lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

New Features in DeltaStreamer :

Browse Source 
(1) Apply transformation when using delta-streamer to ingest data.
 (2) Add Hudi Incremental Source for Delta Streamer
 (3) Allow delta-streamer config-property to be passed as command-line
 (4) Add Hive Integration to Delta-Streamer and address Review comments
 (5) Ensure MultiPartKeysValueExtractor  handle hive style partition description
 (6) Reuse same spark session on both source and transformer
 (7) Support extracting partition fields from _hoodie_partition_path for HoodieIncrSource
 (8) Reuse Binary Avro coders
 (9) Add push down filter for Incremental source
 (10) Add Hoodie DeltaStreamer metrics to track total time taken
This commit is contained in:
Balaji Varadarajan
2018-10-10 10:31:34 -07:00
committed by vinoth chandar
parent c70dbc13e9
commit 3a0044216c
65 changed files with 2752 additions and 911 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
hoodie-client/src/test/java/com/uber/hoodie/common/HoodieTestDataGenerator.java
View File

@@ -75,7 +75,9 @@ public class HoodieTestDataGenerator {
+ "{\"name\": \"end_lat\", \"type\": \"double\"},"
+ "{\"name\": \"end_lon\", \"type\": \"double\"},"
+ "{\"name\":\"fare\",\"type\": \"double\"}]}";
public static Schema avroSchema = HoodieAvroUtils.addMetadataFields(new Schema.Parser().parse(TRIP_EXAMPLE_SCHEMA));
public static Schema avroSchema = new Schema.Parser().parse(TRIP_EXAMPLE_SCHEMA);
public static Schema avroSchemaWithMetadataFields = HoodieAvroUtils.addMetadataFields(avroSchema);
private static Random rand = new Random(46474747);
private List<KeyPartition> existingKeysList = new ArrayList<>();
@@ -100,7 +102,6 @@ public class HoodieTestDataGenerator {
*/
public static TestRawTripPayload generateRandomValue(HoodieKey key, String commitTime) throws IOException {
GenericRecord rec = generateGenericRecord(key.getRecordKey(), "rider-" + commitTime, "driver-" + commitTime, 0.0);
HoodieAvroUtils.addCommitMetadataToRecord(rec, commitTime, "-1");
return new TestRawTripPayload(rec.toString(), key.getRecordKey(), key.getPartitionPath(), TRIP_EXAMPLE_SCHEMA);
}

3
hoodie-client/src/test/java/com/uber/hoodie/io/TestHoodieCompactor.java
View File

@@ -160,7 +160,8 @@ public class TestHoodieCompactor {
// Write them to corresponding avro logfiles
HoodieTestUtils
.writeRecordsToLogFiles(fs, metaClient.getBasePath(), HoodieTestDataGenerator.avroSchema, updatedRecords);
.writeRecordsToLogFiles(fs, metaClient.getBasePath(), HoodieTestDataGenerator.avroSchemaWithMetadataFields,
updatedRecords);
// Verify that all data file has one log file
metaClient = new HoodieTableMetaClient(jsc.hadoopConfiguration(), basePath);

3
hoodie-client/src/test/java/com/uber/hoodie/metrics/TestHoodieMetrics.java
View File

@@ -16,6 +16,7 @@
package com.uber.hoodie.metrics;
import static com.uber.hoodie.metrics.Metrics.registerGauge;
import static org.junit.Assert.assertTrue;
import static org.mockito.Mockito.mock;
import static org.mockito.Mockito.when;
@@ -39,7 +40,7 @@ public class TestHoodieMetrics {
@Test
public void testRegisterGauge() {
metrics.registerGauge("metric1", 123L);
registerGauge("metric1", 123L);
assertTrue(Metrics.getInstance().getRegistry().getGauges().get("metric1").getValue().toString().equals("123"));
}
}

4
hoodie-client/src/test/java/com/uber/hoodie/table/TestMergeOnReadTable.java
View File

@@ -671,8 +671,8 @@ public class TestMergeOnReadTable {
// Write them to corresponding avro logfiles
HoodieTestUtils
.writeRecordsToLogFiles(metaClient.getFs(), metaClient.getBasePath(), HoodieTestDataGenerator.avroSchema,
updatedRecords);
.writeRecordsToLogFiles(metaClient.getFs(), metaClient.getBasePath(),
HoodieTestDataGenerator.avroSchemaWithMetadataFields, updatedRecords);
// Verify that all data file has one log file
metaClient = new HoodieTableMetaClient(jsc.hadoopConfiguration(), basePath);