Struct deltalake::datafusion::parquet::file::properties::WriterProperties

pub struct WriterProperties { /* private fields */ }

Configuration settings for writing parquet files.

All properties except the key-value metadata are immutable, use WriterPropertiesBuilder to assemble these properties.

Example

use parquet::{
    basic::{Compression, Encoding},
    file::properties::*,
    schema::types::ColumnPath,
};

// Create properties with default configuration.
let props = WriterProperties::default();

// Use properties builder to set certain options and assemble the configuration.
let props = WriterProperties::builder()
    .set_writer_version(WriterVersion::PARQUET_1_0)
    .set_encoding(Encoding::PLAIN)
    .set_column_encoding(ColumnPath::from("col1"), Encoding::DELTA_BINARY_PACKED)
    .set_compression(Compression::SNAPPY)
    .build();

assert_eq!(props.writer_version(), WriterVersion::PARQUET_1_0);
assert_eq!(
    props.encoding(&ColumnPath::from("col1")),
    Some(Encoding::DELTA_BINARY_PACKED)
);
assert_eq!(
    props.encoding(&ColumnPath::from("col2")),
    Some(Encoding::PLAIN)
);

Implementations

impl WriterProperties

pub fn new() -> WriterProperties

Create a new WriterProperties with the default settings

See WriterProperties::builder for customising settings

pub fn builder() -> WriterPropertiesBuilder

Returns builder for writer properties with default values.

pub fn data_pagesize_limit(&self) -> usize

👎Deprecated since 41.0.0: Use data_page_size_limit

Returns data page size limit.

Note: this is a best effort limit based on the write batch size

pub fn data_page_size_limit(&self) -> usize

Returns data page size limit.

Note: this is a best effort limit based on the write batch size

For more details see WriterPropertiesBuilder::set_data_page_size_limit

pub fn dictionary_pagesize_limit(&self) -> usize

👎Deprecated since 41.0.0: Use dictionary_page_size_limit

Returns dictionary page size limit.

Note: this is a best effort limit based on the write batch size

pub fn dictionary_page_size_limit(&self) -> usize

Returns dictionary page size limit.

Note: this is a best effort limit based on the write batch size

For more details see WriterPropertiesBuilder::set_dictionary_page_size_limit

pub fn data_page_row_count_limit(&self) -> usize

Returns the maximum page row count

Note: this is a best effort limit based on the write batch size

For more details see WriterPropertiesBuilder::set_data_page_row_count_limit

pub fn write_batch_size(&self) -> usize

Returns configured batch size for writes.

When writing a batch of data, this setting allows to split it internally into smaller batches so we can better estimate the size of a page currently being written.

pub fn max_row_group_size(&self) -> usize

Returns maximum number of rows in a row group.

pub fn writer_version(&self) -> WriterVersion

Returns configured writer version.

pub fn created_by(&self) -> &str

Returns created_by string.

pub fn key_value_metadata(&self) -> Option<&Vec<KeyValue>>

Returns key_value_metadata KeyValue pairs.

pub fn sorting_columns(&self) -> Option<&Vec<SortingColumn>>

Returns sorting columns.

pub fn column_index_truncate_length(&self) -> Option<usize>

Returns the maximum length of truncated min/max values in the column index.

None if truncation is disabled, must be greater than 0 otherwise.

pub fn statistics_truncate_length(&self) -> Option<usize>

Returns the maximum length of truncated min/max values in statistics.

None if truncation is disabled, must be greater than 0 otherwise.

pub fn dictionary_data_page_encoding(&self) -> Encoding

Returns encoding for a data page, when dictionary encoding is enabled. This is not configurable.

pub fn dictionary_page_encoding(&self) -> Encoding

Returns encoding for dictionary page, when dictionary encoding is enabled. This is not configurable.

pub fn encoding(&self, col: &ColumnPath) -> Option<Encoding>

Returns encoding for a column, if set. In case when dictionary is enabled, returns fallback encoding.

If encoding is not set, then column writer will choose the best encoding based on the column type.

pub fn compression(&self, col: &ColumnPath) -> Compression

Returns compression codec for a column.

pub fn dictionary_enabled(&self, col: &ColumnPath) -> bool

Returns true if dictionary encoding is enabled for a column.

pub fn statistics_enabled(&self, col: &ColumnPath) -> EnabledStatistics

Returns true if statistics are enabled for a column.

pub fn max_statistics_size(&self, col: &ColumnPath) -> usize

Returns max size for statistics. Only applicable if statistics are enabled.

pub fn bloom_filter_properties( &self, col: &ColumnPath ) -> Option<&BloomFilterProperties>

Returns the BloomFilterProperties for the given column

Returns None if bloom filter is disabled

Trait Implementations

impl Clone for WriterProperties

fn clone(&self) -> WriterProperties

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for WriterProperties

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Default for WriterProperties

fn default() -> WriterProperties

Returns the “default value” for a type.