Improve ruff_parse_simple to find UTF-8 violations (#5008)

Improves the `ruff_parse_simple` fuzz harness by adding checks for
parsed locations to ensure they all lie on UTF-8 character boundaries.
This will allow for faster identification of issues like #5004.

This also adds additional details for Apple M1 users and clarifies the
importance of using `init-fuzzer.sh` (thanks for the feedback,
@jasikpark 🙂).
This commit is contained in:
Addison Crump 2023-06-12 18:10:23 +02:00 committed by GitHub
parent 9db622afe1
commit 70e6c212d9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 57 additions and 1976 deletions

View file

@ -1,2 +1,3 @@
pub use crate::node::AstNode;
pub use rustpython_ast::*;
pub use rustpython_parser::*;

View file

@ -183,7 +183,7 @@ impl<'a> Generator<'a> {
self.buffer
}
pub(crate) fn unparse_suite<U>(&mut self, suite: &Suite<U>) {
pub fn unparse_suite<U>(&mut self, suite: &Suite<U>) {
for stmt in suite {
self.unparse_stmt(stmt);
}