Skip to main content
Version: 0.13.0

DataFlow

Aspects

dataFlowKey

Key for a Data Flow

Schema
{
"type": "record",
"Aspect": {
"name": "dataFlowKey"
},
"name": "DataFlowKey",
"namespace": "com.linkedin.metadata.key",
"fields": [
{
"Searchable": {
"fieldType": "TEXT_PARTIAL"
},
"type": "string",
"name": "orchestrator",
"doc": "Workflow manager like azkaban, airflow which orchestrates the flow"
},
{
"Searchable": {
"enableAutocomplete": true,
"fieldType": "WORD_GRAM"
},
"type": "string",
"name": "flowId",
"doc": "Unique Identifier of the data flow"
},
{
"Searchable": {
"fieldType": "TEXT_PARTIAL"
},
"type": "string",
"name": "cluster",
"doc": "Cluster where the flow is executed"
}
],
"doc": "Key for a Data Flow"
}

dataFlowInfo

Information about a Data processing flow

Schema
{
"type": "record",
"Aspect": {
"name": "dataFlowInfo"
},
"name": "DataFlowInfo",
"namespace": "com.linkedin.datajob",
"fields": [
{
"Searchable": {
"/*": {
"fieldType": "TEXT",
"queryByDefault": true
}
},
"type": {
"type": "map",
"values": "string"
},
"name": "customProperties",
"default": {},
"doc": "Custom property bag."
},
{
"Searchable": {
"fieldType": "KEYWORD"
},
"java": {
"class": "com.linkedin.common.url.Url",
"coercerClass": "com.linkedin.common.url.UrlCoercer"
},
"type": [
"null",
"string"
],
"name": "externalUrl",
"default": null,
"doc": "URL where the reference exist"
},
{
"Searchable": {
"boostScore": 10.0,
"enableAutocomplete": true,
"fieldNameAliases": [
"_entityName"
],
"fieldType": "WORD_GRAM"
},
"type": "string",
"name": "name",
"doc": "Flow name"
},
{
"Searchable": {
"fieldType": "TEXT",
"hasValuesFieldName": "hasDescription"
},
"type": [
"null",
"string"
],
"name": "description",
"default": null,
"doc": "Flow description"
},
{
"Searchable": {
"fieldType": "TEXT_PARTIAL",
"queryByDefault": false
},
"type": [
"null",
"string"
],
"name": "project",
"default": null,
"doc": "Optional project/namespace associated with the flow"
},
{
"Searchable": {
"/time": {
"fieldName": "createdAt",
"fieldType": "DATETIME"
}
},
"type": [
"null",
{
"type": "record",
"name": "TimeStamp",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "long",
"name": "time",
"doc": "When did the event occur"
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "actor",
"default": null,
"doc": "Optional: The actor urn involved in the event."
}
],
"doc": "A standard event timestamp"
}
],
"name": "created",
"default": null,
"doc": "A timestamp documenting when the asset was created in the source Data Platform (not on DataHub)"
},
{
"Searchable": {
"/time": {
"fieldName": "lastModifiedAt",
"fieldType": "DATETIME"
}
},
"type": [
"null",
"com.linkedin.common.TimeStamp"
],
"name": "lastModified",
"default": null,
"doc": "A timestamp documenting when the asset was last modified in the source Data Platform (not on DataHub)"
}
],
"doc": "Information about a Data processing flow"
}

editableDataFlowProperties

Stores editable changes made to properties. This separates changes made from ingestion pipelines and edits in the UI to avoid accidental overwrites of user-provided data by ingestion pipelines

Schema
{
"type": "record",
"Aspect": {
"name": "editableDataFlowProperties"
},
"name": "EditableDataFlowProperties",
"namespace": "com.linkedin.datajob",
"fields": [
{
"type": {
"type": "record",
"name": "AuditStamp",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "long",
"name": "time",
"doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "actor",
"doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "impersonator",
"default": null,
"doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor."
},
{
"type": [
"null",
"string"
],
"name": "message",
"default": null,
"doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
}
],
"doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
},
"name": "created",
"default": {
"actor": "urn:li:corpuser:unknown",
"impersonator": null,
"time": 0,
"message": null
},
"doc": "An AuditStamp corresponding to the creation of this resource/association/sub-resource. A value of 0 for time indicates missing data."
},
{
"type": "com.linkedin.common.AuditStamp",
"name": "lastModified",
"default": {
"actor": "urn:li:corpuser:unknown",
"impersonator": null,
"time": 0,
"message": null
},
"doc": "An AuditStamp corresponding to the last modification of this resource/association/sub-resource. If no modification has happened since creation, lastModified should be the same as created. A value of 0 for time indicates missing data."
},
{
"type": [
"null",
"com.linkedin.common.AuditStamp"
],
"name": "deleted",
"default": null,
"doc": "An AuditStamp corresponding to the deletion of this resource/association/sub-resource. Logically, deleted MUST have a later timestamp than creation. It may or may not have the same time as lastModified depending upon the resource/association/sub-resource semantics."
},
{
"Searchable": {
"fieldName": "editedDescription",
"fieldType": "TEXT"
},
"type": [
"null",
"string"
],
"name": "description",
"default": null,
"doc": "Edited documentation of the data flow"
}
],
"doc": "Stores editable changes made to properties. This separates changes made from\ningestion pipelines and edits in the UI to avoid accidental overwrites of user-provided data by ingestion pipelines"
}

ownership

Ownership information of an entity.

Schema
{
"type": "record",
"Aspect": {
"name": "ownership"
},
"name": "Ownership",
"namespace": "com.linkedin.common",
"fields": [
{
"type": {
"type": "array",
"items": {
"type": "record",
"name": "Owner",
"namespace": "com.linkedin.common",
"fields": [
{
"Relationship": {
"entityTypes": [
"corpuser",
"corpGroup"
],
"name": "OwnedBy"
},
"Searchable": {
"addToFilters": true,
"fieldName": "owners",
"fieldType": "URN",
"filterNameOverride": "Owned By",
"hasValuesFieldName": "hasOwners",
"queryByDefault": false
},
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "owner",
"doc": "Owner URN, e.g. urn:li:corpuser:ldap, urn:li:corpGroup:group_name, and urn:li:multiProduct:mp_name\n(Caveat: only corpuser is currently supported in the frontend.)"
},
{
"deprecated": true,
"type": {
"type": "enum",
"symbolDocs": {
"BUSINESS_OWNER": "A person or group who is responsible for logical, or business related, aspects of the asset.",
"CONSUMER": "A person, group, or service that consumes the data\nDeprecated! Use TECHNICAL_OWNER or BUSINESS_OWNER instead.",
"CUSTOM": "Set when ownership type is unknown or a when new one is specified as an ownership type entity for which we have no\nenum value for. This is used for backwards compatibility",
"DATAOWNER": "A person or group that is owning the data\nDeprecated! Use TECHNICAL_OWNER instead.",
"DATA_STEWARD": "A steward, expert, or delegate responsible for the asset.",
"DELEGATE": "A person or a group that overseas the operation, e.g. a DBA or SRE.\nDeprecated! Use TECHNICAL_OWNER instead.",
"DEVELOPER": "A person or group that is in charge of developing the code\nDeprecated! Use TECHNICAL_OWNER instead.",
"NONE": "No specific type associated to the owner.",
"PRODUCER": "A person, group, or service that produces/generates the data\nDeprecated! Use TECHNICAL_OWNER instead.",
"STAKEHOLDER": "A person or a group that has direct business interest\nDeprecated! Use TECHNICAL_OWNER, BUSINESS_OWNER, or STEWARD instead.",
"TECHNICAL_OWNER": "person or group who is responsible for technical aspects of the asset."
},
"deprecatedSymbols": {
"CONSUMER": true,
"DATAOWNER": true,
"DELEGATE": true,
"DEVELOPER": true,
"PRODUCER": true,
"STAKEHOLDER": true
},
"name": "OwnershipType",
"namespace": "com.linkedin.common",
"symbols": [
"CUSTOM",
"TECHNICAL_OWNER",
"BUSINESS_OWNER",
"DATA_STEWARD",
"NONE",
"DEVELOPER",
"DATAOWNER",
"DELEGATE",
"PRODUCER",
"CONSUMER",
"STAKEHOLDER"
],
"doc": "Asset owner types"
},
"name": "type",
"doc": "The type of the ownership"
},
{
"Relationship": {
"entityTypes": [
"ownershipType"
],
"name": "ownershipType"
},
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "typeUrn",
"default": null,
"doc": "The type of the ownership\nUrn of type O"
},
{
"type": [
"null",
{
"type": "record",
"name": "OwnershipSource",
"namespace": "com.linkedin.common",
"fields": [
{
"type": {
"type": "enum",
"symbolDocs": {
"AUDIT": "Auditing system or audit logs",
"DATABASE": "Database, e.g. GRANTS table",
"FILE_SYSTEM": "File system, e.g. file/directory owner",
"ISSUE_TRACKING_SYSTEM": "Issue tracking system, e.g. Jira",
"MANUAL": "Manually provided by a user",
"OTHER": "Other sources",
"SERVICE": "Other ownership-like service, e.g. Nuage, ACL service etc",
"SOURCE_CONTROL": "SCM system, e.g. GIT, SVN"
},
"name": "OwnershipSourceType",
"namespace": "com.linkedin.common",
"symbols": [
"AUDIT",
"DATABASE",
"FILE_SYSTEM",
"ISSUE_TRACKING_SYSTEM",
"MANUAL",
"SERVICE",
"SOURCE_CONTROL",
"OTHER"
]
},
"name": "type",
"doc": "The type of the source"
},
{
"type": [
"null",
"string"
],
"name": "url",
"default": null,
"doc": "A reference URL for the source"
}
],
"doc": "Source/provider of the ownership information"
}
],
"name": "source",
"default": null,
"doc": "Source information for the ownership"
}
],
"doc": "Ownership information"
}
},
"name": "owners",
"doc": "List of owners of the entity."
},
{
"Searchable": {
"/*": {
"fieldType": "MAP_ARRAY",
"queryByDefault": false
}
},
"type": [
{
"type": "map",
"values": {
"type": "array",
"items": "string"
}
},
"null"
],
"name": "ownerTypes",
"default": {},
"doc": "Ownership type to Owners map, populated via mutation hook."
},
{
"type": {
"type": "record",
"name": "AuditStamp",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "long",
"name": "time",
"doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "actor",
"doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "impersonator",
"default": null,
"doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor."
},
{
"type": [
"null",
"string"
],
"name": "message",
"default": null,
"doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
}
],
"doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
},
"name": "lastModified",
"default": {
"actor": "urn:li:corpuser:unknown",
"impersonator": null,
"time": 0,
"message": null
},
"doc": "Audit stamp containing who last modified the record and when. A value of 0 in the time field indicates missing data."
}
],
"doc": "Ownership information of an entity."
}

status

The lifecycle status metadata of an entity, e.g. dataset, metric, feature, etc. This aspect is used to represent soft deletes conventionally.

Schema
{
"type": "record",
"Aspect": {
"name": "status"
},
"name": "Status",
"namespace": "com.linkedin.common",
"fields": [
{
"Searchable": {
"fieldType": "BOOLEAN"
},
"type": "boolean",
"name": "removed",
"default": false,
"doc": "Whether the entity has been removed (soft-deleted)."
}
],
"doc": "The lifecycle status metadata of an entity, e.g. dataset, metric, feature, etc.\nThis aspect is used to represent soft deletes conventionally."
}

globalTags

Tag aspect used for applying tags to an entity

Schema
{
"type": "record",
"Aspect": {
"name": "globalTags"
},
"name": "GlobalTags",
"namespace": "com.linkedin.common",
"fields": [
{
"Relationship": {
"/*/tag": {
"entityTypes": [
"tag"
],
"name": "TaggedWith"
}
},
"Searchable": {
"/*/tag": {
"addToFilters": true,
"boostScore": 0.5,
"fieldName": "tags",
"fieldType": "URN",
"filterNameOverride": "Tag",
"hasValuesFieldName": "hasTags",
"queryByDefault": true
}
},
"type": {
"type": "array",
"items": {
"type": "record",
"name": "TagAssociation",
"namespace": "com.linkedin.common",
"fields": [
{
"java": {
"class": "com.linkedin.common.urn.TagUrn"
},
"type": "string",
"name": "tag",
"doc": "Urn of the applied tag"
},
{
"type": [
"null",
"string"
],
"name": "context",
"default": null,
"doc": "Additional context about the association"
}
],
"doc": "Properties of an applied tag. For now, just an Urn. In the future we can extend this with other properties, e.g.\npropagation parameters."
}
},
"name": "tags",
"doc": "Tags associated with a given entity"
}
],
"doc": "Tag aspect used for applying tags to an entity"
}

browsePaths

Shared aspect containing Browse Paths to be indexed for an entity.

Schema
{
"type": "record",
"Aspect": {
"name": "browsePaths"
},
"name": "BrowsePaths",
"namespace": "com.linkedin.common",
"fields": [
{
"Searchable": {
"/*": {
"fieldName": "browsePaths",
"fieldType": "BROWSE_PATH"
}
},
"type": {
"type": "array",
"items": "string"
},
"name": "paths",
"doc": "A list of valid browse paths for the entity.\n\nBrowse paths are expected to be forward slash-separated strings. For example: 'prod/snowflake/datasetName'"
}
],
"doc": "Shared aspect containing Browse Paths to be indexed for an entity."
}

glossaryTerms

Related business terms information

Schema
{
"type": "record",
"Aspect": {
"name": "glossaryTerms"
},
"name": "GlossaryTerms",
"namespace": "com.linkedin.common",
"fields": [
{
"type": {
"type": "array",
"items": {
"type": "record",
"name": "GlossaryTermAssociation",
"namespace": "com.linkedin.common",
"fields": [
{
"Relationship": {
"entityTypes": [
"glossaryTerm"
],
"name": "TermedWith"
},
"Searchable": {
"addToFilters": true,
"fieldName": "glossaryTerms",
"fieldType": "URN",
"filterNameOverride": "Glossary Term",
"hasValuesFieldName": "hasGlossaryTerms"
},
"java": {
"class": "com.linkedin.common.urn.GlossaryTermUrn"
},
"type": "string",
"name": "urn",
"doc": "Urn of the applied glossary term"
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "actor",
"default": null,
"doc": "The user URN which will be credited for adding associating this term to the entity"
},
{
"type": [
"null",
"string"
],
"name": "context",
"default": null,
"doc": "Additional context about the association"
}
],
"doc": "Properties of an applied glossary term."
}
},
"name": "terms",
"doc": "The related business terms"
},
{
"type": {
"type": "record",
"name": "AuditStamp",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "long",
"name": "time",
"doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "actor",
"doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "impersonator",
"default": null,
"doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor."
},
{
"type": [
"null",
"string"
],
"name": "message",
"default": null,
"doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
}
],
"doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
},
"name": "auditStamp",
"doc": "Audit stamp containing who reported the related business term"
}
],
"doc": "Related business terms information"
}

institutionalMemory

Institutional memory of an entity. This is a way to link to relevant documentation and provide description of the documentation. Institutional or tribal knowledge is very important for users to leverage the entity.

Schema
{
"type": "record",
"Aspect": {
"name": "institutionalMemory"
},
"name": "InstitutionalMemory",
"namespace": "com.linkedin.common",
"fields": [
{
"type": {
"type": "array",
"items": {
"type": "record",
"name": "InstitutionalMemoryMetadata",
"namespace": "com.linkedin.common",
"fields": [
{
"java": {
"class": "com.linkedin.common.url.Url",
"coercerClass": "com.linkedin.common.url.UrlCoercer"
},
"type": "string",
"name": "url",
"doc": "Link to an engineering design document or a wiki page."
},
{
"type": "string",
"name": "description",
"doc": "Description of the link."
},
{
"type": {
"type": "record",
"name": "AuditStamp",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "long",
"name": "time",
"doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "actor",
"doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "impersonator",
"default": null,
"doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor."
},
{
"type": [
"null",
"string"
],
"name": "message",
"default": null,
"doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
}
],
"doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
},
"name": "createStamp",
"doc": "Audit stamp associated with creation of this record"
}
],
"doc": "Metadata corresponding to a record of institutional memory."
}
},
"name": "elements",
"doc": "List of records that represent institutional memory of an entity. Each record consists of a link, description, creator and timestamps associated with that record."
}
],
"doc": "Institutional memory of an entity. This is a way to link to relevant documentation and provide description of the documentation. Institutional or tribal knowledge is very important for users to leverage the entity."
}

dataPlatformInstance

The specific instance of the data platform that this entity belongs to

Schema
{
"type": "record",
"Aspect": {
"name": "dataPlatformInstance"
},
"name": "DataPlatformInstance",
"namespace": "com.linkedin.common",
"fields": [
{
"Searchable": {
"addToFilters": true,
"fieldType": "URN",
"filterNameOverride": "Platform"
},
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "platform",
"doc": "Data Platform"
},
{
"Searchable": {
"addToFilters": true,
"fieldName": "platformInstance",
"fieldType": "URN",
"filterNameOverride": "Platform Instance"
},
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "instance",
"default": null,
"doc": "Instance of the data platform (e.g. db instance)"
}
],
"doc": "The specific instance of the data platform that this entity belongs to"
}

browsePathsV2

Shared aspect containing a Browse Path to be indexed for an entity.

Schema
{
"type": "record",
"Aspect": {
"name": "browsePathsV2"
},
"name": "BrowsePathsV2",
"namespace": "com.linkedin.common",
"fields": [
{
"Searchable": {
"/*/id": {
"fieldName": "browsePathV2",
"fieldType": "BROWSE_PATH_V2"
}
},
"type": {
"type": "array",
"items": {
"type": "record",
"name": "BrowsePathEntry",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "string",
"name": "id",
"doc": "The ID of the browse path entry. This is what gets stored in the index.\nIf there's an urn associated with this entry, id and urn will be the same"
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "urn",
"default": null,
"doc": "Optional urn pointing to some entity in DataHub"
}
],
"doc": "Represents a single level in an entity's browsePathV2"
}
},
"name": "path",
"doc": "A valid browse path for the entity. This field is provided by DataHub by default.\nThis aspect is a newer version of browsePaths where we can encode more information in the path.\nThis path is also based on containers for a given entity if it has containers.\n\nThis is stored in elasticsearch as unit-separator delimited strings and only includes platform specific folders or containers.\nThese paths should not include high level info captured elsewhere ie. Platform and Environment."
}
],
"doc": "Shared aspect containing a Browse Path to be indexed for an entity."
}

domains

Links from an Asset to its Domains

Schema
{
"type": "record",
"Aspect": {
"name": "domains"
},
"name": "Domains",
"namespace": "com.linkedin.domain",
"fields": [
{
"Relationship": {
"/*": {
"entityTypes": [
"domain"
],
"name": "AssociatedWith"
}
},
"Searchable": {
"/*": {
"addToFilters": true,
"fieldName": "domains",
"fieldType": "URN",
"filterNameOverride": "Domain",
"hasValuesFieldName": "hasDomain"
}
},
"type": {
"type": "array",
"items": "string"
},
"name": "domains",
"doc": "The Domains attached to an Asset"
}
],
"doc": "Links from an Asset to its Domains"
}

deprecation

Deprecation status of an entity

Schema
{
"type": "record",
"Aspect": {
"name": "deprecation"
},
"name": "Deprecation",
"namespace": "com.linkedin.common",
"fields": [
{
"Searchable": {
"fieldType": "BOOLEAN",
"weightsPerFieldValue": {
"true": 0.5
}
},
"type": "boolean",
"name": "deprecated",
"doc": "Whether the entity is deprecated."
},
{
"type": [
"null",
"long"
],
"name": "decommissionTime",
"default": null,
"doc": "The time user plan to decommission this entity."
},
{
"type": "string",
"name": "note",
"doc": "Additional information about the entity deprecation plan, such as the wiki, doc, RB."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "actor",
"doc": "The user URN which will be credited for modifying this deprecation content."
}
],
"doc": "Deprecation status of an entity"
}

versionInfo

Information about a Data processing job

Schema
{
"type": "record",
"Aspect": {
"name": "versionInfo"
},
"name": "VersionInfo",
"namespace": "com.linkedin.datajob",
"fields": [
{
"Searchable": {
"/*": {
"fieldType": "TEXT",
"queryByDefault": true
}
},
"type": {
"type": "map",
"values": "string"
},
"name": "customProperties",
"default": {},
"doc": "Custom property bag."
},
{
"Searchable": {
"fieldType": "KEYWORD"
},
"java": {
"class": "com.linkedin.common.url.Url",
"coercerClass": "com.linkedin.common.url.UrlCoercer"
},
"type": [
"null",
"string"
],
"name": "externalUrl",
"default": null,
"doc": "URL where the reference exist"
},
{
"type": "string",
"name": "version",
"doc": "The version which can indentify a job version like a commit hash or md5 hash"
},
{
"type": "string",
"name": "versionType",
"doc": "The type of the version like git hash or md5 hash"
}
],
"doc": "Information about a Data processing job"
}

structuredProperties

Properties about an entity governed by StructuredPropertyDefinition

Schema
{
"type": "record",
"Aspect": {
"name": "structuredProperties"
},
"name": "StructuredProperties",
"namespace": "com.linkedin.structured",
"fields": [
{
"type": {
"type": "array",
"items": {
"type": "record",
"name": "StructuredPropertyValueAssignment",
"namespace": "com.linkedin.structured",
"fields": [
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "propertyUrn",
"doc": "The property that is being assigned a value."
},
{
"type": {
"type": "array",
"items": [
"string",
"double"
]
},
"name": "values",
"doc": "The value assigned to the property."
},
{
"type": [
"null",
{
"type": "record",
"name": "AuditStamp",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "long",
"name": "time",
"doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "actor",
"doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "impersonator",
"default": null,
"doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor."
},
{
"type": [
"null",
"string"
],
"name": "message",
"default": null,
"doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
}
],
"doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
}
],
"name": "created",
"default": null,
"doc": "Audit stamp containing who created this relationship edge and when"
},
{
"type": [
"null",
"com.linkedin.common.AuditStamp"
],
"name": "lastModified",
"default": null,
"doc": "Audit stamp containing who last modified this relationship edge and when"
}
]
}
},
"name": "properties",
"doc": "Custom property bag."
}
],
"doc": "Properties about an entity governed by StructuredPropertyDefinition"
}

incidentsSummary

Summary related incidents on an entity.

Schema
{
"type": "record",
"Aspect": {
"name": "incidentsSummary"
},
"name": "IncidentsSummary",
"namespace": "com.linkedin.common",
"fields": [
{
"deprecated": true,
"type": {
"type": "array",
"items": "string"
},
"name": "resolvedIncidents",
"default": [],
"doc": "Resolved incidents for an asset\nDeprecated! Use the richer resolvedIncidentsDetails instead."
},
{
"deprecated": true,
"type": {
"type": "array",
"items": "string"
},
"name": "activeIncidents",
"default": [],
"doc": "Active incidents for an asset\nDeprecated! Use the richer activeIncidentsDetails instead."
},
{
"Relationship": {
"/*/urn": {
"entityTypes": [
"incident"
],
"name": "ResolvedIncidents"
}
},
"Searchable": {
"/*/createdAt": {
"fieldName": "resolvedIncidentCreatedTimes",
"fieldType": "DATETIME"
},
"/*/priority": {
"fieldName": "resolvedIncidentPriorities",
"fieldType": "COUNT"
},
"/*/resolvedAt": {
"fieldName": "resolvedIncidentResolvedTimes",
"fieldType": "DATETIME"
},
"/*/type": {
"fieldName": "resolvedIncidentTypes",
"fieldType": "KEYWORD"
},
"/*/urn": {
"fieldName": "resolvedIncidents",
"fieldType": "URN",
"hasValuesFieldName": "hasResolvedIncidents",
"numValuesFieldName": "numResolvedIncidents"
}
},
"type": {
"type": "array",
"items": {
"type": "record",
"name": "IncidentSummaryDetails",
"namespace": "com.linkedin.common",
"fields": [
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "urn",
"doc": "The urn of the incident"
},
{
"type": "string",
"name": "type",
"doc": "The type of an incident"
},
{
"type": "long",
"name": "createdAt",
"doc": "The time at which the incident was raised in milliseconds since epoch."
},
{
"type": [
"null",
"long"
],
"name": "resolvedAt",
"default": null,
"doc": "The time at which the incident was marked as resolved in milliseconds since epoch. Null if the incident is still active."
},
{
"type": [
"null",
"int"
],
"name": "priority",
"default": null,
"doc": "The priority of the incident"
}
],
"doc": "Summary statistics about incidents on an entity."
}
},
"name": "resolvedIncidentDetails",
"default": [],
"doc": "Summary details about the set of resolved incidents"
},
{
"Relationship": {
"/*/urn": {
"entityTypes": [
"incident"
],
"name": "ActiveIncidents"
}
},
"Searchable": {
"/*/createdAt": {
"fieldName": "activeIncidentCreatedTimes",
"fieldType": "DATETIME"
},
"/*/priority": {
"fieldName": "activeIncidentPriorities",
"fieldType": "COUNT"
},
"/*/type": {
"fieldName": "activeIncidentTypes",
"fieldType": "KEYWORD"
},
"/*/urn": {
"addHasValuesToFilters": true,
"fieldName": "activeIncidents",
"fieldType": "URN",
"hasValuesFieldName": "hasActiveIncidents",
"numValuesFieldName": "numActiveIncidents"
}
},
"type": {
"type": "array",
"items": "com.linkedin.common.IncidentSummaryDetails"
},
"name": "activeIncidentDetails",
"default": [],
"doc": "Summary details about the set of active incidents"
}
],
"doc": "Summary related incidents on an entity."
}

forms

Forms that are assigned to this entity to be filled out

Schema
{
"type": "record",
"Aspect": {
"name": "forms"
},
"name": "Forms",
"namespace": "com.linkedin.common",
"fields": [
{
"Searchable": {
"/*/completedPrompts/*/id": {
"fieldName": "incompleteFormsCompletedPromptIds",
"fieldType": "KEYWORD"
},
"/*/completedPrompts/*/lastModified/time": {
"fieldName": "incompleteFormsCompletedPromptResponseTimes",
"fieldType": "DATETIME"
},
"/*/incompletePrompts/*/id": {
"fieldName": "incompleteFormsIncompletePromptIds",
"fieldType": "KEYWORD"
},
"/*/urn": {
"fieldName": "incompleteForms",
"fieldType": "URN"
}
},
"type": {
"type": "array",
"items": {
"type": "record",
"name": "FormAssociation",
"namespace": "com.linkedin.common",
"fields": [
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "urn",
"doc": "Urn of the applied form"
},
{
"type": {
"type": "array",
"items": {
"type": "record",
"name": "FormPromptAssociation",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "string",
"name": "id",
"doc": "The id for the prompt. This must be GLOBALLY UNIQUE."
},
{
"type": {
"type": "record",
"name": "AuditStamp",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "long",
"name": "time",
"doc": "When did the resource/association/sub-resource move into the specific lifecycle stage represented by this AuditEvent."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "actor",
"doc": "The entity (e.g. a member URN) which will be credited for moving the resource/association/sub-resource into the specific lifecycle stage. It is also the one used to authorize the change."
},
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": [
"null",
"string"
],
"name": "impersonator",
"default": null,
"doc": "The entity (e.g. a service URN) which performs the change on behalf of the Actor and must be authorized to act as the Actor."
},
{
"type": [
"null",
"string"
],
"name": "message",
"default": null,
"doc": "Additional context around how DataHub was informed of the particular change. For example: was the change created by an automated process, or manually."
}
],
"doc": "Data captured on a resource/association/sub-resource level giving insight into when that resource/association/sub-resource moved into a particular lifecycle stage, and who acted to move it into that specific lifecycle stage."
},
"name": "lastModified",
"doc": "The last time this prompt was touched for the entity (set, unset)"
},
{
"type": [
"null",
{
"type": "record",
"name": "FormPromptFieldAssociations",
"namespace": "com.linkedin.common",
"fields": [
{
"type": [
"null",
{
"type": "array",
"items": {
"type": "record",
"name": "FieldFormPromptAssociation",
"namespace": "com.linkedin.common",
"fields": [
{
"type": "string",
"name": "fieldPath",
"doc": "The field path on a schema field."
},
{
"type": "com.linkedin.common.AuditStamp",
"name": "lastModified",
"doc": "The last time this prompt was touched for the field on the entity (set, unset)"
}
],
"doc": "Information about the status of a particular prompt for a specific schema field\non an entity."
}
}
],
"name": "completedFieldPrompts",
"default": null,
"doc": "A list of field-level prompt associations that are not yet complete for this form."
},
{
"type": [
"null",
{
"type": "array",
"items": "com.linkedin.common.FieldFormPromptAssociation"
}
],
"name": "incompleteFieldPrompts",
"default": null,
"doc": "A list of field-level prompt associations that are complete for this form."
}
],
"doc": "Information about the field-level prompt associations on a top-level prompt association."
}
],
"name": "fieldAssociations",
"default": null,
"doc": "Optional information about the field-level prompt associations."
}
],
"doc": "Information about the status of a particular prompt.\nNote that this is where we can add additional information about individual responses:\nactor, timestamp, and the response itself."
}
},
"name": "incompletePrompts",
"default": [],
"doc": "A list of prompts that are not yet complete for this form."
},
{
"type": {
"type": "array",
"items": "com.linkedin.common.FormPromptAssociation"
},
"name": "completedPrompts",
"default": [],
"doc": "A list of prompts that have been completed for this form."
}
],
"doc": "Properties of an applied form."
}
},
"name": "incompleteForms",
"doc": "All incomplete forms assigned to the entity."
},
{
"Searchable": {
"/*/completedPrompts/*/id": {
"fieldName": "completedFormsCompletedPromptIds",
"fieldType": "KEYWORD"
},
"/*/completedPrompts/*/lastModified/time": {
"fieldName": "completedFormsCompletedPromptResponseTimes",
"fieldType": "DATETIME"
},
"/*/incompletePrompts/*/id": {
"fieldName": "completedFormsIncompletePromptIds",
"fieldType": "KEYWORD"
},
"/*/urn": {
"fieldName": "completedForms",
"fieldType": "URN"
}
},
"type": {
"type": "array",
"items": "com.linkedin.common.FormAssociation"
},
"name": "completedForms",
"doc": "All complete forms assigned to the entity."
},
{
"Searchable": {
"/*/form": {
"fieldName": "verifiedForms",
"fieldType": "URN"
}
},
"type": {
"type": "array",
"items": {
"type": "record",
"name": "FormVerificationAssociation",
"namespace": "com.linkedin.common",
"fields": [
{
"java": {
"class": "com.linkedin.common.urn.Urn"
},
"type": "string",
"name": "form",
"doc": "The urn of the form that granted this verification."
},
{
"type": [
"null",
"com.linkedin.common.AuditStamp"
],
"name": "lastModified",
"default": null,
"doc": "An audit stamp capturing who and when verification was applied for this form."
}
],
"doc": "An association between a verification and an entity that has been granted\nvia completion of one or more forms of type 'VERIFICATION'."
}
},
"name": "verifications",
"default": [],
"doc": "Verifications that have been applied to the entity via completed forms."
}
],
"doc": "Forms that are assigned to this entity to be filled out"
}

subTypes

Sub Types. Use this aspect to specialize a generic Entity e.g. Making a Dataset also be a View or also be a LookerExplore

Schema
{
"type": "record",
"Aspect": {
"name": "subTypes"
},
"name": "SubTypes",
"namespace": "com.linkedin.common",
"fields": [
{
"Searchable": {
"/*": {
"addToFilters": true,
"fieldType": "KEYWORD",
"filterNameOverride": "Sub Type",
"queryByDefault": true
}
},
"type": {
"type": "array",
"items": "string"
},
"name": "typeNames",
"doc": "The names of the specific types."
}
],
"doc": "Sub Types. Use this aspect to specialize a generic Entity\ne.g. Making a Dataset also be a View or also be a LookerExplore"
}

Relationships

Outgoing

These are the relationships stored in this entity's aspects

  • OwnedBy

    • Corpuser via ownership.owners.owner
    • CorpGroup via ownership.owners.owner
  • ownershipType

    • OwnershipType via ownership.owners.typeUrn
  • TaggedWith

    • Tag via globalTags.tags
  • TermedWith

    • GlossaryTerm via glossaryTerms.terms.urn
  • AssociatedWith

    • Domain via domains.domains
  • ResolvedIncidents

    • Incident via incidentsSummary.resolvedIncidentDetails
  • ActiveIncidents

    • Incident via incidentsSummary.activeIncidentDetails

Incoming

These are the relationships stored in other entity's aspects

  • IsPartOf

    • DataJob via dataJobKey.flow

Global Metadata Model

Global Graph