[Checkins] SVN: z3c.filetype/ initial import of z3c.filetype
Bernd Dorn
bernd.dorn at fhv.at
Fri Aug 11 09:56:25 EDT 2006
Log message for revision 69401:
initial import of z3c.filetype
Changed:
A z3c.filetype/
A z3c.filetype/trunk/
A z3c.filetype/trunk/LICENSES.txt
A z3c.filetype/trunk/src/
A z3c.filetype/trunk/src/z3c/
A z3c.filetype/trunk/src/z3c/__init__.py
A z3c.filetype/trunk/src/z3c/filetype/
A z3c.filetype/trunk/src/z3c/filetype/README.txt
A z3c.filetype/trunk/src/z3c/filetype/__init__.py
A z3c.filetype/trunk/src/z3c/filetype/api.py
A z3c.filetype/trunk/src/z3c/filetype/guess.py
A z3c.filetype/trunk/src/z3c/filetype/interfaces/
A z3c.filetype/trunk/src/z3c/filetype/interfaces/__init__.py
A z3c.filetype/trunk/src/z3c/filetype/interfaces/filetypes.py
A z3c.filetype/trunk/src/z3c/filetype/magic.mime
A z3c.filetype/trunk/src/z3c/filetype/magic.py
A z3c.filetype/trunk/src/z3c/filetype/magic.txt
A z3c.filetype/trunk/src/z3c/filetype/testdata/
A z3c.filetype/trunk/src/z3c/filetype/testdata/DS_Store
A z3c.filetype/trunk/src/z3c/filetype/testdata/jumps.mov
A z3c.filetype/trunk/src/z3c/filetype/testdata/logo.gif
A z3c.filetype/trunk/src/z3c/filetype/testdata/test.flv
A z3c.filetype/trunk/src/z3c/filetype/testdata/test.gnutar
A z3c.filetype/trunk/src/z3c/filetype/testdata/test.html
A z3c.filetype/trunk/src/z3c/filetype/testdata/test.png
A z3c.filetype/trunk/src/z3c/filetype/testdata/test.tar
A z3c.filetype/trunk/src/z3c/filetype/testdata/test.tgz
A z3c.filetype/trunk/src/z3c/filetype/testdata/test.txt.gz
A z3c.filetype/trunk/src/z3c/filetype/testdata/test2.html
A z3c.filetype/trunk/src/z3c/filetype/testdata/test2.thml
A z3c.filetype/trunk/src/z3c/filetype/testdata/thumbnailImage_small.jpeg
A z3c.filetype/trunk/src/z3c/filetype/tests.py
-=-
Added: z3c.filetype/trunk/LICENSES.txt
===================================================================
--- z3c.filetype/trunk/LICENSES.txt 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/LICENSES.txt 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,18 @@
+========
+LICENCES
+========
+
+z3c.filetype.magic
+==================
+
+Unknown author without a license as stated in the source:
+
+# Found on a russian zope mailing list, and modified to fix bugs in parsing
+# the magic file and string making
+# -- Daniel Berlin <dberlin at dberlin.org>
+
+magic.mime file
+===============
+
+See attributions in file.
+
Property changes on: z3c.filetype/trunk/LICENSES.txt
___________________________________________________________________
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/__init__.py
===================================================================
--- z3c.filetype/trunk/src/z3c/__init__.py 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/__init__.py 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,23 @@
+##############################################################################
+#
+# Copyright (c) 2004 Zope Corporation and Contributors.
+# All Rights Reserved.
+#
+# This software is subject to the provisions of the Zope Public License,
+# Version 2.1 (ZPL). A copy of the ZPL should accompany this distribution.
+# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
+# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
+# FOR A PARTICULAR PURPOSE.
+#
+##############################################################################
+#
+# This file is necessary to make this directory a package.
+
+try:
+ # Declare this a namespace package if pkg_resources is available.
+ import pkg_resources
+ pkg_resources.declare_namespace('z3c')
+except ImportError:
+ pass
+
Property changes on: z3c.filetype/trunk/src/z3c/__init__.py
___________________________________________________________________
Name: svn:keywords
+ Id
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/README.txt
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/README.txt 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/README.txt 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,76 @@
+================
+Filetype Package
+================
+
+This package provides a way to get interfaces that are provided based
+on their content, filename or mime-type.
+
+ >>> from z3c.filetype import api
+
+We take some files for demonstration from the testdata directory.
+
+ >>> import os
+ >>> testData = os.path.join(os.path.dirname(api.__file__),'testdata')
+
+ >>> fileNames = sorted(os.listdir(testData))
+
+ >>> for name in fileNames:
+ ... path = os.path.join(testData, name)
+ ... i = api.getInterfacesFor(file(path))
+ ... print name
+ ... print i
+ DS_Store
+ set([])
+ jumps.mov
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IVideoFile>])
+ logo.gif
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IGIFFile>])
+ test.flv
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IFLVFile>])
+ test.gnutar
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.ITARFile>])
+ test.html
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IHTMLFile>])
+ test.png
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IPNGFile>])
+ test.tar
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.ITARFile>])
+ test.tgz
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IGZIPFile>])
+ test.txt.gz
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IGZIPFile>])
+ test2.html
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IHTMLFile>])
+ test2.thml
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IHTMLFile>])
+ thumbnailImage_small.jpeg
+ set([<InterfaceClass z3c.filetype.interfaces.filetypes.IJPGFile>])
+
+The filename is only used if no interface is found, because we should
+not trust the filename in most cases.
+
+ >>> f = open(os.path.join(testData, 'test.tar'))
+ >>> sorted(api.getInterfacesFor(f))
+ [<InterfaceClass z3c.filetype.interfaces.filetypes.ITARFile>]
+
+ >>> sorted(api.getInterfacesFor(filename="x.png"))
+ [<InterfaceClass z3c.filetype.interfaces.filetypes.IPNGFile>]
+
+ >>> sorted(api.getInterfacesFor(f, filename="x.png"))
+ [<InterfaceClass z3c.filetype.interfaces.filetypes.ITARFile>]
+
+
+If a mimeType is given then the interfaces derived from it is added to
+the result, regardless if the content of the file tells something
+different.
+
+ >>> sorted(api.getInterfacesFor(f, mimeType="text/plain"))
+ [<InterfaceClass z3c.filetype.interfaces.filetypes.ITARFile>,
+ <InterfaceClass z3c.filetype.interfaces.filetypes.ITextFile>]
+
+You can also provide a path instead of a stream.
+
+ >>> f.name
+ '/.../z3c/filetype/testdata/test.tar'
+ >>> sorted(api.getInterfacesFor(f.name))
+ [<InterfaceClass z3c.filetype.interfaces.filetypes.ITARFile>]
Property changes on: z3c.filetype/trunk/src/z3c/filetype/README.txt
___________________________________________________________________
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/__init__.py
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/__init__.py 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/__init__.py 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1 @@
+#package
Property changes on: z3c.filetype/trunk/src/z3c/filetype/__init__.py
___________________________________________________________________
Name: svn:keywords
+ Id
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/api.py
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/api.py 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/api.py 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,86 @@
+from z3c.filetype import magic
+from interfaces import filetypes
+from zope.contenttype import guess_content_type
+from zope import interface
+
+magicFile = magic.MagicFile()
+
+def byMimeType(t):
+
+ """returns interfaces implemented by mimeType"""
+
+ ifaces = [iface for name, iface in vars(filetypes).items() \
+ if name.startswith("I")]
+ res = InterfaceSet()
+ for iface in ifaces:
+ mtm = iface.queryTaggedValue(filetypes.MTM)
+ if mtm is not None:
+ if mtm.match(t):
+ res.add(iface)
+ return res
+
+def getInterfacesFor(file=None, filename=None, mimeType=None):
+
+ """returns a sequence of interfaces that are provided by file like
+ objects (file argument) with an optional filename as name or
+ mimeType as mime-type
+ """
+
+ ifaces = set()
+ if file is not None:
+ t = magicFile.detect(file)
+ if t is not None:
+ ifaces.update(byMimeType(t))
+ if mimeType is not None:
+ ifaces.update(byMimeType(mimeType))
+ if filename is not None and not ifaces:
+ t = guess_content_type(filename)[0]
+ # dont trust this here because zope does not recognize some
+ # binary files.
+ if t and not t == 'text/x-unknown-content-type':
+ ifaces.update(byMimeType(t))
+ return ifaces
+
+
+class InterfaceSet(object):
+
+ """a set that only holds most specific interfaces
+
+ >>> s = InterfaceSet(filetypes.IBinaryFile, filetypes.IImageFile)
+ >>> sorted(s)
+ [<InterfaceClass z3c.filetype.interfaces.filetypes.IBinaryFile>,
+ <InterfaceClass z3c.filetype.interfaces.filetypes.IImageFile>]
+
+ Now we add a jpeg file which is a subclass of all ifaces in the set
+ >>> s.add(filetypes.IJPGFile)
+ >>> sorted(s)
+ [<InterfaceClass z3c.filetype.interfaces.filetypes.IJPGFile>]
+
+ If we add a new which is not a subclass it is contained
+ >>> s.add(filetypes.ITextFile)
+ >>> sorted(s)
+ [<InterfaceClass z3c.filetype.interfaces.filetypes.IJPGFile>,
+ <InterfaceClass z3c.filetype.interfaces.filetypes.ITextFile>]
+
+ """
+
+ def __init__(self, *ifaces):
+ self._data = set()
+ for iface in ifaces:
+ self.add(iface)
+
+ def add(self, iface):
+ assert(issubclass(iface, interface.Interface))
+ toDelete = set()
+ for i in self._data:
+ if issubclass(i,iface):
+ return
+ if issubclass(iface, i):
+ toDelete.add(i)
+ self._data.add(iface)
+ self._data.difference_update(toDelete)
+
+ def __iter__(self):
+
+ return iter(self._data)
+
Property changes on: z3c.filetype/trunk/src/z3c/filetype/api.py
___________________________________________________________________
Name: svn:keywords
+ Id
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/guess.py
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/guess.py 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/guess.py 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,9 @@
+
+def getInterfacesFor(data=None, filename=None, mimeType=None):
+
+ """returns a sequence of interfaces that are provided by files
+ having data as content, filename as name and mimeType as
+ mime-type
+ """
+ raise NotImplementedError
+
Property changes on: z3c.filetype/trunk/src/z3c/filetype/guess.py
___________________________________________________________________
Name: svn:keywords
+ Id
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/interfaces/__init__.py
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/interfaces/__init__.py 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/interfaces/__init__.py 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1 @@
+# interaces package
Property changes on: z3c.filetype/trunk/src/z3c/filetype/interfaces/__init__.py
___________________________________________________________________
Name: svn:keywords
+ Id
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/interfaces/filetypes.py
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/interfaces/filetypes.py 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/interfaces/filetypes.py 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,75 @@
+from zope import interface
+import re
+
+# mimeTypeMatch holds regular expression for matching mime-types
+MTM = 'mimeTypesMatch'
+# mimeType holds the preferred mime type to be returned for this
+# interface
+MT = "mimeType"
+
+class ITypedFile(interface.Interface):
+ """A Type of a file"""
+
+class IBinaryFile(ITypedFile):
+ """Binary file"""
+IBinaryFile.setTaggedValue(MTM,re.compile('application/octet-stream'))
+IBinaryFile.setTaggedValue(MT,'application/octet-stream')
+
+class ITARFile(ITypedFile):
+ """Binary file"""
+ITARFile.setTaggedValue(MTM,re.compile('application/x-tar'))
+ITARFile.setTaggedValue(MT,'application/x-tar')
+
+class IGZIPFile(ITypedFile):
+ """Binary file"""
+IGZIPFile.setTaggedValue(MTM,re.compile('application/x-gzip'))
+IGZIPFile.setTaggedValue(MT,'application/x-gzip')
+
+class ITextFile(ITypedFile):
+ """text files"""
+ITextFile.setTaggedValue(MTM,re.compile('^text/.+$'))
+ITextFile.setTaggedValue(MT,'text/plain')
+
+class IImageFile(ITypedFile):
+ """image files"""
+IImageFile.setTaggedValue(MTM,re.compile('^image/.+$'))
+
+class IJPGFile(IImageFile, IBinaryFile):
+ """jpeg file"""
+IJPGFile.setTaggedValue(MTM,re.compile('image/jpe?g'))
+IJPGFile.setTaggedValue(MT,'image/jpeg')
+
+class IPNGFile(IImageFile, IBinaryFile):
+ """png file"""
+IPNGFile.setTaggedValue(MTM,re.compile('image/png'))
+IPNGFile.setTaggedValue(MT,'image/png')
+
+class IGIFFile(IImageFile, IBinaryFile):
+ """gif file"""
+IGIFFile.setTaggedValue(MTM,re.compile('image/gif'))
+IGIFFile.setTaggedValue(MT,'image/gif')
+
+class IVideoFile(ITypedFile):
+ """video file"""
+IVideoFile.setTaggedValue(MTM,re.compile('^video/.+$'))
+
+class IFLVFile(IVideoFile, IBinaryFile):
+ """Macromedia Flash FLV Video File Format"""
+IFLVFile.setTaggedValue(MTM,re.compile('video/x-flv'))
+IFLVFile.setTaggedValue(MT,'video/x-flv')
+
+class IAudioFile(ITypedFile):
+ """audio file"""
+IAudioFile.setTaggedValue(MTM,re.compile('^audio/.+$'))
+
+class IHTMLFile(ITextFile):
+ """HTML file"""
+IHTMLFile.setTaggedValue(MTM,re.compile('text/html'))
+IHTMLFile.setTaggedValue(MT,'text/html')
+
+class IXMLFile(ITextFile):
+ """XML File"""
+IXMLFile.setTaggedValue(MTM,re.compile('text/xml'))
+IXMLFile.setTaggedValue(MT,'text/xml')
+
+
Property changes on: z3c.filetype/trunk/src/z3c/filetype/interfaces/filetypes.py
___________________________________________________________________
Name: svn:keywords
+ Id
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/magic.mime
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/magic.mime 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/magic.mime 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,916 @@
+# Magic data for KMimeMagic (originally for file(1) command)
+#
+# The format is 4-5 columns:
+# Column #1: byte number to begin checking from, ">" indicates continuation
+# Column #2: type of data to match
+# Column #3: contents of data to match
+# Column #4: MIME type of result
+# Column #5: MIME encoding of result (optional)
+
+#------------------------------------------------------------------------------
+# Localstuff: file(1) magic for locally observed files
+# Add any locally observed files here.
+
+# Real Audio (Magic .ra\0375)
+0 belong 0x2e7261fd audio/x-pn-realaudio
+0 string .RMF application/vnd.rn-realmedia
+
+#video/x-pn-realvideo
+#video/vnd.rn-realvideo
+#application/vnd.rn-realmedia
+# sigh, there are many mimes for that but the above are the most common.
+
+# Taken from magic, converted to magic.mime
+# mime types according to http://www.geocities.com/nevilo/mod.htm:
+# audio/it .it
+# audio/x-zipped-it .itz
+# audio/xm fasttracker modules
+# audio/x-s3m screamtracker modules
+# audio/s3m screamtracker modules
+# audio/x-zipped-mod mdz
+# audio/mod mod
+# audio/x-mod All modules (mod, s3m, 669, mtm, med, xm, it, mdz, stm, itz, xmz, s3z)
+
+# Taken from loader code from mikmod version 2.14
+# by Steve McIntyre (stevem at chiark.greenend.org.uk)
+# <doj at cubic.org> added title printing on 2003-06-24
+0 string MAS_UTrack_V00
+>14 string >/0 audio/x-mod
+#audio/x-tracker-module
+
+#0 string UN05 MikMod UNI format module sound data
+
+0 string Extended\ Module: audio/x-mod
+#audio/x-tracker-module
+##>17 string >\0 Title: "%s"
+
+21 string/c !SCREAM! audio/x-mod
+#audio/x-screamtracker-module
+21 string BMOD2STM audio/x-mod
+#audio/x-screamtracker-module
+1080 string M.K. audio/x-mod
+#audio/x-protracker-module
+#>0 string >\0 Title: "%s"
+1080 string M!K! audio/x-mod
+#audio/x-protracker-module
+#>0 string >\0 Title: "%s"
+1080 string FLT4 audio/x-mod
+#audio/x-startracker-module
+#>0 string >\0 Title: "%s"
+1080 string FLT8 audio/x-mod
+#audio/x-startracker-module
+#>0 string >\0 Title: "%s"
+1080 string 4CHN audio/x-mod
+#audio/x-fasttracker-module
+#>0 string >\0 Title: "%s"
+1080 string 6CHN audio/x-mod
+#audio/x-fasttracker-module
+#>0 string >\0 Title: "%s"
+1080 string 8CHN audio/x-mod
+#audio/x-fasttracker-module
+#>0 string >\0 Title: "%s"
+1080 string CD81 audio/x-mod
+#audio/x-oktalyzer-tracker-module
+#>0 string >\0 Title: "%s"
+1080 string OKTA audio/x-mod
+#audio/x-oktalyzer-tracker-module
+#>0 string >\0 Title: "%s"
+# Not good enough.
+#1082 string CH
+#>1080 string >/0 %.2s-channel Fasttracker "oktalyzer" module sound data
+1080 string 16CN audio/x-mod
+#audio/x-taketracker-module
+#>0 string >\0 Title: "%s"
+1080 string 32CN audio/x-mod
+#audio/x-taketracker-module
+#>0 string >\0 Title: "%s"
+
+# Impuse tracker module (it)
+0 string IMPM audio/x-mod
+#>4 string >\0 "%s"
+#>40 leshort !0 compatible w/ITv%x
+#>42 leshort !0 created w/ITv%x
+
+#------------------------------------------------------------------------------
+# end local stuff
+#------------------------------------------------------------------------------
+
+# xml based formats!
+
+# svg
+
+0 string \<?xml
+# text/xml
+>38 string \<\!DOCTYPE\040svg image/svg+xml
+
+
+# xml
+0 string \<?xml text/xml
+
+
+#------------------------------------------------------------------------------
+# Java
+
+0 short 0xcafe
+>2 short 0xbabe application/java
+
+#------------------------------------------------------------------------------
+# audio: file(1) magic for sound formats
+#
+# from Jan Nicolai Langfeldt <janl at ifi.uio.no>,
+#
+
+# Sun/NeXT audio data
+0 string .snd
+>12 belong 1 audio/basic
+>12 belong 2 audio/basic
+>12 belong 3 audio/basic
+>12 belong 4 audio/basic
+>12 belong 5 audio/basic
+>12 belong 6 audio/basic
+>12 belong 7 audio/basic
+
+>12 belong 23 audio/x-adpcm
+
+# DEC systems (e.g. DECstation 5000) use a variant of the Sun/NeXT format
+# that uses little-endian encoding and has a different magic number
+# (0x0064732E in little-endian encoding).
+0 lelong 0x0064732E
+>12 lelong 1 audio/x-dec-basic
+>12 lelong 2 audio/x-dec-basic
+>12 lelong 3 audio/x-dec-basic
+>12 lelong 4 audio/x-dec-basic
+>12 lelong 5 audio/x-dec-basic
+>12 lelong 6 audio/x-dec-basic
+>12 lelong 7 audio/x-dec-basic
+# compressed (G.721 ADPCM)
+>12 lelong 23 audio/x-dec-adpcm
+
+# Bytes 0-3 of AIFF, AIFF-C, & 8SVX audio files are "FORM"
+# AIFF audio data
+8 string AIFF audio/x-aiff
+# AIFF-C audio data
+8 string AIFC audio/x-aiff
+# IFF/8SVX audio data
+8 string 8SVX audio/x-aiff
+
+
+
+# Creative Labs AUDIO stuff
+# Standard MIDI data
+0 string MThd audio/unknown
+#>9 byte >0 (format %d)
+#>11 byte >1 using %d channels
+# Creative Music (CMF) data
+0 string CTMF audio/unknown
+# SoundBlaster instrument data
+0 string SBI audio/unknown
+# Creative Labs voice data
+0 string Creative\ Voice\ File audio/unknown
+## is this next line right? it came this way...
+#>19 byte 0x1A
+#>23 byte >0 - version %d
+#>22 byte >0 \b.%d
+
+# [GRR 950115: is this also Creative Labs? Guessing that first line
+# should be string instead of unknown-endian long...]
+#0 long 0x4e54524b MultiTrack sound data
+#0 string NTRK MultiTrack sound data
+#>4 long x - version %ld
+
+# Microsoft WAVE format (*.wav)
+# [GRR 950115: probably all of the shorts and longs should be leshort/lelong]
+# Microsoft RIFF
+0 string RIFF
+# - WAVE format
+>8 string WAVE audio/x-wav
+>8 string AVI video/x-msvideo
+#
+0 belong 0x2e7261fd application/x-realaudio
+>8 string CDRA image/x-coreldraw
+
+
+# MPEG Layer 3 sound files
+#0 beshort &0xffe0 audio/mpeg
+#MP3 with ID3 tag
+0 string ID3 audio/mpeg
+# Ogg/Vorbis
+0 string OggS application/ogg
+
+#------------------------------------------------------------------------------
+# c-lang: file(1) magic for C programs or various scripts
+#
+
+# XPM icons (Greg Roelofs, newt at uchicago.edu)
+# ideally should go into "images", but entries below would tag XPM as C source
+0 string /*\ XPM image/x-xpm 7bit
+
+# 3DS (3d Studio files)
+16 beshort 0x3d3d image/x-3ds
+
+# this first will upset you if you're a PL/1 shop... (are there any left?)
+# in which case rm it; ascmagic will catch real C programs
+# C or REXX program text
+#0 string /* text/x-c
+# C++ program text
+#0 string // text/x-c++
+
+#------------------------------------------------------------------------------
+# commands: file(1) magic for various shells and interpreters
+#
+#0 string :\ shell archive or commands for antique kernel text
+0 string #!/bin/sh application/x-shellscript
+0 string #!\ /bin/sh application/x-shellscript
+0 string #!/bin/csh application/x-shellscript
+0 string #!\ /bin/csh application/x-shellscript
+# korn shell magic, sent by George Wu, gwu at clyde.att.com
+0 string #!/bin/ksh application/x-shellscript
+0 string #!\ /bin/ksh application/x-shellscript
+0 string #!/bin/tcsh application/x-shellscript
+0 string #!\ /bin/tcsh application/x-shellscript
+0 string #!/usr/local/tcsh application/x-shellscript
+0 string #!\ /usr/local/tcsh application/x-shellscript
+0 string #!/usr/local/bin/tcsh application/x-shellscript
+0 string #!\ /usr/local/bin/tcsh application/x-shellscript
+# bash shell magic, from Peter Tobias (tobias at server.et-inf.fho-emden.de)
+0 string #!/bin/bash application/x-shellscript
+0 string #!\ /bin/bash application/x-shellscript
+0 string #!/usr/local/bin/bash application/x-shellscript
+0 string #!\ /usr/local/bin/bash application/x-shellscript
+
+#
+# zsh/ash/ae/nawk/gawk magic from cameron at cs.unsw.oz.au (Cameron Simpson)
+0 string #!/bin/zsh application/x-shellscript
+0 string #!/usr/bin/zsh application/x-shellscript
+0 string #!/usr/local/bin/zsh application/x-shellscript
+0 string #!\ /usr/local/bin/zsh application/x-shellscript
+0 string #!/usr/local/bin/ash application/x-shellscript
+0 string #!\ /usr/local/bin/ash application/x-shellscript
+#0 string #!/usr/local/bin/ae Neil Brown's ae
+#0 string #!\ /usr/local/bin/ae Neil Brown's ae
+0 string #!/bin/nawk application/x-nawk
+0 string #!\ /bin/nawk application/x-nawk
+0 string #!/usr/bin/nawk application/x-nawk
+0 string #!\ /usr/bin/nawk application/x-nawk
+0 string #!/usr/local/bin/nawk application/x-nawk
+0 string #!\ /usr/local/bin/nawk application/x-nawk
+0 string #!/bin/gawk application/x-gawk
+0 string #!\ /bin/gawk application/x-gawk
+0 string #!/usr/bin/gawk application/x-gawk
+0 string #!\ /usr/bin/gawk application/x-gawk
+0 string #!/usr/local/bin/gawk application/x-gawk
+0 string #!\ /usr/local/bin/gawk application/x-gawk
+#
+0 string #!/bin/awk application/x-awk
+0 string #!\ /bin/awk application/x-awk
+0 string #!/usr/bin/awk application/x-awk
+0 string #!\ /usr/bin/awk application/x-awk
+0 string BEGIN application/x-awk
+
+# For Larry Wall's perl language. The ``eval'' line recognizes an
+# outrageously clever hack for USG systems.
+# Keith Waclena <keith at cerberus.uchicago.edu>
+0 string #!/bin/perl application/x-perl
+0 string #!\ /bin/perl application/x-perl
+0 string eval\ "exec\ /bin/perl application/x-perl
+0 string #!/usr/bin/perl application/x-perl
+0 string #!\ /usr/bin/perl application/x-perl
+0 string eval\ "exec\ /usr/bin/perl application/x-perl
+0 string #!/usr/local/bin/perl application/x-perl
+0 string #!\ /usr/local/bin/perl application/x-perl
+0 string eval\ "exec\ /usr/local/bin/perl application/x-perl
+
+#------------------------------------------------------------------------------
+# compress: file(1) magic for pure-compression formats (no archives)
+#
+# compress, gzip, pack, compact, huf, squeeze, crunch, freeze, yabba, whap, etc.
+#
+# Formats for various forms of compressed data
+# Formats for "compress" proper have been moved into "compress.c",
+# because it tries to uncompress it to figure out what's inside.
+
+# standard unix compress
+0 string \037\235 application/x-compress
+
+# gzip (GNU zip, not to be confused with [Info-ZIP/PKWARE] zip archiver)
+0 string \037\213 application/x-gzip
+
+0 string PK\003\004 application/x-zip
+
+# RAR archiver (Greg Roelofs, newt at uchicago.edu)
+0 string Rar! application/x-rar
+
+# According to gzip.h, this is the correct byte order for packed data.
+0 string \037\036 application/octet-stream
+#
+# This magic number is byte-order-independent.
+#
+0 short 017437 application/octet-stream
+
+# XXX - why *two* entries for "compacted data", one of which is
+# byte-order independent, and one of which is byte-order dependent?
+#
+# compacted data
+0 short 0x1fff application/octet-stream
+0 string \377\037 application/octet-stream
+# huf output
+0 short 0145405 application/octet-stream
+
+# Squeeze and Crunch...
+# These numbers were gleaned from the Unix versions of the programs to
+# handle these formats. Note that I can only uncrunch, not crunch, and
+# I didn't have a crunched file handy, so the crunch number is untested.
+# Keith Waclena <keith at cerberus.uchicago.edu>
+#0 leshort 0x76FF squeezed data (CP/M, DOS)
+#0 leshort 0x76FE crunched data (CP/M, DOS)
+
+# Freeze
+#0 string \037\237 Frozen file 2.1
+#0 string \037\236 Frozen file 1.0 (or gzip 0.5)
+
+# lzh?
+#0 string \037\240 LZH compressed data
+
+257 string ustar application/x-tar posix
+257 string ustar\040\040 application/x-tar gnu
+
+0 short 070707 application/x-cpio
+0 short 0143561 application/x-cpio swapped
+
+0 string =<ar> application/x-archive
+0 string !<arch>ch> application/x-archive
+>8 string debian application/x-debian-package
+
+#------------------------------------------------------------------------------
+#
+# RPM: file(1) magic for Red Hat Packages Erik Troan (ewt at redhat.com)
+#
+0 beshort 0xedab
+>2 beshort 0xeedb application/x-rpm
+
+0 lelong&0x8080ffff 0x0000081a application/x-arc lzw
+0 lelong&0x8080ffff 0x0000091a application/x-arc squashed
+0 lelong&0x8080ffff 0x0000021a application/x-arc uncompressed
+0 lelong&0x8080ffff 0x0000031a application/x-arc packed
+0 lelong&0x8080ffff 0x0000041a application/x-arc squeezed
+0 lelong&0x8080ffff 0x0000061a application/x-arc crunched
+
+0 leshort 0xea60 application/x-arj
+
+# LHARC/LHA archiver (Greg Roelofs, newt at uchicago.edu)
+2 string -lh0- application/x-lharc lh0
+2 string -lh1- application/x-lharc lh1
+2 string -lz4- application/x-lharc lz4
+2 string -lz5- application/x-lharc lz5
+# [never seen any but the last; -lh4- reported in comp.compression:]
+2 string -lzs- application/x-lha lzs
+2 string -lh\ - application/x-lha lh
+2 string -lhd- application/x-lha lhd
+2 string -lh2- application/x-lha lh2
+2 string -lh3- application/x-lha lh3
+2 string -lh4- application/x-lha lh4
+2 string -lh5- application/x-lha lh5
+2 string -lh6- application/x-lha lh6
+2 string -lh7- application/x-lha lh7
+# Shell archives
+10 string #\ This\ is\ a\ shell\ archive application/octet-stream x-shell
+
+#------------------------------------------------------------------------------
+# frame: file(1) magic for FrameMaker files
+#
+# This stuff came on a FrameMaker demo tape, most of which is
+# copyright, but this file is "published" as witness the following:
+#
+0 string \<MakerFile application/x-frame
+0 string \<MIFFile application/x-frame
+0 string \<MakerDictionary application/x-frame
+0 string \<MakerScreenFon application/x-frame
+0 string \<MML application/x-frame
+0 string \<Book application/x-frame
+0 string \<Maker application/x-frame
+
+#------------------------------------------------------------------------------
+# html: file(1) magic for HTML (HyperText Markup Language) docs
+#
+# from Daniel Quinlan <quinlan at yggdrasil.com>
+#
+0 string \<HEAD text/html
+0 string \<head text/html
+0 string \<TITLE text/html
+0 string \<title text/html
+0 string \<html text/html
+0 string \<HTML text/html
+0 string \<!-- text/html
+0 string \<h1 text/html
+0 string \<H1 text/html
+0 string \<!doctype\ HTML text/html
+0 string \<!DOCTYPE\ HTML text/html
+0 string \<!doctype\ html text/html
+0 string \<!doctype\ HTML text/html
+
+#------------------------------------------------------------------------------
+# images: file(1) magic for image formats (see also "c-lang" for XPM bitmaps)
+#
+# originally from jef at helios.ee.lbl.gov (Jef Poskanzer),
+# additions by janl at ifi.uio.no as well as others. Jan also suggested
+# merging several one- and two-line files into here.
+#
+# XXX - byte order for GIF and TIFF fields?
+# [GRR: TIFF allows both byte orders; GIF is probably little-endian]
+#
+
+# [GRR: what the hell is this doing in here?]
+#0 string xbtoa btoa'd file
+
+# PBMPLUS
+# PBM file
+0 string P1 image/x-portable-bitmap 7bit
+# PGM file
+0 string P2 image/x-portable-greymap 7bit
+# PPM file
+0 string P3 image/x-portable-pixmap 7bit
+# PBM "rawbits" file
+0 string P4 image/x-portable-bitmap
+# PGM "rawbits" file
+0 string P5 image/x-portable-greymap
+# PPM "rawbits" file
+0 string P6 image/x-portable-pixmap
+
+# NIFF (Navy Interchange File Format, a modification of TIFF)
+# [GRR: this *must* go before TIFF]
+0 string IIN1 image/x-niff
+
+# TIFF and friends
+# TIFF file, big-endian
+0 string MM image/tiff
+# TIFF file, little-endian
+0 string II image/tiff
+
+# possible GIF replacements; none yet released!
+# (Greg Roelofs, newt at uchicago.edu)
+#
+# GRR 950115: this was mine ("Zip GIF"):
+# ZIF image (GIF+deflate alpha)
+0 string GIF94z image/unknown
+#
+# GRR 950115: this is Jeremy Wohl's Free Graphics Format (better):
+# FGF image (GIF+deflate beta)
+0 string FGF95a image/unknown
+#
+# GRR 950115: this is Thomas Boutell's Portable Bitmap Format proposal
+# (best; not yet implemented):
+# PBF image (deflate compression)
+0 string PBF image/unknown
+
+# GIF
+0 string GIF image/gif
+
+# JPEG images
+0 beshort 0xffd8 image/jpeg
+
+# PC bitmaps (OS/2, Windoze BMP files) (Greg Roelofs, newt at uchicago.edu)
+0 string BM image/bmp
+#>14 byte 12 (OS/2 1.x format)
+#>14 byte 64 (OS/2 2.x format)
+#>14 byte 40 (Windows 3.x format)
+#0 string IC icon
+#0 string PI pointer
+#0 string CI color icon
+#0 string CP color pointer
+#0 string BA bitmap array
+
+# CDROM Filesystems
+32769 string CD001 application/x-iso9660
+
+# StuffIt X
+0 string StuffIt! application/x-stuffitx
+
+# Newer StuffIt archives (grant at netbsd.org)
+0 string StuffIt application/x-stuffit
+#>162 string >0 : %s
+
+# BinHex is the Macintosh ASCII-encoded file format (see also "apple")
+# Daniel Quinlan, quinlan at yggdrasil.com
+11 string must\ be\ converted\ with\ BinHex\ 4 application/mac-binhex40
+##>41 string x \b, version %.3s
+
+
+#------------------------------------------------------------------------------
+# lisp: file(1) magic for lisp programs
+#
+# various lisp types, from Daniel Quinlan (quinlan at yggdrasil.com)
+0 string ;; text/plain 8bit
+# Emacs 18 - this is always correct, but not very magical.
+0 string \012( application/x-elc
+# Emacs 19
+0 string ;ELC\023\000\000\000 application/x-elc
+
+#------------------------------------------------------------------------------
+# mail.news: file(1) magic for mail and news
+#
+# There are tests to ascmagic.c to cope with mail and news.
+0 string Relay-Version: message/rfc822 7bit
+0 string #!\ rnews message/rfc822 7bit
+0 string N#!\ rnews message/rfc822 7bit
+0 string Forward\ to message/rfc822 7bit
+0 string Pipe\ to message/rfc822 7bit
+0 string Return-Path: message/rfc822 7bit
+0 string Received: message/rfc822
+0 string Path: message/news 8bit
+0 string Xref: message/news 8bit
+0 string From: message/rfc822 7bit
+0 string Article message/news 8bit
+#------------------------------------------------------------------------------
+# msword: file(1) magic for MS Word files
+#
+# Contributor claims:
+# Reversed-engineered MS Word magic numbers
+#
+
+0 string \376\067\0\043 application/msword
+0 string \320\317\021\340\241\261 application/msword
+0 string \333\245-\0\0\0 application/msword
+
+
+
+#------------------------------------------------------------------------------
+# printer: file(1) magic for printer-formatted files
+#
+
+# PostScript
+0 string %! application/postscript
+0 string \004%! application/postscript
+
+# Acrobat
+# (due to clamen at cs.cmu.edu)
+0 string %PDF- application/pdf
+
+#------------------------------------------------------------------------------
+# sc: file(1) magic for "sc" spreadsheet
+#
+38 string Spreadsheet application/x-sc
+
+#------------------------------------------------------------------------------
+# tex: file(1) magic for TeX files
+#
+# XXX - needs byte-endian stuff (big-endian and little-endian DVI?)
+#
+# From <conklin at talisman.kaleida.com>
+
+# Although we may know the offset of certain text fields in TeX DVI
+# and font files, we can't use them reliably because they are not
+# zero terminated. [but we do anyway, christos]
+0 string \367\002 application/x-dvi
+#0 string \367\203 TeX generic font data
+#0 string \367\131 TeX packed font data
+#0 string \367\312 TeX virtual font data
+#0 string This\ is\ TeX, TeX transcript text
+#0 string This\ is\ METAFONT, METAFONT transcript text
+
+# There is no way to detect TeX Font Metric (*.tfm) files without
+# breaking them apart and reading the data. The following patterns
+# match most *.tfm files generated by METAFONT or afm2tfm.
+2 string \000\021 application/x-tex-tfm
+2 string \000\022 application/x-tex-tfm
+#>34 string >\0 (%s)
+
+# Texinfo and GNU Info, from Daniel Quinlan (quinlan at yggdrasil.com)
+0 string \\input\ texinfo text/x-texinfo
+0 string This\ is\ Info\ file text/x-info
+
+# correct TeX magic for Linux (and maybe more)
+# from Peter Tobias (tobias at server.et-inf.fho-emden.de)
+#
+0 leshort 0x02f7 application/x-dvi
+
+# RTF - Rich Text Format
+0 string {\\rtf text/rtf
+
+#------------------------------------------------------------------------------
+# animation: file(1) magic for animation/movie formats
+#
+# animation formats, originally from vax at ccwf.cc.utexas.edu (VaX#n8)
+# MPEG file
+0 belong 0x000001b3 video/mpeg
+0 belong 0x000001ba video/mpeg
+# FLI animation format
+0 leshort 0xAF11 video/fli
+# FLC animation format
+0 leshort 0xAF12 video/flc
+# AVI
+>8 string AVI\ video/avi
+#
+# SGI and Apple formats
+#
+0 string MOVI video/sgi
+4 string moov video/quicktime moov
+4 string mdat video/quicktime mdat
+# The contributor claims:
+# I couldn't find a real magic number for these, however, this
+# -appears- to work. Note that it might catch other files, too,
+# so BE CAREFUL!
+#
+# Note that title and author appear in the two 20-byte chunks
+# at decimal offsets 2 and 22, respectively, but they are XOR'ed with
+# 255 (hex FF)! DL format SUCKS BIG ROCKS.
+#
+# DL file version 1 , medium format (160x100, 4 images/screen)
+0 byte 1 video/unknown
+0 byte 2 video/unknown
+#
+# Databases
+#
+# GDBM magic numbers
+# Will be maintained as part of the GDBM distribution in the future.
+# <downsj at teeny.org>
+0 belong 0x13579ace application/x-gdbm
+0 lelong 0x13579ace application/x-gdbm
+0 string GDBM application/x-gdbm
+#
+0 belong 0x061561 application/x-dbm
+#
+# Executables
+#
+0 string \177ELF
+>4 byte 0
+>4 byte 1
+>4 byte 2
+>5 byte 0
+>5 byte 1
+>>16 leshort 0
+>>16 leshort 1 application/x-object
+>>16 leshort 2 application/x-executable
+>>16 leshort 3 application/x-sharedlib
+>>16 leshort 4 application/x-coredump
+#
+# DOS
+0 string MZ application/x-dosexec
+#
+# KDE
+0 string [KDE\ Desktop\ Entry] application/x-kdelnk
+0 string \#\ KDE\ Config\ File application/x-kdelnk
+# xmcd database file for kscd
+0 string \#\ xmcd text/xmcd
+
+#------------------------------------------------------------------------------
+# pkgadd: file(1) magic for SysV R4 PKG Datastreams
+#
+0 string #\ PaCkAgE\ DaTaStReAm application/x-svr4-package
+
+#PNG Image Format
+0 string \x89PNG image/png
+
+# MNG Video Format, <URL:http://www.libpng.org/pub/mng/spec/>
+0 string \x8aMNG video/x-mng
+0 string \x8aJNG video/x-jng
+
+#------------------------------------------------------------------------------
+# Hierarchical Data Format, used to facilitate scientific data exchange
+# specifications at http://hdf.ncsa.uiuc.edu/
+0 belong 0x0e031301 Hierarchical Data Format (version 4) data
+0 string \211HDF\r\n\032 Hierarchical Data Format (version 5) data
+
+# Adobe Photoshop
+0 string 8BPS image/x-photoshop
+
+# Felix von Leitner <felix-file at fefe.de>
+0 string d8:announce application/x-bittorrent
+
+
+# lotus 1-2-3 document
+0 belong 0x00001a00 application/x-123
+0 belong 0x00000200 application/x-123
+
+# MS Access database
+4 string Standard\ Jet\ DB application/msaccess
+
+## magic for XBase files
+#0 byte 0x02
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0x03
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0x04
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0x05
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0x30
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0x43
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0x7b
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0x83
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0x8b
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0x8e
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0xb3
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 byte 0xf5
+#>8 leshort >0
+#>>12 leshort 0 application/x-dbf
+#
+#0 leshort 0x0006 application/x-dbt
+
+# Debian has entries for the old PGP formats:
+# pgp: file(1) magic for Pretty Good Privacy
+# see http://lists.gnupg.org/pipermail/gnupg-devel/1999-September/016052.html
+0 beshort 0x9900 text/PGP key public ring
+0 beshort 0x9501 text/PGP key security ring
+0 beshort 0x9500 text/PGP key security ring
+0 beshort 0xa600 text/PGP encrypted data
+0 string -----BEGIN\040PGP text/PGP armored data
+>15 string PUBLIC\040KEY\040BLOCK- public key block
+>15 string MESSAGE- message
+>15 string SIGNED\040MESSAGE- signed message
+>15 string PGP\040SIGNATURE- signature
+0 beshort 0x8501 data
+#
+# GnuPG Magic:
+#
+0 beshort 0x9901 text/GnuPG key public ring
+0 beshort 0x8501 text/OpenPGP data
+
+# flash: file(1) magic for Macromedia Flash file format
+#
+# See
+#
+# http://www.macromedia.com/software/flash/open/
+#
+0 string FWS
+>3 byte x application/x-shockwave-flash
+
+# The following paramaters are created for Namazu.
+# <http://www.namazu.org/>
+#
+# 1999/08/13
+#0 string \<!--\ MHonArc text/html; x-type=mhonarc
+0 string BZh application/x-bzip2
+
+# 1999/09/09
+# VRML (suggested by Masao Takaku)
+0 string #VRML\ V1.0\ ascii model/vrml
+0 string #VRML\ V2.0\ utf8 model/vrml
+
+#------------------------------------------------------------------------------
+# ichitaro456: file(1) magic for Just System Word Processor Ichitaro
+#
+# Contributor kenzo-:
+# Reversed-engineered JS Ichitaro magic numbers
+#
+
+0 string DOC
+>43 byte 0x14 application/ichitaro4
+>144 string JDASH application/ichitaro4
+
+0 string DOC
+>43 byte 0x15 application/ichitaro5
+
+0 string DOC
+>43 byte 0x16 application/ichitaro6
+
+#------------------------------------------------------------------------------
+# office97: file(1) magic for MicroSoft Office files
+#
+# Contributor kenzo-:
+# Reversed-engineered MS Office magic numbers
+#
+
+#0 string \320\317\021\340\241\261\032\341
+#>48 byte 0x1B application/excel
+
+2080 string Microsoft\ Excel\ 5.0\ Worksheet application/excel
+2114 string Biff5 application/excel
+
+0 string \224\246\056 application/msword
+
+0 belong 0x31be0000 application/msword
+
+0 string PO^Q` application/msword
+
+0 string \320\317\021\340\241\261\032\341
+>546 string bjbj application/msword
+>546 string jbjb application/msword
+
+512 string R\0o\0o\0t\0\ \0E\0n\0t\0r\0y application/msword
+
+2080 string Microsoft\ Word\ 6.0\ Document application/msword
+2080 string Documento\ Microsoft\ Word\ 6 application/msword
+2112 string MSWordDoc application/msword
+
+#0 string \320\317\021\340\241\261\032\341 application/powerpoint
+0 string \320\317\021\340\241\261\032\341 application/msword
+
+0 string #\ PaCkAgE\ DaTaStReAm application/x-svr4-package
+
+
+# WinNT/WinCE PE files (Warner Losh, imp at village.org)
+#
+128 string PE\000\000 application/octet-stream
+0 string PE\000\000 application/octet-stream
+
+# miscellaneous formats
+0 string LZ application/octet-stream
+
+
+# .EXE formats (Greg Roelofs, newt at uchicago.edu)
+#
+0 string MZ
+>24 string @ application/octet-stream
+
+0 string MZ
+>30 string Copyright\ 1989-1990\ PKWARE\ Inc. application/x-zip
+
+0 string MZ
+>30 string PKLITE\ Copr. application/x-zip
+
+0 string MZ
+>36 string LHa's\ SFX application/x-lha
+
+0 string MZ application/octet-stream
+
+# LHA archiver
+2 string -lh
+>6 string - application/x-lha
+
+
+# Zoo archiver
+20 lelong 0xfdc4a7dc application/x-zoo
+
+# ARC archiver
+0 lelong&0x8080ffff 0x0000081a application/x-arc
+0 lelong&0x8080ffff 0x0000091a application/x-arc
+0 lelong&0x8080ffff 0x0000021a application/x-arc
+0 lelong&0x8080ffff 0x0000031a application/x-arc
+0 lelong&0x8080ffff 0x0000041a application/x-arc
+0 lelong&0x8080ffff 0x0000061a application/x-arc
+
+# Microsoft Outlook's Transport Neutral Encapsulation Format (TNEF)
+0 lelong 0x223e9f78 application/ms-tnef
+
+
+#
+# QuickTime format
+# Contributer: Peter Breton
+#
+
+0 string MOVI video/quicktime
+4 string moov video/quicktime
+4 string mdat video/quicktime
+
+# Video Formate
+0 string RIFF
+# AVI == Audio Video Interleave
+>8 string AVI\
+#>0xbc string >\0 video/x-%s
+
+>>0xbc string DIV3 video/x-DivX-3
+>>0xbc string div3 video/x-divX-3
+>>0xbc string DIV4 video/x-DivX-4
+>>0x70 string DX50 video/x-DIVX-5
+>>0x70 string MP4 video/x-MPEG-4
+>>0xbc string DIVX video/x-DivX
+>8 string WAVE audio/x-wav
+
+# From: stephane.loeuillet at tiscali.f
+# http://www.djvuzone.org/
+0 string AT&TFORM image/x.djvu
+
+# Danny Milosavljevic <danny.milo at gmx.net>
+# this are adrift (adventure game standard) game files, extension .taf
+# depending on version magic continues with 0x93453E6139FA (V 4.0)
+# 0x9445376139FA (V 3.90)
+# 0x9445366139FA (V 3.80)
+# this is from source (http://www.adrift.org.uk/) and I have some taf
+# files, and checked them.
+#0 belong 0x3C423FC9
+#>4 belong 0x6A87C2CF application/x-adrift
+
+
+# local additions
+
+# Macromedia Flash FLV Video File Format
+0 string FLV video/x-flv
Added: z3c.filetype/trunk/src/z3c/filetype/magic.py
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/magic.py 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/magic.py 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,714 @@
+# Found on a russian zope mailing list, and modified to fix bugs in parsing
+# the magic file and string making
+# -- Daniel Berlin <dberlin at dberlin.org>
+import sys, struct, time, re, exceptions, pprint, stat, os, pwd, grp
+
+_mew = 0
+
+_magic = os.path.join(os.path.dirname(__file__),'magic.mime')
+
+mime = 1
+
+_ldate_adjust = lambda x: time.mktime( time.gmtime(x) )
+
+BUFFER_SIZE = 1024 * 128 # 128K should be enough...
+
+class MagicError(exceptions.Exception): pass
+
+def _handle(fmt='@x',adj=None): return fmt, struct.calcsize(fmt), adj
+
+KnownTypes = {
+ 'byte':_handle('@b'),
+ 'byte':_handle('@B'),
+ 'ubyte':_handle('@B'),
+ 'string':('s',0,None),
+ 'pstring':_handle('p'),
+ 'short':_handle('@h'),
+ 'beshort':_handle('>h'),
+ 'leshort':_handle('<h'),
+ 'short':_handle('@H'),
+ 'beshort':_handle('>H'),
+ 'leshort':_handle('<H'),
+ 'ushort':_handle('@H'),
+ 'ubeshort':_handle('>H'),
+ 'uleshort':_handle('<H'),
+
+ 'long':_handle('@l'),
+ 'belong':_handle('>l'),
+ 'lelong':_handle('<l'),
+ 'ulong':_handle('@L'),
+ 'ubelong':_handle('>L'),
+ 'ulelong':_handle('<L'),
+
+ 'date':_handle('=l'),
+ 'bedate':_handle('>l'),
+ 'ledate':_handle('<l'),
+ 'ldate':_handle('=l',_ldate_adjust),
+ 'beldate':_handle('>l',_ldate_adjust),
+ 'leldate':_handle('<l',_ldate_adjust),
+}
+
+_mew_cnt = 0
+def mew(x):
+ global _mew_cnt
+ if _mew :
+ if x=='.' :
+ _mew_cnt += 1
+ if _mew_cnt % 64 == 0 : sys.stderr.write( '\n' )
+ sys.stderr.write( '.' )
+ else:
+ sys.stderr.write( '\b'+x )
+
+def has_format(s):
+ n = 0
+ l = None
+ for c in s :
+ if c == '%' :
+ if l == '%' : n -= 1
+ else : n += 1
+ l = c
+ return n
+
+def read_asciiz(file,size=None,pos=None):
+ s = []
+ if pos :
+ mew('s')
+ file.seek( pos, 0 )
+ mew('z')
+ if size is not None :
+ s = [file.read( size ).split('\0')[0]]
+ else:
+ while 1 :
+ c = file.read(1)
+ if (not c) or (ord(c)==0) or (c=='\n') : break
+ s.append (c)
+ mew('Z')
+ return ''.join(s)
+
+def a2i(v,base=0):
+ if v[-1:] in 'lL' : v = v[:-1]
+ return int( v, base )
+
+_cmap = {
+ '\\' : '\\',
+ '0' : '\0',
+}
+for c in range(ord('a'),ord('z')+1) :
+ try : e = eval('"\\%c"' % chr(c))
+ except ValueError : pass
+ else : _cmap[chr(c)] = e
+else:
+ del c
+ del e
+
+def make_string(s):
+ # hack, is this the right way?
+ s = s.replace('\\<','<')
+ s = s.replace('\\ ',' ')
+ return eval( '"'+s.replace('"','\\"')+'"')
+
+class MagicTestError(MagicError): pass
+
+class MagicTest:
+ def __init__(self,offset,mtype,test,message,line=None,level=None):
+ self.line, self.level = line, level
+ self.mtype = mtype
+ self.mtest = test
+ self.subtests = []
+ self.mask = None
+ self.smod = None
+ self.nmod = None
+ self.offset, self.type, self.test, self.message = \
+ offset,mtype,test,message
+ if self.mtype == 'true' : return # XXX hack to enable level skips
+ if test[-1:]=='\\' and test[-2:]!='\\\\' :
+ self.test += 'n' # looks like someone wanted EOL to match?
+ if mtype[:6]=='string' :
+ if '/' in mtype : # for strings
+ self.type, self.smod = \
+ mtype[:mtype.find('/')], mtype[mtype.find('/')+1:]
+ else:
+ for nm in '&+-' :
+ if nm in mtype : # for integer-based
+ self.nmod, self.type, self.mask = (
+ nm,
+ mtype[:mtype.find(nm)],
+ # convert mask to int, autodetect base
+ int( mtype[mtype.find(nm)+1:], 0 )
+ )
+ break
+ self.struct, self.size, self.cast = KnownTypes[ self.type ]
+ def __str__(self):
+ return '%s %s %s %s' % (
+ self.offset, self.mtype, self.mtest, self.message
+ )
+ def __repr__(self):
+ return 'MagicTest(%s,%s,%s,%s,line=%s,level=%s,subtests=\n%s%s)' % (
+ `self.offset`, `self.mtype`, `self.mtest`, `self.message`,
+ `self.line`, `self.level`,
+ '\t'*self.level, pprint.pformat(self.subtests)
+ )
+ def run(self,file):
+ result = ''
+ do_close = 0
+ try:
+ if type(file) == type('x') :
+ file = open( file, 'r', BUFFER_SIZE )
+ do_close = 1
+# else:
+# saved_pos = file.tell()
+ if self.mtype != 'true' :
+ data = self.read(file)
+ last = file.tell()
+ else:
+ data = last = None
+ if self.check( data ) :
+ result = self.message+' '
+ if has_format( result ) : result %= data
+ for test in self.subtests :
+ m = test.run(file)
+ if m is not None : result += m
+ return make_string( result )
+ finally:
+ if do_close :
+ file.close()
+# else:
+# file.seek( saved_pos, 0 )
+ def get_mod_and_value(self):
+ if self.type[-6:] == 'string' :
+# if 'ustar' in self.test:
+# import pdb;pdb.set_trace()
+ # "something like\tthis\n"
+ if self.test[0] in '=<>' :
+ mod, value = self.test[0], make_string( self.test[1:] )
+ else:
+ mod, value = '=', make_string( self.test )
+ else:
+ if self.test[0] in '=<>&^' :
+ mod, value = self.test[0], a2i(self.test[1:])
+ elif self.test[0] == 'x':
+ mod = self.test[0]
+ value = 0
+ else:
+ mod, value = '=', a2i(self.test)
+ return mod, value
+ def read(self,file):
+ mew( 's' )
+ file.seek( self.offset(file), 0 ) # SEEK_SET
+ mew( 'r' )
+ try:
+ data = rdata = None
+ # XXX self.size might be 0 here...
+ if self.size == 0 :
+ # this is an ASCIIZ string...
+ size = None
+ if self.test != '>\\0' : # magic's hack for string read...
+ value = self.get_mod_and_value()[1]
+ size = (value=='\0') and None or len(value)
+ rdata = data = read_asciiz( file, size=size )
+ else:
+ rdata = file.read( self.size )
+ if not rdata or (len(rdata)!=self.size) : return None
+ data = struct.unpack( self.struct, rdata )[0] # XXX hack??
+ except:
+ print >>sys.stderr, self
+ print >>sys.stderr, '@%s struct=%s size=%d rdata=%s' % (
+ self.offset, `self.struct`, self.size,`rdata`)
+ raise
+ mew( 'R' )
+ if self.cast : data = self.cast( data )
+ if self.mask :
+ try:
+ if self.nmod == '&' : data &= self.mask
+ elif self.nmod == '+' : data += self.mask
+ elif self.nmod == '-' : data -= self.mask
+ else: raise MagicTestError(self.nmod)
+ except:
+ print >>sys.stderr,'data=%s nmod=%s mask=%s' % (
+ `data`, `self.nmod`, `self.mask`
+ )
+ raise
+ return data
+ def check(self,data):
+ mew('.')
+ if self.mtype == 'true' :
+ return '' # not None !
+ mod, value = self.get_mod_and_value()
+ if self.type[-6:] == 'string' :
+ # "something like\tthis\n"
+ if self.smod:
+ #import pdb;pdb.set_trace()
+ xdata = data
+ if 'b' in self.smod : # all blanks are optional
+ xdata = ''.join( data.split() )
+ value = ''.join( value.split() )
+ if 'c' in self.smod : # all blanks are optional
+ xdata = xdata.upper()
+ value = value.upper()
+ if 'B' in self.smod : # compact blanks
+ data = ' '.join( data.split() )
+ if ' ' not in data : return None
+ else:
+ xdata = data
+ try:
+ if mod == '=' : result = data == value
+ elif mod == '<' : result = data < value
+ elif mod == '>' : result = data > value
+ elif mod == '&' : result = data & value
+ elif mod == '^' : result = (data & (~value)) == 0
+ elif mod == 'x' : result = 1
+ else : raise MagicTestError(self.test)
+ if result :
+ zdata, zval = `data`, `value`
+ if self.mtype[-6:]!='string' :
+ try: zdata, zval = hex(data), hex(value)
+ except: zdata, zval = `data`, `value`
+ if 0 : print >>sys.stderr, '%s @%s %s:%s %s %s => %s (%s)' % (
+ '>'*self.level, self.offset,
+ zdata, self.mtype, `mod`, zval, `result`,
+ self.message
+ )
+ return result
+ except:
+ print >>sys.stderr,'mtype=%s data=%s mod=%s value=%s' % (
+ `self.mtype`, `data`, `mod`, `value`
+ )
+ raise
+ def add(self,mt):
+ if not isinstance(mt,MagicTest) :
+ raise MagicTestError((mt,'incorrect subtest type %s'%(type(mt),)))
+ if mt.level == self.level+1 :
+ self.subtests.append( mt )
+ elif self.subtests :
+ self.subtests[-1].add( mt )
+ elif mt.level > self.level+1 :
+ # it's possible to get level 3 just after level 1 !!! :-(
+ level = self.level + 1
+ while level < mt.level :
+ xmt = MagicTest(None,'true','x','',line=self.line,level=level)
+ self.add( xmt )
+ level += 1
+ else:
+ self.add( mt ) # retry...
+ else:
+ raise MagicTestError((mt,'incorrect subtest level %s'%(`mt.level`,)))
+ def last_test(self):
+ return self.subtests[-1]
+#end class MagicTest
+
+class OffsetError(MagicError): pass
+
+class Offset:
+ pos_format = {'b':'<B','B':'>B','s':'<H','S':'>H','l':'<I','L':'>I',}
+ pattern0 = re.compile(r''' # mere offset
+ ^
+ &? # possible ampersand
+ ( 0 # just zero
+ | [1-9]{1,1}[0-9]* # decimal
+ | 0[0-7]+ # octal
+ | 0x[0-9a-f]+ # hex
+ )
+ $
+ ''', re.X|re.I
+ )
+ pattern1 = re.compile(r''' # indirect offset
+ ^\(
+ (?P<base>&?0 # just zero
+ |&?[1-9]{1,1}[0-9]* # decimal
+ |&?0[0-7]* # octal
+ |&?0x[0-9A-F]+ # hex
+ )
+ (?P<type>
+ \. # this dot might be alone
+ [BSL]? # one of this chars in either case
+ )?
+ (?P<sign>
+ [-+]{0,1}
+ )?
+ (?P<off>0 # just zero
+ |[1-9]{1,1}[0-9]* # decimal
+ |0[0-7]* # octal
+ |0x[0-9a-f]+ # hex
+ )?
+ \)$''', re.X|re.I
+ )
+ def __init__(self,s):
+ self.source = s
+ self.value = None
+ self.relative = 0
+ self.base = self.type = self.sign = self.offs = None
+ m = Offset.pattern0.match( s )
+ if m : # just a number
+ if s[0] == '&' :
+ self.relative, self.value = 1, int( s[1:], 0 )
+ else:
+ self.value = int( s, 0 )
+ return
+ m = Offset.pattern1.match( s )
+ if m : # real indirect offset
+ try:
+ self.base = m.group('base')
+ if self.base[0] == '&' :
+ self.relative, self.base = 1, int( self.base[1:], 0 )
+ else:
+ self.base = int( self.base, 0 )
+ if m.group('type') : self.type = m.group('type')[1:]
+ self.sign = m.group('sign')
+ if m.group('off') : self.offs = int( m.group('off'), 0 )
+ if self.sign == '-' : self.offs = 0 - self.offs
+ except:
+ print >>sys.stderr, '$$', m.groupdict()
+ raise
+ return
+ raise OffsetError(`s`)
+ def __call__(self,file=None):
+ if self.value is not None : return self.value
+ pos = file.tell()
+ try:
+ if not self.relative : file.seek( self.offset, 0 )
+ frmt = Offset.pos_format.get( self.type, 'I' )
+ size = struct.calcsize( frmt )
+ data = struct.unpack( frmt, file.read( size ) )
+ if self.offs : data += self.offs
+ return data
+ finally:
+ file.seek( pos, 0 )
+ def __str__(self): return self.source
+ def __repr__(self): return 'Offset(%s)' % `self.source`
+#end class Offset
+
+class MagicFileError(MagicError): pass
+
+class MagicFile:
+ def __init__(self,filename=_magic):
+ self.file = None
+ self.tests = []
+ self.total_tests = 0
+ self.load( filename )
+ self.ack_tests = None
+ self.nak_tests = None
+ def __del__(self):
+ self.close()
+ def load(self,filename=None):
+ self.open( filename )
+ self.parse()
+ self.close()
+ def open(self,filename=None):
+ self.close()
+ if filename is not None :
+ self.filename = filename
+ self.file = open( self.filename, 'r', BUFFER_SIZE )
+ def close(self):
+ if self.file :
+ self.file.close()
+ self.file = None
+ def parse(self):
+ line_no = 0
+ for line in self.file.xreadlines() :
+ line_no += 1
+ if not line or line[0]=='#' : continue
+ line = line.lstrip().rstrip('\r\n')
+ if not line or line[0]=='#' : continue
+ try:
+ x = self.parse_line( line )
+ if x is None :
+ print >>sys.stderr, '#[%04d]#'%line_no, line
+ continue
+ except:
+ print >>sys.stderr, '###[%04d]###'%line_no, line
+ raise
+ self.total_tests += 1
+ level, offset, mtype, test, message = x
+ new_test = MagicTest(offset,mtype,test,message,
+ line=line_no,level=level)
+ try:
+ if level == 0 :
+ self.tests.append( new_test )
+ else:
+ self.tests[-1].add( new_test )
+ except:
+ if 1 :
+ print >>sys.stderr, 'total tests=%s' % (
+ `self.total_tests`,
+ )
+ print >>sys.stderr, 'level=%s' % (
+ `level`,
+ )
+ print >>sys.stderr, 'tests=%s' % (
+ pprint.pformat(self.tests),
+ )
+ raise
+ else:
+ while self.tests[-1].level > 0 :
+ self.tests.pop()
+ def parse_line(self,line):
+ # print >>sys.stderr, 'line=[%s]' % line
+ if (not line) or line[0]=='#' : return None
+ level = 0
+ offset = mtype = test = message = ''
+ mask = None
+ # get optional level (count leading '>')
+ while line and line[0]=='>' :
+ line, level = line[1:], level+1
+ # get offset
+ while line and not line[0].isspace() :
+ offset, line = offset+line[0], line[1:]
+ try:
+ offset = Offset(offset)
+ except:
+ print >>sys.stderr, 'line=[%s]' % line
+ raise
+ # skip spaces
+ line = line.lstrip()
+ # get type
+ c = None
+ while line :
+ last_c, c, line = c, line[0], line[1:]
+ if last_c!='\\' and c.isspace() :
+ break # unescaped space - end of field
+ else:
+ mtype += c
+ if last_c == '\\' :
+ c = None # don't fuck my brain with sequential backslashes
+ # skip spaces
+ line = line.lstrip()
+ # get test
+ c = None
+ while line :
+ last_c, c, line = c, line[0], line[1:]
+ if last_c!='\\' and c.isspace() :
+ break # unescaped space - end of field
+ else:
+ test += c
+ if last_c == '\\' :
+ c = None # don't fuck my brain with sequential backslashes
+ # skip spaces
+ line = line.lstrip()
+ # get message
+ message = line
+ if mime and line.find("\t") != -1:
+ message=line[0:line.find("\t")]
+ #
+ # print '>>', level, offset, mtype, test, message
+ return level, offset, mtype, test, message
+ def detect(self,file):
+ self.ack_tests = 0
+ self.nak_tests = 0
+ answers = []
+ for test in self.tests :
+ message = test.run( file )
+ if message :
+ self.ack_tests += 1
+ answers.append( message )
+ else:
+ self.nak_tests += 1
+ if answers :
+ return '; '.join( answers )
+#end class MagicFile
+
+def username(uid):
+ try:
+ return pwd.getpwuid( uid )[0]
+ except:
+ return '#%s'%uid
+
+def groupname(gid):
+ try:
+ return grp.getgrgid( gid )[0]
+ except:
+ return '#%s'%gid
+
+def get_file_type(fname,follow):
+ t = None
+ if not follow :
+ try:
+ st = os.lstat( fname ) # stat that entry, don't follow links!
+ except os.error, why :
+ pass
+ else:
+ if stat.S_ISLNK(st[stat.ST_MODE]) :
+ t = 'symbolic link'
+ try:
+ lnk = os.readlink( fname )
+ except:
+ t += ' (unreadable)'
+ else:
+ t += ' to '+lnk
+ if t is None :
+ try:
+ st = os.stat( fname )
+ except os.error, why :
+ return "can't stat `%s' (%s)." % (why.filename,why.strerror)
+
+ dmaj, dmin = (st.st_rdev>>8)&0x0FF, st.st_rdev&0x0FF
+
+ if 0 : pass
+ elif stat.S_ISSOCK(st.st_mode) : t = 'socket'
+ elif stat.S_ISLNK (st.st_mode) : t = follow and 'symbolic link' or t
+ elif stat.S_ISREG (st.st_mode) : t = 'file'
+ elif stat.S_ISBLK (st.st_mode) : t = 'block special (%d/%d)'%(dmaj,dmin)
+ elif stat.S_ISDIR (st.st_mode) : t = 'directory'
+ elif stat.S_ISCHR (st.st_mode) : t = 'character special (%d/%d)'%(dmaj,dmin)
+ elif stat.S_ISFIFO(st.st_mode) : t = 'pipe'
+ else: t = '<unknown>'
+
+ if st.st_mode & stat.S_ISUID :
+ t = 'setuid(%d=%s) %s'%(st.st_uid,username(st.st_uid),t)
+ if st.st_mode & stat.S_ISGID :
+ t = 'setgid(%d=%s) %s'%(st.st_gid,groupname(st.st_gid),t)
+ if st.st_mode & stat.S_ISVTX :
+ t = 'sticky '+t
+
+ return t
+
+HELP = '''%s [options] [files...]
+
+Options:
+
+ -?, --help -- this help
+ -m, --magic=<file> -- use this magic <file> instead of %s
+ -f, --files=<namefile> -- read filenames for <namefile>
+* -C, --compile -- write "compiled" magic file
+ -b, --brief -- don't prepend filenames to output lines
++ -c, --check -- check the magic file
+ -i, --mime -- output MIME types
+* -k, --keep-going -- don't stop st the first match
+ -n, --flush -- flush stdout after each line
+ -v, --verson -- print version and exit
+* -z, --compressed -- try to look inside compressed files
+ -L, --follow -- follow symlinks
+ -s, --special -- don't skip special files
+
+* -- not implemented so far ;-)
++ -- implemented, but in another way...
+'''
+
+def main():
+ import getopt
+ global _magic
+ try:
+ brief = 0
+ flush = 0
+ follow= 0
+ mime = 0
+ check = 0
+ special=0
+ try:
+ opts, args = getopt.getopt(
+ sys.argv[1:],
+ '?m:f:CbciknvzLs',
+ ( 'help',
+ 'magic=',
+ 'names=',
+ 'compile',
+ 'brief',
+ 'check',
+ 'mime',
+ 'keep-going',
+ 'flush',
+ 'version',
+ 'compressed',
+ 'follow',
+ 'special',
+ )
+ )
+ except getopt.error, why:
+ print >>sys.stderr, sys.argv[0], why
+ return 1
+ else:
+ files = None
+ for o,v in opts :
+ if o in ('-?','--help'):
+ print HELP % (
+ sys.argv[0],
+ _magic,
+ )
+ return 0
+ elif o in ('-f','--files='):
+ files = v
+ elif o in ('-m','--magic='):
+ _magic = v[:]
+ elif o in ('-C','--compile'):
+ pass
+ elif o in ('-b','--brief'):
+ brief = 1
+ elif o in ('-c','--check'):
+ check = 1
+ elif o in ('-i','--mime'):
+ mime = 1
+ if os.path.exists( _magic+'.mime' ) :
+ _magic += '.mime'
+ print >>sys.stderr,sys.argv[0]+':',\
+ "Using regular magic file `%s'" % _magic
+ elif o in ('-k','--keep-going'):
+ pass
+ elif o in ('-n','--flush'):
+ flush = 1
+ elif o in ('-v','--version'):
+ print 'VERSION'
+ return 0
+ elif o in ('-z','--compressed'):
+ pass
+ elif o in ('-L','--follow'):
+ follow = 1
+ elif o in ('-s','--special'):
+ special = 1
+ else:
+ if files :
+ files = map(lambda x: x.strip(), v.split(','))
+ if '-' in files and '-' in args :
+ error( 1, 'cannot use STDIN simultaneously for file list and data' )
+ for file in files :
+ for name in (
+ (file=='-')
+ and sys.stdin
+ or open(file,'r',BUFFER_SIZE)
+ ).xreadlines():
+ name = name.strip()
+ if name not in args :
+ args.append( name )
+ try:
+ if check : print >>sys.stderr, 'Loading magic database...'
+ t0 = time.time()
+ m = MagicFile(_magic)
+ t1 = time.time()
+ if check :
+ print >>sys.stderr, \
+ m.total_tests, 'tests loaded', \
+ 'for', '%.2f' % (t1-t0), 'seconds'
+ print >>sys.stderr, len(m.tests), 'tests at top level'
+ return 0 # XXX "shortened" form ;-)
+
+ mlen = max( map(len, args) )+1
+ for arg in args :
+ if not brief : print (arg + ':').ljust(mlen),
+ ftype = get_file_type( arg, follow )
+ if (special and ftype.find('special')>=0) \
+ or ftype[-4:] == 'file' :
+ t0 = time.time()
+ try:
+ t = m.detect( arg )
+ except (IOError,os.error), why:
+ t = "can't read `%s' (%s)" % (why.filename,why.strerror)
+ if ftype[-4:] == 'file' : t = ftype[:-4] + t
+ t1 = time.time()
+ print t and t or 'data'
+ if 0 : print \
+ '#\t%d tests ok, %d tests failed for %.2f seconds'%\
+ (m.ack_tests, m.nak_tests, t1-t0)
+ else:
+ print mime and 'application/x-not-regular-file' or ftype
+ if flush : sys.stdout.flush()
+ # print >>sys.stderr, 'DONE'
+ except:
+ if check : return 1
+ raise
+ else:
+ return 0
+ finally:
+ pass
+
+if __name__ == '__main__' :
+ sys.exit( main() )
+# vim:ai
+# EOF #
Property changes on: z3c.filetype/trunk/src/z3c/filetype/magic.py
___________________________________________________________________
Name: svn:keywords
+ Id
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/magic.txt
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/magic.txt 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/magic.txt 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,27 @@
+=======
+ Magic
+=======
+
+Extract filetype from file content
+
+ >>> from z3c.filetype import magic
+ >>> import os
+ >>> m = magic.MagicFile()
+ >>> testData = os.path.join(os.path.dirname(magic.__file__),'testdata')
+ >>> fileNames = sorted(os.listdir(testData))
+ >>> for name in fileNames:
+ ... path = os.path.join(testData, name)
+ ... print name, m.detect(file(path))
+ DS_Store None
+ jumps.mov video/quicktime ; video/quicktime
+ logo.gif image/gif
+ test.flv video/x-flv
+ test.gnutar application/x-tar ; application/x-tar
+ test.html text/html
+ test.png image/png
+ test.tar application/x-tar ; application/x-tar
+ test.tgz application/x-gzip
+ test.txt.gz application/x-gzip
+ test2.html text/html
+ test2.thml text/html
+ thumbnailImage_small.jpeg image/jpeg
Property changes on: z3c.filetype/trunk/src/z3c/filetype/magic.txt
___________________________________________________________________
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/DS_Store
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/DS_Store
___________________________________________________________________
Name: svn:mime-type
+ application/octet-stream
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/jumps.mov
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/jumps.mov
___________________________________________________________________
Name: svn:mime-type
+ application/octet-stream
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/logo.gif
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/logo.gif
___________________________________________________________________
Name: svn:mime-type
+ image/gif
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/test.flv
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/test.flv
___________________________________________________________________
Name: svn:mime-type
+ application/octet-stream
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/test.gnutar
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/test.gnutar
___________________________________________________________________
Name: svn:mime-type
+ application/octet-stream
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/test.html
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/testdata/test.html 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/testdata/test.html 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,8 @@
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<title>Title</title>
+
+<body>
+ body
+</body>
+</html>
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/test.html
___________________________________________________________________
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/test.png
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/test.png
___________________________________________________________________
Name: svn:mime-type
+ image/png
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/test.tar
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/test.tar
___________________________________________________________________
Name: svn:mime-type
+ application/octet-stream
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/test.tgz
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/test.tgz
___________________________________________________________________
Name: svn:mime-type
+ application/octet-stream
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/test.txt.gz
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/test.txt.gz
___________________________________________________________________
Name: svn:mime-type
+ application/gzip
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/test2.html
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/testdata/test2.html 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/testdata/test2.html 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,9 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<title>Title</title>
+
+<body>
+ body
+</body>
+</html>
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/test2.html
___________________________________________________________________
Name: svn:eol-style
+ native
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/test2.thml
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/testdata/test2.thml 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/testdata/test2.thml 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,8 @@
+<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
+<head>
+<title>Title</title>
+
+<body>
+ body
+</body>
+</html>
Added: z3c.filetype/trunk/src/z3c/filetype/testdata/thumbnailImage_small.jpeg
===================================================================
(Binary files differ)
Property changes on: z3c.filetype/trunk/src/z3c/filetype/testdata/thumbnailImage_small.jpeg
___________________________________________________________________
Name: svn:mime-type
+ image/jpeg
Added: z3c.filetype/trunk/src/z3c/filetype/tests.py
===================================================================
--- z3c.filetype/trunk/src/z3c/filetype/tests.py 2006-08-11 12:55:34 UTC (rev 69400)
+++ z3c.filetype/trunk/src/z3c/filetype/tests.py 2006-08-11 13:56:21 UTC (rev 69401)
@@ -0,0 +1,22 @@
+import doctest
+import unittest
+from zope.testing.doctestunit import DocFileSuite, DocTestSuite
+
+def test_suite():
+
+ return unittest.TestSuite(
+ (
+ DocFileSuite('README.txt',
+ optionflags=doctest.NORMALIZE_WHITESPACE|doctest.ELLIPSIS,
+ ),
+ DocFileSuite('magic.txt',
+ optionflags=doctest.NORMALIZE_WHITESPACE|doctest.ELLIPSIS,
+ ),
+ DocTestSuite('z3c.filetype.api',
+ optionflags=doctest.NORMALIZE_WHITESPACE|doctest.ELLIPSIS,
+ ),
+ ))
+
+if __name__ == '__main__':
+ unittest.main(defaultTest='test_suite')
+
Property changes on: z3c.filetype/trunk/src/z3c/filetype/tests.py
___________________________________________________________________
Name: svn:keywords
+ Id
Name: svn:eol-style
+ native
More information about the Checkins
mailing list