pulumi-databricks 1.77.0a1762276204__py3-none-any.whl → 1.78.0__py3-none-any.whl

pulumi_databricks/apps_settings_custom_template.py

@@ -290,6 +290,39 @@ class AppsSettingsCustomTemplate(pulumi.CustomResource):
 
         This example defines a template that requests specific workspace resources with permissions granted.
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        resources_example = databricks.AppsSettingsCustomTemplate("resources_example",
+            name="my-resource-template",
+            description="Template that requires secret and SQL warehouse access",
+            git_repo="https://github.com/example/resource-app.git",
+            path="resource-template",
+            git_provider="github",
+            manifest={
+                "version": 1,
+                "name": "resource-consuming-app",
+                "description": "This app requires access to a secret and SQL warehouse.",
+                "resource_specs": [
+                    {
+                        "name": "my-secret",
+                        "description": "A secret needed by the app",
+                        "secret_spec": {
+                            "permission": "READ",
+                        },
+                    },
+                    {
+                        "name": "warehouse",
+                        "description": "Warehouse access",
+                        "sql_warehouse_spec": {
+                            "permission": "CAN_USE",
+                        },
+                    },
+                ],
+            })
+        ```
+
         ## Import
 
         As of Pulumi v1.5, resources can be imported through configuration.
@@ -361,6 +394,39 @@ class AppsSettingsCustomTemplate(pulumi.CustomResource):
 
         This example defines a template that requests specific workspace resources with permissions granted.
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        resources_example = databricks.AppsSettingsCustomTemplate("resources_example",
+            name="my-resource-template",
+            description="Template that requires secret and SQL warehouse access",
+            git_repo="https://github.com/example/resource-app.git",
+            path="resource-template",
+            git_provider="github",
+            manifest={
+                "version": 1,
+                "name": "resource-consuming-app",
+                "description": "This app requires access to a secret and SQL warehouse.",
+                "resource_specs": [
+                    {
+                        "name": "my-secret",
+                        "description": "A secret needed by the app",
+                        "secret_spec": {
+                            "permission": "READ",
+                        },
+                    },
+                    {
+                        "name": "warehouse",
+                        "description": "Warehouse access",
+                        "sql_warehouse_spec": {
+                            "permission": "CAN_USE",
+                        },
+                    },
+                ],
+            })
+        ```
+
         ## Import
 
         As of Pulumi v1.5, resources can be imported through configuration.

pulumi_databricks/catalog.py

@@ -51,7 +51,7 @@ class CatalogArgs:
         :param pulumi.Input[Mapping[str, pulumi.Input[_builtins.str]]] properties: Extensible Catalog properties.
         :param pulumi.Input[_builtins.str] provider_name: For Delta Sharing Catalogs: the name of the delta sharing provider. Change forces creation of a new resource.
         :param pulumi.Input[_builtins.str] share_name: For Delta Sharing Catalogs: the name of the share under the share provider. Change forces creation of a new resource.
-        :param pulumi.Input[_builtins.str] storage_root: Managed location of the catalog. Location in cloud storage where data for managed tables will be stored. If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
+        :param pulumi.Input[_builtins.str] storage_root: Managed location of the catalog. Location in cloud storage where data for managed tables will be stored.  If the URL contains special characters, such as space, `&`, etc., they should be percent-encoded (space > `%20`, etc.). If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
         """
         if browse_only is not None:
             pulumi.set(__self__, "browse_only", browse_only)
@@ -261,7 +261,7 @@ class CatalogArgs:
     @pulumi.getter(name="storageRoot")
     def storage_root(self) -> Optional[pulumi.Input[_builtins.str]]:
         """
-        Managed location of the catalog. Location in cloud storage where data for managed tables will be stored. If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
+        Managed location of the catalog. Location in cloud storage where data for managed tables will be stored.  If the URL contains special characters, such as space, `&`, etc., they should be percent-encoded (space > `%20`, etc.). If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
         """
         return pulumi.get(self, "storage_root")
 
@@ -316,7 +316,7 @@ class _CatalogState:
         :param pulumi.Input[_builtins.str] securable_type: the type of Unity Catalog securable.
         :param pulumi.Input[_builtins.str] share_name: For Delta Sharing Catalogs: the name of the share under the share provider. Change forces creation of a new resource.
         :param pulumi.Input[_builtins.str] storage_location: effective storage Location URL (full path) for managed tables within catalog.
-        :param pulumi.Input[_builtins.str] storage_root: Managed location of the catalog. Location in cloud storage where data for managed tables will be stored. If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
+        :param pulumi.Input[_builtins.str] storage_root: Managed location of the catalog. Location in cloud storage where data for managed tables will be stored.  If the URL contains special characters, such as space, `&`, etc., they should be percent-encoded (space > `%20`, etc.). If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
         :param pulumi.Input[_builtins.int] updated_at: time at which this catalog was last modified, in epoch milliseconds..
         :param pulumi.Input[_builtins.str] updated_by: username of user who last modified catalog.
         """
@@ -613,7 +613,7 @@ class _CatalogState:
     @pulumi.getter(name="storageRoot")
     def storage_root(self) -> Optional[pulumi.Input[_builtins.str]]:
         """
-        Managed location of the catalog. Location in cloud storage where data for managed tables will be stored. If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
+        Managed location of the catalog. Location in cloud storage where data for managed tables will be stored.  If the URL contains special characters, such as space, `&`, etc., they should be percent-encoded (space > `%20`, etc.). If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
         """
         return pulumi.get(self, "storage_root")
 
@@ -734,7 +734,7 @@ class Catalog(pulumi.CustomResource):
         :param pulumi.Input[Mapping[str, pulumi.Input[_builtins.str]]] properties: Extensible Catalog properties.
         :param pulumi.Input[_builtins.str] provider_name: For Delta Sharing Catalogs: the name of the delta sharing provider. Change forces creation of a new resource.
         :param pulumi.Input[_builtins.str] share_name: For Delta Sharing Catalogs: the name of the share under the share provider. Change forces creation of a new resource.
-        :param pulumi.Input[_builtins.str] storage_root: Managed location of the catalog. Location in cloud storage where data for managed tables will be stored. If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
+        :param pulumi.Input[_builtins.str] storage_root: Managed location of the catalog. Location in cloud storage where data for managed tables will be stored.  If the URL contains special characters, such as space, `&`, etc., they should be percent-encoded (space > `%20`, etc.). If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
         """
         ...
     @overload
@@ -915,7 +915,7 @@ class Catalog(pulumi.CustomResource):
         :param pulumi.Input[_builtins.str] securable_type: the type of Unity Catalog securable.
         :param pulumi.Input[_builtins.str] share_name: For Delta Sharing Catalogs: the name of the share under the share provider. Change forces creation of a new resource.
         :param pulumi.Input[_builtins.str] storage_location: effective storage Location URL (full path) for managed tables within catalog.
-        :param pulumi.Input[_builtins.str] storage_root: Managed location of the catalog. Location in cloud storage where data for managed tables will be stored. If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
+        :param pulumi.Input[_builtins.str] storage_root: Managed location of the catalog. Location in cloud storage where data for managed tables will be stored.  If the URL contains special characters, such as space, `&`, etc., they should be percent-encoded (space > `%20`, etc.). If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
         :param pulumi.Input[_builtins.int] updated_at: time at which this catalog was last modified, in epoch milliseconds..
         :param pulumi.Input[_builtins.str] updated_by: username of user who last modified catalog.
         """
@@ -1109,7 +1109,7 @@ class Catalog(pulumi.CustomResource):
     @pulumi.getter(name="storageRoot")
     def storage_root(self) -> pulumi.Output[Optional[_builtins.str]]:
         """
-        Managed location of the catalog. Location in cloud storage where data for managed tables will be stored. If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
+        Managed location of the catalog. Location in cloud storage where data for managed tables will be stored.  If the URL contains special characters, such as space, `&`, etc., they should be percent-encoded (space > `%20`, etc.). If not specified, the location will default to the metastore root location. Change forces creation of a new resource.
         """
         return pulumi.get(self, "storage_root")
 

pulumi_databricks/cluster_policy.py

@@ -298,6 +298,66 @@ class ClusterPolicy(pulumi.CustomResource):
         * A user who has both cluster create permission and access to cluster policies can select the Free form policy and policies they have access to.
         * A user that has access to only cluster policies, can select the policies they have access to.
 
+        ## Example Usage
+
+        Let us take a look at an example of how you can manage two teams: Marketing and Data Engineering. In the following scenario we want the marketing team to have a really good query experience, so we enabled delta cache for them. On the other hand we want the data engineering team to be able to utilize bigger clusters so we increased the dbus per hour that they can spend. This strategy allows your marketing users and data engineering users to use Databricks in a self service manner but have a different experience in regards to security and performance. And down the line if you need to add more global settings you can propagate them through the "base cluster policy".
+
+        `modules/base-cluster-policy/main.tf` could look like:
+
+        ```python
+        import pulumi
+        import json
+        import pulumi_databricks as databricks
+        import pulumi_std as std
+
+        config = pulumi.Config()
+        # Team that performs the work
+        team = config.require_object("team")
+        # Cluster policy overrides
+        policy_overrides = config.require_object("policyOverrides")
+        default_policy = {
+            "dbus_per_hour": {
+                "type": "range",
+                "maxValue": 10,
+            },
+            "autotermination_minutes": {
+                "type": "fixed",
+                "value": 20,
+                "hidden": True,
+            },
+            "custom_tags.Team": {
+                "type": "fixed",
+                "value": team,
+            },
+        }
+        fair_use = databricks.ClusterPolicy("fair_use",
+            name=f"{team} cluster policy",
+            definition=json.dumps(std.merge(input=[
+                default_policy,
+                policy_overrides,
+            ]).result),
+            libraries=[
+                {
+                    "pypi": {
+                        "package": "databricks-sdk==0.12.0",
+                    },
+                },
+                {
+                    "maven": {
+                        "coordinates": "com.oracle.database.jdbc:ojdbc8:XXXX",
+                    },
+                },
+            ])
+        can_use_cluster_policyinstance_profile = databricks.Permissions("can_use_cluster_policyinstance_profile",
+            cluster_policy_id=fair_use.id,
+            access_controls=[{
+                "group_name": team,
+                "permission_level": "CAN_USE",
+            }])
+        ```
+
+        And custom instances of that base policy module for our marketing and data engineering teams would look like:
+
         ### Overriding the built-in cluster policies
 
         You can override built-in cluster policies by creating a `ClusterPolicy` resource with following attributes:
@@ -405,6 +465,66 @@ class ClusterPolicy(pulumi.CustomResource):
         * A user who has both cluster create permission and access to cluster policies can select the Free form policy and policies they have access to.
         * A user that has access to only cluster policies, can select the policies they have access to.
 
+        ## Example Usage
+
+        Let us take a look at an example of how you can manage two teams: Marketing and Data Engineering. In the following scenario we want the marketing team to have a really good query experience, so we enabled delta cache for them. On the other hand we want the data engineering team to be able to utilize bigger clusters so we increased the dbus per hour that they can spend. This strategy allows your marketing users and data engineering users to use Databricks in a self service manner but have a different experience in regards to security and performance. And down the line if you need to add more global settings you can propagate them through the "base cluster policy".
+
+        `modules/base-cluster-policy/main.tf` could look like:
+
+        ```python
+        import pulumi
+        import json
+        import pulumi_databricks as databricks
+        import pulumi_std as std
+
+        config = pulumi.Config()
+        # Team that performs the work
+        team = config.require_object("team")
+        # Cluster policy overrides
+        policy_overrides = config.require_object("policyOverrides")
+        default_policy = {
+            "dbus_per_hour": {
+                "type": "range",
+                "maxValue": 10,
+            },
+            "autotermination_minutes": {
+                "type": "fixed",
+                "value": 20,
+                "hidden": True,
+            },
+            "custom_tags.Team": {
+                "type": "fixed",
+                "value": team,
+            },
+        }
+        fair_use = databricks.ClusterPolicy("fair_use",
+            name=f"{team} cluster policy",
+            definition=json.dumps(std.merge(input=[
+                default_policy,
+                policy_overrides,
+            ]).result),
+            libraries=[
+                {
+                    "pypi": {
+                        "package": "databricks-sdk==0.12.0",
+                    },
+                },
+                {
+                    "maven": {
+                        "coordinates": "com.oracle.database.jdbc:ojdbc8:XXXX",
+                    },
+                },
+            ])
+        can_use_cluster_policyinstance_profile = databricks.Permissions("can_use_cluster_policyinstance_profile",
+            cluster_policy_id=fair_use.id,
+            access_controls=[{
+                "group_name": team,
+                "permission_level": "CAN_USE",
+            }])
+        ```
+
+        And custom instances of that base policy module for our marketing and data engineering teams would look like:
+
         ### Overriding the built-in cluster policies
 
         You can override built-in cluster policies by creating a `ClusterPolicy` resource with following attributes:

pulumi_databricks/config/__init__.pyi

@@ -54,6 +54,8 @@ debugHeaders: Optional[bool]
 
 debugTruncateBytes: Optional[int]
 
+experimentalIsUnifiedHost: Optional[bool]
+
 googleCredentials: Optional[str]
 
 googleServiceAccount: Optional[str]
@@ -86,3 +88,5 @@ username: Optional[str]
 
 warehouseId: Optional[str]
 
+workspaceId: Optional[str]
+

pulumi_databricks/config/vars.py

@@ -100,6 +100,10 @@ class _ExportableConfig(types.ModuleType):
     def debug_truncate_bytes(self) -> Optional[int]:
         return __config__.get_int('debugTruncateBytes')
 
+    @_builtins.property
+    def experimental_is_unified_host(self) -> Optional[bool]:
+        return __config__.get_bool('experimentalIsUnifiedHost')
+
     @_builtins.property
     def google_credentials(self) -> Optional[str]:
         return __config__.get('googleCredentials')
@@ -164,3 +168,7 @@ class _ExportableConfig(types.ModuleType):
     def warehouse_id(self) -> Optional[str]:
         return __config__.get('warehouseId')
 
+    @_builtins.property
+    def workspace_id(self) -> Optional[str]:
+        return __config__.get('workspaceId')
+

pulumi_databricks/database_synced_database_table.py

@@ -298,15 +298,88 @@ class DatabaseSyncedDatabaseTable(pulumi.CustomResource):
 
         This example creates a Synced Database Table inside a Database Catalog.
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        this = databricks.DatabaseSyncedDatabaseTable("this",
+            name="my_database_catalog.public.synced_table",
+            logical_database_name="databricks_postgres",
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.tpch.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "new_pipeline_spec": {
+                    "storage_catalog": "source_delta",
+                    "storage_schema": "tpch",
+                },
+            })
+        ```
+
         ### Creating a Synced Database Table inside a Standard Catalog
 
         This example creates a Synced Database Table inside a Standard Catalog.
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        this = databricks.DatabaseSyncedDatabaseTable("this",
+            name="my_standard_catalog.public.synced_table",
+            logical_database_name="databricks_postgres",
+            database_instance_name="my-database-instance",
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.tpch.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "new_pipeline_spec": {
+                    "storage_catalog": "source_delta",
+                    "storage_schema": "tpch",
+                },
+            })
+        ```
+
         ### Creating multiple Synced Database Tables and bin packing them into a single pipeline
 
         This example creates two Synced Database Tables. The first one specifies a new pipeline spec,
         which generates a new pipeline. The second one utilizes the pipeline ID of the first table.
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        instance = databricks.DatabaseInstance("instance",
+            name="my-database-instance",
+            capacity="CU_1")
+        synced_table1 = databricks.DatabaseSyncedDatabaseTable("synced_table_1",
+            name="my_standard_catalog.public.synced_table1",
+            logical_database_name="databricks_postgres",
+            database_instance_name=instance.name,
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.tpch.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "new_pipeline_spec": {
+                    "storage_catalog": "source_delta",
+                    "storage_schema": "tpch",
+                },
+            })
+        synced_table2 = databricks.DatabaseSyncedDatabaseTable("synced_table_2",
+            name="my_standard_catalog.public.synced_table2",
+            logical_database_name="databricks_postgres",
+            database_instance_name=instance.name,
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.tpch.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "existing_pipeline_id": synced_table1.data_synchronization_status.pipeline_id,
+            })
+        ```
+
         ### Creating a Synced Database Table with a custom Jobs schedule
 
         This example creates a Synced Database Table and customizes the pipeline schedule. It assumes you already have
@@ -316,6 +389,39 @@ class DatabaseSyncedDatabaseTable(pulumi.CustomResource):
         - A schema in the standard catalog named `"default"`
         - A source delta table named `"source_delta.schema.customer"` with the primary key `"c_custkey"`
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        synced_table = databricks.DatabaseSyncedDatabaseTable("synced_table",
+            name="my_standard_catalog.default.my_synced_table",
+            logical_database_name="terraform_test_db",
+            database_instance_name="my-database-instance",
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.schema.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "new_pipeline_spec": {
+                    "storage_catalog": "source_delta",
+                    "storage_schema": "schema",
+                },
+            })
+        sync_pipeline_schedule_job = databricks.Job("sync_pipeline_schedule_job",
+            name="Synced Pipeline Refresh",
+            description="Job to schedule synced database table pipeline. ",
+            tasks=[{
+                "task_key": "synced-table-pipeline",
+                "pipeline_task": {
+                    "pipeline_id": synced_table.data_synchronization_status.pipeline_id,
+                },
+            }],
+            schedule={
+                "quartz_cron_expression": "0 0 0 * * ?",
+                "timezone_id": "Europe/Helsinki",
+            })
+        ```
+
         ## Import
 
         As of Pulumi v1.5, resources can be imported through configuration.
@@ -375,15 +481,88 @@ class DatabaseSyncedDatabaseTable(pulumi.CustomResource):
 
         This example creates a Synced Database Table inside a Database Catalog.
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        this = databricks.DatabaseSyncedDatabaseTable("this",
+            name="my_database_catalog.public.synced_table",
+            logical_database_name="databricks_postgres",
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.tpch.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "new_pipeline_spec": {
+                    "storage_catalog": "source_delta",
+                    "storage_schema": "tpch",
+                },
+            })
+        ```
+
         ### Creating a Synced Database Table inside a Standard Catalog
 
         This example creates a Synced Database Table inside a Standard Catalog.
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        this = databricks.DatabaseSyncedDatabaseTable("this",
+            name="my_standard_catalog.public.synced_table",
+            logical_database_name="databricks_postgres",
+            database_instance_name="my-database-instance",
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.tpch.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "new_pipeline_spec": {
+                    "storage_catalog": "source_delta",
+                    "storage_schema": "tpch",
+                },
+            })
+        ```
+
         ### Creating multiple Synced Database Tables and bin packing them into a single pipeline
 
         This example creates two Synced Database Tables. The first one specifies a new pipeline spec,
         which generates a new pipeline. The second one utilizes the pipeline ID of the first table.
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        instance = databricks.DatabaseInstance("instance",
+            name="my-database-instance",
+            capacity="CU_1")
+        synced_table1 = databricks.DatabaseSyncedDatabaseTable("synced_table_1",
+            name="my_standard_catalog.public.synced_table1",
+            logical_database_name="databricks_postgres",
+            database_instance_name=instance.name,
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.tpch.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "new_pipeline_spec": {
+                    "storage_catalog": "source_delta",
+                    "storage_schema": "tpch",
+                },
+            })
+        synced_table2 = databricks.DatabaseSyncedDatabaseTable("synced_table_2",
+            name="my_standard_catalog.public.synced_table2",
+            logical_database_name="databricks_postgres",
+            database_instance_name=instance.name,
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.tpch.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "existing_pipeline_id": synced_table1.data_synchronization_status.pipeline_id,
+            })
+        ```
+
         ### Creating a Synced Database Table with a custom Jobs schedule
 
         This example creates a Synced Database Table and customizes the pipeline schedule. It assumes you already have
@@ -393,6 +572,39 @@ class DatabaseSyncedDatabaseTable(pulumi.CustomResource):
         - A schema in the standard catalog named `"default"`
         - A source delta table named `"source_delta.schema.customer"` with the primary key `"c_custkey"`
 
+        ```python
+        import pulumi
+        import pulumi_databricks as databricks
+
+        synced_table = databricks.DatabaseSyncedDatabaseTable("synced_table",
+            name="my_standard_catalog.default.my_synced_table",
+            logical_database_name="terraform_test_db",
+            database_instance_name="my-database-instance",
+            spec={
+                "scheduling_policy": "SNAPSHOT",
+                "source_table_full_name": "source_delta.schema.customer",
+                "primary_key_columns": ["c_custkey"],
+                "create_database_objects_if_missing": True,
+                "new_pipeline_spec": {
+                    "storage_catalog": "source_delta",
+                    "storage_schema": "schema",
+                },
+            })
+        sync_pipeline_schedule_job = databricks.Job("sync_pipeline_schedule_job",
+            name="Synced Pipeline Refresh",
+            description="Job to schedule synced database table pipeline. ",
+            tasks=[{
+                "task_key": "synced-table-pipeline",
+                "pipeline_task": {
+                    "pipeline_id": synced_table.data_synchronization_status.pipeline_id,
+                },
+            }],
+            schedule={
+                "quartz_cron_expression": "0 0 0 * * ?",
+                "timezone_id": "Europe/Helsinki",
+            })
+        ```
+
         ## Import
 
         As of Pulumi v1.5, resources can be imported through configuration.