You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2018/12/31 00:33:44 UTC
[GitHub] srowen commented on a change in pull request #23417:
[SPARK-26374][TEST][SQL] Enable TimestampFormatter in HadoopFsRelationTest
srowen commented on a change in pull request #23417: [SPARK-26374][TEST][SQL] Enable TimestampFormatter in HadoopFsRelationTest
URL: https://github.com/apache/spark/pull/23417#discussion_r244549254
##########
File path: sql/hive/src/test/scala/org/apache/spark/sql/sources/HadoopFsRelationTest.scala
##########
@@ -126,61 +126,60 @@ abstract class HadoopFsRelationTest extends QueryTest with SQLTestUtils with Tes
} else {
Seq(false)
}
- // TODO: Support new parser too, see SPARK-26374.
- withSQLConf(SQLConf.LEGACY_TIME_PARSER_ENABLED.key -> "true") {
- for (dataType <- supportedDataTypes) {
- for (parquetDictionaryEncodingEnabled <- parquetDictionaryEncodingEnabledConfs) {
- val extraMessage = if (isParquetDataSource) {
- s" with parquet.enable.dictionary = $parquetDictionaryEncodingEnabled"
- } else {
- ""
- }
- logInfo(s"Testing $dataType data type$extraMessage")
-
- val extraOptions = Map[String, String](
- "parquet.enable.dictionary" -> parquetDictionaryEncodingEnabled.toString
- )
-
- withTempPath { file =>
- val path = file.getCanonicalPath
-
- val seed = System.nanoTime()
- withClue(s"Random data generated with the seed: ${seed}") {
- val dataGenerator = RandomDataGenerator.forType(
- dataType = dataType,
- nullable = true,
- new Random(seed)
- ).getOrElse {
- fail(s"Failed to create data generator for schema $dataType")
- }
-
- // Create a DF for the schema with random data. The index field is used to sort the
- // DataFrame. This is a workaround for SPARK-10591.
- val schema = new StructType()
- .add("index", IntegerType, nullable = false)
- .add("col", dataType, nullable = true)
- val rdd =
- spark.sparkContext.parallelize((1 to 10).map(i => Row(i, dataGenerator())))
- val df = spark.createDataFrame(rdd, schema).orderBy("index").coalesce(1)
-
- df.write
- .mode("overwrite")
- .format(dataSourceName)
- .option("dataSchema", df.schema.json)
- .options(extraOptions)
- .save(path)
-
- val loadedDF = spark
- .read
- .format(dataSourceName)
- .option("dataSchema", df.schema.json)
- .schema(df.schema)
- .options(extraOptions)
- .load(path)
- .orderBy("index")
-
- checkAnswer(loadedDF, df)
+
+ for (dataType <- supportedDataTypes) {
+ for (parquetDictionaryEncodingEnabled <- parquetDictionaryEncodingEnabledConfs) {
+ val extraMessage = if (isParquetDataSource) {
+ s" with parquet.enable.dictionary = $parquetDictionaryEncodingEnabled"
+ } else {
+ ""
+ }
+ logInfo(s"Testing $dataType data type$extraMessage")
+
+ val extraOptions = Map[String, String](
+ "parquet.enable.dictionary" -> parquetDictionaryEncodingEnabled.toString,
+ "timestampFormat" -> "yyyy-MM-dd'T'HH:mm:ss.SSSXXXXX"
Review comment:
Ah, this is the fix? Great, looks good. Should this... be a default? You know much more about it than I do right now.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org