Merge #423

423: Added `Itertools::dedup_with_count()` and `Itertools::dedup_by_with_count()` r=jswrenn a=orium

Fixes #393.

Co-authored-by: Diogo Sousa <diogogsousa@gmail.com>

src/adaptors/mod.rs

@@ -10,7 +10,7 @@ pub use self::multi_product::*;
 
 use std::fmt;
 use std::mem::replace;
-use std::iter::{Fuse, Peekable, FromIterator};
+use std::iter::{Fuse, Peekable, FromIterator, FusedIterator};
 use std::marker::PhantomData;
 use crate::size_hint;
 
@@ -310,13 +310,13 @@ pub fn cartesian_product<I, J>(mut i: I, j: J) -> Product<I, J>
     }
 }
 
-
 impl<I, J> Iterator for Product<I, J>
     where I: Iterator,
           J: Clone + Iterator,
           I::Item: Clone
 {
     type Item = (I::Item, J::Item);
+
     fn next(&mut self) -> Option<(I::Item, J::Item)> {
         let elt_b = match self.b.next() {
             None => {
@@ -607,18 +607,18 @@ impl<I, J, F> Iterator for MergeBy<I, J, F>
 }
 
 #[derive(Clone, Debug)]
-pub struct CoalesceCore<I>
+pub struct CoalesceCore<I, T>
     where I: Iterator
 {
     iter: I,
-    last: Option<I::Item>,
+    last: Option<T>,
 }
 
-impl<I> CoalesceCore<I>
+impl<I, T> CoalesceCore<I, T>
     where I: Iterator
 {
-    fn next_with<F>(&mut self, mut f: F) -> Option<I::Item>
-        where F: FnMut(I::Item, I::Item) -> Result<I::Item, (I::Item, I::Item)>
+    fn next_with<F>(&mut self, mut f: F) -> Option<T>
+        where F: FnMut(T, I::Item) -> Result<T, (T, T)>
     {
         // this fuses the iterator
         let mut last = match self.last.take() {
@@ -652,7 +652,7 @@ impl<I> CoalesceCore<I>
 pub struct Coalesce<I, F>
     where I: Iterator
 {
-    iter: CoalesceCore<I>,
+    iter: CoalesceCore<I, I::Item>,
     f: F,
 }
 
@@ -705,7 +705,7 @@ impl<I, F> Iterator for Coalesce<I, F>
 pub struct DedupBy<I, Pred>
     where I: Iterator
 {
-    iter: CoalesceCore<I>,
+    iter: CoalesceCore<I, I::Item>,
     dedup_pred: Pred,
 }
 
@@ -718,7 +718,7 @@ pub struct DedupEq;
 
 impl<T: PartialEq> DedupPredicate<T> for DedupEq {
     fn dedup_pair(&mut self, a: &T, b: &T) -> bool {
-        a==b
+        a == b
     }
 }
 
@@ -803,6 +803,79 @@ impl<I, Pred> Iterator for DedupBy<I, Pred>
     }
 }
 
+/// An iterator adaptor that removes repeated duplicates, while keeping a count of how many
+/// repeated elements were present. This will determine equality using a comparison function.
+///
+/// See [`.dedup_by_with_count()`](../trait.Itertools.html#method.dedup_by_with_count) or
+/// [`.dedup_with_count()`](../trait.Itertools.html#method.dedup_with_count) for more information.
+#[must_use = "iterator adaptors are lazy and do nothing unless consumed"]
+pub struct DedupByWithCount<I, Pred>
+    where I: Iterator
+{
+    iter: CoalesceCore<I, (usize, I::Item)>,
+    dedup_pred: Pred,
+}
+
+/// An iterator adaptor that removes repeated duplicates, while keeping a count of how many
+/// repeated elements were present.
+///
+/// See [`.dedup_with_count()`](../trait.Itertools.html#method.dedup_with_count) for more information.
+pub type DedupWithCount<I> = DedupByWithCount<I, DedupEq>;
+
+/// Create a new `DedupByWithCount`.
+pub fn dedup_by_with_count<I, Pred>(mut iter: I, dedup_pred: Pred) -> DedupByWithCount<I, Pred>
+    where I: Iterator,
+{
+    DedupByWithCount {
+        iter: CoalesceCore {
+            last: iter.next().map(|v| (1, v)),
+            iter,
+        },
+        dedup_pred,
+    }
+}
+
+/// Create a new `DedupWithCount`.
+pub fn dedup_with_count<I>(iter: I) -> DedupWithCount<I>
+    where I: Iterator
+{
+    dedup_by_with_count(iter, DedupEq)
+}
+
+impl<I, Pred> fmt::Debug for DedupByWithCount<I, Pred>
+    where I: Iterator + fmt::Debug,
+          I::Item: fmt::Debug,
+{
+    debug_fmt_fields!(Dedup, iter);
+}
+
+impl<I: Clone, Pred: Clone> Clone for DedupByWithCount<I, Pred>
+    where I: Iterator,
+          I::Item: Clone,
+{
+    clone_fields!(iter, dedup_pred);
+}
+
+impl<I, Pred> Iterator for DedupByWithCount<I, Pred>
+    where I: Iterator,
+          Pred: DedupPredicate<I::Item>,
+{
+    type Item = (usize, I::Item);
+
+    fn next(&mut self) -> Option<(usize, I::Item)> {
+        let ref mut dedup_pred = self.dedup_pred;
+        self.iter.next_with(|(c, x), y| {
+            if dedup_pred.dedup_pair(&x, &y) { Ok((c + 1, x)) } else { Err(((c, x), (1, y))) }
+        })
+    }
+
+    fn size_hint(&self) -> (usize, Option<usize>) {
+        self.iter.size_hint()
+    }
+}
+
+impl<I: Iterator, Pred: DedupPredicate<I::Item>> FusedIterator for DedupByWithCount<I, Pred> {}
+
 /// An iterator adaptor that borrows from a `Clone`-able iterator
 /// to only pick off elements while the predicate returns `true`.
 ///

src/lib.rs

@@ -78,6 +78,8 @@ pub mod structs {
     pub use crate::adaptors::{
         Dedup,
         DedupBy,
+        DedupWithCount,
+        DedupByWithCount,
         Interleave,
         InterleaveShortest,
         Product,
@@ -827,7 +829,6 @@ pub trait Itertools : Iterator {
         merge_join_by(self, other, cmp_fn)
     }
 
-
     /// Return an iterator adaptor that flattens an iterator of iterators by
     /// merging them in ascending order.
     ///
@@ -1008,7 +1009,7 @@ pub trait Itertools : Iterator {
     /// use itertools::Itertools;
     ///
     /// let data = vec![(0, 1.), (1, 1.), (0, 2.), (0, 3.), (1, 3.), (1, 2.), (2, 2.)];
-    /// itertools::assert_equal(data.into_iter().dedup_by(|x, y| x.1==y.1),
+    /// itertools::assert_equal(data.into_iter().dedup_by(|x, y| x.1 == y.1),
     ///                         vec![(0, 1.), (0, 2.), (0, 3.), (1, 2.)]);
     /// ```
     fn dedup_by<Cmp>(self, cmp: Cmp) -> DedupBy<Self, Cmp>
@@ -1018,6 +1019,50 @@ pub trait Itertools : Iterator {
         adaptors::dedup_by(self, cmp)
     }
 
+    /// Remove duplicates from sections of consecutive identical elements, while keeping a count of
+    /// how many repeated elements were present.
+    /// If the iterator is sorted, all elements will be unique.
+    ///
+    /// Iterator element type is `(usize, Self::Item)`.
+    ///
+    /// This iterator is *fused*.
+    ///
+    /// ```
+    /// use itertools::Itertools;
+    ///
+    /// let data = vec![1., 1., 2., 3., 3., 2., 2.];
+    /// itertools::assert_equal(data.into_iter().dedup_with_count(),
+    ///                         vec![(2, 1.), (1, 2.), (2, 3.), (2, 2.)]);
+    /// ```
+    fn dedup_with_count(self) -> DedupWithCount<Self>
+        where Self: Sized,
+    {
+        adaptors::dedup_with_count(self)
+    }
+
+    /// Remove duplicates from sections of consecutive identical elements, while keeping a count of
+    /// how many repeated elements were present.
+    /// This will determine equality using a comparison function.
+    /// If the iterator is sorted, all elements will be unique.
+    ///
+    /// Iterator element type is `(usize, Self::Item)`.
+    ///
+    /// This iterator is *fused*.
+    ///
+    /// ```
+    /// use itertools::Itertools;
+    ///
+    /// let data = vec![(0, 1.), (1, 1.), (0, 2.), (0, 3.), (1, 3.), (1, 2.), (2, 2.)];
+    /// itertools::assert_equal(data.into_iter().dedup_by_with_count(|x, y| x.1 == y.1),
+    ///                         vec![(2, (0, 1.)), (1, (0, 2.)), (2, (0, 3.)), (2, (1, 2.))]);
+    /// ```
+    fn dedup_by_with_count<Cmp>(self, cmp: Cmp) -> DedupByWithCount<Self, Cmp>
+        where Self: Sized,
+              Cmp: FnMut(&Self::Item, &Self::Item) -> bool,
+    {
+        adaptors::dedup_by_with_count(self, cmp)
+    }
+
     /// Return an iterator adaptor that filters out elements that have
     /// already been produced once during the iteration. Duplicates
     /// are detected using hash and equality.

tests/test_std.rs

@@ -115,6 +115,33 @@ fn dedup_by() {
     assert_eq!(&xs_d, &ys);
 }
 
+#[test]
+fn dedup_with_count() {
+    let xs: [i32; 8] = [0, 1, 1, 1, 2, 1, 3, 3];
+    let ys: [(usize, &i32); 5] = [(1, &0), (3, &1), (1, &2), (1, &1), (2, &3)];
+
+    it::assert_equal(ys.iter().cloned(), xs.iter().dedup_with_count());
+
+    let xs: [i32; 5] = [0, 0, 0, 0, 0];
+    let ys: [(usize, &i32); 1] = [(5, &0)];
+
+    it::assert_equal(ys.iter().cloned(), xs.iter().dedup_with_count());
+}
+
+
+#[test]
+fn dedup_by_with_count() {
+    let xs = [(0, 0), (0, 1), (1, 1), (2, 1), (0, 2), (3, 1), (0, 3), (1, 3)];
+    let ys = [(1, &(0, 0)), (3, &(0, 1)), (1, &(0, 2)), (1, &(3, 1)), (2, &(0, 3))];
+
+    it::assert_equal(ys.iter().cloned(), xs.iter().dedup_by_with_count(|x, y| x.1==y.1));
+
+    let xs = [(0, 1), (0, 2), (0, 3), (0, 4), (0, 5)];
+    let ys = [( 5, &(0, 1))];
+
+    it::assert_equal(ys.iter().cloned(), xs.iter().dedup_by_with_count(|x, y| x.0==y.0));
+}
+
 #[test]
 fn all_equal() {
     assert!("".chars().all_equal());