dataset: datasource/database/schema/products

checks:
  - schema:
      allow_extra_columns: false
      allow_other_column_order: false
  - row_count:
      threshold:
        must_be_greater_than: 0

  # Dataset integrity rules
  - failed_rows:
      name: "List price must not be negative"
      qualifier: list_price_non_negative
      expression: list_price < 0
  - failed_rows:
      name: "SKU should be unique"
      qualifier: sku_unique
      query: |
        SELECT sku
        FROM datasource.database.schema.products
        WHERE sku IS NOT NULL
        GROUP BY sku
        HAVING COUNT(*) > 1
      threshold:
        must_be: 0
      description: "Prevents duplicate SKUs that break catalog joins and reporting."

columns:
  - name: product_id
    data_type: string
    checks:
      - missing:
      - duplicate:
      - invalid:
          name: "product_id length guardrail"
          valid_min_length: 1
          valid_max_length: 64
  - name: sku
    data_type: string
    checks:
      - missing:
      - invalid:
          name: "sku must be uppercase letters/numbers with separators"
          valid_format:
            name: SKU format
            regex: "^[A-Z0-9][A-Z0-9_-]{0,63}$"
  - name: product_name
    data_type: string
    checks:
      - missing:
      - invalid:
          name: "product_name length guardrail"
          valid_min_length: 2
          valid_max_length: 255
  - name: category
    data_type: string
    checks:
      - missing:
      - invalid:
          name: "category length guardrail"
          valid_min_length: 2
          valid_max_length: 100
  - name: list_price
    data_type: float
    checks:
      - missing:
      - invalid:
          name: "list_price must be zero or positive"
          valid_min: 0
  - name: status
    data_type: string
    checks:
      - missing:
      - invalid:
          name: "Allowed product statuses"
          valid_values:
            - active
            - discontinued
            - out_of_stock
            - draft