Skip to content

Commit 52cbbee

Browse files
kszucsetseidl
andauthored
chore(parquet): apply suggestions from code review
Co-authored-by: Ed Seidl <etseidl@users.noreply.github.com>
1 parent eb271c2 commit 52cbbee

File tree

2 files changed

+7
-9
lines changed

2 files changed

+7
-9
lines changed

parquet/src/arrow/arrow_writer/mod.rs

Lines changed: 4 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -266,18 +266,14 @@ impl<W: Write + Send> ArrowWriter<W> {
266266
let row_group_writer_factory =
267267
ArrowRowGroupWriterFactory::new(&file_writer, arrow_schema.clone());
268268

269-
let cdc_chunkers = match props_ptr.content_defined_chunking() {
270-
Some(opts) => {
271-
let chunkers = file_writer
269+
let cdc_chunkers = props_ptr.content_defined_chunking().map(|opts| {
270+
file_writer
272271
.schema_descr()
273272
.columns()
274273
.iter()
275274
.map(|desc| ContentDefinedChunker::new(desc, opts))
276-
.collect::<Result<Vec<_>>>()?;
277-
Some(chunkers)
278-
}
279-
None => None,
280-
};
275+
.collect::<Result<Vec<_>>>()
276+
}).transpose()?;
281277

282278
Ok(Self {
283279
writer: file_writer,

parquet/src/file/properties.rs

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -83,10 +83,12 @@ pub struct CdcOptions {
8383
pub min_chunk_size: usize,
8484
/// Maximum chunk size in bytes, default is 1024 KiB.
8585
/// The chunker will create a new chunk whenever the chunk size exceeds this value.
86-
/// Note that the parquet writer has a related `data_page_size_limit` property that
86+
/// Note that the parquet writer has a related [`data_page_size_limit`] property that
8787
/// controls the maximum size of a parquet data page after encoding. While setting
8888
/// `data_page_size_limit` to a smaller value than `max_chunk_size` doesn't affect
8989
/// the chunking effectiveness, it results in more small parquet data pages.
90+
///
91+
/// [`data_page_size_limit`]: WriterPropertiesBuilder::set_data_page_size_limit
9092
pub max_chunk_size: usize,
9193
/// Number of bit adjustment to the gearhash mask in order to center the chunk size
9294
/// around the average size more aggressively, default is 0.

0 commit comments

Comments
 (0)