You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@arrow.apache.org by tu...@apache.org on 2022/11/09 17:54:23 UTC
[arrow-rs] branch master updated: Minor: Improve docstrings on WriterPropertiesBuilder (#3068)
This is an automated email from the ASF dual-hosted git repository.
tustvold pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow-rs.git
The following commit(s) were added to refs/heads/master by this push:
new e4e15f8e7 Minor: Improve docstrings on WriterPropertiesBuilder (#3068)
e4e15f8e7 is described below
commit e4e15f8e7efc31db6469198852c3e7719577411d
Author: Andrew Lamb <an...@nerdnetworks.org>
AuthorDate: Wed Nov 9 12:54:17 2022 -0500
Minor: Improve docstrings on WriterPropertiesBuilder (#3068)
---
parquet/src/file/properties.rs | 28 ++++++++++++++++++----------
1 file changed, 18 insertions(+), 10 deletions(-)
diff --git a/parquet/src/file/properties.rs b/parquet/src/file/properties.rs
index dc9feb4ce..cf821df21 100644
--- a/parquet/src/file/properties.rs
+++ b/parquet/src/file/properties.rs
@@ -306,38 +306,46 @@ impl WriterPropertiesBuilder {
self
}
- /// Sets best effort maximum size of a data page in bytes
+ /// Sets best effort maximum size of a data page in bytes.
///
- /// Note: this is a best effort limit based on the write batch size
+ /// Note: this is a best effort limit based on value of
+ /// [`set_write_batch_size`](Self::set_write_batch_size).
pub fn set_data_pagesize_limit(mut self, value: usize) -> Self {
self.data_pagesize_limit = value;
self
}
- /// Sets best effort maximum number of rows in a data page
+ /// Sets best effort maximum number of rows in a data page.
///
///
/// This can be used to limit the number of rows within a page to
- /// yield better page pruning
+ /// yield better page pruning.
///
- /// Note: this is a best effort limit based on the write batch size
+ /// Note: this is a best effort limit based on value of
+ /// [`set_write_batch_size`](Self::set_write_batch_size).
pub fn set_data_page_row_count_limit(mut self, value: usize) -> Self {
self.data_page_row_count_limit = value;
self
}
- /// Sets best effort maximum dictionary page size, in bytes
+ /// Sets best effort maximum dictionary page size, in bytes.
///
- /// Note: this is a best effort limit based on the write batch size
+ /// Note: this is a best effort limit based on value of
+ /// [`set_write_batch_size`](Self::set_write_batch_size).
pub fn set_dictionary_pagesize_limit(mut self, value: usize) -> Self {
self.dictionary_pagesize_limit = value;
self
}
- /// Sets write batch size
+ /// Sets write batch size.
+ ///
+ /// For performance reasons, data for each column is written in
+ /// batches of this size.
///
- /// Data is written in batches of this size, acting as an upper-bound on
- /// the enforcement granularity of page limits
+ /// Additional limits such as such as
+ /// [`set_data_page_row_count_limit`](Self::set_data_page_row_count_limit)
+ /// are checked between batches, and thus the write batch size value acts as an
+ /// upper-bound on the enforcement granularity of other limits.
pub fn set_write_batch_size(mut self, value: usize) -> Self {
self.write_batch_size = value;
self