常见文件类型识别

根据文件的后缀名识别文件类型并不准确，可以使用文件的头信息进行识别： 

以下是各类文件的头： 

FFD8FFE1=JPEG(jpg)

FFD8FF=JPEG(jpg)

89504E47=PNG(png)

89504E=PNG(png)

47494638=GIF(gif)

474946=GIF(gif)

49492A00=TIFF(tif)

424D46=Windows\ Bitmap(bmp)

424D=Windows\ Bitmap(bmp)

41433130=CAD(dwg)

38425053=Adobe\ Photoshop(psd)

7B5C727466=Rich\ Text\ Format(rtf)

3C3F786D6C=XML(xml)

68746D6C3E=HTML(html)

44656C69766572792D646174653A=Email\ [thorough\ only](eml)

44656C69766572792D646174=Email\ [thorough\ only](eml)

CFAD12FEC5FD746F=Outlook\ Express(dbx)

2142444E=Outlook(pst)

D0CF11E0=MS\ Word/Excel(xls.or.doc)

5374616E64617264204A=MS\ Access(mdb)

FF575043=WordPerfect(wpd)

252150532D41646F6265=Postscript(eps.or.ps)

255044462D312E=Adobe\ Acrobat(pdf)

255044=Adobe\ Acrobat(pdf)

AC9EBD8F=Quicken(qdf)

E3828596=Windows\ Password(pwl)

504B0304=ZIP\ Archive(zip)

504B03=ZIP\ Archive(zip)

52617221=RAR\ Archive(rar)

526172=RAR\ Archive(rar)

57415645=Wave(wav)

41564920=AVI(avi)

2E7261FD=Real\ Audio(ram)

2E524D46=Real\ Media(rm)

000001BA=MPEG(mpg)

000001B3=MPEG(mpg)

6D6F6F76=Quicktime(mov)

3026B2758E66CF11=Windows\ Media(asf)

4D546864=MIDI(mid)

###########################

0xFFD8FF=JPEG(jpg;jpeg)

0x89504E470D0A1A0A=PNG(png)

GIF8=GIF(gif)

0x49492A00=TIFF(tif;tiff)

0x4D4D002A=TIFF(tif;tiff)

BM=Bit\ map(bmp)

0x4A47040E000000=AOL\ ART(art)

0x4A47030E000000=AOL\ ART(art)

0x0A050108=PC\ Paintbrush(pcx)

0xD7CDC69A=Graphics\ Metafile(wmf)

0x01000900=Graphics\ Metafile(wmf)

0x02000900=Graphics\ Metafile(wmf)

0x0100000058000000=Enhanced\ Metafile(emf)

CDR=Corel\ Draw(cdr)

0x41433130=CAD(dwg)

8BPS=Adobe\ Photoshop(psd)

rtf=Rich\ Text\ Format(rtf)

HTML(html;htm;php;php3;php4;phtml;shtml)type

Delivery-date:=Email(eml)

0xCFAD12FE=Outlook\ Express(dbx)

0xD0CF11E0A1B11AE1=MS\ Office/OLE2(doc;xls;dot;ppt;xla;ppa;pps;pot;msi;sdw;db)

Standard J=MS\ Access(mdb;mda;mde;mdt)

0xFF575043=WordPerfect(wpd)

writer=OpenOffice\ Writer(sxw)

calc=OpenOffice\ Calc(sxc)

math=OpenOffice\ Math(sxm)

impress=OpenOffice\ Impress(sxi)

draw=OpenOffice\ Draw(sxd)

<MAKERFILE=Adobe\ FrameMaker(fm)

%!PS-Adobe=PostScript(eps.or.ps;ps;eps)

%PDF-1.=Adobe\ Acrobat(pdf)

0xAC9EBD8F=Quicken(qdf)

0x458600000600=QuickBooks\ Backup(qbb)

0x53520100=Sage(sly.or.srt.or.slt;sly;srt;slt)

SAGEBACKUP=Sage\ Backup(1)

0x576F726450726F=Lotus\ WordPro\ v9(lwp)

0x00001A00051004=Lotus\ 123\ v9(123)

0x00001A0002100400=Lotus\ 123\ v5(wk4)

0x00001A0000100400=Lotus\ 123\ v3(wk3)

0x2000604060=Lotus\ 123\ v1(wk1)

0xE3828596=Windows\ Password(pwl)

0x504B0304=ZIP\ Archive(zip;jar)

0x504B3030=ZIP\ Archive(outdated)(zip)

0x5F27A889=Jar\ Archive

Rar!=RAR\ Archive(rar)

0x1F8B08=GZ\ Archive(gz;tgz)

BZh=BZIP\ Archive(bz2)

0x60EA=ARJ\ Archive(arj)

7z\u96c6'=7\uff0dZIP\ Archive(7z)

WAVE=Wave(wav)

AVI=AVI(avi)

.ra?0=Real\ Audio(ram;ra)

.RMF=Real\ Media(rm)

0x000001BA=MPEG(mpg;mpeg)

0x000001B3=MPEG(mpg;mpeg)

moov=Quicktime(mov)

0x3026B2758E66CF11=Windows\ Media(asf)

<\?wpl=MediaPlayer\ Playlist

MThd=MIDI(mid)

MZ=Win32\ Executable(exe;dll;drv;vxd;sys;ocx;vbx)

MZ=Win16\ Executable(exe;dll;drv;vxd;sys;ocx;vbx)

0x7F454C4601010100=ELF\ Executable(elf;;)

494433=MP3

FFFD74=MP3

FFFA51=MP3

FFFA91=MP3

FFFA71=MP3

FFFA61=MP3

FFFDB0=MP3

FFFB90=MP3

FFFB92=MP3

FFFD74=MP3

FFF368=MP3

FFF374=MP3

FFF340=MP3

EFBBBF=Text(txt)

3F5F0300=Windows_Help

4C4E0200=Windows_Help

MZ.00-02=exe

使用方法如下：

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

public class FileTypeDetector {
	private static Map<String,String> head2FileType = new HashMap<String,String>();
	static{
		head2FileType.put("FFD8FFE1", "jpg");
		head2FileType.put("89504E47", "png");
		head2FileType.put("47494638 ", "gif");
		head2FileType.put("49492A00", "tif");
		head2FileType.put("424D", "bmp");
		head2FileType.put("41433130", "dwg");
		head2FileType.put("38425053 ", "psd");
		head2FileType.put("7B5C727466", "rtf");
		head2FileType.put("3C3F786D6C", "xml");
		head2FileType.put("68746D6C3E ", "html");
		head2FileType.put("44656C69766572792D646174", "eml");
		head2FileType.put("CFAD12FEC5FD746F ", "dbx");
		head2FileType.put("2142444E", "pst");
		head2FileType.put("D0CF11E0", "xls/doc");
		head2FileType.put("5374616E64617264204A", "mdb");
		head2FileType.put("FF575043", "wpd");
		head2FileType.put("252150532D41646F6265", "eps/ps");
		head2FileType.put("255044462D312E", "pdf");
		head2FileType.put("E3828596", "pwl");
		head2FileType.put("504B0304", "zip");
		head2FileType.put("52617221", "rar");
		head2FileType.put("57415645", "wav");
		head2FileType.put("41564920", "avi");
		head2FileType.put("2E7261FD", "ram");
		head2FileType.put("2E524D46", "rm");
		head2FileType.put("000001BA", "mpg");
		head2FileType.put("000001B3", "mpg");
		head2FileType.put("6D6F6F76", "mov");
		head2FileType.put("3026B2758E66CF11", "asf");
		head2FileType.put("4D546864", "mid");
	}
	
	private static String bytesToHexString(String fileName) throws IOException{
        FileInputStream fis = null;
        StringBuilder stringBuilder = new StringBuilder();
        try{
	        fis = new FileInputStream(new File(fileName));
	        byte[] b = new byte[4];
	        fis.read(b, 0, b.length);

	        for (int i = 0; i < b.length; i++) {
	            int v = b[i] & 0xFF;
	            String hv = Integer.toHexString(v);
	            if (hv.length() < 2) {
	                stringBuilder.append(0);
	            }
	            stringBuilder.append(hv);
	        }
        }finally{
        	if(fis != null)
        		fis.close();
        }
        return stringBuilder.toString().toUpperCase();
    }
	
	public static String fileType(String fileName) throws IOException{
		String head = bytesToHexString(fileName);
		return head2FileType.get(head);
	}
	
	public static void main(String[] args) throws IOException {
		System.out.println(fileType("d://aaa.png"));
	}
}

原文地址：http://fuliang.iteye.com/blog/769680