arina-ielchiieva commented on a change in pull request #1955: DRILL-7491:
Incorrect count() returned for complex types in parquet
URL: https://github.com/apache/drill/pull/1955#discussion_r366310138
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/physical/base/AbstractGroupScanWithMetadata.java
##########
@@ -167,29 +167,43 @@ public boolean isMatchAllMetadata() {
*/
@Override
public long getColumnValueCount(SchemaPath column) {
- long tableRowCount, colNulls;
- Long nulls;
ColumnStatistics<?> columnStats =
getTableMetadata().getColumnStatistics(column);
- ColumnStatistics<?> nonInterestingColStats = null;
- if (columnStats == null) {
- nonInterestingColStats =
getNonInterestingColumnsMetadata().getColumnStatistics(column);
- }
+ ColumnStatistics<?> nonInterestingColStats = (columnStats == null)
+ ? getNonInterestingColumnsMetadata().getColumnStatistics(column) :
null;
+ long tableRowCount;
if (columnStats != null) {
tableRowCount =
TableStatisticsKind.ROW_COUNT.getValue(getTableMetadata());
} else if (nonInterestingColStats != null) {
tableRowCount =
TableStatisticsKind.ROW_COUNT.getValue(getNonInterestingColumnsMetadata());
+ columnStats = nonInterestingColStats;
+ } else if (existsNestedStatsForColumn(column, getTableMetadata())
+ || existsNestedStatsForColumn(column,
getNonInterestingColumnsMetadata())) {
+ return Statistic.NO_COLUMN_STATS;
} else {
return 0; // returns 0 if the column doesn't exist in the table.
}
- columnStats = columnStats != null ? columnStats : nonInterestingColStats;
- nulls = ColumnStatisticsKind.NULLS_COUNT.getFrom(columnStats);
- colNulls = nulls != null ? nulls : Statistic.NO_COLUMN_STATS;
+ Long nulls = ColumnStatisticsKind.NULLS_COUNT.getFrom(columnStats);
+ if (nulls == null || Statistic.NO_COLUMN_STATS == nulls ||
Statistic.NO_COLUMN_STATS == tableRowCount) {
+ return Statistic.NO_COLUMN_STATS;
+ } else {
+ return tableRowCount - nulls;
+ }
+ }
- return Statistic.NO_COLUMN_STATS == tableRowCount
- || Statistic.NO_COLUMN_STATS == colNulls
- ? Statistic.NO_COLUMN_STATS : tableRowCount - colNulls;
+ /**
+ * For complex columns, stats may be present only for nested fields. For
example, a column path is `a`,
+ * but stats present for `a`.`b`. So before making a decision that column is
absent, the case needs
+ * to be tested.
+ *
+ * @param column column path
+ * @param metadata metadata with column statistics
+ * @return whether stats exists for nested fields
+ */
+ private boolean existsNestedStatsForColumn(SchemaPath column, Metadata
metadata) {
Review comment:
I am not quite sure I follow this method logic because when you call this
method you return that there is no statistics is present but method states that
it checks that nested column statistics exists. I guess we might need to rename
method to depict exactly what it does, for example checking if column exists.
By the way, if stats for nested column exists, can we use it for calculation?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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
