Skip to content

Fix inconsistencies with cpython while parsing format strings #124

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 31, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
73 changes: 65 additions & 8 deletions format/src/format.rs
Original file line number Diff line number Diff line change
Expand Up @@ -863,17 +863,46 @@ impl FormatString {
}

fn parse_part_in_brackets(text: &str) -> Result<FormatPart, FormatParseError> {
let parts: Vec<&str> = text.splitn(2, ':').collect();
let mut chars = text.chars().peekable();

let mut left = String::new();
let mut right = String::new();

let mut split = false;
let mut selected = &mut left;
let mut inside_brackets = false;

while let Some(char) = chars.next() {
if char == '[' {
inside_brackets = true;

selected.push(char);

while let Some(next_char) = chars.next() {
selected.push(next_char);

if next_char == ']' {
inside_brackets = false;
break;
}
if chars.peek().is_none() {
return Err(FormatParseError::MissingRightBracket);
}
}
} else if char == ':' && !split && !inside_brackets {
split = true;
selected = &mut right;
} else {
selected.push(char);
}
}

// before the comma is a keyword or arg index, after the comma is maybe a spec.
let arg_part = parts[0];
let arg_part: &str = &left;

let format_spec = if parts.len() > 1 {
parts[1].to_owned()
} else {
String::new()
};
let format_spec = if split { right } else { String::new() };

// On parts[0] can still be the conversion (!r, !s, !a)
// left can still be the conversion (!r, !s, !a)
let parts: Vec<&str> = arg_part.splitn(2, '!').collect();
// before the bang is a keyword or arg index, after the comma is maybe a conversion spec.
let arg_part = parts[0];
Expand Down Expand Up @@ -1168,6 +1197,34 @@ mod tests {
);
}

#[test]
fn test_square_brackets_inside_format() {
assert_eq!(
FormatString::from_str("{[:123]}"),
Ok(FormatString {
format_parts: vec![FormatPart::Field {
field_name: "[:123]".to_owned(),
conversion_spec: None,
format_spec: "".to_owned(),
}],
}),
);

assert_eq!(FormatString::from_str("{asdf[:123]asdf}"), {
Ok(FormatString {
format_parts: vec![FormatPart::Field {
field_name: "asdf[:123]asdf".to_owned(),
conversion_spec: None,
format_spec: "".to_owned(),
}],
})
});

assert_eq!(FormatString::from_str("{[1234}"), {
Err(FormatParseError::MissingRightBracket)
});
}

#[test]
fn test_format_parse_escape() {
let expected = Ok(FormatString {
Expand Down
Loading