#include <stdarg.h>
|
#include <stdarg.h>
|
#include "support.h"
|
#include "support.h"
|
|
|
#define BYTES_TO_COMPRESS 1000
|
#define BYTES_TO_COMPRESS 1000
|
|
|
/*
|
/*
|
* Compress - data compression program
|
* Compress - data compression program
|
*/
|
*/
|
#define min(a,b) ((a>b) ? b : a)
|
#define min(a,b) ((a>b) ? b : a)
|
|
|
/*
|
/*
|
* machine variants which require cc -Dmachine: pdp11, z8000, pcxt
|
* machine variants which require cc -Dmachine: pdp11, z8000, pcxt
|
*/
|
*/
|
|
|
/*
|
/*
|
* Set USERMEM to the maximum amount of physical user memory available
|
* 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
|
* in bytes. USERMEM is used to determine the maximum BITS that can be used
|
* for compression.
|
* for compression.
|
*
|
*
|
* SACREDMEM is the amount of physical memory saved for others; compress
|
* SACREDMEM is the amount of physical memory saved for others; compress
|
* will hog the rest.
|
* will hog the rest.
|
*/
|
*/
|
#ifndef SACREDMEM
|
#ifndef SACREDMEM
|
#define SACREDMEM 0
|
#define SACREDMEM 0
|
#endif
|
#endif
|
|
|
/* #ifndef USERMEM */
|
/* #ifndef USERMEM */
|
#define USERMEM 60000 /* default user memory */
|
#define USERMEM 60000 /* default user memory */
|
/* #endif */
|
/* #endif */
|
|
|
#ifdef interdata /* (Perkin-Elmer) */
|
#ifdef interdata /* (Perkin-Elmer) */
|
#define SIGNED_COMPARE_SLOW /* signed compare is slower than unsigned */
|
#define SIGNED_COMPARE_SLOW /* signed compare is slower than unsigned */
|
#endif
|
#endif
|
|
|
#ifdef USERMEM
|
#ifdef USERMEM
|
# if USERMEM >= (433484+SACREDMEM)
|
# if USERMEM >= (433484+SACREDMEM)
|
# define PBITS 16
|
# define PBITS 16
|
# else
|
# else
|
# if USERMEM >= (229600+SACREDMEM)
|
# if USERMEM >= (229600+SACREDMEM)
|
# define PBITS 15
|
# define PBITS 15
|
# else
|
# else
|
# if USERMEM >= (127536+SACREDMEM)
|
# if USERMEM >= (127536+SACREDMEM)
|
# define PBITS 14
|
# define PBITS 14
|
# else
|
# else
|
# if USERMEM >= (73464+SACREDMEM)
|
# if USERMEM >= (73464+SACREDMEM)
|
# define PBITS 13
|
# define PBITS 13
|
# else
|
# else
|
# define PBITS 12
|
# define PBITS 12
|
# endif
|
# endif
|
# endif
|
# endif
|
# endif
|
# endif
|
# endif
|
# endif
|
# undef USERMEM
|
# undef USERMEM
|
#endif /* USERMEM */
|
#endif /* USERMEM */
|
|
|
#ifdef PBITS /* Preferred BITS for this memory size */
|
#ifdef PBITS /* Preferred BITS for this memory size */
|
# ifndef BITS
|
# ifndef BITS
|
# define BITS PBITS
|
# define BITS PBITS
|
# endif /* BITS */
|
# endif /* BITS */
|
#endif /* PBITS */
|
#endif /* PBITS */
|
|
|
#if BITS == 16
|
#if BITS == 16
|
# define HSIZE 69001 /* 95% occupancy */
|
# define HSIZE 69001 /* 95% occupancy */
|
#endif
|
#endif
|
#if BITS == 15
|
#if BITS == 15
|
# define HSIZE 35023 /* 94% occupancy */
|
# define HSIZE 35023 /* 94% occupancy */
|
#endif
|
#endif
|
#if BITS == 14
|
#if BITS == 14
|
# define HSIZE 18013 /* 91% occupancy */
|
# define HSIZE 18013 /* 91% occupancy */
|
#endif
|
#endif
|
#if BITS == 13
|
#if BITS == 13
|
# define HSIZE 9001 /* 91% occupancy */
|
# define HSIZE 9001 /* 91% occupancy */
|
#endif
|
#endif
|
#if BITS <= 12
|
#if BITS <= 12
|
# define HSIZE 5003 /* 80% occupancy */
|
# define HSIZE 5003 /* 80% occupancy */
|
#endif
|
#endif
|
|
|
/*
|
/*
|
* a code_int must be able to hold 2**BITS values of type int, and also -1
|
* a code_int must be able to hold 2**BITS values of type int, and also -1
|
*/
|
*/
|
#if BITS > 15
|
#if BITS > 15
|
typedef long int code_int;
|
typedef long int code_int;
|
#else
|
#else
|
typedef int code_int;
|
typedef int code_int;
|
#endif
|
#endif
|
|
|
#ifdef SIGNED_COMPARE_SLOW
|
#ifdef SIGNED_COMPARE_SLOW
|
typedef unsigned long int count_int;
|
typedef unsigned long int count_int;
|
typedef unsigned short int count_short;
|
typedef unsigned short int count_short;
|
#else
|
#else
|
typedef long int count_int;
|
typedef long int count_int;
|
#endif
|
#endif
|
|
|
#ifdef NO_UCHAR
|
#ifdef NO_UCHAR
|
typedef char char_type;
|
typedef char char_type;
|
#else
|
#else
|
typedef unsigned char char_type;
|
typedef unsigned char char_type;
|
#endif /* UCHAR */
|
#endif /* UCHAR */
|
char_type magic_header[] = { "\037\235" }; /* 1F 9D */
|
char_type magic_header[] = { "\037\235" }; /* 1F 9D */
|
|
|
/* Defines for third byte of header */
|
/* Defines for third byte of header */
|
#define BIT_MASK 0x1f
|
#define BIT_MASK 0x1f
|
#define BLOCK_MASK 0x80
|
#define BLOCK_MASK 0x80
|
/* Masks 0x40 and 0x20 are free. I think 0x20 should mean that there is
|
/* Masks 0x40 and 0x20 are free. I think 0x20 should mean that there is
|
a fourth header byte (for expansion).
|
a fourth header byte (for expansion).
|
*/
|
*/
|
#define INIT_BITS 9 /* initial number of bits/code */
|
#define INIT_BITS 9 /* initial number of bits/code */
|
|
|
/*
|
/*
|
* compress.c - File compression ala IEEE Computer, June 1984.
|
* compress.c - File compression ala IEEE Computer, June 1984.
|
*
|
*
|
* Authors: Spencer W. Thomas (decvax!harpo!utah-cs!utah-gr!thomas)
|
* Authors: Spencer W. Thomas (decvax!harpo!utah-cs!utah-gr!thomas)
|
* Jim McKie (decvax!mcvax!jim)
|
* Jim McKie (decvax!mcvax!jim)
|
* Steve Davies (decvax!vax135!petsd!peora!srd)
|
* Steve Davies (decvax!vax135!petsd!peora!srd)
|
* Ken Turkowski (decvax!decwrl!turtlevax!ken)
|
* Ken Turkowski (decvax!decwrl!turtlevax!ken)
|
* James A. Woods (decvax!ihnp4!ames!jaw)
|
* James A. Woods (decvax!ihnp4!ames!jaw)
|
* Joe Orost (decvax!vax135!petsd!joe)
|
* Joe Orost (decvax!vax135!petsd!joe)
|
*
|
*
|
*/
|
*/
|
|
|
#if i386
|
#if i386
|
#include <stdio.h>
|
#include <stdio.h>
|
#include <stdio.h>
|
#include <stdio.h>
|
#include <ctype.h>
|
#include <ctype.h>
|
#include <signal.h>
|
#include <signal.h>
|
#include <sys/types.h>
|
#include <sys/types.h>
|
#include <sys/stat.h>
|
#include <sys/stat.h>
|
#endif
|
#endif
|
|
|
#define ARGVAL() (*++(*argv) || (--argc && *++argv))
|
#define ARGVAL() (*++(*argv) || (--argc && *++argv))
|
|
|
int n_bits; /* number of bits/code */
|
int n_bits; /* number of bits/code */
|
int maxbits = BITS; /* user settable max # bits/code */
|
int maxbits = BITS; /* user settable max # bits/code */
|
code_int maxcode; /* maximum code, given n_bits */
|
code_int maxcode; /* maximum code, given n_bits */
|
code_int maxmaxcode = 1L << BITS; /* should NEVER generate this code */
|
code_int maxmaxcode = 1L << BITS; /* should NEVER generate this code */
|
#ifdef COMPATIBLE /* But wrong! */
|
#ifdef COMPATIBLE /* But wrong! */
|
# define MAXCODE(n_bits) (1L << (n_bits) - 1)
|
# define MAXCODE(n_bits) (1L << (n_bits) - 1)
|
#else
|
#else
|
# define MAXCODE(n_bits) ((1L << (n_bits)) - 1)
|
# define MAXCODE(n_bits) ((1L << (n_bits)) - 1)
|
#endif /* COMPATIBLE */
|
#endif /* COMPATIBLE */
|
|
|
# ifdef sel
|
# ifdef sel
|
/* support gould base register problems */
|
/* support gould base register problems */
|
/*NOBASE*/
|
/*NOBASE*/
|
count_int htab [HSIZE];
|
count_int htab [HSIZE];
|
unsigned short codetab [HSIZE];
|
unsigned short codetab [HSIZE];
|
/*NOBASE*/
|
/*NOBASE*/
|
# else /* !gould */
|
# else /* !gould */
|
count_int htab [HSIZE];
|
count_int htab [HSIZE];
|
unsigned short codetab [HSIZE];
|
unsigned short codetab [HSIZE];
|
# endif /* !gould */
|
# endif /* !gould */
|
#define htabof(i) htab[i]
|
#define htabof(i) htab[i]
|
#define codetabof(i) codetab[i]
|
#define codetabof(i) codetab[i]
|
code_int hsize = HSIZE; /* for dynamic table sizing */
|
code_int hsize = HSIZE; /* for dynamic table sizing */
|
count_int fsize;
|
count_int fsize;
|
|
|
/*
|
/*
|
* To save much memory, we overlay the table used by compress() with those
|
* 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
|
* 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
|
* 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
|
* 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
|
* of htab, and contains characters. There is plenty of room for any
|
* possible stack (stack used to be 8000 characters).
|
* possible stack (stack used to be 8000 characters).
|
*/
|
*/
|
|
|
#define tab_prefixof(i) codetabof(i)
|
#define tab_prefixof(i) codetabof(i)
|
#ifdef XENIX_16
|
#ifdef XENIX_16
|
# define tab_suffixof(i) ((char_type *)htab[(i)>>15])[(i) & 0x7fff]
|
# define tab_suffixof(i) ((char_type *)htab[(i)>>15])[(i) & 0x7fff]
|
# define de_stack ((char_type *)(htab2))
|
# define de_stack ((char_type *)(htab2))
|
#else /* Normal machine */
|
#else /* Normal machine */
|
# define tab_suffixof(i) ((char_type *)(htab))[i]
|
# define tab_suffixof(i) ((char_type *)(htab))[i]
|
# define de_stack ((char_type *)&tab_suffixof(1<<BITS))
|
# define de_stack ((char_type *)&tab_suffixof(1<<BITS))
|
#endif /* XENIX_16 */
|
#endif /* XENIX_16 */
|
|
|
code_int free_ent = 0; /* first unused entry */
|
code_int free_ent = 0; /* first unused entry */
|
int exit_stat = 0;
|
int exit_stat = 0;
|
|
|
code_int getcode();
|
code_int getcode();
|
|
|
int nomagic = 0; /* Use a 3-byte magic number header, unless old file */
|
int nomagic = 0; /* Use a 3-byte magic number header, unless old file */
|
int zcat_flg = 0; /* Write output on stdout, suppress messages */
|
int zcat_flg = 0; /* Write output on stdout, suppress messages */
|
int quiet = 1; /* don't tell me about compression */
|
int quiet = 1; /* don't tell me about compression */
|
|
|
/*
|
/*
|
* block compression parameters -- after all codes are used up,
|
* block compression parameters -- after all codes are used up,
|
* and compression rate changes, start over.
|
* and compression rate changes, start over.
|
*/
|
*/
|
int block_compress = BLOCK_MASK;
|
int block_compress = BLOCK_MASK;
|
int clear_flg = 0;
|
int clear_flg = 0;
|
long int ratio = 0;
|
long int ratio = 0;
|
#define CHECK_GAP 10000 /* ratio check interval */
|
#define CHECK_GAP 10000 /* ratio check interval */
|
count_int checkpoint = CHECK_GAP;
|
count_int checkpoint = CHECK_GAP;
|
/*
|
/*
|
* the next two codes should not be changed lightly, as they must not
|
* the next two codes should not be changed lightly, as they must not
|
* lie within the contiguous general code space.
|
* lie within the contiguous general code space.
|
*/
|
*/
|
#define FIRST 257 /* first free entry */
|
#define FIRST 257 /* first free entry */
|
#define CLEAR 256 /* table clear output code */
|
#define CLEAR 256 /* table clear output code */
|
|
|
int force = 0;
|
int force = 0;
|
char ofname [100];
|
char ofname [100];
|
int (*bgnd_flag)();
|
int (*bgnd_flag)();
|
|
|
/* reset code table */
|
/* reset code table */
|
void cl_hash(register count_int hsize);
|
void cl_hash(register count_int hsize);
|
/* table clear for block compress */
|
/* table clear for block compress */
|
void cl_block ();
|
void cl_block ();
|
void output(code_int code);
|
void output(code_int code);
|
|
|
|
|
int do_decomp = 0;
|
int do_decomp = 0;
|
|
|
static int offset;
|
static int offset;
|
long int in_count = 1; /* length of input */
|
long int in_count = 1; /* length of input */
|
long int bytes_out; /* length of compressed output */
|
long int bytes_out; /* length of compressed output */
|
long int out_count = 0; /* # of codes output (for debugging) */
|
long int out_count = 0; /* # of codes output (for debugging) */
|
|
|
/*
|
/*
|
* compress stdin to stdout
|
* compress stdin to stdout
|
*
|
*
|
* Algorithm: use open addressing double hashing (no chaining) on the
|
* Algorithm: use open addressing double hashing (no chaining) on the
|
* prefix code / next character combination. We do a variant of Knuth's
|
* 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
|
* 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
|
* secondary probe. Here, the modular division first probe is gives way
|
* to a faster exclusive-or manipulation. Also do block compression with
|
* to a faster exclusive-or manipulation. Also do block compression with
|
* an adaptive reset, whereby the code table is cleared when the compression
|
* an adaptive reset, whereby the code table is cleared when the compression
|
* ratio decreases, but after the table fills. The variable-length output
|
* 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
|
* codes are re-sized at this point, and a special CLEAR code is generated
|
* for the decompressor. Late addition: construct the table according to
|
* for the decompressor. Late addition: construct the table according to
|
* file size for noticeable speed improvement on small files. Please direct
|
* file size for noticeable speed improvement on small files. Please direct
|
* questions about this implementation to ames!jaw.
|
* questions about this implementation to ames!jaw.
|
*/
|
*/
|
|
|
int main() {
|
int main() {
|
register long fcode;
|
register long fcode;
|
register code_int i = 0;
|
register code_int i = 0;
|
register int c;
|
register int c;
|
register code_int ent;
|
register code_int ent;
|
#ifdef XENIX_16
|
#ifdef XENIX_16
|
register code_int disp;
|
register code_int disp;
|
#else /* Normal machine */
|
#else /* Normal machine */
|
register int disp;
|
register int disp;
|
#endif
|
#endif
|
register code_int hsize_reg;
|
register code_int hsize_reg;
|
register int hshift;
|
register int hshift;
|
|
|
#ifndef COMPATIBLE
|
#ifndef COMPATIBLE
|
if (nomagic == 0) {
|
if (nomagic == 0) {
|
/* putchar(magic_header[0]); putchar(magic_header[1]);
|
/* putchar(magic_header[0]); putchar(magic_header[1]);
|
putchar((char)(maxbits | block_compress)); */
|
putchar((char)(maxbits | block_compress)); */
|
}
|
}
|
#endif /* COMPATIBLE */
|
#endif /* COMPATIBLE */
|
|
|
offset = 0;
|
offset = 0;
|
bytes_out = 3; /* includes 3-byte header mojo */
|
bytes_out = 3; /* includes 3-byte header mojo */
|
out_count = 0;
|
out_count = 0;
|
clear_flg = 0;
|
clear_flg = 0;
|
ratio = 0;
|
ratio = 0;
|
in_count = 1;
|
in_count = 1;
|
|
|
printf("main: bytes_out %d... hsize %d\n", (int)bytes_out, (int)hsize);
|
printf("main: bytes_out %d... hsize %d\n", (int)bytes_out, (int)hsize);
|
|
|
checkpoint = CHECK_GAP;
|
checkpoint = CHECK_GAP;
|
maxcode = MAXCODE(n_bits = INIT_BITS);
|
maxcode = MAXCODE(n_bits = INIT_BITS);
|
free_ent = ((block_compress) ? FIRST : 256 );
|
free_ent = ((block_compress) ? FIRST : 256 );
|
|
|
|
|
ent = '\0'; /* getchar (); */
|
ent = '\0'; /* getchar (); */
|
|
|
hshift = 0;
|
hshift = 0;
|
for ( fcode = (long) hsize; fcode < 65536L; fcode *= 2L )
|
for ( fcode = (long) hsize; fcode < 65536L; fcode *= 2L )
|
hshift++;
|
hshift++;
|
hshift = 8 - hshift; /* set hash code range bound */
|
hshift = 8 - hshift; /* set hash code range bound */
|
printf("main: hshift %d...\n", hshift);
|
printf("main: hshift %d...\n", hshift);
|
|
|
hsize_reg = hsize;
|
hsize_reg = hsize;
|
cl_hash( (count_int) hsize_reg); /* clear hash table */
|
cl_hash( (count_int) hsize_reg); /* clear hash table */
|
|
|
/*#ifdef SIGNED_COMPARE_SLOW
|
/*#ifdef SIGNED_COMPARE_SLOW
|
while ( (c = getchar()) != (unsigned) EOF ) {
|
while ( (c = getchar()) != (unsigned) EOF ) {
|
#else
|
#else
|
while ( (c = getchar()) != EOF ) {
|
while ( (c = getchar()) != EOF ) {
|
#endif*/
|
#endif*/
|
printf("main: bytes_out %d...\n", (int)bytes_out);
|
printf("main: bytes_out %d...\n", (int)bytes_out);
|
printf("main: hsize_reg %d...\n", (int)hsize_reg);
|
printf("main: hsize_reg %d...\n", (int)hsize_reg);
|
printf("main: before compress %d...\n", (int)in_count);
|
printf("main: before compress %d...\n", (int)in_count);
|
while (in_count < BYTES_TO_COMPRESS) {
|
while (in_count < BYTES_TO_COMPRESS) {
|
c = in_count % 255;
|
c = in_count % 255;
|
|
|
printf("main: compressing %d...\n", (int)in_count);
|
printf("main: compressing %d...\n", (int)in_count);
|
in_count++;
|
in_count++;
|
fcode = (long) (((long) c << maxbits) + ent);
|
fcode = (long) (((long) c << maxbits) + ent);
|
i = (((long)c << hshift) ^ ent); /* xor hashing */
|
i = (((long)c << hshift) ^ ent); /* xor hashing */
|
|
|
if ( htabof (i) == fcode ) {
|
if ( htabof (i) == fcode ) {
|
ent = codetabof (i);
|
ent = codetabof (i);
|
continue;
|
continue;
|
} else if ( (long)htabof (i) < 0 ) /* empty slot */
|
} else if ( (long)htabof (i) < 0 ) /* empty slot */
|
goto nomatch;
|
goto nomatch;
|
|
|
disp = hsize_reg - i; /* secondary hash (after G. Knott) */
|
disp = hsize_reg - i; /* secondary hash (after G. Knott) */
|
if ( i == 0 )
|
if ( i == 0 )
|
disp = 1;
|
disp = 1;
|
probe:
|
probe:
|
if ( (i -= disp) < 0 )
|
if ( (i -= disp) < 0 )
|
i += hsize_reg;
|
i += hsize_reg;
|
|
|
if ( htabof (i) == fcode ) {
|
if ( htabof (i) == fcode ) {
|
ent = codetabof (i);
|
ent = codetabof (i);
|
continue;
|
continue;
|
}
|
}
|
if ( (long)htabof (i) > 0 )
|
if ( (long)htabof (i) > 0 )
|
goto probe;
|
goto probe;
|
nomatch:
|
nomatch:
|
output ( (code_int) ent );
|
output ( (code_int) ent );
|
out_count++;
|
out_count++;
|
ent = c;
|
ent = c;
|
#ifdef SIGNED_COMPARE_SLOW
|
#ifdef SIGNED_COMPARE_SLOW
|
if ( (unsigned) free_ent < (unsigned) maxmaxcode) {
|
if ( (unsigned) free_ent < (unsigned) maxmaxcode) {
|
#else
|
#else
|
if ( free_ent < maxmaxcode ) {
|
if ( free_ent < maxmaxcode ) {
|
#endif
|
#endif
|
codetabof (i) = free_ent++; /* code -> hashtable */
|
codetabof (i) = free_ent++; /* code -> hashtable */
|
htabof (i) = fcode;
|
htabof (i) = fcode;
|
}
|
}
|
else if ( (count_int)in_count >= checkpoint && block_compress )
|
else if ( (count_int)in_count >= checkpoint && block_compress )
|
cl_block ();
|
cl_block ();
|
}
|
}
|
/*
|
/*
|
* Put out the final code.
|
* Put out the final code.
|
*/
|
*/
|
printf("main: output...\n");
|
printf("main: output...\n");
|
output( (code_int)ent );
|
output( (code_int)ent );
|
out_count++;
|
out_count++;
|
output( (code_int)-1 );
|
output( (code_int)-1 );
|
|
|
if(bytes_out > in_count) /* exit(2) if no savings */
|
if(bytes_out > in_count) /* exit(2) if no savings */
|
exit_stat = 2;
|
exit_stat = 2;
|
printf("main: end...\n");
|
printf("main: end...\n");
|
report (0xdeaddead);
|
report (0xdeaddead);
|
return 0;
|
return 0;
|
}
|
}
|
|
|
/*****************************************************************
|
/*****************************************************************
|
* TAG( output )
|
* TAG( output )
|
*
|
*
|
* Output the given code.
|
* Output the given code.
|
* Inputs:
|
* Inputs:
|
* code: A n_bits-bit integer. If == -1, then EOF. This assumes
|
* code: A n_bits-bit integer. If == -1, then EOF. This assumes
|
* that n_bits =< (long)wordsize - 1.
|
* that n_bits =< (long)wordsize - 1.
|
* Outputs:
|
* Outputs:
|
* Outputs code to the file.
|
* Outputs code to the file.
|
* Assumptions:
|
* Assumptions:
|
* Chars are 8 bits long.
|
* Chars are 8 bits long.
|
* Algorithm:
|
* Algorithm:
|
* Maintain a BITS character long buffer (so that 8 codes will
|
* Maintain a BITS character long buffer (so that 8 codes will
|
* fit in it exactly). Use the VAX insv instruction to insert each
|
* 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.
|
* code in turn. When the buffer fills up empty it and start over.
|
*/
|
*/
|
|
|
static char buf[BITS];
|
static char buf[BITS];
|
|
|
#ifndef vax
|
#ifndef vax
|
char_type lmask[9] = {0xff, 0xfe, 0xfc, 0xf8, 0xf0, 0xe0, 0xc0, 0x80, 0x00};
|
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};
|
char_type rmask[9] = {0x00, 0x01, 0x03, 0x07, 0x0f, 0x1f, 0x3f, 0x7f, 0xff};
|
#endif /* vax */
|
#endif /* vax */
|
|
|
void output( code )
|
void output( code )
|
code_int code;
|
code_int code;
|
{
|
{
|
|
|
/*
|
/*
|
* On the VAX, it is important to have the register declarations
|
* On the VAX, it is important to have the register declarations
|
* in exactly the order given, or the asm will break.
|
* in exactly the order given, or the asm will break.
|
*/
|
*/
|
register int r_off = offset, bits= n_bits;
|
register int r_off = offset, bits= n_bits;
|
register char * bp = buf;
|
register char * bp = buf;
|
|
|
if ( code >= 0 ) {
|
if ( code >= 0 ) {
|
#ifdef vax
|
#ifdef vax
|
/* VAX DEPENDENT!! Implementation on other machines is below.
|
/* VAX DEPENDENT!! Implementation on other machines is below.
|
*
|
*
|
* Translation: Insert BITS bits from the argument starting at
|
* Translation: Insert BITS bits from the argument starting at
|
* offset bits from the beginning of buf.
|
* offset bits from the beginning of buf.
|
*/
|
*/
|
0; /* Work around for pcc -O bug with asm and if stmt */
|
0; /* Work around for pcc -O bug with asm and if stmt */
|
asm( "insv 4(ap),r11,r10,(r9)" );
|
asm( "insv 4(ap),r11,r10,(r9)" );
|
#else /* not a vax */
|
#else /* not a vax */
|
/*
|
/*
|
* byte/bit numbering on the VAX is simulated by the following code
|
* byte/bit numbering on the VAX is simulated by the following code
|
*/
|
*/
|
/*
|
/*
|
* Get to the first byte.
|
* Get to the first byte.
|
*/
|
*/
|
bp += (r_off >> 3);
|
bp += (r_off >> 3);
|
r_off &= 7;
|
r_off &= 7;
|
/*
|
/*
|
* Since code is always >= 8 bits, only need to mask the first
|
* Since code is always >= 8 bits, only need to mask the first
|
* hunk on the left.
|
* hunk on the left.
|
*/
|
*/
|
*bp = (*bp & rmask[r_off]) | ((code << r_off) & lmask[r_off]);
|
*bp = (*bp & rmask[r_off]) | ((code << r_off) & lmask[r_off]);
|
bp++;
|
bp++;
|
bits -= (8 - r_off);
|
bits -= (8 - r_off);
|
code >>= 8 - r_off;
|
code >>= 8 - r_off;
|
/* Get any 8 bit parts in the middle (<=1 for up to 16 bits). */
|
/* Get any 8 bit parts in the middle (<=1 for up to 16 bits). */
|
if ( bits >= 8 ) {
|
if ( bits >= 8 ) {
|
*bp++ = code;
|
*bp++ = code;
|
code >>= 8;
|
code >>= 8;
|
bits -= 8;
|
bits -= 8;
|
}
|
}
|
/* Last bits. */
|
/* Last bits. */
|
if(bits)
|
if(bits)
|
*bp = code;
|
*bp = code;
|
#endif /* vax */
|
#endif /* vax */
|
offset += n_bits;
|
offset += n_bits;
|
if ( offset == (n_bits << 3) ) {
|
if ( offset == (n_bits << 3) ) {
|
bp = buf;
|
bp = buf;
|
bits = n_bits;
|
bits = n_bits;
|
bytes_out += bits;
|
bytes_out += bits;
|
/* do
|
/* do
|
putchar(*bp++); */
|
putchar(*bp++); */
|
while(--bits);
|
while(--bits);
|
offset = 0;
|
offset = 0;
|
}
|
}
|
|
|
/*
|
/*
|
* If the next entry is going to be too big for the code size,
|
* If the next entry is going to be too big for the code size,
|
* then increase it, if possible.
|
* then increase it, if possible.
|
*/
|
*/
|
if ( free_ent > maxcode || (clear_flg > 0))
|
if ( free_ent > maxcode || (clear_flg > 0))
|
{
|
{
|
/*
|
/*
|
* Write the whole buffer, because the input side won't
|
* Write the whole buffer, because the input side won't
|
* discover the size increase until after it has read it.
|
* discover the size increase until after it has read it.
|
*/
|
*/
|
if ( offset > 0 ) {
|
if ( offset > 0 ) {
|
/* if( fwrite( buf, 1, n_bits, stdout ) != n_bits)
|
/* if( fwrite( buf, 1, n_bits, stdout ) != n_bits)
|
writeerr(); */
|
writeerr(); */
|
bytes_out += n_bits;
|
bytes_out += n_bits;
|
}
|
}
|
offset = 0;
|
offset = 0;
|
|
|
if ( clear_flg ) {
|
if ( clear_flg ) {
|
maxcode = MAXCODE (n_bits = INIT_BITS);
|
maxcode = MAXCODE (n_bits = INIT_BITS);
|
clear_flg = 0;
|
clear_flg = 0;
|
}
|
}
|
else {
|
else {
|
n_bits++;
|
n_bits++;
|
if ( n_bits == maxbits )
|
if ( n_bits == maxbits )
|
maxcode = maxmaxcode;
|
maxcode = maxmaxcode;
|
else
|
else
|
maxcode = MAXCODE(n_bits);
|
maxcode = MAXCODE(n_bits);
|
}
|
}
|
}
|
}
|
} else {
|
} else {
|
/*
|
/*
|
* At EOF, write the rest of the buffer.
|
* At EOF, write the rest of the buffer.
|
*/
|
*/
|
/* if ( offset > 0 )
|
/* if ( offset > 0 )
|
fwrite( buf, 1, (offset + 7) / 8, stdout ); */
|
fwrite( buf, 1, (offset + 7) / 8, stdout ); */
|
bytes_out += (offset + 7) / 8;
|
bytes_out += (offset + 7) / 8;
|
offset = 0;
|
offset = 0;
|
/* fflush( stdout ); */
|
/* fflush( stdout ); */
|
/* if( ferror( stdout ) )
|
/* if( ferror( stdout ) )
|
writeerr(); */
|
writeerr(); */
|
}
|
}
|
}
|
}
|
|
|
/*
|
/*
|
* Decompress stdin to stdout. This routine adapts to the codes in the
|
* Decompress stdin to stdout. This routine adapts to the codes in the
|
* file building the "string" table on-the-fly; requiring no table to
|
* file building the "string" table on-the-fly; requiring no table to
|
* be stored in the compressed file. The tables used herein are shared
|
* be stored in the compressed file. The tables used herein are shared
|
* with those of the compress() routine. See the definitions above.
|
* with those of the compress() routine. See the definitions above.
|
*/
|
*/
|
|
|
void decompress() {
|
void decompress() {
|
register char_type *stackp;
|
register char_type *stackp;
|
register int finchar;
|
register int finchar;
|
register code_int code, oldcode, incode;
|
register code_int code, oldcode, incode;
|
|
|
/*
|
/*
|
* As above, initialize the first 256 entries in the table.
|
* As above, initialize the first 256 entries in the table.
|
*/
|
*/
|
maxcode = MAXCODE(n_bits = INIT_BITS);
|
maxcode = MAXCODE(n_bits = INIT_BITS);
|
for ( code = 255; code >= 0; code-- ) {
|
for ( code = 255; code >= 0; code-- ) {
|
tab_prefixof(code) = 0;
|
tab_prefixof(code) = 0;
|
tab_suffixof(code) = (char_type)code;
|
tab_suffixof(code) = (char_type)code;
|
}
|
}
|
free_ent = ((block_compress) ? FIRST : 256 );
|
free_ent = ((block_compress) ? FIRST : 256 );
|
|
|
finchar = oldcode = getcode();
|
finchar = oldcode = getcode();
|
if(oldcode == -1) /* EOF already? */
|
if(oldcode == -1) /* EOF already? */
|
return; /* Get out of here */
|
return; /* Get out of here */
|
/* putchar( (char)finchar ); */ /* first code must be 8 bits = char */
|
/* putchar( (char)finchar ); */ /* first code must be 8 bits = char */
|
/* if(ferror(stdout))
|
/* if(ferror(stdout))
|
writeerr(); */
|
writeerr(); */
|
stackp = de_stack;
|
stackp = de_stack;
|
|
|
while ( (code = getcode()) > -1 ) {
|
while ( (code = getcode()) > -1 ) {
|
|
|
if ( (code == CLEAR) && block_compress ) {
|
if ( (code == CLEAR) && block_compress ) {
|
for ( code = 255; code >= 0; code-- )
|
for ( code = 255; code >= 0; code-- )
|
tab_prefixof(code) = 0;
|
tab_prefixof(code) = 0;
|
clear_flg = 1;
|
clear_flg = 1;
|
free_ent = FIRST - 1;
|
free_ent = FIRST - 1;
|
if ( (code = getcode ()) == -1 ) /* O, untimely death! */
|
if ( (code = getcode ()) == -1 ) /* O, untimely death! */
|
break;
|
break;
|
}
|
}
|
incode = code;
|
incode = code;
|
/*
|
/*
|
* Special case for KwKwK string.
|
* Special case for KwKwK string.
|
*/
|
*/
|
if ( code >= free_ent ) {
|
if ( code >= free_ent ) {
|
*stackp++ = finchar;
|
*stackp++ = finchar;
|
code = oldcode;
|
code = oldcode;
|
}
|
}
|
|
|
/*
|
/*
|
* Generate output characters in reverse order
|
* Generate output characters in reverse order
|
*/
|
*/
|
#ifdef SIGNED_COMPARE_SLOW
|
#ifdef SIGNED_COMPARE_SLOW
|
while ( ((unsigned long)code) >= ((unsigned long)256) ) {
|
while ( ((unsigned long)code) >= ((unsigned long)256) ) {
|
#else
|
#else
|
while ( code >= 256 ) {
|
while ( code >= 256 ) {
|
#endif
|
#endif
|
*stackp++ = tab_suffixof(code);
|
*stackp++ = tab_suffixof(code);
|
code = tab_prefixof(code);
|
code = tab_prefixof(code);
|
}
|
}
|
*stackp++ = finchar = tab_suffixof(code);
|
*stackp++ = finchar = tab_suffixof(code);
|
|
|
/*
|
/*
|
* And put them out in forward order
|
* And put them out in forward order
|
*/
|
*/
|
/* do
|
/* do
|
putchar ( *--stackp );
|
putchar ( *--stackp );
|
while ( stackp > de_stack );*/
|
while ( stackp > de_stack );*/
|
|
|
/*
|
/*
|
* Generate the new entry.
|
* Generate the new entry.
|
*/
|
*/
|
if ( (code=free_ent) < maxmaxcode ) {
|
if ( (code=free_ent) < maxmaxcode ) {
|
tab_prefixof(code) = (unsigned short)oldcode;
|
tab_prefixof(code) = (unsigned short)oldcode;
|
tab_suffixof(code) = finchar;
|
tab_suffixof(code) = finchar;
|
free_ent = code+1;
|
free_ent = code+1;
|
}
|
}
|
/*
|
/*
|
* Remember previous code.
|
* Remember previous code.
|
*/
|
*/
|
oldcode = incode;
|
oldcode = incode;
|
}
|
}
|
/* fflush( stdout ); */
|
/* fflush( stdout ); */
|
/* if(ferror(stdout))
|
/* if(ferror(stdout))
|
writeerr(); */
|
writeerr(); */
|
}
|
}
|
|
|
/*****************************************************************
|
/*****************************************************************
|
* TAG( getcode )
|
* TAG( getcode )
|
*
|
*
|
* Read one code from the standard input. If EOF, return -1.
|
* Read one code from the standard input. If EOF, return -1.
|
* Inputs:
|
* Inputs:
|
* stdin
|
* stdin
|
* Outputs:
|
* Outputs:
|
* code or -1 is returned.
|
* code or -1 is returned.
|
*/
|
*/
|
|
|
code_int
|
code_int
|
getcode() {
|
getcode() {
|
/*
|
/*
|
* On the VAX, it is important to have the register declarations
|
* On the VAX, it is important to have the register declarations
|
* in exactly the order given, or the asm will break.
|
* in exactly the order given, or the asm will break.
|
*/
|
*/
|
register code_int code;
|
register code_int code;
|
static int offset = 0, size = 0;
|
static int offset = 0, size = 0;
|
static char_type buf[BITS];
|
static char_type buf[BITS];
|
register int r_off, bits;
|
register int r_off, bits;
|
register char_type *bp = buf;
|
register char_type *bp = buf;
|
|
|
if ( clear_flg > 0 || offset >= size || free_ent > maxcode ) {
|
if ( clear_flg > 0 || offset >= size || free_ent > maxcode ) {
|
/*
|
/*
|
* If the next entry will be too big for the current code
|
* If the next entry will be too big for the current code
|
* size, then we must increase the size. This implies reading
|
* size, then we must increase the size. This implies reading
|
* a new buffer full, too.
|
* a new buffer full, too.
|
*/
|
*/
|
if ( free_ent > maxcode ) {
|
if ( free_ent > maxcode ) {
|
n_bits++;
|
n_bits++;
|
if ( n_bits == maxbits )
|
if ( n_bits == maxbits )
|
maxcode = maxmaxcode; /* won't get any bigger now */
|
maxcode = maxmaxcode; /* won't get any bigger now */
|
else
|
else
|
maxcode = MAXCODE(n_bits);
|
maxcode = MAXCODE(n_bits);
|
}
|
}
|
if ( clear_flg > 0) {
|
if ( clear_flg > 0) {
|
maxcode = MAXCODE (n_bits = INIT_BITS);
|
maxcode = MAXCODE (n_bits = INIT_BITS);
|
clear_flg = 0;
|
clear_flg = 0;
|
}
|
}
|
/* size = fread( buf, 1, n_bits, stdin ); */
|
/* size = fread( buf, 1, n_bits, stdin ); */
|
if ( size <= 0 )
|
if ( size <= 0 )
|
return -1; /* end of file */
|
return -1; /* end of file */
|
offset = 0;
|
offset = 0;
|
/* Round size down to integral number of codes */
|
/* Round size down to integral number of codes */
|
size = (size << 3) - (n_bits - 1);
|
size = (size << 3) - (n_bits - 1);
|
}
|
}
|
r_off = offset;
|
r_off = offset;
|
bits = n_bits;
|
bits = n_bits;
|
#ifdef vax
|
#ifdef vax
|
asm( "extzv r10,r9,(r8),r11" );
|
asm( "extzv r10,r9,(r8),r11" );
|
#else /* not a vax */
|
#else /* not a vax */
|
/*
|
/*
|
* Get to the first byte.
|
* Get to the first byte.
|
*/
|
*/
|
bp += (r_off >> 3);
|
bp += (r_off >> 3);
|
r_off &= 7;
|
r_off &= 7;
|
/* Get first part (low order bits) */
|
/* Get first part (low order bits) */
|
#ifdef NO_UCHAR
|
#ifdef NO_UCHAR
|
code = ((*bp++ >> r_off) & rmask[8 - r_off]) & 0xff;
|
code = ((*bp++ >> r_off) & rmask[8 - r_off]) & 0xff;
|
#else
|
#else
|
code = (*bp++ >> r_off);
|
code = (*bp++ >> r_off);
|
#endif /* NO_UCHAR */
|
#endif /* NO_UCHAR */
|
bits -= (8 - r_off);
|
bits -= (8 - r_off);
|
r_off = 8 - r_off; /* now, offset into code word */
|
r_off = 8 - r_off; /* now, offset into code word */
|
/* Get any 8 bit parts in the middle (<=1 for up to 16 bits). */
|
/* Get any 8 bit parts in the middle (<=1 for up to 16 bits). */
|
if ( bits >= 8 ) {
|
if ( bits >= 8 ) {
|
#ifdef NO_UCHAR
|
#ifdef NO_UCHAR
|
code |= (*bp++ & 0xff) << r_off;
|
code |= (*bp++ & 0xff) << r_off;
|
#else
|
#else
|
code |= *bp++ << r_off;
|
code |= *bp++ << r_off;
|
#endif /* NO_UCHAR */
|
#endif /* NO_UCHAR */
|
r_off += 8;
|
r_off += 8;
|
bits -= 8;
|
bits -= 8;
|
}
|
}
|
/* high order bits. */
|
/* high order bits. */
|
code |= (*bp & rmask[bits]) << r_off;
|
code |= (*bp & rmask[bits]) << r_off;
|
#endif /* vax */
|
#endif /* vax */
|
offset += n_bits;
|
offset += n_bits;
|
|
|
return code;
|
return code;
|
}
|
}
|
|
|
char *
|
char *
|
rindex(s, c) /* For those who don't have it in libc.a */
|
rindex(s, c) /* For those who don't have it in libc.a */
|
register char *s, c;
|
register char *s, c;
|
{
|
{
|
char *p;
|
char *p;
|
for (p = NULL; *s; s++)
|
for (p = NULL; *s; s++)
|
if (*s == c)
|
if (*s == c)
|
p = s;
|
p = s;
|
return(p);
|
return(p);
|
}
|
}
|
|
|
/*
|
/*
|
writeerr()
|
writeerr()
|
{
|
{
|
perror ( ofname );
|
perror ( ofname );
|
unlink ( ofname );
|
unlink ( ofname );
|
exit ( 1 );
|
exit ( 1 );
|
}
|
}
|
*/
|
*/
|
void cl_block () /* table clear for block compress */
|
void cl_block () /* table clear for block compress */
|
{
|
{
|
register long int rat;
|
register long int rat;
|
|
|
checkpoint = in_count + CHECK_GAP;
|
checkpoint = in_count + CHECK_GAP;
|
|
|
if(in_count > 0x007fffff) { /* shift will overflow */
|
if(in_count > 0x007fffff) { /* shift will overflow */
|
rat = bytes_out >> 8;
|
rat = bytes_out >> 8;
|
if(rat == 0) { /* Don't divide by zero */
|
if(rat == 0) { /* Don't divide by zero */
|
rat = 0x7fffffff;
|
rat = 0x7fffffff;
|
} else {
|
} else {
|
rat = in_count / rat;
|
rat = in_count / rat;
|
}
|
}
|
} else {
|
} else {
|
rat = (in_count << 8) / bytes_out; /* 8 fractional bits */
|
rat = (in_count << 8) / bytes_out; /* 8 fractional bits */
|
}
|
}
|
if ( rat > ratio ) {
|
if ( rat > ratio ) {
|
ratio = rat;
|
ratio = rat;
|
} else {
|
} else {
|
ratio = 0;
|
ratio = 0;
|
cl_hash ( (count_int) hsize );
|
cl_hash ( (count_int) hsize );
|
free_ent = FIRST;
|
free_ent = FIRST;
|
clear_flg = 1;
|
clear_flg = 1;
|
output ( (code_int) CLEAR );
|
output ( (code_int) CLEAR );
|
}
|
}
|
}
|
}
|
|
|
void cl_hash(hsize) /* reset code table */
|
void cl_hash(hsize) /* reset code table */
|
register count_int hsize;
|
register count_int hsize;
|
{
|
{
|
#ifndef XENIX_16 /* Normal machine */
|
#ifndef XENIX_16 /* Normal machine */
|
register count_int *htab_p = htab+hsize;
|
register count_int *htab_p = htab+hsize;
|
#else
|
#else
|
register j;
|
register j;
|
register long k = hsize;
|
register long k = hsize;
|
register count_int *htab_p;
|
register count_int *htab_p;
|
#endif
|
#endif
|
register long i;
|
register long i;
|
register long m1 = -1;
|
register long m1 = -1;
|
|
|
#ifdef XENIX_16
|
#ifdef XENIX_16
|
for(j=0; j<=8 && k>=0; j++,k-=8192) {
|
for(j=0; j<=8 && k>=0; j++,k-=8192) {
|
i = 8192;
|
i = 8192;
|
if(k < 8192) {
|
if(k < 8192) {
|
i = k;
|
i = k;
|
}
|
}
|
htab_p = &(htab[j][i]);
|
htab_p = &(htab[j][i]);
|
i -= 16;
|
i -= 16;
|
if(i > 0) {
|
if(i > 0) {
|
#else
|
#else
|
i = hsize - 16;
|
i = hsize - 16;
|
#endif
|
#endif
|
do { /* might use Sys V memset(3) here */
|
do { /* might use Sys V memset(3) here */
|
*(htab_p-16) = m1;
|
*(htab_p-16) = m1;
|
*(htab_p-15) = m1;
|
*(htab_p-15) = m1;
|
*(htab_p-14) = m1;
|
*(htab_p-14) = m1;
|
*(htab_p-13) = m1;
|
*(htab_p-13) = m1;
|
*(htab_p-12) = m1;
|
*(htab_p-12) = m1;
|
*(htab_p-11) = m1;
|
*(htab_p-11) = m1;
|
*(htab_p-10) = m1;
|
*(htab_p-10) = m1;
|
*(htab_p-9) = m1;
|
*(htab_p-9) = m1;
|
*(htab_p-8) = m1;
|
*(htab_p-8) = m1;
|
*(htab_p-7) = m1;
|
*(htab_p-7) = m1;
|
*(htab_p-6) = m1;
|
*(htab_p-6) = m1;
|
*(htab_p-5) = m1;
|
*(htab_p-5) = m1;
|
*(htab_p-4) = m1;
|
*(htab_p-4) = m1;
|
*(htab_p-3) = m1;
|
*(htab_p-3) = m1;
|
*(htab_p-2) = m1;
|
*(htab_p-2) = m1;
|
*(htab_p-1) = m1;
|
*(htab_p-1) = m1;
|
htab_p -= 16;
|
htab_p -= 16;
|
} while ((i -= 16) >= 0);
|
} while ((i -= 16) >= 0);
|
#ifdef XENIX_16
|
#ifdef XENIX_16
|
}
|
}
|
}
|
}
|
#endif
|
#endif
|
for ( i += 16; i > 0; i-- )
|
for ( i += 16; i > 0; i-- )
|
*--htab_p = m1;
|
*--htab_p = m1;
|
}
|
}
|
|
|
|
|