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
//! Second stage lexer declaration
use lang_util::TextRange;
use crate::util::{LineMap, Unescaped};
use super::{NewlineSplitter, NewlineToken, NewlineTokenKind};
mod token;
pub use token::Token;
use Token::*;
pub type TextToken = crate::util::TextToken<token::Token>;
#[derive(Debug, Clone, Copy, PartialEq)]
enum State {
/// Initial state of the preprocessor
Init,
/// Possibly a start of comment
Slash,
/// Line continuation character seen
Backslash,
/// Building an identifier
Ident,
/// Building a digit sequence
Digits { seen_e: bool },
/// Single-line comment
SingleComment,
/// Multi-line comment
MultiComment,
/// Multi-line comment, saw a *
MultiCommentStar,
/// Any kind of horizontal whitespace
Whitespace,
/// Inside a quote string
QuoteString,
/// Insite an angle string
AngleString,
}
impl Default for State {
fn default() -> Self {
Self::Init
}
}
/// A lexer for early lexical analysis stages.
///
/// This lexer does the following:
/// * Assemble digit sequences into single tokens
/// * Assemble identifier characters into single tokens
/// * Eliminate backslash-escaped newlines
/// * Identify single and multi-line comments
/// * Tokenize double-quoted strings and (when asked to) angle-quoted strings
#[derive(Debug, Clone)]
pub struct PreLexer<'i> {
source: &'i str,
input: NewlineSplitter<'i>,
peeked: Option<Option<NewlineToken>>,
state: State,
start: TextRange,
return_to: State,
expect_angle_string: bool,
}
impl<'i> PreLexer<'i> {
pub fn new(input: &'i str) -> Self {
Self {
source: input,
input: NewlineSplitter::new(input),
state: Default::default(),
start: Default::default(),
return_to: Default::default(),
peeked: None,
expect_angle_string: false,
}
}
pub fn input(&self) -> &'i str {
self.source
}
pub fn line_map(&self) -> &LineMap {
self.input.line_map()
}
pub fn into_line_map(self) -> LineMap {
self.input.into_line_map()
}
pub fn set_expect_angle_string(&mut self, expect_angle_string: bool) {
self.expect_angle_string = expect_angle_string;
}
fn peek_token(&mut self) -> Option<(NewlineToken, &'i str)> {
self.peeked
.unwrap_or_else(|| {
let next = self.input.next();
self.peeked = Some(next);
next
})
.map(move |token| (token, token.raw(self.source)))
}
fn next_token(&mut self) -> Option<NewlineToken> {
let result = if let Some(token) = self.peeked.take() {
token
} else {
self.input.next()
};
// Expand the current token
if let Some(token) = &result {
self.start = TextRange::new(self.start.start(), token.range.end());
}
result
}
}
impl<'i> Iterator for PreLexer<'i> {
type Item = TextToken;
fn next(&mut self) -> Option<Self::Item> {
loop {
self.state = match std::mem::take(&mut self.state) {
State::Init => {
let c = self.next_token();
// All the following states need a recorded start point
if let Some(t) = &c {
self.start = t.range;
}
match c {
Some(NewlineToken {
token: NewlineTokenKind::LETTER,
..
}) => {
// Start an identifier
State::Ident
}
Some(NewlineToken {
token: NewlineTokenKind::DIGIT,
..
}) => {
// Start a digit sequence
State::Digits { seen_e: false }
}
Some(NewlineToken {
token: NewlineTokenKind::PUNCT,
range,
}) => {
let t = c.unwrap();
let text = t.raw(self.source);
match text {
"\"" => {
// Also clear the string flag, since it should've started with
// < instead
self.expect_angle_string = false;
State::QuoteString
}
"<" if self.expect_angle_string => {
// Clear the string flag
self.expect_angle_string = false;
State::AngleString
}
"\\" => {
self.return_to = State::Init;
State::Backslash
}
"/" => State::Slash,
"_" => State::Ident,
_ => {
// Punctuation
return Some(TextToken {
token: Token::from_punct(text),
range,
});
}
}
}
Some(NewlineToken {
token: NewlineTokenKind::NEWLINE,
range,
}) => {
// A newline, this completes a potential #include
self.expect_angle_string = false;
// A newline
return Some(TextToken {
token: NEWLINE,
range,
});
}
Some(NewlineToken {
token: NewlineTokenKind::WS,
..
}) => State::Whitespace,
None => {
return None;
}
}
}
State::Slash => {
match self.peek_token() {
Some((_, "/")) => {
self.next_token();
State::SingleComment
}
Some((_, "*")) => {
self.next_token();
State::MultiComment
}
_ => {
// Another char or EOI, so we saw a '/' followed by something else
// Emit the '/' and then we'll reparse the char next round
return Some(TextToken::new(SLASH, self.start));
}
}
}
State::Backslash => {
// Either there's a newline and we should skip it, or there's something else
// and we pass the backslash forward
match self.peek_token() {
Some((
NewlineToken {
token: NewlineTokenKind::NEWLINE,
..
},
_,
)) => {
self.next_token();
if self.return_to == State::Init {
// This line continuation is included nowhere, so we should emit it
return Some(TextToken::new(LINECONT, self.start));
} else {
// This line continuation is part of some other token
self.return_to
}
}
_ => {
if self.return_to == State::SingleComment
|| self.return_to == State::MultiComment
{
// In a comment, consume the backslash, don't emit it
self.next_token();
self.return_to
} else {
return Some(TextToken::new(BACKSLASH, self.start));
}
}
}
}
State::Ident => {
match self.peek_token() {
Some((
NewlineToken {
token: NewlineTokenKind::LETTER,
..
},
_,
))
| Some((
NewlineToken {
token: NewlineTokenKind::DIGIT,
..
},
_,
))
| Some((
NewlineToken {
token: NewlineTokenKind::PUNCT,
..
},
"_",
)) => {
// Continue the ident
self.next_token();
State::Ident
}
Some((_, "\\")) => {
self.next_token();
self.return_to = State::Ident;
State::Backslash
}
_ => {
// Not an ident anymore, return the ident
let token = TextToken::new(Token::IDENT_KW, self.start);
// Check if IDENT_KW is the defined keyword
if Unescaped::new(token.raw(self.source)) == "defined" {
return Some(TextToken::new(Token::DEFINED, self.start));
}
return Some(token);
}
}
}
State::Digits { seen_e } => {
match self.peek_token() {
Some((
NewlineToken {
token: NewlineTokenKind::DIGIT,
..
},
_,
)) => {
self.next_token();
State::Digits { seen_e: false }
}
Some((
NewlineToken {
token: NewlineTokenKind::PUNCT,
..
},
punct,
)) if punct == "." || seen_e && (punct == "+" || punct == "-") => {
self.next_token();
State::Digits { seen_e: false }
}
Some((
NewlineToken {
token: NewlineTokenKind::LETTER,
..
},
ch,
)) => {
self.next_token();
State::Digits {
seen_e: ch == "e" || ch == "E",
}
}
Some((_, "\\")) => {
self.next_token();
self.return_to = State::Digits { seen_e };
State::Backslash
}
_ => {
// Not an ident anymore, return the ident
return Some(TextToken::new(Token::DIGITS, self.start));
}
}
}
State::SingleComment => {
match self.peek_token() {
Some((
NewlineToken {
token: NewlineTokenKind::NEWLINE,
..
},
_,
))
| None => {
// Do not eat the newline yet
return Some(TextToken::new(Token::COMMENT, self.start));
}
Some((_, "\\")) => {
self.next_token();
self.return_to = State::SingleComment;
State::Backslash
}
_ => {
// Any other char
self.next_token();
State::SingleComment
}
}
}
State::MultiComment => {
match self.peek_token() {
Some((_, "*")) => {
self.next_token();
State::MultiCommentStar
}
None => {
// Unfinished comment
return Some(TextToken::new(Token::ERROR, self.start));
}
_ => {
// Any other char
self.next_token();
State::MultiComment
}
}
}
State::MultiCommentStar => {
match self.peek_token() {
Some((_, "/")) => {
self.next_token();
return Some(TextToken::new(Token::COMMENT, self.start));
}
None => {
// Unfinished comment
return Some(TextToken::new(Token::ERROR, self.start));
}
_ => {
// Any other char
self.next_token();
State::MultiComment
}
}
}
State::Whitespace => {
if self
.peek_token()
.map(|(token, _)| token.token == NewlineTokenKind::WS)
.unwrap_or(false)
{
// More whitespace
self.next_token();
State::Whitespace
} else {
// No more whitespace
return Some(TextToken::new(WS, self.start));
}
}
State::QuoteString => {
if let Some((token, text)) = self.peek_token() {
// Release text borrow
let end_quote = text == "\"";
// Always consume the token
self.next_token();
// Extend the range
self.start = TextRange::new(self.start.start(), token.range.end());
if end_quote {
return Some(TextToken::new(QUOTE_STRING, self.start));
} else {
State::QuoteString
}
} else {
// No more tokens, bump an error
return Some(TextToken::new(ERROR, self.start));
}
}
State::AngleString => {
if let Some((token, text)) = self.peek_token() {
// Release text borrow
let end_quote = text == ">";
// Always consume the token
self.next_token();
// Extend the range
self.start = TextRange::new(self.start.start(), token.range.end());
if end_quote {
return Some(TextToken::new(ANGLE_STRING, self.start));
} else {
State::AngleString
}
} else {
// No more tokens, bump an error
return Some(TextToken::new(ERROR, self.start));
}
}
};
}
}
}