1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* gun.c -- simple gunzip to give an example of the use of inflateBack()
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync * Copyright (C) 2003, 2005, 2008, 2010 Mark Adler
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync * For conditions of distribution and use, see copyright notice in zlib.h
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Version 1.6 17 January 2010 Mark Adler */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Version history:
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1.0 16 Feb 2003 First version for testing of inflateBack()
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1.1 21 Feb 2005 Decompress concatenated gzip streams
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Remove use of "this" variable (C++ keyword)
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Fix return value for in()
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Improve allocation failure checking
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Add typecasting for void * structures
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Add -h option for command version and usage
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Add a bunch of comments
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1.2 20 Mar 2005 Add Unix compress (LZW) decompression
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Copy file attributes from input file to output file
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1.3 12 Jun 2005 Add casts for error messages [Oberhumer]
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1.4 8 Dec 2006 LZW decompression speed improvements
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1.5 9 Feb 2008 Avoid warning in latest version of gcc
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1.6 17 Jan 2010 Avoid signed/unsigned comparison warnings
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync gun [ -t ] [ name ... ]
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync decompresses the data in the named gzip files. If no arguments are given,
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync gun will decompress from stdin to stdout. The names must end in .gz, -gz,
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync .z, -z, _z, or .Z. The uncompressed data will be written to a file name
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync with the suffix stripped. On success, the original file is deleted. On
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync failure, the output file is deleted. For most failures, the command will
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync continue to process the remaining names on the command line. A memory
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync allocation failure will abort the command. If -t is specified, then the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync listed files or stdin will be tested as gzip files for integrity (without
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync checking for a proper suffix), no output will be written, and no files
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync will be deleted.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Like gzip, gun allows concatenated gzip streams and will decompress them,
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync writing all of the uncompressed data to the output. Unlike gzip, gun allows
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync an empty file on input, and will produce no error writing an empty output
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync gun will also decompress files made by Unix compress, which uses LZW
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync compression. These files are automatically detected by virtue of their
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync magic header bytes. Since the end of Unix compress stream is marked by the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync end-of-file, they cannot be concantenated. If a Unix compress stream is
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync encountered in an input file, it is the last stream in that file.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Like gunzip and uncompress, the file attributes of the orignal compressed
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync file are maintained in the final uncompressed file, to the extent that the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync user permissions allow it.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync On my Mac OS X PowerPC G4, gun is almost twice as fast as gunzip (version
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1.2.4) is on the same file, when gun is linked with zlib 1.2.2. Also the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync LZW decompression provided by gun is about twice as fast as the standard
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Unix uncompress command.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* external functions and related types and constants */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync#include <string.h> /* strerror(), strcmp(), strlen(), memcpy() */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync#include <unistd.h> /* read(), write(), close(), chown(), unlink() */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync#include "zlib.h" /* inflateBackInit(), inflateBack(), */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* inflateBackEnd(), crc32() */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* function declaration */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* buffer constants */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync#define SIZE 32768U /* input and output buffer sizes */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync#define PIECE 16384 /* limits i/o chunks for 16-bit int case */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* structure for infback() to pass to input function in() -- it maintains the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync input file and a buffer of size SIZE */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Load input buffer, assumed to be empty, and return bytes loaded and a
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync pointer to them. read() is called until the buffer is full, or until it
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync returns end-of-file or error. Return 0 on error. */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsynclocal unsigned in(void *in_desc, unsigned char **buf)
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* structure for infback() to pass to output function out() -- it maintains the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync output file, a running CRC-32 check on the output and the total number of
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync bytes output, both for checking against the gzip trailer. (The length in
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync the gzip trailer is stored modulo 2^32, so it's ok if a long is 32 bits and
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync the output is greater than 4 GB.) */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Write output buffer and update the CRC-32 and total bytes written. write()
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync is called until all of the output is written or an error is encountered.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync On success out() returns 0. For a write failure, out() returns 1. If the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync output file descriptor is -1, then nothing is written.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsynclocal int out(void *out_desc, unsigned char *buf, unsigned len)
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync } while (len != 0);
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* next input byte macro for use inside lunpipe() and gunpipe() */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync#define NEXT() (have ? 0 : (have = in(indp, &next)), \
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* memory for gunpipe() and lunpipe() --
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync the first 256 entries of prefix[] and suffix[] are never used, could
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync have offset the index, but it's faster to waste the memory */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsyncunsigned short prefix[65536]; /* index to LZW prefix string */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsyncunsigned char suffix[65536]; /* one-character LZW suffix */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsyncunsigned char match[65280 + 2]; /* buffer for reversed match or gzip
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 32K sliding window */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* throw out what's left in the current bits byte buffer (this is a vestigial
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync aspect of the compressed data format derived from an implementation that
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync made use of a special VAX machine instruction!) */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync } while (0)
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Decompress a compress (LZW) file from indp to outfile. The compress magic
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync header (two bytes) has already been read and verified. There are have bytes
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync of buffered input at next. strm is used for passing error information back
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync to gunpipe().
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync lunpipe() will return Z_OK on success, Z_BUF_ERROR for an unexpected end of
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync file, read error, or write error (a write error indicated by strm->next_in
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync not equal to Z_NULL), or Z_DATA_ERROR for invalid input.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsynclocal int lunpipe(unsigned have, unsigned char *next, struct ind *indp,
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync int last; /* last byte read by NEXT(), or -1 if EOF */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync int max; /* maximum bits per code for this stream */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync unsigned flags; /* compress flags, then block compress flag */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync unsigned end; /* last valid entry in prefix/suffix tables */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync unsigned final; /* last character written for previous code */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync unsigned stack; /* next position for reversed string */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync unsigned char *p;
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* set up output */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* process remainder of compress header -- a flags byte */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* clear table */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* set up: get first 9-bit code, which is the first decompressed byte, but
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync don't create a table entry until the next code */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync final = prev = (unsigned)last; /* low 8 bits of code */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync outbuf[0] = (unsigned char)final; /* write first decompressed byte */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* decode codes */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* if the table will be full after this, increment the code size */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* get a code of length bits */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (NEXT() == -1) { /* EOF is end of compressed data */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* write remaining buffered output */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync code += (unsigned)last << left; /* middle (or high) bits of code */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (NEXT() == -1) /* can't end in middle of code */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync code += (unsigned)last << left; /* high bits of code */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync rem = (unsigned)last >> (8 - left); /* unused bits from last byte */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* process clear code (256) */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync continue; /* get next code */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* special code to reuse last match */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* Be picky on the allowed code here, and make sure that the code
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync we drop through (prev) will be a valid index so that random
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync input does not cause an exception. The code != end + 1 check is
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync empirically derived, and not checked in the original uncompress
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync code. If this ever causes a problem, that check could be safely
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync removed. Leaving this check in greatly improves gun's ability
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync to detect random or corrupted input after a compress header.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync In any case, the prev > end check must be retained. */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* walk through linked list to generate output in reverse order */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* link new table entry */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* set previous code for next iteration */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* write output in forward order */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync } while (p > match);
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* loop for next code with final and prev as the last match, rem and
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync left provide the first 0..7 bits of the next code, end is the last
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync valid table entry */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Decompress a gzip file from infile to outfile. strm is assumed to have been
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync successfully initialized with inflateBackInit(). The input file may consist
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync of a series of gzip streams, in which case all of them will be decompressed
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync to the output file. If outfile is -1, then the gzip stream(s) integrity is
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync checked and nothing is written.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync The return value is a zlib error code: Z_MEM_ERROR if out of memory,
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Z_DATA_ERROR if the header or the compressed data is invalid, or if the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync trailer CRC-32 check or length doesn't match, Z_BUF_ERROR if the input ends
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync prematurely or a write error occurs, or Z_ERRNO if junk (not a another gzip
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync stream) follows a valid gzip stream.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsynclocal int gunpipe(z_stream *strm, int infile, int outfile)
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* setup input buffer */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* decompress concatenated gzip streams */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync strm->next_in = Z_NULL; /* so Z_BUF_ERROR means EOF */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* look for the two magic header bytes for a gzip stream */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync break; /* empty gzip stream is ok */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (last != 31 || (NEXT() != 139 && last != 157)) {
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync break; /* not a gzip or compress header */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* process a compress (LZW) file -- can't be concatenated after this */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* process remainder of gzip header */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (NEXT() != 8) { /* only deflate method allowed */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* set up output */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* decompress data to output */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync strm->next_in = Z_NULL; /* so Z_BUF_ERROR means EOF */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* check trailer */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* crc error */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* length error */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* go back and look for another gzip stream */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* clean up and return */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Copy file attributes, from -> to, as best we can. This is best effort, so
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync no errors are reported. The mode bits, including suid, sgid, and the sticky
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync bit are copied (if allowed), the owner's user id and group id are copied
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync (again if allowed), and the access and modify times are copied. */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* get all of from's Unix meta data, return if not a regular file */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (stat(from, &was) != 0 || (was.st_mode & S_IFMT) != S_IFREG)
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* set to's mode bits, ignore errors */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* copy owner's user and group, ignore errors */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* copy access and modify times, ignore errors */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Decompress the file inname to the file outnname, of if test is true, just
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync decompress without writing and check the gzip trailer for integrity. If
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync inname is NULL or an empty string, read from stdin. If outname is NULL or
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync an empty string, write to stdout. strm is a pre-initialized inflateBack
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync structure. When appropriate, copy the file attributes from inname to
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync gunzip() returns 1 if there is an out-of-memory error or an unexpected
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync return code from gunpipe(). Otherwise it returns 0.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsynclocal int gunzip(z_stream *strm, char *inname, char *outname, int test)
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* open files */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync outfile = open(outname, O_CREAT | O_TRUNC | O_WRONLY, 0666);
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "gun cannot create %s\n", outname);
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* decompress */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* interpret result */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "gun warning: trailing garbage ignored in %s\n",
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "gun data error on %s: %s\n", inname, strm->msg);
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "gun out of memory error--aborting\n");
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "gun unexpected end of file on %s\n",
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Process the gun command line arguments. See the command syntax near the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync beginning of this source file. */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* initialize inflateBack state for repeated use */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "gun out of memory error--aborting\n");
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* decompress each file to the same name with the suffix removed */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "Copyright (C) 2003-2010 Mark Adler\n");
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "usage: gun [-t] [file1.gz [file2.Z ...]]\n");
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "gun error: no gz type on %s--skipping\n",
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "gun out of memory error--aborting\n");
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (ret) break;
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* clean up */