gwoe-antragspruefer/tests/test_parlamente.py

"""Tests for parlamente.py adapter parsers — pure functions over fixture HTML.

Reproduces the three regression scenarios from the 2026-04-08 adapter session:

1. PortalaAdapter `_parse_hit_list_cards` had a `doctype` vs. `doctype_full`
   NameError that was hot-fixed live on the prod server (commit 1cb030a).
2. ParLDokAdapter `_hit_to_drucksache` needs to map ParlDok 8.x JSON hit
   dicts to Drucksache objects without losing fraction or date info.
3. PortalaAdapter `_normalize_fraktion` and ParLDokAdapter same-named method
   must yield canonical fraction codes for both comma-lists and embedded
   "MdL (Partei)" patterns.
"""
from app.parlamente import ParLDokAdapter, PortalaAdapter, NRWAdapter, Drucksache


# ─────────────────────────────────────────────────────────────────────────────
# PortalaAdapter — Berlin-style HTML cards
# ─────────────────────────────────────────────────────────────────────────────

BE_CARD_FIXTURE = """
<div class="other-prelude">ignored</div>
<div class="record-card efxRecordRepeater">
  <h3 class="h5"><span>Schwimmstatistik für die dritten Klassen der Berliner Schulen</span></h3>
  <span class="h6">Antrag (Eilantrag)&nbsp;<a href="/files/drs19-3104.pdf">Drucksache 19/3104</a> S. 1 bis 24 vom 31.03.2026</span>
</div>
<div class="record-card efxRecordRepeater">
  <h3 class="h5"><span>Klimaneutrales Bauen im Bestand</span></h3>
  <span class="h6">Antrag CDU, SPD&nbsp;<a href="/files/drs19-3107.pdf">Drucksache 19/3107</a> vom 02.04.2026</span>
</div>
"""


def _make_be_adapter():
    return PortalaAdapter(
        bundesland="BE",
        name="test BE",
        base_url="https://pardok.parlament-berlin.de",
        db_id="lah.lissh",
        wahlperiode=19,
        portala_path="/portala",
        document_type=None,
    )


class TestPortalaAdapterCardParser:
    """Issue: doctype/doctype_full NameError (hot-fix 1cb030a)."""

    def test_parses_two_cards_without_nameerror(self):
        """Smoke test — must NOT raise NameError or any other exception.

        Pre-fix this method referenced an undefined ``doctype`` variable
        in the query-filter branch when computing the haystack. The fix
        renamed it to ``doctype_full``. A direct call covers both branches.
        """
        adapter = _make_be_adapter()
        result = adapter._parse_hit_list_cards(BE_CARD_FIXTURE, query_filter="")
        assert len(result) == 2

    def test_first_card_extracts_drucksache_and_title(self):
        adapter = _make_be_adapter()
        result = adapter._parse_hit_list_cards(BE_CARD_FIXTURE, query_filter="")
        d = result[0]
        assert d.drucksache == "19/3104"
        assert "Schwimmstatistik" in d.title
        assert d.datum == "2026-03-31"
        assert d.bundesland == "BE"

    def test_second_card_extracts_fraktionen_from_h6(self):
        """Card 2 packs CDU+SPD into the type line — must split out cleanly."""
        adapter = _make_be_adapter()
        result = adapter._parse_hit_list_cards(BE_CARD_FIXTURE, query_filter="")
        d = result[1]
        assert d.drucksache == "19/3107"
        assert d.fraktionen == ["CDU", "SPD"]
        # The typ string should have the parties stripped back out
        assert d.typ.strip() == "Antrag"

    def test_pdf_link_is_absolute_url(self):
        adapter = _make_be_adapter()
        result = adapter._parse_hit_list_cards(BE_CARD_FIXTURE, query_filter="")
        assert result[0].link.startswith("https://pardok.parlament-berlin.de/")
        assert result[0].link.endswith(".pdf")

    def test_query_filter_uses_doctype_full_not_doctype(self):
        """Regression: the filter branch references doctype_full, not doctype.

        Pre-fix this raised NameError as soon as a query was passed.
        """
        adapter = _make_be_adapter()
        # Schwimmstatistik matches card 1, Klimaneutral matches card 2
        result = adapter._parse_hit_list_cards(BE_CARD_FIXTURE, query_filter="Schwimm")
        assert len(result) == 1
        assert result[0].drucksache == "19/3104"


# ─────────────────────────────────────────────────────────────────────────────
# PortalaAdapter — LSA-style Perl-Dump records
# ─────────────────────────────────────────────────────────────────────────────

LSA_DUMP_FIXTURE = """
<pre>$VAR1 = {
  'WEV06' => [{ 'main' => 'Demokratie beginnt im Klassenzimmer' }],
  'WEV32' => [{
    'main' => 'Antrag B\\x{fc}ndnis 90/Die Gr\\x{fc}nen 06.03.2026 Drucksache <b>8/6726</b> ...',
    '5' => 'drs/wp8/drs/d6726lan.pdf'
  }]
}</pre>
<pre>$VAR1 = {
  'WEV06' => [{ 'main' => 'Andere Drucksache ohne Schul-Bezug' }],
  'WEV32' => [{
    'main' => 'Antrag CDU, SPD 14.01.2026 Drucksache <b>8/6171</b> ...',
    '5' => 'drs/wp8/drs/d6171lan.pdf'
  }]
}</pre>
"""


def _make_lsa_adapter():
    return PortalaAdapter(
        bundesland="LSA",
        name="test LSA",
        base_url="https://padoka.landtag.sachsen-anhalt.de",
        db_id="lsa.lissh",
        wahlperiode=8,
        portala_path="/portal",
        document_type="Antrag",
    )


class TestPortalaAdapterDumpParser:
    def test_parses_two_dump_records(self):
        adapter = _make_lsa_adapter()
        result = adapter._parse_hit_list_dump(LSA_DUMP_FIXTURE, query_filter="")
        assert len(result) == 2

    def test_extracts_drucksache_from_perl_dump(self):
        adapter = _make_lsa_adapter()
        result = adapter._parse_hit_list_dump(LSA_DUMP_FIXTURE, query_filter="")
        assert result[0].drucksache == "8/6726"
        assert result[1].drucksache == "8/6171"

    def test_decodes_perl_hex_escapes_in_urheber(self):
        """The first record has \\x{fc} (ü) and \\x{e4} (ä) in WEV32."""
        adapter = _make_lsa_adapter()
        result = adapter._parse_hit_list_dump(LSA_DUMP_FIXTURE, query_filter="")
        # GRÜNE should be detected from "Bündnis 90/Die Grünen"
        assert "GRÜNE" in result[0].fraktionen

    def test_extracts_date_iso(self):
        adapter = _make_lsa_adapter()
        result = adapter._parse_hit_list_dump(LSA_DUMP_FIXTURE, query_filter="")
        assert result[0].datum == "2026-03-06"
        assert result[1].datum == "2026-01-14"

    def test_pdf_url_uses_pdf_url_prefix(self):
        adapter = _make_lsa_adapter()
        result = adapter._parse_hit_list_dump(LSA_DUMP_FIXTURE, query_filter="")
        assert result[0].link == (
            "https://padoka.landtag.sachsen-anhalt.de/files/drs/wp8/drs/d6726lan.pdf"
        )

    def test_client_side_query_filter(self):
        adapter = _make_lsa_adapter()
        result = adapter._parse_hit_list_dump(LSA_DUMP_FIXTURE, query_filter="Demokratie")
        assert len(result) == 1
        assert result[0].drucksache == "8/6726"


# ─────────────────────────────────────────────────────────────────────────────
# PortalaAdapter — Auto-detection between dump and card formats
# ─────────────────────────────────────────────────────────────────────────────

class TestPortalaAdapterAutoDetect:
    def test_dump_html_routes_to_dump_parser(self):
        adapter = _make_lsa_adapter()
        result = adapter._parse_hit_list_html(LSA_DUMP_FIXTURE, query_filter="")
        assert len(result) == 2

    def test_card_html_routes_to_card_parser(self):
        adapter = _make_be_adapter()
        result = adapter._parse_hit_list_html(BE_CARD_FIXTURE, query_filter="")
        assert len(result) == 2


# ─────────────────────────────────────────────────────────────────────────────
# Adapter._normalize_fraktion — Roundtrip-Test über eine echte Instanz
#
# Die ausführliche Pattern-Sammlung lebt nach #55 in tests/test_parteien.py.
# Hier verifizieren wir nur, dass der Adapter-Shim die zentrale Funktion
# tatsächlich aufruft und das Bundesland korrekt durchreicht.
# ─────────────────────────────────────────────────────────────────────────────

class TestAdapterNormalizeFraktionRoundtrip:
    def test_portala_lsa_adapter_instance(self):
        adapter = _make_lsa_adapter()
        assert "CDU" in adapter._normalize_fraktion("CDU")
        assert adapter._normalize_fraktion("BÜNDNIS 90/DIE GRÜNEN") == ["GRÜNE"]

    def test_portala_be_adapter_instance(self):
        adapter = _make_be_adapter()
        out = adapter._normalize_fraktion("Senat von Berlin")
        assert "Landesregierung" in out

    def test_empty_string(self):
        adapter = _make_lsa_adapter()
        assert adapter._normalize_fraktion("") == []

    def test_freie_waehler_disambiguates_by_adapter_bundesland(self):
        # BB-Adapter → BVB-FW, RP-Adapter → FREIE WÄHLER. Das ist der
        # eigentliche Mehrwert von #55, hier roundtripped via Adapter.
        from app.parlamente import PortalaAdapter
        bb = PortalaAdapter(
            bundesland="BB", name="test BB",
            base_url="https://www.parlamentsdokumentation.brandenburg.de",
            db_id="lap.lap8", wahlperiode=8,
            portala_path="/portal", document_type="Antrag",
        )
        rp = PortalaAdapter(
            bundesland="RP", name="test RP",
            base_url="https://opal.rlp.de",
            db_id="rlp.opal", wahlperiode=18,
            portala_path="/portal", document_type="Antrag",
        )
        assert bb._normalize_fraktion("FREIE WÄHLER") == ["BVB-FW"]
        assert rp._normalize_fraktion("FREIE WÄHLER") == ["FREIE WÄHLER"]


# ─────────────────────────────────────────────────────────────────────────────
# ParLDokAdapter — JSON hit dict → Drucksache mapping
# ─────────────────────────────────────────────────────────────────────────────

def _make_mv_adapter():
    return ParLDokAdapter(
        bundesland="MV",
        name="test MV",
        base_url="https://www.dokumentation.landtag-mv.de",
        wahlperiode=8,
        prefix="/parldok",
        document_typ="Antrag",
    )


SAMPLE_PARLDOK_HIT = {
    "id": 70748,
    "title": "Zweckentfremdung von Sondervermögen des Bundes beenden",
    "date": "18.03.2026",
    "prelink": "/dokument/70748",
    "link": "/dokument/70748#navpanes=0",
    "authorhtml": "FDP",
    "kind": "Drucksache",
    "type": "Antrag",
    "lp": 8,
    "number": "6409",
}


class TestParLDokAdapterHitMapping:
    def test_hit_to_drucksache_basic(self):
        adapter = _make_mv_adapter()
        d = adapter._hit_to_drucksache(SAMPLE_PARLDOK_HIT)
        assert d is not None
        assert d.drucksache == "8/6409"
        assert d.title == "Zweckentfremdung von Sondervermögen des Bundes beenden"
        assert d.datum == "2026-03-18"
        assert d.fraktionen == ["FDP"]
        assert d.typ == "Antrag"
        assert d.bundesland == "MV"

    def test_pdf_link_strips_navpanes_fragment_and_prepends_prefix(self):
        adapter = _make_mv_adapter()
        d = adapter._hit_to_drucksache(SAMPLE_PARLDOK_HIT)
        assert d.link == "https://www.dokumentation.landtag-mv.de/parldok/dokument/70748"
        assert "#navpanes" not in d.link

    def test_missing_lp_returns_none(self):
        adapter = _make_mv_adapter()
        hit = dict(SAMPLE_PARLDOK_HIT)
        del hit["lp"]
        assert adapter._hit_to_drucksache(hit) is None

    def test_mdl_with_party_in_parens(self):
        """MV often packs the MdL into authorhtml: 'Thomas X (AfD)'."""
        adapter = _make_mv_adapter()
        hit = dict(SAMPLE_PARLDOK_HIT, authorhtml="Thomas de Jesus Fernandes (AfD)")
        d = adapter._hit_to_drucksache(hit)
        assert "AfD" in d.fraktionen

    def test_landesregierung_detection(self):
        adapter = _make_mv_adapter()
        hit = dict(SAMPLE_PARLDOK_HIT, authorhtml="Ministerium der Finanzen")
        d = adapter._hit_to_drucksache(hit)
        assert "Landesregierung" in d.fraktionen


class TestParLDokFulltextIdSanitization:
    """Reverse-engineered from bundle.js pd.getFulltextId — must mirror exactly.

    Even though server-side fulltext is currently disabled (#18), the helper
    is kept around in code as documentation. If it ever gets re-activated,
    the sanitization must still match the SPA's behavior 1:1.
    """

    def test_simple_word_unchanged(self):
        assert ParLDokAdapter._fulltext_id("Schule") == "Schule"

    def test_whitespace_becomes_dash(self):
        assert ParLDokAdapter._fulltext_id("Klima Schutz") == "Klima-Schutz"

    def test_umlauts_become_dashes(self):
        # The JS regex is /[^a-zA-z0-9]/ — note the lowercase z, deliberate.
        # Umlauts are non-ASCII so they get replaced.
        assert ParLDokAdapter._fulltext_id("Bürger") == "B-rger"

    def test_punctuation_becomes_dashes(self):
        assert ParLDokAdapter._fulltext_id("CO2-Emission") == "CO2-Emission"


# ─────────────────────────────────────────────────────────────────────────────
# Adapter registry sanity
# ─────────────────────────────────────────────────────────────────────────────

class TestAdapterRegistry:
    def test_active_adapters_present(self):
        from app.parlamente import ADAPTERS
        for code in ["NRW", "MV", "BE", "LSA"]:
            assert code in ADAPTERS, f"missing adapter for {code}"

    def test_get_adapter_returns_none_for_unknown(self):
        from app.parlamente import get_adapter
        assert get_adapter("XX") is None

    def test_mv_adapter_is_parldok_instance(self):
        from app.parlamente import ADAPTERS
        assert isinstance(ADAPTERS["MV"], ParLDokAdapter)

    def test_be_adapter_is_portala_instance(self):
        from app.parlamente import ADAPTERS
        assert isinstance(ADAPTERS["BE"], PortalaAdapter)

    def test_lsa_adapter_is_portala_instance(self):
        from app.parlamente import ADAPTERS
        assert isinstance(ADAPTERS["LSA"], PortalaAdapter)