struct Utf16LeIterator [src]

Fields

bytes: []const u8

i: usize

Members

init (Function)
nextCodepoint (Function)
NextCodepointError (Error Set)

Source

  pub const Utf16LeIterator = struct {
    bytes: []const u8,
    i: usize,

    pub fn init(s: []const u16) Utf16LeIterator {
        return Utf16LeIterator{
            .bytes = mem.sliceAsBytes(s),
            .i = 0,
        };
    }

    pub const NextCodepointError = error{ DanglingSurrogateHalf, ExpectedSecondSurrogateHalf, UnexpectedSecondSurrogateHalf };

    pub fn nextCodepoint(it: *Utf16LeIterator) NextCodepointError!?u21 {
        assert(it.i <= it.bytes.len);
        if (it.i == it.bytes.len) return null;
        var code_units: [2]u16 = undefined;
        code_units[0] = mem.readInt(u16, it.bytes[it.i..][0..2], .little);
        it.i += 2;
        if (utf16IsHighSurrogate(code_units[0])) {
            // surrogate pair
            if (it.i >= it.bytes.len) return error.DanglingSurrogateHalf;
            code_units[1] = mem.readInt(u16, it.bytes[it.i..][0..2], .little);
            const codepoint = try utf16DecodeSurrogatePair(&code_units);
            it.i += 2;
            return codepoint;
        } else if (utf16IsLowSurrogate(code_units[0])) {
            return error.UnexpectedSecondSurrogateHalf;
        } else {
            return code_units[0];
        }
    }
}  