Adds databricks_volume as data source (#3211)

* data_volume * data_volume unit and acceptance tests * docs * WorkspaceDataWithCustomParams test * fixed formatting * Removing unnecessary changes to resource.go * refactored data_volume * making change for consitency with GO SDK v0.35.0 * Update catalog/data_volume.go * Update catalog/data_volume.go * data source as nested strucutre * review comments addressed * acceptance test --------- Co-authored-by: Alex Ott <[email protected]> Co-authored-by: vuong-nguyen <[email protected]>
databricks · Jul 3, 2024 · ff837ab · ff837ab
1 parent c6f949c
commit ff837ab
Show file tree

Hide file tree

Showing 6 changed files with 197 additions and 1 deletion.
diff --git a/catalog/data_volume.go b/catalog/data_volume.go
@@ -0,0 +1,25 @@
+package catalog
+
+import (
+	"context"
+
+	"github.com/databricks/databricks-sdk-go"
+	"github.com/databricks/databricks-sdk-go/service/catalog"
+	"github.com/databricks/terraform-provider-databricks/common"
+)
+
+func DataSourceVolume() common.Resource {
+	return common.WorkspaceData(func(ctx context.Context, data *struct {
+		Id     string              `json:"id,omitempty" tf:"computed"`
+		Name   string              `json:"name"`
+		Volume *catalog.VolumeInfo `json:"volume_info,omitempty" tf:"computed"`
+	}, w *databricks.WorkspaceClient) error {
+		volume, err := w.Volumes.ReadByName(ctx, data.Name)
+		if err != nil {
+			return err
+		}
+		data.Volume = volume
+		data.Id = volume.FullName
+		return nil
+	})
+}
diff --git a/catalog/data_volume_test.go b/catalog/data_volume_test.go
@@ -0,0 +1,50 @@
+package catalog
+
+import (
+	"testing"
+
+	"github.com/databricks/databricks-sdk-go/experimental/mocks"
+	"github.com/databricks/databricks-sdk-go/service/catalog"
+	"github.com/databricks/terraform-provider-databricks/qa"
+	"github.com/stretchr/testify/mock"
+)
+
+func TestDataSourceVolume(t *testing.T) {
+	qa.ResourceFixture{
+		MockWorkspaceClientFunc: func(m *mocks.MockWorkspaceClient) {
+			e := m.GetMockVolumesAPI().EXPECT()
+			e.ReadByName(mock.Anything, "a.b.c").Return(&catalog.VolumeInfo{
+				FullName:    "a.b.c",
+				CatalogName: "a",
+				SchemaName:  "b",
+				Name:        "c",
+				Owner:       "account users",
+				VolumeType:  catalog.VolumeTypeManaged,
+			}, nil)
+		},
+		Resource: DataSourceVolume(),
+		HCL: `
+		name="a.b.c"`,
+		Read:        true,
+		NonWritable: true,
+		ID:          "_",
+	}.ApplyAndExpectData(t, map[string]any{
+		"name":                       "a.b.c",
+		"volume_info.0.full_name":    "a.b.c",
+		"volume_info.0.catalog_name": "a",
+		"volume_info.0.schema_name":  "b",
+		"volume_info.0.name":         "c",
+		"volume_info.0.owner":        "account users",
+		"volume_info.0.volume_type":  "MANAGED",
+	})
+}
+
+func TestDataSourceVolume_Error(t *testing.T) {
+	qa.ResourceFixture{
+		Fixtures:    qa.HTTPFailures,
+		Resource:    DataSourceVolume(),
+		Read:        true,
+		NonWritable: true,
+		ID:          "_",
+	}.ExpectError(t, "i'm a teapot")
+}
diff --git a/common/resource.go b/common/resource.go
@@ -365,7 +365,7 @@ func genericDatabricksData[T, P, C any](
 	hasOther bool) Resource {
 	var dummy T
 	var other P
-	otherFields := StructToSchema(other, NoCustomize)
+	otherFields := StructToSchema(other, nil)
 	s := StructToSchema(dummy, func(m map[string]*schema.Schema) map[string]*schema.Schema {
 		// For WorkspaceData and AccountData, a single data type is used to represent all of the fields of
 		// the resource, so its configuration is correct. For the *WithParams methods, the SdkType parameter

diff --git a/docs/data-sources/volume.md b/docs/data-sources/volume.md
@@ -0,0 +1,69 @@
+---
+subcategory: "Unity Catalog"
+---
+# databricks_volume Data Source
+
+Retrieves details about [databricks_volume](../resources/volume.md) that was created by Terraform or manually. 
+A volume can be identified by its three-level (fully qualified) name (in the form of: `catalog_name`.`schema_name`.`volume_name`) as input. This can be retrieved programmatically using [databricks_volumes](../data-sources/volumes.md) data source.
+
+## Example Usage
+
+* Retrieve details of all volumes in in a _things_ [databricks_schema](../resources/schema.md) of a  _sandbox_ [databricks_catalog](../resources/catalog.md):
+
+```hcl
+data "databricks_volumes" "all" {
+  catalog_name = "sandbox"
+  schema_name  = "things"
+}
+
+data "databricks_volume" {
+  for_each = data.datatbricks_volumes.all.ids
+  name     = each.value
+}
+```
+
+* Search for a specific volume by its fully qualified name
+
+```hcl
+data "databricks_volume" "this" {
+  name = "catalog.schema.volume"
+}
+```
+
+## Argument Reference
+
+* `name` - (Required) a fully qualified name of [databricks_volume](../resources/volume.md): *`catalog`.`schema`.`volume`*
+
+
+## Attribute Reference
+
+In addition to all arguments above, the following attributes are exported:
+
+* `id` - ID of this Unity Catalog Volume in form of `<catalog>.<schema>.<name>`.
+* `volume_info` - TableInfo object for a Unity Catalog table. This contains the following attributes:
+  * `name` - Name of table, relative to parent schema.
+  * `access_point` - the AWS access point to use when accessing s3 bucket for this volume's external location
+  * `browse_only` - indicates whether the principal is limited to retrieving metadata for the volume through the BROWSE privilege when include_browse is enabled in the request. 
+  * `catalog_name` - the name of the catalog where the schema and the volume are
+  * `comment` - the comment attached to the volume
+  * `created_at` - the Unix timestamp at the volume's creation
+  * `created_by` - the identifier of the user who created the volume
+  * `encryption_details` - encryption options that apply to clients connecting to cloud storage
+  * `full_name` - the three-level (fully qualified) name of the volume
+  * `metastore_id` - the unique identifier of the metastore
+  * `name` - the name of the volume
+  * `owner` - the identifier of the user who owns the volume
+  * `schema_name` - the name of the schema where the volume is
+  * `storage_location` - the storage location on the cloud
+  * `updated_at` - the timestamp of the last time changes were made to the volume
+  * `updated_by` - the identifier of the user who updated the volume last time
+  * `volume_id` - the unique identifier of the volume
+  * `volume_type` - whether the volume is `MANAGED` or `EXTERNAL`
+
+## Related Resources
+
+The following resources are used in the same context:
+
+* [databricks_volume](../resources/volume.md) to manage volumes within Unity Catalog.
+* [databricks_schema](../resources/schema.md) to manage schemas within Unity Catalog.
+* [databricks_catalog](../resources/catalog.md) to manage catalogs within Unity Catalog.
diff --git a/internal/acceptance/data_volume_test.go b/internal/acceptance/data_volume_test.go
@@ -0,0 +1,51 @@
+package acceptance
+
+import (
+	"testing"
+
+	"github.com/hashicorp/terraform-plugin-sdk/v2/terraform"
+	"github.com/stretchr/testify/require"
+)
+
+func checkDataSourceVolume(t *testing.T) func(s *terraform.State) error {
+	return func(s *terraform.State) error {
+		_, ok := s.Modules[0].Resources["data.databricks_volume.this"]
+		require.True(t, ok, "data.databricks_volume.this has to be there")
+		return nil
+	}
+}
+func TestUcAccDataSourceVolume(t *testing.T) {
+	unityWorkspaceLevel(t, step{
+		Template: `
+		resource "databricks_catalog" "sandbox" {
+			name         = "sandbox{var.RANDOM}"
+			comment      = "this catalog is managed by terraform"
+			properties = {
+				purpose = "testing"
+			}
+		}
+		
+		resource "databricks_schema" "things" {
+			catalog_name = databricks_catalog.sandbox.id
+			name         = "things{var.RANDOM}"
+			comment      = "this database is managed by terraform"
+			properties = {
+				kind = "various"
+			}
+		}
+
+		resource "databricks_volume" "this" {
+			name         = "volume_data_source_test"
+			catalog_name = databricks_catalog.sandbox.name
+			schema_name  = databricks_schema.things.name
+			volume_type  = "MANAGED"      
+		}
+
+		data "databricks_volume" "this" {
+			name = databricks_volume.this.id
+			depends_on = [ databricks_volume.this ] 
+		}
+		`,
+		Check: checkDataSourceVolume(t),
+	})
+}
diff --git a/provider/provider.go b/provider/provider.go
@@ -113,6 +113,7 @@ func DatabricksProvider() *schema.Provider {
 			"databricks_table":                                catalog.DataSourceTable().ToResource(),
 			"databricks_tables":                               catalog.DataSourceTables().ToResource(),
 			"databricks_views":                                catalog.DataSourceViews().ToResource(),
+			"databricks_volume":                               catalog.DataSourceVolume().ToResource(),
 			"databricks_volumes":                              catalog.DataSourceVolumes().ToResource(),
 			"databricks_user":                                 scim.DataSourceUser().ToResource(),
 			"databricks_zones":                                clusters.DataSourceClusterZones().ToResource(),