Skip to content

Flink: Fix equalityFieldColumns always null in IcebergSink #14952

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.

Sign up for GitHub

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

Open
Guosmilesmile wants to merge 1 commit into
base: main
Choose a base branch
from
+43 −3
Open

Flink: Fix equalityFieldColumns always null in IcebergSink #14952

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
13 changes: 10 additions & 3 deletions flink/v2.1/flink/src/main/java/org/apache/iceberg/flink/sink/IcebergSink.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,7 @@
import org.apache.iceberg.io.WriteResult;
import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
import org.apache.iceberg.relocated.com.google.common.collect.Maps;
import org.apache.iceberg.relocated.com.google.common.collect.Sets;
import org.apache.iceberg.types.TypeUtil;
import org.apache.iceberg.util.SerializableSupplier;
import org.slf4j.Logger;
Expand Down Expand Up @@ -162,7 +163,7 @@ public class IcebergSink
private final transient FlinkMaintenanceConfig flinkMaintenanceConfig;

private final Table table;
private final Set<String> equalityFieldColumns = null;
private final Set<String> equalityFieldColumns;

private IcebergSink(
TableLoader tableLoader,
Expand All @@ -176,7 +177,8 @@ private IcebergSink(
Set<Integer> equalityFieldIds,
String branch,
boolean overwriteMode,
FlinkMaintenanceConfig flinkMaintenanceConfig) {
FlinkMaintenanceConfig flinkMaintenanceConfig,
Set<String> equalityFieldColumns) {
this.tableLoader = tableLoader;
this.snapshotProperties = snapshotProperties;
this.uidSuffix = uidSuffix;
Expand All @@ -198,6 +200,7 @@ private IcebergSink(
this.sinkId = UUID.randomUUID().toString();
this.compactMode = flinkWriteConf.compactMode();
this.flinkMaintenanceConfig = flinkMaintenanceConfig;
this.equalityFieldColumns = equalityFieldColumns;
}

@Override
Expand Down Expand Up @@ -666,6 +669,9 @@ IcebergSink build() {
FlinkMaintenanceConfig flinkMaintenanceConfig =
new FlinkMaintenanceConfig(table, writeOptions, readableConfig);

Set<String> equalityFieldColumnsSet =
equalityFieldColumns != null ? Sets.newHashSet(equalityFieldColumns) : null;

return new IcebergSink(
tableLoader,
table,
Expand All @@ -680,7 +686,8 @@ IcebergSink build() {
equalityFieldIds,
flinkWriteConf.branch(),
overwriteMode,
flinkMaintenanceConfig);
flinkMaintenanceConfig,
equalityFieldColumnsSet);
}

/**
Expand Down
33 changes: 33 additions & 0 deletions ...k/src/test/java/org/apache/iceberg/flink/sink/TestFlinkIcebergSinkV2DistributionMode.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -562,6 +562,39 @@ public void testRangeDistributionStatisticsMigration() throws Exception {
}
}

@TestTemplate
public void testHashDistributionWithPartitionNotInEqualityFields() {
assumeThat(partitioned).isTrue();

List<Row> rows = createRows("");
DataStream<Row> dataStream = env.addSource(createBoundedSource(rows), ROW_TYPE_INFO);

if (isTableSchema) {
IcebergSink.forRow(dataStream, SimpleDataUtil.FLINK_TABLE_SCHEMA)
.table(table)
.tableLoader(tableLoader)
.writeParallelism(writeParallelism)
.distributionMode(DistributionMode.HASH)
.upsert(false)
.equalityFieldColumns(ImmutableList.of("id"))
.append();
} else {
IcebergSink.forRow(dataStream, SimpleDataUtil.FLINK_SCHEMA)
.table(table)
.tableLoader(tableLoader)
.writeParallelism(writeParallelism)
.distributionMode(DistributionMode.HASH)
.upsert(false)
.equalityFieldColumns(ImmutableList.of("id"))
.append();
}

assertThatThrownBy(env::execute)
.isInstanceOf(IllegalStateException.class)
.hasMessageContaining(
"In 'hash' distribution mode with equality fields set, source column 'data' of partition field '1000: data: identity(2)' should be included in equality fields: '[id]'");
}

private BoundedTestSource<Row> createRangeDistributionBoundedSource(
List<List<Row>> rowsPerCheckpoint) {
return new BoundedTestSource<>(rowsPerCheckpoint);
Expand Down