[Data Validation] Add Terraform Template

v2/gcs-spanner-dv/terraform/GCS_Spanner_Data_Validator/dataflow_job.tf

@@ -0,0 +1,292 @@
+
+
+# Autogenerated file. DO NOT EDIT.
+#
+# Copyright (C) 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License"); you may not
+# use this file except in compliance with the License. You may obtain a copy of
+# the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+# License for the specific language governing permissions and limitations under
+# the License.
+#
+
+
+variable "on_delete" {
+  type        = string
+  description = "One of \"drain\" or \"cancel\". Specifies behavior of deletion during terraform destroy."
+}
+
+variable "project" {
+  type        = string
+  description = "The Google Cloud Project ID within which this module provisions resources."
+}
+
+variable "region" {
+  type        = string
+  description = "The region in which the created job should run."
+}
+
+variable "gcsInputDirectory" {
+  type = string
+  description = "This directory is used to read the AVRO files of the records read from source. For example, `gs://your-bucket/your-path`"
+  default = null
+}
+
+variable "projectId" {
+  type = string
+  description = "This is the name of the Cloud Spanner project."
+  default = null
+}
+
+variable "spannerHost" {
+  type = string
+  description = "The Cloud Spanner endpoint to call in the template. For example, `https://batch-spanner.googleapis.com`. Defaults to: https://batch-spanner.googleapis.com."
+  default = null
+}
+
+variable "instanceId" {
+  type = string
+  description = "The destination Cloud Spanner instance."
+
+}
+
+variable "databaseId" {
+  type = string
+  description = "The destination Cloud Spanner database."
+
+}
+
+variable "spannerPriority" {
+  type = string
+  description = "The request priority for Cloud Spanner calls. The value must be one of: [`HIGH`,`MEDIUM`,`LOW`]. Defaults to `HIGH`."
+  default = null
+}
+
+variable "sessionFilePath" {
+  type = string
+  description = "Session file path in Cloud Storage that contains mapping information from Spanner Migration Tool. Defaults to empty."
+  default = null
+}
+
+variable "schemaOverridesFilePath" {
+  type = string
+  description = "A file which specifies the table and the column name overrides from source to spanner. Defaults to empty."
+  default = null
+}
+
+variable "tableOverrides" {
+  type = string
+  description = "These are the table name overrides from source to spanner. They are written in thefollowing format: [{SourceTableName1, SpannerTableName1}, {SourceTableName2, SpannerTableName2}]This example shows mapping Singers table to Vocalists and Albums table to Records. For example, `[{Singers, Vocalists}, {Albums, Records}]`. Defaults to empty."
+  default = null
+}
+
+variable "columnOverrides" {
+  type = string
+  description = "These are the column name overrides from source to spanner. They are written in thefollowing format: [{SourceTableName1.SourceColumnName1, SourceTableName1.SpannerColumnName1}, {SourceTableName2.SourceColumnName1, SourceTableName2.SpannerColumnName1}]Note that the SourceTableName should remain the same in both the source and spanner pair. To override table names, use tableOverrides.The example shows mapping SingerName to TalentName and AlbumName to RecordName in Singers and Albums table respectively. For example, `[{Singers.SingerName, Singers.TalentName}, {Albums.AlbumName, Albums.RecordName}]`. Defaults to empty."
+  default = null
+}
+
+variable "bigQueryDataset" {
+  type = string
+  description = "The BigQuery dataset ID where the validation results will be stored. For example, `validation_report_dataset`"
+
+}
+
+variable "runId" {
+  type = string
+  description = "A unique identifier for the validation run. If not provided, the Dataflow Job Name will be used. For example, `run_20230101_120000`"
+  default = null
+}
+
+variable "transformationJarPath" {
+  type = string
+  description = "Custom jar location in Cloud Storage that contains the custom transformation logic for processing records. Defaults to empty."
+  default = null
+}
+
+variable "transformationClassName" {
+  type = string
+  description = "Fully qualified class name having the custom transformation logic. It is a mandatory field in case transformationJarPath is specified. Defaults to empty."
+  default = null
+}
+
+variable "transformationCustomParameters" {
+  type = string
+  description = "String containing any custom parameters to be passed to the custom transformation class. Defaults to empty."
+  default = null
+}
+
+
+provider "google" {
+    project = var.project
+}
+
+provider "google-beta" {
+    project = var.project
+}
+
+variable "additional_experiments" {
+	type = set(string)
+	description = "List of experiments that should be used by the job. An example value is  'enable_stackdriver_agent_metrics'."
+	default = null
+}
+
+variable "autoscaling_algorithm" {
+	type = string
+	description = "The algorithm to use for autoscaling"
+	default = null
+}
+
+variable "enable_streaming_engine" {
+	type = bool
+	description = "Indicates if the job should use the streaming engine feature."
+	default = null
+}
+
+variable "ip_configuration" {
+	type = string
+	description = "The configuration for VM IPs. Options are 'WORKER_IP_PUBLIC' or 'WORKER_IP_PRIVATE'."
+	default = null
+}
+
+variable "kms_key_name" {
+	type = string
+	description = "The name for the Cloud KMS key for the job. Key format is: projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY"
+	default = null
+}
+
+variable "labels" {
+	type = map(string)
+	description = "User labels to be specified for the job. Keys and values should follow the restrictions specified in the labeling restrictions page. NOTE: This field is non-authoritative, and will only manage the labels present in your configuration.				Please refer to the field 'effective_labels' for all of the labels present on the resource."
+	default = null
+}
+
+variable "launcher_machine_type" {
+	type = string
+	description = "The machine type to use for launching the job. The default is n1-standard-1."
+	default = null
+}
+
+variable "machine_type" {
+	type = string
+	description = "The machine type to use for the job."
+	default = null
+}
+
+variable "max_workers" {
+	type = number
+	description = "The maximum number of Google Compute Engine instances to be made available to your pipeline during execution, from 1 to 1000."
+	default = null
+}
+
+variable "name" {
+	type = string
+}
+
+variable "network" {
+	type = string
+	description = "The network to which VMs will be assigned. If it is not provided, 'default' will be used."
+	default = null
+}
+
+variable "num_workers" {
+	type = number
+	description = "The initial number of Google Compute Engine instances for the job."
+	default = null
+}
+
+variable "sdk_container_image" {
+	type = string
+	description = "Docker registry location of container image to use for the 'worker harness. Default is the container for the version of the SDK. Note this field is only valid for portable pipelines."
+	default = null
+}
+
+variable "service_account_email" {
+	type = string
+	description = "The Service Account email used to create the job."
+	default = null
+}
+
+variable "skip_wait_on_job_termination" {
+	type = bool
+	description = "If true, treat DRAINING and CANCELLING as terminal job states and do not wait for further changes before removing from terraform state and moving on. WARNING: this will lead to job name conflicts if you do not ensure that the job names are different, e.g. by embedding a release ID or by using a random_id."
+	default = null
+}
+
+variable "staging_location" {
+	type = string
+	description = "The Cloud Storage path to use for staging files. Must be a valid Cloud Storage URL, beginning with gs://."
+	default = null
+}
+
+variable "subnetwork" {
+	type = string
+	description = "The subnetwork to which VMs will be assigned. Should be of the form 'regions/REGION/subnetworks/SUBNETWORK'."
+	default = null
+}
+
+variable "temp_location" {
+	type = string
+	description = "The Cloud Storage path to use for temporary files. Must be a valid Cloud Storage URL, beginning with gs://."
+	default = null
+}
+
+resource "google_project_service" "required" {
+    service = "dataflow.googleapis.com"
+    disable_on_destroy = false
+}
+
+resource "google_dataflow_flex_template_job" "generated" {
+    depends_on = [google_project_service.required]
+    provider = google-beta
+    container_spec_gcs_path = "gs://dataflow-templates-${var.region}/latest/flex/GCS_Spanner_Data_Validator"
+    parameters = {
+        gcsInputDirectory = var.gcsInputDirectory
+        projectId = var.projectId
+        spannerHost = var.spannerHost
+        instanceId = var.instanceId
+        databaseId = var.databaseId
+        spannerPriority = var.spannerPriority
+        sessionFilePath = var.sessionFilePath
+        schemaOverridesFilePath = var.schemaOverridesFilePath
+        tableOverrides = var.tableOverrides
+        columnOverrides = var.columnOverrides
+        bigQueryDataset = var.bigQueryDataset
+        runId = var.runId
+        transformationJarPath = var.transformationJarPath
+        transformationClassName = var.transformationClassName
+        transformationCustomParameters = var.transformationCustomParameters
+    }
+
+	additional_experiments = var.additional_experiments
+	autoscaling_algorithm = var.autoscaling_algorithm
+	enable_streaming_engine = var.enable_streaming_engine
+	ip_configuration = var.ip_configuration
+	kms_key_name = var.kms_key_name
+	labels = var.labels
+	launcher_machine_type = var.launcher_machine_type
+	machine_type = var.machine_type
+	max_workers = var.max_workers
+	name = var.name
+	network = var.network
+	num_workers = var.num_workers
+	sdk_container_image = var.sdk_container_image
+	service_account_email = var.service_account_email
+	skip_wait_on_job_termination = var.skip_wait_on_job_termination
+	staging_location = var.staging_location
+	subnetwork = var.subnetwork
+	temp_location = var.temp_location
+    region = var.region
+}
+
+output "dataflow_job_url" {
+    value = "https://console.cloud.google.com/dataflow/jobs/${var.region}/${google_dataflow_flex_template_job.generated.job_id}"
+}
+