gwoe-antragspruefer/app/wahlprogramme.py

448 lines
19 KiB
Python
Raw Normal View History

Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
"""Wahlprogramm-Referenzsystem mit Zitaten und Seitenreferenzen.
Bundesland-bewusst seit Issue #5: ``WAHLPROGRAMME[bundesland][partei]`` statt
flach. Konsumiert ``BUNDESLAENDER`` aus ``bundeslaender.py`` für die
Regierungsfraktionen-Lookup und für Plausibilitätsprüfungen.
Verantwortlich für die schlüsselwortbasierte Fallback-Suche in den
paged-Textversionen der Wahlprogramme. Die semantische Suche lebt in
``embeddings.py``.
"""
import re
from pathlib import Path
from typing import Optional
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
from .bundeslaender import BUNDESLAENDER
# WAHLPROGRAMME[bundesland][partei] -> Metadaten
# Beim Hinzufügen eines neuen Bundeslands: Eintrag hier UND parallel
# in WAHLPROGRAMM_KONTEXT_FILES.
WAHLPROGRAMME: dict[str, dict[str, dict]] = {
"NRW": {
"CDU": {
"file": "cdu-nrw-2022.pdf",
"titel": "Machen, worauf es ankommt",
"partei": "CDU NRW",
"jahr": 2022,
"seiten": 109,
},
"SPD": {
"file": "spd-nrw-2022.pdf",
"titel": "Unser Land von morgen",
"partei": "SPD NRW",
"jahr": 2022,
"seiten": 116,
},
"GRÜNE": {
"file": "gruene-nrw-2022.pdf",
"titel": "Von hier an Zukunft",
"partei": "BÜNDNIS 90/DIE GRÜNEN NRW",
"jahr": 2022,
"seiten": 100,
},
"FDP": {
"file": "fdp-nrw-2022.pdf",
"titel": "Nie gab es mehr zu tun",
"partei": "FDP NRW",
"jahr": 2022,
"seiten": 96,
},
"AfD": {
"file": "afd-nrw-2022.pdf",
"titel": "Wer sonst.",
"partei": "AfD NRW",
"jahr": 2022,
"seiten": 68,
},
},
Activate LSA: Wahlprogramme + ingest + frontend (#2) Brings Sachsen-Anhalt online as the second supported Bundesland after NRW. Closes the gap that issue #2 left open: with the PortalaAdapter already in place from c7242f8, this commit adds the reference data and flips the activation switch. Wahlprogramme (LTW Sachsen-Anhalt 06.06.2021) - Six PDFs added under app/static/referenzen/{cdu,spd,gruene,fdp,afd, linke}-lsa-2021.pdf, plus paged plain-text extractions under app/kontext/*.txt for the keyword fallback search. - Sources verified by hand: - CDU "Unsere Heimat. Unsere Verantwortung." (cdulsa.de, 82 pages) - SPD "Zusammenhalt und neue Chancen" (FES library, 77 pages) - GRÜNE "Verlässlich für Sachsen-Anhalt" (gruene-lsa.de, 164 pages) - FDP "Wahlprogramm zur Landtagswahl 2021" (Naumann-Stiftung, 76 pages) - AfD "Alles für unsere Heimat!" (klimawahlen.de mirror, 64 pages) - LINKE "Wahlprogramm zur Landtagswahl 2021" (dielinke-sachsen-anhalt.de, 88 pages) - The CDU PDF was the trickiest: KAS blocks bot downloads via Cloudflare; the cdulsa.de copy was located by an autonomous web search and verified to be byte-identical with the official document. Embeddings indexed (in production container, OpenAI-compatible DashScope embeddings via the existing index_programm pipeline): - CDU 134, SPD 145, GRÜNE 183, FDP 100, AfD 64, LINKE 143 chunks - Total LSA: 769 new chunks alongside the existing 775 NRW chunks and 335 federal Grundsatzprogramm chunks. wahlprogramme.py - WAHLPROGRAMME["LSA"] populated with all six parties (canonical fraction codes, original titles, page counts). embeddings.py - PROGRAMME extended with the six new "<partei>-lsa-2021" entries that the indexer pipeline expects. bundeslaender.py - LSA flipped to aktiv=True. The frontend dropdown will now offer Sachsen-Anhalt as a selectable bundesland and analyzer.get_bundesland_ context() will produce a real LSA prompt block (CDU/SPD/FDP as governing fractions, all six landtagsfraktionen). End-to-end smoke test (live in production container before commit) - Adapter: PortalaAdapter.search() returned current Anträge of März 2026 (LINKE + GRÜNE) with correct titles and PDF URLs. - Semantic search for an LSA "ÖPNV in der Altmark" sample antrag matched LINKE S.53, SPD S.68, FDP S.52 — all three with similarity > 0.6 and topical hits (Regionalisierungsmittel, ÖPNV-Förderprogramm, Wasserstoffnetz). Resolves issue #2. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 22:12:32 +02:00
# Sachsen-Anhalt — Wahlprogramme zur LTW 06.06.2021. Die aktuelle 8. WP
# (seit 07/2021) wird mit diesen Programmen analysiert.
"LSA": {
"CDU": {
"file": "cdu-lsa-2021.pdf",
"titel": "Unsere Heimat. Unsere Verantwortung.",
"partei": "CDU Sachsen-Anhalt",
"jahr": 2021,
"seiten": 82,
},
"SPD": {
"file": "spd-lsa-2021.pdf",
"titel": "Zusammenhalt und neue Chancen. Politik fürs ganze Land",
"partei": "SPD Sachsen-Anhalt",
"jahr": 2021,
"seiten": 77,
},
"GRÜNE": {
"file": "gruene-lsa-2021.pdf",
"titel": "Verlässlich für Sachsen-Anhalt",
"partei": "BÜNDNIS 90/DIE GRÜNEN Sachsen-Anhalt",
"jahr": 2021,
"seiten": 164,
},
"FDP": {
"file": "fdp-lsa-2021.pdf",
"titel": "Wahlprogramm der FDP Sachsen-Anhalt zur Landtagswahl 2021",
"partei": "FDP Sachsen-Anhalt",
"jahr": 2021,
"seiten": 76,
},
"AfD": {
"file": "afd-lsa-2021.pdf",
"titel": "Alles für unsere Heimat! Programm der AfD Sachsen-Anhalt zur Landtagswahl 2021",
"partei": "AfD Sachsen-Anhalt",
"jahr": 2021,
"seiten": 64,
},
"LINKE": {
"file": "linke-lsa-2021.pdf",
"titel": "Wahlprogramm zur Landtagswahl 2021",
"partei": "DIE LINKE Sachsen-Anhalt",
"jahr": 2021,
"seiten": 88,
},
},
Add MV+BE Wahlprogramme zur jeweils laufenden Legislatur (#4, #10) 11 PDFs in app/static/referenzen/ + Einträge in WAHLPROGRAMME und embeddings.PROGRAMME für die beiden bisher nur per föderalem Grundsatzprogramm-Fallback abgedeckten Landtage: - **MV** (WP 8, seit 26.10.2021): CDU, SPD, GRÜNE, FDP, AfD, LINKE Wahlprogramme zur LTW 26.09.2021. Issue #4. - **BE** (WP 19, konstituiert nach Wiederholungswahl 12.02.2023): CDU, SPD, GRÜNE, LINKE, AfD Programme zur AGH-Wahl 26.09.2021. Die Wiederholungswahl 2023 nutzte dieselben Programme wie die Originalwahl, daher die "be-2023.pdf"-Benennung mit Programm- jahr 2021. Issue #10. Quellen: abgeordnetenwatch.de Mirror für 9 PDFs, library.fes.de für SPD MV, cdu-mv.de direkt für CDU MV, fdp-mv.de direkt für FDP MV. Alle PDFs verifiziert via pdftotext gegen das im Programm genannte Wahldatum, um zu vermeiden, dass aktuellere Wahlkampf-Entwürfe (z.B. das CDU "Berlin-Plan 2026") als Legislatur-Programm fehlinterpretiert werden. Indexierung in die embeddings-DB ist NICHT Teil dieses Commits — sie muss separat im prod-Container ausgeführt werden: docker exec gwoe-antragspruefer python -c " from app.embeddings import index_programm from pathlib import Path d = Path('/app/static/referenzen') for pid in ['cdu-mv-2021','spd-mv-2021','gruene-mv-2021', 'fdp-mv-2021','afd-mv-2021','linke-mv-2021', 'cdu-be-2023','spd-be-2023','gruene-be-2023', 'linke-be-2023','afd-be-2023']: index_programm(pid, d) " Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 08:24:33 +02:00
# Mecklenburg-Vorpommern — Wahlprogramme zur LTW 26.09.2021. Die
# aktuelle 8. WP (seit 26.10.2021) wird mit diesen Programmen
# analysiert. Issue #4.
"MV": {
"CDU": {
"file": "cdu-mv-2021.pdf",
"titel": "Zusammen. Den Blick nach vorn. Gemeinsam die Zukunft meistern",
"partei": "CDU Mecklenburg-Vorpommern",
"jahr": 2021,
"seiten": 56,
},
"SPD": {
"file": "spd-mv-2021.pdf",
"titel": "Verantwortung für heute und morgen — Regierungsprogramm 20212026",
"partei": "SPD Mecklenburg-Vorpommern",
"jahr": 2021,
"seiten": 95,
},
"GRÜNE": {
"file": "gruene-mv-2021.pdf",
"titel": "Für Klima, Land und ein besseres Miteinander",
"partei": "BÜNDNIS 90/DIE GRÜNEN Mecklenburg-Vorpommern",
"jahr": 2021,
"seiten": 88,
},
"FDP": {
"file": "fdp-mv-2021.pdf",
"titel": "Wahlprogramm der Freien Demokraten Mecklenburg-Vorpommern zur Landtagswahl 2021",
"partei": "FDP Mecklenburg-Vorpommern",
"jahr": 2021,
"seiten": 120,
},
"AfD": {
"file": "afd-mv-2021.pdf",
"titel": "Landeswahlprogramm der AfD Mecklenburg-Vorpommern 2021",
"partei": "AfD Mecklenburg-Vorpommern",
"jahr": 2021,
"seiten": 84,
},
"LINKE": {
"file": "linke-mv-2021.pdf",
"titel": "Das ist links! — Zukunftsprogramm für Mecklenburg-Vorpommern",
"partei": "DIE LINKE Mecklenburg-Vorpommern",
"jahr": 2021,
"seiten": 82,
},
},
# Berlin — Wahlprogramme zur Abgeordnetenhauswahl 2021 (am 26.09.2021,
# wiederholt am 12.02.2023). Die laufende 19. WP (seit 27.04.2023) wird
# mit den 2021er Programmen analysiert, weil die Parteien zur
# Wiederholungswahl mit denselben Programmen angetreten sind. Issue #10.
"BE": {
"CDU": {
"file": "cdu-be-2023.pdf",
"titel": "Unser Berlin. Mehr geht nur gemeinsam. — Berlin-Plan der CDU Berlin 20212026",
"partei": "CDU Berlin",
"jahr": 2021,
"seiten": 135,
},
"SPD": {
"file": "spd-be-2023.pdf",
"titel": "Ganz sicher Berlin — Wahlprogramm der SPD Berlin zur Abgeordnetenhauswahl 2021",
"partei": "SPD Berlin",
"jahr": 2021,
"seiten": 86,
},
"GRÜNE": {
"file": "gruene-be-2023.pdf",
"titel": "Unser Plan für Berlin — Landeswahlprogramm BÜNDNIS 90/DIE GRÜNEN Berlin 2021",
"partei": "BÜNDNIS 90/DIE GRÜNEN Berlin",
"jahr": 2021,
"seiten": 280,
},
"LINKE": {
"file": "linke-be-2023.pdf",
"titel": "rot. radikal. realistisch. — Unser Programm für die soziale Stadt",
"partei": "DIE LINKE Berlin",
"jahr": 2021,
"seiten": 130,
},
"AfD": {
"file": "afd-be-2023.pdf",
"titel": "Wahlprogramm der AfD Berlin für die Wahl des Abgeordnetenhauses am 26. September 2021",
"partei": "AfD Berlin",
"jahr": 2021,
"seiten": 166,
},
},
Add 30 Wahlprogramme für TH/BB/HH/SH/BW/RP (#37, #39, #40, #32, #41, #42) Sechs der zehn aktiven Bundesländer hatten bisher keine Wahlprogramme indexiert (alle sechs heute neu aktiviert: BW/HH/TH in Phase 1, SH/BB/RP in Phase 2). Antrag-Analysen für diese BL fielen damit auf föderale Grundsatzprogramme als Fallback zurück. Beschafft via abgeordnetenwatch.de für die jeweils laufende WP: - TH WP8 (LTW 01.09.2024): CDU, AfD, LINKE, BSW, SPD — 5 PDFs - BB WP8 (LTW 22.09.2024): SPD, AfD, CDU, BSW — 4 PDFs - HH WP23 (Bürgerschaftswahl 02.03.2025): SPD, CDU, GRÜNE, LINKE, AfD — 5 PDFs - SH WP20 (LTW 08.05.2022): CDU, SPD, GRÜNE, FDP, SSW — 5 PDFs - BW WP17 (LTW 14.03.2021): GRÜNE, CDU, AfD, SPD, FDP — 5 PDFs - RP WP18 (LTW 14.03.2021): SPD, CDU, AfD, GRÜNE, FREIE WÄHLER, FDP — 6 PDFs Insgesamt 30 PDFs in app/static/referenzen/, plus 30 Einträge in WAHLPROGRAMME[bl][partei] und embeddings.PROGRAMME. Naming-Schema wie etabliert: <partei>-<bl>-<jahr>.pdf, also spd-th-2024.pdf, fw-rp-2021.pdf etc. Wichtig zu Memory feedback_legislaturprogramme: alle BL nutzen das Programm der LAUFENDEN Wahlperiode, NICHT Programme aus späteren Wahlen. BW und RP wählen am 08.03.2026 / 22.03.2026 neu — der 18./19. Landtag konstituiert sich erst, daher sind die 17./18. WP mit den 2021er Programmen weiterhin laufend bis zur Konstituierung. Indexierung im prod-Container ist NICHT Teil dieses Commits — muss separat ausgeführt werden: ssh vserver 'docker exec gwoe-antragspruefer python -c " from app.embeddings import index_programm from pathlib import Path d = Path(\"/app/app/static/referenzen\") for pid in [ \"cdu-th-2024\",\"afd-th-2024\",\"linke-th-2024\",\"bsw-th-2024\",\"spd-th-2024\", \"spd-bb-2024\",\"afd-bb-2024\",\"cdu-bb-2024\",\"bsw-bb-2024\", \"spd-hh-2025\",\"cdu-hh-2025\",\"gruene-hh-2025\",\"linke-hh-2025\",\"afd-hh-2025\", \"cdu-sh-2022\",\"spd-sh-2022\",\"gruene-sh-2022\",\"fdp-sh-2022\",\"ssw-sh-2022\", \"gruene-bw-2021\",\"cdu-bw-2021\",\"afd-bw-2021\",\"spd-bw-2021\",\"fdp-bw-2021\", \"spd-rp-2021\",\"cdu-rp-2021\",\"afd-rp-2021\",\"gruene-rp-2021\",\"fw-rp-2021\",\"fdp-rp-2021\", ]: index_programm(pid, d) "' 77 pytest tests passing — der File-Existenz-Check in test_wahlprogramme.py hätte einen Tippfehler im PDF-Namen sofort gefangen. Erledigt UI-Aktivierungs-Issues #37 (TH), #39 (BB), #40 (HH), #32 (SH), #41 (BW), #42 (RP). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 08:03:11 +02:00
# Thüringen — Wahlprogramme zur LTW 01.09.2024 (WP 8 seit 01.10.2024).
# Brombeer-Koalition CDU+BSW+SPD als Minderheit. Issue #37.
"TH": {
"CDU": {"file": "cdu-th-2024.pdf", "titel": "Wahlprogramm der CDU Thüringen 2024", "partei": "CDU Thüringen", "jahr": 2024, "seiten": 83},
"AfD": {"file": "afd-th-2024.pdf", "titel": "AfD Thüringen Landtagswahlprogramm 2024", "partei": "AfD Thüringen", "jahr": 2024, "seiten": 100},
"LINKE": {"file": "linke-th-2024.pdf", "titel": "DIE LINKE Thüringen Wahlprogramm 2024", "partei": "DIE LINKE Thüringen", "jahr": 2024, "seiten": 100},
"BSW": {"file": "bsw-th-2024.pdf", "titel": "BSW Thüringen Wahlprogramm 2024", "partei": "BSW Thüringen", "jahr": 2024, "seiten": 50},
"SPD": {"file": "spd-th-2024.pdf", "titel": "SPD Thüringen Wahlprogramm 2024", "partei": "SPD Thüringen", "jahr": 2024, "seiten": 100},
},
# Brandenburg — Wahlprogramme zur LTW 22.09.2024 (WP 8 seit 23.10.2024).
# Kabinett Woidke IV (SPD-BSW). Issue #39.
"BB": {
"SPD": {"file": "spd-bb-2024.pdf", "titel": "SPD Brandenburg Wahlprogramm 2024", "partei": "SPD Brandenburg", "jahr": 2024, "seiten": 100},
"AfD": {"file": "afd-bb-2024.pdf", "titel": "AfD Brandenburg Wahlprogramm 2024", "partei": "AfD Brandenburg", "jahr": 2024, "seiten": 100},
"CDU": {"file": "cdu-bb-2024.pdf", "titel": "CDU Brandenburg Wahlprogramm 2024", "partei": "CDU Brandenburg", "jahr": 2024, "seiten": 100},
"BSW": {"file": "bsw-bb-2024.pdf", "titel": "BSW Brandenburg Wahlprogramm 2024", "partei": "BSW Brandenburg", "jahr": 2024, "seiten": 50},
},
# Hamburg — Wahlprogramme zur Bürgerschaftswahl 02.03.2025 (WP 23 seit 26.03.2025).
# Senat Tschentscher III (SPD-GRÜNE). Issue #40.
"HH": {
"SPD": {"file": "spd-hh-2025.pdf", "titel": "SPD Hamburg Wahlprogramm Bürgerschaftswahl 2025", "partei": "SPD Hamburg", "jahr": 2025, "seiten": 100},
"CDU": {"file": "cdu-hh-2025.pdf", "titel": "CDU Hamburg Wahlprogramm Bürgerschaftswahl 2025", "partei": "CDU Hamburg", "jahr": 2025, "seiten": 100},
"GRÜNE": {"file": "gruene-hh-2025.pdf", "titel": "Gute Gründe für Grün — Regierungsprogramm BÜNDNIS 90/DIE GRÜNEN Hamburg 2025", "partei": "BÜNDNIS 90/DIE GRÜNEN Hamburg", "jahr": 2025, "seiten": 100},
"LINKE": {"file": "linke-hh-2025.pdf", "titel": "DIE LINKE Hamburg Wahlprogramm Bürgerschaftswahl 2025", "partei": "DIE LINKE Hamburg", "jahr": 2025, "seiten": 100},
"AfD": {"file": "afd-hh-2025.pdf", "titel": "AfD Hamburg Wahlprogramm Bürgerschaftswahl 2025", "partei": "AfD Hamburg", "jahr": 2025, "seiten": 100},
},
# Schleswig-Holstein — Wahlprogramme zur LTW 08.05.2022 (WP 20 seit 07.06.2022).
# Kabinett Günther II (CDU-GRÜNE). Issue #32.
"SH": {
"CDU": {"file": "cdu-sh-2022.pdf", "titel": "CDU Schleswig-Holstein Wahlprogramm 2022", "partei": "CDU Schleswig-Holstein", "jahr": 2022, "seiten": 100},
"SPD": {"file": "spd-sh-2022.pdf", "titel": "SPD Schleswig-Holstein Wahlprogramm 2022", "partei": "SPD Schleswig-Holstein", "jahr": 2022, "seiten": 100},
"GRÜNE": {"file": "gruene-sh-2022.pdf", "titel": "BÜNDNIS 90/DIE GRÜNEN Schleswig-Holstein Wahlprogramm 2022", "partei": "BÜNDNIS 90/DIE GRÜNEN Schleswig-Holstein", "jahr": 2022, "seiten": 100},
"FDP": {"file": "fdp-sh-2022.pdf", "titel": "FDP Schleswig-Holstein Wahlprogramm 2022", "partei": "FDP Schleswig-Holstein", "jahr": 2022, "seiten": 100},
"SSW": {"file": "ssw-sh-2022.pdf", "titel": "SSW Schleswig-Holstein Wahlprogramm 2022", "partei": "SSW", "jahr": 2022, "seiten": 80},
},
# Baden-Württemberg — Wahlprogramme zur LTW 14.03.2021 (WP 17, läuft bis Konstituierung
# des 18. Landtags nach 08.03.2026). Kabinett Kretschmann III (GRÜNE-CDU) noch
# geschäftsführend. Issue #41.
"BW": {
"GRÜNE": {"file": "gruene-bw-2021.pdf", "titel": "Wachsen wir über uns hinaus — Landtagswahlprogramm BÜNDNIS 90/DIE GRÜNEN Baden-Württemberg 2021", "partei": "BÜNDNIS 90/DIE GRÜNEN Baden-Württemberg", "jahr": 2021, "seiten": 100},
"CDU": {"file": "cdu-bw-2021.pdf", "titel": "Neue Ideen für eine neue Zeit — Regierungsprogramm der CDU Baden-Württemberg zur Landtagswahl 2021", "partei": "CDU Baden-Württemberg", "jahr": 2021, "seiten": 100},
"AfD": {"file": "afd-bw-2021.pdf", "titel": "AfD Baden-Württemberg Landtagswahlprogramm 2021", "partei": "AfD Baden-Württemberg", "jahr": 2021, "seiten": 100},
"SPD": {"file": "spd-bw-2021.pdf", "titel": "SPD Baden-Württemberg Wahlprogramm zur Landtagswahl 2021", "partei": "SPD Baden-Württemberg", "jahr": 2021, "seiten": 100},
"FDP": {"file": "fdp-bw-2021.pdf", "titel": "FDP Baden-Württemberg Landtagswahlprogramm 2021", "partei": "FDP Baden-Württemberg", "jahr": 2021, "seiten": 100},
},
# Rheinland-Pfalz — Wahlprogramme zur LTW 14.03.2021 (WP 18, läuft bis Konstituierung
# des 19. Landtags nach 22.03.2026). Kabinett Schweitzer I (SPD-GRÜNE-FDP) noch
# geschäftsführend. Issue #42.
"RP": {
"SPD": {"file": "spd-rp-2021.pdf", "titel": "Wir mit Ihr — Regierungsprogramm der SPD Rheinland-Pfalz 20212026", "partei": "SPD Rheinland-Pfalz", "jahr": 2021, "seiten": 100},
"CDU": {"file": "cdu-rp-2021.pdf", "titel": "Regierungsprogramm der CDU RLP 202126", "partei": "CDU Rheinland-Pfalz", "jahr": 2021, "seiten": 100},
"AfD": {"file": "afd-rp-2021.pdf", "titel": "AfD Rheinland-Pfalz Wahlprogramm 2021", "partei": "AfD Rheinland-Pfalz", "jahr": 2021, "seiten": 100},
"GRÜNE": {"file": "gruene-rp-2021.pdf", "titel": "BÜNDNIS 90/DIE GRÜNEN Rheinland-Pfalz Landtagswahlprogramm 2021", "partei": "BÜNDNIS 90/DIE GRÜNEN Rheinland-Pfalz", "jahr": 2021, "seiten": 100},
"FREIE WÄHLER": {"file": "fw-rp-2021.pdf", "titel": "FREIE WÄHLER Rheinland-Pfalz Wahlprogramm 2021", "partei": "FREIE WÄHLER Rheinland-Pfalz", "jahr": 2021, "seiten": 80},
"FDP": {"file": "fdp-rp-2021.pdf", "titel": "FDP Rheinland-Pfalz Landtagswahlprogramm 2021", "partei": "FDP Rheinland-Pfalz", "jahr": 2021, "seiten": 100},
},
}
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
# Pro Bundesland: Markdown-Übersichtsdatei mit Wahlprogramm-Zusammenfassungen,
# wird als Kontext in den LLM-Prompt geladen (nicht für die Suche).
WAHLPROGRAMM_KONTEXT_FILES: dict[str, str] = {
"NRW": "wahlprogramme-nrw-2022.md",
}
REFERENZEN_PATH = Path(__file__).parent / "static" / "referenzen"
KONTEXT_PATH = Path(__file__).parent / "kontext"
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
def get_wahlprogramm(bundesland: str, partei: str) -> Optional[dict]:
"""Liefert die Wahlprogramm-Metadaten oder None, wenn keins vorliegt."""
return WAHLPROGRAMME.get(bundesland, {}).get(partei)
def parteien_mit_wahlprogramm(bundesland: str) -> list[str]:
"""Liste der Parteien, für die im gegebenen Bundesland ein Wahlprogramm vorliegt."""
return list(WAHLPROGRAMME.get(bundesland, {}).keys())
def load_wahlprogramm_text(bundesland: str, partei: str) -> dict[int, str]:
"""Lädt Wahlprogramm-Text mit Seitenzuordnung.
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
Returns:
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
Dict mit Seitennummer -> Text. Leer, wenn kein Wahlprogramm hinterlegt
oder die paged-Textdatei fehlt.
"""
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
info = get_wahlprogramm(bundesland, partei)
if not info:
return {}
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
# Versuche paged-Textdatei zu laden
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
paged_file = KONTEXT_PATH / info['file'].replace('.pdf', '-paged.txt')
if not paged_file.exists():
# Fallback: Normale Textdatei
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
txt_file = KONTEXT_PATH / info['file'].replace('.pdf', '.txt')
if txt_file.exists():
return {1: txt_file.read_text()}
return {}
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
text = paged_file.read_text()
pages = {}
current_page = 1
current_text = []
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
for line in text.split('\n'):
if line.startswith('--- PAGE '):
if current_text:
pages[current_page] = '\n'.join(current_text)
match = re.search(r'PAGE (\d+)', line)
if match:
current_page = int(match.group(1))
current_text = []
else:
current_text.append(line)
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
if current_text:
pages[current_page] = '\n'.join(current_text)
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
return pages
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
def search_wahlprogramm(
bundesland: str,
partei: str,
keywords: list[str],
max_results: int = 3,
) -> list[dict]:
"""Sucht relevante Passagen in einem Wahlprogramm.
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
Args:
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
bundesland: Bundesland-Code (NRW, LSA, )
partei: Partei-Kürzel (CDU, SPD, GRÜNE, FDP, AfD, )
keywords: Suchbegriffe
max_results: Maximale Anzahl Ergebnisse
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
Returns:
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
Liste von {bundesland, partei, seite, text, score, url, quelle}
"""
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
info = get_wahlprogramm(bundesland, partei)
if not info:
return []
pages = load_wahlprogramm_text(bundesland, partei)
if not pages:
return []
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
results = []
keywords_lower = [k.lower() for k in keywords]
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
for page_num, text in pages.items():
text_lower = text.lower()
score = sum(1 for kw in keywords_lower if kw in text_lower)
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
if score > 0:
paragraphs = text.split('\n\n')
relevant_paragraphs = []
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
for para in paragraphs:
para_clean = para.strip()
if len(para_clean) < 50:
continue
para_lower = para_clean.lower()
if any(kw in para_lower for kw in keywords_lower):
relevant_paragraphs.append(para_clean)
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
if relevant_paragraphs:
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
best_para = max(
relevant_paragraphs,
key=lambda p: sum(1 for kw in keywords_lower if kw in p.lower()),
)
if len(best_para) > 300:
best_para = best_para[:297] + "..."
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
results.append({
"partei": partei,
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
"bundesland": bundesland,
"seite": page_num,
"text": best_para,
"score": score,
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
"url": f"/static/referenzen/{info['file']}#page={page_num}",
"quelle": f"{info['partei']} Wahlprogramm {info['jahr']}, S. {page_num}",
})
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
results.sort(key=lambda x: x['score'], reverse=True)
return results[:max_results]
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
def find_relevant_quotes(
antrag_text: str,
fraktionen: list[str],
bundesland: str,
) -> dict[str, list[dict]]:
"""Findet relevante Zitate aus Wahlprogrammen für einen Antrag.
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
Args:
antrag_text: Volltext des Antrags
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
fraktionen: Liste der einreichenden Fraktionen
bundesland: Bundesland-Code (Pflichtparameter; bestimmt, welche
Wahlprogramme durchsucht werden und welche Regierungsfraktionen
zusätzlich einbezogen werden).
Returns:
Dict mit Partei -> Liste von Zitaten
"""
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
if bundesland not in BUNDESLAENDER:
raise ValueError(f"Unbekanntes Bundesland: {bundesland}")
# Extrahiere Keywords aus Antrag (einfache Heuristik)
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
stopwords = {
'der', 'die', 'das', 'und', 'oder', 'für', 'mit', 'von', 'zu', 'auf',
'ist', 'sind', 'wird', 'werden', 'hat', 'haben', 'ein', 'eine', 'einer',
'den', 'dem', 'des', 'im', 'in', 'an', 'bei', 'nach', 'über', 'unter',
'durch', 'als', 'auch', 'nur', 'noch', 'aber', 'wenn', 'dass', 'sich',
'nicht', 'wie', 'so', 'aus', 'zum', 'zur', 'vom', 'beim', 'seit', 'bis',
}
words = re.findall(r'\b[A-Za-zäöüÄÖÜß]{4,}\b', antrag_text)
keywords = [w for w in words if w.lower() not in stopwords]
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
word_freq: dict[str, int] = {}
for w in keywords:
w_lower = w.lower()
word_freq[w_lower] = word_freq.get(w_lower, 0) + 1
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
top_keywords = sorted(word_freq.keys(), key=lambda x: word_freq[x], reverse=True)[:15]
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
# Antragsteller + Regierungsfraktionen des Bundeslands
regierungsfraktionen = BUNDESLAENDER[bundesland].regierungsfraktionen
parteien_to_search = set(fraktionen) | set(regierungsfraktionen)
quotes: dict[str, list[dict]] = {}
for partei in parteien_to_search:
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
if get_wahlprogramm(bundesland, partei):
found = search_wahlprogramm(bundesland, partei, top_keywords, max_results=2)
if found:
quotes[partei] = found
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
return quotes
def format_quote_for_prompt(quotes: dict[str, list[dict]]) -> str:
"""Formatiert Zitate für den LLM-Prompt."""
if not quotes:
return ""
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
lines = ["\n## Relevante Passagen aus Wahlprogrammen\n"]
lines.append("Nutze diese Originalzitate als Belege in deiner Bewertung:\n")
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
for partei, zitate in quotes.items():
for z in zitate:
lines.append(f"### {z['quelle']}")
lines.append(f'> "{z["text"]}"')
lines.append("")
Refactor wahlprogramme/embeddings/analyzer for multi-state (#5) Atomic refactor of the three modules that previously hardcoded NRW behaviour. After this commit, every analysis path consults the central BUNDESLAENDER registry for governing fractions, parliament name, and state metadata. wahlprogramme.py - WAHLPROGRAMME is now nested {bundesland: {partei: meta}}; NRW data hoisted unchanged under the "NRW" key. - New WAHLPROGRAMM_KONTEXT_FILES dict maps a state to its overview markdown file (currently only NRW). - find_relevant_quotes(text, fraktionen, bundesland) — bundesland is now a required positional. Governing fractions for the requested state are merged with the submitting fractions before lookup. - Helpers get_wahlprogramm() and parteien_mit_wahlprogramm() expose the new shape to other modules. - ValueError on unknown bundesland (no silent fallback). embeddings.py - Schema migration in init_embeddings_db: adds a `bundesland` column to the chunks table when missing, plus an index, and backfills existing rows from the PROGRAMME registry. Grundsatzprogramme (federal level) keep bundesland NULL by design. - find_relevant_chunks accepts a bundesland filter that matches state rows OR NULL — so federal Grundsatzprogramme remain visible to every analysis. - get_relevant_quotes_for_antrag(text, fraktionen, bundesland, …) — bundesland required, governing fractions read from BUNDESLAENDER instead of hardcoded ["CDU","GRÜNE"]. Order-preserving dedup replaces the previous set-based merge. - index_programm now writes the bundesland column on insert. - Dropped the hardcoded "Wahlprogramm NRW 2022" label in format_quotes_for_prompt — bundesland context is implicit in the surrounding prompt block. analyzer.py - get_bundesland_context reads parlament_name, regierungsfraktionen, landtagsfraktionen and the optional WAHLPROGRAMM_KONTEXT_FILES entry from the central registry. Throws ValueError on unknown OR inactive bundesland — kills the silent NRW fallback that previously masked configuration gaps. - The Antragsteller-detection heuristic now iterates BUNDESLAENDER[bundesland].landtagsfraktionen instead of WAHLPROGRAMME.keys(), so we recognise parties for which we don't yet have a Wahlprogramm PDF. - Both quote lookups (semantic + keyword fallback) now receive the bundesland. Resolves issue #5. Foundation for #2 (LSA), #3 (Berlin), #4 (MV). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-07 18:48:11 +02:00
return "\n".join(lines)