jbimbert commented on a change in pull request #1298: DRILL-5796: Filter
pruning for multi rowgroup parquet file
URL: https://github.com/apache/drill/pull/1298#discussion_r199483001
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/expr/stat/ParquetComparisonPredicate.java
##########
@@ -83,23 +84,26 @@ private ParquetComparisonPredicate(
* where Column1 and Column2 are from same parquet table.
*/
@Override
- public boolean canDrop(RangeExprEvaluator<C> evaluator) {
+ public RowsMatch matches(RangeExprEvaluator<C> evaluator) {
Statistics<C> leftStat = left.accept(evaluator, null);
- if (isNullOrEmpty(leftStat)) {
- return false;
+ if (isNullOrEmpty(leftStat) || !leftStat.hasNonNullValue()) {
+ return RowsMatch.SOME;
}
-
Statistics<C> rightStat = right.accept(evaluator, null);
- if (isNullOrEmpty(rightStat)) {
- return false;
+ if (isNullOrEmpty(rightStat) || !rightStat.hasNonNullValue()) {
+ return RowsMatch.SOME;
}
-
- // if either side is ALL null, = is evaluated to UNKNOWN -> canDrop
if (isAllNulls(leftStat, evaluator.getRowCount()) || isAllNulls(rightStat,
evaluator.getRowCount())) {
- return true;
+ return RowsMatch.NONE;
}
+ return predicate.apply(leftStat, rightStat);
+ }
- return (leftStat.hasNonNullValue() && rightStat.hasNonNullValue()) &&
predicate.test(leftStat, rightStat);
+ /**
+ * If one rowgroup contains some null values, change the RowsMatch.ALL into
RowsMatch.SOME (null values should be discarded by filter)
+ */
+ static RowsMatch checkNull(Statistics leftStat, Statistics rightStat) {
Review comment:
Done
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
