github-actions[bot] commented on code in PR #33935:
URL: https://github.com/apache/doris/pull/33935#discussion_r1577887573
##########
be/src/vec/exec/format/table/iceberg_reader.h:
##########
@@ -134,28 +136,108 @@ class IcebergTableReader : public TableFormatReader {
// owned by scan node
ShardedKVCache* _kv_cache;
IcebergProfile _iceberg_profile;
- std::vector<int64_t> _delete_rows;
+ std::vector<int64_t> _iceberg_delete_rows;
// col names from _file_slot_descs
std::vector<std::string> _file_col_names;
// file column name to table column name map. For iceberg schema evolution.
std::unordered_map<std::string, std::string> _file_col_to_table_col;
// table column name to file column name map. For iceberg schema evolution.
std::unordered_map<std::string, std::string> _table_col_to_file_col;
std::unordered_map<std::string, ColumnValueRangeType>*
_colname_to_value_range;
- // copy from _colname_to_value_range with new column name that is in
parquet file, to support schema evolution.
+ // copy from _colname_to_value_range with new column name that is in
parquet/orc file, to support schema evolution.
std::unordered_map<std::string, ColumnValueRangeType>
_new_colname_to_value_range;
// column id to name map. Collect from FE slot descriptor.
std::unordered_map<int, std::string> _col_id_name_map;
- // col names in the parquet file
+ // col names in the parquet,orc file
std::vector<std::string> _all_required_col_names;
- // col names in table but not in parquet file
+ // col names in table but not in parquet,orc file
std::vector<std::string> _not_in_file_col_names;
io::IOContext* _io_ctx;
bool _has_schema_change = false;
bool _has_iceberg_schema = false;
int64_t _remaining_push_down_count;
+ Fileformat _file_format = Fileformat::NONE;
+
+ const int64_t MIN_SUPPORT_DELETE_FILES_VERSION = 2;
+ const std::string ICEBERG_ROW_POS = "pos";
+ const std::string ICEBERG_FILE_PATH = "file_path";
+ const std::vector<std::string> delete_file_col_names {ICEBERG_ROW_POS,
ICEBERG_FILE_PATH};
+ const std::vector<TypeDescriptor> delete_file_col_types {{TYPE_STRING},
{TYPE_BIGINT}};
+ const int ICEBERG_FILE_PATH_INDEX = 0;
+ const int ICEBERG_FILE_POS_INDEX = 1;
+ const int READ_DELETE_FILE_BATCH_SIZE = 102400;
+
+ //Read position_delete_file TFileRangeDesc, generate DeleteFile
+ virtual Status _read_position_delete_file(const TFileRangeDesc*,
DeleteFile*) = 0;
+
+ void _gen_position_delete_file_range(Block& block, DeleteFile* const
position_delete,
Review Comment:
warning: parameter 'position_delete' is const-qualified in the function
declaration; const-qualification of parameters only has an effect in function
definitions [readability-avoid-const-params-in-decls]
```suggestion
void _gen_position_delete_file_range(Block& block, DeleteFile*
position_delete,
```
--
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]
