compress.c

用c语言写的相当简单的文件压缩小程序非常适合初学者的使用

		if( fwrite( buf, 1, n_bits, stdout ) != n_bits)
			writeerr();
		bytes_out += n_bits;
	    }
	    offset = 0;

	    if ( clear_flg ) {
    	        maxcode = MAXCODE (n_bits = INIT_BITS);
	        clear_flg = 0;
	    }
	    else {
	    	n_bits++;
	    	if ( n_bits == maxbits )
		    maxcode = maxmaxcode;
	    	else
		    maxcode = MAXCODE(n_bits);
	    }
#ifdef DEBUG
	    if ( debug ) {
		fprintf( stderr, "\nChange to %d bits\n", n_bits );
		col = 0;
	    }
#endif /* DEBUG */
	}
    } else {
	/*
	 * At EOF, write the rest of the buffer.
	 */
	if ( offset > 0 )
	    fwrite( buf, 1, (offset + 7) / 8, stdout );
	bytes_out += (offset + 7) / 8;
	offset = 0;
	fflush( stdout );
#ifdef DEBUG
	if ( verbose )
	    fprintf( stderr, "\n" );
#endif /* DEBUG */
	if( ferror( stdout ) )
		writeerr();
    }
}

/*
 * 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.
 */

decompress() {
    register char_type *stackp;
    register int finchar;
    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_prefixof(code) = 0;
	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 */
	writeerr();
    stackp = de_stack;

    while ( (code = getcode()) > -1 ) {

	if ( (code == CLEAR) && block_compress ) {
	    for ( code = 255; code >= 0; code-- )
		tab_prefixof(code) = 0;
	    clear_flg = 1;
	    free_ent = FIRST - 1;
	    if ( (code = getcode ()) == -1 )	/* O, untimely death! */
		break;
	}
	incode = code;
	/*
	 * Special case for KwKwK string.
	 */
	if ( code >= free_ent ) {
            *stackp++ = finchar;
	    code = oldcode;
	}

	/*
	 * Generate output characters in reverse order
	 */
#ifdef SIGNED_COMPARE_SLOW
	while ( ((unsigned long)code) >= ((unsigned long)256) ) {
#else
	while ( code >= 256 ) {
#endif
	    *stackp++ = tab_suffixof(code);
	    code = tab_prefixof(code);
	}
	*stackp++ = finchar = tab_suffixof(code);

	/*
	 * And put them out in forward order
	 */
	do
	    putchar ( *--stackp );
	while ( stackp > de_stack );

	/*
	 * Generate the new entry.
	 */
	if ( (code=free_ent) < maxmaxcode ) {
	    tab_prefixof(code) = (unsigned short)oldcode;
	    tab_suffixof(code) = finchar;
	    free_ent = code+1;
	} 
	/*
	 * Remember previous code.
	 */
	oldcode = incode;
    }
    fflush( stdout );
    if(ferror(stdout))
	writeerr();
}

/*****************************************************************
 * TAG( getcode )
 *
 * Read one code from the standard input.  If EOF, return -1.
 * Inputs:
 * 	stdin
 * Outputs:
 * 	code or -1 is returned.
 */

code_int
getcode() {
    /*
     * On the VAX, it is important to have the register declarations
     * in exactly the order given, or the asm will break.
     */
    register code_int code;
    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 ) {
	    n_bits++;
	    if ( n_bits == maxbits )
		maxcode = maxmaxcode;	/* won't get any bigger now */
	    else
		maxcode = MAXCODE(n_bits);
	}
	if ( clear_flg > 0) {
    	    maxcode = MAXCODE (n_bits = INIT_BITS);
	    clear_flg = 0;
	}
	size = fread( buf, 1, n_bits, stdin );
	if ( size <= 0 )
	    return -1;			/* end of file */
	offset = 0;
	/* Round size down to integral number of codes */
	size = (size << 3) - (n_bits - 1);
    }
    r_off = offset;
    bits = n_bits;
#ifdef vax
    asm( "extzv   r10,r9,(r8),r11" );
#else /* not a vax */
	/*
	 * Get to the first byte.
	 */
	bp += (r_off >> 3);
	r_off &= 7;
	/* Get first part (low order bits) */
#ifdef NO_UCHAR
	code = ((*bp++ >> r_off) & rmask[8 - r_off]) & 0xff;
#else
	code = (*bp++ >> r_off);
#endif /* NO_UCHAR */
	bits -= (8 - r_off);
	r_off = 8 - r_off;		/* now, offset into code word */
	/* Get any 8 bit parts in the middle (<=1 for up to 16 bits). */
	if ( bits >= 8 ) {
#ifdef NO_UCHAR
	    code |= (*bp++ & 0xff) << r_off;
#else
	    code |= *bp++ << r_off;
#endif /* NO_UCHAR */
	    r_off += 8;
	    bits -= 8;
	}
	/* high order bits. */
	code |= (*bp & rmask[bits]) << r_off;
#endif /* vax */
    offset += n_bits;

    return code;
}

char *
rindex(s, c)		/* For those who don't have it in libc.a */
register char *s, c;
{
	char *p;
	for (p = NULL; *s; s++)
	    if (*s == c)
		p = s;
	return(p);
}

#ifdef DEBUG
printcodes()
{
    /*
     * Just print out codes from input file.  For debugging.
     */
    code_int code;
    int col = 0, bits;

    bits = n_bits = INIT_BITS;
    maxcode = MAXCODE(n_bits);
    free_ent = ((block_compress) ? FIRST : 256 );
    while ( ( code = getcode() ) >= 0 ) {
	if ( (code == CLEAR) && block_compress ) {
   	    free_ent = FIRST - 1;
   	    clear_flg = 1;
	}
	else if ( free_ent < maxmaxcode )
	    free_ent++;
	if ( bits != n_bits ) {
	    fprintf(stderr, "\nChange to %d bits\n", n_bits );
	    bits = n_bits;
	    col = 0;
	}
	fprintf(stderr, "%5d%c", code, (col+=6) >= 74 ? (col = 0, '\n') : ' ' );
    }
    putc( '\n', stderr );
    exit( 0 );
}

code_int sorttab[1<<BITS];	/* sorted pointers into htab */

dump_tab()	/* dump string table */
{
    register int i, first;
    register ent;
#define STACK_SIZE	15000
    int stack_top = STACK_SIZE;
    register c;

    if(do_decomp == 0) {	/* compressing */
	register int flag = 1;

	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, 
                                     stack_top);
		for(ent=htabof(sorttab[i]) & ((1<<maxbits)-1);
		    ent > 256;
		    ent=htabof(sorttab[ent]) & ((1<<maxbits)-1)) {
			stack_top = in_stack(htabof(sorttab[ent]) >> maxbits,
						stack_top);
		}
		stack_top = in_stack(ent, stack_top);
		fwrite( &de_stack[stack_top], 1, STACK_SIZE-stack_top, stderr);
	   	stack_top = STACK_SIZE;
	}
   } else if(!debug) {	/* decompressing */

       for ( i = 0; i < free_ent; i++ ) {
	   ent = i;
	   c = tab_suffixof(ent);
	   if ( isascii(c) && isprint(c) )
	       fprintf( stderr, "%5d: %5d/'%c'  \"",
			   ent, tab_prefixof(ent), c );
	   else
	       fprintf( stderr, "%5d: %5d/\\%03o \"",
			   ent, tab_prefixof(ent), c );
	   de_stack[--stack_top] = '\n';
	   de_stack[--stack_top] = '"';
	   for ( ; ent != NULL;
		   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 );
	   stack_top = STACK_SIZE;
       }
    }
}

int
in_stack(c, stack_top)
	register c, stack_top;
{
	if ( (isascii(c) && isprint(c) && c != '\\') || c == ' ' ) {
	    de_stack[--stack_top] = c;
	} else {
	    switch( 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;
	    default:
	 	de_stack[--stack_top] = '0' + c % 8;
	 	de_stack[--stack_top] = '0' + (c / 8) % 8;
	 	de_stack[--stack_top] = '0' + c / 64;
	 	break;
	    }
	    de_stack[--stack_top] = '\\';
	}
	return stack_top;
}
#endif /* DEBUG */

writeerr()
{
    perror ( ofname );
    if (valid)
	unlink ( ofname );
    exit ( 1 );
}

copystat(ifname, ofname)
char *ifname, *ofname;
{
    int mode;
    time_t timep[2];

    fclose(stdin);
    fclose(stdout);
    if (exit_stat == 2 && (!force)) { /* No compression: remove file.Z */
	if(!quiet)
		fprintf(stderr, "No compression -- %s unchanged",
			ifname);
    } else {			/* ***** Successful Compression ***** */
	exit_stat = 0;
	mode = insbuf.st_mode & 07777;
	if (chmod(ofname, mode))		/* Copy modes */
	    perror(ofname);
#ifndef OS2
	chown(ofname, insbuf.st_uid, insbuf.st_gid);	/* Copy ownership */
#endif
	timep[0] = insbuf.st_atime;
	timep[1] = insbuf.st_mtime;
	utime(ofname, timep);	/* Update last accessed and modified times */
	valid = 0;		/* prevent latent ofname removal */
	if (unlink(ifname))	/* Remove input file */
	    perror(ifname);
	if(!quiet)
		fprintf(stderr, " -- replaced with %s",ofname);
	return;		/* Successful return */
    }

    /* Unsuccessful return -- one of the tests failed */
    if (unlink(ofname))
	perror(ofname);
}
/*
 * This routine returns 1 if we are running in the foreground and stderr
 * is a tty.
 */
foreground()
{
	if(bgnd_flag) {	/* background? */
		return(0);
	} else {			/* foreground */
		if(isatty(2)) {		/* and stderr is a tty */
			return(1);
		} else {
			return(0);
		}
	}
}

SIGTYP onintr ( )
{
    if (valid)
	unlink ( ofname );
    exit ( 1 );
}

SIGTYP oops ( )	/* wild pointer -- assume bad input */
{
    if ( do_decomp == 1 ) 
    	fprintf ( stderr, "uncompress: corrupt input\n" );
    if (valid)
	unlink ( ofname );
    exit ( 1 );
}

cl_block ()		/* table clear for block compress */
{
    register long int rat;

    checkpoint = in_count + CHECK_GAP;
#ifdef DEBUG
	if ( debug ) {
    		fprintf ( stderr, "count: %ld, ratio: ", in_count );
     		prratio ( stderr, in_count, bytes_out );
		fprintf ( stderr, "\n");
	}
#endif /* DEBUG */

    if(in_count > 0x007fffff) {	/* shift will overflow */
	rat = bytes_out >> 8;
	if(rat == 0) {		/* Don't divide by zero */
	    rat = 0x7fffffff;
	} else {
	    rat = in_count / rat;
	}
    } else {
	rat = (in_count << 8) / bytes_out;	/* 8 fractional bits */
    }
    if ( rat > ratio ) {
	ratio = rat;
    } else {
	ratio = 0;
#ifdef DEBUG
	if(verbose)
		dump_tab();	/* dump string table */
#endif
 	cl_hash ( (count_int) hsize );
	free_ent = FIRST;
	clear_flg = 1;
	output ( (code_int) CLEAR );
#ifdef DEBUG
	if(debug)
    		fprintf ( stderr, "clear\n" );
#endif /* DEBUG */
    }
}

cl_hash(hsize)		/* reset code table */
	register count_int hsize;
{
#ifndef XENIX_16	/* Normal machine */
	register count_int *htab_p = htab+hsize;
#else
	register j;
	register long k = hsize;
	register count_int *htab_p;
#endif
	register long i;
	register long m1 = -1;

#ifdef XENIX_16
    for(j=0; j<=8 && k>=0; j++,k-=8192) {
	i = 8192;
	if(k < 8192) {
		i = k;
	}
	htab_p = &(htab[j][i]);
	i -= 16;
	if(i > 0) {
#else
	i = hsize - 16;
#endif
 	do {				/* might use Sys V memset(3) here */
		*(htab_p-16) = m1;
		*(htab_p-15) = m1;
		*(htab_p-14) = m1;
		*(htab_p-13) = m1;
		*(htab_p-12) = m1;
		*(htab_p-11) = m1;
		*(htab_p-10) = m1;
		*(htab_p-9) = m1;
		*(htab_p-8) = m1;
		*(htab_p-7) = m1;
		*(htab_p-6) = m1;
		*(htab_p-5) = m1;
		*(htab_p-4) = m1;
		*(htab_p-3) = m1;
		*(htab_p-2) = m1;
		*(htab_p-1) = m1;
		htab_p -= 16;
	} while ((i -= 16) >= 0);
#ifdef XENIX_16
	}
    }
#endif
    	for ( i += 16; i > 0; i-- )
		*--htab_p = m1;
}

prratio(stream, num, den)
FILE *stream;
long int num, den;
{
	register int q;			/* Doesn't need to be long */

	if(num > 214748L) {		/* 2147483647/10000 */
		q = num / (den / 10000L);
	} else {
		q = 10000L * num / den;		/* Long calculations, though */
	}
	if (q < 0) {
		putc('-', stream);
		q = -q;
	}
	fprintf(stream, "%d.%02d%%", q / 100, q % 100);
}

version()
{
	fprintf(stderr, "%s, patchlevel %d\n", version_id, PATCHLEVEL);
	fprintf(stderr, "Options: ");
#ifdef vax
	fprintf(stderr, "vax, ");
#endif
#ifdef SHORTNAMES
	fprintf(stderr,"SHORTNAMES, ");
#endif
#ifdef VOIDSIG
	fprintf(stderr,"VOIDSIG, ");
#endif
#ifdef DIRENT
	fprintf(stderr,"DIRENT, ");
#endif
#ifdef NO_UCHAR
	fprintf(stderr, "NO_UCHAR, ");
#endif
#ifdef SIGNED_COMPARE_SLOW
	fprintf(stderr, "SIGNED_COMPARE_SLOW, ");
#endif
#ifdef XENIX_16
	fprintf(stderr, "XENIX_16, ");
#endif
#ifdef COMPATIBLE
	fprintf(stderr, "COMPATIBLE, ");
#endif
#ifdef DEBUG
	fprintf(stderr, "DEBUG, ");
#endif
#ifdef BSD4
	fprintf(stderr, "BSD4, ");
#endif
	fprintf(stderr, "BITS = %d\n", BITS);
}