[GitHub] [doris] morningman commented on a diff in pull request #11292: [feature-wip][multi-catalog]Support prefetch for orc file format

[GitBox]

morningman commented on code in PR #11292:
URL: https://github.com/apache/doris/pull/11292#discussion_r933095117


##########
be/src/exec/arrow/parquet_reader.h:
##########
@@ -86,8 +85,9 @@ class ParquetReaderWrap final : public ArrowReaderWrap {
                             int32_t* wbtyes);
 
 private:
-    void prefetch_batch();
     Status read_next_batch();
+    void readBatches(arrow::RecordBatchVector& batches, int current_group) 
override;

Review Comment:
   ```suggestion
       void read_batches(arrow::RecordBatchVector& batches, int current_group) 
override;
   ```



##########
be/src/exec/arrow/orc_reader.h:
##########
@@ -40,11 +40,12 @@ class ORCReaderWrap final : public ArrowReaderWrap {
                        const std::vector<SlotDescriptor*>& tuple_slot_descs,
                        const std::vector<ExprContext*>& conjunct_ctxs,
                        const std::string& timezone) override;
-    Status next_batch(std::shared_ptr<arrow::RecordBatch>* batch, bool* eof) 
override;
 
 private:
     Status _next_stripe_reader(bool* eof);
     Status _seek_start_stripe();
+    void readBatches(arrow::RecordBatchVector& batches, int current_group) 
override;

Review Comment:
   ```suggestion
       void read_batches(arrow::RecordBatchVector& batches, int current_group) 
override;
   ```



##########
be/src/exec/arrow/parquet_reader.h:
##########
@@ -86,8 +85,9 @@ class ParquetReaderWrap final : public ArrowReaderWrap {
                             int32_t* wbtyes);
 
 private:
-    void prefetch_batch();
     Status read_next_batch();
+    void readBatches(arrow::RecordBatchVector& batches, int current_group) 
override;
+    bool filterRowGroup(int current_group) override;

Review Comment:
   ```suggestion
       bool filter_row_group(int current_group) override;
   ```



##########
be/src/exec/arrow/orc_reader.h:
##########
@@ -40,11 +40,12 @@ class ORCReaderWrap final : public ArrowReaderWrap {
                        const std::vector<SlotDescriptor*>& tuple_slot_descs,
                        const std::vector<ExprContext*>& conjunct_ctxs,
                        const std::string& timezone) override;
-    Status next_batch(std::shared_ptr<arrow::RecordBatch>* batch, bool* eof) 
override;
 
 private:
     Status _next_stripe_reader(bool* eof);
     Status _seek_start_stripe();
+    void readBatches(arrow::RecordBatchVector& batches, int current_group) 
override;
+    bool filterRowGroup(int current_group) override;

Review Comment:
   ```suggestion
       bool filter_row_group(int current_group) override;
   ```



-- 
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: commits-unsubscr...@doris.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org