alamb commented on code in PR #11444:
URL: https://github.com/apache/datafusion/pull/11444#discussion_r1681367271
##########
datafusion/common/src/file_options/parquet_writer.rs:
##########
@@ -52,92 +53,43 @@ impl ParquetWriterOptions {
impl TryFrom<&TableParquetOptions> for ParquetWriterOptions {
type Error = DataFusionError;
- fn try_from(parquet_options: &TableParquetOptions) -> Result<Self> {
- let ParquetOptions {
- data_pagesize_limit,
- write_batch_size,
- writer_version,
- dictionary_page_size_limit,
- max_row_group_size,
- created_by,
- column_index_truncate_length,
- data_page_row_count_limit,
- bloom_filter_on_write,
- encoding,
- dictionary_enabled,
- compression,
- statistics_enabled,
- max_statistics_size,
- bloom_filter_fpp,
- bloom_filter_ndv,
- // below is not part of ParquetWriterOptions
- enable_page_index: _,
- pruning: _,
- skip_metadata: _,
- metadata_size_hint: _,
- pushdown_filters: _,
- reorder_filters: _,
- allow_single_file_parallelism: _,
- maximum_parallel_row_group_writers: _,
- maximum_buffered_record_batches_per_stream: _,
- bloom_filter_on_read: _,
- } = &parquet_options.global;
-
- let key_value_metadata = if
!parquet_options.key_value_metadata.is_empty() {
- Some(
- parquet_options
- .key_value_metadata
- .clone()
- .drain()
- .map(|(key, value)| KeyValue { key, value })
- .collect::<Vec<_>>(),
- )
- } else {
- None
- };
-
- let mut builder = WriterProperties::builder()
- .set_data_page_size_limit(*data_pagesize_limit)
- .set_write_batch_size(*write_batch_size)
- .set_writer_version(parse_version_string(writer_version.as_str())?)
- .set_dictionary_page_size_limit(*dictionary_page_size_limit)
- .set_max_row_group_size(*max_row_group_size)
- .set_created_by(created_by.clone())
- .set_column_index_truncate_length(*column_index_truncate_length)
- .set_data_page_row_count_limit(*data_page_row_count_limit)
- .set_bloom_filter_enabled(*bloom_filter_on_write)
- .set_key_value_metadata(key_value_metadata);
-
- if let Some(encoding) = &encoding {
- builder = builder.set_encoding(parse_encoding_string(encoding)?);
- }
-
- if let Some(enabled) = dictionary_enabled {
- builder = builder.set_dictionary_enabled(*enabled);
- }
-
- if let Some(compression) = &compression {
- builder =
builder.set_compression(parse_compression_string(compression)?);
- }
-
- if let Some(statistics) = &statistics_enabled {
- builder =
-
builder.set_statistics_enabled(parse_statistics_string(statistics)?);
- }
-
- if let Some(size) = max_statistics_size {
- builder = builder.set_max_statistics_size(*size);
- }
+ fn try_from(parquet_table_options: &TableParquetOptions) -> Result<Self> {
+ // ParquetWriterOptions will have defaults for the remaining fields
(e.g. sorting_columns)
+ Ok(ParquetWriterOptions {
+ writer_options:
WriterPropertiesBuilder::try_from(parquet_table_options)?
+ .build(),
+ })
+ }
+}
- if let Some(fpp) = bloom_filter_fpp {
- builder = builder.set_bloom_filter_fpp(*fpp);
- }
+impl TryFrom<&TableParquetOptions> for WriterPropertiesBuilder {
Review Comment:
Update here is @wiedld mentioned to me that the `TableParquetOptions` are
kept and a new `WrtierProperties` are created for each query so there isn't
anything to be gained with this proposed change
--
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]
