Function utf8_unpack_chunk

rust/stringzilla.rs:1258–1278

Unpacks a UTF-8 byte sequence into UTF-32 codepoints. This function decodes UTF-8 encoded text into individual Unicode codepoints, storing them in a u32 array. It processes as many complete characters as possible given the input and output buffer sizes. # Arguments `text`: The UTF-8 encoded byte slice to decode. `runes`: Output buffer to store decoded codepoints. # Returns A tuple `(bytes_con

(text: &[u8], runes: &mut [u32])

/// ```
///
pub fn utf8_unpack_chunk(text: &[u8], runes: &mut [u32]) -> (usize, usize) {
    let mut runes_unpacked: usize = 0;

    let result = unsafe {
        sz_utf8_unpack_chunk(
            text.as_ptr() as *const c_void,
            text.len(),
            runes.as_mut_ptr(),
            runes.len(),
            &mut runes_unpacked,
        )
    };

    let bytes_consumed = if result.is_null() {
        0
    } else {
        unsafe { result.offset_from(text.as_ptr() as *const c_void) as usize }
    };

    (bytes_consumed, runes_unpacked)
}

/// Computes a 64-bit AES-based hash value for a given byte slice `text`.
/// This function is designed to provide a high-quality hash value for use in