govoplan-datasources/src/govoplan_datasources/backend/search_source.py

from __future__ import annotations

from collections.abc import Mapping, Sequence
from urllib.parse import quote

from sqlalchemy import func, select
from sqlalchemy.orm import Session

from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.modules import ModuleContext
from govoplan_core.core.search import (
    SearchAuthorizationRequest,
    SearchBackfillPage,
    SearchBackfillRequest,
    SearchDocument,
    SearchResourceType,
)
from govoplan_datasources.backend.db.models import DatasourceRecord
from govoplan_datasources.backend.service import ADMIN_SCOPE, CATALOGUE_READ_SCOPE


PROVIDER_ID = "datasources.catalogue"
RESOURCE_TYPE = "datasource"


class DatasourcesSearchSource:
    def resource_types(self) -> Sequence[SearchResourceType]:
        return (
            SearchResourceType(
                provider_id=PROVIDER_ID,
                module_id="datasources",
                resource_type=RESOURCE_TYPE,
                label="Datasources",
                requires_authorization_recheck=True,
            ),
        )

    def backfill(
        self,
        session: object,
        *,
        request: SearchBackfillRequest,
    ) -> SearchBackfillPage:
        _assert_source(request.provider_id, request.resource_type)
        db = _session(session)
        statement = select(DatasourceRecord).where(
            DatasourceRecord.tenant_id == request.tenant_id,
            DatasourceRecord.deleted_at.is_(None),
        )
        if request.cursor:
            statement = statement.where(DatasourceRecord.id > request.cursor)
        rows = list(
            db.scalars(
                statement.order_by(DatasourceRecord.id).limit(request.limit + 1)
            ).all()
        )
        has_more = len(rows) > request.limit
        selected = rows[: request.limit]
        high_watermark = db.scalar(
            select(func.max(DatasourceRecord.updated_at)).where(
                DatasourceRecord.tenant_id == request.tenant_id,
                DatasourceRecord.deleted_at.is_(None),
            )
        )
        return SearchBackfillPage(
            documents=tuple(_document(row) for row in selected),
            next_cursor=selected[-1].id if has_more and selected else None,
            complete=not has_more,
            high_watermark=high_watermark.isoformat() if high_watermark else None,
        )

    def authorize(
        self,
        session: object,
        principal: object,
        *,
        requests: Sequence[SearchAuthorizationRequest],
    ) -> Mapping[str, bool]:
        decisions = {item.reference.key: False for item in requests}
        if not isinstance(principal, ApiPrincipal) or not (
            principal.has(CATALOGUE_READ_SCOPE) or principal.has(ADMIN_SCOPE)
        ):
            return decisions
        db = _session(session)
        eligible = [
            request
            for request in requests
            if request.reference.tenant_id == principal.tenant_id
            and request.reference.module_id == "datasources"
            and request.reference.resource_type == RESOURCE_TYPE
        ]
        resource_ids = {request.reference.resource_id for request in eligible}
        available_ids = (
            set(
                db.scalars(
                    select(DatasourceRecord.id).where(
                        DatasourceRecord.tenant_id == principal.tenant_id,
                        DatasourceRecord.id.in_(resource_ids),
                        DatasourceRecord.deleted_at.is_(None),
                    )
                ).all()
            )
            if resource_ids
            else set()
        )
        for request in eligible:
            decisions[request.reference.key] = (
                request.reference.resource_id in available_ids
            )
        return decisions


def create_datasources_search_source(
    _context: ModuleContext,
) -> DatasourcesSearchSource:
    return DatasourcesSearchSource()


def _document(row: DatasourceRecord) -> SearchDocument:
    datasource_ref = quote(f"datasource:{row.id}", safe="")
    return SearchDocument(
        tenant_id=row.tenant_id,
        module_id="datasources",
        provider_id=PROVIDER_ID,
        resource_type=RESOURCE_TYPE,
        resource_id=row.id,
        title=row.name,
        url=f"/datasources?datasource={datasource_ref}",
        summary=(row.description or row.source_name)[:4000],
        keywords=tuple(
            value[:200]
            for value in (
                row.source_name,
                row.kind,
                row.mode,
                row.shape,
                row.status,
                row.classification,
                row.publication_state,
            )
            if value
        ),
        visibility="restricted",
        acl_tokens=(
            f"scope:{CATALOGUE_READ_SCOPE}",
            f"scope:{ADMIN_SCOPE}",
        ),
        metadata={
            "kind": row.kind,
            "mode": row.mode,
            "shape": row.shape,
            "status": row.status,
            "classification": row.classification,
            "publication_state": row.publication_state,
            "authority_mode": row.authority_mode,
        },
        source_revision=f"{row.schema_version}:{row.updated_at.isoformat()}",
        source_updated_at=row.updated_at,
        requires_authorization_recheck=True,
    )


def _assert_source(provider_id: str, resource_type: str) -> None:
    if provider_id != PROVIDER_ID or resource_type != RESOURCE_TYPE:
        raise ValueError("Unsupported Datasources search source.")


def _session(value: object) -> Session:
    if not isinstance(value, Session):
        raise TypeError("Datasources search requires a SQLAlchemy session.")
    return value


__all__ = [
    "DatasourcesSearchSource",
    "PROVIDER_ID",
    "RESOURCE_TYPE",
    "create_datasources_search_source",
]