Struct arrow2::array::BinaryArray

pub struct BinaryArray<O: Offset> { /* private fields */ }

A BinaryArray is Arrow’s semantically equivalent of an immutable Vec<Option<Vec<u8>>>. It implements Array.

The size of this struct is O(1), as all data is stored behind an std::sync::Arc.

Example

use arrow2::array::BinaryArray;
use arrow2::bitmap::Bitmap;
use arrow2::buffer::Buffer;

let array = BinaryArray::<i32>::from([Some([1, 2].as_ref()), None, Some([3].as_ref())]);
assert_eq!(array.value(0), &[1, 2]);
assert_eq!(array.iter().collect::<Vec<_>>(), vec![Some([1, 2].as_ref()), None, Some([3].as_ref())]);
assert_eq!(array.values_iter().collect::<Vec<_>>(), vec![[1, 2].as_ref(), &[], &[3]]);
// the underlying representation:
assert_eq!(array.values(), &Buffer::from(vec![1, 2, 3]));
assert_eq!(array.offsets().buffer(), &Buffer::from(vec![0, 2, 2, 3]));
assert_eq!(array.validity(), Some(&Bitmap::from([true, false, true])));

Generic parameter

The generic parameter Offset can only be i32 or i64 and tradeoffs maximum array length with memory usage:

• the sum of lengths of all elements cannot exceed Offset::MAX
• the total size of the underlying data is array.len() * size_of::<Offset>() + sum of lengths of all elements

Safety

The following invariants hold:

• Two consecutives offsets casted (as) to usize are valid slices of values.
• len is equal to validity.len(), when defined.

Implementations

impl<O: Offset> BinaryArray<O>

pub fn try_new(
    data_type: DataType,
    offsets: OffsetsBuffer<O>,
    values: Buffer<u8>,
    validity: Option<Bitmap>
) -> Result<Self, Error>

Returns a BinaryArray created from its internal representation.

Errors

This function returns an error iff:

• The last offset is not equal to the values’ length.
• the validity’s length is not equal to offsets.len().
• The data_type’s crate::datatypes::PhysicalType is not equal to either Binary or LargeBinary.

Implementation

This function is O(1)

pub fn from_slice<T: AsRef<[u8]>, P: AsRef<[T]>>(slice: P) -> Self

Creates a new BinaryArray from slices of &[u8].

pub fn from<T: AsRef<[u8]>, P: AsRef<[Option<T>]>>(slice: P) -> Self

Creates a new BinaryArray from a slice of optional &[u8].

pub fn iter(&self) -> ZipValidity<&[u8], BinaryValueIter<'_, O>, BitmapIter<'_>>

Returns an iterator of Option<&[u8]> over every element of this array.

pub fn values_iter(&self) -> BinaryValueIter<'_, O>

Returns an iterator of &[u8] over every element of this array, ignoring the validity

pub fn len(&self) -> usize

Returns the length of this array

pub fn value(&self, i: usize) -> &[u8]

Returns the element at index i

Panics

iff i >= self.len()

pub unsafe fn value_unchecked(&self, i: usize) -> &[u8]

Returns the element at index i

Safety

Assumes that the i < self.len.

pub fn data_type(&self) -> &DataType

Returns the DataType of this array.

pub fn values(&self) -> &Buffer<u8>

Returns the values of this BinaryArray.

pub fn offsets(&self) -> &OffsetsBuffer<O>

Returns the offsets of this BinaryArray.

pub fn validity(&self) -> Option<&Bitmap>

The optional validity.

pub fn slice(&self, offset: usize, length: usize) -> Self

Creates a new BinaryArray by slicing this BinaryArray.

Implementation

This function is O(1): all data will be shared between both arrays.

Panics

iff offset + length > self.len().

pub unsafe fn slice_unchecked(&self, offset: usize, length: usize) -> Self

Creates a new BinaryArray by slicing this BinaryArray.

Implementation

This function is O(1): all data will be shared between both arrays.

Safety

The caller must ensure that offset + length <= self.len().

pub fn boxed(self) -> Box<dyn Array>

Boxes self into a Box<dyn Array>.

pub fn arced(self) -> Arc<dyn Array>

Boxes self into a std::sync::Arc<dyn Array>.

pub fn with_validity(self, validity: Option<Bitmap>) -> Self

Returns this BinaryArray with a new validity.

Panic

Panics iff validity.len() != self.len().

pub fn set_validity(&mut self, validity: Option<Bitmap>)

Sets the validity of this BinaryArray.

Panics

This function panics iff values.len() != self.len().

pub fn into_mut(self) -> Either<Self, MutableBinaryArray<O>>

Try to convert this BinaryArray to a MutableBinaryArray

pub fn new_empty(data_type: DataType) -> Self

Creates an empty BinaryArray, i.e. whose .len is zero.

pub fn new_null(data_type: DataType, length: usize) -> Self

Creates an null BinaryArray, i.e. whose .null_count() == .len().

pub fn default_data_type() -> DataType

Returns the default DataType, DataType::Binary or DataType::LargeBinary

pub fn new(
    data_type: DataType,
    offsets: OffsetsBuffer<O>,
    values: Buffer<u8>,
    validity: Option<Bitmap>
) -> Self

Alias for unwrapping Self::try_new

pub fn from_trusted_len_values_iter<T: AsRef<[u8]>, I: TrustedLen<Item = T>>(
    iterator: I
) -> Self

Returns a BinaryArray from an iterator of trusted length.

The BinaryArray is guaranteed to not have a validity

pub fn from_iter_values<T: AsRef<[u8]>, I: Iterator<Item = T>>(
    iterator: I
) -> Self

Returns a new BinaryArray from a Iterator of &[u8].

The BinaryArray is guaranteed to not have a validity

pub unsafe fn from_trusted_len_iter_unchecked<I, P>(iterator: I) -> Selfwhere
    P: AsRef<[u8]>,
    I: Iterator<Item = Option<P>>,

Creates a BinaryArray from an iterator of trusted length.

Safety

The iterator must be TrustedLen. I.e. that size_hint().1 correctly reports its length.

pub fn from_trusted_len_iter<I, P>(iterator: I) -> Selfwhere
    P: AsRef<[u8]>,
    I: TrustedLen<Item = Option<P>>,

Creates a BinaryArray from a TrustedLen

pub unsafe fn try_from_trusted_len_iter_unchecked<E, I, P>(
    iterator: I
) -> Result<Self, E>where
    P: AsRef<[u8]>,
    I: IntoIterator<Item = Result<Option<P>, E>>,

Creates a BinaryArray from an falible iterator of trusted length.

Safety

The iterator must be TrustedLen. I.e. that size_hint().1 correctly reports its length.

pub fn try_from_trusted_len_iter<E, I, P>(iter: I) -> Result<Self, E>where
    P: AsRef<[u8]>,
    I: TrustedLen<Item = Result<Option<P>, E>>,

Creates a BinaryArray from an fallible iterator of trusted length.

Trait Implementations

impl<O: Offset> Array for BinaryArray<O>

fn as_any(&self) -> &dyn Any

Converts itself to a reference of Any, which enables downcasting to concrete types.

fn as_any_mut(&mut self) -> &mut dyn Any

Converts itself to a mutable reference of Any, which enables mutable downcasting to concrete types.

fn len(&self) -> usize

The length of the Array. Every array has a length corresponding to the number of elements (slots).

fn data_type(&self) -> &DataType

The DataType of the Array. In combination with Array::as_any, this can be used to downcast trait objects (dyn Array) to concrete arrays.

fn validity(&self) -> Option<&Bitmap>

The validity of the Array: every array has an optional Bitmap that, when available specifies whether the array slot is valid or not (null). When the validity is None, all slots are valid.

fn slice(&self, offset: usize, length: usize) -> Box<dyn Array>

Slices the Array, returning a new Box<dyn Array>.

unsafe fn slice_unchecked(&self, offset: usize, length: usize) -> Box<dyn Array>

Slices the Array, returning a new Box<dyn Array>.

fn with_validity(&self, validity: Option<Bitmap>) -> Box<dyn Array>

Clones this Array with a new new assigned bitmap.

fn to_boxed(&self) -> Box<dyn Array>

Clone a &dyn Array to an owned Box<dyn Array>.

fn is_empty(&self) -> bool

whether the array is empty

fn null_count(&self) -> usize

The number of null slots on this Array.

fn is_null(&self, i: usize) -> bool

Returns whether slot i is null.

fn is_valid(&self, i: usize) -> bool

Returns whether slot i is valid.

impl<O: Clone + Offset> Clone for BinaryArray<O>

fn clone(&self) -> BinaryArray<O>

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<O: Offset> Debug for BinaryArray<O>

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

Formats the value using the given formatter.

impl<'a, O: Offset> From<GrowableBinary<'a, O>> for BinaryArray<O>

fn from(val: GrowableBinary<'a, O>) -> Self

Converts to this type from the input type.

impl<O: Offset> From<MutableBinaryArray<O>> for BinaryArray<O>

fn from(other: MutableBinaryArray<O>) -> Self

Converts to this type from the input type.

impl<O: Offset> From<MutableBinaryValuesArray<O>> for BinaryArray<O>

fn from(other: MutableBinaryValuesArray<O>) -> Self

Converts to this type from the input type.

impl<O: Offset, P: AsRef<[u8]>> FromIterator<Option<P>> for BinaryArray<O>

fn from_iter<I: IntoIterator<Item = Option<P>>>(iter: I) -> Self

Creates a value from an iterator.

impl<O: Offset> GenericBinaryArray<O> for BinaryArray<O>

fn values(&self) -> &[u8]

The values of the array

fn offsets(&self) -> &[O]

The offsets of the array

impl<'a, O: Offset> IntoIterator for &'a BinaryArray<O>

type Item = Option<&'a [u8]>

The type of the elements being iterated over.

type IntoIter = ZipValidity<&'a [u8], ArrayValuesIter<'a, BinaryArray<O>>, BitmapIter<'a>>

Which kind of iterator are we turning this into?

fn into_iter(self) -> Self::IntoIter

Creates an iterator from a value.

impl<O: Offset> PartialEq<&(dyn Array + 'static)> for BinaryArray<O>

fn eq(&self, other: &&dyn Array) -> 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<O: Offset> PartialEq<BinaryArray<O>> for &dyn Array

fn eq(&self, other: &BinaryArray<O>) -> 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<O: Offset> PartialEq<BinaryArray<O>> for BinaryArray<O>

fn eq(&self, other: &Self) -> 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.