zoukankan      html  css  js  c++  java
  • java通过文件头内容判断文件类型

    转自:http://space.itpub.net/23071790/viewspace-691870

    /**
     * byte数组转换成16进制字符串
     * @param src
     * @return
     */
     public static String bytesToHexString(byte[] src){     
            StringBuilder stringBuilder = new StringBuilder();     
            if (src == null || src.length <= 0) {     
                return null;     
            }     
            for (int i = 0; i < src.length; i++) {     
                int v = src[i] & 0xFF;     
                String hv = Integer.toHexString(v);     
                if (hv.length() < 2) {     
                    stringBuilder.append(0);     
                }     
                stringBuilder.append(hv);     
            }     
            return stringBuilder.toString();     
      }
     
    /**
     * 根据文件流读取图片文件真实类型
     * @param is
     * @return
     */
     public static String getTypeByStream(FileInputStream is){
         byte[] b = new byte[4];  
         try {
           is.read(b, 0, b.length);
        } catch (IOException e) {
           e.printStackTrace();
        }
         String type = bytesToHexString(b).toUpperCase();
         if(type.contains("FFD8FF")){
             return "jpg";
         }else if(type.contains("89504E47")){
             return "png";
         }else if(type.contains("47494638")){
             return "gif";
         }else if(type.contains("49492A00")){
             return "tif";
         }else if(type.contains("424D")){
             return "bmp";
         }
            return type;
    }
    
    public static void main(String[] args) throws Exception {
    //     String src = "D:/workspace//8129.jpg";
    //     String src = "D:/workspace//temp/1.gif";
         String src = "D:/workspace//temp/2.bmp";
         FileInputStream is = new FileInputStream(src);  
    //        byte[] b = new byte[4];  
    //        is.read(b, 0, b.length);  
    //        System.out.println(bytesToHexString(b));
           
            String type = getTypeByStream(is);
            System.out.println(type);
      /*
       * JPEG (jpg),文件头:FFD8FF
    PNG (png),文件头:89504E47
    GIF (gif),文件头:47494638
    TIFF (tif),文件头:49492A00 
    Windows Bitmap (bmp),文件头:424D
    
       */
        }  

    解析:

    用文件头判断。直接读取文件的前几个字节。
    常用文件的文件头如下:
    JPEG (jpg),文件头:FFD8FF
    PNG (png),文件头:89504E47
    GIF (gif),文件头:47494638
    TIFF (tif),文件头:49492A00 
    Windows Bitmap (bmp),文件头:424D
    CAD (dwg),文件头:41433130
    Adobe Photoshop (psd),文件头:38425053
    Rich Text Format (rtf),文件头:7B5C727466
    XML (xml),文件头:3C3F786D6C
    HTML (html),文件头:68746D6C3E
    Email [thorough only] (eml),文件头:44656C69766572792D646174653A
    Outlook Express (dbx),文件头:CFAD12FEC5FD746F 
    Outlook (pst),文件头:2142444E 
    MS Word/Excel (xls.or.doc),文件头:D0CF11E0
    MS Access (mdb),文件头:5374616E64617264204A
    WordPerfect (wpd),文件头:FF575043
    Postscript. (eps.or.ps),文件头:252150532D41646F6265
    Adobe Acrobat (pdf),文件头:255044462D312E
    Quicken (qdf),文件头:AC9EBD8F 
    Windows Password (pwl),文件头:E3828596 
    ZIP Archive (zip),文件头:504B0304 
    RAR Archive (rar),文件头:52617221 
    Wave (wav),文件头:57415645 
    AVI (avi),文件头:41564920 
    Real Audio (ram),文件头:2E7261FD 
    Real Media (rm),文件头:2E524D46 
    MPEG (mpg),文件头:000001BA 
    MPEG (mpg),文件头:000001B3
    Quicktime (mov),文件头:6D6F6F76 
    Windows Media (asf),文件头:3026B2758E66CF11 
    MIDI (mid),文件头:4D546864
    GRAPHICS FILES
    Adobe Photoshop File (.psd)
    00000000  38 42 50 53 00 01 00 00  00 00 00 00 00 04 00 00  |8BPS............|
    00000010  0b 71 00 00 10 dd 00 08  00 03 00 00 00 00 00 00  |.q...?..........|
    00000020  6f c4 38 42 49 4d 04 04  00 00 00 00 00 07 1c 02  |o?8BIM..........|
    
    JPEG image (.jpg)
    00000000  ff d8 ff e0 00 10 4a 46  49 46 00 01 01 01 00 48  |????..JFIF.....H|
    00000010  00 48 00 00 ff db 00 43  00 06 04 05 06 05 04 06  |.H..??.C........|
    00000020  06 05 06 07 07 06 08 0a  10 0a 0a 09 09 0a 14 0e  |................|
    
    PNG image (.png)
    00000000  89 50 4e 47 0d 0a 1a 0a  00 00 00 0d 49 48 44 52  |.PNG........IHDR|
    00000010  00 00 03 20 00 00 02 58  08 06 00 00 00 9a 76 82  |... ...X......v.|
    00000020  70 00 00 0c d9 69 43 43  50 69 63 63 00 00 78 da  |p...?iCCPicc..x?|
    
    GIF image (.gif)
    00000000  47 49 46 38 39 61 10 00  10 00 b3 0d 00 3f 3f 3f  |GIF89a....?..???|
    00000010  bf bf bf 2a 2a 2a 55 55  55 7f 7f 7f 15 15 15 40  |???***UUU......@|
    00000020  40 40 60 60 60 c0 c0 c0  2f 2f 2f 90 90 90 ff ff  |@@```???///...??|
    
    Adobe Illustrator File (.ai)
    00000000  25 50 44 46 2d 31 2e 34  0d 25 e2 e3 cf d3 0d 0a  |%PDF-1.4.%????..|
    00000010  31 20 30 20 6f 62 6a 3c  3c 2f 50 61 67 65 73 20  |1 0 obj<</Pages |
    00000020  32 20 30 20 52 2f 54 79  70 65 2f 43 61 74 61 6c  |2 0 R/Type/Catal|
    MUSIC FILES
    MP3 Music Track (.mp3)
    00000000  49 44 33 03 00 00 00 00  00 6f 54 49 54 32 00 00  |ID3......oTIT2..|
    00000010  00 0e 00 00 00 54 68 65  20 4f 74 68 65 72 20 4d  |.....The Other M|
    00000020  61 6e 54 52 43 4b 00 00  00 02 00 00 00 33 54 50  |anTRCK.......3TP|
    
    WAV file (.wav)
    00000000  52 49 46 46 62 b7 01 00  57 41 56 45 66 6d 74 20  |RIFFb?..WAVEfmt|
    00000010  10 00 00 00 01 00 01 00  44 ac 00 00 88 58 01 00  |........D?...X..|
    00000020  02 00 10 00 64 61 74 61  3e b7 01 00 57 01 bd 01  |....data>?..W.?.|
    
    AIFF file (.aif)
    00000000  46 4f 52 4d 00 2a ef cc  41 49 46 46 43 4f 4d 54  |FORM.*??AIFFCOMT|
    00000010  00 00 01 c2 00 01 00 00  00 00 00 00 00 12 43 72  |...?..........Cr|
    00000020  65 61 74 6f 72 3a 20 4c  6f 67 69 63 20 50 72 6f  |eator: Logic Pro|
    TEXT FILES
    Text file (often .txt, but not always)
    00000000  48 69 20 65 76 65 72 79  6f 6e 65 2c 0a 0a 48 65  |Hi everyone,..He|
    00000010  72 65 20 61 72 65 20 73  6f 6d 65 20 63 68 61 6e  |re are some chan|
    00000020  67 65 73 20 74 68 61 74  20 77 69 6c 6c 20 68 61  |ges that will ha|
    
    Microsoft Word/Office (.doc, .xls)
    00000000d0 cf 11 e0 a1 b1 1a e100 00 00 00 00 00 00 00  |??.....?........|
    00000010  00 00 00 00 00 00 00 00  3e 00 03 00 fe ff 09 00  |........>...??..|
    00000020  06 00 00 00 00 00 00 00  00 00 00 00 01 00 00 00  |................|
    
    Adobe PDF (.pdf) - Very similar to Adobe Illustrator and other Postscript. formats
    00000000  25 50 44 46 2d 31 2e 34  0d 25 e2 e3 cf d3 0d 0a  |%PDF-1.4.%????..|
    00000010  36 20 30 20 6f 62 6a 20  3c 3c 2f 4c 69 6e 65 61  |6 0 obj <</Linea|
    00000020  72 69 7a 65 64 20 31 2f  4c 20 34 34 30 36 38 2f  |rized 1/L 44068/|
    ANIMATION & VIDEO
    Flash movie (.swf)
    00000000  43 57 53 08 ac 43 00 00  78 9c ed 7a 77 58 93 c9  |CWS.?C..x.?zwX.?|
    00000010  d6 f8 49 25 f4 80 94 50  0d 45 4a 00 e9 45 b0 04  |??I%?..P.EJ.?E?.|
    00000020  44 44 45 e9 55 d0 80 44  01 11 10 11 01 75 0d bd  |DDE?U?.D.....u.?|
    
    Quicktime Movie (.mov)
    00000000  00 00 00 20 66 74 79 70  71 74 20 20 20 05 03 00  |... ftypqt   ...|
    00000010  71 74 20 20 00 00 00 00  00 00 00 00 00 00 00 00  |qt............|
    00000020  00 00 03 55 6d 6f 6f 76  00 00 00 6c 6d 76 68 64  |...Umoov...lmvhd|
  • 相关阅读:
    Spring Boot中常用的三个注解
    Idea插件
    Java微服务 在 Linux 环境启停Shell脚本
    注解
    Oracle树状结构层级查询
    zabbix安装部署(server部分)
    zabbix监控系统客户端安装
    Windows 用bat脚本带配置启动redis,并用vb脚本使其在后台运行。
    svn cleanup failed–previous operation has not finished; run cleanup if it was interrupted
    PHP网页显示乱码问题总结
  • 原文地址:https://www.cnblogs.com/tv151579/p/3105328.html
Copyright © 2011-2022 走看看