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
//! Some span data structures //! //! # Description //! //! This module contains the [`Span`] and [`SpannedStr`] data structures. The //! difference between them is that [`SpannedStr`] contains the inner text while //! [`Span`] contains only its position. Consequently, [`SpannedStr`] is used //! during the lexing and parsing steps, but the AST generated *should* contain //! only [`Span`]. //! //! # A consistency note //! //! Inconsistent results may occur when [`Span`] and [`SpannedStr`] coming from //! different places are used toghether. This is fine for most use-cases, in //! which a single process in invoked for a single input unit. use std::cmp::{Ord, Ordering}; /// Represents a position in the input data. /// /// Positions are 0-indexed, meaning that the first character of each line has /// 0 as column number. The same goes for the line number. #[derive(Copy, Clone, Debug, Eq, PartialEq)] pub struct Position { line: u32, col: u32, offset: u32, } impl Position { const BEGINNING: Position = Position { line: 0, col: 0, offset: 0, }; fn advance_with(self, s: &str) -> Position { let Position { mut line, mut col, mut offset, } = self; s.chars().for_each(|c| { if c == '\n' { line += 1; col = 0 } else { col += 1; } }); offset += s.len() as u32; Position { line, col, offset } } /// Returns the position's line. #[inline] pub const fn line(self) -> u32 { self.line } /// Returns the position's column. #[inline] pub const fn col(self) -> u32 { self.col } /// Returns the position's offset from the beginning of the file. #[inline] pub const fn offset(self) -> u32 { self.offset } } // Note: when the following documentation is modified, remember to update the // doc for Position::Ord accordingly. /// # Warning /// /// Positions can be compared toghether only if they come from the same input /// unit. If they do not, then inconsistencies may occur. /// /// # Panics /// /// In debug mode, this function may panic if the two positions are not from the /// same input unit. In release mode, this function does not panic. impl PartialOrd for Position { fn partial_cmp(&self, other: &Position) -> Option<Ordering> { Some(self.cmp(other)) } } // Note: when the following documentation is modified, remember to update the // doc for Position::PartialOrd accordingly. /// # Warning /// /// Positions can be compared toghether only if they come from the same input /// unit. If they do not, then inconsistencies may occur. /// /// # Panics /// /// In debug mode, this function may panic if the two positions are not from the /// same input unit. In release mode, this function does not panic. impl Ord for Position { #[cfg(debug)] fn cmp(&self, other: &Position) -> Ordering { let offset_provided = self.offset.cmp(&other.offset); let lc_provided = match self.line.cmp(&other.line) { Ordering::Equal => self.col.cmp(&other.col), any => any, }; assert!( offset_provided != lc_provided, "Attempt to perform an inconsistent span comparaison", ); offset_provided } #[cfg(not(debug))] fn cmp(&self, other: &Position) -> Ordering { self.offset.cmp(&other.offset) } } /// Represents the position of a piece of code in the input file. /// /// A `Span` is represented as the start and end position. Every character that /// is between these two position is considered as *inside* the span. #[derive(Copy, Clone, Debug, PartialEq)] pub struct Span { start: Position, end: Position, } impl Span { /// Returns the span's starting position. #[inline] pub const fn start(self) -> Position { self.start } /// Returns the span's ending position. /// /// The position ends on the next non-spanned part: /// /// ```rust /// use lisbeth_error::span::SpannedStr; /// /// let s = SpannedStr::input_file("hello"); /// assert_eq!(s.span().end().col(), 5); /// ``` #[inline] pub const fn end(self) -> Position { self.end } #[inline] const fn split_with(self, mid: Position) -> (Span, Span) { let Span { start, end } = self; let left = Span { start, end: mid }; let right = Span { start: mid, end }; (left, right) } pub(crate) fn of_file(input: &str) -> Span { let start = Position::BEGINNING; let end = start.advance_with(input); Span { start, end } } } /// Represents a portion of input file. /// /// This is represented the same way as [`Span`], but with an additionnal /// content field. /// /// It is initially created with the [`input_file`] function, and can then be /// splitted at desired index. Its content and span can be accessed with the /// [`content`] and [`span`] methods. /// /// # Example /// /// The following code shows how to extract a sequence of numbers separated by /// non-digit characters. /// /// ```rust /// use lisbeth_error::span::{Span, SpannedStr}; /// /// #[derive(Debug)] /// struct Number(u32, Span); /// /// // Parses a number from input, if any failure occurs, returns None /// fn extract_number<'a>(input: SpannedStr<'a>) -> (Number, SpannedStr<'a>) { /// let (matched, tail) = input.take_while(char::is_numeric); /// /// let value = matched.content().parse().unwrap(); /// let number = Number(value, matched.span()); /// (number, tail) /// } /// /// let input = SpannedStr::input_file("42 or nothing"); /// let (number, tail) = extract_number(input); /// /// assert_eq!(number.0, 42); /// assert_eq!(tail.content(), " or nothing"); /// ``` /// /// [`input_file`]: SpannedStr::input_file /// [`content`]: SpannedStr::content /// [`span`]: SpannedStr::span #[derive(Copy, Clone, Debug, PartialEq)] pub struct SpannedStr<'a> { span: Span, content: &'a str, } impl<'a> SpannedStr<'a> { /// Creates a new [`SpannedStr`] from an input file. /// /// This returned spanned string can then be splitted at various places /// during the parsing step. /// /// # Example /// /// ```rust /// use lisbeth_error::span::SpannedStr; /// /// let file_content = "fn main() { println!(\"Hello, world!\"); }"; /// /// let whole_file = SpannedStr::input_file(file_content); /// ``` pub fn input_file(content: &'a str) -> SpannedStr<'a> { let span = Span::of_file(content); SpannedStr { span, content } } // Note: span must represent the same source as content, otherwise // inconsistent results may occur. // // In debug mode, it is ensured that: // - span.start == Position::BEGINNING, // - span.end.offset == content.len(). pub(crate) fn assemble(content: &'a str, span: Span) -> SpannedStr<'a> { debug_assert_eq!( span.start, Position::BEGINNING, "Attempt to create a SpannedStr that does not start at the beginning of the file", ); debug_assert_eq!( span.end.offset as usize, content.len(), "Attempt to create a SpannedStr with an incorrect length", ); SpannedStr { content, span } } /// Returns the contained [`Span`]. /// /// The span contains the position at which the content is located in the /// input data. /// /// # Example /// /// ```rust /// use lisbeth_error::span::SpannedStr; /// /// let a = SpannedStr::input_file("foo bar"); /// let b = SpannedStr::input_file("baz qux"); /// /// // a and b have the same length and the same starting point, so they /// // have the same span. /// assert_eq!(a.span(), b.span()); /// ``` pub const fn span(self) -> Span { self.span } /// Returns the span content. /// /// # Example /// /// ```rust /// use lisbeth_error::span:: SpannedStr; /// /// let a = SpannedStr::input_file("hello"); /// assert_eq!(a.content(), "hello"); /// ``` pub const fn content(self) -> &'a str { self.content } /// Splits the spanned string at a given byte index. /// /// This method works the same way as [str::split_at], but updates the span /// so that it is still correct. /// /// # Panics /// /// This method panics when one of the condition listed in [`str::split_at`] /// is met. /// /// # Example /// /// ```rust /// use lisbeth_error::span::SpannedStr; /// /// let input = SpannedStr::input_file("helloworld"); /// let (left, right) = input.split_at(5); /// /// assert_eq!(left.content(), "hello"); /// assert_eq!(right.content(), "world"); /// ``` pub fn split_at(self, idx: usize) -> (SpannedStr<'a>, SpannedStr<'a>) { let (left_content, right_content) = self.content.split_at(idx); let mid = self.span.start.advance_with(left_content); let (left_span, right_span) = self.span.split_with(mid); let left_sstr = SpannedStr { span: left_span, content: left_content, }; let right_sstr = SpannedStr { span: right_span, content: right_content, }; (left_sstr, right_sstr) } /// Returns the longest prefix of input that match a given a condition. /// /// # Example /// /// ```rust /// use lisbeth_error::span::SpannedStr; /// /// let i = SpannedStr::input_file("42 101"); /// let (number, tail) = i.take_while(char::is_numeric); /// /// assert_eq!(number.content(), "42"); /// assert_eq!(tail.content(), " 101"); /// ``` pub fn take_while<F>(self, mut f: F) -> (SpannedStr<'a>, SpannedStr<'a>) where F: FnMut(char) -> bool, { let idx = self .content .char_indices() .find(|(_, chr)| !f(*chr)) .map(|(idx, _)| idx) .unwrap_or_else(|| self.content.len()); self.split_at(idx) } } #[cfg(test)] mod tests { use super::*; mod position { use super::*; #[test] fn advance_with_no_line_return() { let p = Position::BEGINNING.advance_with("hello, world"); assert_eq!(p.line, 0); assert_eq!(p.col, 12); assert_eq!(p.offset, 12); } #[test] fn advance_with_line_return() { let p = Position::BEGINNING.advance_with("\n\n\n"); assert_eq!(p.line, 3); assert_eq!(p.col, 0); assert_eq!(p.offset, 3); } #[test] fn advance_with_mixed() { let p = Position::BEGINNING.advance_with("Hello,\nworld"); assert_eq!(p.line, 1); assert_eq!(p.col, 5); assert_eq!(p.offset, 12); } #[test] fn advance_with_empty() { let p = Position::BEGINNING.advance_with(""); assert_eq!(p, Position::BEGINNING); } #[test] fn advance_with_two_times() { let p = Position::BEGINNING.advance_with("foo bar"); let p = p.advance_with(" baz"); assert_eq!(p.line, 0); assert_eq!(p.col, 11); assert_eq!(p.offset, 11); } #[test] fn ord_simple() { let p = Position::BEGINNING.advance_with("hello, world!"); let q = p.advance_with(" How are you?"); assert!(p < q); } #[test] fn ord_only_cares_about_offset() { // This is part of the inconsistency paragraph in the module documentation let p = Position { line: 10, col: 20, offset: 1000, }; let q = Position { line: 100, col: 25, offset: 10, }; assert!(p > q); } } mod span { use super::*; #[test] fn of_file() { let i = "hello, world"; let left = Span::of_file("hello, world"); let start = Position::BEGINNING; let end = start.advance_with(i); let right = Span { start, end }; assert_eq!(left, right); } } mod spanned_str { use super::*; #[test] fn input_file_simple() { let sstr = SpannedStr::input_file("hello\nworld"); assert_eq!(sstr.span.start, Position::BEGINNING); assert_eq!(sstr.span.end.line, 1); assert_eq!(sstr.span.end.col, 5); } #[test] fn span_and_content() { let span = Span { start: Position { line: 10, col: 0, offset: 100, }, end: Position { line: 15, col: 10, offset: 150, }, }; let content = "hello, world"; let sstr = SpannedStr { content, span }; assert_eq!(sstr.span(), span); assert_eq!(sstr.content(), content); } #[test] fn split_at_working() { let input = SpannedStr::input_file("foobar"); let (left, right) = input.split_at(3); assert_eq!(left.content, "foo"); assert_eq!(right.content, "bar"); let left_span = Span { start: Position { line: 0, col: 0, offset: 0, }, end: Position { line: 0, col: 3, offset: 3, }, }; let right_span = Span { start: Position { line: 0, col: 3, offset: 3, }, end: Position { line: 0, col: 6, offset: 6, }, }; assert_eq!(left.span, left_span); assert_eq!(right.span, right_span); } #[test] #[should_panic(expected = "byte index 15 is out of bounds of `hello, world`")] fn split_at_out_of_bounds() { let f = SpannedStr::input_file("hello, world"); f.split_at(15); } #[test] #[should_panic( expected = "byte index 2 is not a char boundary; it is inside \'é\' (bytes 1..3) of `Vélo`" )] fn split_at_non_boundary() { let f = SpannedStr::input_file("Vélo"); f.split_at(2); } #[test] fn take_while() { let (left, right) = SpannedStr::input_file("foo bar").take_while(|c| c != ' '); assert_eq!(left.content, "foo"); assert_eq!(right.content, " bar"); } #[test] fn take_while_empty_string() { let input = SpannedStr::input_file(""); let (left, right) = input.take_while(|_| true); assert_eq!(left, input); assert_eq!(right, input); } #[test] fn take_while_non_ascii() { let (left, right) = SpannedStr::input_file("éêè").take_while(|c| c != 'è'); assert_eq!(left.content, "éê"); assert_eq!(right.content, "è"); } } }