vrozov 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_r198899847
########## File path: exec/java-exec/src/main/java/org/apache/drill/exec/store/parquet/ParquetPushDownFilter.java ########## @@ -165,12 +167,32 @@ protected void doOnMatch(RelOptRuleCall call, FilterPrel filter, ProjectPrel pro return; } - RelNode newScan = ScanPrel.create(scan, scan.getTraitSet(), newGroupScan, scan.getRowType());; if (project != null) { newScan = project.copy(project.getTraitSet(), ImmutableList.of(newScan)); } + + RowsMatch matchAll = RowsMatch.ALL; + if (newGroupScan instanceof AbstractParquetGroupScan) { + List<RowGroupInfo> rowGroupInfos = ((AbstractParquetGroupScan) newGroupScan).rowGroupInfos; + for (RowGroupInfo rowGroup : rowGroupInfos) { + if (rowGroup.getRowsMatch() != RowsMatch.ALL) { + matchAll = RowsMatch.SOME; + break; + } + } + } else { + matchAll = RowsMatch.SOME; + } + // If all groups are in RowsMatch.ALL, no need to apply the filter again to their rows => prune the filter + if (matchAll == ParquetFilterPredicate.RowsMatch.ALL) { Review comment: Move this inside `if (newGroupScan instanceof AbstractParquetGroupScan) {`. ---------------------------------------------------------------- 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