diff options
Diffstat (limited to 'library/std/src/io/mod.rs')
| -rw-r--r-- | library/std/src/io/mod.rs | 2993 |
1 files changed, 2993 insertions, 0 deletions
diff --git a/library/std/src/io/mod.rs b/library/std/src/io/mod.rs new file mode 100644 index 00000000000..9eb54c2cc00 --- /dev/null +++ b/library/std/src/io/mod.rs @@ -0,0 +1,2993 @@ +//! Traits, helpers, and type definitions for core I/O functionality. +//! +//! The `std::io` module contains a number of common things you'll need +//! when doing input and output. The most core part of this module is +//! the [`Read`] and [`Write`] traits, which provide the +//! most general interface for reading and writing input and output. +//! +//! # Read and Write +//! +//! Because they are traits, [`Read`] and [`Write`] are implemented by a number +//! of other types, and you can implement them for your types too. As such, +//! you'll see a few different types of I/O throughout the documentation in +//! this module: [`File`]s, [`TcpStream`]s, and sometimes even [`Vec<T>`]s. For +//! example, [`Read`] adds a [`read`][`Read::read`] method, which we can use on +//! [`File`]s: +//! +//! ```no_run +//! use std::io; +//! use std::io::prelude::*; +//! use std::fs::File; +//! +//! fn main() -> io::Result<()> { +//! let mut f = File::open("foo.txt")?; +//! let mut buffer = [0; 10]; +//! +//! // read up to 10 bytes +//! let n = f.read(&mut buffer)?; +//! +//! println!("The bytes: {:?}", &buffer[..n]); +//! Ok(()) +//! } +//! ``` +//! +//! [`Read`] and [`Write`] are so important, implementors of the two traits have a +//! nickname: readers and writers. So you'll sometimes see 'a reader' instead +//! of 'a type that implements the [`Read`] trait'. Much easier! +//! +//! ## Seek and BufRead +//! +//! Beyond that, there are two important traits that are provided: [`Seek`] +//! and [`BufRead`]. Both of these build on top of a reader to control +//! how the reading happens. [`Seek`] lets you control where the next byte is +//! coming from: +//! +//! ```no_run +//! use std::io; +//! use std::io::prelude::*; +//! use std::io::SeekFrom; +//! use std::fs::File; +//! +//! fn main() -> io::Result<()> { +//! let mut f = File::open("foo.txt")?; +//! let mut buffer = [0; 10]; +//! +//! // skip to the last 10 bytes of the file +//! f.seek(SeekFrom::End(-10))?; +//! +//! // read up to 10 bytes +//! let n = f.read(&mut buffer)?; +//! +//! println!("The bytes: {:?}", &buffer[..n]); +//! Ok(()) +//! } +//! ``` +//! +//! [`BufRead`] uses an internal buffer to provide a number of other ways to read, but +//! to show it off, we'll need to talk about buffers in general. Keep reading! +//! +//! ## BufReader and BufWriter +//! +//! Byte-based interfaces are unwieldy and can be inefficient, as we'd need to be +//! making near-constant calls to the operating system. To help with this, +//! `std::io` comes with two structs, [`BufReader`] and [`BufWriter`], which wrap +//! readers and writers. The wrapper uses a buffer, reducing the number of +//! calls and providing nicer methods for accessing exactly what you want. +//! +//! For example, [`BufReader`] works with the [`BufRead`] trait to add extra +//! methods to any reader: +//! +//! ```no_run +//! use std::io; +//! use std::io::prelude::*; +//! use std::io::BufReader; +//! use std::fs::File; +//! +//! fn main() -> io::Result<()> { +//! let f = File::open("foo.txt")?; +//! let mut reader = BufReader::new(f); +//! let mut buffer = String::new(); +//! +//! // read a line into buffer +//! reader.read_line(&mut buffer)?; +//! +//! println!("{}", buffer); +//! Ok(()) +//! } +//! ``` +//! +//! [`BufWriter`] doesn't add any new ways of writing; it just buffers every call +//! to [`write`][`Write::write`]: +//! +//! ```no_run +//! use std::io; +//! use std::io::prelude::*; +//! use std::io::BufWriter; +//! use std::fs::File; +//! +//! fn main() -> io::Result<()> { +//! let f = File::create("foo.txt")?; +//! { +//! let mut writer = BufWriter::new(f); +//! +//! // write a byte to the buffer +//! writer.write(&[42])?; +//! +//! } // the buffer is flushed once writer goes out of scope +//! +//! Ok(()) +//! } +//! ``` +//! +//! ## Standard input and output +//! +//! A very common source of input is standard input: +//! +//! ```no_run +//! use std::io; +//! +//! fn main() -> io::Result<()> { +//! let mut input = String::new(); +//! +//! io::stdin().read_line(&mut input)?; +//! +//! println!("You typed: {}", input.trim()); +//! Ok(()) +//! } +//! ``` +//! +//! Note that you cannot use the [`?` operator] in functions that do not return +//! a [`Result<T, E>`][`Result`]. Instead, you can call [`.unwrap()`] +//! or `match` on the return value to catch any possible errors: +//! +//! ```no_run +//! use std::io; +//! +//! let mut input = String::new(); +//! +//! io::stdin().read_line(&mut input).unwrap(); +//! ``` +//! +//! And a very common source of output is standard output: +//! +//! ```no_run +//! use std::io; +//! use std::io::prelude::*; +//! +//! fn main() -> io::Result<()> { +//! io::stdout().write(&[42])?; +//! Ok(()) +//! } +//! ``` +//! +//! Of course, using [`io::stdout`] directly is less common than something like +//! [`println!`]. +//! +//! ## Iterator types +//! +//! A large number of the structures provided by `std::io` are for various +//! ways of iterating over I/O. For example, [`Lines`] is used to split over +//! lines: +//! +//! ```no_run +//! use std::io; +//! use std::io::prelude::*; +//! use std::io::BufReader; +//! use std::fs::File; +//! +//! fn main() -> io::Result<()> { +//! let f = File::open("foo.txt")?; +//! let reader = BufReader::new(f); +//! +//! for line in reader.lines() { +//! println!("{}", line?); +//! } +//! Ok(()) +//! } +//! ``` +//! +//! ## Functions +//! +//! There are a number of [functions][functions-list] that offer access to various +//! features. For example, we can use three of these functions to copy everything +//! from standard input to standard output: +//! +//! ```no_run +//! use std::io; +//! +//! fn main() -> io::Result<()> { +//! io::copy(&mut io::stdin(), &mut io::stdout())?; +//! Ok(()) +//! } +//! ``` +//! +//! [functions-list]: #functions-1 +//! +//! ## io::Result +//! +//! Last, but certainly not least, is [`io::Result`]. This type is used +//! as the return type of many `std::io` functions that can cause an error, and +//! can be returned from your own functions as well. Many of the examples in this +//! module use the [`?` operator]: +//! +//! ``` +//! use std::io; +//! +//! fn read_input() -> io::Result<()> { +//! let mut input = String::new(); +//! +//! io::stdin().read_line(&mut input)?; +//! +//! println!("You typed: {}", input.trim()); +//! +//! Ok(()) +//! } +//! ``` +//! +//! The return type of `read_input()`, [`io::Result<()>`][`io::Result`], is a very +//! common type for functions which don't have a 'real' return value, but do want to +//! return errors if they happen. In this case, the only purpose of this function is +//! to read the line and print it, so we use `()`. +//! +//! ## Platform-specific behavior +//! +//! Many I/O functions throughout the standard library are documented to indicate +//! what various library or syscalls they are delegated to. This is done to help +//! applications both understand what's happening under the hood as well as investigate +//! any possibly unclear semantics. Note, however, that this is informative, not a binding +//! contract. The implementation of many of these functions are subject to change over +//! time and may call fewer or more syscalls/library functions. +//! +//! [`File`]: crate::fs::File +//! [`TcpStream`]: crate::net::TcpStream +//! [`Vec<T>`]: crate::vec::Vec +//! [`io::stdout`]: stdout +//! [`io::Result`]: crate::io::Result +//! [`?` operator]: ../../book/appendix-02-operators.html +//! [`Result`]: crate::result::Result +//! [`.unwrap()`]: crate::result::Result::unwrap + +#![stable(feature = "rust1", since = "1.0.0")] + +use crate::cmp; +use crate::fmt; +use crate::memchr; +use crate::ops::{Deref, DerefMut}; +use crate::ptr; +use crate::slice; +use crate::str; +use crate::sys; + +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::buffered::IntoInnerError; +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::buffered::{BufReader, BufWriter, LineWriter}; +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::cursor::Cursor; +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::error::{Error, ErrorKind, Result}; +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::stdio::{stderr, stdin, stdout, Stderr, Stdin, Stdout}; +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::stdio::{StderrLock, StdinLock, StdoutLock}; +#[unstable(feature = "print_internals", issue = "none")] +pub use self::stdio::{_eprint, _print}; +#[unstable(feature = "libstd_io_internals", issue = "42788")] +#[doc(no_inline, hidden)] +pub use self::stdio::{set_panic, set_print}; +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::util::{copy, empty, repeat, sink, Empty, Repeat, Sink}; + +mod buffered; +mod cursor; +mod error; +mod impls; +mod lazy; +pub mod prelude; +mod stdio; +mod util; + +const DEFAULT_BUF_SIZE: usize = crate::sys_common::io::DEFAULT_BUF_SIZE; + +struct Guard<'a> { + buf: &'a mut Vec<u8>, + len: usize, +} + +impl Drop for Guard<'_> { + fn drop(&mut self) { + unsafe { + self.buf.set_len(self.len); + } + } +} + +// A few methods below (read_to_string, read_line) will append data into a +// `String` buffer, but we need to be pretty careful when doing this. The +// implementation will just call `.as_mut_vec()` and then delegate to a +// byte-oriented reading method, but we must ensure that when returning we never +// leave `buf` in a state such that it contains invalid UTF-8 in its bounds. +// +// To this end, we use an RAII guard (to protect against panics) which updates +// the length of the string when it is dropped. This guard initially truncates +// the string to the prior length and only after we've validated that the +// new contents are valid UTF-8 do we allow it to set a longer length. +// +// The unsafety in this function is twofold: +// +// 1. We're looking at the raw bytes of `buf`, so we take on the burden of UTF-8 +// checks. +// 2. We're passing a raw buffer to the function `f`, and it is expected that +// the function only *appends* bytes to the buffer. We'll get undefined +// behavior if existing bytes are overwritten to have non-UTF-8 data. +fn append_to_string<F>(buf: &mut String, f: F) -> Result<usize> +where + F: FnOnce(&mut Vec<u8>) -> Result<usize>, +{ + unsafe { + let mut g = Guard { len: buf.len(), buf: buf.as_mut_vec() }; + let ret = f(g.buf); + if str::from_utf8(&g.buf[g.len..]).is_err() { + ret.and_then(|_| { + Err(Error::new(ErrorKind::InvalidData, "stream did not contain valid UTF-8")) + }) + } else { + g.len = g.buf.len(); + ret + } + } +} + +// This uses an adaptive system to extend the vector when it fills. We want to +// avoid paying to allocate and zero a huge chunk of memory if the reader only +// has 4 bytes while still making large reads if the reader does have a ton +// of data to return. Simply tacking on an extra DEFAULT_BUF_SIZE space every +// time is 4,500 times (!) slower than a default reservation size of 32 if the +// reader has a very small amount of data to return. +// +// Because we're extending the buffer with uninitialized data for trusted +// readers, we need to make sure to truncate that if any of this panics. +fn read_to_end<R: Read + ?Sized>(r: &mut R, buf: &mut Vec<u8>) -> Result<usize> { + read_to_end_with_reservation(r, buf, |_| 32) +} + +fn read_to_end_with_reservation<R, F>( + r: &mut R, + buf: &mut Vec<u8>, + mut reservation_size: F, +) -> Result<usize> +where + R: Read + ?Sized, + F: FnMut(&R) -> usize, +{ + let start_len = buf.len(); + let mut g = Guard { len: buf.len(), buf }; + let ret; + loop { + if g.len == g.buf.len() { + unsafe { + // FIXME(danielhenrymantilla): #42788 + // + // - This creates a (mut) reference to a slice of + // _uninitialized_ integers, which is **undefined behavior** + // + // - Only the standard library gets to soundly "ignore" this, + // based on its privileged knowledge of unstable rustc + // internals; + g.buf.reserve(reservation_size(r)); + let capacity = g.buf.capacity(); + g.buf.set_len(capacity); + r.initializer().initialize(&mut g.buf[g.len..]); + } + } + + match r.read(&mut g.buf[g.len..]) { + Ok(0) => { + ret = Ok(g.len - start_len); + break; + } + Ok(n) => g.len += n, + Err(ref e) if e.kind() == ErrorKind::Interrupted => {} + Err(e) => { + ret = Err(e); + break; + } + } + } + + ret +} + +pub(crate) fn default_read_vectored<F>(read: F, bufs: &mut [IoSliceMut<'_>]) -> Result<usize> +where + F: FnOnce(&mut [u8]) -> Result<usize>, +{ + let buf = bufs.iter_mut().find(|b| !b.is_empty()).map_or(&mut [][..], |b| &mut **b); + read(buf) +} + +pub(crate) fn default_write_vectored<F>(write: F, bufs: &[IoSlice<'_>]) -> Result<usize> +where + F: FnOnce(&[u8]) -> Result<usize>, +{ + let buf = bufs.iter().find(|b| !b.is_empty()).map_or(&[][..], |b| &**b); + write(buf) +} + +/// The `Read` trait allows for reading bytes from a source. +/// +/// Implementors of the `Read` trait are called 'readers'. +/// +/// Readers are defined by one required method, [`read()`]. Each call to [`read()`] +/// will attempt to pull bytes from this source into a provided buffer. A +/// number of other methods are implemented in terms of [`read()`], giving +/// implementors a number of ways to read bytes while only needing to implement +/// a single method. +/// +/// Readers are intended to be composable with one another. Many implementors +/// throughout [`std::io`] take and provide types which implement the `Read` +/// trait. +/// +/// Please note that each call to [`read()`] may involve a system call, and +/// therefore, using something that implements [`BufRead`], such as +/// [`BufReader`], will be more efficient. +/// +/// # Examples +/// +/// [`File`]s implement `Read`: +/// +/// ```no_run +/// use std::io; +/// use std::io::prelude::*; +/// use std::fs::File; +/// +/// fn main() -> io::Result<()> { +/// let mut f = File::open("foo.txt")?; +/// let mut buffer = [0; 10]; +/// +/// // read up to 10 bytes +/// f.read(&mut buffer)?; +/// +/// let mut buffer = Vec::new(); +/// // read the whole file +/// f.read_to_end(&mut buffer)?; +/// +/// // read into a String, so that you don't need to do the conversion. +/// let mut buffer = String::new(); +/// f.read_to_string(&mut buffer)?; +/// +/// // and more! See the other methods for more details. +/// Ok(()) +/// } +/// ``` +/// +/// Read from [`&str`] because [`&[u8]`][slice] implements `Read`: +/// +/// ```no_run +/// # use std::io; +/// use std::io::prelude::*; +/// +/// fn main() -> io::Result<()> { +/// let mut b = "This string will be read".as_bytes(); +/// let mut buffer = [0; 10]; +/// +/// // read up to 10 bytes +/// b.read(&mut buffer)?; +/// +/// // etc... it works exactly as a File does! +/// Ok(()) +/// } +/// ``` +/// +/// [`read()`]: Read::read +/// [`&str`]: str +/// [`std::io`]: self +/// [`File`]: crate::fs::File +/// [slice]: ../../std/primitive.slice.html +#[stable(feature = "rust1", since = "1.0.0")] +#[doc(spotlight)] +pub trait Read { + /// Pull some bytes from this source into the specified buffer, returning + /// how many bytes were read. + /// + /// This function does not provide any guarantees about whether it blocks + /// waiting for data, but if an object needs to block for a read and cannot, + /// it will typically signal this via an [`Err`] return value. + /// + /// If the return value of this method is [`Ok(n)`], then it must be + /// guaranteed that `0 <= n <= buf.len()`. A nonzero `n` value indicates + /// that the buffer `buf` has been filled in with `n` bytes of data from this + /// source. If `n` is `0`, then it can indicate one of two scenarios: + /// + /// 1. This reader has reached its "end of file" and will likely no longer + /// be able to produce bytes. Note that this does not mean that the + /// reader will *always* no longer be able to produce bytes. + /// 2. The buffer specified was 0 bytes in length. + /// + /// It is not an error if the returned value `n` is smaller than the buffer size, + /// even when the reader is not at the end of the stream yet. + /// This may happen for example because fewer bytes are actually available right now + /// (e. g. being close to end-of-file) or because read() was interrupted by a signal. + /// + /// No guarantees are provided about the contents of `buf` when this + /// function is called, implementations cannot rely on any property of the + /// contents of `buf` being true. It is recommended that *implementations* + /// only write data to `buf` instead of reading its contents. + /// + /// Correspondingly, however, *callers* of this method may not assume any guarantees + /// about how the implementation uses `buf`. The trait is safe to implement, + /// so it is possible that the code that's supposed to write to the buffer might also read + /// from it. It is your responsibility to make sure that `buf` is initialized + /// before calling `read`. Calling `read` with an uninitialized `buf` (of the kind one + /// obtains via [`MaybeUninit<T>`]) is not safe, and can lead to undefined behavior. + /// + /// [`MaybeUninit<T>`]: crate::mem::MaybeUninit + /// + /// # Errors + /// + /// If this function encounters any form of I/O or other error, an error + /// variant will be returned. If an error is returned then it must be + /// guaranteed that no bytes were read. + /// + /// An error of the [`ErrorKind::Interrupted`] kind is non-fatal and the read + /// operation should be retried if there is nothing else to do. + /// + /// # Examples + /// + /// [`File`]s implement `Read`: + /// + /// [`Ok(n)`]: Ok + /// [`File`]: crate::fs::File + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut f = File::open("foo.txt")?; + /// let mut buffer = [0; 10]; + /// + /// // read up to 10 bytes + /// let n = f.read(&mut buffer[..])?; + /// + /// println!("The bytes: {:?}", &buffer[..n]); + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn read(&mut self, buf: &mut [u8]) -> Result<usize>; + + /// Like `read`, except that it reads into a slice of buffers. + /// + /// Data is copied to fill each buffer in order, with the final buffer + /// written to possibly being only partially filled. This method must + /// behave equivalently to a single call to `read` with concatenated + /// buffers. + /// + /// The default implementation calls `read` with either the first nonempty + /// buffer provided, or an empty one if none exists. + #[stable(feature = "iovec", since = "1.36.0")] + fn read_vectored(&mut self, bufs: &mut [IoSliceMut<'_>]) -> Result<usize> { + default_read_vectored(|b| self.read(b), bufs) + } + + /// Determines if this `Read`er has an efficient `read_vectored` + /// implementation. + /// + /// If a `Read`er does not override the default `read_vectored` + /// implementation, code using it may want to avoid the method all together + /// and coalesce writes into a single buffer for higher performance. + /// + /// The default implementation returns `false`. + #[unstable(feature = "can_vector", issue = "69941")] + fn is_read_vectored(&self) -> bool { + false + } + + /// Determines if this `Read`er can work with buffers of uninitialized + /// memory. + /// + /// The default implementation returns an initializer which will zero + /// buffers. + /// + /// If a `Read`er guarantees that it can work properly with uninitialized + /// memory, it should call [`Initializer::nop()`]. See the documentation for + /// [`Initializer`] for details. + /// + /// The behavior of this method must be independent of the state of the + /// `Read`er - the method only takes `&self` so that it can be used through + /// trait objects. + /// + /// # Safety + /// + /// This method is unsafe because a `Read`er could otherwise return a + /// non-zeroing `Initializer` from another `Read` type without an `unsafe` + /// block. + #[unstable(feature = "read_initializer", issue = "42788")] + #[inline] + unsafe fn initializer(&self) -> Initializer { + Initializer::zeroing() + } + + /// Read all bytes until EOF in this source, placing them into `buf`. + /// + /// All bytes read from this source will be appended to the specified buffer + /// `buf`. This function will continuously call [`read()`] to append more data to + /// `buf` until [`read()`] returns either [`Ok(0)`] or an error of + /// non-[`ErrorKind::Interrupted`] kind. + /// + /// If successful, this function will return the total number of bytes read. + /// + /// # Errors + /// + /// If this function encounters an error of the kind + /// [`ErrorKind::Interrupted`] then the error is ignored and the operation + /// will continue. + /// + /// If any other read error is encountered then this function immediately + /// returns. Any bytes which have already been read will be appended to + /// `buf`. + /// + /// # Examples + /// + /// [`File`]s implement `Read`: + /// + /// [`read()`]: Read::read + /// [`Ok(0)`]: Ok + /// [`File`]: crate::fs::File + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut f = File::open("foo.txt")?; + /// let mut buffer = Vec::new(); + /// + /// // read the whole file + /// f.read_to_end(&mut buffer)?; + /// Ok(()) + /// } + /// ``` + /// + /// (See also the [`std::fs::read`] convenience function for reading from a + /// file.) + /// + /// [`std::fs::read`]: crate::fs::read + #[stable(feature = "rust1", since = "1.0.0")] + fn read_to_end(&mut self, buf: &mut Vec<u8>) -> Result<usize> { + read_to_end(self, buf) + } + + /// Read all bytes until EOF in this source, appending them to `buf`. + /// + /// If successful, this function returns the number of bytes which were read + /// and appended to `buf`. + /// + /// # Errors + /// + /// If the data in this stream is *not* valid UTF-8 then an error is + /// returned and `buf` is unchanged. + /// + /// See [`read_to_end`][readtoend] for other error semantics. + /// + /// [readtoend]: Self::read_to_end + /// + /// # Examples + /// + /// [`File`][file]s implement `Read`: + /// + /// [file]: crate::fs::File + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut f = File::open("foo.txt")?; + /// let mut buffer = String::new(); + /// + /// f.read_to_string(&mut buffer)?; + /// Ok(()) + /// } + /// ``` + /// + /// (See also the [`std::fs::read_to_string`] convenience function for + /// reading from a file.) + /// + /// [`std::fs::read_to_string`]: crate::fs::read_to_string + #[stable(feature = "rust1", since = "1.0.0")] + fn read_to_string(&mut self, buf: &mut String) -> Result<usize> { + // Note that we do *not* call `.read_to_end()` here. We are passing + // `&mut Vec<u8>` (the raw contents of `buf`) into the `read_to_end` + // method to fill it up. An arbitrary implementation could overwrite the + // entire contents of the vector, not just append to it (which is what + // we are expecting). + // + // To prevent extraneously checking the UTF-8-ness of the entire buffer + // we pass it to our hardcoded `read_to_end` implementation which we + // know is guaranteed to only read data into the end of the buffer. + append_to_string(buf, |b| read_to_end(self, b)) + } + + /// Read the exact number of bytes required to fill `buf`. + /// + /// This function reads as many bytes as necessary to completely fill the + /// specified buffer `buf`. + /// + /// No guarantees are provided about the contents of `buf` when this + /// function is called, implementations cannot rely on any property of the + /// contents of `buf` being true. It is recommended that implementations + /// only write data to `buf` instead of reading its contents. The + /// documentation on [`read`] has a more detailed explanation on this + /// subject. + /// + /// # Errors + /// + /// If this function encounters an error of the kind + /// [`ErrorKind::Interrupted`] then the error is ignored and the operation + /// will continue. + /// + /// If this function encounters an "end of file" before completely filling + /// the buffer, it returns an error of the kind [`ErrorKind::UnexpectedEof`]. + /// The contents of `buf` are unspecified in this case. + /// + /// If any other read error is encountered then this function immediately + /// returns. The contents of `buf` are unspecified in this case. + /// + /// If this function returns an error, it is unspecified how many bytes it + /// has read, but it will never read more than would be necessary to + /// completely fill the buffer. + /// + /// # Examples + /// + /// [`File`]s implement `Read`: + /// + /// [`read`]: Read::read + /// [`File`]: crate::fs::File + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut f = File::open("foo.txt")?; + /// let mut buffer = [0; 10]; + /// + /// // read exactly 10 bytes + /// f.read_exact(&mut buffer)?; + /// Ok(()) + /// } + /// ``` + #[stable(feature = "read_exact", since = "1.6.0")] + fn read_exact(&mut self, mut buf: &mut [u8]) -> Result<()> { + while !buf.is_empty() { + match self.read(buf) { + Ok(0) => break, + Ok(n) => { + let tmp = buf; + buf = &mut tmp[n..]; + } + Err(ref e) if e.kind() == ErrorKind::Interrupted => {} + Err(e) => return Err(e), + } + } + if !buf.is_empty() { + Err(Error::new(ErrorKind::UnexpectedEof, "failed to fill whole buffer")) + } else { + Ok(()) + } + } + + /// Creates a "by reference" adaptor for this instance of `Read`. + /// + /// The returned adaptor also implements `Read` and will simply borrow this + /// current reader. + /// + /// # Examples + /// + /// [`File`][file]s implement `Read`: + /// + /// [file]: crate::fs::File + /// + /// ```no_run + /// use std::io; + /// use std::io::Read; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut f = File::open("foo.txt")?; + /// let mut buffer = Vec::new(); + /// let mut other_buffer = Vec::new(); + /// + /// { + /// let reference = f.by_ref(); + /// + /// // read at most 5 bytes + /// reference.take(5).read_to_end(&mut buffer)?; + /// + /// } // drop our &mut reference so we can use f again + /// + /// // original file still usable, read the rest + /// f.read_to_end(&mut other_buffer)?; + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn by_ref(&mut self) -> &mut Self + where + Self: Sized, + { + self + } + + /// Transforms this `Read` instance to an [`Iterator`] over its bytes. + /// + /// The returned type implements [`Iterator`] where the `Item` is + /// [`Result`]`<`[`u8`]`, `[`io::Error`]`>`. + /// The yielded item is [`Ok`] if a byte was successfully read and [`Err`] + /// otherwise. EOF is mapped to returning [`None`] from this iterator. + /// + /// # Examples + /// + /// [`File`][file]s implement `Read`: + /// + /// [file]: crate::fs::File + /// [`Iterator`]: crate::iter::Iterator + /// [`Result`]: crate::result::Result + /// [`io::Error`]: self::Error + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut f = File::open("foo.txt")?; + /// + /// for byte in f.bytes() { + /// println!("{}", byte.unwrap()); + /// } + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn bytes(self) -> Bytes<Self> + where + Self: Sized, + { + Bytes { inner: self } + } + + /// Creates an adaptor which will chain this stream with another. + /// + /// The returned `Read` instance will first read all bytes from this object + /// until EOF is encountered. Afterwards the output is equivalent to the + /// output of `next`. + /// + /// # Examples + /// + /// [`File`][file]s implement `Read`: + /// + /// [file]: crate::fs::File + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut f1 = File::open("foo.txt")?; + /// let mut f2 = File::open("bar.txt")?; + /// + /// let mut handle = f1.chain(f2); + /// let mut buffer = String::new(); + /// + /// // read the value into a String. We could use any Read method here, + /// // this is just one example. + /// handle.read_to_string(&mut buffer)?; + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn chain<R: Read>(self, next: R) -> Chain<Self, R> + where + Self: Sized, + { + Chain { first: self, second: next, done_first: false } + } + + /// Creates an adaptor which will read at most `limit` bytes from it. + /// + /// This function returns a new instance of `Read` which will read at most + /// `limit` bytes, after which it will always return EOF ([`Ok(0)`]). Any + /// read errors will not count towards the number of bytes read and future + /// calls to [`read()`] may succeed. + /// + /// # Examples + /// + /// [`File`]s implement `Read`: + /// + /// [`File`]: crate::fs::File + /// [`Ok(0)`]: Ok + /// [`read()`]: Read::read + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut f = File::open("foo.txt")?; + /// let mut buffer = [0; 5]; + /// + /// // read at most five bytes + /// let mut handle = f.take(5); + /// + /// handle.read(&mut buffer)?; + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn take(self, limit: u64) -> Take<Self> + where + Self: Sized, + { + Take { inner: self, limit } + } +} + +/// A buffer type used with `Read::read_vectored`. +/// +/// It is semantically a wrapper around an `&mut [u8]`, but is guaranteed to be +/// ABI compatible with the `iovec` type on Unix platforms and `WSABUF` on +/// Windows. +#[stable(feature = "iovec", since = "1.36.0")] +#[repr(transparent)] +pub struct IoSliceMut<'a>(sys::io::IoSliceMut<'a>); + +#[stable(feature = "iovec-send-sync", since = "1.44.0")] +unsafe impl<'a> Send for IoSliceMut<'a> {} + +#[stable(feature = "iovec-send-sync", since = "1.44.0")] +unsafe impl<'a> Sync for IoSliceMut<'a> {} + +#[stable(feature = "iovec", since = "1.36.0")] +impl<'a> fmt::Debug for IoSliceMut<'a> { + fn fmt(&self, fmt: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(self.0.as_slice(), fmt) + } +} + +impl<'a> IoSliceMut<'a> { + /// Creates a new `IoSliceMut` wrapping a byte slice. + /// + /// # Panics + /// + /// Panics on Windows if the slice is larger than 4GB. + #[stable(feature = "iovec", since = "1.36.0")] + #[inline] + pub fn new(buf: &'a mut [u8]) -> IoSliceMut<'a> { + IoSliceMut(sys::io::IoSliceMut::new(buf)) + } + + /// Advance the internal cursor of the slice. + /// + /// # Notes + /// + /// Elements in the slice may be modified if the cursor is not advanced to + /// the end of the slice. For example if we have a slice of buffers with 2 + /// `IoSliceMut`s, both of length 8, and we advance the cursor by 10 bytes + /// the first `IoSliceMut` will be untouched however the second will be + /// modified to remove the first 2 bytes (10 - 8). + /// + /// # Examples + /// + /// ``` + /// #![feature(io_slice_advance)] + /// + /// use std::io::IoSliceMut; + /// use std::ops::Deref; + /// + /// let mut buf1 = [1; 8]; + /// let mut buf2 = [2; 16]; + /// let mut buf3 = [3; 8]; + /// let mut bufs = &mut [ + /// IoSliceMut::new(&mut buf1), + /// IoSliceMut::new(&mut buf2), + /// IoSliceMut::new(&mut buf3), + /// ][..]; + /// + /// // Mark 10 bytes as read. + /// bufs = IoSliceMut::advance(bufs, 10); + /// assert_eq!(bufs[0].deref(), [2; 14].as_ref()); + /// assert_eq!(bufs[1].deref(), [3; 8].as_ref()); + /// ``` + #[unstable(feature = "io_slice_advance", issue = "62726")] + #[inline] + pub fn advance<'b>(bufs: &'b mut [IoSliceMut<'a>], n: usize) -> &'b mut [IoSliceMut<'a>] { + // Number of buffers to remove. + let mut remove = 0; + // Total length of all the to be removed buffers. + let mut accumulated_len = 0; + for buf in bufs.iter() { + if accumulated_len + buf.len() > n { + break; + } else { + accumulated_len += buf.len(); + remove += 1; + } + } + + let bufs = &mut bufs[remove..]; + if !bufs.is_empty() { + bufs[0].0.advance(n - accumulated_len) + } + bufs + } +} + +#[stable(feature = "iovec", since = "1.36.0")] +impl<'a> Deref for IoSliceMut<'a> { + type Target = [u8]; + + #[inline] + fn deref(&self) -> &[u8] { + self.0.as_slice() + } +} + +#[stable(feature = "iovec", since = "1.36.0")] +impl<'a> DerefMut for IoSliceMut<'a> { + #[inline] + fn deref_mut(&mut self) -> &mut [u8] { + self.0.as_mut_slice() + } +} + +/// A buffer type used with `Write::write_vectored`. +/// +/// It is semantically a wrapper around an `&[u8]`, but is guaranteed to be +/// ABI compatible with the `iovec` type on Unix platforms and `WSABUF` on +/// Windows. +#[stable(feature = "iovec", since = "1.36.0")] +#[derive(Copy, Clone)] +#[repr(transparent)] +pub struct IoSlice<'a>(sys::io::IoSlice<'a>); + +#[stable(feature = "iovec-send-sync", since = "1.44.0")] +unsafe impl<'a> Send for IoSlice<'a> {} + +#[stable(feature = "iovec-send-sync", since = "1.44.0")] +unsafe impl<'a> Sync for IoSlice<'a> {} + +#[stable(feature = "iovec", since = "1.36.0")] +impl<'a> fmt::Debug for IoSlice<'a> { + fn fmt(&self, fmt: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(self.0.as_slice(), fmt) + } +} + +impl<'a> IoSlice<'a> { + /// Creates a new `IoSlice` wrapping a byte slice. + /// + /// # Panics + /// + /// Panics on Windows if the slice is larger than 4GB. + #[stable(feature = "iovec", since = "1.36.0")] + #[inline] + pub fn new(buf: &'a [u8]) -> IoSlice<'a> { + IoSlice(sys::io::IoSlice::new(buf)) + } + + /// Advance the internal cursor of the slice. + /// + /// # Notes + /// + /// Elements in the slice may be modified if the cursor is not advanced to + /// the end of the slice. For example if we have a slice of buffers with 2 + /// `IoSlice`s, both of length 8, and we advance the cursor by 10 bytes the + /// first `IoSlice` will be untouched however the second will be modified to + /// remove the first 2 bytes (10 - 8). + /// + /// # Examples + /// + /// ``` + /// #![feature(io_slice_advance)] + /// + /// use std::io::IoSlice; + /// use std::ops::Deref; + /// + /// let buf1 = [1; 8]; + /// let buf2 = [2; 16]; + /// let buf3 = [3; 8]; + /// let mut bufs = &mut [ + /// IoSlice::new(&buf1), + /// IoSlice::new(&buf2), + /// IoSlice::new(&buf3), + /// ][..]; + /// + /// // Mark 10 bytes as written. + /// bufs = IoSlice::advance(bufs, 10); + /// assert_eq!(bufs[0].deref(), [2; 14].as_ref()); + /// assert_eq!(bufs[1].deref(), [3; 8].as_ref()); + #[unstable(feature = "io_slice_advance", issue = "62726")] + #[inline] + pub fn advance<'b>(bufs: &'b mut [IoSlice<'a>], n: usize) -> &'b mut [IoSlice<'a>] { + // Number of buffers to remove. + let mut remove = 0; + // Total length of all the to be removed buffers. + let mut accumulated_len = 0; + for buf in bufs.iter() { + if accumulated_len + buf.len() > n { + break; + } else { + accumulated_len += buf.len(); + remove += 1; + } + } + + let bufs = &mut bufs[remove..]; + if !bufs.is_empty() { + bufs[0].0.advance(n - accumulated_len) + } + bufs + } +} + +#[stable(feature = "iovec", since = "1.36.0")] +impl<'a> Deref for IoSlice<'a> { + type Target = [u8]; + + #[inline] + fn deref(&self) -> &[u8] { + self.0.as_slice() + } +} + +/// A type used to conditionally initialize buffers passed to `Read` methods. +#[unstable(feature = "read_initializer", issue = "42788")] +#[derive(Debug)] +pub struct Initializer(bool); + +impl Initializer { + /// Returns a new `Initializer` which will zero out buffers. + #[unstable(feature = "read_initializer", issue = "42788")] + #[inline] + pub fn zeroing() -> Initializer { + Initializer(true) + } + + /// Returns a new `Initializer` which will not zero out buffers. + /// + /// # Safety + /// + /// This may only be called by `Read`ers which guarantee that they will not + /// read from buffers passed to `Read` methods, and that the return value of + /// the method accurately reflects the number of bytes that have been + /// written to the head of the buffer. + #[unstable(feature = "read_initializer", issue = "42788")] + #[inline] + pub unsafe fn nop() -> Initializer { + Initializer(false) + } + + /// Indicates if a buffer should be initialized. + #[unstable(feature = "read_initializer", issue = "42788")] + #[inline] + pub fn should_initialize(&self) -> bool { + self.0 + } + + /// Initializes a buffer if necessary. + #[unstable(feature = "read_initializer", issue = "42788")] + #[inline] + pub fn initialize(&self, buf: &mut [u8]) { + if self.should_initialize() { + unsafe { ptr::write_bytes(buf.as_mut_ptr(), 0, buf.len()) } + } + } +} + +/// A trait for objects which are byte-oriented sinks. +/// +/// Implementors of the `Write` trait are sometimes called 'writers'. +/// +/// Writers are defined by two required methods, [`write`] and [`flush`]: +/// +/// * The [`write`] method will attempt to write some data into the object, +/// returning how many bytes were successfully written. +/// +/// * The [`flush`] method is useful for adaptors and explicit buffers +/// themselves for ensuring that all buffered data has been pushed out to the +/// 'true sink'. +/// +/// Writers are intended to be composable with one another. Many implementors +/// throughout [`std::io`] take and provide types which implement the `Write` +/// trait. +/// +/// [`write`]: Self::write +/// [`flush`]: Self::flush +/// [`std::io`]: index.html +/// +/// # Examples +/// +/// ```no_run +/// use std::io::prelude::*; +/// use std::fs::File; +/// +/// fn main() -> std::io::Result<()> { +/// let data = b"some bytes"; +/// +/// let mut pos = 0; +/// let mut buffer = File::create("foo.txt")?; +/// +/// while pos < data.len() { +/// let bytes_written = buffer.write(&data[pos..])?; +/// pos += bytes_written; +/// } +/// Ok(()) +/// } +/// ``` +/// +/// The trait also provides convenience methods like [`write_all`], which calls +/// `write` in a loop until its entire input has been written. +/// +/// [`write_all`]: Self::write_all +#[stable(feature = "rust1", since = "1.0.0")] +#[doc(spotlight)] +pub trait Write { + /// Write a buffer into this writer, returning how many bytes were written. + /// + /// This function will attempt to write the entire contents of `buf`, but + /// the entire write may not succeed, or the write may also generate an + /// error. A call to `write` represents *at most one* attempt to write to + /// any wrapped object. + /// + /// Calls to `write` are not guaranteed to block waiting for data to be + /// written, and a write which would otherwise block can be indicated through + /// an [`Err`] variant. + /// + /// If the return value is [`Ok(n)`] then it must be guaranteed that + /// `n <= buf.len()`. A return value of `0` typically means that the + /// underlying object is no longer able to accept bytes and will likely not + /// be able to in the future as well, or that the buffer provided is empty. + /// + /// # Errors + /// + /// Each call to `write` may generate an I/O error indicating that the + /// operation could not be completed. If an error is returned then no bytes + /// in the buffer were written to this writer. + /// + /// It is **not** considered an error if the entire buffer could not be + /// written to this writer. + /// + /// An error of the [`ErrorKind::Interrupted`] kind is non-fatal and the + /// write operation should be retried if there is nothing else to do. + /// + /// # Examples + /// + /// ```no_run + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> std::io::Result<()> { + /// let mut buffer = File::create("foo.txt")?; + /// + /// // Writes some prefix of the byte string, not necessarily all of it. + /// buffer.write(b"some bytes")?; + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn write(&mut self, buf: &[u8]) -> Result<usize>; + + /// Like `write`, except that it writes from a slice of buffers. + /// + /// Data is copied from each buffer in order, with the final buffer + /// read from possibly being only partially consumed. This method must + /// behave as a call to `write` with the buffers concatenated would. + /// + /// The default implementation calls `write` with either the first nonempty + /// buffer provided, or an empty one if none exists. + #[stable(feature = "iovec", since = "1.36.0")] + fn write_vectored(&mut self, bufs: &[IoSlice<'_>]) -> Result<usize> { + default_write_vectored(|b| self.write(b), bufs) + } + + /// Determines if this `Write`er has an efficient `write_vectored` + /// implementation. + /// + /// If a `Write`er does not override the default `write_vectored` + /// implementation, code using it may want to avoid the method all together + /// and coalesce writes into a single buffer for higher performance. + /// + /// The default implementation returns `false`. + #[unstable(feature = "can_vector", issue = "69941")] + fn is_write_vectored(&self) -> bool { + false + } + + /// Flush this output stream, ensuring that all intermediately buffered + /// contents reach their destination. + /// + /// # Errors + /// + /// It is considered an error if not all bytes could be written due to + /// I/O errors or EOF being reached. + /// + /// # Examples + /// + /// ```no_run + /// use std::io::prelude::*; + /// use std::io::BufWriter; + /// use std::fs::File; + /// + /// fn main() -> std::io::Result<()> { + /// let mut buffer = BufWriter::new(File::create("foo.txt")?); + /// + /// buffer.write_all(b"some bytes")?; + /// buffer.flush()?; + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn flush(&mut self) -> Result<()>; + + /// Attempts to write an entire buffer into this writer. + /// + /// This method will continuously call [`write`] until there is no more data + /// to be written or an error of non-[`ErrorKind::Interrupted`] kind is + /// returned. This method will not return until the entire buffer has been + /// successfully written or such an error occurs. The first error that is + /// not of [`ErrorKind::Interrupted`] kind generated from this method will be + /// returned. + /// + /// If the buffer contains no data, this will never call [`write`]. + /// + /// # Errors + /// + /// This function will return the first error of + /// non-[`ErrorKind::Interrupted`] kind that [`write`] returns. + /// + /// [`write`]: Self::write + /// + /// # Examples + /// + /// ```no_run + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> std::io::Result<()> { + /// let mut buffer = File::create("foo.txt")?; + /// + /// buffer.write_all(b"some bytes")?; + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn write_all(&mut self, mut buf: &[u8]) -> Result<()> { + while !buf.is_empty() { + match self.write(buf) { + Ok(0) => { + return Err(Error::new(ErrorKind::WriteZero, "failed to write whole buffer")); + } + Ok(n) => buf = &buf[n..], + Err(ref e) if e.kind() == ErrorKind::Interrupted => {} + Err(e) => return Err(e), + } + } + Ok(()) + } + + /// Attempts to write multiple buffers into this writer. + /// + /// This method will continuously call [`write_vectored`] until there is no + /// more data to be written or an error of non-[`ErrorKind::Interrupted`] + /// kind is returned. This method will not return until all buffers have + /// been successfully written or such an error occurs. The first error that + /// is not of [`ErrorKind::Interrupted`] kind generated from this method + /// will be returned. + /// + /// If the buffer contains no data, this will never call [`write_vectored`]. + /// + /// [`write_vectored`]: Self::write_vectored + /// + /// # Notes + /// + /// + /// Unlike `io::Write::write_vectored`, this takes a *mutable* reference to + /// a slice of `IoSlice`s, not an immutable one. That's because we need to + /// modify the slice to keep track of the bytes already written. + /// + /// Once this function returns, the contents of `bufs` are unspecified, as + /// this depends on how many calls to `write_vectored` were necessary. It is + /// best to understand this function as taking ownership of `bufs` and to + /// not use `bufs` afterwards. The underlying buffers, to which the + /// `IoSlice`s point (but not the `IoSlice`s themselves), are unchanged and + /// can be reused. + /// + /// # Examples + /// + /// ``` + /// #![feature(write_all_vectored)] + /// # fn main() -> std::io::Result<()> { + /// + /// use std::io::{Write, IoSlice}; + /// + /// let mut writer = Vec::new(); + /// let bufs = &mut [ + /// IoSlice::new(&[1]), + /// IoSlice::new(&[2, 3]), + /// IoSlice::new(&[4, 5, 6]), + /// ]; + /// + /// writer.write_all_vectored(bufs)?; + /// // Note: the contents of `bufs` is now undefined, see the Notes section. + /// + /// assert_eq!(writer, &[1, 2, 3, 4, 5, 6]); + /// # Ok(()) } + /// ``` + #[unstable(feature = "write_all_vectored", issue = "70436")] + fn write_all_vectored(&mut self, mut bufs: &mut [IoSlice<'_>]) -> Result<()> { + // Guarantee that bufs is empty if it contains no data, + // to avoid calling write_vectored if there is no data to be written. + bufs = IoSlice::advance(bufs, 0); + while !bufs.is_empty() { + match self.write_vectored(bufs) { + Ok(0) => { + return Err(Error::new(ErrorKind::WriteZero, "failed to write whole buffer")); + } + Ok(n) => bufs = IoSlice::advance(bufs, n), + Err(ref e) if e.kind() == ErrorKind::Interrupted => {} + Err(e) => return Err(e), + } + } + Ok(()) + } + + /// Writes a formatted string into this writer, returning any error + /// encountered. + /// + /// This method is primarily used to interface with the + /// [`format_args!()`] macro, but it is rare that this should + /// explicitly be called. The [`write!()`] macro should be favored to + /// invoke this method instead. + /// + /// This function internally uses the [`write_all`][writeall] method on + /// this trait and hence will continuously write data so long as no errors + /// are received. This also means that partial writes are not indicated in + /// this signature. + /// + /// [writeall]: Self::write_all + /// + /// # Errors + /// + /// This function will return any I/O error reported while formatting. + /// + /// # Examples + /// + /// ```no_run + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> std::io::Result<()> { + /// let mut buffer = File::create("foo.txt")?; + /// + /// // this call + /// write!(buffer, "{:.*}", 2, 1.234567)?; + /// // turns into this: + /// buffer.write_fmt(format_args!("{:.*}", 2, 1.234567))?; + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn write_fmt(&mut self, fmt: fmt::Arguments<'_>) -> Result<()> { + // Create a shim which translates a Write to a fmt::Write and saves + // off I/O errors. instead of discarding them + struct Adaptor<'a, T: ?Sized + 'a> { + inner: &'a mut T, + error: Result<()>, + } + + impl<T: Write + ?Sized> fmt::Write for Adaptor<'_, T> { + fn write_str(&mut self, s: &str) -> fmt::Result { + match self.inner.write_all(s.as_bytes()) { + Ok(()) => Ok(()), + Err(e) => { + self.error = Err(e); + Err(fmt::Error) + } + } + } + } + + let mut output = Adaptor { inner: self, error: Ok(()) }; + match fmt::write(&mut output, fmt) { + Ok(()) => Ok(()), + Err(..) => { + // check if the error came from the underlying `Write` or not + if output.error.is_err() { + output.error + } else { + Err(Error::new(ErrorKind::Other, "formatter error")) + } + } + } + } + + /// Creates a "by reference" adaptor for this instance of `Write`. + /// + /// The returned adaptor also implements `Write` and will simply borrow this + /// current writer. + /// + /// # Examples + /// + /// ```no_run + /// use std::io::Write; + /// use std::fs::File; + /// + /// fn main() -> std::io::Result<()> { + /// let mut buffer = File::create("foo.txt")?; + /// + /// let reference = buffer.by_ref(); + /// + /// // we can use reference just like our original buffer + /// reference.write_all(b"some bytes")?; + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn by_ref(&mut self) -> &mut Self + where + Self: Sized, + { + self + } +} + +/// The `Seek` trait provides a cursor which can be moved within a stream of +/// bytes. +/// +/// The stream typically has a fixed size, allowing seeking relative to either +/// end or the current offset. +/// +/// # Examples +/// +/// [`File`][file]s implement `Seek`: +/// +/// [file]: crate::fs::File +/// +/// ```no_run +/// use std::io; +/// use std::io::prelude::*; +/// use std::fs::File; +/// use std::io::SeekFrom; +/// +/// fn main() -> io::Result<()> { +/// let mut f = File::open("foo.txt")?; +/// +/// // move the cursor 42 bytes from the start of the file +/// f.seek(SeekFrom::Start(42))?; +/// Ok(()) +/// } +/// ``` +#[stable(feature = "rust1", since = "1.0.0")] +pub trait Seek { + /// Seek to an offset, in bytes, in a stream. + /// + /// A seek beyond the end of a stream is allowed, but behavior is defined + /// by the implementation. + /// + /// If the seek operation completed successfully, + /// this method returns the new position from the start of the stream. + /// That position can be used later with [`SeekFrom::Start`]. + /// + /// # Errors + /// + /// Seeking to a negative offset is considered an error. + /// + /// [`SeekFrom::Start`]: enum.SeekFrom.html#variant.Start + #[stable(feature = "rust1", since = "1.0.0")] + fn seek(&mut self, pos: SeekFrom) -> Result<u64>; + + /// Returns the length of this stream (in bytes). + /// + /// This method is implemented using up to three seek operations. If this + /// method returns successfully, the seek position is unchanged (i.e. the + /// position before calling this method is the same as afterwards). + /// However, if this method returns an error, the seek position is + /// unspecified. + /// + /// If you need to obtain the length of *many* streams and you don't care + /// about the seek position afterwards, you can reduce the number of seek + /// operations by simply calling `seek(SeekFrom::End(0))` and using its + /// return value (it is also the stream length). + /// + /// Note that length of a stream can change over time (for example, when + /// data is appended to a file). So calling this method multiple times does + /// not necessarily return the same length each time. + /// + /// + /// # Example + /// + /// ```no_run + /// #![feature(seek_convenience)] + /// use std::{ + /// io::{self, Seek}, + /// fs::File, + /// }; + /// + /// fn main() -> io::Result<()> { + /// let mut f = File::open("foo.txt")?; + /// + /// let len = f.stream_len()?; + /// println!("The file is currently {} bytes long", len); + /// Ok(()) + /// } + /// ``` + #[unstable(feature = "seek_convenience", issue = "59359")] + fn stream_len(&mut self) -> Result<u64> { + let old_pos = self.stream_position()?; + let len = self.seek(SeekFrom::End(0))?; + + // Avoid seeking a third time when we were already at the end of the + // stream. The branch is usually way cheaper than a seek operation. + if old_pos != len { + self.seek(SeekFrom::Start(old_pos))?; + } + + Ok(len) + } + + /// Returns the current seek position from the start of the stream. + /// + /// This is equivalent to `self.seek(SeekFrom::Current(0))`. + /// + /// + /// # Example + /// + /// ```no_run + /// #![feature(seek_convenience)] + /// use std::{ + /// io::{self, BufRead, BufReader, Seek}, + /// fs::File, + /// }; + /// + /// fn main() -> io::Result<()> { + /// let mut f = BufReader::new(File::open("foo.txt")?); + /// + /// let before = f.stream_position()?; + /// f.read_line(&mut String::new())?; + /// let after = f.stream_position()?; + /// + /// println!("The first line was {} bytes long", after - before); + /// Ok(()) + /// } + /// ``` + #[unstable(feature = "seek_convenience", issue = "59359")] + fn stream_position(&mut self) -> Result<u64> { + self.seek(SeekFrom::Current(0)) + } +} + +/// Enumeration of possible methods to seek within an I/O object. +/// +/// It is used by the [`Seek`] trait. +/// +/// [`Seek`]: trait.Seek.html +#[derive(Copy, PartialEq, Eq, Clone, Debug)] +#[stable(feature = "rust1", since = "1.0.0")] +pub enum SeekFrom { + /// Sets the offset to the provided number of bytes. + #[stable(feature = "rust1", since = "1.0.0")] + Start(#[stable(feature = "rust1", since = "1.0.0")] u64), + + /// Sets the offset to the size of this object plus the specified number of + /// bytes. + /// + /// It is possible to seek beyond the end of an object, but it's an error to + /// seek before byte 0. + #[stable(feature = "rust1", since = "1.0.0")] + End(#[stable(feature = "rust1", since = "1.0.0")] i64), + + /// Sets the offset to the current position plus the specified number of + /// bytes. + /// + /// It is possible to seek beyond the end of an object, but it's an error to + /// seek before byte 0. + #[stable(feature = "rust1", since = "1.0.0")] + Current(#[stable(feature = "rust1", since = "1.0.0")] i64), +} + +fn read_until<R: BufRead + ?Sized>(r: &mut R, delim: u8, buf: &mut Vec<u8>) -> Result<usize> { + let mut read = 0; + loop { + let (done, used) = { + let available = match r.fill_buf() { + Ok(n) => n, + Err(ref e) if e.kind() == ErrorKind::Interrupted => continue, + Err(e) => return Err(e), + }; + match memchr::memchr(delim, available) { + Some(i) => { + buf.extend_from_slice(&available[..=i]); + (true, i + 1) + } + None => { + buf.extend_from_slice(available); + (false, available.len()) + } + } + }; + r.consume(used); + read += used; + if done || used == 0 { + return Ok(read); + } + } +} + +/// A `BufRead` is a type of `Read`er which has an internal buffer, allowing it +/// to perform extra ways of reading. +/// +/// For example, reading line-by-line is inefficient without using a buffer, so +/// if you want to read by line, you'll need `BufRead`, which includes a +/// [`read_line`] method as well as a [`lines`] iterator. +/// +/// # Examples +/// +/// A locked standard input implements `BufRead`: +/// +/// ```no_run +/// use std::io; +/// use std::io::prelude::*; +/// +/// let stdin = io::stdin(); +/// for line in stdin.lock().lines() { +/// println!("{}", line.unwrap()); +/// } +/// ``` +/// +/// If you have something that implements [`Read`], you can use the [`BufReader` +/// type][`BufReader`] to turn it into a `BufRead`. +/// +/// For example, [`File`] implements [`Read`], but not `BufRead`. +/// [`BufReader`] to the rescue! +/// +/// [`BufReader`]: struct.BufReader.html +/// [`File`]: crate::fs::File +/// [`read_line`]: Self::read_line +/// [`lines`]: Self::lines +/// [`Read`]: trait.Read.html +/// +/// ```no_run +/// use std::io::{self, BufReader}; +/// use std::io::prelude::*; +/// use std::fs::File; +/// +/// fn main() -> io::Result<()> { +/// let f = File::open("foo.txt")?; +/// let f = BufReader::new(f); +/// +/// for line in f.lines() { +/// println!("{}", line.unwrap()); +/// } +/// +/// Ok(()) +/// } +/// ``` +/// +#[stable(feature = "rust1", since = "1.0.0")] +pub trait BufRead: Read { + /// Returns the contents of the internal buffer, filling it with more data + /// from the inner reader if it is empty. + /// + /// This function is a lower-level call. It needs to be paired with the + /// [`consume`] method to function properly. When calling this + /// method, none of the contents will be "read" in the sense that later + /// calling `read` may return the same contents. As such, [`consume`] must + /// be called with the number of bytes that are consumed from this buffer to + /// ensure that the bytes are never returned twice. + /// + /// [`consume`]: Self::consume + /// + /// An empty buffer returned indicates that the stream has reached EOF. + /// + /// # Errors + /// + /// This function will return an I/O error if the underlying reader was + /// read, but returned an error. + /// + /// # Examples + /// + /// A locked standard input implements `BufRead`: + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// + /// let stdin = io::stdin(); + /// let mut stdin = stdin.lock(); + /// + /// let buffer = stdin.fill_buf().unwrap(); + /// + /// // work with buffer + /// println!("{:?}", buffer); + /// + /// // ensure the bytes we worked with aren't returned again later + /// let length = buffer.len(); + /// stdin.consume(length); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn fill_buf(&mut self) -> Result<&[u8]>; + + /// Tells this buffer that `amt` bytes have been consumed from the buffer, + /// so they should no longer be returned in calls to `read`. + /// + /// This function is a lower-level call. It needs to be paired with the + /// [`fill_buf`] method to function properly. This function does + /// not perform any I/O, it simply informs this object that some amount of + /// its buffer, returned from [`fill_buf`], has been consumed and should + /// no longer be returned. As such, this function may do odd things if + /// [`fill_buf`] isn't called before calling it. + /// + /// The `amt` must be `<=` the number of bytes in the buffer returned by + /// [`fill_buf`]. + /// + /// # Examples + /// + /// Since `consume()` is meant to be used with [`fill_buf`], + /// that method's example includes an example of `consume()`. + /// + /// [`fill_buf`]: Self::fill_buf + #[stable(feature = "rust1", since = "1.0.0")] + fn consume(&mut self, amt: usize); + + /// Read all bytes into `buf` until the delimiter `byte` or EOF is reached. + /// + /// This function will read bytes from the underlying stream until the + /// delimiter or EOF is found. Once found, all bytes up to, and including, + /// the delimiter (if found) will be appended to `buf`. + /// + /// If successful, this function will return the total number of bytes read. + /// + /// This function is blocking and should be used carefully: it is possible for + /// an attacker to continuously send bytes without ever sending the delimiter + /// or EOF. + /// + /// # Errors + /// + /// This function will ignore all instances of [`ErrorKind::Interrupted`] and + /// will otherwise return any errors returned by [`fill_buf`]. + /// + /// If an I/O error is encountered then all bytes read so far will be + /// present in `buf` and its length will have been adjusted appropriately. + /// + /// [`fill_buf`]: Self::fill_buf + /// [`ErrorKind::Interrupted`]: enum.ErrorKind.html#variant.Interrupted + /// + /// # Examples + /// + /// [`std::io::Cursor`][`Cursor`] is a type that implements `BufRead`. In + /// this example, we use [`Cursor`] to read all the bytes in a byte slice + /// in hyphen delimited segments: + /// + /// [`Cursor`]: struct.Cursor.html + /// + /// ``` + /// use std::io::{self, BufRead}; + /// + /// let mut cursor = io::Cursor::new(b"lorem-ipsum"); + /// let mut buf = vec![]; + /// + /// // cursor is at 'l' + /// let num_bytes = cursor.read_until(b'-', &mut buf) + /// .expect("reading from cursor won't fail"); + /// assert_eq!(num_bytes, 6); + /// assert_eq!(buf, b"lorem-"); + /// buf.clear(); + /// + /// // cursor is at 'i' + /// let num_bytes = cursor.read_until(b'-', &mut buf) + /// .expect("reading from cursor won't fail"); + /// assert_eq!(num_bytes, 5); + /// assert_eq!(buf, b"ipsum"); + /// buf.clear(); + /// + /// // cursor is at EOF + /// let num_bytes = cursor.read_until(b'-', &mut buf) + /// .expect("reading from cursor won't fail"); + /// assert_eq!(num_bytes, 0); + /// assert_eq!(buf, b""); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn read_until(&mut self, byte: u8, buf: &mut Vec<u8>) -> Result<usize> { + read_until(self, byte, buf) + } + + /// Read all bytes until a newline (the 0xA byte) is reached, and append + /// them to the provided buffer. + /// + /// This function will read bytes from the underlying stream until the + /// newline delimiter (the 0xA byte) or EOF is found. Once found, all bytes + /// up to, and including, the delimiter (if found) will be appended to + /// `buf`. + /// + /// If successful, this function will return the total number of bytes read. + /// + /// If this function returns `Ok(0)`, the stream has reached EOF. + /// + /// This function is blocking and should be used carefully: it is possible for + /// an attacker to continuously send bytes without ever sending a newline + /// or EOF. + /// + /// # Errors + /// + /// This function has the same error semantics as [`read_until`] and will + /// also return an error if the read bytes are not valid UTF-8. If an I/O + /// error is encountered then `buf` may contain some bytes already read in + /// the event that all data read so far was valid UTF-8. + /// + /// [`read_until`]: Self::read_until + /// + /// # Examples + /// + /// [`std::io::Cursor`][`Cursor`] is a type that implements `BufRead`. In + /// this example, we use [`Cursor`] to read all the lines in a byte slice: + /// + /// [`Cursor`]: struct.Cursor.html + /// + /// ``` + /// use std::io::{self, BufRead}; + /// + /// let mut cursor = io::Cursor::new(b"foo\nbar"); + /// let mut buf = String::new(); + /// + /// // cursor is at 'f' + /// let num_bytes = cursor.read_line(&mut buf) + /// .expect("reading from cursor won't fail"); + /// assert_eq!(num_bytes, 4); + /// assert_eq!(buf, "foo\n"); + /// buf.clear(); + /// + /// // cursor is at 'b' + /// let num_bytes = cursor.read_line(&mut buf) + /// .expect("reading from cursor won't fail"); + /// assert_eq!(num_bytes, 3); + /// assert_eq!(buf, "bar"); + /// buf.clear(); + /// + /// // cursor is at EOF + /// let num_bytes = cursor.read_line(&mut buf) + /// .expect("reading from cursor won't fail"); + /// assert_eq!(num_bytes, 0); + /// assert_eq!(buf, ""); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn read_line(&mut self, buf: &mut String) -> Result<usize> { + // Note that we are not calling the `.read_until` method here, but + // rather our hardcoded implementation. For more details as to why, see + // the comments in `read_to_end`. + append_to_string(buf, |b| read_until(self, b'\n', b)) + } + + /// Returns an iterator over the contents of this reader split on the byte + /// `byte`. + /// + /// The iterator returned from this function will return instances of + /// [`io::Result`]`<`[`Vec<u8>`]`>`. Each vector returned will *not* have + /// the delimiter byte at the end. + /// + /// This function will yield errors whenever [`read_until`] would have + /// also yielded an error. + /// + /// [`io::Result`]: self::Result + /// [`Vec<u8>`]: crate::vec::Vec + /// [`read_until`]: Self::read_until + /// + /// # Examples + /// + /// [`std::io::Cursor`][`Cursor`] is a type that implements `BufRead`. In + /// this example, we use [`Cursor`] to iterate over all hyphen delimited + /// segments in a byte slice + /// + /// [`Cursor`]: struct.Cursor.html + /// + /// ``` + /// use std::io::{self, BufRead}; + /// + /// let cursor = io::Cursor::new(b"lorem-ipsum-dolor"); + /// + /// let mut split_iter = cursor.split(b'-').map(|l| l.unwrap()); + /// assert_eq!(split_iter.next(), Some(b"lorem".to_vec())); + /// assert_eq!(split_iter.next(), Some(b"ipsum".to_vec())); + /// assert_eq!(split_iter.next(), Some(b"dolor".to_vec())); + /// assert_eq!(split_iter.next(), None); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + fn split(self, byte: u8) -> Split<Self> + where + Self: Sized, + { + Split { buf: self, delim: byte } + } + + /// Returns an iterator over the lines of this reader. + /// + /// The iterator returned from this function will yield instances of + /// [`io::Result`]`<`[`String`]`>`. Each string returned will *not* have a newline + /// byte (the 0xA byte) or CRLF (0xD, 0xA bytes) at the end. + /// + /// [`io::Result`]: self::Result + /// + /// # Examples + /// + /// [`std::io::Cursor`][`Cursor`] is a type that implements `BufRead`. In + /// this example, we use [`Cursor`] to iterate over all the lines in a byte + /// slice. + /// + /// ``` + /// use std::io::{self, BufRead}; + /// + /// let cursor = io::Cursor::new(b"lorem\nipsum\r\ndolor"); + /// + /// let mut lines_iter = cursor.lines().map(|l| l.unwrap()); + /// assert_eq!(lines_iter.next(), Some(String::from("lorem"))); + /// assert_eq!(lines_iter.next(), Some(String::from("ipsum"))); + /// assert_eq!(lines_iter.next(), Some(String::from("dolor"))); + /// assert_eq!(lines_iter.next(), None); + /// ``` + /// + /// # Errors + /// + /// Each line of the iterator has the same error semantics as [`BufRead::read_line`]. + /// + /// [`BufRead::read_line`]: trait.BufRead.html#method.read_line + #[stable(feature = "rust1", since = "1.0.0")] + fn lines(self) -> Lines<Self> + where + Self: Sized, + { + Lines { buf: self } + } +} + +/// Adaptor to chain together two readers. +/// +/// This struct is generally created by calling [`chain`] on a reader. +/// Please see the documentation of [`chain`] for more details. +/// +/// [`chain`]: trait.Read.html#method.chain +#[stable(feature = "rust1", since = "1.0.0")] +pub struct Chain<T, U> { + first: T, + second: U, + done_first: bool, +} + +impl<T, U> Chain<T, U> { + /// Consumes the `Chain`, returning the wrapped readers. + /// + /// # Examples + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut foo_file = File::open("foo.txt")?; + /// let mut bar_file = File::open("bar.txt")?; + /// + /// let chain = foo_file.chain(bar_file); + /// let (foo_file, bar_file) = chain.into_inner(); + /// Ok(()) + /// } + /// ``` + #[stable(feature = "more_io_inner_methods", since = "1.20.0")] + pub fn into_inner(self) -> (T, U) { + (self.first, self.second) + } + + /// Gets references to the underlying readers in this `Chain`. + /// + /// # Examples + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut foo_file = File::open("foo.txt")?; + /// let mut bar_file = File::open("bar.txt")?; + /// + /// let chain = foo_file.chain(bar_file); + /// let (foo_file, bar_file) = chain.get_ref(); + /// Ok(()) + /// } + /// ``` + #[stable(feature = "more_io_inner_methods", since = "1.20.0")] + pub fn get_ref(&self) -> (&T, &U) { + (&self.first, &self.second) + } + + /// Gets mutable references to the underlying readers in this `Chain`. + /// + /// Care should be taken to avoid modifying the internal I/O state of the + /// underlying readers as doing so may corrupt the internal state of this + /// `Chain`. + /// + /// # Examples + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut foo_file = File::open("foo.txt")?; + /// let mut bar_file = File::open("bar.txt")?; + /// + /// let mut chain = foo_file.chain(bar_file); + /// let (foo_file, bar_file) = chain.get_mut(); + /// Ok(()) + /// } + /// ``` + #[stable(feature = "more_io_inner_methods", since = "1.20.0")] + pub fn get_mut(&mut self) -> (&mut T, &mut U) { + (&mut self.first, &mut self.second) + } +} + +#[stable(feature = "std_debug", since = "1.16.0")] +impl<T: fmt::Debug, U: fmt::Debug> fmt::Debug for Chain<T, U> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.debug_struct("Chain").field("t", &self.first).field("u", &self.second).finish() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Read, U: Read> Read for Chain<T, U> { + fn read(&mut self, buf: &mut [u8]) -> Result<usize> { + if !self.done_first { + match self.first.read(buf)? { + 0 if !buf.is_empty() => self.done_first = true, + n => return Ok(n), + } + } + self.second.read(buf) + } + + fn read_vectored(&mut self, bufs: &mut [IoSliceMut<'_>]) -> Result<usize> { + if !self.done_first { + match self.first.read_vectored(bufs)? { + 0 if bufs.iter().any(|b| !b.is_empty()) => self.done_first = true, + n => return Ok(n), + } + } + self.second.read_vectored(bufs) + } + + unsafe fn initializer(&self) -> Initializer { + let initializer = self.first.initializer(); + if initializer.should_initialize() { initializer } else { self.second.initializer() } + } +} + +#[stable(feature = "chain_bufread", since = "1.9.0")] +impl<T: BufRead, U: BufRead> BufRead for Chain<T, U> { + fn fill_buf(&mut self) -> Result<&[u8]> { + if !self.done_first { + match self.first.fill_buf()? { + buf if buf.is_empty() => { + self.done_first = true; + } + buf => return Ok(buf), + } + } + self.second.fill_buf() + } + + fn consume(&mut self, amt: usize) { + if !self.done_first { self.first.consume(amt) } else { self.second.consume(amt) } + } +} + +/// Reader adaptor which limits the bytes read from an underlying reader. +/// +/// This struct is generally created by calling [`take`] on a reader. +/// Please see the documentation of [`take`] for more details. +/// +/// [`take`]: trait.Read.html#method.take +#[stable(feature = "rust1", since = "1.0.0")] +#[derive(Debug)] +pub struct Take<T> { + inner: T, + limit: u64, +} + +impl<T> Take<T> { + /// Returns the number of bytes that can be read before this instance will + /// return EOF. + /// + /// # Note + /// + /// This instance may reach `EOF` after reading fewer bytes than indicated by + /// this method if the underlying [`Read`] instance reaches EOF. + /// + /// # Examples + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let f = File::open("foo.txt")?; + /// + /// // read at most five bytes + /// let handle = f.take(5); + /// + /// println!("limit: {}", handle.limit()); + /// Ok(()) + /// } + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn limit(&self) -> u64 { + self.limit + } + + /// Sets the number of bytes that can be read before this instance will + /// return EOF. This is the same as constructing a new `Take` instance, so + /// the amount of bytes read and the previous limit value don't matter when + /// calling this method. + /// + /// # Examples + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let f = File::open("foo.txt")?; + /// + /// // read at most five bytes + /// let mut handle = f.take(5); + /// handle.set_limit(10); + /// + /// assert_eq!(handle.limit(), 10); + /// Ok(()) + /// } + /// ``` + #[stable(feature = "take_set_limit", since = "1.27.0")] + pub fn set_limit(&mut self, limit: u64) { + self.limit = limit; + } + + /// Consumes the `Take`, returning the wrapped reader. + /// + /// # Examples + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut file = File::open("foo.txt")?; + /// + /// let mut buffer = [0; 5]; + /// let mut handle = file.take(5); + /// handle.read(&mut buffer)?; + /// + /// let file = handle.into_inner(); + /// Ok(()) + /// } + /// ``` + #[stable(feature = "io_take_into_inner", since = "1.15.0")] + pub fn into_inner(self) -> T { + self.inner + } + + /// Gets a reference to the underlying reader. + /// + /// # Examples + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut file = File::open("foo.txt")?; + /// + /// let mut buffer = [0; 5]; + /// let mut handle = file.take(5); + /// handle.read(&mut buffer)?; + /// + /// let file = handle.get_ref(); + /// Ok(()) + /// } + /// ``` + #[stable(feature = "more_io_inner_methods", since = "1.20.0")] + pub fn get_ref(&self) -> &T { + &self.inner + } + + /// Gets a mutable reference to the underlying reader. + /// + /// Care should be taken to avoid modifying the internal I/O state of the + /// underlying reader as doing so may corrupt the internal limit of this + /// `Take`. + /// + /// # Examples + /// + /// ```no_run + /// use std::io; + /// use std::io::prelude::*; + /// use std::fs::File; + /// + /// fn main() -> io::Result<()> { + /// let mut file = File::open("foo.txt")?; + /// + /// let mut buffer = [0; 5]; + /// let mut handle = file.take(5); + /// handle.read(&mut buffer)?; + /// + /// let file = handle.get_mut(); + /// Ok(()) + /// } + /// ``` + #[stable(feature = "more_io_inner_methods", since = "1.20.0")] + pub fn get_mut(&mut self) -> &mut T { + &mut self.inner + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Read> Read for Take<T> { + fn read(&mut self, buf: &mut [u8]) -> Result<usize> { + // Don't call into inner reader at all at EOF because it may still block + if self.limit == 0 { + return Ok(0); + } + + let max = cmp::min(buf.len() as u64, self.limit) as usize; + let n = self.inner.read(&mut buf[..max])?; + self.limit -= n as u64; + Ok(n) + } + + unsafe fn initializer(&self) -> Initializer { + self.inner.initializer() + } + + fn read_to_end(&mut self, buf: &mut Vec<u8>) -> Result<usize> { + // Pass in a reservation_size closure that respects the current value + // of limit for each read. If we hit the read limit, this prevents the + // final zero-byte read from allocating again. + read_to_end_with_reservation(self, buf, |self_| cmp::min(self_.limit, 32) as usize) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: BufRead> BufRead for Take<T> { + fn fill_buf(&mut self) -> Result<&[u8]> { + // Don't call into inner reader at all at EOF because it may still block + if self.limit == 0 { + return Ok(&[]); + } + + let buf = self.inner.fill_buf()?; + let cap = cmp::min(buf.len() as u64, self.limit) as usize; + Ok(&buf[..cap]) + } + + fn consume(&mut self, amt: usize) { + // Don't let callers reset the limit by passing an overlarge value + let amt = cmp::min(amt as u64, self.limit) as usize; + self.limit -= amt as u64; + self.inner.consume(amt); + } +} + +/// An iterator over `u8` values of a reader. +/// +/// This struct is generally created by calling [`bytes`] on a reader. +/// Please see the documentation of [`bytes`] for more details. +/// +/// [`bytes`]: trait.Read.html#method.bytes +#[stable(feature = "rust1", since = "1.0.0")] +#[derive(Debug)] +pub struct Bytes<R> { + inner: R, +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<R: Read> Iterator for Bytes<R> { + type Item = Result<u8>; + + fn next(&mut self) -> Option<Result<u8>> { + let mut byte = 0; + loop { + return match self.inner.read(slice::from_mut(&mut byte)) { + Ok(0) => None, + Ok(..) => Some(Ok(byte)), + Err(ref e) if e.kind() == ErrorKind::Interrupted => continue, + Err(e) => Some(Err(e)), + }; + } + } +} + +/// An iterator over the contents of an instance of `BufRead` split on a +/// particular byte. +/// +/// This struct is generally created by calling [`split`] on a `BufRead`. +/// Please see the documentation of [`split`] for more details. +/// +/// [`split`]: trait.BufRead.html#method.split +#[stable(feature = "rust1", since = "1.0.0")] +#[derive(Debug)] +pub struct Split<B> { + buf: B, + delim: u8, +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<B: BufRead> Iterator for Split<B> { + type Item = Result<Vec<u8>>; + + fn next(&mut self) -> Option<Result<Vec<u8>>> { + let mut buf = Vec::new(); + match self.buf.read_until(self.delim, &mut buf) { + Ok(0) => None, + Ok(_n) => { + if buf[buf.len() - 1] == self.delim { + buf.pop(); + } + Some(Ok(buf)) + } + Err(e) => Some(Err(e)), + } + } +} + +/// An iterator over the lines of an instance of `BufRead`. +/// +/// This struct is generally created by calling [`lines`] on a `BufRead`. +/// Please see the documentation of [`lines`] for more details. +/// +/// [`lines`]: trait.BufRead.html#method.lines +#[stable(feature = "rust1", since = "1.0.0")] +#[derive(Debug)] +pub struct Lines<B> { + buf: B, +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<B: BufRead> Iterator for Lines<B> { + type Item = Result<String>; + + fn next(&mut self) -> Option<Result<String>> { + let mut buf = String::new(); + match self.buf.read_line(&mut buf) { + Ok(0) => None, + Ok(_n) => { + if buf.ends_with('\n') { + buf.pop(); + if buf.ends_with('\r') { + buf.pop(); + } + } + Some(Ok(buf)) + } + Err(e) => Some(Err(e)), + } + } +} + +#[cfg(test)] +mod tests { + use super::{repeat, Cursor, SeekFrom}; + use crate::cmp::{self, min}; + use crate::io::prelude::*; + use crate::io::{self, IoSlice, IoSliceMut}; + use crate::ops::Deref; + + #[test] + #[cfg_attr(target_os = "emscripten", ignore)] + fn read_until() { + let mut buf = Cursor::new(&b"12"[..]); + let mut v = Vec::new(); + assert_eq!(buf.read_until(b'3', &mut v).unwrap(), 2); + assert_eq!(v, b"12"); + + let mut buf = Cursor::new(&b"1233"[..]); + let mut v = Vec::new(); + assert_eq!(buf.read_until(b'3', &mut v).unwrap(), 3); + assert_eq!(v, b"123"); + v.truncate(0); + assert_eq!(buf.read_until(b'3', &mut v).unwrap(), 1); + assert_eq!(v, b"3"); + v.truncate(0); + assert_eq!(buf.read_until(b'3', &mut v).unwrap(), 0); + assert_eq!(v, []); + } + + #[test] + fn split() { + let buf = Cursor::new(&b"12"[..]); + let mut s = buf.split(b'3'); + assert_eq!(s.next().unwrap().unwrap(), vec![b'1', b'2']); + assert!(s.next().is_none()); + + let buf = Cursor::new(&b"1233"[..]); + let mut s = buf.split(b'3'); + assert_eq!(s.next().unwrap().unwrap(), vec![b'1', b'2']); + assert_eq!(s.next().unwrap().unwrap(), vec![]); + assert!(s.next().is_none()); + } + + #[test] + fn read_line() { + let mut buf = Cursor::new(&b"12"[..]); + let mut v = String::new(); + assert_eq!(buf.read_line(&mut v).unwrap(), 2); + assert_eq!(v, "12"); + + let mut buf = Cursor::new(&b"12\n\n"[..]); + let mut v = String::new(); + assert_eq!(buf.read_line(&mut v).unwrap(), 3); + assert_eq!(v, "12\n"); + v.truncate(0); + assert_eq!(buf.read_line(&mut v).unwrap(), 1); + assert_eq!(v, "\n"); + v.truncate(0); + assert_eq!(buf.read_line(&mut v).unwrap(), 0); + assert_eq!(v, ""); + } + + #[test] + fn lines() { + let buf = Cursor::new(&b"12\r"[..]); + let mut s = buf.lines(); + assert_eq!(s.next().unwrap().unwrap(), "12\r".to_string()); + assert!(s.next().is_none()); + + let buf = Cursor::new(&b"12\r\n\n"[..]); + let mut s = buf.lines(); + assert_eq!(s.next().unwrap().unwrap(), "12".to_string()); + assert_eq!(s.next().unwrap().unwrap(), "".to_string()); + assert!(s.next().is_none()); + } + + #[test] + fn read_to_end() { + let mut c = Cursor::new(&b""[..]); + let mut v = Vec::new(); + assert_eq!(c.read_to_end(&mut v).unwrap(), 0); + assert_eq!(v, []); + + let mut c = Cursor::new(&b"1"[..]); + let mut v = Vec::new(); + assert_eq!(c.read_to_end(&mut v).unwrap(), 1); + assert_eq!(v, b"1"); + + let cap = 1024 * 1024; + let data = (0..cap).map(|i| (i / 3) as u8).collect::<Vec<_>>(); + let mut v = Vec::new(); + let (a, b) = data.split_at(data.len() / 2); + assert_eq!(Cursor::new(a).read_to_end(&mut v).unwrap(), a.len()); + assert_eq!(Cursor::new(b).read_to_end(&mut v).unwrap(), b.len()); + assert_eq!(v, data); + } + + #[test] + fn read_to_string() { + let mut c = Cursor::new(&b""[..]); + let mut v = String::new(); + assert_eq!(c.read_to_string(&mut v).unwrap(), 0); + assert_eq!(v, ""); + + let mut c = Cursor::new(&b"1"[..]); + let mut v = String::new(); + assert_eq!(c.read_to_string(&mut v).unwrap(), 1); + assert_eq!(v, "1"); + + let mut c = Cursor::new(&b"\xff"[..]); + let mut v = String::new(); + assert!(c.read_to_string(&mut v).is_err()); + } + + #[test] + fn read_exact() { + let mut buf = [0; 4]; + + let mut c = Cursor::new(&b""[..]); + assert_eq!(c.read_exact(&mut buf).unwrap_err().kind(), io::ErrorKind::UnexpectedEof); + + let mut c = Cursor::new(&b"123"[..]).chain(Cursor::new(&b"456789"[..])); + c.read_exact(&mut buf).unwrap(); + assert_eq!(&buf, b"1234"); + c.read_exact(&mut buf).unwrap(); + assert_eq!(&buf, b"5678"); + assert_eq!(c.read_exact(&mut buf).unwrap_err().kind(), io::ErrorKind::UnexpectedEof); + } + + #[test] + fn read_exact_slice() { + let mut buf = [0; 4]; + + let mut c = &b""[..]; + assert_eq!(c.read_exact(&mut buf).unwrap_err().kind(), io::ErrorKind::UnexpectedEof); + + let mut c = &b"123"[..]; + assert_eq!(c.read_exact(&mut buf).unwrap_err().kind(), io::ErrorKind::UnexpectedEof); + // make sure the optimized (early returning) method is being used + assert_eq!(&buf, &[0; 4]); + + let mut c = &b"1234"[..]; + c.read_exact(&mut buf).unwrap(); + assert_eq!(&buf, b"1234"); + + let mut c = &b"56789"[..]; + c.read_exact(&mut buf).unwrap(); + assert_eq!(&buf, b"5678"); + assert_eq!(c, b"9"); + } + + #[test] + fn take_eof() { + struct R; + + impl Read for R { + fn read(&mut self, _: &mut [u8]) -> io::Result<usize> { + Err(io::Error::new(io::ErrorKind::Other, "")) + } + } + impl BufRead for R { + fn fill_buf(&mut self) -> io::Result<&[u8]> { + Err(io::Error::new(io::ErrorKind::Other, "")) + } + fn consume(&mut self, _amt: usize) {} + } + + let mut buf = [0; 1]; + assert_eq!(0, R.take(0).read(&mut buf).unwrap()); + assert_eq!(b"", R.take(0).fill_buf().unwrap()); + } + + fn cmp_bufread<Br1: BufRead, Br2: BufRead>(mut br1: Br1, mut br2: Br2, exp: &[u8]) { + let mut cat = Vec::new(); + loop { + let consume = { + let buf1 = br1.fill_buf().unwrap(); + let buf2 = br2.fill_buf().unwrap(); + let minlen = if buf1.len() < buf2.len() { buf1.len() } else { buf2.len() }; + assert_eq!(buf1[..minlen], buf2[..minlen]); + cat.extend_from_slice(&buf1[..minlen]); + minlen + }; + if consume == 0 { + break; + } + br1.consume(consume); + br2.consume(consume); + } + assert_eq!(br1.fill_buf().unwrap().len(), 0); + assert_eq!(br2.fill_buf().unwrap().len(), 0); + assert_eq!(&cat[..], &exp[..]) + } + + #[test] + fn chain_bufread() { + let testdata = b"ABCDEFGHIJKL"; + let chain1 = + (&testdata[..3]).chain(&testdata[3..6]).chain(&testdata[6..9]).chain(&testdata[9..]); + let chain2 = (&testdata[..4]).chain(&testdata[4..8]).chain(&testdata[8..]); + cmp_bufread(chain1, chain2, &testdata[..]); + } + + #[test] + fn chain_zero_length_read_is_not_eof() { + let a = b"A"; + let b = b"B"; + let mut s = String::new(); + let mut chain = (&a[..]).chain(&b[..]); + chain.read(&mut []).unwrap(); + chain.read_to_string(&mut s).unwrap(); + assert_eq!("AB", s); + } + + #[bench] + #[cfg_attr(target_os = "emscripten", ignore)] + fn bench_read_to_end(b: &mut test::Bencher) { + b.iter(|| { + let mut lr = repeat(1).take(10000000); + let mut vec = Vec::with_capacity(1024); + super::read_to_end(&mut lr, &mut vec) + }); + } + + #[test] + fn seek_len() -> io::Result<()> { + let mut c = Cursor::new(vec![0; 15]); + assert_eq!(c.stream_len()?, 15); + + c.seek(SeekFrom::End(0))?; + let old_pos = c.stream_position()?; + assert_eq!(c.stream_len()?, 15); + assert_eq!(c.stream_position()?, old_pos); + + c.seek(SeekFrom::Start(7))?; + c.seek(SeekFrom::Current(2))?; + let old_pos = c.stream_position()?; + assert_eq!(c.stream_len()?, 15); + assert_eq!(c.stream_position()?, old_pos); + + Ok(()) + } + + #[test] + fn seek_position() -> io::Result<()> { + // All `asserts` are duplicated here to make sure the method does not + // change anything about the seek state. + let mut c = Cursor::new(vec![0; 15]); + assert_eq!(c.stream_position()?, 0); + assert_eq!(c.stream_position()?, 0); + + c.seek(SeekFrom::End(0))?; + assert_eq!(c.stream_position()?, 15); + assert_eq!(c.stream_position()?, 15); + + c.seek(SeekFrom::Start(7))?; + c.seek(SeekFrom::Current(2))?; + assert_eq!(c.stream_position()?, 9); + assert_eq!(c.stream_position()?, 9); + + c.seek(SeekFrom::End(-3))?; + c.seek(SeekFrom::Current(1))?; + c.seek(SeekFrom::Current(-5))?; + assert_eq!(c.stream_position()?, 8); + assert_eq!(c.stream_position()?, 8); + + Ok(()) + } + + // A simple example reader which uses the default implementation of + // read_to_end. + struct ExampleSliceReader<'a> { + slice: &'a [u8], + } + + impl<'a> Read for ExampleSliceReader<'a> { + fn read(&mut self, buf: &mut [u8]) -> io::Result<usize> { + let len = cmp::min(self.slice.len(), buf.len()); + buf[..len].copy_from_slice(&self.slice[..len]); + self.slice = &self.slice[len..]; + Ok(len) + } + } + + #[test] + fn test_read_to_end_capacity() -> io::Result<()> { + let input = &b"foo"[..]; + + // read_to_end() generally needs to over-allocate, both for efficiency + // and so that it can distinguish EOF. Assert that this is the case + // with this simple ExampleSliceReader struct, which uses the default + // implementation of read_to_end. Even though vec1 is allocated with + // exactly enough capacity for the read, read_to_end will allocate more + // space here. + let mut vec1 = Vec::with_capacity(input.len()); + ExampleSliceReader { slice: input }.read_to_end(&mut vec1)?; + assert_eq!(vec1.len(), input.len()); + assert!(vec1.capacity() > input.len(), "allocated more"); + + // However, std::io::Take includes an implementation of read_to_end + // that will not allocate when the limit has already been reached. In + // this case, vec2 never grows. + let mut vec2 = Vec::with_capacity(input.len()); + ExampleSliceReader { slice: input }.take(input.len() as u64).read_to_end(&mut vec2)?; + assert_eq!(vec2.len(), input.len()); + assert_eq!(vec2.capacity(), input.len(), "did not allocate more"); + + Ok(()) + } + + #[test] + fn io_slice_mut_advance() { + let mut buf1 = [1; 8]; + let mut buf2 = [2; 16]; + let mut buf3 = [3; 8]; + let mut bufs = &mut [ + IoSliceMut::new(&mut buf1), + IoSliceMut::new(&mut buf2), + IoSliceMut::new(&mut buf3), + ][..]; + + // Only in a single buffer.. + bufs = IoSliceMut::advance(bufs, 1); + assert_eq!(bufs[0].deref(), [1; 7].as_ref()); + assert_eq!(bufs[1].deref(), [2; 16].as_ref()); + assert_eq!(bufs[2].deref(), [3; 8].as_ref()); + + // Removing a buffer, leaving others as is. + bufs = IoSliceMut::advance(bufs, 7); + assert_eq!(bufs[0].deref(), [2; 16].as_ref()); + assert_eq!(bufs[1].deref(), [3; 8].as_ref()); + + // Removing a buffer and removing from the next buffer. + bufs = IoSliceMut::advance(bufs, 18); + assert_eq!(bufs[0].deref(), [3; 6].as_ref()); + } + + #[test] + fn io_slice_mut_advance_empty_slice() { + let empty_bufs = &mut [][..]; + // Shouldn't panic. + IoSliceMut::advance(empty_bufs, 1); + } + + #[test] + fn io_slice_mut_advance_beyond_total_length() { + let mut buf1 = [1; 8]; + let mut bufs = &mut [IoSliceMut::new(&mut buf1)][..]; + + // Going beyond the total length should be ok. + bufs = IoSliceMut::advance(bufs, 9); + assert!(bufs.is_empty()); + } + + #[test] + fn io_slice_advance() { + let buf1 = [1; 8]; + let buf2 = [2; 16]; + let buf3 = [3; 8]; + let mut bufs = &mut [IoSlice::new(&buf1), IoSlice::new(&buf2), IoSlice::new(&buf3)][..]; + + // Only in a single buffer.. + bufs = IoSlice::advance(bufs, 1); + assert_eq!(bufs[0].deref(), [1; 7].as_ref()); + assert_eq!(bufs[1].deref(), [2; 16].as_ref()); + assert_eq!(bufs[2].deref(), [3; 8].as_ref()); + + // Removing a buffer, leaving others as is. + bufs = IoSlice::advance(bufs, 7); + assert_eq!(bufs[0].deref(), [2; 16].as_ref()); + assert_eq!(bufs[1].deref(), [3; 8].as_ref()); + + // Removing a buffer and removing from the next buffer. + bufs = IoSlice::advance(bufs, 18); + assert_eq!(bufs[0].deref(), [3; 6].as_ref()); + } + + #[test] + fn io_slice_advance_empty_slice() { + let empty_bufs = &mut [][..]; + // Shouldn't panic. + IoSlice::advance(empty_bufs, 1); + } + + #[test] + fn io_slice_advance_beyond_total_length() { + let buf1 = [1; 8]; + let mut bufs = &mut [IoSlice::new(&buf1)][..]; + + // Going beyond the total length should be ok. + bufs = IoSlice::advance(bufs, 9); + assert!(bufs.is_empty()); + } + + /// Create a new writer that reads from at most `n_bufs` and reads + /// `per_call` bytes (in total) per call to write. + fn test_writer(n_bufs: usize, per_call: usize) -> TestWriter { + TestWriter { n_bufs, per_call, written: Vec::new() } + } + + struct TestWriter { + n_bufs: usize, + per_call: usize, + written: Vec<u8>, + } + + impl Write for TestWriter { + fn write(&mut self, buf: &[u8]) -> io::Result<usize> { + self.write_vectored(&[IoSlice::new(buf)]) + } + + fn write_vectored(&mut self, bufs: &[IoSlice<'_>]) -> io::Result<usize> { + let mut left = self.per_call; + let mut written = 0; + for buf in bufs.iter().take(self.n_bufs) { + let n = min(left, buf.len()); + self.written.extend_from_slice(&buf[0..n]); + left -= n; + written += n; + } + Ok(written) + } + + fn flush(&mut self) -> io::Result<()> { + Ok(()) + } + } + + #[test] + fn test_writer_read_from_one_buf() { + let mut writer = test_writer(1, 2); + + assert_eq!(writer.write(&[]).unwrap(), 0); + assert_eq!(writer.write_vectored(&[]).unwrap(), 0); + + // Read at most 2 bytes. + assert_eq!(writer.write(&[1, 1, 1]).unwrap(), 2); + let bufs = &[IoSlice::new(&[2, 2, 2])]; + assert_eq!(writer.write_vectored(bufs).unwrap(), 2); + + // Only read from first buf. + let bufs = &[IoSlice::new(&[3]), IoSlice::new(&[4, 4])]; + assert_eq!(writer.write_vectored(bufs).unwrap(), 1); + + assert_eq!(writer.written, &[1, 1, 2, 2, 3]); + } + + #[test] + fn test_writer_read_from_multiple_bufs() { + let mut writer = test_writer(3, 3); + + // Read at most 3 bytes from two buffers. + let bufs = &[IoSlice::new(&[1]), IoSlice::new(&[2, 2, 2])]; + assert_eq!(writer.write_vectored(bufs).unwrap(), 3); + + // Read at most 3 bytes from three buffers. + let bufs = &[IoSlice::new(&[3]), IoSlice::new(&[4]), IoSlice::new(&[5, 5])]; + assert_eq!(writer.write_vectored(bufs).unwrap(), 3); + + assert_eq!(writer.written, &[1, 2, 2, 3, 4, 5]); + } + + #[test] + fn test_write_all_vectored() { + #[rustfmt::skip] // Becomes unreadable otherwise. + let tests: Vec<(_, &'static [u8])> = vec![ + (vec![], &[]), + (vec![IoSlice::new(&[]), IoSlice::new(&[])], &[]), + (vec![IoSlice::new(&[1])], &[1]), + (vec![IoSlice::new(&[1, 2])], &[1, 2]), + (vec![IoSlice::new(&[1, 2, 3])], &[1, 2, 3]), + (vec![IoSlice::new(&[1, 2, 3, 4])], &[1, 2, 3, 4]), + (vec![IoSlice::new(&[1, 2, 3, 4, 5])], &[1, 2, 3, 4, 5]), + (vec![IoSlice::new(&[1]), IoSlice::new(&[2])], &[1, 2]), + (vec![IoSlice::new(&[1]), IoSlice::new(&[2, 2])], &[1, 2, 2]), + (vec![IoSlice::new(&[1, 1]), IoSlice::new(&[2, 2])], &[1, 1, 2, 2]), + (vec![IoSlice::new(&[1, 1]), IoSlice::new(&[2, 2, 2])], &[1, 1, 2, 2, 2]), + (vec![IoSlice::new(&[1, 1]), IoSlice::new(&[2, 2, 2])], &[1, 1, 2, 2, 2]), + (vec![IoSlice::new(&[1, 1, 1]), IoSlice::new(&[2, 2, 2])], &[1, 1, 1, 2, 2, 2]), + (vec![IoSlice::new(&[1, 1, 1]), IoSlice::new(&[2, 2, 2, 2])], &[1, 1, 1, 2, 2, 2, 2]), + (vec![IoSlice::new(&[1, 1, 1, 1]), IoSlice::new(&[2, 2, 2, 2])], &[1, 1, 1, 1, 2, 2, 2, 2]), + (vec![IoSlice::new(&[1]), IoSlice::new(&[2]), IoSlice::new(&[3])], &[1, 2, 3]), + (vec![IoSlice::new(&[1, 1]), IoSlice::new(&[2, 2]), IoSlice::new(&[3, 3])], &[1, 1, 2, 2, 3, 3]), + (vec![IoSlice::new(&[1]), IoSlice::new(&[2, 2]), IoSlice::new(&[3, 3, 3])], &[1, 2, 2, 3, 3, 3]), + (vec![IoSlice::new(&[1, 1, 1]), IoSlice::new(&[2, 2, 2]), IoSlice::new(&[3, 3, 3])], &[1, 1, 1, 2, 2, 2, 3, 3, 3]), + ]; + + let writer_configs = &[(1, 1), (1, 2), (1, 3), (2, 2), (2, 3), (3, 3)]; + + for (n_bufs, per_call) in writer_configs.iter().copied() { + for (mut input, wanted) in tests.clone().into_iter() { + let mut writer = test_writer(n_bufs, per_call); + assert!(writer.write_all_vectored(&mut *input).is_ok()); + assert_eq!(&*writer.written, &*wanted); + } + } + } +} |