feat: Add Document Crawler & Auto-Onboarding service (Phase 1.4)
New standalone Python/FastAPI service for automatic compliance document scanning, LLM-based classification, IPFS archival, and gap analysis. Includes extractors (PDF, DOCX, XLSX, PPTX), keyword fallback classifier, compliance matrix, and full REST API on port 8098. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
75
document-crawler/gap_analysis/compliance_matrix.py
Normal file
75
document-crawler/gap_analysis/compliance_matrix.py
Normal file
@@ -0,0 +1,75 @@
|
||||
"""Required documents per regulation and company type."""
|
||||
|
||||
from dataclasses import dataclass
|
||||
|
||||
|
||||
@dataclass
|
||||
class RequiredDocument:
|
||||
category: str
|
||||
description: str
|
||||
regulation: str
|
||||
severity: str # CRITICAL, HIGH, MEDIUM
|
||||
applies_to: str # universal, data_processor, ai_user, large_company
|
||||
|
||||
|
||||
COMPLIANCE_MATRIX: list[RequiredDocument] = [
|
||||
# Universal — every company
|
||||
RequiredDocument(
|
||||
category="VVT",
|
||||
description="Verzeichnis von Verarbeitungstaetigkeiten fehlt",
|
||||
regulation="Art. 30 DSGVO",
|
||||
severity="CRITICAL",
|
||||
applies_to="universal",
|
||||
),
|
||||
RequiredDocument(
|
||||
category="TOM",
|
||||
description="Technisch-organisatorische Massnahmen nicht dokumentiert",
|
||||
regulation="Art. 32 DSGVO",
|
||||
severity="CRITICAL",
|
||||
applies_to="universal",
|
||||
),
|
||||
RequiredDocument(
|
||||
category="DSE",
|
||||
description="Datenschutzerklaerung fehlt oder unvollstaendig",
|
||||
regulation="Art. 13/14 DSGVO",
|
||||
severity="CRITICAL",
|
||||
applies_to="universal",
|
||||
),
|
||||
RequiredDocument(
|
||||
category="Loeschkonzept",
|
||||
description="Kein Loeschkonzept / keine Loeschfristen definiert",
|
||||
regulation="Art. 17 DSGVO / Art. 5 Abs. 1e DSGVO",
|
||||
severity="HIGH",
|
||||
applies_to="universal",
|
||||
),
|
||||
RequiredDocument(
|
||||
category="Richtlinie",
|
||||
description="Interne Datenschutzrichtlinie fehlt",
|
||||
regulation="Art. 24 DSGVO",
|
||||
severity="MEDIUM",
|
||||
applies_to="universal",
|
||||
),
|
||||
RequiredDocument(
|
||||
category="Schulungsnachweis",
|
||||
description="Keine Datenschutz-Schulungsnachweise vorhanden",
|
||||
regulation="Art. 39 Abs. 1b DSGVO",
|
||||
severity="MEDIUM",
|
||||
applies_to="universal",
|
||||
),
|
||||
# Data processors
|
||||
RequiredDocument(
|
||||
category="AVV",
|
||||
description="Auftragsverarbeitungsvertrag fehlt",
|
||||
regulation="Art. 28 DSGVO",
|
||||
severity="CRITICAL",
|
||||
applies_to="data_processor",
|
||||
),
|
||||
# AI users
|
||||
RequiredDocument(
|
||||
category="DSFA",
|
||||
description="Datenschutz-Folgenabschaetzung fuer KI-Systeme fehlt",
|
||||
regulation="Art. 35 DSGVO / EU AI Act",
|
||||
severity="HIGH",
|
||||
applies_to="ai_user",
|
||||
),
|
||||
]
|
||||
Reference in New Issue
Block a user