codec-re: 00 NN is RLE; full Tran segment-0 decode (4 of 5 events)
User uploaded a Vert-heavy event (JQ0) and a Mic-heavy event (V70). Those two were exactly what was needed to crack the next piece: - 00 NN block = run-length-encoded zero deltas in the current channel. Append NN copies of the current cumulative value (no change). - find_data_start now recognizes 00 NN as a valid first tag (some events begin with a leading 00 NN RLE block). - decode_tran_initial now decodes the FULL segment 0 (not just the first data block). Results across 5 fixture events: - M529LL1A.SP0 (loud-all-channels) : 510 / 510 ✓ - M529LL1L.JQ0 (Vert-heavy) : 510 / 510 ✓ - M529LL1L.V70 (Mic-heavy) : 510 / 510 ✓ - M529LL1A.SV0 (loud-from-start) : 58 / 58 ✓ - M529LL1A.SS0 (loud-from-start) : 42 / 502 (stops at first 30 04) The 30 04 block (only seen in loud-from-start events) hasn't been decoded yet — likely a channel-switch marker for the high-amplitude regime. Also discovered: segment header (40 02) payload bytes [0:2] = T_delta at first sample of new segment, [6:8] = byte length to next segment. Multi-segment Tran decoding still diverges after sample 512 because the per-segment channel ordering after the header is unknown. Tests: 40 pass (up from 36). Files: - minimateplus/waveform_codec.py: find_data_start fix, RLE handling, full segment-0 decode in decode_tran_initial - tests/test_waveform_codec.py: synthetic RLE test, full segment 0 tests for JQ0 and V70 - tests/fixtures/5-11-26/: M529LL1L.JQ0, M529LL1L.V70 + TXT exports - docs/instantel_protocol_reference.md §7.6.1: RLE + segment-header docs
This commit is contained in:
Claude
@@ -0,0 +1,76 @@
|
||||
"""Full Tran decoder: continues across segment headers using T_delta from header bytes [0:2]."""
|
||||
import sys
|
||||
sys.path.insert(0, ".")
|
||||
from analysis.load_bundle import _parse_txt
|
||||
from minimateplus.waveform_codec import walk_body, find_data_start
|
||||
|
||||
|
||||
def s4(n):
|
||||
return n if n < 8 else n - 16
|
||||
|
||||
|
||||
def i8(b):
|
||||
return b if b < 128 else b - 256
|
||||
|
||||
|
||||
def decode_full_tran(body):
|
||||
if len(body) < 7 or body[0:3] != b"\x00\x02\x00":
|
||||
return None
|
||||
T0 = int.from_bytes(body[3:5], "big", signed=True)
|
||||
T1 = int.from_bytes(body[5:7], "big", signed=True)
|
||||
|
||||
i = 7
|
||||
while i + 1 < len(body) and body[i] not in (0x00, 0x10, 0x20, 0x30, 0x40):
|
||||
i += 1
|
||||
|
||||
blocks = walk_body(body, i)
|
||||
T = [T0, T1]
|
||||
cur = T1
|
||||
for blk in blocks:
|
||||
if blk.tag_hi == 0x40:
|
||||
# Segment header carries 2 T deltas (int16 BE each) at bytes [0:2] and [2:4]
|
||||
if len(blk.data) >= 4:
|
||||
delta1 = int.from_bytes(blk.data[0:2], "big", signed=True)
|
||||
cur += delta1
|
||||
T.append(cur)
|
||||
delta2 = int.from_bytes(blk.data[2:4], "big", signed=True)
|
||||
cur += delta2
|
||||
T.append(cur)
|
||||
elif blk.tag_hi == 0x10:
|
||||
for byte in blk.data:
|
||||
for nib in ((byte >> 4) & 0xF, byte & 0xF):
|
||||
cur += s4(nib)
|
||||
T.append(cur)
|
||||
elif blk.tag_hi == 0x20:
|
||||
for byte in blk.data:
|
||||
cur += i8(byte)
|
||||
T.append(cur)
|
||||
elif blk.tag_hi == 0x00:
|
||||
for _ in range(blk.tag_lo):
|
||||
T.append(cur)
|
||||
# 30 NN: skip for now
|
||||
return T
|
||||
|
||||
|
||||
def main():
|
||||
for stem in ("M529LL1L.V70", "M529LL1L.JQ0", "M529LL1A.SP0", "M529LL1A.SS0", "M529LL1A.SV0"):
|
||||
path = f"decode-re/5-11-26/{stem}"
|
||||
with open(path, "rb") as f:
|
||||
body = f.read()[43:-26]
|
||||
_, samples = _parse_txt(path + ".TXT")
|
||||
truth_T = [round(v*200) for v in samples["Tran"]]
|
||||
n_truth = len(truth_T)
|
||||
|
||||
decoded = decode_full_tran(body)
|
||||
n = min(len(decoded), n_truth)
|
||||
matches = sum(1 for i in range(n) if decoded[i] == truth_T[i])
|
||||
div_at = -1
|
||||
for i in range(n):
|
||||
if decoded[i] != truth_T[i]:
|
||||
div_at = i
|
||||
break
|
||||
print(f"{stem}: decoded={len(decoded)}, truth={n_truth}, matches={matches}/{n}, first div={div_at}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,81 @@
|
||||
"""Decode Tran across multiple segments by resetting at 40 02 headers."""
|
||||
import sys
|
||||
sys.path.insert(0, ".")
|
||||
from analysis.load_bundle import _parse_txt
|
||||
from minimateplus.waveform_codec import walk_body, find_data_start
|
||||
|
||||
|
||||
def s4(n):
|
||||
return n if n < 8 else n - 16
|
||||
|
||||
|
||||
def i8(b):
|
||||
return b if b < 128 else b - 256
|
||||
|
||||
|
||||
def decode_full_tran(body):
|
||||
"""Decode all Tran samples in the body, walking through segments."""
|
||||
if len(body) < 7 or body[0:3] != b"\x00\x02\x00":
|
||||
return None
|
||||
T0 = int.from_bytes(body[3:5], "big", signed=True)
|
||||
T1 = int.from_bytes(body[5:7], "big", signed=True)
|
||||
|
||||
# Locate first tag
|
||||
i = 7
|
||||
while i + 1 < len(body) and body[i] not in (0x00, 0x10, 0x20, 0x30, 0x40):
|
||||
i += 1
|
||||
|
||||
blocks = walk_body(body, i)
|
||||
T = [T0, T1]
|
||||
cur = T1
|
||||
for bi, blk in enumerate(blocks):
|
||||
if blk.tag_hi == 0x40:
|
||||
# Segment header — try interpreting bytes [0:2] as new T anchor
|
||||
if len(blk.data) >= 2:
|
||||
new_anchor = int.from_bytes(blk.data[0:2], "big", signed=True)
|
||||
# The next sample IS this anchor value, NOT a delta from cur.
|
||||
T.append(new_anchor)
|
||||
cur = new_anchor
|
||||
elif blk.tag_hi == 0x10:
|
||||
for byte in blk.data:
|
||||
for nib in ((byte >> 4) & 0xF, byte & 0xF):
|
||||
cur += s4(nib)
|
||||
T.append(cur)
|
||||
elif blk.tag_hi == 0x20:
|
||||
for byte in blk.data:
|
||||
cur += i8(byte)
|
||||
T.append(cur)
|
||||
elif blk.tag_hi == 0x00:
|
||||
# RLE: append NN zero deltas
|
||||
for _ in range(blk.tag_lo):
|
||||
T.append(cur)
|
||||
# 30 NN: skip
|
||||
return T
|
||||
|
||||
|
||||
def main():
|
||||
for stem in ("M529LL1L.V70", "M529LL1L.JQ0", "M529LL1A.SP0", "M529LL1A.SS0", "M529LL1A.SV0"):
|
||||
path = f"decode-re/5-11-26/{stem}"
|
||||
with open(path, "rb") as f:
|
||||
body = f.read()[43:-26]
|
||||
_, samples = _parse_txt(path + ".TXT")
|
||||
truth_T = [round(v*200) for v in samples["Tran"]]
|
||||
n_truth = len(truth_T)
|
||||
|
||||
decoded = decode_full_tran(body)
|
||||
n = min(len(decoded), n_truth)
|
||||
matches = sum(1 for i in range(n) if decoded[i] == truth_T[i])
|
||||
# Find first divergence
|
||||
div_at = -1
|
||||
for i in range(n):
|
||||
if decoded[i] != truth_T[i]:
|
||||
div_at = i
|
||||
break
|
||||
print(f"{stem}: decoded={len(decoded)}, truth={n_truth}, matches={matches}/{n}, first div={div_at}")
|
||||
if div_at >= 0 and div_at < 30:
|
||||
print(f" truth around div [{max(0,div_at-3)}:{div_at+8}]: {truth_T[max(0,div_at-3):div_at+8]}")
|
||||
print(f" pred around div [{max(0,div_at-3)}:{div_at+8}]: {decoded[max(0,div_at-3):div_at+8]}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,86 @@
|
||||
"""Test: 00 NN markers might be RLE for zero-deltas in current channel."""
|
||||
import sys
|
||||
sys.path.insert(0, ".")
|
||||
from analysis.load_bundle import _parse_txt
|
||||
from minimateplus.waveform_codec import walk_body, find_data_start
|
||||
|
||||
|
||||
def s4(n):
|
||||
return n if n < 8 else n - 16
|
||||
|
||||
|
||||
def i8(b):
|
||||
return b if b < 128 else b - 256
|
||||
|
||||
|
||||
def decode_with_rle(body):
|
||||
"""Decode Tran assuming:
|
||||
- preamble[3:5], [5:7] = T[0], T[1]
|
||||
- All 10 NN / 20 NN blocks until segment_header (40 02) are Tran deltas
|
||||
- 00 NN markers are RLE: NN/4 zero T deltas (or NN, or NN/2 — try them)
|
||||
"""
|
||||
if len(body) < 9 or body[0:3] != b"\x00\x02\x00":
|
||||
return None, None, None
|
||||
T0 = int.from_bytes(body[3:5], "big", signed=True)
|
||||
T1 = int.from_bytes(body[5:7], "big", signed=True)
|
||||
|
||||
# Find first tag (might be 00 NN, 10 NN, or 20 NN)
|
||||
i = 7
|
||||
while i + 1 < len(body):
|
||||
if body[i] in (0x00, 0x10, 0x20):
|
||||
break
|
||||
i += 1
|
||||
start = i
|
||||
|
||||
blocks = walk_body(body, start)
|
||||
|
||||
results = {}
|
||||
for rle_div in (4, 2, 1): # try different RLE interpretations
|
||||
T = [T0, T1]
|
||||
cur = T1
|
||||
for blk in blocks:
|
||||
if blk.tag_hi == 0x40:
|
||||
break
|
||||
if blk.tag_hi == 0x10:
|
||||
for byte in blk.data:
|
||||
for nib in ((byte >> 4) & 0xF, byte & 0xF):
|
||||
cur += s4(nib)
|
||||
T.append(cur)
|
||||
elif blk.tag_hi == 0x20:
|
||||
for byte in blk.data:
|
||||
cur += i8(byte)
|
||||
T.append(cur)
|
||||
elif blk.tag_hi == 0x00:
|
||||
# RLE of zero deltas
|
||||
n_zeros = blk.tag_lo // rle_div
|
||||
for _ in range(n_zeros):
|
||||
T.append(cur)
|
||||
# 30 NN: skip for now
|
||||
results[rle_div] = T
|
||||
return results, T0, T1
|
||||
|
||||
|
||||
def main():
|
||||
for stem in ("M529LL1L.V70", "M529LL1L.JQ0", "M529LL1A.SP0", "M529LL1A.SS0", "M529LL1A.SV0"):
|
||||
path = f"decode-re/5-11-26/{stem}"
|
||||
with open(path, "rb") as f:
|
||||
body = f.read()[43:-26]
|
||||
_, samples = _parse_txt(path + ".TXT")
|
||||
truth_T = [round(v*200) for v in samples["Tran"]]
|
||||
|
||||
results, T0, T1 = decode_with_rle(body)
|
||||
print(f"\n=== {stem} (T[0]={T0}, T[1]={T1}) ===")
|
||||
for rle_div, T in results.items():
|
||||
n = min(len(T), len(truth_T))
|
||||
matches = sum(1 for i in range(n) if T[i] == truth_T[i])
|
||||
# Find first divergence
|
||||
div_at = -1
|
||||
for i in range(n):
|
||||
if T[i] != truth_T[i]:
|
||||
div_at = i
|
||||
break
|
||||
print(f" rle_div={rle_div}: decoded {len(T)}, matches {matches}/{n}, first div at sample {div_at}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user