Struct arrow::array::array::GenericByteViewArray

pub struct GenericByteViewArray<T>
where
    T: ByteViewType + ?Sized,
{ /* private fields */ }

Variable-size Binary View Layout: An array of variable length bytes view arrays.

Different than crate::GenericByteArray as it stores both an offset and length meaning that take / filter operations can be implemented without copying the underlying data.

See StringViewArray for storing utf8 encoded string data and BinaryViewArray for storing bytes.

A GenericByteViewArray stores variable length byte strings. An array of N elements is stored as N fixed length “views” and a variable number of variable length “buffers”.

Each view is a u128 value layout is different depending on the length of the string stored at that location:

                        ┌──────┬────────────────────────┐
                        │length│      string value      │
   Strings (len <= 12)  │      │    (padded with 0)     │
                        └──────┴────────────────────────┘
                         0    31                      127

                        ┌───────┬───────┬───────┬───────┐
                        │length │prefix │  buf  │offset │
   Strings (len > 12)   │       │       │ index │       │
                        └───────┴───────┴───────┴───────┘
                         0    31       63      95    127

• Strings with length <= 12 are stored directly in the view.

• Strings with length > 12: The first four bytes are stored inline in the view and the entire string is stored in one of the buffers.

Unlike GenericByteArray, there are no constraints on the offsets other than they must point into a valid buffer. However, they can be out of order, non continuous and overlapping.

For example, in the following diagram, the strings “FishWasInTownToday” and “CrumpleFacedFish” are both longer than 12 bytes and thus are stored in a separate buffer while the string “LavaMonster” is stored inlined in the view. In this case, the same bytes for “Fish” are used to store both strings.

                                                                           ┌───┐
                        ┌──────┬──────┬──────┬──────┐               offset │...│
"FishWasInTownTodayYay" │  21  │ Fish │  0   │ 115  │─ ─              103  │Mr.│
                        └──────┴──────┴──────┴──────┘   │      ┌ ─ ─ ─ ─ ▶ │Cru│
                        ┌──────┬──────┬──────┬──────┐                      │mpl│
"CrumpleFacedFish"      │  16  │ Crum │  0   │ 103  │─ ─│─ ─ ─ ┘           │eFa│
                        └──────┴──────┴──────┴──────┘                      │ced│
                        ┌──────┬────────────────────┐   └ ─ ─ ─ ─ ─ ─ ─ ─ ▶│Fis│
"LavaMonster"           │  11  │   LavaMonster\0    │                      │hWa│
                        └──────┴────────────────────┘               offset │sIn│
                                                                      115  │Tow│
                                                                           │nTo│
                                                                           │day│
                                 u128 "views"                              │Yay│
                                                                  buffer 0 │...│
                                                                           └───┘

Implementations

impl<T> GenericByteViewArray<T>

where T: ByteViewType + ?Sized,

pub fn new( views: ScalarBuffer<u128>, buffers: Vec<Buffer>, nulls: Option<NullBuffer> ) -> GenericByteViewArray<T>

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

Panics

Panics if GenericByteViewArray::try_new returns an error

pub fn try_new( views: ScalarBuffer<u128>, buffers: Vec<Buffer>, nulls: Option<NullBuffer> ) -> Result<GenericByteViewArray<T>, ArrowError>

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

Errors

• views.len() != nulls.len()
• ByteViewType::validate fails

pub unsafe fn new_unchecked( views: ScalarBuffer<u128>, buffers: Vec<Buffer>, nulls: Option<NullBuffer> ) -> GenericByteViewArray<T>

Create a new GenericByteViewArray from the provided parts, without validation

Safety

Safe if Self::try_new would not error

pub fn new_null(len: usize) -> GenericByteViewArray<T>

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

pub fn from_iter_values<Ptr, I>(iter: I) -> GenericByteViewArray<T>

where Ptr: AsRef<<T as ByteViewType>::Native>, I: IntoIterator<Item = Ptr>,

Creates a GenericByteViewArray based on an iterator of values without nulls

pub fn into_parts(self) -> (ScalarBuffer<u128>, Vec<Buffer>, Option<NullBuffer>)

Deconstruct this array into its constituent parts

pub fn views(&self) -> &ScalarBuffer<u128>

Returns the views buffer

pub fn data_buffers(&self) -> &[Buffer]

Returns the buffers storing string data

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

Returns the element at index i

Panics

Panics if index i is out of bounds.

pub unsafe fn value_unchecked(&self, idx: usize) -> &<T as ByteViewType>::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 iter(&self) -> ArrayIter<&GenericByteViewArray<T>>

constructs a new iterator

pub fn slice(&self, offset: usize, length: usize) -> GenericByteViewArray<T>

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

Trait Implementations

impl<T> Array for GenericByteViewArray<T>

where T: ByteViewType + ?Sized,

fn as_any(&self) -> &(dyn Any + 'static)

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) -> Arc<dyn Array>

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 buffer 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. 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.

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 logical_nulls(&self) -> Option<NullBuffer>

Returns a potentially computed NullBuffer that represents the logical null values of this array, if any.

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

Returns whether the element at index is null according to Array::nulls

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

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

fn null_count(&self) -> usize

Returns the total number of physical null values in this array.

fn is_nullable(&self) -> bool

Returns false if the array is guaranteed to not contain any logical nulls

impl<'a, T> ArrayAccessor for &'a GenericByteViewArray<T>

where T: ByteViewType + ?Sized,

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

The Arrow type of the element being accessed.

fn value( &self, index: usize ) -> <&'a GenericByteViewArray<T> as ArrayAccessor>::Item

Returns the element at index i

unsafe fn value_unchecked( &self, index: usize ) -> <&'a GenericByteViewArray<T> as ArrayAccessor>::Item

Returns the element at index i

impl<T> Clone for GenericByteViewArray<T>

where T: ByteViewType + ?Sized,

fn clone(&self) -> GenericByteViewArray<T>

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<T> Debug for GenericByteViewArray<T>

where T: ByteViewType + ?Sized,

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

Formats the value using the given formatter.

impl<T> From<ArrayData> for GenericByteViewArray<T>

where T: ByteViewType + ?Sized,

fn from(value: ArrayData) -> GenericByteViewArray<T>

Converts to this type from the input type.

impl<T> From<GenericByteViewArray<T>> for ArrayData

where T: ByteViewType + ?Sized,

fn from(array: GenericByteViewArray<T>) -> ArrayData

Converts to this type from the input type.

impl From<Vec<&str>> for GenericByteViewArray<StringViewType>

fn from(v: Vec<&str>) -> GenericByteViewArray<StringViewType>

Converts to this type from the input type.

impl<Ptr, T> FromIterator<Option<Ptr>> for GenericByteViewArray<T>

where T: ByteViewType + ?Sized, Ptr: AsRef<<T as ByteViewType>::Native>,

fn from_iter<I>(iter: I) -> GenericByteViewArray<T>

where I: IntoIterator<Item = Option<Ptr>>,

Creates a value from an iterator.

impl<'a, T> IntoIterator for &'a GenericByteViewArray<T>

where T: ByteViewType + ?Sized,

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

The type of the elements being iterated over.

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

Which kind of iterator are we turning this into?

fn into_iter(self) -> <&'a GenericByteViewArray<T> as IntoIterator>::IntoIter

Creates an iterator from a value.