))
|
|
return out
|
|
|
|
|
|
def _longest_stride1_column(addrs):
|
|
"""Pick the primary index array: the stride-1 arithmetic run covering the most records."""
|
|
seen = set(addrs)
|
|
best_base, best_len = None, 0
|
|
for a in sorted(seen):
|
|
if a - 1 in seen:
|
|
continue # only start at a run's base
|
|
n = 0
|
|
while a + n in seen:
|
|
n += 1
|
|
if n > best_len:
|
|
best_base, best_len = a, n
|
|
return best_base, best_len
|
|
|
|
|
|
def extract_numeric(scr):
|
|
writes = _int_writes(scr)
|
|
base, n = _longest_stride1_column([a for a, _ in writes])
|
|
if base is None:
|
|
return [], {}
|
|
primary = set(range(base, base + n))
|
|
records, buf = [], []
|
|
for addr, varg in writes:
|
|
buf.append((addr, varg))
|
|
if addr in primary: # primary write closes the record
|
|
rid = addr - base
|
|
fields = {f"0x{a - rid:x}": _val(v) for a, v in buf}
|
|
records.append({"id": rid, "fields": fields})
|
|
buf = []
|
|
return records, {"primary_index_base": f"0x{base:x}", "record_span": n}
|
|
|
|
|
|
def extract_footer(scr):
|
|
records = []
|
|
for i, ins in enumerate(scr.instructions):
|
|
if ins.opcode == COPY_LOCAL_ARRAY and ins.args and ins.args[0][0] == T_GLOBAL_INT:
|
|
addr = ins.args[0][1]
|
|
foff = ins.args[1][1]
|
|
vals = read_footer_array(scr, foff)
|
|
records.append({"id": i, "global_addr": f"0x{addr:x}",
|
|
"footer_off": f"0x{foff:x}",
|
|
"length": len(vals) if vals else 0,
|
|
"values": vals if vals else []})
|
|
return records, {}
|
|
|
|
|
|
def write_data_index(data_dir: Path) -> None:
|
|
"""Regenerate the disposable build/data index from current table JSONs."""
|
|
tables = []
|
|
for path in sorted(data_dir.glob("*.json")):
|
|
if path.name.endswith("-field-profile.json"):
|
|
continue
|
|
try:
|
|
data = json.loads(path.read_text(encoding="utf8"))
|
|
except (OSError, json.JSONDecodeError):
|
|
continue
|
|
if "table" in data and "record_count" in data:
|
|
tables.append((path.name, data))
|
|
lines = [
|
|
"<!-- DO NOT EDIT -- generated by tools/extract_init.py -->",
|
|
"# Parsed INIT data tables",
|
|
"",
|
|
"The JSON files in this directory are generated from SYS4 `*INIT` scripts. Raw global-array",
|
|
"bases remain available in every record; confirmed field meanings live in",
|
|
"`vm-map/globals.toml` and the generated `docs/global-reference.md`.",
|
|
"",
|
|
"| file | mode | records | array fields | record columns |",
|
|
"|---|---|---:|---:|---:|",
|
|
]
|
|
for filename, data in tables:
|
|
columns = len(data.get("field_columns") or [])
|
|
record_columns = len(data.get("record_field_columns") or [])
|
|
lines.append(
|
|
f"| `{filename}` | {data['mode']} | {data['record_count']} | "
|
|
f"{columns} | {record_columns} |"
|
|
)
|
|
lines += [
|
|
"",
|
|
"Name-mode tables expose one-based runtime `id` values, the lookup `name_array_base`,",
|
|
"the first populated `name_write_base`, and the reserved `record_span`. Fields are keyed",
|
|
"by the runtime lookup base used by `lookup-array`, not merely the first written cell.",
|
|
"Linked row-major fields are stored separately in `record_fields`, keyed as",
|
|
"`base/stride/column` from corpus-observed `lookup-array-2d` consumers.",
|
|
"",
|
|
"Use `tools/init_table_profile.py <TABLE> --build` to generate value/population and",
|
|
"direct-consumer evidence. `STINIT` still requires a bespoke mixed numeric/string parser.",
|
|
"",
|
|
]
|
|
(data_dir / "README.md").write_text("\n".join(lines), encoding="utf8")
|
|
|
|
|
|
def main() -> int:
|
|
argv = [a for a in sys.argv[1:] if not a.startswith("--")]
|
|
mode_arg = next((sys.argv[i + 1] for i, a in enumerate(sys.argv) if a == "--mode"), None)
|
|
if not argv:
|
|
raise SystemExit(__doc__)
|
|
name = argv[0].upper().removesuffix(".BIN")
|
|
outname = argv[1] if len(argv) > 1 else name
|
|
scr = sys4load.load(resolve(name))
|
|
|
|
mode = mode_arg or detect_mode(scr)
|
|
extractor = {"name": extract_name, "numeric": extract_numeric, "footer": extract_footer}[mode]
|
|
recs, meta = extractor(scr)
|
|
|
|
cols = sorted({c for r in recs for c in r.get("fields", {})}, key=lambda h: int(h, 16))
|
|
out = {"table": name, "source": scr.path.name, "magic": scr.magic, "mode": mode,
|
|
"record_count": len(recs), **meta,
|
|
"field_columns": cols if mode != "footer" else None, "records": recs}
|
|
outpath = paths.BUILD / "data" / f"{outname}.json"
|
|
outpath.parent.mkdir(parents=True, exist_ok=True)
|
|
outpath.write_text(json.dumps(out, ensure_ascii=False, indent=2), encoding="utf-8")
|
|
write_data_index(outpath.parent)
|
|
print(f"{name}: mode={mode}, {len(recs)} records"
|
|
+ (f", {len(cols)} field-columns" if mode != 'footer' else "")
|
|
+ f" -> build/data/{outname}.json")
|
|
for r in recs[:4]:
|
|
if mode == "footer":
|
|
print(f" id {r['id']:>4} {r['global_addr']} <- footer {r['footer_off']} "
|
|
f"len {r['length']} head={r['values'][:8]}")
|
|
else:
|
|
f4 = {k: r['fields'][k] for k in list(r['fields'])[:4]}
|
|
print(f" id {r['id']:>4} {r.get('name','')!r:12} desc={r.get('desc','')!r} {f4}")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|