home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
PsL Monthly 1993 December
/
PSL Monthly Shareware CD-ROM (December 1993).iso
/
prgmming
/
dos
/
c
/
snippet.exe
/
LZHUF.C
< prev
next >
Wrap
C/C++ Source or Header
|
1990-05-04
|
19KB
|
647 lines
/**************************************************************
lzhuf.c
written by Haruyasu Yoshizaki 1988/11/20
some minor changes 1989/04/06
comments translated by Haruhiko Okumura 1989/04/07
getbit and getbyte modified 1990/03/23 by Paul Edwards
so that they would work on machines where integers are
not necessarily 16 bits (although ANSI guarantees a
minimum of 16). This program has compiled and run with
no errors under Turbo C 2.0, Power C, and SAS/C 4.5
(running on an IBM mainframe under MVS/XA 2.2). Could
people please use YYYY/MM/DD date format so that everyone
in the world can know what format the date is in?
external storage of filesize changed 1990/04/18 by Paul Edwards to
Intel's "little endian" rather than a machine-dependant style so
that files produced on one machine with lzhuf can be decoded on
any other. "little endian" style was chosen since lzhuf
originated on PC's, and therefore they should dictate the
standard.
initialization of something predicting spaces changed 1990/04/22 by
Paul Edwards so that when the compressed file is taken somewhere
else, it will decode properly, without changing ascii spaces to
ebcdic spaces. This was done by changing the ' ' (space literal)
to 0x20 (which is the far most likely character to occur, if you
don't know what environment it will be running on.
**************************************************************/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
FILE *infile, *outfile;
static unsigned long int textsize = 0, codesize = 0, printcount = 0;
char wterr[] = "Can't write.";
static void Error(char *message)
{
printf("\n%s\n", message);
exit(EXIT_FAILURE);
}
/********** LZSS compression **********/
#define N 4096 /* buffer size */
#define F 60 /* lookahead buffer size */
#define THRESHOLD 2
#define NIL N /* leaf of tree */
unsigned char
text_buf[N + F - 1];
static int match_position, match_length,
lson[N + 1], rson[N + 257], dad[N + 1];
static void InitTree(void) /* initialize trees */
{
int i;
for (i = N + 1; i <= N + 256; i++)
rson[i] = NIL; /* root */
for (i = 0; i < N; i++)
dad[i] = NIL; /* node */
}
static void InsertNode(int r) /* insert to tree */
{
int i, p, cmp;
unsigned char *key;
unsigned c;
cmp = 1;
key = &text_buf[r];
p = N + 1 + key[0];
rson[r] = lson[r] = NIL;
match_length = 0;
for ( ; ; ) {
if (cmp >= 0) {
if (rson[p] != NIL)
p = rson[p];
else {
rson[p] = r;
dad[r] = p;
return;
}
} else {
if (lson[p] != NIL)
p = lson[p];
else {
lson[p] = r;
dad[r] = p;
return;
}
}
for (i = 1; i < F; i++)
if ((cmp = key[i] - text_buf[p + i]) != 0)
break;
if (i > THRESHOLD) {
if (i > match_length) {
match_position = ((r - p) & (N - 1)) - 1;
if ((match_length = i) >= F)
break;
}
if (i == match_length) {
if ((c = ((r - p) & (N - 1)) - 1) < match_position) {
match_position = c;
}
}
}
}
dad[r] = dad[p];
lson[r] = lson[p];
rson[r] = rson[p];
dad[lson[p]] = r;
dad[rson[p]] = r;
if (rson[dad[p]] == p)
rson[dad[p]] = r;
else
lson[dad[p]] = r;
dad[p] = NIL; /* remove p */
}
static void DeleteNode(int p) /* remove from tree */
{
int q;
if (dad[p] == NIL)
return; /* not registered */
if (rson[p] == NIL)
q = lson[p];
else
if (lson[p] == NIL)
q = rson[p];
else {
q = lson[p];
if (rson[q] != NIL) {
do {
q = rson[q];
} while (rson[q] != NIL);
rson[dad[q]] = lson[q];
dad[lson[q]] = dad[q];
lson[q] = lson[p];
dad[lson[p]] = q;
}
rson[q] = rson[p];
dad[rson[p]] = q;
}
dad[q] = dad[p];
if (rson[dad[p]] == p)
rson[dad[p]] = q;
else
lson[dad[p]] = q;
dad[p] = NIL;
}
/* Huffman coding */
#define N_CHAR (256 - THRESHOLD + F)
/* kinds of characters (character code = 0..N_CHAR-1) */
#define T (N_CHAR * 2 - 1) /* size of table */
#define R (T - 1) /* position of root */
#define MAX_FREQ 0x8000 /* updates tree when the */
typedef unsigned char uchar;
/* table for encoding and decoding the upper 6 bits of position */
/* for encoding */
uchar p_len[64] = {
0x03, 0x04, 0x04, 0x04, 0x05, 0x05, 0x05, 0x05,
0x05, 0x05, 0x05, 0x05, 0x06, 0x06, 0x06, 0x06,
0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06,
0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07,
0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07,
0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08
};
uchar p_code[64] = {
0x00, 0x20, 0x30, 0x40, 0x50, 0x58, 0x60, 0x68,
0x70, 0x78, 0x80, 0x88, 0x90, 0x94, 0x98, 0x9C,
0xA0, 0xA4, 0xA8, 0xAC, 0xB0, 0xB4, 0xB8, 0xBC,
0xC0, 0xC2, 0xC4, 0xC6, 0xC8, 0xCA, 0xCC, 0xCE,
0xD0, 0xD2, 0xD4, 0xD6, 0xD8, 0xDA, 0xDC, 0xDE,
0xE0, 0xE2, 0xE4, 0xE6, 0xE8, 0xEA, 0xEC, 0xEE,
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF
};
/* for decoding */
uchar d_code[256] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02,
0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02,
0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03,
0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03,
0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04,
0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05, 0x05,
0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06, 0x06,
0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07,
0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08, 0x08,
0x09, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09, 0x09,
0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A, 0x0A,
0x0B, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B, 0x0B,
0x0C, 0x0C, 0x0C, 0x0C, 0x0D, 0x0D, 0x0D, 0x0D,
0x0E, 0x0E, 0x0E, 0x0E, 0x0F, 0x0F, 0x0F, 0x0F,
0x10, 0x10, 0x10, 0x10, 0x11, 0x11, 0x11, 0x11,
0x12, 0x12, 0x12, 0x12, 0x13, 0x13, 0x13, 0x13,
0x14, 0x14, 0x14, 0x14, 0x15, 0x15, 0x15, 0x15,
0x16, 0x16, 0x16, 0x16, 0x17, 0x17, 0x17, 0x17,
0x18, 0x18, 0x19, 0x19, 0x1A, 0x1A, 0x1B, 0x1B,
0x1C, 0x1C, 0x1D, 0x1D, 0x1E, 0x1E, 0x1F, 0x1F,
0x20, 0x20, 0x21, 0x21, 0x22, 0x22, 0x23, 0x23,
0x24, 0x24, 0x25, 0x25, 0x26, 0x26, 0x27, 0x27,
0x28, 0x28, 0x29, 0x29, 0x2A, 0x2A, 0x2B, 0x2B,
0x2C, 0x2C, 0x2D, 0x2D, 0x2E, 0x2E, 0x2F, 0x2F,
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
};
uchar d_len[256] = {
0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03,
0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03,
0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03,
0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03,
0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04,
0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04,
0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04,
0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04, 0x04,
0x04, 0x04, 0x04, 0x04,