Added databricks_job data resource (#1509)

Example: Getting the existing cluster id of specific databricks_job by name or by id:

```
data "databricks_job" "this" {
  job_name = "My job"
}
output "cluster_id" {
  value     = data.databricks_job.job_settings.existing_cluster_id
  sensitive = false
}
```

Co-authored-by: Serge Smertin <[email protected]>

Author: edmondop

README.md

@@ -33,6 +33,7 @@
 | [databricks_instance_profile](docs/resources/instance_profile.md)
 | [databricks_ip_access_list](docs/resources/ip_access_list.md)
 | [databricks_job](docs/resources/job.md)
+| [databricks_job](docs/data-sources/job.md) data
 | [databricks_jobs](docs/data-sources/jobs.md)
 | [databricks_library](docs/resources/library.md)
 | [databricks_metastore](docs/resources/metastore.md)

docs/data-sources/job.md

@@ -0,0 +1,38 @@
+---
+subcategory: "Compute"
+---
+# databricks_job Data Source
+
+-> **Note** If you have a fully automated setup with workspaces created by [databricks_mws_workspaces](../resources/mws_workspaces.md) or [azurerm_databricks_workspace](https://registry.terraform.io/providers/hashicorp/azurerm/latest/docs/resources/databricks_workspace), please make sure to add [depends_on attribute](../index.md#data-resources-and-authentication-is-not-configured-errors) in order to prevent _authentication is not configured for provider_ errors.
+
+Retrieves the settings of [databricks_job](../resources/job.md) by name or by id. Complements the feature of the [databricks_jobs](jobs.md) data source.
+
+## Example Usage
+
+Getting the existing cluster id of specific [databricks_job](../resources/job.md) by name or by id:
+
+```hcl
+data "databricks_job" "this" {
+  job_name = "My job"
+}
+
+output "cluster_id" {
+  value     = data.databricks_job.job_settings.existing_cluster_id
+  sensitive = false
+}
+```
+
+## Attribute Reference
+
+This data source exports the following attributes:
+
+* `job_id` - the id of [databricks_job](../resources/job.md) if the resource was matched by name.
+* `job_name` - the job name of [databricks_job](../resources/job.md) if the resource was matched by id.
+* `job_settings` - the job settings of [databricks_job](../resources/job.md).
+
+## Related Resources
+
+The following resources are used in the same context:
+
+* [databricks_jobs](jobs.md) data to get all jobs and their names from a workspace.
+* [databricks_job](../resources/job.md) to manage [Databricks Jobs](https://docs.databricks.com/jobs.html) to run non-interactive code in a [databricks_cluster](../resources/cluster.md).

jobs/acceptance/data_job_test.go

@@ -0,0 +1,66 @@
+package acceptance
+
+import (
+	"github.com/databricks/terraform-provider-databricks/internal/acceptance"
+
+	"testing"
+)
+
+func TestAccDataSourceQueryableJob(t *testing.T) {
+	acceptance.Test(t, []acceptance.Step{
+		{
+			Template: `
+			data "databricks_current_user" "me" {}
+			data "databricks_spark_version" "latest" {}
+			data "databricks_node_type" "smallest" {
+				local_disk = true
+			}
+
+			resource "databricks_notebook" "this" {
+				path     = "${data.databricks_current_user.me.home}/Terraform{var.RANDOM}"
+				language = "PYTHON"
+				content_base64 = base64encode(<<-EOT
+					# created from ${abspath(path.module)}
+					display(spark.range(10))
+					EOT
+				)
+			}
+
+			resource "databricks_job" "this" {
+				name = "job-datasource-acceptance-test"
+
+				job_cluster {
+					job_cluster_key = "j"
+					new_cluster {
+						num_workers   = 20
+						spark_version = data.databricks_spark_version.latest.id
+						node_type_id  = data.databricks_node_type.smallest.id
+					}
+				}
+
+				task {
+					task_key = "a"
+
+					new_cluster {
+						num_workers   = 1
+						spark_version = data.databricks_spark_version.latest.id
+						node_type_id  = data.databricks_node_type.smallest.id
+					}
+
+					notebook_task {
+						notebook_path = databricks_notebook.this.path
+					}
+				}
+
+			}
+
+			data "databricks_job" "this" {
+				job_name = databricks_job.this.name
+			}
+			
+			output "cluster_workers" {
+				value = data.databricks_job.this.job_settings[0].settings[0].new_cluster[0].num_workers
+            }`,
+		},
+	})
+}

jobs/data_job.go

@@ -0,0 +1,39 @@
+package jobs
+
+import (
+	"context"
+	"fmt"
+	"github.com/databricks/terraform-provider-databricks/common"
+	"github.com/hashicorp/terraform-plugin-sdk/v2/helper/schema"
+)
+
+func DataSourceJob() *schema.Resource {
+	type queryableJobData struct {
+		Id   string `json:"job_id,omitempty" tf:"computed"`
+		Name string `json:"job_name,omitempty" tf:"computed"`
+		Job  *Job   `json:"job_settings,omitempty" tf:"computed"`
+	}
+	return common.DataResource(queryableJobData{}, func(ctx context.Context, e any, c *common.DatabricksClient) error {
+		data := e.(*queryableJobData)
+		jobsAPI := NewJobsAPI(ctx, c)
+		list, err := jobsAPI.List()
+		if err != nil {
+			return err
+		}
+		for _, job := range list.Jobs {
+			currentJob := job // De-referencing the temp variable used by the loop
+			currentJobId := currentJob.ID()
+			currentJobName := currentJob.Settings.Name
+			if currentJobName == data.Name || currentJobId == data.Id {
+				data.Job = &currentJob
+				data.Name = currentJobName
+				data.Id = currentJobId
+				return nil // break the loop after we found the job
+			}
+		}
+		if data.Job == nil {
+			return fmt.Errorf("no job found with specified name or id")
+		}
+		return nil
+	})
+}

jobs/data_job_test.go

@@ -0,0 +1,82 @@
+package jobs
+
+import (
+	"github.com/databricks/terraform-provider-databricks/qa"
+	"testing"
+)
+
+func commonFixtures() []qa.HTTPFixture {
+	return []qa.HTTPFixture{
+		{
+			Method:   "GET",
+			Resource: "/api/2.0/jobs/list",
+			Response: JobList{
+				Jobs: []Job{
+					{
+						JobID: 123,
+						Settings: &JobSettings{
+							Name: "First",
+						},
+					},
+					{
+						JobID: 234,
+						Settings: &JobSettings{
+							Name: "Second",
+						},
+					},
+				},
+			},
+		},
+	}
+
+}
+func TestDataSourceQueryableJobMatchesId(t *testing.T) {
+	qa.ResourceFixture{
+		Fixtures:    commonFixtures(),
+		Resource:    DataSourceJob(),
+		Read:        true,
+		New:         true,
+		NonWritable: true,
+		HCL:         `job_id = "234"`,
+		ID:          "_",
+	}.ApplyAndExpectData(t, map[string]any{
+		"job_id":                         "234",
+		"job_settings.0.settings.0.name": "Second",
+	})
+}
+
+func TestDataSourceQueryableJobMatchesName(t *testing.T) {
+	qa.ResourceFixture{
+		Fixtures:    commonFixtures(),
+		Resource:    DataSourceJob(),
+		Read:        true,
+		NonWritable: true,
+		HCL:         `job_name = "First"`,
+		ID:          "_",
+	}.ApplyAndExpectData(t, map[string]any{
+		"job_id":                         "123",
+		"job_settings.0.settings.0.name": "First",
+	})
+}
+
+func TestDataSourceQueryableJobNoMatchName(t *testing.T) {
+	qa.ResourceFixture{
+		Fixtures:    commonFixtures(),
+		Resource:    DataSourceJob(),
+		Read:        true,
+		NonWritable: true,
+		HCL:         `job_name= "Third"`,
+		ID:          "_",
+	}.ExpectError(t, "no job found with specified name or id")
+}
+
+func TestDataSourceQueryableJobNoMatchId(t *testing.T) {
+	qa.ResourceFixture{
+		Fixtures:    commonFixtures(),
+		Resource:    DataSourceJob(),
+		Read:        true,
+		NonWritable: true,
+		HCL:         `job_id= "567"`,
+		ID:          "_",
+	}.ExpectError(t, "no job found with specified name or id")
+}

provider/provider.go

@@ -47,6 +47,7 @@ func DatabricksProvider() *schema.Provider {
 			"databricks_dbfs_file_paths":         storage.DataSourceDbfsFilePaths(),
 			"databricks_group":                   scim.DataSourceGroup(),
 			"databricks_jobs":                    jobs.DataSourceJobs(),
+			"databricks_job":                     jobs.DataSourceJob(),
 			"databricks_mws_workspaces":          mws.DataSourceMwsWorkspaces(),
 			"databricks_node_type":               clusters.DataSourceNodeType(),
 			"databricks_notebook":                workspace.DataSourceNotebook(),