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
// Copyright 2015 The Rust Project Developers. See the COPYRIGHT // file at the top-level directory of this distribution and at // http://rust-lang.org/COPYRIGHT. // // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or // http://www.apache.org/licenses/LICENSE-2.0> or the MIT license // <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your // option. This file may not be copied, modified, or distributed // except according to those terms. //! Traits, helpers, and type definitions for core I/O functionality. //! //! > **NOTE**: This module is very much a work in progress and is under active //! > development. At this time it is still recommended to use the `old_io` //! > module while the details of this module shake out. #![unstable(feature = "io", reason = "this new I/O module is still under active deveopment and \ APIs are subject to tweaks fairly regularly")] use cmp; use unicode::str as core_str; use error::Error as StdError; use fmt; use iter::Iterator; use marker::Sized; use ops::{Drop, FnOnce}; use option::Option::{self, Some, None}; use ptr::PtrExt; use result::Result::{Ok, Err}; use result; use slice::{self, SliceExt}; use string::String; use str::{self, StrExt}; use vec::Vec; pub use self::buffered::{BufReader, BufWriter, BufStream, LineWriter}; pub use self::buffered::IntoInnerError; pub use self::cursor::Cursor; pub use self::error::{Result, Error, ErrorKind}; pub use self::util::{copy, sink, Sink, empty, Empty, repeat, Repeat}; pub mod prelude; mod buffered; mod cursor; mod error; mod impls; mod util; const DEFAULT_BUF_SIZE: usize = 64 * 1024; // Acquires a slice of the vector `v` from its length to its capacity // (uninitialized data), reads into it, and then updates the length. // // This function is leveraged to efficiently read some bytes into a destination // vector without extra copying and taking advantage of the space that's already // in `v`. // // The buffer we're passing down, however, is pointing at uninitialized data // (the end of a `Vec`), and many operations will be *much* faster if we don't // have to zero it out. In order to prevent LLVM from generating an `undef` // value when reads happen from this uninitialized memory, we force LLVM to // think it's initialized by sending it through a black box. This should prevent // actual undefined behavior after optimizations. fn with_end_to_cap<F>(v: &mut Vec<u8>, f: F) -> Result<usize> where F: FnOnce(&mut [u8]) -> Result<usize> { unsafe { let n = try!(f({ let base = v.as_mut_ptr().offset(v.len() as isize); black_box(slice::from_raw_parts_mut(base, v.capacity() - v.len())) })); // If the closure (typically a `read` implementation) reported that it // read a larger number of bytes than the vector actually has, we need // to be sure to clamp the vector to at most its capacity. let new_len = cmp::min(v.capacity(), v.len() + n); v.set_len(new_len); return Ok(n); } // Semi-hack used to prevent LLVM from retaining any assumptions about // `dummy` over this function call unsafe fn black_box<T>(mut dummy: T) -> T { asm!("" :: "r"(&mut dummy) : "memory"); dummy } } // 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<()> where F: FnOnce(&mut Vec<u8>) -> Result<()> { struct Guard<'a> { s: &'a mut Vec<u8>, len: usize } #[unsafe_destructor] impl<'a> Drop for Guard<'a> { fn drop(&mut self) { unsafe { self.s.set_len(self.len); } } } unsafe { let mut g = Guard { len: buf.len(), s: buf.as_mut_vec() }; let ret = f(g.s); if str::from_utf8(&g.s[g.len..]).is_err() { ret.and_then(|()| { Err(Error::new(ErrorKind::InvalidInput, "stream did not contain valid UTF-8", None)) }) } else { g.len = g.s.len(); ret } } } fn read_to_end<R: Read + ?Sized>(r: &mut R, buf: &mut Vec<u8>) -> Result<()> { loop { if buf.capacity() == buf.len() { buf.reserve(DEFAULT_BUF_SIZE); } match with_end_to_cap(buf, |b| r.read(b)) { Ok(0) => return Ok(()), Ok(_) => {} Err(ref e) if e.kind() == ErrorKind::Interrupted => {} Err(e) => return Err(e), } } } /// A trait for objects which are byte-oriented sources. /// /// Readers are defined by one method, `read`. Each call to `read` will attempt /// to pull bytes from this source into a provided buffer. /// /// Readers are intended to be composable with one another. Many objects /// throughout the I/O and related libraries take and provide types which /// implement the `Read` trait. 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 ben 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. /// /// # 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. fn read(&mut self, buf: &mut [u8]) -> Result<usize>; /// 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 return a call to `read` either: /// /// 1. Returns `Ok(0)`. /// 2. Returns an error which is not of the kind `ErrorKind::Interrupted`. /// /// Until one of these conditions is met the function will continuously /// invoke `read` to append more data to `buf`. /// /// # 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`. fn read_to_end(&mut self, buf: &mut Vec<u8>) -> Result<()> { read_to_end(self, buf) } /// Read all bytes until EOF in this source, placing them into `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` for other error semantics. fn read_to_string(&mut self, buf: &mut String) -> Result<()> { // 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)) } } /// Extension methods for all instances of `Read`, typically imported through /// `std::io::prelude::*`. pub trait ReadExt: Read + Sized { /// Create 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 { self } /// Transform this `Read` instance to an `Iterator` over its bytes. /// /// The returned type implements `Iterator` where the `Item` is `Result<u8, /// R::Err>`. The yielded item is `Ok` if a byte was successfully read and /// `Err` otherwise for I/O errors. EOF is mapped to returning `None` from /// this iterator. fn bytes(self) -> Bytes<Self> { Bytes { inner: self } } /// Transform this `Read` instance to an `Iterator` over `char`s. /// /// This adaptor will attempt to interpret this reader as an UTF-8 encoded /// sequence of characters. The returned iterator will return `None` once /// EOF is reached for this reader. Otherwise each element yielded will be a /// `Result<char, E>` where `E` may contain information about what I/O error /// occurred or where decoding failed. /// /// Currently this adaptor will discard intermediate data read, and should /// be avoided if this is not desired. fn chars(self) -> Chars<Self> { Chars { inner: self } } /// Create 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`. fn chain<R: Read>(self, next: R) -> Chain<Self, R> { Chain { first: self, second: next, done_first: false } } /// Create 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. fn take(self, limit: u64) -> Take<Self> { Take { inner: self, limit: limit } } /// Creates a reader adaptor which will write all read data into the given /// output stream. /// /// Whenever the returned `Read` instance is read it will write the read /// data to `out`. The current semantics of this implementation imply that /// a `write` error will not report how much data was initially read. fn tee<W: Write>(self, out: W) -> Tee<Self, W> { Tee { reader: self, writer: out } } } impl<T: Read> ReadExt for T {} /// A trait for objects which are byte-oriented sinks. /// /// 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 objects /// throughout the I/O and related libraries take and provide types which /// implement the `Write` trait. pub trait Write { /// Write a buffer into this object, 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 indicated through /// an `Err` variant. /// /// If the return value is `Ok(n)` then it must be guaranteed that /// `0 <= 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. fn write(&mut self, buf: &[u8]) -> Result<usize>; /// 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. fn flush(&mut self) -> Result<()>; /// Attempts to write an entire buffer into this write. /// /// This method will continuously call `write` while there is more data to /// write. This method will not return until the entire buffer has been /// successfully written or an error occurs. The first error generated from /// this method will be returned. /// /// # Errors /// /// This function will return the first error that `write` returns. fn write_all(&mut self, mut buf: &[u8]) -> Result<()> { while buf.len() > 0 { match self.write(buf) { Ok(0) => return Err(Error::new(ErrorKind::WriteZero, "failed to write whole buffer", None)), 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!` /// 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` 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. /// /// # Errors /// /// This function will return any I/O error reported while formatting. 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<'a, T: Write + ?Sized> fmt::Write for Adaptor<'a, 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(..) => output.error } } } /// Extension methods for all instances of `Write`, typically imported through /// `std::io::prelude::*`. pub trait WriteExt: Write + Sized { /// Create 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 { self } /// Creates a new writer which will write all data to both this writer and /// another writer. /// /// All data written to the returned writer will both be written to `self` /// as well as `other`. Note that the error semantics of the current /// implementation do not precisely track where errors happen. For example /// an error on the second call to `write` will not report that the first /// call to `write` succeeded. fn broadcast<W: Write>(self, other: W) -> Broadcast<Self, W> { Broadcast { first: self, second: other } } } impl<T: Write> WriteExt for T {} /// An object implementing `Seek` internally has some form of 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 seeking before offset /// 0 is an error. /// /// The behavior when seeking past the end of the stream is implementation /// defined. /// /// This method returns the new position within the stream if the seek /// operation completed successfully. /// /// # Errors /// /// Seeking to a negative offset is considered an error fn seek(&mut self, pos: SeekFrom) -> Result<u64>; } /// Enumeration of possible methods to seek within an I/O object. #[derive(Copy, PartialEq, Eq, Clone, Debug)] pub enum SeekFrom { /// Set the offset to the provided number of bytes. Start(u64), /// Set 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 is an error to /// seek before byte 0. End(i64), /// Set the offset to the current position plus the specified number of /// bytes. /// /// It is possible to seek beyond the end of an object, but is an error to /// seek before byte 0. Current(i64), } fn read_until<R: BufRead + ?Sized>(r: &mut R, delim: u8, buf: &mut Vec<u8>) -> Result<()> { 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 available.position_elem(&delim) { Some(i) => { buf.push_all(&available[..i + 1]); (true, i + 1) } None => { buf.push_all(available); (false, available.len()) } } }; r.consume(used); if done || used == 0 { return Ok(()); } } } /// A Buffer is a type of reader which has some form of internal buffering to /// allow certain kinds of reading operations to be more optimized than others. /// /// This type extends the `Read` trait with a few methods that are not /// possible to reasonably implement with purely a read interface. pub trait BufRead: Read { /// Fills the internal buffer of this object, returning the buffer contents. /// /// None of the contents will be "read" in the sense that later calling /// `read` may return the same contents. /// /// The `consume` function must be called with the number of bytes that are /// consumed from this buffer returned to ensure that the bytes are never /// returned twice. /// /// 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`. fn consume(&mut self, amt: usize); /// Read all bytes until the delimiter `byte` is reached. /// /// This function will continue to read (and buffer) 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 this buffered reader is currently at EOF, then this function will not /// place any more bytes into `buf` and will return `Ok(())`. /// /// # 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. fn read_until(&mut self, byte: u8, buf: &mut Vec<u8>) -> Result<()> { read_until(self, byte, buf) } /// Read all bytes until a newline byte (the 0xA byte) is reached. /// /// This function will continue to read (and buffer) 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 this reader is currently at EOF then this function will not modify /// `buf` and will return `Ok(())`. /// /// # 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. fn read_line(&mut self, buf: &mut String) -> Result<()> { // 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)) } } /// Extension methods for all instances of `BufRead`, typically imported through /// `std::io::prelude::*`. pub trait BufReadExt: BufRead + Sized { /// 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. fn split(self, byte: u8) -> Split<Self> { 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) at the end. /// /// This function will yield errors whenever `read_string` would have also /// yielded an error. fn lines(self) -> Lines<Self> { Lines { buf: self } } } impl<T: BufRead> BufReadExt for T {} /// A `Write` adaptor which will write data to multiple locations. /// /// For more information, see `WriteExt::broadcast`. pub struct Broadcast<T, U> { first: T, second: U, } impl<T: Write, U: Write> Write for Broadcast<T, U> { fn write(&mut self, data: &[u8]) -> Result<usize> { let n = try!(self.first.write(data)); // FIXME: what if the write fails? (we wrote something) try!(self.second.write_all(&data[..n])); Ok(n) } fn flush(&mut self) -> Result<()> { self.first.flush().and(self.second.flush()) } } /// Adaptor to chain together two instances of `Read`. /// /// For more information, see `ReadExt::chain`. pub struct Chain<T, U> { first: T, second: U, done_first: bool, } impl<T: Read, U: Read> Read for Chain<T, U> { fn read(&mut self, buf: &mut [u8]) -> Result<usize> { if !self.done_first { match try!(self.first.read(buf)) { 0 => { self.done_first = true; } n => return Ok(n), } } self.second.read(buf) } } /// Reader adaptor which limits the bytes read from an underlying reader. /// /// For more information, see `ReadExt::take`. 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. pub fn limit(&self) -> u64 { self.limit } } impl<T: Read> Read for Take<T> { fn read(&mut self, buf: &mut [u8]) -> Result<usize> { let max = cmp::min(buf.len() as u64, self.limit) as usize; let n = try!(self.inner.read(&mut buf[..max])); self.limit -= n as u64; Ok(n) } } /// An adaptor which will emit all read data to a specified writer as well. /// /// For more information see `ReadExt::tee` pub struct Tee<R, W> { reader: R, writer: W, } impl<R: Read, W: Write> Read for Tee<R, W> { fn read(&mut self, buf: &mut [u8]) -> Result<usize> { let n = try!(self.reader.read(buf)); // FIXME: what if the write fails? (we read something) try!(self.writer.write_all(&buf[..n])); Ok(n) } } /// A bridge from implementations of `Read` to an `Iterator` of `u8`. /// /// See `ReadExt::bytes` for more information. 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 buf = [0]; match self.inner.read(&mut buf) { Ok(0) => None, Ok(..) => Some(Ok(buf[0])), Err(e) => Some(Err(e)), } } } /// A bridge from implementations of `Read` to an `Iterator` of `char`. /// /// See `ReadExt::chars` for more information. pub struct Chars<R> { inner: R, } /// An enumeration of possible errors that can be generated from the `Chars` /// adapter. #[derive(PartialEq, Clone, Debug)] pub enum CharsError { /// Variant representing that the underlying stream was read successfully /// but it did not contain valid utf8 data. NotUtf8, /// Variant representing that an I/O error occurred. Other(Error), } impl<R: Read> Iterator for Chars<R> { type Item = result::Result<char, CharsError>; fn next(&mut self) -> Option<result::Result<char, CharsError>> { let mut buf = [0]; let first_byte = match self.inner.read(&mut buf) { Ok(0) => return None, Ok(..) => buf[0], Err(e) => return Some(Err(CharsError::Other(e))), }; let width = core_str::utf8_char_width(first_byte); if width == 1 { return Some(Ok(first_byte as char)) } if width == 0 { return Some(Err(CharsError::NotUtf8)) } let mut buf = [first_byte, 0, 0, 0]; { let mut start = 1; while start < width { match self.inner.read(&mut buf[start..width]) { Ok(0) => return Some(Err(CharsError::NotUtf8)), Ok(n) => start += n, Err(e) => return Some(Err(CharsError::Other(e))), } } } Some(match str::from_utf8(&buf[..width]).ok() { Some(s) => Ok(s.char_at(0)), None => Err(CharsError::NotUtf8), }) } } impl StdError for CharsError { fn description(&self) -> &str { match *self { CharsError::NotUtf8 => "invalid utf8 encoding", CharsError::Other(ref e) => e.description(), } } fn cause(&self) -> Option<&StdError> { match *self { CharsError::NotUtf8 => None, CharsError::Other(ref e) => e.cause(), } } } impl fmt::Display for CharsError { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { match *self { CharsError::NotUtf8 => { "byte stream did not contain valid utf8".fmt(f) } CharsError::Other(ref e) => e.fmt(f), } } } /// An iterator over the contents of an instance of `BufRead` split on a /// particular byte. /// /// See `BufReadExt::split` for more information. pub struct Split<B> { buf: B, delim: u8, } 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(()) if buf.len() == 0 => None, Ok(()) => { 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` split on a newline /// byte. /// /// See `BufReadExt::lines` for more information. pub struct Lines<B> { buf: B, } 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(()) if buf.len() == 0 => None, Ok(()) => { if buf.ends_with("\n") { buf.pop(); } Some(Ok(buf)) } Err(e) => Some(Err(e)) } } } #[cfg(test)] mod tests { use prelude::v1::*; use io::prelude::*; use super::Cursor; #[test] fn read_until() { let mut buf = Cursor::new(b"12"); let mut v = Vec::new(); assert_eq!(buf.read_until(b'3', &mut v), Ok(())); 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), Ok(())); assert_eq!(v, b"123"); v.truncate(0); assert_eq!(buf.read_until(b'3', &mut v), Ok(())); assert_eq!(v, b"3"); v.truncate(0); assert_eq!(buf.read_until(b'3', &mut v), Ok(())); assert_eq!(v, []); } #[test] fn split() { let mut buf = Cursor::new(b"12"); let mut s = buf.split(b'3'); assert_eq!(s.next(), Some(Ok(vec![b'1', b'2']))); assert_eq!(s.next(), None); let mut buf = Cursor::new(b"1233"); let mut s = buf.split(b'3'); assert_eq!(s.next(), Some(Ok(vec![b'1', b'2']))); assert_eq!(s.next(), Some(Ok(vec![]))); assert_eq!(s.next(), None); } #[test] fn read_line() { let mut buf = Cursor::new(b"12"); let mut v = String::new(); assert_eq!(buf.read_line(&mut v), Ok(())); 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), Ok(())); assert_eq!(v, "12\n"); v.truncate(0); assert_eq!(buf.read_line(&mut v), Ok(())); assert_eq!(v, "\n"); v.truncate(0); assert_eq!(buf.read_line(&mut v), Ok(())); assert_eq!(v, ""); } #[test] fn lines() { let mut buf = Cursor::new(b"12"); let mut s = buf.lines(); assert_eq!(s.next(), Some(Ok("12".to_string()))); assert_eq!(s.next(), None); let mut buf = Cursor::new(b"12\n\n"); let mut s = buf.lines(); assert_eq!(s.next(), Some(Ok("12".to_string()))); assert_eq!(s.next(), Some(Ok(String::new()))); assert_eq!(s.next(), 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), Ok(())); assert_eq!(v, []); let mut c = Cursor::new(b"1"); let mut v = Vec::new(); assert_eq!(c.read_to_end(&mut v), Ok(())); assert_eq!(v, b"1"); } #[test] fn read_to_string() { let mut c = Cursor::new(b""); let mut v = String::new(); assert_eq!(c.read_to_string(&mut v), Ok(())); assert_eq!(v, ""); let mut c = Cursor::new(b"1"); let mut v = String::new(); assert_eq!(c.read_to_string(&mut v), Ok(())); 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()); } }