Next alpha stage commit

tests/test_feed_discovery.py

@@ -5,8 +5,11 @@ import csv
 from app import feed_discovery
 from app.feed_discovery import (
     FeedCandidate,
+    apply_source_hierarchy,
     build_gtfs_discovery_manifests,
     enrich_ptna_candidate_from_details,
+    parse_opendata_oepnv_dataset_links,
+    parse_opendata_oepnv_detail_page,
     parse_ptna_country_page,
     parse_ptna_detail_fields,
     select_test_run_candidates,
@@ -105,6 +108,7 @@ def test_build_gtfs_discovery_manifests_from_stubbed_sources(tmp_path, monkeypat
     monkeypatch.setattr(feed_discovery, "fetch_mobility_database_candidates", lambda **_: mobility)
     monkeypatch.setattr(feed_discovery, "fetch_mobility_acceptance_candidates", lambda **_: [])
     monkeypatch.setattr(feed_discovery, "fetch_ptna_candidates", lambda **_: ptna)
+    monkeypatch.setattr(feed_discovery, "fetch_opendata_oepnv_candidates", lambda **_: [])
     monkeypatch.setattr(feed_discovery, "load_curated_ingestable_seed", lambda **_: curated)
 
     report = build_gtfs_discovery_manifests(output_dir=tmp_path, countries=["DE", "CH"], test_limit=10)
@@ -116,6 +120,83 @@ def test_build_gtfs_discovery_manifests_from_stubbed_sources(tmp_path, monkeypat
     assert "ptna" in next(row for row in ingestable_rows if row["url"] == "https://example.test/rnv.zip")["source_basis"]
 
 
+def test_parse_opendata_oepnv_catalog_and_details():
+    catalog_html = """
+    <a href="/ht/de/organisation/verkehrsunternehmen/rnv/startseite?tx_vrrkit_view%5Baction%5D=details&amp;tx_vrrkit_view%5Bcontroller%5D=View&amp;tx_vrrkit_view%5Bdataset_name%5D=soll-fahrplandaten-rnv">
+      <span itemprop="headline">Soll-Fahrplandaten (GTFS - General Transit Feed Specification)</span>
+    </a>
+    """
+    links = parse_opendata_oepnv_dataset_links(catalog_html, "https://www.opendata-oepnv.de/ht/de/datensaetze")
+
+    assert len(links) == 1
+    assert links[0].slug == "soll-fahrplandaten-rnv"
+    assert links[0].title.startswith("Soll-Fahrplandaten")
+
+    detail_html = """
+    <div class="element-header">Soll-Fahrplandaten (GTFS - General Transit Feed Specification)</div>
+    <p>In dieser Ressource hinterlegen wir stets den aktuellsten GTFS-Datensatz.</p>
+    <a href="https://gtfs-sandbox-dds.rnv-online.de/latest/gtfs.zip">Download [ZIP]</a>
+    <td id="dodp_license"><a href="/?id=20">Creative Commons</a></td>
+    """
+    candidate = parse_opendata_oepnv_detail_page(
+        detail_html,
+        detail_url=links[0].url,
+        slug=links[0].slug,
+        title_hint=links[0].title,
+    )
+
+    assert candidate.discovery_source == "opendata_oepnv"
+    assert candidate.provider == "Rhein-Neckar-Verkehr"
+    assert candidate.selected_url == "https://gtfs-sandbox-dds.rnv-online.de/latest/gtfs.zip"
+    assert candidate.data_type == "gtfs"
+    assert candidate.authority_level == "operator_feed"
+    assert candidate.import_policy == "qa_or_override_not_additive"
+
+
+def test_opendata_oepnv_registration_required_is_not_direct_ingestable():
+    detail_html = """
+    <div class="element-header">Deutschlandweite Sollfahrplandaten (GTFS)</div>
+    <p>This Download is only available for registered Users.</p>
+    <td id="dodp_license"><a href="http://www.opendefinition.org/licenses/cc-by">Creative Commons Attribution</a></td>
+    """
+    candidate = parse_opendata_oepnv_detail_page(
+        detail_html,
+        detail_url="https://www.opendata-oepnv.de/ht/de/organisation/delfi/startseite?tx_vrrkit_view%5Bdataset_name%5D=deutschlandweite-sollfahrplandaten-gtfs",
+        slug="deutschlandweite-sollfahrplandaten-gtfs",
+    )
+
+    assert candidate.status == "registration_required"
+    assert candidate.selected_url == ""
+    assert candidate.authority_level == "national_official"
+    assert candidate.overlap_role == "review_baseline"
+    assert candidate.import_policy == "review_before_import"
+
+
+def test_source_hierarchy_marks_mirrors_and_regional_feeds():
+    mirror = FeedCandidate(
+        discovery_source="curated_seed",
+        country="DE",
+        provider="DE generated national",
+        selected_url="https://scraped.data.public-transport.earth/de/gtfs.zip",
+        source_basis="European transport feeds mirror",
+    )
+    regional = FeedCandidate(
+        discovery_source="mobility_database",
+        country="DE",
+        provider="Verkehrsverbund Berlin-Brandenburg",
+        selected_url="https://www.vbb.de/vbbgtfs",
+        is_official="True",
+    )
+
+    apply_source_hierarchy(mirror)
+    apply_source_hierarchy(regional)
+
+    assert mirror.authority_level == "mirror"
+    assert mirror.import_policy == "bootstrap_only"
+    assert regional.authority_level == "regional_authority"
+    assert regional.import_policy == "qa_or_override_not_additive"
+
+
 def test_select_test_run_candidates_keeps_overlapping_german_feeds():
     candidates = [
         FeedCandidate(