Struct arrow::array::GenericListArray

source ·
pub struct GenericListArray<OffsetSize>
where OffsetSize: OffsetSizeTrait,
{ /* private fields */ }
Expand description

An array of variable length lists, similar to JSON arrays (e.g. ["A", "B", "C"]).

Lists are represented using offsets into a values child array. Offsets are stored in two adjacent entries of an OffsetBuffer.

Arrow defines ListArray with i32 offsets and LargeListArray with i64 offsets.

Use GenericListBuilder to construct a GenericListArray.

§Representation

A ListArray can represent a list of values of any other supported Arrow type. Each element of the ListArray itself is a list which may be empty, may contain NULL and non-null values, or may itself be NULL.

For example, the ListArray shown in the following diagram stores lists of strings. Note that [] represents an empty (length 0), but non NULL list.

┌─────────────┐
│   [A,B,C]   │
├─────────────┤
│     []      │
├─────────────┤
│    NULL     │
├─────────────┤
│     [D]     │
├─────────────┤
│  [NULL, F]  │
└─────────────┘

The values are stored in a child StringArray and the offsets are stored in an OffsetBuffer as shown in the following diagram. The logical values and offsets are shown on the left, and the actual ListArray encoding on the right.

                                        ┌ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─
                                                                ┌ ─ ─ ─ ─ ─ ─ ┐    │
 ┌─────────────┐  ┌───────┐             │     ┌───┐   ┌───┐       ┌───┐ ┌───┐
 │   [A,B,C]   │  │ (0,3) │                   │ 1 │   │ 0 │     │ │ 1 │ │ A │ │ 0  │
 ├─────────────┤  ├───────┤             │     ├───┤   ├───┤       ├───┤ ├───┤
 │      []     │  │ (3,3) │                   │ 1 │   │ 3 │     │ │ 1 │ │ B │ │ 1  │
 ├─────────────┤  ├───────┤             │     ├───┤   ├───┤       ├───┤ ├───┤
 │    NULL     │  │ (3,4) │                   │ 0 │   │ 3 │     │ │ 1 │ │ C │ │ 2  │
 ├─────────────┤  ├───────┤             │     ├───┤   ├───┤       ├───┤ ├───┤
 │     [D]     │  │ (4,5) │                   │ 1 │   │ 4 │     │ │ ? │ │ ? │ │ 3  │
 ├─────────────┤  ├───────┤             │     ├───┤   ├───┤       ├───┤ ├───┤
 │  [NULL, F]  │  │ (5,7) │                   │ 1 │   │ 5 │     │ │ 1 │ │ D │ │ 4  │
 └─────────────┘  └───────┘             │     └───┘   ├───┤       ├───┤ ├───┤
                                                      │ 7 │     │ │ 0 │ │ ? │ │ 5  │
                                        │  Validity   └───┘       ├───┤ ├───┤
    Logical       Logical                  (nulls)   Offsets    │ │ 1 │ │ F │ │ 6  │
     Values       Offsets               │                         └───┘ └───┘
                                                                │    Values   │    │
                (offsets[i],            │   ListArray               (Array)
               offsets[i+1])                                    └ ─ ─ ─ ─ ─ ─ ┘    │
                                        └ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─


Implementations§

source§

impl<OffsetSize> GenericListArray<OffsetSize>
where OffsetSize: OffsetSizeTrait,

source

pub const DATA_TYPE_CONSTRUCTOR: fn(_: Arc<Field>) -> DataType = _

The data type constructor of list array. The input is the schema of the child array and the output is the DataType, List or LargeList.

source

pub fn try_new( field: Arc<Field>, offsets: OffsetBuffer<OffsetSize>, values: Arc<dyn Array>, nulls: Option<NullBuffer>, ) -> Result<GenericListArray<OffsetSize>, ArrowError>

Create a new GenericListArray from the provided parts

§Errors

Errors if

  • offsets.len() - 1 != nulls.len()
  • offsets.last() > values.len()
  • !field.is_nullable() && values.is_nullable()
  • field.data_type() != values.data_type()
source

pub fn new( field: Arc<Field>, offsets: OffsetBuffer<OffsetSize>, values: Arc<dyn Array>, nulls: Option<NullBuffer>, ) -> GenericListArray<OffsetSize>

Create a new GenericListArray from the provided parts

§Panics

Panics if Self::try_new returns an error

source

pub fn new_null(field: Arc<Field>, len: usize) -> GenericListArray<OffsetSize>

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

source

pub fn into_parts( self, ) -> (Arc<Field>, OffsetBuffer<OffsetSize>, Arc<dyn Array>, Option<NullBuffer>)

Deconstruct this array into its constituent parts

source

pub fn offsets(&self) -> &OffsetBuffer<OffsetSize>

Returns a reference to the offsets of this list

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

source

pub fn values(&self) -> &Arc<dyn Array>

Returns a reference to the values of this list

source

pub fn value_type(&self) -> DataType

Returns a clone of the value type of this list.

source

pub unsafe fn value_unchecked(&self, i: usize) -> Arc<dyn Array>

Returns ith value of this list array.

§Safety

Caller must ensure that the index is within the array bounds

source

pub fn value(&self, i: usize) -> Arc<dyn Array>

Returns ith value of this list array.

source

pub fn value_offsets(&self) -> &[OffsetSize]

Returns the offset values in the offsets buffer

source

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

Returns the length for value at index i.

source

pub fn iter<'a>(&'a self) -> ArrayIter<&'a GenericListArray<OffsetSize>>

constructs a new iterator

source

pub fn slice( &self, offset: usize, length: usize, ) -> GenericListArray<OffsetSize>

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

source

pub fn from_iter_primitive<T, P, I>(iter: I) -> GenericListArray<OffsetSize>
where T: ArrowPrimitiveType, P: IntoIterator<Item = Option<<T as ArrowPrimitiveType>::Native>>, I: IntoIterator<Item = Option<P>>,

Creates a GenericListArray from an iterator of primitive values

§Example

let data = vec![
   Some(vec![Some(0), Some(1), Some(2)]),
   None,
   Some(vec![Some(3), None, Some(5)]),
   Some(vec![Some(6), Some(7)]),
];
let list_array = ListArray::from_iter_primitive::<Int32Type, _, _>(data);
println!("{:?}", list_array);

Trait Implementations§

source§

impl<OffsetSize> Array for GenericListArray<OffsetSize>
where OffsetSize: OffsetSizeTrait,

source§

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

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) -> Arc<dyn Array>

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 is_nullable(&self) -> bool

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

impl<'a, OffsetSize> ArrayAccessor for &'a GenericListArray<OffsetSize>
where OffsetSize: OffsetSizeTrait,

§

type Item = Arc<dyn Array>

The Arrow type of the element being accessed.
source§

fn value( &self, index: usize, ) -> <&'a GenericListArray<OffsetSize> as ArrayAccessor>::Item

Returns the element at index i Read more
source§

unsafe fn value_unchecked( &self, index: usize, ) -> <&'a GenericListArray<OffsetSize> as ArrayAccessor>::Item

Returns the element at index i Read more
source§

impl<OffsetSize> Clone for GenericListArray<OffsetSize>
where OffsetSize: OffsetSizeTrait,

source§

fn clone(&self) -> GenericListArray<OffsetSize>

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<OffsetSize> Debug for GenericListArray<OffsetSize>
where OffsetSize: OffsetSizeTrait,

source§

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

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

impl<OffsetSize> From<ArrayData> for GenericListArray<OffsetSize>
where OffsetSize: OffsetSizeTrait,

source§

fn from(data: ArrayData) -> GenericListArray<OffsetSize>

Converts to this type from the input type.
source§

impl<OffsetSize> From<FixedSizeListArray> for GenericListArray<OffsetSize>
where OffsetSize: OffsetSizeTrait,

source§

fn from(value: FixedSizeListArray) -> GenericListArray<OffsetSize>

Converts to this type from the input type.
source§

impl<OffsetSize> From<GenericListArray<OffsetSize>> for ArrayData
where OffsetSize: OffsetSizeTrait,

source§

fn from(array: GenericListArray<OffsetSize>) -> ArrayData

Converts to this type from the input type.
source§

impl<OffsetSize> From<GenericListArray<OffsetSize>> for GenericByteArray<GenericStringType<OffsetSize>>
where OffsetSize: OffsetSizeTrait,

source§

fn from( v: GenericListArray<OffsetSize>, ) -> GenericByteArray<GenericStringType<OffsetSize>>

Converts to this type from the input type.
source§

impl<T> From<GenericListArray<T>> for GenericByteArray<GenericBinaryType<T>>
where T: OffsetSizeTrait,

source§

fn from(v: GenericListArray<T>) -> GenericByteArray<GenericBinaryType<T>>

Converts to this type from the input type.
source§

impl From<MapArray> for GenericListArray<i32>

source§

fn from(value: MapArray) -> GenericListArray<i32>

Converts to this type from the input type.
source§

impl<OffsetSize> PartialEq for GenericListArray<OffsetSize>
where OffsetSize: OffsetSizeTrait,

source§

fn eq(&self, other: &GenericListArray<OffsetSize>) -> bool

Tests for self and other values to be equal, and is used by ==.
1.0.0 · source§

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

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

Auto Trait Implementations§

§

impl<OffsetSize> Freeze for GenericListArray<OffsetSize>

§

impl<OffsetSize> !RefUnwindSafe for GenericListArray<OffsetSize>

§

impl<OffsetSize> Send for GenericListArray<OffsetSize>

§

impl<OffsetSize> Sync for GenericListArray<OffsetSize>

§

impl<OffsetSize> Unpin for GenericListArray<OffsetSize>
where OffsetSize: Unpin,

§

impl<OffsetSize> !UnwindSafe for GenericListArray<OffsetSize>

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§

default 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,

§

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>,

§

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>,

§

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.