fix(idf_waveforms): _find_waveform_body_offset() — scans every 00 02 00 magic past offset 0x0E00, runs decode_waveform_v2 on each candidate, picks the one that returns the most samples. Validated on 483 prod IDFW files: 0 preamble-only events (was ~50%), 355/483 fully decode, 126/483 partial (BW codec walker-stops-early on loud events — known issue).

IDFH now synthesises a 1-sample-per-interval array from the binary intervals and writes an .h5 so the existing renderer works unchanged. Each "sample" is the per-interval peak ADC count → h5_value = count × geo_fs/32768 yields the right bar height.
This commit is contained in:
2026-05-31 20:51:09 +00:00
parent 43f440812a
commit b2c565f217
3 changed files with 180 additions and 12 deletions
+91
View File
@@ -0,0 +1,91 @@
"""Re-ingest a prod IDFW + IDFH via the patched save_imported_idf and
render both PDFs to confirm charts have data."""
from __future__ import annotations
import sys
import json
import datetime
import tempfile
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
from sfm.waveform_store import WaveformStore
from sfm import report_pdf
import h5py
class FakeDb:
def __init__(self, event):
self.event = event
def get_event(self, _id):
return self.event
def to_ts_iso(ts):
if ts is None:
return None
try:
return datetime.datetime(ts.year, ts.month, ts.day, ts.hour, ts.minute, ts.second).isoformat()
except Exception:
return None
def render_case(idf_path: Path, serial: str, out_pdf: Path, h5_summary: bool = True):
with tempfile.TemporaryDirectory() as td:
store = WaveformStore(Path(td))
ev, rec = store.save_imported_idf(
idf_path.read_bytes(),
idf_path,
idf_report_text=None, # production worst case: no .txt
)
print(f"=== {idf_path.name} ===")
print(f" h5: {rec['hdf5_filename']}, sidecar: {rec['sidecar_filename']}")
h5p = Path(td) / serial / f"{idf_path.name}.h5"
if h5p.exists() and h5_summary:
with h5py.File(h5p) as h:
for ch in ("Tran", "Vert", "Long", "MicL"):
ds = h.get(f"samples/{ch}")
if ds is not None:
n = ds.shape[0]
mx = float(abs(ds[...]).max()) if n else 0
print(f" samples/{ch}: n={n} max_abs={mx:.5f}")
record_type = "Histogram" if idf_path.suffix.upper() == ".IDFH" else "Waveform"
fake_row = {
"serial": serial,
"blastware_filename": rec["filename"],
"record_type": record_type,
"timestamp": to_ts_iso(ev.timestamp),
"sample_rate": ev.sample_rate,
"project": ev.project_info.project if ev.project_info else None,
"client": ev.project_info.client if ev.project_info else None,
"operator": ev.project_info.operator if ev.project_info else None,
"sensor_location": ev.project_info.sensor_location if ev.project_info else None,
"created_at": None,
}
rd = report_pdf.gather_report_data(FakeDb(fake_row), store, event_id="test-1")
print(f" ReportData: channels={ {k: len(v) for k,v in rd.channels.items()} }")
if rd.is_histogram:
print(f" histogram n_intervals={rd.histogram_n_intervals} interval_size={rd.histogram_interval_size}")
pdf = report_pdf.render_event_report_pdf(rd)
out_pdf.write_bytes(pdf)
print(f" PDF: {out_pdf} ({len(pdf)} bytes)")
def main():
out_dir = Path("/tmp/thor_render_test"); out_dir.mkdir(exist_ok=True)
cases = [
# IDFW that decoded to preamble-only under the old codec
("/home/serversdown/seismo-relay-prod-snap/waveforms/UM6047/UM6047_20250804154137.IDFW", "UM6047"),
# IDFW that worked under the old codec (validates no regression)
("/home/serversdown/seismo-relay-prod-snap/waveforms/UM6047/UM6047_20250804104450.IDFW", "UM6047"),
# IDFH histogram
("/home/serversdown/seismo-relay-prod-snap/waveforms/UM6047/UM6047_20250804190047.IDFH", "UM6047"),
]
for path, serial in cases:
render_case(Path(path), serial, out_dir / f"{Path(path).name}.pdf")
if __name__ == "__main__":
main()