madoo.dataset/v1

Madoo dataset — Format-neutral descriptor for a normalized tabular dataset and its row store.

Reference	madoo.dataset/v1
Schema id	urn:madoo:schema:dataset:v1
Version	1.0.0
Served at	GET /api/v1/json-schemas/madoo.dataset/v1 · MCP get_json_schema

Where it appears

• Produced by: input/data → dataset
• Read by: enumerate/data_rows → dataset

Fields

Field	Type	Required	Rules	Description
schema	"madoo.dataset/v1"	yes
source	object	yes	no other fields
source.fileName	string	yes	min length 1; max length 255
source.declaredMediaType	string or null
source.detectedMediaType	string	yes	min length 1
source.sizeBytes	integer	yes	≥ 0
source.sha256	string	yes	pattern “^[a-f0-9]{64}$”
format	one of "csv", "json", "xlsx"	yes
table	object	yes	no other fields
table.kind	one of "sheet", "array", "table"	yes
table.name	string	yes	min length 1; max length 255
table.headerRow	integer or null		≥ 1
rowCount	integer	yes	≥ 0
columnCount	integer	yes	≥ 0
columns	array of objects	yes
columns[].name	string	yes	min length 1; max length 255
columns[].sourceName	string	yes	min length 1; max length 255
columns[].ordinal	integer	yes	≥ 0
columns[].logicalType	one of "unknown", "text", "number", "boolean", "date", "datetime", "json", "mixed"	yes
columns[].nullable	boolean	yes
columns[].samples	array of any	yes	max items 10
policies	object	yes	no other fields
policies.locale	string	yes	min length 1; max length 64
policies.formulaPolicy	one of "cached_value", "reject"	yes
policies.emptyPolicy	"preserve"	yes
rowStore	object	yes	no other fields
rowStore.format	"jsonl"	yes
rowStore.storageRef	string	yes	min length 1
rowStore.mediaType	"application/x-ndjson"	yes
rowStore.sizeBytes	integer	yes	≥ 0
rowStore.sha256	string	yes	pattern “^[a-f0-9]{64}$”
parser	object	yes	no other fields
parser.name	string	yes	min length 1; max length 128
parser.version	string	yes	min length 1; max length 32
warnings	array of objects	yes
warnings[].code	string	yes	min length 1; max length 80
warnings[].message	string	yes	min length 1; max length 1000
warnings[].path	string or null		max length 500

The complete schema

madoo.dataset/v1 (JSON Schema)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "urn:madoo:schema:dataset:v1",
  "title": "Madoo Dataset v1",
  "type": "object",
  "required": [
    "schema",
    "source",
    "format",
    "table",
    "rowCount",
    "columnCount",
    "columns",
    "policies",
    "rowStore",
    "parser",
    "warnings"
  ],
  "properties": {
    "schema": {
      "const": "madoo.dataset/v1"
    },
    "source": {
      "$ref": "#/$defs/source"
    },
    "format": {
      "type": "string",
      "enum": [
        "csv",
        "json",
        "xlsx"
      ]
    },
    "table": {
      "$ref": "#/$defs/table"
    },
    "rowCount": {
      "type": "integer",
      "minimum": 0
    },
    "columnCount": {
      "type": "integer",
      "minimum": 0
    },
    "columns": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/column"
      }
    },
    "policies": {
      "$ref": "#/$defs/policies"
    },
    "rowStore": {
      "$ref": "#/$defs/rowStore"
    },
    "parser": {
      "$ref": "#/$defs/parser"
    },
    "warnings": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/warning"
      }
    }
  },
  "$defs": {
    "source": {
      "type": "object",
      "required": [
        "fileName",
        "detectedMediaType",
        "sizeBytes",
        "sha256"
      ],
      "properties": {
        "fileName": {
          "type": "string",
          "minLength": 1,
          "maxLength": 255
        },
        "declaredMediaType": {
          "type": [
            "string",
            "null"
          ]
        },
        "detectedMediaType": {
          "type": "string",
          "minLength": 1
        },
        "sizeBytes": {
          "type": "integer",
          "minimum": 0
        },
        "sha256": {
          "type": "string",
          "pattern": "^[a-f0-9]{64}$"
        }
      },
      "additionalProperties": false
    },
    "table": {
      "type": "object",
      "required": [
        "kind",
        "name"
      ],
      "properties": {
        "kind": {
          "type": "string",
          "enum": [
            "sheet",
            "array",
            "table"
          ]
        },
        "name": {
          "type": "string",
          "minLength": 1,
          "maxLength": 255
        },
        "headerRow": {
          "type": [
            "integer",
            "null"
          ],
          "minimum": 1
        }
      },
      "additionalProperties": false
    },
    "column": {
      "type": "object",
      "required": [
        "name",
        "sourceName",
        "ordinal",
        "logicalType",
        "nullable",
        "samples"
      ],
      "properties": {
        "name": {
          "type": "string",
          "minLength": 1,
          "maxLength": 255
        },
        "sourceName": {
          "type": "string",
          "minLength": 1,
          "maxLength": 255
        },
        "ordinal": {
          "type": "integer",
          "minimum": 0
        },
        "logicalType": {
          "type": "string",
          "enum": [
            "unknown",
            "text",
            "number",
            "boolean",
            "date",
            "datetime",
            "json",
            "mixed"
          ]
        },
        "nullable": {
          "type": "boolean"
        },
        "samples": {
          "type": "array",
          "maxItems": 10
        }
      },
      "additionalProperties": false
    },
    "policies": {
      "type": "object",
      "required": [
        "locale",
        "formulaPolicy",
        "emptyPolicy"
      ],
      "properties": {
        "locale": {
          "type": "string",
          "minLength": 1,
          "maxLength": 64
        },
        "formulaPolicy": {
          "type": "string",
          "enum": [
            "cached_value",
            "reject"
          ]
        },
        "emptyPolicy": {
          "const": "preserve"
        }
      },
      "additionalProperties": false
    },
    "rowStore": {
      "type": "object",
      "required": [
        "format",
        "storageRef",
        "mediaType",
        "sizeBytes",
        "sha256"
      ],
      "properties": {
        "format": {
          "const": "jsonl"
        },
        "storageRef": {
          "type": "string",
          "minLength": 1
        },
        "mediaType": {
          "const": "application/x-ndjson"
        },
        "sizeBytes": {
          "type": "integer",
          "minimum": 0
        },
        "sha256": {
          "type": "string",
          "pattern": "^[a-f0-9]{64}$"
        }
      },
      "additionalProperties": false
    },
    "parser": {
      "type": "object",
      "required": [
        "name",
        "version"
      ],
      "properties": {
        "name": {
          "type": "string",
          "minLength": 1,
          "maxLength": 128
        },
        "version": {
          "type": "string",
          "minLength": 1,
          "maxLength": 32
        }
      },
      "additionalProperties": false
    },
    "warning": {
      "type": "object",
      "required": [
        "code",
        "message"
      ],
      "properties": {
        "code": {
          "type": "string",
          "minLength": 1,
          "maxLength": 80
        },
        "message": {
          "type": "string",
          "minLength": 1,
          "maxLength": 1000
        },
        "path": {
          "type": [
            "string",
            "null"
          ],
          "maxLength": 500
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}