手机上通用的UTF8转换程序

王朝other·作者佚名  2008-05-31
窄屏简体版  字體: |||超大  

最近发现Java的UTF转换函数有BUG,在某些手机上(如K700)会出现乱码,与是上网查询了一下,在国外论坛上找到了一个UTF8转换函数,在我们公司所有测试机上都能正常转换,觉得效果还可以

private final String readUnicodeFileUTF8(String filename) {

StringBuffer sb = new StringBuffer(256);

try {

int[] surrogatePair = new int[2];

InputStream is = this.getClass().getResourceAsStream(filename);

int val = 0;

int unicharCount = 0;

while ((val = readNextCharFromStreamUTF8(is))!=-1) {

unicharCount++;

if (val <= 0xFFFF) {

// if first value is the Byte Order Mark (BOM), do not add

if (! (unicharCount == 1 && val == 0xFEFF)) {

sb.append((char)val);

}

} else {

supplementCodePointToSurrogatePair(val, surrogatePair);

sb.append((char)surrogatePair[0]);

sb.append((char)surrogatePair[1]);

}

}

is.close();

} catch (Exception e) {};

return new String(sb);

}

private final static int readNextCharFromStreamUTF8(InputStream is) {

int c = -1;

if (is==null) return c;

boolean complete = false;

try {

int byteVal;

int eXPecting=0;

int composedVal=0;

while (!complete && (byteVal = is.read()) != -1) {

if (expecting > 0 && (byteVal & 0xC0) == 0x80) { /* 10xxxxxx */

expecting--;

composedVal = composedVal ((byteVal & 0x3F) << (expecting*6));

if (expecting == 0) {

c = composedVal;

complete = true;

//System.out.println("appending: U+" + Integer.toHexString(composedVal) );

}

} else {

composedVal = 0;

expecting = 0;

if ((byteVal & 0x80) == 0) { /* 0xxxxxxx */

// one byte character, no extending byte expected

c = byteVal;

complete = true;

//System.out.println("appending: U+" + Integer.toHexString(byteVal) );

} else if ((byteVal & 0xE0) == 0xC0) { /* 110xxxxx */

expecting = 1; // expecting 1 extending byte

composedVal = ((byteVal & 0x1F) << 6);

} else if ((byteVal & 0xF0) == 0xE0) { /* 1110xxxx */

expecting = 2; // expecting 2 extending bytes

composedVal = ((byteVal & 0x0F) << 12);

} else if ((byteVal & 0xF8) == 0xF0) { /* 11110xxx */

expecting = 3; // expecting 3 extending bytes

composedVal = ((byteVal & 0x07) << 18);

} else {

// non conformant utf-8, ignore or catch error

}

}

}

} catch (Exception e) {

System.out.println(e.toString());

}

return c;

}

private final static void supplementCodePointToSurrogatePair(int codePoint, int[] surrogatePair) {

int high4 = ((codePoint >> 16) & 0x1F) - 1;

int mid6 = ((codePoint >> 10) & 0x3F);

int low10 = codePoint & 0x3FF;

surrogatePair[0] = (0xD800 (high4 << 6) (mid6));

surrogatePair[1] = (0xDC00 (low10));

}

(出处:http://www.knowsky.com)

 
 
 
免责声明:本文为网络用户发布,其观点仅代表作者个人观点,与本站无关,本站仅提供信息存储服务。文中陈述内容未经本站证实,其真实性、完整性、及时性本站不作任何保证或承诺,请读者仅作参考,并请自行核实相关内容。
 
 
© 2005- 王朝網路 版權所有 導航