github-actions[bot] commented on code in PR #18615:
URL: https://github.com/apache/doris/pull/18615#discussion_r1165222119
##########
be/src/vec/exec/format/orc/vorc_reader.cpp:
##########
@@ -847,32 +1013,254 @@ std::string OrcReader::_get_field_name_lower_case(const
orc::Type* orc_type, int
}
Status OrcReader::get_next_block(Block* block, size_t* read_rows, bool* eof) {
- SCOPED_RAW_TIMER(&_statistics.column_read_time);
- {
- SCOPED_RAW_TIMER(&_statistics.get_batch_time);
- // reset decimal_scale_params_index
- _decimal_scale_params_index = 0;
- if (!_row_reader->next(*_batch)) {
- *eof = true;
- *read_rows = 0;
- return Status::OK();
- }
- }
- const auto& batch_vec =
down_cast<orc::StructVectorBatch*>(_batch.get())->fields;
- for (auto& col : _read_cols_lower_case) {
- auto& column_with_type_and_name = block->get_by_name(col);
+ if (_lazy_read_ctx.can_lazy_read) {
+ std::vector<uint32_t> columns_to_filter;
+ int column_to_keep = block->columns();
+ columns_to_filter.resize(column_to_keep);
+ for (uint32_t i = 0; i < column_to_keep; ++i) {
+ columns_to_filter[i] = i;
+ }
+ uint64_t rr;
+ SCOPED_RAW_TIMER(&_statistics.column_read_time);
+ {
+ SCOPED_RAW_TIMER(&_statistics.get_batch_time);
+ // reset decimal_scale_params_index;
+ _decimal_scale_params_index = 0;
+ rr = _row_reader->nextBatch(*_batch, block);
+ if (rr == 0) {
+ *eof = true;
+ *read_rows = 0;
+ return Status::OK();
+ }
+ }
+ const auto& batch_vec =
down_cast<orc::StructVectorBatch*>(_batch.get())->fields;
+ for (auto& lazy_read_column_name : _lazy_read_ctx.lazy_read_columns) {
+ auto& col_name = _file_col_name_to_col_name[lazy_read_column_name];
+ auto& column_with_type_and_name = block->get_by_name(col_name);
+ auto& column_ptr = column_with_type_and_name.column;
+ auto& column_type = column_with_type_and_name.type;
+ auto orc_col_idx = _colname_to_idx.find(col_name);
+ if (orc_col_idx == _colname_to_idx.end()) {
+ return Status::InternalError("Wrong read column '{}' in orc
file",
+ lazy_read_column_name);
+ }
+ RETURN_IF_ERROR(_orc_column_to_doris_column(
+ col_name, column_ptr, column_type,
_col_orc_type[orc_col_idx->second],
+ batch_vec[orc_col_idx->second], _batch->numElements));
+ }
+ *read_rows = rr;
+
+ RETURN_IF_ERROR(_filter_block_internal(block, columns_to_filter,
*_filter));
+ Block::erase_useless_column(block, column_to_keep);
+ } else {
+ uint64_t rr;
+ SCOPED_RAW_TIMER(&_statistics.column_read_time);
+ {
+ SCOPED_RAW_TIMER(&_statistics.get_batch_time);
+ // reset decimal_scale_params_index;
+ _decimal_scale_params_index = 0;
+ rr = _row_reader->nextBatch(*_batch, block);
Review Comment:
warning: no member named 'nextBatch' in 'orc::RowReader'
[clang-diagnostic-error]
```cpp
rr = _row_reader->nextBatch(*_batch, block);
^
```
--
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]
