如何将字节数组转换为字符串,并将字符串转换为使用GWT的字节数组? [英] How to convert a byte array to a string, and string to a byte array with GWT?
本文介绍了如何将字节数组转换为字符串,并将字符串转换为使用GWT的字节数组?的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!
问题描述
String(byte [] bytes)
构造函数和 String.getBytes()
方法不是由GWT实现的JRE仿真字符串类。 有人知道一个实现吗?我不想使用 char []
,但似乎没有其他解决方案。
解决
public class GwtPlayground 下面的代码应该可以工作,只需指定每个字符的字节数。实现EntryPoint
{
static final Logger logger = Logger.getLogger();
@Override
public void onModuleLoad()
{
VerticalPanel loggerArea = new VerticalPanel();
logger.addHandler(new HasWidgetsLogHandler(loggerArea));
RootPanel.get()。add(loggerArea);
String original = new String(A+\\\↑+\\\ñ+\\\ü+C);
logger.info(original =+ original);
byte [] utfBytes = getBytes(original,2);
字符串roundTrip = getString(utfBytes,2);
logger.info(roundTrip =+ roundTrip);
$ b $ public static byte [] getBytes(String string,int bytesPerChar)
{
char [] chars = string.toCharArray();
byte [] toReturn = new byte [chars.length * bytesPerChar];
for(int i = 0; i< chars.length; i ++)
{
for(int j = 0; j< bytesPerChar; j ++)
toReturn [i * bytesPerChar + j] =(byte)(chars [i]>>(8 *(bytesPerChar_1-j)));
}
返回到返回;
$ b $ public static String getString(byte [] bytes,int bytesPerChar)
{
char [] chars = new char [bytes.length / bytesPerChar];
for(int i = 0; i< chars.length; i ++)
{
for(int j = 0; j< bytesPerChar; j ++)
{
int shift =(bytesPerChar - 1 - j)* 8;
chars [i] | =(0x000000FF<< shift<< (((int)bytes [i * bytesPerChar + j]));
}
}
返回新的字符串(字符);
}
}
正如@Per Wiklander指出的那样,真正支持UTF-8。这是一个真正的UTF-8解码器,从C 这里
private static class UTF8Decoder
{
final byte [] the_input;
int the_index,the_length;
保护UTF8Decoder(byte [] bytes)
{
super();
this.the_input = bytes;
this.the_index = 0;
this.the_length = bytes.length;
}
/ *
获取下一个字节。如果没有更多字节,它将返回UTF8_END。
* /
int get()
{
int c;
c = the_input [the_index]& 0xFF的;
the_index + = 1;
return c;
}
/ *
获取下一个继续字节的6位有效负载。
如果不是连续字节,则返回UTF8_ERROR。
* /
int cont()
{
int c = get(); ((c& 0xC0)== 0x80)
return(c& 0x3F);
else
抛出新的IllegalArgumentException(未能通过严格的UTF-8);
CharSequence getStringUTF8()
{
StringBuilder sb = new StringBuilder(the_input.length); //分配最大大小
while(the_index< the_length)
{
int c; / *字符的第一个字节* /
int r; / *结果* /
c = get();
/ *
如果((c& 0x80)== 0)
(
sb),则零延续(0至127)
* /
。 append((char)c);
一个延续(128到2047)
* /
else if((c& 0xE0)== 0xC0)
{
int c1 = cont();如果(c1> = 0)
{
r =((c& 0x1F)<< 6)|
, C1;
if(r> = 128)
sb.append((char)r);
else
抛出new IllegalArgumentException();
两个延续(2048到55295和57344到65535)
* /
else if((c& 0xF0) == 0xE0)
{
int c1 = cont();
int c2 = cont(); ((c1 | c2)> = 0)
{
r =((c& 0x0F)<= 12) (c1 <6)| C2; (r> = 2048&&(r< 55296 || r> 57343))
sb.append((char)r);
else
抛出new IllegalArgumentException();
三个延续(65536到1114111)
* /
else if((c& 0xF8)== 0xF0)
{
int c1 = cont();
int c2 = cont();
int c3 = cont(); ((c1 | c2 | c3)> = 0)
bb((char)((((c& 0x0F)<< 18)|(c1 << ; 12)|(c2 << 6)| c3)+ 65536)); // TODO这可能不起作用,因为它被转换为char
}
else
抛出新的IllegalArgumentException(失败的严格UTF8解析);
}
return sb;
}
}
The String(byte[] bytes)
constructor and String.getBytes()
method are not implemented by GWT JRE emulation String class.
Does anybody know of an implementation? I do not want to use char[]
, But it seems like there is no other solution.
解决方案
The following code should work, just specify the number of bytes per character.
public class GwtPlayground implements EntryPoint
{
static final Logger logger = Logger.getLogger("");
@Override
public void onModuleLoad()
{
VerticalPanel loggerArea = new VerticalPanel();
logger.addHandler(new HasWidgetsLogHandler(loggerArea));
RootPanel.get().add(loggerArea);
String original = new String("A" + "\uffea" + "\u00f1" + "\u00fc" + "C");
logger.info("original = " + original);
byte[] utfBytes = getBytes(original, 2);
String roundTrip = getString(utfBytes, 2);
logger.info("roundTrip = " + roundTrip);
}
public static byte[] getBytes(String string, int bytesPerChar)
{
char[] chars = string.toCharArray();
byte[] toReturn = new byte[chars.length * bytesPerChar];
for (int i = 0; i < chars.length; i++)
{
for (int j = 0; j < bytesPerChar; j++)
toReturn[i * bytesPerChar + j] = (byte) (chars[i] >>> (8 * (bytesPerChar - 1 - j)));
}
return toReturn;
}
public static String getString(byte[] bytes, int bytesPerChar)
{
char[] chars = new char[bytes.length / bytesPerChar];
for (int i = 0; i < chars.length; i++)
{
for (int j = 0; j < bytesPerChar; j++)
{
int shift = (bytesPerChar - 1 - j) * 8;
chars[i] |= (0x000000FF << shift) & (((int) bytes[i * bytesPerChar + j]) << shift);
}
}
return new String(chars);
}
}
As @Per Wiklander pointed out, this doesn't truely support UTF-8. Here is a true UTF-8 decoder ported from C here
private static class UTF8Decoder
{
final byte[] the_input;
int the_index, the_length;
protected UTF8Decoder( byte[] bytes )
{
super();
this.the_input = bytes;
this.the_index = 0;
this.the_length = bytes.length;
}
/*
Get the next byte. It returns UTF8_END if there are no more bytes.
*/
int get()
{
int c;
c = the_input[the_index] & 0xFF;
the_index += 1;
return c;
}
/*
Get the 6-bit payload of the next continuation byte.
Return UTF8_ERROR if it is not a contination byte.
*/
int cont()
{
int c = get();
if( (c & 0xC0) == 0x80 )
return (c & 0x3F);
else
throw new IllegalArgumentException( "Failed to pass strict UTF-8" );
}
CharSequence getStringUTF8()
{
StringBuilder sb = new StringBuilder( the_input.length ); // allocate a maximum size
while( the_index < the_length )
{
int c; /* the first byte of the character */
int r; /* the result */
c = get();
/*
Zero continuation (0 to 127)
*/
if( (c & 0x80) == 0 )
{
sb.append( (char) c );
}
/*
One continuation (128 to 2047)
*/
else if( (c & 0xE0) == 0xC0 )
{
int c1 = cont();
if( c1 >= 0 )
{
r = ((c & 0x1F) << 6) | c1;
if( r >= 128 )
sb.append( (char) r );
else
throw new IllegalArgumentException();
}
}
/*
Two continuation (2048 to 55295 and 57344 to 65535)
*/
else if( (c & 0xF0) == 0xE0 )
{
int c1 = cont();
int c2 = cont();
if( (c1 | c2) >= 0 )
{
r = ((c & 0x0F) << 12) | (c1 << 6) | c2;
if( r >= 2048 && (r < 55296 || r > 57343) )
sb.append( (char) r );
else
throw new IllegalArgumentException();
}
}
/*
Three continuation (65536 to 1114111)
*/
else if( (c & 0xF8) == 0xF0 )
{
int c1 = cont();
int c2 = cont();
int c3 = cont();
if( (c1 | c2 | c3) >= 0 )
sb.append( (char) ((((c & 0x0F) << 18) | (c1 << 12) | (c2 << 6) | c3) + 65536) ); // TODO this might not work as it is being cast to a char
}
else
throw new IllegalArgumentException( "Failed strict UTF8 parsing" );
}
return sb;
}
}
这篇关于如何将字节数组转换为字符串,并将字符串转换为使用GWT的字节数组?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!
查看全文