mirror of
https://github.com/astral-sh/ruff.git
synced 2025-08-18 09:30:35 +00:00
Replace LALRPOP parser with hand-written parser (#10036)
(Supersedes #9152, authored by @LaBatata101) ## Summary This PR replaces the current parser generated from LALRPOP to a hand-written recursive descent parser. It also updates the grammar for [PEP 646](https://peps.python.org/pep-0646/) so that the parser outputs the correct AST. For example, in `data[*x]`, the index expression is now a tuple with a single starred expression instead of just a starred expression. Beyond the performance improvements, the parser is also error resilient and can provide better error messages. The behavior as seen by any downstream tools isn't changed. That is, the linter and formatter can still assume that the parser will _stop_ at the first syntax error. This will be updated in the following months. For more details about the change here, refer to the PR corresponding to the individual commits and the release blog post. ## Test Plan Write _lots_ and _lots_ of tests for both valid and invalid syntax and verify the output. ## Acknowledgements - @MichaReiser for reviewing 100+ parser PRs and continuously providing guidance throughout the project - @LaBatata101 for initiating the transition to a hand-written parser in #9152 - @addisoncrump for implementing the fuzzer which helped [catch](https://github.com/astral-sh/ruff/pull/10903) [a](https://github.com/astral-sh/ruff/pull/10910) [lot](https://github.com/astral-sh/ruff/pull/10966) [of](https://github.com/astral-sh/ruff/pull/10896) [bugs](https://github.com/astral-sh/ruff/pull/10877) --------- Co-authored-by: Victor Hugo Gomes <labatata101@linuxmail.org> Co-authored-by: Micha Reiser <micha@reiser.io>
This commit is contained in:
parent
e09180b1df
commit
13ffb5bc19
852 changed files with 112948 additions and 103620 deletions
152
crates/ruff_python_parser/src/parser/tests.rs
Normal file
152
crates/ruff_python_parser/src/parser/tests.rs
Normal file
|
@ -0,0 +1,152 @@
|
|||
use crate::{lex, parse, parse_expression, parse_suite, parse_tokens, Mode};
|
||||
|
||||
#[test]
|
||||
fn test_modes() {
|
||||
let source = "a[0][1][2][3][4]";
|
||||
|
||||
assert!(parse(source, Mode::Expression).is_ok());
|
||||
assert!(parse(source, Mode::Module).is_ok());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_expr_mode_invalid_syntax1() {
|
||||
let source = "first second";
|
||||
let error = parse_expression(source).unwrap_err();
|
||||
|
||||
insta::assert_debug_snapshot!(error);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_expr_mode_invalid_syntax2() {
|
||||
let source = r"first
|
||||
|
||||
second
|
||||
";
|
||||
let error = parse_expression(source).unwrap_err();
|
||||
|
||||
insta::assert_debug_snapshot!(error);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_expr_mode_invalid_syntax3() {
|
||||
let source = r"first
|
||||
|
||||
second
|
||||
|
||||
third
|
||||
";
|
||||
let error = parse_expression(source).unwrap_err();
|
||||
|
||||
insta::assert_debug_snapshot!(error);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_expr_mode_valid_syntax() {
|
||||
let source = "first
|
||||
|
||||
";
|
||||
let expr = parse_expression(source).unwrap();
|
||||
|
||||
insta::assert_debug_snapshot!(expr);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_unicode_aliases() {
|
||||
// https://github.com/RustPython/RustPython/issues/4566
|
||||
let source = r#"x = "\N{BACKSPACE}another cool trick""#;
|
||||
let parse_ast = parse_suite(source).unwrap();
|
||||
|
||||
insta::assert_debug_snapshot!(parse_ast);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_ipython_escape_commands() {
|
||||
let parse_ast = parse(
|
||||
r"
|
||||
# Normal Python code
|
||||
(
|
||||
a
|
||||
%
|
||||
b
|
||||
)
|
||||
|
||||
# Dynamic object info
|
||||
??a.foo
|
||||
?a.foo
|
||||
?a.foo?
|
||||
??a.foo()??
|
||||
|
||||
# Line magic
|
||||
%timeit a = b
|
||||
%timeit foo(b) % 3
|
||||
%alias showPath pwd && ls -a
|
||||
%timeit a =\
|
||||
foo(b); b = 2
|
||||
%matplotlib --inline
|
||||
%matplotlib \
|
||||
--inline
|
||||
|
||||
# System shell access
|
||||
!pwd && ls -a | sed 's/^/\ /'
|
||||
!pwd \
|
||||
&& ls -a | sed 's/^/\\ /'
|
||||
!!cd /Users/foo/Library/Application\ Support/
|
||||
|
||||
# Let's add some Python code to make sure that earlier escapes were handled
|
||||
# correctly and that we didn't consume any of the following code as a result
|
||||
# of the escapes.
|
||||
def foo():
|
||||
return (
|
||||
a
|
||||
!=
|
||||
b
|
||||
)
|
||||
|
||||
# Transforms into `foo(..)`
|
||||
/foo 1 2
|
||||
;foo 1 2
|
||||
,foo 1 2
|
||||
|
||||
# Indented escape commands
|
||||
for a in range(5):
|
||||
!ls
|
||||
|
||||
p1 = !pwd
|
||||
p2: str = !pwd
|
||||
foo = %foo \
|
||||
bar
|
||||
|
||||
% foo
|
||||
foo = %foo # comment
|
||||
|
||||
# Help end line magics
|
||||
foo?
|
||||
foo.bar??
|
||||
foo.bar.baz?
|
||||
foo[0]??
|
||||
foo[0][1]?
|
||||
foo.bar[0].baz[1]??
|
||||
foo.bar[0].baz[2].egg??
|
||||
"
|
||||
.trim(),
|
||||
Mode::Ipython,
|
||||
)
|
||||
.unwrap();
|
||||
insta::assert_debug_snapshot!(parse_ast);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_ipython_escape_command_parse_error() {
|
||||
let source = r"
|
||||
a = 1
|
||||
%timeit a == 1
|
||||
"
|
||||
.trim();
|
||||
let lxr = lex(source, Mode::Ipython);
|
||||
let parse_err = parse_tokens(lxr.collect(), source, Mode::Module).unwrap_err();
|
||||
assert_eq!(
|
||||
parse_err.to_string(),
|
||||
"IPython escape commands are only allowed in `Mode::Ipython` at byte range 6..20"
|
||||
.to_string()
|
||||
);
|
||||
}
|
Loading…
Add table
Add a link
Reference in a new issue