# $File: mathematica,v 1.17 2023/06/16 19:33:58 christos Exp $

#------------------------------------------------------------------------------
# $File: mathematica,v 1.17 2023/06/16 19:33:58 christos Exp $
# mathematica: file(1) magic for mathematica files
# "H. Nanosecond" <[email protected]>
# Mathematica a multi-purpose math program
# versions 2.2 and 3.0

0 name wolfram
>0 string x Mathematica notebook version 2.x
!:ext mb
!:mime application/vnd.wolfram.mathematica

#mathematica .mb
0 string \064\024\012\000\035\000\000\000
>0 use wolfram
0 string \064\024\011\000\035\000\000\000
>0 use wolfram

#
0 search/1000 Content-type:\040application/mathematica Mathematica notebook version 2.x
!:ext nb
!:mime application/mathematica

# .ma
# multiple possibilities:

0 string (*^\n\n::[\011frontEndVersion\ =
#>41 string >\0 %s
>0 use wolfram

#0 string (*^\n\n::[\011palette

#0 string (*^\n\n::[\011Information
#>675 string >\0 %s #doesn't work well

# there may be 'cr' instead of 'nl' in some does this matter?

# generic:
0 string (*^\r\r::[\011
>0 use wolfram
0 string (*^\r\n\r\n::[\011
>0 use wolfram
0 string (*^\015
>0 use wolfram
0 string (*^\n\r\n\r::[\011
>0 use wolfram
0 string (*^\r::[\011
>0 use wolfram
0 string (*^\r\n::[\011
>0 use wolfram
0 string (*^\n\n::[\011
>0 use wolfram
0 string (*^\n::[\011
>0 use wolfram

# Mathematica .mx files

#0 string (*This\ is\ a\ Mathematica\ binary\ dump\ file.\ It\ can\ be\ loaded\ with\ Get.*) Mathematica binary file
0 string (*This\ is\ a\ Mathematica\ binary\ Mathematica binary file
#>71 string \000\010\010\010\010\000\000\000\000\000\000\010\100\010\000\000\000
# >71... is optional
>88 string >\0 from %s

# Mathematica files PBF:
# 115 115 101 120 102 106 000 001 000 000 000 203 000 001 000
0 string MMAPBF\000\001\000\000\000\203\000\001\000 Mathematica PBF (fonts I think)

# .ml files These are menu resources I think
# these start with "[0-9][0-9][0-9]\ A~[0-9][0-9][0-9]\
# how to put that into a magic rule?
4 string \ A~ MAthematica .ml file

# .nb files
#too long 0 string (***********************************************************************\n\n\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Mathematica-Compatible Notebook Mathematica 3.0 notebook
0 string (*********************** Mathematica 3.0 notebook

# other (* matches it is a comment start in these langs
# GRR: Too weak; also matches other languages e.g. ML
#0 string (* Mathematica, or Pascal, Modula-2 or 3 code text

#########################
# MatLab v5
# URL: http://fileformats.archiveteam.org/wiki/MAT
# Reference: https://www.mathworks.com/help/pdf_doc/matlab/matfile_format.pdf
# first 116 bytes of header contain text in human-readable form
0 string MATLAB Matlab v
#>11 string/T x \b, at 11 "%.105s"
#!:mime application/octet-stream
!:mime application/x-matlab-data
!:ext mat
# https://de.mathworks.com/help/matlab/import_export/mat-file-versions.html
# level of the MAT-file like: 5.0 7.0 or maybe 7.3
#>7 string x LEVEL "%.3s"
>7 ubyte =0x35 \b5 mat-file
>7 ubyte !0x35
>>7 string x \b%.3s mat-file
>126 short 0x494d (big endian)
>>124 beshort x version %#04x
>126 short 0x4d49 (little endian)
# 0x0100 for level 5.0 and 0x0200 for level 7.0
>>124 leshort x version %#04x
# test again so that default clause works
>126 short x
# created by MATLAB include Platform sometimes without leading comma (0x2C) or missing
# like: GLNX86 PCWIN PCWIN64 SOL2 Windows\0407 nt posix
>>20 search/2 Platform:\040 \b, platform
>>>&0 string x %-0.2s
>>>&2 ubyte !0x2C \b%c
>>>>&0 ubyte !0x2C \b%c
>>>>>&0 ubyte !0x2C \b%c
>>>>>>&0 ubyte !0x2C \b%c
>>>>>>>&0 ubyte !0x2C \b%c
>>>>>>>>&0 ubyte !0x2C \b%c
>>>>>>>>>&0 ubyte !0x2C \b%c
# examples without Platform tag like one_by_zero_char.mat
>>20 default x
>>>11 string x "%s"
# created by MATLAB include time like: Fri Feb 20 15:26:59 2009
>34 search/9/c created\040on:\040 \b, created
>>&0 string x %-.24s
# MatLab v4
# From: Joerg Jenderek
# check for valid imaginary flag of Matlab matrix version 4
13 ushort 0
# check for valid ASCII matrix name
>20 ubyte >0x1F
# skip PreviousEntries.dat with "invalid high" name \304P\344@\001
>>20 ubyte <0304
# skip some Netwfw*.dat and $I3KREPH.dat by checking for non zero number of rows
>>>4 ulong !0
# skip some CD-ROM filesystem like test-hfs.iso by looking for valid big endian type flag
>>>>0 ubelong&0xFFffFF00 0x00000300
>>>>>0 use matlab4
# no example for 8-bit and 16-bit integers matrix
>>>>0 ubelong&0xFFffFF00 0x00000400
>>>>>0 use matlab4
# branch for Little-Endian variant of Matlab MATrix version 4
# skip big endian variant by looking for valid low lttle endian type flag
>>>>0 ulelong <53
# skip tokens.dat and some Netwfw*.dat by check for valid imaginary flag value of MAT version 4
>>>>>12 ulelong <2
# no misidentified little endian MATrix example with "short" matrix name
>>>>>>16 ulelong <3
# skip radeon firmware BONAIRE_sdma.bin HAWAII_sdma.bin KABINI_sdma.bin KAVERI_sdma.bin MULLINS_sdma.bin
# by check for non zero matrix name length
>>>>>>>16 ubelong >0
>>>>>>>>0 use \^matlab4
# little endian MATrix with "long" matrix name or some misidentified samples
>>>>>>16 ulelong >2
# skip TileCacheLogo-*.dat with invalid 2nd character \001 of matrix name with length 96
>>>>>>>21 ubyte >0x1F
>>>>>>>>0 use \^matlab4
# Note: called "MATLAB Mat File" with version "Level 4" by DROID via PUID fmt/1550
# display information of Matlab v4 mat-file
0 name matlab4 Matlab v4 mat-file
#!:mime application/octet-stream
!:mime application/x-matlab-data
!:ext mat
# 20-byte header with 5 long integers that contains information describing certain attributes of the Matrix
# type flag decimal MOPT; maximal 4052=FD4h; maximal 52=34h for little endian
#>0 ubelong x \b, type flag %u
#>0 ubelong x (%#x)
# M: 0~little endian 1~Big Endian 2~VAX D-float 3~VAX G-float 4~Cray
#>0 ubelong/1000 x \b, M=%u
>0 ubelong/1000 0 (little endian)
>0 ubelong/1000 1 (big endian)
>0 ubelong/1000 2 (VAX D-float)
>0 ubelong/1000 3 (VAX G-float)
>0 ubelong/1000 4 (Cray)
# namlen; the length of the matrix name
#>16 ubelong x \b, name length %u
#>(16.L+19) ubyte x \b, TERMINATING NAME CHARACTER=%#x
# nul terminated matrix name like: fit_params testmatrix testsparsecomplex teststringarray
#>20 string x \b, MATRIX NAME="%s"
#>21 ubyte x \b, MAYBE 2ND CHAR=%c
>16 pstring/L x %s
# T indicates the matrix type: 0~numeric 1~text 2~sparse
#>0 ubelong%10 x \b, T=%u
>0 ubelong%10 0 \b, numeric
>0 ubelong%10 1 \b, text
>0 ubelong%10 2 \b, sparse
# mrows; number of rows in the matrix like: 1 3 8
>4 ubelong x \b, rows %u
# ncols; number of columns in the matrix like: 1 3 4 5 9 43
>8 ubelong x \b, columns %u
# imagf; imaginary flag; 1~matrix has an imaginary part 0~only real data
>12 ubelong !0 \b, imaginary (%u)
# real; Real part of the matrix consists of mrows * ncols numbers