Github user aarondav commented on a diff in the pull request: https://github.com/apache/spark/pull/10805#discussion_r50206079 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVParameters.scala --- @@ -107,3 +114,28 @@ private[csv] object ParseModes { true // We default to permissive is the mode string is not valid } } + +private[csv] object CSVCompressionCodecs { + private val shortCompressionCodecNames = Map( + "bzip2" -> classOf[BZip2Codec].getName, + "gzip" -> classOf[GzipCodec].getName, + "lz4" -> classOf[Lz4Codec].getName, + "snappy" -> classOf[SnappyCodec].getName) + + /** + * Return the full version of the given codec class. + * If it is already a class name, just return it. + */ + def getCodecClassName(name: String): String = { + val codecName = shortCompressionCodecNames.getOrElse(name.toLowerCase, name) + val codecClassName = try { + // Validate the codec name + Utils.classForName(codecName) + Some(codecName) + } catch { + case e: ClassNotFoundException => None + } + codecClassName.getOrElse(throw new IllegalArgumentException(s"Codec [$codecName] " + + s"is not available. Available codecs are ${shortCompressionCodecNames.keys.mkString(", ")}.")) --- End diff -- Probably change Available -> Known (since there may be more available)
--- 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