"""Disc-wide: does T8aD flag bit 0x02 imply an `eff` name?

Names come from the NAME IMMEDIATELY PRECEDING each T8aD chunk -- validated
17/18 on GP_TITLE build 4 against the known RATC child order. The single
mismatch is the documented `pteff04.t32` -> registered as `8AX` case, i.e. the
preceding name is the ELEMENT's (opt) name and the child list is the SPRITE's.
This test uses the element name and says so.
"""
import struct, zlib, glob, os, re, collections
NAME = re.compile(rb'[A-Za-z0-9_.]{2,31}\x00')

def entries(base):
    stub = open(base + ".pak", "rb").read()
    if stub[:4] != b"IPFB": return
    n = struct.unpack_from(">I", stub, 4)[0]
    segs = sorted(glob.glob(base + ".p[0-9][0-9]"))
    if not segs: return
    blob = b"".join(open(s, "rb").read() for s in segs)
    for i in range(n):
        h, off, sz = struct.unpack_from(">III", stub, 0x10 + 12 * i)
        st = blob[off:off + sz]
        if len(st) < 10: continue
        try: yield (zlib.decompress(st[10:]) if st[:2] == b"Z1" else st)
        except Exception: continue

set_eff = set_noneff = clear_eff = clear_noneff = 0
examples = []
for pak in sorted(glob.glob("/work/sylph_extract/dat/GP_*.pak")):
    for d in entries(pak[:-4]):
        for m in re.finditer(b"T8aD", d):
            o = m.start()
            try:
                fl = struct.unpack_from(">I", d, o + 4)[0]
                w = struct.unpack_from(">I", d, o + 0x14)[0]
                h = struct.unpack_from(">I", d, o + 0x18)[0]
            except Exception: continue
            if not (0 < w <= 4096 and 0 < h <= 4096): continue
            ms = list(NAME.finditer(d[max(0, o - 64):o]))
            if not ms: continue
            nm = ms[-1].group()[:-1].decode("latin1")
            eff = "eff" in nm.lower()
            if fl & 2:
                if eff: set_eff += 1
                else:
                    set_noneff += 1
                    if len(examples) < 12: examples.append((os.path.basename(pak), nm, f"{fl:08x}", f"{w}x{h}"))
            else:
                clear_eff += 1 if eff else 0
                clear_noneff += 0 if eff else 1
tot = set_eff + set_noneff + clear_eff + clear_noneff
print(f"sprites with a resolvable preceding name: {tot}")
print(f"  bit SET   & name has 'eff' : {set_eff}")
print(f"  bit SET   & name lacks 'eff': {set_noneff}   <-- counterexamples to 'set => eff'")
print(f"  bit clear & name has 'eff' : {clear_eff}")
print(f"  bit clear & name lacks 'eff': {clear_noneff}")
if tot: print(f"\n  P(name has 'eff' | bit set)   = {set_eff/max(set_eff+set_noneff,1):.3f}")
if tot: print(f"  P(name has 'eff' | bit clear) = {clear_eff/max(clear_eff+clear_noneff,1):.3f}")
if examples:
    print("\n  counterexamples (bit set, no 'eff'):")
    for e in examples: print("   ", e)