Enum deltalake::datafusion::parquet::file::statistics::Statistics

pub enum Statistics {
    Boolean(ValueStatistics<bool>),
    Int32(ValueStatistics<i32>),
    Int64(ValueStatistics<i64>),
    Int96(ValueStatistics<Int96>),
    Float(ValueStatistics<f32>),
    Double(ValueStatistics<f64>),
    ByteArray(ValueStatistics<ByteArray>),
    FixedLenByteArray(ValueStatistics<FixedLenByteArray>),
}

Statistics for a column chunk and data page.

Variants

Boolean(ValueStatistics<bool>)

Int32(ValueStatistics<i32>)

Int64(ValueStatistics<i64>)

Int96(ValueStatistics<Int96>)

Float(ValueStatistics<f32>)

Double(ValueStatistics<f64>)

ByteArray(ValueStatistics<ByteArray>)

FixedLenByteArray(ValueStatistics<FixedLenByteArray>)

Implementations

impl Statistics

pub fn new<T>( min: Option<T>, max: Option<T>, distinct_count: Option<u64>, null_count: u64, is_deprecated: bool ) -> Statistics

where T: ParquetValueType,

pub fn boolean( min: Option<bool>, max: Option<bool>, distinct: Option<u64>, nulls: u64, is_deprecated: bool ) -> Statistics

pub fn int32( min: Option<i32>, max: Option<i32>, distinct: Option<u64>, nulls: u64, is_deprecated: bool ) -> Statistics

pub fn int64( min: Option<i64>, max: Option<i64>, distinct: Option<u64>, nulls: u64, is_deprecated: bool ) -> Statistics

pub fn int96( min: Option<Int96>, max: Option<Int96>, distinct: Option<u64>, nulls: u64, is_deprecated: bool ) -> Statistics

pub fn float( min: Option<f32>, max: Option<f32>, distinct: Option<u64>, nulls: u64, is_deprecated: bool ) -> Statistics

pub fn double( min: Option<f64>, max: Option<f64>, distinct: Option<u64>, nulls: u64, is_deprecated: bool ) -> Statistics

pub fn byte_array( min: Option<ByteArray>, max: Option<ByteArray>, distinct: Option<u64>, nulls: u64, is_deprecated: bool ) -> Statistics

pub fn fixed_len_byte_array( min: Option<FixedLenByteArray>, max: Option<FixedLenByteArray>, distinct: Option<u64>, nulls: u64, is_deprecated: bool ) -> Statistics

pub fn is_min_max_deprecated(&self) -> bool

Returns true if statistics have old min and max fields set. This means that the column order is likely to be undefined, which, for old files could mean a signed sort order of values.

Refer to ColumnOrder and SortOrder for more information.

pub fn is_min_max_backwards_compatible(&self) -> bool

Old versions of parquet stored statistics in min and max fields, ordered using signed comparison. This resulted in an undefined ordering for unsigned quantities, such as booleans and unsigned integers.

These fields were therefore deprecated in favour of min_value and max_value, which have a type-defined sort order.

However, not all readers have been updated. For backwards compatibility, this method returns true if the statistics within this have a signed sort order, that is compatible with being stored in the deprecated min and max fields

pub fn distinct_count(&self) -> Option<u64>

Returns optional value of number of distinct values occurring. When it is None, the value should be ignored.

pub fn null_count(&self) -> u64

Returns number of null values for the column. Note that this includes all nulls when column is part of the complex type.

pub fn has_nulls(&self) -> bool

Returns true if statistics collected any null values, false otherwise.

pub fn has_min_max_set(&self) -> bool

Returns true if min value and max value are set. Normally both min/max values will be set to Some(value) or None.

pub fn min_is_exact(&self) -> bool

Returns true if the min value is set, and is an exact min value.

pub fn max_is_exact(&self) -> bool

Returns true if the max value is set, and is an exact max value.

pub fn min_bytes(&self) -> &[u8]

Returns slice of bytes that represent min value. Panics if min value is not set.

pub fn max_bytes(&self) -> &[u8]

Returns slice of bytes that represent max value. Panics if max value is not set.

pub fn physical_type(&self) -> Type

Returns physical type associated with statistics.

Trait Implementations

impl Clone for Statistics

fn clone(&self) -> Statistics

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Statistics

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

Formats the value using the given formatter.

impl Display for Statistics

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

Formats the value using the given formatter.

impl<T> From<ValueStatistics<T>> for Statistics

where T: ParquetValueType,

fn from(t: ValueStatistics<T>) -> Statistics

Converts to this type from the input type.

impl PartialEq for Statistics

fn eq(&self, other: &Statistics) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

This method tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for Statistics