breakpilot-compliance/backend-compliance/compliance/api/dsfa_routes.py

"""
FastAPI routes for DSFA — Datenschutz-Folgenabschaetzung (Art. 35 DSGVO).

Endpoints:
  GET    /v1/dsfa              — Liste (tenant_id + status-filter + skip/limit)
  POST   /v1/dsfa              — Neu erstellen → 201
  GET    /v1/dsfa/stats        — Zähler nach Status
  GET    /v1/dsfa/audit-log    — Audit-Log
  GET    /v1/dsfa/{id}         — Detail
  PUT    /v1/dsfa/{id}         — Update
  DELETE /v1/dsfa/{id}         — Löschen (Art. 17 DSGVO)
  PATCH  /v1/dsfa/{id}/status  — Schnell-Statuswechsel
"""

import logging
from datetime import datetime
from typing import Optional, List

from fastapi import APIRouter, Depends, HTTPException, Query
from pydantic import BaseModel
from sqlalchemy import text
from sqlalchemy.orm import Session

from classroom_engine.database import get_db

logger = logging.getLogger(__name__)
router = APIRouter(prefix="/dsfa", tags=["compliance-dsfa"])

DEFAULT_TENANT_ID = "default"

VALID_STATUSES = {"draft", "in-review", "approved", "needs-update"}
VALID_RISK_LEVELS = {"low", "medium", "high", "critical"}


# =============================================================================
# Pydantic Schemas
# =============================================================================

class DSFACreate(BaseModel):
    title: str
    description: str = ""
    status: str = "draft"
    risk_level: str = "low"
    processing_activity: str = ""
    data_categories: List[str] = []
    recipients: List[str] = []
    measures: List[str] = []
    created_by: str = "system"
    # Section 1
    processing_description: Optional[str] = None
    processing_purpose: Optional[str] = None
    legal_basis: Optional[str] = None
    legal_basis_details: Optional[str] = None
    # Section 2
    necessity_assessment: Optional[str] = None
    proportionality_assessment: Optional[str] = None
    data_minimization: Optional[str] = None
    alternatives_considered: Optional[str] = None
    retention_justification: Optional[str] = None
    # Section 3
    involves_ai: Optional[bool] = None
    overall_risk_level: Optional[str] = None
    risk_score: Optional[int] = None
    # Section 6
    dpo_consulted: Optional[bool] = None
    dpo_name: Optional[str] = None
    dpo_opinion: Optional[str] = None
    dpo_approved: Optional[bool] = None
    authority_consulted: Optional[bool] = None
    authority_reference: Optional[str] = None
    authority_decision: Optional[str] = None
    # Metadata
    version: Optional[int] = None
    conclusion: Optional[str] = None
    federal_state: Optional[str] = None
    authority_resource_id: Optional[str] = None
    submitted_by: Optional[str] = None
    # JSONB Arrays
    data_subjects: Optional[List[str]] = None
    affected_rights: Optional[List[str]] = None
    triggered_rule_codes: Optional[List[str]] = None
    ai_trigger_ids: Optional[List[str]] = None
    wp248_criteria_met: Optional[List[str]] = None
    art35_abs3_triggered: Optional[List[str]] = None
    tom_references: Optional[List[str]] = None
    risks: Optional[List[dict]] = None
    mitigations: Optional[List[dict]] = None
    stakeholder_consultations: Optional[List[dict]] = None
    review_triggers: Optional[List[dict]] = None
    review_comments: Optional[List[dict]] = None
    ai_use_case_modules: Optional[List[dict]] = None
    section_8_complete: Optional[bool] = None
    # JSONB Objects
    threshold_analysis: Optional[dict] = None
    consultation_requirement: Optional[dict] = None
    review_schedule: Optional[dict] = None
    section_progress: Optional[dict] = None
    metadata: Optional[dict] = None


class DSFAUpdate(BaseModel):
    title: Optional[str] = None
    description: Optional[str] = None
    status: Optional[str] = None
    risk_level: Optional[str] = None
    processing_activity: Optional[str] = None
    data_categories: Optional[List[str]] = None
    recipients: Optional[List[str]] = None
    measures: Optional[List[str]] = None
    approved_by: Optional[str] = None
    # Section 1
    processing_description: Optional[str] = None
    processing_purpose: Optional[str] = None
    legal_basis: Optional[str] = None
    legal_basis_details: Optional[str] = None
    # Section 2
    necessity_assessment: Optional[str] = None
    proportionality_assessment: Optional[str] = None
    data_minimization: Optional[str] = None
    alternatives_considered: Optional[str] = None
    retention_justification: Optional[str] = None
    # Section 3
    involves_ai: Optional[bool] = None
    overall_risk_level: Optional[str] = None
    risk_score: Optional[int] = None
    # Section 6
    dpo_consulted: Optional[bool] = None
    dpo_name: Optional[str] = None
    dpo_opinion: Optional[str] = None
    dpo_approved: Optional[bool] = None
    authority_consulted: Optional[bool] = None
    authority_reference: Optional[str] = None
    authority_decision: Optional[str] = None
    # Metadata
    version: Optional[int] = None
    conclusion: Optional[str] = None
    federal_state: Optional[str] = None
    authority_resource_id: Optional[str] = None
    submitted_by: Optional[str] = None
    # JSONB Arrays
    data_subjects: Optional[List[str]] = None
    affected_rights: Optional[List[str]] = None
    triggered_rule_codes: Optional[List[str]] = None
    ai_trigger_ids: Optional[List[str]] = None
    wp248_criteria_met: Optional[List[str]] = None
    art35_abs3_triggered: Optional[List[str]] = None
    tom_references: Optional[List[str]] = None
    risks: Optional[List[dict]] = None
    mitigations: Optional[List[dict]] = None
    stakeholder_consultations: Optional[List[dict]] = None
    review_triggers: Optional[List[dict]] = None
    review_comments: Optional[List[dict]] = None
    ai_use_case_modules: Optional[List[dict]] = None
    section_8_complete: Optional[bool] = None
    # JSONB Objects
    threshold_analysis: Optional[dict] = None
    consultation_requirement: Optional[dict] = None
    review_schedule: Optional[dict] = None
    section_progress: Optional[dict] = None
    metadata: Optional[dict] = None


class DSFAStatusUpdate(BaseModel):
    status: str
    approved_by: Optional[str] = None


# =============================================================================
# Helpers
# =============================================================================

def _get_tenant_id(tenant_id: Optional[str]) -> str:
    return tenant_id or DEFAULT_TENANT_ID


def _dsfa_to_response(row) -> dict:
    """Convert a DB row to a JSON-serializable dict."""
    import json

    def _parse_arr(val):
        """Parse a JSONB array field → list."""
        if val is None:
            return []
        if isinstance(val, list):
            return val
        if isinstance(val, str):
            try:
                parsed = json.loads(val)
                return parsed if isinstance(parsed, list) else []
            except Exception:
                return []
        return val

    def _parse_obj(val):
        """Parse a JSONB object field → dict."""
        if val is None:
            return {}
        if isinstance(val, dict):
            return val
        if isinstance(val, str):
            try:
                parsed = json.loads(val)
                return parsed if isinstance(parsed, dict) else {}
            except Exception:
                return {}
        return val

    def _ts(val):
        """Timestamp → ISO string or None."""
        return val.isoformat() if val else None

    def _get(key, default=None):
        """Safe row access — returns default if key missing (handles old rows)."""
        try:
            v = row[key]
            return default if v is None and default is not None else v
        except (KeyError, IndexError):
            return default

    return {
        # Core fields (always present since Migration 024)
        "id": str(row["id"]),
        "tenant_id": row["tenant_id"],
        "title": row["title"],
        "description": row["description"] or "",
        "status": row["status"] or "draft",
        "risk_level": row["risk_level"] or "low",
        "processing_activity": row["processing_activity"] or "",
        "data_categories": _parse_arr(row["data_categories"]),
        "recipients": _parse_arr(row["recipients"]),
        "measures": _parse_arr(row["measures"]),
        "approved_by": row["approved_by"],
        "approved_at": _ts(row["approved_at"]),
        "created_by": row["created_by"] or "system",
        "created_at": _ts(row["created_at"]),
        "updated_at": _ts(row["updated_at"]),
        # Section 1 (Migration 030)
        "processing_description": _get("processing_description"),
        "processing_purpose": _get("processing_purpose"),
        "legal_basis": _get("legal_basis"),
        "legal_basis_details": _get("legal_basis_details"),
        # Section 2
        "necessity_assessment": _get("necessity_assessment"),
        "proportionality_assessment": _get("proportionality_assessment"),
        "data_minimization": _get("data_minimization"),
        "alternatives_considered": _get("alternatives_considered"),
        "retention_justification": _get("retention_justification"),
        # Section 3
        "involves_ai": _get("involves_ai", False),
        "overall_risk_level": _get("overall_risk_level"),
        "risk_score": _get("risk_score", 0),
        # Section 6
        "dpo_consulted": _get("dpo_consulted", False),
        "dpo_consulted_at": _ts(_get("dpo_consulted_at")),
        "dpo_name": _get("dpo_name"),
        "dpo_opinion": _get("dpo_opinion"),
        "dpo_approved": _get("dpo_approved"),
        "authority_consulted": _get("authority_consulted", False),
        "authority_consulted_at": _ts(_get("authority_consulted_at")),
        "authority_reference": _get("authority_reference"),
        "authority_decision": _get("authority_decision"),
        # Metadata / Versioning
        "version": _get("version", 1),
        "previous_version_id": str(_get("previous_version_id")) if _get("previous_version_id") else None,
        "conclusion": _get("conclusion"),
        "federal_state": _get("federal_state"),
        "authority_resource_id": _get("authority_resource_id"),
        "submitted_for_review_at": _ts(_get("submitted_for_review_at")),
        "submitted_by": _get("submitted_by"),
        # JSONB Arrays
        "data_subjects": _parse_arr(_get("data_subjects")),
        "affected_rights": _parse_arr(_get("affected_rights")),
        "triggered_rule_codes": _parse_arr(_get("triggered_rule_codes")),
        "ai_trigger_ids": _parse_arr(_get("ai_trigger_ids")),
        "wp248_criteria_met": _parse_arr(_get("wp248_criteria_met")),
        "art35_abs3_triggered": _parse_arr(_get("art35_abs3_triggered")),
        "tom_references": _parse_arr(_get("tom_references")),
        "risks": _parse_arr(_get("risks")),
        "mitigations": _parse_arr(_get("mitigations")),
        "stakeholder_consultations": _parse_arr(_get("stakeholder_consultations")),
        "review_triggers": _parse_arr(_get("review_triggers")),
        "review_comments": _parse_arr(_get("review_comments")),
        # Section 8 / AI (Migration 028)
        "ai_use_case_modules": _parse_arr(_get("ai_use_case_modules")),
        "section_8_complete": _get("section_8_complete", False),
        # JSONB Objects
        "threshold_analysis": _parse_obj(_get("threshold_analysis")),
        "consultation_requirement": _parse_obj(_get("consultation_requirement")),
        "review_schedule": _parse_obj(_get("review_schedule")),
        "section_progress": _parse_obj(_get("section_progress")),
        "metadata": _parse_obj(_get("metadata")),
    }


def _log_audit(
    db: Session,
    tenant_id: str,
    dsfa_id,
    action: str,
    changed_by: str = "system",
    old_values=None,
    new_values=None,
):
    import json
    db.execute(
        text("""
            INSERT INTO compliance_dsfa_audit_log
                (tenant_id, dsfa_id, action, changed_by, old_values, new_values)
            VALUES
                (:tenant_id, :dsfa_id, :action, :changed_by,
                 CAST(:old_values AS jsonb), CAST(:new_values AS jsonb))
        """),
        {
            "tenant_id": tenant_id,
            "dsfa_id": str(dsfa_id) if dsfa_id else None,
            "action": action,
            "changed_by": changed_by,
            "old_values": json.dumps(old_values) if old_values else None,
            "new_values": json.dumps(new_values) if new_values else None,
        },
    )


# =============================================================================
# Stats (must be before /{id} to avoid route conflict)
# =============================================================================

@router.get("/stats")
async def get_stats(
    tenant_id: Optional[str] = Query(None),
    db: Session = Depends(get_db),
):
    """Zähler nach Status und Risiko-Level."""
    tid = _get_tenant_id(tenant_id)
    rows = db.execute(
        text("SELECT status, risk_level FROM compliance_dsfas WHERE tenant_id = :tid"),
        {"tid": tid},
    ).fetchall()

    by_status: dict = {}
    by_risk: dict = {}
    for row in rows:
        s = row["status"] or "draft"
        r = row["risk_level"] or "low"
        by_status[s] = by_status.get(s, 0) + 1
        by_risk[r] = by_risk.get(r, 0) + 1

    return {
        "total": len(rows),
        "by_status": by_status,
        "by_risk_level": by_risk,
        "draft_count": by_status.get("draft", 0),
        "in_review_count": by_status.get("in-review", 0),
        "approved_count": by_status.get("approved", 0),
        "needs_update_count": by_status.get("needs-update", 0),
    }


# =============================================================================
# Audit Log (must be before /{id} to avoid route conflict)
# =============================================================================

@router.get("/audit-log")
async def get_audit_log(
    tenant_id: Optional[str] = Query(None),
    limit: int = Query(50, ge=1, le=500),
    offset: int = Query(0, ge=0),
    db: Session = Depends(get_db),
):
    """DSFA Audit-Trail."""
    tid = _get_tenant_id(tenant_id)
    rows = db.execute(
        text("""
            SELECT id, tenant_id, dsfa_id, action, changed_by, old_values, new_values, created_at
            FROM compliance_dsfa_audit_log
            WHERE tenant_id = :tid
            ORDER BY created_at DESC
            LIMIT :limit OFFSET :offset
        """),
        {"tid": tid, "limit": limit, "offset": offset},
    ).fetchall()

    return [
        {
            "id": str(r["id"]),
            "tenant_id": r["tenant_id"],
            "dsfa_id": str(r["dsfa_id"]) if r["dsfa_id"] else None,
            "action": r["action"],
            "changed_by": r["changed_by"],
            "old_values": r["old_values"],
            "new_values": r["new_values"],
            "created_at": r["created_at"].isoformat() if r["created_at"] else None,
        }
        for r in rows
    ]


# =============================================================================
# List + Create
# =============================================================================

@router.get("")
async def list_dsfas(
    tenant_id: Optional[str] = Query(None),
    status: Optional[str] = Query(None),
    risk_level: Optional[str] = Query(None),
    skip: int = Query(0, ge=0),
    limit: int = Query(100, ge=1, le=500),
    db: Session = Depends(get_db),
):
    """Liste aller DSFAs für einen Tenant."""
    tid = _get_tenant_id(tenant_id)

    sql = "SELECT * FROM compliance_dsfas WHERE tenant_id = :tid"
    params: dict = {"tid": tid}

    if status:
        sql += " AND status = :status"
        params["status"] = status
    if risk_level:
        sql += " AND risk_level = :risk_level"
        params["risk_level"] = risk_level

    sql += " ORDER BY created_at DESC LIMIT :limit OFFSET :skip"
    params["limit"] = limit
    params["skip"] = skip

    rows = db.execute(text(sql), params).fetchall()
    return [_dsfa_to_response(r) for r in rows]


@router.post("", status_code=201)
async def create_dsfa(
    request: DSFACreate,
    tenant_id: Optional[str] = Query(None),
    db: Session = Depends(get_db),
):
    """Neue DSFA erstellen."""
    import json

    if request.status not in VALID_STATUSES:
        raise HTTPException(status_code=422, detail=f"Ungültiger Status: {request.status}")
    if request.risk_level not in VALID_RISK_LEVELS:
        raise HTTPException(status_code=422, detail=f"Ungültiges Risiko-Level: {request.risk_level}")

    tid = _get_tenant_id(tenant_id)

    row = db.execute(
        text("""
            INSERT INTO compliance_dsfas
                (tenant_id, title, description, status, risk_level,
                 processing_activity, data_categories, recipients, measures, created_by)
            VALUES
                (:tenant_id, :title, :description, :status, :risk_level,
                 :processing_activity,
                 CAST(:data_categories AS jsonb),
                 CAST(:recipients AS jsonb),
                 CAST(:measures AS jsonb),
                 :created_by)
            RETURNING *
        """),
        {
            "tenant_id": tid,
            "title": request.title,
            "description": request.description,
            "status": request.status,
            "risk_level": request.risk_level,
            "processing_activity": request.processing_activity,
            "data_categories": json.dumps(request.data_categories),
            "recipients": json.dumps(request.recipients),
            "measures": json.dumps(request.measures),
            "created_by": request.created_by,
        },
    ).fetchone()

    db.flush()
    _log_audit(
        db, tid, row["id"], "CREATE", request.created_by,
        new_values={"title": request.title, "status": request.status},
    )
    db.commit()
    return _dsfa_to_response(row)


# =============================================================================
# Single Item (GET / PUT / DELETE / PATCH status)
# =============================================================================

@router.get("/{dsfa_id}")
async def get_dsfa(
    dsfa_id: str,
    tenant_id: Optional[str] = Query(None),
    db: Session = Depends(get_db),
):
    """Einzelne DSFA abrufen."""
    tid = _get_tenant_id(tenant_id)
    row = db.execute(
        text("SELECT * FROM compliance_dsfas WHERE id = :id AND tenant_id = :tid"),
        {"id": dsfa_id, "tid": tid},
    ).fetchone()
    if not row:
        raise HTTPException(status_code=404, detail=f"DSFA {dsfa_id} nicht gefunden")
    return _dsfa_to_response(row)


@router.put("/{dsfa_id}")
async def update_dsfa(
    dsfa_id: str,
    request: DSFAUpdate,
    tenant_id: Optional[str] = Query(None),
    db: Session = Depends(get_db),
):
    """DSFA aktualisieren."""
    import json

    tid = _get_tenant_id(tenant_id)
    existing = db.execute(
        text("SELECT * FROM compliance_dsfas WHERE id = :id AND tenant_id = :tid"),
        {"id": dsfa_id, "tid": tid},
    ).fetchone()
    if not existing:
        raise HTTPException(status_code=404, detail=f"DSFA {dsfa_id} nicht gefunden")

    updates = request.model_dump(exclude_none=True)

    if "status" in updates and updates["status"] not in VALID_STATUSES:
        raise HTTPException(status_code=422, detail=f"Ungültiger Status: {updates['status']}")
    if "risk_level" in updates and updates["risk_level"] not in VALID_RISK_LEVELS:
        raise HTTPException(status_code=422, detail=f"Ungültiges Risiko-Level: {updates['risk_level']}")

    if not updates:
        return _dsfa_to_response(existing)

    set_clauses = []
    params: dict = {"id": dsfa_id, "tid": tid}

    jsonb_fields = {
        "data_categories", "recipients", "measures",
        "data_subjects", "affected_rights", "triggered_rule_codes",
        "ai_trigger_ids", "wp248_criteria_met", "art35_abs3_triggered",
        "tom_references", "risks", "mitigations", "stakeholder_consultations",
        "review_triggers", "review_comments", "ai_use_case_modules",
        "threshold_analysis", "consultation_requirement", "review_schedule",
        "section_progress", "metadata",
    }
    for field, value in updates.items():
        if field in jsonb_fields:
            set_clauses.append(f"{field} = CAST(:{field} AS jsonb)")
            params[field] = json.dumps(value)
        else:
            set_clauses.append(f"{field} = :{field}")
            params[field] = value

    set_clauses.append("updated_at = NOW()")
    sql = f"UPDATE compliance_dsfas SET {', '.join(set_clauses)} WHERE id = :id AND tenant_id = :tid RETURNING *"

    old_values = {"title": existing["title"], "status": existing["status"]}
    row = db.execute(text(sql), params).fetchone()
    _log_audit(db, tid, dsfa_id, "UPDATE", new_values=updates, old_values=old_values)
    db.commit()
    return _dsfa_to_response(row)


@router.delete("/{dsfa_id}")
async def delete_dsfa(
    dsfa_id: str,
    tenant_id: Optional[str] = Query(None),
    db: Session = Depends(get_db),
):
    """DSFA löschen (Art. 17 DSGVO)."""
    tid = _get_tenant_id(tenant_id)
    existing = db.execute(
        text("SELECT id, title FROM compliance_dsfas WHERE id = :id AND tenant_id = :tid"),
        {"id": dsfa_id, "tid": tid},
    ).fetchone()
    if not existing:
        raise HTTPException(status_code=404, detail=f"DSFA {dsfa_id} nicht gefunden")

    _log_audit(db, tid, dsfa_id, "DELETE", old_values={"title": existing["title"]})
    db.execute(
        text("DELETE FROM compliance_dsfas WHERE id = :id AND tenant_id = :tid"),
        {"id": dsfa_id, "tid": tid},
    )
    db.commit()
    return {"success": True, "message": f"DSFA {dsfa_id} gelöscht"}


@router.patch("/{dsfa_id}/status")
async def update_dsfa_status(
    dsfa_id: str,
    request: DSFAStatusUpdate,
    tenant_id: Optional[str] = Query(None),
    db: Session = Depends(get_db),
):
    """Schnell-Statuswechsel."""
    if request.status not in VALID_STATUSES:
        raise HTTPException(status_code=422, detail=f"Ungültiger Status: {request.status}")

    tid = _get_tenant_id(tenant_id)
    existing = db.execute(
        text("SELECT id, status FROM compliance_dsfas WHERE id = :id AND tenant_id = :tid"),
        {"id": dsfa_id, "tid": tid},
    ).fetchone()
    if not existing:
        raise HTTPException(status_code=404, detail=f"DSFA {dsfa_id} nicht gefunden")

    params: dict = {
        "id": dsfa_id, "tid": tid,
        "status": request.status,
        "approved_at": datetime.utcnow() if request.status == "approved" else None,
        "approved_by": request.approved_by,
    }
    row = db.execute(
        text("""
            UPDATE compliance_dsfas
            SET status = :status, approved_at = :approved_at, approved_by = :approved_by, updated_at = NOW()
            WHERE id = :id AND tenant_id = :tid
            RETURNING *
        """),
        params,
    ).fetchone()

    _log_audit(
        db, tid, dsfa_id, "STATUS_CHANGE",
        old_values={"status": existing["status"]},
        new_values={"status": request.status},
    )
    db.commit()
    return _dsfa_to_response(row)