Auto merge of rust-lang#75207 - dylni:add-slice-check-range, r=KodrAus

Add `slice::check_range`

This method is useful for [`RangeBounds`] parameters. It's even been [rewritten](https://github.com/rust-lang/rust/blob/22ee68dc586440f96b76b32fbd6087507c6afdb9/src/librustc_data_structures/sorted_map.rs#L214) [many](https://github.com/rust-lang/rust/blob/22ee68dc586440f96b76b32fbd6087507c6afdb9/library/alloc/src/vec.rs#L1299) [times](https://github.com/rust-lang/rust/blob/22ee68dc586440f96b76b32fbd6087507c6afdb9/library/core/src/slice/mod.rs#L2441) in the standard library, sometimes assuming that the bounds won't be [`usize::MAX`].

For example, [`Vec::drain`] creates an empty iterator when [`usize::MAX`] is used as an inclusive end bound:

```rust
assert!(vec![1].drain(..=usize::max_value()).eq(iter::empty()));
```

If this PR is merged, I'll create another to use it for those methods.

[`RangeBounds`]: https://doc.rust-lang.org/std/ops/trait.RangeBounds.html
[`usize::MAX`]: https://doc.rust-lang.org/std/primitive.usize.html#associatedconstant.MAX
[`Vec::drain`]: https://doc.rust-lang.org/std/vec/struct.Vec.html#method.drain

Author: bors

library/alloc/src/collections/vec_deque.rs

@@ -14,8 +14,7 @@ use core::fmt;
 use core::hash::{Hash, Hasher};
 use core::iter::{once, repeat_with, FromIterator, FusedIterator};
 use core::mem::{self, replace, ManuallyDrop};
-use core::ops::Bound::{Excluded, Included, Unbounded};
-use core::ops::{Index, IndexMut, RangeBounds, Try};
+use core::ops::{Index, IndexMut, Range, RangeBounds, Try};
 use core::ptr::{self, NonNull};
 use core::slice;
 
@@ -1090,24 +1089,18 @@ impl<T> VecDeque<T> {
         self.tail == self.head
     }
 
-    fn range_start_end<R>(&self, range: R) -> (usize, usize)
+    fn range_tail_head<R>(&self, range: R) -> (usize, usize)
     where
         R: RangeBounds<usize>,
     {
-        let len = self.len();
-        let start = match range.start_bound() {
-            Included(&n) => n,
-            Excluded(&n) => n + 1,
-            Unbounded => 0,
-        };
-        let end = match range.end_bound() {
-            Included(&n) => n + 1,
-            Excluded(&n) => n,
-            Unbounded => len,
-        };
-        assert!(start <= end, "lower bound was too large");
-        assert!(end <= len, "upper bound was too large");
-        (start, end)
+        // SAFETY: This buffer is only used to check the range. It might be partially
+        // uninitialized, but `check_range` needs a contiguous slice.
+        // https://github.com/rust-lang/rust/pull/75207#discussion_r471193682
+        let buffer = unsafe { slice::from_raw_parts(self.ptr(), self.len()) };
+        let Range { start, end } = buffer.check_range(range);
+        let tail = self.wrap_add(self.tail, start);
+        let head = self.wrap_add(self.tail, end);
+        (tail, head)
     }
 
     /// Creates an iterator that covers the specified range in the `VecDeque`.
@@ -1138,9 +1131,7 @@ impl<T> VecDeque<T> {
     where
         R: RangeBounds<usize>,
     {
-        let (start, end) = self.range_start_end(range);
-        let tail = self.wrap_add(self.tail, start);
-        let head = self.wrap_add(self.tail, end);
+        let (tail, head) = self.range_tail_head(range);
         Iter {
             tail,
             head,
@@ -1181,9 +1172,7 @@ impl<T> VecDeque<T> {
     where
         R: RangeBounds<usize>,
     {
-        let (start, end) = self.range_start_end(range);
-        let tail = self.wrap_add(self.tail, start);
-        let head = self.wrap_add(self.tail, end);
+        let (tail, head) = self.range_tail_head(range);
         IterMut {
             tail,
             head,
@@ -1237,7 +1226,7 @@ impl<T> VecDeque<T> {
         // When finished, the remaining data will be copied back to cover the hole,
         // and the head/tail values will be restored correctly.
         //
-        let (start, end) = self.range_start_end(range);
+        let (drain_tail, drain_head) = self.range_tail_head(range);
 
         // The deque's elements are parted into three segments:
         // * self.tail  -> drain_tail
@@ -1255,8 +1244,6 @@ impl<T> VecDeque<T> {
         //        T   t   h   H
         // [. . . o o x x o o . . .]
         //
-        let drain_tail = self.wrap_add(self.tail, start);
-        let drain_head = self.wrap_add(self.tail, end);
         let head = self.head;
 
         // "forget" about the values after the start of the drain until after

library/alloc/src/lib.rs

@@ -119,6 +119,7 @@
 #![feature(rustc_attrs)]
 #![feature(receiver_trait)]
 #![feature(min_specialization)]
+#![feature(slice_check_range)]
 #![feature(slice_ptr_get)]
 #![feature(slice_ptr_len)]
 #![feature(staged_api)]

library/alloc/src/string.rs

@@ -47,7 +47,7 @@ use core::fmt;
 use core::hash;
 use core::iter::{FromIterator, FusedIterator};
 use core::ops::Bound::{Excluded, Included, Unbounded};
-use core::ops::{self, Add, AddAssign, Index, IndexMut, RangeBounds};
+use core::ops::{self, Add, AddAssign, Index, IndexMut, Range, RangeBounds};
 use core::ptr;
 use core::str::{lossy, pattern::Pattern};
 
@@ -1506,23 +1506,15 @@ impl String {
         // of the vector version. The data is just plain bytes.
         // Because the range removal happens in Drop, if the Drain iterator is leaked,
         // the removal will not happen.
-        let len = self.len();
-        let start = match range.start_bound() {
-            Included(&n) => n,
-            Excluded(&n) => n + 1,
-            Unbounded => 0,
-        };
-        let end = match range.end_bound() {
-            Included(&n) => n + 1,
-            Excluded(&n) => n,
-            Unbounded => len,
-        };
+        let Range { start, end } = self.as_bytes().check_range(range);
+        assert!(self.is_char_boundary(start));
+        assert!(self.is_char_boundary(end));
 
         // Take out two simultaneous borrows. The &mut String won't be accessed
         // until iteration is over, in Drop.
         let self_ptr = self as *mut _;
-        // slicing does the appropriate bounds checks
-        let chars_iter = self[start..end].chars();
+        // SAFETY: `check_range` and `is_char_boundary` do the appropriate bounds checks.
+        let chars_iter = unsafe { self.get_unchecked(start..end) }.chars();
 
         Drain { start, end, iter: chars_iter, string: self_ptr }
     }

library/alloc/src/vec.rs

@@ -63,8 +63,7 @@ use core::iter::{
 };
 use core::marker::PhantomData;
 use core::mem::{self, ManuallyDrop, MaybeUninit};
-use core::ops::Bound::{Excluded, Included, Unbounded};
-use core::ops::{self, Index, IndexMut, RangeBounds};
+use core::ops::{self, Index, IndexMut, Range, RangeBounds};
 use core::ptr::{self, NonNull};
 use core::slice::{self, SliceIndex};
 
@@ -1306,35 +1305,7 @@ impl<T> Vec<T> {
         // the hole, and the vector length is restored to the new length.
         //
         let len = self.len();
-        let start = match range.start_bound() {
-            Included(&n) => n,
-            Excluded(&n) => n + 1,
-            Unbounded => 0,
-        };
-        let end = match range.end_bound() {
-            Included(&n) => n + 1,
-            Excluded(&n) => n,
-            Unbounded => len,
-        };
-
-        #[cold]
-        #[inline(never)]
-        fn start_assert_failed(start: usize, end: usize) -> ! {
-            panic!("start drain index (is {}) should be <= end drain index (is {})", start, end);
-        }
-
-        #[cold]
-        #[inline(never)]
-        fn end_assert_failed(end: usize, len: usize) -> ! {
-            panic!("end drain index (is {}) should be <= len (is {})", end, len);
-        }
-
-        if start > end {
-            start_assert_failed(start, end);
-        }
-        if end > len {
-            end_assert_failed(end, len);
-        }
+        let Range { start, end } = self.check_range(range);
 
         unsafe {
             // set self.vec length's to start, to be safe in case Drain is leaked

library/core/src/slice/mod.rs

@@ -29,7 +29,7 @@ use crate::intrinsics::{assume, exact_div, is_aligned_and_not_null, unchecked_su
 use crate::iter::*;
 use crate::marker::{self, Copy, Send, Sized, Sync};
 use crate::mem;
-use crate::ops::{self, FnMut, Range};
+use crate::ops::{self, Bound, FnMut, Range, RangeBounds};
 use crate::option::Option;
 use crate::option::Option::{None, Some};
 use crate::ptr::{self, NonNull};
@@ -355,6 +355,79 @@ impl<T> [T] {
         unsafe { &mut *index.get_unchecked_mut(self) }
     }
 
+    /// Converts a range over this slice to [`Range`].
+    ///
+    /// The returned range is safe to pass to [`get_unchecked`] and [`get_unchecked_mut`].
+    ///
+    /// [`get_unchecked`]: #method.get_unchecked
+    /// [`get_unchecked_mut`]: #method.get_unchecked_mut
+    ///
+    /// # Panics
+    ///
+    /// Panics if the range is out of bounds.
+    ///
+    /// # Examples
+    ///
+    /// ```
+    /// #![feature(slice_check_range)]
+    ///
+    /// let v = [10, 40, 30];
+    /// assert_eq!(1..2, v.check_range(1..2));
+    /// assert_eq!(0..2, v.check_range(..2));
+    /// assert_eq!(1..3, v.check_range(1..));
+    /// ```
+    ///
+    /// Panics when [`Index::index`] would panic:
+    ///
+    /// ```should_panic
+    /// #![feature(slice_check_range)]
+    ///
+    /// [10, 40, 30].check_range(2..1);
+    /// ```
+    ///
+    /// ```should_panic
+    /// #![feature(slice_check_range)]
+    ///
+    /// [10, 40, 30].check_range(1..4);
+    /// ```
+    ///
+    /// ```should_panic
+    /// #![feature(slice_check_range)]
+    ///
+    /// [10, 40, 30].check_range(1..=usize::MAX);
+    /// ```
+    ///
+    /// [`Index::index`]: ops::Index::index
+    #[track_caller]
+    #[unstable(feature = "slice_check_range", issue = "none")]
+    pub fn check_range<R: RangeBounds<usize>>(&self, range: R) -> Range<usize> {
+        let start = match range.start_bound() {
+            Bound::Included(&start) => start,
+            Bound::Excluded(start) => {
+                start.checked_add(1).unwrap_or_else(|| slice_start_index_overflow_fail())
+            }
+            Bound::Unbounded => 0,
+        };
+
+        let len = self.len();
+        let end = match range.end_bound() {
+            Bound::Included(end) => {
+                end.checked_add(1).unwrap_or_else(|| slice_end_index_overflow_fail())
+            }
+            Bound::Excluded(&end) => end,
+            Bound::Unbounded => len,
+        };
+
+        if start > end {
+            slice_index_order_fail(start, end);
+        }
+        if end > len {
+            slice_end_index_len_fail(end, len);
+        }
+
+        Range { start, end }
+    }
+
     /// Returns a raw pointer to the slice's buffer.
     ///
     /// The caller must ensure that the slice outlives the pointer this
@@ -2651,26 +2724,11 @@ impl<T> [T] {
     /// ```
     #[stable(feature = "copy_within", since = "1.37.0")]
     #[track_caller]
-    pub fn copy_within<R: ops::RangeBounds<usize>>(&mut self, src: R, dest: usize)
+    pub fn copy_within<R: RangeBounds<usize>>(&mut self, src: R, dest: usize)
     where
         T: Copy,
     {
-        let src_start = match src.start_bound() {
-            ops::Bound::Included(&n) => n,
-            ops::Bound::Excluded(&n) => {
-                n.checked_add(1).unwrap_or_else(|| slice_index_overflow_fail())
-            }
-            ops::Bound::Unbounded => 0,
-        };
-        let src_end = match src.end_bound() {
-            ops::Bound::Included(&n) => {
-                n.checked_add(1).unwrap_or_else(|| slice_index_overflow_fail())
-            }
-            ops::Bound::Excluded(&n) => n,
-            ops::Bound::Unbounded => self.len(),
-        };
-        assert!(src_start <= src_end, "src end is before src start");
-        assert!(src_end <= self.len(), "src is out of bounds");
+        let Range { start: src_start, end: src_end } = self.check_range(src);
         let count = src_end - src_start;
         assert!(dest <= self.len() - count, "dest is out of bounds");
         // SAFETY: the conditions for `ptr::copy` have all been checked above,
@@ -3259,7 +3317,14 @@ fn slice_index_order_fail(index: usize, end: usize) -> ! {
 #[inline(never)]
 #[cold]
 #[track_caller]
-fn slice_index_overflow_fail() -> ! {
+fn slice_start_index_overflow_fail() -> ! {
+    panic!("attempted to index slice from after maximum usize");
+}
+
+#[inline(never)]
+#[cold]
+#[track_caller]
+fn slice_end_index_overflow_fail() -> ! {
     panic!("attempted to index slice up to maximum usize");
 }
 
@@ -3603,15 +3668,15 @@ unsafe impl<T> SliceIndex<[T]> for ops::RangeInclusive<usize> {
     #[inline]
     fn index(self, slice: &[T]) -> &[T] {
         if *self.end() == usize::MAX {
-            slice_index_overflow_fail();
+            slice_end_index_overflow_fail();
         }
         (*self.start()..self.end() + 1).index(slice)
     }
 
     #[inline]
     fn index_mut(self, slice: &mut [T]) -> &mut [T] {
         if *self.end() == usize::MAX {
-            slice_index_overflow_fail();
+            slice_end_index_overflow_fail();
         }
         (*self.start()..self.end() + 1).index_mut(slice)
     }

library/core/tests/slice.rs

@@ -1795,7 +1795,7 @@ fn test_copy_within() {
 }
 
 #[test]
-#[should_panic(expected = "src is out of bounds")]
+#[should_panic(expected = "range end index 14 out of range for slice of length 13")]
 fn test_copy_within_panics_src_too_long() {
     let mut bytes = *b"Hello, World!";
     // The length is only 13, so 14 is out of bounds.
@@ -1810,7 +1810,7 @@ fn test_copy_within_panics_dest_too_long() {
     bytes.copy_within(0..4, 10);
 }
 #[test]
-#[should_panic(expected = "src end is before src start")]
+#[should_panic(expected = "slice index starts at 2 but ends at 1")]
 fn test_copy_within_panics_src_inverted() {
     let mut bytes = *b"Hello, World!";
     // 2 is greater than 1, so this range is invalid.

src/tools/linkchecker/main.rs

@@ -39,6 +39,7 @@ const LINKCHECK_EXCEPTIONS: &[(&str, &[&str])] = &[
             "#method.sort_by_key",
             "#method.make_ascii_uppercase",
             "#method.make_ascii_lowercase",
+            "#method.get_unchecked_mut",
         ],
     ),
     // These try to link to std::collections, but are defined in alloc