[HUDI-811] Restructure test packages (#1607)
* restructure hudi-spark tests * restructure hudi-timeline-service tests * restructure hudi-hadoop-mr hudi-utilities tests * restructure hudi-hive-sync tests
This commit is contained in:
@@ -16,11 +16,9 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.deltastreamer;
|
||||
|
||||
import org.apache.hudi.common.model.HoodieTableType;
|
||||
import org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer;
|
||||
import org.apache.hudi.utilities.deltastreamer.SchedulerConfGenerator;
|
||||
|
||||
import org.junit.jupiter.api.Test;
|
||||
|
||||
@@ -16,9 +16,10 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.functional;
|
||||
|
||||
import org.apache.hudi.payload.AWSDmsAvroPayload;
|
||||
import org.apache.hudi.utilities.UtilHelpers;
|
||||
import org.apache.hudi.utilities.transform.AWSDmsTransformer;
|
||||
|
||||
import org.apache.avro.Schema;
|
||||
@@ -16,7 +16,7 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.functional;
|
||||
|
||||
import org.apache.hudi.client.HoodieReadClient;
|
||||
import org.apache.hudi.client.HoodieWriteClient;
|
||||
@@ -26,6 +26,7 @@ import org.apache.hudi.common.minicluster.HdfsTestService;
|
||||
import org.apache.hudi.common.model.HoodieTestUtils;
|
||||
import org.apache.hudi.common.table.timeline.HoodieActiveTimeline;
|
||||
import org.apache.hudi.common.table.timeline.HoodieTimeline;
|
||||
import org.apache.hudi.utilities.HDFSParquetImporter;
|
||||
|
||||
import org.apache.avro.generic.GenericRecord;
|
||||
import org.apache.hadoop.fs.FSDataOutputStream;
|
||||
@@ -16,7 +16,7 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.functional;
|
||||
|
||||
import org.apache.hudi.DataSourceWriteOptions;
|
||||
import org.apache.hudi.common.HoodieTestDataGenerator;
|
||||
@@ -43,12 +43,13 @@ import org.apache.hudi.utilities.deltastreamer.HoodieDeltaStreamer.Operation;
|
||||
import org.apache.hudi.utilities.schema.FilebasedSchemaProvider;
|
||||
import org.apache.hudi.utilities.schema.SchemaProvider;
|
||||
import org.apache.hudi.utilities.sources.CsvDFSSource;
|
||||
import org.apache.hudi.utilities.sources.DistributedTestDataSource;
|
||||
import org.apache.hudi.utilities.sources.HoodieIncrSource;
|
||||
import org.apache.hudi.utilities.sources.InputBatch;
|
||||
import org.apache.hudi.utilities.sources.ParquetDFSSource;
|
||||
import org.apache.hudi.utilities.sources.TestDataSource;
|
||||
import org.apache.hudi.utilities.sources.config.TestSourceConfig;
|
||||
import org.apache.hudi.utilities.testutils.UtilitiesTestBase;
|
||||
import org.apache.hudi.utilities.testutils.sources.DistributedTestDataSource;
|
||||
import org.apache.hudi.utilities.testutils.sources.config.TestSourceConfig;
|
||||
import org.apache.hudi.utilities.transform.SqlQueryBasedTransformer;
|
||||
import org.apache.hudi.utilities.transform.Transformer;
|
||||
|
||||
@@ -389,7 +390,7 @@ public class TestHoodieDeltaStreamer extends UtilitiesTestBase {
|
||||
new DFSPropertiesConfiguration(dfs, new Path(dfsBasePath + "/" + PROPS_FILENAME_TEST_SOURCE)).getConfig();
|
||||
assertEquals(2, props.getInteger("hoodie.upsert.shuffle.parallelism"));
|
||||
assertEquals("_row_key", props.getString("hoodie.datasource.write.recordkey.field"));
|
||||
assertEquals("org.apache.hudi.utilities.TestHoodieDeltaStreamer$TestGenerator",
|
||||
assertEquals("org.apache.hudi.utilities.functional.TestHoodieDeltaStreamer$TestGenerator",
|
||||
props.getString("hoodie.datasource.write.keygenerator.class"));
|
||||
}
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.functional;
|
||||
|
||||
import org.apache.hudi.DataSourceWriteOptions;
|
||||
import org.apache.hudi.common.HoodieTestDataGenerator;
|
||||
@@ -16,12 +16,13 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.functional;
|
||||
|
||||
import org.apache.hudi.common.HoodieTestDataGenerator;
|
||||
import org.apache.hudi.common.fs.FSUtils;
|
||||
import org.apache.hudi.common.model.HoodieTestUtils;
|
||||
import org.apache.hudi.common.testutils.HoodieCommonTestHarness;
|
||||
import org.apache.hudi.utilities.HoodieSnapshotCopier;
|
||||
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
@@ -16,7 +16,7 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.functional;
|
||||
|
||||
import org.apache.hudi.client.HoodieWriteClient;
|
||||
import org.apache.hudi.common.HoodieClientTestHarness;
|
||||
@@ -28,6 +28,7 @@ import org.apache.hudi.common.table.HoodieTableMetaClient;
|
||||
import org.apache.hudi.config.HoodieIndexConfig;
|
||||
import org.apache.hudi.config.HoodieWriteConfig;
|
||||
import org.apache.hudi.index.HoodieIndex.IndexType;
|
||||
import org.apache.hudi.utilities.HoodieSnapshotExporter;
|
||||
import org.apache.hudi.utilities.HoodieSnapshotExporter.Config;
|
||||
import org.apache.hudi.utilities.HoodieSnapshotExporter.OutputFormatValidator;
|
||||
import org.apache.hudi.utilities.HoodieSnapshotExporter.Partitioner;
|
||||
@@ -16,11 +16,13 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.functional;
|
||||
|
||||
import org.apache.hudi.common.config.TypedProperties;
|
||||
import org.apache.hudi.exception.HoodieException;
|
||||
import org.apache.hudi.utilities.UtilHelpers;
|
||||
import org.apache.hudi.utilities.schema.JdbcbasedSchemaProvider;
|
||||
import org.apache.hudi.utilities.testutils.UtilitiesTestBase;
|
||||
|
||||
import org.apache.avro.Schema;
|
||||
import org.apache.log4j.LogManager;
|
||||
@@ -16,13 +16,12 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.keygen;
|
||||
|
||||
import org.apache.hudi.DataSourceWriteOptions;
|
||||
import org.apache.hudi.common.config.TypedProperties;
|
||||
import org.apache.hudi.common.model.HoodieKey;
|
||||
import org.apache.hudi.common.util.SchemaTestUtil;
|
||||
import org.apache.hudi.utilities.keygen.TimestampBasedKeyGenerator;
|
||||
|
||||
import org.apache.avro.Schema;
|
||||
import org.apache.avro.generic.GenericRecord;
|
||||
@@ -20,8 +20,9 @@ package org.apache.hudi.utilities.sources;
|
||||
|
||||
import org.apache.hudi.common.config.TypedProperties;
|
||||
import org.apache.hudi.common.model.HoodieRecord;
|
||||
import org.apache.hudi.utilities.UtilitiesTestBase;
|
||||
import org.apache.hudi.utilities.schema.FilebasedSchemaProvider;
|
||||
import org.apache.hudi.utilities.testutils.UtilitiesTestBase;
|
||||
import org.apache.hudi.utilities.testutils.sources.AbstractDFSSourceTestBase;
|
||||
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
@@ -45,7 +46,7 @@ public class TestCsvDFSSource extends AbstractDFSSourceTestBase {
|
||||
}
|
||||
|
||||
@Override
|
||||
Source prepareDFSSource() {
|
||||
public Source prepareDFSSource() {
|
||||
TypedProperties props = new TypedProperties();
|
||||
props.setProperty("hoodie.deltastreamer.source.dfs.root", dfsRoot);
|
||||
props.setProperty("hoodie.deltastreamer.csv.header", Boolean.toString(true));
|
||||
@@ -54,7 +55,7 @@ public class TestCsvDFSSource extends AbstractDFSSourceTestBase {
|
||||
}
|
||||
|
||||
@Override
|
||||
void writeNewDataToFile(List<HoodieRecord> records, Path path) throws IOException {
|
||||
public void writeNewDataToFile(List<HoodieRecord> records, Path path) throws IOException {
|
||||
UtilitiesTestBase.Helpers.saveCsvToDFS(
|
||||
true, '\t', Helpers.jsonifyRecords(records), dfs, path.toString());
|
||||
}
|
||||
|
||||
@@ -21,6 +21,7 @@ package org.apache.hudi.utilities.sources;
|
||||
import org.apache.hudi.common.config.TypedProperties;
|
||||
import org.apache.hudi.common.util.Option;
|
||||
import org.apache.hudi.utilities.schema.SchemaProvider;
|
||||
import org.apache.hudi.utilities.testutils.sources.AbstractBaseTestSource;
|
||||
|
||||
import org.apache.avro.generic.GenericRecord;
|
||||
import org.apache.log4j.LogManager;
|
||||
|
||||
@@ -20,7 +20,8 @@ package org.apache.hudi.utilities.sources;
|
||||
|
||||
import org.apache.hudi.common.config.TypedProperties;
|
||||
import org.apache.hudi.common.model.HoodieRecord;
|
||||
import org.apache.hudi.utilities.UtilitiesTestBase;
|
||||
import org.apache.hudi.utilities.testutils.UtilitiesTestBase;
|
||||
import org.apache.hudi.utilities.testutils.sources.AbstractDFSSourceTestBase;
|
||||
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
@@ -41,14 +42,14 @@ public class TestJsonDFSSource extends AbstractDFSSourceTestBase {
|
||||
}
|
||||
|
||||
@Override
|
||||
Source prepareDFSSource() {
|
||||
public Source prepareDFSSource() {
|
||||
TypedProperties props = new TypedProperties();
|
||||
props.setProperty("hoodie.deltastreamer.source.dfs.root", dfsRoot);
|
||||
return new JsonDFSSource(props, jsc, sparkSession, schemaProvider);
|
||||
}
|
||||
|
||||
@Override
|
||||
void writeNewDataToFile(List<HoodieRecord> records, Path path) throws IOException {
|
||||
public void writeNewDataToFile(List<HoodieRecord> records, Path path) throws IOException {
|
||||
UtilitiesTestBase.Helpers.saveStringsToDFS(
|
||||
Helpers.jsonifyRecords(records), dfs, path.toString());
|
||||
}
|
||||
|
||||
@@ -22,11 +22,11 @@ import org.apache.hudi.AvroConversionUtils;
|
||||
import org.apache.hudi.common.HoodieTestDataGenerator;
|
||||
import org.apache.hudi.common.config.TypedProperties;
|
||||
import org.apache.hudi.common.util.Option;
|
||||
import org.apache.hudi.utilities.UtilitiesTestBase;
|
||||
import org.apache.hudi.utilities.deltastreamer.SourceFormatAdapter;
|
||||
import org.apache.hudi.utilities.schema.FilebasedSchemaProvider;
|
||||
import org.apache.hudi.utilities.sources.helpers.KafkaOffsetGen.CheckpointUtils;
|
||||
import org.apache.hudi.utilities.sources.helpers.KafkaOffsetGen.Config;
|
||||
import org.apache.hudi.utilities.testutils.UtilitiesTestBase;
|
||||
|
||||
import org.apache.avro.generic.GenericRecord;
|
||||
import org.apache.kafka.clients.consumer.ConsumerConfig;
|
||||
|
||||
@@ -20,6 +20,7 @@ package org.apache.hudi.utilities.sources;
|
||||
|
||||
import org.apache.hudi.common.config.TypedProperties;
|
||||
import org.apache.hudi.common.model.HoodieRecord;
|
||||
import org.apache.hudi.utilities.testutils.sources.AbstractDFSSourceTestBase;
|
||||
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
@@ -40,14 +41,14 @@ public class TestParquetDFSSource extends AbstractDFSSourceTestBase {
|
||||
}
|
||||
|
||||
@Override
|
||||
Source prepareDFSSource() {
|
||||
public Source prepareDFSSource() {
|
||||
TypedProperties props = new TypedProperties();
|
||||
props.setProperty("hoodie.deltastreamer.source.dfs.root", dfsRoot);
|
||||
return new ParquetDFSSource(props, jsc, sparkSession, schemaProvider);
|
||||
}
|
||||
|
||||
@Override
|
||||
void writeNewDataToFile(List<HoodieRecord> records, Path path) throws IOException {
|
||||
public void writeNewDataToFile(List<HoodieRecord> records, Path path) throws IOException {
|
||||
Helpers.saveParquetToDFS(Helpers.toGenericRecords(records), path);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities;
|
||||
package org.apache.hudi.utilities.testutils;
|
||||
|
||||
import org.apache.hudi.common.HoodieTestDataGenerator;
|
||||
import org.apache.hudi.common.TestRawTripPayload;
|
||||
@@ -31,7 +31,8 @@ import org.apache.hudi.common.util.Option;
|
||||
import org.apache.hudi.exception.HoodieIOException;
|
||||
import org.apache.hudi.hive.HiveSyncConfig;
|
||||
import org.apache.hudi.hive.HoodieHiveClient;
|
||||
import org.apache.hudi.hive.util.HiveTestService;
|
||||
import org.apache.hudi.hive.testutils.HiveTestService;
|
||||
import org.apache.hudi.utilities.UtilHelpers;
|
||||
import org.apache.hudi.utilities.sources.TestDataSource;
|
||||
|
||||
import com.fasterxml.jackson.databind.JsonNode;
|
||||
@@ -91,7 +92,7 @@ public class UtilitiesTestBase {
|
||||
initClass(false);
|
||||
}
|
||||
|
||||
static void initClass(boolean startHiveService) throws Exception {
|
||||
public static void initClass(boolean startHiveService) throws Exception {
|
||||
hdfsTestService = new HdfsTestService();
|
||||
dfsCluster = hdfsTestService.start(true);
|
||||
dfs = dfsCluster.getFileSystem();
|
||||
@@ -16,7 +16,7 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities.sources;
|
||||
package org.apache.hudi.utilities.testutils.sources;
|
||||
|
||||
import org.apache.hudi.common.HoodieTestDataGenerator;
|
||||
import org.apache.hudi.common.config.TypedProperties;
|
||||
@@ -25,7 +25,8 @@ import org.apache.hudi.common.util.Option;
|
||||
import org.apache.hudi.common.util.collection.RocksDBBasedMap;
|
||||
import org.apache.hudi.exception.HoodieIOException;
|
||||
import org.apache.hudi.utilities.schema.SchemaProvider;
|
||||
import org.apache.hudi.utilities.sources.config.TestSourceConfig;
|
||||
import org.apache.hudi.utilities.sources.AvroSource;
|
||||
import org.apache.hudi.utilities.testutils.sources.config.TestSourceConfig;
|
||||
|
||||
import org.apache.avro.generic.GenericRecord;
|
||||
import org.apache.avro.generic.IndexedRecord;
|
||||
@@ -44,7 +45,7 @@ public abstract class AbstractBaseTestSource extends AvroSource {
|
||||
|
||||
private static final Logger LOG = LogManager.getLogger(AbstractBaseTestSource.class);
|
||||
|
||||
static final int DEFAULT_PARTITION_NUM = 0;
|
||||
public static final int DEFAULT_PARTITION_NUM = 0;
|
||||
|
||||
// Static instance, helps with reuse across a test.
|
||||
protected static transient Map<Integer, HoodieTestDataGenerator> dataGeneratorMap = new HashMap<>();
|
||||
@@ -16,15 +16,17 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities.sources;
|
||||
package org.apache.hudi.utilities.testutils.sources;
|
||||
|
||||
import org.apache.hudi.AvroConversionUtils;
|
||||
import org.apache.hudi.common.HoodieTestDataGenerator;
|
||||
import org.apache.hudi.common.model.HoodieRecord;
|
||||
import org.apache.hudi.common.util.Option;
|
||||
import org.apache.hudi.utilities.UtilitiesTestBase;
|
||||
import org.apache.hudi.utilities.deltastreamer.SourceFormatAdapter;
|
||||
import org.apache.hudi.utilities.schema.FilebasedSchemaProvider;
|
||||
import org.apache.hudi.utilities.sources.InputBatch;
|
||||
import org.apache.hudi.utilities.sources.Source;
|
||||
import org.apache.hudi.utilities.testutils.UtilitiesTestBase;
|
||||
|
||||
import org.apache.avro.generic.GenericRecord;
|
||||
import org.apache.hadoop.fs.FileStatus;
|
||||
@@ -52,11 +54,11 @@ import static org.junit.jupiter.api.Assertions.assertTrue;
|
||||
*/
|
||||
public abstract class AbstractDFSSourceTestBase extends UtilitiesTestBase {
|
||||
|
||||
FilebasedSchemaProvider schemaProvider;
|
||||
String dfsRoot;
|
||||
String fileSuffix;
|
||||
HoodieTestDataGenerator dataGenerator = new HoodieTestDataGenerator();
|
||||
boolean useFlattenedSchema = false;
|
||||
protected FilebasedSchemaProvider schemaProvider;
|
||||
protected String dfsRoot;
|
||||
protected String fileSuffix;
|
||||
protected HoodieTestDataGenerator dataGenerator = new HoodieTestDataGenerator();
|
||||
protected boolean useFlattenedSchema = false;
|
||||
|
||||
@BeforeAll
|
||||
public static void initClass() throws Exception {
|
||||
@@ -84,27 +86,25 @@ public abstract class AbstractDFSSourceTestBase extends UtilitiesTestBase {
|
||||
*
|
||||
* @return A {@link Source} using DFS as the file system.
|
||||
*/
|
||||
abstract Source prepareDFSSource();
|
||||
protected abstract Source prepareDFSSource();
|
||||
|
||||
/**
|
||||
* Writes test data, i.e., a {@link List} of {@link HoodieRecord}, to a file on DFS.
|
||||
*
|
||||
* @param records Test data.
|
||||
* @param path The path in {@link Path} of the file to write.
|
||||
* @throws IOException
|
||||
* @param path The path in {@link Path} of the file to write.
|
||||
*/
|
||||
abstract void writeNewDataToFile(List<HoodieRecord> records, Path path) throws IOException;
|
||||
protected abstract void writeNewDataToFile(List<HoodieRecord> records, Path path) throws IOException;
|
||||
|
||||
/**
|
||||
* Generates a batch of test data and writes the data to a file.
|
||||
*
|
||||
* @param filename The name of the file.
|
||||
* @param instantTime The commit time.
|
||||
* @param n The number of records to generate.
|
||||
* @return The file path.
|
||||
* @throws IOException
|
||||
* @param filename The name of the file.
|
||||
* @param instantTime The commit time.
|
||||
* @param n The number of records to generate.
|
||||
* @return The file path.
|
||||
*/
|
||||
Path generateOneFile(String filename, String instantTime, int n) throws IOException {
|
||||
protected Path generateOneFile(String filename, String instantTime, int n) throws IOException {
|
||||
Path path = new Path(dfsRoot, filename + fileSuffix);
|
||||
writeNewDataToFile(dataGenerator.generateInserts(instantTime, n, useFlattenedSchema), path);
|
||||
return path;
|
||||
@@ -16,12 +16,13 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities.sources;
|
||||
package org.apache.hudi.utilities.testutils.sources;
|
||||
|
||||
import org.apache.hudi.common.config.TypedProperties;
|
||||
import org.apache.hudi.common.util.Option;
|
||||
import org.apache.hudi.utilities.schema.SchemaProvider;
|
||||
import org.apache.hudi.utilities.sources.config.TestSourceConfig;
|
||||
import org.apache.hudi.utilities.sources.InputBatch;
|
||||
import org.apache.hudi.utilities.testutils.sources.config.TestSourceConfig;
|
||||
|
||||
import org.apache.avro.generic.GenericRecord;
|
||||
import org.apache.log4j.LogManager;
|
||||
@@ -16,7 +16,7 @@
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.hudi.utilities.sources.config;
|
||||
package org.apache.hudi.utilities.testutils.sources.config;
|
||||
|
||||
/**
|
||||
* Configurations for Test Data Sources.
|
||||
Reference in New Issue
Block a user