JSON Schema vocabulary for Singer schemas

[edgarrmondragon]

Stub.

---

For example OpenAPI defines its own vocabulary on top of Draft 2020-12

1. Custom data types and formats: https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.1.0.md#data-types

2. Examples: https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.1.0.md#schema-object-examples

3. https://spec.openapis.org/oas/3.1/dialect/base

{
    "$id": "https://spec.openapis.org/oas/3.1/dialect/base",
    "$schema": "https://json-schema.org/draft/2020-12/schema",

    "title": "OpenAPI 3.1 Schema Object Dialect",
    "description": "A JSON Schema dialect describing schemas found in OpenAPI documents",

    "$vocabulary": {
        "https://json-schema.org/draft/2020-12/vocab/core": true,
        "https://json-schema.org/draft/2020-12/vocab/applicator": true,
        "https://json-schema.org/draft/2020-12/vocab/unevaluated": true,
        "https://json-schema.org/draft/2020-12/vocab/validation": true,
        "https://json-schema.org/draft/2020-12/vocab/meta-data": true,
        "https://json-schema.org/draft/2020-12/vocab/format-annotation": true,
        "https://json-schema.org/draft/2020-12/vocab/content": true,
        "https://spec.openapis.org/oas/3.1/vocab/base": false
    },

    "$dynamicAnchor": "meta",

    "allOf": [
        { "$ref": "https://json-schema.org/draft/2020-12/schema" },
        { "$ref": "https://spec.openapis.org/oas/3.1/meta/base" }
    ]
}

4. https://spec.openapis.org/oas/3.1/meta/base

{
    "$id": "https://spec.openapis.org/oas/3.1/meta/base",
    "$schema": "https://json-schema.org/draft/2020-12/schema",

    "title": "OAS Base vocabulary",
    "description": "A JSON Schema Vocabulary used in the OpenAPI Schema Dialect",

    "$vocabulary": {
        "https://spec.openapis.org/oas/3.1/vocab/base": true
    },

    "$dynamicAnchor": "meta",

    "type": ["object", "boolean"],
    "properties": {
        "example": true,
        "discriminator": { "$ref": "#/$defs/discriminator" },
        "externalDocs": { "$ref": "#/$defs/external-docs" },
        "xml": { "$ref": "#/$defs/xml" }
    },

    "$defs": {
        "extensible": {
            "patternProperties": {
                "^x-": true
            }
        },

        "discriminator": {
            "$ref": "#/$defs/extensible",
            "type": "object",
            "properties": {
                "propertyName": {
                    "type": "string"
                },
                "mapping": {
                    "type": "object",
                    "additionalProperties": {
                        "type": "string"
                    }
                }
            },
            "required": ["propertyName"],
            "unevaluatedProperties": false
        },

        "external-docs": {
            "$ref": "#/$defs/extensible",
            "type": "object",
            "properties": {
                "url": {
                    "type": "string",
                    "format": "uri-reference"
                },
                "description": {
                    "type": "string"
                }
            },
            "required": ["url"],
            "unevaluatedProperties": false
        },

        "xml": {
            "$ref": "#/$defs/extensible",
            "type": "object",
            "properties": {
                "name": {
                    "type": "string"
                },
                "namespace": {
                    "type": "string",
                    "format": "uri"
                },
                "prefix": {
                    "type": "string"
                },
                "attribute": {
                    "type": "boolean"
                },
                "wrapped": {
                    "type": "boolean"
                }
            },
            "unevaluatedProperties": false
        }
    }
}

Related:

• feat(taps): Support declaring arbitrary SQLAlchemy type instances in SQL tap schemas #2102
• feat: Support integer types other than BIGINT MeltanoLabs/target-postgres#485 (comment)
• feat: Conditionally required settings #1519

[edgarrmondragon]

https://datatracker.ietf.org/doc/html/draft-bhutton-json-schema-validation-00#section-7.2.3

Vocabularies do not support specifically declaring different value sets for keywords. Due to this limitation, and the historically uneven implementation of this keyword, it is RECOMMENDED to define additional keywords in a custom vocabulary rather than additional format attributes if interoperability is desired.

This means we probably should not use custom format values, but rather define custom keywords (e.g. dbtype).