Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/21850#discussion_r204933164
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala
---
@@ -414,6 +414,9 @@ object SimplifyConditionals extends Rule[LogicalPlan]
with PredicateHelper {
// these branches can be pruned away
val (h, t) = branches.span(_._1 != TrueLiteral)
CaseWhen( h :+ t.head, None)
+
+ case CaseWhen((cond, branchValue) :: Nil, elseValue) =>
+ If(cond, branchValue, elseValue.getOrElse(Literal(null,
branchValue.dataType)))
--- End diff --
Before:
```
== Parsed Logical Plan ==
'Project [CASE WHEN isnull('a) THEN 1 END AS col1#181]
+- 'UnresolvedRelation
== Optimized Logical Plan ==
Project [CASE WHEN isnull(a#182) THEN 1 END AS col1#181]
+- Relation[a#182] parquet
```
Generated Java code
```java
/* 043 */ protected void processNext() throws java.io.IOException {
/* 044 */ if (scan_mutableStateArray_1[0] == null) {
/* 045 */ scan_nextBatch_0();
/* 046 */ }
/* 047 */ while (scan_mutableStateArray_1[0] != null) {
/* 048 */ int scan_numRows_0 = scan_mutableStateArray_1[0].numRows();
/* 049 */ int scan_localEnd_0 = scan_numRows_0 - scan_batchIdx_0;
/* 050 */ for (int scan_localIdx_0 = 0; scan_localIdx_0 <
scan_localEnd_0; scan_localIdx_0++) {
/* 051 */ int scan_rowIdx_0 = scan_batchIdx_0 + scan_localIdx_0;
/* 052 */ byte project_caseWhenResultState_0 = -1;
/* 053 */ do {
/* 054 */ boolean scan_isNull_0 =
scan_mutableStateArray_2[0].isNullAt(scan_rowIdx_0);
/* 055 */ int scan_value_0 = scan_isNull_0 ? -1 :
(scan_mutableStateArray_2[0].getInt(scan_rowIdx_0));
/* 056 */ if (!false && scan_isNull_0) {
/* 057 */ project_caseWhenResultState_0 = (byte)(false ? 1 : 0);
/* 058 */ project_project_value_0_0 = 1;
/* 059 */ continue;
/* 060 */ }
/* 061 */
/* 062 */ } while (false);
/* 063 */ // TRUE if any condition is met and the result is null,
or no any condition is met.
/* 064 */ final boolean project_isNull_0 =
(project_caseWhenResultState_0 != 0);
/* 065 */ scan_mutableStateArray_3[1].reset();
/* 066 */
/* 067 */ scan_mutableStateArray_3[1].zeroOutNullBytes();
/* 068 */
/* 069 */ if (project_isNull_0) {
/* 070 */ scan_mutableStateArray_3[1].setNullAt(0);
/* 071 */ } else {
/* 072 */ scan_mutableStateArray_3[1].write(0,
project_project_value_0_0);
/* 073 */ }
/* 074 */ append((scan_mutableStateArray_3[1].getRow()));
/* 075 */ if (shouldStop()) { scan_batchIdx_0 = scan_rowIdx_0 + 1;
return; }
/* 076 */ }
/* 077 */ scan_batchIdx_0 = scan_numRows_0;
/* 078 */ scan_mutableStateArray_1[0] = null;
/* 079 */ scan_nextBatch_0();
/* 080 */ }
/* 081 */ ((org.apache.spark.sql.execution.metric.SQLMetric)
references[1] /* scanTime */).add(scan_scanTime_0 / (1000 * 1000));
/* 082 */ scan_scanTime_0 = 0;
/* 083 */ }
```
After:
```
== Parsed Logical Plan ==
'Project [CASE WHEN isnull('a) THEN 1 END AS b#186]
+- 'UnresolvedRelation `tddddd`
== Optimized Logical Plan ==
Project [if (isnull(a#187)) 1 else null AS b#186]
+- Relation[a#187,b#188] parquet
```
Generated Java code:
```java
/* 042 */ protected void processNext() throws java.io.IOException {
/* 043 */ if (scan_mutableStateArray_1[0] == null) {
/* 044 */ scan_nextBatch_0();
/* 045 */ }
/* 046 */ while (scan_mutableStateArray_1[0] != null) {
/* 047 */ int scan_numRows_0 = scan_mutableStateArray_1[0].numRows();
/* 048 */ int scan_localEnd_0 = scan_numRows_0 - scan_batchIdx_0;
/* 049 */ for (int scan_localIdx_0 = 0; scan_localIdx_0 <
scan_localEnd_0; scan_localIdx_0++) {
/* 050 */ int scan_rowIdx_0 = scan_batchIdx_0 + scan_localIdx_0;
/* 051 */ boolean scan_isNull_0 =
scan_mutableStateArray_2[0].isNullAt(scan_rowIdx_0);
/* 052 */ int scan_value_0 = scan_isNull_0 ? -1 :
(scan_mutableStateArray_2[0].getInt(scan_rowIdx_0));
/* 053 */ boolean project_isNull_0 = false;
/* 054 */ int project_value_0 = -1;
/* 055 */ if (!false && scan_isNull_0) {
/* 056 */ project_isNull_0 = false;
/* 057 */ project_value_0 = 1;
/* 058 */ } else {
/* 059 */ project_isNull_0 = true;
/* 060 */ project_value_0 = -1;
/* 061 */ }
/* 062 */ scan_mutableStateArray_3[1].reset();
/* 063 */
/* 064 */ scan_mutableStateArray_3[1].zeroOutNullBytes();
/* 065 */
/* 066 */ if (project_isNull_0) {
/* 067 */ scan_mutableStateArray_3[1].setNullAt(0);
/* 068 */ } else {
/* 069 */ scan_mutableStateArray_3[1].write(0, project_value_0);
/* 070 */ }
/* 071 */ append((scan_mutableStateArray_3[1].getRow()));
/* 072 */ if (shouldStop()) { scan_batchIdx_0 = scan_rowIdx_0 + 1;
return; }
/* 073 */ }
/* 074 */ scan_batchIdx_0 = scan_numRows_0;
/* 075 */ scan_mutableStateArray_1[0] = null;
/* 076 */ scan_nextBatch_0();
/* 077 */ }
/* 078 */ ((org.apache.spark.sql.execution.metric.SQLMetric)
references[1] /* scanTime */).add(scan_scanTime_0 / (1000 * 1000));
/* 079 */ scan_scanTime_0 = 0;
/* 080 */ }
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
