wgtmac commented on code in PR #15240:
URL: https://github.com/apache/arrow/pull/15240#discussion_r1065956417
##########
cpp/src/parquet/arrow/writer.cc:
##########
@@ -355,6 +381,40 @@ class FileWriterImpl : public FileWriter {
return Status::OK();
}
+ Status NewBufferedRowGroup() override {
+ if (row_group_writer_ != nullptr) {
+ PARQUET_CATCH_NOT_OK(row_group_writer_->Close());
+ }
+ PARQUET_CATCH_NOT_OK(row_group_writer_ =
writer_->AppendBufferedRowGroup());
+ return Status::OK();
+ }
+
+ Status WriteRecordBatch(const RecordBatch& batch) override {
+ if (batch.num_rows() == 0) {
+ return Status::OK();
+ }
+
+ if (row_group_writer_ == nullptr || !row_group_writer_->buffered()) {
+ RETURN_NOT_OK(NewBufferedRowGroup());
+ }
+
+ auto WriteBatch = [&](int64_t offset, int64_t size) {
+ int column_index_start = 0;
+ for (int i = 0; i < batch.num_columns(); i++) {
+ ChunkedArray chunkedArray(batch.column(i));
+ ARROW_ASSIGN_OR_RAISE(
+ std::unique_ptr<ArrowColumnWriterV2> writer,
+ ArrowColumnWriterV2::Make(chunkedArray, offset, size,
schema_manifest_,
+ row_group_writer_, column_index_start));
+ RETURN_NOT_OK(writer->Write(&column_write_context_));
+ column_index_start += writer->leaf_count();
Review Comment:
Fixed
--
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]
