/* 輸出
Original: 黃 彪彪
to unicode: \u9EC4\ \t\u5F6A\u5F6A
from unicode: 黃 彪彪
使用命令轉換: native2ascii -encoding utf-8 a.txt a.txt
Java的properties屬性文件會把字符先轉換成unicode的形式存儲.
*/
import java.io.UnsupportedEncodingException;
public class UnicodeConverter {
public static void main(String[] args) throws UnsupportedEncodingException {
String s = "黃 \t彪\u5F6A";
System.out.println("Original:\t\t" + s);
s = toEncodedUnicode(s, true);
System.out.println("to unicode:\t\t" + s);
s = fromEncodedUnicode(s.toCharArray(), 0, s.length());
System.out.println("from unicode:\t" + s);
}
private static final char[] hexDigit = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A',
'B', 'C', 'D', 'E', 'F' };
private static char toHex(int nibble) {
return hexDigit[(nibble & 0xF)];
}
/**
* 將字符串編碼成 Unicode 形式的字符串. 如 "黃" to "\u9EC4"
* Converts unicodes to encoded \\uxxxx and escapes
* special characters with a preceding slash
*
* @param theString
* 待轉換成Unicode編碼的字符串。
* @param escapeSpace
* 是否忽略空格，為true時在空格后面是否加個反斜杠。
* @return 返回轉換后Unicode編碼的字符串。
*/
public static String toEncodedUnicode(String theString, boolean escapeSpace) {
int len = theString.length();
int bufLen = len * 2;
if (bufLen < 0) {
bufLen = Integer.MAX_VALUE;
}
StringBuffer outBuffer = new StringBuffer(bufLen);
for (int x = 0; x < len; x++) {
char aChar = theString.charAt(x);
// Handle common case first, selecting largest block that
// avoids the specials below
if ((aChar > 61) && (aChar < 127)) {
if (aChar == '\\') {
outBuffer.append('\\');
outBuffer.append('\\');
continue;
}
outBuffer.append(aChar);
continue;
}
switch (aChar) {
case ' ':
if (x == 0 || escapeSpace) outBuffer.append('\\');
outBuffer.append(' ');
break;
case '\t':
outBuffer.append('\\');
outBuffer.append('t');
break;
case '\n':
outBuffer.append('\\');
outBuffer.append('n');
break;
case '\r':
outBuffer.append('\\');
outBuffer.append('r');
break;
case '\f':
outBuffer.append('\\');
outBuffer.append('f');
break;
case '=': // Fall through
case ':': // Fall through
case '#': // Fall through
case '!':
outBuffer.append('\\');
outBuffer.append(aChar);
break;
default:
if ((aChar < 0x0020) || (aChar > 0x007e)) {
// 每個unicode有16位，每四位對應的16進制從高位保存到低位
outBuffer.append('\\');
outBuffer.append('u');
outBuffer.append(toHex((aChar >> 12) & 0xF));
outBuffer.append(toHex((aChar >> 8) & 0xF));
outBuffer.append(toHex((aChar >> 4) & 0xF));
outBuffer.append(toHex(aChar & 0xF));
} else {
outBuffer.append(aChar);
}
}
}
return outBuffer.toString();
}
/**
* 從 Unicode 形式的字符串轉換成對應的編碼的特殊字符串。 如 "\u9EC4" to "黃".
* Converts encoded \\uxxxx to unicode chars
* and changes special saved chars to their original forms
*
* @param in
* Unicode編碼的字符數組。
* @param off
* 轉換的起始偏移量。
* @param len
* 轉換的字符長度。
* @param convtBuf
* 轉換的緩存字符數組。
* @return 完成轉換，返回編碼前的特殊字符串。
*/
public static String fromEncodedUnicode(char[] in, int off, int len) {
char aChar;
char[] out = new char[len]; // 只短不長
int outLen = 0;
int end = off + len;
while (off < end) {
aChar = in[off++];
if (aChar == '\\') {
aChar = in[off++];
if (aChar == 'u') {
// Read the xxxx
int value = 0;
for (int i = 0; i < 4; i++) {
aChar = in[off++];
switch (aChar) {
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
value = (value << 4) + aChar - '0';
break;
case 'a':
case 'b':
case 'c':
case 'd':
case 'e':
case 'f':
value = (value << 4) + 10 + aChar - 'a';
break;
case 'A':
case 'B':
case 'C':
case 'D':
case 'E':
case 'F':
value = (value << 4) + 10 + aChar - 'A';
break;
default:
throw new IllegalArgumentException("Malformed \\uxxxx encoding.");
}
}
out[outLen++] = (char) value;
} else {
if (aChar == 't') {
aChar = '\t';
} else if (aChar == 'r') {
aChar = '\r';
} else if (aChar == 'n') {
aChar = '\n';
} else if (aChar == 'f') {
aChar = '\f';
}
out[outLen++] = aChar;
}
} else {
out[outLen++] = (char) aChar;
}
}
return new String(out, 0, outLen);
}
}