from __future__ import annotations

import csv

from app import feed_discovery
from app.feed_discovery import (
    FeedCandidate,
    build_gtfs_discovery_manifests,
    enrich_ptna_candidate_from_details,
    parse_ptna_country_page,
    parse_ptna_detail_fields,
    select_test_run_candidates,
)


def test_parse_ptna_country_and_detail_pages():
    country_html = """
    <table>
      <tr class="gtfs-tablerow">
        <td><a href="routes.php?feed=DE-BE-VBB">DE-BE-VBB</a></td>
        <td><a href="https://www.vbb.de">Verkehrsverbund Berlin-Brandenburg</a></td>
        <td><a href="https://www.vbb.de">VBB Verkehrsverbund Berlin-Brandenburg GmbH</a></td>
        <td>2026-01-01</td>
        <td>2026-12-12</td>
        <td>20260603</td>
        <td><a href="https://www.vbb.de/vbb-services/api-open-data/datensaetze/">2026-06-03</a></td>
        <td>2026-06-03</td>
        <td><a href="/en/gtfs-details.php?feed=DE-BE-VBB">Details, ...</a></td>
      </tr>
    </table>
    """
    candidates = parse_ptna_country_page(
        country_html,
        country="DE",
        page_url="https://ptna.openstreetmap.de/gtfs/DE/index.php",
    )

    assert len(candidates) == 1
    candidate = candidates[0]
    assert candidate.ptna_feed_id == "DE-BE-VBB"
    assert candidate.country == "DE"
    assert candidate.original_release_url == "https://www.vbb.de/vbb-services/api-open-data/datensaetze/"
    assert candidate.details_url == "https://ptna.openstreetmap.de/en/gtfs-details.php?feed=DE-BE-VBB"

    detail_html = """
    <table>
      <tr><td>Release Url</td><td><a href="https://example.test/gtfs.zip">https://example.test/gtfs.zip</a></td></tr>
      <tr><td>Publisher's License</td><td><a href="https://example.test/license">CC BY 4.0</a></td></tr>
      <tr><td>License given for use in OSM</td><td>Attribution on contributor page is sufficient.</td></tr>
      <tr><td>"network:guid"</td><td>DE-BE-VBB</td></tr>
    </table>
    """
    fields = parse_ptna_detail_fields(detail_html, "https://ptna.openstreetmap.de/en/gtfs-details.php?feed=DE-BE-VBB")
    assert fields["publisher's license"] == "CC BY 4.0"
    assert fields["publisher's license href"] == "https://example.test/license"

    enrich_ptna_candidate_from_details(candidate, detail_html, candidate.details_url)
    assert candidate.selected_url == "https://example.test/gtfs.zip"
    assert candidate.license_text == "CC BY 4.0"
    assert "network:guid=DE-BE-VBB" in candidate.notes


def test_build_gtfs_discovery_manifests_from_stubbed_sources(tmp_path, monkeypatch):
    mobility = [
        FeedCandidate(
            discovery_source="mobility_database",
            country="DE",
            provider="Rhein-Neckar-Verkehr",
            feed_name="RNV",
            stable_id="mdb-rnv",
            status="active",
            is_official="True",
            selected_url="https://example.test/rnv.zip",
            direct_download_url="https://example.test/rnv.zip",
            license_url="https://example.test/license",
            features="Shapes|Feed Information",
            priority="P0",
        )
    ]
    ptna = [
        FeedCandidate(
            discovery_source="ptna",
            country="DE",
            provider="Rhein-Neckar-Verkehr",
            feed_name="RNV",
            ptna_feed_id="DE-BW-RNV",
            selected_url="https://example.test/rnv.zip",
            original_release_url="https://example.test/rnv.zip",
            license_text="CC BY 4.0",
            priority="P2",
        )
    ]
    curated = [
        FeedCandidate(
            discovery_source="curated_seed",
            country="CH",
            provider="Swiss national",
            feed_name="CH Swiss national GTFS",
            selected_url="https://example.test/ch.zip",
            license_text="verify",
            features="rail,bus",
            priority="P0",
        )
    ]
    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, "load_curated_ingestable_seed", lambda **_: curated)

    report = build_gtfs_discovery_manifests(output_dir=tmp_path, countries=["DE", "CH"], test_limit=10)

    assert report["counts"]["candidates"] == 2
    assert report["counts"]["ingestable"] == 2
    ingestable_rows = list(csv.DictReader((tmp_path / "gtfs_ingestable_sources.csv").open(encoding="utf-8")))
    assert {row["url"] for row in ingestable_rows} == {"https://example.test/rnv.zip", "https://example.test/ch.zip"}
    assert "ptna" in next(row for row in ingestable_rows if row["url"] == "https://example.test/rnv.zip")["source_basis"]


def test_select_test_run_candidates_keeps_overlapping_german_feeds():
    candidates = [
        FeedCandidate(
            discovery_source="curated_seed",
            country="DE",
            provider="DB Long-distance Rail GTFS.DE",
            selected_url="https://download.gtfs.de/germany/fv_free/latest.zip",
            priority="P1",
        ),
        FeedCandidate(
            discovery_source="mobility_database",
            country="DE",
            provider="Rhein-Neckar-Verkehr",
            selected_url="https://gtfs-sandbox-dds.rnv-online.de/latest/gtfs.zip",
            priority="P0",
        ),
        FeedCandidate(
            discovery_source="curated_seed",
            country="CH",
            provider="Swiss national",
            selected_url="https://gtfs.geops.ch/dl/gtfs_complete.zip",
            priority="P0",
        ),
    ]

    selected = select_test_run_candidates(candidates, limit=3)

    assert len(selected) == 3
    assert any("gtfs.de" in candidate.selected_url for candidate in selected)
    assert any("rnv" in candidate.selected_url for candidate in selected)