Struct GroupValuesColumn 

pub struct GroupValuesColumn<const STREAMING: bool> {
    schema: Arc<Schema>,
    map: HashTable<(u64, GroupIndexView)>,
    map_size: usize,
    group_index_lists: Vec<Vec<usize>>,
    emit_group_index_list_buffer: Vec<usize>,
    vectorized_operation_buffers: VectorizedOperationBuffers,
    group_values: Vec<Box<dyn GroupColumn>>,
    hashes_buffer: Vec<u64>,
    random_state: RandomState,
}

A GroupValues that stores multiple columns of group values, and supports vectorized operators for them

Fields

schema: Arc<Schema>

map: HashTable<(u64, GroupIndexView)>

map_size: usize

group_index_lists: Vec<Vec<usize>>

emit_group_index_list_buffer: Vec<usize>

vectorized_operation_buffers: VectorizedOperationBuffers

group_values: Vec<Box<dyn GroupColumn>>

hashes_buffer: Vec<u64>

random_state: RandomState

Implementations

impl<const STREAMING: bool> GroupValuesColumn<STREAMING>

pub fn try_new( schema: Arc<Schema>, ) -> Result<GroupValuesColumn<STREAMING>, DataFusionError>

Create a new instance of GroupValuesColumn if supported for the specified schema

Trait Implementations

impl<const STREAMING: bool> GroupValues for GroupValuesColumn<STREAMING>

fn intern( &mut self, cols: &[Arc<dyn Array>], groups: &mut Vec<usize>, ) -> Result<(), DataFusionError>

Calculates the group id for each input row of cols, assigning new group ids as necessary.

fn size(&self) -> usize

Returns the number of bytes of memory used by this GroupValues

fn is_empty(&self) -> bool

Returns true if this GroupValues is empty

fn len(&self) -> usize

The number of values (distinct group values) stored in this GroupValues

fn emit( &mut self, emit_to: EmitTo, ) -> Result<Vec<Arc<dyn Array>>, DataFusionError>

Emits the group values

fn clear_shrink(&mut self, batch: &RecordBatch)

Clear the contents and shrink the capacity to the size of the batch (free up memory usage)