release: bump version to 0.48.0

This commit is contained in:
linkong
2026-05-07 18:06:06 +08:00
parent 421234301a
commit bb9183b8a4
51 changed files with 4609 additions and 400 deletions

View File

@@ -10,7 +10,10 @@ from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from app.core.data_sources import get_data_sources_config
from app.core.time import to_iso8601_utc
from app.core.websocket.broadcaster import broadcaster
from app.models.datasource_config import DataSourceConfig
from app.models.task import CollectionTask
from app.services.collectors.base import BaseCollector
from app.services.vessel_ais_aggregation import (
AISSTREAM_DELIVERY_MODE,
@@ -66,9 +69,20 @@ class AISStreamCollector(BaseCollector):
"bounding_boxes": config.get("bounding_boxes") or DEFAULT_BOUNDING_BOXES,
"message_types": config.get("message_types") or DEFAULT_MESSAGE_TYPES,
"max_messages": int(config.get("max_messages") or 500),
"streaming_enabled": config.get("streaming_enabled", True) is not False,
"streaming_commit_interval": int(config.get("streaming_commit_interval") or 1),
"streaming_max_messages": int(config.get("streaming_max_messages") or 0),
"reconnect_delay_seconds": float(config.get("reconnect_delay_seconds") or 5),
"receive_timeout_seconds": float(config.get("receive_timeout_seconds") or 30),
}
def _build_subscription(self, config: dict[str, Any]) -> dict[str, Any]:
return {
"APIKey": config["api_key"],
"BoundingBoxes": config["bounding_boxes"],
"FilterMessageTypes": config["message_types"],
}
async def fetch(self) -> list[dict[str, Any]]:
config = await self._get_effective_config()
if not config["api_key"]:
@@ -79,11 +93,7 @@ class AISStreamCollector(BaseCollector):
except ImportError as exc:
raise RuntimeError("Python package 'websockets' is required for AISStream") from exc
subscription = {
"APIKey": config["api_key"],
"BoundingBoxes": config["bounding_boxes"],
"FilterMessageTypes": config["message_types"],
}
subscription = self._build_subscription(config)
messages: list[dict[str, Any]] = []
try:
@@ -113,6 +123,157 @@ class AISStreamCollector(BaseCollector):
return messages
async def run(self, db: AsyncSession) -> dict[str, Any]:
"""Run AISStream as a long-lived streaming collector by default."""
config = await self._get_effective_config()
if not config.get("streaming_enabled", True):
return await super().run(db)
if not config["api_key"]:
return {"status": "failed", "error": "AISStream API key is not configured"}
from app.services.collectors.registry import collector_registry
if not collector_registry.is_active(self.name):
return {"status": "skipped", "reason": "Collector is disabled"}
try:
import websockets
except ImportError as exc:
return {"status": "failed", "error": "Python package 'websockets' is required for AISStream"}
start_time = datetime.now(UTC)
task = CollectionTask(
datasource_id=getattr(self, "_datasource_id", 1),
status="running",
phase="connecting",
phase_message="正在连接 AISStream 实时流",
phase_unit="messages",
started_at=start_time,
)
db.add(task)
await db.commit()
self._current_task = task
self._db_session = db
self._last_broadcast_progress = None
await self.resolve_url(db)
await self._publish_task_update(force=True)
records_added = 0
messages_seen = 0
unique_mmsi: set[str] = set()
reconnect_delay = config["reconnect_delay_seconds"]
try:
while True:
config = await self._get_effective_config()
subscription = self._build_subscription(config)
try:
await update_ais_source_health(
db,
source=self.name,
connection_state="connecting",
)
await self.set_phase("connecting", message="正在连接 AISStream 实时流")
await db.commit()
async with websockets.connect(config["endpoint"]) as websocket:
await websocket.send(json.dumps(subscription))
await update_ais_source_health(
db,
source=self.name,
connection_state="connected",
last_success_at=datetime.now(UTC),
)
await self.set_phase(
"streaming",
message="正在接收 AISStream 实时消息",
reset_progress=False,
)
await db.commit()
while True:
try:
raw_message = await asyncio.wait_for(
websocket.recv(),
timeout=config["receive_timeout_seconds"],
)
except TimeoutError:
await update_ais_source_health(
db,
source=self.name,
connection_state="connected",
last_success_at=datetime.now(UTC),
)
await db.commit()
continue
payload = json.loads(raw_message)
if not isinstance(payload, dict):
continue
messages_seen += 1
record = self._normalize_message(payload)
if not record:
continue
unique_mmsi.add(str(record["mmsi"]))
created = await self._save_stream_record(db, record)
if created:
records_added += 1
task.records_processed = messages_seen
task.total_records = None
task.progress = None
task.phase = "streaming"
task.phase_message = "正在接收 AISStream 实时消息"
task.phase_current = messages_seen
task.phase_total = None
task.phase_unit = "messages"
await self._publish_task_update(force=True)
if config["streaming_max_messages"] and messages_seen >= config["streaming_max_messages"]:
task.status = "success"
task.phase = "stopped"
task.phase_message = "AISStream 测试流已停止"
task.completed_at = datetime.now(UTC)
await db.commit()
await self._publish_task_update(force=True)
return {
"status": "success",
"task_id": task.id,
"records_processed": records_added,
"messages_seen": messages_seen,
"unique_mmsi": len(unique_mmsi),
"execution_time_seconds": (datetime.now(UTC) - start_time).total_seconds(),
}
except asyncio.CancelledError:
raise
except Exception as exc:
await update_ais_source_health(
db,
source=self.name,
connection_state="reconnecting",
last_error=f"{exc.__class__.__name__}: {exc}",
)
task.phase = "reconnecting"
task.phase_message = "AISStream 连接中断,正在重连"
task.error_message = f"{exc.__class__.__name__}: {exc}"
await db.commit()
await self._publish_task_update(force=True)
await asyncio.sleep(reconnect_delay)
except asyncio.CancelledError:
task.status = "cancelled"
task.phase = "stopped"
task.phase_message = "AISStream 实时流已停止"
task.completed_at = datetime.now(UTC)
await update_ais_source_health(
db,
source=self.name,
connection_state="disconnected",
last_error=None,
)
await db.commit()
await self._publish_task_update(force=True)
raise
def transform(self, raw_data: list[dict[str, Any]]) -> list[dict[str, Any]]:
records = []
for item in raw_data:
@@ -165,6 +326,60 @@ class AISStreamCollector(BaseCollector):
await self.update_progress(records_added, force=True)
return records_added
async def _save_stream_record(self, db: AsyncSession, item: dict[str, Any]) -> bool:
now = datetime.now(UTC)
observed_at = item.get("received_at") or now
observation = await record_vessel_ais_observation(
db,
source=self.name,
normalized_payload=item,
raw_payload=item.get("_raw_payload") or item,
delivery_mode=AISSTREAM_DELIVERY_MODE,
transport=AISSTREAM_TRANSPORT,
message_type=item.get("_message_type") or "PositionReport",
source_message_id=item.get("_source_message_id"),
observed_at=observed_at,
collected_at=now,
)
await update_ais_source_health(
db,
source=self.name,
connection_state="connected",
observed_count=1,
last_seen_at=observed_at if isinstance(observed_at, datetime) else now,
last_success_at=now,
lag_seconds=max((now - observed_at).total_seconds(), 0) if isinstance(observed_at, datetime) else None,
)
await db.commit()
await self._broadcast_vessel_delta(item, created=observation is not None)
return observation is not None
async def _broadcast_vessel_delta(self, item: dict[str, Any], *, created: bool) -> None:
await broadcaster.broadcast_custom(
"vessels",
{
"action": "upsert",
"source": self.name,
"created": created,
"vessels": [
{
"mmsi": item.get("mmsi"),
"mmsi_display": str(item.get("mmsi")) if item.get("mmsi") is not None else None,
"name": item.get("name"),
"lat": item.get("lat"),
"lon": item.get("lon"),
"sog": item.get("sog"),
"cog": item.get("cog"),
"heading": item.get("heading"),
"nav_status": item.get("nav_status"),
"vessel_type": item.get("vessel_type"),
"vessel_type_name": item.get("vessel_type_name"),
"received_at": to_iso8601_utc(item.get("received_at")),
}
],
},
)
def _normalize_message(self, item: dict[str, Any]) -> dict[str, Any] | None:
message_type = str(item.get("MessageType") or item.get("message_type") or "")
metadata = item.get("MetaData") if isinstance(item.get("MetaData"), dict) else {}