get/guess Charset from File - Android File Input Output

Android examples for File Input Output:File Charset

  1. HOME
  2. Android
  3. File Input Output
  4. File Charset

Description

get/guess Charset from File

Demo Code


//package com.java2s;
import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;

public class Main {
    public static String getCharset(File file) {
        String charset = "GBK";
        byte[] first3Bytes = new byte[3];
        try {//from  w w w. j a  v a2 s .  c o m
            boolean checked = false;
            BufferedInputStream bis = new BufferedInputStream(
                    new FileInputStream(file));
            bis.mark(0);
            int read = bis.read(first3Bytes, 0, 3);
            if (read == -1)
                return charset;
            if (first3Bytes[0] == (byte) 0xFF
                    && first3Bytes[1] == (byte) 0xFE) {
                charset = "UTF-16LE";
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xFE
                    && first3Bytes[1] == (byte) 0xFF) {
                charset = "UTF-16BE";
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xEF
                    && first3Bytes[1] == (byte) 0xBB
                    && first3Bytes[2] == (byte) 0xBF) {
                charset = "UTF-8";
                checked = true;
            }
            bis.reset();
            if (!checked) {
                int loc = 0;
                while ((read = bis.read()) != -1) {
                    loc++;
                    if (read >= 0xF0)
                        break;
                    if (0x80 <= read && read <= 0xBF)
                        break;
                    if (0xC0 <= read && read <= 0xDF) {
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF)
                            continue;
                        else
                            break;
                    } else if (0xE0 <= read && read <= 0xEF) {
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF) {
                            read = bis.read();
                            if (0x80 <= read && read <= 0xBF) {
                                charset = "UTF-8";
                                break;
                            } else
                                break;
                        } else
                            break;
                    }
                }
                System.out.println(loc + " " + Integer.toHexString(read));
            }
            bis.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return charset;
    }
}

Related Tutorials