Auto merge of rust-lang#76325 - lzutao:split-core-str, r=Amanieu

Split core/str/mod.rs to smaller files

Note for reviewer:
* I split to multiple commits for easier reviewing, but I could git squash them all to one if requested.
* Recommend pulling this change locally and using advanced git diff viewer or this command:
  ```bash
  git show --reverse --color-moved=dimmed-zebra --color-moved-ws=ignore-all-space master..
  ```

---

I split `core/str/mod.rs` to these modules:

* `converts`: Contains helper functions to convert from bytes to str.
* `error`: For error structs like Utf8Error.
* `iter`: For iterators of many str methods.
* `traits`: For indexing operations and build in traits on str.
* `validations`: For functions validating utf8 --- This name is awkward, maybe utf8.rs is better.

library/core/src/str/converts.rs

@@ -0,0 +1,192 @@
+//! Ways to create a `str` from bytes slice.
+
+use crate::mem;
+
+use super::validations::run_utf8_validation;
+use super::Utf8Error;
+
+/// Converts a slice of bytes to a string slice.
+///
+/// A string slice ([`&str`]) is made of bytes ([`u8`]), and a byte slice
+/// ([`&[u8]`][byteslice]) is made of bytes, so this function converts between
+/// the two. Not all byte slices are valid string slices, however: [`&str`] requires
+/// that it is valid UTF-8. `from_utf8()` checks to ensure that the bytes are valid
+/// UTF-8, and then does the conversion.
+///
+/// [`&str`]: str
+/// [byteslice]: ../../std/primitive.slice.html
+///
+/// If you are sure that the byte slice is valid UTF-8, and you don't want to
+/// incur the overhead of the validity check, there is an unsafe version of
+/// this function, [`from_utf8_unchecked`], which has the same
+/// behavior but skips the check.
+///
+/// If you need a `String` instead of a `&str`, consider
+/// [`String::from_utf8`][string].
+///
+/// [string]: ../../std/string/struct.String.html#method.from_utf8
+///
+/// Because you can stack-allocate a `[u8; N]`, and you can take a
+/// [`&[u8]`][byteslice] of it, this function is one way to have a
+/// stack-allocated string. There is an example of this in the
+/// examples section below.
+///
+/// [byteslice]: ../../std/primitive.slice.html
+///
+/// # Errors
+///
+/// Returns `Err` if the slice is not UTF-8 with a description as to why the
+/// provided slice is not UTF-8.
+///
+/// # Examples
+///
+/// Basic usage:
+///
+/// ```
+/// use std::str;
+///
+/// // some bytes, in a vector
+/// let sparkle_heart = vec![240, 159, 146, 150];
+///
+/// // We know these bytes are valid, so just use `unwrap()`.
+/// let sparkle_heart = str::from_utf8(&sparkle_heart).unwrap();
+///
+/// assert_eq!("💖", sparkle_heart);
+/// ```
+///
+/// Incorrect bytes:
+///
+/// ```
+/// use std::str;
+///
+/// // some invalid bytes, in a vector
+/// let sparkle_heart = vec![0, 159, 146, 150];
+///
+/// assert!(str::from_utf8(&sparkle_heart).is_err());
+/// ```
+///
+/// See the docs for [`Utf8Error`] for more details on the kinds of
+/// errors that can be returned.
+///
+/// A "stack allocated string":
+///
+/// ```
+/// use std::str;
+///
+/// // some bytes, in a stack-allocated array
+/// let sparkle_heart = [240, 159, 146, 150];
+///
+/// // We know these bytes are valid, so just use `unwrap()`.
+/// let sparkle_heart = str::from_utf8(&sparkle_heart).unwrap();
+///
+/// assert_eq!("💖", sparkle_heart);
+/// ```
+#[stable(feature = "rust1", since = "1.0.0")]
+pub fn from_utf8(v: &[u8]) -> Result<&str, Utf8Error> {
+    run_utf8_validation(v)?;
+    // SAFETY: Just ran validation.
+    Ok(unsafe { from_utf8_unchecked(v) })
+}
+
+/// Converts a mutable slice of bytes to a mutable string slice.
+///
+/// # Examples
+///
+/// Basic usage:
+///
+/// ```
+/// use std::str;
+///
+/// // "Hello, Rust!" as a mutable vector
+/// let mut hellorust = vec![72, 101, 108, 108, 111, 44, 32, 82, 117, 115, 116, 33];
+///
+/// // As we know these bytes are valid, we can use `unwrap()`
+/// let outstr = str::from_utf8_mut(&mut hellorust).unwrap();
+///
+/// assert_eq!("Hello, Rust!", outstr);
+/// ```
+///
+/// Incorrect bytes:
+///
+/// ```
+/// use std::str;
+///
+/// // Some invalid bytes in a mutable vector
+/// let mut invalid = vec![128, 223];
+///
+/// assert!(str::from_utf8_mut(&mut invalid).is_err());
+/// ```
+/// See the docs for [`Utf8Error`] for more details on the kinds of
+/// errors that can be returned.
+#[stable(feature = "str_mut_extras", since = "1.20.0")]
+pub fn from_utf8_mut(v: &mut [u8]) -> Result<&mut str, Utf8Error> {
+    run_utf8_validation(v)?;
+    // SAFETY: Just ran validation.
+    Ok(unsafe { from_utf8_unchecked_mut(v) })
+}
+
+/// Converts a slice of bytes to a string slice without checking
+/// that the string contains valid UTF-8.
+///
+/// See the safe version, [`from_utf8`], for more information.
+///
+/// # Safety
+///
+/// This function is unsafe because it does not check that the bytes passed to
+/// it are valid UTF-8. If this constraint is violated, undefined behavior
+/// results, as the rest of Rust assumes that [`&str`]s are valid UTF-8.
+///
+/// [`&str`]: str
+///
+/// # Examples
+///
+/// Basic usage:
+///
+/// ```
+/// use std::str;
+///
+/// // some bytes, in a vector
+/// let sparkle_heart = vec![240, 159, 146, 150];
+///
+/// let sparkle_heart = unsafe {
+///     str::from_utf8_unchecked(&sparkle_heart)
+/// };
+///
+/// assert_eq!("💖", sparkle_heart);
+/// ```
+#[inline]
+#[stable(feature = "rust1", since = "1.0.0")]
+#[rustc_const_unstable(feature = "const_str_from_utf8_unchecked", issue = "75196")]
+#[allow_internal_unstable(const_fn_transmute)]
+pub const unsafe fn from_utf8_unchecked(v: &[u8]) -> &str {
+    // SAFETY: the caller must guarantee that the bytes `v` are valid UTF-8.
+    // Also relies on `&str` and `&[u8]` having the same layout.
+    unsafe { mem::transmute(v) }
+}
+
+/// Converts a slice of bytes to a string slice without checking
+/// that the string contains valid UTF-8; mutable version.
+///
+/// See the immutable version, [`from_utf8_unchecked()`] for more information.
+///
+/// # Examples
+///
+/// Basic usage:
+///
+/// ```
+/// use std::str;
+///
+/// let mut heart = vec![240, 159, 146, 150];
+/// let heart = unsafe { str::from_utf8_unchecked_mut(&mut heart) };
+///
+/// assert_eq!("💖", heart);
+/// ```
+#[inline]
+#[stable(feature = "str_mut_extras", since = "1.20.0")]
+pub unsafe fn from_utf8_unchecked_mut(v: &mut [u8]) -> &mut str {
+    // SAFETY: the caller must guarantee that the bytes `v`
+    // are valid UTF-8, thus the cast to `*mut str` is safe.
+    // Also, the pointer dereference is safe because that pointer
+    // comes from a reference which is guaranteed to be valid for writes.
+    unsafe { &mut *(v as *mut [u8] as *mut str) }
+}

library/core/src/str/error.rs

@@ -0,0 +1,129 @@
+//! Defines utf8 error type.
+
+use crate::fmt;
+
+/// Errors which can occur when attempting to interpret a sequence of [`u8`]
+/// as a string.
+///
+/// As such, the `from_utf8` family of functions and methods for both [`String`]s
+/// and [`&str`]s make use of this error, for example.
+///
+/// [`String`]: ../../std/string/struct.String.html#method.from_utf8
+/// [`&str`]: super::from_utf8
+///
+/// # Examples
+///
+/// This error type’s methods can be used to create functionality
+/// similar to `String::from_utf8_lossy` without allocating heap memory:
+///
+/// ```
+/// fn from_utf8_lossy<F>(mut input: &[u8], mut push: F) where F: FnMut(&str) {
+///     loop {
+///         match std::str::from_utf8(input) {
+///             Ok(valid) => {
+///                 push(valid);
+///                 break
+///             }
+///             Err(error) => {
+///                 let (valid, after_valid) = input.split_at(error.valid_up_to());
+///                 unsafe {
+///                     push(std::str::from_utf8_unchecked(valid))
+///                 }
+///                 push("\u{FFFD}");
+///
+///                 if let Some(invalid_sequence_length) = error.error_len() {
+///                     input = &after_valid[invalid_sequence_length..]
+///                 } else {
+///                     break
+///                 }
+///             }
+///         }
+///     }
+/// }
+/// ```
+#[derive(Copy, Eq, PartialEq, Clone, Debug)]
+#[stable(feature = "rust1", since = "1.0.0")]
+pub struct Utf8Error {
+    pub(super) valid_up_to: usize,
+    pub(super) error_len: Option<u8>,
+}
+
+impl Utf8Error {
+    /// Returns the index in the given string up to which valid UTF-8 was
+    /// verified.
+    ///
+    /// It is the maximum index such that `from_utf8(&input[..index])`
+    /// would return `Ok(_)`.
+    ///
+    /// # Examples
+    ///
+    /// Basic usage:
+    ///
+    /// ```
+    /// use std::str;
+    ///
+    /// // some invalid bytes, in a vector
+    /// let sparkle_heart = vec![0, 159, 146, 150];
+    ///
+    /// // std::str::from_utf8 returns a Utf8Error
+    /// let error = str::from_utf8(&sparkle_heart).unwrap_err();
+    ///
+    /// // the second byte is invalid here
+    /// assert_eq!(1, error.valid_up_to());
+    /// ```
+    #[stable(feature = "utf8_error", since = "1.5.0")]
+    pub fn valid_up_to(&self) -> usize {
+        self.valid_up_to
+    }
+
+    /// Provides more information about the failure:
+    ///
+    /// * `None`: the end of the input was reached unexpectedly.
+    ///   `self.valid_up_to()` is 1 to 3 bytes from the end of the input.
+    ///   If a byte stream (such as a file or a network socket) is being decoded incrementally,
+    ///   this could be a valid `char` whose UTF-8 byte sequence is spanning multiple chunks.
+    ///
+    /// * `Some(len)`: an unexpected byte was encountered.
+    ///   The length provided is that of the invalid byte sequence
+    ///   that starts at the index given by `valid_up_to()`.
+    ///   Decoding should resume after that sequence
+    ///   (after inserting a [`U+FFFD REPLACEMENT CHARACTER`][U+FFFD]) in case of
+    ///   lossy decoding.
+    ///
+    /// [U+FFFD]: ../../std/char/constant.REPLACEMENT_CHARACTER.html
+    #[stable(feature = "utf8_error_error_len", since = "1.20.0")]
+    pub fn error_len(&self) -> Option<usize> {
+        self.error_len.map(|len| len as usize)
+    }
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl fmt::Display for Utf8Error {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        if let Some(error_len) = self.error_len {
+            write!(
+                f,
+                "invalid utf-8 sequence of {} bytes from index {}",
+                error_len, self.valid_up_to
+            )
+        } else {
+            write!(f, "incomplete utf-8 byte sequence from index {}", self.valid_up_to)
+        }
+    }
+}
+
+/// An error returned when parsing a `bool` using [`from_str`] fails
+///
+/// [`from_str`]: super::FromStr::from_str
+#[derive(Debug, Clone, PartialEq, Eq)]
+#[stable(feature = "rust1", since = "1.0.0")]
+pub struct ParseBoolError {
+    pub(super) _priv: (),
+}
+
+#[stable(feature = "rust1", since = "1.0.0")]
+impl fmt::Display for ParseBoolError {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        "provided string was not `true` or `false`".fmt(f)
+    }
+}