Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/17253#discussion_r105526080 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileScanRDD.scala --- @@ -130,54 +144,35 @@ class FileScanRDD( // Sets InputFileBlockHolder for the file block's information InputFileBlockHolder.set(currentFile.filePath, currentFile.start, currentFile.length) - try { - if (ignoreCorruptFiles) { - currentIterator = new NextIterator[Object] { - private val internalIter = { - try { - // The readFunction may read files before consuming the iterator. - // E.g., vectorized Parquet reader. - readFunction(currentFile) - } catch { - case e @(_: RuntimeException | _: IOException) => - logWarning(s"Skipped the rest content in the corrupted file: $currentFile", e) - Iterator.empty - } - } - - override def getNext(): AnyRef = { - try { - if (internalIter.hasNext) { - internalIter.next() - } else { - finished = true - null - } - } catch { - case e: IOException => - logWarning(s"Skipped the rest content in the corrupted file: $currentFile", e) - finished = true - null + if (ignoreCorruptFiles) { + currentIterator = new NextIterator[Object] { + // The readFunction may read some bytes before consuming the iterator, e.g., + // vectorized Parquet reader. Here we use lazy val to delay the creation of + // iterator so that we will throw exception in `getNext`. + private lazy val internalIter = readCurrentFile() + + override def getNext(): AnyRef = { + try { + if (internalIter.hasNext) { + internalIter.next() + } else { + finished = true + null } + } catch { + // Throw FileNotFoundException even `ignoreCorruptFiles` is true + case e: java.io.FileNotFoundException => throw e --- End diff -- `FileNotFoundException` extends `IOException`
--- 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