init

IT-KIMI_SHI\SINOIT.KIMI

2018-12-07 50eb1d766c470dc6ff927199eaee934f972a8b70

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
package common.util;
 
import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
 
public class CharsetUtil {
    public static String getFilecharset(File sourceFile) {
        String charset = "GBK";
        byte[] first3Bytes = new byte[3];
        try {
            boolean checked = false;
            BufferedInputStream bis = new BufferedInputStream(new FileInputStream(sourceFile));
            bis.mark(0);
            int read = bis.read(first3Bytes, 0, 3);
            if (read == -1) {
                bis.close();
                return charset; // 文件编码为 ANSI
            } else if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
                charset = "UTF-16LE"; // 文件编码为 Unicode
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xFE && first3Bytes[1] == (byte) 0xFF) {
                charset = "UTF-16BE"; // 文件编码为 Unicode big endian
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xEF && first3Bytes[1] == (byte) 0xBB
                    && first3Bytes[2] == (byte) 0xBF) {
                charset = "UTF-8"; // 文件编码为 UTF-8
                checked = true;
            }
            bis.reset();
            if (!checked) {
                while ((read = bis.read()) != -1) {
                    if (read >= 0xF0)
                        break;
                    if (0x80 <= read && read <= 0xBF) // 单独出现BF以下的，也算是GBK
                        break;
                    if (0xC0 <= read && read <= 0xDF) {
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF) // 双字节 (0xC0 - 0xDF)
                            // (0x80
                            // - 0xBF),也可能在GB编码内
                            continue;
                        else
                            break;
                    } else if (0xE0 <= read && read <= 0xEF) {// 也有可能出错，但是几率较小
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF) {
                            read = bis.read();
                            if (0x80 <= read && read <= 0xBF) {
                                charset = "UTF-8";
                                break;
                            } else
                                break;
                        } else
                            break;
                    }
                }
            }
            bis.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return charset;
    }
}