Max Gadget, GPG Dragon Latest Version, Install Android, Sony Xperia, Xiaomi Mi Robot Vacuum, Verizon, Android Marshmallow, Network, stock firmware

Selasa, 17 April 2007

Java's UTF-8 and Unicode writing is broken - Use this fix

Java's UTF-8 and Unicode writing is broken - Use this fix - this blog we have built a few years ago and already very many blog visitors Max Gadget who are satisfied with the information we convey and we say thanks for that, we will then improve the quality of information we convey to you, well according to what you are looking for we will now discuss first about Java's UTF-8 and Unicode writing is broken - Use this fix this information we framework from various trusted sources, please see:

Articles : Java's UTF-8 and Unicode writing is broken - Use this fix
full Link : Java's UTF-8 and Unicode writing is broken - Use this fix

You can also see our article on:


Java's UTF-8 and Unicode writing is broken - Use this fix

Many of you might not believe this but try creating a file in UTF-8 encoding using a java program like this one (found on the java tutorial site)

//example from Sun - Incorrect output
static void writeOutput(String str) {

try {
FileOutputStream fos = new FileOutputStream("test.txt");
Writer out = new OutputStreamWriter(fos, "UTF8");
out.write(str);
out.close();
} catch (IOException e) {
e.printStackTrace();
}
}


This will create a file alright, but that file will not be a true UTF-8 file. Infact, this is a known and documented bug in the JDK that SUN will never fix!
There are other problems with the java.io package when it comes to unicode, for example, the OutputStreamWriter will not write an ASCII stream correctly leaving a '?' at the beginning of the output stream if input stream was Unicode.

After scouring the internet for information on how to get around this, I decided to write a general purpose Unicode converter that would convert FROM and TO any of the following formats:
UTF-8, UTF-16LE, UTF-16BE, UTF-32LE, UTF-32BE, ASCII

Usage:
byte[] outbytes = UnicodeUtils.convert(byte[] inbytes, String desiredoutputEncoding);
(The convertor will auto-sense the encoding of the input bytes)

The famous Shanghai Example:



//Example of usage:
String shanghai = "\u4E0A\u6D77";
byte[] out = UnicodeUtil.convert(shanghai.getBytes("UTF-16"), "UTF-8"); //Shanghai in Chinese
FileOutputStream fos = new FileOutputStream("/tmp/out.htm);
fos.write(out);
fos.close();


The following is the code for UnicodeUtils.java




import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.PushbackInputStream;
import java.io.UnsupportedEncodingException;
import java.io.Writer;

public class UnicodeUtil {

public static byte[] convert(byte[] bytes, String encout) throws Exception {
// Workaround for bug that will not be fixed by SUN
// http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=4508058
UnicodeInputStream uis = new UnicodeInputStream(new ByteArrayInputStream(bytes), "ASCII");
boolean unicodeOutputReqd = (getBOM(encout) != null) ? true : false;
String enc = uis.getEncoding();
String BOM = getBOM(enc); // get the BOM of the inputstream

if (BOM == null) {
// inputstream looks like ascii...
// create a BOM based on the outputstream
BOM = getBOM(encout);
}
uis.close();

ByteArrayOutputStream out = new ByteArrayOutputStream();
BufferedReader br = new BufferedReader(new InputStreamReader(new ByteArrayInputStream(bytes, uis.getBOMOffset(), bytes.length), enc));
Writer w = new BufferedWriter(new OutputStreamWriter(out, encout));

// dont write a BOM for ascii(out) as the OutputStreamWriter
// will not process it correctly.
if (BOM != null && unicodeOutputReqd) {
w.write(BOM);
}

char[] buffer = new char[4096];
int len;
while ((len = br.read(buffer)) != -1) {
w.write(buffer, 0, len);
}

br.close(); // Close the input.
w.close(); // Flush and close output.
return out.toByteArray();
}

public static String getBOM(String enc) throws UnsupportedEncodingException {
if ("UTF-8".equals(enc)) {
byte[] bom = new byte[3];
bom[0] = (byte) 0xEF;
bom[1] = (byte) 0xBB;
bom[2] = (byte) 0xBF;
return new String(bom, enc);
} else if ("UTF-16BE".equals(enc)) {
byte[] bom = new byte[2];
bom[0] = (byte) 0xFE;
bom[1] = (byte) 0xFF;
return new String(bom, enc);
} else if ("UTF-16LE".equals(enc)) {
byte[] bom = new byte[2];
bom[0] = (byte) 0xFF;
bom[1] = (byte) 0xFE;
return new String(bom, enc);
} else if ("UTF-32BE".equals(enc)) {
byte[] bom = new byte[4];
bom[0] = (byte) 0x00;
bom[1] = (byte) 0x00;
bom[2] = (byte) 0xFE;
bom[3] = (byte) 0xFF;
return new String(bom, enc);
} else if ("UTF-32LE".equals(enc)) {
byte[] bom = new byte[4];
bom[0] = (byte) 0x00;
bom[1] = (byte) 0x00;
bom[2] = (byte) 0xFF;
bom[3] = (byte) 0xFE;
return new String(bom, enc);
} else {
return null;
}

}

public static class UnicodeInputStream extends InputStream {
private PushbackInputStream internalIn;

private boolean isInited = false;

private int BOMOffset = -1;

private String defaultEnc;

private String encoding;

public static final int BOM_SIZE = 4;

public UnicodeInputStream(InputStream in, String defaultEnc) {
internalIn = new PushbackInputStream(in, BOM_SIZE);
this.defaultEnc = defaultEnc;
}

public String getDefaultEncoding() {
return defaultEnc;
}

public String getEncoding() {
if (!isInited) {
try {
init();
} catch (IOException ex) {
IllegalStateException ise = new IllegalStateException("Init method failed.");
ise.initCause(ise);
throw ise;
}
}
return encoding;
}

/**
* Read-ahead four bytes and check for BOM marks. Extra bytes are unread
* back to the stream, only BOM bytes are skipped.
*/
protected void init() throws IOException {
if (isInited)
return;

byte bom[] = new byte[BOM_SIZE];
int n, unread;
n = internalIn.read(bom, 0, bom.length);

if ((bom[0] == (byte) 0x00) && (bom[1] == (byte) 0x00) && (bom[2] == (byte) 0xFE) && (bom[3] == (byte) 0xFF)) {
encoding = "UTF-32BE";
unread = n - 4;
} else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE) && (bom[2] == (byte) 0x00) && (bom[3] == (byte) 0x00)) {
encoding = "UTF-32LE";
unread = n - 4;
} else if ((bom[0] == (byte) 0xEF) && (bom[1] == (byte) 0xBB) && (bom[2] == (byte) 0xBF)) {
encoding = "UTF-8";
unread = n - 3;
} else if ((bom[0] == (byte) 0xFE) && (bom[1] == (byte) 0xFF)) {
encoding = "UTF-16BE";
unread = n - 2;
} else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE)) {
encoding = "UTF-16LE";
unread = n - 2;
} else {
// Unicode BOM mark not found, unread all bytes
encoding = defaultEnc;
unread = n;
}
BOMOffset = BOM_SIZE - unread;
if (unread > 0)
internalIn.unread(bom, (n - unread), unread);

isInited = true;
}

public void close() throws IOException {
// init();
isInited = true;
internalIn.close();
}

public int read() throws IOException {
// init();
isInited = true;
return internalIn.read();
}

public int getBOMOffset() {
return BOMOffset;
}
}

}





so much information Java's UTF-8 and Unicode writing is broken - Use this fix

hopefully the information Java's UTF-8 and Unicode writing is broken - Use this fix that we convey can make you satisfied because it can be useful to determine the gadget according to your needs.

you just read the article titled Java's UTF-8 and Unicode writing is broken - Use this fix if you feel this information is useful and want to bookmark or share please use the link https://maxyaquos.blogspot.com/2007/04/java-utf-8-and-unicode-writing-is.html do not forget to go back to this blog to get more information about gadgets.

Tag :
Share on Facebook
Share on Twitter
Share on Google+
Tags :

Related : Java's UTF-8 and Unicode writing is broken - Use this fix

0 komentar:

Posting Komentar