lanyuanxiaoyao/hudi
1
0
Fork 0
Code Activity

[HUDI-575] Spark Streaming with async compaction support (#1752)

Browse Source
This commit is contained in:
Balaji Varadarajan
2020-08-05 07:50:15 -07:00
committed by GitHub
parent 61e027fadd
commit 7a2429f5ba
22 changed files with 835 additions and 304 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
hudi-common/src/test/java/org/apache/hudi/common/testutils/HoodieTestDataGenerator.java
View File

@@ -599,6 +599,26 @@ public class HoodieTestDataGenerator {
return updates;
}
/**
* Generate update for each record in the dataset.
* @param instantTime
* @return
* @throws IOException
*/
public List<HoodieRecord> generateUpdatesForAllRecords(String instantTime) {
List<HoodieRecord> updates = new ArrayList<>();
Map<Integer, KeyPartition> existingKeys = existingKeysBySchema.get(TRIP_EXAMPLE_SCHEMA);
existingKeys.values().forEach(kp -> {
try {
HoodieRecord record = generateUpdateRecord(kp.key, instantTime);
updates.add(record);
} catch (IOException ioe) {
throw new HoodieIOException(ioe.getMessage(), ioe);
}
});
return updates;
}
public List<HoodieRecord> generateUpdatesAsPerSchema(String commitTime, Integer n, String schemaStr) {
return generateUniqueUpdatesStream(commitTime, n, schemaStr).collect(Collectors.toList());
}