{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://library.cdisc.org/api/schemas/dataset",
  "title": "CDISC Dataset (Domain)",
  "description": "Schema representing a CDISC SDTM or ADaM dataset domain specification including all variables.",
  "type": "object",
  "required": ["name", "label"],
  "properties": {
    "name": {
      "type": "string",
      "description": "Dataset/domain abbreviation (e.g., AE, CM, DM)",
      "pattern": "^[A-Z]{2,4}$",
      "examples": ["AE", "CM", "DM", "EX", "LB"]
    },
    "label": {
      "type": "string",
      "description": "Human-readable label for the dataset",
      "examples": ["Adverse Events", "Concomitant/Prior Medications", "Demographics"]
    },
    "description": {
      "type": "string",
      "description": "Detailed description of the dataset purpose and content"
    },
    "datasetClass": {
      "type": "string",
      "description": "SDTM general observation class",
      "enum": ["Events", "Findings", "Interventions", "Special Purpose", "Relationship", "Trial Design"]
    },
    "structure": {
      "type": "string",
      "description": "Dataset structure (one record per subject, one record per visit, etc.)"
    },
    "purpose": {
      "type": "string",
      "description": "Dataset purpose: Tabulation or Analysis",
      "enum": ["Tabulation", "Analysis"]
    },
    "keys": {
      "type": "array",
      "description": "Key variables that uniquely identify a record",
      "items": {
        "type": "string"
      },
      "examples": [["STUDYID", "USUBJID", "AESEQ"]]
    },
    "variables": {
      "type": "array",
      "description": "List of variables (columns) in the dataset",
      "items": {
        "$ref": "#/$defs/Variable"
      }
    },
    "_links": {
      "type": "object",
      "description": "HAL hypermedia links",
      "properties": {
        "self": {
          "$ref": "#/$defs/Link"
        },
        "parentClass": {
          "$ref": "#/$defs/Link"
        },
        "parentProduct": {
          "$ref": "#/$defs/Link"
        }
      }
    }
  },
  "$defs": {
    "Variable": {
      "type": "object",
      "required": ["name", "label", "dataType", "core"],
      "properties": {
        "name": {
          "type": "string",
          "description": "Variable name (e.g., AETERM)",
          "pattern": "^[A-Z][A-Z0-9]{1,7}$"
        },
        "label": {
          "type": "string",
          "description": "Variable label (40 char max)",
          "maxLength": 40
        },
        "description": {
          "type": "string",
          "description": "Detailed variable description"
        },
        "dataType": {
          "type": "string",
          "description": "SAS data type",
          "enum": ["Char", "Num", "date", "datetime", "partialDate", "partialDatetime", "time", "partialTime", "integer", "float", "text", "uri"]
        },
        "length": {
          "type": "integer",
          "description": "Maximum length for character variables",
          "minimum": 1
        },
        "significantDigits": {
          "type": "integer",
          "description": "Number of significant digits for numeric variables"
        },
        "format": {
          "type": "string",
          "description": "SAS format for display",
          "examples": ["DATE9.", "TIME5.", "DATETIME19."]
        },
        "role": {
          "type": "string",
          "description": "Variable role within the SDTM general observation class",
          "enum": [
            "Identifier",
            "Topic",
            "Record Qualifier",
            "Result Qualifier",
            "Synonym Qualifier",
            "Variable Qualifier",
            "Timing",
            "Rule",
            "Grouping Qualifier"
          ]
        },
        "core": {
          "type": "string",
          "description": "Variable core status indicating requirement level",
          "enum": ["Required", "Expected", "Permissible", "Conditionally Required", "Conditionally Expected"]
        },
        "codelistSubmissionValues": {
          "type": "array",
          "description": "Applicable CDISC controlled terminology codelist submission values",
          "items": {
            "type": "string"
          }
        },
        "valueList": {
          "type": "array",
          "description": "Enumerated list of allowed values",
          "items": {
            "type": "string"
          }
        },
        "ordinal": {
          "type": "integer",
          "description": "Variable ordering position within the dataset"
        },
        "simpleDatatype": {
          "type": "string",
          "description": "Simplified datatype",
          "enum": ["text", "integer", "float", "date", "datetime", "time"]
        }
      }
    },
    "Link": {
      "type": "object",
      "properties": {
        "href": {
          "type": "string",
          "format": "uri"
        },
        "title": {
          "type": "string"
        }
      }
    }
  }
}