在开发过程中,可能会遇到文件编码的转换,虽然说开发工具eclipse可以转换编码,但是有的情况却很不方便。比如,原来文件本身的编码是GBK,现在要转换成UTF-8,如果直接在eclipse中把文件编码修改成UTF-8,恭喜你,是乱码,因为不能直接从GBK到UTF-8进行转换,这时就需要我们手动的来转换编码。下面是一个文件编码转换的工具类。
package com.mikan.stuff;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.FilenameFilter;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.nio.charset.Charset;
import java.nio.charset.UnsupportedCharsetException;
public class FileCharsetConverter {
public static void main(String[] args) throws Exception {
convert("D:\\stuff\\src\\main\\java\\com\\mikan\\stuff\\test.txt",
"GBK", "UTF-8", new FilenameFilter() {
@Override
public boolean accept(File dir, String name) {
return name.endsWith("txt");
}
});
}
public static void convert(String fileName, String fromCharsetName,
String toCharsetName) throws Exception {
convert(new File(fileName), fromCharsetName, toCharsetName, null);
}
public static void convert(File file, String fromCharsetName,
String toCharsetName) throws Exception {
convert(file, fromCharsetName, toCharsetName, null);
}
public static void convert(String fileName, String fromCharsetName,
String toCharsetName, FilenameFilter filter) throws Exception {
convert(new File(fileName), fromCharsetName, toCharsetName, filter);
}
public static void convert(File file, String fromCharsetName,
String toCharsetName, FilenameFilter filter) throws Exception {
if (file.isDirectory()) {
File[] fileList = null;
if (filter == null) {
fileList = file.listFiles();
} else {
fileList = file.listFiles(filter);
}
for (File f : fileList) {
convert(f, fromCharsetName, toCharsetName, filter);
}
} else {
if (filter == null
|| filter.accept(file.getParentFile(), file.getName())) {
String fileContent = getFileContentFromCharset(file,
fromCharsetName);
saveFile2Charset(file, toCharsetName, fileContent);
}
}
}
public static String getFileContentFromCharset(File file,
String fromCharsetName) throws Exception {
if (!Charset.isSupported(fromCharsetName)) {
throw new UnsupportedCharsetException(fromCharsetName);
}
InputStream inputStream = new FileInputStream(file);
InputStreamReader reader = new InputStreamReader(inputStream,
fromCharsetName);
char[] chs = new char[(int) file.length()];
reader.read(chs);
String str = new String(chs).trim();
reader.close();
return str;
}
public static void saveFile2Charset(File file, String toCharsetName,
String content) throws Exception {
if (!Charset.isSupported(toCharsetName)) {
throw new UnsupportedCharsetException(toCharsetName);
}
OutputStream outputStream = new FileOutputStream(file);
OutputStreamWriter outWrite = new OutputStreamWriter(outputStream,
toCharsetName);
outWrite.write(content);
outWrite.close();
}
}