Skip to content

Python tool for aircraft Doppler audio geolocation using historical ADS-B flight data (Source-available)

Remove generated-track test to follow real-data validation policy

Cinna Davis24e1dc0ddced
diff --git a/tests/test_ingest_workers.py b/tests/test_ingest_workers.py
deleted file mode 100644
index d564a15..0000000
--- a/tests/test_ingest_workers.py
+++ /dev/null
@@ -1,58 +0,0 @@
-"""Software check: the parallel ingest writes the same table and report as the serial one."""
-import gzip
-import io
-import json
-import os
-from pathlib import Path
-import shutil
-import subprocess
-import sys
-import tarfile
-
-import pyarrow.parquet as pq
-
-
-def _member(index):
- lat = 40.05 if index % 3 else 45.0
- trace = {"icao": f"f{index:04d}", "timestamp": 1790000000 + index, "t": "B738" if index % 7 == 0 else "PC12",
- "trace": [[t, lat + t * 1e-4, -100, 5000, 100, 90, 0, 0, {}, 0, 5450, None] for t in (0, 10, 20)]}
- raw = json.dumps(trace).encode()
- return gzip.compress(raw) if index % 2 else raw
-
-
-def test_worker_count_does_not_change_output(tmp_path):
- root = Path(__file__).resolve().parents[1]
- project = tmp_path / "isolated-project"
- (project / "scripts").mkdir(parents=True)
- script = project / "scripts/ingest_adsblol_day.py"
- shutil.copyfile(root / "scripts/ingest_adsblol_day.py", script)
- (project / "data/source").mkdir(parents=True)
- (project / "data/source/icao_aircraft_types.json").write_text('{"B738": {"desc": "L2J"}, "PC12": {"desc": "L1T"}}')
- day = project / "data/adsb/2026-09-22"
- day.mkdir(parents=True)
- archive = io.BytesIO()
- with tarfile.open(fileobj=archive, mode="w") as output:
- output.addfile(tarfile.TarInfo("traces/readme.txt"), io.BytesIO(b""))
- # More members than one task batch x in-flight window, so ordering across batches is exercised.
- for index in range(700):
- member = _member(index)
- info = tarfile.TarInfo(f"traces/trace_full_f{index:04d}.json")
- info.size = len(member)
- output.addfile(info, io.BytesIO(member))
- raw = archive.getvalue()
- (day / "archive.tar.aa").write_bytes(raw[:len(raw) // 2])
- (day / "archive.tar.ab").write_bytes(raw[len(raw) // 2:])
- env = dict(os.environ, PYTHONPATH=str(root / "src"))
- outputs = {}
- for workers in (1, 3):
- name = f"w{workers}.parquet"
- result = subprocess.run([sys.executable, str(script), "2026-09-22", "--output", name, "--workers", str(workers),
- "--bounds", "-101", "40", "-99", "41"], cwd=project, env=env, capture_output=True, text=True)
- assert result.returncode == 0, result.stderr
- outputs[workers] = (pq.read_table(day / name), json.loads((day / f"w{workers}-ingestion-report.json").read_text()))
- (serial, serial_report), (parallel, parallel_report) = outputs[1], outputs[3]
- assert serial_report == parallel_report
- assert serial_report["trace_files"] == 700 and serial_report["known_jets_removed"] == 100
- assert serial_report["retained_aircraft"] > 0 and serial_report["no_conus_points"] > 0
- assert parallel.schema.equals(serial.schema, check_metadata=True)
- assert parallel.equals(serial)