pitrou commented on code in PR #36377:
URL: https://github.com/apache/arrow/pull/36377#discussion_r1268134956
##########
cpp/src/parquet/arrow/writer.cc:
##########
@@ -469,6 +415,30 @@ class FileWriterImpl : public FileWriter {
return writer_->metadata();
}
+ Status WriteTableUnbuffered(const Table& table, int64_t chunk_size) {
+ auto WriteRowGroup = [&](int64_t offset, int64_t size) {
+ RETURN_NOT_OK(NewRowGroup(size));
+ for (int i = 0; i < table.num_columns(); i++) {
+ RETURN_NOT_OK(WriteColumnChunk(table.column(i), offset, size));
+ }
+ return Status::OK();
+ };
+
+ if (table.num_rows() == 0) {
+ // Append a row group with 0 rows
+ RETURN_NOT_OK_ELSE(WriteRowGroup(0, 0), PARQUET_IGNORE_NOT_OK(Close()));
+ return Status::OK();
+ }
+
+ for (int chunk = 0; chunk * chunk_size < table.num_rows(); chunk++) {
+ int64_t offset = chunk * chunk_size;
+ RETURN_NOT_OK_ELSE(
+ WriteRowGroup(offset, std::min(chunk_size, table.num_rows() -
offset)),
+ PARQUET_IGNORE_NOT_OK(Close()));
Review Comment:
I see, thank you for the explanation. This macro is a bit confusing.
--
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]
