release: bump version to 0.43.0
This commit is contained in:
@@ -31,6 +31,7 @@ COLLECTOR_URL_KEYS = {
|
||||
"opengeofeed_prefix_geo": "opengeofeed.public_csv_url",
|
||||
"nro_delegated_prefix_geo": "nro.delegated_stats_url",
|
||||
"news_live_streams": "news_live_streams.channels_url",
|
||||
"barentswatch_vessels": "barentswatch_vessels.url",
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -94,3 +94,7 @@ news_live_streams:
|
||||
streams_url: "https://iptv-org.github.io/api/streams.json"
|
||||
# IPTV-org 台标 JSON
|
||||
logos_url: "https://iptv-org.github.io/api/logos.json"
|
||||
|
||||
barentswatch_vessels:
|
||||
# BarentsWatch Live AIS latest combined endpoint. Requires an AIS bearer token.
|
||||
url: "https://live.ais.barentswatch.no/v1/latest/combined"
|
||||
|
||||
@@ -4,163 +4,246 @@ DEFAULT_DATASOURCES = {
|
||||
"top500": {
|
||||
"id": 1,
|
||||
"name": "TOP500 Supercomputers",
|
||||
"display_name": "TOP500 超算榜单",
|
||||
"module": "L1",
|
||||
"priority": "P0",
|
||||
"frequency_minutes": 240,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"epoch_ai_gpu": {
|
||||
"id": 2,
|
||||
"name": "Epoch AI GPU Clusters",
|
||||
"display_name": "Epoch AI GPU 集群",
|
||||
"module": "L1",
|
||||
"priority": "P0",
|
||||
"frequency_minutes": 360,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"huggingface_models": {
|
||||
"id": 3,
|
||||
"name": "HuggingFace Models",
|
||||
"display_name": "Hugging Face 模型",
|
||||
"module": "L2",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 720,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"huggingface_datasets": {
|
||||
"id": 4,
|
||||
"name": "HuggingFace Datasets",
|
||||
"display_name": "Hugging Face 数据集",
|
||||
"module": "L2",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 720,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"huggingface_spaces": {
|
||||
"id": 5,
|
||||
"name": "HuggingFace Spaces",
|
||||
"display_name": "Hugging Face Spaces",
|
||||
"module": "L2",
|
||||
"priority": "P2",
|
||||
"frequency_minutes": 1440,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"peeringdb_ixp": {
|
||||
"id": 6,
|
||||
"name": "PeeringDB IXP",
|
||||
"display_name": "PeeringDB 交换中心",
|
||||
"module": "L2",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 1440,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"peeringdb_network": {
|
||||
"id": 7,
|
||||
"name": "PeeringDB Networks",
|
||||
"display_name": "PeeringDB 网络",
|
||||
"module": "L2",
|
||||
"priority": "P2",
|
||||
"frequency_minutes": 2880,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"peeringdb_facility": {
|
||||
"id": 8,
|
||||
"name": "PeeringDB Facilities",
|
||||
"display_name": "PeeringDB 设施",
|
||||
"module": "L2",
|
||||
"priority": "P2",
|
||||
"frequency_minutes": 2880,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"telegeography_cables": {
|
||||
"id": 9,
|
||||
"name": "Submarine Cables",
|
||||
"display_name": "海底光缆",
|
||||
"module": "L2",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 10080,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"telegeography_landing": {
|
||||
"id": 10,
|
||||
"name": "Cable Landing Points",
|
||||
"display_name": "光缆登陆点",
|
||||
"module": "L2",
|
||||
"priority": "P2",
|
||||
"frequency_minutes": 10080,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"telegeography_systems": {
|
||||
"id": 11,
|
||||
"name": "Cable Systems",
|
||||
"display_name": "光缆系统",
|
||||
"module": "L2",
|
||||
"priority": "P2",
|
||||
"frequency_minutes": 10080,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"arcgis_cables": {
|
||||
"id": 15,
|
||||
"name": "ArcGIS Submarine Cables",
|
||||
"display_name": "ArcGIS 海底光缆",
|
||||
"module": "L2",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 10080,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"arcgis_landing_points": {
|
||||
"id": 16,
|
||||
"name": "ArcGIS Landing Points",
|
||||
"display_name": "ArcGIS 登陆点",
|
||||
"module": "L2",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 10080,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"arcgis_cable_landing_relation": {
|
||||
"id": 17,
|
||||
"name": "ArcGIS Cable-Landing Relations",
|
||||
"display_name": "ArcGIS 光缆登陆关系",
|
||||
"module": "L2",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 10080,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"fao_landing_points": {
|
||||
"id": 18,
|
||||
"name": "FAO Landing Points",
|
||||
"display_name": "FAO 登陆点",
|
||||
"module": "L2",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 10080,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"spacetrack_tle": {
|
||||
"id": 19,
|
||||
"name": "Space-Track TLE",
|
||||
"display_name": "Space-Track 轨道根数",
|
||||
"module": "L3",
|
||||
"priority": "P2",
|
||||
"frequency_minutes": 1440,
|
||||
"is_free": True,
|
||||
"requires_credentials": True,
|
||||
"credential_provider": "spacetrack",
|
||||
"credential_status": "planned",
|
||||
},
|
||||
"celestrak_tle": {
|
||||
"id": 20,
|
||||
"name": "CelesTrak TLE",
|
||||
"display_name": "CelesTrak 轨道根数",
|
||||
"module": "L3",
|
||||
"priority": "P2",
|
||||
"frequency_minutes": 1440,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"ris_live_bgp": {
|
||||
"id": 21,
|
||||
"name": "RIPE RIS Live BGP",
|
||||
"display_name": "RIPE RIS 实时 BGP",
|
||||
"module": "L3",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 15,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"bgpstream_bgp": {
|
||||
"id": 22,
|
||||
"name": "CAIDA BGPStream Backfill",
|
||||
"display_name": "CAIDA BGPStream 回填",
|
||||
"module": "L3",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 360,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"iptoasn_prefix_geo": {
|
||||
"id": 23,
|
||||
"name": "IPtoASN Prefix Geography",
|
||||
"display_name": "IPtoASN 前缀地理",
|
||||
"module": "L3",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 1440,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"opengeofeed_prefix_geo": {
|
||||
"id": 24,
|
||||
"name": "OpenGeoFeed Prefix Geography",
|
||||
"display_name": "OpenGeoFeed 前缀地理",
|
||||
"module": "L3",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 1440,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"nro_delegated_prefix_geo": {
|
||||
"id": 25,
|
||||
"name": "NRO Delegated Prefix Geography",
|
||||
"display_name": "NRO 分配前缀地理",
|
||||
"module": "L3",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 1440,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"news_live_streams": {
|
||||
"id": 26,
|
||||
"name": "News Live Streams",
|
||||
"display_name": "新闻直播源",
|
||||
"module": "L4",
|
||||
"priority": "P2",
|
||||
"frequency_minutes": 720,
|
||||
"is_free": True,
|
||||
"requires_credentials": False,
|
||||
},
|
||||
"barentswatch_vessels": {
|
||||
"id": 27,
|
||||
"name": "BarentsWatch AIS Vessels",
|
||||
"display_name": "BarentsWatch AIS 船舶",
|
||||
"module": "L4",
|
||||
"priority": "P1",
|
||||
"frequency_minutes": 1,
|
||||
"is_free": True,
|
||||
"requires_credentials": True,
|
||||
"credential_provider": "barentswatch",
|
||||
"credential_status": "supported",
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
151
backend/app/core/target_schema_registry.py
Normal file
151
backend/app/core/target_schema_registry.py
Normal file
@@ -0,0 +1,151 @@
|
||||
"""Registry of target schemas supported by mapped custom data sources."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime
|
||||
from typing import Any
|
||||
|
||||
from pydantic import BaseModel, Field, ValidationError, field_validator
|
||||
|
||||
|
||||
class VesselAISRecord(BaseModel):
|
||||
mmsi: int = Field(ge=100000000, le=999999999)
|
||||
lat: float = Field(ge=-90, le=90)
|
||||
lon: float = Field(ge=-180, le=180)
|
||||
sog: float | None = None
|
||||
cog: float | None = Field(default=None, ge=0, le=360)
|
||||
heading: int | None = Field(default=None, ge=0, le=511)
|
||||
name: str | None = None
|
||||
vessel_type: str | int | None = None
|
||||
received_at: datetime | None = None
|
||||
|
||||
|
||||
class GeoPointRecord(BaseModel):
|
||||
lat: float = Field(ge=-90, le=90)
|
||||
lon: float = Field(ge=-180, le=180)
|
||||
name: str | None = None
|
||||
type: str | None = None
|
||||
source_id: str | None = None
|
||||
observed_at: datetime | None = None
|
||||
metadata: dict[str, Any] = Field(default_factory=dict)
|
||||
|
||||
|
||||
class GenericRecord(BaseModel):
|
||||
data: dict[str, Any] = Field(default_factory=dict)
|
||||
source_id: str | None = None
|
||||
observed_at: datetime | None = None
|
||||
|
||||
@field_validator("data")
|
||||
@classmethod
|
||||
def require_payload(cls, value: dict[str, Any]) -> dict[str, Any]:
|
||||
if not value:
|
||||
raise ValueError("generic_records requires a non-empty data object")
|
||||
return value
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TargetField:
|
||||
name: str
|
||||
type: str
|
||||
required: bool = False
|
||||
description: str = ""
|
||||
example: Any = None
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"name": self.name,
|
||||
"type": self.type,
|
||||
"required": self.required,
|
||||
"description": self.description,
|
||||
"example": self.example,
|
||||
}
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class TargetSchema:
|
||||
key: str
|
||||
label: str
|
||||
description: str
|
||||
fields: tuple[TargetField, ...]
|
||||
model: type[BaseModel]
|
||||
destination: str
|
||||
|
||||
def to_dict(self) -> dict[str, Any]:
|
||||
return {
|
||||
"key": self.key,
|
||||
"label": self.label,
|
||||
"description": self.description,
|
||||
"destination": self.destination,
|
||||
"fields": [field.to_dict() for field in self.fields],
|
||||
}
|
||||
|
||||
def validate_record(self, record: dict[str, Any]) -> tuple[dict[str, Any] | None, list[str]]:
|
||||
try:
|
||||
return self.model.model_validate(record).model_dump(mode="json"), []
|
||||
except ValidationError as exc:
|
||||
return None, [
|
||||
".".join(str(part) for part in error["loc"]) + f": {error['msg']}"
|
||||
for error in exc.errors()
|
||||
]
|
||||
|
||||
|
||||
TARGET_SCHEMAS: dict[str, TargetSchema] = {
|
||||
"vessel_ais": TargetSchema(
|
||||
key="vessel_ais",
|
||||
label="船舶 AIS",
|
||||
description="船只位置、航速、航向、MMSI 等 AIS 数据。",
|
||||
destination="vessel_position",
|
||||
model=VesselAISRecord,
|
||||
fields=(
|
||||
TargetField("mmsi", "integer", True, "MMSI 九位船舶标识", 257123000),
|
||||
TargetField("lat", "float", True, "纬度", 59.91),
|
||||
TargetField("lon", "float", True, "经度", 10.75),
|
||||
TargetField("sog", "float", False, "对地航速,单位节", 12.4),
|
||||
TargetField("cog", "float", False, "对地航向,0-360 度", 184.5),
|
||||
TargetField("heading", "integer", False, "船首向,0-511", 186),
|
||||
TargetField("name", "string", False, "船名", "OSLO EXPRESS"),
|
||||
TargetField("vessel_type", "string", False, "船型", "cargo"),
|
||||
TargetField("received_at", "datetime", False, "数据接收时间", "2026-04-28T00:00:00Z"),
|
||||
),
|
||||
),
|
||||
"geo_points": TargetSchema(
|
||||
key="geo_points",
|
||||
label="通用地理点",
|
||||
description="带经纬度的通用实体或事件点位。",
|
||||
destination="generic_geo_points",
|
||||
model=GeoPointRecord,
|
||||
fields=(
|
||||
TargetField("lat", "float", True, "纬度", 1.3),
|
||||
TargetField("lon", "float", True, "经度", 103.8),
|
||||
TargetField("name", "string", False, "点位名称", "Singapore"),
|
||||
TargetField("type", "string", False, "点位类型", "datacenter"),
|
||||
TargetField("source_id", "string", False, "来源侧 ID", "sg-1"),
|
||||
TargetField("observed_at", "datetime", False, "观测时间", "2026-04-28T00:00:00Z"),
|
||||
TargetField("metadata", "object", False, "扩展字段", {"provider": "example"}),
|
||||
),
|
||||
),
|
||||
"generic_records": TargetSchema(
|
||||
key="generic_records",
|
||||
label="通用结构化记录",
|
||||
description="未知结构数据沉淀,不直接进入 Earth 图层。",
|
||||
destination="collected_data",
|
||||
model=GenericRecord,
|
||||
fields=(
|
||||
TargetField("data", "object", True, "结构化记录主体", {"raw": "value"}),
|
||||
TargetField("source_id", "string", False, "来源侧 ID", "record-1"),
|
||||
TargetField("observed_at", "datetime", False, "观测时间", "2026-04-28T00:00:00Z"),
|
||||
),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
def list_target_schemas() -> list[dict[str, Any]]:
|
||||
return [schema.to_dict() for schema in TARGET_SCHEMAS.values()]
|
||||
|
||||
|
||||
def get_target_schema(key: str) -> TargetSchema:
|
||||
try:
|
||||
return TARGET_SCHEMAS[key]
|
||||
except KeyError as exc:
|
||||
raise ValueError(f"Unsupported target schema: {key}") from exc
|
||||
Reference in New Issue
Block a user