Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/21829#discussion_r204100563 --- Diff: external/avro/src/main/scala/org/apache/spark/sql/avro/AvroOutputWriterFactory.scala --- @@ -17,21 +17,24 @@ package org.apache.spark.sql.avro +import org.apache.avro.Schema import org.apache.hadoop.mapreduce.TaskAttemptContext import org.apache.spark.sql.execution.datasources.{OutputWriter, OutputWriterFactory} import org.apache.spark.sql.types.StructType private[avro] class AvroOutputWriterFactory( schema: StructType, - avroSchema: SerializableSchema) extends OutputWriterFactory { + avroJsonSchema: String) extends OutputWriterFactory { + + private lazy val avroSchema = new Schema.Parser().parse(avroJsonSchema) --- End diff -- the naming is confusing. We have `schema`, `avroJsonSchema` and `avroSchema`. Also add comments about these variables.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org