wangbo commented on a change in pull request #8318:
URL: https://github.com/apache/incubator-doris/pull/8318#discussion_r825609607
##########
File path: be/src/olap/comparison_predicate.cpp
##########
@@ -145,28 +146,68 @@ COMPARISON_PRED_COLUMN_BLOCK_EVALUATE(LessEqualPredicate,
<=)
COMPARISON_PRED_COLUMN_BLOCK_EVALUATE(GreaterPredicate, >)
COMPARISON_PRED_COLUMN_BLOCK_EVALUATE(GreaterEqualPredicate, >=)
-#define COMPARISON_PRED_COLUMN_EVALUATE(CLASS, OP)
\
+#define COMPARISON_PRED_COLUMN_EVALUATE(CLASS, OP, IS_RANGE)
\
template <class type>
\
void CLASS<type>::evaluate(vectorized::IColumn& column, uint16_t* sel,
uint16_t* size) const { \
uint16_t new_size = 0;
\
if (column.is_nullable()) {
\
- auto* nullable_column =
\
+ auto* nullable_col =
\
vectorized::check_and_get_column<vectorized::ColumnNullable>(column); \
- auto& null_bitmap = reinterpret_cast<const
vectorized::ColumnVector<uint8_t>&>( \
-
*(nullable_column->get_null_map_column_ptr())) \
+ auto& null_bitmap = reinterpret_cast<const
vectorized::ColumnUInt8&>( \
+ nullable_col->get_null_map_column())
\
.get_data();
\
- auto* nest_column_vector =
\
-
vectorized::check_and_get_column<vectorized::PredicateColumnType<type>>( \
- nullable_column->get_nested_column());
\
- auto& data_array = nest_column_vector->get_data();
\
- for (uint16_t i = 0; i < *size; i++) {
\
- uint16_t idx = sel[i];
\
- sel[new_size] = idx;
\
- const type& cell_value = reinterpret_cast<const
type&>(data_array[idx]); \
- bool ret = !null_bitmap[idx] && (cell_value OP _value);
\
- new_size += _opposite ? !ret : ret;
\
+ auto& nested_col = nullable_col->get_nested_column();
\
+ if (nested_col.is_column_dictionary()) {
\
+ if constexpr (std::is_same_v<type, StringValue>) {
\
+ auto* nested_col_ptr = vectorized::check_and_get_column<
\
+
vectorized::ColumnDictionary<vectorized::Int32>>(nested_col); \
+ auto code = nested_col_ptr->find_code(_value);
\
+ if (code < 0 && IS_RANGE) {
\
+ code = nested_col_ptr->find_bound_code(_value, 0 OP 1,
1 OP 1 ); \
+ }
\
+ auto& data_array = nested_col_ptr->get_data();
\
+ for (uint16_t i = 0; i < *size; i++) {
\
+ uint16_t idx = sel[i];
\
+ sel[new_size] = idx;
\
+ const auto& cell_value =
\
+ reinterpret_cast<const
vectorized::Int32&>(data_array[idx]); \
+ bool ret = !null_bitmap[idx] && (cell_value OP code);
\
+ new_size += _opposite ? !ret : ret;
\
+ }
\
+ }
\
+ } else {
\
+ auto* nested_col_ptr =
\
+
vectorized::check_and_get_column<vectorized::PredicateColumnType<type>>( \
+ nested_col);
\
+ auto& data_array = nested_col_ptr->get_data();
\
+ for (uint16_t i = 0; i < *size; i++) {
\
+ uint16_t idx = sel[i];
\
+ sel[new_size] = idx;
\
+ const type& cell_value = reinterpret_cast<const
type&>(data_array[idx]); \
+ bool ret = !null_bitmap[idx] && (cell_value OP _value);
\
+ new_size += _opposite ? !ret : ret;
\
+ }
\
}
\
*size = new_size;
\
+ } else if (column.is_column_dictionary()) {
\
+ if constexpr (std::is_same_v<type, StringValue>) {
\
+ auto& dict_col =
\
+
reinterpret_cast<vectorized::ColumnDictionary<vectorized::Int32>&>(column);\
+ auto& data_array = dict_col.get_data();
\
+ auto code = dict_col.find_code(_value);
\
+ if (code < 0 && IS_RANGE) {
\
+ code = dict_col.find_bound_code(_value, 0 OP 1, 1 OP 1);
\
Review comment:
If there is a range predicate here, we just need to use string sort rule
to sort dict code.
This means ```data_array``` has the same order with string value.
Finally we can compare value and data_array directly here.
So why need ```find_bound_code``` here?
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
