diff options
Diffstat (limited to 'library/alloc/src/string.rs')
| -rw-r--r-- | library/alloc/src/string.rs | 2951 |
1 files changed, 2951 insertions, 0 deletions
diff --git a/library/alloc/src/string.rs b/library/alloc/src/string.rs new file mode 100644 index 000000000..a5118e533 --- /dev/null +++ b/library/alloc/src/string.rs @@ -0,0 +1,2951 @@ +//! A UTF-8โencoded, growable string. +//! +//! This module contains the [`String`] type, the [`ToString`] trait for +//! converting to strings, and several error types that may result from +//! working with [`String`]s. +//! +//! # Examples +//! +//! There are multiple ways to create a new [`String`] from a string literal: +//! +//! ``` +//! let s = "Hello".to_string(); +//! +//! let s = String::from("world"); +//! let s: String = "also this".into(); +//! ``` +//! +//! You can create a new [`String`] from an existing one by concatenating with +//! `+`: +//! +//! ``` +//! let s = "Hello".to_string(); +//! +//! let message = s + " world!"; +//! ``` +//! +//! If you have a vector of valid UTF-8 bytes, you can make a [`String`] out of +//! it. You can do the reverse too. +//! +//! ``` +//! let sparkle_heart = vec![240, 159, 146, 150]; +//! +//! // We know these bytes are valid, so we'll use `unwrap()`. +//! let sparkle_heart = String::from_utf8(sparkle_heart).unwrap(); +//! +//! assert_eq!("๐", sparkle_heart); +//! +//! let bytes = sparkle_heart.into_bytes(); +//! +//! assert_eq!(bytes, [240, 159, 146, 150]); +//! ``` + +#![stable(feature = "rust1", since = "1.0.0")] + +#[cfg(not(no_global_oom_handling))] +use core::char::{decode_utf16, REPLACEMENT_CHARACTER}; +use core::fmt; +use core::hash; +use core::iter::FusedIterator; +#[cfg(not(no_global_oom_handling))] +use core::iter::{from_fn, FromIterator}; +#[cfg(not(no_global_oom_handling))] +use core::ops::Add; +#[cfg(not(no_global_oom_handling))] +use core::ops::AddAssign; +#[cfg(not(no_global_oom_handling))] +use core::ops::Bound::{Excluded, Included, Unbounded}; +use core::ops::{self, Index, IndexMut, Range, RangeBounds}; +use core::ptr; +use core::slice; +#[cfg(not(no_global_oom_handling))] +use core::str::lossy; +use core::str::pattern::Pattern; + +#[cfg(not(no_global_oom_handling))] +use crate::borrow::{Cow, ToOwned}; +use crate::boxed::Box; +use crate::collections::TryReserveError; +use crate::str::{self, Chars, Utf8Error}; +#[cfg(not(no_global_oom_handling))] +use crate::str::{from_boxed_utf8_unchecked, FromStr}; +use crate::vec::Vec; + +/// A UTF-8โencoded, growable string. +/// +/// The `String` type is the most common string type that has ownership over the +/// contents of the string. It has a close relationship with its borrowed +/// counterpart, the primitive [`str`]. +/// +/// # Examples +/// +/// You can create a `String` from [a literal string][`&str`] with [`String::from`]: +/// +/// [`String::from`]: From::from +/// +/// ``` +/// let hello = String::from("Hello, world!"); +/// ``` +/// +/// You can append a [`char`] to a `String` with the [`push`] method, and +/// append a [`&str`] with the [`push_str`] method: +/// +/// ``` +/// let mut hello = String::from("Hello, "); +/// +/// hello.push('w'); +/// hello.push_str("orld!"); +/// ``` +/// +/// [`push`]: String::push +/// [`push_str`]: String::push_str +/// +/// If you have a vector of UTF-8 bytes, you can create a `String` from it with +/// the [`from_utf8`] method: +/// +/// ``` +/// // some bytes, in a vector +/// let sparkle_heart = vec![240, 159, 146, 150]; +/// +/// // We know these bytes are valid, so we'll use `unwrap()`. +/// let sparkle_heart = String::from_utf8(sparkle_heart).unwrap(); +/// +/// assert_eq!("๐", sparkle_heart); +/// ``` +/// +/// [`from_utf8`]: String::from_utf8 +/// +/// # UTF-8 +/// +/// `String`s are always valid UTF-8. If you need a non-UTF-8 string, consider +/// [`OsString`]. It is similar, but without the UTF-8 constraint. Because UTF-8 +/// is a variable width encoding, `String`s are typically smaller than an array of +/// the same `chars`: +/// +/// ``` +/// use std::mem; +/// +/// // `s` is ASCII which represents each `char` as one byte +/// let s = "hello"; +/// assert_eq!(s.len(), 5); +/// +/// // A `char` array with the same contents would be longer because +/// // every `char` is four bytes +/// let s = ['h', 'e', 'l', 'l', 'o']; +/// let size: usize = s.into_iter().map(|c| mem::size_of_val(&c)).sum(); +/// assert_eq!(size, 20); +/// +/// // However, for non-ASCII strings, the difference will be smaller +/// // and sometimes they are the same +/// let s = "๐๐๐๐๐"; +/// assert_eq!(s.len(), 20); +/// +/// let s = ['๐', '๐', '๐', '๐', '๐']; +/// let size: usize = s.into_iter().map(|c| mem::size_of_val(&c)).sum(); +/// assert_eq!(size, 20); +/// ``` +/// +/// This raises interesting questions as to how `s[i]` should work. +/// What should `i` be here? Several options include byte indices and +/// `char` indices but, because of UTF-8 encoding, only byte indices +/// would provide constant time indexing. Getting the `i`th `char`, for +/// example, is available using [`chars`]: +/// +/// ``` +/// let s = "hello"; +/// let third_character = s.chars().nth(2); +/// assert_eq!(third_character, Some('l')); +/// +/// let s = "๐๐๐๐๐"; +/// let third_character = s.chars().nth(2); +/// assert_eq!(third_character, Some('๐')); +/// ``` +/// +/// Next, what should `s[i]` return? Because indexing returns a reference +/// to underlying data it could be `&u8`, `&[u8]`, or something else similar. +/// Since we're only providing one index, `&u8` makes the most sense but that +/// might not be what the user expects and can be explicitly achieved with +/// [`as_bytes()`]: +/// +/// ``` +/// // The first byte is 104 - the byte value of `'h'` +/// let s = "hello"; +/// assert_eq!(s.as_bytes()[0], 104); +/// // or +/// assert_eq!(s.as_bytes()[0], b'h'); +/// +/// // The first byte is 240 which isn't obviously useful +/// let s = "๐๐๐๐๐"; +/// assert_eq!(s.as_bytes()[0], 240); +/// ``` +/// +/// Due to these ambiguities/restrictions, indexing with a `usize` is simply +/// forbidden: +/// +/// ```compile_fail,E0277 +/// let s = "hello"; +/// +/// // The following will not compile! +/// println!("The first letter of s is {}", s[0]); +/// ``` +/// +/// It is more clear, however, how `&s[i..j]` should work (that is, +/// indexing with a range). It should accept byte indices (to be constant-time) +/// and return a `&str` which is UTF-8 encoded. This is also called "string slicing". +/// Note this will panic if the byte indices provided are not character +/// boundaries - see [`is_char_boundary`] for more details. See the implementations +/// for [`SliceIndex<str>`] for more details on string slicing. For a non-panicking +/// version of string slicing, see [`get`]. +/// +/// [`OsString`]: ../../std/ffi/struct.OsString.html "ffi::OsString" +/// [`SliceIndex<str>`]: core::slice::SliceIndex +/// [`as_bytes()`]: str::as_bytes +/// [`get`]: str::get +/// [`is_char_boundary`]: str::is_char_boundary +/// +/// The [`bytes`] and [`chars`] methods return iterators over the bytes and +/// codepoints of the string, respectively. To iterate over codepoints along +/// with byte indices, use [`char_indices`]. +/// +/// [`bytes`]: str::bytes +/// [`chars`]: str::chars +/// [`char_indices`]: str::char_indices +/// +/// # Deref +/// +/// `String` implements <code>[Deref]<Target = [str]></code>, and so inherits all of [`str`]'s +/// methods. In addition, this means that you can pass a `String` to a +/// function which takes a [`&str`] by using an ampersand (`&`): +/// +/// ``` +/// fn takes_str(s: &str) { } +/// +/// let s = String::from("Hello"); +/// +/// takes_str(&s); +/// ``` +/// +/// This will create a [`&str`] from the `String` and pass it in. This +/// conversion is very inexpensive, and so generally, functions will accept +/// [`&str`]s as arguments unless they need a `String` for some specific +/// reason. +/// +/// In certain cases Rust doesn't have enough information to make this +/// conversion, known as [`Deref`] coercion. In the following example a string +/// slice [`&'a str`][`&str`] implements the trait `TraitExample`, and the function +/// `example_func` takes anything that implements the trait. In this case Rust +/// would need to make two implicit conversions, which Rust doesn't have the +/// means to do. For that reason, the following example will not compile. +/// +/// ```compile_fail,E0277 +/// trait TraitExample {} +/// +/// impl<'a> TraitExample for &'a str {} +/// +/// fn example_func<A: TraitExample>(example_arg: A) {} +/// +/// let example_string = String::from("example_string"); +/// example_func(&example_string); +/// ``` +/// +/// There are two options that would work instead. The first would be to +/// change the line `example_func(&example_string);` to +/// `example_func(example_string.as_str());`, using the method [`as_str()`] +/// to explicitly extract the string slice containing the string. The second +/// way changes `example_func(&example_string);` to +/// `example_func(&*example_string);`. In this case we are dereferencing a +/// `String` to a [`str`], then referencing the [`str`] back to +/// [`&str`]. The second way is more idiomatic, however both work to do the +/// conversion explicitly rather than relying on the implicit conversion. +/// +/// # Representation +/// +/// A `String` is made up of three components: a pointer to some bytes, a +/// length, and a capacity. The pointer points to an internal buffer `String` +/// uses to store its data. The length is the number of bytes currently stored +/// in the buffer, and the capacity is the size of the buffer in bytes. As such, +/// the length will always be less than or equal to the capacity. +/// +/// This buffer is always stored on the heap. +/// +/// You can look at these with the [`as_ptr`], [`len`], and [`capacity`] +/// methods: +/// +/// ``` +/// use std::mem; +/// +/// let story = String::from("Once upon a time..."); +/// +// FIXME Update this when vec_into_raw_parts is stabilized +/// // Prevent automatically dropping the String's data +/// let mut story = mem::ManuallyDrop::new(story); +/// +/// let ptr = story.as_mut_ptr(); +/// let len = story.len(); +/// let capacity = story.capacity(); +/// +/// // story has nineteen bytes +/// assert_eq!(19, len); +/// +/// // We can re-build a String out of ptr, len, and capacity. This is all +/// // unsafe because we are responsible for making sure the components are +/// // valid: +/// let s = unsafe { String::from_raw_parts(ptr, len, capacity) } ; +/// +/// assert_eq!(String::from("Once upon a time..."), s); +/// ``` +/// +/// [`as_ptr`]: str::as_ptr +/// [`len`]: String::len +/// [`capacity`]: String::capacity +/// +/// If a `String` has enough capacity, adding elements to it will not +/// re-allocate. For example, consider this program: +/// +/// ``` +/// let mut s = String::new(); +/// +/// println!("{}", s.capacity()); +/// +/// for _ in 0..5 { +/// s.push_str("hello"); +/// println!("{}", s.capacity()); +/// } +/// ``` +/// +/// This will output the following: +/// +/// ```text +/// 0 +/// 8 +/// 16 +/// 16 +/// 32 +/// 32 +/// ``` +/// +/// At first, we have no memory allocated at all, but as we append to the +/// string, it increases its capacity appropriately. If we instead use the +/// [`with_capacity`] method to allocate the correct capacity initially: +/// +/// ``` +/// let mut s = String::with_capacity(25); +/// +/// println!("{}", s.capacity()); +/// +/// for _ in 0..5 { +/// s.push_str("hello"); +/// println!("{}", s.capacity()); +/// } +/// ``` +/// +/// [`with_capacity`]: String::with_capacity +/// +/// We end up with a different output: +/// +/// ```text +/// 25 +/// 25 +/// 25 +/// 25 +/// 25 +/// 25 +/// ``` +/// +/// Here, there's no need to allocate more memory inside the loop. +/// +/// [str]: prim@str "str" +/// [`str`]: prim@str "str" +/// [`&str`]: prim@str "&str" +/// [Deref]: core::ops::Deref "ops::Deref" +/// [`Deref`]: core::ops::Deref "ops::Deref" +/// [`as_str()`]: String::as_str +#[derive(PartialOrd, Eq, Ord)] +#[cfg_attr(not(test), rustc_diagnostic_item = "String")] +#[stable(feature = "rust1", since = "1.0.0")] +pub struct String { + vec: Vec<u8>, +} + +/// A possible error value when converting a `String` from a UTF-8 byte vector. +/// +/// This type is the error type for the [`from_utf8`] method on [`String`]. It +/// is designed in such a way to carefully avoid reallocations: the +/// [`into_bytes`] method will give back the byte vector that was used in the +/// conversion attempt. +/// +/// [`from_utf8`]: String::from_utf8 +/// [`into_bytes`]: FromUtf8Error::into_bytes +/// +/// The [`Utf8Error`] type provided by [`std::str`] represents an error that may +/// occur when converting a slice of [`u8`]s to a [`&str`]. In this sense, it's +/// an analogue to `FromUtf8Error`, and you can get one from a `FromUtf8Error` +/// through the [`utf8_error`] method. +/// +/// [`Utf8Error`]: str::Utf8Error "std::str::Utf8Error" +/// [`std::str`]: core::str "std::str" +/// [`&str`]: prim@str "&str" +/// [`utf8_error`]: FromUtf8Error::utf8_error +/// +/// # Examples +/// +/// Basic usage: +/// +/// ``` +/// // some invalid bytes, in a vector +/// let bytes = vec![0, 159]; +/// +/// let value = String::from_utf8(bytes); +/// +/// assert!(value.is_err()); +/// assert_eq!(vec![0, 159], value.unwrap_err().into_bytes()); +/// ``` +#[stable(feature = "rust1", since = "1.0.0")] +#[cfg_attr(not(no_global_oom_handling), derive(Clone))] +#[derive(Debug, PartialEq, Eq)] +pub struct FromUtf8Error { + bytes: Vec<u8>, + error: Utf8Error, +} + +/// A possible error value when converting a `String` from a UTF-16 byte slice. +/// +/// This type is the error type for the [`from_utf16`] method on [`String`]. +/// +/// [`from_utf16`]: String::from_utf16 +/// # Examples +/// +/// Basic usage: +/// +/// ``` +/// // ๐mu<invalid>ic +/// let v = &[0xD834, 0xDD1E, 0x006d, 0x0075, +/// 0xD800, 0x0069, 0x0063]; +/// +/// assert!(String::from_utf16(v).is_err()); +/// ``` +#[stable(feature = "rust1", since = "1.0.0")] +#[derive(Debug)] +pub struct FromUtf16Error(()); + +impl String { + /// Creates a new empty `String`. + /// + /// Given that the `String` is empty, this will not allocate any initial + /// buffer. While that means that this initial operation is very + /// inexpensive, it may cause excessive allocation later when you add + /// data. If you have an idea of how much data the `String` will hold, + /// consider the [`with_capacity`] method to prevent excessive + /// re-allocation. + /// + /// [`with_capacity`]: String::with_capacity + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s = String::new(); + /// ``` + #[inline] + #[rustc_const_stable(feature = "const_string_new", since = "1.39.0")] + #[stable(feature = "rust1", since = "1.0.0")] + #[must_use] + pub const fn new() -> String { + String { vec: Vec::new() } + } + + /// Creates a new empty `String` with at least the specified capacity. + /// + /// `String`s have an internal buffer to hold their data. The capacity is + /// the length of that buffer, and can be queried with the [`capacity`] + /// method. This method creates an empty `String`, but one with an initial + /// buffer that can hold at least `capacity` bytes. This is useful when you + /// may be appending a bunch of data to the `String`, reducing the number of + /// reallocations it needs to do. + /// + /// [`capacity`]: String::capacity + /// + /// If the given capacity is `0`, no allocation will occur, and this method + /// is identical to the [`new`] method. + /// + /// [`new`]: String::new + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::with_capacity(10); + /// + /// // The String contains no chars, even though it has capacity for more + /// assert_eq!(s.len(), 0); + /// + /// // These are all done without reallocating... + /// let cap = s.capacity(); + /// for _ in 0..10 { + /// s.push('a'); + /// } + /// + /// assert_eq!(s.capacity(), cap); + /// + /// // ...but this may make the string reallocate + /// s.push('a'); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + #[must_use] + pub fn with_capacity(capacity: usize) -> String { + String { vec: Vec::with_capacity(capacity) } + } + + // HACK(japaric): with cfg(test) the inherent `[T]::to_vec` method, which is + // required for this method definition, is not available. Since we don't + // require this method for testing purposes, I'll just stub it + // NB see the slice::hack module in slice.rs for more information + #[inline] + #[cfg(test)] + pub fn from_str(_: &str) -> String { + panic!("not available with cfg(test)"); + } + + /// Converts a vector of bytes to a `String`. + /// + /// A string ([`String`]) is made of bytes ([`u8`]), and a vector of bytes + /// ([`Vec<u8>`]) is made of bytes, so this function converts between the + /// two. Not all byte slices are valid `String`s, however: `String` + /// requires that it is valid UTF-8. `from_utf8()` checks to ensure that + /// the bytes are valid UTF-8, and then does the conversion. + /// + /// 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. + /// + /// This method will take care to not copy the vector, for efficiency's + /// sake. + /// + /// If you need a [`&str`] instead of a `String`, consider + /// [`str::from_utf8`]. + /// + /// The inverse of this method is [`into_bytes`]. + /// + /// # Errors + /// + /// Returns [`Err`] if the slice is not UTF-8 with a description as to why the + /// provided bytes are not UTF-8. The vector you moved in is also included. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// // some bytes, in a vector + /// let sparkle_heart = vec![240, 159, 146, 150]; + /// + /// // We know these bytes are valid, so we'll use `unwrap()`. + /// let sparkle_heart = String::from_utf8(sparkle_heart).unwrap(); + /// + /// assert_eq!("๐", sparkle_heart); + /// ``` + /// + /// Incorrect bytes: + /// + /// ``` + /// // some invalid bytes, in a vector + /// let sparkle_heart = vec![0, 159, 146, 150]; + /// + /// assert!(String::from_utf8(sparkle_heart).is_err()); + /// ``` + /// + /// See the docs for [`FromUtf8Error`] for more details on what you can do + /// with this error. + /// + /// [`from_utf8_unchecked`]: String::from_utf8_unchecked + /// [`Vec<u8>`]: crate::vec::Vec "Vec" + /// [`&str`]: prim@str "&str" + /// [`into_bytes`]: String::into_bytes + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn from_utf8(vec: Vec<u8>) -> Result<String, FromUtf8Error> { + match str::from_utf8(&vec) { + Ok(..) => Ok(String { vec }), + Err(e) => Err(FromUtf8Error { bytes: vec, error: e }), + } + } + + /// Converts a slice of bytes to a string, including invalid characters. + /// + /// Strings are made of bytes ([`u8`]), and a slice of bytes + /// ([`&[u8]`][byteslice]) is made of bytes, so this function converts + /// between the two. Not all byte slices are valid strings, however: strings + /// are required to be valid UTF-8. During this conversion, + /// `from_utf8_lossy()` will replace any invalid UTF-8 sequences with + /// [`U+FFFD REPLACEMENT CHARACTER`][U+FFFD], which looks like this: ๏ฟฝ + /// + /// [byteslice]: prim@slice + /// [U+FFFD]: core::char::REPLACEMENT_CHARACTER + /// + /// If you are sure that the byte slice is valid UTF-8, and you don't want + /// to incur the overhead of the conversion, there is an unsafe version + /// of this function, [`from_utf8_unchecked`], which has the same behavior + /// but skips the checks. + /// + /// [`from_utf8_unchecked`]: String::from_utf8_unchecked + /// + /// This function returns a [`Cow<'a, str>`]. If our byte slice is invalid + /// UTF-8, then we need to insert the replacement characters, which will + /// change the size of the string, and hence, require a `String`. But if + /// it's already valid UTF-8, we don't need a new allocation. This return + /// type allows us to handle both cases. + /// + /// [`Cow<'a, str>`]: crate::borrow::Cow "borrow::Cow" + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// // some bytes, in a vector + /// let sparkle_heart = vec![240, 159, 146, 150]; + /// + /// let sparkle_heart = String::from_utf8_lossy(&sparkle_heart); + /// + /// assert_eq!("๐", sparkle_heart); + /// ``` + /// + /// Incorrect bytes: + /// + /// ``` + /// // some invalid bytes + /// let input = b"Hello \xF0\x90\x80World"; + /// let output = String::from_utf8_lossy(input); + /// + /// assert_eq!("Hello ๏ฟฝWorld", output); + /// ``` + #[must_use] + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn from_utf8_lossy(v: &[u8]) -> Cow<'_, str> { + let mut iter = lossy::Utf8Lossy::from_bytes(v).chunks(); + + let first_valid = if let Some(chunk) = iter.next() { + let lossy::Utf8LossyChunk { valid, broken } = chunk; + if broken.is_empty() { + debug_assert_eq!(valid.len(), v.len()); + return Cow::Borrowed(valid); + } + valid + } else { + return Cow::Borrowed(""); + }; + + const REPLACEMENT: &str = "\u{FFFD}"; + + let mut res = String::with_capacity(v.len()); + res.push_str(first_valid); + res.push_str(REPLACEMENT); + + for lossy::Utf8LossyChunk { valid, broken } in iter { + res.push_str(valid); + if !broken.is_empty() { + res.push_str(REPLACEMENT); + } + } + + Cow::Owned(res) + } + + /// Decode a UTF-16โencoded vector `v` into a `String`, returning [`Err`] + /// if `v` contains any invalid data. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// // ๐music + /// let v = &[0xD834, 0xDD1E, 0x006d, 0x0075, + /// 0x0073, 0x0069, 0x0063]; + /// assert_eq!(String::from("๐music"), + /// String::from_utf16(v).unwrap()); + /// + /// // ๐mu<invalid>ic + /// let v = &[0xD834, 0xDD1E, 0x006d, 0x0075, + /// 0xD800, 0x0069, 0x0063]; + /// assert!(String::from_utf16(v).is_err()); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn from_utf16(v: &[u16]) -> Result<String, FromUtf16Error> { + // This isn't done via collect::<Result<_, _>>() for performance reasons. + // FIXME: the function can be simplified again when #48994 is closed. + let mut ret = String::with_capacity(v.len()); + for c in decode_utf16(v.iter().cloned()) { + if let Ok(c) = c { + ret.push(c); + } else { + return Err(FromUtf16Error(())); + } + } + Ok(ret) + } + + /// Decode a UTF-16โencoded slice `v` into a `String`, replacing + /// invalid data with [the replacement character (`U+FFFD`)][U+FFFD]. + /// + /// Unlike [`from_utf8_lossy`] which returns a [`Cow<'a, str>`], + /// `from_utf16_lossy` returns a `String` since the UTF-16 to UTF-8 + /// conversion requires a memory allocation. + /// + /// [`from_utf8_lossy`]: String::from_utf8_lossy + /// [`Cow<'a, str>`]: crate::borrow::Cow "borrow::Cow" + /// [U+FFFD]: core::char::REPLACEMENT_CHARACTER + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// // ๐mus<invalid>ic<invalid> + /// let v = &[0xD834, 0xDD1E, 0x006d, 0x0075, + /// 0x0073, 0xDD1E, 0x0069, 0x0063, + /// 0xD834]; + /// + /// assert_eq!(String::from("๐mus\u{FFFD}ic\u{FFFD}"), + /// String::from_utf16_lossy(v)); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[must_use] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn from_utf16_lossy(v: &[u16]) -> String { + decode_utf16(v.iter().cloned()).map(|r| r.unwrap_or(REPLACEMENT_CHARACTER)).collect() + } + + /// Decomposes a `String` into its raw components. + /// + /// Returns the raw pointer to the underlying data, the length of + /// the string (in bytes), and the allocated capacity of the data + /// (in bytes). These are the same arguments in the same order as + /// the arguments to [`from_raw_parts`]. + /// + /// After calling this function, the caller is responsible for the + /// memory previously managed by the `String`. The only way to do + /// this is to convert the raw pointer, length, and capacity back + /// into a `String` with the [`from_raw_parts`] function, allowing + /// the destructor to perform the cleanup. + /// + /// [`from_raw_parts`]: String::from_raw_parts + /// + /// # Examples + /// + /// ``` + /// #![feature(vec_into_raw_parts)] + /// let s = String::from("hello"); + /// + /// let (ptr, len, cap) = s.into_raw_parts(); + /// + /// let rebuilt = unsafe { String::from_raw_parts(ptr, len, cap) }; + /// assert_eq!(rebuilt, "hello"); + /// ``` + #[must_use = "`self` will be dropped if the result is not used"] + #[unstable(feature = "vec_into_raw_parts", reason = "new API", issue = "65816")] + pub fn into_raw_parts(self) -> (*mut u8, usize, usize) { + self.vec.into_raw_parts() + } + + /// Creates a new `String` from a length, capacity, and pointer. + /// + /// # Safety + /// + /// This is highly unsafe, due to the number of invariants that aren't + /// checked: + /// + /// * The memory at `buf` needs to have been previously allocated by the + /// same allocator the standard library uses, with a required alignment of exactly 1. + /// * `length` needs to be less than or equal to `capacity`. + /// * `capacity` needs to be the correct value. + /// * The first `length` bytes at `buf` need to be valid UTF-8. + /// + /// Violating these may cause problems like corrupting the allocator's + /// internal data structures. For example, it is normally **not** safe to + /// build a `String` from a pointer to a C `char` array containing UTF-8 + /// _unless_ you are certain that array was originally allocated by the + /// Rust standard library's allocator. + /// + /// The ownership of `buf` is effectively transferred to the + /// `String` which may then deallocate, reallocate or change the + /// contents of memory pointed to by the pointer at will. Ensure + /// that nothing else uses the pointer after calling this + /// function. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// use std::mem; + /// + /// unsafe { + /// let s = String::from("hello"); + /// + // FIXME Update this when vec_into_raw_parts is stabilized + /// // Prevent automatically dropping the String's data + /// let mut s = mem::ManuallyDrop::new(s); + /// + /// let ptr = s.as_mut_ptr(); + /// let len = s.len(); + /// let capacity = s.capacity(); + /// + /// let s = String::from_raw_parts(ptr, len, capacity); + /// + /// assert_eq!(String::from("hello"), s); + /// } + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub unsafe fn from_raw_parts(buf: *mut u8, length: usize, capacity: usize) -> String { + unsafe { String { vec: Vec::from_raw_parts(buf, length, capacity) } } + } + + /// Converts a vector of bytes to a `String` without checking that the + /// string contains valid UTF-8. + /// + /// See the safe version, [`from_utf8`], for more details. + /// + /// [`from_utf8`]: String::from_utf8 + /// + /// # 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, it may cause + /// memory unsafety issues with future users of the `String`, as the rest of + /// the standard library assumes that `String`s are valid UTF-8. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// // some bytes, in a vector + /// let sparkle_heart = vec![240, 159, 146, 150]; + /// + /// let sparkle_heart = unsafe { + /// String::from_utf8_unchecked(sparkle_heart) + /// }; + /// + /// assert_eq!("๐", sparkle_heart); + /// ``` + #[inline] + #[must_use] + #[stable(feature = "rust1", since = "1.0.0")] + pub unsafe fn from_utf8_unchecked(bytes: Vec<u8>) -> String { + String { vec: bytes } + } + + /// Converts a `String` into a byte vector. + /// + /// This consumes the `String`, so we do not need to copy its contents. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s = String::from("hello"); + /// let bytes = s.into_bytes(); + /// + /// assert_eq!(&[104, 101, 108, 108, 111][..], &bytes[..]); + /// ``` + #[inline] + #[must_use = "`self` will be dropped if the result is not used"] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn into_bytes(self) -> Vec<u8> { + self.vec + } + + /// Extracts a string slice containing the entire `String`. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s = String::from("foo"); + /// + /// assert_eq!("foo", s.as_str()); + /// ``` + #[inline] + #[must_use] + #[stable(feature = "string_as_str", since = "1.7.0")] + pub fn as_str(&self) -> &str { + self + } + + /// Converts a `String` into a mutable string slice. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("foobar"); + /// let s_mut_str = s.as_mut_str(); + /// + /// s_mut_str.make_ascii_uppercase(); + /// + /// assert_eq!("FOOBAR", s_mut_str); + /// ``` + #[inline] + #[must_use] + #[stable(feature = "string_as_str", since = "1.7.0")] + pub fn as_mut_str(&mut self) -> &mut str { + self + } + + /// Appends a given string slice onto the end of this `String`. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("foo"); + /// + /// s.push_str("bar"); + /// + /// assert_eq!("foobar", s); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn push_str(&mut self, string: &str) { + self.vec.extend_from_slice(string.as_bytes()) + } + + /// Copies elements from `src` range to the end of the string. + /// + /// ## Panics + /// + /// Panics if the starting point or end point do not lie on a [`char`] + /// boundary, or if they're out of bounds. + /// + /// ## Examples + /// + /// ``` + /// #![feature(string_extend_from_within)] + /// let mut string = String::from("abcde"); + /// + /// string.extend_from_within(2..); + /// assert_eq!(string, "abcdecde"); + /// + /// string.extend_from_within(..2); + /// assert_eq!(string, "abcdecdeab"); + /// + /// string.extend_from_within(4..8); + /// assert_eq!(string, "abcdecdeabecde"); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[unstable(feature = "string_extend_from_within", issue = "none")] + pub fn extend_from_within<R>(&mut self, src: R) + where + R: RangeBounds<usize>, + { + let src @ Range { start, end } = slice::range(src, ..self.len()); + + assert!(self.is_char_boundary(start)); + assert!(self.is_char_boundary(end)); + + self.vec.extend_from_within(src); + } + + /// Returns this `String`'s capacity, in bytes. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s = String::with_capacity(10); + /// + /// assert!(s.capacity() >= 10); + /// ``` + #[inline] + #[must_use] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn capacity(&self) -> usize { + self.vec.capacity() + } + + /// Reserves capacity for at least `additional` bytes more than the + /// current length. The allocator may reserve more space to speculatively + /// avoid frequent allocations. After calling `reserve`, + /// capacity will be greater than or equal to `self.len() + additional`. + /// Does nothing if capacity is already sufficient. + /// + /// # Panics + /// + /// Panics if the new capacity overflows [`usize`]. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::new(); + /// + /// s.reserve(10); + /// + /// assert!(s.capacity() >= 10); + /// ``` + /// + /// This might not actually increase the capacity: + /// + /// ``` + /// let mut s = String::with_capacity(10); + /// s.push('a'); + /// s.push('b'); + /// + /// // s now has a length of 2 and a capacity of at least 10 + /// let capacity = s.capacity(); + /// assert_eq!(2, s.len()); + /// assert!(capacity >= 10); + /// + /// // Since we already have at least an extra 8 capacity, calling this... + /// s.reserve(8); + /// + /// // ... doesn't actually increase. + /// assert_eq!(capacity, s.capacity()); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn reserve(&mut self, additional: usize) { + self.vec.reserve(additional) + } + + /// Reserves the minimum capacity for at least `additional` bytes more than + /// the current length. Unlike [`reserve`], this will not + /// deliberately over-allocate to speculatively avoid frequent allocations. + /// After calling `reserve_exact`, capacity will be greater than or equal to + /// `self.len() + additional`. Does nothing if the capacity is already + /// sufficient. + /// + /// [`reserve`]: String::reserve + /// + /// # Panics + /// + /// Panics if the new capacity overflows [`usize`]. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::new(); + /// + /// s.reserve_exact(10); + /// + /// assert!(s.capacity() >= 10); + /// ``` + /// + /// This might not actually increase the capacity: + /// + /// ``` + /// let mut s = String::with_capacity(10); + /// s.push('a'); + /// s.push('b'); + /// + /// // s now has a length of 2 and a capacity of at least 10 + /// let capacity = s.capacity(); + /// assert_eq!(2, s.len()); + /// assert!(capacity >= 10); + /// + /// // Since we already have at least an extra 8 capacity, calling this... + /// s.reserve_exact(8); + /// + /// // ... doesn't actually increase. + /// assert_eq!(capacity, s.capacity()); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn reserve_exact(&mut self, additional: usize) { + self.vec.reserve_exact(additional) + } + + /// Tries to reserve capacity for at least `additional` bytes more than the + /// current length. The allocator may reserve more space to speculatively + /// avoid frequent allocations. After calling `try_reserve`, capacity will be + /// greater than or equal to `self.len() + additional` if it returns + /// `Ok(())`. Does nothing if capacity is already sufficient. + /// + /// # Errors + /// + /// If the capacity overflows, or the allocator reports a failure, then an error + /// is returned. + /// + /// # Examples + /// + /// ``` + /// use std::collections::TryReserveError; + /// + /// fn process_data(data: &str) -> Result<String, TryReserveError> { + /// let mut output = String::new(); + /// + /// // Pre-reserve the memory, exiting if we can't + /// output.try_reserve(data.len())?; + /// + /// // Now we know this can't OOM in the middle of our complex work + /// output.push_str(data); + /// + /// Ok(output) + /// } + /// # process_data("rust").expect("why is the test harness OOMing on 4 bytes?"); + /// ``` + #[stable(feature = "try_reserve", since = "1.57.0")] + pub fn try_reserve(&mut self, additional: usize) -> Result<(), TryReserveError> { + self.vec.try_reserve(additional) + } + + /// Tries to reserve the minimum capacity for at least `additional` bytes + /// more than the current length. Unlike [`try_reserve`], this will not + /// deliberately over-allocate to speculatively avoid frequent allocations. + /// After calling `try_reserve_exact`, capacity will be greater than or + /// equal to `self.len() + additional` if it returns `Ok(())`. + /// Does nothing if the capacity is already sufficient. + /// + /// Note that the allocator may give the collection more space than it + /// requests. Therefore, capacity can not be relied upon to be precisely + /// minimal. Prefer [`try_reserve`] if future insertions are expected. + /// + /// [`try_reserve`]: String::try_reserve + /// + /// # Errors + /// + /// If the capacity overflows, or the allocator reports a failure, then an error + /// is returned. + /// + /// # Examples + /// + /// ``` + /// use std::collections::TryReserveError; + /// + /// fn process_data(data: &str) -> Result<String, TryReserveError> { + /// let mut output = String::new(); + /// + /// // Pre-reserve the memory, exiting if we can't + /// output.try_reserve_exact(data.len())?; + /// + /// // Now we know this can't OOM in the middle of our complex work + /// output.push_str(data); + /// + /// Ok(output) + /// } + /// # process_data("rust").expect("why is the test harness OOMing on 4 bytes?"); + /// ``` + #[stable(feature = "try_reserve", since = "1.57.0")] + pub fn try_reserve_exact(&mut self, additional: usize) -> Result<(), TryReserveError> { + self.vec.try_reserve_exact(additional) + } + + /// Shrinks the capacity of this `String` to match its length. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("foo"); + /// + /// s.reserve(100); + /// assert!(s.capacity() >= 100); + /// + /// s.shrink_to_fit(); + /// assert_eq!(3, s.capacity()); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn shrink_to_fit(&mut self) { + self.vec.shrink_to_fit() + } + + /// Shrinks the capacity of this `String` with a lower bound. + /// + /// The capacity will remain at least as large as both the length + /// and the supplied value. + /// + /// If the current capacity is less than the lower limit, this is a no-op. + /// + /// # Examples + /// + /// ``` + /// let mut s = String::from("foo"); + /// + /// s.reserve(100); + /// assert!(s.capacity() >= 100); + /// + /// s.shrink_to(10); + /// assert!(s.capacity() >= 10); + /// s.shrink_to(0); + /// assert!(s.capacity() >= 3); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "shrink_to", since = "1.56.0")] + pub fn shrink_to(&mut self, min_capacity: usize) { + self.vec.shrink_to(min_capacity) + } + + /// Appends the given [`char`] to the end of this `String`. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("abc"); + /// + /// s.push('1'); + /// s.push('2'); + /// s.push('3'); + /// + /// assert_eq!("abc123", s); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn push(&mut self, ch: char) { + match ch.len_utf8() { + 1 => self.vec.push(ch as u8), + _ => self.vec.extend_from_slice(ch.encode_utf8(&mut [0; 4]).as_bytes()), + } + } + + /// Returns a byte slice of this `String`'s contents. + /// + /// The inverse of this method is [`from_utf8`]. + /// + /// [`from_utf8`]: String::from_utf8 + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s = String::from("hello"); + /// + /// assert_eq!(&[104, 101, 108, 108, 111], s.as_bytes()); + /// ``` + #[inline] + #[must_use] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn as_bytes(&self) -> &[u8] { + &self.vec + } + + /// Shortens this `String` to the specified length. + /// + /// If `new_len` is greater than the string's current length, this has no + /// effect. + /// + /// Note that this method has no effect on the allocated capacity + /// of the string + /// + /// # Panics + /// + /// Panics if `new_len` does not lie on a [`char`] boundary. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("hello"); + /// + /// s.truncate(2); + /// + /// assert_eq!("he", s); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn truncate(&mut self, new_len: usize) { + if new_len <= self.len() { + assert!(self.is_char_boundary(new_len)); + self.vec.truncate(new_len) + } + } + + /// Removes the last character from the string buffer and returns it. + /// + /// Returns [`None`] if this `String` is empty. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("foo"); + /// + /// assert_eq!(s.pop(), Some('o')); + /// assert_eq!(s.pop(), Some('o')); + /// assert_eq!(s.pop(), Some('f')); + /// + /// assert_eq!(s.pop(), None); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn pop(&mut self) -> Option<char> { + let ch = self.chars().rev().next()?; + let newlen = self.len() - ch.len_utf8(); + unsafe { + self.vec.set_len(newlen); + } + Some(ch) + } + + /// Removes a [`char`] from this `String` at a byte position and returns it. + /// + /// This is an *O*(*n*) operation, as it requires copying every element in the + /// buffer. + /// + /// # Panics + /// + /// Panics if `idx` is larger than or equal to the `String`'s length, + /// or if it does not lie on a [`char`] boundary. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("foo"); + /// + /// assert_eq!(s.remove(0), 'f'); + /// assert_eq!(s.remove(1), 'o'); + /// assert_eq!(s.remove(0), 'o'); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn remove(&mut self, idx: usize) -> char { + let ch = match self[idx..].chars().next() { + Some(ch) => ch, + None => panic!("cannot remove a char from the end of a string"), + }; + + let next = idx + ch.len_utf8(); + let len = self.len(); + unsafe { + ptr::copy(self.vec.as_ptr().add(next), self.vec.as_mut_ptr().add(idx), len - next); + self.vec.set_len(len - (next - idx)); + } + ch + } + + /// Remove all matches of pattern `pat` in the `String`. + /// + /// # Examples + /// + /// ``` + /// #![feature(string_remove_matches)] + /// let mut s = String::from("Trees are not green, the sky is not blue."); + /// s.remove_matches("not "); + /// assert_eq!("Trees are green, the sky is blue.", s); + /// ``` + /// + /// Matches will be detected and removed iteratively, so in cases where + /// patterns overlap, only the first pattern will be removed: + /// + /// ``` + /// #![feature(string_remove_matches)] + /// let mut s = String::from("banana"); + /// s.remove_matches("ana"); + /// assert_eq!("bna", s); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[unstable(feature = "string_remove_matches", reason = "new API", issue = "72826")] + pub fn remove_matches<'a, P>(&'a mut self, pat: P) + where + P: for<'x> Pattern<'x>, + { + use core::str::pattern::Searcher; + + let rejections = { + let mut searcher = pat.into_searcher(self); + // Per Searcher::next: + // + // A Match result needs to contain the whole matched pattern, + // however Reject results may be split up into arbitrary many + // adjacent fragments. Both ranges may have zero length. + // + // In practice the implementation of Searcher::next_match tends to + // be more efficient, so we use it here and do some work to invert + // matches into rejections since that's what we want to copy below. + let mut front = 0; + let rejections: Vec<_> = from_fn(|| { + let (start, end) = searcher.next_match()?; + let prev_front = front; + front = end; + Some((prev_front, start)) + }) + .collect(); + rejections.into_iter().chain(core::iter::once((front, self.len()))) + }; + + let mut len = 0; + let ptr = self.vec.as_mut_ptr(); + + for (start, end) in rejections { + let count = end - start; + if start != len { + // SAFETY: per Searcher::next: + // + // The stream of Match and Reject values up to a Done will + // contain index ranges that are adjacent, non-overlapping, + // covering the whole haystack, and laying on utf8 + // boundaries. + unsafe { + ptr::copy(ptr.add(start), ptr.add(len), count); + } + } + len += count; + } + + unsafe { + self.vec.set_len(len); + } + } + + /// Retains only the characters specified by the predicate. + /// + /// In other words, remove all characters `c` such that `f(c)` returns `false`. + /// This method operates in place, visiting each character exactly once in the + /// original order, and preserves the order of the retained characters. + /// + /// # Examples + /// + /// ``` + /// let mut s = String::from("f_o_ob_ar"); + /// + /// s.retain(|c| c != '_'); + /// + /// assert_eq!(s, "foobar"); + /// ``` + /// + /// Because the elements are visited exactly once in the original order, + /// external state may be used to decide which elements to keep. + /// + /// ``` + /// let mut s = String::from("abcde"); + /// let keep = [false, true, true, false, true]; + /// let mut iter = keep.iter(); + /// s.retain(|_| *iter.next().unwrap()); + /// assert_eq!(s, "bce"); + /// ``` + #[inline] + #[stable(feature = "string_retain", since = "1.26.0")] + pub fn retain<F>(&mut self, mut f: F) + where + F: FnMut(char) -> bool, + { + struct SetLenOnDrop<'a> { + s: &'a mut String, + idx: usize, + del_bytes: usize, + } + + impl<'a> Drop for SetLenOnDrop<'a> { + fn drop(&mut self) { + let new_len = self.idx - self.del_bytes; + debug_assert!(new_len <= self.s.len()); + unsafe { self.s.vec.set_len(new_len) }; + } + } + + let len = self.len(); + let mut guard = SetLenOnDrop { s: self, idx: 0, del_bytes: 0 }; + + while guard.idx < len { + let ch = + // SAFETY: `guard.idx` is positive-or-zero and less that len so the `get_unchecked` + // is in bound. `self` is valid UTF-8 like string and the returned slice starts at + // a unicode code point so the `Chars` always return one character. + unsafe { guard.s.get_unchecked(guard.idx..len).chars().next().unwrap_unchecked() }; + let ch_len = ch.len_utf8(); + + if !f(ch) { + guard.del_bytes += ch_len; + } else if guard.del_bytes > 0 { + // SAFETY: `guard.idx` is in bound and `guard.del_bytes` represent the number of + // bytes that are erased from the string so the resulting `guard.idx - + // guard.del_bytes` always represent a valid unicode code point. + // + // `guard.del_bytes` >= `ch.len_utf8()`, so taking a slice with `ch.len_utf8()` len + // is safe. + ch.encode_utf8(unsafe { + crate::slice::from_raw_parts_mut( + guard.s.as_mut_ptr().add(guard.idx - guard.del_bytes), + ch.len_utf8(), + ) + }); + } + + // Point idx to the next char + guard.idx += ch_len; + } + + drop(guard); + } + + /// Inserts a character into this `String` at a byte position. + /// + /// This is an *O*(*n*) operation as it requires copying every element in the + /// buffer. + /// + /// # Panics + /// + /// Panics if `idx` is larger than the `String`'s length, or if it does not + /// lie on a [`char`] boundary. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::with_capacity(3); + /// + /// s.insert(0, 'f'); + /// s.insert(1, 'o'); + /// s.insert(2, 'o'); + /// + /// assert_eq!("foo", s); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn insert(&mut self, idx: usize, ch: char) { + assert!(self.is_char_boundary(idx)); + let mut bits = [0; 4]; + let bits = ch.encode_utf8(&mut bits).as_bytes(); + + unsafe { + self.insert_bytes(idx, bits); + } + } + + #[cfg(not(no_global_oom_handling))] + unsafe fn insert_bytes(&mut self, idx: usize, bytes: &[u8]) { + let len = self.len(); + let amt = bytes.len(); + self.vec.reserve(amt); + + unsafe { + ptr::copy(self.vec.as_ptr().add(idx), self.vec.as_mut_ptr().add(idx + amt), len - idx); + ptr::copy_nonoverlapping(bytes.as_ptr(), self.vec.as_mut_ptr().add(idx), amt); + self.vec.set_len(len + amt); + } + } + + /// Inserts a string slice into this `String` at a byte position. + /// + /// This is an *O*(*n*) operation as it requires copying every element in the + /// buffer. + /// + /// # Panics + /// + /// Panics if `idx` is larger than the `String`'s length, or if it does not + /// lie on a [`char`] boundary. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("bar"); + /// + /// s.insert_str(0, "foo"); + /// + /// assert_eq!("foobar", s); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "insert_str", since = "1.16.0")] + pub fn insert_str(&mut self, idx: usize, string: &str) { + assert!(self.is_char_boundary(idx)); + + unsafe { + self.insert_bytes(idx, string.as_bytes()); + } + } + + /// Returns a mutable reference to the contents of this `String`. + /// + /// # Safety + /// + /// This function is unsafe because the returned `&mut Vec` allows writing + /// bytes which are not valid UTF-8. If this constraint is violated, using + /// the original `String` after dropping the `&mut Vec` may violate memory + /// safety, as the rest of the standard library assumes that `String`s are + /// valid UTF-8. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("hello"); + /// + /// unsafe { + /// let vec = s.as_mut_vec(); + /// assert_eq!(&[104, 101, 108, 108, 111][..], &vec[..]); + /// + /// vec.reverse(); + /// } + /// assert_eq!(s, "olleh"); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub unsafe fn as_mut_vec(&mut self) -> &mut Vec<u8> { + &mut self.vec + } + + /// Returns the length of this `String`, in bytes, not [`char`]s or + /// graphemes. In other words, it might not be what a human considers the + /// length of the string. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let a = String::from("foo"); + /// assert_eq!(a.len(), 3); + /// + /// let fancy_f = String::from("ฦoo"); + /// assert_eq!(fancy_f.len(), 4); + /// assert_eq!(fancy_f.chars().count(), 3); + /// ``` + #[inline] + #[must_use] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn len(&self) -> usize { + self.vec.len() + } + + /// Returns `true` if this `String` has a length of zero, and `false` otherwise. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut v = String::new(); + /// assert!(v.is_empty()); + /// + /// v.push('a'); + /// assert!(!v.is_empty()); + /// ``` + #[inline] + #[must_use] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn is_empty(&self) -> bool { + self.len() == 0 + } + + /// Splits the string into two at the given byte index. + /// + /// Returns a newly allocated `String`. `self` contains bytes `[0, at)`, and + /// the returned `String` contains bytes `[at, len)`. `at` must be on the + /// boundary of a UTF-8 code point. + /// + /// Note that the capacity of `self` does not change. + /// + /// # Panics + /// + /// Panics if `at` is not on a `UTF-8` code point boundary, or if it is beyond the last + /// code point of the string. + /// + /// # Examples + /// + /// ``` + /// # fn main() { + /// let mut hello = String::from("Hello, World!"); + /// let world = hello.split_off(7); + /// assert_eq!(hello, "Hello, "); + /// assert_eq!(world, "World!"); + /// # } + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "string_split_off", since = "1.16.0")] + #[must_use = "use `.truncate()` if you don't need the other half"] + pub fn split_off(&mut self, at: usize) -> String { + assert!(self.is_char_boundary(at)); + let other = self.vec.split_off(at); + unsafe { String::from_utf8_unchecked(other) } + } + + /// Truncates this `String`, removing all contents. + /// + /// While this means the `String` will have a length of zero, it does not + /// touch its capacity. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("foo"); + /// + /// s.clear(); + /// + /// assert!(s.is_empty()); + /// assert_eq!(0, s.len()); + /// assert_eq!(3, s.capacity()); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn clear(&mut self) { + self.vec.clear() + } + + /// Removes the specified range from the string in bulk, returning all + /// removed characters as an iterator. + /// + /// The returned iterator keeps a mutable borrow on the string to optimize + /// its implementation. + /// + /// # Panics + /// + /// Panics if the starting point or end point do not lie on a [`char`] + /// boundary, or if they're out of bounds. + /// + /// # Leaking + /// + /// If the returned iterator goes out of scope without being dropped (due to + /// [`core::mem::forget`], for example), the string may still contain a copy + /// of any drained characters, or may have lost characters arbitrarily, + /// including characters outside the range. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("ฮฑ is alpha, ฮฒ is beta"); + /// let beta_offset = s.find('ฮฒ').unwrap_or(s.len()); + /// + /// // Remove the range up until the ฮฒ from the string + /// let t: String = s.drain(..beta_offset).collect(); + /// assert_eq!(t, "ฮฑ is alpha, "); + /// assert_eq!(s, "ฮฒ is beta"); + /// + /// // A full range clears the string, like `clear()` does + /// s.drain(..); + /// assert_eq!(s, ""); + /// ``` + #[stable(feature = "drain", since = "1.6.0")] + pub fn drain<R>(&mut self, range: R) -> Drain<'_> + where + R: RangeBounds<usize>, + { + // Memory safety + // + // The String version of Drain does not have the memory safety issues + // 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 Range { start, end } = slice::range(range, ..self.len()); + 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 _; + // SAFETY: `slice::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 } + } + + /// Removes the specified range in the string, + /// and replaces it with the given string. + /// The given string doesn't need to be the same length as the range. + /// + /// # Panics + /// + /// Panics if the starting point or end point do not lie on a [`char`] + /// boundary, or if they're out of bounds. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let mut s = String::from("ฮฑ is alpha, ฮฒ is beta"); + /// let beta_offset = s.find('ฮฒ').unwrap_or(s.len()); + /// + /// // Replace the range up until the ฮฒ from the string + /// s.replace_range(..beta_offset, "ฮ is capital alpha; "); + /// assert_eq!(s, "ฮ is capital alpha; ฮฒ is beta"); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "splice", since = "1.27.0")] + pub fn replace_range<R>(&mut self, range: R, replace_with: &str) + where + R: RangeBounds<usize>, + { + // Memory safety + // + // Replace_range does not have the memory safety issues of a vector Splice. + // of the vector version. The data is just plain bytes. + + // WARNING: Inlining this variable would be unsound (#81138) + let start = range.start_bound(); + match start { + Included(&n) => assert!(self.is_char_boundary(n)), + Excluded(&n) => assert!(self.is_char_boundary(n + 1)), + Unbounded => {} + }; + // WARNING: Inlining this variable would be unsound (#81138) + let end = range.end_bound(); + match end { + Included(&n) => assert!(self.is_char_boundary(n + 1)), + Excluded(&n) => assert!(self.is_char_boundary(n)), + Unbounded => {} + }; + + // Using `range` again would be unsound (#81138) + // We assume the bounds reported by `range` remain the same, but + // an adversarial implementation could change between calls + unsafe { self.as_mut_vec() }.splice((start, end), replace_with.bytes()); + } + + /// Converts this `String` into a <code>[Box]<[str]></code>. + /// + /// This will drop any excess capacity. + /// + /// [str]: prim@str "str" + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s = String::from("hello"); + /// + /// let b = s.into_boxed_str(); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "box_str", since = "1.4.0")] + #[must_use = "`self` will be dropped if the result is not used"] + #[inline] + pub fn into_boxed_str(self) -> Box<str> { + let slice = self.vec.into_boxed_slice(); + unsafe { from_boxed_utf8_unchecked(slice) } + } +} + +impl FromUtf8Error { + /// Returns a slice of [`u8`]s bytes that were attempted to convert to a `String`. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// // some invalid bytes, in a vector + /// let bytes = vec![0, 159]; + /// + /// let value = String::from_utf8(bytes); + /// + /// assert_eq!(&[0, 159], value.unwrap_err().as_bytes()); + /// ``` + #[must_use] + #[stable(feature = "from_utf8_error_as_bytes", since = "1.26.0")] + pub fn as_bytes(&self) -> &[u8] { + &self.bytes[..] + } + + /// Returns the bytes that were attempted to convert to a `String`. + /// + /// This method is carefully constructed to avoid allocation. It will + /// consume the error, moving out the bytes, so that a copy of the bytes + /// does not need to be made. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// // some invalid bytes, in a vector + /// let bytes = vec![0, 159]; + /// + /// let value = String::from_utf8(bytes); + /// + /// assert_eq!(vec![0, 159], value.unwrap_err().into_bytes()); + /// ``` + #[must_use = "`self` will be dropped if the result is not used"] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn into_bytes(self) -> Vec<u8> { + self.bytes + } + + /// Fetch a `Utf8Error` to get more details about the conversion failure. + /// + /// The [`Utf8Error`] type provided by [`std::str`] represents an error that may + /// occur when converting a slice of [`u8`]s to a [`&str`]. In this sense, it's + /// an analogue to `FromUtf8Error`. See its documentation for more details + /// on using it. + /// + /// [`std::str`]: core::str "std::str" + /// [`&str`]: prim@str "&str" + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// // some invalid bytes, in a vector + /// let bytes = vec![0, 159]; + /// + /// let error = String::from_utf8(bytes).unwrap_err().utf8_error(); + /// + /// // the first byte is invalid here + /// assert_eq!(1, error.valid_up_to()); + /// ``` + #[must_use] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn utf8_error(&self) -> Utf8Error { + self.error + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl fmt::Display for FromUtf8Error { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Display::fmt(&self.error, f) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl fmt::Display for FromUtf16Error { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Display::fmt("invalid utf-16: lone surrogate found", f) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl Clone for String { + fn clone(&self) -> Self { + String { vec: self.vec.clone() } + } + + fn clone_from(&mut self, source: &Self) { + self.vec.clone_from(&source.vec); + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl FromIterator<char> for String { + fn from_iter<I: IntoIterator<Item = char>>(iter: I) -> String { + let mut buf = String::new(); + buf.extend(iter); + buf + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "string_from_iter_by_ref", since = "1.17.0")] +impl<'a> FromIterator<&'a char> for String { + fn from_iter<I: IntoIterator<Item = &'a char>>(iter: I) -> String { + let mut buf = String::new(); + buf.extend(iter); + buf + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a> FromIterator<&'a str> for String { + fn from_iter<I: IntoIterator<Item = &'a str>>(iter: I) -> String { + let mut buf = String::new(); + buf.extend(iter); + buf + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "extend_string", since = "1.4.0")] +impl FromIterator<String> for String { + fn from_iter<I: IntoIterator<Item = String>>(iter: I) -> String { + let mut iterator = iter.into_iter(); + + // Because we're iterating over `String`s, we can avoid at least + // one allocation by getting the first string from the iterator + // and appending to it all the subsequent strings. + match iterator.next() { + None => String::new(), + Some(mut buf) => { + buf.extend(iterator); + buf + } + } + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_str2", since = "1.45.0")] +impl FromIterator<Box<str>> for String { + fn from_iter<I: IntoIterator<Item = Box<str>>>(iter: I) -> String { + let mut buf = String::new(); + buf.extend(iter); + buf + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "herd_cows", since = "1.19.0")] +impl<'a> FromIterator<Cow<'a, str>> for String { + fn from_iter<I: IntoIterator<Item = Cow<'a, str>>>(iter: I) -> String { + let mut iterator = iter.into_iter(); + + // Because we're iterating over CoWs, we can (potentially) avoid at least + // one allocation by getting the first item and appending to it all the + // subsequent items. + match iterator.next() { + None => String::new(), + Some(cow) => { + let mut buf = cow.into_owned(); + buf.extend(iterator); + buf + } + } + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl Extend<char> for String { + fn extend<I: IntoIterator<Item = char>>(&mut self, iter: I) { + let iterator = iter.into_iter(); + let (lower_bound, _) = iterator.size_hint(); + self.reserve(lower_bound); + iterator.for_each(move |c| self.push(c)); + } + + #[inline] + fn extend_one(&mut self, c: char) { + self.push(c); + } + + #[inline] + fn extend_reserve(&mut self, additional: usize) { + self.reserve(additional); + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "extend_ref", since = "1.2.0")] +impl<'a> Extend<&'a char> for String { + fn extend<I: IntoIterator<Item = &'a char>>(&mut self, iter: I) { + self.extend(iter.into_iter().cloned()); + } + + #[inline] + fn extend_one(&mut self, &c: &'a char) { + self.push(c); + } + + #[inline] + fn extend_reserve(&mut self, additional: usize) { + self.reserve(additional); + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a> Extend<&'a str> for String { + fn extend<I: IntoIterator<Item = &'a str>>(&mut self, iter: I) { + iter.into_iter().for_each(move |s| self.push_str(s)); + } + + #[inline] + fn extend_one(&mut self, s: &'a str) { + self.push_str(s); + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_str2", since = "1.45.0")] +impl Extend<Box<str>> for String { + fn extend<I: IntoIterator<Item = Box<str>>>(&mut self, iter: I) { + iter.into_iter().for_each(move |s| self.push_str(&s)); + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "extend_string", since = "1.4.0")] +impl Extend<String> for String { + fn extend<I: IntoIterator<Item = String>>(&mut self, iter: I) { + iter.into_iter().for_each(move |s| self.push_str(&s)); + } + + #[inline] + fn extend_one(&mut self, s: String) { + self.push_str(&s); + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "herd_cows", since = "1.19.0")] +impl<'a> Extend<Cow<'a, str>> for String { + fn extend<I: IntoIterator<Item = Cow<'a, str>>>(&mut self, iter: I) { + iter.into_iter().for_each(move |s| self.push_str(&s)); + } + + #[inline] + fn extend_one(&mut self, s: Cow<'a, str>) { + self.push_str(&s); + } +} + +/// A convenience impl that delegates to the impl for `&str`. +/// +/// # Examples +/// +/// ``` +/// assert_eq!(String::from("Hello world").find("world"), Some(6)); +/// ``` +#[unstable( + feature = "pattern", + reason = "API not fully fleshed out and ready to be stabilized", + issue = "27721" +)] +impl<'a, 'b> Pattern<'a> for &'b String { + type Searcher = <&'b str as Pattern<'a>>::Searcher; + + fn into_searcher(self, haystack: &'a str) -> <&'b str as Pattern<'a>>::Searcher { + self[..].into_searcher(haystack) + } + + #[inline] + fn is_contained_in(self, haystack: &'a str) -> bool { + self[..].is_contained_in(haystack) + } + + #[inline] + fn is_prefix_of(self, haystack: &'a str) -> bool { + self[..].is_prefix_of(haystack) + } + + #[inline] + fn strip_prefix_of(self, haystack: &'a str) -> Option<&'a str> { + self[..].strip_prefix_of(haystack) + } + + #[inline] + fn is_suffix_of(self, haystack: &'a str) -> bool { + self[..].is_suffix_of(haystack) + } + + #[inline] + fn strip_suffix_of(self, haystack: &'a str) -> Option<&'a str> { + self[..].strip_suffix_of(haystack) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl PartialEq for String { + #[inline] + fn eq(&self, other: &String) -> bool { + PartialEq::eq(&self[..], &other[..]) + } + #[inline] + fn ne(&self, other: &String) -> bool { + PartialEq::ne(&self[..], &other[..]) + } +} + +macro_rules! impl_eq { + ($lhs:ty, $rhs: ty) => { + #[stable(feature = "rust1", since = "1.0.0")] + #[allow(unused_lifetimes)] + impl<'a, 'b> PartialEq<$rhs> for $lhs { + #[inline] + fn eq(&self, other: &$rhs) -> bool { + PartialEq::eq(&self[..], &other[..]) + } + #[inline] + fn ne(&self, other: &$rhs) -> bool { + PartialEq::ne(&self[..], &other[..]) + } + } + + #[stable(feature = "rust1", since = "1.0.0")] + #[allow(unused_lifetimes)] + impl<'a, 'b> PartialEq<$lhs> for $rhs { + #[inline] + fn eq(&self, other: &$lhs) -> bool { + PartialEq::eq(&self[..], &other[..]) + } + #[inline] + fn ne(&self, other: &$lhs) -> bool { + PartialEq::ne(&self[..], &other[..]) + } + } + }; +} + +impl_eq! { String, str } +impl_eq! { String, &'a str } +#[cfg(not(no_global_oom_handling))] +impl_eq! { Cow<'a, str>, str } +#[cfg(not(no_global_oom_handling))] +impl_eq! { Cow<'a, str>, &'b str } +#[cfg(not(no_global_oom_handling))] +impl_eq! { Cow<'a, str>, String } + +#[stable(feature = "rust1", since = "1.0.0")] +#[rustc_const_unstable(feature = "const_default_impls", issue = "87864")] +impl const Default for String { + /// Creates an empty `String`. + #[inline] + fn default() -> String { + String::new() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl fmt::Display for String { + #[inline] + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Display::fmt(&**self, f) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl fmt::Debug for String { + #[inline] + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(&**self, f) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl hash::Hash for String { + #[inline] + fn hash<H: hash::Hasher>(&self, hasher: &mut H) { + (**self).hash(hasher) + } +} + +/// Implements the `+` operator for concatenating two strings. +/// +/// This consumes the `String` on the left-hand side and re-uses its buffer (growing it if +/// necessary). This is done to avoid allocating a new `String` and copying the entire contents on +/// every operation, which would lead to *O*(*n*^2) running time when building an *n*-byte string by +/// repeated concatenation. +/// +/// The string on the right-hand side is only borrowed; its contents are copied into the returned +/// `String`. +/// +/// # Examples +/// +/// Concatenating two `String`s takes the first by value and borrows the second: +/// +/// ``` +/// let a = String::from("hello"); +/// let b = String::from(" world"); +/// let c = a + &b; +/// // `a` is moved and can no longer be used here. +/// ``` +/// +/// If you want to keep using the first `String`, you can clone it and append to the clone instead: +/// +/// ``` +/// let a = String::from("hello"); +/// let b = String::from(" world"); +/// let c = a.clone() + &b; +/// // `a` is still valid here. +/// ``` +/// +/// Concatenating `&str` slices can be done by converting the first to a `String`: +/// +/// ``` +/// let a = "hello"; +/// let b = " world"; +/// let c = a.to_string() + b; +/// ``` +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl Add<&str> for String { + type Output = String; + + #[inline] + fn add(mut self, other: &str) -> String { + self.push_str(other); + self + } +} + +/// Implements the `+=` operator for appending to a `String`. +/// +/// This has the same behavior as the [`push_str`][String::push_str] method. +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "stringaddassign", since = "1.12.0")] +impl AddAssign<&str> for String { + #[inline] + fn add_assign(&mut self, other: &str) { + self.push_str(other); + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl ops::Index<ops::Range<usize>> for String { + type Output = str; + + #[inline] + fn index(&self, index: ops::Range<usize>) -> &str { + &self[..][index] + } +} +#[stable(feature = "rust1", since = "1.0.0")] +impl ops::Index<ops::RangeTo<usize>> for String { + type Output = str; + + #[inline] + fn index(&self, index: ops::RangeTo<usize>) -> &str { + &self[..][index] + } +} +#[stable(feature = "rust1", since = "1.0.0")] +impl ops::Index<ops::RangeFrom<usize>> for String { + type Output = str; + + #[inline] + fn index(&self, index: ops::RangeFrom<usize>) -> &str { + &self[..][index] + } +} +#[stable(feature = "rust1", since = "1.0.0")] +impl ops::Index<ops::RangeFull> for String { + type Output = str; + + #[inline] + fn index(&self, _index: ops::RangeFull) -> &str { + unsafe { str::from_utf8_unchecked(&self.vec) } + } +} +#[stable(feature = "inclusive_range", since = "1.26.0")] +impl ops::Index<ops::RangeInclusive<usize>> for String { + type Output = str; + + #[inline] + fn index(&self, index: ops::RangeInclusive<usize>) -> &str { + Index::index(&**self, index) + } +} +#[stable(feature = "inclusive_range", since = "1.26.0")] +impl ops::Index<ops::RangeToInclusive<usize>> for String { + type Output = str; + + #[inline] + fn index(&self, index: ops::RangeToInclusive<usize>) -> &str { + Index::index(&**self, index) + } +} + +#[stable(feature = "derefmut_for_string", since = "1.3.0")] +impl ops::IndexMut<ops::Range<usize>> for String { + #[inline] + fn index_mut(&mut self, index: ops::Range<usize>) -> &mut str { + &mut self[..][index] + } +} +#[stable(feature = "derefmut_for_string", since = "1.3.0")] +impl ops::IndexMut<ops::RangeTo<usize>> for String { + #[inline] + fn index_mut(&mut self, index: ops::RangeTo<usize>) -> &mut str { + &mut self[..][index] + } +} +#[stable(feature = "derefmut_for_string", since = "1.3.0")] +impl ops::IndexMut<ops::RangeFrom<usize>> for String { + #[inline] + fn index_mut(&mut self, index: ops::RangeFrom<usize>) -> &mut str { + &mut self[..][index] + } +} +#[stable(feature = "derefmut_for_string", since = "1.3.0")] +impl ops::IndexMut<ops::RangeFull> for String { + #[inline] + fn index_mut(&mut self, _index: ops::RangeFull) -> &mut str { + unsafe { str::from_utf8_unchecked_mut(&mut *self.vec) } + } +} +#[stable(feature = "inclusive_range", since = "1.26.0")] +impl ops::IndexMut<ops::RangeInclusive<usize>> for String { + #[inline] + fn index_mut(&mut self, index: ops::RangeInclusive<usize>) -> &mut str { + IndexMut::index_mut(&mut **self, index) + } +} +#[stable(feature = "inclusive_range", since = "1.26.0")] +impl ops::IndexMut<ops::RangeToInclusive<usize>> for String { + #[inline] + fn index_mut(&mut self, index: ops::RangeToInclusive<usize>) -> &mut str { + IndexMut::index_mut(&mut **self, index) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl ops::Deref for String { + type Target = str; + + #[inline] + fn deref(&self) -> &str { + unsafe { str::from_utf8_unchecked(&self.vec) } + } +} + +#[stable(feature = "derefmut_for_string", since = "1.3.0")] +impl ops::DerefMut for String { + #[inline] + fn deref_mut(&mut self) -> &mut str { + unsafe { str::from_utf8_unchecked_mut(&mut *self.vec) } + } +} + +/// A type alias for [`Infallible`]. +/// +/// This alias exists for backwards compatibility, and may be eventually deprecated. +/// +/// [`Infallible`]: core::convert::Infallible "convert::Infallible" +#[stable(feature = "str_parse_error", since = "1.5.0")] +pub type ParseError = core::convert::Infallible; + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl FromStr for String { + type Err = core::convert::Infallible; + #[inline] + fn from_str(s: &str) -> Result<String, Self::Err> { + Ok(String::from(s)) + } +} + +/// A trait for converting a value to a `String`. +/// +/// This trait is automatically implemented for any type which implements the +/// [`Display`] trait. As such, `ToString` shouldn't be implemented directly: +/// [`Display`] should be implemented instead, and you get the `ToString` +/// implementation for free. +/// +/// [`Display`]: fmt::Display +#[cfg_attr(not(test), rustc_diagnostic_item = "ToString")] +#[stable(feature = "rust1", since = "1.0.0")] +pub trait ToString { + /// Converts the given value to a `String`. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let i = 5; + /// let five = String::from("5"); + /// + /// assert_eq!(five, i.to_string()); + /// ``` + #[rustc_conversion_suggestion] + #[stable(feature = "rust1", since = "1.0.0")] + fn to_string(&self) -> String; +} + +/// # Panics +/// +/// In this implementation, the `to_string` method panics +/// if the `Display` implementation returns an error. +/// This indicates an incorrect `Display` implementation +/// since `fmt::Write for String` never returns an error itself. +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: fmt::Display + ?Sized> ToString for T { + // A common guideline is to not inline generic functions. However, + // removing `#[inline]` from this method causes non-negligible regressions. + // See <https://github.com/rust-lang/rust/pull/74852>, the last attempt + // to try to remove it. + #[inline] + default fn to_string(&self) -> String { + let mut buf = String::new(); + let mut formatter = core::fmt::Formatter::new(&mut buf); + // Bypass format_args!() to avoid write_str with zero-length strs + fmt::Display::fmt(self, &mut formatter) + .expect("a Display implementation returned an error unexpectedly"); + buf + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "char_to_string_specialization", since = "1.46.0")] +impl ToString for char { + #[inline] + fn to_string(&self) -> String { + String::from(self.encode_utf8(&mut [0; 4])) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "u8_to_string_specialization", since = "1.54.0")] +impl ToString for u8 { + #[inline] + fn to_string(&self) -> String { + let mut buf = String::with_capacity(3); + let mut n = *self; + if n >= 10 { + if n >= 100 { + buf.push((b'0' + n / 100) as char); + n %= 100; + } + buf.push((b'0' + n / 10) as char); + n %= 10; + } + buf.push((b'0' + n) as char); + buf + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "i8_to_string_specialization", since = "1.54.0")] +impl ToString for i8 { + #[inline] + fn to_string(&self) -> String { + let mut buf = String::with_capacity(4); + if self.is_negative() { + buf.push('-'); + } + let mut n = self.unsigned_abs(); + if n >= 10 { + if n >= 100 { + buf.push('1'); + n -= 100; + } + buf.push((b'0' + n / 10) as char); + n %= 10; + } + buf.push((b'0' + n) as char); + buf + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "str_to_string_specialization", since = "1.9.0")] +impl ToString for str { + #[inline] + fn to_string(&self) -> String { + String::from(self) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_str_to_string_specialization", since = "1.17.0")] +impl ToString for Cow<'_, str> { + #[inline] + fn to_string(&self) -> String { + self[..].to_owned() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "string_to_string_specialization", since = "1.17.0")] +impl ToString for String { + #[inline] + fn to_string(&self) -> String { + self.to_owned() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl AsRef<str> for String { + #[inline] + fn as_ref(&self) -> &str { + self + } +} + +#[stable(feature = "string_as_mut", since = "1.43.0")] +impl AsMut<str> for String { + #[inline] + fn as_mut(&mut self) -> &mut str { + self + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl AsRef<[u8]> for String { + #[inline] + fn as_ref(&self) -> &[u8] { + self.as_bytes() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl From<&str> for String { + /// Converts a `&str` into a [`String`]. + /// + /// The result is allocated on the heap. + #[inline] + fn from(s: &str) -> String { + s.to_owned() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "from_mut_str_for_string", since = "1.44.0")] +impl From<&mut str> for String { + /// Converts a `&mut str` into a [`String`]. + /// + /// The result is allocated on the heap. + #[inline] + fn from(s: &mut str) -> String { + s.to_owned() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "from_ref_string", since = "1.35.0")] +impl From<&String> for String { + /// Converts a `&String` into a [`String`]. + /// + /// This clones `s` and returns the clone. + #[inline] + fn from(s: &String) -> String { + s.clone() + } +} + +// note: test pulls in libstd, which causes errors here +#[cfg(not(test))] +#[stable(feature = "string_from_box", since = "1.18.0")] +impl From<Box<str>> for String { + /// Converts the given boxed `str` slice to a [`String`]. + /// It is notable that the `str` slice is owned. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s1: String = String::from("hello world"); + /// let s2: Box<str> = s1.into_boxed_str(); + /// let s3: String = String::from(s2); + /// + /// assert_eq!("hello world", s3) + /// ``` + fn from(s: Box<str>) -> String { + s.into_string() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_from_str", since = "1.20.0")] +impl From<String> for Box<str> { + /// Converts the given [`String`] to a boxed `str` slice that is owned. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s1: String = String::from("hello world"); + /// let s2: Box<str> = Box::from(s1); + /// let s3: String = String::from(s2); + /// + /// assert_eq!("hello world", s3) + /// ``` + fn from(s: String) -> Box<str> { + s.into_boxed_str() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "string_from_cow_str", since = "1.14.0")] +impl<'a> From<Cow<'a, str>> for String { + /// Converts a clone-on-write string to an owned + /// instance of [`String`]. + /// + /// This extracts the owned string, + /// clones the string if it is not already owned. + /// + /// # Example + /// + /// ``` + /// # use std::borrow::Cow; + /// // If the string is not owned... + /// let cow: Cow<str> = Cow::Borrowed("eggplant"); + /// // It will allocate on the heap and copy the string. + /// let owned: String = String::from(cow); + /// assert_eq!(&owned[..], "eggplant"); + /// ``` + fn from(s: Cow<'a, str>) -> String { + s.into_owned() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a> From<&'a str> for Cow<'a, str> { + /// Converts a string slice into a [`Borrowed`] variant. + /// No heap allocation is performed, and the string + /// is not copied. + /// + /// # Example + /// + /// ``` + /// # use std::borrow::Cow; + /// assert_eq!(Cow::from("eggplant"), Cow::Borrowed("eggplant")); + /// ``` + /// + /// [`Borrowed`]: crate::borrow::Cow::Borrowed "borrow::Cow::Borrowed" + #[inline] + fn from(s: &'a str) -> Cow<'a, str> { + Cow::Borrowed(s) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a> From<String> for Cow<'a, str> { + /// Converts a [`String`] into an [`Owned`] variant. + /// No heap allocation is performed, and the string + /// is not copied. + /// + /// # Example + /// + /// ``` + /// # use std::borrow::Cow; + /// let s = "eggplant".to_string(); + /// let s2 = "eggplant".to_string(); + /// assert_eq!(Cow::from(s), Cow::<'static, str>::Owned(s2)); + /// ``` + /// + /// [`Owned`]: crate::borrow::Cow::Owned "borrow::Cow::Owned" + #[inline] + fn from(s: String) -> Cow<'a, str> { + Cow::Owned(s) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_from_string_ref", since = "1.28.0")] +impl<'a> From<&'a String> for Cow<'a, str> { + /// Converts a [`String`] reference into a [`Borrowed`] variant. + /// No heap allocation is performed, and the string + /// is not copied. + /// + /// # Example + /// + /// ``` + /// # use std::borrow::Cow; + /// let s = "eggplant".to_string(); + /// assert_eq!(Cow::from(&s), Cow::Borrowed("eggplant")); + /// ``` + /// + /// [`Borrowed`]: crate::borrow::Cow::Borrowed "borrow::Cow::Borrowed" + #[inline] + fn from(s: &'a String) -> Cow<'a, str> { + Cow::Borrowed(s.as_str()) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_str_from_iter", since = "1.12.0")] +impl<'a> FromIterator<char> for Cow<'a, str> { + fn from_iter<I: IntoIterator<Item = char>>(it: I) -> Cow<'a, str> { + Cow::Owned(FromIterator::from_iter(it)) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_str_from_iter", since = "1.12.0")] +impl<'a, 'b> FromIterator<&'b str> for Cow<'a, str> { + fn from_iter<I: IntoIterator<Item = &'b str>>(it: I) -> Cow<'a, str> { + Cow::Owned(FromIterator::from_iter(it)) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_str_from_iter", since = "1.12.0")] +impl<'a> FromIterator<String> for Cow<'a, str> { + fn from_iter<I: IntoIterator<Item = String>>(it: I) -> Cow<'a, str> { + Cow::Owned(FromIterator::from_iter(it)) + } +} + +#[stable(feature = "from_string_for_vec_u8", since = "1.14.0")] +impl From<String> for Vec<u8> { + /// Converts the given [`String`] to a vector [`Vec`] that holds values of type [`u8`]. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s1 = String::from("hello world"); + /// let v1 = Vec::from(s1); + /// + /// for b in v1 { + /// println!("{b}"); + /// } + /// ``` + fn from(string: String) -> Vec<u8> { + string.into_bytes() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl fmt::Write for String { + #[inline] + fn write_str(&mut self, s: &str) -> fmt::Result { + self.push_str(s); + Ok(()) + } + + #[inline] + fn write_char(&mut self, c: char) -> fmt::Result { + self.push(c); + Ok(()) + } +} + +/// A draining iterator for `String`. +/// +/// This struct is created by the [`drain`] method on [`String`]. See its +/// documentation for more. +/// +/// [`drain`]: String::drain +#[stable(feature = "drain", since = "1.6.0")] +pub struct Drain<'a> { + /// Will be used as &'a mut String in the destructor + string: *mut String, + /// Start of part to remove + start: usize, + /// End of part to remove + end: usize, + /// Current remaining range to remove + iter: Chars<'a>, +} + +#[stable(feature = "collection_debug", since = "1.17.0")] +impl fmt::Debug for Drain<'_> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.debug_tuple("Drain").field(&self.as_str()).finish() + } +} + +#[stable(feature = "drain", since = "1.6.0")] +unsafe impl Sync for Drain<'_> {} +#[stable(feature = "drain", since = "1.6.0")] +unsafe impl Send for Drain<'_> {} + +#[stable(feature = "drain", since = "1.6.0")] +impl Drop for Drain<'_> { + fn drop(&mut self) { + unsafe { + // Use Vec::drain. "Reaffirm" the bounds checks to avoid + // panic code being inserted again. + let self_vec = (*self.string).as_mut_vec(); + if self.start <= self.end && self.end <= self_vec.len() { + self_vec.drain(self.start..self.end); + } + } + } +} + +impl<'a> Drain<'a> { + /// Returns the remaining (sub)string of this iterator as a slice. + /// + /// # Examples + /// + /// ``` + /// let mut s = String::from("abc"); + /// let mut drain = s.drain(..); + /// assert_eq!(drain.as_str(), "abc"); + /// let _ = drain.next().unwrap(); + /// assert_eq!(drain.as_str(), "bc"); + /// ``` + #[must_use] + #[stable(feature = "string_drain_as_str", since = "1.55.0")] + pub fn as_str(&self) -> &str { + self.iter.as_str() + } +} + +#[stable(feature = "string_drain_as_str", since = "1.55.0")] +impl<'a> AsRef<str> for Drain<'a> { + fn as_ref(&self) -> &str { + self.as_str() + } +} + +#[stable(feature = "string_drain_as_str", since = "1.55.0")] +impl<'a> AsRef<[u8]> for Drain<'a> { + fn as_ref(&self) -> &[u8] { + self.as_str().as_bytes() + } +} + +#[stable(feature = "drain", since = "1.6.0")] +impl Iterator for Drain<'_> { + type Item = char; + + #[inline] + fn next(&mut self) -> Option<char> { + self.iter.next() + } + + fn size_hint(&self) -> (usize, Option<usize>) { + self.iter.size_hint() + } + + #[inline] + fn last(mut self) -> Option<char> { + self.next_back() + } +} + +#[stable(feature = "drain", since = "1.6.0")] +impl DoubleEndedIterator for Drain<'_> { + #[inline] + fn next_back(&mut self) -> Option<char> { + self.iter.next_back() + } +} + +#[stable(feature = "fused", since = "1.26.0")] +impl FusedIterator for Drain<'_> {} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "from_char_for_string", since = "1.46.0")] +impl From<char> for String { + /// Allocates an owned [`String`] from a single character. + /// + /// # Example + /// ```rust + /// let c: char = 'a'; + /// let s: String = String::from(c); + /// assert_eq!("a", &s[..]); + /// ``` + #[inline] + fn from(c: char) -> Self { + c.to_string() + } +} |