Github user lw-lin commented on a diff in the pull request: https://github.com/apache/spark/pull/17070#discussion_r103102422 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/HDFSMetadataLog.scala --- @@ -268,6 +274,37 @@ class HDFSMetadataLog[T <: AnyRef : ClassTag](sparkSession: SparkSession, path: new FileSystemManager(metadataPath, hadoopConf) } } + + /** + * Parse the log version from the given `text` -- will throw exception when the parsed version + * exceeds `maxSupportedVersion`, or when `text` is malformed (such as "xyz", "v", "v-1", + * "v123xyz" etc.) + */ + private[sql] def parseVersion(text: String, maxSupportedVersion: Int): Int = { + if (text.length > 0 && text(0) == 'v') { + val version = + try { text.substring(1, text.length).toInt } + catch { + case _: NumberFormatException => + throw new IllegalStateException(s"Log file was malformed: failed to read correct log " + + s"version from $text.") + } + if (version > 0) { + if (version > maxSupportedVersion) { + throw new IllegalStateException(s"UnsupportedLogVersion: maximum supported log version " + + s"is v${maxSupportedVersion}, but encountered v$version. The log file was produced " + + s"by a newer version of Spark and cannot be read by this version. Please upgrade.") + } + else { --- End diff -- done
--- 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