1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123
//! A modified version of the Rust standard library's `std::io` module, suitable
//! for use in Mycelium and other kernels.
//!
//! The traits and functions here are mostly identical to (and copied from!) the
//! standard library's `std::io` module, with the following differences:
//!
//! - `Read::read_to_end` and `Read::read_to_string` require the "alloc" feature
//! flag on `mycelium_util` (which is enabled by default). Bootloaders & other
//! code which cannot allocate may disable this feature flag.
//! - `Read::read_vectored` and `Write::write_vectored` do not exist.
//! - Most of the `BufRead` utility functions (`lines`, `split`, `read_until`)
//! require the "alloc" feature
//! - `BufReader` and `BufWriter` require the "alloc" feature (and are not yet implemented).
//! - The `io::Error` type takes an `ErrorKind` and an optional `&'static str`,
//! and does not wrap another error. This is because we need to be able to
//! construct I/O errors even when we cannot allocate.
mod cursor;
mod error;
mod impls;
mod initializer;
pub mod prelude;
mod util;
pub use self::cursor::Cursor;
pub use self::error::{Error, ErrorKind, Result};
pub use self::initializer::Initializer;
pub use self::util::{copy, empty, repeat, sink, Empty, Repeat, Sink};
use core::{cmp, fmt, slice, str};
#[cfg(feature = "alloc")]
use alloc::{string::String, vec::Vec};
// FIXME(eliza): calculate based on arch?
const DEFAULT_BUF_SIZE: usize = 256;
/// 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.
///
/// This is essentially a vendored version of the [`std::io::Read`] trait from
/// the Rust standard library, modified to work without `std`. See the
/// module-level docs for [`mycelium_util::io`] for more information on how
/// `mycelium_util`'s `io` module differs from `std`'s.
///
/// [`read()`]: Self::read
/// [`mycelium_util::io`]: crate::io
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 but 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.
///
/// 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>`]: ../mem/union.MaybeUninit.html
///
/// # 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.
fn read(&mut self, buf: &mut [u8]) -> Result<usize>;
/// 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.
///
/// [`Initializer::nop()`]: struct.Initializer.html#method.nop
/// [`Initializer`]: struct.Initializer.html
#[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`.
///
/// [`read()`]: trait.Read.html#tymethod.read
/// [`ErrorKind::Interrupted`]: enum.ErrorKind.html#variant.Interrupted
#[cfg(feature = "alloc")]
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]: #method.read_to_end
#[cfg(feature = "alloc")]
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.
///
/// # 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.
///
/// [`ErrorKind::Interrupted`]: enum.ErrorKind.html#variant.Interrupted
/// [`ErrorKind::UnexpectedEof`]: enum.ErrorKind.html#variant.UnexpectedEof
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.
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.
///
/// [`Iterator`]: ../../std/iter/trait.Iterator.html
/// [`Result`]: ../../std/result/enum.Result.html
/// [`io::Error`]: ../../std/io/struct.Error.html
/// [`u8`]: ../../std/primitive.u8.html
/// [`Ok`]: ../../std/result/enum.Result.html#variant.Ok
/// [`Err`]: ../../std/result/enum.Result.html#variant.Err
/// [`None`]: ../../std/option/enum.Option.html#variant.None
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]: ../fs/struct.File.html
///
/// ```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(())
/// }
/// ```
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()`](Self::read) may succeed.
fn take(self, limit: u64) -> Take<Self>
where
Self: Sized,
{
Take { inner: self, limit }
}
}
/// 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 adapters and explicit buffers
/// themselves for ensuring that all buffered data has been pushed out to the
/// 'true sink'.
///
/// This is essentially a vendored version of the [`std::io::Write`] trait from
/// the Rust standard library, modified to work without `std`. See the
/// module-level docs for [`mycelium_util::io`] for more information on how
/// `mycelium_util`'s `io` module differs from `std`'s.
///
/// [`write`]: Write::write
/// [`flush`]: Write::flush
/// [`mycelium_util::io`]: crate::io
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.
///
/// [`Err`]: ../../std/result/enum.Result.html#variant.Err
/// [`Ok(n)`]: ../../std/result/enum.Result.html#variant.Ok
fn write(&mut self, buf: &[u8]) -> Result<usize>;
/// Flush this output stream, ensuring that all intermediately buffered
/// contents reach their destination.
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.
///
/// # Errors
///
/// This function will return the first error of
/// non-[`ErrorKind::Interrupted`] kind that [`write`] returns.
///
/// [`write`]: #tymethod.write
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(())
}
/// Writes a formatted string into this writer, returning any error
/// encountered.
///
/// This method is primarily used to interface with the
/// [`format_args!`][formatargs] macro, but it is rare that this should
/// explicitly be called. The [`write!`][write] macro should be favored to
/// invoke this method instead.
///
/// [formatargs]: ../macro.format_args.html
/// [write]: ../macro.write.html
///
/// 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]: #method.write_all
///
/// # Errors
///
/// This function will return any I/O error reported while formatting.
fn write_fmt(&mut self, fmt: fmt::Arguments<'_>) -> Result<()> {
let mut output = WriteFmtAdaptor::new(self);
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.
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.
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
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.
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))`.
fn stream_position(&mut self) -> Result<u64> {
self.seek(SeekFrom::Current(0))
}
}
/// 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.
///
/// [`BufReader`]: struct.BufReader.html
/// [`read_line`]: #method.read_line
/// [`lines`]: #method.lines
/// [`Read`]: trait.Read.html
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.
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`].
///
/// [`fill_buf`]: Self::fill_buf
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.
///
/// # 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
#[cfg(feature = "alloc")]
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.
///
/// # 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
#[cfg(feature = "alloc")]
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`]: type.Result.html
/// [`Vec<u8>`]: ...alloc/vec/struct.Vec.html
/// [`read_until`]: #method.read_until
#[cfg(feature = "alloc")]
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`]: type.Result.html
/// [`String`]: ../string/struct.String.html
///
/// # Errors
///
/// Each line of the iterator has the same error semantics as [`BufRead::read_line`].
///
/// [`BufRead::read_line`]: trait.BufRead.html#method.read_line
#[cfg(feature = "alloc")]
fn lines(self) -> Lines<Self>
where
Self: Sized,
{
Lines { buf: self }
}
}
/// 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)]
pub enum SeekFrom {
/// Sets the offset to the provided number of bytes.
Start(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.
End(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.
Current(i64),
}
/// 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
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.
pub fn into_inner(self) -> (T, U) {
(self.first, self.second)
}
/// Gets references to the underlying readers in this `Chain`.
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`.
pub fn get_mut(&mut self) -> (&mut T, &mut U) {
(&mut self.first, &mut self.second)
}
}
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()
}
}
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)
}
}
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()? {
&[] => 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
#[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.
///
/// [`Read`]:trait.Read.html
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.
pub fn set_limit(&mut self, limit: u64) {
self.limit = limit;
}
/// Consumes the `Take`, returning the wrapped reader.
pub fn into_inner(self) -> T {
self.inner
}
/// Gets a reference to the underlying reader.
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`.
pub fn get_mut(&mut self) -> &mut T {
&mut self.inner
}
}
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)
}
#[cfg(feature = "alloc")]
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)
}
}
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
#[derive(Debug)]
pub struct Bytes<R> {
inner: R,
}
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
#[cfg(feature = "alloc")]
#[derive(Debug)]
pub struct Split<B> {
buf: B,
delim: u8,
}
#[cfg(feature = "alloc")]
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
#[cfg(feature = "alloc")]
#[derive(Debug)]
pub struct Lines<B> {
buf: B,
}
#[cfg(feature = "alloc")]
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)),
}
}
}
// 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.
#[cfg(feature = "alloc")]
fn read_to_end<R: Read + ?Sized>(r: &mut R, buf: &mut Vec<u8>) -> Result<usize> {
read_to_end_with_reservation(r, buf, |_| 32)
}
#[cfg(feature = "alloc")]
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
}
#[cfg(feature = "alloc")]
struct Guard<'a> {
buf: &'a mut Vec<u8>,
len: usize,
}
#[cfg(feature = "alloc")]
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.
#[cfg(feature = "alloc")]
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
}
}
}
#[cfg(feature = "alloc")]
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),
};
// This is intentionally simple. We may improve upon it in the future with a
// proper `memchr` implementation if it proves to be necessary.
match available.iter().position(|&c| c == delim) {
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);
}
}
}
// Create a shim which translates a Write to a fmt::Write and saves
// off I/O errors. instead of discarding them
pub(crate) struct WriteFmtAdaptor<'a, T: ?Sized + 'a> {
inner: &'a mut T,
error: Result<()>,
}
impl<'a, T: ?Sized + 'a> WriteFmtAdaptor<'a, T> {
pub(crate) fn new(inner: &'a mut T) -> Self {
Self {
inner,
error: Ok(()),
}
}
}
impl<T: Write + ?Sized> fmt::Write for WriteFmtAdaptor<'_, 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)
}
}
}
}