1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* gzjoin -- command to join gzip files into one gzip file
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Copyright (C) 2004 Mark Adler, all rights reserved
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync version 1.0, 11 Dec 2004
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync This software is provided 'as-is', without any express or implied
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync warranty. In no event will the author be held liable for any damages
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync arising from the use of this software.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Permission is granted to anyone to use this software for any purpose,
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync including commercial applications, and to alter it and redistribute it
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync freely, subject to the following restrictions:
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1. The origin of this software must not be misrepresented; you must not
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync claim that you wrote the original software. If you use this software
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync in a product, an acknowledgment in the product documentation would be
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync appreciated but is not required.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 2. Altered source versions must be plainly marked as such, and must not be
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync misrepresented as being the original software.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 3. This notice may not be removed or altered from any source distribution.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Mark Adler madler@alumni.caltech.edu
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync * Change history:
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync * 1.0 11 Dec 2004 - First version
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync * 1.1 12 Jun 2005 - Changed ssize_t to long for portability
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync gzjoin takes one or more gzip files on the command line and writes out a
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync single gzip file that will uncompress to the concatenation of the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync uncompressed data from the individual gzip files. gzjoin does this without
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync having to recompress any of the data and without having to calculate a new
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync crc32 for the concatenated uncompressed data. gzjoin does however have to
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync decompress all of the input data in order to find the bits in the compressed
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync data that need to be modified to concatenate the streams.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync gzjoin does not do an integrity check on the input gzip files other than
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync checking the gzip header and decompressing the compressed data. They are
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync otherwise assumed to be complete and correct.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync Each joint between gzip files removes at least 18 bytes of previous trailer
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync and subsequent header, and inserts an average of about three bytes to the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync compressed data in order to connect the streams. The output gzip file
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync has a minimal ten-byte gzip header with no file name or modification time.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync This program was written to illustrate the use of the Z_BLOCK option of
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync inflate() and the crc32_combine() function. gzjoin will not compile with
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync versions of zlib earlier than 1.2.3.
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync#include <stdio.h> /* fputs(), fprintf(), fwrite(), putc() */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* crc32(), crc32_combine(), inflateInit2(), inflate(), inflateEnd() */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* exit with an error (return a value to allow use in an expression) */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fprintf(stderr, "gzjoin error: %s%s, output incomplete\n", why1, why2);
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* -- simple buffered file input with access to the buffer -- */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync#define CHUNK 32768 /* must be a power of two and fit in unsigned */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* bin buffered input file type */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsynctypedef struct {
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync unsigned char *buf; /* allocated buffer of length CHUNK */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* close a buffered file and free allocated memory */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* open a buffered file for input, return a pointer to type bin, or NULL on
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* load buffer from file, return -1 on read error, 0 or 1 on success, with
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync 1 indicating that end-of-file was reached */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync len = (long)read(in->fd, in->buf + in->left, CHUNK - in->left);
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* get a byte from the file, bail if end of file */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* get a four-byte little-endian unsigned integer from file */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* skip bytes in file */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* check pointer */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* easy case -- skip bytes in buffer */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* skip what's in buffer, discard buffer contents */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* seek past multiples of CHUNK bytes */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (left == 0) {
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* exact number of chunks: seek all the way minus one byte to check
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync for end-of-file with a read */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* skip the integral chunks, update skip with remainder */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* read more input and skip remainder */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* -- end of buffered input functions -- */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* skip the gzip header from file in */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* verify gzip magic header and compression method */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (bget(in) != 0x1f || bget(in) != 0x8b || bget(in) != 8)
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* get and verify flags */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* skip modification time, extra flags, and os */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* skip extra field if present */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* skip file name if present */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* skip comment if present */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* skip header crc if present */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* write a four-byte little-endian unsigned integer to out */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Load up zlib stream from buffered input, bail if end of file */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Write header for gzip file to out and initialize trailer. */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsynclocal void gzinit(unsigned long *crc, unsigned long *tot, FILE *out)
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fwrite("\x1f\x8b\x08\0\0\0\0\0\0\xff", 1, 10, out);
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* Copy the compressed data from name, zeroing the last block bit of the last
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync block if clr is true, and adding empty blocks as needed to get to a byte
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync boundary. If clr is false, then the last block becomes the last block of
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync the output, and the gzip trailer is written. crc and tot maintains the
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync crc and length (modulo 2^32) of the output for the trailer. The resulting
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync gzip file is written to out. gzinit() must be called before the first call
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync of gzcopy() to write the gzip header and to initialize crc and tot. */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsynclocal void gzcopy(char *name, int clr, unsigned long *crc, unsigned long *tot,
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync int pos; /* where the "last block" bit is in byte */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync unsigned char *start; /* start of compressed data in buffer */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync unsigned char *junk; /* buffer for uncompressed data -- discarded */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync z_off_t len; /* length of uncompressed data (support > 4 GB) */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* open gzip file and skip header */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* allocate buffer for uncompressed data and initialize raw inflate
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* inflate and copy compressed data, clear last-block bit if requested */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* if input used and output done, write used input and get more */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* decompress -- return early when end-of-block reached */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* update length of uncompressed data */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* check for block boundary (only get this when block copied out) */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* if that was the last block, then done */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* number of unused bits in last byte */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* find the next last-block bit */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (pos != 0) {
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* next last-block bit is in last used byte */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* next last-block bit is in next unused byte */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* don't have that byte yet -- get it */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* update buffer with unused input */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* copy used input, write empty blocks to get to byte boundary */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* already at byte boundary, or last file: write last byte */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* append empty blocks to last byte */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync last &= ((0x100 >> pos) - 1); /* assure unused bits are zero */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* odd -- append an empty stored block */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* even -- append 1, 2, or 3 empty fixed blocks */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* update crc and tot */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* clean up */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* write trailer if this is the last gzip file */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync/* join the gzip files on the command line, write result to stdout */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync unsigned long crc, tot; /* running crc and total uncompressed length */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* skip command name */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* show usage if no arguments */
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync if (argc == 0) {
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync fputs("gzjoin usage: gzjoin f1.gz [f2.gz [f3.gz ...]] > fjoin.gz\n",
1b33c96954667ba382fa595baf7b31290bfdd517vboxsync /* join gzip files on command line and write to stdout */