最近在做一个文本阅读器,显示时需要获得本地导入的txt的编码字符集,网上搜了,都不行,还在搜,请高手给个成熟的方法,谢谢了。在线狂等中.
我的代码(不可用):
private static void judgeTextCode(String strFilePath) {
FileInputStream fis = null;
try {
fis = new FileInputStream(strFilePath);
int a = fis.read();
int b = fis.read();
if(a==0xFF&&b==0xFE) {
System.out.println("----------Unicode------");
}
else if(a==0xFE&&b==0xFF) {
System.out.println("----------UTF-16BE------");
}
else if(a==0xEF&&b==0xBB) {
System.out.println("----------UTF-8------");
} else {
System.out.println("----------GBK------");
}
} catch(Exception e) {
e.printStackTrace();
} finally {
try {
if(fis != null) {
fis.close();
}
} catch(Exception e) {
e.printStackTrace();
}
}
}java
我的代码(不可用):
private static void judgeTextCode(String strFilePath) {
FileInputStream fis = null;
try {
fis = new FileInputStream(strFilePath);
int a = fis.read();
int b = fis.read();
if(a==0xFF&&b==0xFE) {
System.out.println("----------Unicode------");
}
else if(a==0xFE&&b==0xFF) {
System.out.println("----------UTF-16BE------");
}
else if(a==0xEF&&b==0xBB) {
System.out.println("----------UTF-8------");
} else {
System.out.println("----------GBK------");
}
} catch(Exception e) {
e.printStackTrace();
} finally {
try {
if(fis != null) {
fis.close();
}
} catch(Exception e) {
e.printStackTrace();
}
}
}java
try {
String charset = getCharset(new File("c:\\2.txt"));
System.out.println(charset);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public static String toHex(byte[] byteArray) {
int i;
StringBuffer buf = new StringBuffer("");
int len = byteArray.length;
for (int offset = 0; offset < len; offset++) {
i = byteArray[offset];
if (i < 0)
i += 256;
if (i < 16)
buf.append("0");
buf.append(Integer.toHexString(i));
}
return buf.toString().toUpperCase();
}
private static String getCharset(File fileName) throws IOException {
BufferedInputStream bin = new BufferedInputStream(new FileInputStream(fileName));
byte[] b = new byte[10];
bin.read(b, 0, b.length);
String first = toHex(b);
//这里可以看到各种编码的前几个字符是什么,gbk编码前面没有多余的
String code = null;
if (first.startsWith("EFBBBF")) {
code = "UTF-8";
} else if (first.startsWith("FEFF00")) {
code = "UTF-16BE";
} else if (first.startsWith("FFFE")) {
code = "Unicode";
} else if (first.startsWith("FFFE")) {
code = "Unicode";
} else {
code = "GBK";
}
return code;
}
code = "GBK";
}GBK改为ANSI
public static void getCharset(String path) {
CodepageDetectorProxy detector = CodepageDetectorProxy.getInstance();
detector.add(new ParsingDetector(false));
detector.add(ASCIIDetector.getInstance());
detector.add(UnicodeDetector.getInstance());
java.nio.charset.Charset charset = null;
File f=new File(path);
try {
charset = detector.detectCodepage(new BufferedInputStream(new FileInputStream(f)),100);
} catch (Exception ex) {ex.printStackTrace();}
if(charset!=null){
System.out.println(f.getName()+"编码是:"+charset.name());
}else{
System.out.println(f.getName()+"未知");
}
}
但总是报:java.lang.IllegalArgumentException: More than the given length had to be read and the given stream could not be reset. Undetermined state for this detection.
at info.monitorenter.cpdetector.io.CodepageDetectorProxy.detectCodepage(CodepageDetectorProxy.java:198)
谁用过这个探测器啊,指点下
inputStream.read(head);
String code = "gbk";
if (head[0] == -1 && head[1] == -2){
code = "UTF-16";
}
if (head[0] == -2 && head[1] == -1){
code = "Unicode";
}
if (head[0] == -17 && head[1] == -69 && head[2] == -65){
code = "UTF-8";
}