2taud.py: fix: stereo samples not converting correctly

This commit is contained in:
minjaesong
2026-05-21 02:55:41 +09:00
parent 8e8374ba99
commit 5b9b96c8de
3 changed files with 50 additions and 22 deletions

View File

@@ -294,11 +294,11 @@ def _it214_decompress_block(payload: bytes, num_samples: int,
return out return out
def it214_decompress(blob: bytes, smp_offset: int, num_samples: int, def _it214_decompress_channel(blob: bytes, pos: int, num_samples: int,
is_16bit: bool, is_it215: bool) -> bytes: is_16bit: bool, is_it215: bool) -> tuple:
"""Decode IT2.14/IT2.15 compressed sample data. Returns raw PCM bytes (signed).""" """Decode one channel of IT2.14/IT2.15 compressed data. Returns
(raw PCM bytes, next position after consumed blocks)."""
block_size = 0x4000 if is_16bit else 0x8000 block_size = 0x4000 if is_16bit else 0x8000
pos = smp_offset
out_samples = [] out_samples = []
while len(out_samples) < num_samples: while len(out_samples) < num_samples:
@@ -318,9 +318,24 @@ def it214_decompress(blob: bytes, smp_offset: int, num_samples: int,
result = bytearray(len(out_samples) * 2) result = bytearray(len(out_samples) * 2)
for i, s in enumerate(out_samples): for i, s in enumerate(out_samples):
struct.pack_into('<h', result, i * 2, max(-32768, min(32767, s))) struct.pack_into('<h', result, i * 2, max(-32768, min(32767, s)))
return bytes(result) return bytes(result), pos
else: else:
return bytes(s & 0xFF for s in out_samples) return bytes(s & 0xFF for s in out_samples), pos
def it214_decompress(blob: bytes, smp_offset: int, num_samples: int,
is_16bit: bool, is_it215: bool,
is_stereo: bool = False) -> bytes:
"""Decode IT2.14/IT2.15 compressed sample data. Returns raw PCM bytes
(signed). For stereo samples, returns the left channel block followed
by the right channel block (matching IT's on-disk SF_SS layout)."""
left, pos = _it214_decompress_channel(blob, smp_offset, num_samples,
is_16bit, is_it215)
if not is_stereo:
return left
right, _ = _it214_decompress_channel(blob, pos, num_samples,
is_16bit, is_it215)
return left + right
# ── IT sample parser ────────────────────────────────────────────────────────── # ── IT sample parser ──────────────────────────────────────────────────────────
@@ -384,7 +399,7 @@ def parse_samples(data: bytes, h: ITHeader, decompress: bool) -> list:
try: try:
is_it215 = bool(s.cvt & 0x04) is_it215 = bool(s.cvt & 0x04)
raw = it214_decompress(data, s.smp_point, s.length, raw = it214_decompress(data, s.smp_point, s.length,
s.is_16bit, is_it215) s.is_16bit, is_it215, s.is_stereo)
s.sample_data = normalise_sample(raw, True, s.sample_data = normalise_sample(raw, True,
s.is_16bit, s.is_stereo, s.name) s.is_16bit, s.is_stereo, s.name)
s.length = len(s.sample_data) s.length = len(s.sample_data)

View File

@@ -592,7 +592,7 @@ def build_sample_inst_bin(samples: list) -> tuple:
# PT hard-pans channels in LRRL order: 0=L 1=R 2=R 3=L (and tile for >4). # PT hard-pans channels in LRRL order: 0=L 1=R 2=R 3=L (and tile for >4).
def _default_channel_pan(ch_idx: int) -> int: def _default_channel_pan(ch_idx: int) -> int:
side = (ch_idx % 4) side = (ch_idx % 4)
return 16 if side in (0, 3) else 47 return 8 if side in (0, 3) else 55
def build_pattern(grid: list, ch_idx: int, default_pan: int, def build_pattern(grid: list, ch_idx: int, default_pan: int,

View File

@@ -614,31 +614,44 @@ def build_project_data(*, project_name: str = '',
def normalise_sample(raw: bytes, signed: bool, is_16bit: bool, def normalise_sample(raw: bytes, signed: bool, is_16bit: bool,
is_stereo: bool, name: str) -> bytes: is_stereo: bool, name: str) -> bytes:
"""Return unsigned 8-bit mono sample bytes, downmixing/depthing as needed.""" """Return unsigned 8-bit mono sample bytes, downmixing/depthing as needed.
Stereo samples are stored as a split (non-interleaved) layout — the full
left channel block followed by the full right channel block — matching the
on-disk format used by IT, S3M, and XM (Schism's SF_SS).
"""
out = [] out = []
stride = (2 if is_16bit else 1) * (2 if is_stereo else 1) bps = 2 if is_16bit else 1
i = 0 chans = 2 if is_stereo else 1
while i + stride <= len(raw): n_frames = len(raw) // (bps * chans)
chan_bytes = n_frames * bps
for i in range(n_frames):
if is_16bit: if is_16bit:
if is_stereo: if is_stereo:
l16 = struct.unpack_from('<h', raw, i)[0] l16 = struct.unpack_from('<h', raw, i*2)[0]
r16 = struct.unpack_from('<h', raw, i+2)[0] r16 = struct.unpack_from('<h', raw, chan_bytes + i*2)[0]
s = (l16 + r16) >> 1 s = (l16 + r16) >> 1
else: else:
s = struct.unpack_from('<h', raw, i)[0] s = struct.unpack_from('<h', raw, i*2)[0]
v = (s >> 8) + 128 v = (s >> 8) + 128
else: else:
if is_stereo: if is_stereo:
l8 = raw[i]; r8 = raw[i+1] l8 = raw[i]
raw_s = (l8 + r8) // 2 r8 = raw[chan_bytes + i]
if signed:
l_s = l8 - 256 if l8 >= 0x80 else l8
r_s = r8 - 256 if r8 >= 0x80 else r8
v = ((l_s + r_s) >> 1) + 128
else:
v = (l8 + r8) >> 1
else: else:
raw_s = raw[i] raw_s = raw[i]
if signed: if signed:
v = (raw_s ^ 0x80) & 0xFF v = (raw_s ^ 0x80) & 0xFF
else: else:
v = raw_s v = raw_s
out.append(v & 0xFF) out.append(v & 0xFF)
i += stride
if is_16bit or is_stereo: if is_16bit or is_stereo:
vprint(f" info: '{name}' converted to unsigned 8-bit mono ({len(out)} samples)") vprint(f" info: '{name}' converted to unsigned 8-bit mono ({len(out)} samples)")
return bytes(out) return bytes(out)