fresh-borzoni commented on code in PR #3432:
URL: https://github.com/apache/fluss/pull/3432#discussion_r3359579994
##########
fluss-flink/fluss-flink-common/src/main/java/org/apache/fluss/flink/source/FlussSourceBuilder.java:
##########
@@ -324,6 +347,22 @@ public FlussSource<OUT> build() {
? tableInfo.getRowType().project(projectedFields)
: tableInfo.getRowType();
+ // union read (lake historical + Fluss) only applies to full startup
mode, like the SQL
+ // connector; other startup modes read Fluss only.
+ LakeSource<LakeSplit> lakeSource = null;
+ if (tableInfo.getTableConfig().isDataLakeEnabled()
+ && offsetsInitializer instanceof SnapshotOffsetsInitializer) {
+ lakeSource =
+ LakeSourceUtils.createLakeSource(tablePath,
tableInfo.getProperties().toMap());
+ if (lakeSource != null && projectedFields != null) {
+ int[][] nestedProjectedFields = new
int[projectedFields.length][];
+ for (int i = 0; i < projectedFields.length; i++) {
+ nestedProjectedFields[i] = new int[] {projectedFields[i]};
+ }
+ lakeSource.withProject(nestedProjectedFields);
+ }
+ }
Review Comment:
setBounded() only works on a lake table started from full(). Other options
seems that the job starts and then crashes later with a message like
"lakeSource' is null in batch mode". Both bad cases just mean lakeSource came
out null.
Should we check it explicitly and early?
##########
fluss-flink/fluss-flink-common/src/main/java/org/apache/fluss/flink/source/FlussSourceBuilder.java:
##########
@@ -324,6 +347,22 @@ public FlussSource<OUT> build() {
? tableInfo.getRowType().project(projectedFields)
: tableInfo.getRowType();
+ // union read (lake historical + Fluss) only applies to full startup
mode, like the SQL
+ // connector; other startup modes read Fluss only.
+ LakeSource<LakeSplit> lakeSource = null;
+ if (tableInfo.getTableConfig().isDataLakeEnabled()
+ && offsetsInitializer instanceof SnapshotOffsetsInitializer) {
+ lakeSource =
+ LakeSourceUtils.createLakeSource(tablePath,
tableInfo.getProperties().toMap());
Review Comment:
What about filters?
##########
fluss-lake/fluss-lake-iceberg/src/test/java/org/apache/fluss/lake/iceberg/flink/FlinkUnionReadDataStreamITCase.java:
##########
@@ -0,0 +1,460 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.fluss.lake.iceberg.flink;
+
+import org.apache.fluss.client.initializer.OffsetsInitializer;
+import org.apache.fluss.config.AutoPartitionTimeUnit;
+import org.apache.fluss.config.ConfigOptions;
+import org.apache.fluss.flink.source.FlussSource;
+import org.apache.fluss.flink.source.FlussSourceBuilder;
+import org.apache.fluss.flink.source.deserializer.RowDataDeserializationSchema;
+import org.apache.fluss.metadata.Schema;
+import org.apache.fluss.metadata.TableDescriptor;
+import org.apache.fluss.metadata.TablePath;
+import org.apache.fluss.row.InternalRow;
+import org.apache.fluss.types.DataTypes;
+
+import org.apache.flink.api.common.RuntimeExecutionMode;
+import org.apache.flink.api.common.eventtime.WatermarkStrategy;
+import org.apache.flink.core.execution.JobClient;
+import org.apache.flink.streaming.api.datastream.DataStreamSource;
+import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
+import org.apache.flink.table.data.RowData;
+import org.apache.flink.types.Row;
+import org.apache.flink.types.RowKind;
+import org.apache.flink.util.CloseableIterator;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.data.IcebergGenerics;
+import org.apache.iceberg.data.Record;
+import org.apache.iceberg.io.CloseableIterable;
+import org.junit.jupiter.api.BeforeAll;
+import org.junit.jupiter.api.Test;
+import org.junit.jupiter.params.ParameterizedTest;
+import org.junit.jupiter.params.provider.ValueSource;
+
+import javax.annotation.Nullable;
+
+import java.time.Duration;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+import java.util.stream.Collectors;
+
+import static org.apache.fluss.lake.iceberg.utils.IcebergConversions.toIceberg;
+import static org.apache.fluss.testutils.DataTestUtils.row;
+import static org.apache.fluss.testutils.common.CommonTestUtils.waitUntil;
+import static org.assertj.core.api.Assertions.assertThat;
+
+/**
+ * Integration tests for union read through the DataStream {@link FlussSource}.
+ *
+ * <p>These tests mirror the Flink SQL union-read coverage ({@code
FlinkUnionReadLogTableITCase} and
+ * {@code FlinkUnionReadPrimaryKeyTableITCase}) but exercise the programmatic
DataStream source.
+ * Each test asserts the three properties that make a union read meaningful:
Review Comment:
: ... mm?
--
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]
