# ©AngelaMos | 2026
# .dlp-scanner.yml

scan:
  file:
    max_file_size_mb: 100
    recursive: true
    exclude_patterns:
      - "*.pyc"
      - "__pycache__"
      - ".git"
      - "node_modules"
      - ".venv"
    include_extensions:
      - ".pdf"
      - ".docx"
      - ".xlsx"
      - ".xls"
      - ".csv"
      - ".json"
      - ".xml"
      - ".yaml"
      - ".yml"
      - ".txt"
      - ".log"
      - ".eml"
      - ".msg"
      - ".parquet"
      - ".avro"
      - ".tar.gz"
      - ".tar.bz2"
      - ".zip"

  database:
    sample_percentage: 5
    max_rows_per_table: 10000
    timeout_seconds: 30
    exclude_tables: []
    include_tables: []

  network:
    bpf_filter: ""
    entropy_threshold: 7.2
    dns_label_entropy_threshold: 4.0
    max_packets: 0

detection:
  min_confidence: 0.20
  severity_threshold: "low"
  context_window_tokens: 10
  enable_rules:
    - "*"
  disable_rules: []
  allowlists:
    values:
      - "123-45-6789"
      - "000-00-0000"
      - "4111111111111111"
    domains:
      - "example.com"
      - "test.com"
    file_patterns:
      - "test_*"
      - "*_fixture*"
      - "mock_*"

compliance:
  frameworks:
    - "HIPAA"
    - "PCI_DSS"
    - "GDPR"
    - "CCPA"
    - "SOX"
    - "GLBA"

output:
  format: "console"
  output_file: ""
  redaction_style: "partial"
  verbose: false
  color: true

logging:
  level: "INFO"
  json_output: false
  log_file: ""