release: bump version to 0.47.0

backend/tests/test_vessels.py

@@ -1,4 +1,5 @@
 from datetime import datetime, timedelta, timezone
+from unittest.mock import AsyncMock
 
 import pytest
 from httpx import ASGITransport, AsyncClient
@@ -6,9 +7,16 @@ from httpx import ASGITransport, AsyncClient
 from app.api.v1.visualization import convert_vessels_to_geojson
 from app.db.session import get_db
 from app.main import app
-from app.models.vessel import VesselPosition, VesselStatic
+from app.models.vessel import AISRawObservation, VesselPosition, VesselStatic
 from app.services import barentswatch
+from app.services.collectors.aisstream import AISStreamCollector
 from app.services.collectors.vessel_ais import VesselAISCollector
+from app.services.vessel_ais_aggregation import (
+    aggregate_vessel_observations,
+    build_field_conflict_candidates,
+    build_observation_hash,
+    record_vessel_ais_observation,
+)
 
 
 def test_vessel_collector_transforms_barentswatch_like_records():
@@ -35,6 +43,328 @@ def test_vessel_collector_transforms_barentswatch_like_records():
     assert records[0]["lat"] == pytest.approx(59.91)
 
 
+def test_vessel_observation_hash_is_stable_for_same_payload():
+    observed_at = datetime(2026, 4, 30, 12, 0, tzinfo=timezone.utc)
+    payload = {
+        "mmsi": 257123000,
+        "lat": 59.91,
+        "lon": 10.73,
+        "received_at": observed_at,
+    }
+
+    first = build_observation_hash(
+        source="barentswatch_vessels",
+        entity_key="257123000",
+        message_type="PositionReport",
+        observed_at=observed_at,
+        normalized_payload=payload,
+    )
+    second = build_observation_hash(
+        source="barentswatch_vessels",
+        entity_key="257123000",
+        message_type="PositionReport",
+        observed_at=observed_at,
+        normalized_payload=dict(reversed(payload.items())),
+    )
+
+    assert first == second
+    assert len(first) == 64
+
+
+@pytest.mark.asyncio
+async def test_record_vessel_ais_observation_skips_existing_hash():
+    observed_at = datetime(2026, 4, 30, 12, 0, tzinfo=timezone.utc)
+
+    class _Result:
+        def scalar_one_or_none(self):
+            return 123
+
+    class _Session:
+        def __init__(self):
+            self.added = []
+
+        async def execute(self, _stmt):
+            return _Result()
+
+        def add(self, item):
+            self.added.append(item)
+
+    db = _Session()
+    observation = await record_vessel_ais_observation(
+        db,
+        source="barentswatch_vessels",
+        normalized_payload={
+            "mmsi": 257123000,
+            "lat": 59.91,
+            "lon": 10.73,
+            "received_at": observed_at,
+        },
+        delivery_mode="polling",
+        transport="http",
+        observed_at=observed_at.isoformat(),
+    )
+
+    assert observation is None
+    assert db.added == []
+
+
+def test_build_field_conflict_candidates_from_raw_observations():
+    observations = [
+        AISRawObservation(
+            source="barentswatch_vessels",
+            normalized_payload={"name": "OSLO TRADER", "flag": "NO"},
+        ),
+        AISRawObservation(
+            source="aisstream_vessels",
+            normalized_payload={"name": "OSLO TRADER II", "flag": "NO"},
+        ),
+    ]
+
+    conflicts = build_field_conflict_candidates(observations)
+
+    assert conflicts == [
+        {
+            "field": "name",
+            "candidates": {
+                "aisstream_vessels": "OSLO TRADER II",
+                "barentswatch_vessels": "OSLO TRADER",
+            },
+            "status": "candidate",
+        }
+    ]
+
+
+@pytest.mark.asyncio
+async def test_aggregate_vessel_observations_prefers_realtime_and_records_conflict():
+    observed_at = datetime.now(timezone.utc) - timedelta(minutes=5)
+
+    class _Result:
+        def scalar_one_or_none(self):
+            return None
+
+    class _Session:
+        def __init__(self):
+            self.added = []
+
+        async def execute(self, _stmt):
+            return _Result()
+
+        def add(self, item):
+            self.added.append(item)
+
+    db = _Session()
+    observations = [
+        AISRawObservation(
+            id=1,
+            source="barentswatch_vessels",
+            entity_key="257123000",
+            delivery_mode="polling",
+            transport="http",
+            observed_at=observed_at,
+            collected_at=observed_at,
+            normalized_payload={
+                "mmsi": 257123000,
+                "name": "OSLO TRADER",
+                "lat": 59.91,
+                "lon": 10.73,
+            },
+        ),
+        AISRawObservation(
+            id=2,
+            source="aisstream_vessels",
+            entity_key="257123000",
+            delivery_mode="realtime_stream",
+            transport="websocket",
+            observed_at=observed_at + timedelta(seconds=10),
+            collected_at=observed_at + timedelta(seconds=10),
+            normalized_payload={
+                "mmsi": 257123000,
+                "vessel_type": 79,
+                "lat": 59.92,
+                "lon": 10.74,
+            },
+            raw_payload={"MetaData": {"ShipName": "OSLO TRADER II         "}},
+        ),
+    ]
+
+    vessels = await aggregate_vessel_observations(db, observations)
+
+    assert vessels[0]["lat"] == pytest.approx(59.92)
+    assert vessels[0]["field_sources"]["lat"] == "aisstream_vessels"
+    assert vessels[0]["name"] == "OSLO TRADER II"
+    assert vessels[0]["vessel_type_name"] == "Cargo"
+    assert vessels[0]["source_summary"]["aisstream_vessels"]["observation_count"] == 1
+    assert vessels[0]["source_summary"]["barentswatch_vessels"]["delivery_mode"] == "polling"
+    assert vessels[0]["conflict_count"] == 0
+    assert db.added == []
+
+
+@pytest.mark.asyncio
+async def test_vessel_collector_writes_raw_observations_without_changing_position_save(monkeypatch):
+    collector = VesselAISCollector()
+    collector.update_progress = AsyncMock()
+    record_observation = AsyncMock()
+    update_health = AsyncMock()
+    monkeypatch.setattr(
+        "app.services.collectors.vessel_ais.record_vessel_ais_observation",
+        record_observation,
+    )
+    monkeypatch.setattr(
+        "app.services.collectors.vessel_ais.update_ais_source_health",
+        update_health,
+    )
+
+    class _Session:
+        def __init__(self):
+            self.added = []
+            self.committed = False
+
+        async def get(self, *_args):
+            return None
+
+        def add(self, item):
+            self.added.append(item)
+
+        async def execute(self, _stmt):
+            return None
+
+        async def commit(self):
+            self.committed = True
+
+    db = _Session()
+    observed_at = datetime(2026, 4, 30, 12, 0, tzinfo=timezone.utc)
+
+    saved = await collector._save_data(
+        db,
+        [
+            {
+                "mmsi": 257123000,
+                "name": "OSLO TRADER",
+                "lat": 59.91,
+                "lon": 10.73,
+                "received_at": observed_at,
+            }
+        ],
+    )
+
+    assert saved == 1
+    assert db.committed is True
+    assert any(isinstance(item, VesselStatic) for item in db.added)
+    assert any(isinstance(item, VesselPosition) for item in db.added)
+    record_observation.assert_awaited_once()
+    assert record_observation.await_args.kwargs["source"] == "barentswatch_vessels"
+    assert record_observation.await_args.kwargs["normalized_payload"]["mmsi"] == 257123000
+    update_health.assert_awaited_once()
+
+
+def test_aisstream_collector_normalizes_position_report():
+    collector = AISStreamCollector()
+
+    records = collector.transform(
+        [
+            {
+                "MessageType": "PositionReport",
+                "MetaData": {
+                    "MMSI": 257123000,
+                    "ShipName": "OSLO TRADER         ",
+                    "time_utc": "2026-04-30T12:00:00Z",
+                },
+                "Message": {
+                    "PositionReport": {
+                        "Latitude": 59.91,
+                        "Longitude": 10.73,
+                        "Sog": 12.4,
+                        "Cog": 214,
+                        "TrueHeading": 215,
+                        "NavigationalStatus": 0,
+                    }
+                },
+            }
+        ]
+    )
+
+    assert len(records) == 1
+    assert records[0]["mmsi"] == 257123000
+    assert records[0]["lat"] == pytest.approx(59.91)
+    assert records[0]["name"] == "OSLO TRADER"
+    assert records[0]["_message_type"] == "PositionReport"
+
+
+def test_aisstream_collector_maps_ship_static_type_name():
+    collector = AISStreamCollector()
+
+    records = collector.transform(
+        [
+            {
+                "MessageType": "ShipStaticData",
+                "MetaData": {
+                    "MMSI": 257123000,
+                    "time_utc": "2026-04-30T12:00:00Z",
+                },
+                "Message": {
+                    "ShipStaticData": {
+                        "Name": "OSLO TRADER",
+                        "Type": 79,
+                        "CallSign": "LAAB",
+                    }
+                },
+            }
+        ]
+    )
+
+    assert len(records) == 1
+    assert records[0]["vessel_type"] == 79
+    assert records[0]["vessel_type_name"] == "Cargo"
+
+
+@pytest.mark.asyncio
+async def test_aisstream_collector_writes_only_raw_observations(monkeypatch):
+    collector = AISStreamCollector()
+    collector.update_progress = AsyncMock()
+    record_observation = AsyncMock(return_value=object())
+    update_health = AsyncMock()
+    monkeypatch.setattr(
+        "app.services.collectors.aisstream.record_vessel_ais_observation",
+        record_observation,
+    )
+    monkeypatch.setattr(
+        "app.services.collectors.aisstream.update_ais_source_health",
+        update_health,
+    )
+
+    class _Session:
+        def __init__(self):
+            self.added = []
+            self.committed = False
+
+        def add(self, item):
+            self.added.append(item)
+
+        async def commit(self):
+            self.committed = True
+
+    db = _Session()
+    saved = await collector._save_data(
+        db,
+        [
+            {
+                "mmsi": 257123000,
+                "lat": 59.91,
+                "lon": 10.73,
+                "received_at": datetime(2026, 4, 30, 12, 0, tzinfo=timezone.utc),
+                "_message_type": "PositionReport",
+            }
+        ],
+    )
+
+    assert saved == 1
+    assert db.added == []
+    assert db.committed is True
+    record_observation.assert_awaited_once()
+    assert record_observation.await_args.kwargs["source"] == "aisstream_vessels"
+    update_health.assert_awaited_once()
+
+
 def test_barentswatch_reads_credentials_from_zshrc(tmp_path):
     zshrc = tmp_path / ".zshrc"
     zshrc.write_text(
@@ -137,7 +467,7 @@ async def test_vessels_geojson_endpoint_filters_type_and_bbox():
         async with AsyncClient(transport=transport, base_url="http://test") as client:
             response = await client.get(
                 "/api/v1/visualization/geo/vessels",
-                params={"bbox": "0,50,20,70", "type": "cargo"},
+                params={"bbox": "0,50,20,70", "type": "cargo", "limit": 0},
             )
 
         assert response.status_code == 200