[SPARK-31586][SQL] Replace expression TimeSub(l, r) with TimeAdd(l -r)

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

@@ -278,7 +278,7 @@ class Analyzer(
    * 1. if both side are interval, stays the same;
    * 2. else if the left side is date and the right side is interval,
    *    turns it to [[DateAddInterval(l, -r)]];
-   * 3. else if the right side is an interval, turns it to [[TimeSub]];
+   * 3. else if the right side is an interval, turns it to [[TimeAdd(l, -r)]];
    * 4. else if one side is timestamp, turns it to [[SubtractTimestamps]];
    * 5. else if the right side is date, turns it to [[DateDiff]]/[[SubtractDates]];
    * 6. else if the left side is date, turns it to [[DateSub]];
@@ -308,7 +308,7 @@ class Analyzer(
         case s @ Subtract(l, r) if s.childrenResolved => (l.dataType, r.dataType) match {
           case (CalendarIntervalType, CalendarIntervalType) => s
           case (DateType, CalendarIntervalType) => DateAddInterval(l, UnaryMinus(r))
-          case (_, CalendarIntervalType) => Cast(TimeSub(l, r), l.dataType)
+          case (_, CalendarIntervalType) => Cast(TimeAdd(l, UnaryMinus(r)), l.dataType)
           case (TimestampType, _) => SubtractTimestamps(l, r)
           case (_, TimestampType) => SubtractTimestamps(l, r)
           case (_, DateType) => SubtractDates(l, r)

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

@@ -232,8 +232,6 @@ object StreamingJoinHelper extends PredicateHelper with Logging {
           collect(left, negate) ++ collect(right, !negate)
         case TimeAdd(left, right, _) =>
           collect(left, negate) ++ collect(right, negate)
-        case TimeSub(left, right, _) =>
-          collect(left, negate) ++ collect(right, !negate)
         case UnaryMinus(child) =>
           collect(child, !negate)
         case CheckOverflow(child, _, _) =>

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

@@ -831,10 +831,7 @@ object TypeCoercion {
       case s @ SubtractTimestamps(_, DateType()) =>
         s.copy(startTimestamp = Cast(s.startTimestamp, TimestampType))
 
-      case t @ TimeAdd(DateType(), _, _) => t.copy(start = Cast(t.start, TimestampType))
       case t @ TimeAdd(StringType(), _, _) => t.copy(start = Cast(t.start, TimestampType))
-      case t @ TimeSub(DateType(), _, _) => t.copy(start = Cast(t.start, TimestampType))
-      case t @ TimeSub(StringType(), _, _) => t.copy(start = Cast(t.start, TimestampType))
     }
   }
 

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

@@ -1330,41 +1330,6 @@ case class FromUTCTimestamp(left: Expression, right: Expression)
   }
 }
 
-/**
- * Subtracts an interval from timestamp.
- */
-case class TimeSub(start: Expression, interval: Expression, timeZoneId: Option[String] = None)
-  extends BinaryExpression with TimeZoneAwareExpression with ExpectsInputTypes {
-
-  def this(start: Expression, interval: Expression) = this(start, interval, None)
-
-  override def left: Expression = start
-  override def right: Expression = interval
-
-  override def toString: String = s"$left - $right"
-  override def sql: String = s"${left.sql} - ${right.sql}"
-  override def inputTypes: Seq[AbstractDataType] = Seq(TimestampType, CalendarIntervalType)
-
-  override def dataType: DataType = TimestampType
-
-  override def withTimeZone(timeZoneId: String): TimeZoneAwareExpression =
-    copy(timeZoneId = Option(timeZoneId))
-
-  override def nullSafeEval(start: Any, interval: Any): Any = {
-    val itvl = interval.asInstanceOf[CalendarInterval]
-    DateTimeUtils.timestampAddInterval(
-      start.asInstanceOf[Long], 0 - itvl.months, 0 - itvl.days, 0 - itvl.microseconds, zoneId)
-  }
-
-  override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
-    val zid = ctx.addReferenceObj("zoneId", zoneId, classOf[ZoneId].getName)
-    val dtu = DateTimeUtils.getClass.getName.stripSuffix("$")
-    defineCodeGen(ctx, ev, (sd, i) => {
-      s"""$dtu.timestampAddInterval($sd, 0 - $i.months, 0 - $i.days, 0 - $i.microseconds, $zid)"""
-    })
-  }
-}
-
 /**
  * Returns the date that is num_months after start_date.
  */

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/DateExpressionsSuite.scala

@@ -465,54 +465,54 @@ class DateExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
       sdf.setTimeZone(TimeZone.getTimeZone(zid))
 
       checkEvaluation(
-        TimeSub(
+        TimeAdd(
           Literal(new Timestamp(sdf.parse("2016-03-31 10:00:00.000").getTime)),
-          Literal(new CalendarInterval(1, 0, 0)),
+          UnaryMinus(Literal(new CalendarInterval(1, 0, 0))),
           timeZoneId),
         DateTimeUtils.fromJavaTimestamp(
           new Timestamp(sdf.parse("2016-02-29 10:00:00.000").getTime)))
       checkEvaluation(
-        TimeSub(
+        TimeAdd(
           Literal(new Timestamp(sdf.parse("2016-03-31 10:00:00.000").getTime)),
-          Literal(new CalendarInterval(1, 1, 0)),
+          UnaryMinus(Literal(new CalendarInterval(1, 1, 0))),
           timeZoneId),
         DateTimeUtils.fromJavaTimestamp(
           new Timestamp(sdf.parse("2016-02-28 10:00:00.000").getTime)))
       checkEvaluation(
-        TimeSub(
+        TimeAdd(
           Literal(new Timestamp(sdf.parse("2016-03-30 00:00:01.000").getTime)),
-          Literal(new CalendarInterval(1, 0, 2000000.toLong)),
+          UnaryMinus(Literal(new CalendarInterval(1, 0, 2000000.toLong))),
           timeZoneId),
         DateTimeUtils.fromJavaTimestamp(
           new Timestamp(sdf.parse("2016-02-28 23:59:59.000").getTime)))
       checkEvaluation(
-        TimeSub(
+        TimeAdd(
           Literal(new Timestamp(sdf.parse("2016-03-30 00:00:01.000").getTime)),
-          Literal(new CalendarInterval(1, 1, 2000000.toLong)),
+          UnaryMinus(Literal(new CalendarInterval(1, 1, 2000000.toLong))),
           timeZoneId),
         DateTimeUtils.fromJavaTimestamp(
           new Timestamp(sdf.parse("2016-02-27 23:59:59.000").getTime)))
 
       checkEvaluation(
-        TimeSub(
+        TimeAdd(
           Literal.create(null, TimestampType),
-          Literal(new CalendarInterval(1, 2, 123000L)),
+          UnaryMinus(Literal(new CalendarInterval(1, 2, 123000L))),
           timeZoneId),
         null)
       checkEvaluation(
-        TimeSub(
+        TimeAdd(
           Literal(new Timestamp(sdf.parse("2016-01-29 10:00:00.000").getTime)),
-          Literal.create(null, CalendarIntervalType),
+          UnaryMinus(Literal.create(null, CalendarIntervalType)),
           timeZoneId),
         null)
       checkEvaluation(
-        TimeSub(
+        TimeAdd(
           Literal.create(null, TimestampType),
-          Literal.create(null, CalendarIntervalType),
+          UnaryMinus(Literal.create(null, CalendarIntervalType)),
           timeZoneId),
         null)
-      checkConsistencyBetweenInterpretedAndCodegen(
-        (start: Expression, interval: Expression) => TimeSub(start, interval, timeZoneId),
+      checkConsistencyBetweenInterpretedAndCodegen((start: Expression, interval: Expression) =>
+        TimeAdd(start, UnaryMinus(interval), timeZoneId),
         TimestampType, CalendarIntervalType)
     }
   }

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/ExpressionSQLBuilderSuite.scala

@@ -172,10 +172,6 @@ class ExpressionSQLBuilderSuite extends SparkFunSuite {
       "`a` + INTERVAL '1 hours'"
     )
 
-    checkSQL(
-      TimeSub('a, interval),
-      "`a` - INTERVAL '1 hours'"
-    )
     checkSQL(
       DateAddInterval('a, interval),
       "`a` + INTERVAL '1 hours'"

sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/StreamingSymmetricHashJoinHelper.scala

@@ -23,13 +23,11 @@ import org.apache.spark.{Partition, SparkContext, TaskContext}
 import org.apache.spark.internal.Logging
 import org.apache.spark.rdd.{RDD, ZippedPartitionsBaseRDD, ZippedPartitionsPartition, ZippedPartitionsRDD2}
 import org.apache.spark.sql.catalyst.analysis.StreamingJoinHelper
-import org.apache.spark.sql.catalyst.expressions.{Add, And, Attribute, AttributeReference, AttributeSet, BoundReference, Cast, CheckOverflow, Expression, ExpressionSet, GreaterThan, GreaterThanOrEqual, LessThan, LessThanOrEqual, Literal, Multiply, NamedExpression, PreciseTimestampConversion, PredicateHelper, Subtract, TimeAdd, TimeSub, UnaryMinus}
+import org.apache.spark.sql.catalyst.expressions.{And, Attribute, AttributeSet, BoundReference, Expression, NamedExpression, PredicateHelper}
 import org.apache.spark.sql.catalyst.plans.logical.EventTimeWatermark._
 import org.apache.spark.sql.execution.SparkPlan
 import org.apache.spark.sql.execution.streaming.WatermarkSupport.watermarkExpression
 import org.apache.spark.sql.execution.streaming.state.{StateStoreCoordinatorRef, StateStoreProvider, StateStoreProviderId}
-import org.apache.spark.sql.types._
-import org.apache.spark.unsafe.types.CalendarInterval
 
 
 /**

sql/core/src/test/resources/sql-tests/results/ansi/datetime.sql.out

@@ -152,7 +152,7 @@ struct<CAST(TIMESTAMP '2011-11-11 11:11:11' + INTERVAL '2 days' AS TIMESTAMP):ti
 -- !query
 select timestamp'2011-11-11 11:11:11' - interval '2' day
 -- !query schema
-struct<CAST(TIMESTAMP '2011-11-11 11:11:11' - INTERVAL '2 days' AS TIMESTAMP):timestamp>
+struct<CAST(TIMESTAMP '2011-11-11 11:11:11' + (- INTERVAL '2 days') AS TIMESTAMP):timestamp>
 -- !query output
 2011-11-09 11:11:11
 
@@ -178,23 +178,23 @@ requirement failed: Cannot add hours, minutes or seconds, milliseconds, microsec
 -- !query
 select '2011-11-11' - interval '2' day
 -- !query schema
-struct<CAST(CAST(2011-11-11 AS TIMESTAMP) - INTERVAL '2 days' AS STRING):string>
+struct<CAST(CAST(2011-11-11 AS TIMESTAMP) + (- INTERVAL '2 days') AS STRING):string>
 -- !query output
 2011-11-09 00:00:00
 
 
 -- !query
 select '2011-11-11 11:11:11' - interval '2' second
 -- !query schema
-struct<CAST(CAST(2011-11-11 11:11:11 AS TIMESTAMP) - INTERVAL '2 seconds' AS STRING):string>
+struct<CAST(CAST(2011-11-11 11:11:11 AS TIMESTAMP) + (- INTERVAL '2 seconds') AS STRING):string>
 -- !query output
 2011-11-11 11:11:09
 
 
 -- !query
 select '1' - interval '2' second
 -- !query schema
-struct<CAST(CAST(1 AS TIMESTAMP) - INTERVAL '2 seconds' AS STRING):string>
+struct<CAST(CAST(1 AS TIMESTAMP) + (- INTERVAL '2 seconds') AS STRING):string>
 -- !query output
 NULL
 
@@ -205,7 +205,7 @@ select 1 - interval '2' second
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-cannot resolve '1 - INTERVAL '2 seconds'' due to data type mismatch: argument 1 requires timestamp type, however, '1' is of int type.; line 1 pos 7
+cannot resolve '1 + (- INTERVAL '2 seconds')' due to data type mismatch: argument 1 requires timestamp type, however, '1' is of int type.; line 1 pos 7
 
 
 -- !query

sql/core/src/test/resources/sql-tests/results/ansi/interval.sql.out

@@ -705,7 +705,7 @@ select
   interval '2-2' year to month + tsval
 from interval_arithmetic
 -- !query schema
-struct<tsval:timestamp,CAST(tsval - INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp,CAST(tsval - INTERVAL '-2 years -2 months' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '-2 years -2 months' AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '2 years 2 months') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp>
+struct<tsval:timestamp,CAST(tsval + (- INTERVAL '2 years 2 months') AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '-2 years -2 months') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '-2 years -2 months' AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '2 years 2 months') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp>
 -- !query output
 2012-01-01 00:00:00	2009-11-01 00:00:00	2014-03-01 00:00:00	2014-03-01 00:00:00	2009-11-01 00:00:00	2009-11-01 00:00:00	2014-03-01 00:00:00
 
@@ -749,7 +749,7 @@ select
   interval '99 11:22:33.123456789' day to second + tsval
 from interval_arithmetic
 -- !query schema
-struct<tsval:timestamp,CAST(tsval - INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval - INTERVAL '-99 days -11 hours -22 minutes -33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '-99 days -11 hours -22 minutes -33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp>
+struct<tsval:timestamp,CAST(tsval + (- INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds') AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '-99 days -11 hours -22 minutes -33.123456 seconds') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '-99 days -11 hours -22 minutes -33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp>
 -- !query output
 2012-01-01 00:00:00	2011-09-23 12:37:26.876544	2012-04-09 11:22:33.123456	2012-04-09 11:22:33.123456	2011-09-23 12:37:26.876544	2011-09-23 12:37:26.876544	2012-04-09 11:22:33.123456
 

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

@@ -126,7 +126,7 @@ struct<CAST(TIMESTAMP '2011-11-11 11:11:11' + INTERVAL '2 days' AS TIMESTAMP):ti
 -- !query
 select timestamp'2011-11-11 11:11:11' - interval '2' day
 -- !query schema
-struct<CAST(TIMESTAMP '2011-11-11 11:11:11' - INTERVAL '2 days' AS TIMESTAMP):timestamp>
+struct<CAST(TIMESTAMP '2011-11-11 11:11:11' + (- INTERVAL '2 days') AS TIMESTAMP):timestamp>
 -- !query output
 2011-11-09 11:11:11
 
@@ -150,23 +150,23 @@ struct<DATE '2011-11-11' + (- INTERVAL '2 seconds'):date>
 -- !query
 select '2011-11-11' - interval '2' day
 -- !query schema
-struct<CAST(CAST(2011-11-11 AS TIMESTAMP) - INTERVAL '2 days' AS STRING):string>
+struct<CAST(CAST(2011-11-11 AS TIMESTAMP) + (- INTERVAL '2 days') AS STRING):string>
 -- !query output
 2011-11-09 00:00:00
 
 
 -- !query
 select '2011-11-11 11:11:11' - interval '2' second
 -- !query schema
-struct<CAST(CAST(2011-11-11 11:11:11 AS TIMESTAMP) - INTERVAL '2 seconds' AS STRING):string>
+struct<CAST(CAST(2011-11-11 11:11:11 AS TIMESTAMP) + (- INTERVAL '2 seconds') AS STRING):string>
 -- !query output
 2011-11-11 11:11:09
 
 
 -- !query
 select '1' - interval '2' second
 -- !query schema
-struct<CAST(CAST(1 AS TIMESTAMP) - INTERVAL '2 seconds' AS STRING):string>
+struct<CAST(CAST(1 AS TIMESTAMP) + (- INTERVAL '2 seconds') AS STRING):string>
 -- !query output
 NULL
 
@@ -177,7 +177,7 @@ select 1 - interval '2' second
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-cannot resolve '1 - INTERVAL '2 seconds'' due to data type mismatch: argument 1 requires timestamp type, however, '1' is of int type.; line 1 pos 7
+cannot resolve '1 + (- INTERVAL '2 seconds')' due to data type mismatch: argument 1 requires timestamp type, however, '1' is of int type.; line 1 pos 7
 
 
 -- !query

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

@@ -684,7 +684,7 @@ select
   interval '2-2' year to month + tsval
 from interval_arithmetic
 -- !query schema
-struct<tsval:timestamp,CAST(tsval - INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp,CAST(tsval - INTERVAL '-2 years -2 months' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '-2 years -2 months' AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '2 years 2 months') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp>
+struct<tsval:timestamp,CAST(tsval + (- INTERVAL '2 years 2 months') AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '-2 years -2 months') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '-2 years -2 months' AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '2 years 2 months') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '2 years 2 months' AS TIMESTAMP):timestamp>
 -- !query output
 2012-01-01 00:00:00	2009-11-01 00:00:00	2014-03-01 00:00:00	2014-03-01 00:00:00	2009-11-01 00:00:00	2009-11-01 00:00:00	2014-03-01 00:00:00
 
@@ -727,7 +727,7 @@ select
   interval '99 11:22:33.123456789' day to second + tsval
 from interval_arithmetic
 -- !query schema
-struct<tsval:timestamp,CAST(tsval - INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval - INTERVAL '-99 days -11 hours -22 minutes -33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '-99 days -11 hours -22 minutes -33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp>
+struct<tsval:timestamp,CAST(tsval + (- INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds') AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '-99 days -11 hours -22 minutes -33.123456 seconds') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '-99 days -11 hours -22 minutes -33.123456 seconds' AS TIMESTAMP):timestamp,CAST(tsval + (- INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds') AS TIMESTAMP):timestamp,CAST(tsval + INTERVAL '99 days 11 hours 22 minutes 33.123456 seconds' AS TIMESTAMP):timestamp>
 -- !query output
 2012-01-01 00:00:00	2011-09-23 12:37:26.876544	2012-04-09 11:22:33.123456	2012-04-09 11:22:33.123456	2011-09-23 12:37:26.876544	2011-09-23 12:37:26.876544	2012-04-09 11:22:33.123456