from pathlib import Path

from job_research.models import ApecListing, ApecRunMeta, ListingWarning
from job_research.storage import apec_run_paths


def test_apec_models_serialize_expected_listing_shape() -> None:
    listing = ApecListing(
        source="apec",
        source_job_id="123",
        url="https://example.test/job/123",
        title="Data Engineer",
        company="Example",
        location="Paris",
        contract_type="CDI",
        description_text="Build pipelines",
        published_at="2026-06-01",
        fetched_at="2026-06-01T10:00:00Z",
        warnings=[
            ListingWarning(
                field="location",
                message="Location inferred from page text",
            )
        ],
    )
    run_meta = ApecRunMeta(
        derived_queries=["Data Engineer"],
        fetched_count=1,
        normalized_count=1,
        deduplicated_count=1,
        failed_count=0,
        listing_errors=[],
    )

    assert listing.model_dump()["source"] == "apec"
    assert listing.model_dump()["warnings"][0]["field"] == "location"
    assert run_meta.model_dump()["derived_queries"] == ["Data Engineer"]


def test_apec_run_paths_builds_expected_layout(tmp_path: Path) -> None:
    paths = apec_run_paths(tmp_path, run_id="2026-06-01T10-00-00Z")
    run_dir = tmp_path / "apec" / "runs" / "2026-06-01T10-00-00Z"

    assert paths["run_dir"] == run_dir
    assert paths["listings"] == run_dir / "listings.yaml"
    assert paths["run_meta"] == run_dir / "run-meta.yaml"
    assert paths["snapshots"] == run_dir / "snapshots"


def test_apec_run_artifacts_include_snapshot_and_meta(tmp_path: Path) -> None:
    paths = apec_run_paths(tmp_path, run_id="2026-06-01T10-00-00Z")
    paths["snapshots"].mkdir(parents=True, exist_ok=True)

    snapshot = paths["snapshots"] / "job-123.html"
    snapshot.write_text("<html>snapshot</html>", encoding="utf-8")

    assert snapshot.read_text(encoding="utf-8") == "<html>snapshot</html>"