tokio/tokio-io/src/io/buf_reader.rs

use super::DEFAULT_BUF_SIZE;
use crate::{AsyncBufRead, AsyncRead};
use futures_core::ready;
use pin_utils::{unsafe_pinned, unsafe_unpinned};
use std::io::{self, Read};
use std::pin::Pin;
use std::task::{Context, Poll};
use std::{cmp, fmt};

/// The `BufReader` struct adds buffering to any reader.
///
/// It can be excessively inefficient to work directly with a [`AsyncRead`]
/// instance. A `BufReader` performs large, infrequent reads on the underlying
/// [`AsyncRead`] and maintains an in-memory buffer of the results.
///
/// `BufReader` can improve the speed of programs that make *small* and
/// *repeated* read calls to the same file or network socket. It does not
/// help when reading very large amounts at once, or reading just one or a few
/// times. It also provides no advantage when reading from a source that is
/// already in memory, like a `Vec<u8>`.
///
/// When the `BufReader` is dropped, the contents of its buffer will be
/// discarded. Creating multiple instances of a `BufReader` on the same
/// stream can cause data loss.
// TODO: Examples
pub struct BufReader<R> {
    inner: R,
    buf: Box<[u8]>,
    pos: usize,
    cap: usize,
}

impl<R: AsyncRead> BufReader<R> {
    unsafe_pinned!(inner: R);
    unsafe_unpinned!(pos: usize);
    unsafe_unpinned!(cap: usize);

    /// Creates a new `BufReader` with a default buffer capacity. The default is currently 8 KB,
    /// but may change in the future.
    pub fn new(inner: R) -> Self {
        Self::with_capacity(DEFAULT_BUF_SIZE, inner)
    }

    /// Creates a new `BufReader` with the specified buffer capacity.
    pub fn with_capacity(capacity: usize, inner: R) -> Self {
        unsafe {
            let mut buffer = Vec::with_capacity(capacity);
            buffer.set_len(capacity);
            inner.prepare_uninitialized_buffer(&mut buffer);
            Self {
                inner,
                buf: buffer.into_boxed_slice(),
                pos: 0,
                cap: 0,
            }
        }
    }

    /// Gets a reference to the underlying reader.
    ///
    /// It is inadvisable to directly read from the underlying reader.
    pub fn get_ref(&self) -> &R {
        &self.inner
    }

    /// Gets a mutable reference to the underlying reader.
    ///
    /// It is inadvisable to directly read from the underlying reader.
    pub fn get_mut(&mut self) -> &mut R {
        &mut self.inner
    }

    /// Gets a pinned mutable reference to the underlying reader.
    ///
    /// It is inadvisable to directly read from the underlying reader.
    pub fn get_pin_mut(self: Pin<&mut Self>) -> Pin<&mut R> {
        self.inner()
    }

    /// Consumes this `BufWriter`, returning the underlying reader.
    ///
    /// Note that any leftover data in the internal buffer is lost.
    pub fn into_inner(self) -> R {
        self.inner
    }

    /// Returns a reference to the internally buffered data.
    ///
    /// Unlike `fill_buf`, this will not attempt to fill the buffer if it is empty.
    pub fn buffer(&self) -> &[u8] {
        &self.buf[self.pos..self.cap]
    }

    /// Invalidates all data in the internal buffer.
    #[inline]
    fn discard_buffer(mut self: Pin<&mut Self>) {
        *self.as_mut().pos() = 0;
        *self.cap() = 0;
    }
}

impl<R: AsyncRead> AsyncRead for BufReader<R> {
    fn poll_read(
        mut self: Pin<&mut Self>,
        cx: &mut Context<'_>,
        buf: &mut [u8],
    ) -> Poll<io::Result<usize>> {
        // If we don't have any buffered data and we're doing a massive read
        // (larger than our internal buffer), bypass our internal buffer
        // entirely.
        if self.pos == self.cap && buf.len() >= self.buf.len() {
            let res = ready!(self.as_mut().inner().poll_read(cx, buf));
            self.discard_buffer();
            return Poll::Ready(res);
        }
        let mut rem = ready!(self.as_mut().poll_fill_buf(cx))?;
        let nread = rem.read(buf)?;
        self.consume(nread);
        Poll::Ready(Ok(nread))
    }

    // we can't skip unconditionally because of the large buffer case in read.
    unsafe fn prepare_uninitialized_buffer(&self, buf: &mut [u8]) -> bool {
        self.inner.prepare_uninitialized_buffer(buf)
    }
}

impl<R: AsyncRead> AsyncBufRead for BufReader<R> {
    fn poll_fill_buf(self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<io::Result<&[u8]>> {
        let Self {
            inner,
            buf,
            cap,
            pos,
        } = unsafe { self.get_unchecked_mut() };
        let mut inner = unsafe { Pin::new_unchecked(inner) };

        // If we've reached the end of our internal buffer then we need to fetch
        // some more data from the underlying reader.
        // Branch using `>=` instead of the more correct `==`
        // to tell the compiler that the pos..cap slice is always valid.
        if *pos >= *cap {
            debug_assert!(*pos == *cap);
            *cap = ready!(inner.as_mut().poll_read(cx, buf))?;
            *pos = 0;
        }
        Poll::Ready(Ok(&buf[*pos..*cap]))
    }

    fn consume(mut self: Pin<&mut Self>, amt: usize) {
        *self.as_mut().pos() = cmp::min(self.pos + amt, self.cap);
    }
}

impl<R: AsyncRead + fmt::Debug> fmt::Debug for BufReader<R> {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        f.debug_struct("BufReader")
            .field("reader", &self.inner)
            .field(
                "buffer",
                &format_args!("{}/{}", self.cap - self.pos, self.buf.len()),
            )
            .finish()
    }
}