Struct arrow_array::array::GenericByteArray

pub struct GenericByteArray<T: ByteArrayType> { /* private fields */ }

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")]);

Implementations

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

pub const fn get_data_type() -> DataType

👎Deprecated: please use Self::DATA_TYPE instead

Get the data type of the array.

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

Creates a GenericBinaryArray from a vector of byte slices

See also Self::from_iter_values

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

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

pub fn from_iter_values<Ptr, I>(iter: I) -> Selfwhere Ptr: AsRef<[u8]>, I: IntoIterator<Item = Ptr>,

Creates a GenericBinaryArray based on an iterator of values without nulls

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

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

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

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()

impl<T: ByteArrayType> GenericByteArray<T>

pub const DATA_TYPE: DataType = T::DATA_TYPE

Data type of the array.

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

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

pub 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

pub fn new_null(len: usize) -> Self

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

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

Deconstruct this array into its constituent parts

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.

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

pub fn values(&self) -> &Buffer

Returns the values of this array

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

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

Returns the raw value data

pub fn is_ascii(&self) -> bool

Returns true if all data within this array is ASCII

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

Returns the offset values in the offsets buffer

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

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

Returns the element at index i

Panics

Panics if index i is out of bounds.

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

constructs a new iterator

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

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

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.

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

pub const fn get_data_type() -> DataType

👎Deprecated: please use Self::DATA_TYPE instead

Get the data type of the array.

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.

pub fn from_iter_values<Ptr, I>(iter: I) -> Selfwhere Ptr: AsRef<str>, I: IntoIterator<Item = Ptr>,

Creates a GenericStringArray based on an iterator of values without nulls

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

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

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

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()

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

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

fn as_any(&self) -> &dyn Any

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

fn to_data(&self) -> ArrayData

Returns the underlying data of this array

fn into_data(self) -> ArrayData

Returns the underlying data of this array

fn data_type(&self) -> &DataType

Returns a reference to the DataType of this array.

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

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

fn len(&self) -> usize

Returns the length (i.e., number of elements) of this array.

fn is_empty(&self) -> bool

Returns whether this array is empty.

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.

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

Returns the null buffers of this array if any

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.

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.

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

Returns whether the element at index is null. When using this function on a slice, the index is relative to the slice.

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

Returns whether the element at index is not null. When using this function on a slice, the index is relative to the slice.

fn null_count(&self) -> usize

Returns the total number of null values in this array.

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

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

The Arrow type of the element being accessed.

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

Returns the element at index i

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

Returns the element at index i

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

fn clone(&self) -> Self

Returns a copy of the value.

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

Performs copy-assignment from source.

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

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

Formats the value using the given formatter.

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

fn from(data: ArrayData) -> Self

Converts to this type from the input type.

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

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

Converts to this type from the input type.

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

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

Converts to this type from the input type.

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

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

Converts to this type from the input type.

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

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

Creates a value from an iterator.

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

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

Creates a value from an iterator.

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

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

The type of the elements being iterated over.

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

Which kind of iterator are we turning this into?

fn into_iter(self) -> Self::IntoIter

Creates an iterator from a value.

impl<OffsetSize: OffsetSizeTrait> PartialEq<GenericByteArray<GenericBinaryType<OffsetSize>>> for GenericBinaryArray<OffsetSize>

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.

impl<OffsetSize: OffsetSizeTrait> PartialEq<GenericByteArray<GenericStringType<OffsetSize>>> for GenericStringArray<OffsetSize>

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.