public ByteVector putUTF8(final String stringValue) {
int charLength = stringValue.length();
if (charLength > 65535) {
// If no. of characters> 65535, than however UTF-8 encoded length, wont fit in 2 bytes.
throw new IllegalArgumentException("UTF8 string too large");
}
for (int i = 0; i < charLength; ++i) {
char charValue = stringValue.charAt(i);
if (charValue >= '\u0001' && charValue <= '\u007F') {
// Unicode code-point encoding in utf-8 fits in 1 byte.
currentData[currentLength++] = (byte) charValue;
} else {
// doesnt fit in 1 byte.
length = currentLength;
return encodeUtf8(stringValue, i, 65535);
}
}
...
}
但是当代码点映射 > 1字节时,它调用 encodeUTF8方法:
final ByteVector encodeUtf8(final String stringValue, final int offset, final int maxByteLength /*= 65535 */) {
int charLength = stringValue.length();
int byteLength = offset;
for (int i = offset; i < charLength; ++i) {
char charValue = stringValue.charAt(i);
if (charValue >= 0x0001 && charValue <= 0x007F) {
byteLength++;
} else if (charValue <= 0x07FF) {
byteLength += 2;
} else {
byteLength += 3;
}
}
...
}