feat: Add support to seed data when using RunBigQueryContainer

docs/modules/gcloud.md

@@ -17,7 +17,7 @@ go get github.com/testcontainers/testcontainers-go/modules/gcloud
 ## Usage example
 
 !!!info
-    By default, the all the emulators use `gcr.io/google.com/cloudsdktool/cloud-sdk:367.0.0-emulators` as the default Docker image, except for the BigQuery emulator, which uses `ghcr.io/goccy/bigquery-emulator:0.4.3`, and Spanner, which uses `gcr.io/cloud-spanner-emulator/emulator:1.4.0`.
+    By default, the all the emulators use `gcr.io/google.com/cloudsdktool/cloud-sdk:367.0.0-emulators` as the default Docker image, except for the BigQuery emulator, which uses `ghcr.io/goccy/bigquery-emulator:0.6.1`, and Spanner, which uses `gcr.io/cloud-spanner-emulator/emulator:1.4.0`.
 
 ### BigQuery
 
@@ -28,6 +28,17 @@ go get github.com/testcontainers/testcontainers-go/modules/gcloud
 
 It's important to set the `option.WithEndpoint()` option using the container's URI, as shown in the client example above.
 
+#### Data Yaml (Seed File)
+
+If you would like to do additional initialization in the BigQuery container, add a `data.yaml` file to the container request with the `WithDataYamlFile` function.
+Those files will be copied after the container is created but before it's started. The startup command then used will look like `--project test --data-from-yaml /data.yaml`.
+
+An example of a `data.yaml` file that seeds the BigQuery instance with datasets and tables is shown below:
+
+<!--codeinclude-->
+[Data Yaml content](../../modules/gcloud/testdata/data.yaml)
+<!--/codeinclude-->
+
 ### BigTable
 
 <!--codeinclude-->

modules/gcloud/bigquery.go

@@ -13,7 +13,7 @@ import (
 func RunBigQueryContainer(ctx context.Context, opts ...testcontainers.ContainerCustomizer) (*GCloudContainer, error) {
 	req := testcontainers.GenericContainerRequest{
 		ContainerRequest: testcontainers.ContainerRequest{
-			Image:        "ghcr.io/goccy/bigquery-emulator:0.4.3",
+			Image:        "ghcr.io/goccy/bigquery-emulator:0.6.1",
 			ExposedPorts: []string{"9050/tcp", "9060/tcp"},
 			WaitingFor:   wait.ForHTTP("/discovery/v1/apis/bigquery/v2/rest").WithPort("9050/tcp").WithStartupTimeout(time.Second * 5),
 		},
@@ -25,20 +25,20 @@ func RunBigQueryContainer(ctx context.Context, opts ...testcontainers.ContainerC
 		return nil, err
 	}
 
-	req.Cmd = []string{"--project", settings.ProjectID}
+	req.Cmd = append(req.Cmd, "--project", settings.ProjectID)
 
 	container, err := testcontainers.GenericContainer(ctx, req)
 	if err != nil {
 		return nil, err
 	}
 
-	spannerContainer, err := newGCloudContainer(ctx, 9050, container, settings)
+	bigqueryContainer, err := newGCloudContainer(ctx, 9050, container, settings)
 	if err != nil {
 		return nil, err
 	}
 
 	// always prepend http:// to the URI
-	spannerContainer.URI = "http://" + spannerContainer.URI
+	bigqueryContainer.URI = "http://" + bigqueryContainer.URI
 
-	return spannerContainer, nil
+	return bigqueryContainer, nil
 }

modules/gcloud/bigquery_test.go

@@ -5,6 +5,8 @@ import (
 	"errors"
 	"fmt"
 	"log"
+	"path/filepath"
+	"testing"
 
 	"cloud.google.com/go/bigquery"
 	"google.golang.org/api/iterator"
@@ -23,7 +25,7 @@ func ExampleRunBigQueryContainer() {
 
 	bigQueryContainer, err := gcloud.RunBigQueryContainer(
 		ctx,
-		testcontainers.WithImage("ghcr.io/goccy/bigquery-emulator:0.4.3"),
+		testcontainers.WithImage("ghcr.io/goccy/bigquery-emulator:0.6.1"),
 		gcloud.WithProjectID("bigquery-project"),
 	)
 	if err != nil {
@@ -78,8 +80,75 @@ func ExampleRunBigQueryContainer() {
 		}
 	}
 
-	fmt.Println(val)
+	fmt.Println(val[0])
+	// Output:
+	// 30
+}
+
+func TestBigQueryWithDataYamlFile(t *testing.T) {
+	ctx := context.Background()
+
+	absPath, err := filepath.Abs(filepath.Join(".", "testdata", "data.yaml"))
+	if err != nil {
+		log.Fatalf("failed to run container: %v", err)
+	}
+
+	bigQueryContainer, err := gcloud.RunBigQueryContainer(
+		ctx,
+		testcontainers.WithImage("ghcr.io/goccy/bigquery-emulator:0.6.1"),
+		gcloud.WithProjectID("test"),
+		gcloud.WithDataYamlFile(absPath),
+	)
+	if err != nil {
+		log.Fatalf("failed to run container: %v", err)
+	}
+
+	defer func() {
+		if err := bigQueryContainer.Terminate(ctx); err != nil {
+			log.Fatalf("failed to terminate container: %v", err)
+		}
+	}()
+
+	projectID := bigQueryContainer.Settings.ProjectID
+
+	opts := []option.ClientOption{
+		option.WithEndpoint(bigQueryContainer.URI),
+		option.WithGRPCDialOption(grpc.WithTransportCredentials(insecure.NewCredentials())),
+		option.WithoutAuthentication(),
+		internaloption.SkipDialSettingsValidation(),
+	}
+
+	client, err := bigquery.NewClient(ctx, projectID, opts...)
+	if err != nil {
+		log.Fatalf("failed to create bigquery client: %v", err) // nolint:gocritic
+	}
+	defer client.Close()
+
+	selectQuery := client.Query("SELECT * FROM dataset1.table_a where name = @name")
+	selectQuery.QueryConfig.Parameters = []bigquery.QueryParameter{
+		{Name: "name", Value: "bob"},
+	}
+	it, err := selectQuery.Read(ctx)
+	if err != nil {
+		log.Fatalf("failed to read query: %v", err)
+	}
+
+	var val []bigquery.Value
+	for {
+		err := it.Next(&val)
+		if errors.Is(err, iterator.Done) {
+			break
+		}
+		if err != nil {
+			log.Fatalf("failed to iterate: %v", err)
+		}
+	}
 
 	// Output:
 	// [30]
+	expectedValue := int64(30)
+	actualValue := val[0]
+	if expectedValue != actualValue {
+		t.Errorf("BigQuery value didn't match. \nExpected %v, \nbut got: %v", expectedValue, actualValue)
+	}
 }

modules/gcloud/gcloud.go

@@ -41,12 +41,14 @@ func newGCloudContainer(ctx context.Context, port int, c testcontainers.Containe
 }
 
 type options struct {
-	ProjectID string
+	ProjectID    string
+	DataYamlFile string
 }
 
 func defaultOptions() options {
 	return options{
-		ProjectID: defaultProjectID,
+		ProjectID:    defaultProjectID,
+		DataYamlFile: "/data.yaml",
 	}
 }
 
@@ -69,6 +71,22 @@ func WithProjectID(projectID string) Option {
 	}
 }
 
+// WithDataYamlFile seeds the Bigquery project for the GCloud container.
+func WithDataYamlFile(dataYamlFile string) testcontainers.CustomizeRequestOption {
+	return func(req *testcontainers.GenericContainerRequest) error {
+		dataFile := testcontainers.ContainerFile{
+			HostFilePath:      dataYamlFile,
+			ContainerFilePath: "/data.yaml",
+			FileMode:          0o755,
+		}
+
+		req.Files = append(req.Files, dataFile)
+		req.Cmd = append(req.Cmd, "--data-from-yaml", "/data.yaml")
+
+		return nil
+	}
+}
+
 // applyOptions applies the options to the container request and returns the settings.
 func applyOptions(req *testcontainers.GenericContainerRequest, opts []testcontainers.ContainerCustomizer) (options, error) {
 	settings := defaultOptions()

modules/gcloud/go.mod

@@ -72,6 +72,7 @@ require (
 	github.com/shirou/gopsutil/v3 v3.23.12 // indirect
 	github.com/shoenig/go-m1cpu v0.1.6 // indirect
 	github.com/sirupsen/logrus v1.9.3 // indirect
+	github.com/stretchr/objx v0.5.2 // indirect
 	github.com/tklauser/go-sysconf v0.3.12 // indirect
 	github.com/tklauser/numcpus v0.6.1 // indirect
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect

modules/gcloud/go.sum

@@ -191,8 +191,9 @@ github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ
 github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
-github.com/stretchr/objx v0.5.0 h1:1zr/of2m5FGMsad5YfcqgdqdWrIhu+EBEJRhR1U7z/c=
 github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
+github.com/stretchr/objx v0.5.2 h1:xuMeJ0Sdp5ZMRXx/aWO6RZxdr3beISkG5/G/aIRr3pY=
+github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=

modules/gcloud/testdata/data.yaml

@@ -0,0 +1,20 @@
+projects:
+  - id: test
+    datasets:
+      - id: dataset1
+        tables:
+          - id: table_a
+            columns:
+              - name: id
+                type: INTEGER
+              - name: name
+                type: STRING
+              - name: createdAt
+                type: TIMESTAMP
+            data:
+              - id: 1
+                name: alice
+                createdAt: "2022-10-21T00:00:00"
+              - id: 30
+                name: bob
+                createdAt: "2022-10-21T00:00:00"