Prevent invalid utf8 indexing in cell magic detection (#9146)

The example below used to panic because we tried to split at 2 bytes in
the 4-bytes character `转`.
```python
def sample_func(xx):
    """
    转置 (transpose)
    """
    return xx.T
```

Fixes #9145
Fixes https://github.com/astral-sh/ruff-vscode/issues/362

The second commit is a small test refactoring.
This commit is contained in:
konsti 2023-12-15 15:15:46 +01:00 committed by GitHub
parent 3ce145c476
commit cd3c2f773f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 72 additions and 54 deletions

View file

@ -421,17 +421,18 @@ mod tests {
));
}
#[test_case(Path::new("markdown.json"), false; "markdown")]
#[test_case(Path::new("only_magic.json"), true; "only_magic")]
#[test_case(Path::new("code_and_magic.json"), true; "code_and_magic")]
#[test_case(Path::new("only_code.json"), true; "only_code")]
#[test_case(Path::new("cell_magic.json"), false; "cell_magic")]
#[test_case(Path::new("valid_cell_magic.json"), true; "valid_cell_magic")]
#[test_case(Path::new("automagic.json"), false; "automagic")]
#[test_case(Path::new("automagics.json"), false; "automagics")]
#[test_case(Path::new("automagic_before_code.json"), false; "automagic_before_code")]
#[test_case(Path::new("automagic_after_code.json"), true; "automagic_after_code")]
fn test_is_valid_code_cell(path: &Path, expected: bool) -> Result<()> {
#[test_case("markdown", false)]
#[test_case("only_magic", true)]
#[test_case("code_and_magic", true)]
#[test_case("only_code", true)]
#[test_case("cell_magic", false)]
#[test_case("valid_cell_magic", true)]
#[test_case("automagic", false)]
#[test_case("automagics", false)]
#[test_case("automagic_before_code", false)]
#[test_case("automagic_after_code", true)]
#[test_case("unicode_magic_gh9145", true)]
fn test_is_valid_code_cell(cell: &str, expected: bool) -> Result<()> {
/// Read a Jupyter cell from the `resources/test/fixtures/jupyter/cell` directory.
fn read_jupyter_cell(path: impl AsRef<Path>) -> Result<Cell> {
let path = notebook_path("cell").join(path);
@ -439,7 +440,10 @@ mod tests {
Ok(serde_json::from_str(&source_code)?)
}
assert_eq!(read_jupyter_cell(path)?.is_valid_code_cell(), expected);
assert_eq!(
read_jupyter_cell(format!("{cell}.json"))?.is_valid_code_cell(),
expected
);
Ok(())
}