Function find_whitespace_utf8

rust/stringzilla.rs:1829–1848

Finds the first whitespace character in UTF-8 encoded text. Searches for any of the 29 Unicode whitespace characters (includes all newlines per Unicode standard, plus spaces, tabs, and various Unicode space characters). The complete set includes: - All 8 newline characters (see [`find_newline_utf8`]) - U+0009 (CHARACTER TABULATION `\t`) - U+001F (UNIT SEPARATOR) - U+0020 (SPACE) - U+00A0 (NO-BRE

(text: T)

/// assert_eq!(span.length, 1);
/// ```
pub fn find_whitespace_utf8<T>(text: T) -> Option<IndexSpan>
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();
    let mut matched_length: usize = 0;

    let result = unsafe { sz_utf8_find_whitespace(text_pointer, text_length, &mut matched_length as *mut usize) };

    if result.is_null() {
        None
    } else {
        let offset = unsafe { (result as *const u8).offset_from(text_pointer as *const u8) }
            .try_into()
            .unwrap();
        Some(IndexSpan::new(offset, matched_length))
    }
}

/// Counts the number of UTF-8 characters in the text.
///