mirror of
https://github.com/astral-sh/ruff.git
synced 2025-07-23 21:15:19 +00:00
550b643e33
* Add script for ecosystem wide checks of all rules and fixes This adds my personal script for checking an entire checkout of ~2.1k packages for panics, autofix errors and similar problems. It's not really meant to be used by anybody else but i thought it's better if it lives in the repo than if it doesn't. For reference, this is the current output of failing autofixes: https://gist.github.com/konstin/c3fada0135af6cacec74f166adf87a00. Trimmed down to the useful information: https://gist.github.com/konstin/c864f4c300c7903a24fdda49635c5da9 * Keep github template intact * Remove the need for ripgrep * sort output
62 lines
2.2 KiB
Python
62 lines
2.2 KiB
Python
"""Generate the confusables.rs file from the VS Code ambiguous.json file."""
|
|
import json
|
|
import subprocess
|
|
from pathlib import Path
|
|
|
|
CONFUSABLES_RS_PATH = "crates/ruff/src/rules/ruff/rules/confusables.rs"
|
|
AMBIGUOUS_JSON_URL = "https://raw.githubusercontent.com/hediet/vscode-unicode-data/main/out/ambiguous.json"
|
|
|
|
|
|
def get_mapping_data() -> dict:
|
|
"""
|
|
Get the ambiguous character mapping data from the vscode-unicode-data repository.
|
|
|
|
Uses the system's `curl` command to download the data,
|
|
instead of adding a dependency to a Python-native HTTP client.
|
|
"""
|
|
content = subprocess.check_output(
|
|
["curl", "-sSL", AMBIGUOUS_JSON_URL],
|
|
encoding="utf-8",
|
|
)
|
|
# The content is a JSON object literal wrapped in a JSON string, so double decode:
|
|
return json.loads(json.loads(content))
|
|
|
|
|
|
def format_confusables_rs(raw_data: dict) -> str:
|
|
"""Format the downloaded data into a Rust source file."""
|
|
prelude = """
|
|
/// This file is auto-generated by scripts/update_ambiguous_characters.py.
|
|
|
|
use once_cell::sync::Lazy;
|
|
use rustc_hash::FxHashMap;
|
|
|
|
/// Via: <https://github.com/hediet/vscode-unicode-data/blob/main/out/ambiguous.json>
|
|
/// See: <https://github.com/microsoft/vscode/blob/095ddabc52b82498ee7f718a34f9dd11d59099a8/src/vs/base/common/strings.ts#L1094>
|
|
pub(crate) static CONFUSABLES: Lazy<FxHashMap<u32, u8>> = Lazy::new(|| {
|
|
#[allow(clippy::unreadable_literal)]
|
|
FxHashMap::from_iter([
|
|
""".lstrip()
|
|
tuples = []
|
|
for _category, items in raw_data.items():
|
|
for i in range(0, len(items), 2):
|
|
tuples.append(f"({items[i]}, {items[i + 1]}),")
|
|
postlude = """])});"""
|
|
|
|
print(f"{len(tuples)} confusable tuples.")
|
|
|
|
return prelude + "\n".join(tuples) + postlude
|
|
|
|
|
|
def main() -> None:
|
|
print("Retrieving data...")
|
|
mapping_data = get_mapping_data()
|
|
formatted_data = format_confusables_rs(mapping_data)
|
|
confusables_path = Path(__file__).parent.parent / CONFUSABLES_RS_PATH
|
|
confusables_path.write_text(formatted_data, encoding="utf-8")
|
|
print("Formatting Rust file with cargo fmt...")
|
|
subprocess.check_call(["cargo", "fmt", "--", confusables_path])
|
|
print("Done.")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|