add support for delta lake for big tables (#11215) (#18915)

[upstream:c015e3ff8450ee011bb290f13683991e18ecb109]

Signed-off-by: Modular Magician <[email protected]>

Author: modular-magician

.changelog/11215.txt

@@ -0,0 +1,3 @@
+```release-note:enhancement
+bigquery: added support for value `DELTA_LAKE` to `source_format` in `google_bigquery_table` resource
+```

google/services/bigquery/resource_bigquery_table.go

@@ -517,7 +517,7 @@ func ResourceBigQueryTable() *schema.Resource {
 							Optional:    true,
 							Description: `Please see sourceFormat under ExternalDataConfiguration in Bigquery's public API documentation (https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#externaldataconfiguration) for supported formats. To use "GOOGLE_SHEETS" the scopes must include "googleapis.com/auth/drive.readonly".`,
 							ValidateFunc: validation.StringInSlice([]string{
-								"CSV", "GOOGLE_SHEETS", "NEWLINE_DELIMITED_JSON", "AVRO", "ICEBERG", "DATASTORE_BACKUP", "PARQUET", "ORC", "BIGTABLE",
+								"CSV", "GOOGLE_SHEETS", "NEWLINE_DELIMITED_JSON", "AVRO", "ICEBERG", "DATASTORE_BACKUP", "PARQUET", "ORC", "BIGTABLE", "DELTA_LAKE",
 							}, false),
 						},
 						// SourceURIs [Required] The fully-qualified URIs that point to your data in Google Cloud.

google/services/bigquery/resource_bigquery_table_test.go

@@ -642,6 +642,26 @@ func TestAccBigQueryTable_MaterializedView_NonIncremental_basic(t *testing.T) {
 	})
 }
 
+func TestAccBigQueryExternalDataTable_deltaLake(t *testing.T) {
+	t.Parallel()
+
+	bucketName := acctest.TestBucketName(t)
+
+	datasetID := fmt.Sprintf("tf_test_%s", acctest.RandString(t, 10))
+	tableID := fmt.Sprintf("tf_test_%s", acctest.RandString(t, 10))
+
+	acctest.VcrTest(t, resource.TestCase{
+		PreCheck:                 func() { acctest.AccTestPreCheck(t) },
+		ProtoV5ProviderFactories: acctest.ProtoV5ProviderFactories(t),
+		CheckDestroy:             testAccCheckBigQueryTableDestroyProducer(t),
+		Steps: []resource.TestStep{
+			{
+				Config: testAccBigQueryTableFromGCSDeltaLake(datasetID, tableID, bucketName),
+			},
+		},
+	})
+}
+
 func TestAccBigQueryExternalDataTable_parquet(t *testing.T) {
 	t.Parallel()
 
@@ -2644,6 +2664,44 @@ resource "google_bigquery_table" "test" {
 `, connectionID, datasetID, bucketName, objectName, tableID, metadataCacheMode, maxStaleness)
 }
 
+func testAccBigQueryTableFromGCSDeltaLake(datasetID, tableID, bucketName string) string {
+	return fmt.Sprintf(`
+resource "google_bigquery_dataset" "test" {
+  dataset_id = "%s"
+}
+
+resource "google_storage_bucket" "test" {
+  name          = "%s"
+  location      = "US"
+  force_destroy = true
+}
+
+# Setup Empty Delta Lake table in Bucket.
+
+// Upload Metadata File.
+resource "google_storage_bucket_object" "metadata" {
+	name    = "_delta_log/00000000000000000000.json"
+	source = "./test-fixtures/simple/metadata/00000000000000000000.json"
+	bucket = google_storage_bucket.test.name
+}
+
+resource "google_bigquery_table" "test" {
+  deletion_protection = false
+  table_id   = "%s"
+  dataset_id = google_bigquery_dataset.test.dataset_id
+  external_data_configuration {
+    autodetect    = true
+    source_format = "DELTA_LAKE"
+	reference_file_schema_uri = "gs://${google_storage_bucket.test.name}/${google_storage_bucket_object.metadata.name}"
+
+    source_uris = [
+      "gs://${google_storage_bucket.test.name}/*",
+    ]
+  }
+}
+`, datasetID, bucketName, tableID)
+}
+
 func testAccBigQueryTableFromGCSParquet(datasetID, tableID, bucketName, objectName string) string {
 	return fmt.Sprintf(`
 resource "google_bigquery_dataset" "test" {

google/services/bigquery/test-fixtures/simple/metadata/00000000000000000000.json

@@ -0,0 +1,6 @@
+{"commitInfo":{"timestamp":1706278148531,"operation":"WRITE","operationParameters":{"mode":"Overwrite","partitionBy":"[\"country\"]"},"isolationLevel":"Serializable","isBlindAppend":false,"operationMetrics":{"numFiles":"3","numOutputRows":"5","numOutputBytes":"3045"},"engineInfo":"Apache-Spark/3.4.0 Delta-Lake/2.4.0","txnId":"1cbc9537-63eb-4799-8647-2d947ae8fa41"}}
+{"protocol":{"minReaderVersion":1,"minWriterVersion":2}}
+{"metaData":{"id":"1f110132-a652-4be9-815e-348f294515cf","format":{"provider":"parquet","options":{}},"schemaString":"{\"type\":\"struct\",\"fields\":[{\"name\":\"first_name\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"last_name\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"country\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"continent\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}}]}","partitionColumns":["country"],"configuration":{},"createdTime":1706278146762}}
+{"add":{"path":"country=Argentina/part-00000-8d0390a3-f797-4265-b9c2-da1c941680a3.c000.snappy.parquet","partitionValues":{"country":"Argentina"},"size":1018,"modificationTime":1706278148083,"dataChange":true,"stats":"{\"numRecords\":1,\"minValues\":{\"first_name\":\"Ernesto\",\"last_name\":\"Guevara\",\"continent\":\"NaN\"},\"maxValues\":{\"first_name\":\"Ernesto\",\"last_name\":\"Guevara\",\"continent\":\"NaN\"},\"nullCount\":{\"first_name\":0,\"last_name\":0,\"continent\":0}}"}}
+{"add":{"path":"country=China/part-00000-88fba1af-b28d-4303-9c85-9a97be631d40.c000.snappy.parquet","partitionValues":{"country":"China"},"size":1002,"modificationTime":1706278148138,"dataChange":true,"stats":"{\"numRecords\":2,\"minValues\":{\"first_name\":\"Bruce\",\"last_name\":\"Lee\",\"continent\":\"Asia\"},\"maxValues\":{\"first_name\":\"Jack\",\"last_name\":\"Ma\",\"continent\":\"Asia\"},\"nullCount\":{\"first_name\":0,\"last_name\":0,\"continent\":0}}"}}
+{"add":{"path":"country=Germany/part-00000-030076e1-5ec9-47c2-830a-1569f823b6ee.c000.snappy.parquet","partitionValues":{"country":"Germany"},"size":1025,"modificationTime":1706278148185,"dataChange":true,"stats":"{\"numRecords\":2,\"minValues\":{\"first_name\":\"Soraya\",\"last_name\":\"Jala\",\"continent\":\"NaN\"},\"maxValues\":{\"first_name\":\"Wolfgang\",\"last_name\":\"Manche\",\"continent\":\"NaN\"},\"nullCount\":{\"first_name\":0,\"last_name\":0,\"continent\":0}}"}}