Syplheed-Reborn/tools/extract_movie_subtitles.py

#!/usr/bin/env python3
import struct, zlib, re, os
MOD=0x00FFF9D7; RECIP=0x80031493
def rol(v,n,b=32):
    v&=(1<<b)-1; return ((v<<n)|(v>>(b-n)))&((1<<b)-1)
def nh(name):
    bs=bytearray(name.encode('latin-1'))
    for i,b in enumerate(bs):
        if 0x41<=b<=0x5A: bs[i]=b+0x20
    a=0;bb=0
    for byte in bs:
        c=(byte if byte<0x80 else byte-0x100)&0xFFFFFFFF
        a=((rol(a,8)&0xFFFFFF00)+c)&0xFFFFFFFF
        bb=(bb+c)&0xFFFFFFFF
        hi=((a*RECIP)>>32)&0xFFFFFFFF; q=rol(hi,9)&0x1FF
        a=(a-(q*MOD))&0xFFFFFFFF
    return (((bb<<24)&0xFF000000)|(a&0xFFFFFF))&0xFFFFFFFF

EX="/home/fabi/RE Project Sylpheed/sylph_extract"
def load_pak(base):
    """base like dat/movie/eng ; returns list of (hash,off,size), data bytes"""
    pak=open(f"{EX}/{base}.pak","rb").read()
    n=struct.unpack(">I",pak[4:8])[0]
    es=[struct.unpack(">III",pak[16+12*i:28+12*i]) for i in range(n)]
    p00=f"{EX}/{base}.p00"
    data=open(p00,"rb").read() if os.path.exists(p00) else pak
    return es, data
def unz(blob):
    if blob[:2]==b'Z1':
        zi=blob.find(b'\x78\xda');
        if zi<0: zi=blob.find(b'\x78\x9c')
        return zlib.decompress(blob[zi:])
    return blob

# --- verify the track key scheme ---
es,data=load_pak("dat/movie/eng")
keys={h for h,_,_ in es}
for mv,exp in [("S00A",0x6F2D9663),("hokyu_DS_s02A",0x3662B1F8),("RT01C_1",0x756F69FB),("S16A",0xEEB85377)]:
    k=nh(f"subtitle_{mv}.tbl")
    print(f"subtitle_{mv}.tbl -> {k:08X}  expect {exp:08X}  inpak={k in keys}  {'OK' if k==exp else 'MISMATCH'}")

# --- build MSG_DEMO text table from GP_MAIN_GAME_E ---
es2,data2=load_pak("dat/GP_MAIN_GAME_E")
text={}  # 'MSG_DEMO_ddd_ppp_ll' -> string
keyrx=re.compile(r'^MSG_DEMO_\d+(_\d+)*$')
for h,o,s in es2:
    dec=unz(data2[o:o+s])
    if dec[:4]!=b'IXUD': continue
    # walk null-terminated utf-16le strings in the whole block
    toks=re.findall(rb'(?:[\x20-\x7e]\x00){2,}', dec)
    toks=[t.decode('utf-16-le') for t in toks]
    # pair: text followed by its key
    for i in range(len(toks)-1):
        if keyrx.match(toks[i+1]) and not keyrx.match(toks[i]):
            text[toks[i+1]]=toks[i]
print(f"\nMSG_DEMO text lines loaded: {len(text)}")

# --- render a movie's subtitle transcript ---
def track_for(mv):
    k=nh(f"subtitle_{mv}.tbl")
    for h,o,s in es:
        if h==k: return unz(data[o:o+s])
    return None
# index text by integer demo id -> ordered list of lines
bydemo={}
for k,v in text.items():
    m=re.match(r'MSG_DEMO_(\d+)_',k)
    if m: bydemo.setdefault(int(m.group(1)),[]).append((k,v))
for d in bydemo: bydemo[d].sort()

def transcript(mv):
    dec=track_for(mv)
    if not dec: return f"[no track for {mv}]"
    toks=re.findall(rb'(?:[\x20-\x7e]\x00){2,}', dec)
    toks=[t.decode('utf-16-le') for t in toks]
    out=[f"=== {mv}.wmv ==="]
    # collect all MSG_DEMO ids and timecodes in order; pair positionally
    seq=[('id',int(re.match(r'MSG_DEMO_(\d+)$',t).group(1))) if re.match(r'MSG_DEMO_(\d+)$',t)
         else ('tc',t) if re.match(r'\d\d:\d\d\.\d\d$',t) else ('x',t) for t in toks]
    ids=[v for k,v in seq if k=='id']; tcs=[v for k,v in seq if k=='tc']
    for j,demo in enumerate(ids):
        tc=tcs[j] if j<len(tcs) else "--:--.--"
        lines=[v for _,v in bydemo.get(demo,[])]
        out.append(f"  {tc}  [{demo:3d}] "+(" ".join(lines) if lines else "(no text on disc)"))
    return "\n".join(out)

for mv in ["S00A","S16A","hokyu_DS_s02A"]:
    print(); print(transcript(mv))