Skip to content
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

Jump to bottom

[VL] Enable Spark functions for translate, add_months, array_min, array_max #3687

Merged
merged 4 commits into from
Nov 14, 2023
Merged

[VL] Enable Spark functions for translate, add_months, array_min, array_max #3687

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f61549d
Initial commit
PHILO-HE Nov 13, 2023
cd021dd
Ignore some tests
PHILO-HE Nov 13, 2023
ebb0d96
Fix date_format tests
PHILO-HE Nov 13, 2023
029f7ad
Move date_format back
PHILO-HE Nov 13, 2023
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
4 changes: 0 additions & 4 deletions cpp/velox/substrait/SubstraitToVeloxPlanValidator.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,15 +45,11 @@ static const std::unordered_set<std::string> kBlackList = {
"json_array_length",
"from_unixtime",
"repeat",
"translate",
"add_months",
"date_format",
"trunc",
"sequence",
"posexplode",
"arrays_overlap",
"array_min",
"array_max",
"approx_percentile"};

bool validateColNames(const ::substrait::NamedStruct& schema) {
Expand Down
1 change: 1 addition & 0 deletions ...-ut/spark32/src/test/scala/io/glutenproject/utils/clickhouse/ClickHouseTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -678,6 +678,7 @@ class ClickHouseTestSettings extends BackendTestSettings {
.exclude("WeekDay")
.exclude("WeekOfYear")
.exclude("DateFormat")
.exclude("Gluten - DateFormat")
.exclude("Hour")
.exclude("Minute")
.exclude("date add interval")
Expand Down
2 changes: 2 additions & 0 deletions gluten-ut/spark32/src/test/scala/io/glutenproject/utils/velox/VeloxTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,6 +207,8 @@ class VeloxTestSettings extends BackendTestSettings {
.exclude("to_unix_timestamp")
// Unsupported format: yyyy-MM-dd HH:mm:ss.SSS
.exclude("SPARK-33498: GetTimestamp,UnixTimestamp,ToUnixTimestamp with parseError")
// Replaced by a gluten test to pass timezone through config.
.exclude("DateFormat")
enableSuite[GlutenDecimalExpressionSuite]
enableSuite[GlutenStringFunctionsSuite]
enableSuite[GlutenRegexpExpressionsSuite]
Expand Down
5 changes: 3 additions & 2 deletions gluten-ut/spark32/src/test/scala/org/apache/spark/sql/GlutenSQLQueryTestSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -240,8 +240,9 @@ class GlutenSQLQueryTestSuite
"current_database_catalog.sql",
"date.sql",
"datetime-formatting-invalid.sql",
"datetime-formatting-legacy.sql",
"datetime-formatting.sql",
// Velox had different handling for some illegal cases.
// "datetime-formatting-legacy.sql",
// "datetime-formatting.sql",
"datetime-legacy.sql",
"datetime-parsing-invalid.sql",
"datetime-parsing-legacy.sql",
Expand Down
60 changes: 59 additions & 1 deletion ...src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenDateExpressionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ import org.apache.spark.sql.catalyst.util.DateTimeTestUtils._
import org.apache.spark.sql.catalyst.util.DateTimeUtils
import org.apache.spark.sql.catalyst.util.DateTimeUtils.{getZoneId, TimeZoneUTC}
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.{DateType, IntegerType, StringType}
import org.apache.spark.sql.types.{DateType, IntegerType, StringType, TimestampType}
import org.apache.spark.unsafe.types.UTF8String

import java.sql.{Date, Timestamp}
Expand Down Expand Up @@ -285,4 +285,62 @@ class GlutenDateExpressionsSuite extends DateExpressionsSuite with GlutenTestsTr
GenerateUnsafeProjection.generate(
ToUnixTimestamp(Literal("2015-07-24"), Literal("\""), UTC_OPT) :: Nil)
}

// Modified based on vanilla spark to explicitly set timezone in config.
test(GlutenTestConstants.GLUTEN_TEST + "DateFormat") {
val PST_OPT = Option(PST.getId)
val JST_OPT = Option(JST.getId)

Seq("legacy", "corrected").foreach {
legacyParserPolicy =>
withSQLConf(
SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy,
SQLConf.SESSION_LOCAL_TIMEZONE.key -> UTC_OPT.get) {
checkEvaluation(
DateFormatClass(Literal.create(null, TimestampType), Literal("y"), UTC_OPT),
null)
checkEvaluation(
DateFormatClass(
Cast(Literal(d), TimestampType, UTC_OPT),
Literal.create(null, StringType),
UTC_OPT),
null)

checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, UTC_OPT), Literal("y"), UTC_OPT),
"2015")
checkEvaluation(DateFormatClass(Literal(ts), Literal("y"), UTC_OPT), "2013")
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, UTC_OPT), Literal("H"), UTC_OPT),
"0")
checkEvaluation(DateFormatClass(Literal(ts), Literal("H"), UTC_OPT), "13")
}

withSQLConf(
SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy,
SQLConf.SESSION_LOCAL_TIMEZONE.key -> PST_OPT.get) {
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, PST_OPT), Literal("y"), PST_OPT),
"2015")
checkEvaluation(DateFormatClass(Literal(ts), Literal("y"), PST_OPT), "2013")
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, PST_OPT), Literal("H"), PST_OPT),
"0")
checkEvaluation(DateFormatClass(Literal(ts), Literal("H"), PST_OPT), "5")
}

withSQLConf(
SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy,
SQLConf.SESSION_LOCAL_TIMEZONE.key -> PST_OPT.get) {
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, JST_OPT), Literal("y"), JST_OPT),
"2015")
checkEvaluation(DateFormatClass(Literal(ts), Literal("y"), JST_OPT), "2013")
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, JST_OPT), Literal("H"), JST_OPT),
"0")
checkEvaluation(DateFormatClass(Literal(ts), Literal("H"), JST_OPT), "22")
}
}
}
}
1 change: 1 addition & 0 deletions ...-ut/spark33/src/test/scala/io/glutenproject/utils/clickhouse/ClickHouseTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -721,6 +721,7 @@ class ClickHouseTestSettings extends BackendTestSettings {
.exclude("WeekDay")
.exclude("WeekOfYear")
.exclude("DateFormat")
.exclude("Gluten - DateFormat")
.exclude("Hour")
.exclude("Minute")
.exclude("date add interval")
Expand Down
2 changes: 2 additions & 0 deletions gluten-ut/spark33/src/test/scala/io/glutenproject/utils/velox/VeloxTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,6 +146,8 @@ class VeloxTestSettings extends BackendTestSettings {
.exclude("to_unix_timestamp")
// Unsupported format: yyyy-MM-dd HH:mm:ss.SSS
.exclude("SPARK-33498: GetTimestamp,UnixTimestamp,ToUnixTimestamp with parseError")
// Replaced by a gluten test to pass timezone through config.
.exclude("DateFormat")
enableSuite[GlutenDecimalExpressionSuite]
enableSuite[GlutenHashExpressionsSuite]
enableSuite[GlutenIntervalExpressionsSuite]
Expand Down
5 changes: 3 additions & 2 deletions gluten-ut/spark33/src/test/scala/org/apache/spark/sql/GlutenSQLQueryTestSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,8 +242,9 @@ class GlutenSQLQueryTestSuite
"current_database_catalog.sql",
"date.sql",
"datetime-formatting-invalid.sql",
"datetime-formatting-legacy.sql",
"datetime-formatting.sql",
// Velox had different handling for some illegal cases.
// "datetime-formatting-legacy.sql",
// "datetime-formatting.sql",
"datetime-legacy.sql",
"datetime-parsing-invalid.sql",
"datetime-parsing-legacy.sql",
Expand Down
58 changes: 58 additions & 0 deletions ...src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenDateExpressionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -285,4 +285,62 @@ class GlutenDateExpressionsSuite extends DateExpressionsSuite with GlutenTestsTr
GenerateUnsafeProjection.generate(
ToUnixTimestamp(Literal("2015-07-24"), Literal("\""), UTC_OPT) :: Nil)
}

// Modified based on vanilla spark to explicitly set timezone in config.
test(GLUTEN_TEST + "DateFormat") {
val PST_OPT = Option(PST.getId)
val JST_OPT = Option(JST.getId)

Seq("legacy", "corrected").foreach {
legacyParserPolicy =>
withSQLConf(
SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy,
SQLConf.SESSION_LOCAL_TIMEZONE.key -> UTC_OPT.get) {
checkEvaluation(
DateFormatClass(Literal.create(null, TimestampType), Literal("y"), UTC_OPT),
null)
checkEvaluation(
DateFormatClass(
Cast(Literal(d), TimestampType, UTC_OPT),
Literal.create(null, StringType),
UTC_OPT),
null)

checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, UTC_OPT), Literal("y"), UTC_OPT),
"2015")
checkEvaluation(DateFormatClass(Literal(ts), Literal("y"), UTC_OPT), "2013")
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, UTC_OPT), Literal("H"), UTC_OPT),
"0")
checkEvaluation(DateFormatClass(Literal(ts), Literal("H"), UTC_OPT), "13")
}

withSQLConf(
SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy,
SQLConf.SESSION_LOCAL_TIMEZONE.key -> PST_OPT.get) {
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, PST_OPT), Literal("y"), PST_OPT),
"2015")
checkEvaluation(DateFormatClass(Literal(ts), Literal("y"), PST_OPT), "2013")
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, PST_OPT), Literal("H"), PST_OPT),
"0")
checkEvaluation(DateFormatClass(Literal(ts), Literal("H"), PST_OPT), "5")
}

withSQLConf(
SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy,
SQLConf.SESSION_LOCAL_TIMEZONE.key -> PST_OPT.get) {
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, JST_OPT), Literal("y"), JST_OPT),
"2015")
checkEvaluation(DateFormatClass(Literal(ts), Literal("y"), JST_OPT), "2013")
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, JST_OPT), Literal("H"), JST_OPT),
"0")
checkEvaluation(DateFormatClass(Literal(ts), Literal("H"), JST_OPT), "22")
}
}
}
}
2 changes: 2 additions & 0 deletions gluten-ut/spark34/src/test/scala/io/glutenproject/utils/velox/VeloxTestSettings.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,6 +153,8 @@ class VeloxTestSettings extends BackendTestSettings {
.exclude("to_unix_timestamp")
// Unsupported format: yyyy-MM-dd HH:mm:ss.SSS
.exclude("SPARK-33498: GetTimestamp,UnixTimestamp,ToUnixTimestamp with parseError")
// Replaced by a gluten test to pass timezone through config.
.exclude("DateFormat")
enableSuite[GlutenDecimalExpressionSuite]
enableSuite[GlutenHashExpressionsSuite]
enableSuite[GlutenIntervalExpressionsSuite]
Expand Down
5 changes: 3 additions & 2 deletions gluten-ut/spark34/src/test/scala/org/apache/spark/sql/GlutenSQLQueryTestSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,8 +245,9 @@ class GlutenSQLQueryTestSuite
"current_database_catalog.sql",
// "date.sql",
// "datetime-formatting-invalid.sql",
"datetime-formatting-legacy.sql",
"datetime-formatting.sql",
// Velox had different handling for some illegal cases.
// "datetime-formatting-legacy.sql",
// "datetime-formatting.sql",
// "datetime-legacy.sql",
// "datetime-parsing-invalid.sql",
"datetime-parsing-legacy.sql",
Expand Down
58 changes: 58 additions & 0 deletions ...src/test/scala/org/apache/spark/sql/catalyst/expressions/GlutenDateExpressionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -285,4 +285,62 @@ class GlutenDateExpressionsSuite extends DateExpressionsSuite with GlutenTestsTr
GenerateUnsafeProjection.generate(
ToUnixTimestamp(Literal("2015-07-24"), Literal("\""), UTC_OPT) :: Nil)
}

// Modified based on vanilla spark to explicitly set timezone in config.
test(GLUTEN_TEST + "DateFormat") {
val PST_OPT = Option(PST.getId)
val JST_OPT = Option(JST.getId)

Seq("legacy", "corrected").foreach {
legacyParserPolicy =>
withSQLConf(
SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy,
SQLConf.SESSION_LOCAL_TIMEZONE.key -> UTC_OPT.get) {
checkEvaluation(
DateFormatClass(Literal.create(null, TimestampType), Literal("y"), UTC_OPT),
null)
checkEvaluation(
DateFormatClass(
Cast(Literal(d), TimestampType, UTC_OPT),
Literal.create(null, StringType),
UTC_OPT),
null)

checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, UTC_OPT), Literal("y"), UTC_OPT),
"2015")
checkEvaluation(DateFormatClass(Literal(ts), Literal("y"), UTC_OPT), "2013")
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, UTC_OPT), Literal("H"), UTC_OPT),
"0")
checkEvaluation(DateFormatClass(Literal(ts), Literal("H"), UTC_OPT), "13")
}

withSQLConf(
SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy,
SQLConf.SESSION_LOCAL_TIMEZONE.key -> PST_OPT.get) {
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, PST_OPT), Literal("y"), PST_OPT),
"2015")
checkEvaluation(DateFormatClass(Literal(ts), Literal("y"), PST_OPT), "2013")
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, PST_OPT), Literal("H"), PST_OPT),
"0")
checkEvaluation(DateFormatClass(Literal(ts), Literal("H"), PST_OPT), "5")
}

withSQLConf(
SQLConf.LEGACY_TIME_PARSER_POLICY.key -> legacyParserPolicy,
SQLConf.SESSION_LOCAL_TIMEZONE.key -> PST_OPT.get) {
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, JST_OPT), Literal("y"), JST_OPT),
"2015")
checkEvaluation(DateFormatClass(Literal(ts), Literal("y"), JST_OPT), "2013")
checkEvaluation(
DateFormatClass(Cast(Literal(d), TimestampType, JST_OPT), Literal("H"), JST_OPT),
"0")
checkEvaluation(DateFormatClass(Literal(ts), Literal("H"), JST_OPT), "22")
}
}
}
}
Loading