lokeshj1703 commented on code in PR #11816:
URL: https://github.com/apache/hudi/pull/11816#discussion_r1753774436
##########
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/keygen/KeyGenUtils.java:
##########
@@ -66,29 +66,25 @@ public class KeyGenUtils {
public static KeyGeneratorType inferKeyGeneratorType(
Option<String> recordsKeyFields, String partitionFields) {
boolean autoGenerateRecordKeys = !recordsKeyFields.isPresent();
- if (autoGenerateRecordKeys) {
- return inferKeyGeneratorTypeForAutoKeyGen(partitionFields);
- } else {
- if (!StringUtils.isNullOrEmpty(partitionFields)) {
- int numPartFields = partitionFields.split(",").length;
- int numRecordKeyFields = recordsKeyFields.get().split(",").length;
- if (numPartFields == 1 && numRecordKeyFields == 1) {
- return KeyGeneratorType.SIMPLE;
- }
- return KeyGeneratorType.COMPLEX;
- }
- return KeyGeneratorType.NON_PARTITION;
+ KeyGeneratorType partitionKeyGeneratorType =
inferKeyGeneratorTypeFromPartitionFields(partitionFields);
+ if (autoGenerateRecordKeys || partitionKeyGeneratorType !=
KeyGeneratorType.SIMPLE) {
+ return partitionKeyGeneratorType;
}
+ int numRecordKeyFields = recordsKeyFields.get().split(",").length;
+ return numRecordKeyFields == 1 ? KeyGeneratorType.SIMPLE :
KeyGeneratorType.COMPLEX;
}
// When auto record key gen is enabled, our inference will be based on
partition path only.
- private static KeyGeneratorType inferKeyGeneratorTypeForAutoKeyGen(String
partitionFields) {
+ static KeyGeneratorType inferKeyGeneratorTypeFromPartitionFields(String
partitionFields) {
if (!StringUtils.isNullOrEmpty(partitionFields)) {
- int numPartFields = partitionFields.split(",").length;
- if (numPartFields == 1) {
+ String[] partitonFields = partitionFields.split(",");
+ if
(partitonFields[0].contains(BaseKeyGenerator.CUSTOM_KEY_GENERATOR_SPLIT_REGEX))
{
+ return KeyGeneratorType.CUSTOM;
Review Comment:
I did not find similar logic for other engines. It seems like the same logic
is reused based on
`org.apache.hudi.DataSourceWriteOptions#KEYGENERATOR_CLASS_NAME`
--
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]
