问题一
public static String GB2312_Unicode( String gb2312 )
{
String unicode = "";
try
{
byte[] test = gb2312.getBytes("Unicode");
String tag = "\\u";
for(int i=2;i<test.length;i+=2)
{
unicode = unicode + tag + Integer.toHexString(test[i+1])+Integer.toHexString(test[i]);
}
unicode = unicode.replace( "ffffff","" );
}
catch ( java.io.IOException e )
{
logger.error( e );
}
return unicode;
}上面为获得汉字的Unicode码,问题出在 Integer.toHexString(test[i+1])+Integer.toHexString(test[i]) 处,为什么有些汉字转码出来的为 **** 可以直接使用,而有些转码出来的则为 ********** ,其中多了6个f?
问题二
public static String Unicode_GB2312( String unicode )
{
String gb2312 = "";try
{
gb2312 = new String(unicode.getBytes("GB2312"));
}
catch ( java.io.IOException e )
{
logger.error( e );
}
return gb2312;
}上面为Unicode码转GB2312,参数unicode为我从页面获得的 \u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd unicode码字符串,但是返回的为什么还是原来的unicode码字符串?而我在里面如果写成常量 String unicode = "\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd"; 则可以正常的返回我GB2312汉字。
public static String GB2312_Unicode( String gb2312 )
{
String unicode = "";
try
{
byte[] test = gb2312.getBytes("Unicode");
String tag = "\\u";
for(int i=2;i<test.length;i+=2)
{
unicode = unicode + tag + Integer.toHexString(test[i+1])+Integer.toHexString(test[i]);
}
unicode = unicode.replace( "ffffff","" );
}
catch ( java.io.IOException e )
{
logger.error( e );
}
return unicode;
}上面为获得汉字的Unicode码,问题出在 Integer.toHexString(test[i+1])+Integer.toHexString(test[i]) 处,为什么有些汉字转码出来的为 **** 可以直接使用,而有些转码出来的则为 ********** ,其中多了6个f?
问题二
public static String Unicode_GB2312( String unicode )
{
String gb2312 = "";try
{
gb2312 = new String(unicode.getBytes("GB2312"));
}
catch ( java.io.IOException e )
{
logger.error( e );
}
return gb2312;
}上面为Unicode码转GB2312,参数unicode为我从页面获得的 \u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd unicode码字符串,但是返回的为什么还是原来的unicode码字符串?而我在里面如果写成常量 String unicode = "\u4e2d\u534e\u4eba\u6c11\u5171\u548c\u56fd"; 则可以正常的返回我GB2312汉字。
你这个转编码的算法肯定是不能正常工作的。
第一个问题没有编译,不知道具体问题出在哪里,但是肯定这个算法不理想。因为这个转为16进制后位数肯定是有问题的
贴一段代码给你。但是反便宜的算法我还没有找到
private String native2asciiString(String data) {
StringBuffer b = new StringBuffer(); // JavaScript is sensitive to some UNICODE characters. So for
// the sake of simplicity, we just escape everything.
// notice that "\" is so special,so do some change at the some time
char[] ch = data.toCharArray();
for (int j = 0; j < ch.length; j++) {
if (ch[j] < 128) {
String entity = entities[ch[j]];
if (entity == null)
b.append(ch[j]);
else
b.append(entity);
} else {
b.append(native2ascii(ch[j]));
}
} return b.toString(); } /**
* Create an escaped Unicode character
*
* @param c
* @return The unicode character in escaped string form
*/
private static String native2ascii(char c) {
StringBuffer b = new StringBuffer();
for (int i = 0; i < 4; i++) {
b.append(Integer.toHexString(c & 0x000F).toUpperCase());
c >>>= 4;
}
b.append("u\\");
return b.reverse().toString();
}
如果你想给一个默认值的话就写成 String s = "\\u4e2d"。
GB2312_Unicode的标准方法我是没有看到过有,如果你非要用编码的方式解决汉化问题可以考虑使用别的编码方式,apache的开源项目commons里面有关于编码的实用包。
private String loadConvert (char[] in, int off, int len, char[] convtBuf) {
if (convtBuf.length < len) {
int newLen = len * 2;
if (newLen < 0) {
newLen = Integer.MAX_VALUE;
}
convtBuf = new char[newLen];
}
char aChar;
char[] out = convtBuf;
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);
}
private String saveConvert(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)) {
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();
}