Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[HUDI-7139] Fix operation type for bulk insert with row writer in Hudi Streamer #10175

Merged
merged 1 commit into from
Nov 25, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -26,9 +26,7 @@
import org.apache.hudi.common.table.timeline.HoodieInstant;
import org.apache.hudi.common.util.Option;
import org.apache.hudi.config.HoodieWriteConfig;
import org.apache.hudi.table.action.HoodieWriteMetadata;

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;

Expand All @@ -44,12 +42,8 @@ public HoodieStreamerDatasetBulkInsertCommitActionExecutor(HoodieWriteConfig con

@Override
protected void preExecute() {
// no op
}

@Override
protected void afterExecute(HoodieWriteMetadata<JavaRDD<WriteStatus>> result) {
// no op
table.validateInsertSchema();
writeClient.preWrite(instantTime, getWriteOperationType(), table.getMetaClient());
}

@Override
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -1377,7 +1377,10 @@ private void testBulkInsertRowWriterMultiBatches(Boolean useSchemaProvider, List
if (i == 2 || i == 4) { // this validation reloads the timeline. So, we are validating only for first and last batch.
// validate commit metadata for all completed commits to have valid schema in extra metadata.
HoodieTableMetaClient metaClient = HoodieTableMetaClient.builder().setBasePath(tableBasePath).setConf(jsc.hadoopConfiguration()).build();
metaClient.reloadActiveTimeline().getCommitsTimeline().filterCompletedInstants().getInstants().forEach(entry -> assertValidSchemaInCommitMetadata(entry, metaClient));
metaClient.reloadActiveTimeline().getCommitsTimeline()
.filterCompletedInstants().getInstants()
.forEach(entry -> assertValidSchemaAndOperationTypeInCommitMetadata(
entry, metaClient, WriteOperationType.BULK_INSERT));
}
}
} finally {
Expand Down Expand Up @@ -1743,15 +1746,21 @@ private void testParquetDFSSource(boolean useSchemaProvider, List<String> transf
assertRecordCount(parquetRecordsCount + 100, tableBasePath, sqlContext);
// validate commit metadata for all completed commits to have valid schema in extra metadata.
HoodieTableMetaClient metaClient = HoodieTableMetaClient.builder().setBasePath(tableBasePath).setConf(jsc.hadoopConfiguration()).build();
metaClient.reloadActiveTimeline().getCommitsTimeline().filterCompletedInstants().getInstants().forEach(entry -> assertValidSchemaInCommitMetadata(entry, metaClient));
metaClient.reloadActiveTimeline().getCommitsTimeline()
.filterCompletedInstants().getInstants()
.forEach(entry -> assertValidSchemaAndOperationTypeInCommitMetadata(
entry, metaClient, WriteOperationType.INSERT));
testNum++;
}

private void assertValidSchemaInCommitMetadata(HoodieInstant instant, HoodieTableMetaClient metaClient) {
private void assertValidSchemaAndOperationTypeInCommitMetadata(HoodieInstant instant,
HoodieTableMetaClient metaClient,
WriteOperationType operationType) {
try {
HoodieCommitMetadata commitMetadata = HoodieCommitMetadata
.fromBytes(metaClient.getActiveTimeline().getInstantDetails(instant).get(), HoodieCommitMetadata.class);
assertFalse(StringUtils.isNullOrEmpty(commitMetadata.getMetadata(HoodieCommitMetadata.SCHEMA_KEY)));
assertEquals(operationType, commitMetadata.getOperationType());
} catch (IOException ioException) {
throw new HoodieException("Failed to parse commit metadata for " + instant.toString());
}
Expand Down
Loading