diff --git a/app/parlamente.py b/app/parlamente.py
index db35487..8ec3cc6 100644
--- a/app/parlamente.py
+++ b/app/parlamente.py
@@ -443,7 +443,9 @@ class PortalaAdapter(ParlamentAdapter):
out.append("CDU")
if has(r"\bSPD\b"):
out.append("SPD")
- if has(r"\bFDP\b"):
+ # F.D.P. (with dots, historical SH/HB-style) and FDP (modern) — same
+ # flexible pattern as ParLDokAdapter so the test suite stays consistent.
+ if has(r"\bF\.?\s*D\.?\s*P\.?\b"):
out.append("FDP")
if has(r"\bAFD\b"):
out.append("AfD")
@@ -451,7 +453,9 @@ class PortalaAdapter(ParlamentAdapter):
out.append("LINKE")
if has(r"\bBSW\b"):
out.append("BSW")
- if has(r"LANDESREGIERUNG|SENAT VON BERLIN|REGIERENDE[RN]?\s+BÜRGERMEISTER|MINISTER\b|STAATSKANZLEI"):
+ # MINISTERIUM/MINISTER beide treffen — \bMINISTER ohne abschließende
+ # Wortgrenze, damit "Ministerium der Finanzen" mit erfasst wird.
+ if has(r"LANDESREGIERUNG|SENAT VON BERLIN|REGIERENDE[RN]?\s+BÜRGERMEISTER|\bMINISTER|STAATSKANZLEI|MINISTERPRÄSIDENT"):
out.append("Landesregierung")
return out
@@ -944,7 +948,10 @@ class ParLDokAdapter(ParlamentAdapter):
out.append("LINKE")
if re.search(r"\bBSW\b", u):
out.append("BSW")
- if re.search(r"LANDESREGIERUNG|MINISTER\b|STAATSKANZLEI|MINISTERPRÄSIDENT", u):
+ # \bMINISTER ohne abschließende Wortgrenze, damit MINISTERIUM
+ # auch trifft (z.B. "Ministerium der Finanzen" als Urheber von
+ # Landesregierungs-Drucksachen).
+ if re.search(r"LANDESREGIERUNG|\bMINISTER|STAATSKANZLEI|MINISTERPRÄSIDENT", u):
out.append("Landesregierung")
return out
diff --git a/pytest.ini b/pytest.ini
new file mode 100644
index 0000000..4dc8d52
--- /dev/null
+++ b/pytest.ini
@@ -0,0 +1,5 @@
+[pytest]
+testpaths = tests
+asyncio_mode = auto
+filterwarnings =
+ ignore::DeprecationWarning
diff --git a/requirements-dev.txt b/requirements-dev.txt
new file mode 100644
index 0000000..0f66d22
--- /dev/null
+++ b/requirements-dev.txt
@@ -0,0 +1,13 @@
+# Test- und Entwicklungs-Abhängigkeiten — getrennt von requirements.txt,
+# damit der prod-Container sie nicht installieren muss.
+#
+# Installation lokal:
+# pip install -r requirements.txt -r requirements-dev.txt
+#
+# Tests laufen lassen:
+# pytest -v tests/
+
+-r requirements.txt
+
+pytest>=8.0.0
+pytest-asyncio>=0.24.0
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/tests/conftest.py b/tests/conftest.py
new file mode 100644
index 0000000..9f50970
--- /dev/null
+++ b/tests/conftest.py
@@ -0,0 +1,51 @@
+"""Shared pytest fixtures and path setup.
+
+Stubs heavy optional dependencies (``fitz``/PyMuPDF, ``bs4``/BeautifulSoup,
+``openai``) so the test suite can run without the full prod requirements
+installed. The tests in this directory are pure unit tests over parser
+logic and prompt formatters — they neither parse PDFs nor make HTTP
+calls, so the stubs are inert placeholders that satisfy the import
+machinery but never get exercised.
+
+If a test ever does need real PyMuPDF or httpx integration, give it a
+fixture marked with ``@pytest.mark.integration`` and skip it by default.
+"""
+import sys
+import types
+from pathlib import Path
+
+# Make the `app` package importable when pytest is run from the webapp/ root.
+ROOT = Path(__file__).resolve().parent.parent
+sys.path.insert(0, str(ROOT))
+
+
+def _stub(name: str, **attrs) -> None:
+ if name in sys.modules:
+ return
+ mod = types.ModuleType(name)
+ for k, v in attrs.items():
+ setattr(mod, k, v)
+ sys.modules[name] = mod
+
+
+_stub("fitz") # PyMuPDF — used for PDF parsing, not in unit tests
+_stub("bs4", BeautifulSoup=lambda *a, **kw: None) # only needed by NRWAdapter live calls
+_stub("openai", OpenAI=lambda **kw: None) # only needed by embeddings live calls
+
+
+# pydantic_settings is a small but external dep that's not in the test
+# environment. Stub it with a minimal BaseSettings shim so app.config can
+# import without crashing — the tests don't actually read settings values.
+class _BaseSettingsShim:
+ model_config: dict = {}
+
+ def __init__(self, **kwargs):
+ for k, v in kwargs.items():
+ setattr(self, k, v)
+
+
+def _settings_config_dict(**kwargs):
+ return kwargs
+
+
+_stub("pydantic_settings", BaseSettings=_BaseSettingsShim, SettingsConfigDict=_settings_config_dict)
diff --git a/tests/test_analyzer.py b/tests/test_analyzer.py
new file mode 100644
index 0000000..a42fe32
--- /dev/null
+++ b/tests/test_analyzer.py
@@ -0,0 +1,62 @@
+"""Tests for analyzer.py JSON-stripping logic.
+
+Reproduces the markdown-codeblock-stripping in the LLM retry loop. Real
+Qwen responses sometimes wrap their JSON in ```json …``` fences (despite
+the prompt asking for raw JSON), and the analyzer must tolerate that
+without resorting to retries.
+"""
+import json
+import sys
+import types
+
+# Stub openai before importing analyzer
+if "openai" not in sys.modules:
+ openai_stub = types.ModuleType("openai")
+ openai_stub.OpenAI = lambda **kw: None
+ sys.modules["openai"] = openai_stub
+
+
+def _strip_markdown_fences(content: str) -> str:
+ """Mirror the analyzer's markdown-stripping snippet so we can unit-test
+ the parsing rules without actually invoking the LLM.
+
+ Keep this in sync with analyzer.py around the `if content.startswith("```")`
+ branch — if the analyzer changes, this helper changes too. The point of
+ the duplication is that the analyzer's stripping is buried in an async
+ LLM call that we cannot easily unit-test directly.
+ """
+ content = content.strip()
+ if content.startswith("```"):
+ content = content.split("\n", 1)[1]
+ if content.endswith("```"):
+ content = content.rsplit("```", 1)[0]
+ if content.startswith("```json"):
+ content = content[7:]
+ return content.strip()
+
+
+SAMPLE_JSON = '{"gwoeScore": 7.0, "title": "Test"}'
+
+
+class TestMarkdownStripping:
+ def test_plain_json_unchanged(self):
+ assert _strip_markdown_fences(SAMPLE_JSON) == SAMPLE_JSON
+
+ def test_json_in_markdown_fence(self):
+ wrapped = f"```json\n{SAMPLE_JSON}\n```"
+ cleaned = _strip_markdown_fences(wrapped)
+ assert json.loads(cleaned)["gwoeScore"] == 7.0
+
+ def test_json_in_plain_fence(self):
+ wrapped = f"```\n{SAMPLE_JSON}\n```"
+ cleaned = _strip_markdown_fences(wrapped)
+ assert json.loads(cleaned)["gwoeScore"] == 7.0
+
+ def test_leading_whitespace_stripped(self):
+ wrapped = f" \n {SAMPLE_JSON} \n "
+ assert json.loads(_strip_markdown_fences(wrapped))["gwoeScore"] == 7.0
+
+ def test_trailing_fence_stripped(self):
+ wrapped = f"{SAMPLE_JSON}\n```"
+ cleaned = _strip_markdown_fences(wrapped)
+ assert json.loads(cleaned)["gwoeScore"] == 7.0
diff --git a/tests/test_bundeslaender.py b/tests/test_bundeslaender.py
new file mode 100644
index 0000000..0660b8f
--- /dev/null
+++ b/tests/test_bundeslaender.py
@@ -0,0 +1,81 @@
+"""Tests for bundeslaender.py — sanity over 16-state registry.
+
+Includes the #48 classification regression: TH must be ParlDok, HB must
+be StarWeb, SN must be Eigensystem (not ParlDok).
+"""
+from app.bundeslaender import BUNDESLAENDER, get, aktive_bundeslaender, alle_bundeslaender
+
+
+class TestRegistryStructure:
+ def test_sixteen_bundeslaender(self):
+ assert len(BUNDESLAENDER) == 16
+
+ def test_codes_are_uppercase(self):
+ for code in BUNDESLAENDER:
+ assert code.isupper(), f"{code} is not uppercase"
+
+ def test_each_entry_has_naechste_wahl_or_none(self):
+ for code, bl in BUNDESLAENDER.items():
+ assert bl.naechste_wahl is None or len(bl.naechste_wahl) == 10
+
+ def test_wahlperiode_is_positive_integer(self):
+ for bl in BUNDESLAENDER.values():
+ assert isinstance(bl.wahlperiode, int) and bl.wahlperiode > 0
+
+
+class TestActiveBundeslaender:
+ def test_four_active_bundeslaender(self):
+ active = aktive_bundeslaender()
+ codes = {bl.code for bl in active}
+ assert codes == {"NRW", "LSA", "MV", "BE"}
+
+ def test_alle_bundeslaender_returns_all_sixteen(self):
+ assert len(alle_bundeslaender()) == 16
+
+ def test_alle_bundeslaender_active_first(self):
+ out = alle_bundeslaender()
+ active_codes = {bl.code for bl in aktive_bundeslaender()}
+ # The first len(active) entries must all be active
+ for bl in out[: len(active_codes)]:
+ assert bl.code in active_codes
+
+
+class TestGetHelper:
+ def test_returns_bundesland_for_known_code(self):
+ bl = get("NRW")
+ assert bl is not None
+ assert bl.name == "Nordrhein-Westfalen"
+
+ def test_returns_none_for_unknown_code(self):
+ assert get("XX") is None
+
+
+class TestClassificationFix48:
+ """Regression: #48 corrected three doku_system entries that the
+ follow-up adapter issues depend on."""
+
+ def test_th_is_parldok_not_starweb(self):
+ assert BUNDESLAENDER["TH"].doku_system == "ParlDok"
+
+ def test_hb_is_starweb_not_paris(self):
+ """PARiS is just a StarWeb skin — must be classified as StarWeb."""
+ assert BUNDESLAENDER["HB"].doku_system == "StarWeb"
+
+ def test_sn_is_eigensystem_not_parldok(self):
+ """EDAS is ASP.NET-Webforms, NOT ParlDok-compatible with MV."""
+ assert BUNDESLAENDER["SN"].doku_system == "Eigensystem"
+
+
+class TestWahltermineSane:
+ """All upcoming elections must be in chronological order and in the
+ near future (sanity check that someone has not pasted a 1990 date)."""
+
+ def test_no_election_before_2026(self):
+ for bl in BUNDESLAENDER.values():
+ if bl.naechste_wahl:
+ assert bl.naechste_wahl >= "2026-01-01"
+
+ def test_no_election_after_2035(self):
+ for bl in BUNDESLAENDER.values():
+ if bl.naechste_wahl:
+ assert bl.naechste_wahl < "2035-01-01"
diff --git a/tests/test_embeddings.py b/tests/test_embeddings.py
new file mode 100644
index 0000000..48ee6b5
--- /dev/null
+++ b/tests/test_embeddings.py
@@ -0,0 +1,151 @@
+"""Tests for embeddings.py prompt formatting.
+
+Reproduces the LLM-Halluzinations-Bug from the 2026-04-08 session
+(commits 1b5fd96 + bc7f4a6): the original ``format_quotes_for_prompt``
+rendered each chunk as ``- S. X: "text"`` without any reference to the
+programme name. As a result the LLM hallucinated familiar source labels
+("FDP NRW Wahlprogramm 2022") for chunks that actually came from MV/BE,
+because that was the strongest training-set prior for budget-policy
+citations.
+
+Fix: prepend the fully-qualified PROGRAMME[programm_id]["name"] to each
+quote.
+"""
+import sys
+import types
+
+# Stub openai before importing embeddings, since the test environment may
+# not have it installed and we don't actually need to make API calls.
+if "openai" not in sys.modules:
+ openai_stub = types.ModuleType("openai")
+ openai_stub.OpenAI = lambda **kw: None
+ sys.modules["openai"] = openai_stub
+
+from app.embeddings import _chunk_source_label, format_quotes_for_prompt
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# _chunk_source_label — fully-qualified programme name + page
+# ─────────────────────────────────────────────────────────────────────────────
+
+class TestChunkSourceLabel:
+ def test_known_programme_id(self):
+ chunk = {"programm_id": "fdp-mv-2021", "seite": 73, "text": "..."}
+ label = _chunk_source_label(chunk)
+ assert "FDP Mecklenburg-Vorpommern" in label
+ assert "S. 73" in label
+
+ def test_known_programme_id_for_be(self):
+ chunk = {"programm_id": "spd-be-2023", "seite": 24, "text": "..."}
+ label = _chunk_source_label(chunk)
+ assert "SPD Berlin" in label
+ assert "2021" in label # the BE-2023.pdf files contain 2021er programmes
+ assert "S. 24" in label
+
+ def test_unknown_programme_id_falls_back_to_id(self):
+ chunk = {"programm_id": "fake-xx-9999", "seite": 1, "text": "..."}
+ label = _chunk_source_label(chunk)
+ # Should not crash, should at least include the id and the page
+ assert "fake-xx-9999" in label
+ assert "S. 1" in label
+
+ def test_missing_seite_uses_questionmark(self):
+ chunk = {"programm_id": "cdu-mv-2021", "text": "..."}
+ label = _chunk_source_label(chunk)
+ assert "?" in label
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# format_quotes_for_prompt — every chunk must carry programme identification
+# ─────────────────────────────────────────────────────────────────────────────
+
+EXAMPLE_QUOTES = {
+ "FDP": {
+ "wahlprogramm": [
+ {
+ "programm_id": "fdp-mv-2021",
+ "partei": "FDP",
+ "typ": "wahlprogramm",
+ "seite": 73,
+ "text": "Die Grundsätze von Wirtschaftlichkeit und Sparsamkeit",
+ "similarity": 0.63,
+ },
+ ],
+ "parteiprogramm": [
+ {
+ "programm_id": "fdp-grundsatz",
+ "partei": "FDP",
+ "typ": "parteiprogramm",
+ "seite": 93,
+ "text": "Liberale Marktwirtschaft erfordert solide Haushalte",
+ "similarity": 0.60,
+ },
+ ],
+ },
+ "SPD": {
+ "wahlprogramm": [
+ {
+ "programm_id": "spd-mv-2021",
+ "partei": "SPD",
+ "typ": "wahlprogramm",
+ "seite": 22,
+ "text": "Verkehrswende weg vom motorisierten Individualverkehr",
+ "similarity": 0.58,
+ },
+ ],
+ },
+}
+
+
+class TestFormatQuotesForPrompt:
+ def test_empty_input_returns_empty_string(self):
+ assert format_quotes_for_prompt({}) == ""
+
+ def test_renders_party_headings(self):
+ out = format_quotes_for_prompt(EXAMPLE_QUOTES)
+ assert "### FDP" in out
+ assert "### SPD" in out
+
+ def test_every_chunk_has_programme_name(self):
+ """Regression: pre-fix this used "S. X:" only, no programme name —
+ the LLM then hallucinated NRW-2022 sources from training data."""
+ out = format_quotes_for_prompt(EXAMPLE_QUOTES)
+ # Each of the three chunks must reference its source programme
+ assert "FDP Mecklenburg-Vorpommern" in out
+ assert "FDP Grundsatzprogramm" in out
+ assert "SPD Mecklenburg-Vorpommern" in out
+
+ def test_contains_strict_citation_instruction(self):
+ """The prompt header must explicitly forbid hallucinated sources."""
+ out = format_quotes_for_prompt(EXAMPLE_QUOTES)
+ assert "ausschließlich" in out.lower() or "verbatim" in out.lower() or "wörtlich" in out.lower()
+
+ def test_no_nrw_2022_appears_unless_chunks_are_actually_nrw(self):
+ """Sanity: a pure MV+SPD chunk set must not mention NRW anywhere."""
+ out = format_quotes_for_prompt(EXAMPLE_QUOTES)
+ assert "NRW" not in out
+ assert "Nordrhein-Westfalen" not in out
+
+ def test_renders_separate_blocks_for_wahl_and_parteiprogramm(self):
+ out = format_quotes_for_prompt(EXAMPLE_QUOTES)
+ assert "**Wahlprogramm:**" in out
+ assert "**Grundsatzprogramm:**" in out
+
+ def test_text_truncated_at_500_chars(self):
+ long_chunk = {
+ "FDP": {
+ "wahlprogramm": [
+ {
+ "programm_id": "fdp-mv-2021",
+ "seite": 1,
+ "text": "A" * 1000, # 1000 chars → should be truncated
+ "similarity": 0.7,
+ }
+ ],
+ }
+ }
+ out = format_quotes_for_prompt(long_chunk)
+ # Truncation marker
+ assert "..." in out
+ # Original chunk text 1000 chars not present in full
+ assert "A" * 1000 not in out
diff --git a/tests/test_parlamente.py b/tests/test_parlamente.py
new file mode 100644
index 0000000..75c0ad6
--- /dev/null
+++ b/tests/test_parlamente.py
@@ -0,0 +1,328 @@
+"""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 = """
+ignored
+
+
Schwimmstatistik für die dritten Klassen der Berliner Schulen
+
Antrag (Eilantrag) Drucksache 19/3104 S. 1 bis 24 vom 31.03.2026
+
$VAR1 = {
+ 'WEV06' => [{ 'main' => 'Demokratie beginnt im Klassenzimmer' }],
+ 'WEV32' => [{
+ 'main' => 'Antrag B\\x{fc}ndnis 90/Die Gr\\x{fc}nen 06.03.2026 Drucksache 8/6726 ...',
+ '5' => 'drs/wp8/drs/d6726lan.pdf'
+ }]
+}
+$VAR1 = {
+ 'WEV06' => [{ 'main' => 'Andere Drucksache ohne Schul-Bezug' }],
+ 'WEV32' => [{
+ 'main' => 'Antrag CDU, SPD 14.01.2026 Drucksache 8/6171 ...',
+ '5' => 'drs/wp8/drs/d6171lan.pdf'
+ }]
+}
+"""
+
+
+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
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# PortalaAdapter._normalize_fraktion — canonical fraction codes
+# ─────────────────────────────────────────────────────────────────────────────
+
+class TestPortalaAdapterNormalizeFraktion:
+ def test_comma_separated_list(self):
+ out = PortalaAdapter._normalize_fraktion("CDU, SPD, F.D.P.")
+ assert "CDU" in out and "SPD" in out and "FDP" in out
+
+ def test_buendnis_90_die_gruenen(self):
+ out = PortalaAdapter._normalize_fraktion("BÜNDNIS 90/DIE GRÜNEN")
+ assert out == ["GRÜNE"]
+
+ def test_die_linke(self):
+ out = PortalaAdapter._normalize_fraktion("DIE LINKE")
+ assert out == ["LINKE"]
+
+ def test_bsw(self):
+ out = PortalaAdapter._normalize_fraktion("BSW")
+ assert out == ["BSW"]
+
+ def test_landesregierung_keywords(self):
+ out = PortalaAdapter._normalize_fraktion("Senat von Berlin")
+ assert "Landesregierung" in out
+
+ def test_empty_string(self):
+ assert PortalaAdapter._normalize_fraktion("") == []
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# 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)
diff --git a/tests/test_wahlprogramme.py b/tests/test_wahlprogramme.py
new file mode 100644
index 0000000..dedbfd2
--- /dev/null
+++ b/tests/test_wahlprogramme.py
@@ -0,0 +1,118 @@
+"""Tests for wahlprogramme.py — registry consistency + file existence."""
+from app.wahlprogramme import (
+ WAHLPROGRAMME,
+ REFERENZEN_PATH,
+ get_wahlprogramm,
+ parteien_mit_wahlprogramm,
+)
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Registry consistency
+# ─────────────────────────────────────────────────────────────────────────────
+
+class TestRegistryStructure:
+ def test_active_bundeslaender_present(self):
+ for code in ["NRW", "LSA", "MV", "BE"]:
+ assert code in WAHLPROGRAMME, f"missing wahlprogramme entry for {code}"
+
+ def test_each_entry_has_required_keys(self):
+ required = {"file", "titel", "partei", "jahr", "seiten"}
+ for bl, parteien in WAHLPROGRAMME.items():
+ for partei, info in parteien.items():
+ missing = required - set(info.keys())
+ assert not missing, f"{bl}/{partei} missing keys: {missing}"
+
+ def test_jahr_is_integer(self):
+ for bl, parteien in WAHLPROGRAMME.items():
+ for partei, info in parteien.items():
+ assert isinstance(info["jahr"], int), f"{bl}/{partei} jahr not int"
+
+ def test_seiten_is_positive_integer(self):
+ for bl, parteien in WAHLPROGRAMME.items():
+ for partei, info in parteien.items():
+ assert isinstance(info["seiten"], int)
+ assert info["seiten"] > 0
+
+ def test_file_extension_is_pdf(self):
+ for bl, parteien in WAHLPROGRAMME.items():
+ for partei, info in parteien.items():
+ assert info["file"].endswith(".pdf")
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# File existence — every registered file must exist on disk
+# ─────────────────────────────────────────────────────────────────────────────
+
+class TestFileExistence:
+ """Catches typos in the file field that would silently break embedding
+ indexing or PDF download links."""
+
+ def test_every_registered_pdf_exists(self):
+ missing = []
+ for bl, parteien in WAHLPROGRAMME.items():
+ for partei, info in parteien.items():
+ path = REFERENZEN_PATH / info["file"]
+ if not path.exists():
+ missing.append(f"{bl}/{partei}: {info['file']}")
+ assert not missing, "missing PDFs:\n " + "\n ".join(missing)
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# Lookup helpers
+# ─────────────────────────────────────────────────────────────────────────────
+
+class TestGetWahlprogramm:
+ def test_returns_dict_for_known_combination(self):
+ info = get_wahlprogramm("MV", "CDU")
+ assert info is not None
+ assert info["partei"] == "CDU Mecklenburg-Vorpommern"
+
+ def test_returns_none_for_unknown_bundesland(self):
+ assert get_wahlprogramm("XX", "CDU") is None
+
+ def test_returns_none_for_unknown_partei(self):
+ assert get_wahlprogramm("NRW", "BSW") is None
+
+
+class TestParteienMitWahlprogramm:
+ def test_nrw_has_five_parteien(self):
+ parteien = parteien_mit_wahlprogramm("NRW")
+ assert len(parteien) == 5
+ assert set(parteien) == {"CDU", "SPD", "GRÜNE", "FDP", "AfD"}
+
+ def test_mv_has_six_parteien(self):
+ parteien = parteien_mit_wahlprogramm("MV")
+ assert set(parteien) == {"CDU", "SPD", "GRÜNE", "FDP", "AfD", "LINKE"}
+
+ def test_be_has_five_parteien(self):
+ parteien = parteien_mit_wahlprogramm("BE")
+ assert set(parteien) == {"CDU", "SPD", "GRÜNE", "LINKE", "AfD"}
+
+ def test_unknown_bundesland_empty_list(self):
+ assert parteien_mit_wahlprogramm("XX") == []
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# embeddings.PROGRAMME consistency cross-check
+# ─────────────────────────────────────────────────────────────────────────────
+
+class TestEmbeddingsRegistryConsistency:
+ """Every entry in WAHLPROGRAMME must also exist in embeddings.PROGRAMME
+ so the indexer can find it. Mismatch is the kind of bug a manual smoke
+ misses but would show up during indexing."""
+
+ def test_every_wahlprogramm_has_embeddings_entry(self):
+ from app.embeddings import PROGRAMME
+
+ # Build expected programm_id from filename: "cdu-mv-2021.pdf" → "cdu-mv-2021"
+ missing = []
+ for bl, parteien in WAHLPROGRAMME.items():
+ for partei, info in parteien.items():
+ pid = info["file"].rsplit(".", 1)[0]
+ if pid not in PROGRAMME:
+ missing.append(f"{bl}/{partei} → {pid}")
+ assert not missing, (
+ "WAHLPROGRAMME entries missing in embeddings.PROGRAMME:\n "
+ + "\n ".join(missing)
+ )