#!/usr/bin/env python3
"""Parse (and re-serialize) a Project Sylpheed save file.

The retail save lives in Xenia's content tree as a single file:

    <content>/<XUID>/535107D4/00000001/game01/savedata

It is a `GDHA` container whose payload is **zlib-deflated** (`78 da`). The
payload is a self-describing chunk stream written by the title's serializer at
`0x822C00E8`; every field below is read off that function and its callee
`0x822BF678`, not guessed:

    'GDAA'                              container magic
    u32 len, char[len]                  current game phase, e.g. "GP_BUNK"
                                        (index < 29 into the GP_* name table at
                                        0x820A5680; the .pe lists GP_HANGAR,
                                        GP_READY_ROOM, GP_BUNK, GP_MOVIE,
                                        GP_OPTIONS, GP_MISSION_*)
    'GHAD' + 122 bytes                  the progress block (see GHAD_LAYOUT)
    u32 16, then 16 x ('SHAB' + 5*u32)  the save-slot table
    u32 4, "BUNK", 'NETA', u32          trailer

`u32 16` and the 20-byte slot stride are literals in the serializer
(`addi r28,r0,16` / `addi r29,r29,20` at 0x822C01B0/0x822C0264), and the
in-memory struct is written field-by-field with no packing changes, so a file
offset here IS the offset in the live save object (base + 8 for GHAD, base + 136
for the slot table, whose end at base + 456 is the next field the serializer
touches).

Usage:
    savegame.py <savedata>            # parse and print
    savegame.py <savedata> --verify   # parse, re-serialize, assert byte-identical
"""
import struct
import sys
import zlib

# (name, offset in the GHAD block, size). Read off 0x822BF678: ten u32, one u64
# (`ld r11,40(r30)`), four more u32, a raw 4-byte field at +64 and a raw 54-byte
# blob at +68 — 122 bytes, which is exactly what the file carries.
GHAD_LAYOUT = [
    ("u32_00", 0, 4), ("u32_04", 4, 4), ("u32_08", 8, 4), ("u32_12", 12, 4),
    ("u32_16", 16, 4), ("u32_20", 20, 4), ("u32_24", 24, 4), ("u32_28", 28, 4),
    ("u32_32", 32, 4), ("u32_36", 36, 4),
    ("u64_40", 40, 8),
    ("u32_48", 48, 4), ("u32_52", 52, 4), ("u32_56", 56, 4), ("u32_60", 60, 4),
    ("raw_64", 64, 4),
    ("blob_68", 68, 54),
]
GHAD_SIZE = 122
SLOT_COUNT = 16
SLOT_FIELDS = 5          # 5 u32 per slot; the last two read as a FILETIME


def unwrap(raw):
    """GDHA container -> (header bytes, inflated payload)."""
    if raw[:4] != b"GDHA":
        raise ValueError("not a GDHA container: %r" % raw[:4])
    i = raw.find(b"\x78\xda")
    if i < 0:
        raise ValueError("no zlib stream")
    return raw[:i], zlib.decompress(raw[i:])


def parse(payload):
    if payload[:4] != b"GDAA":
        raise ValueError("not a GDAA payload: %r" % payload[:4])
    o = 4
    (nlen,) = struct.unpack_from(">I", payload, o); o += 4
    phase = payload[o:o + nlen].decode("ascii"); o += nlen
    if payload[o:o + 4] != b"GHAD":
        raise ValueError("expected GHAD at %#x" % o)
    o += 4
    ghad_at = o
    ghad = {}
    for name, off, size in GHAD_LAYOUT:
        b = payload[ghad_at + off: ghad_at + off + size]
        ghad[name] = struct.unpack(">I", b)[0] if size == 4 and not name.startswith("raw") \
            else struct.unpack(">Q", b)[0] if size == 8 else b
    o = ghad_at + GHAD_SIZE
    (count,) = struct.unpack_from(">I", payload, o); o += 4
    slots = []
    for _ in range(count):
        if payload[o:o + 4] != b"SHAB":
            raise ValueError("expected SHAB at %#x" % o)
        o += 4
        vals = struct.unpack_from(">%dI" % SLOT_FIELDS, payload, o)
        o += 4 * SLOT_FIELDS
        slots.append(vals)
    (tlen,) = struct.unpack_from(">I", payload, o); o += 4
    tname = payload[o:o + tlen].decode("ascii"); o += tlen
    ttag = payload[o:o + 4]; o += 4
    (tval,) = struct.unpack_from(">I", payload, o); o += 4
    if o != len(payload):
        raise ValueError("trailing %d bytes" % (len(payload) - o))
    return dict(phase=phase, ghad=ghad, slot_count=count, slots=slots,
                trailer=(tname, ttag.decode("ascii"), tval))


def serialize(p):
    out = bytearray(b"GDAA")
    out += struct.pack(">I", len(p["phase"])) + p["phase"].encode("ascii")
    out += b"GHAD"
    blk = bytearray(GHAD_SIZE)
    for name, off, size in GHAD_LAYOUT:
        v = p["ghad"][name]
        blk[off:off + size] = v if isinstance(v, bytes) else \
            struct.pack(">I", v) if size == 4 else struct.pack(">Q", v)
    out += blk
    out += struct.pack(">I", p["slot_count"])
    for s in p["slots"]:
        out += b"SHAB" + struct.pack(">%dI" % SLOT_FIELDS, *s)
    tname, ttag, tval = p["trailer"]
    out += struct.pack(">I", len(tname)) + tname.encode("ascii")
    out += ttag.encode("ascii") + struct.pack(">I", tval)
    return bytes(out)


def filetime(hi, lo):
    """The two trailing slot u32 read as a Windows FILETIME (100 ns since 1601)."""
    import datetime
    ticks = (hi << 32) | lo
    if not ticks:
        return "-"
    try:
        return (datetime.datetime(1601, 1, 1) +
                datetime.timedelta(microseconds=ticks // 10)).strftime("%Y-%m-%d %H:%M:%S")
    except OverflowError:
        return "?"


def main():
    path = sys.argv[1]
    raw = open(path, "rb").read()
    hdr, payload = unwrap(raw)
    p = parse(payload)
    if "--verify" in sys.argv:
        again = serialize(p)
        ok = again == payload
        print("round-trip %s (%d bytes)" % ("OK — byte-identical" if ok else "MISMATCH", len(payload)))
        if not ok:
            for i, (a, b) in enumerate(zip(payload, again)):
                if a != b:
                    print("  first diff at %#x: %02x != %02x" % (i, a, b))
                    break
        return 0 if ok else 1
    print("container : GDHA, %d bytes header + %d bytes deflate -> %d bytes"
          % (len(hdr), len(raw) - len(hdr), len(payload)))
    print("phase     : %s" % p["phase"])
    print("GHAD:")
    for name, off, size in GHAD_LAYOUT:
        v = p["ghad"][name]
        print("  +%-3d %-8s %s" % (off, name,
              v.hex(" ") if isinstance(v, bytes) else "%-10d (%#x)" % (v, v)))
    print("slots     : %d" % p["slot_count"])
    for i, s in enumerate(p["slots"]):
        used = any(s[:3])
        print("  [%2d] %s a=%-6d b=%-8d c=%-10d time=%s"
              % (i, "USED " if used else "empty", s[0], s[1], s[2], filetime(s[3], s[4])))
    print("trailer   : len=%d name=%r tag=%r val=%#x"
          % (len(p["trailer"][0]), p["trailer"][0], p["trailer"][1], p["trailer"][2]))
    return 0


if __name__ == "__main__":
    sys.exit(main())