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
//! Streaming parser extensions for `BufRead`. //! //! This is a one-off experiment to see if we can extend the `std::io::BufRead` //! traits with better parsing capabilities. The name is a riff on the //! [`nom`](https://docs.rs/nom) parser, which you should probably check out. //! //! # Why? //! //! The purpose of this crate is to make authoring streaming parsers easier. And //! the way we do this is by providing more operations that decouple //! "looking at bytes" from "consuming bytes". So hence we introduce `fill_` //! counterparts for `read_until` and `read_exact`. And two new methods: //! `read_while` and `fill_while` that read bytes into a buffer based on a //! predicate. //! //! Together this should make it easier to parse bytes from streams. //! //! # Methods //! //! Methods prefixed with `fill_` don't [`consume`] bytes. This means that in order to move the //! `BufRead` cursor forward, the `consume` method needs to be called. This means the same bytes //! can be read multiple times. //! //! Methods prefixed with `read_` *do* `consume` bytes. This means when this method is called, the //! cursor moves forward, which means the same bytes *cannot* be read multiple times. //! //! - [`BufReadExt::fill_exact`] reads bytes until a buffer has been filled, doesn't consume bytes. //! - [`BufReadExt::fill_until`] reads bytes until a byte has been encountered, doesn't consume bytes. //! - [`BufReadExt::fill_while`] reads bytes based on a predicate, doesn't consume bytes. //! - [`BufReadExt::read_while`] reads bytes based on a predicate, consumes bytes. //! //! [`consume`]: https://doc.rust-lang.org/std/io/trait.BufRead.html#tymethod.consume //! [`BufReadExt::fill_exact`]: trait.BufReadExt.html#method.fill_exact //! [`BufReadExt::fill_until`]: trait.BufReadExt.html#method.fill_until //! [`BufReadExt::fill_while`]: trait.BufReadExt.html#method.fill_while //! [`BufReadExt::read_while`]: trait.BufReadExt.html#method.read_while //! //! # Todos //! //! - `AsyncRead` support //! - [byte-ordered reads/writes](https://github.com/async-rs/async-std/issues/578) //! //! # Examples //! //! ``` //! use std::io::{self, BufRead}; //! use omnom::prelude::*; //! //! let mut cursor = io::Cursor::new(b"lorem-ipsum"); //! let mut buf = vec![]; //! //! // cursor is at 'l' //! let num_bytes = cursor.fill_until(b'-', &mut buf) //! .expect("reading from cursor won't fail"); //! assert_eq!(buf, b"lorem-"); //! assert_eq!(num_bytes, 6); //! cursor.consume(num_bytes); //! buf.clear(); //! //! // cursor is at 'i' //! let num_bytes = cursor.fill_until(b'-', &mut buf) //! .expect("reading from cursor won't fail"); //! assert_eq!(buf, b"ipsum"); //! assert_eq!(num_bytes, 5); //! cursor.consume(num_bytes); //! buf.clear(); //! //! // cursor is at EOF //! let num_bytes = cursor.fill_until(b'-', &mut buf) //! .expect("reading from cursor won't fail"); //! assert_eq!(num_bytes, 0); //! assert_eq!(buf, b""); //! ``` #![forbid(unsafe_code, future_incompatible, rust_2018_idioms)] #![deny(missing_debug_implementations, nonstandard_style)] #![warn(missing_docs, missing_doc_code_examples, unreachable_pub)] use std::io::{self, BufRead, ErrorKind, Read}; use std::slice; /// The `omnom` prelude. pub mod prelude { pub use crate::BufReadExt; } /// Extend `BufRead` with methods for streaming parsing. pub trait BufReadExt: BufRead { /// Read bytes based on a predicate. /// /// `read_while` takes a predicate as an argument. /// It will call this on each byte, and copy it to the slice if the /// predicate evaluates to `true`. Returns the amount of bytes read. /// /// # Errors /// /// If this function encounters an error of the kind /// `ErrorKind::Interrupted` then the error is ignored and the operation /// will continue. /// /// If any other read error is encountered then this function immediately /// returns. Any bytes which have already been read will be appended to /// `buf`. /// /// # Examples /// /// [`std::io::Cursor`][`Cursor`] is a type that implements `BufRead`. In /// this example, we use [`Cursor`] to read bytes in a byte slice until /// we encounter a hyphen: /// /// ``` /// use std::io::{self, BufRead}; /// use omnom::prelude::*; /// /// let mut cursor = io::Cursor::new(b"lorem-ipsum"); /// let mut buf = vec![]; /// /// let num_bytes = cursor.read_while(&mut buf, |b| b != b'-') /// .expect("reading from cursor won't fail"); /// assert_eq!(buf, b"lorem"); /// ``` fn read_while<P>(&mut self, buf: &mut Vec<u8>, mut predicate: P) -> io::Result<usize> where P: FnMut(u8) -> bool, { let mut read = 0; loop { let mut byte = 0; match self.read(slice::from_mut(&mut byte)) { Ok(0) => break, Ok(_) => { if predicate(byte) { buf.extend_from_slice(&[byte]); read += 1; } else { read += 1; break; } } Err(ref e) if e.kind() == ErrorKind::Interrupted => continue, Err(e) => { self.consume(read); return Err(e); } }; } self.consume(read); Ok(read) } /// Try reading based on a predicate. /// /// `read_while` takes a predicate as an argument. /// It will call this on each byte, and copy it to the slice if the /// predicate evaluates to `true`. Returns the amount of bytes read. /// /// Unlike `read_while` after consuming bytes through this method you'll /// have to manually call [`BufRead::consume`](https://doc.rust-lang.org/std/io/trait.BufRead.html#tymethod.consume). /// /// # Errors /// /// If this function encounters an error of the kind /// `ErrorKind::Interrupted` then the error is ignored and the operation /// will continue. /// /// If any other read error is encountered then this function immediately /// returns. Any bytes which have already been read will be appended to /// `buf`. /// /// # Examples /// /// [`std::io::Cursor`][`Cursor`] is a type that implements `BufRead`. In /// this example, we use [`Cursor`] to read bytes in a byte slice until /// we encounter a hyphen: /// /// [`Cursor`]: https://doc.rust-lang.org/std/io/struct.Cursor.html /// /// ``` /// use std::io::{self, BufRead}; /// use omnom::prelude::*; /// /// let mut cursor = io::Cursor::new(b"lorem-ipsum"); /// let mut buf = vec![]; /// /// let num_bytes = cursor.fill_while(&mut buf, |b| b != b'-') /// .expect("reading from cursor won't fail"); /// assert_eq!(buf, b"lorem"); /// cursor.consume(num_bytes); /// ``` fn fill_while<P>(&mut self, buf: &mut Vec<u8>, mut predicate: P) -> io::Result<usize> where Self: Read, P: FnMut(u8) -> bool, { let mut read = 0; loop { let mut byte = 0; match self.read(slice::from_mut(&mut byte)) { Ok(0) => break, Ok(_) => { if predicate(byte) { buf.extend_from_slice(&[byte]); read += 1; } else { read += 1; break; } } Err(ref e) if e.kind() == ErrorKind::Interrupted => continue, Err(e) => return Err(e), }; } Ok(read) } /// 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`. /// /// Unlike `read_until` after consuming bytes through this method you'll /// have to manually call [`BufRead::consume`]. /// /// 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 [`BufRead::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. /// /// [`BufRead::consume`]: https://doc.rust-lang.org/std/io/trait.BufRead.html#tymethod.consume /// [`BufRead::fill_buf`]: https://doc.rust-lang.org/std/io/trait.BufRead.html#tymethod.consume /// [`ErrorKind::Interrupted`]: https://doc.rust-lang.org/std/io/enum.ErrorKind.html#variant.Interrupted /// /// # Examples /// /// [`std::io::Cursor`][`Cursor`] is a type that implements `BufRead`. In /// this example, we use [`Cursor`] to read all the bytes in a byte slice /// in hyphen delimited segments: /// /// [`Cursor`]: https://doc.rust-lang.org/std/io/struct.Cursor.html /// /// ``` /// use std::io::{self, BufRead}; /// use omnom::prelude::*; /// /// let mut cursor = io::Cursor::new(b"lorem-ipsum"); /// let mut buf = vec![]; /// /// // cursor is at 'l' /// let num_bytes = cursor.fill_until(b'-', &mut buf) /// .expect("reading from cursor won't fail"); /// assert_eq!(buf, b"lorem-"); /// assert_eq!(num_bytes, 6); /// cursor.consume(num_bytes); /// buf.clear(); /// /// // cursor is at 'i' /// let num_bytes = cursor.fill_until(b'-', &mut buf) /// .expect("reading from cursor won't fail"); /// assert_eq!(buf, b"ipsum"); /// assert_eq!(num_bytes, 5); /// cursor.consume(num_bytes); /// buf.clear(); /// /// // cursor is at EOF /// let num_bytes = cursor.fill_until(b'-', &mut buf) /// .expect("reading from cursor won't fail"); /// assert_eq!(num_bytes, 0); /// assert_eq!(buf, b""); /// ``` fn fill_until(&mut self, byte: u8, buf: &mut Vec<u8>) -> io::Result<usize> { let mut read = 0; loop { let available = match self.fill_buf() { Ok(n) => n, Err(ref e) if e.kind() == ErrorKind::Interrupted => continue, Err(e) => return Err(e), }; let available = &available[read..]; let (done, used) = match memchr::memchr(byte, available) { Some(i) => { buf.extend_from_slice(&available[..=i]); (true, i + 1) } None => { buf.extend_from_slice(available); (false, available.len()) } }; read += used; if done || used == 0 { return Ok(read); } } } /// 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`. /// /// Unlike `read_exact`, after reading bytes through this method you'll /// have to manually call [`BufRead::consume`]. /// /// 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. /// /// # Examples /// /// [`File`]s implement `Read`: /// /// [`File`]: https://doc.rust-lang.org/std/fs/struct.File.html /// [`ErrorKind::Interrupted`]: https://doc.rust-lang.org/std/io/enum.ErrorKind.html#variant.Interrupted /// [`ErrorKind::UnexpectedEof`]: https://doc.rust-lang.org/std/io/enum.ErrorKind.html#variant.UnexpectedEof /// [`ErrorKind::UnexpectedEof`]: ../../std/io/enum.ErrorKind.html#variant.UnexpectedEof /// /// ```no_run /// use std::io::{self, BufReader}; /// use std::io::prelude::*; /// use std::fs::File; /// use omnom::prelude::*; /// /// let mut cursor = io::Cursor::new(b"lorem-ipsum"); /// let mut buf = vec![0; 5]; /// /// // read exactly 5 bytes /// cursor.fill_exact(&mut buf).unwrap(); /// assert_eq!(buf, b"lorem"); /// buf.clear(); /// /// // the same bytes can be read again /// cursor.fill_exact(&mut buf).unwrap(); /// assert_eq!(buf, b"lorem"); /// buf.clear(); /// cursor.consume(5); /// /// // after consuming bytes we read new bytes /// cursor.fill_exact(&mut buf).unwrap(); /// assert_eq!(buf, b"-ipsu"); /// ``` fn fill_exact(&mut self, buf: &mut [u8]) -> io::Result<()> { loop { let available = match self.fill_buf() { Ok(n) => n, Err(ref e) if e.kind() == ErrorKind::Interrupted => continue, Err(e) => return Err(e), }; if available.len() >= buf.len() { buf.copy_from_slice(&available[..buf.len()]); break; } } Ok(()) } } impl<T: BufRead> BufReadExt for T {}