msdos

UNIX下FILE命令的实现源码

#------------------------------------------------------------------------------
# msdos:  file(1) magic for MS-DOS files
#

# .BAT files (Daniel Quinlan, [e-mail])
0	string	@echo\ off	MS-DOS batch file text

# XXX - according to Microsoft's spec, at an offset of 0x3c in a
# PE-format executable is the offset in the file of the PE header;
# unfortunately, that's a little-endian offset, and there's no way
# to specify an indirect offset with a specified byte order.
# So, for now, we assume the standard MS-DOS stub, which puts the
# PE header at 0x80 = 128.
#
# Required OS version and subsystem version were 4.0 on some NT 3.51
# executables built with Visual C++ 4.0, so it's not clear that
# they're interesting.  The user version was 0.0, but there's
# probably some linker directive to set it.  The linker version was
# 3.0, except for one ".exe" which had it as 4.20 (same damn linker!).
#
128	string		PE\0\0	MS Windows PE
>150	leshort&0x0100	>0	32-bit
>132	leshort		0x0	unknown processor
>132	leshort		0x14c	Intel 80386
>132	leshort		0x166	MIPS R4000
>132	leshort		0x184	Alpha
>132	leshort		0x268	Motorola 68000
>132	leshort		0x1f0	PowerPC
>132	leshort		0x290	PA-RISC
>148	leshort		>27
>>220	leshort		0	unknown subsystem
>>220	leshort		1	native
>>220	leshort		2	GUI
>>220	leshort		3	console
>>220	leshort		7	POSIX
>150	leshort&0x2000	=0	executable
#>>136	ledate		x	stamp %s,
>>150	leshort&0x0001	>0	not relocatable
#>>150	leshort&0x0004	=0	with line numbers,
#>>150	leshort&0x0008	=0	with local symbols,
#>>150	leshort&0x0200	=0	with debug symbols,
>>150	leshort&0x1000	>0	system file
#>>148	leshort		>0
#>>>154	byte		x	linker %d
#>>>155	byte		x	\b.%d,
#>>148	leshort		>27
#>>>192	leshort		x	requires OS %d
#>>>194	leshort		x	\b.%d,
#>>>196	leshort		x	user version %d
#>>>198	leshort		x	\b.%d,
#>>>200	leshort		x	subsystem version %d
#>>>202	leshort		x	\b.%d,
>150	leshort&0x2000	>0	DLL
#>>136	ledate		x	stamp %s,
>>150	leshort&0x0001	>0	not relocatable
#>>150	leshort&0x0004	=0	with line numbers,
#>>150	leshort&0x0008	=0	with local symbols,
#>>150	leshort&0x0200	=0	with debug symbols,
>>150	leshort&0x1000	>0	system file
#>>148	leshort		>0
#>>>154	byte		x	linker %d
#>>>155	byte		x	\b.%d,
#>>148	leshort		>27
#>>>192	leshort		x	requires OS %d
#>>>194	leshort		x	\b.%d,
#>>>196	leshort		x	user version %d
#>>>198	leshort		x	\b.%d,
#>>>200	leshort		x	subsystem version %d
#>>>202	leshort		x	\b.%d,
0	leshort		0x14c	MS Windows COFF Intel 80386 object file
#>4	ledate		x	stamp %s
0	leshort		0x166	MS Windows COFF MIPS R4000 object file
#>4	ledate		x	stamp %s
0	leshort		0x184	MS Windows COFF Alpha object file
#>4	ledate		x	stamp %s
0	leshort		0x268	MS Windows COFF Motorola 68000 object file
#>4	ledate		x	stamp %s
0	leshort		0x1f0	MS Windows COFF PowerPC object file
#>4	ledate		x	stamp %s
0	leshort		0x290	MS Windows COFF PA-RISC object file
#>4	ledate		x	stamp %s

# .EXE formats (Greg Roelofs, [e-mail])
#
0	string	MZ		MS-DOS executable (EXE)
>24	string	@		\b, OS/2 or MS Windows
>>0xe7	string	LH/2\ Self-Extract	\b, %s
>>0xe9	string	PKSFX2		\b, %s
>>122	string	Windows\ self-extracting\ ZIP	\b, %s
>0x1c	string	RJSX\xff\xff	\b, ARJ SFX
>0x1c	string	diet\xf9\x9c	\b, diet compressed
>0x1e	string	Copyright\ 1989-1990\ PKWARE\ Inc.	\b, PKSFX
# JM: 0x1e "PKLITE Copr. 1990-92 PKWARE Inc. All Rights Reserved\7\0\0\0"
>0x1e	string	PKLITE\ Copr.	\b, %.6s compressed
>0x24	string	LHa's\ SFX	\b, %.15s
>0x24	string	LHA's\ SFX	\b, %.15s
>1638	string	-lh5-		\b, LHa SFX archive v2.13S
>7195	string	Rar!		\b, RAR self-extracting archive
#
# [GRR 950118:  file 3.15 has a buffer-size limitation; offsets bigger than
#   8161 bytes are ignored.  To make the following entries work, increase
#   HOWMANY in file.h to 32K at least, and maybe to 70K or more for OS/2,
#   NT/Win32 and VMS.]
# [GRR:  some company sells a self-extractor/displayer for image data(!)]
#
>11696	string	PK\003\004	\b, PKZIP SFX archive v1.1
>13297	string	PK\003\004	\b, PKZIP SFX archive v1.93a
>15588	string	PK\003\004	\b, PKZIP2 SFX archive v1.09
>15770	string	PK\003\004	\b, PKZIP SFX archive v2.04g
>28374	string	PK\003\004	\b, PKZIP2 SFX archive v1.02
#
# Info-ZIP self-extractors
#    these are the DOS versions:
>25115	string	PK\003\004	\b, Info-ZIP SFX archive v5.12
>26331	string	PK\003\004	\b, Info-ZIP SFX archive v5.12 w/decryption
#    these are the OS/2 versions (OS/2 is flagged above):
>47031	string	PK\003\004	\b, Info-ZIP SFX archive v5.12
>49845	string	PK\003\004	\b, Info-ZIP SFX archive v5.12 w/decryption
#    this is the NT/Win32 version:
>69120	string	PK\003\004	\b, Info-ZIP NT SFX archive v5.12 w/decryption
#
# TELVOX Teleinformatica CODEC self-extractor for OS/2:
>49801	string	\x79\xff\x80\xff\x76\xff	\b, CODEC archive v3.21
>>49824	leshort		=1			\b, 1 file
>>49824	leshort		>1			\b, %u files

# .COM formats (Daniel Quinlan, [e-mail])
# Uncommenting only the first two lines will cover about 2/3 of COM files,
# but it isn't feasible to match all COM files since there must be at least
# two dozen different one-byte "magics".
#0	byte		0xe9		MS-DOS executable (COM)
#>6	string	SFX\ of\ LHarc	(%s)
#0	byte		0x8c		MS-DOS executable (COM)
# 0xeb conflicts with "sequent" magic
#0	byte		0xeb		MS-DOS executable (COM)
#0	byte		0xb8		MS-DOS executable (COM)

# miscellaneous formats
0	string		LZ		MS-DOS executable (built-in)
#0	byte		0xf0		MS-DOS program library data
#

#
# Windows NT Registry files.
#
0	string		regf		Windows NT Registry file

# Popular applications
2080	string	Microsoft\ Word\ 6.0\ Document	%s
2080	string	Documento\ Microsoft\ Word\ 6 Spanish Microsoft Word 6 document data
# Pawel Wiecek <[e-mail]> (for polish Word)
2112	string	MSWordDoc			Microsoft Word document data
#
0	belong	0x31be0000			Microsoft Word Document
#
0       string  PO^Q`				Microsoft Word 6.0 Document
#
0	string	\376\067\0\043			Microsoft Office Document
0	string	\320\317\021\340\241\261	Microsoft Office Document
0	string	\333\245-\0\0\0			Microsoft Office Document
#
2080	string	Microsoft\ Excel\ 5.0\ Worksheet	%s
#
# Pawel Wiecek <[e-mail]> (for polish Excel)
2114	string	Biff5		Microsoft Excel 5.0 Worksheet
#
0	belong	0x00001a00	Lotus 1-2-3
>4	belong	0x00100400	wk3 document data
>4	belong	0x02100400	wk4 document data
>4	belong	0x07800100	fm3 or fmb document data
>4	belong	0x07800000	fm3 or fmb document data
#
0	belong	0x00000200 	Lotus 1-2-3
>4	belong	0x06040600	wk1 document data
>4	belong	0x06800200	fmt document data

# Help files
0	string	?_\3\0		MS Windows Help Data

# Microsoft CAB distribution format  Dale Worley <[e-mail]>
0	string		MSCF\000\000\000\000	Microsoft CAB file

#  DeIsL1.isu what this is I don't know
0	string	\161\250\000\000\001\002	DeIsL1.isu whatever that is

# Winamp .avs
#0	string	Nullsoft\ AVS\ Preset\ \060\056\061\032	A plug in for Winamp ms-windows Freeware media player
0	string	Nullsoft\ AVS\ Preset\ 	Winamp plug in

# Hyper terminal:
0	string	HyperTerminal\ 	hyperterm
>15	string	1.0\ --\ HyperTerminal\ data\ file	MS-windows Hyperterminal

# Windows Metafont .WMF
0	string	\327\315\306\232\000\000\000\000\000\000	ms-windows metafont .wmf

#tz3 files whatever that is (MS Works files)
0	string	\003\001\001\004\070\001\000\000	tz3 ms-works file
0	string	\003\002\001\004\070\001\000\000	tz3 ms-works file
0	string	\003\003\001\004\070\001\000\000	tz3 ms-works file

# PGP sig files .sig
#0 string \211\000\077\003\005\000\063\237\127 065 to  \027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\065\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\066\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\067\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\070\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\077\003\005\000\063\237\127\071\027\266\151\064\005\045\101\233\021\002 PGP sig
0 string \211\000\225\003\005\000\062\122\207\304\100\345\042 PGP sig

# windows zips files .dmf
0	string	MDIF\032\000\010\000\000\000\372\046\100\175\001\000\001\036\001\000 Ms-windows special zipped file


# Windows help file FTG FTS
0	string	\164\146\115\122\012\000\000\000\001\000\000\000	ms-windows help cache

# grp old windows 3.1 group files
0 string  \120\115\103\103	Ms-windows 3.1 group files


# lnk files windows symlinks
0	string	\114\000\000\000\001\024\002\000\000\000\000\000\300\000\000\000\000\000\000\106	ms-Windows shortcut

#ico files
0	string	\102\101\050\000\000\000\056\000\000\000\000\000\000\000	Icon for ms-windows
0	string	\000\000\001\000	ms-windows icon resource
>4	byte	1			- 1 icon
>4	byte	>1			- %d icons
>>6	byte	>0			\b, %dx
>>>7	byte	>0			\b%d
>>8	byte	0			\b, 256-colors
>>8	byte	>0			\b, %d-colors


# True Type fonts currently misidentified as raw G3 data

0	string	\000\001\000\000\000 MS-Windows true type font .ttf


# .chr files
0	string	PK\010\010BGI	Borland font 
>4	string	>\0	%s
# then there is a copyright notice


# .bgi files
0	string	pk\010\010BGI	Borland device 
>4	string	>\0	%s
# then there is a copyright notice


# recycled/info the windows trash bin index
9	string	\000\000\000\030\001\000\000\000 ms-windows recycled bin info


##### put in Either Magic/font or Magic/news
# Acroread or something  files wrongly identified as G3  .pfm
# these have the form \000 \001 any? \002 \000 \000
# or \000 \001 any? \022 \000 \000
0	string  \000\001 pfm?
>3	string  \022\000\000Copyright\  yes
>3	string  \002\000\000Copyright\  yes
#>3	string  >\0     oops, not a font file. Cancel that.
#it clashes with ttf files so put it lower down.

# From Doug Lee via a FreeBSD pr
9	string		GERBILDOC	First Choice document
9	string		GERBILDB	First Choice database
9	string		GERBILCLIP	First Choice database
0	string		GERBIL		First Choice device file
9	string		RABBITGRAPH	RabbitGraph file
0	string		DCU1		Borland Delphi .DCU file
0	string		!<spell>	MKS Spell hash list (old format)
0	string		!<spell2>	MKS Spell hash list
0	string		AH		Halo(TM) bitmapped font file
0	leshort		0x601A		Atari ST contiguous executable
>14	lelong		&gt;0		- not stripped
0	leshort		0x601B		Atari ST non-contig executable
>14	lelong		&gt;0		- not stripped
0	lelong		0x08086b70	TurboC BGI file
0	lelong		0x08084b50	TurboC Font file

# WARNING: below line conflicts with Infocom game data Z-machine 3
0	byte		0x03		DBase 3 data file
>0x04	lelong		0		(no records)
>0x04	lelong		>0		(%ld records)
0	byte		0x83		DBase 3 data file with memo(s)
>0x04	lelong		0		(no records)
>0x04	lelong		>0		(%ld records)
0	leshort		0x0006		DBase 3 index file
0	string		PMCC		Windows 3.x .GRP file
1	string		RDC-meg		MegaDots 
>8	byte		>0x2F		version %c
>9	byte		>0x2F		\b.%c file
0	lelong		0x4C
>4	lelong		0x00021401	Windows shortcut file

# DOS EPS Binary File Header
# From: Ed Sznyter <[e-mail]>
0	belong		0xC5D0D3C6	DOS EPS Binary File
>4	long		>0		Postscript starts at byte %d
>>8	long		>0		length %d
>>>12	long		>0		Metafile starts at byte %d
>>>>16	long		>0		length %d
>>>20	long		>0		TIFF starts at byte %d
>>>>24	long		>0		length %d

# TNEF magic From "Joomy" <[e-mail]> 
0	leshort		0x223e9f78	TNEF