Struct DedupMergeIterator 

pub struct DedupMergeIterator<K, V, I>
where
    K: Ord,
    I: Iterator<Item = DedupEntry<K, V>>,
{ /* private fields */ }

Implementations

impl<K, V, I> DedupMergeIterator<K, V, I>

where K: Ord, I: Iterator<Item = DedupEntry<K, V>>,

pub fn new<S: IntoIterator<Item = I>>(streams: S) -> Self

Examples found in repository

examples/sample_app.rs (line 197)

fn compact_last_prices() {
    use subms_merge_iterator::{DedupEntry, DedupMergeIterator};
    println!("\n== dedup: compact the last-price rows ==");
    let flushed = PRICE_FLUSHED
        .iter()
        .map(|&(k, v)| DedupEntry::new(k, v))
        .collect::<Vec<_>>();
    let memtable = PRICE_MEMTABLE
        .iter()
        .map(|&(k, v)| DedupEntry::new(k, v))
        .collect::<Vec<_>>();

    let compacted: Vec<(&str, i64)> =
        DedupMergeIterator::new([flushed.into_iter(), memtable.into_iter()])
            .map(|e| (e.key, e.value))
            .collect();
    println!("  compacted last prices: {compacted:?}");
    assert_eq!(compacted, vec![("AAPL", 152), ("MSFT", 300)]);
}

examples/perf_features.rs (line 350)

fn main() -> io::Result<()> {
    let path = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
        .join("..")
        .join(".subms")
        .join("features")
        .join("rust.json");
    let existing = std::fs::read_to_string(&path).unwrap_or_default();
    let mut manifest = SubMsFeatureManifest::load_str("rust", &existing);
    // Stamp the box these numbers came from. The bench runs wherever it is
    // invoked, so an unstamped manifest is indistinguishable from a fleet
    // capture; the renderer will not publish one it cannot attribute.
    let (source, instance) = SubMsP99Source::from_env();
    manifest.set_p99_source(source, instance.as_deref());

    // The baseline: a plain merge step with no feature enabled. Every feature
    // decorates this step, so it is what they are classified against. Swept as
    // well as measured, because a base that itself drifted with size would make
    // every feature's flat reading meaningless.
    let base_sw = sweep("base/next", |n| {
        per_element(|| MergeIterator::new(plain_streams(n)), n, true)
    });
    let base_p50 = base_sw[base_sw.len() - 1].1;
    eprintln!("base next p50: {base_p50}ns/element");

    // ---------- seek-to: skip forward past a key ----------
    #[cfg(feature = "seek-to")]
    {
        let sw = sweep("seek-to/seek", |n| seek_only(n, true));
        let (cat, reason) = classify_feature(&sw, Some(base_p50), None);

        let mut p99 = BTreeMap::new();
        p99.insert("seek".to_string(), seek_only(CANON, false));
        p99.insert("next_after_seek".to_string(), seek_then_next(CANON, false));
        manifest.set_feature("seek-to", cat, &p99, &reason);
    }

    // ---------- reverse: descending merge + seek_for_prev ----------
    #[cfg(feature = "reverse")]
    {
        let sw = sweep("reverse/next", |n| {
            per_element(|| ReverseMergeIterator::new(descending_streams(n)), n, true)
        });
        let (cat, reason) = classify_feature(&sw, Some(base_p50), None);

        let mut p99 = BTreeMap::new();
        p99.insert(
            "reverse_next".to_string(),
            per_element(
                || ReverseMergeIterator::new(descending_streams(CANON)),
                CANON,
                false,
            ),
        );
        p99.insert(
            "seek_for_prev".to_string(),
            seek_for_prev_only(CANON, false),
        );
        manifest.set_feature("reverse", cat, &p99, &reason);
    }

    // ---------- tombstones: delete markers mask same-key entries ----------
    #[cfg(feature = "tombstones")]
    {
        // Every 8th key is a tombstone, so one next in eight pops twice and
        // loops to find the next live key. The decoration is per element.
        let sw = sweep("tombstones/next", |n| {
            per_element(
                || TombstoneMergeIterator::new(tombstone_streams(n)),
                n / 8 * 7,
                true,
            )
        });
        let (cat, reason) = classify_feature(&sw, Some(base_p50), None);

        let mut p99 = BTreeMap::new();
        p99.insert(
            "tombstones_next".to_string(),
            per_element(
                || TombstoneMergeIterator::new(tombstone_streams(CANON)),
                CANON / 8 * 7,
                false,
            ),
        );
        manifest.set_feature("tombstones", cat, &p99, &reason);
    }

    // ---------- dedup: collapse equal keys, latest source wins ----------
    #[cfg(feature = "dedup")]
    {
        // Halved key space, so every key is carried by two sources and every
        // next pops twice: the collapse path runs on every element yielded.
        let sw = sweep("dedup/next", |n| {
            per_element(|| DedupMergeIterator::new(dedup_streams(n)), n / 2, true)
        });
        let (cat, reason) = classify_feature(&sw, Some(base_p50), None);

        let mut p99 = BTreeMap::new();
        p99.insert(
            "dedup_next".to_string(),
            per_element(
                || DedupMergeIterator::new(dedup_streams(CANON)),
                CANON / 2,
                false,
            ),
        );
        manifest.set_feature("dedup", cat, &p99, &reason);
    }

    // ---------- priority: explicit per-source precedence on key tie ----------
    #[cfg(feature = "priority")]
    {
        // Same collide-on-halved-keys shape as dedup, plus a priority field in
        // the heap comparison, so the two figures are directly comparable.
        let sw = sweep("priority/next", |n| {
            per_element(
                || PriorityMergeIterator::new(priority_sources(n)),
                n / 2,
                true,
            )
        });
        let (cat, reason) = classify_feature(&sw, Some(base_p50), None);

        let mut p99 = BTreeMap::new();
        p99.insert(
            "priority_next".to_string(),
            per_element(
                || PriorityMergeIterator::new(priority_sources(CANON)),
                CANON / 2,
                false,
            ),
        );
        manifest.set_feature("priority", cat, &p99, &reason);
    }

    std::fs::create_dir_all(path.parent().unwrap())?;
    std::fs::write(&path, manifest.to_json())?;
    io::stdout().write_all(manifest.to_json().as_bytes())?;
    Ok(())
}

Trait Implementations

impl<K, V, I> Iterator for DedupMergeIterator<K, V, I>

where K: Ord, I: Iterator<Item = DedupEntry<K, V>>,

type Item = DedupEntry<K, V>

The type of the elements being iterated over.

fn next(&mut self) -> Option<DedupEntry<K, V>>

Advances the iterator and returns the next value.

fn next_chunk<const N: usize>( &mut self, ) -> Result<[Self::Item; N], IntoIter<Self::Item, N>>

where Self: Sized,

🔬This is a nightly-only experimental API. (iter_next_chunk)

Advances the iterator and returns an array containing the next N values.

fn size_hint(&self) -> (usize, Option<usize>)

Returns the bounds on the remaining length of the iterator.

fn count(self) -> usize

where Self: Sized,

Consumes the iterator, counting the number of iterations and returning it.

fn last(self) -> Option<Self::Item>

where Self: Sized,

Consumes the iterator, returning the last element.

fn advance_by(&mut self, n: usize) -> Result<(), NonZero<usize>>

🔬This is a nightly-only experimental API. (iter_advance_by)

Advances the iterator by n elements.

fn nth(&mut self, n: usize) -> Option<Self::Item>

Returns the nth element of the iterator.

fn step_by(self, step: usize) -> StepBy<Self>

where Self: Sized,

Creates an iterator starting at the same point, but stepping by the given amount at each iteration.

fn chain<U>(self, other: U) -> Chain<Self, <U as IntoIterator>::IntoIter>

where Self: Sized, U: IntoIterator<Item = Self::Item>,

Takes two iterators and creates a new iterator over both in sequence.

fn zip<U>(self, other: U) -> Zip<Self, <U as IntoIterator>::IntoIter>

where Self: Sized, U: IntoIterator,

‘Zips up’ two iterators into a single iterator of pairs.

fn intersperse(self, separator: Self::Item) -> Intersperse<Self>

where Self: Sized, Self::Item: Clone,

🔬This is a nightly-only experimental API. (iter_intersperse)

Creates a new iterator which places a copy of separator between items of the original iterator.

fn intersperse_with<G>(self, separator: G) -> IntersperseWith<Self, G>

where Self: Sized, G: FnMut() -> Self::Item,

🔬This is a nightly-only experimental API. (iter_intersperse)

Creates a new iterator which places an item generated by separator between items of the original iterator.

fn map<B, F>(self, f: F) -> Map<Self, F>

where Self: Sized, F: FnMut(Self::Item) -> B,

Takes a closure and creates an iterator which calls that closure on each element.

fn for_each<F>(self, f: F)

where Self: Sized, F: FnMut(Self::Item),

Calls a closure on each element of an iterator.

fn filter<P>(self, predicate: P) -> Filter<Self, P>

where Self: Sized, P: FnMut(&Self::Item) -> bool,

Creates an iterator which uses a closure to determine if an element should be yielded.

fn filter_map<B, F>(self, f: F) -> FilterMap<Self, F>

where Self: Sized, F: FnMut(Self::Item) -> Option<B>,

Creates an iterator that both filters and maps.

fn enumerate(self) -> Enumerate<Self>

where Self: Sized,

Creates an iterator which gives the current iteration count as well as the next value.

fn peekable(self) -> Peekable<Self>

where Self: Sized,

Creates an iterator which can use the peek and peek_mut methods to look at the next element of the iterator without consuming it. See their documentation for more information.

fn skip_while<P>(self, predicate: P) -> SkipWhile<Self, P>

where Self: Sized, P: FnMut(&Self::Item) -> bool,

Creates an iterator that skips elements based on a predicate.

fn take_while<P>(self, predicate: P) -> TakeWhile<Self, P>

where Self: Sized, P: FnMut(&Self::Item) -> bool,

Creates an iterator that yields elements based on a predicate.

fn map_while<B, P>(self, predicate: P) -> MapWhile<Self, P>

where Self: Sized, P: FnMut(Self::Item) -> Option<B>,

Creates an iterator that both yields elements based on a predicate and maps.

fn skip(self, n: usize) -> Skip<Self>

where Self: Sized,

Creates an iterator that skips the first n elements.

fn take(self, n: usize) -> Take<Self>

where Self: Sized,

Creates an iterator that yields the first n elements, or fewer if the underlying iterator ends sooner.

fn scan<St, B, F>(self, initial_state: St, f: F) -> Scan<Self, St, F>

where Self: Sized, F: FnMut(&mut St, Self::Item) -> Option<B>,

An iterator adapter which, like fold, holds internal state, but unlike fold, produces a new iterator.

fn flat_map<U, F>(self, f: F) -> FlatMap<Self, U, F>

where Self: Sized, U: IntoIterator, F: FnMut(Self::Item) -> U,

Creates an iterator that works like map, but flattens nested structure.

fn map_windows<F, R, const N: usize>(self, f: F) -> MapWindows<Self, F, N>

where Self: Sized, F: FnMut(&[Self::Item; N]) -> R,

🔬This is a nightly-only experimental API. (iter_map_windows)

Calls the given function f for each contiguous window of size N over self and returns an iterator over the outputs of f. Like slice::windows(), the windows during mapping overlap as well.

fn fuse(self) -> Fuse<Self>

where Self: Sized,

Creates an iterator which ends after the first None.

fn inspect<F>(self, f: F) -> Inspect<Self, F>

where Self: Sized, F: FnMut(&Self::Item),

Does something with each element of an iterator, passing the value on.

fn by_ref(&mut self) -> &mut Self

where Self: Sized,

Creates a “by reference” adapter for this instance of Iterator.

fn collect<B>(self) -> B

where B: FromIterator<Self::Item>, Self: Sized,

Transforms an iterator into a collection.

fn collect_into<E>(self, collection: &mut E) -> &mut E

where E: Extend<Self::Item>, Self: Sized,

🔬This is a nightly-only experimental API. (iter_collect_into)

Collects all the items from an iterator into a collection.

fn partition<B, F>(self, f: F) -> (B, B)

where Self: Sized, B: Default + Extend<Self::Item>, F: FnMut(&Self::Item) -> bool,

Consumes an iterator, creating two collections from it.

fn is_partitioned<P>(self, predicate: P) -> bool

where Self: Sized, P: FnMut(Self::Item) -> bool,

🔬This is a nightly-only experimental API. (iter_is_partitioned)

Checks if the elements of this iterator are partitioned according to the given predicate, such that all those that return true precede all those that return false.

fn try_fold<B, F, R>(&mut self, init: B, f: F) -> R

where Self: Sized, F: FnMut(B, Self::Item) -> R, R: Try<Output = B>,

An iterator method that applies a function as long as it returns successfully, producing a single, final value.

fn try_for_each<F, R>(&mut self, f: F) -> R

where Self: Sized, F: FnMut(Self::Item) -> R, R: Try<Output = ()>,

An iterator method that applies a fallible function to each item in the iterator, stopping at the first error and returning that error.

fn fold<B, F>(self, init: B, f: F) -> B

where Self: Sized, F: FnMut(B, Self::Item) -> B,

Folds every element into an accumulator by applying an operation, returning the final result.

fn reduce<F>(self, f: F) -> Option<Self::Item>

where Self: Sized, F: FnMut(Self::Item, Self::Item) -> Self::Item,

Reduces the elements to a single one, by repeatedly applying a reducing operation.

fn try_reduce<R>( &mut self, f: impl FnMut(Self::Item, Self::Item) -> R, ) -> <<R as Try>::Residual as Residual<Option<<R as Try>::Output>>>::TryType

where Self: Sized, R: Try<Output = Self::Item>, <R as Try>::Residual: Residual<Option<Self::Item>>,

🔬This is a nightly-only experimental API. (iterator_try_reduce)

Reduces the elements to a single one by repeatedly applying a reducing operation. If the closure returns a failure, the failure is propagated back to the caller immediately.

fn all<F>(&mut self, f: F) -> bool

where Self: Sized, F: FnMut(Self::Item) -> bool,

Tests if every element of the iterator matches a predicate.

fn any<F>(&mut self, f: F) -> bool

where Self: Sized, F: FnMut(Self::Item) -> bool,

Tests if any element of the iterator matches a predicate.

fn find<P>(&mut self, predicate: P) -> Option<Self::Item>

where Self: Sized, P: FnMut(&Self::Item) -> bool,

Searches for an element of an iterator that satisfies a predicate.

fn find_map<B, F>(&mut self, f: F) -> Option<B>

where Self: Sized, F: FnMut(Self::Item) -> Option<B>,

Applies function to the elements of iterator and returns the first non-none result.

fn try_find<R>( &mut self, f: impl FnMut(&Self::Item) -> R, ) -> <<R as Try>::Residual as Residual<Option<Self::Item>>>::TryType

where Self: Sized, R: Try<Output = bool>, <R as Try>::Residual: Residual<Option<Self::Item>>,

🔬This is a nightly-only experimental API. (try_find)

Applies function to the elements of iterator and returns the first true result or the first error.

fn position<P>(&mut self, predicate: P) -> Option<usize>

where Self: Sized, P: FnMut(Self::Item) -> bool,

Searches for an element in an iterator, returning its index.

fn max_by_key<B, F>(self, f: F) -> Option<Self::Item>

where B: Ord, Self: Sized, F: FnMut(&Self::Item) -> B,

Returns the element that gives the maximum value from the specified function.

fn max_by<F>(self, compare: F) -> Option<Self::Item>

where Self: Sized, F: FnMut(&Self::Item, &Self::Item) -> Ordering,

Returns the element that gives the maximum value with respect to the specified comparison function.

fn min_by_key<B, F>(self, f: F) -> Option<Self::Item>

where B: Ord, Self: Sized, F: FnMut(&Self::Item) -> B,

Returns the element that gives the minimum value from the specified function.

fn min_by<F>(self, compare: F) -> Option<Self::Item>

where Self: Sized, F: FnMut(&Self::Item, &Self::Item) -> Ordering,

Returns the element that gives the minimum value with respect to the specified comparison function.

fn unzip<A, B, FromA, FromB>(self) -> (FromA, FromB)

where FromA: Default + Extend<A>, FromB: Default + Extend<B>, Self: Sized + Iterator<Item = (A, B)>,

Converts an iterator of pairs into a pair of containers.

fn copied<'a, T>(self) -> Copied<Self>

where T: Copy + 'a, Self: Sized + Iterator<Item = &'a T>,

Creates an iterator which copies all of its elements.

fn cloned<'a, T>(self) -> Cloned<Self>

where T: Clone + 'a, Self: Sized + Iterator<Item = &'a T>,

Creates an iterator which clones all of its elements.

fn array_chunks<const N: usize>(self) -> ArrayChunks<Self, N>

where Self: Sized,

🔬This is a nightly-only experimental API. (iter_array_chunks)

Returns an iterator over N elements of the iterator at a time.

fn sum<S>(self) -> S

where Self: Sized, S: Sum<Self::Item>,

Sums the elements of an iterator.

fn product<P>(self) -> P

where Self: Sized, P: Product<Self::Item>,

Iterates over the entire iterator, multiplying all the elements.

fn cmp_by<I, F>(self, other: I, cmp: F) -> Ordering

where Self: Sized, I: IntoIterator, F: FnMut(Self::Item, <I as IntoIterator>::Item) -> Ordering,

🔬This is a nightly-only experimental API. (iter_order_by)

Lexicographically compares the elements of this Iterator with those of another with respect to the specified comparison function.

fn partial_cmp<I>(self, other: I) -> Option<Ordering>

where I: IntoIterator, Self::Item: PartialOrd<<I as IntoIterator>::Item>, Self: Sized,

Lexicographically compares the PartialOrd elements of this Iterator with those of another. The comparison works like short-circuit evaluation, returning a result without comparing the remaining elements. As soon as an order can be determined, the evaluation stops and a result is returned.

fn partial_cmp_by<I, F>(self, other: I, partial_cmp: F) -> Option<Ordering>

where Self: Sized, I: IntoIterator, F: FnMut(Self::Item, <I as IntoIterator>::Item) -> Option<Ordering>,

🔬This is a nightly-only experimental API. (iter_order_by)

Lexicographically compares the elements of this Iterator with those of another with respect to the specified comparison function.

fn eq<I>(self, other: I) -> bool

where I: IntoIterator, Self::Item: PartialEq<<I as IntoIterator>::Item>, Self: Sized,

Determines if the elements of this Iterator are equal to those of another.

fn eq_by<I, F>(self, other: I, eq: F) -> bool

where Self: Sized, I: IntoIterator, F: FnMut(Self::Item, <I as IntoIterator>::Item) -> bool,

🔬This is a nightly-only experimental API. (iter_order_by)

Determines if the elements of this Iterator are equal to those of another with respect to the specified equality function.

fn ne<I>(self, other: I) -> bool

where I: IntoIterator, Self::Item: PartialEq<<I as IntoIterator>::Item>, Self: Sized,

Determines if the elements of this Iterator are not equal to those of another.

fn lt<I>(self, other: I) -> bool

where I: IntoIterator, Self::Item: PartialOrd<<I as IntoIterator>::Item>, Self: Sized,

Determines if the elements of this Iterator are lexicographically less than those of another.

fn le<I>(self, other: I) -> bool

where I: IntoIterator, Self::Item: PartialOrd<<I as IntoIterator>::Item>, Self: Sized,

Determines if the elements of this Iterator are lexicographically less or equal to those of another.

fn gt<I>(self, other: I) -> bool

where I: IntoIterator, Self::Item: PartialOrd<<I as IntoIterator>::Item>, Self: Sized,

Determines if the elements of this Iterator are lexicographically greater than those of another.

fn ge<I>(self, other: I) -> bool

where I: IntoIterator, Self::Item: PartialOrd<<I as IntoIterator>::Item>, Self: Sized,

Determines if the elements of this Iterator are lexicographically greater than or equal to those of another.

fn is_sorted_by<F>(self, compare: F) -> bool

where Self: Sized, F: FnMut(&Self::Item, &Self::Item) -> bool,

Checks if the elements of this iterator are sorted using the given comparator function.

fn is_sorted_by_key<F, K>(self, f: F) -> bool

where Self: Sized, F: FnMut(Self::Item) -> K, K: PartialOrd,

Checks if the elements of this iterator are sorted using the given key extraction function.