use of com.google.cloud.bigquery.storage.v1beta2.JsonStreamWriter in project java-bigquerystorage by googleapis.
the class WriteToDefaultStream method writeToDefaultStream.
public static void writeToDefaultStream(String projectId, String datasetName, String tableName) throws DescriptorValidationException, InterruptedException, IOException {
BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();
Table table = bigquery.getTable(datasetName, tableName);
TableName parentTable = TableName.of(projectId, datasetName, tableName);
Schema schema = table.getDefinition().getSchema();
TableSchema tableSchema = BqToBqStorageSchemaConverter.convertTableSchema(schema);
// https://googleapis.dev/java/google-cloud-bigquerystorage/latest/com/google/cloud/bigquery/storage/v1/JsonStreamWriter.html
try (JsonStreamWriter writer = JsonStreamWriter.newBuilder(parentTable.toString(), tableSchema).build()) {
// much writes as possible. Creating a writer for just one write is an antipattern.
for (int i = 0; i < 2; i++) {
// Create a JSON object that is compatible with the table schema.
JSONArray jsonArr = new JSONArray();
for (int j = 0; j < 10; j++) {
JSONObject record = new JSONObject();
record.put("test_string", String.format("record %03d-%03d", i, j));
jsonArr.put(record);
}
ApiFuture<AppendRowsResponse> future = writer.append(jsonArr);
AppendRowsResponse response = future.get();
}
System.out.println("Appended records successfully.");
} catch (ExecutionException e) {
// If the wrapped exception is a StatusRuntimeException, check the state of the operation.
// If the state is INTERNAL, CANCELLED, or ABORTED, you can retry. For more information, see:
// https://grpc.github.io/grpc-java/javadoc/io/grpc/StatusRuntimeException.html
System.out.println("Failed to append records. \n" + e.toString());
}
}
use of com.google.cloud.bigquery.storage.v1beta2.JsonStreamWriter in project dataproc-templates by GoogleCloudPlatform.
the class PubSubToBQ method writeToBQ.
public static void writeToBQ(JavaDStream<SparkPubsubMessage> pubSubStream, String outputProjectID, String pubSubBQOutputDataset, String PubSubBQOutputTable, Integer batchSize) {
pubSubStream.foreachRDD(new VoidFunction<JavaRDD<SparkPubsubMessage>>() {
@Override
public void call(JavaRDD<SparkPubsubMessage> sparkPubsubMessageJavaRDD) throws Exception {
sparkPubsubMessageJavaRDD.foreachPartition(new VoidFunction<Iterator<SparkPubsubMessage>>() {
@Override
public void call(Iterator<SparkPubsubMessage> sparkPubsubMessageIterator) throws Exception {
BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();
Table table = bigquery.getTable(pubSubBQOutputDataset, PubSubBQOutputTable);
TableName parentTable = TableName.of(outputProjectID, pubSubBQOutputDataset, PubSubBQOutputTable);
Schema schema = table.getDefinition().getSchema();
JsonStreamWriter writer = JsonStreamWriter.newBuilder(parentTable.toString(), schema).build();
JSONArray jsonArr = new JSONArray();
while (sparkPubsubMessageIterator.hasNext()) {
SparkPubsubMessage message = sparkPubsubMessageIterator.next();
JSONObject record = new JSONObject(new String(message.getData()));
jsonArr.put(record);
if (jsonArr.length() == batchSize) {
ApiFuture<AppendRowsResponse> future = writer.append(jsonArr);
AppendRowsResponse response = future.get();
jsonArr = new JSONArray();
}
}
if (jsonArr.length() > 0) {
ApiFuture<AppendRowsResponse> future = writer.append(jsonArr);
AppendRowsResponse response = future.get();
}
writer.close();
}
});
}
});
}
use of com.google.cloud.bigquery.storage.v1beta2.JsonStreamWriter in project java-bigquerystorage by googleapis.
the class WritePendingStream method writePendingStream.
public static void writePendingStream(String projectId, String datasetName, String tableName) throws DescriptorValidationException, InterruptedException, IOException {
try (BigQueryWriteClient client = BigQueryWriteClient.create()) {
// Initialize a write stream for the specified table.
// For more information on WriteStream.Type, see:
// https://googleapis.dev/java/google-cloud-bigquerystorage/latest/com/google/cloud/bigquery/storage/v1/WriteStream.Type.html
WriteStream stream = WriteStream.newBuilder().setType(WriteStream.Type.PENDING).build();
TableName parentTable = TableName.of(projectId, datasetName, tableName);
CreateWriteStreamRequest createWriteStreamRequest = CreateWriteStreamRequest.newBuilder().setParent(parentTable.toString()).setWriteStream(stream).build();
WriteStream writeStream = client.createWriteStream(createWriteStreamRequest);
// https://googleapis.dev/java/google-cloud-bigquerystorage/latest/com/google/cloud/bigquery/storage/v1beta2/JsonStreamWriter.html
try (JsonStreamWriter writer = JsonStreamWriter.newBuilder(writeStream.getName(), writeStream.getTableSchema()).build()) {
// Write two batches to the stream, each with 10 JSON records.
for (int i = 0; i < 2; i++) {
// Create a JSON object that is compatible with the table schema.
JSONArray jsonArr = new JSONArray();
for (int j = 0; j < 10; j++) {
JSONObject record = new JSONObject();
record.put("col1", String.format("batch-record %03d-%03d", i, j));
jsonArr.put(record);
}
ApiFuture<AppendRowsResponse> future = writer.append(jsonArr);
AppendRowsResponse response = future.get();
}
FinalizeWriteStreamResponse finalizeResponse = client.finalizeWriteStream(writeStream.getName());
System.out.println("Rows written: " + finalizeResponse.getRowCount());
}
// Commit the streams.
BatchCommitWriteStreamsRequest commitRequest = BatchCommitWriteStreamsRequest.newBuilder().setParent(parentTable.toString()).addWriteStreams(writeStream.getName()).build();
BatchCommitWriteStreamsResponse commitResponse = client.batchCommitWriteStreams(commitRequest);
// If the response does not have a commit time, it means the commit operation failed.
if (commitResponse.hasCommitTime() == false) {
for (StorageError err : commitResponse.getStreamErrorsList()) {
System.out.println(err.getErrorMessage());
}
throw new RuntimeException("Error committing the streams");
}
System.out.println("Appended and committed records successfully.");
} catch (ExecutionException e) {
// If the wrapped exception is a StatusRuntimeException, check the state of the operation.
// If the state is INTERNAL, CANCELLED, or ABORTED, you can retry. For more information, see:
// https://grpc.github.io/grpc-java/javadoc/io/grpc/StatusRuntimeException.html
System.out.println(e);
}
}
use of com.google.cloud.bigquery.storage.v1beta2.JsonStreamWriter in project java-bigquerystorage by googleapis.
the class AppendCompleteCallback method writeToDefaultStream.
// writeToDefaultStream: Writes records from the source file to the destination table.
public static void writeToDefaultStream(String projectId, String datasetName, String tableName, String dataFile) throws DescriptorValidationException, InterruptedException, IOException {
BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();
// Get the schema of the destination table and convert to the equivalent BigQueryStorage type.
Table table = bigquery.getTable(datasetName, tableName);
Schema schema = table.getDefinition().getSchema();
TableSchema tableSchema = BqToBqStorageSchemaConverter.convertTableSchema(schema);
// Use the JSON stream writer to send records in JSON format.
TableName parentTable = TableName.of(projectId, datasetName, tableName);
try (JsonStreamWriter writer = JsonStreamWriter.newBuilder(parentTable.toString(), tableSchema).build()) {
// Read JSON data from the source file and send it to the Write API.
BufferedReader reader = new BufferedReader(new FileReader(dataFile));
String line = reader.readLine();
while (line != null) {
// As a best practice, send batches of records, instead of single records at a time.
JSONArray jsonArr = new JSONArray();
for (int i = 0; i < 100; i++) {
JSONObject record = new JSONObject(line);
jsonArr.put(record);
line = reader.readLine();
if (line == null) {
break;
}
}
// batch
ApiFuture<AppendRowsResponse> future = writer.append(jsonArr);
// The append method is asynchronous. Rather than waiting for the method to complete,
// which can hurt performance, register a completion callback and continue streaming.
ApiFutures.addCallback(future, new AppendCompleteCallback(), MoreExecutors.directExecutor());
}
}
}
use of com.google.cloud.bigquery.storage.v1beta2.JsonStreamWriter in project java-bigquerystorage by googleapis.
the class WriteBufferedStream method writeBufferedStream.
public static void writeBufferedStream(String projectId, String datasetName, String tableName) throws DescriptorValidationException, InterruptedException, IOException {
try (BigQueryWriteClient client = BigQueryWriteClient.create()) {
// Initialize a write stream for the specified table.
// For more information on WriteStream.Type, see:
// https://googleapis.dev/java/google-cloud-bigquerystorage/latest/com/google/cloud/bigquery/storage/v1/WriteStream.Type.html
WriteStream stream = WriteStream.newBuilder().setType(WriteStream.Type.BUFFERED).build();
TableName parentTable = TableName.of(projectId, datasetName, tableName);
CreateWriteStreamRequest createWriteStreamRequest = CreateWriteStreamRequest.newBuilder().setParent(parentTable.toString()).setWriteStream(stream).build();
WriteStream writeStream = client.createWriteStream(createWriteStreamRequest);
// https://googleapis.dev/java/google-cloud-bigquerystorage/latest/com/google/cloud/bigquery/storage/v1beta2/JsonStreamWriter.html
try (JsonStreamWriter writer = JsonStreamWriter.newBuilder(writeStream.getName(), writeStream.getTableSchema()).build()) {
// Write two batches to the stream, each with 10 JSON records.
for (int i = 0; i < 2; i++) {
JSONArray jsonArr = new JSONArray();
for (int j = 0; j < 10; j++) {
// Create a JSON object that is compatible with the table schema.
JSONObject record = new JSONObject();
record.put("col1", String.format("buffered-record %03d", i));
jsonArr.put(record);
}
ApiFuture<AppendRowsResponse> future = writer.append(jsonArr);
AppendRowsResponse response = future.get();
}
// Flush the buffer.
FlushRowsRequest flushRowsRequest = FlushRowsRequest.newBuilder().setWriteStream(writeStream.getName()).setOffset(// Advance the cursor to the latest record.
Int64Value.of(10 * 2 - 1)).build();
FlushRowsResponse flushRowsResponse = client.flushRows(flushRowsRequest);
// You can continue to write to the stream after flushing the buffer.
}
// Finalize the stream after use.
FinalizeWriteStreamRequest finalizeWriteStreamRequest = FinalizeWriteStreamRequest.newBuilder().setName(writeStream.getName()).build();
client.finalizeWriteStream(finalizeWriteStreamRequest);
System.out.println("Appended and committed records successfully.");
} catch (ExecutionException e) {
// If the wrapped exception is a StatusRuntimeException, check the state of the operation.
// If the state is INTERNAL, CANCELLED, or ABORTED, you can retry. For more information, see:
// https://grpc.github.io/grpc-java/javadoc/io/grpc/StatusRuntimeException.html
System.out.println(e);
}
}
Aggregations