Gabriel39 commented on code in PR #69723:
URL: https://github.com/apache/doris/pull/69723#discussion_r4420491643
##########
be/src/exec/operator/file_scan_operator.cpp:
##########
@@ -245,41 +138,12 @@ Status
FileScanLocalState::_init_scanners(std::list<ScannerSPtr>* scanners) {
scan_params = _split_source->get_params();
}
RETURN_IF_ERROR(validate_file_scan_support(*scan_params));
- const bool is_load =
-
state()->desc_tbl().get_tuple_descriptor(scan_params->src_tuple_id) != nullptr;
- // TODO: Use scanner v2 for all queries.
- const bool use_file_scanner_v2 =
- should_use_file_scanner_v2(state()->query_options(), is_load,
*scan_params);
- _operator_profile->add_info_string("UseScannerV2", use_file_scanner_v2 ?
"true" : "false");
- const auto* output_tuple_desc =
state()->desc_tbl().get_tuple_descriptor(_output_tuple_id);
- DORIS_CHECK(output_tuple_desc != nullptr);
- const bool metadata_only_count =
- is_count_star_pushdown() &&
_split_source->all_ranges_have_table_level_row_count();
- if (!is_load && !use_file_scanner_v2 && !metadata_only_count &&
- std::ranges::any_of(output_tuple_desc->slots(), [](const
SlotDescriptor* slot) {
- return contains_variant_type(slot->type());
- })) {
- // A syntactic COUNT(*) alone is insufficient: every assigned range
must prove that the
- // legacy scanner will emit metadata counts without decoding a Variant
carrier.
- return Status::NotSupported(
- "External VARIANT columns require FileScannerV2; the legacy
file scanner does "
- "not support VARIANT");
- }
- if (use_file_scanner_v2) {
- _parquet_profile_cache =
-
std::make_unique<format::parquet::ParquetProfileCache>(_scanner_profile.get());
- }
+ _parquet_profile_cache =
+
std::make_unique<format::parquet::ParquetProfileCache>(_scanner_profile.get());
for (int i = 0; i < _max_scanners; ++i) {
- ScannerSPtr scanner;
- if (use_file_scanner_v2) {
- scanner = FileScannerV2::create_shared(state(), this, p._limit,
_split_source,
- _scanner_profile.get(),
p._kv_cache.get(),
- &p._colname_to_slot_id);
- } else {
- scanner = FileScanner::create_shared(state(), this, p._limit,
_split_source,
- _scanner_profile.get(),
p._kv_cache.get(),
- &p._colname_to_slot_id);
- }
+ ScannerSPtr scanner = FileScannerV2::create_shared(
+ state(), this, p._limit, _split_source,
_scanner_profile.get(), p._kv_cache.get(),
Review Comment:
Fixed in a3f0ca0afd0. V2 now appends the selected file path at its open,
read, residual-filter and row-ID boundaries, covering split preparation and
runtime-filter refresh failures as well. The range name comes directly from the
selected range, so failures before prepare_split cannot retain the preceding
file. Original status codes and the ORC nextBatch prefix are preserved. Five
new regressions cover these paths; four reproduced the missing path before the
fix. All 216 selected BE ASAN tests pass, including all 187 ORC tests.
clang-format 16, build hygiene and changed-line clang-tidy also pass.
--
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]
