feat(import): parse paired BW ASCII reports on /db/import/blastware_file

Blastware's ACH writes a per-event ASCII report (.TXT) alongside each
event binary, containing the rich derived per-channel fields BW
computes (PPV, ZC Freq, Time of Peak, Peak Acceleration, Peak
Displacement, Peak Vector Sum + time, sensor self-check Pass/Fail,
monitor-log timestamps).  None of this lives in the BW binary itself.

When the watcher daemon forwards both files to /db/import/blastware_file
in one multipart POST, we now:

  - Pair binaries with their .TXT partners by filename match
  - Parse the report into a structured BwAsciiReport
  - Land the rich fields in a new top-level `bw_report` block of the
    sidecar JSON
  - Overlay the report's peaks/project_info/timestamp/sample_rate/
    record_time/total_samples/pretrig_samples onto the canonical
    sidecar fields (the report values are device-authoritative; the
    BW-binary STRT-derived values had bugs like reading the 0x46
    record-type marker as rectime)

This unblocks the monthly-summary review workflow — events become
sortable/filterable by peak, location, project, etc. — without
depending on the still-undecoded waveform body codec.
This commit is contained in:
2026-05-08 23:56:43 +00:00
parent 510cec8395
commit cdfe4ad3c8
6 changed files with 1097 additions and 24 deletions
+189 -14
View File
@@ -26,6 +26,12 @@ from typing import Optional, Union
from .models import Event, PeakValues, ProjectInfo, Timestamp
from . import blastware_file as _bw # avoid circular reference at module load
from .bw_ascii_report import BwAsciiReport
# Reference pressure for dB(L) → psi conversion (20 µPa expressed in psi).
# Same constant as sfm/sfm_webapp.html so server-side and browser-side
# conversions agree.
_DBL_REF_PSI = 2.9e-9
log = logging.getLogger(__name__)
@@ -94,6 +100,101 @@ def _peak_values_to_dict(pv: Optional[PeakValues]) -> dict:
}
def _bw_report_to_dict(report: BwAsciiReport) -> dict:
"""Project a parsed BW ASCII report into the sidecar's `bw_report` block.
All fields are rendered as plain JSON-compatible types (no datetime
objects). Channels are uniformly lowercased for stable JSON keys.
"""
def _ch(ch_name: str) -> dict:
cs = report.channels.get(ch_name)
if cs is None:
return {}
out = {
"ppv_ips": cs.ppv_ips,
"zc_freq_hz": cs.zc_freq_hz,
"time_of_peak_s": cs.time_of_peak_s,
"peak_accel_g": cs.peak_accel_g,
"peak_disp_in": cs.peak_disp_in,
}
# Drop all-None entries — keeps the JSON tidy for partial reports.
return {k: v for k, v in out.items() if v is not None}
def _sc(ch_name: str) -> dict:
sc = report.sensor_check.get(ch_name)
if sc is None:
return {}
out = {
"freq_hz": sc.test_freq_hz,
"ratio": sc.test_ratio,
"amplitude_mv": sc.test_amplitude_mv,
"result": sc.test_results,
}
return {k: v for k, v in out.items() if v is not None}
monitor_log = []
for entry in report.monitor_log:
e = {
"start": entry.start_time.isoformat() if entry.start_time else None,
"stop": entry.stop_time.isoformat() if entry.stop_time else None,
"description": entry.description,
}
monitor_log.append({k: v for k, v in e.items() if v is not None})
return {
"available": True,
"event_type": report.event_type,
"version": report.version,
"trigger": {
"channel": report.trigger_channel,
"geo_level_ips": report.geo_trigger_level_ips,
},
"recording": {
"sample_rate_sps": report.sample_rate_sps,
"record_time_s": report.record_time_s,
"pretrig_s": report.pretrig_s,
"stop_mode": report.record_stop_mode,
"geo_range_ips": report.geo_range_ips,
"units": report.units,
},
"device": {
"battery_volts": report.battery_volts,
"calibration_date": report.calibration_date.isoformat() if report.calibration_date else None,
"calibration_by": report.calibration_by,
},
"peaks": {
"tran": _ch("Tran"),
"vert": _ch("Vert"),
"long": _ch("Long"),
"vector_sum": {
"ips": report.peak_vector_sum_ips,
"time_s": report.peak_vector_sum_time_s,
},
},
"mic": {
"weighting": report.mic.weighting,
"pspl_dbl": report.mic.pspl_dbl,
"zc_freq_hz": report.mic.zc_freq_hz,
"time_of_peak_s": report.mic.time_of_peak_s,
},
"sensor_check": {
"tran": _sc("Tran"),
"vert": _sc("Vert"),
"long": _sc("Long"),
"mic": _sc("MicL"),
},
"monitor_log": monitor_log,
"pc_sw_version": report.pc_sw_version,
}
def _dbl_to_psi(pspl_dbl: float) -> float:
"""Convert dB(L) sound pressure level back to psi. Uses the same
20 µPa reference (= 2.9e-9 psi) as the webapp so server-side and
browser-side conversions agree."""
return _DBL_REF_PSI * (10.0 ** (pspl_dbl / 20.0))
def _project_info_to_dict(pi: Optional[ProjectInfo]) -> dict:
if pi is None:
return {
@@ -123,35 +224,104 @@ def event_to_sidecar_dict(
captured_at: Optional[datetime.datetime] = None,
review: Optional[dict] = None,
extensions: Optional[dict] = None,
bw_report: Optional[BwAsciiReport] = None,
) -> dict:
"""
Build a v1 sidecar dict from an Event + the surrounding metadata.
Pure helper — no file I/O. Callers stitch the result into a sidecar
via `write_sidecar()` (or POST it back via the PATCH endpoint).
When *bw_report* is supplied (e.g. by the ACH-forwarded import path
where Blastware writes a per-event ASCII report alongside the binary),
its decoded fields are folded into the sidecar:
- A new top-level ``bw_report`` block carries the rich derived
per-channel stats (Peak Acceleration, Peak Displacement, ZC Freq,
Time of Peak), the Peak Vector Sum + time, the per-channel sensor
self-check results, and monitor-log timestamps.
- ``peak_values`` is overlaid from the report (the report's PPV/PVS
values are computed by the device firmware and are authoritative;
anything ``read_blastware_file()`` derived from samples is
approximate at best until the body codec is decoded).
- ``project_info`` is overlaid from the report when the report
supplies a non-empty value (the report mirrors the device's
compliance config, which is what BW shows in its event report).
- ``event.timestamp`` is overlaid from the report's Event Date +
Event Time (BW's report timestamps are second-resolution and
match the binary's footer; we prefer the report value because
the BW-binary footer timestamp can drift on some firmware).
"""
if source_kind not in {"sfm-live", "sfm-ach", "bw-import"}:
raise ValueError(f"unknown source_kind: {source_kind!r}")
captured_at = captured_at or datetime.datetime.utcnow()
return {
# ── Overlay event fields from the report when present ───────────────────
timestamp_iso = _ts_iso(event.timestamp)
if bw_report and bw_report.event_datetime:
timestamp_iso = bw_report.event_datetime.isoformat()
# Build peak_values, optionally overlaid from the report. The report
# stores Mic peak as PSPL (dB(L)); we convert to psi to match the
# existing peak_values.mic_psi field.
peak_dict = _peak_values_to_dict(event.peak_values)
if bw_report:
ch = bw_report.channels
if (t := ch.get("Tran")) and t.ppv_ips is not None: peak_dict["transverse"] = t.ppv_ips
if (v := ch.get("Vert")) and v.ppv_ips is not None: peak_dict["vertical"] = v.ppv_ips
if (l := ch.get("Long")) and l.ppv_ips is not None: peak_dict["longitudinal"] = l.ppv_ips
if bw_report.peak_vector_sum_ips is not None:
peak_dict["vector_sum"] = bw_report.peak_vector_sum_ips
if bw_report.mic.pspl_dbl is not None and bw_report.mic.pspl_dbl > 0:
peak_dict["mic_psi"] = _dbl_to_psi(bw_report.mic.pspl_dbl)
# Project info: overlay from report (the report mirrors the
# session-start compliance config that BW renders in event reports).
proj_dict = _project_info_to_dict(event.project_info)
if bw_report:
if bw_report.project: proj_dict["project"] = bw_report.project
if bw_report.client: proj_dict["client"] = bw_report.client
if bw_report.operator: proj_dict["operator"] = bw_report.operator
if bw_report.sensor_location: proj_dict["sensor_location"] = bw_report.sensor_location
# Event-block fields: overlay from report where available.
event_block = {
"serial": serial,
"timestamp": timestamp_iso,
"waveform_key": event._waveform_key.hex() if event._waveform_key else None,
"record_type": event.record_type,
"sample_rate": event.sample_rate,
"rectime_seconds": event.rectime_seconds,
"total_samples": event.total_samples,
"pretrig_samples": event.pretrig_samples,
}
if bw_report:
# Report values are authoritative — they're the user-configured
# values BW reads back, not STRT-derived guesses. In particular
# `event.rectime_seconds` from `read_blastware_file()` reads
# STRT[18] which is actually the `0x46` record-type marker (= 70)
# rather than the user's Record Time setting. Always overwrite.
if bw_report.sample_rate_sps:
event_block["sample_rate"] = bw_report.sample_rate_sps
if bw_report.record_time_s is not None:
event_block["rectime_seconds"] = bw_report.record_time_s
# Derive total_samples + pretrig_samples per channel from the
# report's sample_rate × times. These match the row count of
# the report's sample table (verified: event-c reports 1024 sps
# × (1.0 + 0.25) = 1280 rows).
if (sr := bw_report.sample_rate_sps) and bw_report.record_time_s is not None:
pretrig_s = abs(bw_report.pretrig_s) if bw_report.pretrig_s is not None else 0.0
event_block["total_samples"] = int(round(sr * (bw_report.record_time_s + pretrig_s)))
event_block["pretrig_samples"] = int(round(sr * pretrig_s))
out = {
"schema_version": SCHEMA_VERSION,
"kind": SIDECAR_KIND,
"event": {
"serial": serial,
"timestamp": _ts_iso(event.timestamp),
"waveform_key": event._waveform_key.hex() if event._waveform_key else None,
"record_type": event.record_type,
"sample_rate": event.sample_rate,
"rectime_seconds": event.rectime_seconds,
"total_samples": event.total_samples,
"pretrig_samples": event.pretrig_samples,
},
"peak_values": _peak_values_to_dict(event.peak_values),
"project_info": _project_info_to_dict(event.project_info),
"event": event_block,
"peak_values": peak_dict,
"project_info": proj_dict,
"blastware": {
"filename": blastware_filename,
@@ -177,6 +347,11 @@ def event_to_sidecar_dict(
"extensions": extensions or {},
}
if bw_report:
out["bw_report"] = _bw_report_to_dict(bw_report)
return out
# ── Sidecar IO ────────────────────────────────────────────────────────────────