squawk-lexer 2.45.0

use std::str::Chars;

/// Peekable iterator over a char sequence.
///
/// Next characters can be peeked via `first` method,
/// and position can be shifted forward via `bump` method.
/// based on:
/// - <https://github.com/rust-lang/rust/blob/d1b7355d3d7b4ead564dbecb1d240fcc74fff21b/compiler/rustc_lexer/src/cursor.rs>
/// - <https://github.com/astral-sh/ruff/blob/d1079680bb29f6b797b5df15327195300f635f3c/crates/ruff_python_parser/src/lexer/cursor.rs>
///
pub(crate) struct Cursor<'a> {
    /// Iterator over chars. Slightly faster than a &str.
    chars: Chars<'a>,
    len_remaining: usize,
}

pub(crate) const EOF_CHAR: char = '\0';

impl<'a> Cursor<'a> {
    pub(crate) fn new(input: &'a str) -> Cursor<'a> {
        Cursor {
            len_remaining: input.len(),
            chars: input.chars(),
        }
    }

    /// Peeks the next symbol from the input stream without consuming it.
    /// If requested position doesn't exist, `EOF_CHAR` is returned.
    /// However, getting `EOF_CHAR` doesn't always mean actual end of file,
    /// it should be checked with `is_eof` method.
    pub(crate) fn first(&self) -> char {
        // `.next()` optimizes better than `.nth(0)`
        self.chars.clone().next().unwrap_or(EOF_CHAR)
    }

    /// Checks if there is nothing more to consume.
    pub(crate) fn is_eof(&self) -> bool {
        self.chars.as_str().is_empty()
    }

    /// Returns amount of already consumed symbols.
    pub(crate) fn pos_within_token(&self) -> u32 {
        (self.len_remaining - self.chars.as_str().len()) as u32
    }

    /// Resets the number of bytes consumed to 0.
    pub(crate) fn reset_pos_within_token(&mut self) {
        self.len_remaining = self.chars.as_str().len();
    }

    /// Moves to the next character.
    pub(crate) fn bump(&mut self) -> Option<char> {
        let c = self.chars.next()?;
        Some(c)
    }

    /// Eats symbols while predicate returns true or until the end of file is reached.
    pub(crate) fn eat_while(&mut self, mut predicate: impl FnMut(char) -> bool) {
        // It was tried making optimized version of this for eg. line comments, but
        // LLVM can inline all of this and compile it down to fast iteration over bytes.
        while predicate(self.first()) && !self.is_eof() {
            self.bump();
        }
    }
}