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
//! A lexical analyzer for JavaScript source code.
//!
//! The Lexer splits its input source code into a sequence of input elements called tokens, represented by the [Token](../ast/token/struct.Token.html) structure.
//! It also removes whitespace and comments and attaches them to the next token.
use std::char::from_u32;
use std::error;
use std::fmt;
use std::iter::Peekable;
use std::str::Chars;
use std::str::FromStr;
use syntax::ast::punc::Punctuator;
use syntax::ast::token::{Token, TokenData};
#[allow(unused)]
macro_rules! vop {
($this:ident, $assign_op:expr, $op:expr) => ({
let preview = $this.preview_next()?;
match preview {
'=' => {
$this.next()?;
$assign_op
}
_ => $op,
}
});
($this:ident, $assign_op:expr, $op:expr, {$($case:pat => $block:expr), +}) => ({
let preview = $this.preview_next()?;
match preview {
'=' => {
$this.next()?;
$assign_op
},
$($case => $block)+,
_ => $op
}
});
($this:ident, $op:expr, {$($case:pat => $block:expr),+}) => {
let preview = $this.preview_next()?;
match preview {
$($case => $block) +,
_ => $op
}
}
}
macro_rules! op {
($this:ident, $assign_op:expr, $op:expr) => ({
let punc = vop!($this, $assign_op, $op);
$this.push_punc(punc);
});
($this:ident, $assign_op:expr, $op:expr, {$($case:pat => $block:expr),+}) => ({
let punc = vop!($this, $assign_op, $op, {$($case => $block),+});
$this.push_punc(punc);
});
($this:ident, $op:expr, {$($case:pat => $block:expr),+}) => ({
let punc = vop!($this, $op, {$($case => $block),+});
$this.push_punc();
});
}
/// An error that occurred during lexing or compiling of the source input.
#[derive(Debug, Clone)]
pub struct LexerError {
details: String,
}
impl LexerError {
fn new(msg: &str) -> LexerError {
LexerError {
details: msg.to_string(),
}
}
}
impl fmt::Display for LexerError {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "{}", self.details)
}
}
impl error::Error for LexerError {
fn description(&self) -> &str {
&self.details
}
fn cause(&self) -> Option<&error::Error> {
// Generic error, underlying cause isn't tracked.
None
}
}
/// A lexical analyzer for JavaScript source code
pub struct Lexer<'a> {
// The list fo tokens generated so far
pub tokens: Vec<Token>,
// The current line number in the script
line_number: u64,
// the current column number in the script
column_number: u64,
// The full string
buffer: Peekable<Chars<'a>>,
}
impl<'a> Lexer<'a> {
/// Returns a Lexer with a buffer inside
///
/// # Arguments
///
/// * `buffer` - A string slice that holds the source code.
/// The buffer needs to have a lifetime as long as the Lexer instance itself
///
/// # Example
///
/// ```rust,no_run
/// let buffer = std::fs::read_to_string("yourSourceCode.js").unwrap();
/// let lexer = boa::syntax::lexer::Lexer::new(&buffer);
/// ```
pub fn new(buffer: &'a str) -> Lexer<'a> {
Lexer {
tokens: Vec::new(),
line_number: 1,
column_number: 0,
buffer: buffer.chars().peekable(),
}
}
/// Push tokens onto the token queue
fn push_token(&mut self, tk: TokenData) {
self.tokens
.push(Token::new(tk, self.line_number, self.column_number))
}
/// Push a punctuation token
fn push_punc(&mut self, punc: Punctuator) {
self.push_token(TokenData::Punctuator(punc));
}
/// next fetches the next token and return it, or a LexerError if there are no more.
fn next(&mut self) -> Result<char, LexerError> {
match self.buffer.next() {
Some(char) => Ok(char),
None => Err(LexerError::new("finished")),
}
}
/// read_line attempts to read until the end of the line and returns the String object or a LexerError
fn read_line(&mut self) -> Result<String, LexerError> {
let mut buf = String::new();
loop {
let ch = self.next()?;
match ch {
_ if ch.is_ascii_control() => {
break;
}
_ => {
buf.push(ch);
}
}
}
Ok(buf)
}
/// Preview the next character but don't actually increment
fn preview_next(&mut self) -> Result<char, LexerError> {
// No need to return a reference, we can return a copy
match self.buffer.peek() {
Some(v) => Ok(*v),
None => Err(LexerError::new("finished")),
}
}
/// next_is compares the character passed in to the next character, if they match true is returned and the buffer is incremented
fn next_is(&mut self, peek: char) -> Result<bool, LexerError> {
let result = self.preview_next()? == peek;
if result {
self.buffer.next();
}
Ok(result)
}
pub fn lex(&mut self) -> Result<(), LexerError> {
loop {
// Check if we've reached the end
match self.preview_next() {
Ok(_) => (), // If there are still characters, carry on
Err(e) => {
if e.details == "finished" {
// If there are no more characters left in the Chars iterator, we should just return
return Ok(());
} else {
return Err(e);
}
}
}
self.column_number += 1;
let ch = self.next()?;
match ch {
'"' | '\'' => {
let mut buf = String::new();
loop {
match self.next()? {
'\'' if ch == '\'' => {
break;
}
'"' if ch == '"' => {
break;
}
'\\' => {
let escape = self.next()?;
if escape != '\n' {
let escaped_ch = match escape {
'n' => '\n',
'r' => '\r',
't' => '\t',
'b' => '\x08',
'f' => '\x0c',
'0' => '\0',
'x' => {
let mut nums = String::with_capacity(2);
for _ in 0u8..2 {
nums.push(self.next()?);
}
self.column_number += 2;
let as_num = match u64::from_str_radix(&nums, 16) {
Ok(v) => v,
Err(_) => 0,
};
match from_u32(as_num as u32) {
Some(v) => v,
None => panic!(
"{}:{}: {} is not a valid unicode scalar value",
self.line_number, self.column_number, as_num
),
}
}
'u' => {
let mut nums = String::new();
for _ in 0u8..4 {
nums.push(self.next()?);
}
self.column_number += 4;
let as_num = match u64::from_str_radix(&nums, 16) {
Ok(v) => v,
Err(_) => 0,
};
match from_u32(as_num as u32) {
Some(v) => v,
None => panic!(
"{}:{}: {} is not a valid unicode scalar value",
self.line_number, self.column_number, as_num
),
}
}
'\'' | '"' => escape,
_ => panic!(
"{}:{}: Invalid escape `{}`",
self.line_number, self.column_number, ch
),
};
buf.push(escaped_ch);
}
}
ch => buf.push(ch),
}
}
let str_length = buf.len() as u64;
self.push_token(TokenData::StringLiteral(buf));
// Why +1? Quotation marks are not included,
// So technically it would be +2, (for both " ") but we want to be 1 less
// to compensate for the incrementing at the top
self.column_number += str_length + 1;
}
'0' => {
let mut buf = String::new();
let num = if self.next_is('x')? {
loop {
let ch = self.preview_next()?;
match ch {
ch if ch.is_digit(16) => {
buf.push(self.next()?);
}
_ => break,
}
}
u64::from_str_radix(&buf, 16).unwrap()
} else {
loop {
let ch = self.preview_next()?;
match ch {
ch if ch.is_digit(8) => {
buf.push(ch);
self.next()?;
}
'8' | '9' | '.' => {
buf.push(ch);
self.next()?;
}
_ => break,
}
}
u64::from_str_radix(&buf, 8).unwrap()
};
self.push_token(TokenData::NumericLiteral(num as f64))
}
_ if ch.is_digit(10) => {
let mut buf = ch.to_string();
loop {
let ch = self.preview_next()?;
match ch {
'.' => {
buf.push(self.next()?);
}
_ if ch.is_digit(10) => {
buf.push(self.next()?);
}
_ => break,
}
}
// TODO make this a bit more safe -------------------------------VVVV
self.push_token(TokenData::NumericLiteral(f64::from_str(&buf).unwrap()))
}
_ if ch.is_alphabetic() || ch == '$' || ch == '_' => {
let mut buf = ch.to_string();
loop {
let ch = self.preview_next()?;
match ch {
_ if ch.is_alphabetic() || ch.is_digit(10) || ch == '_' => {
buf.push(self.next()?);
}
_ => {
break;
}
}
}
// Match won't compare &String to &str so i need to convert it :(
let buf_compare: &str = &buf;
self.push_token(match buf_compare {
"true" => TokenData::BooleanLiteral(true),
"false" => TokenData::BooleanLiteral(false),
"null" => TokenData::NullLiteral,
slice => match FromStr::from_str(slice) {
Ok(keyword) => TokenData::Keyword(keyword),
Err(_) => TokenData::Identifier(buf.clone()),
},
});
// Move position forward the length of keyword
self.column_number += (buf_compare.len() - 1) as u64;
}
';' => self.push_punc(Punctuator::Semicolon),
':' => self.push_punc(Punctuator::Colon),
'.' => self.push_punc(Punctuator::Dot),
'(' => self.push_punc(Punctuator::OpenParen),
')' => self.push_punc(Punctuator::CloseParen),
',' => self.push_punc(Punctuator::Comma),
'{' => self.push_punc(Punctuator::OpenBlock),
'}' => self.push_punc(Punctuator::CloseBlock),
'[' => self.push_punc(Punctuator::OpenBracket),
']' => self.push_punc(Punctuator::CloseBracket),
'?' => self.push_punc(Punctuator::Question),
// Comments
'/' => {
let token = match self.preview_next()? {
// Matched comment
'/' => {
let comment = self.read_line()?;
TokenData::Comment(comment)
}
'*' => {
let mut buf = String::new();
loop {
match self.next()? {
'*' => {
if self.next_is('/')? {
break;
} else {
buf.push('*')
}
}
ch => buf.push(ch),
}
}
TokenData::Comment(buf)
}
'=' => TokenData::Punctuator(Punctuator::AssignDiv),
_ => TokenData::Punctuator(Punctuator::Div),
};
self.push_token(token)
}
'*' => op!(self, Punctuator::AssignMul, Punctuator::Mul),
'+' => op!(self, Punctuator::AssignAdd, Punctuator::Add, {
'+' => Punctuator::Inc
}),
'-' => op!(self, Punctuator::AssignSub, Punctuator::AssignSub, {
'+' => Punctuator::Inc
}),
'%' => op!(self, Punctuator::AssignMod, Punctuator::Mod),
'|' => op!(self, Punctuator::AssignOr, Punctuator::Or, {
'|' => Punctuator::BoolOr
}),
'&' => op!(self, Punctuator::AssignAnd, Punctuator::And, {
'&' => Punctuator::BoolAnd
}),
'^' => op!(self, Punctuator::AssignXor, Punctuator::Xor),
'=' => op!(self, if self.next_is('=')? {
Punctuator::StrictEq
} else {
Punctuator::Eq
}, Punctuator::Assign, {
'>' => Punctuator::Arrow
}),
'<' => op!(self, Punctuator::LessThanOrEq, Punctuator::LessThan, {
'<' => vop!(self, Punctuator::AssignLeftSh, Punctuator::LeftSh)
}),
'>' => op!(self, Punctuator::GreaterThanOrEq, Punctuator::GreaterThan, {
'>' => vop!(self, Punctuator::AssignRightSh, Punctuator::RightSh, {
'>' => vop!(self, Punctuator::AssignURightSh, Punctuator::URightSh)
})
}),
'!' => op!(
self,
vop!(self, Punctuator::StrictNotEq, Punctuator::NotEq),
Punctuator::Not
),
'~' => self.push_punc(Punctuator::Neg),
'\n' | '\u{2028}' | '\u{2029}' => {
self.line_number += 1;
self.column_number = 0;
}
'\r' => {
self.column_number = 0;
}
' ' => (),
ch => panic!(
"{}:{}: Unexpected '{}'",
self.line_number, self.column_number, ch
),
}
}
}
}