xiarixiaoyao commented on a change in pull request #4013:
URL: https://github.com/apache/hudi/pull/4013#discussion_r753758254
##########
File path:
hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/TestOptimizeTable.scala
##########
@@ -88,19 +88,28 @@ class TestOptimizeTable extends HoodieClientTestBase {
.save(basePath)
assertEquals(1000, spark.read.format("hudi").load(basePath).count())
+ // use unsorted col as filter.
assertEquals(1000,
- spark.read.option(DataSourceReadOptions.ENABLE_DATA_SKIPPING.key(),
"true").format("hudi").load(basePath).count())
+ spark.read.option(DataSourceReadOptions.ENABLE_DATA_SKIPPING.key(),
"true")
+ .format("hudi").load(basePath).where("end_lat >= 0").count())
+ // use sorted col as filter.
+ assertEquals(1000,
+ spark.read.option(DataSourceReadOptions.ENABLE_DATA_SKIPPING.key(),
"true")
+ .format("hudi").load(basePath).where("begin_lon >= 0").count())
}
@Test
def testCollectMinMaxStatistics(): Unit = {
val testPath = new Path(System.getProperty("java.io.tmpdir"), "minMax")
val statisticPath = new Path(System.getProperty("java.io.tmpdir"), "stat")
val fs = testPath.getFileSystem(spark.sparkContext.hadoopConfiguration)
+ val complexDataFrame = createComplexDataFrame(spark)
+
complexDataFrame.repartition(3).write.mode("overwrite").save(testPath.toString)
+ val df = spark.read.load(testPath.toString)
try {
- val complexDataFrame = createComplexDataFrame(spark)
-
complexDataFrame.repartition(3).write.mode("overwrite").save(testPath.toString)
- val df = spark.read.load(testPath.toString)
+ // test z-order sort for all primitive type, should not throw error.
Review comment:
fixed.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
