indexOfPos

pub fn findPos(comptime T: type, haystack: []const T, start_index: usize, needle: []const T) ?usize {
    if (needle.len > haystack.len) return null;
    if (needle.len < 2) {
        if (needle.len == 0) return start_index;
        // findScalarPos is significantly faster than findPosLinear
        return findScalarPos(T, haystack, start_index, needle[0]);
    }

    if (!std.meta.hasUniqueRepresentation(T) or haystack.len < 52 or needle.len <= 4)
        return findPosLinear(T, haystack, start_index, needle);

    const haystack_bytes = sliceAsBytes(haystack);
    const needle_bytes = sliceAsBytes(needle);

    var skip_table: [256]usize = undefined;
    boyerMooreHorspoolPreprocess(needle_bytes, skip_table[0..]);

    var i: usize = start_index * @sizeOf(T);
    while (i <= haystack_bytes.len - needle_bytes.len) {
        if (i % @sizeOf(T) == 0 and mem.eql(u8, haystack_bytes[i .. i + needle_bytes.len], needle_bytes)) {
            return @divExact(i, @sizeOf(T));
        }
        i += skip_table[haystack_bytes[i + needle_bytes.len - 1]];
    }

    return null;
}