planet/backend/app/services/earth_layer_adapters.py

"""Earth layer adapter registry for datasource-backed refresh behavior."""

from __future__ import annotations

from dataclasses import dataclass, field
from typing import Any

from sqlalchemy.ext.asyncio import AsyncSession


@dataclass(frozen=True)
class EarthLayerAdapter:
    sources: frozenset[str]
    layers: tuple[str, ...]
    cache_patterns: tuple[str, ...]
    tables: frozenset[str] = field(default_factory=frozenset)
    derived_models: tuple[str, ...] = field(default_factory=tuple)
    refresh_strategy: str = "clear_then_reload"


EARTH_LAYER_ADAPTERS: tuple[EarthLayerAdapter, ...] = (
    EarthLayerAdapter(
        sources=frozenset({"barentswatch_vessels", "aisstream_vessels", "vessel_static", "vessel_position", "vessel_current_state", "ais_raw_observations", "ais_source_health"}),
        tables=frozenset({"vessel_static", "vessel_position", "vessel_current_state", "ais_raw_observations", "ais_source_health"}),
        layers=("vessels",),
        cache_patterns=("vessels*", "summary*"),
        derived_models=("ais_raw_observations", "ais_conflict_records", "ais_source_health"),
        refresh_strategy="delta",
    ),
    EarthLayerAdapter(
        sources=frozenset(
            {
                "telegeography_cables",
                "telegeography_landing",
                "telegeography_landing_points",
                "telegeography_systems",
                "telegeography_cable_systems",
                "arcgis_cables",
                "arcgis_landing_points",
                "arcgis_cable_landing_relation",
                "arcgis_cable_landing_relations",
                "fao_landing_points",
            }
        ),
        tables=frozenset({"collected_data"}),
        layers=("cables",),
        cache_patterns=("cables*", "landing-points*", "summary*"),
    ),
    EarthLayerAdapter(
        sources=frozenset({"celestrak_tle", "spacetrack_tle"}),
        tables=frozenset({"collected_data"}),
        layers=("satellites",),
        cache_patterns=("satellites*", "summary*"),
    ),
    EarthLayerAdapter(
        sources=frozenset(
            {
                "top500",
                "top500_supercomputers",
                "epoch_ai_gpu",
                "huggingface_models",
                "huggingface_datasets",
                "huggingface_spaces",
                "compute_center_locations",
            }
        ),
        tables=frozenset({"compute_center_locations"}),
        layers=("computeCenters",),
        cache_patterns=("compute-centers*", "summary*"),
        refresh_strategy="reload",
    ),
    EarthLayerAdapter(
        sources=frozenset(
            {
                "ris_live_bgp",
                "bgpstream_bgp",
                "iptoasn_prefix_geo",
                "opengeofeed_prefix_geo",
                "nro_delegated_prefix_geo",
                "bgp_observations",
                "bgp_anomalies",
                "bgp_incidents",
                "bgp_collector_locations",
            }
        ),
        tables=frozenset({"bgp_observations", "bgp_anomalies", "bgp_incidents", "bgp_collector_locations"}),
        layers=("bgp",),
        cache_patterns=("bgp*", "summary*"),
        derived_models=("bgp_observations", "bgp_anomalies", "bgp_incidents"),
    ),
    EarthLayerAdapter(
        sources=frozenset({"news_live_streams"}),
        tables=frozenset({"collected_data"}),
        layers=("media",),
        cache_patterns=("summary*",),
        refresh_strategy="reload",
    ),
    EarthLayerAdapter(
        sources=frozenset({"media_news_archive", "earth_news_items"}),
        tables=frozenset({"earth_news_items"}),
        layers=("news",),
        cache_patterns=("summary*",),
        refresh_strategy="reload",
    ),
    EarthLayerAdapter(
        sources=frozenset({"earth_interactables"}),
        tables=frozenset({"earth_interactables"}),
        layers=("interactables",),
        cache_patterns=("interactables*", "summary*"),
        refresh_strategy="delta",
    ),
)

_ADAPTERS_BY_SOURCE = {
    source: adapter
    for adapter in EARTH_LAYER_ADAPTERS
    for source in adapter.sources
}
_ADAPTERS_BY_TABLE = {
    table: adapter
    for adapter in EARTH_LAYER_ADAPTERS
    for table in adapter.tables
}


def get_earth_layer_adapter_for_source(source: str | None) -> EarthLayerAdapter | None:
    return _ADAPTERS_BY_SOURCE.get(str(source or "").strip())


def get_earth_layer_adapter_for_change(table: str | None, source: str | None) -> EarthLayerAdapter | None:
    table_key = str(table or "").strip()
    source_key = str(source or "").strip()
    if table_key and table_key != "collected_data":
        adapter = _ADAPTERS_BY_TABLE.get(table_key)
        if adapter is not None:
            return adapter
    return get_earth_layer_adapter_for_source(source_key)


def get_earth_update_layers_for_source(source: str | None) -> list[str]:
    adapter = get_earth_layer_adapter_for_source(source)
    return list(adapter.layers) if adapter else []


def get_earth_update_layers_for_change(table: str | None, source: str | None) -> list[str]:
    adapter = get_earth_layer_adapter_for_change(table, source)
    return list(adapter.layers) if adapter else []


def get_earth_refresh_strategy_for_change(table: str | None, source: str | None) -> str | None:
    adapter = get_earth_layer_adapter_for_change(table, source)
    return adapter.refresh_strategy if adapter else None


def get_earth_cache_patterns_for_source(source: str | None) -> list[str]:
    adapter = get_earth_layer_adapter_for_source(source)
    return list(adapter.cache_patterns) if adapter else []


async def clear_derived_datasource_data(db: AsyncSession, source: str) -> dict[str, int]:
    adapter = get_earth_layer_adapter_for_source(source)
    if adapter is None or not adapter.derived_models:
        return {}

    from app.models.bgp_anomaly import BGPAnomaly
    from app.models.bgp_incident import BGPIncident
    from app.models.bgp_observation import BGPObservation
    from app.models.vessel import AISConflictRecord, AISRawObservation, AISSourceHealth

    model_by_key: dict[str, Any] = {
        "bgp_observations": BGPObservation,
        "bgp_anomalies": BGPAnomaly,
        "bgp_incidents": BGPIncident,
        "ais_raw_observations": AISRawObservation,
        "ais_conflict_records": AISConflictRecord,
        "ais_source_health": AISSourceHealth,
    }
    deleted_counts: dict[str, int] = {}
    for key in adapter.derived_models:
        model = model_by_key.get(key)
        if model is None:
            continue
        if key == "ais_conflict_records":
            result = await db.execute(model.__table__.delete().where(model.selected_source == source))
        else:
            result = await db.execute(model.__table__.delete().where(model.source == source))
        deleted_counts[key] = int(result.rowcount or 0)
    return deleted_counts