1//! Ways to create a `str` from bytes slice.
2
3use super::Utf8Error;
4use super::validations::run_utf8_validation;
5use crate::{mem, ptr};
6
7/// Converts a slice of bytes to a string slice.
8///
9/// A string slice ([`&str`]) is made of bytes ([`u8`]), and a byte slice
10/// ([`&[u8]`][byteslice]) is made of bytes, so this function converts between
11/// the two. Not all byte slices are valid string slices, however: [`&str`] requires
12/// that it is valid UTF-8. `from_utf8()` checks to ensure that the bytes are valid
13/// UTF-8, and then does the conversion.
14///
15/// [`&str`]: str
16/// [byteslice]: slice
17///
18/// If you are sure that the byte slice is valid UTF-8, and you don't want to
19/// incur the overhead of the validity check, there is an unsafe version of
20/// this function, [`from_utf8_unchecked`], which has the same
21/// behavior but skips the check.
22///
23/// If you need a `String` instead of a `&str`, consider
24/// [`String::from_utf8`][string].
25///
26/// [string]: ../../std/string/struct.String.html#method.from_utf8
27///
28/// Because you can stack-allocate a `[u8; N]`, and you can take a
29/// [`&[u8]`][byteslice] of it, this function is one way to have a
30/// stack-allocated string. There is an example of this in the
31/// examples section below.
32///
33/// [byteslice]: slice
34///
35/// # Errors
36///
37/// Returns `Err` if the slice is not UTF-8 with a description as to why the
38/// provided slice is not UTF-8.
39///
40/// # Examples
41///
42/// Basic usage:
43///
44/// ```
45/// use std::str;
46///
47/// // some bytes, in a vector
48/// let sparkle_heart = vec![240, 159, 146, 150];
49///
50/// // We can use the ? (try) operator to check if the bytes are valid
51/// let sparkle_heart = str::from_utf8(&sparkle_heart)?;
52///
53/// assert_eq!("💖", sparkle_heart);
54/// # Ok::<_, str::Utf8Error>(())
55/// ```
56///
57/// Incorrect bytes:
58///
59/// ```
60/// use std::str;
61///
62/// // some invalid bytes, in a vector
63/// let sparkle_heart = vec![0, 159, 146, 150];
64///
65/// assert!(str::from_utf8(&sparkle_heart).is_err());
66/// ```
67///
68/// See the docs for [`Utf8Error`] for more details on the kinds of
69/// errors that can be returned.
70///
71/// A "stack allocated string":
72///
73/// ```
74/// use std::str;
75///
76/// // some bytes, in a stack-allocated array
77/// let sparkle_heart = [240, 159, 146, 150];
78///
79/// // We know these bytes are valid, so just use `unwrap()`.
80/// let sparkle_heart: &str = str::from_utf8(&sparkle_heart).unwrap();
81///
82/// assert_eq!("💖", sparkle_heart);
83/// ```
84#[stable(feature = "rust1", since = "1.0.0")]
85#[rustc_const_stable(feature = "const_str_from_utf8_shared", since = "1.63.0")]
86#[rustc_diagnostic_item = "str_from_utf8"]
87pub const fn from_utf8(v: &[u8]) -> Result<&str, Utf8Error> {
88 // FIXME(const-hack): This should use `?` again, once it's `const`
89 match run_utf8_validation(v) {
90 Ok(_) => {
91 // SAFETY: validation succeeded.
92 Ok(unsafe { from_utf8_unchecked(v) })
93 }
94 Err(err: Utf8Error) => Err(err),
95 }
96}
97
98/// Converts a mutable slice of bytes to a mutable string slice.
99///
100/// # Examples
101///
102/// Basic usage:
103///
104/// ```
105/// use std::str;
106///
107/// // "Hello, Rust!" as a mutable vector
108/// let mut hellorust = vec![72, 101, 108, 108, 111, 44, 32, 82, 117, 115, 116, 33];
109///
110/// // As we know these bytes are valid, we can use `unwrap()`
111/// let outstr = str::from_utf8_mut(&mut hellorust).unwrap();
112///
113/// assert_eq!("Hello, Rust!", outstr);
114/// ```
115///
116/// Incorrect bytes:
117///
118/// ```
119/// use std::str;
120///
121/// // Some invalid bytes in a mutable vector
122/// let mut invalid = vec![128, 223];
123///
124/// assert!(str::from_utf8_mut(&mut invalid).is_err());
125/// ```
126/// See the docs for [`Utf8Error`] for more details on the kinds of
127/// errors that can be returned.
128#[stable(feature = "str_mut_extras", since = "1.20.0")]
129#[rustc_const_stable(feature = "const_str_from_utf8", since = "1.87.0")]
130#[rustc_diagnostic_item = "str_from_utf8_mut"]
131pub const fn from_utf8_mut(v: &mut [u8]) -> Result<&mut str, Utf8Error> {
132 // FIXME(const-hack): This should use `?` again, once it's `const`
133 match run_utf8_validation(v) {
134 Ok(_) => {
135 // SAFETY: validation succeeded.
136 Ok(unsafe { from_utf8_unchecked_mut(v) })
137 }
138 Err(err: Utf8Error) => Err(err),
139 }
140}
141
142/// Converts a slice of bytes to a string slice without checking
143/// that the string contains valid UTF-8.
144///
145/// See the safe version, [`from_utf8`], for more information.
146///
147/// # Safety
148///
149/// The bytes passed in must be valid UTF-8.
150///
151/// # Examples
152///
153/// Basic usage:
154///
155/// ```
156/// use std::str;
157///
158/// // some bytes, in a vector
159/// let sparkle_heart = vec![240, 159, 146, 150];
160///
161/// let sparkle_heart = unsafe {
162/// str::from_utf8_unchecked(&sparkle_heart)
163/// };
164///
165/// assert_eq!("💖", sparkle_heart);
166/// ```
167#[inline]
168#[must_use]
169#[stable(feature = "rust1", since = "1.0.0")]
170#[rustc_const_stable(feature = "const_str_from_utf8_unchecked", since = "1.55.0")]
171#[rustc_diagnostic_item = "str_from_utf8_unchecked"]
172pub const unsafe fn from_utf8_unchecked(v: &[u8]) -> &str {
173 // SAFETY: the caller must guarantee that the bytes `v` are valid UTF-8.
174 // Also relies on `&str` and `&[u8]` having the same layout.
175 unsafe { mem::transmute(src:v) }
176}
177
178/// Converts a slice of bytes to a string slice without checking
179/// that the string contains valid UTF-8; mutable version.
180///
181/// See the immutable version, [`from_utf8_unchecked()`] for more information.
182///
183/// # Examples
184///
185/// Basic usage:
186///
187/// ```
188/// use std::str;
189///
190/// let mut heart = vec![240, 159, 146, 150];
191/// let heart = unsafe { str::from_utf8_unchecked_mut(&mut heart) };
192///
193/// assert_eq!("💖", heart);
194/// ```
195#[inline]
196#[must_use]
197#[stable(feature = "str_mut_extras", since = "1.20.0")]
198#[rustc_const_stable(feature = "const_str_from_utf8_unchecked_mut", since = "1.83.0")]
199#[rustc_diagnostic_item = "str_from_utf8_unchecked_mut"]
200pub const unsafe fn from_utf8_unchecked_mut(v: &mut [u8]) -> &mut str {
201 // SAFETY: the caller must guarantee that the bytes `v`
202 // are valid UTF-8, thus the cast to `*mut str` is safe.
203 // Also, the pointer dereference is safe because that pointer
204 // comes from a reference which is guaranteed to be valid for writes.
205 unsafe { &mut *(v as *mut [u8] as *mut str) }
206}
207
208/// Creates a `&str` from a pointer and a length.
209///
210/// The pointed-to bytes must be valid UTF-8.
211/// If this might not be the case, use `str::from_utf8(slice::from_raw_parts(ptr, len))`,
212/// which will return an `Err` if the data isn't valid UTF-8.
213///
214/// This function is the `str` equivalent of [`slice::from_raw_parts`](crate::slice::from_raw_parts).
215/// See that function's documentation for safety concerns and examples.
216///
217/// The mutable version of this function is [`from_raw_parts_mut`].
218#[inline]
219#[must_use]
220#[unstable(feature = "str_from_raw_parts", issue = "119206")]
221pub const unsafe fn from_raw_parts<'a>(ptr: *const u8, len: usize) -> &'a str {
222 // SAFETY: the caller must uphold the safety contract for `from_raw_parts`.
223 unsafe { &*ptr::from_raw_parts(data_pointer:ptr, metadata:len) }
224}
225
226/// Creates a `&mut str` from a pointer and a length.
227///
228/// The pointed-to bytes must be valid UTF-8.
229/// If this might not be the case, use `str::from_utf8_mut(slice::from_raw_parts_mut(ptr, len))`,
230/// which will return an `Err` if the data isn't valid UTF-8.
231///
232/// This function is the `str` equivalent of [`slice::from_raw_parts_mut`](crate::slice::from_raw_parts_mut).
233/// See that function's documentation for safety concerns and examples.
234///
235/// The immutable version of this function is [`from_raw_parts`].
236#[inline]
237#[must_use]
238#[unstable(feature = "str_from_raw_parts", issue = "119206")]
239pub const unsafe fn from_raw_parts_mut<'a>(ptr: *mut u8, len: usize) -> &'a mut str {
240 // SAFETY: the caller must uphold the safety contract for `from_raw_parts_mut`.
241 unsafe { &mut *ptr::from_raw_parts_mut(data_pointer:ptr, metadata:len) }
242}
243

Provided by KDAB

Privacy Policy