Implementing Gdpr Data Subject Access Request

from agent import DSARWorkflowEngine

engine = DSARWorkflowEngine(config_path="dsar_config.json")

# Register a new DSAR
request = engine.register_dsar(
    requester_name="Jane Smith",
    requester_email="jane.smith@example.com",
    request_channel="email",
    request_text="I would like a copy of all personal data you hold about me.",
    identity_docs=["passport_verified"],
)
print(f"DSAR ID: {request['dsar_id']}, Deadline: {request['deadline']}")

from agent import PIIDiscoveryEngine

pii_engine = PIIDiscoveryEngine()

# Scan structured data (database)
db_results = pii_engine.scan_database(
    connection_string="postgresql://user:pass@localhost/appdb",
    search_identifiers={"email": "jane.smith@example.com", "name": "Jane Smith"},
)

# Scan unstructured data (files, logs)
file_results = pii_engine.scan_files(
    directories=["/var/log/app", "/data/exports", "/data/documents"],
    search_identifiers={"email": "jane.smith@example.com", "name": "Jane Smith"},
)

# Scan with NER for contextual PII detection
ner_results = pii_engine.scan_with_ner(
    text_corpus=file_results["raw_text_matches"],
    entity_types=["PERSON", "EMAIL", "PHONE_NUMBER", "LOCATION", "DATE_OF_BIRTH"],
)

all_pii = pii_engine.consolidate_results(db_results, file_results, ner_results)
print(f"Found {all_pii['total_records']} PII records across {all_pii['source_count']} sources")

from agent import DataMapper

mapper = DataMapper(data_inventory_path="data_inventory.json")

# Map PII to Article 15 categories
mapped_data = mapper.map_to_article15(
    pii_records=all_pii,
    data_subject_id="jane.smith@example.com",
)

# Output includes processing purposes, recipients, retention for each data category
for category in mapped_data["categories"]:
    print(f"Category: {category['name']}")
    print(f"  Purpose: {category['processing_purpose']}")
    print(f"  Legal basis: {category['legal_basis']}")
    print(f"  Retention: {category['retention_period']}")
    print(f"  Recipients: {', '.join(category['recipients'])}")

from agent import ExemptionReviewer

reviewer = ExemptionReviewer()

# Check for applicable exemptions
review_result = reviewer.review_exemptions(
    mapped_data=mapped_data,
    exemption_checks=[
        "third_party_data",
        "legal_professional_privilege",
        "trade_secrets",
        "crime_prevention",
        "management_forecasting",
    ],
)

# Apply redactions where exemptions apply
redacted_data = reviewer.apply_redactions(mapped_data, review_result["exemptions"])
print(f"Applied {review_result['exemption_count']} exemptions")

from agent import DSARResponseGenerator

generator = DSARResponseGenerator(template_dir="templates/")

# Generate complete response package
response = generator.generate_response(
    dsar_id=request["dsar_id"],
    data_subject="Jane Smith",
    mapped_data=redacted_data,
    format="pdf",  # or "json", "csv"
)

# Package includes: cover letter, data export, supplementary info, audit log
for doc in response["documents"]:
    print(f"Generated: {doc['filename']} ({doc['type']})")

from agent import DSARAuditLogger

logger = DSARAuditLogger(log_path="dsar_audit_logs/")

# Log complete DSAR lifecycle
logger.log_event(request["dsar_id"], "request_received", {
    "channel": "email",
    "identity_verified": True,
})
logger.log_event(request["dsar_id"], "pii_discovery_complete", {
    "records_found": all_pii["total_records"],
    "sources_scanned": all_pii["source_count"],
})
logger.log_event(request["dsar_id"], "response_sent", {
    "format": "pdf",
    "documents_count": len(response["documents"]),
    "exemptions_applied": review_result["exemption_count"],
})

# Generate compliance report
compliance_report = logger.generate_compliance_report(request["dsar_id"])

from agent import DSARWorkflowEngine, PIIDiscoveryEngine, DSARResponseGenerator

# Full automated pipeline
engine = DSARWorkflowEngine(config_path="dsar_config.json")
pii = PIIDiscoveryEngine()
gen = DSARResponseGenerator(template_dir="templates/")

# 1. Intake
req = engine.register_dsar(
    requester_name="John Doe",
    requester_email="john.doe@example.com",
    request_channel="web_form",
    request_text="Please provide all my data under GDPR Article 15.",
    identity_docs=["email_verified", "account_match"],
)

# 2. Discover
results = pii.full_scan(
    search_identifiers={"email": "john.doe@example.com"},
    sources=["database", "files", "logs"],
)

# 3. Generate response
response = gen.generate_response(
    dsar_id=req["dsar_id"],
    data_subject="John Doe",
    mapped_data=results,
)

# 4. Track deadline
engine.update_status(req["dsar_id"], "response_sent")
print(f"DSAR {req['dsar_id']} completed, {engine.days_remaining(req['dsar_id'])} days remaining")

from agent import PIIPatternMatcher

matcher = PIIPatternMatcher()

# Test individual patterns
test_text = "Contact jane.smith@example.com or call +44 20 7946 0958. SSN: 123-45-6789"
matches = matcher.scan_text(test_text)
for m in matches:
    print(f"  [{m['type']}] '{m['value']}' (confidence: {m['confidence']})")