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
use quote::ToTokens;
use syn::{parse_macro_input, AttributeArgs, ItemMod};
mod errors;
mod expansion;
use expansion::*;
#[proc_macro_attribute]
/// Marks the top level AST node where parsing should start.
///
/// ## Example
/// ```ignore
/// #[rust_sitter::language]
/// pub struct Code {
/// ...
/// }
/// ```
pub fn language(
_attr: proc_macro::TokenStream,
item: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
item
}
#[proc_macro_attribute]
/// This annotation marks a node as extra, which can safely be skipped while parsing.
/// This is useful for handling whitespace/newlines/comments.
///
/// ## Example
/// ```ignore
/// #[rust_sitter::extra]
/// struct Whitespace {
/// #[rust_sitter::leaf(pattern = r"\s")]
/// _whitespace: (),
/// }
/// ```
pub fn extra(
_attr: proc_macro::TokenStream,
item: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
item
}
#[proc_macro_attribute]
/// Defines a field which matches a specific token in the source string.
/// The token can be defined by passing one of two arguments
/// - `text`: a string literal that will be exactly matched
/// - `pattern`: a regular expression that will be matched against the source string
///
/// If the resulting token needs to be converted into a richer type at runtime,
/// such as a number, then the `transform` argument can be used to specify a function
/// that will be called with the token's text.
///
/// The attribute can also be applied to a struct or enum variant with no fields.
///
/// ## Examples
///
/// Using the `leaf` attribute on a field:
/// ```ignore
/// Number(
/// #[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())]
/// u32
/// )
/// ```
///
/// Using the attribute on a unit struct or unit enum variant:
/// ```ignore
/// #[rust_sitter::leaf(text = "9")]
/// struct BigDigit;
///
/// enum SmallDigit {
/// #[rust_sitter::leaf(text = "0")]
/// Zero,
/// #[rust_sitter::leaf(text = "1")]
/// One,
/// }
/// ```
///
pub fn leaf(
_attr: proc_macro::TokenStream,
item: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
item
}
#[proc_macro_attribute]
/// Defines a field that does not correspond to anything in the input string,
/// such as some metadata. Takes a single, unnamed argument, which is the value
/// used to populate the field at runtime.
///
/// ## Example
/// ```ignore
/// struct MyNode {
/// ...,
/// #[rust_sitter::skip(false)]
/// node_visited: bool
/// }
/// ```
pub fn skip(
_attr: proc_macro::TokenStream,
item: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
item
}
#[proc_macro_attribute]
/// Defines a precedence level for a non-terminal that has no associativity.
///
/// This annotation takes a single, unnamed parameter, which specifies the precedence level.
/// This is used to resolve conflicts with other non-terminals, so that the one with the higher
/// precedence will bind more tightly (appear lower in the parse tree).
///
/// ## Example
/// ```ignore
/// #[rust_sitter::prec(1)]
/// PriorityExpr(Box<Expr>, Box<Expr>)
/// ```
pub fn prec(
_attr: proc_macro::TokenStream,
item: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
item
}
#[proc_macro_attribute]
/// Defines a precedence level for a non-terminal that should be left-associative.
/// For example, with subtraction we expect 1 - 2 - 3 to be parsed as (1 - 2) - 3,
/// which corresponds to a left-associativity.
///
/// This annotation takes a single, unnamed parameter, which specifies the precedence level.
/// This is used to resolve conflicts with other non-terminals, so that the one with the higher
/// precedence will bind more tightly (appear lower in the parse tree).
///
/// ## Example
/// ```ignore
/// #[rust_sitter::prec_left(1)]
/// Subtract(Box<Expr>, Box<Expr>)
/// ```
pub fn prec_left(
_attr: proc_macro::TokenStream,
item: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
item
}
#[proc_macro_attribute]
/// Defines a precedence level for a non-terminal that should be right-associative.
/// For example, with cons we could have 1 :: 2 :: 3 to be parsed as 1 :: (2 :: 3),
/// which corresponds to a right-associativity.
///
/// This annotation takes a single, unnamed parameter, which specifies the precedence level.
/// This is used to resolve conflicts with other non-terminals, so that the one with the higher
/// precedence will bind more tightly (appear lower in the parse tree).
///
/// ## Example
/// ```ignore
/// #[rust_sitter::prec_right(1)]
/// Cons(Box<Expr>, Box<Expr>)
/// ```
pub fn prec_right(
_attr: proc_macro::TokenStream,
item: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
item
}
#[proc_macro_attribute]
/// On `Vec<_>` typed fields, specifies a non-terminal that should be parsed in between the elements.
/// The [`rust_sitter::repeat`] annotation must be used on the field as well.
///
/// This annotation takes a single, unnamed argument, which specifies a field type to parse. This can
/// either be a reference to another type, or can be defined as a `leaf` field. Generally, the argument
/// is parsed using the same rules as an unnamed field of an enum variant.
///
/// ## Example
/// ```ignore
/// #[rust_sitter::delimited(
/// #[rust_sitter::leaf(text = ",")]
/// ()
/// )]
/// numbers: Vec<Number>
/// ```
pub fn delimited(
_attr: proc_macro::TokenStream,
item: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
item
}
#[proc_macro_attribute]
/// On `Vec<_>` typed fields, specifies additional config for how the repeated elements should
/// be parsed. In particular, this annotation takes the following named arguments:
/// - `non_empty` - if this argument is `true`, then there must be at least one element parsed
///
/// ## Example
/// ```ignore
/// #[rust_sitter::repeat(non_empty = true)]
/// numbers: Vec<Number>
/// ```
pub fn repeat(
_attr: proc_macro::TokenStream,
item: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
item
}
/// Mark a module to be analyzed for a Rust Sitter grammar. Takes a single, unnamed argument, which
/// specifies the name of the grammar. This name must be unique across all Rust Sitter grammars within
/// a compilation unit.
#[proc_macro_attribute]
pub fn grammar(
attr: proc_macro::TokenStream,
input: proc_macro::TokenStream,
) -> proc_macro::TokenStream {
let attrs: AttributeArgs = parse_macro_input!(attr);
let module: ItemMod = parse_macro_input!(input);
let expanded = expand_grammar(syn::parse_quote! {
#[rust_sitter::grammar[#(#attrs),*]]
#module
})
.map(ToTokens::into_token_stream)
.unwrap_or_else(syn::Error::into_compile_error);
proc_macro::TokenStream::from(expanded)
}
#[cfg(test)]
mod tests {
use std::fs::File;
use std::io::{Read, Write};
use std::process::Command;
use quote::ToTokens;
use syn::{parse_quote, Result};
use tempfile::tempdir;
use super::expand_grammar;
fn rustfmt_code(code: &str) -> String {
let dir = tempdir().unwrap();
let file_path = dir.path().join("temp.rs");
let mut file = File::create(file_path.clone()).unwrap();
writeln!(file, "{code}").unwrap();
drop(file);
Command::new("rustfmt")
.arg(file_path.to_str().unwrap())
.spawn()
.unwrap()
.wait()
.unwrap();
let mut file = File::open(file_path).unwrap();
let mut data = String::new();
file.read_to_string(&mut data).unwrap();
drop(file);
dir.close().unwrap();
data
}
#[test]
fn enum_transformed_fields() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
#[rust_sitter::language]
pub enum Expression {
Number(
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse::<i32>().unwrap())]
i32
),
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
#[test]
fn enum_recursive() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
#[rust_sitter::language]
pub enum Expression {
Number(
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())]
i32
),
Neg(
#[rust_sitter::leaf(text = "-")]
(),
Box<Expression>
),
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
#[test]
fn enum_prec_left() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
#[rust_sitter::language]
pub enum Expression {
Number(
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())]
i32
),
#[rust_sitter::prec_left(1)]
Sub(
Box<Expression>,
#[rust_sitter::leaf(text = "-")]
(),
Box<Expression>
),
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
#[test]
fn struct_extra() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
#[rust_sitter::language]
pub enum Expression {
Number(
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())] i32,
),
}
#[rust_sitter::extra]
struct Whitespace {
#[rust_sitter::leaf(pattern = r"\s")]
_whitespace: (),
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
#[test]
fn grammar_unboxed_field() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
#[rust_sitter::language]
pub struct Language {
e: Expression,
}
pub enum Expression {
Number(
#[rust_sitter::leaf(pattern = r"\d+", transform = |v: &str| v.parse::<i32>().unwrap())]
i32
),
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
#[test]
fn struct_repeat() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
#[rust_sitter::language]
pub struct NumberList {
numbers: Vec<Number>,
}
pub struct Number {
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())]
v: i32
}
#[rust_sitter::extra]
struct Whitespace {
#[rust_sitter::leaf(pattern = r"\s")]
_whitespace: (),
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
#[test]
fn struct_optional() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
#[rust_sitter::language]
pub struct Language {
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())]
v: Option<i32>,
t: Option<Number>,
}
pub struct Number {
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())]
v: i32
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
#[test]
fn enum_with_unamed_vector() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
pub struct Number {
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())]
value: u32
}
#[rust_sitter::language]
pub enum Expr {
Numbers(
#[rust_sitter::repeat(non_empty = true)]
Vec<Number>
)
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
#[test]
fn enum_with_named_field() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
#[rust_sitter::language]
pub enum Expr {
Number(
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())]
u32
),
Neg {
#[rust_sitter::leaf(text = "!")]
_bang: (),
value: Box<Expr>,
}
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
#[test]
fn spanned_in_vec() -> Result<()> {
insta::assert_snapshot!(rustfmt_code(
&expand_grammar(parse_quote! {
#[rust_sitter::grammar("test")]
mod grammar {
use rust_sitter::Spanned;
#[rust_sitter::language]
pub struct NumberList {
numbers: Vec<Spanned<Number>>,
}
pub struct Number {
#[rust_sitter::leaf(pattern = r"\d+", transform = |v| v.parse().unwrap())]
v: i32
}
#[rust_sitter::extra]
struct Whitespace {
#[rust_sitter::leaf(pattern = r"\s")]
_whitespace: (),
}
}
})?
.to_token_stream()
.to_string()
));
Ok(())
}
}