compress.c

这是一个同样来自贝尔实验室的和UNIX有着渊源的操作系统, 其简洁的设计和实现易于我们学习和理解

		bits -= 8;
	}
	/* high order bits. */
	code |= (*bp & rmask[bits]) << r_off;
	offset += n_bits;
	return code;
}

#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 */

#define STACK_SIZE	15000

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

	if(do_decomp == 0) {	/* compressing */
	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(int c, int 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);
	unlink(ofname);
	exit(1);
}

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

	fclose(stdout);
	if (stat(ifname, &statbuf)) {		/* Get stat on input file */
		perror(ifname);
		return;
	}
	if (!S_ISREG(statbuf.st_mode)) {
		if (quiet)
			fprintf(stderr, "%s: ", ifname);
		fprintf(stderr, " -- not a regular file: unchanged");
		exit_stat = 1;
	} else if (exit_stat == 2 && !force) {
		/* No compression: remove file.Z */
		if (!quiet)
			fprintf(stderr, " -- file unchanged");
	} else {			/* Successful Compression */
		exit_stat = 0;
		mode = statbuf.st_mode & 0777;
		if (chmod(ofname, mode))		/* Copy modes */
			perror(ofname);
		/* Copy ownership */
		chown(ofname, statbuf.st_uid, statbuf.st_gid);
		timep[0] = statbuf.st_atime;
		timep[1] = statbuf.st_mtime;
		/* Update last accessed and modified times */
		utime(ofname, timep);
//		if (unlink(ifname))	/* Remove input file */
//			perror(ifname);
		return;			/* success */
	}

	/* 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 */
		return isatty(2);	/* and stderr is a tty */
}

void
onintr(int x)
{
	unlink(ofname);
	exit(1);
}

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

cl_block ()		/* table clear for block compress */
{
	long 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 */
count_int hsize;
{
	count_int *htab_p = htab+hsize;
	long i;
	long m1 = -1;

	i = hsize - 16;
 	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);
	for ( i += 16; i > 0; i-- )
		*--htab_p = m1;
}

prratio(stream, num, den)
FILE *stream;
long num, den;
{
	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\n", rcs_ident);
	fprintf(stderr, "Options: ");
#ifdef DEBUG
	fprintf(stderr, "DEBUG, ");
#endif
#ifdef BSD4_2
	fprintf(stderr, "BSD4_2, ");
#endif
	fprintf(stderr, "BITS = %d\n", BITS);
}

/*
 * The revision-history novel:
 *
 * $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 version of vax asm routines.  Changed structure to arrays to
 * save much memory.  Do unsigned compares where possible (faster on
 * Perkin-Elmer)
 *
 * 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
 * Minor fixes.
 *
 * Revision 1.2  84/07/05  00:27:27  thomas
 * Add variable bit length output.
 */