arrow_array::array

Struct GenericByteArray

Source
pub struct GenericByteArray<T: ByteArrayType> {
    data_type: DataType,
    value_offsets: OffsetBuffer<T::Offset>,
    value_data: Buffer,
    nulls: Option<NullBuffer>,
}
Expand description

An array of variable length byte arrays

See StringArray and LargeStringArray for storing utf8 encoded string data

See BinaryArray and LargeBinaryArray for storing arbitrary bytes

§Example: From a Vec

let arr: GenericByteArray<Utf8Type> = vec!["hello", "world", ""].into();
assert_eq!(arr.value_data(), b"helloworld");
assert_eq!(arr.value_offsets(), &[0, 5, 10, 10]);
let values: Vec<_> = arr.iter().collect();
assert_eq!(values, &[Some("hello"), Some("world"), Some("")]);

§Example: From an optional Vec

let arr: GenericByteArray<Utf8Type> = vec![Some("hello"), Some("world"), Some(""), None].into();
assert_eq!(arr.value_data(), b"helloworld");
assert_eq!(arr.value_offsets(), &[0, 5, 10, 10, 10]);
let values: Vec<_> = arr.iter().collect();
assert_eq!(values, &[Some("hello"), Some("world"), Some(""), None]);

§Example: From an iterator of option

let arr: GenericByteArray<Utf8Type> = (0..5).map(|x| (x % 2 == 0).then(|| x.to_string())).collect();
let values: Vec<_> = arr.iter().collect();
assert_eq!(values, &[Some("0"), None, Some("2"), None, Some("4")]);

§Example: Using Builder

let mut builder = GenericByteBuilder::<Utf8Type>::new();
builder.append_value("hello");
builder.append_null();
builder.append_value("world");
let array = builder.finish();
let values: Vec<_> = array.iter().collect();
assert_eq!(values, &[Some("hello"), None, Some("world")]);

Fields§

§data_type: DataType§value_offsets: OffsetBuffer<T::Offset>§value_data: Buffer§nulls: Option<NullBuffer>

Implementations§

Source§

impl<OffsetSize: OffsetSizeTrait> GenericByteArray<GenericBinaryType<OffsetSize>>

Source

pub const fn get_data_type() -> DataType

👎Deprecated: please use Self::DATA_TYPE instead

Get the data type of the array.

Source

pub fn from_vec(v: Vec<&[u8]>) -> Self

Creates a GenericBinaryArray from a vector of byte slices

See also Self::from_iter_values

Source

pub fn from_opt_vec(v: Vec<Option<&[u8]>>) -> Self

Creates a GenericBinaryArray from a vector of Optional (null) byte slices

Source

fn from_list(v: GenericListArray<OffsetSize>) -> Self

Source

pub fn take_iter<'a>( &'a self, indexes: impl Iterator<Item = Option<usize>> + 'a, ) -> impl Iterator<Item = Option<&'a [u8]>>

Returns an iterator that returns the values of array.value(i) for an iterator with each element i

Source

pub unsafe fn take_iter_unchecked<'a>( &'a self, indexes: impl Iterator<Item = Option<usize>> + 'a, ) -> impl Iterator<Item = Option<&'a [u8]>>

Returns an iterator that returns the values of array.value(i) for an iterator with each element i

§Safety

caller must ensure that the indexes in the iterator are less than the array.len()

Source§

impl<T: ByteArrayType> GenericByteArray<T>

Source

pub const DATA_TYPE: DataType = T::DATA_TYPE

Data type of the array.

Source

pub fn new( offsets: OffsetBuffer<T::Offset>, values: Buffer, nulls: Option<NullBuffer>, ) -> Self

Create a new GenericByteArray from the provided parts, panicking on failure

§Panics

Panics if GenericByteArray::try_new returns an error

Source

pub fn try_new( offsets: OffsetBuffer<T::Offset>, values: Buffer, nulls: Option<NullBuffer>, ) -> Result<Self, ArrowError>

Create a new GenericByteArray from the provided parts, returning an error on failure

§Errors
  • offsets.len() - 1 != nulls.len()
  • Any consecutive pair of offsets does not denote a valid slice of values
Source

pub unsafe fn new_unchecked( offsets: OffsetBuffer<T::Offset>, values: Buffer, nulls: Option<NullBuffer>, ) -> Self

Create a new GenericByteArray from the provided parts, without validation

§Safety

Safe if Self::try_new would not error

Source

pub fn new_null(len: usize) -> Self

Create a new GenericByteArray of length len where all values are null

Source

pub fn new_scalar(value: impl AsRef<T::Native>) -> Scalar<Self>

Create a new Scalar from v

Source

pub fn from_iter_values<Ptr, I>(iter: I) -> Self
where Ptr: AsRef<T::Native>, I: IntoIterator<Item = Ptr>,

Creates a GenericByteArray based on an iterator of values without nulls

Source

pub fn into_parts(self) -> (OffsetBuffer<T::Offset>, Buffer, Option<NullBuffer>)

Deconstruct this array into its constituent parts

Source

pub fn value_length(&self, i: usize) -> T::Offset

Returns the length for value at index i.

§Panics

Panics if index i is out of bounds.

Source

pub fn offsets(&self) -> &OffsetBuffer<T::Offset>

Returns a reference to the offsets of this array

Unlike Self::value_offsets this returns the [OffsetBuffer] allowing for zero-copy cloning

Source

pub fn values(&self) -> &Buffer

Returns the values of this array

Unlike Self::value_data this returns the [Buffer] allowing for zero-copy cloning

Source

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

Returns the raw value data

Source

pub fn is_ascii(&self) -> bool

Returns true if all data within this array is ASCII

Source

pub fn value_offsets(&self) -> &[T::Offset]

Returns the offset values in the offsets buffer

Source

pub unsafe fn value_unchecked(&self, i: usize) -> &T::Native

Returns the element at index i

§Safety

Caller is responsible for ensuring that the index is within the bounds of the array

Source

pub fn value(&self, i: usize) -> &T::Native

Returns the element at index i

§Panics

Panics if index i is out of bounds.

Source

pub fn iter(&self) -> ArrayIter<&Self>

constructs a new iterator

Source

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

Returns a zero-copy slice of this array with the indicated offset and length.

Source

pub fn into_builder(self) -> Result<GenericByteBuilder<T>, Self>

Returns GenericByteBuilder of this byte array for mutating its values if the underlying offset and data buffers are not shared by others.

Source§

impl<OffsetSize: OffsetSizeTrait> GenericByteArray<GenericStringType<OffsetSize>>

Source

pub const fn get_data_type() -> DataType

👎Deprecated: please use Self::DATA_TYPE instead

Get the data type of the array.

Source

pub fn num_chars(&self, i: usize) -> usize

Returns the number of Unicode Scalar Value in the string at index i.

§Performance

This function has O(n) time complexity where n is the string length. If you can make sure that all chars in the string are in the range U+0x0000 ~ U+0x007F, please use the function value_length which has O(1) time complexity.

Source

pub fn take_iter<'a>( &'a self, indexes: impl Iterator<Item = Option<usize>> + 'a, ) -> impl Iterator<Item = Option<&'a str>>

Returns an iterator that returns the values of array.value(i) for an iterator with each element i

Source

pub unsafe fn take_iter_unchecked<'a>( &'a self, indexes: impl Iterator<Item = Option<usize>> + 'a, ) -> impl Iterator<Item = Option<&'a str>>

Returns an iterator that returns the values of array.value(i) for an iterator with each element i

§Safety

caller must ensure that the indexes in the iterator are less than the array.len()

Source

pub fn try_from_binary( v: GenericBinaryArray<OffsetSize>, ) -> Result<Self, ArrowError>

Fallibly creates a GenericStringArray from a GenericBinaryArray returning an error if GenericBinaryArray contains invalid UTF-8 data

Trait Implementations§

Source§

impl<T: ByteArrayType> Array for GenericByteArray<T>

Source§

fn as_any(&self) -> &dyn Any

Returns the array as Any so that it can be downcasted to a specific implementation. Read more
Source§

fn to_data(&self) -> ArrayData

Returns the underlying data of this array
Source§

fn into_data(self) -> ArrayData

Returns the underlying data of this array Read more
Source§

fn data_type(&self) -> &DataType

Returns a reference to the [DataType] of this array. Read more
Source§

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

Returns a zero-copy slice of this array with the indicated offset and length. Read more
Source§

fn len(&self) -> usize

Returns the length (i.e., number of elements) of this array. Read more
Source§

fn is_empty(&self) -> bool

Returns whether this array is empty. Read more
Source§

fn offset(&self) -> usize

Returns the offset into the underlying data used by this array(-slice). Note that the underlying data can be shared by many arrays. This defaults to 0. Read more
Source§

fn nulls(&self) -> Option<&NullBuffer>

Returns the null buffer of this array if any. Read more
Source§

fn get_buffer_memory_size(&self) -> usize

Returns the total number of bytes of memory pointed to by this array. The buffers store bytes in the Arrow memory format, and include the data as well as the validity map. Note that this does not always correspond to the exact memory usage of an array, since multiple arrays can share the same buffers or slices thereof.
Source§

fn get_array_memory_size(&self) -> usize

Returns the total number of bytes of memory occupied physically by this array. This value will always be greater than returned by get_buffer_memory_size() and includes the overhead of the data structures that contain the pointers to the various buffers.
Source§

fn logical_nulls(&self) -> Option<NullBuffer>

Returns a potentially computed [NullBuffer] that represents the logical null values of this array, if any. Read more
Source§

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

Returns whether the element at index is null according to Array::nulls Read more
Source§

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

Returns whether the element at index is not null, the opposite of Self::is_null. Read more
Source§

fn null_count(&self) -> usize

Returns the total number of physical null values in this array. Read more
Source§

fn logical_null_count(&self) -> usize

Returns the total number of logical null values in this array. Read more
Source§

fn is_nullable(&self) -> bool

Returns false if the array is guaranteed to not contain any logical nulls Read more
Source§

impl<'a, T: ByteArrayType> ArrayAccessor for &'a GenericByteArray<T>

Source§

type Item = &'a <T as ByteArrayType>::Native

The Arrow type of the element being accessed.
Source§

fn value(&self, index: usize) -> Self::Item

Returns the element at index i Read more
Source§

unsafe fn value_unchecked(&self, index: usize) -> Self::Item

Returns the element at index i Read more
Source§

impl<T: ByteArrayType> Clone for GenericByteArray<T>

Source§

fn clone(&self) -> Self

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<T: ByteArrayType> Debug for GenericByteArray<T>

Source§

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

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

impl<FROM, V> From<&GenericByteArray<FROM>> for GenericByteViewArray<V>
where FROM: ByteArrayType, FROM::Offset: OffsetSizeTrait + ToPrimitive, V: ByteViewType<Native = FROM::Native>,

Efficiently convert a GenericByteArray to a GenericByteViewArray

For example this method can convert a StringArray to a StringViewArray.

If the offsets are all less than u32::MAX, the new GenericByteViewArray is built without copying the underlying string data (views are created directly into the existing buffer)

Source§

fn from(byte_array: &GenericByteArray<FROM>) -> Self

Converts to this type from the input type.
Source§

impl<T: ByteArrayType> From<ArrayData> for GenericByteArray<T>

Source§

fn from(data: ArrayData) -> Self

Converts to this type from the input type.
Source§

impl<OffsetSize: OffsetSizeTrait> From<GenericByteArray<GenericBinaryType<OffsetSize>>> for GenericStringArray<OffsetSize>

Source§

fn from(v: GenericBinaryArray<OffsetSize>) -> Self

Converts to this type from the input type.
Source§

impl<OffsetSize: OffsetSizeTrait> From<GenericByteArray<GenericStringType<OffsetSize>>> for GenericBinaryArray<OffsetSize>

Source§

fn from(value: GenericStringArray<OffsetSize>) -> Self

Converts to this type from the input type.
Source§

impl<T: ByteArrayType> From<GenericByteArray<T>> for ArrayData

Source§

fn from(array: GenericByteArray<T>) -> Self

Converts to this type from the input type.
Source§

impl<'a, Ptr, T: ByteArrayType> FromIterator<&'a Option<Ptr>> for GenericByteArray<T>
where Ptr: AsRef<T::Native> + 'a,

Source§

fn from_iter<I: IntoIterator<Item = &'a Option<Ptr>>>(iter: I) -> Self

Creates a value from an iterator. Read more
Source§

impl<Ptr, T: ByteArrayType> FromIterator<Option<Ptr>> for GenericByteArray<T>
where Ptr: AsRef<T::Native>,

Source§

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

Creates a value from an iterator. Read more
Source§

impl<'a, T: ByteArrayType> IntoIterator for &'a GenericByteArray<T>

Source§

type Item = Option<&'a <T as ByteArrayType>::Native>

The type of the elements being iterated over.
Source§

type IntoIter = ArrayIter<&'a GenericByteArray<T>>

Which kind of iterator are we turning this into?
Source§

fn into_iter(self) -> Self::IntoIter

Creates an iterator from a value. 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§

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> Datum for T
where T: Array,

Source§

fn get(&self) -> (&dyn Array, bool)

Returns the value for this Datum and a boolean indicating if the value is scalar
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,

Source§

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>,

Source§

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>,

Source§

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.
§

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