mirror of
https://github.com/astral-sh/ruff.git
synced 2025-08-04 02:39:12 +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
2
.gitattributes
vendored
2
.gitattributes
vendored
|
@ -8,5 +8,7 @@ crates/ruff_linter/resources/test/fixtures/pycodestyle/W391_3.py text eol=crlf
|
|||
crates/ruff_python_formatter/resources/test/fixtures/ruff/docstring_code_examples_crlf.py text eol=crlf
|
||||
crates/ruff_python_formatter/tests/snapshots/format@docstring_code_examples_crlf.py.snap text eol=crlf
|
||||
|
||||
crates/ruff_python_parser/resources/inline linguist-generated=true
|
||||
|
||||
ruff.schema.json linguist-generated=true text=auto eol=lf
|
||||
*.md.snap linguist-language=Markdown
|
||||
|
|
219
Cargo.lock
generated
219
Cargo.lock
generated
|
@ -143,15 +143,6 @@ version = "0.7.4"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "96d30a06541fbafbc7f82ed10c06164cfbd2c401138f6addd8404629c4b16711"
|
||||
|
||||
[[package]]
|
||||
name = "ascii-canvas"
|
||||
version = "3.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8824ecca2e851cec16968d54a01dd372ef8f95b244fb84b84e70128be347c3c6"
|
||||
dependencies = [
|
||||
"term",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "autocfg"
|
||||
version = "1.1.0"
|
||||
|
@ -173,21 +164,6 @@ dependencies = [
|
|||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "bit-set"
|
||||
version = "0.5.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0700ddab506f33b20a03b13996eccd309a48e5ff77d0d95926aa0210fb4e95f1"
|
||||
dependencies = [
|
||||
"bit-vec",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "bit-vec"
|
||||
version = "0.6.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "349f9b6a179ed607305526ca489b34ad0a41aed5f7980fa90eb03160b69598fb"
|
||||
|
||||
[[package]]
|
||||
name = "bitflags"
|
||||
version = "1.3.2"
|
||||
|
@ -640,16 +616,6 @@ dependencies = [
|
|||
"dirs-sys 0.4.1",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "dirs-next"
|
||||
version = "2.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b98cf8ebf19c3d1b223e151f99a4f9f0690dca41414773390fc824184ac833e1"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"dirs-sys-next",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "dirs-sys"
|
||||
version = "0.3.7"
|
||||
|
@ -673,17 +639,6 @@ dependencies = [
|
|||
"windows-sys 0.48.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "dirs-sys-next"
|
||||
version = "0.1.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4ebda144c4fe02d1f7ea1a7d9641b6fc6b580adcfa024ae48797ecdeb6825b4d"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"redox_users",
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "drop_bomb"
|
||||
version = "0.1.5"
|
||||
|
@ -702,15 +657,6 @@ version = "1.10.0"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "11157ac094ffbdde99aa67b23417ebdd801842852b500e395a45a9c0aac03e4a"
|
||||
|
||||
[[package]]
|
||||
name = "ena"
|
||||
version = "0.14.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c533630cf40e9caa44bd91aadc88a75d75a4c3a12b4cfde353cbed41daa1e1f1"
|
||||
dependencies = [
|
||||
"log",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "encode_unicode"
|
||||
version = "0.3.6"
|
||||
|
@ -783,12 +729,6 @@ dependencies = [
|
|||
"windows-sys 0.52.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "fixedbitset"
|
||||
version = "0.4.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0ce7134b9999ecaf8bcd65542e436736ef32ddca1b3e06094cb6ec5755203b80"
|
||||
|
||||
[[package]]
|
||||
name = "flate2"
|
||||
version = "1.0.28"
|
||||
|
@ -1147,15 +1087,6 @@ dependencies = [
|
|||
"either",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "itertools"
|
||||
version = "0.11.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b1c173a5686ce8bfa551b3563d0c2170bf24ca44da99c7ca4bfdab5418c3fe57"
|
||||
dependencies = [
|
||||
"either",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "itertools"
|
||||
version = "0.12.1"
|
||||
|
@ -1206,33 +1137,6 @@ dependencies = [
|
|||
"libc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lalrpop"
|
||||
version = "0.20.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "55cb077ad656299f160924eb2912aa147d7339ea7d69e1b5517326fdcec3c1ca"
|
||||
dependencies = [
|
||||
"ascii-canvas",
|
||||
"bit-set",
|
||||
"ena",
|
||||
"itertools 0.11.0",
|
||||
"lalrpop-util",
|
||||
"petgraph",
|
||||
"regex",
|
||||
"regex-syntax 0.8.2",
|
||||
"string_cache",
|
||||
"term",
|
||||
"tiny-keccak",
|
||||
"unicode-xid",
|
||||
"walkdir",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "lalrpop-util"
|
||||
version = "0.20.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "507460a910eb7b32ee961886ff48539633b788a36b65692b95f225b844c82553"
|
||||
|
||||
[[package]]
|
||||
name = "lazy_static"
|
||||
version = "1.4.0"
|
||||
|
@ -1333,16 +1237,6 @@ version = "0.4.13"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "01cda141df6706de531b6c46c3a33ecca755538219bd484262fa09410c13539c"
|
||||
|
||||
[[package]]
|
||||
name = "lock_api"
|
||||
version = "0.4.11"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3c168f8615b12bc01f9c17e2eb0cc07dcae1940121185446edc3744920e8ef45"
|
||||
dependencies = [
|
||||
"autocfg",
|
||||
"scopeguard",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "log"
|
||||
version = "0.4.21"
|
||||
|
@ -1437,12 +1331,6 @@ version = "1.0.9"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "308d96db8debc727c3fd9744aac51751243420e46edf401010908da7f8d5e57c"
|
||||
|
||||
[[package]]
|
||||
name = "new_debug_unreachable"
|
||||
version = "1.0.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e4a24736216ec316047a1fc4252e27dabb04218aa4a3f37c6e7ddbf1f9782b54"
|
||||
|
||||
[[package]]
|
||||
name = "nix"
|
||||
version = "0.28.0"
|
||||
|
@ -1561,29 +1449,6 @@ version = "0.1.1"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b15813163c1d831bf4a13c3610c05c0d03b39feb07f7e09fa234dac9b15aaf39"
|
||||
|
||||
[[package]]
|
||||
name = "parking_lot"
|
||||
version = "0.12.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3742b2c103b9f06bc9fff0a37ff4912935851bee6d36f3c02bcc755bcfec228f"
|
||||
dependencies = [
|
||||
"lock_api",
|
||||
"parking_lot_core",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "parking_lot_core"
|
||||
version = "0.9.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4c42a9226546d68acdd9c0a280d17ce19bfe27a46bf68784e4066115788d008e"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"libc",
|
||||
"redox_syscall",
|
||||
"smallvec",
|
||||
"windows-targets 0.48.5",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "paste"
|
||||
version = "1.0.14"
|
||||
|
@ -1687,23 +1552,13 @@ version = "2.3.1"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
|
||||
|
||||
[[package]]
|
||||
name = "petgraph"
|
||||
version = "0.6.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e1d3afd2628e69da2be385eb6f2fd57c8ac7977ceeff6dc166ff1657b0e386a9"
|
||||
dependencies = [
|
||||
"fixedbitset",
|
||||
"indexmap",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "phf"
|
||||
version = "0.11.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ade2d8b8f33c7333b51bcf0428d37e217e9f32192ae4772156f65063b8ce03dc"
|
||||
dependencies = [
|
||||
"phf_shared 0.11.2",
|
||||
"phf_shared",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
@ -1713,7 +1568,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
|||
checksum = "e8d39688d359e6b34654d328e262234662d16cc0f60ec8dcbe5e718709342a5a"
|
||||
dependencies = [
|
||||
"phf_generator",
|
||||
"phf_shared 0.11.2",
|
||||
"phf_shared",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
@ -1722,19 +1577,10 @@ version = "0.11.2"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "48e4cc64c2ad9ebe670cb8fd69dd50ae301650392e81c05f9bfcb2d5bdbc24b0"
|
||||
dependencies = [
|
||||
"phf_shared 0.11.2",
|
||||
"phf_shared",
|
||||
"rand",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "phf_shared"
|
||||
version = "0.10.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b6796ad771acdc0123d2a88dc428b5e38ef24456743ddb1744ed628f9815c096"
|
||||
dependencies = [
|
||||
"siphasher",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "phf_shared"
|
||||
version = "0.11.2"
|
||||
|
@ -1773,12 +1619,6 @@ version = "0.2.17"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
|
||||
|
||||
[[package]]
|
||||
name = "precomputed-hash"
|
||||
version = "0.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
|
||||
|
||||
[[package]]
|
||||
name = "pretty_assertions"
|
||||
version = "1.4.0"
|
||||
|
@ -2336,22 +2176,24 @@ dependencies = [
|
|||
name = "ruff_python_parser"
|
||||
version = "0.0.0"
|
||||
dependencies = [
|
||||
"annotate-snippets 0.9.2",
|
||||
"anyhow",
|
||||
"bitflags 2.5.0",
|
||||
"bstr",
|
||||
"drop_bomb",
|
||||
"insta",
|
||||
"is-macro",
|
||||
"itertools 0.12.1",
|
||||
"lalrpop",
|
||||
"lalrpop-util",
|
||||
"memchr",
|
||||
"ruff_python_ast",
|
||||
"ruff_source_file",
|
||||
"ruff_text_size",
|
||||
"rustc-hash",
|
||||
"static_assertions",
|
||||
"tiny-keccak",
|
||||
"unicode-ident",
|
||||
"unicode-normalization",
|
||||
"unicode_names2",
|
||||
"walkdir",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
@ -2632,12 +2474,6 @@ version = "1.0.1"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e1cf6437eb19a8f4a6cc0f7dca544973b0b78843adbfeb3683d1a94a0024a294"
|
||||
|
||||
[[package]]
|
||||
name = "scopeguard"
|
||||
version = "1.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
|
||||
|
||||
[[package]]
|
||||
name = "seahash"
|
||||
version = "4.1.0"
|
||||
|
@ -2803,19 +2639,6 @@ version = "1.1.0"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
|
||||
|
||||
[[package]]
|
||||
name = "string_cache"
|
||||
version = "0.8.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f91138e76242f575eb1d3b38b4f1362f10d3a43f47d182a5b359af488a02293b"
|
||||
dependencies = [
|
||||
"new_debug_unreachable",
|
||||
"once_cell",
|
||||
"parking_lot",
|
||||
"phf_shared 0.10.0",
|
||||
"precomputed-hash",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "strip-ansi-escapes"
|
||||
version = "0.2.0"
|
||||
|
@ -2899,17 +2722,6 @@ dependencies = [
|
|||
"windows-sys 0.52.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "term"
|
||||
version = "0.7.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c59df8ac95d96ff9bede18eb7300b0fda5e5d8d90960e76f8e14ae765eedbf1f"
|
||||
dependencies = [
|
||||
"dirs-next",
|
||||
"rustversion",
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "terminal_size"
|
||||
version = "0.3.0"
|
||||
|
@ -3016,15 +2828,6 @@ dependencies = [
|
|||
"tikv-jemalloc-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tiny-keccak"
|
||||
version = "2.0.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2c9d3793400a45f954c52e73d068316d76b6f4e36977e3fcebb13a2721e80237"
|
||||
dependencies = [
|
||||
"crunchy",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tinytemplate"
|
||||
version = "1.2.1"
|
||||
|
@ -3245,12 +3048,6 @@ version = "0.1.11"
|
|||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e51733f11c9c4f72aa0c160008246859e340b00807569a0da0e7a1079b27ba85"
|
||||
|
||||
[[package]]
|
||||
name = "unicode-xid"
|
||||
version = "0.2.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f962df74c8c05a667b5ee8bcf162993134c104e96440b663c8daa176dc772d8c"
|
||||
|
||||
[[package]]
|
||||
name = "unicode_names2"
|
||||
version = "1.2.2"
|
||||
|
|
|
@ -52,7 +52,6 @@ is-wsl = { version = "0.4.0" }
|
|||
itertools = { version = "0.12.1" }
|
||||
js-sys = { version = "0.3.69" }
|
||||
jod-thread = { version = "0.1.2" }
|
||||
lalrpop-util = { version = "0.20.0", default-features = false }
|
||||
lexical-parse-float = { version = "0.8.0", features = ["format"] }
|
||||
libc = { version = "0.2.153" }
|
||||
libcst = { version = "1.1.0", default-features = false }
|
||||
|
|
|
@ -11,3 +11,9 @@ ned = "ned"
|
|||
pn = "pn" # `import panel as pd` is a thing
|
||||
poit = "poit"
|
||||
BA = "BA" # acronym for "Bad Allowed", used in testing.
|
||||
|
||||
[default]
|
||||
extend-ignore-re = [
|
||||
# Line ignore with trailing "spellchecker:disable-line"
|
||||
"(?Rm)^.*#\\s*spellchecker:disable-line$"
|
||||
]
|
||||
|
|
|
@ -523,7 +523,7 @@ from module import =
|
|||
----- stdout -----
|
||||
|
||||
----- stderr -----
|
||||
error: Failed to parse main.py:2:20: Unexpected token '='
|
||||
error: Failed to parse main.py:2:20: Expected an import name
|
||||
"###);
|
||||
|
||||
Ok(())
|
||||
|
|
|
@ -731,11 +731,11 @@ fn stdin_parse_error() {
|
|||
success: false
|
||||
exit_code: 1
|
||||
----- stdout -----
|
||||
-:1:17: E999 SyntaxError: Unexpected token '='
|
||||
-:1:17: E999 SyntaxError: Expected an import name
|
||||
Found 1 error.
|
||||
|
||||
----- stderr -----
|
||||
error: Failed to parse at 1:17: Unexpected token '='
|
||||
error: Failed to parse at 1:17: Expected an import name
|
||||
"###);
|
||||
}
|
||||
|
||||
|
|
|
@ -53,6 +53,7 @@ file_resolver.extend_exclude = [
|
|||
"crates/ruff/resources/",
|
||||
"crates/ruff_linter/resources/",
|
||||
"crates/ruff_python_formatter/resources/",
|
||||
"crates/ruff_python_parser/resources/",
|
||||
]
|
||||
file_resolver.force_exclude = false
|
||||
file_resolver.include = [
|
||||
|
|
|
@ -247,7 +247,7 @@ pub(crate) fn expression(expr: &Expr, checker: &mut Checker) {
|
|||
}
|
||||
}
|
||||
}
|
||||
ExprContext::Del => {}
|
||||
_ => {}
|
||||
}
|
||||
if checker.enabled(Rule::SixPY3) {
|
||||
flake8_2020::rules::name_or_attribute(checker, expr);
|
||||
|
|
|
@ -998,6 +998,7 @@ impl<'a> Visitor<'a> for Checker<'a> {
|
|||
ExprContext::Load => self.handle_node_load(expr),
|
||||
ExprContext::Store => self.handle_node_store(id, expr),
|
||||
ExprContext::Del => self.handle_node_delete(expr),
|
||||
ExprContext::Invalid => {}
|
||||
},
|
||||
_ => {}
|
||||
}
|
||||
|
|
|
@ -194,7 +194,7 @@ impl DisplayParseError {
|
|||
// Translate the byte offset to a location in the originating source.
|
||||
let location =
|
||||
if let Some(jupyter_index) = source_kind.as_ipy_notebook().map(Notebook::index) {
|
||||
let source_location = source_code.source_location(error.offset);
|
||||
let source_location = source_code.source_location(error.location.start());
|
||||
|
||||
ErrorLocation::Cell(
|
||||
jupyter_index
|
||||
|
@ -208,7 +208,7 @@ impl DisplayParseError {
|
|||
},
|
||||
)
|
||||
} else {
|
||||
ErrorLocation::File(source_code.source_location(error.offset))
|
||||
ErrorLocation::File(source_code.source_location(error.location.start()))
|
||||
};
|
||||
|
||||
Self {
|
||||
|
@ -275,27 +275,7 @@ impl<'a> DisplayParseErrorType<'a> {
|
|||
|
||||
impl Display for DisplayParseErrorType<'_> {
|
||||
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
|
||||
match self.0 {
|
||||
ParseErrorType::Eof => write!(f, "Expected token but reached end of file."),
|
||||
ParseErrorType::ExtraToken(ref tok) => write!(
|
||||
f,
|
||||
"Got extraneous token: {tok}",
|
||||
tok = TruncateAtNewline(&tok)
|
||||
),
|
||||
ParseErrorType::InvalidToken => write!(f, "Got invalid token"),
|
||||
ParseErrorType::UnrecognizedToken(ref tok, ref expected) => {
|
||||
if let Some(expected) = expected.as_ref() {
|
||||
write!(
|
||||
f,
|
||||
"Expected '{expected}', but got {tok}",
|
||||
tok = TruncateAtNewline(&tok)
|
||||
)
|
||||
} else {
|
||||
write!(f, "Unexpected token {tok}", tok = TruncateAtNewline(&tok))
|
||||
}
|
||||
}
|
||||
ParseErrorType::Lexical(ref error) => write!(f, "{error}"),
|
||||
}
|
||||
write!(f, "{}", TruncateAtNewline(&self.0))
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
@ -67,7 +67,7 @@ impl<'a> Visitor<'a> for LoadedNamesVisitor<'a> {
|
|||
Expr::Name(name) => match &name.ctx {
|
||||
ExprContext::Load => self.loaded.push(name),
|
||||
ExprContext::Store => self.stored.push(name),
|
||||
ExprContext::Del => {}
|
||||
_ => {}
|
||||
},
|
||||
_ => visitor::walk_expr(self, expr),
|
||||
}
|
||||
|
|
|
@ -14,5 +14,3 @@ bom_unsorted.py:1:1: I001 [*] Import block is un-sorted or un-formatted
|
|||
2 |-import bar
|
||||
1 |+import bar
|
||||
2 |+import foo
|
||||
|
||||
|
||||
|
|
|
@ -81,7 +81,7 @@ pub(crate) fn syntax_error(
|
|||
parse_error: &ParseError,
|
||||
locator: &Locator,
|
||||
) {
|
||||
let rest = locator.after(parse_error.offset);
|
||||
let rest = locator.after(parse_error.location.start());
|
||||
|
||||
// Try to create a non-empty range so that the diagnostic can print a caret at the
|
||||
// right position. This requires that we retrieve the next character, if any, and take its length
|
||||
|
@ -95,6 +95,6 @@ pub(crate) fn syntax_error(
|
|||
SyntaxError {
|
||||
message: format!("{}", DisplayParseErrorType::new(&parse_error.error)),
|
||||
},
|
||||
TextRange::at(parse_error.offset, len),
|
||||
TextRange::at(parse_error.location.start(), len),
|
||||
));
|
||||
}
|
||||
|
|
|
@ -1,12 +1,9 @@
|
|||
---
|
||||
source: crates/ruff_linter/src/rules/pycodestyle/mod.rs
|
||||
---
|
||||
E999.py:3:1: E999 SyntaxError: unindent does not match any outer indentation level
|
||||
E999.py:2:9: E999 SyntaxError: Expected an indented block after function definition
|
||||
|
|
||||
2 | def x():
|
||||
| ^ E999
|
||||
3 |
|
||||
| ^ E999
|
||||
4 |
|
||||
|
|
||||
|
||||
|
||||
|
|
|
@ -110,5 +110,3 @@ UP027.py:10:17: UP027 [*] Replace unpacked list comprehension with a generator e
|
|||
14 14 |
|
||||
15 15 | # Should not change
|
||||
16 16 | foo = [fn(x) for x in items]
|
||||
|
||||
|
||||
|
|
|
@ -1600,7 +1600,7 @@ mod tests {
|
|||
fn any_over_stmt_type_alias() {
|
||||
let seen = RefCell::new(Vec::new());
|
||||
let name = Expr::Name(ExprName {
|
||||
id: "x".to_string(),
|
||||
id: "x".into(),
|
||||
range: TextRange::default(),
|
||||
ctx: ExprContext::Load,
|
||||
});
|
||||
|
|
|
@ -1,6 +1,7 @@
|
|||
#![allow(clippy::derive_partial_eq_without_eq)]
|
||||
|
||||
use std::cell::OnceCell;
|
||||
|
||||
use std::fmt;
|
||||
use std::fmt::Debug;
|
||||
use std::ops::Deref;
|
||||
|
@ -947,12 +948,19 @@ impl Ranged for FStringExpressionElement {
|
|||
}
|
||||
}
|
||||
|
||||
/// An `FStringLiteralElement` with an empty `value` is an invalid f-string element.
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
pub struct FStringLiteralElement {
|
||||
pub range: TextRange,
|
||||
pub value: Box<str>,
|
||||
}
|
||||
|
||||
impl FStringLiteralElement {
|
||||
pub fn is_valid(&self) -> bool {
|
||||
!self.value.is_empty()
|
||||
}
|
||||
}
|
||||
|
||||
impl Ranged for FStringLiteralElement {
|
||||
fn range(&self) -> TextRange {
|
||||
self.range
|
||||
|
@ -1571,6 +1579,9 @@ bitflags! {
|
|||
/// for why we track the casing of the `r` prefix,
|
||||
/// but not for any other prefix
|
||||
const R_PREFIX_UPPER = 1 << 4;
|
||||
|
||||
/// The string was deemed invalid by the parser.
|
||||
const INVALID = 1 << 5;
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -1621,6 +1632,12 @@ impl StringLiteralFlags {
|
|||
}
|
||||
}
|
||||
|
||||
#[must_use]
|
||||
pub fn with_invalid(mut self) -> Self {
|
||||
self.0 |= StringLiteralFlagsInner::INVALID;
|
||||
self
|
||||
}
|
||||
|
||||
pub const fn prefix(self) -> StringLiteralPrefix {
|
||||
if self.0.contains(StringLiteralFlagsInner::U_PREFIX) {
|
||||
debug_assert!(!self.0.intersects(
|
||||
|
@ -1737,6 +1754,15 @@ impl StringLiteral {
|
|||
pub fn as_str(&self) -> &str {
|
||||
self
|
||||
}
|
||||
|
||||
/// Creates an invalid string literal with the given range.
|
||||
pub fn invalid(range: TextRange) -> Self {
|
||||
Self {
|
||||
range,
|
||||
value: "".into(),
|
||||
flags: StringLiteralFlags::default().with_invalid(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl From<StringLiteral> for Expr {
|
||||
|
@ -1952,6 +1978,9 @@ bitflags! {
|
|||
/// See https://black.readthedocs.io/en/stable/the_black_code_style/current_style.html#r-strings-and-r-strings
|
||||
/// for why we track the casing of the `r` prefix, but not for any other prefix
|
||||
const R_PREFIX_UPPER = 1 << 3;
|
||||
|
||||
/// The bytestring was deemed invalid by the parser.
|
||||
const INVALID = 1 << 4;
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -2025,6 +2054,12 @@ impl BytesLiteralFlags {
|
|||
self
|
||||
}
|
||||
|
||||
#[must_use]
|
||||
pub fn with_invalid(mut self) -> Self {
|
||||
self.0 |= BytesLiteralFlagsInner::INVALID;
|
||||
self
|
||||
}
|
||||
|
||||
pub const fn prefix(self) -> ByteStringPrefix {
|
||||
if self.0.contains(BytesLiteralFlagsInner::R_PREFIX_LOWER) {
|
||||
debug_assert!(!self.0.contains(BytesLiteralFlagsInner::R_PREFIX_UPPER));
|
||||
|
@ -2094,6 +2129,15 @@ impl BytesLiteral {
|
|||
pub fn as_slice(&self) -> &[u8] {
|
||||
self
|
||||
}
|
||||
|
||||
/// Creates a new invalid bytes literal with the given range.
|
||||
pub fn invalid(range: TextRange) -> Self {
|
||||
Self {
|
||||
range,
|
||||
value: Box::new([]),
|
||||
flags: BytesLiteralFlags::default().with_invalid(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl From<BytesLiteral> for Expr {
|
||||
|
@ -2726,6 +2770,7 @@ pub enum ExprContext {
|
|||
Load,
|
||||
Store,
|
||||
Del,
|
||||
Invalid,
|
||||
}
|
||||
|
||||
/// See also [boolop](https://docs.python.org/3/library/ast.html#ast.BoolOp)
|
||||
|
@ -3506,10 +3551,17 @@ impl IpyEscapeKind {
|
|||
}
|
||||
}
|
||||
|
||||
/// An `Identifier` with an empty `id` is invalid.
|
||||
///
|
||||
/// For example, in the following code `id` will be empty.
|
||||
/// ```python
|
||||
/// def 1():
|
||||
/// ...
|
||||
/// ```
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Hash)]
|
||||
pub struct Identifier {
|
||||
id: String,
|
||||
range: TextRange,
|
||||
pub id: String,
|
||||
pub range: TextRange,
|
||||
}
|
||||
|
||||
impl Identifier {
|
||||
|
@ -3520,6 +3572,10 @@ impl Identifier {
|
|||
range,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn is_valid(&self) -> bool {
|
||||
!self.id.is_empty()
|
||||
}
|
||||
}
|
||||
|
||||
impl Identifier {
|
||||
|
|
|
@ -71,8 +71,6 @@ for x in (y := [1, 2, 3]):
|
|||
async for x in (y := [1, 2, 3]):
|
||||
pass
|
||||
|
||||
del (x := 1)
|
||||
|
||||
try:
|
||||
pass
|
||||
except (e := Exception):
|
||||
|
|
|
@ -110,3 +110,14 @@ self.assertEqual(
|
|||
suite._tests[0].id().split(".")[0],
|
||||
os.path.basename(os.getcwd()),
|
||||
)
|
||||
|
||||
# PEP 646 introduced starred expression in indexes
|
||||
# https://peps.python.org/pep-0646/#change-1-star-expressions-in-indexes
|
||||
data[*x]
|
||||
data[*x,]
|
||||
data[
|
||||
*x,
|
||||
]
|
||||
data[ # comment 1
|
||||
*x, # comment 2
|
||||
] # comment 3
|
||||
|
|
|
@ -427,3 +427,9 @@ def function_with_one_argument_and_a_keyword_separator(
|
|||
*, argument: str
|
||||
) -> ReallyReallyReallyReallyReallyReallyReallyReallyLongName:
|
||||
pass
|
||||
|
||||
|
||||
# PEP 646 introduced type var tuple in parameter annotation
|
||||
# https://peps.python.org/pep-0646/#change-2-args-as-a-typevartuple
|
||||
def function_with_variadic_generics(*args: *tuple[int]): ...
|
||||
def function_with_variadic_generics(*args: *tuple[int],): ...
|
||||
|
|
|
@ -5,8 +5,8 @@ expression: comments.debug(test_case.source_code)
|
|||
{
|
||||
Node {
|
||||
kind: ModModule,
|
||||
range: 0..0,
|
||||
source: ``,
|
||||
range: 0..35,
|
||||
source: `⏎`,
|
||||
}: {
|
||||
"leading": [
|
||||
SourceComment {
|
||||
|
|
|
@ -1,13 +1,14 @@
|
|||
use ruff_formatter::{format_args, write, FormatRuleWithOptions};
|
||||
use ruff_formatter::{format_args, FormatRuleWithOptions};
|
||||
use ruff_python_ast::AnyNodeRef;
|
||||
use ruff_python_ast::ExprTuple;
|
||||
use ruff_text_size::Ranged;
|
||||
use ruff_text_size::{Ranged, TextRange};
|
||||
|
||||
use crate::builders::parenthesize_if_expands;
|
||||
use crate::comments::SourceComment;
|
||||
use crate::expression::parentheses::{
|
||||
empty_parenthesized, optional_parentheses, parenthesized, NeedsParentheses, OptionalParentheses,
|
||||
};
|
||||
use crate::other::commas::has_trailing_comma;
|
||||
use crate::prelude::*;
|
||||
|
||||
#[derive(Debug, Clone, Copy, Eq, PartialEq, Default)]
|
||||
|
@ -138,7 +139,27 @@ impl FormatNodeRule<ExprTuple> for FormatExprTuple {
|
|||
}
|
||||
[single] => match self.parentheses {
|
||||
TupleParentheses::Preserve if !is_parenthesized => {
|
||||
write!(f, [single.format(), token(",")])
|
||||
single.format().fmt(f)?;
|
||||
// The `TupleParentheses::Preserve` is only set by subscript expression
|
||||
// formatting. With PEP 646, a single element starred expression in the slice
|
||||
// position of a subscript expression is actually a tuple expression. For
|
||||
// example:
|
||||
//
|
||||
// ```python
|
||||
// data[*x]
|
||||
// # ^^ single element tuple expression without a trailing comma
|
||||
//
|
||||
// data[*x,]
|
||||
// # ^^^ single element tuple expression with a trailing comma
|
||||
// ```
|
||||
//
|
||||
//
|
||||
// This means that the formatter should only add a trailing comma if there is
|
||||
// one already.
|
||||
if has_trailing_comma(TextRange::new(single.end(), item.end()), f.context()) {
|
||||
token(",").fmt(f)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
_ =>
|
||||
// A single element tuple always needs parentheses and a trailing comma, except when inside of a subscript
|
||||
|
|
|
@ -135,7 +135,7 @@ pub fn format_module_source(
|
|||
let source_type = options.source_type();
|
||||
let (tokens, comment_ranges) =
|
||||
tokens_and_ranges(source, source_type).map_err(|err| ParseError {
|
||||
offset: err.location(),
|
||||
location: err.location(),
|
||||
error: ParseErrorType::Lexical(err.into_error()),
|
||||
})?;
|
||||
let module = parse_tokens(tokens, source, source_type.as_mode())?;
|
||||
|
|
|
@ -17,7 +17,7 @@ impl FormatNodeRule<ModModule> for FormatModModule {
|
|||
if body.is_empty() {
|
||||
// Only preserve an empty line if the source contains an empty line too.
|
||||
if !f.context().comments().has_leading(item)
|
||||
&& lines_after(range.end(), f.context().source()) != 0
|
||||
&& lines_after(range.start(), f.context().source()) != 0
|
||||
{
|
||||
empty_line().fmt(f)
|
||||
} else {
|
||||
|
|
|
@ -9,20 +9,23 @@ use crate::MagicTrailingComma;
|
|||
/// should be respected).
|
||||
pub(crate) fn has_magic_trailing_comma(range: TextRange, context: &PyFormatContext) -> bool {
|
||||
match context.options().magic_trailing_comma() {
|
||||
MagicTrailingComma::Respect => {
|
||||
let first_token = SimpleTokenizer::new(context.source(), range)
|
||||
.skip_trivia()
|
||||
// Skip over any closing parentheses belonging to the expression
|
||||
.find(|token| token.kind() != SimpleTokenKind::RParen);
|
||||
|
||||
matches!(
|
||||
first_token,
|
||||
Some(SimpleToken {
|
||||
kind: SimpleTokenKind::Comma,
|
||||
..
|
||||
})
|
||||
)
|
||||
}
|
||||
MagicTrailingComma::Respect => has_trailing_comma(range, context),
|
||||
MagicTrailingComma::Ignore => false,
|
||||
}
|
||||
}
|
||||
|
||||
/// Returns `true` if the range ends with a trailing comma.
|
||||
pub(crate) fn has_trailing_comma(range: TextRange, context: &PyFormatContext) -> bool {
|
||||
let first_token = SimpleTokenizer::new(context.source(), range)
|
||||
.skip_trivia()
|
||||
// Skip over any closing parentheses belonging to the expression
|
||||
.find(|token| token.kind() != SimpleTokenKind::RParen);
|
||||
|
||||
matches!(
|
||||
first_token,
|
||||
Some(SimpleToken {
|
||||
kind: SimpleTokenKind::Comma,
|
||||
..
|
||||
})
|
||||
)
|
||||
}
|
||||
|
|
|
@ -73,7 +73,7 @@ pub fn format_range(
|
|||
|
||||
let (tokens, comment_ranges) =
|
||||
tokens_and_ranges(source, options.source_type()).map_err(|err| ParseError {
|
||||
offset: err.location(),
|
||||
location: err.location(),
|
||||
error: ParseErrorType::Lexical(err.into_error()),
|
||||
})?;
|
||||
|
||||
|
|
|
@ -13,6 +13,3 @@ input_file: crates/ruff_python_formatter/resources/test/fixtures/ruff/empty_mult
|
|||
```python
|
||||
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
|
|
@ -11,6 +11,3 @@ input_file: crates/ruff_python_formatter/resources/test/fixtures/ruff/empty_trai
|
|||
```python
|
||||
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
|
|
@ -77,8 +77,6 @@ for x in (y := [1, 2, 3]):
|
|||
async for x in (y := [1, 2, 3]):
|
||||
pass
|
||||
|
||||
del (x := 1)
|
||||
|
||||
try:
|
||||
pass
|
||||
except (e := Exception):
|
||||
|
@ -180,8 +178,6 @@ for x in (y := [1, 2, 3]):
|
|||
async for x in (y := [1, 2, 3]):
|
||||
pass
|
||||
|
||||
del (x := 1)
|
||||
|
||||
try:
|
||||
pass
|
||||
except (e := Exception):
|
||||
|
@ -207,6 +203,3 @@ def f():
|
|||
async def f():
|
||||
await (x := 1)
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
|
|
@ -116,6 +116,17 @@ self.assertEqual(
|
|||
suite._tests[0].id().split(".")[0],
|
||||
os.path.basename(os.getcwd()),
|
||||
)
|
||||
|
||||
# PEP 646 introduced starred expression in indexes
|
||||
# https://peps.python.org/pep-0646/#change-1-star-expressions-in-indexes
|
||||
data[*x]
|
||||
data[*x,]
|
||||
data[
|
||||
*x,
|
||||
]
|
||||
data[ # comment 1
|
||||
*x, # comment 2
|
||||
] # comment 3
|
||||
```
|
||||
|
||||
## Output
|
||||
|
@ -231,7 +242,13 @@ self.assertEqual(
|
|||
suite._tests[0].id().split(".")[0],
|
||||
os.path.basename(os.getcwd()),
|
||||
)
|
||||
|
||||
# PEP 646 introduced starred expression in indexes
|
||||
# https://peps.python.org/pep-0646/#change-1-star-expressions-in-indexes
|
||||
data[*x]
|
||||
data[*x,]
|
||||
data[*x,]
|
||||
data[ # comment 1
|
||||
*x, # comment 2
|
||||
] # comment 3
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
|
|
@ -433,6 +433,12 @@ def function_with_one_argument_and_a_keyword_separator(
|
|||
*, argument: str
|
||||
) -> ReallyReallyReallyReallyReallyReallyReallyReallyLongName:
|
||||
pass
|
||||
|
||||
|
||||
# PEP 646 introduced type var tuple in parameter annotation
|
||||
# https://peps.python.org/pep-0646/#change-2-args-as-a-typevartuple
|
||||
def function_with_variadic_generics(*args: *tuple[int]): ...
|
||||
def function_with_variadic_generics(*args: *tuple[int],): ...
|
||||
```
|
||||
|
||||
## Output
|
||||
|
@ -1014,4 +1020,12 @@ def function_with_one_argument_and_a_keyword_separator(
|
|||
*, argument: str
|
||||
) -> ReallyReallyReallyReallyReallyReallyReallyReallyLongName:
|
||||
pass
|
||||
|
||||
|
||||
# PEP 646 introduced type var tuple in parameter annotation
|
||||
# https://peps.python.org/pep-0646/#change-2-args-as-a-typevartuple
|
||||
def function_with_variadic_generics(*args: *tuple[int]): ...
|
||||
def function_with_variadic_generics(
|
||||
*args: *tuple[int],
|
||||
): ...
|
||||
```
|
||||
|
|
54
crates/ruff_python_parser/CONTRIBUTING.md
Normal file
54
crates/ruff_python_parser/CONTRIBUTING.md
Normal file
|
@ -0,0 +1,54 @@
|
|||
# Contributing to the Python Parser
|
||||
|
||||
## Development
|
||||
|
||||
### Inline tests
|
||||
|
||||
The parser crate supports writing inline tests. These are tests that are written
|
||||
in the source code itself, and are extracted to a separate file and run with the
|
||||
test suite. They are written in the form of comments with a specific format. There
|
||||
are two forms of inline tests:
|
||||
|
||||
Test that the parser successfully parses the input with no syntax errors. They're
|
||||
written in the following format:
|
||||
|
||||
```rs
|
||||
// test_ok this_is_the_test_name
|
||||
// def foo():
|
||||
// pass
|
||||
println!("some rust code");
|
||||
```
|
||||
|
||||
Test that the parser fails to parse the input with a syntax error. They're written
|
||||
in the following format:
|
||||
|
||||
```rs
|
||||
// test_err this_is_the_test_name
|
||||
// [1, 2
|
||||
println!("some rust code");
|
||||
```
|
||||
|
||||
Note that the difference between the two is the `test_ok` and `test_err` keywords.
|
||||
The comment block must be independent of any other comment blocks. For example, the
|
||||
following is not extracted:
|
||||
|
||||
```rs
|
||||
// Some random comment
|
||||
//
|
||||
// test_ok this_is_the_test_name
|
||||
// def foo():
|
||||
// pass
|
||||
println!("some rust code");
|
||||
```
|
||||
|
||||
To generate the corresponding Python files for the inline tests, run the following command:
|
||||
|
||||
```sh
|
||||
cargo test --package ruff_python_parser --test generate_inline_tests
|
||||
```
|
||||
|
||||
Then, run the Parser test suite with the following command:
|
||||
|
||||
```sh
|
||||
cargo test --package ruff_python_parser
|
||||
```
|
|
@ -9,7 +9,6 @@ homepage = { workspace = true }
|
|||
documentation = { workspace = true }
|
||||
repository = { workspace = true }
|
||||
license = { workspace = true }
|
||||
build = "build.rs"
|
||||
|
||||
[lib]
|
||||
|
||||
|
@ -18,10 +17,11 @@ ruff_python_ast = { path = "../ruff_python_ast" }
|
|||
ruff_text_size = { path = "../ruff_text_size" }
|
||||
|
||||
anyhow = { workspace = true }
|
||||
bitflags = { workspace = true }
|
||||
drop_bomb = { workspace = true }
|
||||
bstr = { workspace = true }
|
||||
is-macro = { workspace = true }
|
||||
itertools = { workspace = true }
|
||||
lalrpop-util = { workspace = true, default-features = false }
|
||||
memchr = { workspace = true }
|
||||
rustc-hash = { workspace = true }
|
||||
static_assertions = { workspace = true }
|
||||
|
@ -30,12 +30,11 @@ unicode_names2 = { workspace = true }
|
|||
unicode-normalization = { workspace = true }
|
||||
|
||||
[dev-dependencies]
|
||||
insta = { workspace = true }
|
||||
ruff_source_file = { path = "../ruff_source_file" }
|
||||
|
||||
[build-dependencies]
|
||||
anyhow = { workspace = true }
|
||||
lalrpop = { version = "0.20.0", default-features = false, optional = true }
|
||||
tiny-keccak = { version = "2", features = ["sha3"] }
|
||||
annotate-snippets = { workspace = true }
|
||||
insta = { workspace = true, features = ["glob"] }
|
||||
walkdir = { workspace = true }
|
||||
|
||||
[lints]
|
||||
workspace = true
|
||||
|
|
|
@ -1,112 +0,0 @@
|
|||
use std::fmt::Write as _;
|
||||
use std::fs::File;
|
||||
use std::io::{BufRead, BufReader};
|
||||
use std::path::{Path, PathBuf};
|
||||
use tiny_keccak::{Hasher, Sha3};
|
||||
|
||||
fn main() {
|
||||
const SOURCE: &str = "src/python.lalrpop";
|
||||
println!("cargo:rerun-if-changed={SOURCE}");
|
||||
|
||||
let target;
|
||||
let error;
|
||||
|
||||
#[cfg(feature = "lalrpop")]
|
||||
{
|
||||
let out_dir = PathBuf::from(std::env::var_os("OUT_DIR").unwrap());
|
||||
target = out_dir.join("src/python.rs");
|
||||
}
|
||||
#[cfg(not(feature = "lalrpop"))]
|
||||
{
|
||||
target = PathBuf::from("src/python.rs");
|
||||
error = "python.lalrpop and src/python.rs doesn't match. This is a ruff_python_parser bug. Please report it unless you are editing ruff_python_parser. Run `lalrpop src/python.lalrpop` to build ruff_python_parser again.";
|
||||
}
|
||||
|
||||
let Some(message) = requires_lalrpop(SOURCE, &target) else {
|
||||
return;
|
||||
};
|
||||
|
||||
#[cfg(feature = "lalrpop")]
|
||||
{
|
||||
let Err(e) = try_lalrpop() else {
|
||||
return;
|
||||
};
|
||||
error = e;
|
||||
}
|
||||
|
||||
println!("cargo:warning={message}");
|
||||
panic!("running lalrpop failed. {error:?}");
|
||||
}
|
||||
|
||||
fn requires_lalrpop(source: &str, target: &Path) -> Option<String> {
|
||||
let Ok(target) = File::open(target) else {
|
||||
return Some("python.rs doesn't exist. regenerate.".to_owned());
|
||||
};
|
||||
|
||||
let sha_prefix = "// sha3: ";
|
||||
let Some(sha3_line) = BufReader::with_capacity(128, target)
|
||||
.lines()
|
||||
.find_map(|line| {
|
||||
let line = line.unwrap();
|
||||
line.starts_with(sha_prefix).then_some(line)
|
||||
})
|
||||
else {
|
||||
// no sha3 line - maybe old version of lalrpop installed
|
||||
return Some("python.rs doesn't include sha3 hash. regenerate.".to_owned());
|
||||
};
|
||||
let expected_sha3_str = sha3_line.strip_prefix(sha_prefix).unwrap();
|
||||
|
||||
let actual_sha3 = {
|
||||
let mut hasher = Sha3::v256();
|
||||
let mut f = BufReader::new(File::open(source).unwrap());
|
||||
let mut line = String::new();
|
||||
while f.read_line(&mut line).unwrap() != 0 {
|
||||
if line.ends_with('\n') {
|
||||
line.pop();
|
||||
if line.ends_with('\r') {
|
||||
line.pop();
|
||||
}
|
||||
}
|
||||
hasher.update(line.as_bytes());
|
||||
hasher.update(b"\n");
|
||||
line.clear();
|
||||
}
|
||||
let mut hash = [0u8; 32];
|
||||
hasher.finalize(&mut hash);
|
||||
hash
|
||||
};
|
||||
let eq = sha_equal(expected_sha3_str, &actual_sha3);
|
||||
if !eq {
|
||||
let mut actual_sha3_str = String::new();
|
||||
for byte in actual_sha3 {
|
||||
write!(actual_sha3_str, "{byte:02x}").unwrap();
|
||||
}
|
||||
return Some(format!(
|
||||
"python.rs hash expected: {expected_sha3_str} but actual: {actual_sha3_str}"
|
||||
));
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
#[cfg(feature = "lalrpop")]
|
||||
fn try_lalrpop() -> Result<(), Box<dyn std::error::Error>> {
|
||||
// We are not using lalrpop::process_root() or Configuration::process_current_dir()
|
||||
// because of https://github.com/lalrpop/lalrpop/issues/699.
|
||||
lalrpop::Configuration::new()
|
||||
.use_cargo_dir_conventions()
|
||||
.set_in_dir(Path::new("."))
|
||||
.process()
|
||||
}
|
||||
|
||||
fn sha_equal(expected_sha3_str: &str, actual_sha3: &[u8; 32]) -> bool {
|
||||
assert!(
|
||||
expected_sha3_str.len() == 64,
|
||||
"lalrpop version? hash bug is fixed in 0.19.8"
|
||||
);
|
||||
|
||||
let mut expected_sha3 = [0u8; 32];
|
||||
for (i, b) in expected_sha3.iter_mut().enumerate() {
|
||||
*b = u8::from_str_radix(&expected_sha3_str[i * 2..][..2], 16).unwrap();
|
||||
}
|
||||
*actual_sha3 == expected_sha3
|
||||
}
|
6
crates/ruff_python_parser/resources/.editorconfig
Normal file
6
crates/ruff_python_parser/resources/.editorconfig
Normal file
|
@ -0,0 +1,6 @@
|
|||
# Check http://editorconfig.org for more information
|
||||
# This is the main config file for this project:
|
||||
root = true
|
||||
|
||||
[*.py]
|
||||
insert_final_newline = false
|
|
@ -0,0 +1,4 @@
|
|||
x: *int = 1
|
||||
x: yield a = 1
|
||||
x: yield from b = 1
|
||||
x: y := int = 1
|
|
@ -0,0 +1,10 @@
|
|||
"abc": str = "def"
|
||||
call(): str = "no"
|
||||
*x: int = 1, 2
|
||||
# Tuple assignment
|
||||
x,: int = 1
|
||||
x, y: int = 1, 2
|
||||
(x, y): int = 1, 2
|
||||
# List assignment
|
||||
[x]: int = 1
|
||||
[x, y]: int = 1, 2
|
|
@ -0,0 +1,3 @@
|
|||
x: Any = *a and b
|
||||
x: Any = x := 1
|
||||
x: list = [x, *a | b, *a or b]
|
|
@ -0,0 +1 @@
|
|||
x: int =
|
|
@ -0,0 +1,2 @@
|
|||
a: type X = int
|
||||
lambda: type X = int
|
|
@ -0,0 +1 @@
|
|||
assert x,
|
|
@ -0,0 +1 @@
|
|||
assert
|
|
@ -0,0 +1,4 @@
|
|||
assert False, *x
|
||||
assert False, assert x
|
||||
assert False, yield x
|
||||
assert False, x := 1
|
|
@ -0,0 +1,4 @@
|
|||
assert *x
|
||||
assert assert x
|
||||
assert yield x
|
||||
assert x := 1
|
|
@ -0,0 +1,4 @@
|
|||
1 = 1
|
||||
x = 1 = 2
|
||||
x = 1 = y = 2 = z
|
||||
["a", "b"] = ["a", "b"]
|
|
@ -0,0 +1,5 @@
|
|||
x = *a and b
|
||||
x = *yield x
|
||||
x = *yield from x
|
||||
x = *lambda x: x
|
||||
x = x := 1
|
|
@ -0,0 +1,4 @@
|
|||
a = pass = c
|
||||
a + b
|
||||
a = b = pass = c
|
||||
a + b
|
|
@ -0,0 +1,6 @@
|
|||
x =
|
||||
1 + 1
|
||||
x = y =
|
||||
2 + 2
|
||||
x = = y
|
||||
3 + 3
|
|
@ -0,0 +1,8 @@
|
|||
async class Foo: ...
|
||||
async while test: ...
|
||||
async x = 1
|
||||
async async def foo(): ...
|
||||
# TODO(dhruvmanila): Here, `match` is actually a Name token because
|
||||
# of the soft keyword # transformer
|
||||
async match test:
|
||||
case _: ...
|
|
@ -0,0 +1,6 @@
|
|||
1 += 1
|
||||
"a" += "b"
|
||||
*x += 1
|
||||
pass += 1
|
||||
x += pass
|
||||
(x + y) += 1
|
|
@ -0,0 +1,5 @@
|
|||
x += *a and b
|
||||
x += *yield x
|
||||
x += *yield from x
|
||||
x += *lambda x: x
|
||||
x += y := 1
|
|
@ -0,0 +1,4 @@
|
|||
x +=
|
||||
1 + 1
|
||||
x += y +=
|
||||
2 + 2
|
|
@ -0,0 +1,3 @@
|
|||
class Foo:
|
||||
class Foo():
|
||||
x = 42
|
|
@ -0,0 +1,3 @@
|
|||
class : ...
|
||||
class (): ...
|
||||
class (metaclass=ABC): ...
|
|
@ -0,0 +1,3 @@
|
|||
class Foo[T1, *T2(a, b):
|
||||
pass
|
||||
x = 10
|
|
@ -0,0 +1,6 @@
|
|||
# Here, the error is highlighted at the `pass` token
|
||||
if True:
|
||||
pass
|
||||
# The parser is at the end of the program, so let's highlight
|
||||
# at the newline token after `:`
|
||||
if True:
|
|
@ -0,0 +1 @@
|
|||
if True: if True: pass
|
|
@ -0,0 +1,2 @@
|
|||
(async)
|
||||
(x async x in iter)
|
|
@ -0,0 +1,6 @@
|
|||
@*x
|
||||
@(*x)
|
||||
@((*x))
|
||||
@yield x
|
||||
@yield from x
|
||||
def foo(): ...
|
|
@ -0,0 +1,5 @@
|
|||
@def foo(): ...
|
||||
@
|
||||
def foo(): ...
|
||||
@@
|
||||
def foo(): ...
|
|
@ -0,0 +1,3 @@
|
|||
@x def foo(): ...
|
||||
@x async def foo(): ...
|
||||
@x class Foo: ...
|
|
@ -0,0 +1,4 @@
|
|||
@foo
|
||||
async with x: ...
|
||||
@foo
|
||||
x = 1
|
|
@ -0,0 +1,4 @@
|
|||
del x, y.
|
||||
z
|
||||
del x, y[
|
||||
z
|
|
@ -0,0 +1 @@
|
|||
del
|
|
@ -0,0 +1,2 @@
|
|||
import a..b
|
||||
import a...b
|
|
@ -0,0 +1,8 @@
|
|||
try:
|
||||
pass
|
||||
except yield x:
|
||||
pass
|
||||
try:
|
||||
pass
|
||||
except* *x:
|
||||
pass
|
|
@ -0,0 +1,6 @@
|
|||
try:
|
||||
pass
|
||||
except Exception as:
|
||||
pass
|
||||
except Exception as
|
||||
pass
|
|
@ -0,0 +1,13 @@
|
|||
try:
|
||||
pass
|
||||
except as exc:
|
||||
pass
|
||||
# If a '*' is present then exception type is required
|
||||
try:
|
||||
pass
|
||||
except*:
|
||||
pass
|
||||
except*
|
||||
pass
|
||||
except* as exc:
|
||||
pass
|
|
@ -0,0 +1,4 @@
|
|||
try:
|
||||
pass
|
||||
except as:
|
||||
pass
|
|
@ -0,0 +1,12 @@
|
|||
try:
|
||||
pass
|
||||
except x, y:
|
||||
pass
|
||||
except x, y as exc:
|
||||
pass
|
||||
try:
|
||||
pass
|
||||
except* x, y:
|
||||
pass
|
||||
except* x, y as eg:
|
||||
pass
|
|
@ -0,0 +1,2 @@
|
|||
f"{}"
|
||||
f"{ }"
|
|
@ -0,0 +1 @@
|
|||
f"{x!z}"
|
|
@ -0,0 +1,2 @@
|
|||
f"{x!123}"
|
||||
f"{x!'a'}"
|
|
@ -0,0 +1,4 @@
|
|||
# Starred expression inside f-string has a minimum precedence of bitwise or.
|
||||
f"{*}"
|
||||
f"{*x and y}"
|
||||
f"{*yield x}"
|
|
@ -0,0 +1 @@
|
|||
f"{lambda x: x}"
|
|
@ -0,0 +1,5 @@
|
|||
f"{"
|
||||
f"{foo!r"
|
||||
f"{foo="
|
||||
f"{"
|
||||
f"""{"""
|
|
@ -0,0 +1,2 @@
|
|||
f"hello {x:"
|
||||
f"hello {x:.3f"
|
|
@ -0,0 +1,3 @@
|
|||
for x in *a and b: ...
|
||||
for x in yield a: ...
|
||||
for target in x := 1: ...
|
|
@ -0,0 +1,6 @@
|
|||
for 1 in x: ...
|
||||
for "a" in x: ...
|
||||
for *x and y in z: ...
|
||||
for *x | y in z: ...
|
||||
for await x in z: ...
|
||||
for [x, 1, y, *["a"]] in z: ...
|
|
@ -0,0 +1,2 @@
|
|||
for a b: ...
|
||||
for a: ...
|
|
@ -0,0 +1,2 @@
|
|||
for x in:
|
||||
a = 1
|
|
@ -0,0 +1 @@
|
|||
for in x: ...
|
|
@ -0,0 +1,3 @@
|
|||
from x import a.
|
||||
from x import a.b
|
||||
from x import a, b.c, d, e.f, g
|
|
@ -0,0 +1,3 @@
|
|||
from x import
|
||||
from x import ()
|
||||
from x import ,,
|
|
@ -0,0 +1,2 @@
|
|||
from
|
||||
from import x
|
|
@ -0,0 +1,4 @@
|
|||
from x import (a, b
|
||||
1 + 1
|
||||
from x import (a, b,
|
||||
2 + 2
|
|
@ -0,0 +1,4 @@
|
|||
from x import *, a
|
||||
from x import a, *, b
|
||||
from x import *, a as b
|
||||
from x import *, *, a
|
|
@ -0,0 +1,3 @@
|
|||
from a import b,
|
||||
from a import b as c,
|
||||
from a import b, c,
|
|
@ -0,0 +1,3 @@
|
|||
def foo():
|
||||
def foo() -> int:
|
||||
x = 42
|
|
@ -0,0 +1,3 @@
|
|||
def foo() -> *int: ...
|
||||
def foo() -> (*int): ...
|
||||
def foo() -> yield x: ...
|
|
@ -0,0 +1,2 @@
|
|||
def (): ...
|
||||
def () -> int: ...
|
|
@ -0,0 +1 @@
|
|||
def foo() -> : ...
|
|
@ -0,0 +1,5 @@
|
|||
def foo(a: int, b:
|
||||
def foo():
|
||||
return 42
|
||||
def foo(a: int, b: str
|
||||
x = 10
|
|
@ -0,0 +1,3 @@
|
|||
def foo[T1, *T2(a, b):
|
||||
return a + b
|
||||
x = 10
|
|
@ -0,0 +1,2 @@
|
|||
def foo() -> int,: ...
|
||||
def foo() -> int, str: ...
|
|
@ -0,0 +1 @@
|
|||
global
|
|
@ -0,0 +1 @@
|
|||
global x + 1
|
|
@ -0,0 +1,3 @@
|
|||
global ,
|
||||
global x,
|
||||
global x, y,
|
|
@ -0,0 +1,6 @@
|
|||
if x:
|
||||
pass
|
||||
elif y
|
||||
pass
|
||||
else:
|
||||
pass
|
|
@ -0,0 +1,2 @@
|
|||
if True:
|
||||
1 + 1
|
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Add a link
Reference in a new issue