vinothchandar commented on a change in pull request #2645:
URL: https://github.com/apache/hudi/pull/2645#discussion_r597997690
##########
File path:
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/HoodieMergeHandle.java
##########
@@ -394,4 +405,36 @@ public IOType getIOType() {
public HoodieBaseFile baseFileForMerge() {
return baseFileToMerge;
}
+
+ /**
+ * A special record returned by {@link HoodieRecordPayload}, which means
+ * {@link HoodieMergeHandle} should just skip this record.
+ */
+ private static class IgnoreRecord implements GenericRecord {
Review comment:
want to understand the need for this better.
##########
File path:
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/io/HoodieWriteHandle.java
##########
@@ -54,9 +53,18 @@
public abstract class HoodieWriteHandle<T extends HoodieRecordPayload, I, K,
O> extends HoodieIOHandle<T, I, K, O> {
private static final Logger LOG =
LogManager.getLogger(HoodieWriteHandle.class);
+ /**
+ * The input schema of the incoming dataframe.
+ */
+ protected final Schema inputSchema;
Review comment:
as we discussed in the other PR, we typically call this the `writeSchema`
##########
File path:
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/HoodieBaseSqlTest.scala
##########
@@ -0,0 +1,72 @@
+/*
+ * 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.hudi
+
+import java.io.File
+
+import org.apache.spark.sql.{Row, SparkSession}
+import org.apache.spark.util.Utils
+import org.scalactic.source
+import org.scalatest.{BeforeAndAfterAll, FunSuite, Tag}
+
+class HoodieBaseSqlTest extends FunSuite with BeforeAndAfterAll {
Review comment:
can we start all test classes using `Testxxxx` convention. Thats what
we use throughout the project.
##########
File path:
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/keygen/UuidKeyGenerator.java
##########
@@ -0,0 +1,52 @@
+/*
+ * 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.hudi.keygen;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.UUID;
+import java.util.stream.Collectors;
+import org.apache.avro.generic.GenericRecord;
+import org.apache.hudi.common.config.TypedProperties;
+import org.apache.hudi.keygen.constant.KeyGeneratorOptions;
+
+/**
+ * A KeyGenerator which use the uuid as the record key.
+ */
+public class UuidKeyGenerator extends BuiltinKeyGenerator {
Review comment:
to revisit why we want this.
##########
File path: hudi-spark-datasource/hudi-spark2/src/main/antlr4/imports/SqlBase.g4
##########
@@ -0,0 +1,1099 @@
+/*
+ * Licensed 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.
+ *
+ * This file is an adaptation of Presto's
presto-parser/src/main/antlr4/com/facebook/presto/sql/parser/SqlBase.g4 grammar.
Review comment:
I thought we planned to just use Spark SQL keywords and limit to Spark3
(which should already recognize delete/merge?). Is antlr really needed for the
first pass?
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/table/HoodieTableMetaClient.java
##########
@@ -617,6 +619,16 @@ public PropertyBuilder setTableName(String tableName) {
return this;
}
+ public PropertyBuilder setTableSchema(String tableSchema) {
+ this.tableSchema = tableSchema;
+ return this;
+ }
+
+ public PropertyBuilder setRowKeyFields(String rowKeyFields) {
Review comment:
Can we just persist the key generator class? this kind of assumes that
keys are actually present right in the table schema?
##########
File path:
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/HoodieSparkSessionExtension.scala
##########
@@ -0,0 +1,48 @@
+/*
+ * 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.hudi
+
+import org.apache.spark.SPARK_VERSION
+import org.apache.spark.sql.SparkSessionExtensions
+import org.apache.spark.sql.hudi.analysis.HoodieAnalysis
+import org.apache.spark.sql.hudi.parser.HoodieSqlParser
+
+/**
+ * The Hoodie SparkSessionExtension for extending the syntax and add the
rules.
+ */
+class HoodieSparkSessionExtension extends (SparkSessionExtensions => Unit) {
+ override def apply(extensions: SparkSessionExtensions): Unit = {
+ if (SPARK_VERSION.startsWith("2.")) {
Review comment:
is the injection of antlr parse done only for spark2?
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/table/HoodieTableMetaClient.java
##########
@@ -617,6 +619,16 @@ public PropertyBuilder setTableName(String tableName) {
return this;
}
+ public PropertyBuilder setTableSchema(String tableSchema) {
Review comment:
I am not sure if this has to go into hoodie.properties. we want schema
to be somthing that can overtime.
--
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.
For queries about this service, please contact Infrastructure at:
[email protected]
