Auto merge of #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.
This commit is contained in:
bors
commit
9bb55dc864
192
library/core/src/str/converts.rs
Normal file
192
library/core/src/str/converts.rs
Normal file
@ -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) }
|
||||
}
|
||||
129
library/core/src/str/error.rs
Normal file
129
library/core/src/str/error.rs
Normal file
@ -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)
|
||||
}
|
||||
}
|
||||
1255
library/core/src/str/iter.rs
Normal file
1255
library/core/src/str/iter.rs
Normal file
File diff suppressed because it is too large
Load Diff
@ -1,7 +1,9 @@
|
||||
use crate::char;
|
||||
use crate::fmt::{self, Write};
|
||||
use crate::mem;
|
||||
use crate::str as core_str;
|
||||
|
||||
use super::from_utf8_unchecked;
|
||||
use super::validations::utf8_char_width;
|
||||
|
||||
/// Lossy UTF-8 string.
|
||||
#[unstable(feature = "str_internals", issue = "none")]
|
||||
@ -66,14 +68,14 @@ impl<'a> Iterator for Utf8LossyChunksIter<'a> {
|
||||
|
||||
if byte < 128 {
|
||||
} else {
|
||||
let w = core_str::utf8_char_width(byte);
|
||||
let w = utf8_char_width(byte);
|
||||
|
||||
macro_rules! error {
|
||||
() => {{
|
||||
// SAFETY: We have checked up to `i` that source is valid UTF-8.
|
||||
unsafe {
|
||||
let r = Utf8LossyChunk {
|
||||
valid: core_str::from_utf8_unchecked(&self.source[0..i_]),
|
||||
valid: from_utf8_unchecked(&self.source[0..i_]),
|
||||
broken: &self.source[i_..i],
|
||||
};
|
||||
self.source = &self.source[i..];
|
||||
@ -133,7 +135,7 @@ impl<'a> Iterator for Utf8LossyChunksIter<'a> {
|
||||
|
||||
let r = Utf8LossyChunk {
|
||||
// SAFETY: We have checked that the entire source is valid UTF-8.
|
||||
valid: unsafe { core_str::from_utf8_unchecked(self.source) },
|
||||
valid: unsafe { from_utf8_unchecked(self.source) },
|
||||
broken: &[],
|
||||
};
|
||||
self.source = &[];
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
597
library/core/src/str/traits.rs
Normal file
597
library/core/src/str/traits.rs
Normal file
@ -0,0 +1,597 @@
|
||||
//! Trait implementations for `str`.
|
||||
|
||||
use crate::cmp::Ordering;
|
||||
use crate::ops;
|
||||
use crate::ptr;
|
||||
use crate::slice::SliceIndex;
|
||||
|
||||
use super::ParseBoolError;
|
||||
|
||||
/// Implements ordering of strings.
|
||||
///
|
||||
/// Strings are ordered lexicographically by their byte values. This orders Unicode code
|
||||
/// points based on their positions in the code charts. This is not necessarily the same as
|
||||
/// "alphabetical" order, which varies by language and locale. Sorting strings according to
|
||||
/// culturally-accepted standards requires locale-specific data that is outside the scope of
|
||||
/// the `str` type.
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
impl Ord for str {
|
||||
#[inline]
|
||||
fn cmp(&self, other: &str) -> Ordering {
|
||||
self.as_bytes().cmp(other.as_bytes())
|
||||
}
|
||||
}
|
||||
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
impl PartialEq for str {
|
||||
#[inline]
|
||||
fn eq(&self, other: &str) -> bool {
|
||||
self.as_bytes() == other.as_bytes()
|
||||
}
|
||||
#[inline]
|
||||
fn ne(&self, other: &str) -> bool {
|
||||
!(*self).eq(other)
|
||||
}
|
||||
}
|
||||
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
impl Eq for str {}
|
||||
|
||||
/// Implements comparison operations on strings.
|
||||
///
|
||||
/// Strings are compared lexicographically by their byte values. This compares Unicode code
|
||||
/// points based on their positions in the code charts. This is not necessarily the same as
|
||||
/// "alphabetical" order, which varies by language and locale. Comparing strings according to
|
||||
/// culturally-accepted standards requires locale-specific data that is outside the scope of
|
||||
/// the `str` type.
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
impl PartialOrd for str {
|
||||
#[inline]
|
||||
fn partial_cmp(&self, other: &str) -> Option<Ordering> {
|
||||
Some(self.cmp(other))
|
||||
}
|
||||
}
|
||||
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
impl<I> ops::Index<I> for str
|
||||
where
|
||||
I: SliceIndex<str>,
|
||||
{
|
||||
type Output = I::Output;
|
||||
|
||||
#[inline]
|
||||
fn index(&self, index: I) -> &I::Output {
|
||||
index.index(self)
|
||||
}
|
||||
}
|
||||
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
impl<I> ops::IndexMut<I> for str
|
||||
where
|
||||
I: SliceIndex<str>,
|
||||
{
|
||||
#[inline]
|
||||
fn index_mut(&mut self, index: I) -> &mut I::Output {
|
||||
index.index_mut(self)
|
||||
}
|
||||
}
|
||||
|
||||
#[inline(never)]
|
||||
#[cold]
|
||||
#[track_caller]
|
||||
fn str_index_overflow_fail() -> ! {
|
||||
panic!("attempted to index str up to maximum usize");
|
||||
}
|
||||
|
||||
/// Implements substring slicing with syntax `&self[..]` or `&mut self[..]`.
|
||||
///
|
||||
/// Returns a slice of the whole string, i.e., returns `&self` or `&mut
|
||||
/// self`. Equivalent to `&self[0 .. len]` or `&mut self[0 .. len]`. Unlike
|
||||
/// other indexing operations, this can never panic.
|
||||
///
|
||||
/// This operation is `O(1)`.
|
||||
///
|
||||
/// Prior to 1.20.0, these indexing operations were still supported by
|
||||
/// direct implementation of `Index` and `IndexMut`.
|
||||
///
|
||||
/// Equivalent to `&self[0 .. len]` or `&mut self[0 .. len]`.
|
||||
#[stable(feature = "str_checked_slicing", since = "1.20.0")]
|
||||
unsafe impl SliceIndex<str> for ops::RangeFull {
|
||||
type Output = str;
|
||||
#[inline]
|
||||
fn get(self, slice: &str) -> Option<&Self::Output> {
|
||||
Some(slice)
|
||||
}
|
||||
#[inline]
|
||||
fn get_mut(self, slice: &mut str) -> Option<&mut Self::Output> {
|
||||
Some(slice)
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked(self, slice: *const str) -> *const Self::Output {
|
||||
slice
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked_mut(self, slice: *mut str) -> *mut Self::Output {
|
||||
slice
|
||||
}
|
||||
#[inline]
|
||||
fn index(self, slice: &str) -> &Self::Output {
|
||||
slice
|
||||
}
|
||||
#[inline]
|
||||
fn index_mut(self, slice: &mut str) -> &mut Self::Output {
|
||||
slice
|
||||
}
|
||||
}
|
||||
|
||||
/// Implements substring slicing with syntax `&self[begin .. end]` or `&mut
|
||||
/// self[begin .. end]`.
|
||||
///
|
||||
/// Returns a slice of the given string from the byte range
|
||||
/// [`begin`, `end`).
|
||||
///
|
||||
/// This operation is `O(1)`.
|
||||
///
|
||||
/// Prior to 1.20.0, these indexing operations were still supported by
|
||||
/// direct implementation of `Index` and `IndexMut`.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `begin` or `end` does not point to the starting byte offset of
|
||||
/// a character (as defined by `is_char_boundary`), if `begin > end`, or if
|
||||
/// `end > len`.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// let s = "Löwe 老虎 Léopard";
|
||||
/// assert_eq!(&s[0 .. 1], "L");
|
||||
///
|
||||
/// assert_eq!(&s[1 .. 9], "öwe 老");
|
||||
///
|
||||
/// // these will panic:
|
||||
/// // byte 2 lies within `ö`:
|
||||
/// // &s[2 ..3];
|
||||
///
|
||||
/// // byte 8 lies within `老`
|
||||
/// // &s[1 .. 8];
|
||||
///
|
||||
/// // byte 100 is outside the string
|
||||
/// // &s[3 .. 100];
|
||||
/// ```
|
||||
#[stable(feature = "str_checked_slicing", since = "1.20.0")]
|
||||
unsafe impl SliceIndex<str> for ops::Range<usize> {
|
||||
type Output = str;
|
||||
#[inline]
|
||||
fn get(self, slice: &str) -> Option<&Self::Output> {
|
||||
if self.start <= self.end
|
||||
&& slice.is_char_boundary(self.start)
|
||||
&& slice.is_char_boundary(self.end)
|
||||
{
|
||||
// SAFETY: just checked that `start` and `end` are on a char boundary,
|
||||
// and we are passing in a safe reference, so the return value will also be one.
|
||||
// We also checked char boundaries, so this is valid UTF-8.
|
||||
Some(unsafe { &*self.get_unchecked(slice) })
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
fn get_mut(self, slice: &mut str) -> Option<&mut Self::Output> {
|
||||
if self.start <= self.end
|
||||
&& slice.is_char_boundary(self.start)
|
||||
&& slice.is_char_boundary(self.end)
|
||||
{
|
||||
// SAFETY: just checked that `start` and `end` are on a char boundary.
|
||||
// We know the pointer is unique because we got it from `slice`.
|
||||
Some(unsafe { &mut *self.get_unchecked_mut(slice) })
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked(self, slice: *const str) -> *const Self::Output {
|
||||
let slice = slice as *const [u8];
|
||||
// SAFETY: the caller guarantees that `self` is in bounds of `slice`
|
||||
// which satisfies all the conditions for `add`.
|
||||
let ptr = unsafe { slice.as_ptr().add(self.start) };
|
||||
let len = self.end - self.start;
|
||||
ptr::slice_from_raw_parts(ptr, len) as *const str
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked_mut(self, slice: *mut str) -> *mut Self::Output {
|
||||
let slice = slice as *mut [u8];
|
||||
// SAFETY: see comments for `get_unchecked`.
|
||||
let ptr = unsafe { slice.as_mut_ptr().add(self.start) };
|
||||
let len = self.end - self.start;
|
||||
ptr::slice_from_raw_parts_mut(ptr, len) as *mut str
|
||||
}
|
||||
#[inline]
|
||||
fn index(self, slice: &str) -> &Self::Output {
|
||||
let (start, end) = (self.start, self.end);
|
||||
match self.get(slice) {
|
||||
Some(s) => s,
|
||||
None => super::slice_error_fail(slice, start, end),
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
fn index_mut(self, slice: &mut str) -> &mut Self::Output {
|
||||
// is_char_boundary checks that the index is in [0, .len()]
|
||||
// cannot reuse `get` as above, because of NLL trouble
|
||||
if self.start <= self.end
|
||||
&& slice.is_char_boundary(self.start)
|
||||
&& slice.is_char_boundary(self.end)
|
||||
{
|
||||
// SAFETY: just checked that `start` and `end` are on a char boundary,
|
||||
// and we are passing in a safe reference, so the return value will also be one.
|
||||
unsafe { &mut *self.get_unchecked_mut(slice) }
|
||||
} else {
|
||||
super::slice_error_fail(slice, self.start, self.end)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Implements substring slicing with syntax `&self[.. end]` or `&mut
|
||||
/// self[.. end]`.
|
||||
///
|
||||
/// Returns a slice of the given string from the byte range [`0`, `end`).
|
||||
/// Equivalent to `&self[0 .. end]` or `&mut self[0 .. end]`.
|
||||
///
|
||||
/// This operation is `O(1)`.
|
||||
///
|
||||
/// Prior to 1.20.0, these indexing operations were still supported by
|
||||
/// direct implementation of `Index` and `IndexMut`.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `end` does not point to the starting byte offset of a
|
||||
/// character (as defined by `is_char_boundary`), or if `end > len`.
|
||||
#[stable(feature = "str_checked_slicing", since = "1.20.0")]
|
||||
unsafe impl SliceIndex<str> for ops::RangeTo<usize> {
|
||||
type Output = str;
|
||||
#[inline]
|
||||
fn get(self, slice: &str) -> Option<&Self::Output> {
|
||||
if slice.is_char_boundary(self.end) {
|
||||
// SAFETY: just checked that `end` is on a char boundary,
|
||||
// and we are passing in a safe reference, so the return value will also be one.
|
||||
Some(unsafe { &*self.get_unchecked(slice) })
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
fn get_mut(self, slice: &mut str) -> Option<&mut Self::Output> {
|
||||
if slice.is_char_boundary(self.end) {
|
||||
// SAFETY: just checked that `end` is on a char boundary,
|
||||
// and we are passing in a safe reference, so the return value will also be one.
|
||||
Some(unsafe { &mut *self.get_unchecked_mut(slice) })
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked(self, slice: *const str) -> *const Self::Output {
|
||||
let slice = slice as *const [u8];
|
||||
let ptr = slice.as_ptr();
|
||||
ptr::slice_from_raw_parts(ptr, self.end) as *const str
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked_mut(self, slice: *mut str) -> *mut Self::Output {
|
||||
let slice = slice as *mut [u8];
|
||||
let ptr = slice.as_mut_ptr();
|
||||
ptr::slice_from_raw_parts_mut(ptr, self.end) as *mut str
|
||||
}
|
||||
#[inline]
|
||||
fn index(self, slice: &str) -> &Self::Output {
|
||||
let end = self.end;
|
||||
match self.get(slice) {
|
||||
Some(s) => s,
|
||||
None => super::slice_error_fail(slice, 0, end),
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
fn index_mut(self, slice: &mut str) -> &mut Self::Output {
|
||||
if slice.is_char_boundary(self.end) {
|
||||
// SAFETY: just checked that `end` is on a char boundary,
|
||||
// and we are passing in a safe reference, so the return value will also be one.
|
||||
unsafe { &mut *self.get_unchecked_mut(slice) }
|
||||
} else {
|
||||
super::slice_error_fail(slice, 0, self.end)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Implements substring slicing with syntax `&self[begin ..]` or `&mut
|
||||
/// self[begin ..]`.
|
||||
///
|
||||
/// Returns a slice of the given string from the byte range [`begin`,
|
||||
/// `len`). Equivalent to `&self[begin .. len]` or `&mut self[begin ..
|
||||
/// len]`.
|
||||
///
|
||||
/// This operation is `O(1)`.
|
||||
///
|
||||
/// Prior to 1.20.0, these indexing operations were still supported by
|
||||
/// direct implementation of `Index` and `IndexMut`.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `begin` does not point to the starting byte offset of
|
||||
/// a character (as defined by `is_char_boundary`), or if `begin > len`.
|
||||
#[stable(feature = "str_checked_slicing", since = "1.20.0")]
|
||||
unsafe impl SliceIndex<str> for ops::RangeFrom<usize> {
|
||||
type Output = str;
|
||||
#[inline]
|
||||
fn get(self, slice: &str) -> Option<&Self::Output> {
|
||||
if slice.is_char_boundary(self.start) {
|
||||
// SAFETY: just checked that `start` is on a char boundary,
|
||||
// and we are passing in a safe reference, so the return value will also be one.
|
||||
Some(unsafe { &*self.get_unchecked(slice) })
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
fn get_mut(self, slice: &mut str) -> Option<&mut Self::Output> {
|
||||
if slice.is_char_boundary(self.start) {
|
||||
// SAFETY: just checked that `start` is on a char boundary,
|
||||
// and we are passing in a safe reference, so the return value will also be one.
|
||||
Some(unsafe { &mut *self.get_unchecked_mut(slice) })
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked(self, slice: *const str) -> *const Self::Output {
|
||||
let slice = slice as *const [u8];
|
||||
// SAFETY: the caller guarantees that `self` is in bounds of `slice`
|
||||
// which satisfies all the conditions for `add`.
|
||||
let ptr = unsafe { slice.as_ptr().add(self.start) };
|
||||
let len = slice.len() - self.start;
|
||||
ptr::slice_from_raw_parts(ptr, len) as *const str
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked_mut(self, slice: *mut str) -> *mut Self::Output {
|
||||
let slice = slice as *mut [u8];
|
||||
// SAFETY: identical to `get_unchecked`.
|
||||
let ptr = unsafe { slice.as_mut_ptr().add(self.start) };
|
||||
let len = slice.len() - self.start;
|
||||
ptr::slice_from_raw_parts_mut(ptr, len) as *mut str
|
||||
}
|
||||
#[inline]
|
||||
fn index(self, slice: &str) -> &Self::Output {
|
||||
let (start, end) = (self.start, slice.len());
|
||||
match self.get(slice) {
|
||||
Some(s) => s,
|
||||
None => super::slice_error_fail(slice, start, end),
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
fn index_mut(self, slice: &mut str) -> &mut Self::Output {
|
||||
if slice.is_char_boundary(self.start) {
|
||||
// SAFETY: just checked that `start` is on a char boundary,
|
||||
// and we are passing in a safe reference, so the return value will also be one.
|
||||
unsafe { &mut *self.get_unchecked_mut(slice) }
|
||||
} else {
|
||||
super::slice_error_fail(slice, self.start, slice.len())
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Implements substring slicing with syntax `&self[begin ..= end]` or `&mut
|
||||
/// self[begin ..= end]`.
|
||||
///
|
||||
/// Returns a slice of the given string from the byte range
|
||||
/// [`begin`, `end`]. Equivalent to `&self [begin .. end + 1]` or `&mut
|
||||
/// self[begin .. end + 1]`, except if `end` has the maximum value for
|
||||
/// `usize`.
|
||||
///
|
||||
/// This operation is `O(1)`.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `begin` does not point to the starting byte offset of
|
||||
/// a character (as defined by `is_char_boundary`), if `end` does not point
|
||||
/// to the ending byte offset of a character (`end + 1` is either a starting
|
||||
/// byte offset or equal to `len`), if `begin > end`, or if `end >= len`.
|
||||
#[stable(feature = "inclusive_range", since = "1.26.0")]
|
||||
unsafe impl SliceIndex<str> for ops::RangeInclusive<usize> {
|
||||
type Output = str;
|
||||
#[inline]
|
||||
fn get(self, slice: &str) -> Option<&Self::Output> {
|
||||
if *self.end() == usize::MAX { None } else { (*self.start()..self.end() + 1).get(slice) }
|
||||
}
|
||||
#[inline]
|
||||
fn get_mut(self, slice: &mut str) -> Option<&mut Self::Output> {
|
||||
if *self.end() == usize::MAX {
|
||||
None
|
||||
} else {
|
||||
(*self.start()..self.end() + 1).get_mut(slice)
|
||||
}
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked(self, slice: *const str) -> *const Self::Output {
|
||||
// SAFETY: the caller must uphold the safety contract for `get_unchecked`.
|
||||
unsafe { (*self.start()..self.end() + 1).get_unchecked(slice) }
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked_mut(self, slice: *mut str) -> *mut Self::Output {
|
||||
// SAFETY: the caller must uphold the safety contract for `get_unchecked_mut`.
|
||||
unsafe { (*self.start()..self.end() + 1).get_unchecked_mut(slice) }
|
||||
}
|
||||
#[inline]
|
||||
fn index(self, slice: &str) -> &Self::Output {
|
||||
if *self.end() == usize::MAX {
|
||||
str_index_overflow_fail();
|
||||
}
|
||||
(*self.start()..self.end() + 1).index(slice)
|
||||
}
|
||||
#[inline]
|
||||
fn index_mut(self, slice: &mut str) -> &mut Self::Output {
|
||||
if *self.end() == usize::MAX {
|
||||
str_index_overflow_fail();
|
||||
}
|
||||
(*self.start()..self.end() + 1).index_mut(slice)
|
||||
}
|
||||
}
|
||||
|
||||
/// Implements substring slicing with syntax `&self[..= end]` or `&mut
|
||||
/// self[..= end]`.
|
||||
///
|
||||
/// Returns a slice of the given string from the byte range [0, `end`].
|
||||
/// Equivalent to `&self [0 .. end + 1]`, except if `end` has the maximum
|
||||
/// value for `usize`.
|
||||
///
|
||||
/// This operation is `O(1)`.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `end` does not point to the ending byte offset of a character
|
||||
/// (`end + 1` is either a starting byte offset as defined by
|
||||
/// `is_char_boundary`, or equal to `len`), or if `end >= len`.
|
||||
#[stable(feature = "inclusive_range", since = "1.26.0")]
|
||||
unsafe impl SliceIndex<str> for ops::RangeToInclusive<usize> {
|
||||
type Output = str;
|
||||
#[inline]
|
||||
fn get(self, slice: &str) -> Option<&Self::Output> {
|
||||
if self.end == usize::MAX { None } else { (..self.end + 1).get(slice) }
|
||||
}
|
||||
#[inline]
|
||||
fn get_mut(self, slice: &mut str) -> Option<&mut Self::Output> {
|
||||
if self.end == usize::MAX { None } else { (..self.end + 1).get_mut(slice) }
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked(self, slice: *const str) -> *const Self::Output {
|
||||
// SAFETY: the caller must uphold the safety contract for `get_unchecked`.
|
||||
unsafe { (..self.end + 1).get_unchecked(slice) }
|
||||
}
|
||||
#[inline]
|
||||
unsafe fn get_unchecked_mut(self, slice: *mut str) -> *mut Self::Output {
|
||||
// SAFETY: the caller must uphold the safety contract for `get_unchecked_mut`.
|
||||
unsafe { (..self.end + 1).get_unchecked_mut(slice) }
|
||||
}
|
||||
#[inline]
|
||||
fn index(self, slice: &str) -> &Self::Output {
|
||||
if self.end == usize::MAX {
|
||||
str_index_overflow_fail();
|
||||
}
|
||||
(..self.end + 1).index(slice)
|
||||
}
|
||||
#[inline]
|
||||
fn index_mut(self, slice: &mut str) -> &mut Self::Output {
|
||||
if self.end == usize::MAX {
|
||||
str_index_overflow_fail();
|
||||
}
|
||||
(..self.end + 1).index_mut(slice)
|
||||
}
|
||||
}
|
||||
|
||||
/// Parse a value from a string
|
||||
///
|
||||
/// `FromStr`'s [`from_str`] method is often used implicitly, through
|
||||
/// [`str`]'s [`parse`] method. See [`parse`]'s documentation for examples.
|
||||
///
|
||||
/// [`from_str`]: FromStr::from_str
|
||||
/// [`parse`]: str::parse
|
||||
///
|
||||
/// `FromStr` does not have a lifetime parameter, and so you can only parse types
|
||||
/// that do not contain a lifetime parameter themselves. In other words, you can
|
||||
/// parse an `i32` with `FromStr`, but not a `&i32`. You can parse a struct that
|
||||
/// contains an `i32`, but not one that contains an `&i32`.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// Basic implementation of `FromStr` on an example `Point` type:
|
||||
///
|
||||
/// ```
|
||||
/// use std::str::FromStr;
|
||||
/// use std::num::ParseIntError;
|
||||
///
|
||||
/// #[derive(Debug, PartialEq)]
|
||||
/// struct Point {
|
||||
/// x: i32,
|
||||
/// y: i32
|
||||
/// }
|
||||
///
|
||||
/// impl FromStr for Point {
|
||||
/// type Err = ParseIntError;
|
||||
///
|
||||
/// fn from_str(s: &str) -> Result<Self, Self::Err> {
|
||||
/// let coords: Vec<&str> = s.trim_matches(|p| p == '(' || p == ')' )
|
||||
/// .split(',')
|
||||
/// .collect();
|
||||
///
|
||||
/// let x_fromstr = coords[0].parse::<i32>()?;
|
||||
/// let y_fromstr = coords[1].parse::<i32>()?;
|
||||
///
|
||||
/// Ok(Point { x: x_fromstr, y: y_fromstr })
|
||||
/// }
|
||||
/// }
|
||||
///
|
||||
/// let p = Point::from_str("(1,2)");
|
||||
/// assert_eq!(p.unwrap(), Point{ x: 1, y: 2} )
|
||||
/// ```
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
pub trait FromStr: Sized {
|
||||
/// The associated error which can be returned from parsing.
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
type Err;
|
||||
|
||||
/// Parses a string `s` to return a value of this type.
|
||||
///
|
||||
/// If parsing succeeds, return the value inside [`Ok`], otherwise
|
||||
/// when the string is ill-formatted return an error specific to the
|
||||
/// inside [`Err`]. The error type is specific to implementation of the trait.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// Basic usage with [`i32`][ithirtytwo], a type that implements `FromStr`:
|
||||
///
|
||||
/// [ithirtytwo]: ../../std/primitive.i32.html
|
||||
///
|
||||
/// ```
|
||||
/// use std::str::FromStr;
|
||||
///
|
||||
/// let s = "5";
|
||||
/// let x = i32::from_str(s).unwrap();
|
||||
///
|
||||
/// assert_eq!(5, x);
|
||||
/// ```
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
fn from_str(s: &str) -> Result<Self, Self::Err>;
|
||||
}
|
||||
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
impl FromStr for bool {
|
||||
type Err = ParseBoolError;
|
||||
|
||||
/// Parse a `bool` from a string.
|
||||
///
|
||||
/// Yields a `Result<bool, ParseBoolError>`, because `s` may or may not
|
||||
/// actually be parseable.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use std::str::FromStr;
|
||||
///
|
||||
/// assert_eq!(FromStr::from_str("true"), Ok(true));
|
||||
/// assert_eq!(FromStr::from_str("false"), Ok(false));
|
||||
/// assert!(<bool as FromStr>::from_str("not even a boolean").is_err());
|
||||
/// ```
|
||||
///
|
||||
/// Note, in many cases, the `.parse()` method on `str` is more proper.
|
||||
///
|
||||
/// ```
|
||||
/// assert_eq!("true".parse(), Ok(true));
|
||||
/// assert_eq!("false".parse(), Ok(false));
|
||||
/// assert!("not even a boolean".parse::<bool>().is_err());
|
||||
/// ```
|
||||
#[inline]
|
||||
fn from_str(s: &str) -> Result<bool, ParseBoolError> {
|
||||
match s {
|
||||
"true" => Ok(true),
|
||||
"false" => Ok(false),
|
||||
_ => Err(ParseBoolError { _priv: () }),
|
||||
}
|
||||
}
|
||||
}
|
||||
275
library/core/src/str/validations.rs
Normal file
275
library/core/src/str/validations.rs
Normal file
@ -0,0 +1,275 @@
|
||||
//! Operations related to UTF-8 validation.
|
||||
|
||||
use crate::mem;
|
||||
|
||||
use super::Utf8Error;
|
||||
|
||||
/// Returns the initial codepoint accumulator for the first byte.
|
||||
/// The first byte is special, only want bottom 5 bits for width 2, 4 bits
|
||||
/// for width 3, and 3 bits for width 4.
|
||||
#[inline]
|
||||
fn utf8_first_byte(byte: u8, width: u32) -> u32 {
|
||||
(byte & (0x7F >> width)) as u32
|
||||
}
|
||||
|
||||
/// Returns the value of `ch` updated with continuation byte `byte`.
|
||||
#[inline]
|
||||
fn utf8_acc_cont_byte(ch: u32, byte: u8) -> u32 {
|
||||
(ch << 6) | (byte & CONT_MASK) as u32
|
||||
}
|
||||
|
||||
/// Checks whether the byte is a UTF-8 continuation byte (i.e., starts with the
|
||||
/// bits `10`).
|
||||
#[inline]
|
||||
pub(super) fn utf8_is_cont_byte(byte: u8) -> bool {
|
||||
(byte & !CONT_MASK) == TAG_CONT_U8
|
||||
}
|
||||
|
||||
#[inline]
|
||||
fn unwrap_or_0(opt: Option<&u8>) -> u8 {
|
||||
match opt {
|
||||
Some(&byte) => byte,
|
||||
None => 0,
|
||||
}
|
||||
}
|
||||
|
||||
/// Reads the next code point out of a byte iterator (assuming a
|
||||
/// UTF-8-like encoding).
|
||||
#[unstable(feature = "str_internals", issue = "none")]
|
||||
#[inline]
|
||||
pub fn next_code_point<'a, I: Iterator<Item = &'a u8>>(bytes: &mut I) -> Option<u32> {
|
||||
// Decode UTF-8
|
||||
let x = *bytes.next()?;
|
||||
if x < 128 {
|
||||
return Some(x as u32);
|
||||
}
|
||||
|
||||
// Multibyte case follows
|
||||
// Decode from a byte combination out of: [[[x y] z] w]
|
||||
// NOTE: Performance is sensitive to the exact formulation here
|
||||
let init = utf8_first_byte(x, 2);
|
||||
let y = unwrap_or_0(bytes.next());
|
||||
let mut ch = utf8_acc_cont_byte(init, y);
|
||||
if x >= 0xE0 {
|
||||
// [[x y z] w] case
|
||||
// 5th bit in 0xE0 .. 0xEF is always clear, so `init` is still valid
|
||||
let z = unwrap_or_0(bytes.next());
|
||||
let y_z = utf8_acc_cont_byte((y & CONT_MASK) as u32, z);
|
||||
ch = init << 12 | y_z;
|
||||
if x >= 0xF0 {
|
||||
// [x y z w] case
|
||||
// use only the lower 3 bits of `init`
|
||||
let w = unwrap_or_0(bytes.next());
|
||||
ch = (init & 7) << 18 | utf8_acc_cont_byte(y_z, w);
|
||||
}
|
||||
}
|
||||
|
||||
Some(ch)
|
||||
}
|
||||
|
||||
/// Reads the last code point out of a byte iterator (assuming a
|
||||
/// UTF-8-like encoding).
|
||||
#[inline]
|
||||
pub(super) fn next_code_point_reverse<'a, I>(bytes: &mut I) -> Option<u32>
|
||||
where
|
||||
I: DoubleEndedIterator<Item = &'a u8>,
|
||||
{
|
||||
// Decode UTF-8
|
||||
let w = match *bytes.next_back()? {
|
||||
next_byte if next_byte < 128 => return Some(next_byte as u32),
|
||||
back_byte => back_byte,
|
||||
};
|
||||
|
||||
// Multibyte case follows
|
||||
// Decode from a byte combination out of: [x [y [z w]]]
|
||||
let mut ch;
|
||||
let z = unwrap_or_0(bytes.next_back());
|
||||
ch = utf8_first_byte(z, 2);
|
||||
if utf8_is_cont_byte(z) {
|
||||
let y = unwrap_or_0(bytes.next_back());
|
||||
ch = utf8_first_byte(y, 3);
|
||||
if utf8_is_cont_byte(y) {
|
||||
let x = unwrap_or_0(bytes.next_back());
|
||||
ch = utf8_first_byte(x, 4);
|
||||
ch = utf8_acc_cont_byte(ch, y);
|
||||
}
|
||||
ch = utf8_acc_cont_byte(ch, z);
|
||||
}
|
||||
ch = utf8_acc_cont_byte(ch, w);
|
||||
|
||||
Some(ch)
|
||||
}
|
||||
|
||||
// use truncation to fit u64 into usize
|
||||
const NONASCII_MASK: usize = 0x80808080_80808080u64 as usize;
|
||||
|
||||
/// Returns `true` if any byte in the word `x` is nonascii (>= 128).
|
||||
#[inline]
|
||||
fn contains_nonascii(x: usize) -> bool {
|
||||
(x & NONASCII_MASK) != 0
|
||||
}
|
||||
|
||||
/// Walks through `v` checking that it's a valid UTF-8 sequence,
|
||||
/// returning `Ok(())` in that case, or, if it is invalid, `Err(err)`.
|
||||
#[inline(always)]
|
||||
pub(super) fn run_utf8_validation(v: &[u8]) -> Result<(), Utf8Error> {
|
||||
let mut index = 0;
|
||||
let len = v.len();
|
||||
|
||||
let usize_bytes = mem::size_of::<usize>();
|
||||
let ascii_block_size = 2 * usize_bytes;
|
||||
let blocks_end = if len >= ascii_block_size { len - ascii_block_size + 1 } else { 0 };
|
||||
let align = v.as_ptr().align_offset(usize_bytes);
|
||||
|
||||
while index < len {
|
||||
let old_offset = index;
|
||||
macro_rules! err {
|
||||
($error_len: expr) => {
|
||||
return Err(Utf8Error { valid_up_to: old_offset, error_len: $error_len });
|
||||
};
|
||||
}
|
||||
|
||||
macro_rules! next {
|
||||
() => {{
|
||||
index += 1;
|
||||
// we needed data, but there was none: error!
|
||||
if index >= len {
|
||||
err!(None)
|
||||
}
|
||||
v[index]
|
||||
}};
|
||||
}
|
||||
|
||||
let first = v[index];
|
||||
if first >= 128 {
|
||||
let w = UTF8_CHAR_WIDTH[first as usize];
|
||||
// 2-byte encoding is for codepoints \u{0080} to \u{07ff}
|
||||
// first C2 80 last DF BF
|
||||
// 3-byte encoding is for codepoints \u{0800} to \u{ffff}
|
||||
// first E0 A0 80 last EF BF BF
|
||||
// excluding surrogates codepoints \u{d800} to \u{dfff}
|
||||
// ED A0 80 to ED BF BF
|
||||
// 4-byte encoding is for codepoints \u{1000}0 to \u{10ff}ff
|
||||
// first F0 90 80 80 last F4 8F BF BF
|
||||
//
|
||||
// Use the UTF-8 syntax from the RFC
|
||||
//
|
||||
// https://tools.ietf.org/html/rfc3629
|
||||
// UTF8-1 = %x00-7F
|
||||
// UTF8-2 = %xC2-DF UTF8-tail
|
||||
// UTF8-3 = %xE0 %xA0-BF UTF8-tail / %xE1-EC 2( UTF8-tail ) /
|
||||
// %xED %x80-9F UTF8-tail / %xEE-EF 2( UTF8-tail )
|
||||
// UTF8-4 = %xF0 %x90-BF 2( UTF8-tail ) / %xF1-F3 3( UTF8-tail ) /
|
||||
// %xF4 %x80-8F 2( UTF8-tail )
|
||||
match w {
|
||||
2 => {
|
||||
if next!() & !CONT_MASK != TAG_CONT_U8 {
|
||||
err!(Some(1))
|
||||
}
|
||||
}
|
||||
3 => {
|
||||
match (first, next!()) {
|
||||
(0xE0, 0xA0..=0xBF)
|
||||
| (0xE1..=0xEC, 0x80..=0xBF)
|
||||
| (0xED, 0x80..=0x9F)
|
||||
| (0xEE..=0xEF, 0x80..=0xBF) => {}
|
||||
_ => err!(Some(1)),
|
||||
}
|
||||
if next!() & !CONT_MASK != TAG_CONT_U8 {
|
||||
err!(Some(2))
|
||||
}
|
||||
}
|
||||
4 => {
|
||||
match (first, next!()) {
|
||||
(0xF0, 0x90..=0xBF) | (0xF1..=0xF3, 0x80..=0xBF) | (0xF4, 0x80..=0x8F) => {}
|
||||
_ => err!(Some(1)),
|
||||
}
|
||||
if next!() & !CONT_MASK != TAG_CONT_U8 {
|
||||
err!(Some(2))
|
||||
}
|
||||
if next!() & !CONT_MASK != TAG_CONT_U8 {
|
||||
err!(Some(3))
|
||||
}
|
||||
}
|
||||
_ => err!(Some(1)),
|
||||
}
|
||||
index += 1;
|
||||
} else {
|
||||
// Ascii case, try to skip forward quickly.
|
||||
// When the pointer is aligned, read 2 words of data per iteration
|
||||
// until we find a word containing a non-ascii byte.
|
||||
if align != usize::MAX && align.wrapping_sub(index) % usize_bytes == 0 {
|
||||
let ptr = v.as_ptr();
|
||||
while index < blocks_end {
|
||||
// SAFETY: since `align - index` and `ascii_block_size` are
|
||||
// multiples of `usize_bytes`, `block = ptr.add(index)` is
|
||||
// always aligned with a `usize` so it's safe to dereference
|
||||
// both `block` and `block.offset(1)`.
|
||||
unsafe {
|
||||
let block = ptr.add(index) as *const usize;
|
||||
// break if there is a nonascii byte
|
||||
let zu = contains_nonascii(*block);
|
||||
let zv = contains_nonascii(*block.offset(1));
|
||||
if zu | zv {
|
||||
break;
|
||||
}
|
||||
}
|
||||
index += ascii_block_size;
|
||||
}
|
||||
// step from the point where the wordwise loop stopped
|
||||
while index < len && v[index] < 128 {
|
||||
index += 1;
|
||||
}
|
||||
} else {
|
||||
index += 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
// https://tools.ietf.org/html/rfc3629
|
||||
static UTF8_CHAR_WIDTH: [u8; 256] = [
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, // 0x1F
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, // 0x3F
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, // 0x5F
|
||||
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
|
||||
1, // 0x7F
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, // 0x9F
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, // 0xBF
|
||||
0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
|
||||
2, // 0xDF
|
||||
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, // 0xEF
|
||||
4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xFF
|
||||
];
|
||||
|
||||
/// Given a first byte, determines how many bytes are in this UTF-8 character.
|
||||
#[unstable(feature = "str_internals", issue = "none")]
|
||||
#[inline]
|
||||
pub fn utf8_char_width(b: u8) -> usize {
|
||||
UTF8_CHAR_WIDTH[b as usize] as usize
|
||||
}
|
||||
|
||||
/// Mask of the value bits of a continuation byte.
|
||||
const CONT_MASK: u8 = 0b0011_1111;
|
||||
/// Value of the tag bits (tag mask is !CONT_MASK) of a continuation byte.
|
||||
const TAG_CONT_U8: u8 = 0b1000_0000;
|
||||
|
||||
// truncate `&str` to length at most equal to `max`
|
||||
// return `true` if it were truncated, and the new str.
|
||||
pub(super) fn truncate_to_char_boundary(s: &str, mut max: usize) -> (bool, &str) {
|
||||
if max >= s.len() {
|
||||
(false, s)
|
||||
} else {
|
||||
while !s.is_char_boundary(max) {
|
||||
max -= 1;
|
||||
}
|
||||
(true, &s[..max])
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user