nsivabalan commented on code in PR #8107:
URL: https://github.com/apache/hudi/pull/8107#discussion_r1185755227
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieSparkSqlWriter.scala:
##########
@@ -1118,47 +1124,74 @@ object HoodieSparkSqlWriter {
Some(writerSchema))
avroRecords.mapPartitions(it => {
+ val sparkPartitionId = TaskContext.getPartitionId()
+ val keyGenProps = new TypedProperties(config.getProps)
+ if (autoGenerateRecordKeys) {
+
keyGenProps.setProperty(KeyGenUtils.RECORD_KEY_GEN_PARTITION_ID_CONFIG,
String.valueOf(sparkPartitionId))
+
keyGenProps.setProperty(KeyGenUtils.RECORD_KEY_GEN_INSTANT_TIME_CONFIG,
instantTime)
+ }
+ val keyGenerator =
HoodieSparkKeyGeneratorFactory.createKeyGenerator(keyGenProps)
+ .asInstanceOf[BaseKeyGenerator]
+
val dataFileSchema = new Schema.Parser().parse(dataFileSchemaStr)
val consistentLogicalTimestampEnabled = parameters.getOrElse(
DataSourceWriteOptions.KEYGENERATOR_CONSISTENT_LOGICAL_TIMESTAMP_ENABLED.key(),
DataSourceWriteOptions.KEYGENERATOR_CONSISTENT_LOGICAL_TIMESTAMP_ENABLED.defaultValue()).toBoolean
- it.map { avroRecord =>
+ val recordRecordKeyPairItr = it.map(avroRecord => {
+ (avroRecord, keyGenerator.getRecordKey(avroRecord))
+ })
Review Comment:
not required anymore. It was a residue from last clean up.
--
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]
