0pt/services/api/tests/test_connectors_provenance.py

"""
Verifies the P010 provenance additions (BEFORE_STATE.md §3: source,
retrieval timestamp, transform, version, producer were absent from the real
dataflow) land correctly on every real connector's output — mocked HTTP,
real parsing code.
"""
from __future__ import annotations

import httpx
import pytest
import respx

from sources.connectors import brreg_by_orgnr, make_provenance, CONNECTOR_VERSIONS


class TestMakeProvenanceFactory:
    def test_populates_all_new_fields_honestly_and_leaves_the_rest_none(self):
        p = make_provenance("name", "brreg", 0.97, 3)
        assert p.field_name == "name"
        assert p.source_id == "brreg"
        assert p.retrieved_at is not None
        assert p.freshness == p.retrieved_at[:10]  # date prefix of the same instant
        assert p.transform == "raw_fetch"
        assert p.connector_version == CONNECTOR_VERSIONS["brreg"]
        assert p.producer == "0pt-engine"
        # Never guessed — these are filled by later pipeline stages, not at fetch time.
        assert p.quality is None
        assert p.entity_resolution is None
        assert p.artifact_ref is None

    def test_transform_override_is_honored(self):
        p = make_provenance("name", "companies_house", 0.0, 0, transform="unavailable_no_key")
        assert p.transform == "unavailable_no_key"

    def test_unknown_source_id_has_no_fabricated_version(self):
        p = make_provenance("x", "some_future_source", 0.5, 1)
        assert p.connector_version is None  # honestly unknown, not guessed


class TestBrregConnectorProvenance:
    @pytest.mark.asyncio
    @respx.mock
    async def test_real_parsing_path_produces_fully_populated_provenance(self):
        respx.get("https://data.brreg.no/enhetsregisteret/api/enheter/923609016").mock(
            return_value=httpx.Response(200, json={
                "navn": "Volvo Personvagnar Norge AS", "konkurs": False,
                "forretningsadresse": {"adresse": ["Storgata 1"]},
            })
        )
        res = await brreg_by_orgnr("923609016")
        assert res is not None
        assert len(res.provenance) == 3  # name, status, address
        for p in res.provenance:
            assert p.source_id == "brreg"
            assert p.connector_version == "brreg-connector@1"
            assert p.producer == "0pt-engine"
            assert p.retrieved_at is not None
            assert p.transform == "raw_fetch"