Function count_utf8

rust/stringzilla.rs:1877–1886

Counts the number of UTF-8 characters in the text. This function efficiently counts UTF-8 characters by identifying character start bytes (non-continuation bytes). Uses SIMD acceleration when available. # Arguments `text`: The UTF-8 encoded byte slice to count characters in. # Returns The number of UTF-8 characters (codepoints) in the text. # Examples ``` use stringzilla::stringzilla as sz;

(text: T)

/// assert_eq!(sz::count_utf8(text_cjk), 4);
/// ```
pub fn count_utf8<T>(text: T) -> usize
where
    T: AsRef<[u8]>,
{
    let text_ref = text.as_ref();
    let text_pointer = text_ref.as_ptr() as *const c_void;
    let text_length = text_ref.len();

    unsafe { sz_utf8_count(text_pointer, text_length) }
}

/// Finds the byte offset of the Nth UTF-8 character (0-indexed).
///