home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
The Atari Compendium
/
The Atari Compendium (Toad Computers) (1994).iso
/
files
/
compress
/
compress.arc
/
COMPRESS.C
next >
Wrap
C/C++ Source or Header
|
1987-08-17
|
41KB
|
1,494 lines
/*
* Compress - data compression program
*/
#define min(a,b) ((a>b) ? b : a)
#define ATARI /* MWC for ATARI ST */
/*
* machine variants which require cc -Dmachine: pdp11, z8000, pcxt
*/
/*
* Set USERMEM to the maximum amount of physical user memory available
* in bytes. USERMEM is used to determine the maximum BITS that can be used
* for compression.
*
* SACREDMEM is the amount of physical memory saved for others; compress
* will hog the rest.
*/
#ifndef SACREDMEM
#define SACREDMEM 0
#endif
#ifndef USERMEM
# define USERMEM 100000 /* default user memory */
#endif
#ifdef interdata /* (Perkin-Elmer) */
#define SIGNED_COMPARE_SLOW /* signed compare is slower than unsigned */
#endif
#ifdef pdp11
# define BITS 12 /* max bits/code for 16-bit machine */
# define NO_UCHAR /* also if "unsigned char" functions as signed char */
# undef USERMEM
#endif /* pdp11 */ /* don't forget to compile with -i */
#ifdef z8000
# define BITS 12
# undef vax /* weird preprocessor */
# undef USERMEM
#endif /* z8000 */
#ifdef pcxt
# define BITS 12
# undef USERMEM
#endif /* pcxt */
#ifdef ATARI
#define BITS 13
#define SIGNED_COMPARE_SLOW
#undef USERMEM
#endif /* MWC on ATARI 520 SHOULD WORK */
#ifdef USERMEM
# if USERMEM >= (433484+SACREDMEM)
# define PBITS 16
# else
# if USERMEM >= (229600+SACREDMEM)
# define PBITS 15
# else
# if USERMEM >= (127536+SACREDMEM)
# define PBITS 14
# else
# if USERMEM >= (73464+SACREDMEM)
# define PBITS 13
# else
# define PBITS 12
# endif
# endif
# endif
# endif
# undef USERMEM
#endif /* USERMEM */
#ifdef PBITS /* Preferred BITS for this memory size */
# ifndef BITS
# define BITS PBITS
# endif
#endif /* PBITS */
#if BITS == 16
# define HSIZE 69001 /* 95% occupancy */
#endif
#if BITS == 15
# define HSIZE 35023 /* 94% occupancy */
#endif
#if BITS == 14
# define HSIZE 18013 /* 91% occupancy */
#endif
#if BITS == 13
# define HSIZE 9001 /* 91% occupancy */
#endif
#if BITS <= 12
# define HSIZE 5003 /* 80% occupancy */
#endif
#ifdef M_XENIX /* Stupid compiler can't handle arrays with */
# if BITS == 16 /* more than 65535 bytes - so we fake it */
# define XENIX_16
# else
# if BITS > 13 /* Code only handles BITS = 12, 13, or 16 */
# define BITS 13
# endif
# endif
#endif
/*
* a code_int must be able to hold 2**BITS values of type int, and also -1
*/
#if BITS > 15
typedef long int code_int;
#else
typedef int code_int;
#endif
#ifdef SIGNED_COMPARE_SLOW
typedef unsigned long int count_int;
typedef unsigned short int count_short;
#else
typedef long int count_int;
#endif
#undef NO_UCHAR
#ifdef NO_UCHAR
typedef char char_type;
#else
typedef unsigned char char_type;
#endif /* UCHAR */
char_type magic_header[] = { "\037\235" }; /* 1F 9D */
/* Defines for third byte of header */
#define BIT_MASK 0x1f
#define BLOCK_MASK 0x80
/* Masks 0x40 and 0x20 are free. I think 0x20 should mean that there is
a fourth header byte (for expansion).
*/
#define INIT_BITS 9 /* initial number of bits/code */
/*
* compress.c - File compression ala IEEE Computer, June 1984.
*
* Authors: Spencer W. Thomas (decvax!harpo!utah-cs!utah-gr!thomas)
* Jim McKie (decvax!mcvax!jim)
* Steve Davies (decvax!vax135!petsd!peora!srd)
* Ken Turkowski (decvax!decwrl!turtlevax!ken)
* James A. Woods (decvax!ihnp4!ames!jaw)
* Joe Orost (decvax!vax135!petsd!joe)
*
* $Header: compress.c,v 4.0 85/07/30 12:50:00 joe Release $
* $Log: compress.c,v $
* Revision 4.0 85/07/30 12:50:00 joe
* Removed ferror() calls in output routine on every output except first.
* Prepared for release to the world.
*
* Revision 3.6 85/07/04 01:22:21 joe
* Remove much wasted storage by overlaying hash table with the tables
* used by decompress: tab_suffix[1<<BITS], stack[8000]. Updated USERMEM
* computations. Fixed dump_tab() DEBUG routine.
*
* Revision 3.5 85/06/30 20:47:21 jaw
* Change hash function to use exclusive-or. Rip out hash cache. These
* speedups render the megamemory version defunct, for now. Make decoder
* stack global. Parts of the RCS trunks 2.7, 2.6, and 2.1 no longer apply.
*
* Revision 3.4 85/06/27 12:00:00 ken
* Get rid of all floating-point calculations by doing all compression ratio
* calculations in fixed point.
*
* Revision 3.3 85/06/24 21:53:24 joe
* Incorporate portability suggestion for M_XENIX. Got rid of text on #else
* and #endif lines. Cleaned up #ifdefs for vax and interdata.
*
* Revision 3.2 85/06/06 21:53:24 jaw
* Incorporate portability suggestions for Z8000, IBM PC/XT from mailing list.
* Default to "quiet" output (no compression statistics).
*
* Revision 3.1 85/05/12 18:56:13 jaw
* Integrate decompress() stack speedups (from early pointer mods by McKie).
* Repair multi-file USERMEM gaffe. Unify 'force' flags to mimic semantics
* of SVR2 'pack'. Streamline block-compress table clear logic. Increase
* output byte count by magic number size.
*
* Revision 3.0 84/11/27 11:50:00 petsd!joe
* Set HSIZE depending on BITS. Set BITS depending on USERMEM. Unrolled
* loops in clear routines. Added "-C" flag for 2.0 compatibility. Used
* unsigned compares on Perkin-Elmer. Fixed foreground check.
*
* Revision 2.7 84/11/16 19:35:39 ames!jaw
* Cache common hash codes based on input statistics; this improves
* performance for low-density raster images. Pass on #ifdef bundle
* from Turkowski.
*
* Revision 2.6 84/11/05 19:18:21 ames!jaw
* Vary size of hash tables to reduce time for small files.
* Tune PDP-11 hash function.
*
* Revision 2.5 84/10/30 20:15:14 ames!jaw
* Junk chaining; replace with the simpler (and, on the VAX, faster)
* double hashing, discussed within. Make block compression standard.
*
* Revision 2.4 84/10/16 11:11:11 ames!jaw
* Introduce adaptive reset for block compression, to boost the rate
* another several percent. (See mailing list notes.)
*
* Revision 2.3 84/09/22 22:00:00 petsd!joe
* Implemented "-B" block compress. Implemented REVERSE sorting of tab_next.
* Bug fix for last bits. Changed fwrite to putchar loop everywhere.
*
* Revision 2.2 84/09/18 14:12:21 ames!jaw
* Fold in news changes, small machine typedef from thomas,
* #ifdef interdata from joe.
*
* Revision 2.1 84/09/10 12:34:56 ames!jaw
* Configured fast table lookup for 32-bit machines.
* This cuts user time in half for b <= FBITS, and is useful for news batching
* from VAX to PDP sites. Also sped up decompress() [fwrite->putc] and
* added signal catcher [plus beef in writeerr()] to delete effluvia.
*
* Revision 2.0 84/08/28 22:00:00 petsd!joe
* Add check for foreground before prompting user. Insert maxbits into
* compressed file. Force file being uncompressed to end with ".Z".
* Added "-c" flag and "zcat". Prepared for release.
*
* Revision 1.10 84/08/24 18:28:00 turtlevax!ken
* Will only compress regular files (no directories), added a magic number
* header (plus an undocumented -n flag to handle old files without headers),
* added -f flag to force overwriting of possibly existing destination file,
* otherwise the user is prompted for a response. Will tack on a .Z to a
* filename if it doesn't have one when decompressing. Will only replace
* file if it was compressed.
*
* Revision 1.9 84/08/16 17:28:00 turtlevax!ken
* Removed scanargs(), getopt(), added .Z extension and unlimited number of
* filenames to compress. Flags may be clustered (-Ddvb12) or separated
* (-D -d -v -b 12), or combination thereof. Modes and other status is
* copied with copystat(). -O bug for 4.2 seems to have disappeared with
* 1.8.
*
* Revision 1.8 84/08/09 23:15:00 joe
* Made it compatible with vax version, installed jim's fixes/enhancements
*
* Revision 1.6 84/08/01 22:08:00 joe
* Sped up algorithm significantly by sorting the compress chain.
*
* Revision 1.5 84/07/13 13:11:00 srd
* Added C versi