dataset: datasource/database/schema/customers

checks:
  - schema:
      allow_extra_columns: false
      allow_other_column_order: false
  - row_count:
      threshold:
        must_be_greater_than: 0
  - failed_rows:
      name: "Email should be unique (if present)"
      qualifier: email_unique
      query: |
        SELECT email
        FROM customers
        WHERE email IS NOT NULL AND email <> ''
        GROUP BY email
        HAVING COUNT(*) > 1
      threshold:
        must_be: 0

columns:
  - name: customer_id
    data_type: string
    checks:
      - missing:
      - duplicate:
      - invalid:
          name: "customer_id length guardrail"
          valid_min_length: 1
          valid_max_length: 64
  - name: email
    data_type: string
    checks:
      - invalid:
          name: "email format (basic)"
          valid_format:
            name: Email pattern
            regex: "^[^@\\s]+@[^@\\s]+\\.[^@\\s]+$"
          threshold:
            metric: percent
            must_be_less_than: 0.5
  - name: country_code
    data_type: string
    checks:
      - missing:
      - invalid:
          name: "Two-letter country code"
          valid_format:
            name: ISO-3166 alpha-2
            regex: "^[A-Z]{2}$"
  - name: status
    data_type: string
    checks:
      - missing:
      - invalid:
          name: "Allowed customer statuses"
          valid_values:
            - active
            - inactive
            - banned