Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Deprecate "max statistics size" property in WriterProperties #6884

Merged
merged 1 commit into from
Dec 17, 2024
Merged

Deprecate "max statistics size" property in WriterProperties #6884

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions parquet/src/bin/parquet-rewrite.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,6 +242,7 @@ fn main() {
if let Some(value) = args.dictionary_page_size_limit {
writer_properties_builder = writer_properties_builder.set_dictionary_page_size_limit(value);
}
#[allow(deprecated)]
if let Some(value) = args.max_statistics_size {
writer_properties_builder = writer_properties_builder.set_max_statistics_size(value);
}
Expand Down
20 changes: 12 additions & 8 deletions parquet/src/file/properties.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ pub const DEFAULT_DATA_PAGE_ROW_COUNT_LIMIT: usize = 20_000;
/// Default value for [`WriterProperties::statistics_enabled`]
pub const DEFAULT_STATISTICS_ENABLED: EnabledStatistics = EnabledStatistics::Page;
/// Default value for [`WriterProperties::max_statistics_size`]
#[deprecated(since = "54.0.0", note = "Unused; will be removed in 56.0.0")]
pub const DEFAULT_MAX_STATISTICS_SIZE: usize = 4096;
/// Default value for [`WriterProperties::max_row_group_size`]
pub const DEFAULT_MAX_ROW_GROUP_SIZE: usize = 1024 * 1024;
Expand Down Expand Up @@ -351,7 +352,9 @@ impl WriterProperties {

/// Returns max size for statistics.
/// Only applicable if statistics are enabled.
#[deprecated(since = "54.0.0", note = "Unused; will be removed in 56.0.0")]
pub fn max_statistics_size(&self, col: &ColumnPath) -> usize {
#[allow(deprecated)]
self.column_properties
.get(col)
.and_then(|c| c.max_statistics_size())
Expand Down Expand Up @@ -602,7 +605,9 @@ impl WriterPropertiesBuilder {
/// Sets default max statistics size for all columns (defaults to `4096`).
///
/// Applicable only if statistics are enabled.
#[deprecated(since = "54.0.0", note = "Unused; will be removed in 56.0.0")]
pub fn set_max_statistics_size(mut self, value: usize) -> Self {
#[allow(deprecated)]
self.default_column_properties
.set_max_statistics_size(value);
self
Expand Down Expand Up @@ -707,7 +712,9 @@ impl WriterPropertiesBuilder {
/// Sets max size for statistics for a specific column.
///
/// Takes precedence over [`Self::set_max_statistics_size`].
#[deprecated(since = "54.0.0", note = "Unused; will be removed in 56.0.0")]
pub fn set_column_max_statistics_size(mut self, col: ColumnPath, value: usize) -> Self {
#[allow(deprecated)]
self.get_mut_props(col).set_max_statistics_size(value);
self
}
Expand Down Expand Up @@ -895,6 +902,7 @@ struct ColumnProperties {
codec: Option<Compression>,
dictionary_enabled: Option<bool>,
statistics_enabled: Option<EnabledStatistics>,
#[deprecated(since = "54.0.0", note = "Unused; will be removed in 56.0.0")]
max_statistics_size: Option<usize>,
/// bloom filter related properties
bloom_filter_properties: Option<BloomFilterProperties>,
Expand Down Expand Up @@ -933,6 +941,8 @@ impl ColumnProperties {
}

/// Sets max size for statistics for this column.
#[deprecated(since = "54.0.0", note = "Unused; will be removed in 56.0.0")]
#[allow(deprecated)]
fn set_max_statistics_size(&mut self, value: usize) {
self.max_statistics_size = Some(value);
}
Expand Down Expand Up @@ -997,7 +1007,9 @@ impl ColumnProperties {
}

/// Returns optional max size in bytes for statistics.
#[deprecated(since = "54.0.0", note = "Unused; will be removed in 56.0.0")]
fn max_statistics_size(&self) -> Option<usize> {
#[allow(deprecated)]
self.max_statistics_size
}

Expand Down Expand Up @@ -1141,10 +1153,6 @@ mod tests {
props.statistics_enabled(&ColumnPath::from("col")),
DEFAULT_STATISTICS_ENABLED
);
assert_eq!(
props.max_statistics_size(&ColumnPath::from("col")),
DEFAULT_MAX_STATISTICS_SIZE
);
assert!(props
.bloom_filter_properties(&ColumnPath::from("col"))
.is_none());
Expand Down Expand Up @@ -1221,13 +1229,11 @@ mod tests {
.set_compression(Compression::GZIP(Default::default()))
.set_dictionary_enabled(false)
.set_statistics_enabled(EnabledStatistics::None)
.set_max_statistics_size(50)
// specific column settings
.set_column_encoding(ColumnPath::from("col"), Encoding::RLE)
.set_column_compression(ColumnPath::from("col"), Compression::SNAPPY)
.set_column_dictionary_enabled(ColumnPath::from("col"), true)
.set_column_statistics_enabled(ColumnPath::from("col"), EnabledStatistics::Chunk)
.set_column_max_statistics_size(ColumnPath::from("col"), 123)
.set_column_bloom_filter_enabled(ColumnPath::from("col"), true)
.set_column_bloom_filter_ndv(ColumnPath::from("col"), 100_u64)
.set_column_bloom_filter_fpp(ColumnPath::from("col"), 0.1)
Expand Down Expand Up @@ -1259,7 +1265,6 @@ mod tests {
props.statistics_enabled(&ColumnPath::from("a")),
EnabledStatistics::None
);
assert_eq!(props.max_statistics_size(&ColumnPath::from("a")), 50);

assert_eq!(
props.encoding(&ColumnPath::from("col")),
Expand All @@ -1274,7 +1279,6 @@ mod tests {
props.statistics_enabled(&ColumnPath::from("col")),
EnabledStatistics::Chunk
);
assert_eq!(props.max_statistics_size(&ColumnPath::from("col")), 123);
assert_eq!(
props.bloom_filter_properties(&ColumnPath::from("col")),
Some(&BloomFilterProperties { fpp: 0.1, ndv: 100 })
Expand Down
Loading