Struct parquet::file::properties::WriterProperties

source ·
pub struct WriterProperties { /* private fields */ }
Expand description

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§

source§

impl WriterProperties

source

pub fn new() -> Self

Create a new WriterProperties with the default settings

See WriterProperties::builder for customising settings

source

pub fn builder() -> WriterPropertiesBuilder

Returns builder for writer properties with default values.

source

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

source

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

source

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

source

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

source

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

source

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.

source

pub fn max_row_group_size(&self) -> usize

Returns maximum number of rows in a row group.

source

pub fn writer_version(&self) -> WriterVersion

Returns configured writer version.

source

pub fn created_by(&self) -> &str

Returns created_by string.

source

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

Returns key_value_metadata KeyValue pairs.

source

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

Returns sorting columns.

source

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.

source

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.

source

pub fn dictionary_data_page_encoding(&self) -> Encoding

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

source

pub fn dictionary_page_encoding(&self) -> Encoding

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

source

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.

source

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

Returns compression codec for a column.

source

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

Returns true if dictionary encoding is enabled for a column.

source

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

Returns true if statistics are enabled for a column.

source

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

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

source

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§

source§

impl Clone for WriterProperties

source§

fn clone(&self) -> WriterProperties

Returns a copy of the value. Read more
1.0.0 · source§

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

Performs copy-assignment from source. Read more
source§

impl Debug for WriterProperties

source§

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

Formats the value using the given formatter. Read more
source§

impl Default for WriterProperties

source§

fn default() -> Self

Returns the “default value” for a type. Read more

Auto Trait Implementations§

Blanket Implementations§

source§

impl<T> Any for T
where T: 'static + ?Sized,

source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
source§

impl<T> Borrow<T> for T
where T: ?Sized,

source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
source§

impl<T> CloneToUninit for T
where T: Clone,

source§

default unsafe fn clone_to_uninit(&self, dst: *mut T)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dst. Read more
source§

impl<T> From<T> for T

source§

fn from(t: T) -> T

Returns the argument unchanged.

source§

impl<T, U> Into<U> for T
where U: From<T>,

source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

source§

impl<T> ToOwned for T
where T: Clone,

§

type Owned = T

The resulting type after obtaining ownership.
source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
source§

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more
source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

§

type Error = Infallible

The type returned in the event of a conversion error.
source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
source§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

source§

fn vzip(self) -> V

source§

impl<T> Allocation for T
where T: RefUnwindSafe + Send + Sync,