yihua commented on code in PR #11770:
URL: https://github.com/apache/hudi/pull/11770#discussion_r1720367677
##########
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/functional/TestCOWDataSource.scala:
##########
@@ -1494,15 +1494,11 @@ class TestCOWDataSource extends
HoodieSparkClientTestBase with ScalaAssertionSup
assert(firstDF.count() == 2)
- // data_date is the partition field. Persist to the parquet file using the
origin values, and read it.
- // TODO(HUDI-3204) we have to revert this to pre-existing behavior from
0.10
Review Comment:
HUDI-3204 is what this PR also fixes. I see other `TODO(HUDI-3204)` that
are not addressed by this PR. Could you check and fix all of them?
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieHadoopFsRelationFactory.scala:
##########
@@ -75,6 +75,9 @@ abstract class HoodieBaseHadoopFsRelationFactory(val
sqlContext: SQLContext,
protected lazy val basePath: StoragePath = metaClient.getBasePath
protected lazy val partitionColumns: Array[String] =
tableConfig.getPartitionFields.orElse(Array.empty)
+ //placeholder until pr to persist field types lands
Review Comment:
Add a TODO with JIRA ticket.
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/vectorized/ColumnarBatchUtils.java:
##########
@@ -0,0 +1,91 @@
+/*
+ * 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.spark.sql.vectorized;
+
+import org.apache.spark.sql.types.StructType;
+
+import java.util.function.UnaryOperator;
+
+public class ColumnarBatchUtils {
+
+ public static UnaryOperator<ColumnarBatch> generateProjection(StructType
from, StructType to) {
+ if (from.length() < to.length()) {
+ throw new IllegalStateException(from + " has less columns than " + to);
+ }
+
+ if (from.equals(to)) {
+ return UnaryOperator.identity();
+ }
+
+ int[] projection = new int[to.size()];
+ for (int i = 0; i < to.length(); i++) {
+ projection[i] = from.fieldIndex(to.fields()[i].name());
+ }
+
+ return columnarBatch -> {
+ ColumnVector[] vectors = new ColumnVector[projection.length];
+ for (int i = 0; i < projection.length; i++) {
+ vectors[i] = columnarBatch.column(projection[i]);
+ }
+
+ //do this until we get rid of spark 2
+ ColumnarBatch b = new ColumnarBatch(vectors);
+ b.setNumRows(columnarBatch.numRows());
+ return b;
+ };
+ }
+
+ // public static UnaryOperator<ColumnarBatch>
generateProjectionInplace(StructType from, StructType to) {
Review Comment:
Can this be removed if not used?
--
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]
