Files
aimsight-data/extraction/pump_diff.py
T
maximeandClaude Opus 5.5 ca366c150e Runs in data_diff/<SERIAL>/runs/<run>/: new_run.sh creates one, run_config.sh <SERIAL> <run> computes it
- The user's layout: the station's root holds only what is the same for every run (images_diff/, images/, metrics/,
  weather/); each run's folder holds what depends on it: config.yaml, displacement/, camera/, targets.csv,
  patterns.json.
- processing/new_run.sh <SERIAL> <run>: config.yaml of a new, empty run, the cloud's processing written in full (the
  patterns of sensors.json, the camera, optical's current commit); never over an existing one.
- processing/run_config.sh <SERIAL> <run>: reads the run's config.yaml (patterns, camera, emulator.version, checked
  against $OPTICAL's commit and local changes) and writes its displacement/, camera/, targets.csv (from its patterns)
  and patterns.json (the patterns as given to the emulator). No configs/, no runs/<name>/ outside data_diff/.
- pump_diff no longer writes targets.csv: it depends on the run.

JUNGFRAU run01 (2026-09-01, 2026-10-12..16, 525 images, 18 s): 7875 rows as data/, the same rejections, corr within
0.034 px; a run created by new_run.sh and run as is gives run01 exactly.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-19 10:52:46 +01:00

308 lines
18 KiB
Python

"""Pumps the differential images (OPTICAL_SHIFT-DIFF) of stations from the AIMsight platform, full size, with what is
needed to measure them again: every pattern of the unit (archived ones included) and the unit's properties. READ-ONLY.
Never touches data/ nor pump.py's pumping; design: docs/superpowers/specs/2026-11-19-pump-diff-design.md.
Run through extraction/pump_diff.sh, under WSL, from anywhere (see README.md):
extraction/pump_diff.sh --from 2026-09-01 --to 2026-09-08 JUNGFRAU a range (its history starts here)
extraction/pump_diff.sh JUNGFRAU from its last indexed day up to now
extraction/pump_diff.sh the same for every station of data_diff/
Output (default: the repository's data_diff/, next to this folder), the tree of data/ so that the other repositories
read it the same way (docs/superpowers/specs/2026-11-19-configurations-design.md):
<STATION>/images_diff/<YYYYMMDD>T<HHMM>Z_<measurement_id>.png the S3 object as is, named as in data/
<STATION>/images_diff/index/<STATION>_diff_<YYYYMMDD>.csv every measurement of the day in the database:
measurement_id, time_utc (exact), measurement_group_id, file (empty without image), status (ok; no_uuid: never
reached S3; s3_missing: S3 returned nothing), properties (the measurement's JSON)
<STATION>/images_diff/sensors.json every sensor of the unit: id, name, type, time_utc, properties [{name, value,
time_utc, status}] (every property row as stored), rewritten at each run
<STATION>/images_diff/unit.json the acquisition unit: id, serial_number, product_number, properties
(under images_diff/, the tools of aimsight-tools do not see them: data.find_files skips that folder)
<STATION>/metrics/, images/ (IRON, one per --every minutes), weather/: as pump.py and weather.py write them into
data/, with their own functions. Not targets.csv: it depends on the run (its patterns), each run writes its own
(processing/run_config.py)
Resumable: a day whose index exists and is before the last indexed day is not read again; the last indexed day and
the later ones are (pumped while running, a day is incomplete); an image on disk is never downloaded again. An index
is written after its day's metrics, IRON and DIFF images, every DIFF file through a temporary one: an indexed day is
complete; a day whose metrics failed gets no index. Without --from, a station with nothing indexed is skipped (its
history starts only on an explicit --from). Stops before a day when the disk has less than --min-free-gb left.
Same reads as pump.py (measurement, acquisition_unit; the copied queries of the app, branch `explo`), plus the
`property` rows of the sensors and of the unit (AcquisitionUnit.list_sensors, Sensor.properties of
app/aimsight_database.py). Variables read (names only, none is printed): AIMSIGHT_DATABASE_USER / _PSWD / _TURL /
_NAME / _PORT, AIMSIGHT_S3_URL / _ACCESS_KEY / _SECRET_KEY / _BUCKET.
"""
import argparse
import csv
import io
import json
import os
import shutil
import sys
import time
from collections import Counter
from datetime import date, datetime, timedelta, timezone
from pathlib import Path
UTC = timezone.utc
MTYPE = "OPTICAL_SHIFT-DIFF"
INDEX = ["measurement_id", "time_utc", "measurement_group_id", "file", "status", "properties"]
def write_atomic(path, data):
"""A file is either complete or absent: a run stopped in the middle leaves nothing that looks done."""
path.parent.mkdir(parents=True, exist_ok=True)
tmp = path.with_name(path.name + ".tmp")
tmp.write_bytes(data)
os.replace(tmp, path)
def indexed_days(folder):
return {datetime.strptime(p.stem.rsplit("_", 1)[1], "%Y%m%d").date()
for p in (folder / "images_diff" / "index").glob(f"{folder.name}_diff_*.csv")}
def days_to_pump(indexed, start, end):
"""The days of [start, end) to read: the missing ones, and from the last indexed day on (perhaps incomplete).
Without start: from the last indexed day; None when nothing is indexed."""
last = max(indexed, default=None)
if start is None:
if last is None:
return None
start = last
days = (start + timedelta(days=k) for k in range((end - start).days))
return [d for d in days if last is None or d not in indexed or d >= last]
def pump_day(rows, client, bucket, ext, folder, station, day):
"""The images of one day's measurements (rows: id, time_utc, measurement_group_id, measurement_uuid, properties),
then its index. Returns the counts per status, plus the new images and their bytes."""
c, index = Counter(), []
for m in rows:
t = m.time_utc.astimezone(UTC)
name, status = f"{t:%Y%m%dT%H%M}Z_{m.id}.{ext}", "ok"
path = folder / "images_diff" / name
if m.measurement_uuid is None: # the image never reached S3 (unfinished multipart upload)
name, status = "", "no_uuid"
elif not path.exists():
try:
data = client.get_object(Bucket=bucket, Key=m.measurement_uuid)["Body"].read()
except Exception: # like the app's get_measurement_payload: S3 not answering, the image is missing
data = None
if data:
write_atomic(path, data)
c["new"], c["bytes"] = c["new"] + 1, c["bytes"] + len(data)
else:
name, status = "", "s3_missing"
c[status] += 1
index.append([m.id, t.isoformat(), "" if m.measurement_group_id is None else m.measurement_group_id, name,
status, "" if m.properties is None else json.dumps(m.properties, sort_keys=True)])
out = io.StringIO()
w = csv.writer(out, lineterminator="\n")
w.writerow(INDEX)
w.writerows(index)
write_atomic(folder / "images_diff" / "index" / f"{station}_diff_{day:%Y%m%d}.csv", out.getvalue().encode())
return c
def prop(name, value, t, status):
return {"name": name, "value": value, "time_utc": t.isoformat(), "status": status}
def sensors_json(conn, unit):
"""Every sensor of the unit, any type, archived included (`archive` is one of their properties), with every
property row: a pattern redrawn on the platform is a new sensor, the old one stays."""
from sqlalchemy import text
rows = conn.execute(text("""
SELECT s.id, s.name, s.type, s.time_utc, dt.name AS prop, p.value, p.time_utc AS ptime, p.status
FROM sensor s LEFT JOIN property p ON p.sensor_id = s.id LEFT JOIN datatype dt ON dt.id = p.datatype_id
WHERE s.acquisition_unit_id = :au ORDER BY s.id, dt.name, p.time_utc"""), {"au": unit}).all()
sensors = {}
for r in rows:
s = sensors.setdefault(r.id, {"id": r.id, "name": r.name, "type": r.type, "time_utc": r.time_utc.isoformat(),
"properties": []})
if r.prop is not None:
s["properties"].append(prop(r.prop, r.value, r.ptime, r.status))
return list(sensors.values())
def unit_json(conn, unit):
"""The acquisition unit and its own property rows (focal_distance, pixel_size, algorithm...), not its sensors'."""
from sqlalchemy import text
u = conn.execute(text("SELECT id, serial_number, product_number FROM acquisition_unit WHERE id = :au"),
{"au": unit}).one()
rows = conn.execute(text("""
SELECT dt.name, p.value, p.time_utc, p.status FROM property p JOIN datatype dt ON dt.id = p.datatype_id
WHERE p.acquisition_unit_id = :au AND p.sensor_id IS NULL ORDER BY dt.name, p.time_utc"""), {"au": unit}).all()
return {"id": u.id, "serial_number": u.serial_number, "product_number": u.product_number,
"properties": [prop(*r) for r in rows]}
def to_json(obj):
return json.dumps(obj, indent=1, ensure_ascii=False, default=str).encode()
def main():
p = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
p.add_argument("stations", nargs="*", help="serial number of the system, as in the URL of the System page; "
"none: the stations already in --out")
p.add_argument("--from", dest="start", help="first UTC day, YYYY-MM-DD; without: the last indexed day of each "
"station (a station with nothing indexed is skipped)")
p.add_argument("--to", dest="end", help="last UTC day, excluded, YYYY-MM-DD; without: up to now")
p.add_argument("--delay", type=int, default=60, help="maximum duration of a query, in s (default 60: database "
"shared with production)")
p.add_argument("--every", type=int, default=60, help="IRON images: one per slot of N minutes, 0 = all (default 60, "
"as pump.sh)")
p.add_argument("--min-free-gb", type=float, default=50, help="stop before a day when less is free (default 50)")
p.add_argument("--out", type=Path, default=Path(__file__).resolve().parent.parent / "data_diff")
a = p.parse_args()
import boto3
from sqlalchemy import create_engine, text
from sqlalchemy.engine import URL
from pump import DB_NAMES, acquisition_unit, pump_images, pump_metrics, root_cause
tomorrow = datetime.now(UTC).date() + timedelta(days=1)
start = datetime.strptime(a.start, "%Y-%m-%d").date() if a.start else None
end = min(datetime.strptime(a.end, "%Y-%m-%d").date(), tomorrow) if a.end else tomorrow
stations = a.stations or sorted(f.name for f in a.out.glob("*") if f.is_dir())
if not stations:
sys.exit(f"No station: name one, with --from (nothing in {a.out} yet)")
missing = [n for n in DB_NAMES if not os.environ.get(n)]
if missing:
sys.exit(f"Missing variables (names only): {', '.join(missing)}")
# the engine and the S3 client of pump.py's main
url = URL.create("postgresql+psycopg2", username=os.environ["AIMSIGHT_DATABASE_USER"],
password=os.environ["AIMSIGHT_DATABASE_PSWD"], host=os.environ["AIMSIGHT_DATABASE_TURL"],
port=int(os.environ.get("AIMSIGHT_DATABASE_PORT", "5432")),
database=os.environ["AIMSIGHT_DATABASE_NAME"])
engine = create_engine(url, connect_args={
"options": f"-c timezone=utc -c default_transaction_read_only=on -c statement_timeout={a.delay}s"})
client = boto3.client("s3", endpoint_url=os.environ.get("AIMSIGHT_S3_URL", "http://s3:3900"),
aws_access_key_id=os.environ.get("AIMSIGHT_S3_ACCESS_KEY", ""),
aws_secret_access_key=os.environ.get("AIMSIGHT_S3_SECRET_KEY", ""),
region_name="garage", use_ssl=False)
bucket = os.environ.get("AIMSIGHT_S3_BUCKET", "measurements-assets")
try:
with engine.connect() as conn:
mt = conn.execute(text("SELECT id, extension FROM measurement_type WHERE name = :n"), {"n": MTYPE}).first()
conn.rollback()
if mt is None:
sys.exit(f"Unknown measurement type {MTYPE}")
for station in stations:
system_id = conn.execute(text("SELECT id FROM system WHERE serial_number = :s"),
{"s": station}).scalar()
unit = system_id and acquisition_unit(conn, system_id)
conn.rollback()
if not unit:
print(f"{station}: " + ("unknown system" if system_id is None else "no recognised acquisition unit"))
continue
folder = a.out / station
days = days_to_pump(indexed_days(folder), start, end)
if days is None:
print(f"{station}: nothing indexed yet, its history starts with --from")
continue
try: # what the database holds, so that an empty day is explained (LENZSPITZE: none after 2026-10-13)
first, last = (conn.execute(text(
"SELECT time_utc FROM measurement WHERE acquisition_unit_id = :au AND measurement_type_id = :mt "
f"ORDER BY time_utc {o} LIMIT 1"), {"au": unit, "mt": mt.id}).scalar() for o in ("ASC", "DESC"))
print(f"{station}: differential images in the database from {first:%Y-%m-%d} to {last:%Y-%m-%d}"
if first else f"{station}: no differential image in the database")
sens = sensors_json(conn, unit)
write_atomic(folder / "images_diff" / "sensors.json", to_json(sens))
write_atomic(folder / "images_diff" / "unit.json", to_json(unit_json(conn, unit)))
except Exception as e: # the next run writes them
print(f"{station} images range, sensors.json, unit.json: failed ({root_cause(e)}), run again")
finally:
conn.rollback()
print(f"{station}: {len(days)} days, from {days[0] if days else '-'} to {days[-1] if days else '-'}")
for day in days:
free = shutil.disk_usage(a.out).free / 1e9
if free < a.min_free_gb:
sys.exit(f"Stopped before {station} {day}: {free:.0f} GB free, under --min-free-gb "
f"{a.min_free_gb:g}")
nxt = day + timedelta(days=1)
try: # as pump.py into data/; a day whose metrics or IRON images failed stays open (no index)
if not pump_metrics(conn, system_id, station, day, nxt, a.out, True):
print(f"{station} {day}: left open (metrics failed), run again")
continue
pump_images(conn, (client, bucket), unit, station, day, nxt, "images", a.every, a.out)
except Exception as e:
print(f"{station} {day}: left open ({root_cause(e)}), run again")
continue
finally:
conn.rollback()
a0 = datetime.combine(day, datetime.min.time(), UTC)
try:
rows = conn.execute(text(
"SELECT id, time_utc, measurement_group_id, measurement_uuid, properties FROM measurement "
"WHERE acquisition_unit_id = :au AND measurement_type_id = :mt AND time_utc >= :a "
"AND time_utc < :b ORDER BY time_utc"),
{"au": unit, "mt": mt.id, "a": a0, "b": a0 + timedelta(days=1)}).all()
except Exception as e: # no index for the day: the next run reads it again
print(f"{station} {day}: failed ({root_cause(e)}), run again")
continue
finally:
conn.rollback()
c = pump_day(rows, client, bucket, mt.extension, folder, station, day)
print(f"{station} {day}: {c['new']} new images, {c['bytes'] / 1e6:.0f} MB ({len(rows)} in "
f"database: {c['ok']} on disk, {c['no_uuid']} never reached S3, {c['s3_missing']} not "
"returned by S3)")
time.sleep(0.5)
try: # the MeteoSwiss weather of the days now in --out, as pump.sh does for data/
import weather
weather.main(stations, a.out)
except Exception as e: # the next run fetches it
print(f"weather: failed ({type(e).__name__}: {e}), run again")
finally:
engine.dispose()
def check():
"""Without database or S3: `python3 extraction/pump_diff.py --check`."""
import tempfile
from types import SimpleNamespace
d = lambda n: date(2026, 11, n) # noqa: E731
assert days_to_pump(set(), d(1), d(4)) == [d(1), d(2), d(3)]
assert days_to_pump({d(1), d(2), d(5)}, d(1), d(7)) == [d(3), d(4), d(5), d(6)] # the last indexed day: again
assert days_to_pump({d(2)}, None, d(5)) == [d(2), d(3), d(4)]
assert days_to_pump(set(), None, d(5)) is None # no --from, nothing indexed: skipped
class S3:
def get_object(self, Bucket, Key):
if Key == "refused":
raise OSError("NoSuchKey")
return {"Body": io.BytesIO(b"png")}
t = lambda h, m: datetime(2026, 11, 3, h, m, 7, 250000, tzinfo=UTC) # noqa: E731
rows = [SimpleNamespace(id=1, time_utc=t(10, 0), measurement_group_id=5, measurement_uuid="a", properties={"e": 1}),
SimpleNamespace(id=2, time_utc=t(10, 0), measurement_group_id=5, measurement_uuid="b", properties=None),
SimpleNamespace(id=3, time_utc=t(10, 15), measurement_group_id=None, measurement_uuid=None, properties={}),
SimpleNamespace(id=4, time_utc=t(10, 30), measurement_group_id=None, measurement_uuid="refused",
properties={})]
with tempfile.TemporaryDirectory() as tmp:
folder = Path(tmp) / "S"
(folder / "images_diff").mkdir(parents=True)
(folder / "images_diff" / "20261103T1000Z_2.png").write_bytes(b"old") # a burst: same minute, other id
c = pump_day(rows, S3(), "bucket", "png", folder, "S", d(3))
assert dict(c) == {"ok": 2, "new": 1, "bytes": 3, "no_uuid": 1, "s3_missing": 1}, c
assert (folder / "images_diff" / "20261103T1000Z_1.png").read_bytes() == b"png"
assert (folder / "images_diff" / "20261103T1000Z_2.png").read_bytes() == b"old" # never downloaded again
assert not list(folder.rglob("*.tmp"))
with open(folder / "images_diff" / "index" / "S_diff_20261103.csv", newline="") as fp:
index = list(csv.DictReader(fp))
assert [r["status"] for r in index] == ["ok", "ok", "no_uuid", "s3_missing"], index
assert [r["file"] for r in index] == ["20261103T1000Z_1.png", "20261103T1000Z_2.png", "", ""], index
assert index[0]["time_utc"] == "2026-11-03T10:00:07.250000+00:00" and index[0]["properties"] == '{"e": 1}'
assert index[1]["properties"] == "" and index[2]["measurement_group_id"] == "", index
assert indexed_days(folder) == {d(3)}
print("ok")
if __name__ == "__main__":
check() if sys.argv[1:] == ["--check"] else main()