Files
breakpilot-lehrer/klausur-service/backend/dsfa_sources_registry.py
Benjamin Admin 9ba420fa91
Some checks failed
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-school (push) Successful in 42s
CI / test-go-edu-search (push) Successful in 34s
CI / test-python-klausur (push) Failing after 2m51s
CI / test-python-agent-core (push) Successful in 21s
CI / test-nodejs-website (push) Successful in 29s
Fix: Remove broken getKlausurApiUrl and clean up empty lines
sed replacement left orphaned hostname references in story page
and empty lines in getApiBase functions.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-24 16:02:04 +02:00

1141 lines
49 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""
DSFA Sources Registry — Pure data definitions.
Contains:
- LICENSE_REGISTRY: License metadata for all supported licenses
- DSFA_SOURCES: All DSFA source definitions (EU, DSK, Bundeslaender, etc.)
- DSFA_CHUNK_CONFIG: Chunking strategy configuration per source type
"""
# =============================================================================
# License Registry
# =============================================================================
LICENSE_REGISTRY = {
"DL-DE-BY-2.0": {
"name": "Datenlizenz Deutschland Namensnennung Version 2.0",
"url": "https://www.govdata.de/dl-de/by-2-0",
"attribution_required": True,
"modification_allowed": True,
"commercial_use": True,
"template": "Quelle: {source_name}, Datenlizenz Deutschland Namensnennung Version 2.0"
},
"DL-DE-ZERO-2.0": {
"name": "Datenlizenz Deutschland Zero Version 2.0",
"url": "https://www.govdata.de/dl-de/zero-2-0",
"attribution_required": False,
"modification_allowed": True,
"commercial_use": True,
"template": None
},
"CC-BY-4.0": {
"name": "Creative Commons Attribution 4.0 International",
"url": "https://creativecommons.org/licenses/by/4.0/",
"attribution_required": True,
"modification_allowed": True,
"commercial_use": True,
"template": "© {organization} | CC BY 4.0"
},
"EDPB-LICENSE": {
"name": "EDPB Document License",
"url": "https://edpb.europa.eu/about-edpb/legal-notice_en",
"attribution_required": True,
"modification_allowed": True,
"commercial_use": True,
"template": "Source: {source_name}, European Data Protection Board"
},
"PUBLIC_DOMAIN": {
"name": "Public Domain",
"url": None,
"attribution_required": False,
"modification_allowed": True,
"commercial_use": True,
"template": None
},
"PROPRIETARY": {
"name": "Proprietary (internal use only)",
"url": None,
"attribution_required": False,
"modification_allowed": False,
"commercial_use": True,
"template": "© BreakPilot - Internal Use Only"
},
"OGL-3.0": {
"name": "Open Government Licence v3.0",
"url": "https://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/",
"attribution_required": True,
"modification_allowed": True,
"commercial_use": True,
"template": "Contains public sector information licensed under the Open Government Licence v3.0. Source: {source_name}"
}
}
# =============================================================================
# DSFA Sources Registry
# =============================================================================
DSFA_SOURCES = [
# === Primärquellen (EU/DSGVO) ===
{
"source_code": "GDPR_ART35",
"name": "Art. 35 DSGVO - DSFA",
"full_name": "Datenschutz-Folgenabschätzung gemäß Artikel 35 DSGVO",
"organization": "Europäische Union",
"source_url": "https://eur-lex.europa.eu/eli/reg/2016/679/oj/deu",
"eur_lex_celex": "32016R0679",
"license_code": "CC-BY-4.0",
"attribution_text": "Quelle: DSGVO Art. 35 (EUR-Lex)",
"document_type": "regulation",
"language": "de"
},
{
"source_code": "GDPR_ART36",
"name": "Art. 36 DSGVO - Behördenkonsultation",
"full_name": "Vorherige Konsultation gemäß Artikel 36 DSGVO",
"organization": "Europäische Union",
"source_url": "https://eur-lex.europa.eu/eli/reg/2016/679/oj/deu",
"eur_lex_celex": "32016R0679",
"license_code": "CC-BY-4.0",
"attribution_text": "Quelle: DSGVO Art. 36 (EUR-Lex)",
"document_type": "regulation",
"language": "de"
},
{
"source_code": "GDPR_RECITALS",
"name": "Erwägungsgründe 75, 84, 89-91 DSGVO",
"full_name": "Erwägungsgründe zur Datenschutz-Folgenabschätzung",
"organization": "Europäische Union",
"source_url": "https://eur-lex.europa.eu/eli/reg/2016/679/oj/deu",
"eur_lex_celex": "32016R0679",
"license_code": "CC-BY-4.0",
"attribution_text": "Quelle: DSGVO Erwägungsgründe (EUR-Lex)",
"document_type": "regulation",
"language": "de"
},
# === WP29/EDPB Leitlinien ===
{
"source_code": "WP248",
"name": "WP248 rev.01 - Leitlinien zur DSFA",
"full_name": "Leitlinien zur Datenschutz-Folgenabschätzung und Beantwortung der Frage, ob eine Verarbeitung 'wahrscheinlich ein hohes Risiko' birgt",
"organization": "Artikel-29-Datenschutzgruppe / EDPB",
"source_url": "https://ec.europa.eu/newsroom/article29/items/611236/en",
"license_code": "EDPB-LICENSE",
"attribution_text": "Quelle: WP248 rev.01, Artikel-29-Datenschutzgruppe (2017), bestätigt durch EDPB",
"document_type": "guideline",
"language": "de"
},
# === DSK Dokumente ===
{
"source_code": "DSK_KP5",
"name": "Kurzpapier Nr. 5 - DSFA nach Art. 35 DS-GVO",
"full_name": "DSK Kurzpapier Nr. 5: Datenschutz-Folgenabschätzung nach Art. 35 DS-GVO",
"organization": "Datenschutzkonferenz (DSK)",
"source_url": "https://www.datenschutzkonferenz-online.de/media/kp/dsk_kpnr_5.pdf",
"license_code": "DL-DE-BY-2.0",
"license_url": "https://www.govdata.de/dl-de/by-2-0",
"attribution_text": "Quelle: DSK Kurzpapier Nr. 5 (Stand: 2018), Datenlizenz Deutschland Namensnennung Version 2.0",
"document_type": "guideline",
"language": "de"
},
# === Muss-Listen Bund ===
{
"source_code": "BFDI_MUSS_PUBLIC",
"name": "BfDI DSFA-Liste (öffentlicher Bereich)",
"full_name": "Liste der Verarbeitungsvorgänge nach Art. 35 Abs. 4 DSGVO - Öffentlicher Bereich",
"organization": "Bundesbeauftragter für den Datenschutz und die Informationsfreiheit",
"source_url": "https://www.bfdi.bund.de/SharedDocs/Downloads/DE/Muster/Liste_VerarbeitungsvorgaengeArt35.pdf",
"license_code": "DL-DE-ZERO-2.0",
"attribution_text": "Quelle: BfDI, Liste gem. Art. 35 Abs. 4 DSGVO (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "BFDI_MUSS_PRIVATE",
"name": "BfDI DSFA-Liste (nicht-öffentlicher Bereich)",
"full_name": "Liste der Verarbeitungsvorgänge nach Art. 35 Abs. 4 DSGVO - Nicht-öffentlicher Bereich",
"organization": "Bundesbeauftragter für den Datenschutz und die Informationsfreiheit",
"source_url": "https://www.bfdi.bund.de/SharedDocs/Downloads/DE/Muster/Liste_VerarbeitungsvorgaengeArt35.pdf",
"license_code": "DL-DE-ZERO-2.0",
"attribution_text": "Quelle: BfDI, Liste gem. Art. 35 Abs. 4 DSGVO (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# === Muss-Listen Länder ===
# Baden-Württemberg
{
"source_code": "BW_MUSS_PUBLIC",
"name": "LfDI BW DSFA-Liste (öffentlich)",
"organization": "Landesbeauftragter für Datenschutz BW",
"source_url": "https://www.baden-wuerttemberg.datenschutz.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI Baden-Württemberg, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "BW_MUSS_PRIVATE",
"name": "LfDI BW DSFA-Liste (nicht-öffentlich)",
"organization": "Landesbeauftragter für Datenschutz BW",
"source_url": "https://www.baden-wuerttemberg.datenschutz.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI Baden-Württemberg, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Bayern
{
"source_code": "BY_MUSS_PUBLIC",
"name": "BayLDA DSFA-Liste (öffentlich)",
"organization": "Bayerisches Landesamt für Datenschutzaufsicht",
"source_url": "https://www.lda.bayern.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: BayLDA, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "BY_MUSS_PRIVATE",
"name": "BayLDA DSFA-Liste (nicht-öffentlich)",
"organization": "Bayerisches Landesamt für Datenschutzaufsicht",
"source_url": "https://www.lda.bayern.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: BayLDA, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Berlin
{
"source_code": "BE_MUSS_PUBLIC",
"name": "BlnBDI DSFA-Liste (öffentlich)",
"organization": "Berliner Beauftragte für Datenschutz",
"source_url": "https://www.datenschutz-berlin.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: BlnBDI, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "BE_MUSS_PRIVATE",
"name": "BlnBDI DSFA-Liste (nicht-öffentlich)",
"organization": "Berliner Beauftragte für Datenschutz",
"source_url": "https://www.datenschutz-berlin.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: BlnBDI, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Brandenburg
{
"source_code": "BB_MUSS_PUBLIC",
"name": "LDA BB DSFA-Liste (öffentlich)",
"organization": "Landesbeauftragte für Datenschutz Brandenburg",
"source_url": "https://www.lda.brandenburg.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LDA Brandenburg, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "BB_MUSS_PRIVATE",
"name": "LDA BB DSFA-Liste (nicht-öffentlich)",
"organization": "Landesbeauftragte für Datenschutz Brandenburg",
"source_url": "https://www.lda.brandenburg.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LDA Brandenburg, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Bremen
{
"source_code": "HB_MUSS_PUBLIC",
"name": "LfDI HB DSFA-Liste (öffentlich)",
"organization": "Landesbeauftragte für Datenschutz Bremen",
"source_url": "https://www.datenschutz.bremen.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI Bremen, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "HB_MUSS_PRIVATE",
"name": "LfDI HB DSFA-Liste (nicht-öffentlich)",
"organization": "Landesbeauftragte für Datenschutz Bremen",
"source_url": "https://www.datenschutz.bremen.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI Bremen, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Hamburg
{
"source_code": "HH_MUSS_PUBLIC",
"name": "HmbBfDI DSFA-Liste (öffentlich)",
"organization": "Hamburgische Beauftragte für Datenschutz",
"source_url": "https://datenschutz-hamburg.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: HmbBfDI, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "HH_MUSS_PRIVATE",
"name": "HmbBfDI DSFA-Liste (nicht-öffentlich)",
"organization": "Hamburgische Beauftragte für Datenschutz",
"source_url": "https://datenschutz-hamburg.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: HmbBfDI, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Hessen
{
"source_code": "HE_MUSS_PUBLIC",
"name": "HBDI DSFA-Liste (öffentlich)",
"organization": "Hessischer Beauftragter für Datenschutz",
"source_url": "https://datenschutz.hessen.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: HBDI, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "HE_MUSS_PRIVATE",
"name": "HBDI DSFA-Liste (nicht-öffentlich)",
"organization": "Hessischer Beauftragter für Datenschutz",
"source_url": "https://datenschutz.hessen.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: HBDI, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Mecklenburg-Vorpommern
{
"source_code": "MV_MUSS_PUBLIC",
"name": "LfDI MV DSFA-Liste (öffentlich)",
"organization": "Landesbeauftragter für Datenschutz MV",
"source_url": "https://www.datenschutz-mv.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI MV, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "MV_MUSS_PRIVATE",
"name": "LfDI MV DSFA-Liste (nicht-öffentlich)",
"organization": "Landesbeauftragter für Datenschutz MV",
"source_url": "https://www.datenschutz-mv.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI MV, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Niedersachsen
{
"source_code": "NI_MUSS_PUBLIC",
"name": "LfD NI DSFA-Liste (öffentlich)",
"organization": "Die Landesbeauftragte für den Datenschutz Niedersachsen",
"source_url": "https://www.lfd.niedersachsen.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfD Niedersachsen, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "NI_MUSS_PRIVATE",
"name": "LfD NI DSFA-Liste (nicht-öffentlich)",
"organization": "Die Landesbeauftragte für den Datenschutz Niedersachsen",
"source_url": "https://www.lfd.niedersachsen.de/download/131098",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfD Niedersachsen, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Nordrhein-Westfalen
{
"source_code": "NW_MUSS_PUBLIC",
"name": "LDI NRW DSFA-Liste (öffentlich)",
"organization": "Landesbeauftragte für Datenschutz NRW",
"source_url": "https://www.ldi.nrw.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LDI NRW, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "NW_MUSS_PRIVATE",
"name": "LDI NRW DSFA-Liste (nicht-öffentlich)",
"organization": "Landesbeauftragte für Datenschutz NRW",
"source_url": "https://www.ldi.nrw.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LDI NRW, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Rheinland-Pfalz
{
"source_code": "RP_MUSS_PUBLIC",
"name": "LfDI RP DSFA-Liste (öffentlich)",
"organization": "Landesbeauftragter für Datenschutz Rheinland-Pfalz",
"source_url": "https://www.datenschutz.rlp.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI Rheinland-Pfalz, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "RP_MUSS_PRIVATE",
"name": "LfDI RP DSFA-Liste (nicht-öffentlich)",
"organization": "Landesbeauftragter für Datenschutz Rheinland-Pfalz",
"source_url": "https://www.datenschutz.rlp.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI Rheinland-Pfalz, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Saarland
{
"source_code": "SL_MUSS_PUBLIC",
"name": "LfDI SL DSFA-Liste (öffentlich)",
"organization": "Landesbeauftragte für Datenschutz Saarland",
"source_url": "https://www.datenschutz.saarland.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI Saarland, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "SL_MUSS_PRIVATE",
"name": "LfDI SL DSFA-Liste (nicht-öffentlich)",
"organization": "Landesbeauftragte für Datenschutz Saarland",
"source_url": "https://www.datenschutz.saarland.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfDI Saarland, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Sachsen
{
"source_code": "SN_MUSS_PUBLIC",
"name": "SDB DSFA-Liste (öffentlich)",
"organization": "Sächsischer Datenschutzbeauftragter",
"source_url": "https://www.saechsdsb.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: SDB Sachsen, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "SN_MUSS_PRIVATE",
"name": "SDB DSFA-Liste (nicht-öffentlich)",
"organization": "Sächsischer Datenschutzbeauftragter",
"source_url": "https://www.saechsdsb.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: SDB Sachsen, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Sachsen-Anhalt
{
"source_code": "ST_MUSS_PUBLIC",
"name": "LfD ST DSFA-Liste (öffentlich)",
"organization": "Landesbeauftragter für Datenschutz Sachsen-Anhalt",
"source_url": "https://datenschutz.sachsen-anhalt.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfD Sachsen-Anhalt, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "ST_MUSS_PRIVATE",
"name": "LfD ST DSFA-Liste (nicht-öffentlich)",
"organization": "Landesbeauftragter für Datenschutz Sachsen-Anhalt",
"source_url": "https://datenschutz.sachsen-anhalt.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: LfD Sachsen-Anhalt, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Schleswig-Holstein
{
"source_code": "SH_MUSS_PUBLIC",
"name": "ULD DSFA-Liste (öffentlich)",
"organization": "Unabhängiges Landeszentrum für Datenschutz SH",
"source_url": "https://www.datenschutzzentrum.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: ULD Schleswig-Holstein, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "SH_MUSS_PRIVATE",
"name": "ULD DSFA-Liste (nicht-öffentlich)",
"organization": "Unabhängiges Landeszentrum für Datenschutz SH",
"source_url": "https://www.datenschutzzentrum.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: ULD Schleswig-Holstein, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# Thüringen
{
"source_code": "TH_MUSS_PUBLIC",
"name": "TLfDI DSFA-Liste (öffentlich)",
"organization": "Thüringer Landesbeauftragter für Datenschutz",
"source_url": "https://www.tlfdi.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: TLfDI Thüringen, DSFA-Muss-Liste (öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
{
"source_code": "TH_MUSS_PRIVATE",
"name": "TLfDI DSFA-Liste (nicht-öffentlich)",
"organization": "Thüringer Landesbeauftragter für Datenschutz",
"source_url": "https://www.tlfdi.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: TLfDI Thüringen, DSFA-Muss-Liste (nicht-öffentlicher Bereich)",
"document_type": "checklist",
"language": "de"
},
# === Sonstige ===
{
"source_code": "AI_ACT_DSFA",
"name": "AI Act Bezüge zu DSFA",
"full_name": "AI Act Artikel mit Bezug zur Datenschutz-Folgenabschätzung",
"organization": "Europäische Union",
"source_url": "https://eur-lex.europa.eu/eli/reg/2024/1689/oj",
"license_code": "CC-BY-4.0",
"attribution_text": "Quelle: AI Act (EU) 2024/1689, EUR-Lex",
"document_type": "regulation",
"language": "de"
},
{
"source_code": "DSK_OH_KI",
"name": "DSK Orientierungshilfe KI",
"full_name": "DSK Orientierungshilfe KI und Datenschutz",
"organization": "Datenschutzkonferenz (DSK)",
"source_url": "https://www.datenschutzkonferenz-online.de",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: DSK Orientierungshilfe KI und Datenschutz",
"document_type": "guideline",
"language": "de"
},
{
"source_code": "EDSA_GUIDELINES",
"name": "EDPB Guidelines on DPIA",
"full_name": "European Data Protection Board Guidelines on DPIA",
"organization": "European Data Protection Board",
"source_url": "https://edpb.europa.eu",
"license_code": "EDPB-LICENSE",
"attribution_text": "Source: EDPB Guidelines on Data Protection Impact Assessment",
"document_type": "guideline",
"language": "en"
},
# === DSK Weitere Kurzpapiere ===
{
"source_code": "DSK_KP18",
"name": "Kurzpapier Nr. 18 - Risiko für die Rechte und Freiheiten",
"full_name": "DSK Kurzpapier Nr. 18: Risiko für die Rechte und Freiheiten natürlicher Personen",
"organization": "Datenschutzkonferenz (DSK)",
"source_url": "https://www.datenschutzkonferenz-online.de/media/kp/dsk_kpnr_18.pdf",
"license_code": "DL-DE-BY-2.0",
"license_url": "https://www.govdata.de/dl-de/by-2-0",
"attribution_text": "Quelle: DSK Kurzpapier Nr. 18 (Risiko), Datenlizenz Deutschland Namensnennung Version 2.0",
"document_type": "guideline",
"language": "de"
},
# === Standard-Datenschutzmodell ===
{
"source_code": "SDM_V2",
"name": "Standard-Datenschutzmodell V2.0",
"full_name": "SDM-Methode der Datenschutzaufsichtsbehörden V2.0",
"organization": "Datenschutzkonferenz (DSK)",
"source_url": "https://www.datenschutzkonferenz-online.de/media/ah/20191106_SDM-Methode_V2.0.pdf",
"license_code": "DL-DE-BY-2.0",
"license_url": "https://www.govdata.de/dl-de/by-2-0",
"attribution_text": "Quelle: SDM V2.0, Datenschutzkonferenz (DSK), Datenlizenz Deutschland Namensnennung Version 2.0",
"document_type": "methodology",
"language": "de"
},
# === Internes Dokument ===
{
"source_code": "BREAKPILOT_DSFA_GUIDE",
"name": "Datenschutz-Folgenabschätzung in Deutschland",
"full_name": "BreakPilot DSFA-Leitfaden (intern)",
"organization": "BreakPilot",
"source_url": None,
"license_code": "PROPRIETARY",
"attribution_text": "Quelle: BreakPilot DSFA-Leitfaden (intern)",
"document_type": "guideline",
"language": "de"
},
{
"source_code": "BREAKPILOT_BASELINE",
"name": "Baseline-DSFA Katalog",
"full_name": "BreakPilot Baseline-DSFA Katalog (proprietär)",
"organization": "BreakPilot",
"source_url": None,
"license_code": "PROPRIETARY",
"attribution_text": "Quelle: BreakPilot Baseline-DSFA Katalog (intern)",
"document_type": "catalog",
"language": "de"
},
{
"source_code": "BREAKPILOT_DSFA_DE",
"name": "DSFA in Deutschland Dokument",
"full_name": "BreakPilot DSFA in Deutschland (proprietär)",
"organization": "BreakPilot",
"source_url": None,
"license_code": "PROPRIETARY",
"attribution_text": "Quelle: BreakPilot DSFA in Deutschland (intern)",
"document_type": "guideline",
"language": "de"
},
# === VVT-Quellen (Verarbeitungsverzeichnis Art. 30 DSGVO) ===
{
"source_code": "DSK_KP1",
"name": "Kurzpapier Nr. 1 - Verarbeitungsverzeichnis",
"full_name": "DSK Kurzpapier Nr. 1: Verzeichnis von Verarbeitungstaetigkeiten nach Art. 30 DS-GVO",
"organization": "Datenschutzkonferenz (DSK)",
"source_url": "https://www.datenschutzkonferenz-online.de/media/kp/dsk_kpnr_1.pdf",
"license_code": "DL-DE-BY-2.0",
"license_url": "https://www.govdata.de/dl-de/by-2-0",
"attribution_text": "Quelle: DSK Kurzpapier Nr. 1 (Stand: 2018), Datenlizenz Deutschland Namensnennung Version 2.0",
"document_type": "guideline",
"language": "de"
},
{
"source_code": "ICO_ROPA",
"name": "ICO Records of Processing Activities",
"full_name": "ICO Guidance on Documentation and Records of Processing Activities (RoPA)",
"organization": "Information Commissioner's Office (ICO)",
"source_url": "https://ico.org.uk/for-organisations/uk-gdpr-guidance-and-resources/accountability-and-governance/documentation-record-of-processing-activities/",
"license_code": "OGL-3.0",
"license_url": "https://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/",
"attribution_text": "Contains public sector information licensed under the Open Government Licence v3.0. Source: ICO RoPA Guidance",
"document_type": "guideline",
"language": "en"
},
{
"source_code": "BREAKPILOT_VVT_SPEC",
"name": "VVT Generator Spezifikation",
"full_name": "BreakPilot VVT Generator Spezifikation (proprietaer)",
"organization": "BreakPilot",
"source_url": None,
"license_code": "PROPRIETARY",
"attribution_text": "Quelle: BreakPilot VVT Generator Spezifikation (intern)",
"document_type": "specification",
"language": "de"
},
# === SDM Bausteine V3.0 (TOM Gewaehrleistungsziele) ===
{
"source_code": "SDM_BAUSTEINE",
"name": "SDM Bausteine V3.0",
"full_name": "Standard-Datenschutzmodell Bausteine Version 3.0",
"organization": "Konferenz der unabhaengigen Datenschutzaufsichtsbehoerden",
"source_url": "https://www.datenschutz-mv.de/datenschutz/sdm/",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: SDM Bausteine V3.0, Konferenz der unabhaengigen Datenschutzaufsichtsbehoerden des Bundes und der Laender, Lizenz: dl-de/by-2-0",
"document_type": "standard",
"language": "de"
},
# === DSK Kurzpapier Nr. 7 (Loeschung) ===
{
"source_code": "DSK_KP7",
"name": "DSK Kurzpapier Nr. 7 - Loeschung",
"full_name": "Kurzpapier Nr. 7: Marktortprinzip und Loeschung personenbezogener Daten",
"organization": "Datenschutzkonferenz (DSK)",
"source_url": "https://www.datenschutzkonferenz-online.de/kurzpapiere.html",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: DSK Kurzpapier Nr. 7, Datenschutzkonferenz, Lizenz: dl-de/by-2-0",
"document_type": "guidance",
"language": "de"
},
# === BreakPilot Loeschfristen + TOM Spec (intern) ===
{
"source_code": "BREAKPILOT_LF_TOM_SPEC",
"name": "Loeschfristen & TOM Generator Spezifikation",
"full_name": "BreakPilot Loeschfristen und TOM Generator Spezifikation (proprietaer)",
"organization": "BreakPilot",
"source_url": None,
"license_code": "PROPRIETARY",
"attribution_text": "Quelle: BreakPilot Loeschfristen & TOM Generator Spezifikation (intern)",
"document_type": "specification",
"language": "de"
},
# === Compliance Advisor Agent - Zusaetzliche Quellen ===
{
"source_code": "DSGVO_VOLLTEXT",
"name": "DSGVO Volltext",
"full_name": "Verordnung (EU) 2016/679 - Datenschutz-Grundverordnung (Volltext mit Erwaegsgruenden)",
"organization": "Europaeische Union",
"source_url": "https://eur-lex.europa.eu/eli/reg/2016/679/oj/deu",
"license_code": "CC-BY-4.0",
"attribution_text": "Quelle: DSGVO Volltext, Europaeische Union, CC BY 4.0",
"document_type": "legislation",
"language": "de"
},
{
"source_code": "BDSG_VOLLTEXT",
"name": "BDSG Volltext",
"full_name": "Bundesdatenschutzgesetz (BDSG) - Volltext",
"organization": "Bundesrepublik Deutschland",
"source_url": "https://www.gesetze-im-internet.de/bdsg_2018/",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Quelle: BDSG, Bundesrepublik Deutschland",
"document_type": "legislation",
"language": "de"
},
{
"source_code": "AI_ACT_SUMMARY",
"name": "AI Act Zusammenfassung",
"full_name": "EU KI-Verordnung (AI Act) - Zusammenfassung und Kernpunkte",
"organization": "Europaeische Union",
"source_url": "https://eur-lex.europa.eu/legal-content/DE/TXT/?uri=CELEX:32024R1689",
"license_code": "CC-BY-4.0",
"attribution_text": "Quelle: AI Act, Europaeische Union, CC BY 4.0",
"document_type": "legislation",
"language": "de"
},
{
"source_code": "DSK_KURZPAPIERE_ALLE",
"name": "DSK Kurzpapiere (alle 20)",
"full_name": "Datenschutzkonferenz - Alle 20 Kurzpapiere zur DSGVO",
"organization": "Datenschutzkonferenz (DSK)",
"source_url": "https://www.datenschutzkonferenz-online.de/kurzpapiere.html",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: DSK Kurzpapiere, Datenschutzkonferenz, Lizenz: dl-de/by-2-0",
"document_type": "guidance",
"language": "de"
},
{
"source_code": "SDM_V3",
"name": "Standard-Datenschutzmodell V3.0",
"full_name": "SDM - Standard-Datenschutzmodell Version 3.0",
"organization": "Datenschutzkonferenz (DSK)",
"source_url": "https://www.datenschutz-mv.de/datenschutz/sdm/",
"license_code": "DL-DE-BY-2.0",
"attribution_text": "Quelle: SDM V3.0, Datenschutzkonferenz, Lizenz: dl-de/by-2-0",
"document_type": "standard",
"language": "de"
},
# === EDPB Ergaenzende Leitlinien ===
# MIGRATED to bp_legal_corpus via migrate_rag_chunks.py (2026-02-10)
{
"source_code": "EDPB_GUIDELINES_2_2019",
"name": "EDPB Leitlinien 2/2019 zu Art. 6(1)(b)",
"full_name": "EDPB Leitlinien 2/2019 zur Verarbeitung personenbezogener Daten auf Grundlage von Art. 6 Abs. 1 lit. b DSGVO",
"organization": "European Data Protection Board",
"source_url": "https://edpb.europa.eu/our-work-tools/our-documents/guidelines/guidelines-22019-processing-personal-data-under-article-61b_en",
"license_code": "EDPB-LICENSE",
"attribution_text": "Source: EDPB Guidelines 2/2019, European Data Protection Board",
"document_type": "guideline",
"language": "en",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "EDPB_GUIDELINES_3_2019",
"name": "EDPB Leitlinien 3/2019 Videoueberwachung",
"full_name": "EDPB Leitlinien 3/2019 zur Verarbeitung personenbezogener Daten durch Videoueberwachung",
"organization": "European Data Protection Board",
"source_url": "https://edpb.europa.eu/our-work-tools/our-documents/guidelines/guidelines-32019-processing-personal-data-through-video_en",
"license_code": "EDPB-LICENSE",
"attribution_text": "Source: EDPB Guidelines 3/2019, European Data Protection Board",
"document_type": "guideline",
"language": "en",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "EDPB_GUIDELINES_5_2020",
"name": "EDPB Leitlinien 5/2020 Einwilligung",
"full_name": "EDPB Leitlinien 5/2020 zur Einwilligung gemaess Verordnung 2016/679",
"organization": "European Data Protection Board",
"source_url": "https://edpb.europa.eu/our-work-tools/our-documents/guidelines/guidelines-052020-consent-under-regulation-2016679_en",
"license_code": "EDPB-LICENSE",
"attribution_text": "Source: EDPB Guidelines 5/2020, European Data Protection Board",
"document_type": "guideline",
"language": "en",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "EDPB_GUIDELINES_7_2020",
"name": "EDPB Leitlinien 7/2020 Controller/Processor",
"full_name": "EDPB Leitlinien 7/2020 zu den Begriffen Verantwortlicher und Auftragsverarbeiter",
"organization": "European Data Protection Board",
"source_url": "https://edpb.europa.eu/our-work-tools/our-documents/guidelines/guidelines-072020-concepts-controller-and-processor-gdpr_en",
"license_code": "EDPB-LICENSE",
"attribution_text": "Source: EDPB Guidelines 7/2020, European Data Protection Board",
"document_type": "guideline",
"language": "en",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "EDPB_GUIDELINES_1_2022",
"name": "EDPB Leitlinien 1/2022 Bussgelder",
"full_name": "EDPB Leitlinien 04/2022 zur Berechnung von Bussgeldern nach der DSGVO",
"organization": "European Data Protection Board",
"source_url": "https://edpb.europa.eu/our-work-tools/our-documents/guidelines/guidelines-042022-calculation-administrative-fines-under-gdpr_en",
"license_code": "EDPB-LICENSE",
"attribution_text": "Source: EDPB Guidelines 04/2022, European Data Protection Board",
"document_type": "guideline",
"language": "en",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "SCC_FULL_TEXT",
"name": "Standard Contractual Clauses Volltext",
"full_name": "Standardvertragsklauseln fuer die Uebermittlung personenbezogener Daten an Drittlaender (2021/914/EU)",
"organization": "Europaeische Kommission",
"source_url": "https://eur-lex.europa.eu/eli/dec_impl/2021/914/oj",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Quelle: SCC Volltext, Europaeische Kommission (EUR-Lex)",
"document_type": "regulation",
"language": "de",
"migrated_to": "bp_legal_corpus"
},
# === Nationale Datenschutzgesetze (DSGVO-Umsetzungen) ===
# MIGRATED to bp_legal_corpus via migrate_rag_chunks.py (2026-02-10)
# These sources are kept here for reference but will be skipped during ingestion.
# Ingestion should target bp_legal_corpus for these source codes.
{
"source_code": "BDSG_FULL",
"name": "BDSG Volltext (Deutschland)",
"full_name": "Bundesdatenschutzgesetz (BDSG) - Volltext inkl. aller Teile",
"organization": "Bundesrepublik Deutschland",
"source_url": "https://www.gesetze-im-internet.de/bdsg_2018/",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Quelle: BDSG, Bundesrepublik Deutschland (gesetze-im-internet.de)",
"document_type": "legislation",
"language": "de",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "AT_DSG",
"name": "DSG Oesterreich",
"full_name": "Bundesgesetz zum Schutz natuerlicher Personen bei der Verarbeitung personenbezogener Daten (Datenschutzgesetz - DSG)",
"organization": "Republik Oesterreich",
"source_url": "https://www.ris.bka.gv.at/GeltendeFassung.wxe?Abfrage=Bundesnormen&Gesetzesnummer=10001597",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Quelle: DSG, Republik Oesterreich (RIS)",
"document_type": "legislation",
"language": "de",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "CH_DSG",
"name": "DSG Schweiz (revDSG 2023)",
"full_name": "Bundesgesetz ueber den Datenschutz (Datenschutzgesetz, DSG) - revidierte Fassung 2023",
"organization": "Schweizerische Eidgenossenschaft",
"source_url": "https://www.fedlex.admin.ch/eli/cc/2022/491/de",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Quelle: DSG, Schweizerische Eidgenossenschaft (Fedlex)",
"document_type": "legislation",
"language": "de",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "LI_DSG",
"name": "DSG Liechtenstein",
"full_name": "Datenschutzgesetz (DSG) Liechtenstein",
"organization": "Fuerstentum Liechtenstein",
"source_url": "https://www.gesetze.li/konso/2018.272",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Quelle: DSG, Fuerstentum Liechtenstein (gesetze.li)",
"document_type": "legislation",
"language": "de",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "FR_CNIL_GUIDE",
"name": "CNIL Guide RGPD",
"full_name": "Guide pratique RGPD - Commission Nationale de l'Informatique et des Libertes",
"organization": "CNIL (France)",
"source_url": "https://www.cnil.fr/fr/rgpd-de-quoi-parle-t-on",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Source: CNIL Guide RGPD, Commission Nationale de l'Informatique et des Libertes",
"document_type": "guideline",
"language": "fr",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "ES_LOPDGDD",
"name": "LOPDGDD Spanien",
"full_name": "Ley Organica de Proteccion de Datos Personales y garantia de los derechos digitales",
"organization": "Reino de Espana",
"source_url": "https://www.boe.es/buscar/act.php?id=BOE-A-2018-16673",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Fuente: LOPDGDD, Reino de Espana (BOE)",
"document_type": "legislation",
"language": "es",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "IT_CODICE_PRIVACY",
"name": "Codice Privacy Italien",
"full_name": "Codice in materia di protezione dei dati personali (D.Lgs. 196/2003, aggiornato D.Lgs. 101/2018)",
"organization": "Repubblica Italiana",
"source_url": "https://www.garanteprivacy.it/home/docweb/-/docweb-display/docweb/9042678",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Fonte: Codice Privacy, Garante per la protezione dei dati personali",
"document_type": "legislation",
"language": "it",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "NL_UAVG",
"name": "UAVG Niederlande",
"full_name": "Uitvoeringswet Algemene verordening gegevensbescherming (UAVG)",
"organization": "Koninkrijk der Nederlanden",
"source_url": "https://wetten.overheid.nl/BWBR0040940/",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Bron: UAVG, Koninkrijk der Nederlanden (wetten.overheid.nl)",
"document_type": "legislation",
"language": "nl",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "BE_DPA_LAW",
"name": "Datenschutzgesetz Belgien",
"full_name": "Loi relative a la protection des personnes physiques a l'egard des traitements de donnees a caractere personnel",
"organization": "Royaume de Belgique",
"source_url": "https://www.ejustice.just.fgov.be/cgi_loi/change_lg.pl?language=fr&la=F&cn=2018073046",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Source: Loi Protection des Donnees, Royaume de Belgique (eJustice)",
"document_type": "legislation",
"language": "fr",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "LU_DPA_LAW",
"name": "Datenschutzgesetz Luxemburg",
"full_name": "Loi du 1er aout 2018 portant organisation de la Commission nationale pour la protection des donnees",
"organization": "Grand-Duche de Luxembourg",
"source_url": "https://legilux.public.lu/eli/etat/leg/loi/2018/08/01/a686/jo",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Source: Loi Protection des Donnees, Grand-Duche de Luxembourg (Legilux)",
"document_type": "legislation",
"language": "fr",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "IE_DPA_2018",
"name": "Data Protection Act 2018 Ireland",
"full_name": "Data Protection Act 2018 (Act No. 7 of 2018) - Ireland",
"organization": "Government of Ireland",
"source_url": "https://www.irishstatutebook.ie/eli/2018/act/7/enacted/en/html",
"license_code": "OGL-3.0",
"attribution_text": "Contains public sector information licensed under the Open Government Licence v3.0. Source: Data Protection Act 2018, Ireland",
"document_type": "legislation",
"language": "en",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "UK_DPA_2018",
"name": "Data Protection Act 2018 UK",
"full_name": "Data Protection Act 2018 (c. 12) - United Kingdom",
"organization": "Government of the United Kingdom",
"source_url": "https://www.legislation.gov.uk/ukpga/2018/12/contents/enacted",
"license_code": "OGL-3.0",
"attribution_text": "Contains public sector information licensed under the Open Government Licence v3.0. Source: Data Protection Act 2018, UK",
"document_type": "legislation",
"language": "en",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "UK_GDPR",
"name": "UK GDPR (retained EU law)",
"full_name": "United Kingdom General Data Protection Regulation (UK GDPR) - retained EU law",
"organization": "Government of the United Kingdom",
"source_url": "https://www.legislation.gov.uk/eur/2016/679/contents",
"license_code": "OGL-3.0",
"attribution_text": "Contains public sector information licensed under the Open Government Licence v3.0. Source: UK GDPR, legislation.gov.uk",
"document_type": "legislation",
"language": "en",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "NO_PERSONOPPLYSNINGSLOVEN",
"name": "Personopplysningsloven Norwegen",
"full_name": "Lov om behandling av personopplysninger (personopplysningsloven)",
"organization": "Kongeriket Norge",
"source_url": "https://lovdata.no/dokument/NL/lov/2018-06-15-38",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Kilde: Personopplysningsloven, Kongeriket Norge (Lovdata)",
"document_type": "legislation",
"language": "no",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "SE_DATASKYDDSLAG",
"name": "Dataskyddslag Schweden",
"full_name": "Lag (2018:218) med kompletterande bestammelser till EU:s dataskyddsforordning",
"organization": "Konungariket Sverige",
"source_url": "https://www.riksdagen.se/sv/dokument-och-lagar/dokument/svensk-forfattningssamling/lag-2018218-med-kompletterande-bestammelser-till_sfs-2018-218/",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Kalla: Dataskyddslag (2018:218), Konungariket Sverige (Riksdagen)",
"document_type": "legislation",
"language": "sv",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "DK_DATABESKYTTELSESLOVEN",
"name": "Databeskyttelsesloven Daenemark",
"full_name": "Lov om supplerende bestemmelser til forordning om beskyttelse af fysiske personer i forbindelse med behandling af personoplysninger",
"organization": "Kongeriget Danmark",
"source_url": "https://www.retsinformation.dk/eli/lta/2018/502",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Kilde: Databeskyttelsesloven, Kongeriget Danmark (Retsinformation)",
"document_type": "legislation",
"language": "da",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "FI_TIETOSUOJALAKI",
"name": "Tietosuojalaki Finnland",
"full_name": "Tietosuojalaki (1050/2018) - Datenschutzgesetz Finnland",
"organization": "Suomen tasavalta",
"source_url": "https://www.finlex.fi/fi/laki/ajantasa/2018/20181050",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Lahde: Tietosuojalaki, Suomen tasavalta (Finlex)",
"document_type": "legislation",
"language": "fi",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "PL_UODO",
"name": "UODO Polen",
"full_name": "Ustawa o ochronie danych osobowych - Datenschutzgesetz Polen",
"organization": "Rzeczpospolita Polska",
"source_url": "https://isap.sejm.gov.pl/isap.nsf/DocDetails.xsp?id=WDU20180001000",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Zrodlo: Ustawa o ochronie danych osobowych, Rzeczpospolita Polska (ISAP)",
"document_type": "legislation",
"language": "pl",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "CZ_ZOU",
"name": "Zakon o ochrane osobnich udaju Tschechien",
"full_name": "Zakon c. 110/2019 Sb. o zpracovani osobnich udaju",
"organization": "Ceska republika",
"source_url": "https://www.zakonyprolidi.cz/cs/2019-110",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Zdroj: Zakon o ochrane osobnich udaju, Ceska republika (zakonyprolidi.cz)",
"document_type": "legislation",
"language": "cs",
"migrated_to": "bp_legal_corpus"
},
{
"source_code": "HU_INFOTV",
"name": "Informacios torvenye Ungarn",
"full_name": "2011. evi CXII. torveny az informacios onrendelkezesi jogrol es az informacioszabadsagrol (Infotv.)",
"organization": "Magyarorszag",
"source_url": "https://njt.hu/jogszabaly/2011-112-00-00",
"license_code": "PUBLIC_DOMAIN",
"attribution_text": "Forras: Infotv., Magyarorszag (njt.hu)",
"document_type": "legislation",
"language": "hu",
"migrated_to": "bp_legal_corpus"
},
]
# =============================================================================
# Chunking Configuration
# =============================================================================
DSFA_CHUNK_CONFIG = {
# WP248 - Kriterien einzeln chunken
"WP248": {
"strategy": "section_based",
"section_markers": [r"K1[:\s]", r"K2[:\s]", r"K3[:\s]", r"K4[:\s]", r"K5[:\s]",
r"K6[:\s]", r"K7[:\s]", r"K8[:\s]", r"K9[:\s]"],
"max_chunk_size": 1500,
"overlap": 200
},
# DSK Kurzpapier - Prozessschritte einzeln
"DSK_KP5": {
"strategy": "section_based",
"section_markers": [r"Schritt\s*1", r"Schritt\s*2", r"Schritt\s*3",
r"Schritt\s*4", r"Schritt\s*5", r"Schritt\s*6"],
"max_chunk_size": 1200,
"overlap": 150
},
# SDM V2.0 - Gewährleistungsziele einzeln
'SDM_V2': {
'strategy': 'section_based',
'section_markers': [
r'Gewährleistungsziel\s+\d',
r'\d+\.\d+\s+',
],
'max_chunk_size': 1200,
'overlap': 150,
'categories': ['sdm_goal', 'methodology', 'implementation']
},
# Muss-Listen - Jeder Eintrag = 1 Chunk
"MUSS_LISTEN": {
"strategy": "list_item",
"list_markers": [r"^•", r"^-", r"^\d+\."],
"max_chunk_size": 800,
"overlap": 0
},
# DSK Kurzpapier Nr. 1 - VVT Schritte einzeln
"DSK_KP1": {
"strategy": "section_based",
"section_markers": [r"Schritt\s+\d", r"\d+\.\s+"],
"max_chunk_size": 1000,
"overlap": 150,
"categories": ["vvt_guidance", "art30_requirements", "controller_duties"]
},
# ICO RoPA - Sections einzeln
"ICO_ROPA": {
"strategy": "section_based",
"section_markers": [r"What\s+should", r"How\s+to", r"Controller", r"Processor"],
"max_chunk_size": 1000,
"overlap": 150,
"categories": ["vvt_guidance", "art30_requirements", "ropa_templates"]
},
# SDM Bausteine - Gewaehrleistungsziele einzeln
"SDM_BAUSTEINE": {
"strategy": "section_based",
"section_markers": [
r"Baustein\s+\d",
r"Gewaehrleistungsziel",
r"\d+\.\d+\s+",
],
"max_chunk_size": 1200,
"overlap": 150,
"categories": ["sdm_goal", "tom_measure", "implementation"]
},
# DSK Kurzpapier Nr. 7 - Loeschung
"DSK_KP7": {
"strategy": "section_based",
"section_markers": [r"Schritt\s+\d", r"\d+\.\s+", r"Loeschkonzept"],
"max_chunk_size": 1000,
"overlap": 150,
"categories": ["loeschung", "art17_requirements", "retention_guidance"]
},
# Fallback
"DEFAULT": {
"strategy": "recursive",
"max_chunk_size": 1000,
"overlap": 200
}
}