alexeykudinkin commented on code in PR #6358:
URL: https://github.com/apache/hudi/pull/6358#discussion_r1024677695
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieSparkSqlWriter.scala:
##########
@@ -347,6 +378,95 @@ object HoodieSparkSqlWriter {
}
}
+ /**
+ * Deduces writer's schema based on
+ * <ul>
+ * <li>Source's schema</li>
+ * <li>Target table's schema (including Hudi's [[InternalSchema]]
representation)</li>
+ * </ul>
+ */
+ def deduceWriterSchema(sourceSchema: Schema,
+ latestTableSchemaOpt: Option[Schema],
+ internalSchemaOpt: Option[InternalSchema],
+ opts: Map[String, String]): Schema = {
+ val shouldReconcileSchema =
opts(DataSourceWriteOptions.RECONCILE_SCHEMA.key()).toBoolean
+ val shouldValidateSchemasCompatibility =
opts.getOrDefault(HoodieWriteConfig.AVRO_SCHEMA_VALIDATE_ENABLE.key,
+ HoodieWriteConfig.AVRO_SCHEMA_VALIDATE_ENABLE.defaultValue).toBoolean
+
+ latestTableSchemaOpt match {
Review Comment:
1. There's nothing to canonicalize against for the 1st commit (we simply
take incoming schema as canonical one)
2. This is an issue that is addressed by this PR
--
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]
