use of com.google.bigtable.repackaged.com.google.bigtable.v2.ReadRowsRequest in project java-bigquerystorage by googleapis.
the class ReadRowsRetryTest method multipleRetryTestWithNonZeroInitialOffset.
@Test
public void multipleRetryTestWithNonZeroInitialOffset() {
ReadRowsRequest request = RpcExpectation.createRequest("fake-stream", 17);
service.expectations.add(RpcExpectation.create().expectRequest("fake-stream", 17).respondWithNumberOfRows(5).respondWithStatus(Code.UNAVAILABLE));
service.expectations.add(RpcExpectation.create().expectRequest("fake-stream", 22).respondWithNumberOfRows(10).respondWithNumberOfRows(7).respondWithStatus(Code.UNAVAILABLE));
service.expectations.add(RpcExpectation.create().expectRequest("fake-stream", 39).respondWithNumberOfRows(3));
Assert.assertEquals(25, getRowCount(request));
}
use of com.google.bigtable.repackaged.com.google.bigtable.v2.ReadRowsRequest in project java-bigquerystorage by googleapis.
the class StorageArrowSample method main.
public static void main(String... args) throws Exception {
// Sets your Google Cloud Platform project ID.
// String projectId = "YOUR_PROJECT_ID";
String projectId = args[0];
Integer snapshotMillis = null;
if (args.length > 1) {
snapshotMillis = Integer.parseInt(args[1]);
}
try (BigQueryReadClient client = BigQueryReadClient.create()) {
String parent = String.format("projects/%s", projectId);
// This example uses baby name data from the public datasets.
String srcTable = String.format("projects/%s/datasets/%s/tables/%s", "bigquery-public-data", "usa_names", "usa_1910_current");
// We specify the columns to be projected by adding them to the selected fields,
// and set a simple filter to restrict which rows are transmitted.
TableReadOptions options = TableReadOptions.newBuilder().addSelectedFields("name").addSelectedFields("number").addSelectedFields("state").setRowRestriction("state = \"WA\"").build();
// Start specifying the read session we want created.
ReadSession.Builder sessionBuilder = ReadSession.newBuilder().setTable(srcTable).setDataFormat(DataFormat.ARROW).setReadOptions(options);
// Optionally specify the snapshot time. When unspecified, snapshot time is "now".
if (snapshotMillis != null) {
Timestamp t = Timestamp.newBuilder().setSeconds(snapshotMillis / 1000).setNanos((int) ((snapshotMillis % 1000) * 1000000)).build();
TableModifiers modifiers = TableModifiers.newBuilder().setSnapshotTime(t).build();
sessionBuilder.setTableModifiers(modifiers);
}
// Begin building the session creation request.
CreateReadSessionRequest.Builder builder = CreateReadSessionRequest.newBuilder().setParent(parent).setReadSession(sessionBuilder).setMaxStreamCount(1);
ReadSession session = client.createReadSession(builder.build());
// Setup a simple reader and start a read session.
try (SimpleRowReader reader = new SimpleRowReader(session.getArrowSchema())) {
// Assert that there are streams available in the session. An empty table may not have
// data available. If no sessions are available for an anonymous (cached) table, consider
// writing results of a query to a named table rather than consuming cached results
// directly.
Preconditions.checkState(session.getStreamsCount() > 0);
// Use the first stream to perform reading.
String streamName = session.getStreams(0).getName();
ReadRowsRequest readRowsRequest = ReadRowsRequest.newBuilder().setReadStream(streamName).build();
// Process each block of rows as they arrive and decode using our simple row reader.
ServerStream<ReadRowsResponse> stream = client.readRowsCallable().call(readRowsRequest);
for (ReadRowsResponse response : stream) {
Preconditions.checkState(response.hasArrowRecordBatch());
reader.processRows(response.getArrowRecordBatch());
}
}
}
}
use of com.google.bigtable.repackaged.com.google.bigtable.v2.ReadRowsRequest in project java-bigquerystorage by googleapis.
the class StorageSample method main.
public static void main(String... args) throws Exception {
// Sets your Google Cloud Platform project ID.
// String projectId = "YOUR_PROJECT_ID";
String projectId = args[0];
Integer snapshotMillis = null;
if (args.length > 1) {
snapshotMillis = Integer.parseInt(args[1]);
}
try (BigQueryReadClient client = BigQueryReadClient.create()) {
String parent = String.format("projects/%s", projectId);
// This example uses baby name data from the public datasets.
String srcTable = String.format("projects/%s/datasets/%s/tables/%s", "bigquery-public-data", "usa_names", "usa_1910_current");
// We specify the columns to be projected by adding them to the selected fields,
// and set a simple filter to restrict which rows are transmitted.
TableReadOptions options = TableReadOptions.newBuilder().addSelectedFields("name").addSelectedFields("number").addSelectedFields("state").setRowRestriction("state = \"WA\"").build();
// Start specifying the read session we want created.
ReadSession.Builder sessionBuilder = ReadSession.newBuilder().setTable(srcTable).setDataFormat(DataFormat.AVRO).setReadOptions(options);
// Optionally specify the snapshot time. When unspecified, snapshot time is "now".
if (snapshotMillis != null) {
Timestamp t = Timestamp.newBuilder().setSeconds(snapshotMillis / 1000).setNanos((int) ((snapshotMillis % 1000) * 1000000)).build();
TableModifiers modifiers = TableModifiers.newBuilder().setSnapshotTime(t).build();
sessionBuilder.setTableModifiers(modifiers);
}
// Begin building the session creation request.
CreateReadSessionRequest.Builder builder = CreateReadSessionRequest.newBuilder().setParent(parent).setReadSession(sessionBuilder).setMaxStreamCount(1);
// Request the session creation.
ReadSession session = client.createReadSession(builder.build());
SimpleRowReader reader = new SimpleRowReader(new Schema.Parser().parse(session.getAvroSchema().getSchema()));
// Assert that there are streams available in the session. An empty table may not have
// data available. If no sessions are available for an anonymous (cached) table, consider
// writing results of a query to a named table rather than consuming cached results directly.
Preconditions.checkState(session.getStreamsCount() > 0);
// Use the first stream to perform reading.
String streamName = session.getStreams(0).getName();
ReadRowsRequest readRowsRequest = ReadRowsRequest.newBuilder().setReadStream(streamName).build();
// Process each block of rows as they arrive and decode using our simple row reader.
ServerStream<ReadRowsResponse> stream = client.readRowsCallable().call(readRowsRequest);
for (ReadRowsResponse response : stream) {
Preconditions.checkState(response.hasAvroRows());
reader.processRows(response.getAvroRows());
}
}
}
use of com.google.bigtable.repackaged.com.google.bigtable.v2.ReadRowsRequest in project beam by apache.
the class BigQueryIOStorageReadTest method testReadFromBigQueryIO.
@Test
public void testReadFromBigQueryIO() throws Exception {
fakeDatasetService.createDataset("foo.com:project", "dataset", "", "", null);
TableReference tableRef = BigQueryHelpers.parseTableSpec("foo.com:project:dataset.table");
Table table = new Table().setTableReference(tableRef).setNumBytes(10L).setSchema(TABLE_SCHEMA);
fakeDatasetService.createTable(table);
CreateReadSessionRequest expectedCreateReadSessionRequest = CreateReadSessionRequest.newBuilder().setParent("projects/project-id").setReadSession(ReadSession.newBuilder().setTable("projects/foo.com:project/datasets/dataset/tables/table").setDataFormat(DataFormat.AVRO)).setMaxStreamCount(10).build();
ReadSession readSession = ReadSession.newBuilder().setName("readSessionName").setAvroSchema(AvroSchema.newBuilder().setSchema(AVRO_SCHEMA_STRING)).addStreams(ReadStream.newBuilder().setName("streamName")).setDataFormat(DataFormat.AVRO).build();
ReadRowsRequest expectedReadRowsRequest = ReadRowsRequest.newBuilder().setReadStream("streamName").build();
List<GenericRecord> records = Lists.newArrayList(createRecord("A", 1, AVRO_SCHEMA), createRecord("B", 2, AVRO_SCHEMA), createRecord("C", 3, AVRO_SCHEMA), createRecord("D", 4, AVRO_SCHEMA));
List<ReadRowsResponse> readRowsResponses = Lists.newArrayList(createResponse(AVRO_SCHEMA, records.subList(0, 2), 0.0, 0.50), createResponse(AVRO_SCHEMA, records.subList(2, 4), 0.5, 0.75));
StorageClient fakeStorageClient = mock(StorageClient.class, withSettings().serializable());
when(fakeStorageClient.createReadSession(expectedCreateReadSessionRequest)).thenReturn(readSession);
when(fakeStorageClient.readRows(expectedReadRowsRequest, "")).thenReturn(new FakeBigQueryServerStream<>(readRowsResponses));
PCollection<KV<String, Long>> output = p.apply(BigQueryIO.read(new ParseKeyValue()).from("foo.com:project:dataset.table").withMethod(Method.DIRECT_READ).withFormat(DataFormat.AVRO).withTestServices(new FakeBigQueryServices().withDatasetService(fakeDatasetService).withStorageClient(fakeStorageClient)));
PAssert.that(output).containsInAnyOrder(ImmutableList.of(KV.of("A", 1L), KV.of("B", 2L), KV.of("C", 3L), KV.of("D", 4L)));
p.run();
}
use of com.google.bigtable.repackaged.com.google.bigtable.v2.ReadRowsRequest in project beam by apache.
the class BigQueryIOStorageReadTest method testFractionConsumed.
@Test
public void testFractionConsumed() throws Exception {
ReadSession readSession = ReadSession.newBuilder().setName("readSession").setAvroSchema(AvroSchema.newBuilder().setSchema(AVRO_SCHEMA_STRING)).build();
ReadRowsRequest expectedRequest = ReadRowsRequest.newBuilder().setReadStream("readStream").build();
List<GenericRecord> records = Lists.newArrayList(createRecord("A", 1, AVRO_SCHEMA), createRecord("B", 2, AVRO_SCHEMA), createRecord("C", 3, AVRO_SCHEMA), createRecord("D", 4, AVRO_SCHEMA), createRecord("E", 5, AVRO_SCHEMA), createRecord("F", 6, AVRO_SCHEMA), createRecord("G", 7, AVRO_SCHEMA));
List<ReadRowsResponse> responses = Lists.newArrayList(createResponse(AVRO_SCHEMA, records.subList(0, 2), 0.0, 0.25), // to such responses.
createResponse(AVRO_SCHEMA, Lists.newArrayList(), 0.25, 0.25), createResponse(AVRO_SCHEMA, records.subList(2, 4), 0.3, 0.5), createResponse(AVRO_SCHEMA, records.subList(4, 7), 0.7, 1.0));
StorageClient fakeStorageClient = mock(StorageClient.class);
when(fakeStorageClient.readRows(expectedRequest, "")).thenReturn(new FakeBigQueryServerStream<>(responses));
BigQueryStorageStreamSource<TableRow> streamSource = BigQueryStorageStreamSource.create(readSession, ReadStream.newBuilder().setName("readStream").build(), TABLE_SCHEMA, new TableRowParser(), TableRowJsonCoder.of(), new FakeBigQueryServices().withStorageClient(fakeStorageClient));
BoundedReader<TableRow> reader = streamSource.createReader(options);
// Before call to BoundedReader#start, fraction consumed must be zero.
assertEquals(0.0, reader.getFractionConsumed(), DELTA);
// Reads A.
assertTrue(reader.start());
assertEquals(0.125, reader.getFractionConsumed(), DELTA);
// Reads B.
assertTrue(reader.advance());
assertEquals(0.25, reader.getFractionConsumed(), DELTA);
// Reads C.
assertTrue(reader.advance());
assertEquals(0.4, reader.getFractionConsumed(), DELTA);
// Reads D.
assertTrue(reader.advance());
assertEquals(0.5, reader.getFractionConsumed(), DELTA);
// Reads E.
assertTrue(reader.advance());
assertEquals(0.8, reader.getFractionConsumed(), DELTA);
// Reads F.
assertTrue(reader.advance());
assertEquals(0.9, reader.getFractionConsumed(), DELTA);
// Reads G.
assertTrue(reader.advance());
assertEquals(1.0, reader.getFractionConsumed(), DELTA);
// Reaches the end.
assertFalse(reader.advance());
// We are done with the stream, so we should report 100% consumption.
assertEquals(Double.valueOf(1.0), reader.getFractionConsumed());
}
Aggregations