This is an automated email from the ASF dual-hosted git repository.
dongjoon pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 5a74036 [SPARK-26853][SQL] Add example and version for commonly used
aggregate function descriptions
5a74036 is described below
commit 5a7403623d0525c23ab8ae575e9d1383e3e10635
Author: Dilip Biswal <[email protected]>
AuthorDate: Mon Feb 11 23:24:54 2019 -0800
[SPARK-26853][SQL] Add example and version for commonly used aggregate
function descriptions
## What changes were proposed in this pull request?
This improves the expression description for commonly used aggregate
functions such as Max, Min, Count, etc.
## How was this patch tested?
Verified the function description manually from the shell.
Closes #23756 from dilipbiswal/dkb_expr_description_aggregate.
Authored-by: Dilip Biswal <[email protected]>
Signed-off-by: Dongjoon Hyun <[email protected]>
---
.../aggregate/ApproximatePercentile.scala | 3 +-
.../catalyst/expressions/aggregate/Average.scala | 10 ++++-
.../expressions/aggregate/CentralMomentAgg.scala | 52 +++++++++++++++++++---
.../sql/catalyst/expressions/aggregate/Corr.scala | 8 +++-
.../sql/catalyst/expressions/aggregate/Count.scala | 12 ++++-
.../expressions/aggregate/CountMinSketchAgg.scala | 3 +-
.../expressions/aggregate/Covariance.scala | 16 ++++++-
.../sql/catalyst/expressions/aggregate/First.scala | 13 +++++-
.../aggregate/HyperLogLogPlusPlus.scala | 9 +++-
.../sql/catalyst/expressions/aggregate/Last.scala | 13 +++++-
.../sql/catalyst/expressions/aggregate/Max.scala | 8 +++-
.../sql/catalyst/expressions/aggregate/Min.scala | 8 +++-
.../expressions/aggregate/Percentile.scala | 10 ++++-
.../sql/catalyst/expressions/aggregate/Sum.scala | 12 ++++-
.../expressions/aggregate/UnevaluableAggs.scala | 27 +++++++++++
.../catalyst/expressions/aggregate/collect.scala | 16 ++++++-
16 files changed, 195 insertions(+), 25 deletions(-)
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala
index c790d87..ea0ed2e 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/ApproximatePercentile.scala
@@ -64,7 +64,8 @@ import org.apache.spark.sql.types._
[10.0,10.0,10.0]
> SELECT _FUNC_(10.0, 0.5, 100);
10.0
- """)
+ """,
+ since = "2.1.0")
case class ApproximatePercentile(
child: Expression,
percentageExpression: Expression,
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Average.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Average.scala
index 8dd80dc..66ac730 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Average.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Average.scala
@@ -24,7 +24,15 @@ import org.apache.spark.sql.catalyst.util.TypeUtils
import org.apache.spark.sql.types._
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the mean calculated from values of a group.")
+ usage = "_FUNC_(expr) - Returns the mean calculated from values of a group.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (1), (2), (3) AS tab(col);
+ 2.0
+ > SELECT _FUNC_(col) FROM VALUES (1), (2), (NULL) AS tab(col);
+ 1.5
+ """,
+ since = "1.0.0")
case class Average(child: Expression) extends DeclarativeAggregate with
ImplicitCastInputTypes {
override def prettyName: String = "avg"
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CentralMomentAgg.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CentralMomentAgg.scala
index e2ff0ef..1870c58 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CentralMomentAgg.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CentralMomentAgg.scala
@@ -135,7 +135,13 @@ abstract class CentralMomentAgg(child: Expression)
// Compute the population standard deviation of a column
// scalastyle:off line.size.limit
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the population standard deviation calculated
from values of a group.")
+ usage = "_FUNC_(expr) - Returns the population standard deviation calculated
from values of a group.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (1), (2), (3) AS tab(col);
+ 0.816496580927726
+ """,
+ since = "1.6.0")
// scalastyle:on line.size.limit
case class StddevPop(child: Expression) extends CentralMomentAgg(child) {
@@ -151,7 +157,13 @@ case class StddevPop(child: Expression) extends
CentralMomentAgg(child) {
// Compute the sample standard deviation of a column
// scalastyle:off line.size.limit
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the sample standard deviation calculated
from values of a group.")
+ usage = "_FUNC_(expr) - Returns the sample standard deviation calculated
from values of a group.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (1), (2), (3) AS tab(col);
+ 1.0
+ """,
+ since = "1.6.0")
// scalastyle:on line.size.limit
case class StddevSamp(child: Expression) extends CentralMomentAgg(child) {
@@ -167,7 +179,13 @@ case class StddevSamp(child: Expression) extends
CentralMomentAgg(child) {
// Compute the population variance of a column
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the population variance calculated from
values of a group.")
+ usage = "_FUNC_(expr) - Returns the population variance calculated from
values of a group.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (1), (2), (3) AS tab(col);
+ 0.6666666666666666
+ """,
+ since = "1.6.0")
case class VariancePop(child: Expression) extends CentralMomentAgg(child) {
override protected def momentOrder = 2
@@ -181,7 +199,13 @@ case class VariancePop(child: Expression) extends
CentralMomentAgg(child) {
// Compute the sample variance of a column
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the sample variance calculated from values
of a group.")
+ usage = "_FUNC_(expr) - Returns the sample variance calculated from values
of a group.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (1), (2), (3) AS tab(col);
+ 1.0
+ """,
+ since = "1.6.0")
case class VarianceSamp(child: Expression) extends CentralMomentAgg(child) {
override protected def momentOrder = 2
@@ -195,7 +219,15 @@ case class VarianceSamp(child: Expression) extends
CentralMomentAgg(child) {
}
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the skewness value calculated from values of
a group.")
+ usage = "_FUNC_(expr) - Returns the skewness value calculated from values of
a group.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (-10), (-20), (100), (1000) AS tab(col);
+ 1.1135657469022013
+ > SELECT _FUNC_(col) FROM VALUES (-1000), (-100), (10), (20) AS tab(col);
+ -1.1135657469022011
+ """,
+ since = "1.6.0")
case class Skewness(child: Expression) extends CentralMomentAgg(child) {
override def prettyName: String = "skewness"
@@ -209,7 +241,15 @@ case class Skewness(child: Expression) extends
CentralMomentAgg(child) {
}
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the kurtosis value calculated from values of
a group.")
+ usage = "_FUNC_(expr) - Returns the kurtosis value calculated from values of
a group.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (-10), (-20), (100), (1000) AS tab(col);
+ -0.7014368047529618
+ > SELECT _FUNC_(col) FROM VALUES (1), (10), (100), (10), (1) as tab(col);
+ 0.19432323191698986
+ """,
+ since = "1.6.0")
case class Kurtosis(child: Expression) extends CentralMomentAgg(child) {
override protected def momentOrder = 4
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Corr.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Corr.scala
index e14cc71..91446e0 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Corr.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Corr.scala
@@ -93,7 +93,13 @@ abstract class PearsonCorrelation(x: Expression, y:
Expression)
// scalastyle:off line.size.limit
@ExpressionDescription(
- usage = "_FUNC_(expr1, expr2) - Returns Pearson coefficient of correlation
between a set of number pairs.")
+ usage = "_FUNC_(expr1, expr2) - Returns Pearson coefficient of correlation
between a set of number pairs.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(c1, c2) FROM VALUES (3, 2), (3, 3), (6, 4) as tab(c1,
c2);
+ 0.8660254037844387
+ """,
+ since = "1.6.0")
// scalastyle:on line.size.limit
case class Corr(x: Expression, y: Expression)
extends PearsonCorrelation(x, y) {
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Count.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Count.scala
index d402f2d..2a8edac 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Count.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Count.scala
@@ -29,7 +29,17 @@ import org.apache.spark.sql.types._
_FUNC_(expr[, expr...]) - Returns the number of rows for which the
supplied expression(s) are all non-null.
_FUNC_(DISTINCT expr[, expr...]) - Returns the number of rows for which
the supplied expression(s) are unique and non-null.
- """)
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_(*) FROM VALUES (NULL), (5), (5), (20) AS tab(col);
+ 4
+ > SELECT _FUNC_(col) FROM VALUES (NULL), (5), (5), (20) AS tab(col);
+ 3
+ > SELECT _FUNC_(DISTINCT col) FROM VALUES (NULL), (5), (5), (10) AS
tab(col);
+ 2
+ """,
+ since = "1.0.0")
// scalastyle:on line.size.limit
case class Count(children: Seq[Expression]) extends DeclarativeAggregate {
override def nullable: Boolean = false
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAgg.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAgg.scala
index dae88c7..4bd13cf 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAgg.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/CountMinSketchAgg.scala
@@ -43,7 +43,8 @@ import org.apache.spark.util.sketch.CountMinSketch
confidence and seed. The result is an array of bytes, which can be
deserialized to a
`CountMinSketch` before usage. Count-min sketch is a probabilistic data
structure used for
cardinality estimation using sub-linear space.
- """)
+ """,
+ since = "2.2.0")
case class CountMinSketchAgg(
child: Expression,
epsExpression: Expression,
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Covariance.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Covariance.scala
index ee28eb5..ac99fa8 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Covariance.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Covariance.scala
@@ -80,7 +80,13 @@ abstract class Covariance(x: Expression, y: Expression)
}
@ExpressionDescription(
- usage = "_FUNC_(expr1, expr2) - Returns the population covariance of a set
of number pairs.")
+ usage = "_FUNC_(expr1, expr2) - Returns the population covariance of a set
of number pairs.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(c1, c2) FROM VALUES (1,1), (2,2), (3,3) AS tab(c1, c2);
+ 0.6666666666666666
+ """,
+ since = "2.0.0")
case class CovPopulation(left: Expression, right: Expression) extends
Covariance(left, right) {
override val evaluateExpression: Expression = {
If(n === 0.0, Literal.create(null, DoubleType), ck / n)
@@ -90,7 +96,13 @@ case class CovPopulation(left: Expression, right:
Expression) extends Covariance
@ExpressionDescription(
- usage = "_FUNC_(expr1, expr2) - Returns the sample covariance of a set of
number pairs.")
+ usage = "_FUNC_(expr1, expr2) - Returns the sample covariance of a set of
number pairs.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(c1, c2) FROM VALUES (1,1), (2,2), (3,3) AS tab(c1, c2);
+ 1.0
+ """,
+ since = "2.0.0")
case class CovSample(left: Expression, right: Expression) extends
Covariance(left, right) {
override val evaluateExpression: Expression = {
If(n === 0.0, Literal.create(null, DoubleType),
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/First.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/First.scala
index f51bfd5..9f35139 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/First.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/First.scala
@@ -33,8 +33,17 @@ import org.apache.spark.sql.types._
@ExpressionDescription(
usage = """
_FUNC_(expr[, isIgnoreNull]) - Returns the first value of `expr` for a
group of rows.
- If `isIgnoreNull` is true, returns only non-null values.
- """)
+ If `isIgnoreNull` is true, returns only non-null values.""",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (10), (5), (20) AS tab(col);
+ 10
+ > SELECT _FUNC_(col) FROM VALUES (NULL), (5), (20) AS tab(col);
+ NULL
+ > SELECT _FUNC_(col, true) FROM VALUES (NULL), (5), (20) AS tab(col);
+ 5
+ """,
+ since = "2.0.0")
case class First(child: Expression, ignoreNullsExpr: Expression)
extends DeclarativeAggregate with ExpectsInputTypes {
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlus.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlus.scala
index 0b73788..e3c628e 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlus.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/HyperLogLogPlusPlus.scala
@@ -47,8 +47,13 @@ import org.apache.spark.sql.types._
@ExpressionDescription(
usage = """
_FUNC_(expr[, relativeSD]) - Returns the estimated cardinality by
HyperLogLog++.
- `relativeSD` defines the maximum estimation error allowed.
- """)
+ `relativeSD` defines the maximum estimation error allowed.""",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col1) FROM VALUES (1), (1), (2), (2), (3) tab(col1);
+ 3
+ """,
+ since = "1.6.0")
case class HyperLogLogPlusPlus(
child: Expression,
relativeSD: Double = 0.05,
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Last.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Last.scala
index 2650d7b..405719f 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Last.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Last.scala
@@ -33,8 +33,17 @@ import org.apache.spark.sql.types._
@ExpressionDescription(
usage = """
_FUNC_(expr[, isIgnoreNull]) - Returns the last value of `expr` for a
group of rows.
- If `isIgnoreNull` is true, returns only non-null values.
- """)
+ If `isIgnoreNull` is true, returns only non-null values""",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (10), (5), (20) AS tab(col);
+ 20
+ > SELECT _FUNC_(col) FROM VALUES (10), (5), (NULL) AS tab(col);
+ NULL
+ > SELECT _FUNC_(col, true) FROM VALUES (10), (5), (NULL) AS tab(col);
+ 5
+ """,
+ since = "2.0.0")
case class Last(child: Expression, ignoreNullsExpr: Expression)
extends DeclarativeAggregate with ExpectsInputTypes {
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Max.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Max.scala
index 71099eb..7520db1 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Max.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Max.scala
@@ -24,7 +24,13 @@ import org.apache.spark.sql.catalyst.util.TypeUtils
import org.apache.spark.sql.types._
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the maximum value of `expr`.")
+ usage = "_FUNC_(expr) - Returns the maximum value of `expr`.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (10), (50), (20) AS tab(col);
+ 50
+ """,
+ since = "1.0.0")
case class Max(child: Expression) extends DeclarativeAggregate {
override def children: Seq[Expression] = child :: Nil
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Min.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Min.scala
index 8c4ba93..106eb96 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Min.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Min.scala
@@ -24,7 +24,13 @@ import org.apache.spark.sql.catalyst.util.TypeUtils
import org.apache.spark.sql.types._
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the minimum value of `expr`.")
+ usage = "_FUNC_(expr) - Returns the minimum value of `expr`.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (10), (-1), (20) AS tab(col);
+ -1
+ """,
+ since = "1.0.0")
case class Min(child: Expression) extends DeclarativeAggregate {
override def children: Seq[Expression] = child :: Nil
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Percentile.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Percentile.scala
index 4894036..a91a6d7 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Percentile.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Percentile.scala
@@ -54,7 +54,15 @@ import org.apache.spark.util.collection.OpenHashMap
of the percentage array must be between 0.0 and 1.0. The value of
frequency should be
positive integral
- """)
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col, 0.3) FROM VALUES (0), (10) AS tab(col);
+ 3.0
+ > SELECT _FUNC_(col, array(0.25, 0.75)) FROM VALUES (0), (10) AS
tab(col);
+ [2.5,7.5]
+ """,
+ since = "2.1.0")
case class Percentile(
child: Expression,
percentageExpression: Expression,
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Sum.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Sum.scala
index 761dba1..ef204ec 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Sum.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Sum.scala
@@ -24,7 +24,17 @@ import org.apache.spark.sql.catalyst.util.TypeUtils
import org.apache.spark.sql.types._
@ExpressionDescription(
- usage = "_FUNC_(expr) - Returns the sum calculated from values of a group.")
+ usage = "_FUNC_(expr) - Returns the sum calculated from values of a group.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (5), (10), (15) AS tab(col);
+ 30
+ > SELECT _FUNC_(col) FROM VALUES (NULL), (10), (15) AS tab(col);
+ 25
+ > SELECT _FUNC_(col) FROM VALUES (NULL), (NULL) AS tab(col);
+ NULL
+ """,
+ since = "1.0.0")
case class Sum(child: Expression) extends DeclarativeAggregate with
ImplicitCastInputTypes {
override def children: Seq[Expression] = child :: Nil
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/UnevaluableAggs.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/UnevaluableAggs.scala
index fc33ef9..4562fbc 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/UnevaluableAggs.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/UnevaluableAggs.scala
@@ -42,6 +42,15 @@ abstract class UnevaluableBooleanAggBase(arg: Expression)
@ExpressionDescription(
usage = "_FUNC_(expr) - Returns true if all values of `expr` are true.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (true), (true), (true) AS tab(col);
+ true
+ > SELECT _FUNC_(col) FROM VALUES (NULL), (true), (true) AS tab(col);
+ true
+ > SELECT _FUNC_(col) FROM VALUES (true), (false), (true) AS tab(col);
+ false
+ """,
since = "3.0.0")
case class EveryAgg(arg: Expression) extends UnevaluableBooleanAggBase(arg) {
override def nodeName: String = "Every"
@@ -49,6 +58,15 @@ case class EveryAgg(arg: Expression) extends
UnevaluableBooleanAggBase(arg) {
@ExpressionDescription(
usage = "_FUNC_(expr) - Returns true if at least one value of `expr` is
true.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (true), (false), (false) AS tab(col);
+ true
+ > SELECT _FUNC_(col) FROM VALUES (NULL), (true), (false) AS tab(col);
+ true
+ > SELECT _FUNC_(col) FROM VALUES (false), (false), (NULL) AS tab(col);
+ false
+ """,
since = "3.0.0")
case class AnyAgg(arg: Expression) extends UnevaluableBooleanAggBase(arg) {
override def nodeName: String = "Any"
@@ -56,6 +74,15 @@ case class AnyAgg(arg: Expression) extends
UnevaluableBooleanAggBase(arg) {
@ExpressionDescription(
usage = "_FUNC_(expr) - Returns true if at least one value of `expr` is
true.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (true), (false), (false) AS tab(col);
+ true
+ > SELECT _FUNC_(col) FROM VALUES (NULL), (true), (false) AS tab(col);
+ true
+ > SELECT _FUNC_(col) FROM VALUES (false), (false), (NULL) AS tab(col);
+ false
+ """,
since = "3.0.0")
case class SomeAgg(arg: Expression) extends UnevaluableBooleanAggBase(arg) {
override def nodeName: String = "Some"
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala
index be972f0..7cc43df 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala
@@ -86,7 +86,13 @@ abstract class Collect[T <: Growable[Any] with
Iterable[Any]] extends TypedImper
* Collect a list of elements.
*/
@ExpressionDescription(
- usage = "_FUNC_(expr) - Collects and returns a list of non-unique elements.")
+ usage = "_FUNC_(expr) - Collects and returns a list of non-unique elements.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (1), (2), (1) AS tab(col);
+ [1,2,1]
+ """,
+ since = "2.0.0")
case class CollectList(
child: Expression,
mutableAggBufferOffset: Int = 0,
@@ -109,7 +115,13 @@ case class CollectList(
* Collect a set of unique elements.
*/
@ExpressionDescription(
- usage = "_FUNC_(expr) - Collects and returns a set of unique elements.")
+ usage = "_FUNC_(expr) - Collects and returns a set of unique elements.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(col) FROM VALUES (1), (2), (1) AS tab(col);
+ [1,2]
+ """,
+ since = "2.0.0")
case class CollectSet(
child: Expression,
mutableAggBufferOffset: Int = 0,
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
