[SPARK-20909][SQL] Add build-int SQL function - DAYOFWEEK

## What changes were proposed in this pull request?

Add build-int SQL function - DAYOFWEEK

## How was this patch tested?

unit tests

Author: Yuming Wang <wgyumg@gmail.com>

Closes #18134 from wangyum/SPARK-20909.
This commit is contained in:
Yuming Wang 2017-05-30 15:40:50 +09:00 committed by Takuya UESHIN
parent 96a4d1d082
commit d797ed0ef1
5 changed files with 64 additions and 1 deletions

View file

@ -360,6 +360,7 @@ object FunctionRegistry {
expression[ToUTCTimestamp]("to_utc_timestamp"), expression[ToUTCTimestamp]("to_utc_timestamp"),
expression[TruncDate]("trunc"), expression[TruncDate]("trunc"),
expression[UnixTimestamp]("unix_timestamp"), expression[UnixTimestamp]("unix_timestamp"),
expression[DayOfWeek]("dayofweek"),
expression[WeekOfYear]("weekofyear"), expression[WeekOfYear]("weekofyear"),
expression[Year]("year"), expression[Year]("year"),
expression[TimeWindow]("window"), expression[TimeWindow]("window"),

View file

@ -402,6 +402,44 @@ case class DayOfMonth(child: Expression) extends UnaryExpression with ImplicitCa
} }
} }
// scalastyle:off line.size.limit
@ExpressionDescription(
usage = "_FUNC_(date) - Returns the day of the week for date/timestamp (1 = Sunday, 2 = Monday, ..., 7 = Saturday).",
extended = """
Examples:
> SELECT _FUNC_('2009-07-30');
5
""")
// scalastyle:on line.size.limit
case class DayOfWeek(child: Expression) extends UnaryExpression with ImplicitCastInputTypes {
override def inputTypes: Seq[AbstractDataType] = Seq(DateType)
override def dataType: DataType = IntegerType
@transient private lazy val c = {
Calendar.getInstance(DateTimeUtils.getTimeZone("UTC"))
}
override protected def nullSafeEval(date: Any): Any = {
c.setTimeInMillis(date.asInstanceOf[Int] * 1000L * 3600L * 24L)
c.get(Calendar.DAY_OF_WEEK)
}
override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
nullSafeCodeGen(ctx, ev, time => {
val cal = classOf[Calendar].getName
val c = ctx.freshName("cal")
val dtu = DateTimeUtils.getClass.getName.stripSuffix("$")
ctx.addMutableState(cal, c, s"""$c = $cal.getInstance($dtu.getTimeZone("UTC"));""")
s"""
$c.setTimeInMillis($time * 1000L * 3600L * 24L);
${ev.value} = $c.get($cal.DAY_OF_WEEK);
"""
})
}
}
// scalastyle:off line.size.limit // scalastyle:off line.size.limit
@ExpressionDescription( @ExpressionDescription(
usage = "_FUNC_(date) - Returns the week of the year of the given date. A week is considered to start on a Monday and week 1 is the first week with >3 days.", usage = "_FUNC_(date) - Returns the week of the year of the given date. A week is considered to start on a Monday and week 1 is the first week with >3 days.",

View file

@ -196,6 +196,20 @@ class DateExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
} }
} }
test("DayOfWeek") {
checkEvaluation(DayOfWeek(Literal.create(null, DateType)), null)
checkEvaluation(DayOfWeek(Literal(d)), Calendar.WEDNESDAY)
checkEvaluation(DayOfWeek(Cast(Literal(sdfDate.format(d)), DateType, gmtId)),
Calendar.WEDNESDAY)
checkEvaluation(DayOfWeek(Cast(Literal(ts), DateType, gmtId)), Calendar.FRIDAY)
checkEvaluation(DayOfWeek(Cast(Literal("2011-05-06"), DateType, gmtId)), Calendar.FRIDAY)
checkEvaluation(DayOfWeek(Literal(new Date(sdf.parse("2017-05-27 13:10:15").getTime))),
Calendar.SATURDAY)
checkEvaluation(DayOfWeek(Literal(new Date(sdf.parse("1582-10-15 13:10:15").getTime))),
Calendar.FRIDAY)
checkConsistencyBetweenInterpretedAndCodegen(DayOfWeek, DateType)
}
test("WeekOfYear") { test("WeekOfYear") {
checkEvaluation(WeekOfYear(Literal.create(null, DateType)), null) checkEvaluation(WeekOfYear(Literal.create(null, DateType)), null)
checkEvaluation(WeekOfYear(Literal(d)), 15) checkEvaluation(WeekOfYear(Literal(d)), 15)

View file

@ -6,3 +6,5 @@ select current_date = current_date(), current_timestamp = current_timestamp();
select to_date(null), to_date('2016-12-31'), to_date('2016-12-31', 'yyyy-MM-dd'); select to_date(null), to_date('2016-12-31'), to_date('2016-12-31', 'yyyy-MM-dd');
select to_timestamp(null), to_timestamp('2016-12-31 00:12:00'), to_timestamp('2016-12-31', 'yyyy-MM-dd'); select to_timestamp(null), to_timestamp('2016-12-31 00:12:00'), to_timestamp('2016-12-31', 'yyyy-MM-dd');
select dayofweek('2007-02-03'), dayofweek('2009-07-30'), dayofweek('2017-05-27'), dayofweek(null), dayofweek('1582-10-15 13:10:15');

View file

@ -1,5 +1,5 @@
-- Automatically generated by SQLQueryTestSuite -- Automatically generated by SQLQueryTestSuite
-- Number of queries: 3 -- Number of queries: 4
-- !query 0 -- !query 0
@ -24,3 +24,11 @@ select to_timestamp(null), to_timestamp('2016-12-31 00:12:00'), to_timestamp('20
struct<to_timestamp(NULL):timestamp,to_timestamp('2016-12-31 00:12:00'):timestamp,to_timestamp('2016-12-31', 'yyyy-MM-dd'):timestamp> struct<to_timestamp(NULL):timestamp,to_timestamp('2016-12-31 00:12:00'):timestamp,to_timestamp('2016-12-31', 'yyyy-MM-dd'):timestamp>
-- !query 2 output -- !query 2 output
NULL 2016-12-31 00:12:00 2016-12-31 00:00:00 NULL 2016-12-31 00:12:00 2016-12-31 00:00:00
-- !query 3
select dayofweek('2007-02-03'), dayofweek('2009-07-30'), dayofweek('2017-05-27'), dayofweek(null), dayofweek('1582-10-15 13:10:15')
-- !query 3 schema
struct<dayofweek(CAST(2007-02-03 AS DATE)):int,dayofweek(CAST(2009-07-30 AS DATE)):int,dayofweek(CAST(2017-05-27 AS DATE)):int,dayofweek(CAST(NULL AS DATE)):int,dayofweek(CAST(1582-10-15 13:10:15 AS DATE)):int>
-- !query 3 output
7 5 7 NULL 6