Files
Claude ae0e17b5dc codec-re: handoff polish — readmes, skeleton, remove decode-re/ duplicate
Three things to make pickup smoother:

1. analysis/README.md (NEW): catalogues the ~25 scratch scripts.
   Categorizes them as "still useful" / "superseded — keep for
   archaeology" / "pure exploration".  Tells a fresh engineer which
   files to read first and which to ignore.

2. scratch/next_experiment_skeleton.py (NEW): stub + spec for the
   segment-channel scoring analyzer.  Includes the fixture loader,
   block walker, and decode-segment-as-channel helper — just enough
   scaffolding that the next pass starts from "fill in
   score_segment_against_all_channels()" rather than from scratch.
   Already runs and confirms 13 segments per 3-sec event with sample
   starts going to 6590 (way past the 3328 actual samples) — strong
   evidence that not all segments carry Tran.

3. Removed decode-re/ duplicate.  It was a mirror of tests/fixtures/.
   Analysis scripts that hardcoded decode-re/ paths updated to point
   at tests/fixtures/.  CLAUDE.md note updated: future event uploads
   go directly into a dated subdirectory under tests/fixtures/.

All 40 tests still pass.  Skeleton runs.
2026-05-20 17:28:54 +00:00

82 lines
2.7 KiB
Python

"""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"tests/fixtures/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()