@@ -2870,18 +2870,10 @@ index 3072657a095..599d169cf8a 100644
28702870 checkAnswer(
28712871 // "fruit" column in this file is encoded using DELTA_LENGTH_BYTE_ARRAY.
28722872diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala
2873- index c530dc0d3df..cf073150fd1 100644
2873+ index c530dc0d3df..d23069689da 100644
28742874--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala
28752875+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetQuerySuite.scala
2876- @@ -27,6 +27,7 @@ import org.apache.parquet.hadoop.ParquetOutputFormat
2877-
2878- import org.apache.spark.{DebugFilesystem, SparkConf, SparkException}
2879- import org.apache.spark.sql._
2880- + import org.apache.spark.sql.IgnoreCometNativeDataFusion
2881- import org.apache.spark.sql.catalyst.{InternalRow, TableIdentifier}
2882- import org.apache.spark.sql.catalyst.expressions.SpecificInternalRow
2883- import org.apache.spark.sql.catalyst.util.ArrayData
2884- @@ -996,7 +997,11 @@ abstract class ParquetQuerySuite extends QueryTest with ParquetTest with SharedS
2876+ @@ -996,7 +996,11 @@ abstract class ParquetQuerySuite extends QueryTest with ParquetTest with SharedS
28852877 Seq(Some("A"), Some("A"), None).toDF().repartition(1)
28862878 .write.parquet(path.getAbsolutePath)
28872879 val df = spark.read.parquet(path.getAbsolutePath)
@@ -2894,17 +2886,7 @@ index c530dc0d3df..cf073150fd1 100644
28942886 }
28952887 }
28962888 }
2897- @@ -1042,7 +1047,8 @@ abstract class ParquetQuerySuite extends QueryTest with ParquetTest with SharedS
2898- testMigration(fromTsType = "TIMESTAMP_MICROS", toTsType = "INT96")
2899- }
2900-
2901- - test("SPARK-34212 Parquet should read decimals correctly") {
2902- + test("SPARK-34212 Parquet should read decimals correctly",
2903- + IgnoreCometNativeDataFusion("https://github.com/apache/datafusion-comet/issues/4343")) {
2904- def readParquet(schema: String, path: File): DataFrame = {
2905- spark.read.schema(schema).parquet(path.toString)
2906- }
2907- @@ -1060,7 +1066,8 @@ abstract class ParquetQuerySuite extends QueryTest with ParquetTest with SharedS
2889+ @@ -1060,7 +1064,8 @@ abstract class ParquetQuerySuite extends QueryTest with ParquetTest with SharedS
29082890 checkAnswer(readParquet(schema2, path), df)
29092891 }
29102892
@@ -2914,7 +2896,7 @@ index c530dc0d3df..cf073150fd1 100644
29142896 val schema1 = "a DECIMAL(3, 2), b DECIMAL(18, 3), c DECIMAL(37, 3)"
29152897 checkAnswer(readParquet(schema1, path), df)
29162898 val schema2 = "a DECIMAL(3, 0), b DECIMAL(18, 1), c DECIMAL(37, 1)"
2917- @@ -1084,7 +1091 ,8 @@ abstract class ParquetQuerySuite extends QueryTest with ParquetTest with SharedS
2899+ @@ -1084,7 +1089 ,8 @@ abstract class ParquetQuerySuite extends QueryTest with ParquetTest with SharedS
29182900 val df = sql(s"SELECT 1 a, 123456 b, ${Int.MaxValue.toLong * 10} c, CAST('1.2' AS BINARY) d")
29192901 df.write.parquet(path.toString)
29202902
@@ -3054,18 +3036,9 @@ index 56076175d60..5872d9962cc 100644
30543036 val e = testSchemaMismatch(dir.getCanonicalPath, vectorizedReaderEnabled = true)
30553037 assert(e.getCause.isInstanceOf[SchemaColumnConvertNotSupportedException])
30563038diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetTypeWideningSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetTypeWideningSuite.scala
3057- index 09ed6955a51..6b5be93cffd 100644
3039+ index 09ed6955a51..236a4e99824 100644
30583040--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetTypeWideningSuite.scala
30593041+++ b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetTypeWideningSuite.scala
3060- @@ -24,7 +24,7 @@ import org.apache.parquet.format.converter.ParquetMetadataConverter
3061- import org.apache.parquet.hadoop.{ParquetFileReader, ParquetOutputFormat}
3062-
3063- import org.apache.spark.SparkException
3064- - import org.apache.spark.sql.{DataFrame, QueryTest, Row}
3065- + import org.apache.spark.sql.{DataFrame, IgnoreCometNativeDataFusion, QueryTest, Row}
3066- import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanHelper
3067- import org.apache.spark.sql.execution.datasources.SchemaColumnConvertNotSupportedException
3068- import org.apache.spark.sql.functions.col
30693042@@ -65,7 +65,9 @@ class ParquetTypeWideningSuite
30703043 withClue(
30713044 s"with dictionary encoding '$dictionaryEnabled' with timestamp rebase mode " +
@@ -3096,56 +3069,6 @@ index 09ed6955a51..6b5be93cffd 100644
30963069 )
30973070 }
30983071 test(s"parquet widening conversion $fromType -> $toType") {
3099- @@ -231,7 +234,8 @@ class ParquetTypeWideningSuite
3100- (Seq("2020-01-01", "2020-01-02", "1312-02-27"), DateType, TimestampType)
3101- )
3102- }
3103- - test(s"unsupported parquet conversion $fromType -> $toType") {
3104- + test(s"unsupported parquet conversion $fromType -> $toType",
3105- + IgnoreCometNativeDataFusion("https://github.com/apache/datafusion-comet/issues/4297")) {
3106- checkAllParquetReaders(values, fromType, toType, expectError = true)
3107- }
3108-
3109- @@ -257,7 +261,8 @@ class ParquetTypeWideningSuite
3110- (Seq("1", "2"), LongType, DecimalType(LongDecimal.precision, 1))
3111- )
3112- }
3113- - test(s"unsupported parquet conversion $fromType -> $toType") {
3114- + test(s"unsupported parquet conversion $fromType -> $toType",
3115- + IgnoreCometNativeDataFusion("https://github.com/apache/datafusion-comet/issues/4344")) {
3116- checkAllParquetReaders(values, fromType, toType,
3117- expectError =
3118- // parquet-mr allows reading decimals into a smaller precision decimal type without
3119- @@ -271,7 +276,8 @@ class ParquetTypeWideningSuite
3120- (Seq("2020-01-01", "2020-01-02", "1312-02-27"), TimestampNTZType, DateType))
3121- outputTimestampType <- ParquetOutputTimestampType.values
3122- }
3123- - test(s"unsupported parquet timestamp conversion $fromType ($outputTimestampType) -> $toType") {
3124- + test(s"unsupported parquet timestamp conversion $fromType ($outputTimestampType) -> $toType",
3125- + IgnoreCometNativeDataFusion("https://github.com/apache/datafusion-comet/issues/4297")) {
3126- withSQLConf(
3127- SQLConf.PARQUET_OUTPUT_TIMESTAMP_TYPE.key -> outputTimestampType.toString,
3128- SQLConf.PARQUET_INT96_REBASE_MODE_IN_WRITE.key -> LegacyBehaviorPolicy.CORRECTED.toString
3129- @@ -291,7 +297,8 @@ class ParquetTypeWideningSuite
3130- Seq(7 -> 5, 10 -> 5, 20 -> 5, 12 -> 10, 20 -> 10, 22 -> 20)
3131- }
3132- test(
3133- - s"parquet decimal precision change Decimal($fromPrecision, 2) -> Decimal($toPrecision, 2)") {
3134- + s"parquet decimal precision change Decimal($fromPrecision, 2) -> Decimal($toPrecision, 2)",
3135- + IgnoreCometNativeDataFusion("https://github.com/apache/datafusion-comet/issues/4343")) {
3136- checkAllParquetReaders(
3137- values = Seq("1.23", "10.34"),
3138- fromType = DecimalType(fromPrecision, 2),
3139- @@ -322,7 +329,8 @@ class ParquetTypeWideningSuite
3140- Seq((5, 2) -> (6, 4), (10, 4) -> (12, 7), (20, 5) -> (22, 8))
3141- }
3142- test(s"parquet decimal precision and scale change Decimal($fromPrecision, $fromScale) -> " +
3143- - s"Decimal($toPrecision, $toScale)"
3144- + s"Decimal($toPrecision, $toScale)",
3145- + IgnoreCometNativeDataFusion("https://github.com/apache/datafusion-comet/issues/4343")
3146- ) {
3147- checkAllParquetReaders(
3148- values = Seq("1.23", "10.34"),
31493072diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetVariantShreddingSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetVariantShreddingSuite.scala
31503073index 1cc6d3afbee..8275727fbb4 100644
31513074--- a/sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetVariantShreddingSuite.scala
0 commit comments