File¶

{
  "$id": "https://open-metadata.org/schema/entity/data/file.json",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "title": "File",
  "description": "A File represents an individual file in cloud storage or file shares.",
  "type": "object",
  "javaType": "org.openmetadata.schema.entity.data.File",
  "javaInterfaces": [
    "org.openmetadata.schema.EntityInterface"
  ],
  "definitions": {
    "fileType": {
      "description": "Type of file",
      "type": "string",
      "enum": [
        "CSV",
        "TSV",
        "JSON",
        "Parquet",
        "Avro",
        "ORC",
        "Excel",
        "PDF",
        "Image",
        "Video",
        "Audio",
        "Document",
        "Archive",
        "Other"
      ]
    },
    "compressionType": {
      "description": "Compression type",
      "type": "string",
      "enum": [
        "None",
        "Gzip",
        "Bzip2",
        "Snappy",
        "LZO",
        "Zstd"
      ]
    },
    "fileVersion": {
      "type": "object",
      "description": "A version of the file",
      "properties": {
        "versionId": {
          "description": "Version identifier",
          "type": "string"
        },
        "timestamp": {
          "description": "When this version was created",
          "$ref": "../../type/basic.json#/definitions/timestamp"
        },
        "size": {
          "description": "Size in bytes",
          "type": "number"
        },
        "modifiedBy": {
          "description": "User who modified this version",
          "type": "string"
        }
      }
    },
    "fileSchema": {
      "type": "object",
      "description": "Schema for structured files",
      "properties": {
        "columns": {
          "description": "Columns in the file",
          "type": "array",
          "items": {
            "$ref": "../databases/column.json"
          }
        },
        "delimiter": {
          "description": "Delimiter for CSV/TSV files",
          "type": "string"
        },
        "header": {
          "description": "Whether file has header row",
          "type": "boolean"
        },
        "encoding": {
          "description": "File encoding (UTF-8, ASCII, etc.)",
          "type": "string"
        }
      }
    }
  },
  "properties": {
    "id": {
      "description": "Unique identifier of the file",
      "$ref": "../../type/basic.json#/definitions/uuid"
    },
    "name": {
      "description": "Name of the file",
      "$ref": "../../type/basic.json#/definitions/entityName"
    },
    "fullyQualifiedName": {
      "description": "Fully qualified name of the file",
      "$ref": "../../type/basic.json#/definitions/fullyQualifiedEntityName"
    },
    "displayName": {
      "description": "Display name for the file",
      "type": "string"
    },
    "description": {
      "description": "Description of the file",
      "$ref": "../../type/basic.json#/definitions/markdown"
    },
    "fileType": {
      "$ref": "#/definitions/fileType"
    },
    "path": {
      "description": "Full path to the file (e.g., s3://bucket/path/file.csv)",
      "type": "string"
    },
    "size": {
      "description": "File size in bytes",
      "type": "number"
    },
    "compressionType": {
      "$ref": "#/definitions/compressionType"
    },
    "container": {
      "description": "Container/bucket where file is stored",
      "$ref": "../../type/entityReference.json"
    },
    "service": {
      "description": "Storage service where file is stored",
      "$ref": "../../type/entityReference.json"
    },
    "fileSchema": {
      "$ref": "#/definitions/fileSchema"
    },
    "versions": {
      "description": "File versions",
      "type": "array",
      "items": {
        "$ref": "#/definitions/fileVersion"
      }
    },
    "createdAt": {
      "description": "When the file was created",
      "$ref": "../../type/basic.json#/definitions/timestamp"
    },
    "modifiedAt": {
      "description": "When the file was last modified",
      "$ref": "../../type/basic.json#/definitions/timestamp"
    },
    "modifiedBy": {
      "description": "User who last modified the file",
      "type": "string"
    },
    "checksum": {
      "description": "Checksum/hash of the file (MD5, SHA256, etc.)",
      "type": "string"
    },
    "encryption": {
      "description": "Encryption information",
      "type": "object",
      "properties": {
        "encrypted": {
          "type": "boolean"
        },
        "algorithm": {
          "type": "string"
        }
      }
    },
    "owner": {
      "description": "Owner of this file",
      "$ref": "../../type/entityReference.json"
    },
    "tags": {
      "description": "Tags for this file",
      "type": "array",
      "items": {
        "$ref": "../../type/tagLabel.json"
      }
    },
    "version": {
      "description": "Metadata version of the entity",
      "$ref": "../../type/entityHistory.json#/definitions/entityVersion"
    },
    "updatedAt": {
      "description": "Last update time corresponding to the new version of the entity in Unix epoch time milliseconds",
      "$ref": "../../type/basic.json#/definitions/timestamp"
    },
    "updatedBy": {
      "description": "User who made the update",
      "type": "string"
    },
    "href": {
      "description": "Link to this file resource",
      "$ref": "../../type/basic.json#/definitions/href"
    },
    "changeDescription": {
      "description": "Change that led to this version of the entity",
      "$ref": "../../type/entityHistory.json#/definitions/changeDescription"
    },
    "deleted": {
      "description": "When true indicates the entity has been soft deleted",
      "type": "boolean",
      "default": false
    },
    "domain": {
      "description": "Domain the file belongs to",
      "$ref": "../../type/entityReference.json"
    }
  },
  "required": [
    "id",
    "name",
    "fileType",
    "path",
    "container"
  ],
  "additionalProperties": false
}

{
  "@context": {
    "@vocab": "https://open-metadata.org/schema/entity/data/",
    "rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
    "rdfs": "http://www.w3.org/2000/01/rdf-schema#",
    "owl": "http://www.w3.org/2002/07/owl#",
    "xsd": "http://www.w3.org/2001/XMLSchema#",
    "dcterms": "http://purl.org/dc/terms/",
    "dcat": "http://www.w3.org/ns/dcat#",
    "skos": "http://www.w3.org/2004/02/skos/core#",
    "om": "https://open-metadata.org/schema/",

    "File": {
      "@id": "om:File",
      "@type": "@id"
    },
    "id": {
      "@id": "om:id",
      "@type": "xsd:string"
    },
    "name": {
      "@id": "om:name",
      "@type": "xsd:string"
    },
    "fullyQualifiedName": {
      "@id": "om:fullyQualifiedName",
      "@type": "xsd:string"
    },
    "description": {
      "@id": "dcterms:description",
      "@type": "xsd:string"
    },
    "fileType": {
      "@id": "om:fileType",
      "@type": "@id"
    },
    "path": {
      "@id": "dcat:accessURL",
      "@type": "xsd:anyURI"
    },
    "size": {
      "@id": "dcat:byteSize",
      "@type": "xsd:integer"
    },
    "compressionType": {
      "@id": "om:compressionType",
      "@type": "@id"
    },
    "container": {
      "@id": "om:storedIn",
      "@type": "@id"
    },
    "service": {
      "@id": "om:hasService",
      "@type": "@id"
    },
    "fileSchema": {
      "@id": "om:hasSchema",
      "@type": "@id"
    },
    "checksum": {
      "@id": "om:checksum",
      "@type": "xsd:string"
    },
    "modifiedAt": {
      "@id": "dcterms:modified",
      "@type": "xsd:dateTime"
    },
    "modifiedBy": {
      "@id": "om:modifiedBy",
      "@type": "xsd:string"
    },
    "owner": {
      "@id": "om:owner",
      "@type": "@id"
    },
    "tags": {
      "@id": "om:tags",
      "@type": "@id",
      "@container": "@set"
    },
    "domain": {
      "@id": "om:domain",
      "@type": "@id"
    }
  }
}