Struct arrow_array::array::RunArray

pub struct RunArray<R: RunEndIndexType> { /* private fields */ }

An array of run-end encoded values

This encoding is variation on run-length encoding (RLE) and is good for representing data containing same values repeated consecutively.

RunArray contains run_ends array and values array of same length. The run_ends array stores the indexes at which the run ends. The values array stores the value of each run. Below example illustrates how a logical array is represented in RunArray

┌ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─┐
  ┌─────────────────┐  ┌─────────┐       ┌─────────────────┐
│ │        A        │  │    2    │ │     │        A        │     
  ├─────────────────┤  ├─────────┤       ├─────────────────┤
│ │        D        │  │    3    │ │     │        A        │    run length of 'A' = runs_ends[0] - 0 = 2
  ├─────────────────┤  ├─────────┤       ├─────────────────┤
│ │        B        │  │    6    │ │     │        D        │    run length of 'D' = run_ends[1] - run_ends[0] = 1
  └─────────────────┘  └─────────┘       ├─────────────────┤
│        values          run_ends  │     │        B        │     
                                         ├─────────────────┤
└ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ─┘     │        B        │     
                                         ├─────────────────┤
               RunArray                  │        B        │    run length of 'B' = run_ends[2] - run_ends[1] = 3
              length = 3                 └─────────────────┘
  
                                            Logical array
                                               Contents

Implementations

impl<R: RunEndIndexType> RunArray<R>

pub fn logical_len(run_ends: &PrimitiveArray<R>) -> usize

Calculates the logical length of the array encoded by the given run_ends array.

pub fn try_new( run_ends: &PrimitiveArray<R>, values: &dyn Array ) -> Result<Self, ArrowError>

Attempts to create RunArray using given run_ends (index where a run ends) and the values (value of the run). Returns an error if the given data is not compatible with RunEndEncoded specification.

pub fn run_ends(&self) -> &RunEndBuffer<R::Native>

Returns a reference to RunEndBuffer

pub fn values(&self) -> &ArrayRef

Returns a reference to values array

Note: any slicing of this RunArray array is not applied to the returned array and must be handled separately

pub fn get_start_physical_index(&self) -> usize

Returns the physical index at which the array slice starts.

pub fn get_end_physical_index(&self) -> usize

Returns the physical index at which the array slice ends.

pub fn downcast<V: 'static>(&self) -> Option<TypedRunArray<'_, R, V>>

Downcast this RunArray to a TypedRunArray

use arrow_array::{Array, ArrayAccessor, RunArray, StringArray, types::Int32Type};

let orig = [Some("a"), Some("b"), None];
let run_array = RunArray::<Int32Type>::from_iter(orig);
let typed = run_array.downcast::<StringArray>().unwrap();
assert_eq!(typed.value(0), "a");
assert_eq!(typed.value(1), "b");
assert!(typed.values().is_null(2));

pub fn get_physical_index(&self, logical_index: usize) -> usize

Returns index to the physical array for the given index to the logical array. This function adjusts the input logical index based on ArrayData::offset Performs a binary search on the run_ends array for the input index.

The result is arbitrary if logical_index >= self.len()

pub fn get_physical_indices<I>( &self, logical_indices: &[I] ) -> Result<Vec<usize>, ArrowError>where I: ArrowNativeType,

Returns the physical indices of the input logical indices. Returns error if any of the logical index cannot be converted to physical index. The logical indices are sorted and iterated along with run_ends array to find matching physical index. The approach used here was chosen over finding physical index for each logical index using binary search using the function get_physical_index. Running benchmarks on both approaches showed that the approach used here scaled well for larger inputs. See https://github.com/apache/arrow-rs/pull/3622#issuecomment-1407753727 for more details.

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

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

Trait Implementations

impl<T: RunEndIndexType> Array for RunArray<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 buffer of this array if any.

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

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

fn is_nullable(&self) -> bool

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

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 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.

impl<R: RunEndIndexType> Clone for RunArray<R>

fn clone(&self) -> Self

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<R: RunEndIndexType> Debug for RunArray<R>

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

Formats the value using the given formatter.

impl<R: RunEndIndexType> From<ArrayData> for RunArray<R>

fn from(data: ArrayData) -> Self

Converts to this type from the input type.

impl<R: RunEndIndexType> From<RunArray<R>> for ArrayData

fn from(array: RunArray<R>) -> Self

Converts to this type from the input type.

impl<'a, T: RunEndIndexType> FromIterator<&'a str> for RunArray<T>

Constructs a RunArray from an iterator of strings.

Example:

use arrow_array::{RunArray, PrimitiveArray, StringArray, types::Int16Type};

let test = vec!["a", "a", "b", "c"];
let array: RunArray<Int16Type> = test.into_iter().collect();
assert_eq!(
    "RunArray {run_ends: [2, 3, 4], values: StringArray\n[\n  \"a\",\n  \"b\",\n  \"c\",\n]}\n",
    format!("{:?}", array)
);

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

Creates a value from an iterator.

impl<'a, T: RunEndIndexType> FromIterator<Option<&'a str>> for RunArray<T>

Constructs a RunArray from an iterator of optional strings.

Example:

use arrow_array::{RunArray, PrimitiveArray, StringArray, types::Int16Type};

let test = vec!["a", "a", "b", "c", "c"];
let array: RunArray<Int16Type> = test
    .iter()
    .map(|&x| if x == "b" { None } else { Some(x) })
    .collect();
assert_eq!(
    "RunArray {run_ends: [2, 3, 5], values: StringArray\n[\n  \"a\",\n  null,\n  \"c\",\n]}\n",
    format!("{:?}", array)
);

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

Creates a value from an iterator.