diff --git a/.gitignore b/.gitignore index d6e4855..90e5d24 100644 --- a/.gitignore +++ b/.gitignore @@ -1,6 +1,6 @@ /bridges/captures/ /example-events/ - +/tests/fixtures/ /manuals/ # Python build artifacts diff --git a/docs/histogram_codec_re_status.md b/docs/histogram_codec_re_status.md index 3a37450..6fa388c 100644 --- a/docs/histogram_codec_re_status.md +++ b/docs/histogram_codec_re_status.md @@ -12,7 +12,21 @@ implementation lives in `minimateplus/histogram_codec.py`. in-repo histogram fixture corpus decodes byte-exact against BW's ASCII export. -24 regression tests pass against ~3,500 blocks across 5 fixtures. +26 regression tests pass against ~3,500 blocks across 5 in-repo +fixtures, plus a synthetic regression block taken from a real +BE9558 prod event to lock in the uint8-peak interpretation. + +**Important correction (2026-05-21):** the per-channel peak count +is `uint8` at byte[6]/[10]/[14]/[18], NOT `uint16 LE` at byte[6:8] +etc. The N844 fixture corpus the original RE was done against has +zero values in bytes [7]/[11]/[15]/[19] for every block, so the +two interpretations happened to be equivalent. Cross-correlating +non-N844 events (BE9558 Tran-drift, BE18003 Histogram+Continuous) +against BW's per-interval ASCII export — 4 channels × ~1400 blocks +per event × multiple events = 100% byte-exact only when the peak +is read as uint8. Reading as uint16 LE produced peaks up to 268 +in/s per channel and 35× inflated PVS sums when first deployed to +prod (rolled back, root-caused, and fixed in commit 7183b95+1). ## Body format @@ -27,15 +41,21 @@ Each block represents one histogram interval. Block layout: [1] segment_id (uint8) 0x00..0x03 — 256 blocks per segment [2:4] block_ctr (uint16 LE) resets each segment (0x0100, 0x0101, …) [4:6] 0x000a (uint16 LE) constant marker (= 10) -[6:8] T_peak_count uint16 LE Tran peak (count × 0.005 → in/s at Normal) +[6] T_peak_count uint8 Tran peak (count × 0.005 → in/s at Normal, + max 1.275 in/s — fits in uint8) +[7] T_annotation uint8 empirically non-zero on intervals with sub-Hz + or unmeasurable freq; meaning not fully RE'd [8:10] T_halfperiod uint16 LE Tran half-period in samples (freq_Hz = 512 / halfp; ≤ 5 means ">100 Hz") -[10:12] V_peak_count uint16 LE Vert peak +[10] V_peak_count uint8 Vert peak +[11] V_annotation uint8 [12:14] V_halfperiod uint16 LE Vert freq half-period -[14:16] L_peak_count uint16 LE Long peak +[14] L_peak_count uint8 Long peak +[15] L_annotation uint8 [16:18] L_halfperiod uint16 LE Long freq half-period -[18:20] M_peak_count uint16 LE MicL peak count +[18] M_peak_count uint8 MicL peak count (dB via waveform_codec.mic_count_to_db) +[19] M_annotation uint8 [20:22] M_halfperiod uint16 LE MicL freq half-period [22:24] 0x00 0x00 constant [24:28] 4-byte variable purpose unknown — possibly CRC, @@ -99,6 +119,16 @@ slot[8] = 9 → 512/9 = 56.9 → 57 Hz ✓ M_freq ## What's NOT yet decoded +- **Annotation bytes (`block[7]/[11]/[15]/[19]`)**. Empirically + non-zero on intervals where the per-channel ZC frequency comes + out as `N/A` or sub-Hz (`<1.0`, `1.X`). Hypothesis tested in the + RE session: byte != 0 ↔ sub-Hz freq. Only ~50% correlation + across the K558 corpus, so the relationship is more complex. + Possibilities: time-of-peak-within-interval, halfp extension for + very-long-period signals, or a debug/diagnostic field the firmware + writes opportunistically. Doesn't affect peak amplitudes or + waveform reconstruction. Captured as `record["annotations"]` for + future RE. - **4-byte variable metadata field (bytes 24:28)**. Not needed for waveform reconstruction. Speculation: per-block CRC, sub-second timestamp offset, or a Mic psi(L) count not in the 9 samples. diff --git a/minimateplus/histogram_codec.py b/minimateplus/histogram_codec.py index adc0714..36e399d 100644 --- a/minimateplus/histogram_codec.py +++ b/minimateplus/histogram_codec.py @@ -28,18 +28,32 @@ iterate 32-stride and stop before the tail. [1] segment_id (uint8) 0x00..0x03 — 256 blocks per segment [2:4] block_ctr (uint16 LE) resets each segment (0x0100, 0x0101, …) [4:6] 0x000a (uint16 LE) constant marker (= 10) - [6:8] T_peak_count uint16 LE Tran peak (count × 0.005 → in/s) + [6] T_peak_count uint8 Tran peak (count × 0.005 → in/s, max 1.275 in/s) + [7] T_annotation uint8 empirically non-zero on intervals with sub-Hz + or unmeasurable Tran freq; meaning not fully RE'd [8:10] T_halfperiod uint16 LE Tran half-period in samples (freq = 512 / halfp Hz) - [10:12] V_peak_count uint16 LE + [10] V_peak_count uint8 + [11] V_annotation uint8 [12:14] V_halfperiod uint16 LE - [14:16] L_peak_count uint16 LE + [14] L_peak_count uint8 + [15] L_annotation uint8 [16:18] L_halfperiod uint16 LE - [18:20] M_peak_count uint16 LE MicL peak (count → dB via mic_count_to_db) + [18] M_peak_count uint8 MicL peak (count → dB via mic_count_to_db) + [19] M_annotation uint8 [20:22] M_halfperiod uint16 LE MicL half-period in samples (freq = 512 / halfp Hz) [22:24] 0x00 0x00 constant [24:28] 4-byte variable purpose unknown (possibly CRC or timestamp delta) [28:32] 0x1e 0x0a 0x00 0x00 constant block-end signature +NOTE on peak-count width: an earlier interpretation treated the peak +fields as uint16 LE spanning [6:8] / [10:12] / [14:16] / [18:20]. +That happened to be byte-exact against the N844 fixture corpus only +because every annotation byte in those fixtures was zero, making +``uint16 LE == uint8``. Cross-correlating BE9558 (K558) Tran-drift +and BE18003 (T003) Histogram+Continuous events against the BW ASCII +export proved peak is uint8 alone — see test_histogram_codec.py +and docs/histogram_codec_re_status.md. + Block-identification anchor: ``block[22:24] == b"\\x00\\x00"`` AND ``block[28:32] == b"\\x1e\\x0a\\x00\\x00"``. This is the reliable distinguisher from non-block content in the file. @@ -101,30 +115,6 @@ _BLOCK_SIZE = 32 # additional validation that we're looking at a real block. _BLOCK_MARKER = 10 -# Maximum plausible peak-count value. The geophone tops out at 10 in/s -# at Normal range = 2000 counts at the 0.005 in/s per count scale. -# Sensitive range (1.25 in/s FS) tops at ~250. Mic peak counts have -# been observed up to ~400 (≈ 100 dB(L)) and per the protocol doc can -# reach ~813 (140 dB(L)). 2200 covers Normal full-scale plus ~10% -# headroom for quantization edge cases while keeping every physically -# implausible value out of the PVS computation. -# -# Some prod blocks have been observed with peak-count fields whose -# HIGH byte is non-zero (block[7] != 0 etc.) — observed across BE9558 -# and BE18003 units in Histogram-mode events. Reading these as -# uint16 LE produces values like 30981 / 41733 / 62469, which scale -# to physically impossible peaks (150+ in/s). Best guess: an -# undocumented "time-of-peak-within-interval" extension byte the -# device writes in some sub-mode (possibly Histogram+Continuous). -# Until reverse-engineered, blocks exceeding this bound are skipped -# rather than propagating bogus values into PVS computations. -# -# Earlier we tried 4096 — that allowed peak counts up to 4096 × 0.005 -# = 20.48 in/s per channel, which produced 35× inflated PVS sums when -# the extension-byte blocks slipped through. See feat/wire-histogram-codec -# branch history for the rollback. -_MAX_PEAK_COUNT = 2200 - # Geo peak scaling: stored as "count × 0.005 in/s" where 1 count = one # 0.005 in/s display quantum. Equivalent to the waveform codec's # 16-count-unit output (1 unit = 0.005 in/s = 16 ADC counts). @@ -156,23 +146,36 @@ def _decode_block(block: bytes) -> Optional[dict]: """Decode one 32-byte histogram block. Caller must have validated with ``_is_data_block`` first. - Returns ``None`` if any peak field exceeds ``_MAX_PEAK_COUNT`` — - those blocks contain an undocumented extension byte format whose - naive uint16 LE interpretation gives physically impossible peaks. - Skipping the block is safer than propagating bogus values into - PVS computations downstream. + Returns a record with per-channel peak counts (uint8) and + half-periods (uint16 LE). """ - # All 16-bit fields are little-endian unsigned. Peak counts are - # always non-negative; half-periods are always positive when valid. - t_peak, t_halfp, v_peak, v_halfp, l_peak, l_halfp, m_peak, m_halfp = struct.unpack_from( - " _MAX_PEAK_COUNT or v_peak > _MAX_PEAK_COUNT - or l_peak > _MAX_PEAK_COUNT or m_peak > _MAX_PEAK_COUNT): - return None + # Peak counts are uint8 at bytes [6] / [10] / [14] / [18]. The + # adjacent bytes [7] / [11] / [15] / [19] hold an annotation field + # whose meaning isn't fully understood (empirically non-zero in + # intervals with sub-Hz or unmeasurable geo frequencies, mostly + # zero otherwise — see test fixtures from BE9558/BE18003 corpora). + # Crucially, those annotation bytes are NOT the high byte of the + # peak count: cross-correlating against BW's per-interval ASCII + # export proves the peak is uint8 alone. + # + # Reading the peak as uint16 LE (the original interpretation) was + # accidentally correct only because every block in the N844 fixture + # corpus had a zero annotation byte; non-N844 events with non-zero + # annotation bytes decoded to physically impossible peaks (e.g. + # 268 in/s per channel) and produced 35× inflated PVS sums when + # first run against prod data. See histogram_codec_re_status.md. + t_peak = block[6] + v_peak = block[10] + l_peak = block[14] + m_peak = block[18] + t_halfp = block[8] | (block[9] << 8) + v_halfp = block[12] | (block[13] << 8) + l_halfp = block[16] | (block[17] << 8) + m_halfp = block[20] | (block[21] << 8) segment_id = block[1] block_ctr = block[2] | (block[3] << 8) var_meta = bytes(block[24:28]) + annotations = (block[7], block[11], block[15], block[19]) return { "segment_id": segment_id, "block_ctr": block_ctr, @@ -185,6 +188,7 @@ def _decode_block(block: bytes) -> Optional[dict]: "m_peak": m_peak, "m_halfp": m_halfp, "meta_var": var_meta, + "annotations": annotations, } @@ -192,10 +196,15 @@ def walk_body(body: bytes) -> List[dict]: """Walk the body and return one dict per histogram interval. Iterates 32-byte strides from offset 0. Yields a decoded record - for every block that passes ``_is_data_block`` validation AND has - plausible peak values (``_decode_block`` returns None for blocks - with out-of-bound peaks). Stops when the remaining bytes are too - short to form a complete block. + for every block that passes ``_is_data_block`` validation. Stops + when the remaining bytes are too short to form a complete block. + + In Histogram+Continuous mode the body interleaves data blocks with + other 32-byte content (likely continuous-mode waveform blocks) that + fail the data-block validation; the walker naturally skips them + without losing 32-byte alignment. Use ``block_ctr`` from each + returned record to map back to the original interval index — the + record list is sparse when other block types are interleaved. """ records: List[dict] = [] for off in range(0, len(body) - _BLOCK_SIZE + 1, _BLOCK_SIZE): diff --git a/tests/test_histogram_codec.py b/tests/test_histogram_codec.py index 8e521f3..6a42e27 100644 --- a/tests/test_histogram_codec.py +++ b/tests/test_histogram_codec.py @@ -335,3 +335,51 @@ def test_geo_count_to_ins_scale(): assert geo_count_to_ins(1) == pytest.approx(0.005) assert geo_count_to_ins(10) == pytest.approx(0.050) assert geo_count_to_ins(0) == 0.0 + + +# ── Regression: peak is uint8 byte[N], NOT uint16 LE byte[N:N+2] ──────────── +# +# Block taken verbatim from K558LKZU.RE0H (BE9558) interval 12 — a real +# field event where the Tran channel had developed a DC offset and was +# producing sub-Hz drift content the device couldn't characterize. +# The annotation byte at [7] = 0xd2 is non-zero in that case. The +# legacy codec read [6:8] as uint16 LE, producing T_peak = 53763 → +# 268 in/s — physically impossible and 35× too high for the actual +# 0.015 in/s value (T_lo = 3 alone gives the correct count). +# Verified against the paired BW ASCII export. +_K558_INTERVAL_12_BLOCK = bytes.fromhex( + "00 00 0c 01 0a 00 03 d2 45 00 02 00 02 00 02 00" + "02 00 10 00 06 00 00 00 0e 91 2f 00 1e 0a 00 00".replace(" ", "") +) + + +def test_extension_byte_does_not_inflate_peak(): + """The annotation byte at [7]/[11]/[15]/[19] must NOT contribute to + the peak count. Decoded T_peak must be 3 (uint8 byte[6]), NOT + 53763 (uint16 LE byte[6:8]).""" + body = _K558_INTERVAL_12_BLOCK + records = decode_histogram_body_full(body) + assert records is not None + assert len(records) == 1 + r = records[0] + assert r["t_peak"] == 3, f"T_peak should be 3 (uint8), got {r['t_peak']}" + assert r["v_peak"] == 2 + assert r["l_peak"] == 2 + assert r["m_peak"] == 16 + # Half-periods unchanged — still uint16 LE. + assert r["t_halfp"] == 0x0045 # 69 → 7.4 Hz + assert r["m_halfp"] == 6 # → 85.3 Hz + # Annotation byte is preserved (for future RE) but does not affect peak. + assert r["annotations"] == (0xd2, 0x00, 0x00, 0x00) + + +def test_extension_byte_decoded_to_correct_in_s(): + """End-to-end: the channel-grouped output for the K558 ext block + should give T = 3 counts = 0.015 in/s, not 53763 counts = 268 in/s.""" + channels = decode_histogram_body(_K558_INTERVAL_12_BLOCK) + assert channels is not None + assert channels["Tran"] == [3] + assert geo_count_to_ins(channels["Tran"][0]) == pytest.approx(0.015) + assert channels["Vert"] == [2] + assert channels["Long"] == [2] + assert channels["MicL"] == [16]