sandip-db commented on code in PR #44163: URL: https://github.com/apache/spark/pull/44163#discussion_r1414522386
########## sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/xml/XmlSuite.scala: ########## @@ -2178,4 +2186,58 @@ class XmlSuite extends QueryTest with SharedSparkSession { ) testWriteReadRoundTrip(df, Map("nullValue" -> "null", "prefersDecimal" -> "true")) } + + test("Enabling/disabling ignoreCorruptFiles/ignoreMissingFiles") { + withCorruptFile(inputFile => { + withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "false") { + val e = intercept[SparkException] { + spark.read.option("rowTag", "ROW").xml(inputFile.toURI.toString).collect() + } + assert(ExceptionUtils.getRootCause(e).isInstanceOf[EOFException]) + assert(ExceptionUtils.getRootCause(e).getMessage === "Unexpected end of input stream") + val e2 = intercept[SparkException] { + spark.read + .option("rowTag", "ROW") + .option("multiLine", true) + .xml(inputFile.toURI.toString) + .collect() + } + assert(ExceptionUtils.getRootCause(e2).isInstanceOf[EOFException]) + assert(ExceptionUtils.getRootCause(e2).getMessage === "Unexpected end of input stream") + } + withSQLConf(SQLConf.IGNORE_CORRUPT_FILES.key -> "true") { + assert(spark.read.option("rowTag", "ROW").xml(inputFile.toURI.toString).collect().isEmpty) + assert( Review Comment: Not sure how this is working without `ignoreCorruptFiles` handling in `XMLDataSource`. -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org