Skip to content

chore: Add ignored tests for reading complex types from Parquet #1167

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Dec 12, 2024
Merged

chore: Add ignored tests for reading complex types from Parquet #1167

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1ad3eb0
Add ignored tests for reading structs from Parquet
andygrove Dec 12, 2024
27d3f80
add basic map test
andygrove Dec 12, 2024
b0ad61c
add tests for Map and Array
andygrove Dec 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
127 changes: 127 additions & 0 deletions spark/src/test/scala/org/apache/comet/CometExpressionSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2195,6 +2195,133 @@ class CometExpressionSuite extends CometTestBase with AdaptiveSparkPlanHelper {
}
}

ignore("get_struct_field - select primitive fields") {
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe we can consider to move complex type tests to other test suites later.

withTempPath { dir =>
// create input file with Comet disabled
withSQLConf(CometConf.COMET_ENABLED.key -> "false") {
val df = spark
.range(5)
// Add both a null struct and null inner value
.select(when(col("id") > 1, struct(when(col("id") > 2, col("id")).alias("id")))
.alias("nested1"))

df.write.parquet(dir.toString())
}

Seq("", "parquet").foreach { v1List =>
withSQLConf(SQLConf.USE_V1_SOURCE_LIST.key -> v1List) {
val df = spark.read.parquet(dir.toString())
checkSparkAnswerAndOperator(df.select("nested1.id"))
}
}
}
}

ignore("get_struct_field - select subset of struct") {
withTempPath { dir =>
// create input file with Comet disabled
withSQLConf(CometConf.COMET_ENABLED.key -> "false") {
val df = spark
.range(5)
// Add both a null struct and null inner value
.select(
when(
col("id") > 1,
struct(
when(col("id") > 2, col("id")).alias("id"),
when(col("id") > 2, struct(when(col("id") > 3, col("id")).alias("id")))
.as("nested2")))
.alias("nested1"))

df.write.parquet(dir.toString())
}

Seq("", "parquet").foreach { v1List =>
withSQLConf(SQLConf.USE_V1_SOURCE_LIST.key -> v1List) {
val df = spark.read.parquet(dir.toString())
checkSparkAnswerAndOperator(df.select("nested1.id"))
checkSparkAnswerAndOperator(df.select("nested1.nested2"))
checkSparkAnswerAndOperator(df.select("nested1.nested2.id"))
checkSparkAnswerAndOperator(df.select("nested1.id", "nested1.nested2.id"))
}
}
}
}

ignore("get_struct_field - read entire struct") {
withTempPath { dir =>
// create input file with Comet disabled
withSQLConf(CometConf.COMET_ENABLED.key -> "false") {
val df = spark
.range(5)
// Add both a null struct and null inner value
.select(
when(
col("id") > 1,
struct(
when(col("id") > 2, col("id")).alias("id"),
when(col("id") > 2, struct(when(col("id") > 3, col("id")).alias("id")))
.as("nested2")))
.alias("nested1"))

df.write.parquet(dir.toString())
}

Seq("", "parquet").foreach { v1List =>
withSQLConf(SQLConf.USE_V1_SOURCE_LIST.key -> v1List) {
val df = spark.read.parquet(dir.toString())
checkSparkAnswerAndOperator(df.select("nested1"))
}
}
}
}

ignore("read map[int, int] from parquet") {
withTempPath { dir =>
// create input file with Comet disabled
withSQLConf(CometConf.COMET_ENABLED.key -> "false") {
val df = spark
.range(5)
// Spark does not allow null as a key but does allow null as a
// value, and the entire map be null
.select(
when(col("id") > 1, map(col("id"), when(col("id") > 2, col("id")))).alias("map1"))
df.write.parquet(dir.toString())
}

Seq("", "parquet").foreach { v1List =>
withSQLConf(SQLConf.USE_V1_SOURCE_LIST.key -> v1List) {
val df = spark.read.parquet(dir.toString())
checkSparkAnswerAndOperator(df.select("map1"))
checkSparkAnswerAndOperator(df.select(map_keys(col("map1"))))
checkSparkAnswerAndOperator(df.select(map_values(col("map1"))))
}
}
}
}

ignore("read array[int] from parquet") {
withTempPath { dir =>
// create input file with Comet disabled
withSQLConf(CometConf.COMET_ENABLED.key -> "false") {
val df = spark
.range(5)
// Spark does not allow null as a key but does allow null as a
// value, and the entire map be null
.select(when(col("id") > 1, sequence(lit(0), col("id") * 2)).alias("array1"))
df.write.parquet(dir.toString())
}

Seq("", "parquet").foreach { v1List =>
withSQLConf(SQLConf.USE_V1_SOURCE_LIST.key -> v1List) {
val df = spark.read.parquet(dir.toString())
checkSparkAnswerAndOperator(df.select("array1"))
checkSparkAnswerAndOperator(df.select(element_at(col("array1"), lit(1))))
}
}
}
}

test("CreateArray") {
Seq(true, false).foreach { dictionaryEnabled =>
withTempDir { dir =>
Expand Down
Loading