JAVA按字节截取UTF-8编码的字符串(其他编码也适用)

代码如下,有更好的意见请留言.

	public static void main(String[] args) throws Exception {
		String encode = "UTF-8";
		// 截取10字节,不出错
		int sublen = 10;
		// UTF-8字节
		String srcStr = "出错出hh错出错hello1出错";
		// 先转化成char
		char[] srcStrChars = srcStr.toCharArray();
		int cnt = 0;
		Charset cs = Charset.forName(encode);
		CharBuffer cb = CharBuffer.allocate(1);
		ByteBuffer resultBuff = ByteBuffer.allocate(sublen);
		for (int i = 0; i < srcStrChars.length; i++) {
			char c = srcStrChars[i];
			cb.put(c);
			cb.flip();
			ByteBuffer bb = cs.encode(cb);
			cnt += bb.array().length;
			if(cnt > sublen){
				break;
			}
			resultBuff.put(bb);
			cb.clear();
		}
		String result = new String(resultBuff.array(), encode);
		System.out.println(result);
	}

 

评论

2 楼 祈祷末日 2015-03-04  

private static final Charset charset = Charset.forName("Shift_JIS");
private static final CharsetEncoder charsetEncoder = charset.newEncoder();
private static String truncTH(String str, int capacity, String csn) throws UnsupportedEncodingException {
if (str.getBytes(charset).length <= capacity)
return str;
CharBuffer in = CharBuffer.wrap(str.toCharArray(), 0, str.length());
charsetEncoder.reset();
charsetEncoder.encode(in, ByteBuffer.allocate(capacity), true);
return in.flip().toString();
}

1 楼 cpfok 2015-01-09  

祈祷末日 写道

private static String cutStringAsUtf8(String inStr) {
int maxLength = 12;
if (StringUtils.isEmpty(inStr)) {
return inStr;
}
Charset utf8 = StandardCharsets.UTF_8;
byte[] binary = inStr.getBytes(utf8);
int size = binary.length;
if (size <= maxLength) {
return inStr;
}
int last = binary[maxLength] & 0xff;
int lastIndex;
if ((last & 0x80) == 0) {
lastIndex = maxLength;
} else {
int foundIndex = -1;
for (int currentIndex = maxLength; currentIndex >= 0; currentIndex--) {
int b = binary[currentIndex] & 0xff;
if ((b & 0xc0) == 0xc0) {
foundIndex = currentIndex;
break;
}
}
if (foundIndex > 0) {
lastIndex = foundIndex;
} else {
throw new IllegalArgumentException("Can't Truncate String");
}
}
return new String(Arrays.copyOf(binary, lastIndex), utf8);
}

这个针对UTF-8字节截取处理的方法很好,我补充点注释这样就能看明白点了.
// 截取位置是单字节判断处理
if ((last & 0x80) == 0) {
lastIndex = maxLength;
} else {
// 截取位置是双字节判断处理
int foundIndex = -1;
// 寻找当前文字,字节开始的位置
for (int currentIndex = maxLength; currentIndex >= 0; currentIndex--) {
int b = binary[currentIndex] & 0xff;
if ((b & 0xc0) == 0xc0) {
foundIndex = currentIndex;
break;
}
}
if (foundIndex > 0) {
lastIndex = foundIndex;
} else {
throw new IllegalArgumentException("Can't Truncate String");
}
}