razajafri commented on a change in pull request #31284:
URL: https://github.com/apache/spark/pull/31284#discussion_r568824046
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetIOSuite.scala
##########
@@ -1205,6 +1205,32 @@ class ParquetIOSuite extends QueryTest with ParquetTest
with SharedSparkSession
}
}
}
+
+ test("SPARK-34167: read LongDecimals with precision < 10, VectorizedReader
off") {
+ // decimal32-written-as-64-bit.snappy.parquet was generated using a
3rd-party library. It has
+ // 10 rows of Decimal(9, 1) written as LongDecimal instead of an IntDecimal
+
readParquetFile(testFile("test-data/decimal32-written-as-64-bit.snappy.parquet"),
false) {
+ df => assert(10 == df.collect().length)
+ }
+ // decimal32-written-as-64-bit-dict.snappy.parquet was generated using a
3rd-party library. It
+ // has 2048 rows of Decimal(3, 1) written as LongDecimal instead of an
IntDecimal
+
readParquetFile(testFile("test-data/decimal32-written-as-64-bit-dict.snappy.parquet"),
false) {
+ df => assert(2048 == df.collect().length)
+ }
+ }
+
+ test("SPARK-34167: read LongDecimals with precision < 10, VectorizedReader
on") {
+ // decimal32-written-as-64-bit.snappy.parquet was generated using a
3rd-party library. It has
+ // 10 rows of Decimal(9, 1) written as LongDecimal instead of an IntDecimal
+
readParquetFile(testFile("test-data/decimal32-written-as-64-bit.snappy.parquet"))
{ df =>
Review comment:
no, it uses the GPU to write the file.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
