/**
* Write String using specified encoding
*
* <p>When this is called multiple times, all but the last value has a trailing null
*
* @param encoder
* @param next
* @param i
* @param noOfValues
* @return
* @throws CharacterCodingException
*/
private ByteBuffer writeString(CharsetEncoder encoder, String next, int i, int noOfValues)
throws CharacterCodingException {
ByteBuffer bb;
if ((i + 1) == noOfValues) {
bb = encoder.encode(CharBuffer.wrap(next));
} else {
bb = encoder.encode(CharBuffer.wrap(next + '\0'));
}
bb.rewind();
return bb;
}
public static void main(String args[]) throws Exception {
String inputFile = "samplein.txt";
String outputFile = "sampleout.txt";
RandomAccessFile inf = new RandomAccessFile(inputFile, "r");
RandomAccessFile outf = new RandomAccessFile(outputFile, "rw");
long inputLength = new File(inputFile).length();
FileChannel inc = inf.getChannel();
FileChannel outc = outf.getChannel();
MappedByteBuffer inputData = inc.map(FileChannel.MapMode.READ_ONLY, 0, inputLength);
Charset latin1 = Charset.forName("ISO-8859-1");
CharsetDecoder decoder = latin1.newDecoder();
CharsetEncoder encoder = latin1.newEncoder();
CharBuffer cb = decoder.decode(inputData);
// Process char data here
ByteBuffer outputData = encoder.encode(cb);
outc.write(outputData);
inf.close();
outf.close();
}
/**
* Creates a string in a specfied character set.
*
* @param value String constant, must not be null
* @param charsetName Name of the character set, may be null
* @param collation Collation, may be null
* @throws IllegalCharsetNameException If the given charset name is illegal
* @throws UnsupportedCharsetException If no support for the named charset is available in this
* instance of the Java virtual machine
* @throws RuntimeException If the given value cannot be represented in the given charset
*/
public NlsString(String value, String charsetName, SqlCollation collation) {
assert value != null;
if (null != charsetName) {
charsetName = charsetName.toUpperCase();
this.charsetName = charsetName;
String javaCharsetName = SqlUtil.translateCharacterSetName(charsetName);
if (javaCharsetName == null) {
throw new UnsupportedCharsetException(charsetName);
}
this.charset = Charset.forName(javaCharsetName);
CharsetEncoder encoder = charset.newEncoder();
// dry run to see if encoding hits any problems
try {
encoder.encode(CharBuffer.wrap(value));
} catch (CharacterCodingException ex) {
throw RESOURCE.charsetEncoding(value, javaCharsetName).ex();
}
} else {
this.charsetName = null;
this.charset = null;
}
this.collation = collation;
this.value = value;
}
static byte[] encode(char[] cc, Charset cs, boolean testDirect, Time t) throws Exception {
ByteBuffer bbf;
CharBuffer cbf;
CharsetEncoder enc = cs.newEncoder();
String csn = cs.name();
if (testDirect) {
bbf = ByteBuffer.allocateDirect(cc.length * 4);
cbf = ByteBuffer.allocateDirect(cc.length * 2).asCharBuffer();
cbf.put(cc).flip();
} else {
bbf = ByteBuffer.allocate(cc.length * 4);
cbf = CharBuffer.wrap(cc);
}
CoderResult cr = null;
long t1 = System.nanoTime() / 1000;
for (int i = 0; i < iteration; i++) {
cbf.rewind();
bbf.clear();
enc.reset();
cr = enc.encode(cbf, bbf, true);
}
long t2 = System.nanoTime() / 1000;
t.t = (t2 - t1) / iteration;
if (cr != CoderResult.UNDERFLOW) {
System.out.println("ENC-----------------");
int pos = cbf.position();
System.out.printf(" cr=%s, cbf.pos=%d, cc[pos]=%x%n", cr.toString(), pos, cc[pos] & 0xffff);
throw new RuntimeException("Encoding err: " + csn);
}
byte[] bb = new byte[bbf.position()];
bbf.flip();
bbf.get(bb);
return bb;
}
/**
* Write String in UTF-BEBOM format
*
* <p>When this is called multiple times, all but the last value has a trailing null
*
* @param next
* @param i
* @param noOfValues
* @return
* @throws CharacterCodingException
*/
private ByteBuffer writeStringUTF16BEBOM(String next, int i, int noOfValues)
throws CharacterCodingException {
CharsetEncoder encoder =
Charset.forName(TextEncoding.CHARSET_UTF_16_BE_ENCODING_FORMAT).newEncoder();
encoder.onMalformedInput(CodingErrorAction.IGNORE);
encoder.onUnmappableCharacter(CodingErrorAction.IGNORE);
ByteBuffer bb = null;
// Add BOM
if ((i + 1) == noOfValues) {
bb = encoder.encode(CharBuffer.wrap('\ufeff' + next));
} else {
bb = encoder.encode(CharBuffer.wrap('\ufeff' + next + '\0'));
}
bb.rewind();
return bb;
}
public static void main(String args[]) throws Exception {
String s = "abc\uD800\uDC00qrst"; // Valid surrogate
char[] c = s.toCharArray();
CharsetEncoder enc =
Charset.forName("ISO8859_1").newEncoder().onUnmappableCharacter(CodingErrorAction.REPLACE);
/* Process the first 4 characters, including the high surrogate
which should be stored */
ByteBuffer bb = ByteBuffer.allocate(10);
CharBuffer cb = CharBuffer.wrap(c);
cb.limit(4);
enc.encode(cb, bb, false);
cb.limit(7);
enc.encode(cb, bb, true);
byte[] first = bb.array();
for (int i = 0; i < 7; i++)
System.err.printf("[%d]=%d was %d\n", i, (int) first[i] & 0xffff, (int) c[i] & 0xffff);
}
public static void main(String[] args) throws Exception {
// 创建简体中文对应的Charset
Charset cn = Charset.forName("GBK");
// 获取cn对象对应的编码器和解码器
CharsetEncoder cnEncoder = cn.newEncoder();
CharsetDecoder cnDecoder = cn.newDecoder();
// 创建一个CharBuffer对象
CharBuffer cbuff = CharBuffer.allocate(8);
cbuff.put('孙');
cbuff.put('悟');
cbuff.put('空');
cbuff.flip();
// 将CharBuffer中的字符序列转换成字节序列
ByteBuffer bbuff = cnEncoder.encode(cbuff);
// 循环访问ByteBuffer中的每个字节
for (int i = 0; i < bbuff.capacity(); i++) {
System.out.print(bbuff.get(i) + " ");
}
// 将ByteBuffer的数据解码成字符序列
System.out.println("\n" + cnDecoder.decode(bbuff));
}
static CoderResult encodeCR(char[] cc, Charset cs, boolean testDirect) throws Exception {
ByteBuffer bbf;
CharBuffer cbf;
CharsetEncoder enc = cs.newEncoder();
if (testDirect) {
bbf = ByteBuffer.allocateDirect(cc.length * 4);
cbf = ByteBuffer.allocateDirect(cc.length * 2).asCharBuffer();
cbf.put(cc).flip();
} else {
bbf = ByteBuffer.allocate(cc.length * 4);
cbf = CharBuffer.wrap(cc);
}
CoderResult cr = null;
for (int i = 0; i < iteration; i++) {
cbf.rewind();
bbf.clear();
enc.reset();
cr = enc.encode(cbf, bbf, true);
}
return cr;
}
@Override
public void visitFile(PsiFile file) {
super.visitFile(file);
if (InjectedLanguageManager.getInstance(file.getProject()).isInjectedFragment(file)
|| !file.isPhysical()) {
return;
}
final VirtualFile virtualFile = file.getVirtualFile();
final String text = file.getText();
final Charset charset =
LoadTextUtil.extractCharsetFromFileContent(file.getProject(), virtualFile, text);
final CharsetEncoder encoder =
charset.newEncoder().onUnmappableCharacter(CodingErrorAction.REPORT);
final CharBuffer charBuffer = CharBuffer.allocate(1);
final ByteBuffer byteBuffer = ByteBuffer.allocate(10);
final int length = text.length();
for (int i = 0; i < length; i++) {
final char c = text.charAt(i);
if (c != '\\') {
continue;
}
boolean isEscape = true;
int previousChar = i - 1;
while (previousChar >= 0 && text.charAt(previousChar) == '\\') {
isEscape = !isEscape;
previousChar--;
}
if (!isEscape) {
continue;
}
int nextChar = i;
do {
nextChar++;
if (nextChar >= length) {
break;
}
} while (text.charAt(nextChar) == 'u'); // \uuuu0061 is a legal unicode escape
if (nextChar == i + 1 || nextChar + 3 >= length) {
continue;
}
if (StringUtil.isHexDigit(text.charAt(nextChar))
&& StringUtil.isHexDigit(text.charAt(nextChar + 1))
&& StringUtil.isHexDigit(text.charAt(nextChar + 2))
&& StringUtil.isHexDigit(text.charAt(nextChar + 3))) {
final int escapeEnd = nextChar + 4;
final char d = (char) Integer.parseInt(text.substring(nextChar, escapeEnd), 16);
if (Character.isISOControl(d)) {
continue;
}
byteBuffer.clear();
charBuffer.clear();
charBuffer.put(d).rewind();
final CoderResult coderResult = encoder.encode(charBuffer, byteBuffer, true);
if (!coderResult.isUnmappable()) {
final PsiElement element = file.findElementAt(i);
if (element != null && isSuppressedFor(element)) {
return;
}
registerErrorAtOffset(file, i, escapeEnd - i, Character.valueOf(d));
}
}
}
}