ModifiedUtf8.java 文件源码

/**
 * Returns the number of bytes the modified UTF-8 representation of 's' would take. Note
 * that this is just the space for the bytes representing the characters, not the length
 * which precedes those bytes, because different callers represent the length differently,
 * as two, four, or even eight bytes. If {@code shortLength} is true, we'll throw an
 * exception if the string is too long for its length to be represented by a short.
 */
public static long countBytes(String s, boolean shortLength) throws UTFDataFormatException {
    long result = 0;
    final int length = s.length();
    for (int i = 0; i < length; ++i) {
        char ch = s.charAt(i);
        if (ch != 0 && ch <= 127) { // U+0000 uses two bytes.
            ++result;
        } else if (ch <= 2047) {
            result += 2;
        } else {
            result += 3;
        }
        if (shortLength && result > 65535) {
            throw new UTFDataFormatException("String more than 65535 UTF bytes long");
        }
    }
    return result;
}