[SPARK-31146][SQL] Leverage the helper method for aliasing in built-in SQL expressions

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala

@@ -218,7 +218,7 @@ object FunctionRegistry {
     expression[PosExplode]("posexplode"),
     expressionGeneratorOuter[PosExplode]("posexplode_outer"),
     expression[Rand]("rand"),
-    expression[Rand]("random"),
+    expression[Rand]("random", true),
     expression[Randn]("randn"),
     expression[Stack]("stack"),
     expression[CaseWhen]("when"),
@@ -235,7 +235,7 @@ object FunctionRegistry {
     expression[BRound]("bround"),
     expression[Cbrt]("cbrt"),
     expression[Ceil]("ceil"),
-    expression[Ceil]("ceiling"),
+    expression[Ceil]("ceiling", true),
     expression[Cos]("cos"),
     expression[Cosh]("cosh"),
     expression[Conv]("conv"),
@@ -252,20 +252,20 @@ object FunctionRegistry {
     expression[Log1p]("log1p"),
     expression[Log2]("log2"),
     expression[Log]("ln"),
-    expression[Remainder]("mod"),
+    expression[Remainder]("mod", true),
     expression[UnaryMinus]("negative"),
     expression[Pi]("pi"),
     expression[Pmod]("pmod"),
     expression[UnaryPositive]("positive"),
-    expression[Pow]("pow"),
+    expression[Pow]("pow", true),
     expression[Pow]("power"),
     expression[ToRadians]("radians"),
     expression[Rint]("rint"),
     expression[Round]("round"),
     expression[ShiftLeft]("shiftleft"),
     expression[ShiftRight]("shiftright"),
     expression[ShiftRightUnsigned]("shiftrightunsigned"),
-    expression[Signum]("sign"),
+    expression[Signum]("sign", true),
     expression[Signum]("signum"),
     expression[Sin]("sin"),
     expression[Sinh]("sinh"),
@@ -323,12 +323,12 @@ object FunctionRegistry {
 
     // string functions
     expression[Ascii]("ascii"),
-    expression[Chr]("char"),
+    expression[Chr]("char", true),
     expression[Chr]("chr"),
     expression[Base64]("base64"),
     expression[BitLength]("bit_length"),
-    expression[Length]("char_length"),
-    expression[Length]("character_length"),
+    expression[Length]("char_length", true),
+    expression[Length]("character_length", true),
     expression[ConcatWs]("concat_ws"),
     expression[Decode]("decode"),
     expression[Elt]("elt"),
@@ -351,7 +351,7 @@ object FunctionRegistry {
     expression[JsonTuple]("json_tuple"),
     expression[ParseUrl]("parse_url"),
     expression[StringLocate]("position"),
-    expression[FormatString]("printf"),
+    expression[FormatString]("printf", true),
     expression[RegExpExtract]("regexp_extract"),
     expression[RegExpReplace]("regexp_replace"),
     expression[StringRepeat]("repeat"),
@@ -364,21 +364,21 @@ object FunctionRegistry {
     expression[SoundEx]("soundex"),
     expression[StringSpace]("space"),
     expression[StringSplit]("split"),
-    expression[Substring]("substr"),
+    expression[Substring]("substr", true),
     expression[Substring]("substring"),
     expression[Left]("left"),
     expression[Right]("right"),
     expression[SubstringIndex]("substring_index"),
     expression[StringTranslate]("translate"),
     expression[StringTrim]("trim"),
-    expression[Upper]("ucase"),
+    expression[Upper]("ucase", true),
     expression[UnBase64]("unbase64"),
     expression[Unhex]("unhex"),
     expression[Upper]("upper"),
     expression[XPathList]("xpath"),
     expression[XPathBoolean]("xpath_boolean"),
     expression[XPathDouble]("xpath_double"),
-    expression[XPathDouble]("xpath_number"),
+    expression[XPathDouble]("xpath_number", true),
     expression[XPathFloat]("xpath_float"),
     expression[XPathInt]("xpath_int"),
     expression[XPathLong]("xpath_long"),
@@ -393,7 +393,7 @@ object FunctionRegistry {
     expression[DateAdd]("date_add"),
     expression[DateFormatClass]("date_format"),
     expression[DateSub]("date_sub"),
-    expression[DayOfMonth]("day"),
+    expression[DayOfMonth]("day", true),
     expression[DayOfYear]("dayofyear"),
     expression[DayOfMonth]("dayofmonth"),
     expression[FromUnixTime]("from_unixtime"),
@@ -404,7 +404,7 @@ object FunctionRegistry {
     expression[Month]("month"),
     expression[MonthsBetween]("months_between"),
     expression[NextDay]("next_day"),
-    expression[CurrentTimestamp]("now"),
+    expression[CurrentTimestamp]("now", true),
     expression[Quarter]("quarter"),
     expression[Second]("second"),
     expression[ParseToTimestamp]("to_timestamp"),
@@ -445,7 +445,7 @@ object FunctionRegistry {
     expression[MapConcat]("map_concat"),
     expression[Size]("size"),
     expression[Slice]("slice"),
-    expression[Size]("cardinality"),
+    expression[Size]("cardinality", true),
     expression[ArraysZip]("arrays_zip"),
     expression[SortArray]("sort_array"),
     expression[Shuffle]("shuffle"),
@@ -478,7 +478,7 @@ object FunctionRegistry {
     expression[Uuid]("uuid"),
     expression[Murmur3Hash]("hash"),
     expression[XxHash64]("xxhash64"),
-    expression[Sha1]("sha"),
+    expression[Sha1]("sha", true),
     expression[Sha1]("sha1"),
     expression[Sha2]("sha2"),
     expression[SparkPartitionID]("spark_partition_id"),
@@ -488,7 +488,7 @@ object FunctionRegistry {
     expression[MonotonicallyIncreasingID]("monotonically_increasing_id"),
     expression[CurrentDatabase]("current_database"),
     expression[CallMethodViaReflection]("reflect"),
-    expression[CallMethodViaReflection]("java_method"),
+    expression[CallMethodViaReflection]("java_method", true),
     expression[SparkVersion]("version"),
     expression[TypeOf]("typeof"),
 
@@ -590,7 +590,9 @@ object FunctionRegistry {
       if (varargCtor.isDefined) {
         // If there is an apply method that accepts Seq[Expression], use that one.
         try {
-          varargCtor.get.newInstance(expressions).asInstanceOf[Expression]
+          val exp = varargCtor.get.newInstance(expressions).asInstanceOf[Expression]
+          if (setAlias) exp.setTagValue(FUNC_ALIAS, name)
+          exp
         } catch {
           // the exception is an invocation exception. To get a meaningful message, we need the
           // cause.

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/CallMethodViaReflection.scala

@@ -20,7 +20,7 @@ package org.apache.spark.sql.catalyst.expressions
 import java.lang.reflect.{Method, Modifier}
 
 import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
+import org.apache.spark.sql.catalyst.analysis.{FunctionRegistry, TypeCheckResult}
 import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.{TypeCheckFailure, TypeCheckSuccess}
 import org.apache.spark.sql.catalyst.expressions.codegen.CodegenFallback
 import org.apache.spark.sql.types._
@@ -55,7 +55,7 @@ import org.apache.spark.util.Utils
 case class CallMethodViaReflection(children: Seq[Expression])
   extends Expression with CodegenFallback {
 
-  override def prettyName: String = "reflect"
+  override def prettyName: String = getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse("reflect")
 
   override def checkInputDataTypes(): TypeCheckResult = {
     if (children.size < 2) {

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Expression.scala

@@ -20,7 +20,7 @@ package org.apache.spark.sql.catalyst.expressions
 import java.util.Locale
 
 import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.analysis.{TypeCheckResult, TypeCoercion}
+import org.apache.spark.sql.catalyst.analysis.{FunctionRegistry, TypeCheckResult, TypeCoercion}
 import org.apache.spark.sql.catalyst.expressions.aggregate.DeclarativeAggregate
 import org.apache.spark.sql.catalyst.expressions.codegen._
 import org.apache.spark.sql.catalyst.expressions.codegen.Block._
@@ -258,7 +258,8 @@ abstract class Expression extends TreeNode[Expression] {
    * Returns a user-facing string representation of this expression's name.
    * This should usually match the name of the function in SQL.
    */
-  def prettyName: String = nodeName.toLowerCase(Locale.ROOT)
+  def prettyName: String =
+    getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse(nodeName.toLowerCase(Locale.ROOT))
 
   protected def flatArguments: Iterator[Any] = stringArgs.flatMap {
     case t: Iterable[_] => t

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/First.scala

@@ -117,7 +117,5 @@ case class First(child: Expression, ignoreNullsExpr: Expression)
 
   override lazy val evaluateExpression: AttributeReference = first
 
-  override def prettyName: String = getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse("first")
-
   override def toString: String = s"$prettyName($child)${if (ignoreNulls) " ignore nulls"}"
 }

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/Last.scala

@@ -115,7 +115,5 @@ case class Last(child: Expression, ignoreNullsExpr: Expression)
 
   override lazy val evaluateExpression: AttributeReference = last
 
-  override def prettyName: String = getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse("last")
-
   override def toString: String = s"$prettyName($child)${if (ignoreNulls) " ignore nulls"}"
 }

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/arithmetic.scala

@@ -18,7 +18,7 @@
 package org.apache.spark.sql.catalyst.expressions
 
 import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.analysis.{TypeCheckResult, TypeCoercion}
+import org.apache.spark.sql.catalyst.analysis.{FunctionRegistry, TypeCheckResult, TypeCoercion}
 import org.apache.spark.sql.catalyst.expressions.codegen._
 import org.apache.spark.sql.catalyst.expressions.codegen.Block._
 import org.apache.spark.sql.catalyst.util.{IntervalUtils, TypeUtils}
@@ -457,6 +457,18 @@ case class Remainder(left: Expression, right: Expression) extends DivModLike {
 
   override def symbol: String = "%"
   override def decimalMethod: String = "remainder"
+  override def toString: String = {
+    getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse(sqlOperator) match {
+      case operator if operator == sqlOperator => s"($left $sqlOperator $right)"
+      case funcName => s"$funcName($left, $right)"
+    }
+  }
+  override def sql: String = {
+    getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse(sqlOperator) match {
+      case operator if operator == sqlOperator => s"(${left.sql} $sqlOperator ${right.sql})"
+      case funcName => s"$funcName(${left.sql}, ${right.sql})"
+    }
+  }
 
   private lazy val mod: (Any, Any) => Any = dataType match {
     // special cases to make float/double primitive types faster

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala

@@ -29,6 +29,7 @@ import org.apache.commons.text.StringEscapeUtils
 import org.apache.spark.SparkUpgradeException
 import org.apache.spark.sql.AnalysisException
 import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.analysis.FunctionRegistry
 import org.apache.spark.sql.catalyst.expressions.codegen._
 import org.apache.spark.sql.catalyst.expressions.codegen.Block._
 import org.apache.spark.sql.catalyst.util.{DateTimeUtils, LegacyDateFormats, TimestampFormatter}
@@ -99,7 +100,8 @@ case class CurrentTimestamp() extends LeafExpression with CodegenFallback {
 
   override def eval(input: InternalRow): Any = currentTimestamp()
 
-  override def prettyName: String = "current_timestamp"
+  override def prettyName: String =
+    getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse("current_timestamp")
 }
 
 /**

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala

@@ -21,7 +21,7 @@ import java.{lang => jl}
 import java.util.Locale
 
 import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
+import org.apache.spark.sql.catalyst.analysis.{FunctionRegistry, TypeCheckResult}
 import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.{TypeCheckFailure, TypeCheckSuccess}
 import org.apache.spark.sql.catalyst.expressions.codegen._
 import org.apache.spark.sql.catalyst.expressions.codegen.Block._
@@ -62,8 +62,8 @@ abstract class UnaryMathExpression(val f: Double => Double, name: String)
   override def inputTypes: Seq[AbstractDataType] = Seq(DoubleType)
   override def dataType: DataType = DoubleType
   override def nullable: Boolean = true
-  override def toString: String = s"$name($child)"
-  override def prettyName: String = name
+  override def toString: String = s"$prettyName($child)"
+  override def prettyName: String = getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse(name)
 
   protected override def nullSafeEval(input: Any): Any = {
     f(input.asInstanceOf[Double])
@@ -115,9 +115,9 @@ abstract class BinaryMathExpression(f: (Double, Double) => Double, name: String)
 
   override def inputTypes: Seq[DataType] = Seq(DoubleType, DoubleType)
 
-  override def toString: String = s"$name($left, $right)"
+  override def toString: String = s"$prettyName($left, $right)"
 
-  override def prettyName: String = name
+  override def prettyName: String = getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse(name)
 
   override def dataType: DataType = DoubleType
 

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringExpressions.scala

@@ -27,7 +27,7 @@ import scala.collection.mutable.ArrayBuffer
 import org.apache.commons.codec.binary.{Base64 => CommonsBase64}
 
 import org.apache.spark.sql.catalyst.InternalRow
-import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
+import org.apache.spark.sql.catalyst.analysis.{FunctionRegistry, TypeCheckResult}
 import org.apache.spark.sql.catalyst.expressions.codegen._
 import org.apache.spark.sql.catalyst.expressions.codegen.Block._
 import org.apache.spark.sql.catalyst.util.{ArrayData, GenericArrayData, TypeUtils}
@@ -1450,7 +1450,7 @@ case class ParseUrl(children: Seq[Expression])
 // scalastyle:on line.size.limit
 case class FormatString(children: Expression*) extends Expression with ImplicitCastInputTypes {
 
-  require(children.nonEmpty, "format_string() should take at least 1 argument")
+  require(children.nonEmpty, s"$prettyName() should take at least 1 argument")
 
   override def foldable: Boolean = children.forall(_.foldable)
   override def nullable: Boolean = children(0).nullable
@@ -1517,7 +1517,8 @@ case class FormatString(children: Expression*) extends Expression with ImplicitC
       }""")
   }
 
-  override def prettyName: String = "format_string"
+  override def prettyName: String = getTagValue(
+    FunctionRegistry.FUNC_ALIAS).getOrElse("format_string")
 }
 
 /**

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/xml/xpath.scala

@@ -17,7 +17,7 @@
 
 package org.apache.spark.sql.catalyst.expressions.xml
 
-import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
+import org.apache.spark.sql.catalyst.analysis.{FunctionRegistry, TypeCheckResult}
 import org.apache.spark.sql.catalyst.analysis.TypeCheckResult.TypeCheckFailure
 import org.apache.spark.sql.catalyst.expressions._
 import org.apache.spark.sql.catalyst.expressions.codegen.CodegenFallback
@@ -160,7 +160,8 @@ case class XPathFloat(xml: Expression, path: Expression) extends XPathExtract {
   """)
 // scalastyle:on line.size.limit
 case class XPathDouble(xml: Expression, path: Expression) extends XPathExtract {
-  override def prettyName: String = "xpath_double"
+  override def prettyName: String =
+    getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse("xpath_double")
   override def dataType: DataType = DoubleType
 
   override def nullSafeEval(xml: Any, path: Any): Any = {

sql/core/src/test/resources/sql-tests/results/operators.sql.out

@@ -293,15 +293,15 @@ struct<COT(CAST(-1 AS DOUBLE)):double>
 -- !query
 select ceiling(0)
 -- !query schema
-struct<CEIL(CAST(0 AS DOUBLE)):bigint>
+struct<ceiling(CAST(0 AS DOUBLE)):bigint>
 -- !query output
 0
 
 
 -- !query
 select ceiling(1)
 -- !query schema
-struct<CEIL(CAST(1 AS DOUBLE)):bigint>
+struct<ceiling(CAST(1 AS DOUBLE)):bigint>
 -- !query output
 1
 
@@ -317,7 +317,7 @@ struct<CEIL(1234567890123456):bigint>
 -- !query
 select ceiling(1234567890123456)
 -- !query schema
-struct<CEIL(1234567890123456):bigint>
+struct<ceiling(1234567890123456):bigint>
 -- !query output
 1234567890123456
 
@@ -333,7 +333,7 @@ struct<CEIL(0.01):decimal(1,0)>
 -- !query
 select ceiling(-0.10)
 -- !query schema
-struct<CEIL(-0.10):decimal(1,0)>
+struct<ceiling(-0.10):decimal(1,0)>
 -- !query output
 0
 
@@ -389,7 +389,7 @@ true
 -- !query
 select mod(7, 2), mod(7, 0), mod(0, 2), mod(7, null), mod(null, 2), mod(null, null)
 -- !query schema
-struct<(7 % 2):int,(7 % 0):int,(0 % 2):int,(7 % CAST(NULL AS INT)):int,(CAST(NULL AS INT) % 2):int,(CAST(NULL AS DOUBLE) % CAST(NULL AS DOUBLE)):double>
+struct<mod(7, 2):int,mod(7, 0):int,mod(0, 2):int,mod(7, CAST(NULL AS INT)):int,mod(CAST(NULL AS INT), 2):int,mod(CAST(NULL AS DOUBLE), CAST(NULL AS DOUBLE)):double>
 -- !query output
 1	NULL	0	NULL	NULL	NULL
 
@@ -405,15 +405,15 @@ struct<bit_length(abc):int>
 -- !query
 select CHAR_LENGTH('abc')
 -- !query schema
-struct<length(abc):int>
+struct<char_length(abc):int>
 -- !query output
 3
 
 
 -- !query
 select CHARACTER_LENGTH('abc')
 -- !query schema
-struct<length(abc):int>
+struct<character_length(abc):int>
 -- !query output
 3
 

sql/core/src/test/resources/sql-tests/results/postgreSQL/insert.sql.out

@@ -64,7 +64,7 @@ struct<>
 -- !query
 select col1, col2, char_length(col3) from inserttest
 -- !query schema
-struct<col1:int,col2:int,length(col3):int>
+struct<col1:int,col2:int,char_length(col3):int>
 -- !query output
 30	50	10000
 NULL	3	7