b363c28539
Split dsi_document_checker.py (466 LOC) into doc_checks/ package (9 files). Two-pass L1→L2 logic: L1 checks "Is it mentioned?", L2 checks "Is it correct?" (e.g. controller has full address, specific Art. 6 lit., concrete time periods). 138 total checks (62 L1 + 76 L2) across 7 doc types: - DSE Art. 13: 31, Impressum §5 TMG: 16, Cookie §25 TDDDG: 15 - Widerruf §355: 15, AGB §305ff: 21, Social Media Art. 26: 20, DSFA Art. 35: 18 Frontend: hierarchical L1→L2 display with dual progress bars (green=completeness, blue=correctness). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
360 lines
14 KiB
Python
360 lines
14 KiB
Python
"""
|
|
DSE (Datenschutzinformation) checks — Art. 13/14 DSGVO.
|
|
|
|
Level 1: Pflichtangabe erwaehnt?
|
|
Level 2: Pflichtangabe korrekt/vollstaendig?
|
|
"""
|
|
|
|
ART13_CHECKLIST = [
|
|
# ── L1: Verantwortlicher ──────────────────────────────────────────
|
|
{
|
|
"id": "controller",
|
|
"label": "Verantwortlicher (Art. 13(1)(a))",
|
|
"level": 1, "parent": None,
|
|
"patterns": [
|
|
r"verantwortlich\w*\s+(?:ist|im sinne|fuer|f(?:ue|ü)r)",
|
|
r"kontaktdaten\s+des\s+verantwortlichen",
|
|
r"name\s+(?:und|&)\s+kontaktdaten\s+des",
|
|
r"controller", r"verantwortliche\s+stelle",
|
|
r"responsible\s+(?:party|for)",
|
|
],
|
|
"severity": "HIGH",
|
|
},
|
|
{
|
|
"id": "controller_address",
|
|
"label": "Vollstaendige Anschrift (PLZ + Ort)",
|
|
"level": 2, "parent": "controller",
|
|
"patterns": [
|
|
r"\d{5}\s+[A-Z\u00c0-\u017e]\w+",
|
|
r"[A-Z\u00c0-\u017e]\w+(?:str|stra(?:ss|ß)e|weg|platz|allee|gasse)\s*\.?\s*\d",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
{
|
|
"id": "controller_email",
|
|
"label": "E-Mail-Adresse des Verantwortlichen",
|
|
"level": 2, "parent": "controller",
|
|
"patterns": [
|
|
r"[a-z0-9._%+\-]+@[a-z0-9.\-]+\.[a-z]{2,}",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
{
|
|
"id": "controller_phone",
|
|
"label": "Telefonnummer des Verantwortlichen",
|
|
"level": 2, "parent": "controller",
|
|
"patterns": [
|
|
r"(?:tel(?:efon)?|phone|fon)\s*[.:]\s*[\+\d][\d\s/\-]{6,}",
|
|
r"\+49\s*[\d\s/\-]{8,}",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
|
|
# ── L1: Datenschutzbeauftragter ───────────────────────────────────
|
|
{
|
|
"id": "dpo",
|
|
"label": "Datenschutzbeauftragter (Art. 13(1)(b))",
|
|
"level": 1, "parent": None,
|
|
"patterns": [
|
|
r"datenschutzbeauftragt", r"data\s+protection\s+officer",
|
|
r"kontaktdaten\s+de[rs]\s+(?:beh(?:oe|ö)rdlichen\s+)?datenschutz",
|
|
r"dsb", r"dpo",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
{
|
|
"id": "dpo_contact",
|
|
"label": "Kontaktdaten des DSB (E-Mail oder Telefon)",
|
|
"level": 2, "parent": "dpo",
|
|
"patterns": [
|
|
r"datenschutz(?:beauftragter?|beauftragte).*?[a-z0-9._%+\-]+@",
|
|
r"dsb.*?@|dpo.*?@",
|
|
r"datenschutz@",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
|
|
# ── L1: Zwecke der Verarbeitung ───────────────────────────────────
|
|
{
|
|
"id": "purposes",
|
|
"label": "Zwecke der Verarbeitung (Art. 13(1)(c))",
|
|
"level": 1, "parent": None,
|
|
"patterns": [
|
|
r"zweck\w*\s+(?:der|und|die)\s+(?:verarbeitung|datenerhebung|datenverarbeitung|rechtsgrundlage)",
|
|
r"purpose\w*\s+(?:of|for)\s+(?:processing|data)",
|
|
r"zu\s+welch\w+\s+zweck",
|
|
r"welche\s+daten\s+werden.*verarbeitet",
|
|
r"daten\s+werden\s+(?:zu|fuer|für)\s+(?:folgende|diese)",
|
|
],
|
|
"severity": "HIGH",
|
|
},
|
|
{
|
|
"id": "purposes_specific",
|
|
"label": "Konkrete Zwecke benannt (min. 2)",
|
|
"level": 2, "parent": "purposes",
|
|
"patterns": [
|
|
r"(?:kontaktaufnahme|vertragserfuellung|vertragserf(?:ue|ü)llung|newsletter|analyse|statistik|werbung|marketing|bewerbung|bestellabwicklung|kundenkonto)",
|
|
r"(?:bereitstellung|betrieb|sicherheit|optimierung)\s+(?:der|des|unserer|unseres)",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
|
|
# ── L1: Rechtsgrundlage ───────────────────────────────────────────
|
|
{
|
|
"id": "legal_basis",
|
|
"label": "Rechtsgrundlage (Art. 13(1)(c))",
|
|
"level": 1, "parent": None,
|
|
"patterns": [
|
|
r"rechtsgrundlage", r"art\.\s*6\s*(?:abs|absatz)?\s*\.?\s*1",
|
|
r"legal\s+basis", r"berechtigtes\s+interesse",
|
|
r"auf\s+grundlage\s+(?:von|des|der)\s+(?:art|§)",
|
|
r"lit\.\s*[a-f][\s\)]",
|
|
r"gem(?:ae|ä)(?:ss|ß)\s+art",
|
|
r"§\s*\d+\s+(?:abs|ihkg|bdsg|ldsg|bbig|tdddg)",
|
|
r"einwilligung\s+gem",
|
|
],
|
|
"severity": "HIGH",
|
|
},
|
|
{
|
|
"id": "legal_basis_consent_6a",
|
|
"label": "Art. 6(1)(a) — Einwilligung",
|
|
"level": 2, "parent": "legal_basis",
|
|
"patterns": [
|
|
r"art\.\s*6\s*(?:abs\.\s*)?1\s*(?:s\.\s*1\s*)?(?:lit\.\s*)?a",
|
|
r"einwilligung\s+(?:gem|nach|i\.?\s*s\.?\s*d\.?)",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "legal_basis_contract_6b",
|
|
"label": "Art. 6(1)(b) — Vertragserfullung",
|
|
"level": 2, "parent": "legal_basis",
|
|
"patterns": [
|
|
r"art\.\s*6\s*(?:abs\.\s*)?1\s*(?:s\.\s*1\s*)?(?:lit\.\s*)?b",
|
|
r"vertragserf(?:ue|ü)llung",
|
|
r"durchf(?:ue|ü)hrung\s+(?:eines|des|vorvertragliche)",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "legal_basis_interest_6f",
|
|
"label": "Art. 6(1)(f) — Berechtigtes Interesse",
|
|
"level": 2, "parent": "legal_basis",
|
|
"patterns": [
|
|
r"art\.\s*6\s*(?:abs\.\s*)?1\s*(?:s\.\s*1\s*)?(?:lit\.\s*)?f",
|
|
r"berechtigte[sn]?\s+interesse",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "legal_basis_balancing",
|
|
"label": "Interessenabwaegung dokumentiert",
|
|
"level": 2, "parent": "legal_basis",
|
|
"patterns": [
|
|
r"interessenabw(?:ae|ä)gung",
|
|
r"(?:ueberwiegen|überwiegen).*interesse",
|
|
r"abw(?:ae|ä)gung.*(?:recht|interesse|freiheit)",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
|
|
# ── L1: Empfaenger ────────────────────────────────────────────────
|
|
{
|
|
"id": "recipients",
|
|
"label": "Empfaenger (Art. 13(1)(e))",
|
|
"level": 1, "parent": None,
|
|
"patterns": [
|
|
r"empf(?:ae|ä)nger", r"(?:ueber|über|weiter)mitt(?:el|l)ung",
|
|
r"recipient", r"weitergabe\s+(?:an|von)\s+daten",
|
|
r"dritte", r"third\s+part",
|
|
r"auftragsverarbeit",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
{
|
|
"id": "recipients_categories",
|
|
"label": "Konkrete Empfaenger-Kategorien benannt",
|
|
"level": 2, "parent": "recipients",
|
|
"patterns": [
|
|
r"(?:hosting|server|cloud|payment|zahlungs|versand|logistik|steuerberater|buchhalter|newsletter|crm|erp)",
|
|
r"(?:dienstleister|auftragnehmer|subunternehmer).*(?:fuer|für|im bereich)",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "recipients_processor",
|
|
"label": "Auftragsverarbeiter erwaehnt",
|
|
"level": 2, "parent": "recipients",
|
|
"patterns": [
|
|
r"auftragsverarbeit(?:er|ung)",
|
|
r"art\.\s*28",
|
|
r"avv|av-vertrag|auftragsverarbeitungsvertrag",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
|
|
# ── L1: Drittlandtransfer ─────────────────────────────────────────
|
|
{
|
|
"id": "third_country",
|
|
"label": "Drittlandtransfer (Art. 13(1)(f))",
|
|
"level": 1, "parent": None,
|
|
"patterns": [
|
|
r"drittland", r"dritt\s*staat", r"drittl(?:ae|ä)nder",
|
|
r"third\s+countr", r"angemessenheitsbeschluss",
|
|
r"standard\s*vertragsklausel", r"scc",
|
|
r"(?:ueber|über)mittlung.*(?:ausserhalb|außerhalb)",
|
|
r"(?:europ(?:ae|ä)ischen\s+wirtschaftsraum|ewr|eea)",
|
|
r"privacy\s+shield", r"data\s+privacy\s+framework",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
{
|
|
"id": "third_country_mechanism",
|
|
"label": "Transfermechanismus benannt (SCC/DPF/Angemessenheit)",
|
|
"level": 2, "parent": "third_country",
|
|
"patterns": [
|
|
r"standard\s*vertragsklausel|scc|standard\s+contractual",
|
|
r"data\s+privacy\s+framework|dpf",
|
|
r"angemessenheitsbeschluss|adequacy\s+decision",
|
|
r"art\.\s*4[5-9]",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
|
|
# ── L1: Speicherdauer ─────────────────────────────────────────────
|
|
{
|
|
"id": "retention",
|
|
"label": "Speicherdauer (Art. 13(2)(a))",
|
|
"level": 1, "parent": None,
|
|
"patterns": [
|
|
r"speicherdauer", r"aufbewahrungsfrist",
|
|
r"(?:wie\s+lange|dauer)\s+(?:der\s+)?(?:werden|gespeicher|speicherung)",
|
|
r"retention\s+period", r"l(?:oe|ö)sch(?:ung|frist|konzept)",
|
|
r"daten\s+werden\s+gel(?:oe|ö)scht",
|
|
r"(?:\d+\s+(?:tage|monate|jahre)|nach\s+\d+\s+(?:tag|monat|jahr))",
|
|
r"dauer\s+der\s+speicherung",
|
|
r"aufbewahrung(?:sdauer|spflicht|szeit)",
|
|
r"gesetzliche.*aufbewahrung",
|
|
],
|
|
"severity": "HIGH",
|
|
},
|
|
{
|
|
"id": "retention_periods",
|
|
"label": "Konkrete Zeitangaben (Tage/Monate/Jahre)",
|
|
"level": 2, "parent": "retention",
|
|
"patterns": [
|
|
r"\d+\s+(?:tage?|monate?|jahre?|days?|months?|years?)",
|
|
r"(?:6|10)\s+jahre.*(?:handels|steuer|hgb|ao)",
|
|
r"(?:nach|innerhalb)\s+(?:von\s+)?\d+\s+(?:tag|monat|jahr)",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
{
|
|
"id": "retention_deletion",
|
|
"label": "Loeschkonzept/-prozess beschrieben",
|
|
"level": 2, "parent": "retention",
|
|
"patterns": [
|
|
r"l(?:oe|ö)schkonzept", r"l(?:oe|ö)schfrist",
|
|
r"(?:regel|routinem(?:ae|ä)(?:ss|ß)ig).*l(?:oe|ö)sch",
|
|
r"nach\s+(?:ablauf|wegfall).*(?:gel(?:oe|ö)scht|l(?:oe|ö)sch)",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
|
|
# ── L1: Betroffenenrechte ─────────────────────────────────────────
|
|
{
|
|
"id": "rights",
|
|
"label": "Betroffenenrechte (Art. 13(2)(b))",
|
|
"level": 1, "parent": None,
|
|
"patterns": [
|
|
r"recht\s+auf\s+auskunft", r"recht\s+auf\s+l(?:oe|ö)schung",
|
|
r"recht\s+auf\s+berichtigung", r"widerspruchsrecht",
|
|
r"art\.\s*1[5-9]", r"art\.\s*2[0-2]",
|
|
r"right\s+to\s+(?:access|erasure|rectification|object)",
|
|
r"betroffenenrecht", r"rechte\s+(?:des|der)\s+betroffenen",
|
|
r"ihnen\s+(?:stehen|steht)\s+(?:ein|folgende)\s+recht",
|
|
],
|
|
"severity": "HIGH",
|
|
},
|
|
{
|
|
"id": "rights_art15",
|
|
"label": "Recht auf Auskunft (Art. 15)",
|
|
"level": 2, "parent": "rights",
|
|
"patterns": [r"art\.\s*15", r"recht\s+auf\s+auskunft", r"right\s+(?:of|to)\s+access"],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "rights_art16",
|
|
"label": "Recht auf Berichtigung (Art. 16)",
|
|
"level": 2, "parent": "rights",
|
|
"patterns": [r"art\.\s*16", r"recht\s+auf\s+berichtigung", r"right\s+to\s+rectification"],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "rights_art17",
|
|
"label": "Recht auf Loeschung (Art. 17)",
|
|
"level": 2, "parent": "rights",
|
|
"patterns": [r"art\.\s*17", r"recht\s+auf\s+l(?:oe|ö)schung", r"right\s+to\s+erasure"],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "rights_art18",
|
|
"label": "Recht auf Einschraenkung (Art. 18)",
|
|
"level": 2, "parent": "rights",
|
|
"patterns": [r"art\.\s*18", r"einschr(?:ae|ä)nkung\s+der\s+verarbeitung", r"right\s+to\s+restriction"],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "rights_art20",
|
|
"label": "Recht auf Datenportabilitaet (Art. 20)",
|
|
"level": 2, "parent": "rights",
|
|
"patterns": [r"art\.\s*20", r"daten(?:ue|ü)bertragbarkeit|datenportabilit", r"right\s+to\s+data\s+portability"],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "rights_art21",
|
|
"label": "Widerspruchsrecht (Art. 21)",
|
|
"level": 2, "parent": "rights",
|
|
"patterns": [r"art\.\s*21", r"widerspruchsrecht", r"right\s+to\s+object"],
|
|
"severity": "LOW",
|
|
},
|
|
{
|
|
"id": "rights_art22_profiling",
|
|
"label": "Automatisierte Entscheidungen / Profiling (Art. 22)",
|
|
"level": 2, "parent": "rights",
|
|
"patterns": [
|
|
r"art\.\s*22", r"automatisierte\s+entscheidung",
|
|
r"profiling", r"automated\s+(?:decision|individual)",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
|
|
# ── L1: Beschwerderecht ───────────────────────────────────────────
|
|
{
|
|
"id": "complaint",
|
|
"label": "Beschwerderecht (Art. 13(2)(d))",
|
|
"level": 1, "parent": None,
|
|
"patterns": [
|
|
r"beschwerderecht", r"aufsichtsbeh(?:oe|ö)rde",
|
|
r"right\s+to\s+lodge\s+a\s+complaint",
|
|
r"supervisory\s+authority", r"datenschutzbeh(?:oe|ö)rde",
|
|
r"recht\s+auf\s+beschwerde", r"art\.\s*77",
|
|
r"beschwerde.*(?:wenden|einlegen|erheben)",
|
|
r"(?:zust(?:ae|ä)ndige|competent)\s+(?:beh(?:oe|ö)rde|authority)",
|
|
],
|
|
"severity": "MEDIUM",
|
|
},
|
|
{
|
|
"id": "complaint_authority_named",
|
|
"label": "Konkrete Aufsichtsbehoerde benannt",
|
|
"level": 2, "parent": "complaint",
|
|
"patterns": [
|
|
r"(?:landes|l)(?:beauftragt|datenschutz).*(?:niedersachsen|bayern|nrw|nordrhein|hessen|baden|schleswig|brandenburg|sachsen|berlin|hamburg|bremen|thueringen|thüringen|saarland|rheinland|mecklenburg)",
|
|
r"l(?:an)?fdi\s+\w+",
|
|
r"bfdi",
|
|
r"(?:bayerische|hessische|s(?:ae|ä)chsische|berliner)\s+(?:datenschutz|aufsicht)",
|
|
],
|
|
"severity": "LOW",
|
|
},
|
|
]
|