serversdownandClaude Opus 4.8
75ac610c61
A real trigger is recorded twice — as a triggered waveform (stamped at the trigger instant) and inside the scheduled histogram whose interval contains it (stamped at the 7am/7pm interval start). The two twins routinely differ by HOURS, so the old ±5-minute window in find_twins silently missed them — which broke review propagation (flagging one twin left its twin unflagged). Twins are now matched by: same serial + identical peak_vector_sum + OPPOSITE record type + the waveform's timestamp falling within the histogram's interval (bounded by the next same-serial histogram). Matching keys off record timestamps (not call-in/received times, which drift with field connectivity). window_seconds is retained but ignored. Rewrote test_find_twins + test_twin_propagation for the new contract (incl. the 75-min-apart UM12947 case, cross-type exclusion, containing-interval selection, open-ended latest interval). Full suite: 264 passed; the 16 failures are pre-existing (missing gitignored fixtures + a v0.26.0 codec case), unchanged from baseline. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01YDXjZCr4RqT2U3QvMDhgzf
72 lines
3.2 KiB
Python
72 lines
3.2 KiB
Python
import sqlite3
|
|
from sfm.database import SeismoDb
|
|
from minimateplus.models import Event, Timestamp
|
|
|
|
|
|
def _ins(db, key, serial, pvs, ts, record_type="Waveform"):
|
|
ev = Event(index=0)
|
|
ev._waveform_key = bytes.fromhex(key)
|
|
ev.timestamp = ts
|
|
db.insert_events([ev], serial=serial)
|
|
row = [r for r in db.query_events(serial=serial) if r["waveform_key"] == key][0]
|
|
with sqlite3.connect(db.db_path) as c:
|
|
c.execute("UPDATE events SET peak_vector_sum=?, record_type=? WHERE id=?",
|
|
(pvs, record_type, row["id"]))
|
|
return row["id"]
|
|
|
|
|
|
def _ts(hour, minute, second=0, day=25):
|
|
return Timestamp(raw=b"", flag=0x10, year=2026, unknown_byte=0, month=2, day=day,
|
|
hour=hour, minute=minute, second=second)
|
|
|
|
|
|
def test_histogram_and_waveform_twin_across_hours(tmp_path):
|
|
# The real UM12947 case: histogram stamped at its 7pm interval start, the
|
|
# triggered waveform 75 min later — same serial + identical PVS. The old
|
|
# ±5-min window missed this; interval matching catches it, both directions.
|
|
db = SeismoDb(tmp_path / "s.db")
|
|
hist_pm = _ins(db, "01110001", "BE1", 0.4763, _ts(19, 31, 17), "Histogram")
|
|
wave = _ins(db, "01110002", "BE1", 0.4763, _ts(20, 46, 44), "Waveform")
|
|
_ins(db, "01110003", "BE1", 0.0100, _ts(7, 0, 0, day=26), "Histogram") # bounds the interval
|
|
assert {r["id"] for r in db.find_twins(hist_pm)} == {wave}
|
|
assert {r["id"] for r in db.find_twins(wave)} == {hist_pm}
|
|
|
|
|
|
def test_same_type_not_twinned(tmp_path):
|
|
# Two waveforms, same serial + PVS, seconds apart → NOT twins (cross-type only).
|
|
db = SeismoDb(tmp_path / "s.db")
|
|
a = _ins(db, "01110001", "BE1", 0.4763, _ts(20, 19, 5), "Waveform")
|
|
_ins(db, "01110002", "BE1", 0.4763, _ts(20, 19, 45), "Waveform")
|
|
assert db.find_twins(a) == []
|
|
|
|
|
|
def test_waveform_matches_only_the_containing_interval(tmp_path):
|
|
# Two overnight intervals with the same PVS; a waveform in the SECOND interval
|
|
# must twin with that histogram, never the first — even though PVS matches both.
|
|
db = SeismoDb(tmp_path / "s.db")
|
|
h1 = _ins(db, "01110001", "BE1", 0.4763, _ts(19, 0, 0, day=25), "Histogram")
|
|
h2 = _ins(db, "01110002", "BE1", 0.4763, _ts(7, 0, 0, day=26), "Histogram")
|
|
w = _ins(db, "01110003", "BE1", 0.4763, _ts(8, 0, 0, day=26), "Waveform")
|
|
assert {r["id"] for r in db.find_twins(w)} == {h2}
|
|
assert w not in {r["id"] for r in db.find_twins(h1)}
|
|
|
|
|
|
def test_different_pvs_not_twinned(tmp_path):
|
|
db = SeismoDb(tmp_path / "s.db")
|
|
h = _ins(db, "01110001", "BE1", 0.4763, _ts(19, 0, 0), "Histogram")
|
|
_ins(db, "01110002", "BE1", 0.9999, _ts(20, 0, 0), "Waveform") # different PVS
|
|
assert db.find_twins(h) == []
|
|
|
|
|
|
def test_open_ended_latest_interval(tmp_path):
|
|
# A waveform after the latest histogram (nothing bounds the interval) still twins.
|
|
db = SeismoDb(tmp_path / "s.db")
|
|
h = _ins(db, "01110001", "BE1", 0.4763, _ts(19, 0, 0), "Histogram")
|
|
w = _ins(db, "01110002", "BE1", 0.4763, _ts(23, 30, 0), "Waveform")
|
|
assert {r["id"] for r in db.find_twins(h)} == {w}
|
|
|
|
|
|
def test_missing_fields_returns_empty(tmp_path):
|
|
db = SeismoDb(tmp_path / "s.db")
|
|
assert db.find_twins("nonexistent-id") == []
|