Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/10882#discussion_r50617297
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DecimalPrecision.scala
---
@@ -0,0 +1,261 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.catalyst.analysis
+
+import org.apache.spark.sql.catalyst.expressions.Literal._
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.types._
+
+
+// scalastyle:off
+/**
+ * Calculates and propagates precision for fixed-precision decimals. Hive
has a number of
+ * rules for this based on the SQL standard and MS SQL:
+ *
https://cwiki.apache.org/confluence/download/attachments/27362075/Hive_Decimal_Precision_Scale_Support.pdf
+ * https://msdn.microsoft.com/en-us/library/ms190476.aspx
+ *
+ * In particular, if we have expressions e1 and e2 with precision/scale
p1/s2 and p2/s2
+ * respectively, then the following operations have the following
precision / scale:
+ *
+ * Operation Result Precision Result Scale
+ *
------------------------------------------------------------------------
+ * e1 + e2 max(s1, s2) + max(p1-s1, p2-s2) + 1 max(s1, s2)
+ * e1 - e2 max(s1, s2) + max(p1-s1, p2-s2) + 1 max(s1, s2)
+ * e1 * e2 p1 + p2 + 1 s1 + s2
+ * e1 / e2 p1 - s1 + s2 + max(6, s1 + p2 + 1) max(6, s1 + p2 +
1)
+ * e1 % e2 min(p1-s1, p2-s2) + max(s1, s2) max(s1, s2)
+ * e1 union e2 max(s1, s2) + max(p1-s1, p2-s2) max(s1, s2)
+ * sum(e1) p1 + 10 s1
+ * avg(e1) p1 + 4 s1 + 4
+ *
+ * Catalyst also has unlimited-precision decimals. For those, all ops
return unlimited precision.
+ *
+ * To implement the rules for fixed-precision types, we introduce casts to
turn them to unlimited
+ * precision, do the math on unlimited-precision numbers, then introduce
casts back to the
+ * required fixed precision. This allows us to do all rounding and
overflow handling in the
+ * cast-to-fixed-precision operator.
+ *
+ * In addition, when mixing non-decimal types with decimals, we use the
following rules:
+ * - BYTE gets turned into DECIMAL(3, 0)
+ * - SHORT gets turned into DECIMAL(5, 0)
+ * - INT gets turned into DECIMAL(10, 0)
+ * - LONG gets turned into DECIMAL(20, 0)
+ * - FLOAT and DOUBLE cause fixed-length decimals to turn into DOUBLE
+ */
+// scalastyle:on
+object DecimalPrecision extends Rule[LogicalPlan] {
+ import scala.math.{max, min}
+
+ private def isFloat(t: DataType): Boolean = t == FloatType || t ==
DoubleType
+
+ // Returns the wider decimal type that's wider than both of them
+ def widerDecimalType(d1: DecimalType, d2: DecimalType): DecimalType = {
+ widerDecimalType(d1.precision, d1.scale, d2.precision, d2.scale)
+ }
+ // max(s1, s2) + max(p1-s1, p2-s2), max(s1, s2)
+ def widerDecimalType(p1: Int, s1: Int, p2: Int, s2: Int): DecimalType = {
+ val scale = max(s1, s2)
+ val range = max(p1 - s1, p2 - s2)
+ DecimalType.bounded(range + scale, scale)
+ }
+
+ private def promotePrecision(e: Expression, dataType: DataType):
Expression = {
+ PromotePrecision(Cast(e, dataType))
+ }
+
+ def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators {
+ // fix decimal precision for expressions
+ case q => q.transformExpressions(
+
decimalAndDecimal.orElse(integralAndDecimalLiteral).orElse(nondecimalAndDecimal))
--- End diff --
i broke the previous monolithic decimal precision rule into 2 parts, and
then added integralAndDecimalLiteral
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
