Mirror/zeek
1
0
Fork 0
mirror of https://github.com/zeek/zeek.git synced 2025-10-04 15:48:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Merge remote-tracking branch 'origin/master' into topic/bernhard/hyperloglog

Browse source
This commit is contained in:
Bernhard Amann 2013-07-30 14:31:09 -07:00
commit 5b9d80e50d
247 changed files with 2729 additions and 5372 deletions
Download patch file Download diff file Expand all files Collapse all files

3
.gitmodules vendored
View file

@ -16,3 +16,6 @@
[submodule "cmake"]
path = cmake
url = git://git.bro-ids.org/cmake
[submodule "magic"]
path = magic
url = git://git.bro.org/bromagic

86
CHANGES
View file

@ -1,4 +1,90 @@
2.1-945 | 2013-07-30 10:05:10 -0700
* Make hashers serializable. (Matthias Vallentin)
* Add docs and use default value for hasher names. (Matthias
Vallentin)
2.1-939 | 2013-07-29 15:42:38 -0700
* Added Exec, Dir, and ActiveHTTP modules. (Seth Hall)
base/utils/exec.bro provides a module to start external processes
asynchronously and retrieve their output on termination.
base/utils/dir.bro uses it to monitor a directory for changes, and
base/utils/active-http.bro for providing an interface for querying
remote web servers.
2.1-930 | 2013-07-29 15:06:07 -0700
* Major file analysis overhaul in naming and appearance, along with
fixes and test updates. (Seth Hall and Jon Siwek)
Includes:
* Added protocol description functions that provide a super
compressed log representation. (Seth Hall)
* Added mime types to http.log (Seth Hall)
* Add jar files to the default MHR lookups. (Seth Hall)
* Adding CAB files for MHR checking. (Seth Hall)
* Improve malware hash registry script.
- Include a link to a virustotal search in the notice sub message field.
- Give all information returned from Team Cymru in the notice message.
- Add more file types to match on to the default set.
* Make the custom libmagic database a git submodule.
* Add an is_orig parameter to file_over_new_connection event.
* Recorrected the module name to Files.
* Added Files::analyzer_name to get a more readable name for a
file analyzer.
* Improved and just overall better handled multipart mime
transfers in HTTP and SMTP. HTTP now has orig_fuids and
resp_fuids log fields since multiple "files" can be transferred
with multipart mime in a single request/response pair. SMTP has
an fuids field which has file unique IDs for all parts
transferred. FTP and IRC have a log field named fuid added
because only a single file can be transferred per irc and ftp
log line.
2.1-895 | 2013-07-29 14:07:35 -0700
* Adding a test for a DNSKEY RR. (Robin Sommer)
2.1-894 | 2013-07-29 16:44:41 -0400
* Updates for the Intel Framework. (Seth Hall)
- policy/frameworks/intel/seen is the new location for the
scripts that push data into the intel framework for checking.
- The new policy/frameworks/intel/do_notice script adds an
example mechanism for data driven notices.
- Remove the Intel insertion after heuristically detecting SSH
bruteforcing.
- Intel importing format has changed (refer to docs).
- All string matching is now case insensitive.
- SMTP intel script has been updated to extract email
addresses correctly.
- Small fix sneaking into the smtp base script to actually
extract individual email addresses in the To: field
correctly.
2.1-888 | 2013-07-25 12:02:41 -0700
* Protection about broken traces with empty pcap headers. (Matt

7
CMakeLists.txt
View file

@ -18,7 +18,7 @@ get_filename_component(BRO_SCRIPT_INSTALL_PATH ${BRO_SCRIPT_INSTALL_PATH}
ABSOLUTE)
set(BRO_MAGIC_INSTALL_PATH ${BRO_ROOT_DIR}/share/bro/magic)
set(BRO_MAGIC_SOURCE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/magic)
set(BRO_MAGIC_SOURCE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/magic/database)
configure_file(bro-path-dev.in ${CMAKE_CURRENT_BINARY_DIR}/bro-path-dev)
file(WRITE ${CMAKE_CURRENT_BINARY_DIR}/bro-path-dev.sh
@ -201,9 +201,8 @@ CheckOptionalBuildSources(aux/broctl Broctl INSTALL_BROCTL)
CheckOptionalBuildSources(aux/bro-aux Bro-Aux INSTALL_AUX_TOOLS)
CheckOptionalBuildSources(aux/broccoli Broccoli INSTALL_BROCCOLI)
install(DIRECTORY ./magic/ DESTINATION ${BRO_MAGIC_INSTALL_PATH} FILES_MATCHING
PATTERN "COPYING" EXCLUDE
PATTERN "*"
install(DIRECTORY ./magic/database/
DESTINATION ${BRO_MAGIC_INSTALL_PATH}
)
########################################################################

8
NEWS
View file

@ -80,7 +80,7 @@ New Functionality
with the following user-visibible functionality (some of that was
already available before, but done differently):
[TODO: This will probably change with further script updates.]
[TODO: Update with changes from 984e9793db56.]
- A binary input reader interfaces the input framework with file
analysis, allowing to inject files on disk into Bro's
@ -121,6 +121,12 @@ New Functionality
See <INSERT LINK> for full documentation.
- base/utils/exec.bro provides a module to start external processes
asynchronously and retrieve their output on termination.
base/utils/dir.bro uses it to monitor a directory for changes, and
base/utils/active-http.bro for providing an interface for querying
remote web servers.
Changed Functionality
~~~~~~~~~~~~~~~~~~~~~

2
VERSION
View file

@ -1 +1 @@
2.1-888
2.1-945

2
aux/binpac

@ -1 +1 @@
Subproject commit 896ddedde55c48ec2163577fc258b49c418abb3e
Subproject commit 314fa8f65fc240e960c23c3bba98623436a72b98

2
aux/bro-aux

@ -1 +1 @@
Subproject commit a9942558c7d3dfd80148b8aaded64c82ade3d117
Subproject commit 91d258cc8b2f74cd02fc93dfe61f73ec9f0dd489

2
aux/broccoli

@ -1 +1 @@
Subproject commit 889f9c65944ceac20ad9230efc39d33e6e1221c3
Subproject commit d59c73b6e0966ad63bbc63a35741b5f68263e7b1

2
aux/broctl

@ -1 +1 @@
Subproject commit 0cd102805e73343cab3f9fd4a76552e13940dad9
Subproject commit 52fd91261f41fa1528f7b964837a364d7991889e

24
doc/intel.rst
View file

@ -27,10 +27,7 @@ Quick Start
Load the package of scripts that sends data into the Intelligence
Framework to be checked by loading this script in local.bro::
@load policy/frameworks/intel
(TODO: find some good mechanism for getting setup with good data
quickly)
@load policy/frameworks/intel/seen
Refer to the "Loading Intelligence" section below to see the format
for Intelligence Framework text files, then load those text files with
@ -61,16 +58,14 @@ data out to all of the nodes that need it.
Here is an example of the intelligence data format. Note that all
whitespace separators are literal tabs and fields containing only a
hyphen a considered to be null values.::
hyphen are considered to be null values.::
#fields host net str str_type meta.source meta.desc meta.url
1.2.3.4 - - - source1 Sending phishing email http://source1.com/badhosts/1.2.3.4
- 31.131.248.0/21 - - spamhaus-drop SBL154982 - -
- - a.b.com Intel::DOMAIN source2 Name used for data exfiltration -
#fields indicator indicator_type meta.source meta.desc meta.url
1.2.3.4 Intel::ADDR source1 Sending phishing email http://source1.com/badhosts/1.2.3.4
a.b.com Intel::DOMAIN source2 Name used for data exfiltration -
For more examples of built in `str_type` values, please refer to the
autogenerated documentation for the intelligence framework (TODO:
figure out how to do this link).
For more examples of built in `indicator_type` values, please refer to the
autogenerated documentation for the intelligence framework.
To load the data once files are created, use the following example
code to define files to load with your own file names of course::
@ -90,8 +85,7 @@ When some bit of data is extracted (such as an email address in the
"From" header in a message over SMTP), the Intelligence Framework
needs to be informed that this data was discovered and it's presence
should be checked within the intelligence data set. This is
accomplished through the Intel::seen (TODO: do a reference link)
function.
accomplished through the Intel::seen function.
Typically users won't need to work with this function due to built in
hook scripts that Bro ships with that will "see" data and send it into
@ -106,7 +100,7 @@ The full package of hook scripts that Bro ships with for sending this
"seen" data into the intelligence framework can be loading by adding
this line to local.bro::
@load policy/frameworks/intel
@load policy/frameworks/intel/seen
Intelligence Matches
********************

4
doc/scripts/CMakeLists.txt
View file

@ -99,7 +99,7 @@ macro(REST_TARGET srcDir broInput)
COMMAND "${CMAKE_COMMAND}"
ARGS -E remove_directory .state
# generate the reST documentation using bro
COMMAND BROPATH=${BROPATH}:${srcDir} BROMAGIC=${CMAKE_SOURCE_DIR}/magic ${CMAKE_BINARY_DIR}/src/bro
COMMAND BROPATH=${BROPATH}:${srcDir} BROMAGIC=${CMAKE_SOURCE_DIR}/magic/database ${CMAKE_BINARY_DIR}/src/bro
ARGS -b -Z ${broInput} || (rm -rf .state *.log *.rst && exit 1)
# move generated doc into a new directory tree that
# defines the final structure of documents
@ -130,7 +130,7 @@ add_custom_command(OUTPUT proto-analyzers.rst
COMMAND "${CMAKE_COMMAND}"
ARGS -E remove_directory .state
# generate the reST documentation using bro
COMMAND BROPATH=${BROPATH}:${srcDir} BROMAGIC=${CMAKE_SOURCE_DIR}/magic ${CMAKE_BINARY_DIR}/src/bro
COMMAND BROPATH=${BROPATH}:${srcDir} BROMAGIC=${CMAKE_SOURCE_DIR}/magic/database ${CMAKE_BINARY_DIR}/src/bro
ARGS -b -Z base/init-bare.bro || (rm -rf .state *.log *.rst && exit 1)
# move generated doc into a new directory tree that
# defines the final structure of documents

45
doc/scripts/DocSourcesList.cmake
View file

@ -74,6 +74,8 @@ rest_target(${CMAKE_BINARY_DIR}/scripts base/bif/plugins/Bro_ZIP.events.bif.bro)
rest_target(${CMAKE_BINARY_DIR}/scripts base/bif/reporter.bif.bro)
rest_target(${CMAKE_BINARY_DIR}/scripts base/bif/strings.bif.bro)
rest_target(${CMAKE_BINARY_DIR}/scripts base/bif/types.bif.bro)
rest_target(${psd} base/files/extract/main.bro)
rest_target(${psd} base/files/hash/main.bro)
rest_target(${psd} base/frameworks/analyzer/main.bro)
rest_target(${psd} base/frameworks/cluster/main.bro)
rest_target(${psd} base/frameworks/cluster/nodes/manager.bro)
@ -83,7 +85,7 @@ rest_target(${psd} base/frameworks/cluster/setup-connections.bro)
rest_target(${psd} base/frameworks/communication/main.bro)
rest_target(${psd} base/frameworks/control/main.bro)
rest_target(${psd} base/frameworks/dpd/main.bro)
rest_target(${psd} base/frameworks/file-analysis/main.bro)
rest_target(${psd} base/frameworks/files/main.bro)
rest_target(${psd} base/frameworks/input/main.bro)
rest_target(${psd} base/frameworks/input/readers/ascii.bro)
rest_target(${psd} base/frameworks/input/readers/benchmark.bro)
@ -137,25 +139,22 @@ rest_target(${psd} base/protocols/conn/main.bro)
rest_target(${psd} base/protocols/conn/polling.bro)
rest_target(${psd} base/protocols/dns/consts.bro)
rest_target(${psd} base/protocols/dns/main.bro)
rest_target(${psd} base/protocols/ftp/file-analysis.bro)
rest_target(${psd} base/protocols/ftp/file-extract.bro)
rest_target(${psd} base/protocols/ftp/files.bro)
rest_target(${psd} base/protocols/ftp/gridftp.bro)
rest_target(${psd} base/protocols/ftp/main.bro)
rest_target(${psd} base/protocols/ftp/utils-commands.bro)
rest_target(${psd} base/protocols/http/file-analysis.bro)
rest_target(${psd} base/protocols/http/file-extract.bro)
rest_target(${psd} base/protocols/http/file-hash.bro)
rest_target(${psd} base/protocols/http/file-ident.bro)
rest_target(${psd} base/protocols/ftp/utils.bro)
rest_target(${psd} base/protocols/http/entities.bro)
rest_target(${psd} base/protocols/http/files.bro)
rest_target(${psd} base/protocols/http/main.bro)
rest_target(${psd} base/protocols/http/utils.bro)
rest_target(${psd} base/protocols/irc/dcc-send.bro)
rest_target(${psd} base/protocols/irc/file-analysis.bro)
rest_target(${psd} base/protocols/irc/files.bro)
rest_target(${psd} base/protocols/irc/main.bro)
rest_target(${psd} base/protocols/modbus/consts.bro)
rest_target(${psd} base/protocols/modbus/main.bro)
rest_target(${psd} base/protocols/smtp/entities-excerpt.bro)
rest_target(${psd} base/protocols/smtp/entities.bro)
rest_target(${psd} base/protocols/smtp/file-analysis.bro)
rest_target(${psd} base/protocols/smtp/files.bro)
rest_target(${psd} base/protocols/smtp/main.bro)
rest_target(${psd} base/protocols/socks/consts.bro)
rest_target(${psd} base/protocols/socks/main.bro)
@ -165,9 +164,12 @@ rest_target(${psd} base/protocols/ssl/main.bro)
rest_target(${psd} base/protocols/ssl/mozilla-ca-list.bro)
rest_target(${psd} base/protocols/syslog/consts.bro)
rest_target(${psd} base/protocols/syslog/main.bro)
rest_target(${psd} base/utils/active-http.bro)
rest_target(${psd} base/utils/addrs.bro)
rest_target(${psd} base/utils/conn-ids.bro)
rest_target(${psd} base/utils/dir.bro)
rest_target(${psd} base/utils/directions-and-hosts.bro)
rest_target(${psd} base/utils/exec.bro)
rest_target(${psd} base/utils/files.bro)
rest_target(${psd} base/utils/numbers.bro)
rest_target(${psd} base/utils/paths.bro)
@ -183,15 +185,18 @@ rest_target(${psd} policy/frameworks/control/controllee.bro)
rest_target(${psd} policy/frameworks/control/controller.bro)
rest_target(${psd} policy/frameworks/dpd/detect-protocols.bro)
rest_target(${psd} policy/frameworks/dpd/packet-segment-logging.bro)
rest_target(${psd} policy/frameworks/intel/conn-established.bro)
rest_target(${psd} policy/frameworks/intel/dns.bro)
rest_target(${psd} policy/frameworks/intel/http-host-header.bro)
rest_target(${psd} policy/frameworks/intel/http-url.bro)
rest_target(${psd} policy/frameworks/intel/http-user-agents.bro)
rest_target(${psd} policy/frameworks/intel/smtp-url-extraction.bro)
rest_target(${psd} policy/frameworks/intel/smtp.bro)
rest_target(${psd} policy/frameworks/intel/ssl.bro)
rest_target(${psd} policy/frameworks/intel/where-locations.bro)
rest_target(${psd} policy/frameworks/files/detect-MHR.bro)
rest_target(${psd} policy/frameworks/files/hash-all-files.bro)
rest_target(${psd} policy/frameworks/intel/do_notice.bro)
rest_target(${psd} policy/frameworks/intel/seen/conn-established.bro)
rest_target(${psd} policy/frameworks/intel/seen/dns.bro)
rest_target(${psd} policy/frameworks/intel/seen/http-host-header.bro)
rest_target(${psd} policy/frameworks/intel/seen/http-url.bro)
rest_target(${psd} policy/frameworks/intel/seen/http-user-agents.bro)
rest_target(${psd} policy/frameworks/intel/seen/smtp-url-extraction.bro)
rest_target(${psd} policy/frameworks/intel/seen/smtp.bro)
rest_target(${psd} policy/frameworks/intel/seen/ssl.bro)
rest_target(${psd} policy/frameworks/intel/seen/where-locations.bro)
rest_target(${psd} policy/frameworks/packet-filter/shunt.bro)
rest_target(${psd} policy/frameworks/software/version-changes.bro)
rest_target(${psd} policy/frameworks/software/vulnerable.bro)
@ -215,7 +220,6 @@ rest_target(${psd} policy/protocols/dns/detect-external-names.bro)
rest_target(${psd} policy/protocols/ftp/detect-bruteforcing.bro)
rest_target(${psd} policy/protocols/ftp/detect.bro)
rest_target(${psd} policy/protocols/ftp/software.bro)
rest_target(${psd} policy/protocols/http/detect-MHR.bro)
rest_target(${psd} policy/protocols/http/detect-sqli.bro)
rest_target(${psd} policy/protocols/http/detect-webapps.bro)
rest_target(${psd} policy/protocols/http/header-names.bro)
@ -227,6 +231,7 @@ rest_target(${psd} policy/protocols/modbus/known-masters-slaves.bro)
rest_target(${psd} policy/protocols/modbus/track-memmap.bro)
rest_target(${psd} policy/protocols/smtp/blocklists.bro)
rest_target(${psd} policy/protocols/smtp/detect-suspicious-orig.bro)
rest_target(${psd} policy/protocols/smtp/entities-excerpt.bro)
rest_target(${psd} policy/protocols/smtp/software.bro)
rest_target(${psd} policy/protocols/ssh/detect-bruteforcing.bro)
rest_target(${psd} policy/protocols/ssh/geo-data.bro)

1
magic Submodule

@ -0,0 +1 @@
Subproject commit e87fe13a7b776182ffc8c75076d42702f5c28fed

29
magic/COPYING
View file

@ -1,29 +0,0 @@
# $File: LEGAL.NOTICE,v 1.15 2006/05/03 18:48:33 christos Exp $
# Copyright (c) Ian F. Darwin 1986, 1987, 1989, 1990, 1991, 1992, 1994, 1995.
# Software written by Ian F. Darwin and others;
# maintained 1994- Christos Zoulas.
#
# This software is not subject to any export provision of the United States
# Department of Commerce, and may be exported to any country or planet.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
# 1. Redistributions of source code must retain the above copyright
# notice immediately at the beginning of the file, without modification,
# this list of conditions, and the following disclaimer.
# 2. Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR
# ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
# SUCH DAMAGE.

208
magic/animation
View file

@ -1,208 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: animation,v 1.47 2013/02/06 14:18:52 christos Exp $
# animation: file(1) magic for animation/movie formats
#
# animation formats
# MPEG, FLI, DL originally from vax@ccwf.cc.utexas.edu (VaX#n8)
# FLC, SGI, Apple originally from Daniel Quinlan (quinlan@yggdrasil.com)
# SGI and Apple formats
0 string MOVI Silicon Graphics movie file
!:mime video/x-sgi-movie
4 string moov Apple QuickTime
!:mime video/quicktime
4 string mdat Apple QuickTime movie (unoptimized)
!:mime video/quicktime
#4 string wide Apple QuickTime movie (unoptimized)
#!:mime video/quicktime
#4 string skip Apple QuickTime movie (modified)
#!:mime video/quicktime
#4 string free Apple QuickTime movie (modified)
#!:mime video/quicktime
4 string idsc Apple QuickTime image (fast start)
!:mime image/x-quicktime
#4 string idat Apple QuickTime image (unoptimized)
#!:mime image/x-quicktime
4 string pckg Apple QuickTime compressed archive
!:mime application/x-quicktime-player
4 string/W jP JPEG 2000 image
!:mime image/jp2
4 string ftyp ISO Media
>8 string isom \b, MPEG v4 system, version 1
!:mime video/mp4
>8 string mp41 \b, MPEG v4 system, version 1
!:mime video/mp4
>8 string mp42 \b, MPEG v4 system, version 2
!:mime video/mp4
>8 string/W jp2 \b, JPEG 2000
!:mime image/jp2
>8 string 3ge \b, MPEG v4 system, 3GPP
!:mime video/3gpp
>8 string 3gg \b, MPEG v4 system, 3GPP
!:mime video/3gpp
>8 string 3gp \b, MPEG v4 system, 3GPP
!:mime video/3gpp
>8 string 3gs \b, MPEG v4 system, 3GPP
!:mime video/3gpp
>8 string 3g2 \b, MPEG v4 system, 3GPP2
!:mime video/3gpp2
>8 string mmp4 \b, MPEG v4 system, 3GPP Mobile
!:mime video/mp4
>8 string avc1 \b, MPEG v4 system, 3GPP JVT AVC
!:mime video/3gpp
>8 string/W M4A \b, MPEG v4 system, iTunes AAC-LC
!:mime audio/mp4
>8 string/W M4V \b, MPEG v4 system, iTunes AVC-LC
!:mime video/mp4
>8 string/W qt \b, Apple QuickTime movie
!:mime video/quicktime
# MPEG sequences
# Scans for all common MPEG header start codes
0 belong&0xFFFFFF00 0x00000100
>3 byte 0xBA MPEG sequence
!:mime video/mpeg
# GRR too general as it catches also FoxPro Memo example NG.FPT
>3 byte 0xB0 MPEG sequence, v4
!:mime video/mpeg4-generic
>3 byte 0xB5 MPEG sequence, v4
!:mime video/mpeg4-generic
>3 byte 0xB3 MPEG sequence
!:mime video/mpeg
# MPEG ADTS Audio (*.mpx/mxa/aac)
# from dreesen@math.fu-berlin.de
# modified to fully support MPEG ADTS
# MP3, M1A
# modified by Joerg Jenderek
# GRR the original test are too common for many DOS files
# so don't accept as MP3 until we've tested the rate
0 beshort&0xFFFE 0xFFFA
# rates
>2 byte&0xF0 0x10 MPEG ADTS, layer III, v1, 32 kbps
!:mime audio/mpeg
>2 byte&0xF0 0x20 MPEG ADTS, layer III, v1, 40 kbps
!:mime audio/mpeg
>2 byte&0xF0 0x30 MPEG ADTS, layer III, v1, 48 kbps
!:mime audio/mpeg
>2 byte&0xF0 0x40 MPEG ADTS, layer III, v1, 56 kbps
!:mime audio/mpeg
>2 byte&0xF0 0x50 MPEG ADTS, layer III, v1, 64 kbps
!:mime audio/mpeg
>2 byte&0xF0 0x60 MPEG ADTS, layer III, v1, 80 kbps
!:mime audio/mpeg
>2 byte&0xF0 0x70 MPEG ADTS, layer III, v1, 96 kbps
!:mime audio/mpeg
>2 byte&0xF0 0x80 MPEG ADTS, layer III, v1, 112 kbps
!:mime audio/mpeg
>2 byte&0xF0 0x90 MPEG ADTS, layer III, v1, 128 kbps
!:mime audio/mpeg
>2 byte&0xF0 0xA0 MPEG ADTS, layer III, v1, 160 kbps
!:mime audio/mpeg
>2 byte&0xF0 0xB0 MPEG ADTS, layer III, v1, 192 kbps
!:mime audio/mpeg
>2 byte&0xF0 0xC0 MPEG ADTS, layer III, v1, 224 kbps
!:mime audio/mpeg
>2 byte&0xF0 0xD0 MPEG ADTS, layer III, v1, 256 kbps
!:mime audio/mpeg
>2 byte&0xF0 0xE0 MPEG ADTS, layer III, v1, 320 kbps
!:mime audio/mpeg
# MP2, M1A
0 beshort&0xFFFE 0xFFFC MPEG ADTS, layer II, v1
!:mime audio/mpeg
# MP3, M2A
0 beshort&0xFFFE 0xFFF2 MPEG ADTS, layer III, v2
!:mime audio/mpeg
# MPA, M2A
0 beshort&0xFFFE 0xFFF6 MPEG ADTS, layer I, v2
!:mime audio/mpeg
# MP3, M25A
0 beshort&0xFFFE 0xFFE2 MPEG ADTS, layer III, v2.5
!:mime audio/mpeg
# Stored AAC streams (instead of the MP4 format)
0 string ADIF MPEG ADIF, AAC
!:mime audio/x-hx-aac-adif
# Live or stored single AAC stream (used with MPEG-2 systems)
0 beshort&0xFFF6 0xFFF0 MPEG ADTS, AAC
!:mime audio/x-hx-aac-adts
# Live MPEG-4 audio streams (instead of RTP FlexMux)
0 beshort&0xFFE0 0x56E0 MPEG-4 LOAS
!:mime audio/x-mp4a-latm
# This magic isn't strong enough (matches plausible ISO-8859-1 text)
#0 beshort 0x4DE1 MPEG-4 LO-EP audio stream
#!:mime audio/x-mp4a-latm
# Summary: FLI animation format
# Created by: Daniel Quinlan <quinlan@yggdrasil.com>
# Modified by (1): Abel Cheung <abelcheung@gmail.com> (avoid over-generic detection)
4 leshort 0xAF11
# standard FLI always has 320x200 resolution and 8 bit color
>8 leshort 320
>>10 leshort 200
>>>12 leshort 8 FLI animation, 320x200x8
!:mime video/x-fli
# Summary: FLC animation format
# Created by: Daniel Quinlan <quinlan@yggdrasil.com>
# Modified by (1): Abel Cheung <abelcheung@gmail.com> (avoid over-generic detection)
4 leshort 0xAF12
# standard FLC always use 8 bit color
>12 leshort 8 FLC animation
!:mime video/x-flc
# Microsoft Advanced Streaming Format (ASF) <mpruett@sgi.com>
0 belong 0x3026b275 Microsoft ASF
!:mime video/x-ms-asf
# MNG Video Format, <URL:http://www.libpng.org/pub/mng/spec/>
0 string \x8aMNG MNG video data,
!:mime video/x-mng
# JNG Video Format, <URL:http://www.libpng.org/pub/mng/spec/>
0 string \x8bJNG JNG video data,
!:mime video/x-jng
# VRML (Virtual Reality Modelling Language)
0 string/w #VRML\ V1.0\ ascii VRML 1 file
!:mime model/vrml
0 string/w #VRML\ V2.0\ utf8 ISO/IEC 14772 VRML 97 file
!:mime model/vrml
# X3D (Extensible 3D) [http://www.web3d.org/specifications/x3d-3.0.dtd]
# From Michel Briand <michelbriand@free.fr>
0 string/t \<?xml\ version="
!:strength +1
>20 search/1000/cw \<!DOCTYPE\ X3D X3D (Extensible 3D) model xml text
!:mime model/x3d
# MPEG file
# MPEG sequences
# FIXME: This section is from the old magic.mime file and needs integrating with the rest
0 belong 0x000001BA
>4 byte &0x40
!:mime video/mp2p
>4 byte ^0x40
!:mime video/mpeg
0 belong 0x000001BB
!:mime video/mpeg
0 belong 0x000001B0
!:mime video/mp4v-es
0 belong 0x000001B5
!:mime video/mp4v-es
0 belong 0x000001B3
!:mime video/mpv
0 belong&0xFF5FFF1F 0x47400010
!:mime video/mp2t
0 belong 0x00000001
>4 byte&0x1F 0x07
!:mime video/h264

242
magic/archive
View file

@ -1,242 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: archive,v 1.78 2013/02/06 14:18:52 christos Exp $
# archive: file(1) magic for archive formats (see also "msdos" for self-
# extracting compressed archives)
#
# cpio, ar, arc, arj, hpack, lha/lharc, rar, squish, uc2, zip, zoo, etc.
# pre-POSIX "tar" archives are handled in the C code.
# POSIX tar archives
257 string ustar\0 POSIX tar archive
!:mime application/x-tar # encoding: posix
257 string ustar\040\040\0 GNU tar archive
!:mime application/x-tar # encoding: gnu
# cpio archives
#
# Yes, the top two "cpio archive" formats *are* supposed to just be "short".
# The idea is to indicate archives produced on machines with the same
# byte order as the machine running "file" with "cpio archive", and
# to indicate archives produced on machines with the opposite byte order
# from the machine running "file" with "byte-swapped cpio archive".
#
# The SVR4 "cpio(4)" hints that there are additional formats, but they
# are defined as "short"s; I think all the new formats are
# character-header formats and thus are strings, not numbers.
0 short 070707 cpio archive
!:mime application/x-cpio
0 short 0143561 byte-swapped cpio archive
!:mime application/x-cpio # encoding: swapped
#
# System V Release 1 portable(?) archive format.
#
0 string =<ar> System V Release 1 ar archive
!:mime application/x-archive
#
# Debian package; it's in the portable archive format, and needs to go
# before the entry for regular portable archives, as it's recognized as
# a portable archive whose first member has a name beginning with
# "debian".
#
0 string =!<arch>\ndebian
!:mime application/x-debian-package
#
# MIPS archive; they're in the portable archive format, and need to go
# before the entry for regular portable archives, as it's recognized as
# a portable archive whose first member has a name beginning with
# "__________E".
#
0 string =!<arch>\n__________E MIPS archive
!:mime application/x-archive
#
# BSD/SVR2-and-later portable archive formats.
#
0 string =!<arch> current ar archive
!:mime application/x-archive
# ARC archiver, from Daniel Quinlan (quinlan@yggdrasil.com)
#
# The first byte is the magic (0x1a), byte 2 is the compression type for
# the first file (0x01 through 0x09), and bytes 3 to 15 are the MS-DOS
# filename of the first file (null terminated). Since some types collide
# we only test some types on basis of frequency: 0x08 (83%), 0x09 (5%),
# 0x02 (5%), 0x03 (3%), 0x04 (2%), 0x06 (2%). 0x01 collides with terminfo.
0 lelong&0x8080ffff 0x0000081a ARC archive data, dynamic LZW
!:mime application/x-arc
0 lelong&0x8080ffff 0x0000091a ARC archive data, squashed
!:mime application/x-arc
0 lelong&0x8080ffff 0x0000021a ARC archive data, uncompressed
!:mime application/x-arc
0 lelong&0x8080ffff 0x0000031a ARC archive data, packed
!:mime application/x-arc
0 lelong&0x8080ffff 0x0000041a ARC archive data, squeezed
!:mime application/x-arc
0 lelong&0x8080ffff 0x0000061a ARC archive data, crunched
!:mime application/x-arc
# [JW] stuff taken from idarc, obviously ARC successors:
0 lelong&0x8080ffff 0x00000a1a PAK archive data
!:mime application/x-arc
0 lelong&0x8080ffff 0x0000141a ARC+ archive data
!:mime application/x-arc
0 lelong&0x8080ffff 0x0000481a HYP archive data
!:mime application/x-arc
# ARJ archiver (jason@jarthur.Claremont.EDU)
0 leshort 0xea60 ARJ archive data
!:mime application/x-arj
# LHARC/LHA archiver (Greg Roelofs, newt@uchicago.edu)
2 string -lh0- LHarc 1.x/ARX archive data [lh0]
!:mime application/x-lharc
2 string -lh1- LHarc 1.x/ARX archive data [lh1]
!:mime application/x-lharc
2 string -lz4- LHarc 1.x archive data [lz4]
!:mime application/x-lharc
2 string -lz5- LHarc 1.x archive data [lz5]
!:mime application/x-lharc
# [never seen any but the last; -lh4- reported in comp.compression:]
2 string -lzs- LHa/LZS archive data [lzs]
!:mime application/x-lha
2 string -lh\40- LHa 2.x? archive data [lh ]
!:mime application/x-lha
2 string -lhd- LHa 2.x? archive data [lhd]
!:mime application/x-lha
2 string -lh2- LHa 2.x? archive data [lh2]
!:mime application/x-lha
2 string -lh3- LHa 2.x? archive data [lh3]
!:mime application/x-lha
2 string -lh4- LHa (2.x) archive data [lh4]
!:mime application/x-lha
2 string -lh5- LHa (2.x) archive data [lh5]
!:mime application/x-lha
2 string -lh6- LHa (2.x) archive data [lh6]
!:mime application/x-lha
2 string -lh7- LHa (2.x)/LHark archive data [lh7]
!:mime application/x-lha
# RAR archiver (Greg Roelofs, newt@uchicago.edu)
0 string Rar! RAR archive data,
!:mime application/x-rar
# PKZIP multi-volume archive
0 string PK\x07\x08PK\x03\x04 Zip multi-volume archive data, at least PKZIP v2.50 to extract
!:mime application/zip
# Zip archives (Greg Roelofs, c/o zip-bugs@wkuvx1.wku.edu)
0 string PK\003\004
# Specialised zip formats which start with a member named 'mimetype'
# (stored uncompressed, with no 'extra field') containing the file's MIME type.
# Check for have 8-byte name, 0-byte extra field, name "mimetype", and
# contents starting with "application/":
>26 string \x8\0\0\0mimetypeapplication/
# OpenDocument formats (for OpenOffice 2.x / StarOffice >= 8)
# http://lists.oasis-open.org/archives/office/200505/msg00006.html
# (mimetype contains "application/vnd.oasis.opendocument.<SUBTYPE>")
>>50 string vnd.oasis.opendocument. OpenDocument
>>>73 string text
>>>>77 byte !0x2d Text
!:mime application/vnd.oasis.opendocument.text
>>>>77 string -template Text Template
!:mime application/vnd.oasis.opendocument.text-template
>>>>77 string -web HTML Document Template
!:mime application/vnd.oasis.opendocument.text-web
>>>>77 string -master Master Document
!:mime application/vnd.oasis.opendocument.text-master
>>>73 string graphics
>>>>81 byte !0x2d Drawing
!:mime application/vnd.oasis.opendocument.graphics
>>>>81 string -template Template
!:mime application/vnd.oasis.opendocument.graphics-template
>>>73 string presentation
>>>>85 byte !0x2d Presentation
!:mime application/vnd.oasis.opendocument.presentation
>>>>85 string -template Template
!:mime application/vnd.oasis.opendocument.presentation-template
>>>73 string spreadsheet
>>>>84 byte !0x2d Spreadsheet
!:mime application/vnd.oasis.opendocument.spreadsheet
>>>>84 string -template Template
!:mime application/vnd.oasis.opendocument.spreadsheet-template
>>>73 string chart
>>>>78 byte !0x2d Chart
!:mime application/vnd.oasis.opendocument.chart
>>>>78 string -template Template
!:mime application/vnd.oasis.opendocument.chart-template
>>>73 string formula
>>>>80 byte !0x2d Formula
!:mime application/vnd.oasis.opendocument.formula
>>>>80 string -template Template
!:mime application/vnd.oasis.opendocument.formula-template
>>>73 string database Database
!:mime application/vnd.oasis.opendocument.database
>>>73 string image
>>>>78 byte !0x2d Image
!:mime application/vnd.oasis.opendocument.image
>>>>78 string -template Template
!:mime application/vnd.oasis.opendocument.image-template
# EPUB (OEBPS) books using OCF (OEBPS Container Format)
# http://www.idpf.org/ocf/ocf1.0/download/ocf10.htm, section 4.
# From: Ralf Brown <ralf.brown@gmail.com>
>0x1E string mimetypeapplication/epub+zip EPUB document
!:mime application/epub+zip
# Catch other ZIP-with-mimetype formats
# In a ZIP file, the bytes immediately after a member's contents are
# always "PK". The 2 regex rules here print the "mimetype" member's
# contents up to the first 'P'. Luckily, most MIME types don't contain
# any capital 'P's. This is a kludge.
# (mimetype contains "application/<OTHER>")
>>50 string !epub+zip
>>>50 string !vnd.oasis.opendocument.
>>>>50 string !vnd.sun.xml.
>>>>>50 string !vnd.kde.
>>>>>>38 regex [!-OQ-~]+ Zip data (MIME type "%s"?)
!:mime application/zip
# (mimetype contents other than "application/*")
>26 string \x8\0\0\0mimetype
>>38 string !application/
>>>38 regex [!-OQ-~]+ Zip data (MIME type "%s"?)
!:mime application/zip
# Java Jar files
>(26.s+30) leshort 0xcafe Java Jar file data (zip)
!:mime application/jar
# Generic zip archives (Greg Roelofs, c/o zip-bugs@wkuvx1.wku.edu)
# Next line excludes specialized formats:
>(26.s+30) leshort !0xcafe
>>26 string !\x8\0\0\0mimetype Zip archive data
!:mime application/zip
# Zoo archiver
20 lelong 0xfdc4a7dc Zoo archive data
!:mime application/x-zoo
# Shell archives
10 string #\ This\ is\ a\ shell\ archive shell archive text
!:mime application/octet-stream
# Felix von Leitner <felix-file@fefe.de>
0 string d8:announce BitTorrent file
!:mime application/x-bittorrent
# EET archive
# From: Tilman Sauerbeck <tilman@code-monkey.de>
0 belong 0x1ee7ff00 EET archive
!:mime application/x-eet
# Symbian installation files
# http://www.thouky.co.uk/software/psifs/sis.html
# http://developer.symbian.com/main/downloads/papers/SymbianOSv91/softwareinstallsis.pdf
8 lelong 0x10000419 Symbian installation file
!:mime application/vnd.symbian.install
0 lelong 0x10201A7A Symbian installation file (Symbian OS 9.x)
!:mime x-epoc/x-sisx-app

19
magic/assembler
View file

@ -1,19 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: assembler,v 1.3 2013/01/04 17:23:28 christos Exp $
# make: file(1) magic for assembler source
#
0 regex \^[\020\t]*\\.asciiz assembler source text
!:mime text/x-asm
0 regex \^[\020\t]*\\.byte assembler source text
!:mime text/x-asm
0 regex \^[\020\t]*\\.even assembler source text
!:mime text/x-asm
0 regex \^[\020\t]*\\.globl assembler source text
!:mime text/x-asm
0 regex \^[\020\t]*\\.text assembler source text
!:mime text/x-asm
0 regex \^[\020\t]*\\.file assembler source text
!:mime text/x-asm
0 regex \^[\020\t]*\\.type assembler source text
!:mime text/x-asm

149
magic/audio
View file

@ -1,149 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: audio,v 1.65 2012/10/31 13:38:40 christos Exp $
# audio: file(1) magic for sound formats (see also "iff")
#
# Jan Nicolai Langfeldt (janl@ifi.uio.no), Dan Quinlan (quinlan@yggdrasil.com),
# and others
#
# Sun/NeXT audio data
0 string .snd Sun/NeXT audio data:
>12 belong 1 8-bit ISDN mu-law,
!:mime audio/basic
>12 belong 2 8-bit linear PCM [REF-PCM],
!:mime audio/basic
>12 belong 3 16-bit linear PCM,
!:mime audio/basic
>12 belong 4 24-bit linear PCM,
!:mime audio/basic
>12 belong 5 32-bit linear PCM,
!:mime audio/basic
>12 belong 6 32-bit IEEE floating point,
!:mime audio/basic
>12 belong 7 64-bit IEEE floating point,
!:mime audio/basic
>12 belong 23 8-bit ISDN mu-law compressed (CCITT G.721 ADPCM voice enc.),
!:mime 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
0 lelong 0x0064732E DEC audio data:
>12 lelong 1 8-bit ISDN mu-law,
!:mime audio/x-dec-basic
>12 lelong 2 8-bit linear PCM [REF-PCM],
!:mime audio/x-dec-basic
>12 lelong 3 16-bit linear PCM,
!:mime audio/x-dec-basic
>12 lelong 4 24-bit linear PCM,
!:mime audio/x-dec-basic
>12 lelong 5 32-bit linear PCM,
!:mime audio/x-dec-basic
>12 lelong 6 32-bit IEEE floating point,
!:mime audio/x-dec-basic
>12 lelong 7 64-bit IEEE floating point,
!:mime audio/x-dec-basic
>12 lelong 23 8-bit ISDN mu-law compressed (CCITT G.721 ADPCM voice enc.),
!:mime audio/x-dec-basic
# Creative Labs AUDIO stuff
0 string MThd Standard MIDI data
!:mime audio/midi
0 string CTMF Creative Music (CMF) data
!:mime audio/x-unknown
0 string SBI SoundBlaster instrument data
!:mime audio/x-unknown
0 string Creative\ Voice\ File Creative Labs voice data
!:mime audio/x-unknown
# Real Audio (Magic .ra\0375)
0 belong 0x2e7261fd RealAudio sound file
!:mime audio/x-pn-realaudio
0 string .RMF\0\0\0 RealMedia file
!:mime application/vnd.rn-realmedia
# 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@chiark.greenend.org.uk)
# <doj@cubic.org> added title printing on 2003-06-24
0 string MAS_UTrack_V00
>14 string >/0 ultratracker V1.%.1s module sound data
!:mime audio/x-mod
#audio/x-tracker-module
0 string Extended\ Module: Fasttracker II module sound data
!:mime audio/x-mod
#audio/x-tracker-module
21 string/c =!SCREAM! Screamtracker 2 module sound data
!:mime audio/x-mod
#audio/x-screamtracker-module
21 string BMOD2STM Screamtracker 2 module sound data
!:mime audio/x-mod
#audio/x-screamtracker-module
1080 string M.K. 4-channel Protracker module sound data
!:mime audio/x-mod
#audio/x-protracker-module
1080 string M!K! 4-channel Protracker module sound data
!:mime audio/x-mod
#audio/x-protracker-module
1080 string FLT4 4-channel Startracker module sound data
!:mime audio/x-mod
#audio/x-startracker-module
1080 string FLT8 8-channel Startracker module sound data
!:mime audio/x-mod
#audio/x-startracker-module
1080 string 4CHN 4-channel Fasttracker module sound data
!:mime audio/x-mod
#audio/x-fasttracker-module
1080 string 6CHN 6-channel Fasttracker module sound data
!:mime audio/x-mod
#audio/x-fasttracker-module
1080 string 8CHN 8-channel Fasttracker module sound data
!:mime audio/x-mod
#audio/x-fasttracker-module
1080 string CD81 8-channel Octalyser module sound data
!:mime audio/x-mod
#audio/x-octalysertracker-module
1080 string OKTA 8-channel Octalyzer module sound data
!:mime audio/x-mod
#audio/x-octalysertracker-module
# Not good enough.
#1082 string CH
#>1080 string >/0 %.2s-channel Fasttracker "oktalyzer" module sound data
1080 string 16CN 16-channel Taketracker module sound data
!:mime audio/x-mod
#audio/x-taketracker-module
1080 string 32CN 32-channel Taketracker module sound data
!:mime audio/x-mod
#audio/x-taketracker-module
# Impulse tracker module (audio/x-it)
0 string IMPM Impulse Tracker module sound data -
!:mime audio/x-mod
# Free lossless audio codec <http://flac.sourceforge.net>
# From: Przemyslaw Augustyniak <silvathraec@rpg.pl>
0 string fLaC FLAC audio bitstream data
!:mime audio/x-flac
# Monkey's Audio compressed audio format (.ape)
# From danny.milo@gmx.net (Danny Milosavljevic)
# New version from Abel Cheung <abel (@) oaka.org>
0 string MAC\040 Monkey's Audio compressed format
!:mime audio/x-ape
# musepak support From: "Jiri Pejchal" <jiri.pejchal@gmail.com>
0 string MP+ Musepack audio
!:mime audio/x-musepack

47
magic/c-lang
View file

@ -1,47 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: c-lang,v 1.16 2011/12/09 08:02:16 rrt Exp $
# c-lang: file(1) magic for C and related languages programs
#
# BCPL
0 search/8192 "libhdr" BCPL source text
!:mime text/x-bcpl
0 search/8192 "LIBHDR" BCPL source text
!:mime text/x-bcpl
# C
0 regex \^#include C source text
!:mime text/x-c
0 regex \^char C source text
!:mime text/x-c
0 regex \^double C source text
!:mime text/x-c
0 regex \^extern C source text
!:mime text/x-c
0 regex \^float C source text
!:mime text/x-c
0 regex \^struct C source text
!:mime text/x-c
0 regex \^union C source text
!:mime text/x-c
0 search/8192 main( C source text
!:mime text/x-c
# C++
# The strength of these rules is increased so they beat the C rules above
0 regex \^template C++ source text
!:strength + 5
!:mime text/x-c++
0 regex \^virtual C++ source text
!:strength + 5
!:mime text/x-c++
0 regex \^class C++ source text
!:strength + 5
!:mime text/x-c++
0 regex \^public: C++ source text
!:strength + 5
!:mime text/x-c++
0 regex \^private: C++ source text
!:strength + 5
!:mime text/x-c++

31
magic/cafebabe
View file

@ -1,31 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: cafebabe,v 1.13 2013/02/26 21:04:38 christos Exp $
# Cafe Babes unite!
#
# Since Java bytecode and Mach-O universal binaries have the same magic number,
# the test must be performed in the same "magic" sequence to get both right.
# The long at offset 4 in a Mach-O universal binary tells the number of
# architectures; the short at offset 4 in a Java bytecode file is the JVM minor
# version and the short at offset 6 is the JVM major version. Since there are only
# only 18 labeled Mach-O architectures at current, and the first released
# Java class format was version 43.0, we can safely choose any number
# between 18 and 39 to test the number of architectures against
# (and use as a hack). Let's not use 18, because the Mach-O people
# might add another one or two as time goes by...
#
### JAVA START ###
0 belong 0xcafebabe
!:mime application/x-java-applet
0 belong 0xcafed00d JAR compressed with pack200,
>5 byte x version %d.
>4 byte x \b%d
!:mime application/x-java-pack200
0 belong 0xcafed00d JAR compressed with pack200,
>5 byte x version %d.
>4 byte x \b%d
!:mime application/x-java-pack200
### JAVA END ###

82
magic/commands
View file

@ -1,82 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: commands,v 1.44 2013/02/05 15:20:47 christos Exp $
# commands: file(1) magic for various shells and interpreters
#
#0 string/w : shell archive or script for antique kernel text
0 string/wt #!\ /bin/sh POSIX shell script text executable
!:mime text/x-shellscript
0 string/wt #!\ /bin/csh C shell script text executable
!:mime text/x-shellscript
# korn shell magic, sent by George Wu, gwu@clyde.att.com
0 string/wt #!\ /bin/ksh Korn shell script text executable
!:mime text/x-shellscript
0 string/wt #!\ /bin/tcsh Tenex C shell script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/bin/tcsh Tenex C shell script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/local/tcsh Tenex C shell script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/local/bin/tcsh Tenex C shell script text executable
!:mime text/x-shellscript
#
# zsh/ash/ae/nawk/gawk magic from cameron@cs.unsw.oz.au (Cameron Simpson)
0 string/wt #!\ /bin/zsh Paul Falstad's zsh script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/bin/zsh Paul Falstad's zsh script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/local/bin/zsh Paul Falstad's zsh script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/local/bin/ash Neil Brown's ash script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/local/bin/ae Neil Brown's ae script text executable
!:mime text/x-shellscript
0 string/wt #!\ /bin/nawk new awk script text executable
!:mime text/x-nawk
0 string/wt #!\ /usr/bin/nawk new awk script text executable
!:mime text/x-nawk
0 string/wt #!\ /usr/local/bin/nawk new awk script text executable
!:mime text/x-nawk
0 string/wt #!\ /bin/gawk GNU awk script text executable
!:mime text/x-gawk
0 string/wt #!\ /usr/bin/gawk GNU awk script text executable
!:mime text/x-gawk
0 string/wt #!\ /usr/local/bin/gawk GNU awk script text executable
!:mime text/x-gawk
#
0 string/wt #!\ /bin/awk awk script text executable
!:mime text/x-awk
0 string/wt #!\ /usr/bin/awk awk script text executable
!:mime text/x-awk
# bash shell magic, from Peter Tobias (tobias@server.et-inf.fho-emden.de)
0 string/wt #!\ /bin/bash Bourne-Again shell script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/bin/bash Bourne-Again shell script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/local/bash Bourne-Again shell script text executable
!:mime text/x-shellscript
0 string/wt #!\ /usr/local/bin/bash Bourne-Again shell script text executable
!:mime text/x-shellscript
# PHP scripts
# Ulf Harnhammar <ulfh@update.uu.se>
0 search/1/c =<?php PHP script text
!:strength + 10
!:mime text/x-php
0 search/1 =<?\n PHP script text
!:mime text/x-php
0 search/1 =<?\r PHP script text
!:mime text/x-php
0 search/1/w #!\ /usr/local/bin/php PHP script text executable
!:strength + 10
!:mime text/x-php
0 search/1/w #!\ /usr/bin/php PHP script text executable
!:strength + 10
!:mime text/x-php
# Smarty compiled template, http://www.smarty.net/
# Elan Ruusamae <glen@delfi.ee>
0 string =<?php\ /*\ Smarty\ version Smarty compiled template
>24 regex [0-9.]+ \b, version %s
!:mime text/x-php

77
magic/compress
View file

@ -1,77 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: compress,v 1.48 2011/12/07 18:39:43 christos Exp $
# compress: file(1) magic for pure-compression formats (no archives)
#
# compress, gzip, pack, compact, huf, squeeze, crunch, freeze, yabba, 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 compress'd data
!:mime application/x-compress
!:apple LZIVZIVU
# gzip (GNU zip, not to be confused with Info-ZIP or PKWARE zip archiver)
# Edited by Chris Chittleborough <cchittleborough@yahoo.com.au>, March 2002
# * Original filename is only at offset 10 if "extra field" absent
# * Produce shorter output - notably, only report compression methods
# other than 8 ("deflate", the only method defined in RFC 1952).
0 string \037\213 gzip compressed data
!:mime application/x-gzip
# packed data, Huffman (minimum redundancy) codes on a byte-by-byte basis
0 string \037\036 packed data
!:mime application/octet-stream
#
# This magic number is byte-order-independent.
0 short 0x1f1f old packed data
!:mime 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?
#
0 short 0x1fff compacted data
!:mime application/octet-stream
# This string is valid for SunOS (BE) and a matching "short" is listed
# in the Ultrix (LE) magic file.
0 string \377\037 compacted data
!:mime application/octet-stream
0 short 0145405 huf output
!:mime application/octet-stream
# bzip2
0 string BZh bzip2 compressed data
!:mime application/x-bzip2
# lzip
0 string LZIP lzip compressed data
!:mime application/x-lzip
# 7-zip archiver, from Thomas Klausner (wiz@danbala.tuwien.ac.at)
# http://www.7-zip.org or DOC/7zFormat.txt
#
0 string 7z\274\257\047\034 7-zip archive data,
>6 byte x version %d
>7 byte x \b.%d
!:mime application/x-7z-compressed
# Type: LZMA
0 lelong&0xffffff =0x5d
>12 leshort =0xff LZMA compressed data,
>>5 lequad =0xffffffffffffffff streamed
>>5 lequad !0xffffffffffffffff non-streamed, size %lld
!:mime application/x-lzma
# http://tukaani.org/xz/xz-file-format.txt
0 ustring \xFD7zXZ\x00 XZ compressed data
!:mime application/x-xz
# https://github.com/ckolivas/lrzip/blob/master/doc/magic.header.txt
0 string LRZI LRZIP compressed data
>4 byte x - version %d
>5 byte x \b.%d
!:mime application/x-lrzip

47
magic/database
View file

@ -1,47 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: database,v 1.32 2013/02/06 14:18:52 christos Exp $
# database: file(1) magic for various databases
#
# extracted from header/code files by Graeme Wilford (eep2gw@ee.surrey.ac.uk)
#
#
# GDBM magic numbers
# Will be maintained as part of the GDBM distribution in the future.
# <downsj@teeny.org>
0 belong 0x13579ace GNU dbm 1.x or ndbm database, big endian
!:mime application/x-gdbm
0 lelong 0x13579ace GNU dbm 1.x or ndbm database, little endian
!:mime application/x-gdbm
0 string GDBM GNU dbm 2.x database
!:mime application/x-gdbm
#
# Berkeley DB
#
# Ian Darwin's file /etc/magic files: big/little-endian version.
#
# Hash 1.85/1.86 databases store metadata in network byte order.
# Btree 1.85/1.86 databases store the metadata in host byte order.
# Hash and Btree 2.X and later databases store the metadata in host byte order.
0 long 0x00061561 Berkeley DB
!:mime application/x-dbm
# MS Access database
4 string Standard\ Jet\ DB Microsoft Access Database
!:mime application/x-msaccess
4 string Standard\ ACE\ DB Microsoft Access Database
!:mime application/x-msaccess
# Tokyo Cabinet magic data
# http://tokyocabinet.sourceforge.net/index.html
0 string ToKyO\ CaBiNeT\n Tokyo Cabinet
>14 string x \b (%s)
>32 byte 0 \b, Hash
!:mime application/x-tokyocabinet-hash
>32 byte 1 \b, B+ tree
!:mime application/x-tokyocabinet-btree
>32 byte 2 \b, Fixed-length
!:mime application/x-tokyocabinet-fixed
>32 byte 3 \b, Table
!:mime application/x-tokyocabinet-table

25
magic/diff
View file

@ -1,25 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: diff,v 1.13 2012/06/16 14:43:36 christos Exp $
# diff: file(1) magic for diff(1) output
#
0 search/1 diff\ diff output text
!:mime text/x-diff
0 search/1 ***\ diff output text
!:mime text/x-diff
0 search/1 Only\ in\ diff output text
!:mime text/x-diff
0 search/1 Common\ subdirectories:\ diff output text
!:mime text/x-diff
0 search/1 Index: RCS/CVS diff output text
!:mime text/x-diff
# unified diff
0 search/4096 ---\
>&0 search/1024 \n
>>&0 search/1 +++\
>>>&0 search/1024 \n
>>>>&0 search/1 @@ unified diff output text
!:mime text/x-diff
!:strength + 90

43
magic/elf
View file

@ -1,43 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# elf: file(1) magic for ELF executables
#
# We have to check the byte order flag to see what byte order all the
# other stuff in the header is in.
#
# What're the correct byte orders for the nCUBE and the Fujitsu VPP500?
#
# Created by: unknown
# Modified by (1): Daniel Quinlan <quinlan@yggdrasil.com>
# Modified by (2): Peter Tobias <tobias@server.et-inf.fho-emden.de> (core support)
# Modified by (3): Christian 'Dr. Disk' Hechelmann <drdisk@ds9.au.s.shuttle.de> (fix of core support)
# Modified by (4): <gerardo.cacciari@gmail.com> (VMS Itanium)
# Modified by (5): Matthias Urlichs <smurf@debian.org> (Listing of many architectures)
0 string \177ELF ELF
>4 byte 0 invalid class
>4 byte 1 32-bit
>4 byte 2 64-bit
>5 byte 0 invalid byte order
>5 byte 1 LSB
>>16 leshort 0 no file type,
!:strength *2
!:mime application/octet-stream
>>16 leshort 1 relocatable,
!:mime application/x-object
>>16 leshort 2 executable,
!:mime application/x-executable
>>16 leshort 3 shared object,
!:mime application/x-sharedlib
>>16 leshort 4 core file
!:mime application/x-coredump
>5 byte 2 MSB
>>16 beshort 0 no file type,
!:mime application/octet-stream
>>16 beshort 1 relocatable,
!:mime application/x-object
>>16 beshort 2 executable,
!:mime application/x-executable
>>16 beshort 3 shared object,
!:mime application/x-sharedlib
>>16 beshort 4 core file,
!:mime application/x-coredump

34
magic/epoc
View file

@ -1,34 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: epoc,v 1.7 2009/09/19 16:28:09 christos Exp $
# EPOC : file(1) magic for EPOC documents [Psion Series 5/Osaris/Geofox 1]
# Stefan Praszalowicz <hpicollo@worldnet.fr> and Peter Breitenlohner <peb@mppmu.mpg.de>
# Useful information for improving this file can be found at:
# http://software.frodo.looijaard.name/psiconv/formats/Index.html
#------------------------------------------------------------------------------
0 lelong 0x10000037 Psion Series 5
>4 lelong 0x10000042 multi-bitmap image
!:mime image/x-epoc-mbm
>4 lelong 0x1000006D
>>8 lelong 0x1000007D Sketch image
!:mime image/x-epoc-sketch
>>8 lelong 0x1000007F Word file
!:mime application/x-epoc-word
>>8 lelong 0x10000085 OPL program (TextEd)
!:mime application/x-epoc-opl
>>8 lelong 0x10000088 Sheet file
!:mime application/x-epoc-sheet
>4 lelong 0x10000073 OPO module
!:mime application/x-epoc-opo
>4 lelong 0x10000074 OPL application
!:mime application/x-epoc-app
0 lelong 0x10000050 Psion Series 5
>4 lelong 0x1000006D database
>>8 lelong 0x10000084 Agenda file
!:mime application/x-epoc-agenda
>>8 lelong 0x10000086 Data file
!:mime application/x-epoc-data
>>8 lelong 0x10000CEA Jotter file
!:mime application/x-epoc-jotter

12
magic/filesystems
View file

@ -1,12 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: filesystems,v 1.76 2013/02/18 18:45:41 christos Exp $
# filesystems: file(1) magic for different filesystems
#
# CDROM Filesystems
# Modified for UDF by gerardo.cacciari@gmail.com
32769 string CD001 #
!:mime application/x-iso9660-image
37633 string CD001 ISO 9660 CD-ROM filesystem data (raw 2352 byte sectors)
!:mime application/x-iso9660-image

18
magic/flash
View file

@ -1,18 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: flash,v 1.8 2009/09/19 16:28:09 christos Exp $
# flash: file(1) magic for Macromedia Flash file format
#
# See
#
# http://www.macromedia.com/software/flash/open/
#
0 string FWS Macromedia Flash data,
>3 byte x version %d
!:mime application/x-shockwave-flash
0 string CWS Macromedia Flash data (compressed),
!:mime application/x-shockwave-flash
# From: Cal Peake <cp@absolutedigital.net>
0 string FLV Macromedia Flash Video
!:mime video/x-flv

32
magic/fonts
View file

@ -1,32 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: fonts,v 1.25 2013/02/06 14:18:52 christos Exp $
# fonts: file(1) magic for font data
#
# X11 font files in SNF (Server Natural Format) format
# updated by Joerg Jenderek at Feb 2013
# http://computer-programming-forum.com/51-perl/8f22fb96d2e34bab.htm
0 belong 00000004 X11 SNF font data, MSB first
#>104 belong 00000004 X11 SNF font data, MSB first
!:mime application/x-font-sfn
# GRR: line below too general as it catches also Xbase index file t3-CHAR.NDX
0 lelong 00000004
>104 lelong 00000004 X11 SNF font data, LSB first
!:mime application/x-font-sfn
# True Type fonts
0 string \000\001\000\000\000 TrueType font data
!:mime application/x-font-ttf
# Opentype font data from Avi Bercovich
0 string OTTO OpenType font data
!:mime application/vnd.ms-opentype
# Gurkan Sengun <gurkan@linuks.mine.nu>, www.linuks.mine.nu
0 string SplineFontDB: Spline Font Database
!:mime application/vnd.font-fontforge-sfd
# EOT
34 string LP Embedded OpenType (EOT)
!:mime application/vnd.ms-fontobject

7
magic/fortran
View file

@ -1,7 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: fortran,v 1.6 2009/09/19 16:28:09 christos Exp $
# FORTRAN source
0 regex/100 \^[Cc][\ \t] FORTRAN program
!:mime text/x-fortran
!:strength - 5

31
magic/frame
View file

@ -1,31 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# 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:
#
# Note that this is the Framemaker Maker Interchange Format, not the
# Normal format which would be application/vnd.framemaker.
#
0 string \<MakerFile FrameMaker document
!:mime application/x-mif
0 string \<MIFFile FrameMaker MIF (ASCII) file
!:mime application/x-mif
0 search/1 \<MakerDictionary FrameMaker Dictionary text
!:mime application/x-mif
0 string \<MakerScreenFont FrameMaker Font file
!:mime application/x-mif
0 string \<MML FrameMaker MML file
!:mime application/x-mif
0 string \<BookFile FrameMaker Book file
!:mime application/x-mif
# XXX - this book entry should be verified, if you find one, uncomment this
#0 string \<Book\ FrameMaker Book (ASCII) file
#!:mime application/x-mif
#>6 string 3.0 (3.0)
#>6 string 2.0 (2.0)
#>6 string 1.0 (1.0)
0 string \<Maker Intermediate Print File FrameMaker IPL file
!:mime application/x-mif

13
magic/gimp
View file

@ -1,13 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: gimp,v 1.6 2009/09/19 16:28:09 christos Exp $
# GIMP Gradient: file(1) magic for the GIMP's gradient data files
# by Federico Mena <federico@nuclecu.unam.mx>
#------------------------------------------------------------------------------
# XCF: file(1) magic for the XCF image format used in the GIMP developed
# by Spencer Kimball and Peter Mattis
# ('Bucky' LaDieu, nega@vt.edu)
0 string gimp\ xcf GIMP XCF image data,
!:mime image/x-xcf

23
magic/gnu
View file

@ -1,23 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: gnu,v 1.13 2012/01/03 17:16:54 christos Exp $
# gnu: file(1) magic for various GNU tools
#
# GNU nlsutils message catalog file format
#
# GNU message catalog (.mo and .gmo files)
# GnuPG
# The format is very similar to pgp
# Note: magic.mime had 0x8501 for the next line instead of 0x8502
0 beshort 0x8502 GPG encrypted data
!:mime text/PGP # encoding: data
# This magic is not particularly good, as the keyrings don't have true
# magic. Nevertheless, it covers many keyrings.
0 beshort 0x9901 GPG key public ring
!:mime application/x-gnupg-keyring
# gettext message catalogue
0 regex \^msgid\ GNU gettext message catalogue text
!:mime text/x-po

8
magic/gnumeric
View file

@ -1,8 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# gnumeric: file(1) magic for Gnumeric spreadsheet
# This entry is only semi-helpful, as Gnumeric compresses its files, so
# they will ordinarily reported as "compressed", but at least -z helps
39 string =<gmr:Workbook Gnumeric spreadsheet
!:mime application/x-gnumeric

51
magic/icc
View file

@ -1,51 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# icc: file(1) magic for International Color Consortium file formats
#
# Color profiles as per the ICC's "Image technology colour management -
# Architecture, profile format, and data structure" specification.
# See
#
# http://www.color.org/specification/ICC1v43_2010-12.pdf
#
# for Specification ICC.1:2010 (Profile version 4.3.0.0).
#
# Bytes 36 to 39 contain a generic profile file signature of "acsp";
# bytes 40 to 43 "may be used to identify the primary platform/operating
# system framework for which the profile was created".
#
# There are other fields that might be worth dumping as well.
#
# This appears to be what's used for Apple ColorSync profiles.
# Instead of adding that, Apple just changed the generic "acsp" entry
# to be for "ColorSync ICC Color Profile" rather than "Kodak Color
# Management System, ICC Profile".
# Yes, it's "APPL", not "AAPL"; see the spec.
36 string acspAPPL ColorSync ICC Profile
!:mime application/vnd.iccprofile
# Microsoft ICM color profile
36 string acspMSFT Microsoft ICM Color Profile
!:mime application/vnd.iccprofile
# Yes, that's a blank after "SGI".
36 string acspSGI\ SGI ICC Profile
!:mime application/vnd.iccprofile
# XXX - is this what's used for the Sun KCMS or not? The standard file
# uses just "acsp" for that, but Apple's file uses it for "ColorSync",
# and there *is* an identified "primary platform" value of SUNW.
36 string acspSUNW Sun KCMS ICC Profile
!:mime application/vnd.iccprofile
# Any other profile.
# XXX - should we use "acsp\0\0\0\0" for "no primary platform" profiles,
# and use "acsp" for everything else and dump the "primary platform"
# string in those cases?
36 string acsp ICC Profile
!:mime application/vnd.iccprofile

21
magic/iff
View file

@ -1,21 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: iff,v 1.12 2009/09/19 16:28:09 christos Exp $
# iff: file(1) magic for Interchange File Format (see also "audio" & "images")
#
# Daniel Quinlan (quinlan@yggdrasil.com) -- IFF was designed by Electronic
# Arts for file interchange. It has also been used by Apple, SGI, and
# especially Commodore-Amiga.
#
# IFF files begin with an 8 byte FORM header, followed by a 4 character
# FORM type, which is followed by the first chunk in the FORM.
0 string FORM IFF data
#>4 belong x \b, FORM is %d bytes long
# audio formats
>8 string AIFF \b, AIFF audio
!:mime audio/x-aiff
>8 string AIFC \b, AIFF-C compressed audio
!:mime audio/x-aiff
>8 string 8SVX \b, 8SVX 8-bit sampled sound voice
!:mime audio/x-aiff

255
magic/images
View file

@ -1,255 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: images,v 1.80 2013/02/06 14:18:52 christos Exp $
# images: file(1) magic for image formats (see also "iff", and "c-lang" for
# XPM bitmaps)
#
# originally from jef@helios.ee.lbl.gov (Jef Poskanzer),
# additions by janl@ifi.uio.no as well as others. Jan also suggested
# merging several one- and two-line files into here.
#
# little magic: PCX (first byte is 0x0a)
# PBMPLUS images
# The next byte following the magic is always whitespace.
# strength is changed to try these patterns before "x86 boot sector"
0 search/1 P1
>3 regex =[0-9]*\ [0-9]* Netpbm PBM image text
>3 regex =[0-9]+\ \b, size = %sx
>>3 regex =\ [0-9]+ \b%s
!:strength + 45
!:mime image/x-portable-bitmap
0 search/1 P2
>3 regex =[0-9]*\ [0-9]* Netpbm PGM image text
>3 regex =[0-9]+\ \b, size = %sx
>>3 regex =\ [0-9]+ \b%s
!:strength + 45
!:mime image/x-portable-greymap
0 search/1 P3 Netpbm PPM image text
>3 regex =[0-9]*\ [0-9]* Netpbm PPM image text
>3 regex =[0-9]+\ \b, size = %sx
>>3 regex =\ [0-9]+ \b%s
!:strength + 45
!:mime image/x-portable-pixmap
0 string P4
>3 regex =[0-9]*\ [0-9]* Netpbm PBM "rawbits" image data
>3 regex =[0-9]+\ \b, size = %sx
>>3 regex =\ [0-9]+ \b%s
!:strength + 45
!:mime image/x-portable-bitmap
0 string P5
>3 regex =[0-9]*\ [0-9]* Netpbm PGM "rawbits" image data
>3 regex =[0-9]+\ \b, size = %sx
>>3 regex =\ [0-9]+ \b%s
!:strength + 45
!:mime image/x-portable-greymap
0 string P6
>3 regex =[0-9]*\ [0-9]* Netpbm PPM "rawbits" image data
>3 regex =[0-9]+\ \b, size = %sx
>>3 regex =\ [0-9]+ \b%s
!:strength + 45
!:mime image/x-portable-pixmap
0 string P7 Netpbm PAM image file
!:mime image/x-portable-pixmap
# NIFF (Navy Interchange File Format, a modification of TIFF) images
# [GRR: this *must* go before TIFF]
0 string IIN1 NIFF image data
!:mime image/x-niff
# Canon RAW version 1 (CRW) files are a type of Canon Image File Format
# (CIFF) file. These are apparently all little-endian.
# From: Adam Buchbinder <adam.buchbinder@gmail.com>
# URL: http://www.sno.phy.queensu.ca/~phil/exiftool/canon_raw.html
0 string II\x1a\0\0\0HEAPCCDR Canon CIFF raw image data
!:mime image/x-canon-crw
# Canon RAW version 2 (CR2) files are a kind of TIFF with an extra magic
# number. Put this above the TIFF test to make sure we detect them.
# These are apparently all little-endian.
# From: Adam Buchbinder <adam.buchbinder@gmail.com>
# URL: http://libopenraw.freedesktop.org/wiki/Canon_CR2
0 string II\x2a\0\x10\0\0\0CR Canon CR2 raw image data
!:mime image/x-canon-cr2
# Tag Image File Format, from Daniel Quinlan (quinlan@yggdrasil.com)
# The second word of TIFF files is the TIFF version number, 42, which has
# never changed. The TIFF specification recommends testing for it.
0 string MM\x00\x2a TIFF image data, big-endian
!:mime image/tiff
0 string II\x2a\x00 TIFF image data, little-endian
!:mime image/tiff
0 string MM\x00\x2b Big TIFF image data, big-endian
!:mime image/tiff
0 string II\x2b\x00 Big TIFF image data, little-endian
!:mime image/tiff
# PNG [Portable Network Graphics, or "PNG's Not GIF"] images
# (Greg Roelofs, newt@uchicago.edu)
# (Albert Cahalan, acahalan@cs.uml.edu)
#
# 137 P N G \r \n ^Z \n [4-byte length] H E A D [HEAD data] [HEAD crc] ...
#
0 string \x89PNG\x0d\x0a\x1a\x0a PNG image data
!:mime image/png
# possible GIF replacements; none yet released!
# (Greg Roelofs, newt@uchicago.edu)
#
# GRR 950115: this was mine ("Zip GIF"):
0 string GIF94z ZIF image (GIF+deflate alpha)
!:mime image/x-unknown
#
# GRR 950115: this is Jeremy Wohl's Free Graphics Format (better):
#
0 string FGF95a FGF image (GIF+deflate beta)
!:mime image/x-unknown
#
# GRR 950115: this is Thomas Boutell's Portable Bitmap Format proposal
# (best; not yet implemented):
#
0 string PBF PBF image (deflate compression)
!:mime image/x-unknown
# GIF
0 string GIF8 GIF image data
!:mime image/gif
!:apple 8BIMGIFf
# From: Joerg Jenderek <joerg.jen.der.ek@gmx.net>
# most files with the extension .EPA and some with .BMP
0 string \x11\x06 Award BIOS Logo, 136 x 84
!:mime image/x-award-bioslogo
0 string \x11\x09 Award BIOS Logo, 136 x 126
!:mime image/x-award-bioslogo
#0 string \x07\x1f BIOS Logo corrupted?
# http://www.blackfiveservices.co.uk/awbmtools.shtml
# http://biosgfx.narod.ru/v3/
# http://biosgfx.narod.ru/abr-2/
0 string AWBM
>4 leshort <1981 Award BIOS bitmap
!:mime image/x-award-bmp
# PC bitmaps (OS/2, Windows BMP files) (Greg Roelofs, newt@uchicago.edu)
0 string BM
>14 leshort 12 PC bitmap, OS/2 1.x format
!:mime image/x-ms-bmp
>14 leshort 64 PC bitmap, OS/2 2.x format
!:mime image/x-ms-bmp
>14 leshort 40 PC bitmap, Windows 3.x format
!:mime image/x-ms-bmp
>14 leshort 128 PC bitmap, Windows NT/2000 format
!:mime image/x-ms-bmp
# XPM icons (Greg Roelofs, newt@uchicago.edu)
0 search/1 /*\ XPM\ */ X pixmap image text
!:mime image/x-xpmi
# DICOM medical imaging data
128 string DICM DICOM medical imaging data
!:mime application/dicom
# XWD - X Window Dump file.
# As described in /usr/X11R6/include/X11/XWDFile.h
# used by the xwd program.
# Bradford Castalia, idaeim, 1/01
# updated by Adam Buchbinder, 2/09
# The following assumes version 7 of the format; the first long is the length
# of the header, which is at least 25 4-byte longs, and the one at offset 8
# is a constant which is always either 1 or 2. Offset 12 is the pixmap depth,
# which is a maximum of 32.
0 belong >100
>8 belong <3
>>12 belong <33
>>>4 belong 7 XWD X Window Dump image data
!:mime image/x-xwindowdump
# PCX image files
# From: Dan Fandrich <dan@coneharvesters.com>
# updated by Joerg Jenderek at Feb 2013 by http://de.wikipedia.org/wiki/PCX
# http://web.archive.org/web/20100206055706/http://www.qzx.com/pc-gpe/pcx.txt
# GRR: original test was still too general as it catches xbase examples T5.DBT,T6.DBT with 0xa000000
# test for bytes 0x0a,version byte (0,2,3,4,5),compression byte flag(0,1), bit depth (>0) of PCX or T5.DBT,T6.DBT
0 ubelong&0xffF8fe00 0x0a000000
# for PCX bit depth > 0
>3 ubyte >0
# test for valid versions
>>1 ubyte <6
>>>1 ubyte !1 PCX
!:mime image/x-pcx
# Adobe Photoshop
# From: Asbjoern Sloth Toennesen <asbjorn@lila.io>
0 string 8BPS Adobe Photoshop Image
!:mime image/vnd.adobe.photoshop
# Summary: DjVu image / document
# Extension: .djvu
# Reference: http://djvu.org/docs/DjVu3Spec.djvu
# Submitted by: Stephane Loeuillet <stephane.loeuillet@tiscali.fr>
# Modified by (1): Abel Cheung <abelcheung@gmail.com>
0 string AT&TFORM
>12 string DJVM DjVu multiple page document
!:mime image/vnd.djvu
>12 string DJVU DjVu image or single page document
!:mime image/vnd.djvu
>12 string DJVI DjVu shared document
!:mime image/vnd.djvu
>12 string THUM DjVu page thumbnails
!:mime image/vnd.djvu
# Originally by Marc Espie
# Modified by Robert Minsk <robertminsk at yahoo.com>
# http://www.openexr.com/openexrfilelayout.pdf
0 lelong 20000630 OpenEXR image data,
!:mime image/x-exr
# SMPTE Digital Picture Exchange Format, SMPTE DPX
#
# ANSI/SMPTE 268M-1994, SMPTE Standard for File Format for Digital
# Moving-Picture Exchange (DPX), v1.0, 18 February 1994
# Robert Minsk <robertminsk at yahoo.com>
0 string SDPX DPX image data, big-endian,
!:mime image/x-dpx
#-----------------------------------------------------------------------
# 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
!:mime application/x-hdf
0 string \211HDF\r\n\032\n Hierarchical Data Format (version 5) data
!:mime application/x-hdf
# http://www.cartesianinc.com/Tech/
0 string CPC\262 Cartesian Perceptual Compression image
!:mime image/x-cpi
# Polar Monitor Bitmap (.pmb) used as logo for Polar Electro watches
# From: Markus Heidelberg <markus.heidelberg at web.de>
0 string/t [BitmapInfo2] Polar Monitor Bitmap text
!:mime image/x-polar-monitor-bitmap
# Type: Olympus ORF raw images.
# URL: http://libopenraw.freedesktop.org/wiki/Olympus_ORF
# From: Adam Buchbinder <adam.buchbinder@gmail.com>
0 string MMOR Olympus ORF raw image data, big-endian
!:mime image/x-olympus-orf
0 string IIRO Olympus ORF raw image data, little-endian
!:mime image/x-olympus-orf
0 string IIRS Olympus ORF raw image data, little-endian
!:mime image/x-olympus-orf
# Type: Foveon X3F
# URL: http://www.photofo.com/downloads/x3f-raw-format.pdf
# From: Adam Buchbinder <adam.buchbinder@gmail.com>
# Note that the MIME type isn't defined anywhere that I can find; if
# there's a canonical type for this format, it should replace this one.
0 string FOVb Foveon X3F raw image data
!:mime image/x-x3f
# Paint.NET file
# From Adam Buchbinder <adam.buchbinder@gmail.com>
0 string PDN3 Paint.NET image data
!:mime image/x-paintnet

16
magic/java
View file

@ -1,16 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------
# $File: java,v 1.13 2011/12/08 12:12:46 rrt Exp $
# Java ByteCode and Mach-O binaries (e.g., Mac OS X) use the
# same magic number, 0xcafebabe, so they are both handled
# in the entry called "cafebabe".
#------------------------------------------------------------
0 belong 0xfeedfeed Java KeyStore
!:mime application/x-java-keystore
0 belong 0xcececece Java JCE KeyStore
!:mime application/x-java-jce-keystore
# Java source
0 regex ^import.*;$ Java source
!:mime text/x-java

17
magic/javascript
View file

@ -1,17 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: $
# javascript: magic for javascript and node.js scripts.
#
0 search/1/w #!/bin/node Node.js script text executable
!:mime application/javascript
0 search/1/w #!/usr/bin/node Node.js script text executable
!:mime application/javascript
0 search/1/w #!/bin/nodejs Node.js script text executable
!:mime application/javascript
0 search/1/w #!/usr/bin/nodejs Node.js script text executable
!:mime application/javascript
0 search/1 #!/usr/bin/env\ node Node.js script text executable
!:mime application/javascript
0 search/1 #!/usr/bin/env\ nodejs Node.js script text executable
!:mime application/javascript

31
magic/jpeg
View file

@ -1,31 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: jpeg,v 1.18 2012/08/01 12:12:36 christos Exp $
# JPEG images
# SunOS 5.5.1 had
#
# 0 string \377\330\377\340 JPEG file
# 0 string \377\330\377\356 JPG file
#
# both of which turn into "JPEG image data" here.
#
0 beshort 0xffd8 JPEG image data
!:mime image/jpeg
!:apple 8BIMJPEG
!:strength +2
# From: David Santinoli <david@santinoli.com>
0 string \x00\x00\x00\x0C\x6A\x50\x20\x20\x0D\x0A\x87\x0A JPEG 2000
# From: Johan van der Knijff <johan.vanderknijff@kb.nl>
# Added sub-entries for JP2, JPX, JPM and MJ2 formats; added mimetypes
# https://github.com/bitsgalore/jp2kMagic
#
# Now read value of 'Brand' field, which yields a few possibilities:
>20 string \x6a\x70\x32\x20 Part 1 (JP2)
!:mime image/jp2
>20 string \x6a\x70\x78\x20 Part 2 (JPX)
!:mime image/jpx
>20 string \x6a\x70\x6d\x20 Part 6 (JPM)
!:mime image/jpm
>20 string \x6d\x6a\x70\x32 Part 3 (MJ2)
!:mime video/mj2

11
magic/kde
View file

@ -1,11 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: kde,v 1.4 2009/09/19 16:28:10 christos Exp $
# kde: file(1) magic for KDE
0 string/t [KDE\ Desktop\ Entry] KDE desktop entry
!:mime application/x-kdelnk
0 string/t #\ KDE\ Config\ File KDE config file
!:mime application/x-kdelnk
0 string/t #\ xmcd xmcd database file for kscd
!:mime text/x-xmcd

30
magic/kml
View file

@ -1,30 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: kml,v 1.2 2009/09/19 16:28:10 christos Exp $
# Type: Google KML, formerly Keyhole Markup Language
# Future development of this format has been handed
# over to the Open Geospatial Consortium.
# http://www.opengeospatial.org/standards/kml/
# From: Asbjoern Sloth Toennesen <asbjorn@lila.io>
0 string/t \<?xml
>20 search/400 \ xmlns=
>>&0 regex ['"]http://earth.google.com/kml Google KML document
!:mime application/vnd.google-earth.kml+xml
#------------------------------------------------------------------------------
# Type: OpenGIS KML, formerly Keyhole Markup Language
# This standard is maintained by the
# Open Geospatial Consortium.
# http://www.opengeospatial.org/standards/kml/
# From: Asbjoern Sloth Toennesen <asbjorn@lila.io>
>>&0 regex ['"]http://www.opengis.net/kml OpenGIS KML document
!:mime application/vnd.google-earth.kml+xml
#------------------------------------------------------------------------------
# Type: Google KML Archive (ZIP based)
# http://code.google.com/apis/kml/documentation/kml_tut.html
# From: Asbjoern Sloth Toennesen <asbjorn@lila.io>
0 string PK\003\004
>4 byte 0x14
>>30 string doc.kml Compressed Google KML Document, including resources.
!:mime application/vnd.google-earth.kmz

22
magic/linux
View file

@ -1,22 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: linux,v 1.46 2013/01/06 21:26:48 christos Exp $
# linux: file(1) magic for Linux files
#
# Values for Linux/i386 binaries, from Daniel Quinlan <quinlan@yggdrasil.com>
# The following basic Linux magic is useful for reference, but using
# "long" magic is a better practice in order to avoid collisions.
#
# 2 leshort 100 Linux/i386
# >0 leshort 0407 impure executable (OMAGIC)
# >0 leshort 0410 pure executable (NMAGIC)
# >0 leshort 0413 demand-paged executable (ZMAGIC)
# >0 leshort 0314 demand-paged executable (QMAGIC)
#
# SYSLINUX boot logo files (from 'ppmtolss16' sources)
# http://www.syslinux.org/wiki/index.php/SYSLINUX#Display_graphic_from_filename:
# file extension .lss .16
0 lelong =0x1413f33d SYSLINUX' LSS16 image data
# syslinux-4.05/mime/image/x-lss16.xml
!:mime image/x-lss16

42
magic/lisp
View file

@ -1,42 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# lisp: file(1) magic for lisp programs
#
# various lisp types, from Daniel Quinlan (quinlan@yggdrasil.com)
# updated by Joerg Jenderek
# GRR: This lot is too weak
#0 string ;;
# windows INF files often begin with semicolon and use CRLF as line end
# lisp files are mainly created on unix system with LF as line end
#>2 search/4096 !\r Lisp/Scheme program text
#>2 search/4096 \r Windows INF file
0 search/4096 (setq\ Lisp/Scheme program text
!:mime text/x-lisp
0 search/4096 (defvar\ Lisp/Scheme program text
!:mime text/x-lisp
0 search/4096 (defparam\ Lisp/Scheme program text
!:mime text/x-lisp
0 search/4096 (defun\ Lisp/Scheme program text
!:mime text/x-lisp
0 search/4096 (autoload\ Lisp/Scheme program text
!:mime text/x-lisp
0 search/4096 (custom-set-variables\ Lisp/Scheme program text
!:mime text/x-lisp
# Emacs 18 - this is always correct, but not very magical.
0 string \012( Emacs v18 byte-compiled Lisp data
!:mime application/x-elc
# Emacs 19+ - ver. recognition added by Ian Springer
# Also applies to XEmacs 19+ .elc files; could tell them apart with regexs
# - Chris Chittleborough <cchittleborough@yahoo.com.au>
0 string ;ELC
>4 byte >18
>4 byte <32 Emacs/XEmacs v%d byte-compiled Lisp data
!:mime application/x-elc
# From: David Allouche <david@allouche.net>
0 search/1 \<TeXmacs| TeXmacs document text
!:mime text/texmacs

17
magic/lua
View file

@ -1,17 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: lua,v 1.5 2009/09/19 16:28:10 christos Exp $
# lua: file(1) magic for Lua scripting language
# URL: http://www.lua.org/
# From: Reuben Thomas <rrt@sc3d.org>, Seo Sanghyeon <tinuviel@sparcs.kaist.ac.kr>
# Lua scripts
0 search/1/w #!\ /usr/bin/lua Lua script text executable
!:mime text/x-lua
0 search/1/w #!\ /usr/local/bin/lua Lua script text executable
!:mime text/x-lua
0 search/1 #!/usr/bin/env\ lua Lua script text executable
!:mime text/x-lua
0 search/1 #!\ /usr/bin/env\ lua Lua script text executable
!:mime text/x-lua

7
magic/m4
View file

@ -1,7 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# make: file(1) magic for M4 scripts
#
0 regex \^dnl\ M4 macro processor script text
!:mime text/x-m4

21
magic/macintosh
View file

@ -1,21 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: macintosh,v 1.21 2010/09/20 19:19:17 rrt Exp $
# macintosh description
#
# BinHex is the Macintosh ASCII-encoded file format (see also "apple")
# Daniel Quinlan, quinlan@yggdrasil.com
11 string must\ be\ converted\ with\ BinHex BinHex binary text
!:mime application/mac-binhex40
# Stuffit archives are the de facto standard of compression for Macintosh
# files obtained from most archives. (franklsm@tuns.ca)
0 string SIT! StuffIt Archive (data)
!:mime application/x-stuffit
!:apple SIT!SIT!
# Newer StuffIt archives (grant@netbsd.org)
0 string StuffIt StuffIt Archive
!:mime application/x-stuffit
!:apple SIT!SIT!
#>162 string >0 : %s

35
magic/mail.news
View file

@ -1,35 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: mail.news,v 1.21 2012/06/21 01:44:52 christos Exp $
# mail.news: file(1) magic for mail and news
#
# Unfortunately, saved netnews also has From line added in some news software.
#0 string From mail text
0 string/t Relay-Version: old news text
!:mime message/rfc822
0 string/t #!\ rnews batched news text
!:mime message/rfc822
0 string/t N#!\ rnews mailed, batched news text
!:mime message/rfc822
0 string/t Forward\ to mail forwarding text
!:mime message/rfc822
0 string/t Pipe\ to mail piping text
!:mime message/rfc822
0 string/tc delivered-to: SMTP mail text
!:mime message/rfc822
0 string/tc return-path: SMTP mail text
!:mime message/rfc822
0 string/t Path: news text
!:mime message/news
0 string/t Xref: news text
!:mime message/news
0 string/t From: news or mail text
!:mime message/rfc822
0 string/t Article saved news text
!:mime message/news
0 string/t Received: RFC 822 mail text
!:mime message/rfc822
# TNEF files...
0 lelong 0x223E9F78 Transport Neutral Encapsulation Format
!:mime application/vnd.ms-tnef

16
magic/make
View file

@ -1,16 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# make: file(1) magic for makefiles
#
0 regex \^CFLAGS makefile script text
!:mime text/x-makefile
0 regex \^LDFLAGS makefile script text
!:mime text/x-makefile
0 regex \^all: makefile script text
!:mime text/x-makefile
0 regex \^.PRECIOUS makefile script text
!:mime text/x-makefile
0 regex \^SUBDIRS automake makefile script text
!:mime text/x-makefile

29
magic/marc21
View file

@ -1,29 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#--------------------------------------------
# marc21: file(1) magic for MARC 21 Format
#
# Kevin Ford (kefo@loc.gov)
#
# MARC21 formats are for the representation and communication
# of bibliographic and related information in machine-readable
# form. For more info, see http://www.loc.gov/marc/
# leader position 20-21 must be 45
20 string 45
# leader starts with 5 digits, followed by codes specific to MARC format
>0 regex/1 (^[0-9]{5})[acdnp][^bhlnqsu-z] MARC21 Bibliographic
!:mime application/marc
>0 regex/1 (^[0-9]{5})[acdnosx][z] MARC21 Authority
!:mime application/marc
>0 regex/1 (^[0-9]{5})[cdn][uvxy] MARC21 Holdings
!:mime application/marc
0 regex/1 (^[0-9]{5})[acdn][w] MARC21 Classification
!:mime application/marc
>0 regex/1 (^[0-9]{5})[cdn][q] MARC21 Community
!:mime application/marc
# leader position 22-23, should be "00" but is it?
>0 regex/1 (^.{21})([^0]{2}) (non-conforming)
!:mime application/marc

17
magic/matroska
View file

@ -1,17 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: matroska,v 1.7 2012/08/26 10:06:15 christos Exp $
# matroska: file(1) magic for Matroska files
#
# See http://www.matroska.org/
#
# EBML id:
0 belong 0x1a45dfa3
# DocType id:
>4 search/4096 \x42\x82
# DocType contents:
>>&1 string webm WebM
!:mime video/webm
>>&1 string matroska Matroska data
!:mime video/x-matroska

9
magic/misctools
View file

@ -1,9 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#-----------------------------------------------------------------------------
# $File: misctools,v 1.12 2010/09/29 18:36:49 rrt Exp $
# misctools: file(1) magic for miscellaneous UNIX tools.
#
0 string/c BEGIN:VCALENDAR vCalendar calendar file
!:mime text/calendar
0 string/c BEGIN:VCARD vCard visiting card
!:mime text/x-vcard

368
magic/msdos
View file

@ -1,368 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: msdos,v 1.84 2013/02/05 13:55:22 christos Exp $
# msdos: file(1) magic for MS-DOS files
#
# .BAT files (Daniel Quinlan, quinlan@yggdrasil.com)
# updated by Joerg Jenderek at Oct 2008,Apr 2011
0 string/t @
>1 string/cW \ echo\ off DOS batch file text
!:mime text/x-msdos-batch
>1 string/cW echo\ off DOS batch file text
!:mime text/x-msdos-batch
>1 string/cW rem DOS batch file text
!:mime text/x-msdos-batch
>1 string/cW set\ DOS batch file text
!:mime text/x-msdos-batch
# Tests for various EXE types.
#
# Many of the compressed formats were extraced from IDARC 1.23 source code.
#
0 string/b MZ DOS MZ
!:mime application/x-dosexec
# All non-DOS EXE extensions have the relocation table more than 0x40 bytes into the file.
>0x18 leshort <0x40 MS-DOS executable
# These traditional tests usually work but not always. When test quality support is
# implemented these can be turned on.
#>>0x18 leshort 0x1c (Borland compiler)
#>>0x18 leshort 0x1e (MS compiler)
# If the relocation table is 0x40 or more bytes into the file, it's definitely
# not a DOS EXE.
>0x18 leshort >0x3f
# Maybe it's a PE?
>>(0x3c.l) string PE\0\0 PE
>>>(0x3c.l+24) leshort 0x010b \b32 executable
>>>(0x3c.l+24) leshort 0x020b \b32+ executable
>>>(0x3c.l+24) leshort 0x0107 ROM image
>>>(0x3c.l+24) default x Unknown PE signature
>>>>&0 leshort x 0x%x
>>>(0x3c.l+22) leshort&0x2000 >0 (DLL)
>>>(0x3c.l+92) leshort 1 (native)
>>>(0x3c.l+92) leshort 2 (GUI)
>>>(0x3c.l+92) leshort 3 (console)
>>>(0x3c.l+92) leshort 7 (POSIX)
>>>(0x3c.l+92) leshort 9 (Windows CE)
>>>(0x3c.l+92) leshort 10 (EFI application)
>>>(0x3c.l+92) leshort 11 (EFI boot service driver)
>>>(0x3c.l+92) leshort 12 (EFI runtime driver)
>>>(0x3c.l+92) leshort 13 (EFI ROM)
>>>(0x3c.l+92) leshort 14 (XBOX)
>>>(0x3c.l+92) leshort 15 (Windows boot application)
>>>(0x3c.l+92) default x (Unknown subsystem
>>>>&0 leshort x 0x%x)
>>>(0x3c.l+4) leshort 0x14c Intel 80386
>>>(0x3c.l+4) leshort 0x166 MIPS R4000
>>>(0x3c.l+4) leshort 0x168 MIPS R10000
>>>(0x3c.l+4) leshort 0x184 Alpha
>>>(0x3c.l+4) leshort 0x1a2 Hitachi SH3
>>>(0x3c.l+4) leshort 0x1a6 Hitachi SH4
>>>(0x3c.l+4) leshort 0x1c0 ARM
>>>(0x3c.l+4) leshort 0x1c2 ARM Thumb
>>>(0x3c.l+4) leshort 0x1c4 ARMv7 Thumb
>>>(0x3c.l+4) leshort 0x1f0 PowerPC
>>>(0x3c.l+4) leshort 0x200 Intel Itanium
>>>(0x3c.l+4) leshort 0x266 MIPS16
>>>(0x3c.l+4) leshort 0x268 Motorola 68000
>>>(0x3c.l+4) leshort 0x290 PA-RISC
>>>(0x3c.l+4) leshort 0x366 MIPSIV
>>>(0x3c.l+4) leshort 0x466 MIPS16 with FPU
>>>(0x3c.l+4) leshort 0xebc EFI byte code
>>>(0x3c.l+4) leshort 0x8664 x86-64
>>>(0x3c.l+4) leshort 0xc0ee MSIL
>>>(0x3c.l+4) default x Unknown processor type
>>>>&0 leshort x 0x%x
>>>(0x3c.l+22) leshort&0x0200 >0 (stripped to external PDB)
>>>(0x3c.l+22) leshort&0x1000 >0 system file
>>>(0x3c.l+24) leshort 0x010b
>>>>(0x3c.l+232) lelong >0 Mono/.Net assembly
>>>(0x3c.l+24) leshort 0x020b
>>>>(0x3c.l+248) lelong >0 Mono/.Net assembly
# hooray, there's a DOS extender using the PE format, with a valid PE
# executable inside (which just prints a message and exits if run in win)
>>>(8.s*16) string 32STUB \b, 32rtm DOS extender
>>>(8.s*16) string !32STUB \b, for MS Windows
>>>(0x3c.l+0xf8) string UPX0 \b, UPX compressed
>>>(0x3c.l+0xf8) search/0x140 PEC2 \b, PECompact2 compressed
>>>(0x3c.l+0xf8) search/0x140 UPX2
>>>>(&0x10.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
>>>(0x3c.l+0xf8) search/0x140 .idata
>>>>(&0xe.l+(-4)) string PK\3\4 \b, ZIP self-extracting archive (Info-Zip)
>>>>(&0xe.l+(-4)) string ZZ0 \b, ZZip self-extracting archive
>>>>(&0xe.l+(-4)) string ZZ1 \b, ZZip self-extracting archive
>>>(0x3c.l+0xf8) search/0x140 .rsrc
>>>>(&0x0f.l+(-4)) string a\\\4\5 \b, WinHKI self-extracting archive
>>>>(&0x0f.l+(-4)) string Rar! \b, RAR self-extracting archive
>>>>(&0x0f.l+(-4)) search/0x3000 MSCF \b, InstallShield self-extracting archive
>>>>(&0x0f.l+(-4)) search/32 Nullsoft \b, Nullsoft Installer self-extracting archive
>>>(0x3c.l+0xf8) search/0x140 .data
>>>>(&0x0f.l) string WEXTRACT \b, MS CAB-Installer self-extracting archive
>>>(0x3c.l+0xf8) search/0x140 .petite\0 \b, Petite compressed
>>>>(0x3c.l+0xf7) byte x
>>>>>(&0x104.l+(-4)) string =!sfx! \b, ACE self-extracting archive
>>>(0x3c.l+0xf8) search/0x140 .WISE \b, WISE installer self-extracting archive
>>>(0x3c.l+0xf8) search/0x140 .dz\0\0\0 \b, Dzip self-extracting archive
>>>&(0x3c.l+0xf8) search/0x100 _winzip_ \b, ZIP self-extracting archive (WinZip)
>>>&(0x3c.l+0xf8) search/0x100 SharedD \b, Microsoft Installer self-extracting archive
>>>0x30 string Inno \b, InnoSetup self-extracting archive
# Hmm, not a PE but the relocation table is too high for a traditional DOS exe,
# must be one of the unusual subformats.
>>(0x3c.l) string !PE\0\0 MS-DOS executable
>>(0x3c.l) string NE \b, NE
>>>(0x3c.l+0x36) byte 1 for OS/2 1.x
>>>(0x3c.l+0x36) byte 2 for MS Windows 3.x
>>>(0x3c.l+0x36) byte 3 for MS-DOS
>>>(0x3c.l+0x36) byte 4 for Windows 386
>>>(0x3c.l+0x36) byte 5 for Borland Operating System Services
>>>(0x3c.l+0x36) default x
>>>>(0x3c.l+0x36) byte x (unknown OS %x)
>>>(0x3c.l+0x36) byte 0x81 for MS-DOS, Phar Lap DOS extender
>>>(0x3c.l+0x0c) leshort&0x8003 0x8002 (DLL)
>>>(0x3c.l+0x0c) leshort&0x8003 0x8001 (driver)
>>>&(&0x24.s-1) string ARJSFX \b, ARJ self-extracting archive
>>>(0x3c.l+0x70) search/0x80 WinZip(R)\ Self-Extractor \b, ZIP self-extracting archive (WinZip)
>>(0x3c.l) string LX\0\0 \b, LX
>>>(0x3c.l+0x0a) leshort <1 (unknown OS)
>>>(0x3c.l+0x0a) leshort 1 for OS/2
>>>(0x3c.l+0x0a) leshort 2 for MS Windows
>>>(0x3c.l+0x0a) leshort 3 for DOS
>>>(0x3c.l+0x0a) leshort >3 (unknown OS)
>>>(0x3c.l+0x10) lelong&0x28000 =0x8000 (DLL)
>>>(0x3c.l+0x10) lelong&0x20000 >0 (device driver)
>>>(0x3c.l+0x10) lelong&0x300 0x300 (GUI)
>>>(0x3c.l+0x10) lelong&0x28300 <0x300 (console)
>>>(0x3c.l+0x08) leshort 1 i80286
>>>(0x3c.l+0x08) leshort 2 i80386
>>>(0x3c.l+0x08) leshort 3 i80486
>>>(8.s*16) string emx \b, emx
>>>>&1 string x %s
>>>&(&0x54.l-3) string arjsfx \b, ARJ self-extracting archive
# MS Windows system file, supposedly a collection of LE executables
>>(0x3c.l) string W3 \b, W3 for MS Windows
>>(0x3c.l) string LE\0\0 \b, LE executable
>>>(0x3c.l+0x0a) leshort 1
# some DOS extenders use LE files with OS/2 header
>>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
>>>>0x240 search/0x200 WATCOM\ C/C++ for MS-DOS, DOS4GW DOS extender
>>>>0x440 search/0x100 CauseWay\ DOS\ Extender for MS-DOS, CauseWay DOS extender
>>>>0x40 search/0x40 PMODE/W for MS-DOS, PMODE/W DOS extender
>>>>0x40 search/0x40 STUB/32A for MS-DOS, DOS/32A DOS extender (stub)
>>>>0x40 search/0x80 STUB/32C for MS-DOS, DOS/32A DOS extender (configurable stub)
>>>>0x40 search/0x80 DOS/32A for MS-DOS, DOS/32A DOS extender (embedded)
# this is a wild guess; hopefully it is a specific signature
>>>>&0x24 lelong <0x50
>>>>>(&0x4c.l) string \xfc\xb8WATCOM
>>>>>>&0 search/8 3\xdbf\xb9 \b, 32Lite compressed
# another wild guess: if real OS/2 LE executables exist, they probably have higher start EIP
#>>>>(0x3c.l+0x1c) lelong >0x10000 for OS/2
# fails with DOS-Extenders.
>>>(0x3c.l+0x0a) leshort 2 for MS Windows
>>>(0x3c.l+0x0a) leshort 3 for DOS
>>>(0x3c.l+0x0a) leshort 4 for MS Windows (VxD)
>>>(&0x7c.l+0x26) string UPX \b, UPX compressed
>>>&(&0x54.l-3) string UNACE \b, ACE self-extracting archive
# looks like ASCII, probably some embedded copyright message.
# and definitely not NE/LE/LX/PE
>>0x3c lelong >0x20000000
>>>(4.s*512) leshort !0x014c \b, MZ for MS-DOS
# header data too small for extended executable
>2 long !0
>>0x18 leshort <0x40
>>>(4.s*512) leshort !0x014c
>>>>&(2.s-514) string !LE
>>>>>&-2 string !BW \b, MZ for MS-DOS
>>>>&(2.s-514) string LE \b, LE
>>>>>0x240 search/0x100 DOS/4G for MS-DOS, DOS4GW DOS extender
# educated guess since indirection is still not capable enough for complex offset
# calculations (next embedded executable would be at &(&2*512+&0-2)
# I suspect there are only LE executables in these multi-exe files
>>>>&(2.s-514) string BW
>>>>>0x240 search/0x100 DOS/4G ,\b LE for MS-DOS, DOS4GW DOS extender (embedded)
>>>>>0x240 search/0x100 !DOS/4G ,\b BW collection for MS-DOS
# This sequence skips to the first COFF segment, usually .text
>(4.s*512) leshort 0x014c \b, COFF
>>(8.s*16) string go32stub for MS-DOS, DJGPP go32 DOS extender
>>(8.s*16) string emx
>>>&1 string x for DOS, Win or OS/2, emx %s
>>&(&0x42.l-3) byte x
>>>&0x26 string UPX \b, UPX compressed
# and yet another guess: small .text, and after large .data is unusal, could be 32lite
>>&0x2c search/0xa0 .text
>>>&0x0b lelong <0x2000
>>>>&0 lelong >0x6000 \b, 32lite compressed
>(8.s*16) string $WdX \b, WDos/X DOS extender
# By now an executable type should have been printed out. The executable
# may be a self-uncompressing archive, so look for evidence of that and
# print it out.
#
# Some signatures below from Greg Roelofs, newt@uchicago.edu.
#
>0x35 string \x8e\xc0\xb9\x08\x00\xf3\xa5\x4a\x75\xeb\x8e\xc3\x8e\xd8\x33\xff\xbe\x30\x00\x05 \b, aPack compressed
>0xe7 string LH/2\ Self-Extract \b, %s
>0x1c string UC2X \b, UCEXE compressed
>0x1c string WWP\ \b, WWPACK compressed
>0x1c string RJSX \b, ARJ self-extracting archive
>0x1c string diet \b, diet compressed
>0x1c string LZ09 \b, LZEXE v0.90 compressed
>0x1c string LZ91 \b, LZEXE v0.91 compressed
>0x1c string tz \b, TinyProg compressed
>0x1e string Copyright\ 1989-1990\ PKWARE\ Inc. Self-extracting PKZIP archive
!:mime application/zip
# Yes, this really is "Copr", not "Corp."
>0x1e string PKLITE\ Copr. Self-extracting PKZIP archive
!:mime application/zip
# winarj stores a message in the stub instead of the sig in the MZ header
>0x20 search/0xe0 aRJsfX \b, ARJ self-extracting archive
>0x20 string AIN
>>0x23 string 2 \b, AIN 2.x compressed
>>0x23 string <2 \b, AIN 1.x compressed
>>0x23 string >2 \b, AIN 1.x compressed
>0x24 string LHa's\ SFX \b, LHa self-extracting archive
!:mime application/x-lha
>0x24 string LHA's\ SFX \b, LHa self-extracting archive
!:mime application/x-lha
>0x24 string \ $ARX \b, ARX self-extracting archive
>0x24 string \ $LHarc \b, LHarc self-extracting archive
>0x20 string SFX\ by\ LARC \b, LARC self-extracting archive
>0x40 string aPKG \b, aPackage self-extracting archive
>0x64 string W\ Collis\0\0 \b, Compack compressed
>0x7a string Windows\ self-extracting\ ZIP \b, ZIP self-extracting archive
>>&0xf4 search/0x140 \x0\x40\x1\x0
>>>(&0.l+(4)) string MSCF \b, WinHKI CAB self-extracting archive
>1638 string -lh5- \b, LHa self-extracting archive v2.13S
>0x17888 string Rar! \b, RAR self-extracting archive
# Skip to the end of the EXE. This will usually work fine in the PE case
# because the MZ image is hardcoded into the toolchain and almost certainly
# won't match any of these signatures.
>(4.s*512) long x
>>&(2.s-517) byte x
>>>&0 string PK\3\4 \b, ZIP self-extracting archive
>>>&0 string Rar! \b, RAR self-extracting archive
>>>&0 string =!\x11 \b, AIN 2.x self-extracting archive
>>>&0 string =!\x12 \b, AIN 2.x self-extracting archive
>>>&0 string =!\x17 \b, AIN 1.x self-extracting archive
>>>&0 string =!\x18 \b, AIN 1.x self-extracting archive
>>>&7 search/400 **ACE** \b, ACE self-extracting archive
>>>&0 search/0x480 UC2SFX\ Header \b, UC2 self-extracting archive
# a few unknown ZIP sfxes, no idea if they are needed or if they are
# already captured by the generic patterns above
>(8.s*16) search/0x20 PKSFX \b, ZIP self-extracting archive (PKZIP)
# TODO: how to add this? >FileSize-34 string Windows\ Self-Installing\ Executable \b, ZIP self-extracting archive
#
# 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
# Popular applications
2080 string Microsoft\ Word\ 6.0\ Document %s
!:mime application/msword
2080 string Documento\ Microsoft\ Word\ 6 Spanish Microsoft Word 6 document data
!:mime application/msword
# Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Word)
2112 string MSWordDoc Microsoft Word document data
!:mime application/msword
#
0 belong 0x31be0000 Microsoft Word Document
!:mime application/msword
#
0 string/b PO^Q` Microsoft Word 6.0 Document
!:mime application/msword
#
0 string/b \376\067\0\043 Microsoft Office Document
!:mime application/msword
0 string/b \333\245-\0\0\0 Microsoft Office Document
!:mime application/msword
512 string/b \354\245\301 Microsoft Word Document
!:mime application/msword
#
0 string/b \xDB\xA5\x2D\x00 Microsoft WinWord 2.0 Document
!:mime application/msword
#
2080 string Microsoft\ Excel\ 5.0\ Worksheet %s
!:mime application/vnd.ms-excel
#
0 string/b \xDB\xA5\x2D\x00 Microsoft WinWord 2.0 Document
!:mime application/msword
2080 string Foglio\ di\ lavoro\ Microsoft\ Exce %s
!:mime application/vnd.ms-excel
#
# Pawel Wiecek <coven@i17linuxb.ists.pwr.wroc.pl> (for polish Excel)
2114 string Biff5 Microsoft Excel 5.0 Worksheet
!:mime application/vnd.ms-excel
# Italian MS-Excel
2121 string Biff5 Microsoft Excel 5.0 Worksheet
!:mime application/vnd.ms-excel
0 string/b \x09\x04\x06\x00\x00\x00\x10\x00 Microsoft Excel Worksheet
!:mime application/vnd.ms-excel
#
0 belong 0x00001a00 Lotus 1-2-3
!:mime application/x-123
#
0 belong 0x00000200 Lotus 1-2-3
!:mime application/x-123
0 string/b WordPro\0 Lotus WordPro
!:mime application/vnd.lotus-wordpro
0 string/b WordPro\r\373 Lotus WordPro
!:mime application/vnd.lotus-wordpro
# Windows icons (Ian Springer <ips@fpk.hp.com>)
0 string/b \000\000\001\000 MS Windows icon resource
!:mime image/x-icon
# .PIF files added by Joerg Jenderek from http://smsoft.ru/en/pifdoc.htm
# only for windows versions equal or greater 3.0
0x171 string MICROSOFT\ PIFEX\0 Windows Program Information File
!:mime application/x-dosexec
# TNEF magic From "Joomy" <joomy@se-ed.net>
# Microsoft Outlook's Transport Neutral Encapsulation Format (TNEF)
0 leshort 0x223e9f78 TNEF
!:mime application/vnd.ms-tnef
#------------------------------------------------------------------------------
# From Stuart Caie <kyzer@4u.net> (developer of cabextract)
# Microsoft Cabinet files
0 string/b MSCF\0\0\0\0 Microsoft Cabinet archive data
!:mime application/vnd.ms-cab-compressed
# from http://filext.com by Derek M Jones <derek@knosof.co.uk>
# False positive with PPT (also currently this string is too long)
#0 string/b \xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x3E\x00\x03\x00\xFE\xFF\x09\x00\x06 Microsoft Installer
0 string/b \320\317\021\340\241\261\032\341 Microsoft Office Document
#>48 byte 0x1B Excel Document
#!:mime application/vnd.ms-excel
>546 string bjbj Microsoft Word Document
!:mime application/msword
>546 string jbjb Microsoft Word Document
!:mime application/msword
0 string/b \224\246\056 Microsoft Word Document
!:mime application/msword
512 string R\0o\0o\0t\0\ \0E\0n\0t\0r\0y Microsoft Word Document
!:mime application/msword
# MS eBook format (.lit)
0 string/b ITOLITLS Microsoft Reader eBook Data
>8 lelong x \b, version %u
!:mime application/x-ms-reader

12
magic/neko
View file

@ -1,12 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------
# $File: java,v 1.12 2009/09/19 16:28:10 christos Exp $
# From: Mikhail Gusarov <dottedmag@dottedmag.net>
# NekoVM (http://nekovm.org/) bytecode
0 string NEKO NekoVM bytecode
>4 lelong x (%d global symbols,
>8 lelong x %d global fields,
>12 lelong x %d bytecode ops)
!:mime application/x-nekovm-bytecode

11
magic/pascal
View file

@ -1,11 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# pascal: file(1) magic for Pascal source
#
0 search/8192 (input, Pascal source text
!:mime text/x-pascal
0 regex \^program Pascal source text
!:mime text/x-pascal
0 regex \^record Pascal source text
!:mime text/x-pascal

8
magic/pdf
View file

@ -1,8 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# pdf: file(1) magic for Portable Document Format
#
0 string %PDF- PDF document
!:mime application/pdf

26
magic/perl
View file

@ -1,26 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: perl,v 1.19 2012/06/20 21:16:25 christos Exp $
# perl: file(1) magic for Larry Wall's perl language.
#
# The `eval' lines recognizes an outrageously clever hack.
# Keith Waclena <keith@cerberus.uchicago.edu>
# Send additions to <perl5-porters@perl.org>
0 search/1/w #!\ /bin/perl Perl script text executable
!:mime text/x-perl
0 search/1 eval\ "exec\ /bin/perl Perl script text
!:mime text/x-perl
0 search/1/w #!\ /usr/bin/perl Perl script text executable
!:mime text/x-perl
0 search/1 eval\ "exec\ /usr/bin/perl Perl script text
!:mime text/x-perl
0 search/1/w #!\ /usr/local/bin/perl Perl script text executable
!:mime text/x-perl
0 search/1 eval\ "exec\ /usr/local/bin/perl Perl script text
!:mime text/x-perl
0 search/1 eval\ '(exit\ $?0)'\ &&\ eval\ 'exec Perl script text
!:mime text/x-perl
0 search/1 #!/usr/bin/env\ perl Perl script text executable
!:mime text/x-perl
0 search/1 #!\ /usr/bin/env\ perl Perl script text executable
!:mime text/x-perl

27
magic/pgp
View file

@ -1,27 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# pgp: file(1) magic for Pretty Good Privacy
# see http://lists.gnupg.org/pipermail/gnupg-devel/1999-September/016052.html
#
0 beshort 0x9900 PGP key public ring
!:mime application/x-pgp-keyring
0 beshort 0x9501 PGP key security ring
!:mime application/x-pgp-keyring
0 beshort 0x9500 PGP key security ring
!:mime application/x-pgp-keyring
0 beshort 0xa600 PGP encrypted data
#!:mime application/pgp-encrypted
#0 string -----BEGIN\040PGP text/PGP armored data
!:mime text/PGP # encoding: 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
2 string ---BEGIN\ PGP\ PUBLIC\ KEY\ BLOCK- PGP public key block
!:mime application/pgp-keys
0 string -----BEGIN\040PGP\40MESSAGE- PGP message
!:mime application/pgp
0 string -----BEGIN\040PGP\40SIGNATURE- PGP signature
!:mime application/pgp-signature

7
magic/pkgadd
View file

@ -1,7 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# pkgadd: file(1) magic for SysV R4 PKG Datastreams
#
0 string #\ PaCkAgE\ DaTaStReAm pkg Datastream (SVR4)
!:mime application/x-svr4-package

14
magic/printer
View file

@ -1,14 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: printer,v 1.24 2011/05/08 16:34:51 christos Exp $
# printer: file(1) magic for printer-formatted files
#
# PostScript, updated by Daniel Quinlan (quinlan@yggdrasil.com)
0 string %! PostScript document text
!:mime application/postscript
!:apple ASPSTEXT
# Some PCs have the annoying habit of adding a ^D as a document separator
0 string \004%! PostScript document text
!:mime application/postscript
!:apple ASPSTEXT

46
magic/python
View file

@ -1,46 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: python,v 1.21 2012/06/21 01:12:51 christos Exp $
# python: file(1) magic for python
#
0 search/1/w #!\ /usr/bin/python Python script text executable
!:mime text/x-python
0 search/1/w #!\ /usr/local/bin/python Python script text executable
!:mime text/x-python
0 search/1 #!/usr/bin/env\ python Python script text executable
!:mime text/x-python
0 search/1 #!\ /usr/bin/env\ python Python script text executable
!:mime text/x-python
# from module.submodule import func1, func2
0 regex \^from\\s+(\\w|\\.)+\\s+import.*$ Python script text executable
!:mime text/x-python
# def __init__ (self, ...):
0 search/4096 def\ __init__
>&0 search/64 self Python script text executable
!:mime text/x-python
# comments
0 search/4096 '''
>&0 regex .*'''$ Python script text executable
!:mime text/x-python
0 search/4096 """
>&0 regex .*"""$ Python script text executable
!:mime text/x-python
# try:
# except: or finally:
# block
0 search/4096 try:
>&0 regex \^\\s*except.*: Python script text executable
!:mime text/x-python
>&0 search/4096 finally: Python script text executable
!:mime text/x-python
# def name(args, args):
0 regex \^(\ |\\t)*def\ +[a-zA-Z]+
>&0 regex \ *\\(([a-zA-Z]|,|\ )*\\):$ Python script text executable
!:mime text/x-python

36
magic/riff
View file

@ -1,36 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: riff,v 1.22 2011/09/06 11:00:06 christos Exp $
# riff: file(1) magic for RIFF format
# See
#
# http://www.seanet.com/users/matts/riffmci/riffmci.htm
#
# AVI section extended by Patrik Radman <patrik+file-magic@iki.fi>
#
0 string RIFF RIFF (little-endian) data
# Microsoft WAVE format (*.wav)
>8 string WAVE \b, WAVE audio
!:mime audio/x-wav
# Corel Draw Picture
>8 string CDRA \b, Corel Draw Picture
!:mime image/x-coreldraw
# AVI == Audio Video Interleave
>8 string AVI\040 \b, AVI
!:mime video/x-msvideo
#------------------------------------------------------------------------------
# Sony Wave64
# see http://www.vcs.de/fileadmin/user_upload/MBS/PDF/Whitepaper/Informations_about_Sony_Wave64.pdf
# 128 bit RIFF-GUID { 66666972-912E-11CF-A5D6-28DB04C10000 } in little-endian
0 string riff\x2E\x91\xCF\x11\xA5\xD6\x28\xDB\x04\xC1\x00\x00 Sony Wave64 RIFF data
# 128 bit + total file size (64 bits) so 24 bytes
# then WAVE-GUID { 65766177-ACF3-11D3-8CD1-00C04F8EDB8A }
>24 string wave\xF3\xAC\xD3\x11\x8C\xD1\x00\xC0\x4F\x8E\xDB\x8A \b, WAVE 64 audio
!:mime audio/x-w64
#------------------------------------------------------------------------------
# MBWF/RF64
# see EBU TECH 3306 http://tech.ebu.ch/docs/tech/tech3306-2009.pdf
0 string RF64\xff\xff\xff\xffWAVEds64 MBWF/RF64 audio
!:mime audio/x-wav

12
magic/rpm
View file

@ -1,12 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: rpm,v 1.11 2011/06/14 12:47:41 christos Exp $
#
# RPM: file(1) magic for Red Hat Packages Erik Troan (ewt@redhat.com)
#
0 belong 0xedabeedb RPM
!:mime application/x-rpm
#delta RPM Daniel Novotny (dnovotny@redhat.com)
0 string drpm Delta RPM
!:mime application/x-rpm

9
magic/rtf
View file

@ -1,9 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# rtf: file(1) magic for Rich Text Format (RTF)
#
# Duncan P. Simpson, D.P.Simpson@dcs.warwick.ac.uk
#
0 string {\\rtf Rich Text Format data,
!:mime text/rtf

28
magic/ruby
View file

@ -1,28 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: ruby,v 1.4 2010/07/08 20:24:13 christos Exp $
# ruby: file(1) magic for Ruby scripting language
# URL: http://www.ruby-lang.org/
# From: Reuben Thomas <rrt@sc3d.org>
# Ruby scripts
0 search/1/w #!\ /usr/bin/ruby Ruby script text executable
!:mime text/x-ruby
0 search/1/w #!\ /usr/local/bin/ruby Ruby script text executable
!:mime text/x-ruby
0 search/1 #!/usr/bin/env\ ruby Ruby script text executable
!:mime text/x-ruby
0 search/1 #!\ /usr/bin/env\ ruby Ruby script text executable
!:mime text/x-ruby
# What looks like ruby, but does not have a shebang
# (modules and such)
# From: Lubomir Rintel <lkundrak@v3.sk>
0 regex \^[\ \t]*require[\ \t]'[A-Za-z_/]+'
>0 regex include\ [A-Z]|def\ [a-z]|\ do$
>>0 regex \^[\ \t]*end([\ \t]*[;#].*)?$ Ruby script text
!:mime text/x-ruby
0 regex \^[\ \t]*(class|module)[\ \t][A-Z]
>0 regex (modul|includ)e\ [A-Z]|def\ [a-z]
>>0 regex \^[\ \t]*end([\ \t]*[;#].*)?$ Ruby module source text
!:mime text/x-ruby

7
magic/sc
View file

@ -1,7 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# sc: file(1) magic for "sc" spreadsheet
#
38 string Spreadsheet sc spreadsheet file
!:mime application/x-sc

82
magic/sgml
View file

@ -1,82 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: sgml,v 1.28 2012/04/28 21:20:26 christos Exp $
# Type: SVG Vectorial Graphics
# From: Noel Torres <tecnico@ejerciciosresueltos.com>
0 string \<?xml\ version="
>15 string >\0
>>19 search/4096 \<svg SVG Scalable Vector Graphics image
!:mime image/svg+xml
>>19 search/4096 \<gnc-v2 GnuCash file
!:mime application/x-gnucash
# Sitemap file
0 string/t \<?xml\ version="
>15 string >\0
>>19 search/4096 \<urlset XML Sitemap document text
!:mime application/xml-sitemap
# xhtml
0 string/t \<?xml\ version="
>15 string >\0
>>19 search/4096/cWbt \<!doctype\ html XHTML document text
!:mime text/html
0 string/t \<?xml\ version='
>15 string >\0
>>19 search/4096/cWbt \<!doctype\ html XHTML document text
!:mime text/html
0 string/t \<?xml\ version="
>15 string >\0
>>19 search/4096/cWbt \<html broken XHTML document text
!:mime text/html
#------------------------------------------------------------------------------
# sgml: file(1) magic for Standard Generalized Markup Language
# HyperText Markup Language (HTML) is an SGML document type,
# from Daniel Quinlan (quinlan@yggdrasil.com)
# adapted to string extenstions by Anthon van der Neut <anthon@mnt.org)
0 search/4096/cWt \<!doctype\ html HTML document text
!:mime text/html
!:strength + 5
0 search/4096/cwt \<head HTML document text
!:mime text/html
!:strength + 5
0 search/4096/cwt \<title HTML document text
!:mime text/html
!:strength + 5
0 search/4096/cwt \<html HTML document text
!:mime text/html
!:strength + 5
0 search/4096/cwt \<script HTML document text
!:mime text/html
!:strength + 5
0 search/4096/cwt \<style HTML document text
!:mime text/html
!:strength + 5
0 search/4096/cwt \<table HTML document text
!:mime text/html
!:strength + 5
0 search/4096/cwt \<a\ href= HTML document text
!:mime text/html
!:strength + 5
# Extensible markup language (XML), a subset of SGML
# from Marc Prud'hommeaux (marc@apocalypse.org)
0 search/1/cwt \<?xml XML document text
!:mime application/xml
!:strength + 5
0 string/t \<?xml\ version\ " XML
!:mime application/xml
!:strength + 5
0 string/t \<?xml\ version=" XML
!:mime application/xml
!:strength + 5
0 string \<?xml\ version=' XML
!:mime application/xml
!:strength + 5
0 search/1/wbt \<?xml XML document text
!:mime application/xml
!:strength - 10
0 search/1/wt \<?XML broken XML document text
!:mime application/xml
!:strength - 10

17
magic/sniffer
View file

@ -1,17 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# sniffer: file(1) magic for packet capture files
#
# From: guy@alum.mit.edu (Guy Harris)
#
#
# "libpcap" capture files.
# (We call them "tcpdump capture file(s)" for now, as "tcpdump" is
# the main program that uses that format, but there are other programs
# that use "libpcap", or that use the same capture file format.)
#
0 ubelong 0xa1b2c3d4 tcpdump capture file (big-endian)
!:mime application/vnd.tcpdump.pcap
0 ulelong 0xa1b2c3d4 tcpdump capture file (little-endian)
!:mime application/vnd.tcpdump.pcap

23
magic/tcl
View file

@ -1,23 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# file: file(1) magic for Tcl scripting language
# URL: http://www.tcl.tk/
# From: gustaf neumann
# Tcl scripts
0 search/1/w #!\ /usr/bin/tcl Tcl script text executable
!:mime text/x-lua
0 search/1/w #!\ /usr/local/bin/tcl Tcl script text executable
!:mime text/x-tcl
0 search/1 #!/usr/bin/env\ tcl Tcl script text executable
!:mime text/x-tcl
0 search/1 #!\ /usr/bin/env\ tcl Tcl script text executable
!:mime text/x-tcl
0 search/1/w #!\ /usr/bin/wish Tcl/Tk script text executable
!:mime text/x-tcl
0 search/1/w #!\ /usr/local/bin/wish Tcl/Tk script text executable
!:mime text/x-tcl
0 search/1 #!/usr/bin/env\ wish Tcl/Tk script text executable
!:mime text/x-tcl
0 search/1 #!\ /usr/bin/env\ wish Tcl/Tk script text executable
!:mime text/x-tcl

56
magic/tex
View file

@ -1,56 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: tex,v 1.17 2010/09/20 19:19:17 rrt Exp $
# tex: file(1) magic for TeX files
#
# XXX - needs byte-endian stuff (big-endian and little-endian DVI?)
#
# From <conklin@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 TeX DVI file
!:mime application/x-dvi
# 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 TeX font metric data
!:mime application/x-tex-tfm
2 string \000\022 TeX font metric data
!:mime application/x-tex-tfm
# Texinfo and GNU Info, from Daniel Quinlan (quinlan@yggdrasil.com)
0 search/1 \\input\ texinfo Texinfo source text
!:mime text/x-texinfo
0 search/1 This\ is\ Info\ file GNU Info text
!:mime text/x-info
# TeX documents, from Daniel Quinlan (quinlan@yggdrasil.com)
0 search/4096 \\input TeX document text
!:mime text/x-tex
!:strength + 15
0 search/4096 \\section LaTeX document text
!:mime text/x-tex
!:strength + 18
0 search/4096 \\setlength LaTeX document text
!:mime text/x-tex
!:strength + 15
0 search/4096 \\documentstyle LaTeX document text
!:mime text/x-tex
!:strength + 18
0 search/4096 \\chapter LaTeX document text
!:mime text/x-tex
!:strength + 18
0 search/4096 \\documentclass LaTeX 2e document text
!:mime text/x-tex
!:strength + 15
0 search/4096 \\relax LaTeX auxiliary file
!:mime text/x-tex
!:strength + 15
0 search/4096 \\contentsline LaTeX table of contents
!:mime text/x-tex
!:strength + 15
0 search/4096 %\ -*-latex-*- LaTeX document text
!:mime text/x-tex

22
magic/troff
View file

@ -1,22 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# troff: file(1) magic for *roff
#
# updated by Daniel Quinlan (quinlan@yggdrasil.com)
# troff input
0 search/1 .\\" troff or preprocessor input text
!:mime text/troff
0 search/1 '\\" troff or preprocessor input text
!:mime text/troff
0 search/1 '.\\" troff or preprocessor input text
!:mime text/troff
0 search/1 \\" troff or preprocessor input text
!:mime text/troff
0 search/1 ''' troff or preprocessor input text
!:mime text/troff
0 regex/20 \^\\.[A-Za-z0-9][A-Za-z0-9][\ \t] troff or preprocessor input text
!:mime text/troff
0 regex/20 \^\\.[A-Za-z0-9][A-Za-z0-9]$ troff or preprocessor input text
!:mime text/troff

26
magic/vorbis
View file

@ -1,26 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File$
# vorbis: file(1) magic for Ogg/Vorbis files
#
# From Felix von Leitner <leitner@fefe.de>
# Extended by Beni Cherniavsky <cben@crosswinds.net>
# Further extended by Greg Wooledge <greg@wooledge.org>
#
# Most (everything but the number of channels and bitrate) is commented
# out with `##' as it's not interesting to the average user. The most
# probable things advanced users would want to uncomment are probably
# the number of comments and the encoder version.
#
# FIXME: The first match has been made a search, so that it can skip
# over prepended ID3 tags. This will work for MIME type detection, but
# won't work for detecting other properties of the file (they all need
# to be made relative to the search). In any case, if the file has ID3
# tags, the ID3 information will be printed, not the Ogg information,
# so until that's fixed, this doesn't matter.
# FIXME[2]: Disable the above for now, since search assumes text mode.
#
# --- Ogg Framing ---
#0 search/1000 OggS Ogg data
0 string OggS Ogg data
!:mime application/ogg

14
magic/warc
View file

@ -1,14 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: warc,v 1.2 2009/09/19 16:28:13 christos Exp $
# warc: file(1) magic for WARC files
0 string WARC/ WARC Archive
>5 string x version %.4s
!:mime application/warc
#------------------------------------------------------------------------------
# Arc File Format from Internet Archive
# see http://www.archive.org/web/researcher/ArcFileFormat.php
0 string filedesc:// Internet Archive File
!:mime application/x-ia-arc

19
magic/windows
View file

@ -1,19 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: windows,v 1.4 2009/09/19 16:28:13 christos Exp $
# windows: file(1) magic for Microsoft Windows
#
# This file is mainly reserved for files where programs
# using them are run almost always on MS Windows 3.x or
# above, or files only used exclusively in Windows OS,
# where there is no better category to allocate for.
# For example, even though WinZIP almost run on Windows
# only, it is better to treat them as "archive" instead.
# For format usable in DOS, such as generic executable
# format, please specify under "msdos" file.
#
# From: Pal Tamas <folti@balabit.hu>
# Autorun File
0 string/c [autorun]\r\n Microsoft Windows Autorun file.
!:mime application/x-setupscript.

43
magic/wordprocessors
View file

@ -1,43 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: wordprocessors,v 1.16 2012/10/29 17:36:49 christos Exp $
# wordprocessors: file(1) magic fo word processors.
#
# Hangul (Korean) Word Processor File
# From: Won-Kyu Park <wkpark@kldp.org>
512 string R\0o\0o\0t\0 Hangul (Korean) Word Processor File 2000
!:mime application/x-hwp
# Quark Express from http://www.garykessler.net/library/file_sigs.html
2 string MMXPR3 Motorola Quark Express Document (English)
!:mime application/x-quark-xpress-3
#------------------------------------------------------------------------------
# ichitaro456: file(1) magic for Just System Word Processor Ichitaro
#
# Contributor kenzo-:
# Reversed-engineered JS Ichitaro magic numbers
#
0 string DOC
>43 byte 0x14 Just System Word Processor Ichitaro v4
!:mime application/x-ichitaro4
0 string DOC
>43 byte 0x15 Just System Word Processor Ichitaro v5
!:mime application/x-ichitaro5
0 string DOC
>43 byte 0x16 Just System Word Processor Ichitaro v6
!:mime application/x-ichitaro6
# Type: Freemind mindmap documents
# From: Jamie Thompson <debian-bugs@jamie-thompson.co.uk>
0 string/w \<map\ version Freemind document
!:mime application/x-freemind
# Type: Scribus
# From: Werner Fink <werner@suse.de>
0 string \<SCRIBUSUTF8NEW\ Version Scribus Document
!:mime application/x-scribus

11
magic/xwindows
View file

@ -1,11 +0,0 @@
# See COPYING file in this directory for original libmagic copyright.
#------------------------------------------------------------------------------
# $File: xwindows,v 1.7 2011/05/03 01:44:17 christos Exp $
# xwindows: file(1) magic for various X/Window system file formats.
# Xcursor data
# X11 mouse cursor format defined in libXcursor, see
# http://www.x.org/archive/X11R6.8.1/doc/Xcursor.3.html
# http://cgit.freedesktop.org/xorg/lib/libXcursor/tree/include/X11/Xcursor/Xcursor.h
0 string Xcur Xcursor data
!:mime image/x-xcursor

1
scripts/base/files/extract/__load__.bro Normal file
View file

@ -0,0 +1 @@
@load ./main

38
scripts/base/files/extract/main.bro Normal file
View file

@ -0,0 +1,38 @@
@load base/frameworks/files
@load base/utils/paths
module FileExtract;
export {
## The prefix where files are extracted to.
const prefix = "./extract_files/" &redef;
redef record Files::Info += {
## Local filenames of extracted file.
extracted: string &optional &log;
};
redef record Files::AnalyzerArgs += {
## The local filename to which to write an extracted file.
## This field is used in the core by the extraction plugin
## to know where to write the file to. It's also optional
extract_filename: string &optional;
};
}
function on_add(f: fa_file, args: Files::AnalyzerArgs)
{
if ( ! args?$extract_filename )
args$extract_filename = cat("extract-", f$source, "-", f$id);
f$info$extracted = args$extract_filename;
args$extract_filename = build_path_compressed(prefix, args$extract_filename);
}
event bro_init() &priority=10
{
Files::register_analyzer_add_callback(Files::ANALYZER_EXTRACT, on_add);
# Create the extraction directory.
mkdir(prefix);
}

1
scripts/base/files/hash/__load__.bro Normal file
View file

@ -0,0 +1 @@
@load ./main

32
scripts/base/files/hash/main.bro Normal file
View file

@ -0,0 +1,32 @@
@load base/frameworks/files
module FileHash;
export {
redef record Files::Info += {
## An MD5 digest of the file contents.
md5: string &log &optional;
## A SHA1 digest of the file contents.
sha1: string &log &optional;
## A SHA256 digest of the file contents.
sha256: string &log &optional;
};
}
event file_hash(f: fa_file, kind: string, hash: string) &priority=5
{
switch ( kind ) {
case "md5":
f$info$md5 = hash;
break;
case "sha1":
f$info$sha1 = hash;
break;
case "sha256":
f$info$sha256 = hash;
break;
}
}

12
scripts/base/frameworks/analyzer/main.bro
View file

@ -81,6 +81,13 @@ export {
## Returns: The analyzer name corresponding to the tag.
global name: function(tag: Analyzer::Tag) : string;
## Translates an analyzer's name to a tag enum value.
##
## name: The analyzer name.
##
## Returns: The analyzer tag corresponding to the name.
global get_tag: function(name: string): Analyzer::Tag;
## Schedules an analyzer for a future connection originating from a given IP
## address and port.
##
@ -187,6 +194,11 @@ function name(atype: Analyzer::Tag) : string
return __name(atype);
}
function get_tag(name: string): Analyzer::Tag
{
return __tag(name);
}
function schedule_analyzer(orig: addr, resp: addr, resp_p: port,
analyzer: Analyzer::Tag, tout: interval) : bool
{

261
scripts/base/frameworks/file-analysis/main.bro
View file

@ -1,261 +0,0 @@
##! An interface for driving the analysis of files, possibly independent of
##! any network protocol over which they're transported.
@load base/bif/file_analysis.bif
@load base/frameworks/logging
module FileAnalysis;
export {
redef enum Log::ID += {
## Logging stream for file analysis.
LOG
};
## A structure which represents a desired type of file analysis.
type AnalyzerArgs: record {
## The type of analysis.
tag: FileAnalysis::Tag;
## The local filename to which to write an extracted file. Must be
## set when *tag* is :bro:see:`FileAnalysis::ANALYZER_EXTRACT`.
extract_filename: string &optional;
## An event which will be generated for all new file contents,
## chunk-wise. Used when *tag* is
## :bro:see:`FileAnalysis::ANALYZER_DATA_EVENT`.
chunk_event: event(f: fa_file, data: string, off: count) &optional;
## An event which will be generated for all new file contents,
## stream-wise. Used when *tag* is
## :bro:see:`FileAnalysis::ANALYZER_DATA_EVENT`.
stream_event: event(f: fa_file, data: string) &optional;
} &redef;
## Contains all metadata related to the analysis of a given file.
## For the most part, fields here are derived from ones of the same name
## in :bro:see:`fa_file`.
type Info: record {
## An identifier associated with a single file.
id: string &log;
## Identifier associated with a container file from which this one was
## extracted as part of the file analysis.
parent_id: string &log &optional;
## An identification of the source of the file data. E.g. it may be
## a network protocol over which it was transferred, or a local file
## path which was read, or some other input source.
source: string &log &optional;
## If the source of this file is is a network connection, this field
## may be set to indicate the directionality.
is_orig: bool &log &optional;
## The time at which the last activity for the file was seen.
last_active: time &log;
## Number of bytes provided to the file analysis engine for the file.
seen_bytes: count &log &default=0;
## Total number of bytes that are supposed to comprise the full file.
total_bytes: count &log &optional;
## The number of bytes in the file stream that were completely missed
## during the process of analysis e.g. due to dropped packets.
missing_bytes: count &log &default=0;
## The number of not all-in-sequence bytes in the file stream that
## were delivered to file analyzers due to reassembly buffer overflow.
overflow_bytes: count &log &default=0;
## The amount of time between receiving new data for this file that
## the analysis engine will wait before giving up on it.
timeout_interval: interval &log &optional;
## The number of bytes at the beginning of a file to save for later
## inspection in *bof_buffer* field.
bof_buffer_size: count &log &optional;
## A mime type provided by libmagic against the *bof_buffer*, or
## in the cases where no buffering of the beginning of file occurs,
## an initial guess of the mime type based on the first data seen.
mime_type: string &log &optional;
## Whether the file analysis timed out at least once for the file.
timedout: bool &log &default=F;
## Connection UIDS over which the file was transferred.
conn_uids: set[string] &log;
## A set of analysis types done during the file analysis.
analyzers: set[FileAnalysis::Tag];
## Local filenames of extracted files.
extracted_files: set[string] &log;
## An MD5 digest of the file contents.
md5: string &log &optional;
## A SHA1 digest of the file contents.
sha1: string &log &optional;
## A SHA256 digest of the file contents.
sha256: string &log &optional;
} &redef;
## A table that can be used to disable file analysis completely for
## any files transferred over given network protocol analyzers.
const disable: table[Analyzer::Tag] of bool = table() &redef;
## Event that can be handled to access the Info record as it is sent on
## to the logging framework.
global log_file_analysis: event(rec: Info);
## The salt concatenated to unique file handle strings generated by
## :bro:see:`get_file_handle` before hashing them in to a file id
## (the *id* field of :bro:see:`fa_file`).
## Provided to help mitigate the possiblility of manipulating parts of
## network connections that factor in to the file handle in order to
## generate two handles that would hash to the same file id.
const salt = "I recommend changing this." &redef;
## Sets the *timeout_interval* field of :bro:see:`fa_file`, which is
## used to determine the length of inactivity that is allowed for a file
## before internal state related to it is cleaned up. When used within a
## :bro:see:`file_timeout` handler, the analysis will delay timing out
## again for the period specified by *t*.
##
## f: the file.
##
## t: the amount of time the file can remain inactive before discarding.
##
## Returns: true if the timeout interval was set, or false if analysis
## for the *id* isn't currently active.
global set_timeout_interval: function(f: fa_file, t: interval): bool;
## Adds an analyzer to the analysis of a given file.
##
## f: the file.
##
## args: the analyzer type to add along with any arguments it takes.
##
## Returns: true if the analyzer will be added, or false if analysis
## for the *id* isn't currently active or the *args*
## were invalid for the analyzer type.
global add_analyzer: function(f: fa_file, args: AnalyzerArgs): bool;
## Removes an analyzer from the analysis of a given file.
##
## f: the file.
##
## args: the analyzer (type and args) to remove.
##
## Returns: true if the analyzer will be removed, or false if analysis
## for the *id* isn't currently active.
global remove_analyzer: function(f: fa_file, args: AnalyzerArgs): bool;
## Stops/ignores any further analysis of a given file.
##
## f: the file.
##
## Returns: true if analysis for the given file will be ignored for the
## rest of it's contents, or false if analysis for the *id*
## isn't currently active.
global stop: function(f: fa_file): bool;
}
redef record fa_file += {
info: Info &optional;
};
function set_info(f: fa_file)
{
if ( ! f?$info )
{
local tmp: Info;
f$info = tmp;
}
f$info$id = f$id;
if ( f?$parent_id ) f$info$parent_id = f$parent_id;
if ( f?$source ) f$info$source = f$source;
if ( f?$is_orig ) f$info$is_orig = f$is_orig;
f$info$last_active = f$last_active;
f$info$seen_bytes = f$seen_bytes;
if ( f?$total_bytes ) f$info$total_bytes = f$total_bytes;
f$info$missing_bytes = f$missing_bytes;
f$info$overflow_bytes = f$overflow_bytes;
f$info$timeout_interval = f$timeout_interval;
f$info$bof_buffer_size = f$bof_buffer_size;
if ( f?$mime_type ) f$info$mime_type = f$mime_type;
if ( f?$conns )
for ( cid in f$conns )
add f$info$conn_uids[f$conns[cid]$uid];
}
function set_timeout_interval(f: fa_file, t: interval): bool
{
return __set_timeout_interval(f$id, t);
}
function add_analyzer(f: fa_file, args: AnalyzerArgs): bool
{
if ( ! __add_analyzer(f$id, args) ) return F;
set_info(f);
add f$info$analyzers[args$tag];
if ( args$tag == FileAnalysis::ANALYZER_EXTRACT )
add f$info$extracted_files[args$extract_filename];
return T;
}
function remove_analyzer(f: fa_file, args: AnalyzerArgs): bool
{
return __remove_analyzer(f$id, args);
}
function stop(f: fa_file): bool
{
return __stop(f$id);
}
event bro_init() &priority=5
{
Log::create_stream(FileAnalysis::LOG,
[$columns=Info, $ev=log_file_analysis]);
}
event file_timeout(f: fa_file) &priority=5
{
set_info(f);
f$info$timedout = T;
}
event file_hash(f: fa_file, kind: string, hash: string) &priority=5
{
set_info(f);
switch ( kind ) {
case "md5":
f$info$md5 = hash;
break;
case "sha1":
f$info$sha1 = hash;
break;
case "sha256":
f$info$sha256 = hash;
break;
}
}
event file_state_remove(f: fa_file) &priority=5
{
set_info(f);
}
event file_state_remove(f: fa_file) &priority=-5
{
Log::write(FileAnalysis::LOG, f$info);
}

0
scripts/base/frameworks/file-analysis/__load__.bro → scripts/base/frameworks/files/__load__.bro
View file

371
scripts/base/frameworks/files/main.bro Normal file
View file

@ -0,0 +1,371 @@
##! An interface for driving the analysis of files, possibly independent of
##! any network protocol over which they're transported.
@load base/bif/file_analysis.bif
@load base/frameworks/analyzer
@load base/frameworks/logging
@load base/utils/site
module Files;
export {
redef enum Log::ID += {
## Logging stream for file analysis.
LOG
};
## A structure which represents a desired type of file analysis.
type AnalyzerArgs: record {
## An event which will be generated for all new file contents,
## chunk-wise. Used when *tag* is
## :bro:see:`Files::ANALYZER_DATA_EVENT`.
chunk_event: event(f: fa_file, data: string, off: count) &optional;
## An event which will be generated for all new file contents,
## stream-wise. Used when *tag* is
## :bro:see:`Files::ANALYZER_DATA_EVENT`.
stream_event: event(f: fa_file, data: string) &optional;
} &redef;
## Contains all metadata related to the analysis of a given file.
## For the most part, fields here are derived from ones of the same name
## in :bro:see:`fa_file`.
type Info: record {
## The time when the file was first seen.
ts: time &log;
## An identifier associated with a single file.
fuid: string &log;
## If this file was transferred over a network
## connection this should show the host or hosts that
## the data sourced from.
tx_hosts: set[addr] &log;
## If this file was transferred over a network
## connection this should show the host or hosts that
## the data traveled to.
rx_hosts: set[addr] &log;
## Connection UIDS over which the file was transferred.
conn_uids: set[string] &log;
## An identification of the source of the file data. E.g. it may be
## a network protocol over which it was transferred, or a local file
## path which was read, or some other input source.
source: string &log &optional;
## A value to represent the depth of this file in relation
## to its source. In SMTP, it is the depth of the MIME
## attachment on the message. In HTTP, it is the depth of the
## request within the TCP connection.
depth: count &default=0 &log;
## A set of analysis types done during the file analysis.
analyzers: set[string] &log;
## A mime type provided by libmagic against the *bof_buffer*, or
## in the cases where no buffering of the beginning of file occurs,
## an initial guess of the mime type based on the first data seen.
mime_type: string &log &optional;
## A filename for the file if one is available from the source
## for the file. These will frequently come from
## "Content-Disposition" headers in network protocols.
filename: string &log &optional;
## The duration the file was analyzed for.
duration: interval &log &default=0secs;
## If the source of this file is a network connection, this field
## indicates if the data originated from the local network or not as
## determined by the configured bro:see:`Site::local_nets`.
local_orig: bool &log &optional;
## If the source of this file is a network connection, this field
## indicates if the file is being sent by the originator of the connection
## or the responder.
is_orig: bool &log &optional;
## Number of bytes provided to the file analysis engine for the file.
seen_bytes: count &log &default=0;
## Total number of bytes that are supposed to comprise the full file.
total_bytes: count &log &optional;
## The number of bytes in the file stream that were completely missed
## during the process of analysis e.g. due to dropped packets.
missing_bytes: count &log &default=0;
## The number of not all-in-sequence bytes in the file stream that
## were delivered to file analyzers due to reassembly buffer overflow.
overflow_bytes: count &log &default=0;
## Whether the file analysis timed out at least once for the file.
timedout: bool &log &default=F;
## Identifier associated with a container file from which this one was
## extracted as part of the file analysis.
parent_fuid: string &log &optional;
} &redef;
## A table that can be used to disable file analysis completely for
## any files transferred over given network protocol analyzers.
const disable: table[Files::Tag] of bool = table() &redef;
## The salt concatenated to unique file handle strings generated by
## :bro:see:`get_file_handle` before hashing them in to a file id
## (the *id* field of :bro:see:`fa_file`).
## Provided to help mitigate the possiblility of manipulating parts of
## network connections that factor in to the file handle in order to
## generate two handles that would hash to the same file id.
const salt = "I recommend changing this." &redef;
## Sets the *timeout_interval* field of :bro:see:`fa_file`, which is
## used to determine the length of inactivity that is allowed for a file
## before internal state related to it is cleaned up. When used within a
## :bro:see:`file_timeout` handler, the analysis will delay timing out
## again for the period specified by *t*.
##
## f: the file.
##
## t: the amount of time the file can remain inactive before discarding.
##
## Returns: true if the timeout interval was set, or false if analysis
## for the *id* isn't currently active.
global set_timeout_interval: function(f: fa_file, t: interval): bool;
## Adds an analyzer to the analysis of a given file.
##
## f: the file.
##
## tag: the analyzer type.
##
## args: any parameters the analyzer takes.
##
## Returns: true if the analyzer will be added, or false if analysis
## for the *id* isn't currently active or the *args*
## were invalid for the analyzer type.
global add_analyzer: function(f: fa_file,
tag: Files::Tag,
args: AnalyzerArgs &default=AnalyzerArgs()): bool;
## Removes an analyzer from the analysis of a given file.
##
## f: the file.
##
## args: the analyzer (type and args) to remove.
##
## Returns: true if the analyzer will be removed, or false if analysis
## for the *id* isn't currently active.
global remove_analyzer: function(f: fa_file,
tag: Files::Tag,
args: AnalyzerArgs &default=AnalyzerArgs()): bool;
## Stops/ignores any further analysis of a given file.
##
## f: the file.
##
## Returns: true if analysis for the given file will be ignored for the
## rest of it's contents, or false if analysis for the *id*
## isn't currently active.
global stop: function(f: fa_file): bool;
## Translates an file analyzer enum value to a string with the analyzer's name.
##
## tag: The analyzer tag.
##
## Returns: The analyzer name corresponding to the tag.
global analyzer_name: function(tag: Files::Tag): string;
## Provides a text description regarding metadata of the file.
## For example, with HTTP it would return a URL.
##
## f: The file to be described.
##
## Returns a text description regarding metadata of the file.
global describe: function(f: fa_file): string;
type ProtoRegistration: record {
## A callback to generate a file handle on demand when
## one is needed by the core.
get_file_handle: function(c: connection, is_orig: bool): string;
## A callback to "describe" a file. In the case of an HTTP
## transfer the most obvious description would be the URL.
## It's like an extremely compressed version of the normal log.
describe: function(f: fa_file): string
&default=function(f: fa_file): string { return ""; };
};
## Register callbacks for protocols that work with the Files framework.
## The callbacks must uniquely identify a file and each protocol can
## only have a single callback registered for it.
##
## tag: Tag for the protocol analyzer having a callback being registered.
##
## reg: A :bro:see:`ProtoRegistration` record.
##
## Returns: true if the protocol being registered was not previously registered.
global register_protocol: function(tag: Analyzer::Tag, reg: ProtoRegistration): bool;
## Register a callback for file analyzers to use if they need to do some manipulation
## when they are being added to a file before the core code takes over. This is
## unlikely to be interesting for users and should only be called by file analyzer
## authors but it *not required*.
##
## tag: Tag for the file analyzer.
##
## callback: Function to execute when the given file analyzer is being added.
global register_analyzer_add_callback: function(tag: Files::Tag, callback: function(f: fa_file, args: AnalyzerArgs));
## Event that can be handled to access the Info record as it is sent on
## to the logging framework.
global log_files: event(rec: Info);
}
redef record fa_file += {
info: Info &optional;
};
redef record AnalyzerArgs += {
# This is used interally for the core file analyzer api.
tag: Files::Tag &optional;
};
# Store the callbacks for protocol analyzers that have files.
global registered_protocols: table[Analyzer::Tag] of ProtoRegistration = table();
global analyzer_add_callbacks: table[Files::Tag] of function(f: fa_file, args: AnalyzerArgs) = table();
event bro_init() &priority=5
{
Log::create_stream(Files::LOG, [$columns=Info, $ev=log_files]);
}
function set_info(f: fa_file)
{
if ( ! f?$info )
{
local tmp: Info = Info($ts=f$last_active,
$fuid=f$id);
f$info = tmp;
}
if ( f?$parent_id )
f$info$parent_fuid = f$parent_id;
if ( f?$source )
f$info$source = f$source;
f$info$duration = f$last_active - f$info$ts;
f$info$seen_bytes = f$seen_bytes;
if ( f?$total_bytes )
f$info$total_bytes = f$total_bytes;
f$info$missing_bytes = f$missing_bytes;
f$info$overflow_bytes = f$overflow_bytes;
if ( f?$is_orig )
f$info$is_orig = f$is_orig;
if ( f?$mime_type )
f$info$mime_type = f$mime_type;
}
function set_timeout_interval(f: fa_file, t: interval): bool
{
return __set_timeout_interval(f$id, t);
}
function add_analyzer(f: fa_file, tag: Files::Tag, args: AnalyzerArgs): bool
{
# This is to construct the correct args for the core API.
args$tag = tag;
add f$info$analyzers[Files::analyzer_name(tag)];
if ( tag in analyzer_add_callbacks )
analyzer_add_callbacks[tag](f, args);
if ( ! __add_analyzer(f$id, args) )
{
Reporter::warning(fmt("Analyzer %s not added successfully to file %s.", tag, f$id));
return F;
}
return T;
}
function register_analyzer_add_callback(tag: Files::Tag, callback: function(f: fa_file, args: AnalyzerArgs))
{
analyzer_add_callbacks[tag] = callback;
}
function remove_analyzer(f: fa_file, tag: Files::Tag, args: AnalyzerArgs): bool
{
args$tag = tag;
return __remove_analyzer(f$id, args);
}
function stop(f: fa_file): bool
{
return __stop(f$id);
}
function analyzer_name(tag: Files::Tag): string
{
return __analyzer_name(tag);
}
event file_new(f: fa_file) &priority=10
{
set_info(f);
}
event file_over_new_connection(f: fa_file, c: connection, is_orig: bool) &priority=10
{
set_info(f);
add f$info$conn_uids[c$uid];
local cid = c$id;
add f$info$tx_hosts[f$is_orig ? cid$orig_h : cid$resp_h];
if( |Site::local_nets| > 0 )
f$info$local_orig=Site::is_local_addr(f$is_orig ? cid$orig_h : cid$resp_h);
add f$info$rx_hosts[f$is_orig ? cid$resp_h : cid$orig_h];
}
event file_timeout(f: fa_file) &priority=10
{
set_info(f);
f$info$timedout = T;
}
event file_state_remove(f: fa_file) &priority=10
{
set_info(f);
}
event file_state_remove(f: fa_file) &priority=-10
{
Log::write(Files::LOG, f$info);
}
function register_protocol(tag: Analyzer::Tag, reg: ProtoRegistration): bool
{
local result = (tag !in registered_protocols);
registered_protocols[tag] = reg;
return result;
}
function describe(f: fa_file): string
{
local tag = Analyzer::get_tag(f$source);
if ( tag !in registered_protocols )
return "";
local handler = registered_protocols[tag];
return handler$describe(f);
}
event get_file_handle(tag: Analyzer::Tag, c: connection, is_orig: bool) &priority=5
{
if ( tag !in registered_protocols )
return;
local handler = registered_protocols[tag];
set_file_handle(handler$get_file_handle(c, is_orig));
}

138
scripts/base/frameworks/intel/main.bro
View file

@ -10,13 +10,14 @@ module Intel;
export {
redef enum Log::ID += { LOG };
## String data needs to be further categoried since it could represent
## and number of types of data.
type StrType: enum {
## Enum type to represent various types of intelligence data.
type Type: enum {
## An IP address.
ADDR,
## A complete URL without the prefix "http://".
URL,
## User-Agent string, typically HTTP or mail message body.
USER_AGENT,
## Software name.
SOFTWARE,
## Email address.
EMAIL,
## DNS domain name.
@ -44,16 +45,13 @@ export {
## Represents a piece of intelligence.
type Item: record {
## The IP address if the intelligence is about an IP address.
host: addr &optional;
## The network if the intelligence is about a CIDR block.
net: subnet &optional;
## The string if the intelligence is about a string.
str: string &optional;
## The type of data that is in the string if the $str field is set.
str_type: StrType &optional;
## The intelligence indicator.
indicator: string;
## Metadata for the item. Typically represents more deeply \
## The type of data that the indicator field represents.
indicator_type: Type;
## Metadata for the item. Typically represents more deeply
## descriptive data for a piece of intelligence.
meta: MetaData;
};
@ -65,16 +63,16 @@ export {
IN_ANYWHERE,
};
## The $host field and combination of $str and $str_type fields are mutually
## exclusive. These records *must* represent either an IP address being
## seen or a string being seen.
type Seen: record {
## The IP address if the data seen is an IP address.
host: addr &log &optional;
## The string if the data is about a string.
str: string &log &optional;
## The type of data that is in the string if the $str field is set.
str_type: StrType &log &optional;
indicator: string &log &optional;
## The type of data that the indicator represents.
indicator_type: Type &log &optional;
## If the indicator type was :bro:enum:`Intel::ADDR`, then this
## field will be present.
host: addr &optional;
## Where the data was discovered.
where: Where &log;
@ -100,7 +98,7 @@ export {
## Where the data was seen.
seen: Seen &log;
## Sources which supplied data that resulted in this match.
sources: set[string] &log;
sources: set[string] &log &default=string_set();
};
## Intelligence data manipulation functions.
@ -135,8 +133,8 @@ const have_full_data = T &redef;
# The in memory data structure for holding intelligence.
type DataStore: record {
net_data: table[subnet] of set[MetaData];
string_data: table[string, StrType] of set[MetaData];
host_data: table[addr] of set[MetaData];
string_data: table[string, Type] of set[MetaData];
};
global data_store: DataStore &redef;
@ -144,8 +142,8 @@ global data_store: DataStore &redef;
# This is primarily for workers to do the initial quick matches and store
# a minimal amount of data for the full match to happen on the manager.
type MinDataStore: record {
net_data: set[subnet];
string_data: set[string, StrType];
host_data: set[addr];
string_data: set[string, Type];
};
global min_data_store: MinDataStore &redef;
@ -157,15 +155,13 @@ event bro_init() &priority=5
function find(s: Seen): bool
{
if ( s?$host &&
((have_full_data && s$host in data_store$net_data) ||
(s$host in min_data_store$net_data)))
if ( s?$host )
{
return T;
return ((s$host in min_data_store$host_data) ||
(have_full_data && s$host in data_store$host_data));
}
else if ( s?$str && s?$str_type &&
((have_full_data && [s$str, s$str_type] in data_store$string_data) ||
([s$str, s$str_type] in min_data_store$string_data)))
else if ( ([to_lower(s$indicator), s$indicator_type] in min_data_store$string_data) ||
(have_full_data && [to_lower(s$indicator), s$indicator_type] in data_store$string_data) )
{
return T;
}
@ -177,8 +173,7 @@ function find(s: Seen): bool
function get_items(s: Seen): set[Item]
{
local item: Item;
local return_data: set[Item] = set();
local return_data: set[Item];
if ( ! have_full_data )
{
@ -191,26 +186,23 @@ function get_items(s: Seen): set[Item]
if ( s?$host )
{
# See if the host is known about and it has meta values
if ( s$host in data_store$net_data )
if ( s$host in data_store$host_data )
{
for ( m in data_store$net_data[s$host] )
for ( m in data_store$host_data[s$host] )
{
# TODO: the lookup should be finding all and not just most specific
# and $host/$net should have the correct value.
item = [$host=s$host, $meta=m];
add return_data[item];
add return_data[Item($indicator=cat(s$host), $indicator_type=ADDR, $meta=m)];
}
}
}
else if ( s?$str && s?$str_type )
else
{
local lower_indicator = to_lower(s$indicator);
# See if the string is known about and it has meta values
if ( [s$str, s$str_type] in data_store$string_data )
if ( [lower_indicator, s$indicator_type] in data_store$string_data )
{
for ( m in data_store$string_data[s$str, s$str_type] )
for ( m in data_store$string_data[lower_indicator, s$indicator_type] )
{
item = [$str=s$str, $str_type=s$str_type, $meta=m];
add return_data[item];
add return_data[Item($indicator=s$indicator, $indicator_type=s$indicator_type, $meta=m)];
}
}
}
@ -222,6 +214,12 @@ function Intel::seen(s: Seen)
{
if ( find(s) )
{
if ( s?$host )
{
s$indicator = cat(s$host);
s$indicator_type = Intel::ADDR;
}
if ( have_full_data )
{
local items = get_items(s);
@ -250,8 +248,7 @@ function has_meta(check: MetaData, metas: set[MetaData]): bool
event Intel::match(s: Seen, items: set[Item]) &priority=5
{
local empty_set: set[string] = set();
local info: Info = [$ts=network_time(), $seen=s, $sources=empty_set];
local info: Info = [$ts=network_time(), $seen=s];
if ( s?$conn )
{
@ -267,52 +264,37 @@ event Intel::match(s: Seen, items: set[Item]) &priority=5
function insert(item: Item)
{
if ( item?$str && !item?$str_type )
{
event reporter_warning(network_time(), fmt("You must provide a str_type for strings or this item doesn't make sense. Item: %s", item), "");
return;
}
# Create and fill out the meta data item.
local meta = item$meta;
local metas: set[MetaData];
if ( item?$host )
# All intelligence is case insensitive at the moment.
local lower_indicator = to_lower(item$indicator);
if ( item$indicator_type == ADDR )
{
local host = mask_addr(item$host, is_v4_addr(item$host) ? 32 : 128);
local host = to_addr(item$indicator);
if ( have_full_data )
{
if ( host !in data_store$net_data )
data_store$net_data[host] = set();
if ( host !in data_store$host_data )
data_store$host_data[host] = set();
metas = data_store$net_data[host];
metas = data_store$host_data[host];
}
add min_data_store$net_data[host];
add min_data_store$host_data[host];
}
else if ( item?$net )
else
{
if ( have_full_data )
{
if ( item$net !in data_store$net_data )
data_store$net_data[item$net] = set();
if ( [lower_indicator, item$indicator_type] !in data_store$string_data )
data_store$string_data[lower_indicator, item$indicator_type] = set();
metas = data_store$net_data[item$net];
metas = data_store$string_data[lower_indicator, item$indicator_type];
}
add min_data_store$net_data[item$net];
}
else if ( item?$str )
{
if ( have_full_data )
{
if ( [item$str, item$str_type] !in data_store$string_data )
data_store$string_data[item$str, item$str_type] = set();
metas = data_store$string_data[item$str, item$str_type];
}
add min_data_store$string_data[item$str, item$str_type];
add min_data_store$string_data[lower_indicator, item$indicator_type];
}
local updated = F;

45
scripts/base/frameworks/notice/main.bro
View file

@ -68,6 +68,25 @@ export {
## the notice policy.
iconn: icmp_conn &optional;
## A file record if the notice is relted to a file. The
## reference to the actual fa_file record will be deleted after applying
## the notice policy.
f: fa_file &optional;
## A file unique ID if this notice is related to a file. If the $f
## field is provided, this will be automatically filled out.
fuid: string &log &optional;
## A mime type if the notice is related to a file. If the $f field
## is provided, this will be automatically filled out.
file_mime_type: string &log &optional;
## Frequently files can be "described" to give a bit more context.
## This field will typically be automatically filled out from an
## fa_file record. For example, if a notice was related to a
## file over HTTP, the URL of the request would be shown.
file_desc: string &log &optional;
## The transport protocol. Filled automatically when either conn, iconn
## or p is specified.
proto: transport_proto &log &optional;
@ -460,10 +479,28 @@ function apply_policy(n: Notice::Info)
if ( ! n?$ts )
n$ts = network_time();
if ( n?$f )
{
if ( ! n?$fuid )
n$fuid = n$f$id;
if ( ! n?$file_mime_type && n$f?$mime_type )
n$file_mime_type = n$f$mime_type;
n$file_desc = Files::describe(n$f);
if ( n$f?$conns && |n$f$conns| == 1 )
{
for ( id in n$f$conns )
n$conn = n$f$conns[id];
}
}
if ( n?$conn )
{
if ( ! n?$id )
n$id = n$conn$id;
if ( ! n?$uid )
n$uid = n$conn$uid;
}
@ -513,13 +550,15 @@ function apply_policy(n: Notice::Info)
if ( ! n?$suppress_for )
n$suppress_for = default_suppression_interval;
# Delete the connection record if it's there so we aren't sending that
# to remote machines. It can cause problems due to the size of the
# connection record.
# Delete the connection and file records if they're there so we
# aren't sending that to remote machines. It can cause problems
# due to the size of those records.
if ( n?$conn )
delete n$conn;
if ( n?$iconn )
delete n$iconn;
if ( n?$f )
delete n$f;
}
function internal_NOTICE(n: Notice::Info)

4
scripts/base/init-bare.bro
View file

@ -328,7 +328,7 @@ type fa_file: record {
## An identification of the source of the file data. E.g. it may be
## a network protocol over which it was transferred, or a local file
## path which was read, or some other input source.
source: string &optional;
source: string;
## If the source of this file is is a network connection, this field
## may be set to indicate the directionality.
@ -3049,6 +3049,6 @@ const snaplen = 8192 &redef;
@load base/frameworks/logging
@load base/frameworks/input
@load base/frameworks/analyzer
@load base/frameworks/file-analysis
@load base/frameworks/files
@load base/bif

6
scripts/base/init-default.bro
View file

@ -5,9 +5,12 @@
##! you actually want.
@load base/utils/site
@load base/utils/active-http
@load base/utils/addrs
@load base/utils/conn-ids
@load base/utils/dir
@load base/utils/directions-and-hosts
@load base/utils/exec
@load base/utils/files
@load base/utils/numbers
@load base/utils/paths
@ -49,4 +52,7 @@
@load base/protocols/syslog
@load base/protocols/tunnels
@load base/files/hash
@load base/files/extract
@load base/misc/find-checksum-offloading

4
scripts/base/protocols/ftp/__load__.bro
View file

@ -1,7 +1,7 @@
@load ./utils-commands
@load ./main
@load ./file-analysis
@load ./file-extract
@load ./utils
@load ./files
@load ./gridftp
@load-sigs ./dpd.sig

48
scripts/base/protocols/ftp/file-analysis.bro
View file

@ -1,48 +0,0 @@
@load ./main
@load base/utils/conn-ids
@load base/frameworks/file-analysis/main
module FTP;
export {
## Default file handle provider for FTP.
global get_file_handle: function(c: connection, is_orig: bool): string;
}
function get_handle_string(c: connection): string
{
return cat(Analyzer::ANALYZER_FTP_DATA, " ", c$start_time, " ", id_string(c$id));
}
function get_file_handle(c: connection, is_orig: bool): string
{
if ( [c$id$resp_h, c$id$resp_p] !in ftp_data_expected ) return "";
local info: FTP::Info = ftp_data_expected[c$id$resp_h, c$id$resp_p];
if ( info$passive )
# FTP client initiates data channel.
if ( is_orig )
# Don't care about FTP client data.
return "";
else
# Do care about FTP server data.
return get_handle_string(c);
else
# FTP server initiates dta channel.
if ( is_orig )
# Do care about FTP server data.
return get_handle_string(c);
else
# Don't care about FTP client data.
return "";
}
module GLOBAL;
event get_file_handle(tag: Analyzer::Tag, c: connection, is_orig: bool)
&priority=5
{
if ( tag != Analyzer::ANALYZER_FTP_DATA ) return;
set_file_handle(FTP::get_file_handle(c, is_orig));
}

90
scripts/base/protocols/ftp/file-extract.bro
View file

@ -1,90 +0,0 @@
##! File extraction support for FTP.
@load ./main
@load base/utils/files
module FTP;
export {
## Pattern of file mime types to extract from FTP transfers.
const extract_file_types = /NO_DEFAULT/ &redef;
## The on-disk prefix for files to be extracted from FTP-data transfers.
const extraction_prefix = "ftp-item" &redef;
}
redef record Info += {
## On disk file where it was extracted to.
extraction_file: string &log &optional;
## Indicates if the current command/response pair should attempt to
## extract the file if a file was transferred.
extract_file: bool &default=F;
};
function get_extraction_name(f: fa_file): string
{
local r = fmt("%s-%s.dat", extraction_prefix, f$id);
return r;
}
event file_new(f: fa_file) &priority=5
{
if ( ! f?$source ) return;
if ( f$source != "FTP_DATA" ) return;
if ( f?$mime_type && extract_file_types in f$mime_type )
{
FileAnalysis::add_analyzer(f, [$tag=FileAnalysis::ANALYZER_EXTRACT,
$extract_filename=get_extraction_name(f)]);
return;
}
if ( ! f?$conns ) return;
for ( cid in f$conns )
{
local c: connection = f$conns[cid];
if ( [cid$resp_h, cid$resp_p] !in ftp_data_expected ) next;
local s = ftp_data_expected[cid$resp_h, cid$resp_p];
if ( ! s$extract_file ) next;
FileAnalysis::add_analyzer(f, [$tag=FileAnalysis::ANALYZER_EXTRACT,
$extract_filename=get_extraction_name(f)]);
return;
}
}
event file_state_remove(f: fa_file) &priority=4
{
if ( ! f?$source ) return;
if ( f$source != "FTP_DATA" ) return;
if ( ! f?$info ) return;
for ( filename in f$info$extracted_files )
{
local s: FTP::Info;
s$ts = network_time();
s$tags = set();
s$user = "<ftp-data>";
s$extraction_file = filename;
if ( f?$conns )
for ( cid in f$conns )
{
s$uid = f$conns[cid]$uid;
s$id = cid;
}
Log::write(FTP::LOG, s);
}
}
event log_ftp(rec: Info) &priority=-10
{
delete rec$extraction_file;
delete rec$extract_file;
}

60
scripts/base/protocols/ftp/files.bro Normal file
View file

@ -0,0 +1,60 @@
@load ./main
@load ./utils
@load base/utils/conn-ids
@load base/frameworks/files
module FTP;
export {
redef record Info += {
## File unique ID.
fuid: string &optional &log;
};
## Default file handle provider for FTP.
global get_file_handle: function(c: connection, is_orig: bool): string;
## Describe the file being transferred.
global describe_file: function(f: fa_file): string;
}
function get_file_handle(c: connection, is_orig: bool): string
{
if ( [c$id$resp_h, c$id$resp_p] !in ftp_data_expected )
return "";
return cat(Analyzer::ANALYZER_FTP_DATA, c$start_time, c$id, is_orig);
}
function describe_file(f: fa_file): string
{
# This shouldn't be needed, but just in case...
if ( f$source != "FTP" )
return "";
for ( cid in f$conns )
{
if ( f$conns[cid]?$ftp )
return FTP::describe(f$conns[cid]$ftp);
}
return "";
}
event bro_init() &priority=5
{
Files::register_protocol(Analyzer::ANALYZER_FTP_DATA,
[$get_file_handle = FTP::get_file_handle,
$describe = FTP::describe_file]);
}
event file_over_new_connection(f: fa_file, c: connection, is_orig: bool) &priority=5
{
if ( [c$id$resp_h, c$id$resp_p] !in ftp_data_expected )
return;
local ftp = ftp_data_expected[c$id$resp_h, c$id$resp_p];
ftp$fuid = f$id;
if ( f?$mime_type )
ftp$mime_type = f$mime_type;
}

42
scripts/base/protocols/ftp/main.bro
View file

@ -63,8 +63,6 @@ export {
reply_code: count &log &optional;
## Reply message from the server in response to the command.
reply_msg: string &log &optional;
## Arbitrary tags that may indicate a particular attribute of this command.
tags: set[string] &log;
## Expected FTP data channel.
data_channel: ExpectedDataChannel &log &optional;
@ -104,6 +102,8 @@ export {
global log_ftp: event(rec: Info);
}
@load ./utils
# Add the state tracking information variable to the connection record
redef record connection += {
ftp: Info &optional;
@ -171,10 +171,16 @@ function set_ftp_session(c: connection)
function ftp_message(s: Info)
{
# If it either has a tag associated with it (something detected)
# or it's a deliberately logged command.
if ( |s$tags| > 0 || (s?$cmdarg && s$cmdarg$cmd in logged_commands) )
{
s$ts=s$cmdarg$ts;
s$command=s$cmdarg$cmd;
s$arg = s$cmdarg$arg;
if ( s$cmdarg$cmd in file_cmds )
s$arg = build_url_ftp(s);
if ( s$arg == "" )
delete s$arg;
if ( s?$password &&
! s$capture_password &&
to_lower(s$user) !in guest_ids )
@ -182,25 +188,8 @@ function ftp_message(s: Info)
s$password = "<hidden>";
}
local arg = s$cmdarg$arg;
if ( s$cmdarg$cmd in file_cmds )
{
local comp_path = build_path_compressed(s$cwd, arg);
if ( comp_path[0] != "/" )
comp_path = cat("/", comp_path);
arg = fmt("ftp://%s%s", addr_to_uri(s$id$resp_h), comp_path);
}
s$ts=s$cmdarg$ts;
s$command=s$cmdarg$cmd;
if ( arg == "" )
delete s$arg;
else
s$arg=arg;
if ( s?$cmdarg && s$command in logged_commands)
Log::write(FTP::LOG, s);
}
# The MIME and file_size fields are specific to file transfer commands
# and may not be used in all commands so they need reset to "blank"
@ -209,8 +198,6 @@ function ftp_message(s: Info)
delete s$file_size;
# Same with data channel.
delete s$data_channel;
# Tags are cleared everytime too.
s$tags = set();
}
function add_expected_data_channel(s: Info, chan: ExpectedDataChannel)
@ -218,7 +205,8 @@ function add_expected_data_channel(s: Info, chan: ExpectedDataChannel)
s$passive = chan$passive;
s$data_channel = chan;
ftp_data_expected[chan$resp_h, chan$resp_p] = s;
Analyzer::schedule_analyzer(chan$orig_h, chan$resp_h, chan$resp_p, Analyzer::ANALYZER_FTP_DATA,
Analyzer::schedule_analyzer(chan$orig_h, chan$resp_h, chan$resp_p,
Analyzer::ANALYZER_FTP_DATA,
5mins);
}

47
scripts/base/protocols/ftp/utils.bro Normal file
View file

@ -0,0 +1,47 @@
##! Utilities specific for FTP processing.
@load ./main
@load base/utils/addrs
module FTP;
export {
## Creates a URL from an :bro:type:`FTP::Info` record.
##
## rec: An :bro:type:`FTP::Info` record.
##
## Returns: A URL, not prefixed by "ftp://".
global build_url: function(rec: Info): string;
## Creates a URL from an :bro:type:`FTP::Info` record.
##
## rec: An :bro:type:`FTP::Info` record.
##
## Returns: A URL prefixed with "ftp://".
global build_url_ftp: function(rec: Info): string;
## Create an extremely shortened representation of a log line.
global describe: function(rec: Info): string;
}
function build_url(rec: Info): string
{
if ( !rec?$arg )
return "";
local comp_path = build_path_compressed(rec$cwd, rec$arg);
if ( comp_path[0] != "/" )
comp_path = cat("/", comp_path);
return fmt("%s%s", addr_to_uri(rec$id$resp_h), comp_path);
}
function build_url_ftp(rec: Info): string
{
return fmt("ftp://%s", build_url(rec));
}
function describe(rec: Info): string
{
return build_url_ftp(rec);
}

6
scripts/base/protocols/http/__load__.bro
View file

@ -1,8 +1,6 @@
@load ./main
@load ./entities
@load ./utils
@load ./file-analysis
@load ./file-ident
@load ./file-hash
@load ./file-extract
@load ./files
@load-sigs ./dpd.sig

109
scripts/base/protocols/http/entities.bro Normal file
View file

@ -0,0 +1,109 @@
##! Analysis and logging for MIME entities found in HTTP sessions.
@load base/frameworks/files
@load base/utils/strings
@load base/utils/files
@load ./main
module HTTP;
export {
type Entity: record {
## Filename for the entity if discovered from a header.
filename: string &optional;
};
redef record Info += {
## An ordered vector of file unique IDs.
orig_fuids: vector of string &log &optional;
## An ordered vector of mime types.
orig_mime_types: vector of string &log &optional;
## An ordered vector of file unique IDs.
resp_fuids: vector of string &log &optional;
## An ordered vector of mime types.
resp_mime_types: vector of string &log &optional;
## The current entity.
current_entity: Entity &optional;
## Current number of MIME entities in the HTTP request message body.
orig_mime_depth: count &default=0;
## Current number of MIME entities in the HTTP response message body.
resp_mime_depth: count &default=0;
};
}
event http_begin_entity(c: connection, is_orig: bool) &priority=10
{
set_state(c, F, is_orig);
if ( is_orig )
++c$http$orig_mime_depth;
else
++c$http$resp_mime_depth;
c$http$current_entity = Entity();
}
event http_header(c: connection, is_orig: bool, name: string, value: string) &priority=3
{
if ( name == "CONTENT-DISPOSITION" &&
/[fF][iI][lL][eE][nN][aA][mM][eE]/ in value )
{
c$http$current_entity$filename = extract_filename_from_content_disposition(value);
}
else if ( name == "CONTENT-TYPE" &&
/[nN][aA][mM][eE][:blank:]*=/ in value )
{
c$http$current_entity$filename = extract_filename_from_content_disposition(value);
}
}
event file_over_new_connection(f: fa_file, c: connection, is_orig: bool) &priority=5
{
if ( f$source == "HTTP" && c?$http )
{
if ( c$http?$current_entity && c$http$current_entity?$filename )
f$info$filename = c$http$current_entity$filename;
if ( f$is_orig )
{
if ( ! c$http?$orig_mime_types )
c$http$orig_fuids = string_vec(f$id);
else
c$http$orig_fuids[|c$http$orig_fuids|] = f$id;
if ( f?$mime_type )
{
if ( ! c$http?$orig_mime_types )
c$http$orig_mime_types = string_vec(f$mime_type);
else
c$http$orig_mime_types[|c$http$orig_mime_types|] = f$mime_type;
}
}
else
{
if ( ! c$http?$resp_mime_types )
c$http$resp_fuids = string_vec(f$id);
else
c$http$resp_fuids[|c$http$resp_fuids|] = f$id;
if ( f?$mime_type )
{
if ( ! c$http?$resp_mime_types )
c$http$resp_mime_types = string_vec(f$mime_type);
else
c$http$resp_mime_types[|c$http$resp_mime_types|] = f$mime_type;
}
}
}
}
event http_end_entity(c: connection, is_orig: bool) &priority=5
{
if ( c?$http && c$http?$current_entity )
delete c$http$current_entity;
}

54
scripts/base/protocols/http/file-analysis.bro
View file

@ -1,54 +0,0 @@
@load ./main
@load ./utils
@load base/utils/conn-ids
@load base/frameworks/file-analysis/main
module HTTP;
export {
redef record HTTP::Info += {
## Number of MIME entities in the HTTP request message body so far.
request_mime_level: count &default=0;
## Number of MIME entities in the HTTP response message body so far.
response_mime_level: count &default=0;
};
## Default file handle provider for HTTP.
global get_file_handle: function(c: connection, is_orig: bool): string;
}
event http_begin_entity(c: connection, is_orig: bool) &priority=5
{
if ( ! c?$http )
return;
if ( is_orig )
++c$http$request_mime_level;
else
++c$http$response_mime_level;
}
function get_file_handle(c: connection, is_orig: bool): string
{
if ( ! c?$http ) return "";
local mime_level: count =
is_orig ? c$http$request_mime_level : c$http$response_mime_level;
local mime_level_str: string = mime_level > 1 ? cat(mime_level) : "";
if ( c$http$range_request )
return cat(Analyzer::ANALYZER_HTTP, " ", is_orig, " ", c$id$orig_h, " ",
build_url(c$http));
return cat(Analyzer::ANALYZER_HTTP, " ", c$start_time, " ", is_orig, " ",
c$http$trans_depth, mime_level_str, " ", id_string(c$id));
}
module GLOBAL;
event get_file_handle(tag: Analyzer::Tag, c: connection, is_orig: bool)
&priority=5
{
if ( tag != Analyzer::ANALYZER_HTTP ) return;
set_file_handle(HTTP::get_file_handle(c, is_orig));
}

100
scripts/base/protocols/http/file-extract.bro
View file

@ -1,100 +0,0 @@
##! Extracts the items from HTTP traffic, one per file. At this time only
##! the message body from the server can be extracted with this script.
@load ./main
@load ./file-analysis
module HTTP;
export {
## Pattern of file mime types to extract from HTTP response entity bodies.
const extract_file_types = /NO_DEFAULT/ &redef;
## The on-disk prefix for files to be extracted from HTTP entity bodies.
const extraction_prefix = "http-item" &redef;
redef record Info += {
## On-disk location where files in request body were extracted.
extracted_request_files: vector of string &log &optional;
## On-disk location where files in response body were extracted.
extracted_response_files: vector of string &log &optional;
## Indicates if the response body is to be extracted or not. Must be
## set before or by the first :bro:see:`file_new` for the file content.
extract_file: bool &default=F;
};
}
function get_extraction_name(f: fa_file): string
{
local r = fmt("%s-%s.dat", extraction_prefix, f$id);
return r;
}
function add_extraction_file(c: connection, is_orig: bool, fn: string)
{
if ( is_orig )
{
if ( ! c$http?$extracted_request_files )
c$http$extracted_request_files = vector();
c$http$extracted_request_files[|c$http$extracted_request_files|] = fn;
}
else
{
if ( ! c$http?$extracted_response_files )
c$http$extracted_response_files = vector();
c$http$extracted_response_files[|c$http$extracted_response_files|] = fn;
}
}
event file_new(f: fa_file) &priority=5
{
if ( ! f?$source ) return;
if ( f$source != "HTTP" ) return;
if ( ! f?$conns ) return;
local fname: string;
local c: connection;
if ( f?$mime_type && extract_file_types in f$mime_type )
{
fname = get_extraction_name(f);
FileAnalysis::add_analyzer(f, [$tag=FileAnalysis::ANALYZER_EXTRACT,
$extract_filename=fname]);
for ( cid in f$conns )
{
c = f$conns[cid];
if ( ! c?$http ) next;
add_extraction_file(c, f$is_orig, fname);
}
return;
}
local extracting: bool = F;
for ( cid in f$conns )
{
c = f$conns[cid];
if ( ! c?$http ) next;
if ( ! c$http$extract_file ) next;
fname = get_extraction_name(f);
FileAnalysis::add_analyzer(f, [$tag=FileAnalysis::ANALYZER_EXTRACT,
$extract_filename=fname]);
extracting = T;
break;
}
if ( extracting )
for ( cid in f$conns )
{
c = f$conns[cid];
if ( ! c?$http ) next;
add_extraction_file(c, f$is_orig, fname);
}
}

68
scripts/base/protocols/http/file-hash.bro
View file

@ -1,68 +0,0 @@
##! Calculate hashes for HTTP body transfers.
@load ./main
@load ./file-analysis
module HTTP;
export {
redef record Info += {
## MD5 sum for a file transferred over HTTP calculated from the
## response body.
md5: string &log &optional;
## This value can be set per-transfer to determine per request
## if a file should have an MD5 sum generated. It must be
## set to T at the time of or before the first chunk of body data.
calc_md5: bool &default=F;
};
## Generate MD5 sums for these filetypes.
const generate_md5 = /application\/x-dosexec/ # Windows and DOS executables
| /application\/x-executable/ # *NIX executable binary
&redef;
}
event file_new(f: fa_file) &priority=5
{
if ( ! f?$source ) return;
if ( f$source != "HTTP" ) return;
if ( f?$mime_type && generate_md5 in f$mime_type )
{
FileAnalysis::add_analyzer(f, [$tag=FileAnalysis::ANALYZER_MD5]);
return;
}
if ( ! f?$conns ) return;
for ( cid in f$conns )
{
local c: connection = f$conns[cid];
if ( ! c?$http ) next;
if ( ! c$http$calc_md5 ) next;
FileAnalysis::add_analyzer(f, [$tag=FileAnalysis::ANALYZER_MD5]);
return;
}
}
event file_state_remove(f: fa_file) &priority=4
{
if ( ! f?$source ) return;
if ( f$source != "HTTP" ) return;
if ( ! f?$conns ) return;
if ( ! f?$info ) return;
if ( ! f$info?$md5 ) return;
for ( cid in f$conns )
{
local c: connection = f$conns[cid];
if ( ! c?$http ) next;
c$http$md5 = f$info$md5;
}
}

105
scripts/base/protocols/http/file-ident.bro
View file

@ -1,105 +0,0 @@
##! Identification of file types in HTTP response bodies with file content sniffing.
@load base/frameworks/notice
@load ./main
@load ./utils
@load ./file-analysis
module HTTP;
export {
redef enum Notice::Type += {
## Indicates when the file extension doesn't seem to match the file
## contents.
Incorrect_File_Type,
};
redef record Info += {
## Mime type of response body identified by content sniffing.
mime_type: string &log &optional;
};
## Mapping between mime type strings (without character set) and
## regular expressions for URLs.
## The :bro:enum:`HTTP::Incorrect_File_Type` notice is generated if the
## pattern doesn't match the mime type that was discovered.
const mime_types_extensions: table[string] of pattern = {
["application/x-dosexec"] = /\.([eE][xX][eE]|[dD][lL][lL])/,
} &redef;
## A pattern for filtering out :bro:enum:`HTTP::Incorrect_File_Type` urls
## that are not noteworthy before a notice is created. Each
## pattern added should match the complete URL (the matched URLs include
## "http://" at the beginning).
const ignored_incorrect_file_type_urls = /^$/ &redef;
}
event file_new(f: fa_file) &priority=5
{
if ( ! f?$source ) return;
if ( f$source != "HTTP" ) return;
if ( ! f?$mime_type ) return;
if ( ! f?$conns ) return;
for ( cid in f$conns )
{
local c: connection = f$conns[cid];
if ( ! c?$http ) next;
c$http$mime_type = f$mime_type;
local mime_str: string = c$http$mime_type;
if ( mime_str !in mime_types_extensions ) next;
if ( ! c$http?$uri ) next;
if ( mime_types_extensions[mime_str] in c$http$uri ) next;
local url = build_url_http(c$http);
if ( url == ignored_incorrect_file_type_urls ) next;
local message = fmt("%s %s %s", mime_str, c$http$method, url);
NOTICE([$note=Incorrect_File_Type,
$msg=message,
$conn=c]);
}
}
event file_over_new_connection(f: fa_file, c: connection) &priority=5
{
if ( ! f?$source ) return;
if ( f$source != "HTTP" ) return;
if ( ! f?$mime_type ) return;
if ( ! c?$http ) return;
# Spread the mime around (e.g. for partial content, file_type event only
# happens once for the first connection, but if there's subsequent
# connections to transfer the same file, they'll be lacking the mime_type
# field if we don't do this).
c$http$mime_type = f$mime_type;
}
# Tracks byte-range request / partial content response mime types, indexed
# by [connection, uri] pairs. This is needed because a person can pipeline
# byte-range requests over multiple connections to the same uri. Without
# the tracking, only the first request in the pipeline for each connection
# would get a mime_type field assigned to it (by the FileAnalysis policy hooks).
global partial_types: table[conn_id, string] of string &read_expire=5mins;
# Priority 4 so that it runs before the handler that will write to http.log.
event http_message_done(c: connection, is_orig: bool, stat: http_message_stat)
&priority=4
{
if ( ! c$http$range_request ) return;
if ( ! c$http?$uri ) return;
if ( c$http?$mime_type )
{
partial_types[c$id, c$http$uri] = c$http$mime_type;
return;
}
if ( [c$id, c$http$uri] in partial_types )
c$http$mime_type = partial_types[c$id, c$http$uri];
}

Some files were not shown because too many files have changed in this diff Show more