acryl-datahub-cloud 0.3.8rc8__py3-none-any.whl → 0.3.8rc10__py3-none-any.whl

acryl_datahub_cloud/metadata/schemas/Ownership.avsc

@@ -0,0 +1,255 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "ownership"
+  },
+  "name": "Ownership",
+  "namespace": "com.linkedin.pegasus2avro.common",
+  "fields": [
+    {
+      "type": {
+        "type": "array",
+        "items": {
+          "type": "record",
+          "name": "Owner",
+          "namespace": "com.linkedin.pegasus2avro.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.pegasus2avro.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.)",
+              "Urn": "Urn",
+              "entityTypes": [
+                "corpuser",
+                "corpGroup"
+              ]
+            },
+            {
+              "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.pegasus2avro.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"
+              },
+              "Searchable": {
+                "fieldName": "ownershipTypeUrn",
+                "fieldType": "URN",
+                "queryByDefault": false
+              },
+              "java": {
+                "class": "com.linkedin.pegasus2avro.common.urn.Urn"
+              },
+              "type": [
+                "null",
+                "string"
+              ],
+              "name": "typeUrn",
+              "default": null,
+              "doc": "The type of the ownership\nUrn of type O",
+              "Urn": "Urn",
+              "entityTypes": [
+                "ownershipType"
+              ]
+            },
+            {
+              "type": [
+                "null",
+                {
+                  "type": "record",
+                  "name": "OwnershipSource",
+                  "namespace": "com.linkedin.pegasus2avro.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.pegasus2avro.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": {
+        "/$key": {
+          "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.pegasus2avro.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.pegasus2avro.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.",
+            "Urn": "Urn"
+          },
+          {
+            "java": {
+              "class": "com.linkedin.pegasus2avro.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.",
+            "Urn": "Urn"
+          },
+          {
+            "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."
+}

acryl_datahub_cloud/metadata/schemas/OwnershipTypeInfo.avsc

@@ -0,0 +1,103 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "ownershipTypeInfo"
+  },
+  "name": "OwnershipTypeInfo",
+  "namespace": "com.linkedin.pegasus2avro.ownership",
+  "fields": [
+    {
+      "Searchable": {
+        "boostScore": 10.0,
+        "enableAutocomplete": true,
+        "fieldType": "WORD_GRAM"
+      },
+      "type": "string",
+      "name": "name",
+      "doc": "Display name of the Ownership Type"
+    },
+    {
+      "type": [
+        "null",
+        "string"
+      ],
+      "name": "description",
+      "default": null,
+      "doc": "Description of the Ownership Type"
+    },
+    {
+      "Searchable": {
+        "/actor": {
+          "fieldName": "createdBy",
+          "fieldType": "URN"
+        },
+        "/time": {
+          "fieldName": "createdAt",
+          "fieldType": "DATETIME"
+        }
+      },
+      "type": {
+        "type": "record",
+        "name": "AuditStamp",
+        "namespace": "com.linkedin.pegasus2avro.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.pegasus2avro.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.",
+            "Urn": "Urn"
+          },
+          {
+            "java": {
+              "class": "com.linkedin.pegasus2avro.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.",
+            "Urn": "Urn"
+          },
+          {
+            "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",
+      "doc": "Audit stamp capturing the time and actor who created the Ownership Type."
+    },
+    {
+      "Searchable": {
+        "/actor": {
+          "fieldName": "lastModifiedBy",
+          "fieldType": "URN"
+        },
+        "/time": {
+          "fieldName": "lastModifiedAt",
+          "fieldType": "DATETIME"
+        }
+      },
+      "type": "com.linkedin.pegasus2avro.common.AuditStamp",
+      "name": "lastModified",
+      "doc": "Audit stamp capturing the time and actor who last modified the Ownership Type."
+    }
+  ],
+  "doc": "Information about an ownership type"
+}

acryl_datahub_cloud/metadata/schemas/OwnershipTypeKey.avsc

@@ -0,0 +1,23 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "ownershipTypeKey",
+    "keyForEntity": "ownershipType",
+    "entityCategory": "core",
+    "entityAspects": [
+      "ownershipTypeInfo",
+      "status"
+    ],
+    "entityDoc": "Ownership Type represents a user-created ownership category for a person or group who is responsible for an asset."
+  },
+  "name": "OwnershipTypeKey",
+  "namespace": "com.linkedin.pegasus2avro.metadata.key",
+  "fields": [
+    {
+      "type": "string",
+      "name": "id",
+      "doc": "Unique ID for the data ownership type name i.e. Business Owner, Data Steward, Technical Owner, etc..\nShould be separate from the name used for displaying an Ownership Type."
+    }
+  ],
+  "doc": "Key for a Ownership Type"
+}

acryl_datahub_cloud/metadata/schemas/PartitionsSummary.avsc

@@ -0,0 +1,59 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "partitionsSummary"
+  },
+  "name": "PartitionsSummary",
+  "namespace": "com.linkedin.pegasus2avro.dataset",
+  "fields": [
+    {
+      "type": [
+        "null",
+        {
+          "type": "record",
+          "name": "PartitionSummary",
+          "namespace": "com.linkedin.pegasus2avro.dataset",
+          "fields": [
+            {
+              "type": "string",
+              "name": "partition",
+              "doc": "A unique id / value for the partition for which statistics were collected,\ngenerated by applying the key definition to a given row."
+            },
+            {
+              "type": [
+                "null",
+                "long"
+              ],
+              "name": "createdTime",
+              "default": null,
+              "doc": "The created time for a given partition."
+            },
+            {
+              "type": [
+                "null",
+                "long"
+              ],
+              "name": "lastModifiedTime",
+              "default": null,
+              "doc": "The last modified / touched time for a given partition."
+            }
+          ],
+          "doc": "Defines how the data is partitioned"
+        }
+      ],
+      "name": "minPartition",
+      "default": null,
+      "doc": "The minimum partition as ordered"
+    },
+    {
+      "type": [
+        "null",
+        "com.linkedin.pegasus2avro.dataset.PartitionSummary"
+      ],
+      "name": "maxPartition",
+      "default": null,
+      "doc": "The maximum partition as ordered"
+    }
+  ],
+  "doc": "Defines how the data is partitioned for Data Lake tables (e.g. Hive, S3, Iceberg, Delta, Hudi, etc)."
+}

acryl_datahub_cloud/metadata/schemas/PlatformEvent.avsc

@@ -0,0 +1,52 @@
+{
+  "type": "record",
+  "name": "PlatformEvent",
+  "namespace": "com.linkedin.pegasus2avro.mxe",
+  "fields": [
+    {
+      "type": {
+        "type": "record",
+        "name": "PlatformEventHeader",
+        "namespace": "com.linkedin.pegasus2avro.mxe",
+        "fields": [
+          {
+            "type": "long",
+            "name": "timestampMillis",
+            "doc": "The event timestamp field as epoch at UTC in milli seconds."
+          }
+        ],
+        "doc": "A header included with each DataHub platform event."
+      },
+      "name": "header",
+      "doc": "Header information stored with the event."
+    },
+    {
+      "type": "string",
+      "name": "name",
+      "doc": "The name of the event, e.g. the type of event. For example, 'notificationRequestEvent', 'entityChangeEvent'"
+    },
+    {
+      "type": {
+        "type": "record",
+        "name": "GenericPayload",
+        "namespace": "com.linkedin.pegasus2avro.mxe",
+        "fields": [
+          {
+            "type": "bytes",
+            "name": "value",
+            "doc": "The value of the event, serialized as bytes."
+          },
+          {
+            "type": "string",
+            "name": "contentType",
+            "doc": "The content type, which represents the fashion in which the event was serialized.\nThe only type currently supported is application/json."
+          }
+        ],
+        "doc": "Generic payload record structure for serializing a Platform Event."
+      },
+      "name": "payload",
+      "doc": "The event payload."
+    }
+  ],
+  "doc": "A DataHub Platform Event."
+}

acryl_datahub_cloud/metadata/schemas/PlatformResourceInfo.avsc

@@ -0,0 +1,109 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "platformResourceInfo"
+  },
+  "name": "PlatformResourceInfo",
+  "namespace": "com.linkedin.pegasus2avro.platformresource",
+  "fields": [
+    {
+      "Searchable": {
+        "fieldType": "KEYWORD"
+      },
+      "type": "string",
+      "name": "resourceType",
+      "doc": "The type of the resource. \nIntended as a loose specifier of the generic type of the resource.\nProducer is not forced to conform to a specific set of symbols for\nresource types.\nThe @PlatformResourceType enumeration offers a paved path for agreed upon\ncommon terms, but is not required to be followed.\nExample values could be: conversation, user, grant, etc.\nResource types are indexed for ease of access. \ne.g. Get me all platform resources of type user for the platform looker"
+    },
+    {
+      "Searchable": {
+        "fieldType": "KEYWORD"
+      },
+      "type": "string",
+      "name": "primaryKey",
+      "doc": "The primary key for this platform resource.\ne.g. for a slack member this would be the memberID.\nprimary keys specified here don't need to include any additional specificity for the\n     dataPlatform\nThe @PlatformResourceKey is supposed to represent that"
+    },
+    {
+      "Searchable": {
+        "/*": {
+          "fieldType": "KEYWORD"
+        }
+      },
+      "type": [
+        "null",
+        {
+          "type": "array",
+          "items": "string"
+        }
+      ],
+      "name": "secondaryKeys",
+      "default": null,
+      "doc": "The secondary keys this platform resource can be located by.\nI.e., for a slack member this would be email or phone."
+    },
+    {
+      "type": [
+        "null",
+        {
+          "type": "record",
+          "name": "SerializedValue",
+          "namespace": "com.linkedin.pegasus2avro.common",
+          "fields": [
+            {
+              "type": "bytes",
+              "name": "blob",
+              "doc": "The serialized blob value."
+            },
+            {
+              "type": {
+                "type": "enum",
+                "name": "SerializedValueContentType",
+                "namespace": "com.linkedin.pegasus2avro.common",
+                "symbols": [
+                  "JSON",
+                  "BINARY"
+                ]
+              },
+              "name": "contentType",
+              "default": "JSON",
+              "doc": "The content-type of the serialized blob value."
+            },
+            {
+              "type": [
+                "null",
+                {
+                  "type": "enum",
+                  "name": "SerializedValueSchemaType",
+                  "namespace": "com.linkedin.pegasus2avro.common",
+                  "symbols": [
+                    "AVRO",
+                    "PROTOBUF",
+                    "PEGASUS",
+                    "THRIFT",
+                    "JSON",
+                    "NONE"
+                  ]
+                }
+              ],
+              "name": "schemaType",
+              "default": null,
+              "doc": "The schema type for the schema that models the object that was serialized\n       into the blob.\nAbsence of this field indicates that the schema is not known.\nIf the schema is known, the value should be set to the appropriate schema\ntype.\nUse the NONE value if the existing schema categories do not apply."
+            },
+            {
+              "type": [
+                "null",
+                "string"
+              ],
+              "name": "schemaRef",
+              "default": null,
+              "doc": "An optional reference to the schema that models the object.\ne.g., 'com.linkedin.pegasus2avro.platformresource.slack.SlackConversation'"
+            }
+          ],
+          "doc": "Captures the serialized value of a (usually) schema-d blob."
+        }
+      ],
+      "name": "value",
+      "default": null,
+      "doc": "The serialized value of this platform resource item."
+    }
+  ],
+  "doc": "Platform Resource Info.\nThese entities are for miscelaneous data that is used in non-core parts of the system.\nFor instance, if we want to persist & retrieve data from auxiliary integrations such as Slack or Microsoft Teams."
+}

acryl_datahub_cloud/metadata/schemas/PlatformResourceKey.avsc

@@ -0,0 +1,24 @@
+{
+  "type": "record",
+  "Aspect": {
+    "name": "platformResourceKey",
+    "keyForEntity": "platformResource",
+    "entityCategory": "core",
+    "entityAspects": [
+      "dataPlatformInstance",
+      "platformResourceInfo",
+      "status"
+    ],
+    "entityDoc": "Platform Resources are assets that are unmodeled and stored outside of the core data model. They are stored in DataHub primarily to help with application-specific use-cases that are not sufficiently generalized to move into the core data model."
+  },
+  "name": "PlatformResourceKey",
+  "namespace": "com.linkedin.pegasus2avro.platformresource",
+  "fields": [
+    {
+      "type": "string",
+      "name": "id",
+      "doc": "A unique id for this entity.\nThere are no constraints on the format of this id, but most implementations\nwill choose to use a UUID.\nThis id should be globally unique for the entire DataHub instance and\n     uniquely identify the resource that is being stored, so most\n     implementations\nwill combine logical attributes like platform name, platform instance,\nplatform-specific-id and the resource type to create the unique id.\ne.g. slack:slack-instance:slack-user-id:user-info \nor guid(slack, slack-instance, slack-user-id, user-info) etc."
+    }
+  ],
+  "doc": "Key for a Platform Resource.\nPlatform Resources are assets that are not part of the core data model.\nThey are stored in DataHub primarily to help with application-specific\nuse-cases that are not sufficiently generalized to move into the core data model.\nFor instance, if we want to persist & retrieve additional user profile data \nfrom auxiliary integrations such as Slack or Microsoft Teams for resolving details later."
+}