* Copyright (c) 1985, 1986 The Regents of the University of California.
* This code is derived from software contributed to Berkeley by
* James A. Woods, derived from original work by Spencer Thomas
* Redistribution and use in source and binary forms are permitted
* provided that the above copyright notice and this paragraph are
* duplicated in all such forms and that any documentation,
* advertising materials, and other materials related to such
* distribution and use acknowledge that the software was developed
* by the University of California, Berkeley. The name of the
* University may not be used to endorse or promote products derived
* from this software without specific prior written permission.
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED
* WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE.
"@(#) Copyright (c) 1985, 1986 The Regents of the University of California.\n\
static char sccsid
[] = "@(#)compress.c 5.10 (Berkeley) %G%";
* Compress - data compression program
#define min(a,b) ((a>b) ? b : a)
* 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
* SACREDMEM is the amount of physical memory saved for others; compress
# define USERMEM 450000 /* default user memory */
#ifdef interdata /* (Perkin-Elmer) */
#define SIGNED_COMPARE_SLOW /* signed compare is slower than unsigned */
# define BITS 12 /* max bits/code for 16-bit machine */
# define NO_UCHAR /* also if "unsigned char" functions as signed char */
#endif /* pdp11 */ /* don't forget to compile with -i */
# undef vax /* weird preprocessor */
# if USERMEM >= (433484+SACREDMEM)
# if USERMEM >= (229600+SACREDMEM)
# if USERMEM >= (127536+SACREDMEM)
# if USERMEM >= (73464+SACREDMEM)
#ifdef PBITS /* Preferred BITS for this memory size */
# define HSIZE 69001 /* 95% occupancy */
# define HSIZE 35023 /* 94% occupancy */
# define HSIZE 18013 /* 91% occupancy */
# define HSIZE 9001 /* 91% occupancy */
# define HSIZE 5003 /* 80% occupancy */
#ifdef M_XENIX /* Stupid compiler can't handle arrays with */
# if BITS == 16 /* more than 65535 bytes - so we fake it */
# if BITS > 13 /* Code only handles BITS = 12, 13, or 16 */
* a code_int must be able to hold 2**BITS values of type int, and also -1
typedef long int code_int
;
#ifdef SIGNED_COMPARE_SLOW
typedef unsigned long int count_int
;
typedef unsigned short int count_short
;
typedef long int count_int
;
typedef unsigned char char_type
;
char_type magic_header
[] = { "\037\235" }; /* 1F 9D */
/* Defines for third byte of header */
/* 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!utah-cs!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 $
* 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
* 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
* 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 version of vax asm routines. Changed structure to arrays to
* save much memory. Do unsigned compares where possible (faster on
* Revision 1.4 84/07/05 03:11:11 thomas
* Clean up the code a little and lint it. (Lint complains about all
* the regs used in the asm, but I'm not going to "fix" this.)
* Revision 1.3 84/07/05 02:06:54 thomas
* Revision 1.2 84/07/05 00:27:27 thomas
* Add variable bit length output.
static char rcs_ident
[] = "$Header: compress.c,v 4.0 85/07/30 12:50:00 joe Release $";
#define ARGVAL() (*++(*argv) || (--argc && *++argv))
int n_bits
; /* number of bits/code */
int maxbits
= BITS
; /* user settable max # bits/code */
code_int maxcode
; /* maximum code, given n_bits */
code_int maxmaxcode
= 1 << BITS
; /* should NEVER generate this code */
#ifdef COMPATIBLE /* But wrong! */
# define MAXCODE(n_bits) (1 << (n_bits) - 1)
# define MAXCODE(n_bits) ((1 << (n_bits)) - 1)
count_int htab8
[HSIZE
-65536];
htab0
, htab1
, htab2
, htab3
, htab4
, htab5
, htab6
, htab7
, htab8
};
#define htabof(i) (htab[(i) >> 13][(i) & 0x1fff])
unsigned short code0tab
[16384];
unsigned short code1tab
[16384];
unsigned short code2tab
[16384];
unsigned short code3tab
[16384];
unsigned short code4tab
[16384];
unsigned short * codetab
[5] = {
code0tab
, code1tab
, code2tab
, code3tab
, code4tab
};
#define codetabof(i) (codetab[(i) >> 14][(i) & 0x3fff])
#else /* Normal machine */
#ifdef sel /* gould base register braindamage */
unsigned short codetab
[HSIZE
];
unsigned short codetab
[HSIZE
];
#define htabof(i) htab[i]
#define codetabof(i) codetab[i]
code_int hsize
= HSIZE
; /* for dynamic table sizing */
* To save much memory, we overlay the table used by compress() with those
* used by decompress(). The tab_prefix table is the same size and type
* as the codetab. The tab_suffix table needs 2**BITS characters. We
* get this from the beginning of htab. The output stack uses the rest
* of htab, and contains characters. There is plenty of room for any
* possible stack (stack used to be 8000 characters).
#define tab_prefixof(i) codetabof(i)
# define tab_suffixof(i) ((char_type *)htab[(i)>>15])[(i) & 0x7fff]
# define de_stack ((char_type *)(htab2))
#else /* Normal machine */
# define tab_suffixof(i) ((char_type *)(htab))[i]
# define de_stack ((char_type *)&tab_suffixof(1<<BITS))
code_int free_ent
= 0; /* first unused entry */
int exit_stat
= 0; /* per-file status */
int perm_stat
= 0; /* permanent status */
fprintf(stderr
,"Usage: compress [-dDVfc] [-b maxbits] [file ...]\n");
fprintf(stderr
,"Usage: compress [-fvc] [-b maxbits] [file ...]\n");
int nomagic
= 0; /* Use a 3-byte magic number header, unless old file */
int zcat_flg
= 0; /* Write output on stdout, suppress messages */
int precious
= 1; /* Don't unlink output file on interrupt */
int quiet
= 1; /* don't tell me about compression */
* block compression parameters -- after all codes are used up,
* and compression rate changes, start over.
int block_compress
= BLOCK_MASK
;
#define CHECK_GAP 10000 /* ratio check interval */
count_int checkpoint
= CHECK_GAP
;
* the next two codes should not be changed lightly, as they must not
* lie within the contiguous general code space.
#define FIRST 257 /* first free entry */
#define CLEAR 256 /* table clear output code */
/*****************************************************************
* Algorithm from "A Technique for High Performance Data Compression",
* Terry A. Welch, IEEE Computer Vol 17, No 6 (June 1984), pp 8-19.
* Usage: compress [-dfvc] [-b bits] [file ...]
* -d: If given, decompression is done instead.
* -c: Write output on stdout, don't remove original.
* -b: Parameter limits the max number of bits/code.
* -f: Forces output file to be generated, even if one already
* exists, and even if no space is saved by compressing.
* If -f is not used, the user will be prompted if stdin is
* a tty, otherwise, the output file will not be overwritten.
* -v: Write compression statistics
* file ...: Files to be compressed. If none specified, stdin
* file.Z: Compressed form of file with same mode, owner, and utimes
* or stdout (if stdin used as input)
* When filenames are given, replaces with the compressed version
* (.Z suffix) only if the file decreases in size.
* Modified Lempel-Ziv method (LZW). Basically finds common
* substrings and replaces them with a variable size code. This is
* deterministic, and can be done on the fly. Thus, the decompression
* procedure needs no input table, but tracks the way the table was built.
register int argc
; char **argv
;
int overwrite
= 0; /* Do not overwrite unless given -f flag */
char **filelist
, **fileptr
;
char *cp
, *rindex(), *malloc();
/* This bg check only works for sh. */
if ( (oldint
= signal ( SIGINT
, SIG_IGN
)) != SIG_IGN
) {
signal ( SIGINT
, onintr
);
signal ( SIGSEGV
, oops
);
bgnd_flag
= oldint
!= SIG_DFL
;
#ifdef notdef /* This works for csh but we don't want it. */
if (bgnd_flag
== 0 && ioctl(2, TIOCGPGRP
, (char *)&tgrp
) == 0 &&
nomagic
= 1; /* Original didn't have a magic number */
filelist
= fileptr
= (char **)(malloc(argc
* sizeof(*argv
)));
if((cp
= rindex(argv
[0], '/')) != 0) {
if(strcmp(cp
, "uncompress") == 0) {
} else if(strcmp(cp
, "zcat") == 0) {
/* 4.2BSD dependent - take it out if not */
* All flags are optional.
* -V => print Version; debug verbose
* -f => force overwrite of output file
* -n => no header: useful to uncompress old files
* -b maxbits => maxbits. If -b is specified, then maxbits MUST be
* -c => cat all output to stdout
* -C => generate output compatible with compress 2.0.
* if a string is left, must be an input filename.
for (argc
--, argv
++; argc
> 0; argc
--, argv
++) {
if (**argv
== '-') { /* A flag argument */
while (*++(*argv
)) { /* Process all flags in this arg */
fprintf(stderr
, "Missing maxbits\n");
fprintf(stderr
, "Unknown flag: '%c'; ", **argv
);
else { /* Input file name */
*fileptr
++ = *argv
; /* Build input file list */
if(maxbits
< INIT_BITS
) maxbits
= INIT_BITS
;
if (maxbits
> BITS
) maxbits
= BITS
;
maxmaxcode
= 1 << maxbits
;
for (fileptr
= filelist
; *fileptr
; fileptr
++) {
if (do_decomp
) { /* DECOMPRESSION */
/* Check for .Z suffix */
if (strcmp(*fileptr
+ strlen(*fileptr
) - 2, ".Z") != 0) {
strcpy(tempname
, *fileptr
);
if ((freopen(*fileptr
, "r", stdin
)) == NULL
) {
/* Check the magic number */
if ((getchar() != (magic_header
[0] & 0xFF))
|| (getchar() != (magic_header
[1] & 0xFF))) {
fprintf(stderr
, "%s: not in compressed format\n",
maxbits
= getchar(); /* set -b from file */
block_compress
= maxbits
& BLOCK_MASK
;
maxmaxcode
= 1 << maxbits
;
"%s: compressed with %d bits, can only handle %d bits\n",
*fileptr
, maxbits
, BITS
);
/* Generate output filename */
strcpy(ofname
, *fileptr
);
ofname
[strlen(*fileptr
) - 2] = '\0'; /* Strip off .Z */
} else { /* COMPRESSION */
if (strcmp(*fileptr
+ strlen(*fileptr
) - 2, ".Z") == 0) {
fprintf(stderr
, "%s: already has .Z suffix -- no change\n",
if ((freopen(*fileptr
, "r", stdin
)) == NULL
) {
stat ( *fileptr
, &statbuf
);
fsize
= (long) statbuf
.st_size
;
* tune hash table size for small files -- ad hoc,
* but the sizes match earlier #defines, which
* serve as upper bounds on the number of output codes.
hsize
= min ( 5003, HSIZE
);
else if ( fsize
< (1 << 13) )
hsize
= min ( 9001, HSIZE
);
else if ( fsize
< (1 << 14) )
hsize
= min ( 18013, HSIZE
);
else if ( fsize
< (1 << 15) )
hsize
= min ( 35023, HSIZE
);
else if ( fsize
< 47000 )
hsize
= min ( 50021, HSIZE
);
/* Generate output filename */
strcpy(ofname
, *fileptr
);
#ifndef BSD4_2 /* Short filenames */
if ((cp
=rindex(ofname
,'/')) != NULL
) cp
++;
fprintf(stderr
,"%s: filename too long to tack on .Z\n",cp
);
#endif /* BSD4_2 Long filenames allowed */
/* Check for overwrite of existing file */
if (overwrite
== 0 && zcat_flg
== 0) {
if (stat(ofname
, &statbuf
) == 0) {
fprintf(stderr
, "%s already exists;", ofname
);
if (bgnd_flag
== 0 && isatty(2)) {
fprintf(stderr
, " do you wish to overwrite %s (y or n)? ",
while (response
[1] != '\n') {
if (read(2, response
+1, 1) < 0) { /* Ack! */
if (response
[0] != 'y') {
fprintf(stderr
, "\tnot overwritten\n");
if(zcat_flg
== 0) { /* Open output file */
if (freopen(ofname
, "w", stdout
) == NULL
) {
fprintf(stderr
, "%s: ", *fileptr
);
/* Actually do the compression/decompression */
if (do_decomp
== 0) compress();
else if (debug
== 0) decompress();
copystat(*fileptr
, ofname
); /* Copy stats */
if((exit_stat
== 1) || (!quiet
))
} else { /* Standard input */
/* Check the magic number */
if ((getchar()!=(magic_header
[0] & 0xFF))
|| (getchar()!=(magic_header
[1] & 0xFF))) {
fprintf(stderr
, "stdin: not in compressed format\n");
maxbits
= getchar(); /* set -b from file */
block_compress
= maxbits
& BLOCK_MASK
;
maxmaxcode
= 1 << maxbits
;
fsize
= 100000; /* assume stdin large for USERMEM */
"stdin: compressed with %d bits, can only handle %d bits\n",
if (debug
== 0) decompress();
exit(perm_stat
? perm_stat
: exit_stat
);
long int in_count
= 1; /* length of input */
long int bytes_out
; /* length of compressed output */
long int out_count
= 0; /* # of codes output (for debugging) */
* compress stdin to stdout
* Algorithm: use open addressing double hashing (no chaining) on the
* prefix code / next character combination. We do a variant of Knuth's
* algorithm D (vol. 3, sec. 6.4) along with G. Knott's relatively-prime
* secondary probe. Here, the modular division first probe is gives way
* to a faster exclusive-or manipulation. Also do block compression with
* an adaptive reset, whereby the code table is cleared when the compression
* ratio decreases, but after the table fills. The variable-length output
* codes are re-sized at this point, and a special CLEAR code is generated
* for the decompressor. Late addition: construct the table according to
* file size for noticeable speed improvement on small files. Please direct
* questions about this implementation to ames!jaw.
#else /* Normal machine */
register code_int hsize_reg
;
putchar(magic_header
[0]); putchar(magic_header
[1]);
putchar((char)(maxbits
| block_compress
));
bytes_out
= 3; /* includes 3-byte header mojo */
maxcode
= MAXCODE(n_bits
= INIT_BITS
);
free_ent
= ((block_compress
) ? FIRST
: 256 );
for ( fcode
= (long) hsize
; fcode
< 65536L; fcode
*= 2L )
hshift
= 8 - hshift
; /* set hash code range bound */
cl_hash( (count_int
) hsize_reg
); /* clear hash table */
#ifdef SIGNED_COMPARE_SLOW
while ( (c
= getchar()) != (unsigned) EOF
) {
while ( (c
= getchar()) != EOF
) {
fcode
= (long) (((long) c
<< maxbits
) + ent
);
i
= ((c
<< hshift
) ^ ent
); /* xor hashing */
if ( htabof (i
) == fcode
) {
} else if ( (long)htabof (i
) < 0 ) /* empty slot */
disp
= hsize_reg
- i
; /* secondary hash (after G. Knott) */
if ( htabof (i
) == fcode
) {
if ( (long)htabof (i
) > 0 )
output ( (code_int
) ent
);
#ifdef SIGNED_COMPARE_SLOW
if ( (unsigned) free_ent
< (unsigned) maxmaxcode
) {
if ( free_ent
< maxmaxcode
) {
codetabof (i
) = free_ent
++; /* code -> hashtable */
else if ( (count_int
)in_count
>= checkpoint
&& block_compress
)
* Put out the final code.
* Print out stats on stderr
if(zcat_flg
== 0 && !quiet
) {
"%ld chars in, %ld codes (%ld bytes) out, compression factor: ",
in_count
, out_count
, bytes_out
);
prratio( stderr
, in_count
, bytes_out
);
fprintf( stderr
, "\tCompression as in compact: " );
prratio( stderr
, in_count
-bytes_out
, in_count
);
fprintf( stderr
, "\tLargest code (of last block) was %d (%d bits)\n",
fprintf( stderr
, "Compression: " );
prratio( stderr
, in_count
-bytes_out
, in_count
);
if(bytes_out
> in_count
) /* exit(2) if no savings */
/*****************************************************************
* code: A n_bits-bit integer. If == -1, then EOF. This assumes
* that n_bits =< (long)wordsize - 1.
* Outputs code to the file.
* Maintain a BITS character long buffer (so that 8 codes will
* fit in it exactly). Use the VAX insv instruction to insert each
* code in turn. When the buffer fills up empty it and start over.
char_type lmask
[9] = {0xff, 0xfe, 0xfc, 0xf8, 0xf0, 0xe0, 0xc0, 0x80, 0x00};
char_type rmask
[9] = {0x00, 0x01, 0x03, 0x07, 0x0f, 0x1f, 0x3f, 0x7f, 0xff};
* On the VAX, it is important to have the register declarations
* in exactly the order given, or the asm will break.
register int r_off
= offset
, bits
= n_bits
;
register char * bp
= buf
;
fprintf( stderr
, "%5d%c", code
,
(col
+=6) >= 74 ? (col
= 0, '\n') : ' ' );
/* VAX DEPENDENT!! Implementation on other machines is below.
* Translation: Insert BITS bits from the argument starting at
* offset bits from the beginning of buf.
0; /* Work around for pcc -O bug with asm and if stmt */
asm( "insv 4(ap),r11,r10,(r9)" );
* byte/bit numbering on the VAX is simulated by the following code
* Since code is always >= 8 bits, only need to mask the first
*bp
= (*bp
& rmask
[r_off
]) | (code
<< r_off
) & lmask
[r_off
];
/* Get any 8 bit parts in the middle (<=1 for up to 16 bits). */
if ( offset
== (n_bits
<< 3) ) {
* If the next entry is going to be too big for the code size,
* then increase it, if possible.
if ( free_ent
> maxcode
|| (clear_flg
> 0))
* Write the whole buffer, because the input side won't
* discover the size increase until after it has read it.
if( fwrite( buf
, 1, n_bits
, stdout
) != n_bits
)
maxcode
= MAXCODE (n_bits
= INIT_BITS
);
maxcode
= MAXCODE(n_bits
);
fprintf( stderr
, "\nChange to %d bits\n", n_bits
);
* At EOF, write the rest of the buffer.
fwrite( buf
, 1, (offset
+ 7) / 8, stdout
);
bytes_out
+= (offset
+ 7) / 8;
* Decompress stdin to stdout. This routine adapts to the codes in the
* file building the "string" table on-the-fly; requiring no table to
* be stored in the compressed file. The tables used herein are shared
* with those of the compress() routine. See the definitions above.
register char_type
*stackp
;
register code_int code
, oldcode
, incode
;
* As above, initialize the first 256 entries in the table.
maxcode
= MAXCODE(n_bits
= INIT_BITS
);
for ( code
= 255; code
>= 0; code
-- ) {
tab_suffixof(code
) = (char_type
)code
;
free_ent
= ((block_compress
) ? FIRST
: 256 );
finchar
= oldcode
= getcode();
if(oldcode
== -1) /* EOF already? */
return; /* Get out of here */
putchar( (char)finchar
); /* first code must be 8 bits = char */
if(ferror(stdout
)) /* Crash if can't write */
while ( (code
= getcode()) > -1 ) {
if ( (code
== CLEAR
) && block_compress
) {
for ( code
= 255; code
>= 0; code
-- )
if ( (code
= getcode ()) == -1 ) /* O, untimely death! */
* Special case for KwKwK string.
if ( code
>= free_ent
) {
* Generate output characters in reverse order
#ifdef SIGNED_COMPARE_SLOW
while ( ((unsigned long)code
) >= ((unsigned long)256) ) {
*stackp
++ = tab_suffixof(code
);
code
= tab_prefixof(code
);
*stackp
++ = finchar
= tab_suffixof(code
);
* And put them out in forward order
while ( stackp
> de_stack
);
* Generate the new entry.
if ( (code
=free_ent
) < maxmaxcode
) {
tab_prefixof(code
) = (unsigned short)oldcode
;
tab_suffixof(code
) = finchar
;
* Remember previous code.
/*****************************************************************
* Read one code from the standard input. If EOF, return -1.
* code or -1 is returned.
* On the VAX, it is important to have the register declarations
* in exactly the order given, or the asm will break.
static int offset
= 0, size
= 0;
static char_type buf
[BITS
];
register int r_off
, bits
;
register char_type
*bp
= buf
;
if ( clear_flg
> 0 || offset
>= size
|| free_ent
> maxcode
) {
* If the next entry will be too big for the current code
* size, then we must increase the size. This implies reading
* a new buffer full, too.
if ( free_ent
> maxcode
) {
maxcode
= maxmaxcode
; /* won't get any bigger now */
maxcode
= MAXCODE(n_bits
);
maxcode
= MAXCODE (n_bits
= INIT_BITS
);
size
= fread( buf
, 1, n_bits
, stdin
);
return -1; /* end of file */
/* Round size down to integral number of codes */
size
= (size
<< 3) - (n_bits
- 1);
asm( "extzv r10,r9,(r8),r11" );
/* Get first part (low order bits) */
code
= ((*bp
++ >> r_off
) & rmask
[8 - r_off
]) & 0xff;
r_off
= 8 - r_off
; /* now, offset into code word */
/* Get any 8 bit parts in the middle (<=1 for up to 16 bits). */
code
|= (*bp
++ & 0xff) << r_off
;
code
|= (*bp
& rmask
[bits
]) << r_off
;
rindex(s
, c
) /* For those who don't have it in libc.a */
* Just print out codes from input file. For debugging.
bits
= n_bits
= INIT_BITS
;
maxcode
= MAXCODE(n_bits
);
free_ent
= ((block_compress
) ? FIRST
: 256 );
while ( ( code
= getcode() ) >= 0 ) {
if ( (code
== CLEAR
) && block_compress
) {
else if ( free_ent
< maxmaxcode
)
fprintf(stderr
, "\nChange to %d bits\n", n_bits
);
fprintf(stderr
, "%5d%c", code
, (col
+=6) >= 74 ? (col
= 0, '\n') : ' ' );
code_int sorttab
[1<<BITS
]; /* sorted pointers into htab */
dump_tab() /* dump string table */
int stack_top
= STACK_SIZE
;
if(do_decomp
== 0) { /* compressing */
for(i
=0; i
<hsize
; i
++) { /* build sort pointers */
if((long)htabof(i
) >= 0) {
sorttab
[codetabof(i
)] = i
;
first
= block_compress
? FIRST
: 256;
for(i
= first
; i
< free_ent
; i
++) {
fprintf(stderr
, "%5d: \"", i
);
de_stack
[--stack_top
] = '\n';
de_stack
[--stack_top
] = '"';
stack_top
= in_stack((htabof(sorttab
[i
])>>maxbits
)&0xff,
for(ent
=htabof(sorttab
[i
]) & ((1<<maxbits
)-1);
ent
=htabof(sorttab
[ent
]) & ((1<<maxbits
)-1)) {
stack_top
= in_stack(htabof(sorttab
[ent
]) >> maxbits
,
stack_top
= in_stack(ent
, stack_top
);
fwrite( &de_stack
[stack_top
], 1, STACK_SIZE
-stack_top
, stderr
);
} else if(!debug
) { /* decompressing */
for ( i
= 0; i
< free_ent
; i
++ ) {
if ( isascii(c
) && isprint(c
) )
fprintf( stderr
, "%5d: %5d/'%c' \"",
ent
, tab_prefixof(ent
), c
);
fprintf( stderr
, "%5d: %5d/\\%03o \"",
ent
, tab_prefixof(ent
), c
);
de_stack
[--stack_top
] = '\n';
de_stack
[--stack_top
] = '"';
ent
= (ent
>= FIRST
? tab_prefixof(ent
) : NULL
) ) {
stack_top
= in_stack(tab_suffixof(ent
), stack_top
);
fwrite( &de_stack
[stack_top
], 1, STACK_SIZE
- stack_top
, stderr
);
if ( (isascii(c
) && isprint(c
) && c
!= '\\') || c
== ' ' ) {
de_stack
[--stack_top
] = c
;
case '\n': de_stack
[--stack_top
] = 'n'; break;
case '\t': de_stack
[--stack_top
] = 't'; break;
case '\b': de_stack
[--stack_top
] = 'b'; break;
case '\f': de_stack
[--stack_top
] = 'f'; break;
case '\r': de_stack
[--stack_top
] = 'r'; break;
case '\\': de_stack
[--stack_top
] = '\\'; break;
de_stack
[--stack_top
] = '0' + c
% 8;
de_stack
[--stack_top
] = '0' + (c
/ 8) % 8;
de_stack
[--stack_top
] = '0' + c
/ 64;
de_stack
[--stack_top
] = '\\';
if (stat(ifname
, &statbuf
)) { /* Get stat on input file */
if ((statbuf
.st_mode
& S_IFMT
/*0170000*/) != S_IFREG
/*0100000*/) {
fprintf(stderr
, "%s: ", ifname
);
fprintf(stderr
, " -- not a regular file: unchanged");
} else if (statbuf
.st_nlink
> 1) {
fprintf(stderr
, "%s: ", ifname
);
fprintf(stderr
, " -- has %d other links: unchanged",
} else if (exit_stat
== 2 && (!force
)) { /* No compression: remove file.Z */
fprintf(stderr
, " -- file unchanged");
} else { /* ***** Successful Compression ***** */
mode
= statbuf
.st_mode
& 07777;
if (chmod(ofname
, mode
)) /* Copy modes */
chown(ofname
, statbuf
.st_uid
, statbuf
.st_gid
); /* Copy ownership */
timep
[0] = statbuf
.st_atime
;
timep
[1] = statbuf
.st_mtime
;
utime(ofname
, timep
); /* Update last accessed and modified times */
if (unlink(ifname
)) /* Remove input file */
fprintf(stderr
, " -- replaced with %s", ofname
);
return; /* Successful return */
/* Unsuccessful return -- one of the tests failed */
oops ( ) /* wild pointer -- assume bad input */
fprintf ( stderr
, "uncompress: corrupt input\n" );
cl_block () /* table clear for block compress */
checkpoint
= in_count
+ CHECK_GAP
;
fprintf ( stderr
, "count: %ld, ratio: ", in_count
);
prratio ( stderr
, in_count
, bytes_out
);
if(in_count
> 0x007fffff) { /* shift will overflow */
if(rat
== 0) { /* Don't divide by zero */
rat
= (in_count
<< 8) / bytes_out
; /* 8 fractional bits */
dump_tab(); /* dump string table */
cl_hash ( (count_int
) hsize
);
output ( (code_int
) CLEAR
);
fprintf ( stderr
, "clear\n" );
cl_hash(hsize
) /* reset code table */
register count_int hsize
;
#ifndef XENIX_16 /* Normal machine */
register count_int
*htab_p
= htab
+hsize
;
register count_int
*htab_p
;
for(j
=0; j
<=8 && k
>=0; j
++,k
-=8192) {
do { /* might use Sys V memset(3) here */
} while ((i
-= 16) >= 0);
for ( i
+= 16; i
> 0; i
-- )
prratio(stream
, num
, den
)
register int q
; /* Doesn't need to be long */
if(num
> 214748L) { /* 2147483647/10000 */
q
= num
/ (den
/ 10000L);
q
= 10000L * num
/ den
; /* Long calculations, though */
fprintf(stream
, "%d.%02d%%", q
/ 100, q
% 100);
fprintf(stderr
, "%s, Berkeley 5.10 %G%\n", rcs_ident
);
fprintf(stderr
, "Options: ");
fprintf(stderr
, "vax, ");
fprintf(stderr
, "NO_UCHAR, ");
#ifdef SIGNED_COMPARE_SLOW
fprintf(stderr
, "SIGNED_COMPARE_SLOW, ");
fprintf(stderr
, "XENIX_16, ");
fprintf(stderr
, "COMPATIBLE, ");
fprintf(stderr
, "DEBUG, ");
fprintf(stderr
, "BSD4_2, ");
fprintf(stderr
, "BITS = %d\n", BITS
);