morningman commented on code in PR #57959:
URL: https://github.com/apache/doris/pull/57959#discussion_r2529535486
##########
be/src/vec/exec/format/parquet/vparquet_reader.cpp:
##########
@@ -1083,9 +1083,40 @@ Status ParquetReader::_process_column_stat_filter(const
tparquet::RowGroup& row_
_t_metadata->created_by, stat)
.ok();
};
+ std::function<bool(ParquetPredicate::ColumnStat*, int)>
get_bloom_filter_func =
+ [&](ParquetPredicate::ColumnStat* stat, const int cid) {
+ auto* slot = _tuple_descriptor->slots()[cid];
+ if
(!_table_info_node_ptr->children_column_exists(slot->col_name())) {
+ return false;
+ }
+ const auto& file_col_name =
+
_table_info_node_ptr->children_file_column_name(slot->col_name());
+ const FieldSchema* col_schema =
+ _file_metadata->schema().get_column(file_col_name);
+ int parquet_col_id = col_schema->physical_column_index;
+ auto meta_data =
row_group.columns[parquet_col_id].meta_data;
+ if (!meta_data.__isset.bloom_filter_offset) {
+ return false;
+ }
+ auto primitive_type =
+
remove_nullable(col_schema->data_type)->get_primitive_type();
+ if
(!ParquetPredicate::bloom_filter_supported(primitive_type)) {
+ return false;
+ }
+ if (!stat->bloom_filter) {
+ auto st = ParquetPredicate::read_bloom_filter(
Review Comment:
We should add some log or profile to notice it.
--
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]
