linliu-code commented on code in PR #10137: URL: https://github.com/apache/hudi/pull/10137#discussion_r1409955152
########## hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/SparkFileFormatInternalRowReaderContext.scala: ########## @@ -77,14 +78,18 @@ class SparkFileFormatInternalRowReaderContext(baseFileReader: Option[Partitioned } }).asInstanceOf[ClosableIterator[InternalRow]] } else { - if (baseFileReader.isEmpty) { - throw new IllegalArgumentException("Base file reader is missing when instantiating " - + "SparkFileFormatInternalRowReaderContext."); + val key = generateKey(dataSchema, requiredSchema) + if (!readerMaps.contains(key)) { + throw new IllegalStateException("schemas don't hash to a known reader") } - new CloseableInternalRowIterator(baseFileReader.get.apply(fileInfo)) + new CloseableInternalRowIterator(readerMaps(key).apply(fileInfo)) } } + private def generateKey(dataSchema: Schema, requestedSchema: Schema): Long = { Review Comment: Hi Jon, i really feel that if you can split this PR into smaller PRs, that would be much easier for reviewers to understand and easier for the CI to pass. -- 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: commits-unsubscr...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org