llmx/llmx-rs/utils/string/src/lib.rs

// Truncate a &str to a byte budget at a char boundary (prefix)
#[inline]
pub fn take_bytes_at_char_boundary(s: &str, maxb: usize) -> &str {
    if s.len() <= maxb {
        return s;
    }
    let mut last_ok = 0;
    for (i, ch) in s.char_indices() {
        let nb = i + ch.len_utf8();
        if nb > maxb {
            break;
        }
        last_ok = nb;
    }
    &s[..last_ok]
}

// Take a suffix of a &str within a byte budget at a char boundary
#[inline]
pub fn take_last_bytes_at_char_boundary(s: &str, maxb: usize) -> &str {
    if s.len() <= maxb {
        return s;
    }
    let mut start = s.len();
    let mut used = 0usize;
    for (i, ch) in s.char_indices().rev() {
        let nb = ch.len_utf8();
        if used + nb > maxb {
            break;
        }
        start = i;
        used += nb;
        if start == 0 {
            break;
        }
    }
    &s[start..]
}