diff options
Diffstat (limited to 'usr.bin/file/Magdir/compress')
-rw-r--r-- | usr.bin/file/Magdir/compress | 76 |
1 files changed, 61 insertions, 15 deletions
diff --git a/usr.bin/file/Magdir/compress b/usr.bin/file/Magdir/compress index 6309c180..2cf8d19 100644 --- a/usr.bin/file/Magdir/compress +++ b/usr.bin/file/Magdir/compress @@ -1,25 +1,60 @@ + +#------------------------------------------------------------------------------ +# 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. -# According to gzip.h, this is the correct byte order for packed data. -# -0 string \037\036 packed data +# standard unix compress +0 string \037\235 compress'd data +>2 byte&0x80 >0 block compressed +>2 byte&0x1f x %d bits +# gzip (GNU zip, not to be confused with Info-ZIP or PKWARE zip archiver) +0 string \037\213 gzip compressed data +>2 byte <8 \b, reserved method, +>2 byte 8 \b, deflated, +>3 byte &0x01 ASCII, +>3 byte &0x02 continuation, +>3 byte &0x04 extra field, +>3 byte &0x08 original filename, +>3 byte &0x10 comment, +>3 byte &0x20 encrypted, +>4 ledate x last modified: %s, +>8 byte 2 max compression, +>8 byte 4 max speed, +>9 byte =0x00 os: MS-DOS +>9 byte =0x01 os: Amiga +>9 byte =0x02 os: VMS +>9 byte =0x03 os: Unix +>9 byte =0x05 os: Atari +>9 byte =0x06 os: OS/2 +>9 byte =0x07 os: MacOS +>9 byte =0x0A os: Tops/20 +>9 byte =0x0B os: Win/32 + +# packed data, Huffman (minimum redundancy) codes on a byte-by-byte basis +0 string \037\036 packed data +>2 belong >1 \b, %d characters originally +>2 belong =1 \b, %d character originally # -# This magic number is byte-order-independent. -# +# This magic number is byte-order-independent. XXX - Does that mean this +# is big-endian, little-endian, either, or that you can't tell? +# this short is valid for SunOS 0 short 017437 old packed data -# # 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 +# 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 0 short 0145405 huf output -# + # Squeeze and Crunch... # These numbers were gleaned from the Unix versions of the programs to # handle these formats. Note that I can only uncrunch, not crunch, and @@ -27,14 +62,25 @@ # Keith Waclena <keith@cerberus.uchicago.edu> 0 leshort 0x76FF squeezed data (CP/M, DOS) 0 leshort 0x76FE crunched data (CP/M, DOS) + # Freeze -0 string \037\237 Frozen file 2.1 -0 string \037\236 Frozen file 1.0 (or gzip 0.5) +0 string \037\237 frozen file 2.1 +0 string \037\236 frozen file 1.0 (or gzip 0.5) + +# SCO compress -H (LZH) +0 string \037\240 SCO compress -H (LZH) data + +# European GSM 06.10 is a provisional standard for full-rate speech +# transcoding, prI-ETS 300 036, which uses RPE/LTP (residual pulse +# excitation/long term prediction) coding at 13 kbit/s. # -# Standard unix compress +# There's only a magic nibble (4 bits); that nibble repeats every 33 +# bytes. This isn't suited for use, but maybe we can use it someday. # -0 string \037\235 compressed data ->2 byte&0x80 >0 block compressed ->2 byte&0x1f x %d bits - -0 string \037\240 LZH compressed data +# This will cause very short GSM files to be declared as data and +# mismatches to be declared as data too! +#0 byte&0xF0 0xd0 data +#>33 byte&0xF0 0xd0 +#>66 byte&0xF0 0xd0 +#>99 byte&0xF0 0xd0 +#>132 byte&0xF0 0xd0 GSM 06.10 compressed audio |