Struct differential_dataflow::operators::arrange::Arranged

pub struct Arranged<G: Scope, K, V, R, T>where
    G::Timestamp: Lattice + Ord,
    T: TraceReader<K, V, G::Timestamp, R> + Clone,{
    pub stream: Stream<G, T::Batch>,
    pub trace: T,
}

An arranged collection of (K,V) values.

An Arranged allows multiple differential operators to share the resources (communication, computation, memory) required to produce and maintain an indexed representation of a collection.

Fields

stream: Stream<G, T::Batch>

A stream containing arranged updates.

This stream contains the same batches of updates the trace itself accepts, so there should be no additional overhead to receiving these records. The batches can be navigated just as the batches in the trace, by key and by value.

trace: T

A shared trace, updated by the Arrange operator and readable by others.

Implementations

impl<G: Scope, K, V, R, T> Arranged<G, K, V, R, T>where
    G::Timestamp: Lattice + Ord,
    T: TraceReader<K, V, G::Timestamp, R> + Clone,

pub fn enter<'a, TInner>(
    &self,
    child: &Child<'a, G, TInner>
) -> Arranged<Child<'a, G, TInner>, K, V, R, TraceEnter<K, V, G::Timestamp, R, T, TInner>>where
    T::Batch: Clone,
    K: 'static,
    V: 'static,
    G::Timestamp: Clone + Default + 'static,
    TInner: Refines<G::Timestamp> + Lattice + Timestamp + Clone + Default + 'static,
    R: 'static,

Brings an arranged collection into a nested scope.

This method produces a proxy trace handle that uses the same backing data, but acts as if the timestamps have all been extended with an additional coordinate with the default value. The resulting collection does not vary with the new timestamp coordinate.

pub fn enter_at<'a, TInner, F>(
    &self,
    child: &Child<'a, G, TInner>,
    logic: F
) -> Arranged<Child<'a, G, TInner>, K, V, R, TraceEnterAt<K, V, G::Timestamp, R, T, TInner, F>>where
    T::Batch: Clone,
    K: 'static,
    V: 'static,
    G::Timestamp: Clone + Default + 'static,
    TInner: Refines<G::Timestamp> + Lattice + Timestamp + Clone + Default + 'static,
    R: 'static,
    F: Fn(&K, &V, &G::Timestamp) -> TInner + 'static,

Brings an arranged collection into a nested scope.

This method produces a proxy trace handle that uses the same backing data, but acts as if the timestamps have all been extended with an additional coordinate with the default value. The resulting collection does not vary with the new timestamp coordinate.

pub fn filter<F>(
    &self,
    logic: F
) -> Arranged<G, K, V, R, TraceFilter<K, V, G::Timestamp, R, T, F>>where
    T::Batch: Clone,
    K: 'static,
    V: 'static,
    G::Timestamp: Clone + Default + 'static,
    R: 'static,
    F: Fn(&K, &V) -> bool + 'static,

Filters an arranged collection.

This method produces a new arrangement backed by the same shared arrangement as self, paired with user-specified logic that can filter by key and value. The resulting collection is restricted to the keys and values that return true under the user predicate.

Examples

extern crate timely;
extern crate differential_dataflow;

use differential_dataflow::input::Input;
use differential_dataflow::operators::arrange::ArrangeByKey;

fn main() {
    ::timely::example(|scope| {

        let arranged =
        scope.new_collection_from(0 .. 10).1
             .map(|x| (x, x+1))
             .arrange_by_key();

        arranged
            .filter(|k,v| k == v)
            .as_collection(|k,v| (*k,*v))
            .assert_empty();
    });
}

pub fn as_collection<D: Data, L>(&self, logic: L) -> Collection<G, D, R>where
    R: Diff,
    T::Batch: Clone + 'static,
    K: Clone,
    V: Clone,
    L: Fn(&K, &V) -> D + 'static,

Flattens the stream into a Collection.

The underlying Stream<G, BatchWrapper<T::Batch>> is a much more efficient way to access the data, and this method should only be used when the data need to be transformed or exchanged, rather than supplied as arguments to an operator using the same key-value structure.

pub fn flat_map_ref<I, L>(&self, logic: L) -> Collection<G, I::Item, R>where
    R: Diff,
    T::Batch: Clone + 'static,
    K: Clone,
    V: Clone,
    I: IntoIterator,
    I::Item: Data,
    L: Fn(&K, &V) -> I + 'static,

Extracts elements from an arrangement as a collection.

The supplied logic may produce an iterator over output values, allowing either filtering or flat mapping as part of the extraction.

pub fn lookup(
    &self,
    queries: &Stream<G, (K, G::Timestamp)>
) -> Stream<G, (K, V, G::Timestamp, R)>where
    G::Timestamp: Data + Lattice + Ord + TotalOrder,
    K: Data + Hashable,
    V: Data,
    R: Diff,
    T: 'static,

Report values associated with keys at certain times.

This method consumes a stream of (key, time) queries and reports the corresponding stream of (key, value, time, diff) accumulations in the self trace.

Trait Implementations

impl<G: Scope, K, V, R, T> Clone for Arranged<G, K, V, R, T>where
    G::Timestamp: Lattice + Ord,
    T: TraceReader<K, V, G::Timestamp, R> + Clone,

fn clone(&self) -> Self

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<G: Scope, K: Data, T1, R: Diff> Count<G, K, R> for Arranged<G, K, (), R, T1>where
    G::Timestamp: Lattice + Ord,
    T1: TraceReader<K, (), G::Timestamp, R> + Clone + 'static,
    T1::Batch: BatchReader<K, (), G::Timestamp, R>,

fn count(&self) -> Collection<G, (K, R), isize>

Counts the number of occurrences of each element.

impl<G: Scope, K: Data, R: Diff, T1> CountTotal<G, K, R> for Arranged<G, K, (), R, T1>where
    G::Timestamp: TotalOrder + Lattice + Ord,
    T1: TraceReader<K, (), G::Timestamp, R> + Clone + 'static,
    T1::Batch: BatchReader<K, (), G::Timestamp, R>,

fn count_total(&self) -> Collection<G, (K, R), isize>

Counts the number of occurrences of each element.

impl<G: Scope, K: Data, V: Data, T1, R: Diff> Group<G, K, V, R> for Arranged<G, K, V, R, T1>where
    G::Timestamp: Lattice + Ord,
    T1: TraceReader<K, V, G::Timestamp, R> + Clone + 'static,
    T1::Batch: BatchReader<K, V, G::Timestamp, R>,

fn group<L, V2: Data, R2: Diff>(&self, logic: L) -> Collection<G, (K, V2), R2>where
    L: Fn(&K, &[(&V, R)], &mut Vec<(V2, R2)>) + 'static,

Groups records by their first field, and applies reduction logic to the associated values.

impl<G: Scope, K: Data, V: Data, T1, R: Diff> GroupArranged<G, K, V, R> for Arranged<G, K, V, R, T1>where
    G::Timestamp: Lattice + Ord,
    T1: TraceReader<K, V, G::Timestamp, R> + Clone + 'static,
    T1::Batch: BatchReader<K, V, G::Timestamp, R>,

fn group_arranged<L, V2, T2, R2>(
    &self,
    logic: L
) -> Arranged<G, K, V2, R2, TraceAgent<K, V2, G::Timestamp, R2, T2>>where
    V2: Data,
    R2: Diff,
    T2: Trace<K, V2, G::Timestamp, R2> + 'static,
    T2::Batch: Batch<K, V2, G::Timestamp, R2>,
    L: Fn(&K, &[(&V, R)], &mut Vec<(V2, R2)>) + 'static,

Applies group to arranged data, and returns an arrangement of output data.

impl<G, K, V, R, T> Join<G, K, V, R> for Arranged<G, K, V, R, T>where
    G: Scope,
    G::Timestamp: Lattice + Ord,
    K: Data + Hashable,
    V: Data,
    R: Diff,
    T: TraceReader<K, V, G::Timestamp, R> + Clone + 'static,
    T::Batch: BatchReader<K, V, G::Timestamp, R> + 'static,

fn join_map<V2: Data, R2: Diff, D: Data, L>(
    &self,
    other: &Collection<G, (K, V2), R2>,
    logic: L
) -> Collection<G, D, <R as Mul<R2>>::Output>where
    R: Mul<R2>,
    <R as Mul<R2>>::Output: Diff,
    L: Fn(&K, &V, &V2) -> D + 'static,

Matches pairs (key,val1) and (key,val2) based on key and then applies a function.

fn semijoin<R2: Diff>(
    &self,
    other: &Collection<G, K, R2>
) -> Collection<G, (K, V), <R as Mul<R2>>::Output>where
    R: Mul<R2>,
    <R as Mul<R2>>::Output: Diff,

Matches pairs (key, val) and key based on key, producing the former with frequencies multiplied.

fn antijoin<R2: Diff>(
    &self,
    other: &Collection<G, K, R2>
) -> Collection<G, (K, V), R>where
    R: Mul<R2, Output = R>,

Matches pairs (key, val) and key based on key, discarding values in the first collection if their key is present in the second.

fn join<V2: Data, R2: Diff>(
    &self,
    other: &Collection<G, (K, V2), R2>
) -> Collection<G, (K, (V, V2)), <R as Mul<R2>>::Output>where
    R: Mul<R2>,
    <R as Mul<R2>>::Output: Diff,

Matches pairs (key,val1) and (key,val2) based on key and then applies a function.

impl<G, K, V, R1, T1> JoinCore<G, K, V, R1> for Arranged<G, K, V, R1, T1>where
    K: Ord,
    G: Scope,
    G::Timestamp: Lattice + Ord + Debug,
    K: Debug + Eq + 'static,
    V: Ord + Clone + Debug + 'static,
    R1: Diff,
    T1: TraceReader<K, V, G::Timestamp, R1> + Clone + 'static,
    T1::Batch: BatchReader<K, V, G::Timestamp, R1> + 'static,

fn join_core<V2, T2, R2, I, L>(
    &self,
    other: &Arranged<G, K, V2, R2, T2>,
    result: L
) -> Collection<G, I::Item, <R1 as Mul<R2>>::Output>where
    V2: Ord + Clone + Debug + 'static,
    T2: TraceReader<K, V2, G::Timestamp, R2> + Clone + 'static,
    T2::Batch: BatchReader<K, V2, G::Timestamp, R2> + 'static,
    R2: Diff,
    R1: Mul<R2>,
    <R1 as Mul<R2>>::Output: Diff,
    I: IntoIterator,
    I::Item: Data,
    L: Fn(&K, &V, &V2) -> I + 'static,

Joins two arranged collections with the same key type.

impl<G: Scope, K: Data, T1, R1: Diff> Threshold<G, K, R1> for Arranged<G, K, (), R1, T1>where
    G::Timestamp: Lattice + Ord,
    T1: TraceReader<K, (), G::Timestamp, R1> + Clone + 'static,
    T1::Batch: BatchReader<K, (), G::Timestamp, R1>,

fn threshold<R2: Diff, F: Fn(&K, R1) -> R2 + 'static>(
    &self,
    thresh: F
) -> Collection<G, K, R2>

Transforms the multiplicity of records.

fn distinct(&self) -> Collection<G, K, isize>

Reduces the collection to one occurrence of each distinct element.

impl<G: Scope, K: Data, R: Diff, T1> ThresholdTotal<G, K, R> for Arranged<G, K, (), R, T1>where
    G::Timestamp: TotalOrder + Lattice + Ord,
    T1: TraceReader<K, (), G::Timestamp, R> + Clone + 'static,
    T1::Batch: BatchReader<K, (), G::Timestamp, R>,

fn threshold_total<R2: Diff, F: Fn(&K, R) -> R2 + 'static>(
    &self,
    thresh: F
) -> Collection<G, K, R2>

Reduces the collection to one occurrence of each distinct element.

fn distinct_total(&self) -> Collection<G, K, isize>

Reduces the collection to one occurrence of each distinct element.