[SPARK-25454][SQL] Avoid precision loss in division with decimal with…

… negative scale
apache · Sep 18, 2018 · 7c4b454 · 7c4b454
1 parent b66e14d
commit 7c4b454
Show file tree

Hide file tree

Showing 4 changed files with 19 additions and 5 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecision.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecision.scala
@@ -129,16 +129,17 @@ object DecimalPrecision extends TypeCoercionRule {
         resultType)
 
     case Divide(e1 @ DecimalType.Expression(p1, s1), e2 @ DecimalType.Expression(p2, s2)) =>
+      val adjP2 = if (s2 < 0) p2 - s2 else p2
       val resultType = if (SQLConf.get.decimalOperationsAllowPrecisionLoss) {
         // Precision: p1 - s1 + s2 + max(6, s1 + p2 + 1)
         // Scale: max(6, s1 + p2 + 1)
         val intDig = p1 - s1 + s2
-        val scale = max(DecimalType.MINIMUM_ADJUSTED_SCALE, s1 + p2 + 1)
+        val scale = max(DecimalType.MINIMUM_ADJUSTED_SCALE, s1 + adjP2 + 1)
         val prec = intDig + scale
         DecimalType.adjustPrecisionScale(prec, scale)
       } else {
         var intDig = min(DecimalType.MAX_SCALE, p1 - s1 + s2)
-        var decDig = min(DecimalType.MAX_SCALE, max(6, s1 + p2 + 1))
+        var decDig = min(DecimalType.MAX_SCALE, max(6, s1 + adjP2 + 1))
         val diff = (intDig + decDig) - DecimalType.MAX_SCALE
         if (diff > 0) {
           decDig -= diff / 2 + 1

diff --git a/...atalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecisionSuite.scala b/...atalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecisionSuite.scala
@@ -276,9 +276,11 @@ class DecimalPrecisionSuite extends AnalysisTest with BeforeAndAfter {
     val a = AttributeReference("a", DecimalType(3, -10))()
     val b = AttributeReference("b", DecimalType(1, -1))()
     val c = AttributeReference("c", DecimalType(35, 1))()
+    val nonNegative = AttributeReference("nn", DecimalType(11, 0))()
     checkType(Multiply(a, b), DecimalType(5, -11))
     checkType(Multiply(a, c), DecimalType(38, -9))
     checkType(Multiply(b, c), DecimalType(37, 0))
+    checkType(Divide(nonNegative, a), DecimalType(15, 14))
   }
 
   /** strength reduction for integer/decimal comparisons */

diff --git a/...e/src/test/resources/sql-tests/inputs/typeCoercion/native/decimalArithmeticOperations.sql b/...e/src/test/resources/sql-tests/inputs/typeCoercion/native/decimalArithmeticOperations.sql
@@ -83,4 +83,7 @@ select 12345678912345678912345678912.1234567 + 9999999999999999999999999999999.1
 select 123456789123456789.1234567890 * 1.123456789123456789;
 select 12345678912345.123456789123 / 0.000000012345678;
 
+-- division with negative scale operands
+select 26393499451/ 1000e6;
+
 drop table decimals_test;
diff --git a/.../test/resources/sql-tests/results/typeCoercion/native/decimalArithmeticOperations.sql.out b/.../test/resources/sql-tests/results/typeCoercion/native/decimalArithmeticOperations.sql.out
@@ -1,5 +1,5 @@
 -- Automatically generated by SQLQueryTestSuite
--- Number of queries: 40
+-- Number of queries: 41
 
 
 -- !query 0
@@ -328,8 +328,16 @@ NULL
 
 
 -- !query 39
-drop table decimals_test
+select 26393499451/ 1000e6
 -- !query 39 schema
-struct<>
+struct<(CAST(CAST(26393499451 AS DECIMAL(11,0)) AS DECIMAL(11,0)) / CAST(1.000E+9 AS DECIMAL(11,0))):decimal(16,11)>
 -- !query 39 output
+26.393499451
+
+
+-- !query 40
+drop table decimals_test
+-- !query 40 schema
+struct<>
+-- !query 40 output