Github user kuien commented on a diff in the pull request:
https://github.com/apache/hawq/pull/1397#discussion_r219430232
--- Diff: src/backend/cdb/cdbparquetrowgroup.c ---
@@ -322,6 +306,92 @@ ParquetRowGroupReader_ScanNextTuple(
return false;
}
+/*
+ * Get specified attributes of a tuple from current row group into slot.
+ */
+void
+ParquetRowGroupReader_ScanNextTupleColumns(
+ TupleDesc tupDesc,
+ ParquetRowGroupReader *rowGroupReader,
+ int
*hawqAttrToParquetColNum,
+ bool *projs,
+ TupleTableSlot *slot,
+ List *attsList)
+{
+ int natts = slot->tts_tupleDescriptor->natts;
+ Assert(natts <= tupDesc->natts);
+
+ Datum *values = slot_get_values(slot);
+ bool *nulls = slot_get_isnull(slot);
+
+ int colReaderIndex = 0;
+ for(int i = 0; i < natts; i++)
+ {
+ /* it is not expensive to do twice in case of bloomfilter */
+ if(projs[i] == false)
+ {
+ nulls[i] = true;
+ continue;
+ }
+
+ /* skip those attributes not in given list */
+ if (attsList != NIL && list_find_int(attsList, i) >= 0)
--- End diff --
typo, should be < 0
---
