trim() the string when cast stringToTimestamp and stringToDate

apache · Nov 5, 2018 · d297817 · d297817
1 parent c71db43
commit d297817
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 9 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/Cast.scala
@@ -359,7 +359,7 @@ case class Cast(child: Expression, dataType: DataType, timeZoneId: Option[String
   // TimestampConverter
   private[this] def castToTimestamp(from: DataType): Any => Any = from match {
     case StringType =>
-      buildCast[UTF8String](_, utfs => DateTimeUtils.stringToTimestamp(utfs, timeZone).orNull)
+      buildCast[UTF8String](_, s => DateTimeUtils.stringToTimestamp(s.trim(), timeZone).orNull)
     case BooleanType =>
       buildCast[Boolean](_, b => if (b) 1L else 0)
     case LongType =>
@@ -402,7 +402,7 @@ case class Cast(child: Expression, dataType: DataType, timeZoneId: Option[String
   // DateConverter
   private[this] def castToDate(from: DataType): Any => Any = from match {
     case StringType =>
-      buildCast[UTF8String](_, s => DateTimeUtils.stringToDate(s).orNull)
+      buildCast[UTF8String](_, s => DateTimeUtils.stringToDate(s.trim()).orNull)
     case TimestampType =>
       // throw valid precision more than seconds, according to Hive.
       // Timestamp.nanos is in 0 to 999,999,999, no more than a second.
@@ -907,7 +907,7 @@ case class Cast(child: Expression, dataType: DataType, timeZoneId: Option[String
       val intOpt = ctx.freshVariable("intOpt", classOf[Option[Integer]])
       (c, evPrim, evNull) => code"""
         scala.Option<Integer> $intOpt =
-          org.apache.spark.sql.catalyst.util.DateTimeUtils.stringToDate($c);
+          org.apache.spark.sql.catalyst.util.DateTimeUtils.stringToDate($c.trim());
         if ($intOpt.isDefined()) {
           $evPrim = ((Integer) $intOpt.get()).intValue();
         } else {
@@ -1010,7 +1010,7 @@ case class Cast(child: Expression, dataType: DataType, timeZoneId: Option[String
       (c, evPrim, evNull) =>
         code"""
           scala.Option<Long> $longOpt =
-            org.apache.spark.sql.catalyst.util.DateTimeUtils.stringToTimestamp($c, $tz);
+            org.apache.spark.sql.catalyst.util.DateTimeUtils.stringToTimestamp($c.trim(), $tz);
           if ($longOpt.isDefined()) {
             $evPrim = ((Long) $longOpt.get()).longValue();
           } else {

diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CastSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/CastSuite.scala
@@ -98,8 +98,10 @@ class CastSuite extends SparkFunSuite with ExpressionEvalHelper {
     c = Calendar.getInstance()
     c.set(2015, 2, 18, 0, 0, 0)
     c.set(Calendar.MILLISECOND, 0)
-    checkEvaluation(Cast(Literal("2015-03-18"), DateType), new Date(c.getTimeInMillis))
-    checkEvaluation(Cast(Literal("2015-03-18 "), DateType), new Date(c.getTimeInMillis))
+
+    Seq("2015-03-18", " 2015-03-18", "2015-03-18 ", " 2015-03-18 ").foreach { s =>
+      checkEvaluation(Cast(Literal(s), DateType), new Date(c.getTimeInMillis))
+    }
     checkEvaluation(Cast(Literal("2015-03-18 123142"), DateType), new Date(c.getTimeInMillis))
     checkEvaluation(Cast(Literal("2015-03-18T123123"), DateType), new Date(c.getTimeInMillis))
     checkEvaluation(Cast(Literal("2015-03-18T"), DateType), new Date(c.getTimeInMillis))
@@ -130,9 +132,9 @@ class CastSuite extends SparkFunSuite with ExpressionEvalHelper {
       c = Calendar.getInstance(tz)
       c.set(2015, 2, 18, 0, 0, 0)
       c.set(Calendar.MILLISECOND, 0)
-      checkCastStringToTimestamp("2015-03-18", new Timestamp(c.getTimeInMillis))
-      checkCastStringToTimestamp("2015-03-18 ", new Timestamp(c.getTimeInMillis))
-      checkCastStringToTimestamp("2015-03-18T", new Timestamp(c.getTimeInMillis))
+      Seq("2015-03-18", " 2015-03-18", "2015-03-18 ", " 2015-03-18 ", "2015-03-18T").foreach { s =>
+        checkCastStringToTimestamp(s, new Timestamp(c.getTimeInMillis))
+      }
 
       c = Calendar.getInstance(tz)
       c.set(2015, 2, 18, 12, 3, 17)