Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/13431#discussion_r65305575 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/text/TextFileFormat.scala --- @@ -96,16 +96,23 @@ class TextFileFormat extends FileFormat with DataSourceRegister { sparkSession.sparkContext.broadcast(new SerializableConfiguration(hadoopConf)) (file: PartitionedFile) => { - val unsafeRow = new UnsafeRow(1) - val bufferHolder = new BufferHolder(unsafeRow) - val unsafeRowWriter = new UnsafeRowWriter(bufferHolder, 1) - - new HadoopFileLinesReader(file, broadcastedHadoopConf.value.value).map { line => - // Writes to an UnsafeRow directly - bufferHolder.reset() - unsafeRowWriter.write(0, line.getBytes, 0, line.getLength) - unsafeRow.setTotalSize(bufferHolder.totalSize()) - unsafeRow + val reader = new HadoopFileLinesReader(file, broadcastedHadoopConf.value.value) + + if (requiredSchema.isEmpty) { --- End diff -- should we put this `if` out of the returned function?
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org