nsivabalan commented on code in PR #10677:
URL: https://github.com/apache/hudi/pull/10677#discussion_r1503040143
##########
hudi-common/src/main/java/org/apache/hudi/avro/AvroSchemaUtils.java:
##########
@@ -428,25 +408,95 @@ public static void checkSchemaCompatible(
boolean allowProjection,
Set<String> dropPartitionColNames) throws SchemaCompatibilityException {
- String errorMessage = null;
-
- if (!allowProjection && !canProject(tableSchema, writerSchema,
dropPartitionColNames)) {
- errorMessage = "Column dropping is not allowed";
+ if (!allowProjection) {
+ List<Schema.Field> missingFields = findMissingFields(tableSchema,
writerSchema, dropPartitionColNames);
+ if (!missingFields.isEmpty()) {
+ throw new
MissingSchemaFieldException(missingFields.stream().map(Schema.Field::name).collect(Collectors.toList()));
+ }
}
// TODO(HUDI-4772) re-enable validations in case partition columns
// being dropped from the data-file after fixing the write
schema
- if (dropPartitionColNames.isEmpty() && shouldValidate &&
!isSchemaCompatible(tableSchema, writerSchema)) {
- errorMessage = "Failed schema compatibility check";
+ if (dropPartitionColNames.isEmpty() && shouldValidate) {
+ AvroSchemaCompatibility.SchemaPairCompatibility result =
+ AvroSchemaCompatibility.checkReaderWriterCompatibility(writerSchema,
tableSchema, true);
+ if (result.getType() !=
AvroSchemaCompatibility.SchemaCompatibilityType.COMPATIBLE) {
+ throw new SchemaBackwardsCompatibilityException(result);
+ }
}
+ }
- if (errorMessage != null) {
- String errorDetails = String.format(
- "%s\nwriterSchema: %s\ntableSchema: %s",
- errorMessage,
- writerSchema,
- tableSchema);
- throw new SchemaCompatibilityException(errorDetails);
+ /**
+ * Validate whether the {@code incomingSchema} is a valid evolution of
{@code tableSchema}.
+ *
+ * @param incomingSchema schema of the incoming dataset
+ * @param tableSchema latest table schema
+ */
+ public static void checkValidEvolution(Schema incomingSchema, Schema
tableSchema) {
Review Comment:
+1 in addition to explicitly calling out the mis-aligning fields, we could
also print the entire schema.
##########
hudi-common/src/main/java/org/apache/hudi/exception/MissingSchemaFieldException.java:
##########
@@ -0,0 +1,36 @@
+/*
+ * 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.exception;
+
+import java.util.List;
+
+/**
+ * Thrown when the schema of the incoming data is missing fields that are in
the table schema.
+ */
+public class MissingSchemaFieldException extends SchemaCompatibilityException {
Review Comment:
yes, lets ensure we revisit them all and remove unnecessary ones. we should
have SchemaCompatibilityException at the top, and we can have subclasses that
extends from this class for specific exceptions.
--
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]
