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
//! Frame a stream of bytes based on a length prefix
//!
//! Many protocols delimit their frames by prefacing frame data with a
//! frame head that specifies the length of the frame. The
//! `length_delimited` module provides utilities for handling the length
//! based framing. This allows the consumer to work with entire frames
//! without having to worry about buffering or other framing logic.
//!
//! # Getting started
//!
//! If implementing a protocol from scratch, using length delimited framing
//! is an easy way to get started. [`LengthDelimitedCodec::new()`] will
//! return a length delimited codec using default configuration values.
//! This can then be used to construct a framer to adapt a full-duplex
//! byte stream into a stream of frames.
//!
//! ```
//! use tokio::io::{AsyncRead, AsyncWrite};
//! use tokio_util::codec::{Framed, LengthDelimitedCodec};
//!
//! fn bind_transport<T: AsyncRead + AsyncWrite>(io: T)
//! -> Framed<T, LengthDelimitedCodec>
//! {
//! Framed::new(io, LengthDelimitedCodec::new())
//! }
//! # pub fn main() {}
//! ```
//!
//! The returned transport implements `Sink + Stream` for `BytesMut`. It
//! encodes the frame with a big-endian `u32` header denoting the frame
//! payload length:
//!
//! ```text
//! +----------+--------------------------------+
//! | len: u32 | frame payload |
//! +----------+--------------------------------+
//! ```
//!
//! Specifically, given the following:
//!
//! ```
//! use tokio::io::{AsyncRead, AsyncWrite};
//! use tokio_util::codec::{Framed, LengthDelimitedCodec};
//!
//! use futures::SinkExt;
//! use bytes::Bytes;
//!
//! async fn write_frame<T>(io: T) -> Result<(), Box<dyn std::error::Error>>
//! where
//! T: AsyncRead + AsyncWrite + Unpin,
//! {
//! let mut transport = Framed::new(io, LengthDelimitedCodec::new());
//! let frame = Bytes::from("hello world");
//!
//! transport.send(frame).await?;
//! Ok(())
//! }
//! ```
//!
//! The encoded frame will look like this:
//!
//! ```text
//! +---- len: u32 ----+---- data ----+
//! | \x00\x00\x00\x0b | hello world |
//! +------------------+--------------+
//! ```
//!
//! # Decoding
//!
//! [`FramedRead`] adapts an [`AsyncRead`] into a `Stream` of [`BytesMut`],
//! such that each yielded [`BytesMut`] value contains the contents of an
//! entire frame. There are many configuration parameters enabling
//! [`FramedRead`] to handle a wide range of protocols. Here are some
//! examples that will cover the various options at a high level.
//!
//! ## Example 1
//!
//! The following will parse a `u16` length field at offset 0, omitting the
//! frame head in the yielded `BytesMut`.
//!
//! ```
//! # use tokio_stream::StreamExt;
//! # use tokio_util::codec::LengthDelimitedCodec;
//! # #[tokio::main]
//! # async fn main() {
//! # let io: &[u8] = b"\x00\x0BHello world";
//! let mut reader = LengthDelimitedCodec::builder()
//! .length_field_offset(0) // default value
//! .length_field_type::<u16>()
//! .length_adjustment(0) // default value
//! .new_read(io);
//! # let res = reader.next().await.unwrap().unwrap().to_vec();
//! # assert_eq!(res, b"Hello world");
//! # }
//! ```
//!
//! The following frame will be decoded as such:
//!
//! ```text
//! INPUT DECODED
//! +-- len ---+--- Payload ---+ +--- Payload ---+
//! | \x00\x0B | Hello world | --> | Hello world |
//! +----------+---------------+ +---------------+
//! ```
//!
//! The value of the length field is 11 (`\x0B`) which represents the length
//! of the payload, `hello world`. By default, [`FramedRead`] assumes that
//! the length field represents the number of bytes that **follows** the
//! length field. Thus, the entire frame has a length of 13: 2 bytes for the
//! frame head + 11 bytes for the payload.
//!
//! ## Example 2
//!
//! The following will parse a `u16` length field at offset 0, including the
//! frame head in the yielded `BytesMut`.
//!
//! ```
//! # use tokio_stream::StreamExt;
//! # use tokio_util::codec::LengthDelimitedCodec;
//! # #[tokio::main]
//! # async fn main() {
//! # let io: &[u8] = b"\x00\x0BHello world";
//! let mut reader = LengthDelimitedCodec::builder()
//! .length_field_offset(0) // default value
//! .length_field_type::<u16>()
//! .length_adjustment(2) // Add head size to length
//! .num_skip(0) // Do NOT skip the head
//! .new_read(io);
//! # let res = reader.next().await.unwrap().unwrap().to_vec();
//! # assert_eq!(res, b"\x00\x0BHello world");
//! # }
//! ```
//!
//! The following frame will be decoded as such:
//!
//! ```text
//! INPUT DECODED
//! +-- len ---+--- Payload ---+ +-- len ---+--- Payload ---+
//! | \x00\x0B | Hello world | --> | \x00\x0B | Hello world |
//! +----------+---------------+ +----------+---------------+
//! ```
//!
//! This is similar to the first example, the only difference is that the
//! frame head is **included** in the yielded `BytesMut` value. To achieve
//! this, we need to add the header size to the length with `length_adjustment`,
//! and set `num_skip` to `0` to prevent skipping the head.
//!
//! ## Example 3
//!
//! The following will parse a `u16` length field at offset 0, omitting the
//! frame head in the yielded `BytesMut`. In this case, the length field
//! **includes** the frame head length.
//!
//! ```
//! # use tokio_stream::StreamExt;
//! # use tokio_util::codec::LengthDelimitedCodec;
//! # #[tokio::main]
//! # async fn main() {
//! # let io: &[u8] = b"\x00\x0DHello world";
//! let mut reader = LengthDelimitedCodec::builder()
//! .length_field_offset(0) // default value
//! .length_field_type::<u16>()
//! .length_adjustment(-2) // size of head
//! .new_read(io);
//! # let res = reader.next().await.unwrap().unwrap().to_vec();
//! # assert_eq!(res, b"Hello world");
//! # }
//! ```
//!
//! The following frame will be decoded as such:
//!
//! ```text
//! INPUT DECODED
//! +-- len ---+--- Payload ---+ +--- Payload ---+
//! | \x00\x0D | Hello world | --> | Hello world |
//! +----------+---------------+ +---------------+
//! ```
//!
//! In most cases, the length field represents the length of the payload
//! only, as shown in the previous examples. However, in some protocols the
//! length field represents the length of the whole frame, including the
//! head. In such cases, we specify a negative `length_adjustment` to adjust
//! the value provided in the frame head to represent the payload length.
//!
//! ## Example 4
//!
//! The following will parse a 3 byte length field at offset 0 in a 5 byte
//! frame head, including the frame head in the yielded `BytesMut`.
//!
//! ```
//! # use tokio_stream::StreamExt;
//! # use tokio_util::codec::LengthDelimitedCodec;
//! # #[tokio::main]
//! # async fn main() {
//! # let io: &[u8] = b"\x00\x00\x0B\xCA\xFEHello world";
//! let mut reader = LengthDelimitedCodec::builder()
//! .length_field_offset(0) // default value
//! .length_field_length(3)
//! .length_adjustment(3 + 2) // len field and remaining head
//! .num_skip(0)
//! .new_read(io);
//! # let res = reader.next().await.unwrap().unwrap().to_vec();
//! # assert_eq!(res, b"\x00\x00\x0B\xCA\xFEHello world");
//! # }
//! ```
//!
//! The following frame will be decoded as such:
//!
//! ```text
//! INPUT
//! +---- len -----+- head -+--- Payload ---+
//! | \x00\x00\x0B | \xCAFE | Hello world |
//! +--------------+--------+---------------+
//!
//! DECODED
//! +---- len -----+- head -+--- Payload ---+
//! | \x00\x00\x0B | \xCAFE | Hello world |
//! +--------------+--------+---------------+
//! ```
//!
//! A more advanced example that shows a case where there is extra frame
//! head data between the length field and the payload. In such cases, it is
//! usually desirable to include the frame head as part of the yielded
//! `BytesMut`. This lets consumers of the length delimited framer to
//! process the frame head as needed.
//!
//! The positive `length_adjustment` value lets `FramedRead` factor in the
//! additional head into the frame length calculation.
//!
//! ## Example 5
//!
//! The following will parse a `u16` length field at offset 1 of a 4 byte
//! frame head. The first byte and the length field will be omitted from the
//! yielded `BytesMut`, but the trailing 2 bytes of the frame head will be
//! included.
//!
//! ```
//! # use tokio_stream::StreamExt;
//! # use tokio_util::codec::LengthDelimitedCodec;
//! # #[tokio::main]
//! # async fn main() {
//! # let io: &[u8] = b"\xCA\x00\x0B\xFEHello world";
//! let mut reader = LengthDelimitedCodec::builder()
//! .length_field_offset(1) // length of hdr1
//! .length_field_type::<u16>()
//! .length_adjustment(1) // length of hdr2
//! .num_skip(3) // length of hdr1 + LEN
//! .new_read(io);
//! # let res = reader.next().await.unwrap().unwrap().to_vec();
//! # assert_eq!(res, b"\xFEHello world");
//! # }
//! ```
//!
//! The following frame will be decoded as such:
//!
//! ```text
//! INPUT
//! +- hdr1 -+-- len ---+- hdr2 -+--- Payload ---+
//! | \xCA | \x00\x0B | \xFE | Hello world |
//! +--------+----------+--------+---------------+
//!
//! DECODED
//! +- hdr2 -+--- Payload ---+
//! | \xFE | Hello world |
//! +--------+---------------+
//! ```
//!
//! The length field is situated in the middle of the frame head. In this
//! case, the first byte in the frame head could be a version or some other
//! identifier that is not needed for processing. On the other hand, the
//! second half of the head is needed.
//!
//! `length_field_offset` indicates how many bytes to skip before starting
//! to read the length field. `length_adjustment` is the number of bytes to
//! skip starting at the end of the length field. In this case, it is the
//! second half of the head.
//!
//! ## Example 6
//!
//! The following will parse a `u16` length field at offset 1 of a 4 byte
//! frame head. The first byte and the length field will be omitted from the
//! yielded `BytesMut`, but the trailing 2 bytes of the frame head will be
//! included. In this case, the length field **includes** the frame head
//! length.
//!
//! ```
//! # use tokio_stream::StreamExt;
//! # use tokio_util::codec::LengthDelimitedCodec;
//! # #[tokio::main]
//! # async fn main() {
//! # let io: &[u8] = b"\xCA\x00\x0F\xFEHello world";
//! let mut reader = LengthDelimitedCodec::builder()
//! .length_field_offset(1) // length of hdr1
//! .length_field_type::<u16>()
//! .length_adjustment(-3) // length of hdr1 + LEN, negative
//! .num_skip(3)
//! .new_read(io);
//! # let res = reader.next().await.unwrap().unwrap().to_vec();
//! # assert_eq!(res, b"\xFEHello world");
//! # }
//! ```
//!
//! The following frame will be decoded as such:
//!
//! ```text
//! INPUT
//! +- hdr1 -+-- len ---+- hdr2 -+--- Payload ---+
//! | \xCA | \x00\x0F | \xFE | Hello world |
//! +--------+----------+--------+---------------+
//!
//! DECODED
//! +- hdr2 -+--- Payload ---+
//! | \xFE | Hello world |
//! +--------+---------------+
//! ```
//!
//! Similar to the example above, the difference is that the length field
//! represents the length of the entire frame instead of just the payload.
//! The length of `hdr1` and `len` must be counted in `length_adjustment`.
//! Note that the length of `hdr2` does **not** need to be explicitly set
//! anywhere because it already is factored into the total frame length that
//! is read from the byte stream.
//!
//! ## Example 7
//!
//! The following will parse a 3 byte length field at offset 0 in a 4 byte
//! frame head, excluding the 4th byte from the yielded `BytesMut`.
//!
//! ```
//! # use tokio_stream::StreamExt;
//! # use tokio_util::codec::LengthDelimitedCodec;
//! # #[tokio::main]
//! # async fn main() {
//! # let io: &[u8] = b"\x00\x00\x0B\xFFHello world";
//! let mut reader = LengthDelimitedCodec::builder()
//! .length_field_offset(0) // default value
//! .length_field_length(3)
//! .length_adjustment(0) // default value
//! .num_skip(4) // skip the first 4 bytes
//! .new_read(io);
//! # let res = reader.next().await.unwrap().unwrap().to_vec();
//! # assert_eq!(res, b"Hello world");
//! # }
//! ```
//!
//! The following frame will be decoded as such:
//!
//! ```text
//! INPUT DECODED
//! +------- len ------+--- Payload ---+ +--- Payload ---+
//! | \x00\x00\x0B\xFF | Hello world | => | Hello world |
//! +------------------+---------------+ +---------------+
//! ```
//!
//! A simple example where there are unused bytes between the length field
//! and the payload.
//!
//! # Encoding
//!
//! [`FramedWrite`] adapts an [`AsyncWrite`] into a `Sink` of [`BytesMut`],
//! such that each submitted [`BytesMut`] is prefaced by a length field.
//! There are fewer configuration options than [`FramedRead`]. Given
//! protocols that have more complex frame heads, an encoder should probably
//! be written by hand using [`Encoder`].
//!
//! Here is a simple example, given a `FramedWrite` with the following
//! configuration:
//!
//! ```
//! # use tokio::io::AsyncWrite;
//! # use tokio_util::codec::LengthDelimitedCodec;
//! # fn write_frame<T: AsyncWrite>(io: T) {
//! # let _ =
//! LengthDelimitedCodec::builder()
//! .length_field_type::<u16>()
//! .new_write(io);
//! # }
//! # pub fn main() {}
//! ```
//!
//! A payload of `hello world` will be encoded as:
//!
//! ```text
//! +- len: u16 -+---- data ----+
//! | \x00\x0b | hello world |
//! +------------+--------------+
//! ```
//!
//! [`LengthDelimitedCodec::new()`]: method@LengthDelimitedCodec::new
//! [`FramedRead`]: struct@FramedRead
//! [`FramedWrite`]: struct@FramedWrite
//! [`AsyncRead`]: trait@tokio::io::AsyncRead
//! [`AsyncWrite`]: trait@tokio::io::AsyncWrite
//! [`Encoder`]: trait@Encoder
//! [`BytesMut`]: bytes::BytesMut
use crate::codec::{Decoder, Encoder, Framed, FramedRead, FramedWrite};
use tokio::io::{AsyncRead, AsyncWrite};
use bytes::{Buf, BufMut, Bytes, BytesMut};
use std::error::Error as StdError;
use std::io::{self, Cursor};
use std::{cmp, fmt, mem};
/// Configure length delimited `LengthDelimitedCodec`s.
///
/// `Builder` enables constructing configured length delimited codecs. Note
/// that not all configuration settings apply to both encoding and decoding. See
/// the documentation for specific methods for more detail.
///
/// Note that the if the value of [`Builder::max_frame_length`] becomes larger than
/// what can actually fit in [`Builder::length_field_length`], it will be clipped to
/// the maximum value that can fit.
#[derive(Debug, Clone, Copy)]
pub struct Builder {
// Maximum frame length
max_frame_len: usize,
// Number of bytes representing the field length
length_field_len: usize,
// Number of bytes in the header before the length field
length_field_offset: usize,
// Adjust the length specified in the header field by this amount
length_adjustment: isize,
// Total number of bytes to skip before reading the payload, if not set,
// `length_field_len + length_field_offset`
num_skip: Option<usize>,
// Length field byte order (little or big endian)
length_field_is_big_endian: bool,
}
/// An error when the number of bytes read is more than max frame length.
pub struct LengthDelimitedCodecError {
_priv: (),
}
/// A codec for frames delimited by a frame head specifying their lengths.
///
/// This allows the consumer to work with entire frames without having to worry
/// about buffering or other framing logic.
///
/// See [module level] documentation for more detail.
///
/// [module level]: index.html
#[derive(Debug, Clone)]
pub struct LengthDelimitedCodec {
// Configuration values
builder: Builder,
// Read state
state: DecodeState,
}
#[derive(Debug, Clone, Copy)]
enum DecodeState {
Head,
Data(usize),
}
// ===== impl LengthDelimitedCodec ======
impl LengthDelimitedCodec {
/// Creates a new `LengthDelimitedCodec` with the default configuration values.
pub fn new() -> Self {
Self {
builder: Builder::new(),
state: DecodeState::Head,
}
}
/// Creates a new length delimited codec builder with default configuration
/// values.
pub fn builder() -> Builder {
Builder::new()
}
/// Returns the current max frame setting
///
/// This is the largest size this codec will accept from the wire. Larger
/// frames will be rejected.
pub fn max_frame_length(&self) -> usize {
self.builder.max_frame_len
}
/// Updates the max frame setting.
///
/// The change takes effect the next time a frame is decoded. In other
/// words, if a frame is currently in process of being decoded with a frame
/// size greater than `val` but less than the max frame length in effect
/// before calling this function, then the frame will be allowed.
pub fn set_max_frame_length(&mut self, val: usize) {
self.builder.max_frame_length(val);
}
fn decode_head(&mut self, src: &mut BytesMut) -> io::Result<Option<usize>> {
let head_len = self.builder.num_head_bytes();
let field_len = self.builder.length_field_len;
if src.len() < head_len {
// Not enough data
return Ok(None);
}
let n = {
let mut src = Cursor::new(&mut *src);
// Skip the required bytes
src.advance(self.builder.length_field_offset);
// match endianness
let n = if self.builder.length_field_is_big_endian {
src.get_uint(field_len)
} else {
src.get_uint_le(field_len)
};
if n > self.builder.max_frame_len as u64 {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
LengthDelimitedCodecError { _priv: () },
));
}
// The check above ensures there is no overflow
let n = n as usize;
// Adjust `n` with bounds checking
let n = if self.builder.length_adjustment < 0 {
n.checked_sub(-self.builder.length_adjustment as usize)
} else {
n.checked_add(self.builder.length_adjustment as usize)
};
// Error handling
match n {
Some(n) => n,
None => {
return Err(io::Error::new(
io::ErrorKind::InvalidInput,
"provided length would overflow after adjustment",
));
}
}
};
src.advance(self.builder.get_num_skip());
// Ensure that the buffer has enough space to read the incoming
// payload
src.reserve(n.saturating_sub(src.len()));
Ok(Some(n))
}
fn decode_data(&self, n: usize, src: &mut BytesMut) -> Option<BytesMut> {
// At this point, the buffer has already had the required capacity
// reserved. All there is to do is read.
if src.len() < n {
return None;
}
Some(src.split_to(n))
}
}
impl Decoder for LengthDelimitedCodec {
type Item = BytesMut;
type Error = io::Error;
fn decode(&mut self, src: &mut BytesMut) -> io::Result<Option<BytesMut>> {
let n = match self.state {
DecodeState::Head => match self.decode_head(src)? {
Some(n) => {
self.state = DecodeState::Data(n);
n
}
None => return Ok(None),
},
DecodeState::Data(n) => n,
};
match self.decode_data(n, src) {
Some(data) => {
// Update the decode state
self.state = DecodeState::Head;
// Make sure the buffer has enough space to read the next head
src.reserve(self.builder.num_head_bytes().saturating_sub(src.len()));
Ok(Some(data))
}
None => Ok(None),
}
}
}
impl Encoder<Bytes> for LengthDelimitedCodec {
type Error = io::Error;
fn encode(&mut self, data: Bytes, dst: &mut BytesMut) -> Result<(), io::Error> {
let n = data.len();
if n > self.builder.max_frame_len {
return Err(io::Error::new(
io::ErrorKind::InvalidInput,
LengthDelimitedCodecError { _priv: () },
));
}
// Adjust `n` with bounds checking
let n = if self.builder.length_adjustment < 0 {
n.checked_add(-self.builder.length_adjustment as usize)
} else {
n.checked_sub(self.builder.length_adjustment as usize)
};
let n = n.ok_or_else(|| {
io::Error::new(
io::ErrorKind::InvalidInput,
"provided length would overflow after adjustment",
)
})?;
// Reserve capacity in the destination buffer to fit the frame and
// length field (plus adjustment).
dst.reserve(self.builder.length_field_len + n);
if self.builder.length_field_is_big_endian {
dst.put_uint(n as u64, self.builder.length_field_len);
} else {
dst.put_uint_le(n as u64, self.builder.length_field_len);
}
// Write the frame to the buffer
dst.extend_from_slice(&data[..]);
Ok(())
}
}
impl Default for LengthDelimitedCodec {
fn default() -> Self {
Self::new()
}
}
// ===== impl Builder =====
mod builder {
/// Types that can be used with `Builder::length_field_type`.
pub trait LengthFieldType {}
impl LengthFieldType for u8 {}
impl LengthFieldType for u16 {}
impl LengthFieldType for u32 {}
impl LengthFieldType for u64 {}
#[cfg(any(
target_pointer_width = "16",
target_pointer_width = "32",
target_pointer_width = "64",
))]
impl LengthFieldType for usize {}
}
impl Builder {
/// Creates a new length delimited codec builder with default configuration
/// values.
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .length_field_offset(0)
/// .length_field_type::<u16>()
/// .length_adjustment(0)
/// .num_skip(0)
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn new() -> Builder {
Builder {
// Default max frame length of 8MB
max_frame_len: 8 * 1_024 * 1_024,
// Default byte length of 4
length_field_len: 4,
// Default to the header field being at the start of the header.
length_field_offset: 0,
length_adjustment: 0,
// Total number of bytes to skip before reading the payload, if not set,
// `length_field_len + length_field_offset`
num_skip: None,
// Default to reading the length field in network (big) endian.
length_field_is_big_endian: true,
}
}
/// Read the length field as a big endian integer
///
/// This is the default setting.
///
/// This configuration option applies to both encoding and decoding.
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .big_endian()
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn big_endian(&mut self) -> &mut Self {
self.length_field_is_big_endian = true;
self
}
/// Read the length field as a little endian integer
///
/// The default setting is big endian.
///
/// This configuration option applies to both encoding and decoding.
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .little_endian()
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn little_endian(&mut self) -> &mut Self {
self.length_field_is_big_endian = false;
self
}
/// Read the length field as a native endian integer
///
/// The default setting is big endian.
///
/// This configuration option applies to both encoding and decoding.
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .native_endian()
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn native_endian(&mut self) -> &mut Self {
if cfg!(target_endian = "big") {
self.big_endian()
} else {
self.little_endian()
}
}
/// Sets the max frame length in bytes
///
/// This configuration option applies to both encoding and decoding. The
/// default value is 8MB.
///
/// When decoding, the length field read from the byte stream is checked
/// against this setting **before** any adjustments are applied. When
/// encoding, the length of the submitted payload is checked against this
/// setting.
///
/// When frames exceed the max length, an `io::Error` with the custom value
/// of the `LengthDelimitedCodecError` type will be returned.
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .max_frame_length(8 * 1024 * 1024)
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn max_frame_length(&mut self, val: usize) -> &mut Self {
self.max_frame_len = val;
self
}
/// Sets the unsigned integer type used to represent the length field.
///
/// The default type is [`u32`]. The max type is [`u64`] (or [`usize`] on
/// 64-bit targets).
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .length_field_type::<u32>()
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
///
/// Unlike [`Builder::length_field_length`], this does not fail at runtime
/// and instead produces a compile error:
///
/// ```compile_fail
/// # use tokio::io::AsyncRead;
/// # use tokio_util::codec::LengthDelimitedCodec;
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .length_field_type::<u128>()
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn length_field_type<T: builder::LengthFieldType>(&mut self) -> &mut Self {
self.length_field_length(mem::size_of::<T>())
}
/// Sets the number of bytes used to represent the length field
///
/// The default value is `4`. The max value is `8`.
///
/// This configuration option applies to both encoding and decoding.
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .length_field_length(4)
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn length_field_length(&mut self, val: usize) -> &mut Self {
assert!(val > 0 && val <= 8, "invalid length field length");
self.length_field_len = val;
self
}
/// Sets the number of bytes in the header before the length field
///
/// This configuration option only applies to decoding.
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .length_field_offset(1)
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn length_field_offset(&mut self, val: usize) -> &mut Self {
self.length_field_offset = val;
self
}
/// Delta between the payload length specified in the header and the real
/// payload length
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .length_adjustment(-2)
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn length_adjustment(&mut self, val: isize) -> &mut Self {
self.length_adjustment = val;
self
}
/// Sets the number of bytes to skip before reading the payload
///
/// Default value is `length_field_len + length_field_offset`
///
/// This configuration option only applies to decoding
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .num_skip(4)
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn num_skip(&mut self, val: usize) -> &mut Self {
self.num_skip = Some(val);
self
}
/// Create a configured length delimited `LengthDelimitedCodec`
///
/// # Examples
///
/// ```
/// use tokio_util::codec::LengthDelimitedCodec;
/// # pub fn main() {
/// LengthDelimitedCodec::builder()
/// .length_field_offset(0)
/// .length_field_type::<u16>()
/// .length_adjustment(0)
/// .num_skip(0)
/// .new_codec();
/// # }
/// ```
pub fn new_codec(&self) -> LengthDelimitedCodec {
let mut builder = *self;
builder.adjust_max_frame_len();
LengthDelimitedCodec {
builder,
state: DecodeState::Head,
}
}
/// Create a configured length delimited `FramedRead`
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncRead;
/// use tokio_util::codec::LengthDelimitedCodec;
///
/// # fn bind_read<T: AsyncRead>(io: T) {
/// LengthDelimitedCodec::builder()
/// .length_field_offset(0)
/// .length_field_type::<u16>()
/// .length_adjustment(0)
/// .num_skip(0)
/// .new_read(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn new_read<T>(&self, upstream: T) -> FramedRead<T, LengthDelimitedCodec>
where
T: AsyncRead,
{
FramedRead::new(upstream, self.new_codec())
}
/// Create a configured length delimited `FramedWrite`
///
/// # Examples
///
/// ```
/// # use tokio::io::AsyncWrite;
/// # use tokio_util::codec::LengthDelimitedCodec;
/// # fn write_frame<T: AsyncWrite>(io: T) {
/// LengthDelimitedCodec::builder()
/// .length_field_type::<u16>()
/// .new_write(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn new_write<T>(&self, inner: T) -> FramedWrite<T, LengthDelimitedCodec>
where
T: AsyncWrite,
{
FramedWrite::new(inner, self.new_codec())
}
/// Create a configured length delimited `Framed`
///
/// # Examples
///
/// ```
/// # use tokio::io::{AsyncRead, AsyncWrite};
/// # use tokio_util::codec::LengthDelimitedCodec;
/// # fn write_frame<T: AsyncRead + AsyncWrite>(io: T) {
/// # let _ =
/// LengthDelimitedCodec::builder()
/// .length_field_type::<u16>()
/// .new_framed(io);
/// # }
/// # pub fn main() {}
/// ```
pub fn new_framed<T>(&self, inner: T) -> Framed<T, LengthDelimitedCodec>
where
T: AsyncRead + AsyncWrite,
{
Framed::new(inner, self.new_codec())
}
fn num_head_bytes(&self) -> usize {
let num = self.length_field_offset + self.length_field_len;
cmp::max(num, self.num_skip.unwrap_or(0))
}
fn get_num_skip(&self) -> usize {
self.num_skip
.unwrap_or(self.length_field_offset + self.length_field_len)
}
fn adjust_max_frame_len(&mut self) {
// Calculate the maximum number that can be represented using `length_field_len` bytes.
let max_number = match 1u64.checked_shl((8 * self.length_field_len) as u32) {
Some(shl) => shl - 1,
None => u64::MAX,
};
let max_allowed_len = max_number.saturating_add_signed(self.length_adjustment as i64);
if self.max_frame_len as u64 > max_allowed_len {
self.max_frame_len = usize::try_from(max_allowed_len).unwrap_or(usize::MAX);
}
}
}
impl Default for Builder {
fn default() -> Self {
Self::new()
}
}
// ===== impl LengthDelimitedCodecError =====
impl fmt::Debug for LengthDelimitedCodecError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.debug_struct("LengthDelimitedCodecError").finish()
}
}
impl fmt::Display for LengthDelimitedCodecError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.write_str("frame size too big")
}
}
impl StdError for LengthDelimitedCodecError {}