wjones127 commented on code in PR #14018:
URL: https://github.com/apache/arrow/pull/14018#discussion_r1002196934
##########
cpp/src/parquet/arrow/writer.h:
##########
@@ -54,36 +57,69 @@ class PARQUET_EXPORT FileWriter {
std::shared_ptr<ArrowWriterProperties>
arrow_properties,
std::unique_ptr<FileWriter>* out);
+ /// \brief Try to create an Arrow to Parquet file writer.
+ ///
+ /// \param schema schema of data that will be passed.
+ /// \param pool memory pool to use.
+ /// \param sink output stream to write Parquet data.
+ /// \param properties general Parquet writer properties.
+ /// \param arrow_properties Arrow-specific writer properties.
+ ///
+ /// \since 11.0.0
+ static ::arrow::Result<std::unique_ptr<FileWriter>> Open(
+ const ::arrow::Schema& schema, MemoryPool* pool,
+ std::shared_ptr<::arrow::io::OutputStream> sink,
+ std::shared_ptr<WriterProperties> properties =
default_writer_properties(),
+ std::shared_ptr<ArrowWriterProperties> arrow_properties =
+ default_arrow_writer_properties());
+
+ ARROW_DEPRECATED("Deprecated in 11.0.0. Use result variants instead.")
static ::arrow::Status Open(const ::arrow::Schema& schema, MemoryPool* pool,
std::shared_ptr<::arrow::io::OutputStream> sink,
std::shared_ptr<WriterProperties> properties,
std::unique_ptr<FileWriter>* writer);
-
+ ARROW_DEPRECATED("Deprecated in 11.0.0. Use result variants instead.")
static ::arrow::Status Open(const ::arrow::Schema& schema, MemoryPool* pool,
std::shared_ptr<::arrow::io::OutputStream> sink,
std::shared_ptr<WriterProperties> properties,
std::shared_ptr<ArrowWriterProperties>
arrow_properties,
std::unique_ptr<FileWriter>* writer);
+ /// Return the Arrow schema to be written to.
virtual std::shared_ptr<::arrow::Schema> schema() const = 0;
/// \brief Write a Table to Parquet.
- virtual ::arrow::Status WriteTable(const ::arrow::Table& table, int64_t
chunk_size) = 0;
-
+ ///
+ /// \param table Arrow table to write.
+ /// \param chunk_size maximum size of row groups to write.
+ virtual ::arrow::Status WriteTable(
+ const ::arrow::Table& table, int64_t chunk_size =
DEFAULT_MAX_ROW_GROUP_LENGTH) = 0;
Review Comment:
I provided a reasonable default, which aligns with the file-level default
max.
--
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]
