danny0405 commented on code in PR #9923:
URL: https://github.com/apache/hudi/pull/9923#discussion_r1373980908
##########
hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/source/TestIncrementalInputSplits.java:
##########
@@ -191,6 +196,85 @@ void testInputSplitsWithPartitionPruner(
assertEquals(expectedPartitions, partitions);
}
+ @Test
+ void testInsertInputSplitsWithSpeedLimit() throws Exception {
+ Configuration conf = TestConfigurations.getDefaultConf(basePath);
+ conf.set(FlinkOptions.READ_AS_STREAMING, true);
+ conf.set(FlinkOptions.READ_STREAMING_SKIP_CLUSTERING, true);
+ conf.set(FlinkOptions.READ_STREAMING_SKIP_COMPACT, true);
+ // insert data
+ TestData.writeData(TestData.DATA_SET_INSERT, conf);
+ TestData.writeData(TestData.DATA_SET_INSERT, conf);
+ TestData.writeData(TestData.DATA_SET_INSERT, conf);
+ TestData.writeData(TestData.DATA_SET_INSERT, conf);
+
+ HoodieTimeline commitsTimeline = metaClient.reloadActiveTimeline()
+ .filter(hoodieInstant ->
hoodieInstant.getAction().equals(HoodieTimeline.COMMIT_ACTION));
+ List<HoodieInstant> instants = commitsTimeline.getInstants();
+ List<HoodieCommitMetadata> metadataList = instants.stream()
+ .map(instant -> WriteProfiles.getCommitMetadata(tableName, new
Path(basePath), instant, commitsTimeline)).collect(Collectors.toList());
+ FileStatus[] fileStatuses = WriteProfiles.getFilesFromMetadata(new
Path(basePath), metaClient.getHadoopConf(), metadataList,
metaClient.getTableType());
+ HoodieTableFileSystemView fileSystemView =
+ new HoodieTableFileSystemView(metaClient, commitsTimeline,
fileStatuses);
+ Map<String, String> file2Instant = fileSystemView.getAllFileSlices("par1")
+ .collect(Collectors.toMap(FileSlice::getFileId,
FileSlice::getBaseInstantTime));
+ IncrementalInputSplits iis = IncrementalInputSplits.builder()
+ .conf(conf)
+ .path(new Path(basePath))
+ .rowType(TestConfigurations.ROW_TYPE)
+ .partitionPruner(null)
+ .build();
+
+ IncrementalInputSplits.Result result = iis.inputSplits(metaClient, null,
null, false);
+ result.getInputSplits().stream().forEach(split -> {
+ if (file2Instant.containsKey(split.getFileId())) {
+ assertEquals(split.getLatestCommit(),
file2Instant.get(split.getFileId()));
+ }
+ });
+ }
+
+ @Test
+ void testUpsertInputSplitsWithSpeedLimit() throws Exception {
+ Configuration conf = TestConfigurations.getDefaultConf(basePath);
+ conf.set(FlinkOptions.READ_AS_STREAMING, true);
+ conf.set(FlinkOptions.READ_STREAMING_SKIP_CLUSTERING, true);
+ conf.set(FlinkOptions.READ_STREAMING_SKIP_COMPACT, true);
+ conf.set(FlinkOptions.OPERATION, WriteOperationType.UPSERT.value());
+
+ // insert data
+ TestData.writeData(TestData.DATA_SET_INSERT, conf);
+ TestData.writeData(TestData.DATA_SET_UPDATE_INSERT, conf);
+ TestData.writeData(TestData.DATA_SET_UPDATE_INSERT, conf);
+ TestData.writeData(TestData.DATA_SET_UPDATE_INSERT, conf);
+
+ HoodieTimeline commitsTimeline = metaClient.reloadActiveTimeline()
+ .filter(hoodieInstant ->
hoodieInstant.getAction().equals(HoodieTimeline.DELTA_COMMIT_ACTION));
+ List<HoodieInstant> instants = commitsTimeline.getInstants();
+ List<HoodieCommitMetadata> metadataList = instants.stream()
+ .map(instant -> WriteProfiles.getCommitMetadata(tableName, new
Path(basePath), instant, commitsTimeline)).collect(Collectors.toList());
+ FileStatus[] fileStatuses = WriteProfiles.getFilesFromMetadata(new
Path(basePath), metaClient.getHadoopConf(), metadataList,
metaClient.getTableType());
+ HoodieTableFileSystemView fileSystemView =
+ new HoodieTableFileSystemView(metaClient, commitsTimeline,
fileStatuses);
+ Map<String, String> file2Instant = fileSystemView.getAllFileSlices("par1")
+ .collect(Collectors.toMap(FileSlice::getFileId, fileSlice ->
fileSlice.getLatestLogFile().isPresent()
+ ? fileSlice.getLatestLogFile().get().getDeltaCommitTime()
+ : fileSlice.getBaseInstantTime()));
+
+ IncrementalInputSplits iis = IncrementalInputSplits.builder()
+ .conf(conf)
+ .path(new Path(basePath))
+ .rowType(TestConfigurations.ROW_TYPE)
+ .partitionPruner(null)
+ .build();
Review Comment:
Did you add a test case where split latest commit not equals the
`lastInstant` ?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]