Import zlib into Python tree.
diff --git a/Modules/zlib/examples/README.examples b/Modules/zlib/examples/README.examples
new file mode 100644
index 0000000..5632d7a
--- /dev/null
+++ b/Modules/zlib/examples/README.examples
@@ -0,0 +1,42 @@
+This directory contains examples of the use of zlib.
+
+fitblk.c
+ compress just enough input to nearly fill a requested output size
+ - zlib isn't designed to do this, but fitblk does it anyway
+
+gun.c
+ uncompress a gzip file
+ - illustrates the use of inflateBack() for high speed file-to-file
+ decompression using call-back functions
+ - is approximately twice as fast as gzip -d
+ - also provides Unix uncompress functionality, again twice as fast
+
+gzappend.c
+ append to a gzip file
+ - illustrates the use of the Z_BLOCK flush parameter for inflate()
+ - illustrates the use of deflatePrime() to start at any bit
+
+gzjoin.c
+ join gzip files without recalculating the crc or recompressing
+ - illustrates the use of the Z_BLOCK flush parameter for inflate()
+ - illustrates the use of crc32_combine()
+
+gzlog.c
+gzlog.h
+ efficiently maintain a message log file in gzip format
+ - illustrates use of raw deflate and Z_SYNC_FLUSH
+ - illustrates use of gzip header extra field
+
+zlib_how.html
+ painfully comprehensive description of zpipe.c (see below)
+ - describes in excruciating detail the use of deflate() and inflate()
+
+zpipe.c
+ reads and writes zlib streams from stdin to stdout
+ - illustrates the proper use of deflate() and inflate()
+ - deeply commented in zlib_how.html (see above)
+
+zran.c
+ index a zlib or gzip stream and randomly access it
+ - illustrates the use of Z_BLOCK, inflatePrime(), and
+ inflateSetDictionary() to provide random access
diff --git a/Modules/zlib/examples/fitblk.c b/Modules/zlib/examples/fitblk.c
new file mode 100644
index 0000000..c61de5c
--- /dev/null
+++ b/Modules/zlib/examples/fitblk.c
@@ -0,0 +1,233 @@
+/* fitblk.c: example of fitting compressed output to a specified size
+ Not copyrighted -- provided to the public domain
+ Version 1.1 25 November 2004 Mark Adler */
+
+/* Version history:
+ 1.0 24 Nov 2004 First version
+ 1.1 25 Nov 2004 Change deflateInit2() to deflateInit()
+ Use fixed-size, stack-allocated raw buffers
+ Simplify code moving compression to subroutines
+ Use assert() for internal errors
+ Add detailed description of approach
+ */
+
+/* Approach to just fitting a requested compressed size:
+
+ fitblk performs three compression passes on a portion of the input
+ data in order to determine how much of that input will compress to
+ nearly the requested output block size. The first pass generates
+ enough deflate blocks to produce output to fill the requested
+ output size plus a specfied excess amount (see the EXCESS define
+ below). The last deflate block may go quite a bit past that, but
+ is discarded. The second pass decompresses and recompresses just
+ the compressed data that fit in the requested plus excess sized
+ buffer. The deflate process is terminated after that amount of
+ input, which is less than the amount consumed on the first pass.
+ The last deflate block of the result will be of a comparable size
+ to the final product, so that the header for that deflate block and
+ the compression ratio for that block will be about the same as in
+ the final product. The third compression pass decompresses the
+ result of the second step, but only the compressed data up to the
+ requested size minus an amount to allow the compressed stream to
+ complete (see the MARGIN define below). That will result in a
+ final compressed stream whose length is less than or equal to the
+ requested size. Assuming sufficient input and a requested size
+ greater than a few hundred bytes, the shortfall will typically be
+ less than ten bytes.
+
+ If the input is short enough that the first compression completes
+ before filling the requested output size, then that compressed
+ stream is return with no recompression.
+
+ EXCESS is chosen to be just greater than the shortfall seen in a
+ two pass approach similar to the above. That shortfall is due to
+ the last deflate block compressing more efficiently with a smaller
+ header on the second pass. EXCESS is set to be large enough so
+ that there is enough uncompressed data for the second pass to fill
+ out the requested size, and small enough so that the final deflate
+ block of the second pass will be close in size to the final deflate
+ block of the third and final pass. MARGIN is chosen to be just
+ large enough to assure that the final compression has enough room
+ to complete in all cases.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include "zlib.h"
+
+#define local static
+
+/* print nastygram and leave */
+local void quit(char *why)
+{
+ fprintf(stderr, "fitblk abort: %s\n", why);
+ exit(1);
+}
+
+#define RAWLEN 4096 /* intermediate uncompressed buffer size */
+
+/* compress from file to def until provided buffer is full or end of
+ input reached; return last deflate() return value, or Z_ERRNO if
+ there was read error on the file */
+local int partcompress(FILE *in, z_streamp def)
+{
+ int ret, flush;
+ unsigned char raw[RAWLEN];
+
+ flush = Z_NO_FLUSH;
+ do {
+ def->avail_in = fread(raw, 1, RAWLEN, in);
+ if (ferror(in))
+ return Z_ERRNO;
+ def->next_in = raw;
+ if (feof(in))
+ flush = Z_FINISH;
+ ret = deflate(def, flush);
+ assert(ret != Z_STREAM_ERROR);
+ } while (def->avail_out != 0 && flush == Z_NO_FLUSH);
+ return ret;
+}
+
+/* recompress from inf's input to def's output; the input for inf and
+ the output for def are set in those structures before calling;
+ return last deflate() return value, or Z_MEM_ERROR if inflate()
+ was not able to allocate enough memory when it needed to */
+local int recompress(z_streamp inf, z_streamp def)
+{
+ int ret, flush;
+ unsigned char raw[RAWLEN];
+
+ flush = Z_NO_FLUSH;
+ do {
+ /* decompress */
+ inf->avail_out = RAWLEN;
+ inf->next_out = raw;
+ ret = inflate(inf, Z_NO_FLUSH);
+ assert(ret != Z_STREAM_ERROR && ret != Z_DATA_ERROR &&
+ ret != Z_NEED_DICT);
+ if (ret == Z_MEM_ERROR)
+ return ret;
+
+ /* compress what was decompresed until done or no room */
+ def->avail_in = RAWLEN - inf->avail_out;
+ def->next_in = raw;
+ if (inf->avail_out != 0)
+ flush = Z_FINISH;
+ ret = deflate(def, flush);
+ assert(ret != Z_STREAM_ERROR);
+ } while (ret != Z_STREAM_END && def->avail_out != 0);
+ return ret;
+}
+
+#define EXCESS 256 /* empirically determined stream overage */
+#define MARGIN 8 /* amount to back off for completion */
+
+/* compress from stdin to fixed-size block on stdout */
+int main(int argc, char **argv)
+{
+ int ret; /* return code */
+ unsigned size; /* requested fixed output block size */
+ unsigned have; /* bytes written by deflate() call */
+ unsigned char *blk; /* intermediate and final stream */
+ unsigned char *tmp; /* close to desired size stream */
+ z_stream def, inf; /* zlib deflate and inflate states */
+
+ /* get requested output size */
+ if (argc != 2)
+ quit("need one argument: size of output block");
+ ret = strtol(argv[1], argv + 1, 10);
+ if (argv[1][0] != 0)
+ quit("argument must be a number");
+ if (ret < 8) /* 8 is minimum zlib stream size */
+ quit("need positive size of 8 or greater");
+ size = (unsigned)ret;
+
+ /* allocate memory for buffers and compression engine */
+ blk = malloc(size + EXCESS);
+ def.zalloc = Z_NULL;
+ def.zfree = Z_NULL;
+ def.opaque = Z_NULL;
+ ret = deflateInit(&def, Z_DEFAULT_COMPRESSION);
+ if (ret != Z_OK || blk == NULL)
+ quit("out of memory");
+
+ /* compress from stdin until output full, or no more input */
+ def.avail_out = size + EXCESS;
+ def.next_out = blk;
+ ret = partcompress(stdin, &def);
+ if (ret == Z_ERRNO)
+ quit("error reading input");
+
+ /* if it all fit, then size was undersubscribed -- done! */
+ if (ret == Z_STREAM_END && def.avail_out >= EXCESS) {
+ /* write block to stdout */
+ have = size + EXCESS - def.avail_out;
+ if (fwrite(blk, 1, have, stdout) != have || ferror(stdout))
+ quit("error writing output");
+
+ /* clean up and print results to stderr */
+ ret = deflateEnd(&def);
+ assert(ret != Z_STREAM_ERROR);
+ free(blk);
+ fprintf(stderr,
+ "%u bytes unused out of %u requested (all input)\n",
+ size - have, size);
+ return 0;
+ }
+
+ /* it didn't all fit -- set up for recompression */
+ inf.zalloc = Z_NULL;
+ inf.zfree = Z_NULL;
+ inf.opaque = Z_NULL;
+ inf.avail_in = 0;
+ inf.next_in = Z_NULL;
+ ret = inflateInit(&inf);
+ tmp = malloc(size + EXCESS);
+ if (ret != Z_OK || tmp == NULL)
+ quit("out of memory");
+ ret = deflateReset(&def);
+ assert(ret != Z_STREAM_ERROR);
+
+ /* do first recompression close to the right amount */
+ inf.avail_in = size + EXCESS;
+ inf.next_in = blk;
+ def.avail_out = size + EXCESS;
+ def.next_out = tmp;
+ ret = recompress(&inf, &def);
+ if (ret == Z_MEM_ERROR)
+ quit("out of memory");
+
+ /* set up for next reocmpression */
+ ret = inflateReset(&inf);
+ assert(ret != Z_STREAM_ERROR);
+ ret = deflateReset(&def);
+ assert(ret != Z_STREAM_ERROR);
+
+ /* do second and final recompression (third compression) */
+ inf.avail_in = size - MARGIN; /* assure stream will complete */
+ inf.next_in = tmp;
+ def.avail_out = size;
+ def.next_out = blk;
+ ret = recompress(&inf, &def);
+ if (ret == Z_MEM_ERROR)
+ quit("out of memory");
+ assert(ret == Z_STREAM_END); /* otherwise MARGIN too small */
+
+ /* done -- write block to stdout */
+ have = size - def.avail_out;
+ if (fwrite(blk, 1, have, stdout) != have || ferror(stdout))
+ quit("error writing output");
+
+ /* clean up and print results to stderr */
+ free(tmp);
+ ret = inflateEnd(&inf);
+ assert(ret != Z_STREAM_ERROR);
+ ret = deflateEnd(&def);
+ assert(ret != Z_STREAM_ERROR);
+ free(blk);
+ fprintf(stderr,
+ "%u bytes unused out of %u requested (%lu input)\n",
+ size - have, size, def.total_in);
+ return 0;
+}
diff --git a/Modules/zlib/examples/gun.c b/Modules/zlib/examples/gun.c
new file mode 100644
index 0000000..bfec590
--- /dev/null
+++ b/Modules/zlib/examples/gun.c
@@ -0,0 +1,693 @@
+/* gun.c -- simple gunzip to give an example of the use of inflateBack()
+ * Copyright (C) 2003, 2005 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ Version 1.3 12 June 2005 Mark Adler */
+
+/* Version history:
+ 1.0 16 Feb 2003 First version for testing of inflateBack()
+ 1.1 21 Feb 2005 Decompress concatenated gzip streams
+ Remove use of "this" variable (C++ keyword)
+ Fix return value for in()
+ Improve allocation failure checking
+ Add typecasting for void * structures
+ Add -h option for command version and usage
+ Add a bunch of comments
+ 1.2 20 Mar 2005 Add Unix compress (LZW) decompression
+ Copy file attributes from input file to output file
+ 1.3 12 Jun 2005 Add casts for error messages [Oberhumer]
+ */
+
+/*
+ gun [ -t ] [ name ... ]
+
+ decompresses the data in the named gzip files. If no arguments are given,
+ gun will decompress from stdin to stdout. The names must end in .gz, -gz,
+ .z, -z, _z, or .Z. The uncompressed data will be written to a file name
+ with the suffix stripped. On success, the original file is deleted. On
+ failure, the output file is deleted. For most failures, the command will
+ continue to process the remaining names on the command line. A memory
+ allocation failure will abort the command. If -t is specified, then the
+ listed files or stdin will be tested as gzip files for integrity (without
+ checking for a proper suffix), no output will be written, and no files
+ will be deleted.
+
+ Like gzip, gun allows concatenated gzip streams and will decompress them,
+ writing all of the uncompressed data to the output. Unlike gzip, gun allows
+ an empty file on input, and will produce no error writing an empty output
+ file.
+
+ gun will also decompress files made by Unix compress, which uses LZW
+ compression. These files are automatically detected by virtue of their
+ magic header bytes. Since the end of Unix compress stream is marked by the
+ end-of-file, they cannot be concantenated. If a Unix compress stream is
+ encountered in an input file, it is the last stream in that file.
+
+ Like gunzip and uncompress, the file attributes of the orignal compressed
+ file are maintained in the final uncompressed file, to the extent that the
+ user permissions allow it.
+
+ On my Mac OS X PowerPC G4, gun is almost twice as fast as gunzip (version
+ 1.2.4) is on the same file, when gun is linked with zlib 1.2.2. Also the
+ LZW decompression provided by gun is about twice as fast as the standard
+ Unix uncompress command.
+ */
+
+/* external functions and related types and constants */
+#include <stdio.h> /* fprintf() */
+#include <stdlib.h> /* malloc(), free() */
+#include <string.h> /* strerror(), strcmp(), strlen(), memcpy() */
+#include <errno.h> /* errno */
+#include <fcntl.h> /* open() */
+#include <unistd.h> /* read(), write(), close(), chown(), unlink() */
+#include <sys/types.h>
+#include <sys/stat.h> /* stat(), chmod() */
+#include <utime.h> /* utime() */
+#include "zlib.h" /* inflateBackInit(), inflateBack(), */
+ /* inflateBackEnd(), crc32() */
+
+/* function declaration */
+#define local static
+
+/* buffer constants */
+#define SIZE 32768U /* input and output buffer sizes */
+#define PIECE 16384 /* limits i/o chunks for 16-bit int case */
+
+/* structure for infback() to pass to input function in() -- it maintains the
+ input file and a buffer of size SIZE */
+struct ind {
+ int infile;
+ unsigned char *inbuf;
+};
+
+/* Load input buffer, assumed to be empty, and return bytes loaded and a
+ pointer to them. read() is called until the buffer is full, or until it
+ returns end-of-file or error. Return 0 on error. */
+local unsigned in(void *in_desc, unsigned char **buf)
+{
+ int ret;
+ unsigned len;
+ unsigned char *next;
+ struct ind *me = (struct ind *)in_desc;
+
+ next = me->inbuf;
+ *buf = next;
+ len = 0;
+ do {
+ ret = PIECE;
+ if ((unsigned)ret > SIZE - len)
+ ret = (int)(SIZE - len);
+ ret = (int)read(me->infile, next, ret);
+ if (ret == -1) {
+ len = 0;
+ break;
+ }
+ next += ret;
+ len += ret;
+ } while (ret != 0 && len < SIZE);
+ return len;
+}
+
+/* structure for infback() to pass to output function out() -- it maintains the
+ output file, a running CRC-32 check on the output and the total number of
+ bytes output, both for checking against the gzip trailer. (The length in
+ the gzip trailer is stored modulo 2^32, so it's ok if a long is 32 bits and
+ the output is greater than 4 GB.) */
+struct outd {
+ int outfile;
+ int check; /* true if checking crc and total */
+ unsigned long crc;
+ unsigned long total;
+};
+
+/* Write output buffer and update the CRC-32 and total bytes written. write()
+ is called until all of the output is written or an error is encountered.
+ On success out() returns 0. For a write failure, out() returns 1. If the
+ output file descriptor is -1, then nothing is written.
+ */
+local int out(void *out_desc, unsigned char *buf, unsigned len)
+{
+ int ret;
+ struct outd *me = (struct outd *)out_desc;
+
+ if (me->check) {
+ me->crc = crc32(me->crc, buf, len);
+ me->total += len;
+ }
+ if (me->outfile != -1)
+ do {
+ ret = PIECE;
+ if ((unsigned)ret > len)
+ ret = (int)len;
+ ret = (int)write(me->outfile, buf, ret);
+ if (ret == -1)
+ return 1;
+ buf += ret;
+ len -= ret;
+ } while (len != 0);
+ return 0;
+}
+
+/* next input byte macro for use inside lunpipe() and gunpipe() */
+#define NEXT() (have ? 0 : (have = in(indp, &next)), \
+ last = have ? (have--, (int)(*next++)) : -1)
+
+/* memory for gunpipe() and lunpipe() --
+ the first 256 entries of prefix[] and suffix[] are never used, could
+ have offset the index, but it's faster to waste the memory */
+unsigned char inbuf[SIZE]; /* input buffer */
+unsigned char outbuf[SIZE]; /* output buffer */
+unsigned short prefix[65536]; /* index to LZW prefix string */
+unsigned char suffix[65536]; /* one-character LZW suffix */
+unsigned char match[65280 + 2]; /* buffer for reversed match or gzip
+ 32K sliding window */
+
+/* throw out what's left in the current bits byte buffer (this is a vestigial
+ aspect of the compressed data format derived from an implementation that
+ made use of a special VAX machine instruction!) */
+#define FLUSHCODE() \
+ do { \
+ left = 0; \
+ rem = 0; \
+ if (chunk > have) { \
+ chunk -= have; \
+ have = 0; \
+ if (NEXT() == -1) \
+ break; \
+ chunk--; \
+ if (chunk > have) { \
+ chunk = have = 0; \
+ break; \
+ } \
+ } \
+ have -= chunk; \
+ next += chunk; \
+ chunk = 0; \
+ } while (0)
+
+/* Decompress a compress (LZW) file from indp to outfile. The compress magic
+ header (two bytes) has already been read and verified. There are have bytes
+ of buffered input at next. strm is used for passing error information back
+ to gunpipe().
+
+ lunpipe() will return Z_OK on success, Z_BUF_ERROR for an unexpected end of
+ file, read error, or write error (a write error indicated by strm->next_in
+ not equal to Z_NULL), or Z_DATA_ERROR for invalid input.
+ */
+local int lunpipe(unsigned have, unsigned char *next, struct ind *indp,
+ int outfile, z_stream *strm)
+{
+ int last; /* last byte read by NEXT(), or -1 if EOF */
+ int chunk; /* bytes left in current chunk */
+ int left; /* bits left in rem */
+ unsigned rem; /* unused bits from input */
+ int bits; /* current bits per code */
+ unsigned code; /* code, table traversal index */
+ unsigned mask; /* mask for current bits codes */
+ int max; /* maximum bits per code for this stream */
+ int flags; /* compress flags, then block compress flag */
+ unsigned end; /* last valid entry in prefix/suffix tables */
+ unsigned temp; /* current code */
+ unsigned prev; /* previous code */
+ unsigned final; /* last character written for previous code */
+ unsigned stack; /* next position for reversed string */
+ unsigned outcnt; /* bytes in output buffer */
+ struct outd outd; /* output structure */
+
+ /* set up output */
+ outd.outfile = outfile;
+ outd.check = 0;
+
+ /* process remainder of compress header -- a flags byte */
+ flags = NEXT();
+ if (last == -1)
+ return Z_BUF_ERROR;
+ if (flags & 0x60) {
+ strm->msg = (char *)"unknown lzw flags set";
+ return Z_DATA_ERROR;
+ }
+ max = flags & 0x1f;
+ if (max < 9 || max > 16) {
+ strm->msg = (char *)"lzw bits out of range";
+ return Z_DATA_ERROR;
+ }
+ if (max == 9) /* 9 doesn't really mean 9 */
+ max = 10;
+ flags &= 0x80; /* true if block compress */
+
+ /* clear table */
+ bits = 9;
+ mask = 0x1ff;
+ end = flags ? 256 : 255;
+
+ /* set up: get first 9-bit code, which is the first decompressed byte, but
+ don't create a table entry until the next code */
+ if (NEXT() == -1) /* no compressed data is ok */
+ return Z_OK;
+ final = prev = (unsigned)last; /* low 8 bits of code */
+ if (NEXT() == -1) /* missing a bit */
+ return Z_BUF_ERROR;
+ if (last & 1) { /* code must be < 256 */
+ strm->msg = (char *)"invalid lzw code";
+ return Z_DATA_ERROR;
+ }
+ rem = (unsigned)last >> 1; /* remaining 7 bits */
+ left = 7;
+ chunk = bits - 2; /* 7 bytes left in this chunk */
+ outbuf[0] = (unsigned char)final; /* write first decompressed byte */
+ outcnt = 1;
+
+ /* decode codes */
+ stack = 0;
+ for (;;) {
+ /* if the table will be full after this, increment the code size */
+ if (end >= mask && bits < max) {
+ FLUSHCODE();
+ bits++;
+ mask <<= 1;
+ mask++;
+ }
+
+ /* get a code of length bits */
+ if (chunk == 0) /* decrement chunk modulo bits */
+ chunk = bits;
+ code = rem; /* low bits of code */
+ if (NEXT() == -1) { /* EOF is end of compressed data */
+ /* write remaining buffered output */
+ if (outcnt && out(&outd, outbuf, outcnt)) {
+ strm->next_in = outbuf; /* signal write error */
+ return Z_BUF_ERROR;
+ }
+ return Z_OK;
+ }
+ code += (unsigned)last << left; /* middle (or high) bits of code */
+ left += 8;
+ chunk--;
+ if (bits > left) { /* need more bits */
+ if (NEXT() == -1) /* can't end in middle of code */
+ return Z_BUF_ERROR;
+ code += (unsigned)last << left; /* high bits of code */
+ left += 8;
+ chunk--;
+ }
+ code &= mask; /* mask to current code length */
+ left -= bits; /* number of unused bits */
+ rem = (unsigned)last >> (8 - left); /* unused bits from last byte */
+
+ /* process clear code (256) */
+ if (code == 256 && flags) {
+ FLUSHCODE();
+ bits = 9; /* initialize bits and mask */
+ mask = 0x1ff;
+ end = 255; /* empty table */
+ continue; /* get next code */
+ }
+
+ /* special code to reuse last match */
+ temp = code; /* save the current code */
+ if (code > end) {
+ /* Be picky on the allowed code here, and make sure that the code
+ we drop through (prev) will be a valid index so that random
+ input does not cause an exception. The code != end + 1 check is
+ empirically derived, and not checked in the original uncompress
+ code. If this ever causes a problem, that check could be safely
+ removed. Leaving this check in greatly improves gun's ability
+ to detect random or corrupted input after a compress header.
+ In any case, the prev > end check must be retained. */
+ if (code != end + 1 || prev > end) {
+ strm->msg = (char *)"invalid lzw code";
+ return Z_DATA_ERROR;
+ }
+ match[stack++] = (unsigned char)final;
+ code = prev;
+ }
+
+ /* walk through linked list to generate output in reverse order */
+ while (code >= 256) {
+ match[stack++] = suffix[code];
+ code = prefix[code];
+ }
+ match[stack++] = (unsigned char)code;
+ final = code;
+
+ /* link new table entry */
+ if (end < mask) {
+ end++;
+ prefix[end] = (unsigned short)prev;
+ suffix[end] = (unsigned char)final;
+ }
+
+ /* set previous code for next iteration */
+ prev = temp;
+
+ /* write output in forward order */
+ while (stack > SIZE - outcnt) {
+ while (outcnt < SIZE)
+ outbuf[outcnt++] = match[--stack];
+ if (out(&outd, outbuf, outcnt)) {
+ strm->next_in = outbuf; /* signal write error */
+ return Z_BUF_ERROR;
+ }
+ outcnt = 0;
+ }
+ do {
+ outbuf[outcnt++] = match[--stack];
+ } while (stack);
+
+ /* loop for next code with final and prev as the last match, rem and
+ left provide the first 0..7 bits of the next code, end is the last
+ valid table entry */
+ }
+}
+
+/* Decompress a gzip file from infile to outfile. strm is assumed to have been
+ successfully initialized with inflateBackInit(). The input file may consist
+ of a series of gzip streams, in which case all of them will be decompressed
+ to the output file. If outfile is -1, then the gzip stream(s) integrity is
+ checked and nothing is written.
+
+ The return value is a zlib error code: Z_MEM_ERROR if out of memory,
+ Z_DATA_ERROR if the header or the compressed data is invalid, or if the
+ trailer CRC-32 check or length doesn't match, Z_BUF_ERROR if the input ends
+ prematurely or a write error occurs, or Z_ERRNO if junk (not a another gzip
+ stream) follows a valid gzip stream.
+ */
+local int gunpipe(z_stream *strm, int infile, int outfile)
+{
+ int ret, first, last;
+ unsigned have, flags, len;
+ unsigned char *next;
+ struct ind ind, *indp;
+ struct outd outd;
+
+ /* setup input buffer */
+ ind.infile = infile;
+ ind.inbuf = inbuf;
+ indp = &ind;
+
+ /* decompress concatenated gzip streams */
+ have = 0; /* no input data read in yet */
+ first = 1; /* looking for first gzip header */
+ strm->next_in = Z_NULL; /* so Z_BUF_ERROR means EOF */
+ for (;;) {
+ /* look for the two magic header bytes for a gzip stream */
+ if (NEXT() == -1) {
+ ret = Z_OK;
+ break; /* empty gzip stream is ok */
+ }
+ if (last != 31 || (NEXT() != 139 && last != 157)) {
+ strm->msg = (char *)"incorrect header check";
+ ret = first ? Z_DATA_ERROR : Z_ERRNO;
+ break; /* not a gzip or compress header */
+ }
+ first = 0; /* next non-header is junk */
+
+ /* process a compress (LZW) file -- can't be concatenated after this */
+ if (last == 157) {
+ ret = lunpipe(have, next, indp, outfile, strm);
+ break;
+ }
+
+ /* process remainder of gzip header */
+ ret = Z_BUF_ERROR;
+ if (NEXT() != 8) { /* only deflate method allowed */
+ if (last == -1) break;
+ strm->msg = (char *)"unknown compression method";
+ ret = Z_DATA_ERROR;
+ break;
+ }
+ flags = NEXT(); /* header flags */
+ NEXT(); /* discard mod time, xflgs, os */
+ NEXT();
+ NEXT();
+ NEXT();
+ NEXT();
+ NEXT();
+ if (last == -1) break;
+ if (flags & 0xe0) {
+ strm->msg = (char *)"unknown header flags set";
+ ret = Z_DATA_ERROR;
+ break;
+ }
+ if (flags & 4) { /* extra field */
+ len = NEXT();
+ len += (unsigned)(NEXT()) << 8;
+ if (last == -1) break;
+ while (len > have) {
+ len -= have;
+ have = 0;
+ if (NEXT() == -1) break;
+ len--;
+ }
+ if (last == -1) break;
+ have -= len;
+ next += len;
+ }
+ if (flags & 8) /* file name */
+ while (NEXT() != 0 && last != -1)
+ ;
+ if (flags & 16) /* comment */
+ while (NEXT() != 0 && last != -1)
+ ;
+ if (flags & 2) { /* header crc */
+ NEXT();
+ NEXT();
+ }
+ if (last == -1) break;
+
+ /* set up output */
+ outd.outfile = outfile;
+ outd.check = 1;
+ outd.crc = crc32(0L, Z_NULL, 0);
+ outd.total = 0;
+
+ /* decompress data to output */
+ strm->next_in = next;
+ strm->avail_in = have;
+ ret = inflateBack(strm, in, indp, out, &outd);
+ if (ret != Z_STREAM_END) break;
+ next = strm->next_in;
+ have = strm->avail_in;
+ strm->next_in = Z_NULL; /* so Z_BUF_ERROR means EOF */
+
+ /* check trailer */
+ ret = Z_BUF_ERROR;
+ if (NEXT() != (outd.crc & 0xff) ||
+ NEXT() != ((outd.crc >> 8) & 0xff) ||
+ NEXT() != ((outd.crc >> 16) & 0xff) ||
+ NEXT() != ((outd.crc >> 24) & 0xff)) {
+ /* crc error */
+ if (last != -1) {
+ strm->msg = (char *)"incorrect data check";
+ ret = Z_DATA_ERROR;
+ }
+ break;
+ }
+ if (NEXT() != (outd.total & 0xff) ||
+ NEXT() != ((outd.total >> 8) & 0xff) ||
+ NEXT() != ((outd.total >> 16) & 0xff) ||
+ NEXT() != ((outd.total >> 24) & 0xff)) {
+ /* length error */
+ if (last != -1) {
+ strm->msg = (char *)"incorrect length check";
+ ret = Z_DATA_ERROR;
+ }
+ break;
+ }
+
+ /* go back and look for another gzip stream */
+ }
+
+ /* clean up and return */
+ return ret;
+}
+
+/* Copy file attributes, from -> to, as best we can. This is best effort, so
+ no errors are reported. The mode bits, including suid, sgid, and the sticky
+ bit are copied (if allowed), the owner's user id and group id are copied
+ (again if allowed), and the access and modify times are copied. */
+local void copymeta(char *from, char *to)
+{
+ struct stat was;
+ struct utimbuf when;
+
+ /* get all of from's Unix meta data, return if not a regular file */
+ if (stat(from, &was) != 0 || (was.st_mode & S_IFMT) != S_IFREG)
+ return;
+
+ /* set to's mode bits, ignore errors */
+ (void)chmod(to, was.st_mode & 07777);
+
+ /* copy owner's user and group, ignore errors */
+ (void)chown(to, was.st_uid, was.st_gid);
+
+ /* copy access and modify times, ignore errors */
+ when.actime = was.st_atime;
+ when.modtime = was.st_mtime;
+ (void)utime(to, &when);
+}
+
+/* Decompress the file inname to the file outnname, of if test is true, just
+ decompress without writing and check the gzip trailer for integrity. If
+ inname is NULL or an empty string, read from stdin. If outname is NULL or
+ an empty string, write to stdout. strm is a pre-initialized inflateBack
+ structure. When appropriate, copy the file attributes from inname to
+ outname.
+
+ gunzip() returns 1 if there is an out-of-memory error or an unexpected
+ return code from gunpipe(). Otherwise it returns 0.
+ */
+local int gunzip(z_stream *strm, char *inname, char *outname, int test)
+{
+ int ret;
+ int infile, outfile;
+
+ /* open files */
+ if (inname == NULL || *inname == 0) {
+ inname = "-";
+ infile = 0; /* stdin */
+ }
+ else {
+ infile = open(inname, O_RDONLY, 0);
+ if (infile == -1) {
+ fprintf(stderr, "gun cannot open %s\n", inname);
+ return 0;
+ }
+ }
+ if (test)
+ outfile = -1;
+ else if (outname == NULL || *outname == 0) {
+ outname = "-";
+ outfile = 1; /* stdout */
+ }
+ else {
+ outfile = open(outname, O_CREAT | O_TRUNC | O_WRONLY, 0666);
+ if (outfile == -1) {
+ close(infile);
+ fprintf(stderr, "gun cannot create %s\n", outname);
+ return 0;
+ }
+ }
+ errno = 0;
+
+ /* decompress */
+ ret = gunpipe(strm, infile, outfile);
+ if (outfile > 2) close(outfile);
+ if (infile > 2) close(infile);
+
+ /* interpret result */
+ switch (ret) {
+ case Z_OK:
+ case Z_ERRNO:
+ if (infile > 2 && outfile > 2) {
+ copymeta(inname, outname); /* copy attributes */
+ unlink(inname);
+ }
+ if (ret == Z_ERRNO)
+ fprintf(stderr, "gun warning: trailing garbage ignored in %s\n",
+ inname);
+ break;
+ case Z_DATA_ERROR:
+ if (outfile > 2) unlink(outname);
+ fprintf(stderr, "gun data error on %s: %s\n", inname, strm->msg);
+ break;
+ case Z_MEM_ERROR:
+ if (outfile > 2) unlink(outname);
+ fprintf(stderr, "gun out of memory error--aborting\n");
+ return 1;
+ case Z_BUF_ERROR:
+ if (outfile > 2) unlink(outname);
+ if (strm->next_in != Z_NULL) {
+ fprintf(stderr, "gun write error on %s: %s\n",
+ outname, strerror(errno));
+ }
+ else if (errno) {
+ fprintf(stderr, "gun read error on %s: %s\n",
+ inname, strerror(errno));
+ }
+ else {
+ fprintf(stderr, "gun unexpected end of file on %s\n",
+ inname);
+ }
+ break;
+ default:
+ if (outfile > 2) unlink(outname);
+ fprintf(stderr, "gun internal error--aborting\n");
+ return 1;
+ }
+ return 0;
+}
+
+/* Process the gun command line arguments. See the command syntax near the
+ beginning of this source file. */
+int main(int argc, char **argv)
+{
+ int ret, len, test;
+ char *outname;
+ unsigned char *window;
+ z_stream strm;
+
+ /* initialize inflateBack state for repeated use */
+ window = match; /* reuse LZW match buffer */
+ strm.zalloc = Z_NULL;
+ strm.zfree = Z_NULL;
+ strm.opaque = Z_NULL;
+ ret = inflateBackInit(&strm, 15, window);
+ if (ret != Z_OK) {
+ fprintf(stderr, "gun out of memory error--aborting\n");
+ return 1;
+ }
+
+ /* decompress each file to the same name with the suffix removed */
+ argc--;
+ argv++;
+ test = 0;
+ if (argc && strcmp(*argv, "-h") == 0) {
+ fprintf(stderr, "gun 1.3 (12 Jun 2005)\n");
+ fprintf(stderr, "Copyright (c) 2005 Mark Adler\n");
+ fprintf(stderr, "usage: gun [-t] [file1.gz [file2.Z ...]]\n");
+ return 0;
+ }
+ if (argc && strcmp(*argv, "-t") == 0) {
+ test = 1;
+ argc--;
+ argv++;
+ }
+ if (argc)
+ do {
+ if (test)
+ outname = NULL;
+ else {
+ len = (int)strlen(*argv);
+ if (strcmp(*argv + len - 3, ".gz") == 0 ||
+ strcmp(*argv + len - 3, "-gz") == 0)
+ len -= 3;
+ else if (strcmp(*argv + len - 2, ".z") == 0 ||
+ strcmp(*argv + len - 2, "-z") == 0 ||
+ strcmp(*argv + len - 2, "_z") == 0 ||
+ strcmp(*argv + len - 2, ".Z") == 0)
+ len -= 2;
+ else {
+ fprintf(stderr, "gun error: no gz type on %s--skipping\n",
+ *argv);
+ continue;
+ }
+ outname = malloc(len + 1);
+ if (outname == NULL) {
+ fprintf(stderr, "gun out of memory error--aborting\n");
+ ret = 1;
+ break;
+ }
+ memcpy(outname, *argv, len);
+ outname[len] = 0;
+ }
+ ret = gunzip(&strm, *argv, outname, test);
+ if (outname != NULL) free(outname);
+ if (ret) break;
+ } while (argv++, --argc);
+ else
+ ret = gunzip(&strm, NULL, NULL, test);
+
+ /* clean up */
+ inflateBackEnd(&strm);
+ return ret;
+}
diff --git a/Modules/zlib/examples/gzappend.c b/Modules/zlib/examples/gzappend.c
new file mode 100644
index 0000000..e9e878e
--- /dev/null
+++ b/Modules/zlib/examples/gzappend.c
@@ -0,0 +1,500 @@
+/* gzappend -- command to append to a gzip file
+
+ Copyright (C) 2003 Mark Adler, all rights reserved
+ version 1.1, 4 Nov 2003
+
+ This software is provided 'as-is', without any express or implied
+ warranty. In no event will the author be held liable for any damages
+ arising from the use of this software.
+
+ Permission is granted to anyone to use this software for any purpose,
+ including commercial applications, and to alter it and redistribute it
+ freely, subject to the following restrictions:
+
+ 1. The origin of this software must not be misrepresented; you must not
+ claim that you wrote the original software. If you use this software
+ in a product, an acknowledgment in the product documentation would be
+ appreciated but is not required.
+ 2. Altered source versions must be plainly marked as such, and must not be
+ misrepresented as being the original software.
+ 3. This notice may not be removed or altered from any source distribution.
+
+ Mark Adler madler@alumni.caltech.edu
+ */
+
+/*
+ * Change history:
+ *
+ * 1.0 19 Oct 2003 - First version
+ * 1.1 4 Nov 2003 - Expand and clarify some comments and notes
+ * - Add version and copyright to help
+ * - Send help to stdout instead of stderr
+ * - Add some preemptive typecasts
+ * - Add L to constants in lseek() calls
+ * - Remove some debugging information in error messages
+ * - Use new data_type definition for zlib 1.2.1
+ * - Simplfy and unify file operations
+ * - Finish off gzip file in gztack()
+ * - Use deflatePrime() instead of adding empty blocks
+ * - Keep gzip file clean on appended file read errors
+ * - Use in-place rotate instead of auxiliary buffer
+ * (Why you ask? Because it was fun to write!)
+ */
+
+/*
+ gzappend takes a gzip file and appends to it, compressing files from the
+ command line or data from stdin. The gzip file is written to directly, to
+ avoid copying that file, in case it's large. Note that this results in the
+ unfriendly behavior that if gzappend fails, the gzip file is corrupted.
+
+ This program was written to illustrate the use of the new Z_BLOCK option of
+ zlib 1.2.x's inflate() function. This option returns from inflate() at each
+ block boundary to facilitate locating and modifying the last block bit at
+ the start of the final deflate block. Also whether using Z_BLOCK or not,
+ another required feature of zlib 1.2.x is that inflate() now provides the
+ number of unusued bits in the last input byte used. gzappend will not work
+ with versions of zlib earlier than 1.2.1.
+
+ gzappend first decompresses the gzip file internally, discarding all but
+ the last 32K of uncompressed data, and noting the location of the last block
+ bit and the number of unused bits in the last byte of the compressed data.
+ The gzip trailer containing the CRC-32 and length of the uncompressed data
+ is verified. This trailer will be later overwritten.
+
+ Then the last block bit is cleared by seeking back in the file and rewriting
+ the byte that contains it. Seeking forward, the last byte of the compressed
+ data is saved along with the number of unused bits to initialize deflate.
+
+ A deflate process is initialized, using the last 32K of the uncompressed
+ data from the gzip file to initialize the dictionary. If the total
+ uncompressed data was less than 32K, then all of it is used to initialize
+ the dictionary. The deflate output bit buffer is also initialized with the
+ last bits from the original deflate stream. From here on, the data to
+ append is simply compressed using deflate, and written to the gzip file.
+ When that is complete, the new CRC-32 and uncompressed length are written
+ as the trailer of the gzip file.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include "zlib.h"
+
+#define local static
+#define LGCHUNK 14
+#define CHUNK (1U << LGCHUNK)
+#define DSIZE 32768U
+
+/* print an error message and terminate with extreme prejudice */
+local void bye(char *msg1, char *msg2)
+{
+ fprintf(stderr, "gzappend error: %s%s\n", msg1, msg2);
+ exit(1);
+}
+
+/* return the greatest common divisor of a and b using Euclid's algorithm,
+ modified to be fast when one argument much greater than the other, and
+ coded to avoid unnecessary swapping */
+local unsigned gcd(unsigned a, unsigned b)
+{
+ unsigned c;
+
+ while (a && b)
+ if (a > b) {
+ c = b;
+ while (a - c >= c)
+ c <<= 1;
+ a -= c;
+ }
+ else {
+ c = a;
+ while (b - c >= c)
+ c <<= 1;
+ b -= c;
+ }
+ return a + b;
+}
+
+/* rotate list[0..len-1] left by rot positions, in place */
+local void rotate(unsigned char *list, unsigned len, unsigned rot)
+{
+ unsigned char tmp;
+ unsigned cycles;
+ unsigned char *start, *last, *to, *from;
+
+ /* normalize rot and handle degenerate cases */
+ if (len < 2) return;
+ if (rot >= len) rot %= len;
+ if (rot == 0) return;
+
+ /* pointer to last entry in list */
+ last = list + (len - 1);
+
+ /* do simple left shift by one */
+ if (rot == 1) {
+ tmp = *list;
+ memcpy(list, list + 1, len - 1);
+ *last = tmp;
+ return;
+ }
+
+ /* do simple right shift by one */
+ if (rot == len - 1) {
+ tmp = *last;
+ memmove(list + 1, list, len - 1);
+ *list = tmp;
+ return;
+ }
+
+ /* otherwise do rotate as a set of cycles in place */
+ cycles = gcd(len, rot); /* number of cycles */
+ do {
+ start = from = list + cycles; /* start index is arbitrary */
+ tmp = *from; /* save entry to be overwritten */
+ for (;;) {
+ to = from; /* next step in cycle */
+ from += rot; /* go right rot positions */
+ if (from > last) from -= len; /* (pointer better not wrap) */
+ if (from == start) break; /* all but one shifted */
+ *to = *from; /* shift left */
+ }
+ *to = tmp; /* complete the circle */
+ } while (--cycles);
+}
+
+/* structure for gzip file read operations */
+typedef struct {
+ int fd; /* file descriptor */
+ int size; /* 1 << size is bytes in buf */
+ unsigned left; /* bytes available at next */
+ unsigned char *buf; /* buffer */
+ unsigned char *next; /* next byte in buffer */
+ char *name; /* file name for error messages */
+} file;
+
+/* reload buffer */
+local int readin(file *in)
+{
+ int len;
+
+ len = read(in->fd, in->buf, 1 << in->size);
+ if (len == -1) bye("error reading ", in->name);
+ in->left = (unsigned)len;
+ in->next = in->buf;
+ return len;
+}
+
+/* read from file in, exit if end-of-file */
+local int readmore(file *in)
+{
+ if (readin(in) == 0) bye("unexpected end of ", in->name);
+ return 0;
+}
+
+#define read1(in) (in->left == 0 ? readmore(in) : 0, \
+ in->left--, *(in->next)++)
+
+/* skip over n bytes of in */
+local void skip(file *in, unsigned n)
+{
+ unsigned bypass;
+
+ if (n > in->left) {
+ n -= in->left;
+ bypass = n & ~((1U << in->size) - 1);
+ if (bypass) {
+ if (lseek(in->fd, (off_t)bypass, SEEK_CUR) == -1)
+ bye("seeking ", in->name);
+ n -= bypass;
+ }
+ readmore(in);
+ if (n > in->left)
+ bye("unexpected end of ", in->name);
+ }
+ in->left -= n;
+ in->next += n;
+}
+
+/* read a four-byte unsigned integer, little-endian, from in */
+unsigned long read4(file *in)
+{
+ unsigned long val;
+
+ val = read1(in);
+ val += (unsigned)read1(in) << 8;
+ val += (unsigned long)read1(in) << 16;
+ val += (unsigned long)read1(in) << 24;
+ return val;
+}
+
+/* skip over gzip header */
+local void gzheader(file *in)
+{
+ int flags;
+ unsigned n;
+
+ if (read1(in) != 31 || read1(in) != 139) bye(in->name, " not a gzip file");
+ if (read1(in) != 8) bye("unknown compression method in", in->name);
+ flags = read1(in);
+ if (flags & 0xe0) bye("unknown header flags set in", in->name);
+ skip(in, 6);
+ if (flags & 4) {
+ n = read1(in);
+ n += (unsigned)(read1(in)) << 8;
+ skip(in, n);
+ }
+ if (flags & 8) while (read1(in) != 0) ;
+ if (flags & 16) while (read1(in) != 0) ;
+ if (flags & 2) skip(in, 2);
+}
+
+/* decompress gzip file "name", return strm with a deflate stream ready to
+ continue compression of the data in the gzip file, and return a file
+ descriptor pointing to where to write the compressed data -- the deflate
+ stream is initialized to compress using level "level" */
+local int gzscan(char *name, z_stream *strm, int level)
+{
+ int ret, lastbit, left, full;
+ unsigned have;
+ unsigned long crc, tot;
+ unsigned char *window;
+ off_t lastoff, end;
+ file gz;
+
+ /* open gzip file */
+ gz.name = name;
+ gz.fd = open(name, O_RDWR, 0);
+ if (gz.fd == -1) bye("cannot open ", name);
+ gz.buf = malloc(CHUNK);
+ if (gz.buf == NULL) bye("out of memory", "");
+ gz.size = LGCHUNK;
+ gz.left = 0;
+
+ /* skip gzip header */
+ gzheader(&gz);
+
+ /* prepare to decompress */
+ window = malloc(DSIZE);
+ if (window == NULL) bye("out of memory", "");
+ strm->zalloc = Z_NULL;
+ strm->zfree = Z_NULL;
+ strm->opaque = Z_NULL;
+ ret = inflateInit2(strm, -15);
+ if (ret != Z_OK) bye("out of memory", " or library mismatch");
+
+ /* decompress the deflate stream, saving append information */
+ lastbit = 0;
+ lastoff = lseek(gz.fd, 0L, SEEK_CUR) - gz.left;
+ left = 0;
+ strm->avail_in = gz.left;
+ strm->next_in = gz.next;
+ crc = crc32(0L, Z_NULL, 0);
+ have = full = 0;
+ do {
+ /* if needed, get more input */
+ if (strm->avail_in == 0) {
+ readmore(&gz);
+ strm->avail_in = gz.left;
+ strm->next_in = gz.next;
+ }
+
+ /* set up output to next available section of sliding window */
+ strm->avail_out = DSIZE - have;
+ strm->next_out = window + have;
+
+ /* inflate and check for errors */
+ ret = inflate(strm, Z_BLOCK);
+ if (ret == Z_STREAM_ERROR) bye("internal stream error!", "");
+ if (ret == Z_MEM_ERROR) bye("out of memory", "");
+ if (ret == Z_DATA_ERROR)
+ bye("invalid compressed data--format violated in", name);
+
+ /* update crc and sliding window pointer */
+ crc = crc32(crc, window + have, DSIZE - have - strm->avail_out);
+ if (strm->avail_out)
+ have = DSIZE - strm->avail_out;
+ else {
+ have = 0;
+ full = 1;
+ }
+
+ /* process end of block */
+ if (strm->data_type & 128) {
+ if (strm->data_type & 64)
+ left = strm->data_type & 0x1f;
+ else {
+ lastbit = strm->data_type & 0x1f;
+ lastoff = lseek(gz.fd, 0L, SEEK_CUR) - strm->avail_in;
+ }
+ }
+ } while (ret != Z_STREAM_END);
+ inflateEnd(strm);
+ gz.left = strm->avail_in;
+ gz.next = strm->next_in;
+
+ /* save the location of the end of the compressed data */
+ end = lseek(gz.fd, 0L, SEEK_CUR) - gz.left;
+
+ /* check gzip trailer and save total for deflate */
+ if (crc != read4(&gz))
+ bye("invalid compressed data--crc mismatch in ", name);
+ tot = strm->total_out;
+ if ((tot & 0xffffffffUL) != read4(&gz))
+ bye("invalid compressed data--length mismatch in", name);
+
+ /* if not at end of file, warn */
+ if (gz.left || readin(&gz))
+ fprintf(stderr,
+ "gzappend warning: junk at end of gzip file overwritten\n");
+
+ /* clear last block bit */
+ lseek(gz.fd, lastoff - (lastbit != 0), SEEK_SET);
+ if (read(gz.fd, gz.buf, 1) != 1) bye("reading after seek on ", name);
+ *gz.buf = (unsigned char)(*gz.buf ^ (1 << ((8 - lastbit) & 7)));
+ lseek(gz.fd, -1L, SEEK_CUR);
+ if (write(gz.fd, gz.buf, 1) != 1) bye("writing after seek to ", name);
+
+ /* if window wrapped, build dictionary from window by rotating */
+ if (full) {
+ rotate(window, DSIZE, have);
+ have = DSIZE;
+ }
+
+ /* set up deflate stream with window, crc, total_in, and leftover bits */
+ ret = deflateInit2(strm, level, Z_DEFLATED, -15, 8, Z_DEFAULT_STRATEGY);
+ if (ret != Z_OK) bye("out of memory", "");
+ deflateSetDictionary(strm, window, have);
+ strm->adler = crc;
+ strm->total_in = tot;
+ if (left) {
+ lseek(gz.fd, --end, SEEK_SET);
+ if (read(gz.fd, gz.buf, 1) != 1) bye("reading after seek on ", name);
+ deflatePrime(strm, 8 - left, *gz.buf);
+ }
+ lseek(gz.fd, end, SEEK_SET);
+
+ /* clean up and return */
+ free(window);
+ free(gz.buf);
+ return gz.fd;
+}
+
+/* append file "name" to gzip file gd using deflate stream strm -- if last
+ is true, then finish off the deflate stream at the end */
+local void gztack(char *name, int gd, z_stream *strm, int last)
+{
+ int fd, len, ret;
+ unsigned left;
+ unsigned char *in, *out;
+
+ /* open file to compress and append */
+ fd = 0;
+ if (name != NULL) {
+ fd = open(name, O_RDONLY, 0);
+ if (fd == -1)
+ fprintf(stderr, "gzappend warning: %s not found, skipping ...\n",
+ name);
+ }
+
+ /* allocate buffers */
+ in = fd == -1 ? NULL : malloc(CHUNK);
+ out = malloc(CHUNK);
+ if (out == NULL) bye("out of memory", "");
+
+ /* compress input file and append to gzip file */
+ do {
+ /* get more input */
+ len = fd == -1 ? 0 : read(fd, in, CHUNK);
+ if (len == -1) {
+ fprintf(stderr,
+ "gzappend warning: error reading %s, skipping rest ...\n",
+ name);
+ len = 0;
+ }
+ strm->avail_in = (unsigned)len;
+ strm->next_in = in;
+ if (len) strm->adler = crc32(strm->adler, in, (unsigned)len);
+
+ /* compress and write all available output */
+ do {
+ strm->avail_out = CHUNK;
+ strm->next_out = out;
+ ret = deflate(strm, last && len == 0 ? Z_FINISH : Z_NO_FLUSH);
+ left = CHUNK - strm->avail_out;
+ while (left) {
+ len = write(gd, out + CHUNK - strm->avail_out - left, left);
+ if (len == -1) bye("writing gzip file", "");
+ left -= (unsigned)len;
+ }
+ } while (strm->avail_out == 0 && ret != Z_STREAM_END);
+ } while (len != 0);
+
+ /* write trailer after last entry */
+ if (last) {
+ deflateEnd(strm);
+ out[0] = (unsigned char)(strm->adler);
+ out[1] = (unsigned char)(strm->adler >> 8);
+ out[2] = (unsigned char)(strm->adler >> 16);
+ out[3] = (unsigned char)(strm->adler >> 24);
+ out[4] = (unsigned char)(strm->total_in);
+ out[5] = (unsigned char)(strm->total_in >> 8);
+ out[6] = (unsigned char)(strm->total_in >> 16);
+ out[7] = (unsigned char)(strm->total_in >> 24);
+ len = 8;
+ do {
+ ret = write(gd, out + 8 - len, len);
+ if (ret == -1) bye("writing gzip file", "");
+ len -= ret;
+ } while (len);
+ close(gd);
+ }
+
+ /* clean up and return */
+ free(out);
+ if (in != NULL) free(in);
+ if (fd > 0) close(fd);
+}
+
+/* process the compression level option if present, scan the gzip file, and
+ append the specified files, or append the data from stdin if no other file
+ names are provided on the command line -- the gzip file must be writable
+ and seekable */
+int main(int argc, char **argv)
+{
+ int gd, level;
+ z_stream strm;
+
+ /* ignore command name */
+ argv++;
+
+ /* provide usage if no arguments */
+ if (*argv == NULL) {
+ printf("gzappend 1.1 (4 Nov 2003) Copyright (C) 2003 Mark Adler\n");
+ printf(
+ "usage: gzappend [-level] file.gz [ addthis [ andthis ... ]]\n");
+ return 0;
+ }
+
+ /* set compression level */
+ level = Z_DEFAULT_COMPRESSION;
+ if (argv[0][0] == '-') {
+ if (argv[0][1] < '0' || argv[0][1] > '9' || argv[0][2] != 0)
+ bye("invalid compression level", "");
+ level = argv[0][1] - '0';
+ if (*++argv == NULL) bye("no gzip file name after options", "");
+ }
+
+ /* prepare to append to gzip file */
+ gd = gzscan(*argv++, &strm, level);
+
+ /* append files on command line, or from stdin if none */
+ if (*argv == NULL)
+ gztack(NULL, gd, &strm, 1);
+ else
+ do {
+ gztack(*argv, gd, &strm, argv[1] == NULL);
+ } while (*++argv != NULL);
+ return 0;
+}
diff --git a/Modules/zlib/examples/gzjoin.c b/Modules/zlib/examples/gzjoin.c
new file mode 100644
index 0000000..129347c
--- /dev/null
+++ b/Modules/zlib/examples/gzjoin.c
@@ -0,0 +1,448 @@
+/* gzjoin -- command to join gzip files into one gzip file
+
+ Copyright (C) 2004 Mark Adler, all rights reserved
+ version 1.0, 11 Dec 2004
+
+ This software is provided 'as-is', without any express or implied
+ warranty. In no event will the author be held liable for any damages
+ arising from the use of this software.
+
+ Permission is granted to anyone to use this software for any purpose,
+ including commercial applications, and to alter it and redistribute it
+ freely, subject to the following restrictions:
+
+ 1. The origin of this software must not be misrepresented; you must not
+ claim that you wrote the original software. If you use this software
+ in a product, an acknowledgment in the product documentation would be
+ appreciated but is not required.
+ 2. Altered source versions must be plainly marked as such, and must not be
+ misrepresented as being the original software.
+ 3. This notice may not be removed or altered from any source distribution.
+
+ Mark Adler madler@alumni.caltech.edu
+ */
+
+/*
+ * Change history:
+ *
+ * 1.0 11 Dec 2004 - First version
+ * 1.1 12 Jun 2005 - Changed ssize_t to long for portability
+ */
+
+/*
+ gzjoin takes one or more gzip files on the command line and writes out a
+ single gzip file that will uncompress to the concatenation of the
+ uncompressed data from the individual gzip files. gzjoin does this without
+ having to recompress any of the data and without having to calculate a new
+ crc32 for the concatenated uncompressed data. gzjoin does however have to
+ decompress all of the input data in order to find the bits in the compressed
+ data that need to be modified to concatenate the streams.
+
+ gzjoin does not do an integrity check on the input gzip files other than
+ checking the gzip header and decompressing the compressed data. They are
+ otherwise assumed to be complete and correct.
+
+ Each joint between gzip files removes at least 18 bytes of previous trailer
+ and subsequent header, and inserts an average of about three bytes to the
+ compressed data in order to connect the streams. The output gzip file
+ has a minimal ten-byte gzip header with no file name or modification time.
+
+ This program was written to illustrate the use of the Z_BLOCK option of
+ inflate() and the crc32_combine() function. gzjoin will not compile with
+ versions of zlib earlier than 1.2.3.
+ */
+
+#include <stdio.h> /* fputs(), fprintf(), fwrite(), putc() */
+#include <stdlib.h> /* exit(), malloc(), free() */
+#include <fcntl.h> /* open() */
+#include <unistd.h> /* close(), read(), lseek() */
+#include "zlib.h"
+ /* crc32(), crc32_combine(), inflateInit2(), inflate(), inflateEnd() */
+
+#define local static
+
+/* exit with an error (return a value to allow use in an expression) */
+local int bail(char *why1, char *why2)
+{
+ fprintf(stderr, "gzjoin error: %s%s, output incomplete\n", why1, why2);
+ exit(1);
+ return 0;
+}
+
+/* -- simple buffered file input with access to the buffer -- */
+
+#define CHUNK 32768 /* must be a power of two and fit in unsigned */
+
+/* bin buffered input file type */
+typedef struct {
+ char *name; /* name of file for error messages */
+ int fd; /* file descriptor */
+ unsigned left; /* bytes remaining at next */
+ unsigned char *next; /* next byte to read */
+ unsigned char *buf; /* allocated buffer of length CHUNK */
+} bin;
+
+/* close a buffered file and free allocated memory */
+local void bclose(bin *in)
+{
+ if (in != NULL) {
+ if (in->fd != -1)
+ close(in->fd);
+ if (in->buf != NULL)
+ free(in->buf);
+ free(in);
+ }
+}
+
+/* open a buffered file for input, return a pointer to type bin, or NULL on
+ failure */
+local bin *bopen(char *name)
+{
+ bin *in;
+
+ in = malloc(sizeof(bin));
+ if (in == NULL)
+ return NULL;
+ in->buf = malloc(CHUNK);
+ in->fd = open(name, O_RDONLY, 0);
+ if (in->buf == NULL || in->fd == -1) {
+ bclose(in);
+ return NULL;
+ }
+ in->left = 0;
+ in->next = in->buf;
+ in->name = name;
+ return in;
+}
+
+/* load buffer from file, return -1 on read error, 0 or 1 on success, with
+ 1 indicating that end-of-file was reached */
+local int bload(bin *in)
+{
+ long len;
+
+ if (in == NULL)
+ return -1;
+ if (in->left != 0)
+ return 0;
+ in->next = in->buf;
+ do {
+ len = (long)read(in->fd, in->buf + in->left, CHUNK - in->left);
+ if (len < 0)
+ return -1;
+ in->left += (unsigned)len;
+ } while (len != 0 && in->left < CHUNK);
+ return len == 0 ? 1 : 0;
+}
+
+/* get a byte from the file, bail if end of file */
+#define bget(in) (in->left ? 0 : bload(in), \
+ in->left ? (in->left--, *(in->next)++) : \
+ bail("unexpected end of file on ", in->name))
+
+/* get a four-byte little-endian unsigned integer from file */
+local unsigned long bget4(bin *in)
+{
+ unsigned long val;
+
+ val = bget(in);
+ val += (unsigned long)(bget(in)) << 8;
+ val += (unsigned long)(bget(in)) << 16;
+ val += (unsigned long)(bget(in)) << 24;
+ return val;
+}
+
+/* skip bytes in file */
+local void bskip(bin *in, unsigned skip)
+{
+ /* check pointer */
+ if (in == NULL)
+ return;
+
+ /* easy case -- skip bytes in buffer */
+ if (skip <= in->left) {
+ in->left -= skip;
+ in->next += skip;
+ return;
+ }
+
+ /* skip what's in buffer, discard buffer contents */
+ skip -= in->left;
+ in->left = 0;
+
+ /* seek past multiples of CHUNK bytes */
+ if (skip > CHUNK) {
+ unsigned left;
+
+ left = skip & (CHUNK - 1);
+ if (left == 0) {
+ /* exact number of chunks: seek all the way minus one byte to check
+ for end-of-file with a read */
+ lseek(in->fd, skip - 1, SEEK_CUR);
+ if (read(in->fd, in->buf, 1) != 1)
+ bail("unexpected end of file on ", in->name);
+ return;
+ }
+
+ /* skip the integral chunks, update skip with remainder */
+ lseek(in->fd, skip - left, SEEK_CUR);
+ skip = left;
+ }
+
+ /* read more input and skip remainder */
+ bload(in);
+ if (skip > in->left)
+ bail("unexpected end of file on ", in->name);
+ in->left -= skip;
+ in->next += skip;
+}
+
+/* -- end of buffered input functions -- */
+
+/* skip the gzip header from file in */
+local void gzhead(bin *in)
+{
+ int flags;
+
+ /* verify gzip magic header and compression method */
+ if (bget(in) != 0x1f || bget(in) != 0x8b || bget(in) != 8)
+ bail(in->name, " is not a valid gzip file");
+
+ /* get and verify flags */
+ flags = bget(in);
+ if ((flags & 0xe0) != 0)
+ bail("unknown reserved bits set in ", in->name);
+
+ /* skip modification time, extra flags, and os */
+ bskip(in, 6);
+
+ /* skip extra field if present */
+ if (flags & 4) {
+ unsigned len;
+
+ len = bget(in);
+ len += (unsigned)(bget(in)) << 8;
+ bskip(in, len);
+ }
+
+ /* skip file name if present */
+ if (flags & 8)
+ while (bget(in) != 0)
+ ;
+
+ /* skip comment if present */
+ if (flags & 16)
+ while (bget(in) != 0)
+ ;
+
+ /* skip header crc if present */
+ if (flags & 2)
+ bskip(in, 2);
+}
+
+/* write a four-byte little-endian unsigned integer to out */
+local void put4(unsigned long val, FILE *out)
+{
+ putc(val & 0xff, out);
+ putc((val >> 8) & 0xff, out);
+ putc((val >> 16) & 0xff, out);
+ putc((val >> 24) & 0xff, out);
+}
+
+/* Load up zlib stream from buffered input, bail if end of file */
+local void zpull(z_streamp strm, bin *in)
+{
+ if (in->left == 0)
+ bload(in);
+ if (in->left == 0)
+ bail("unexpected end of file on ", in->name);
+ strm->avail_in = in->left;
+ strm->next_in = in->next;
+}
+
+/* Write header for gzip file to out and initialize trailer. */
+local void gzinit(unsigned long *crc, unsigned long *tot, FILE *out)
+{
+ fwrite("\x1f\x8b\x08\0\0\0\0\0\0\xff", 1, 10, out);
+ *crc = crc32(0L, Z_NULL, 0);
+ *tot = 0;
+}
+
+/* Copy the compressed data from name, zeroing the last block bit of the last
+ block if clr is true, and adding empty blocks as needed to get to a byte
+ boundary. If clr is false, then the last block becomes the last block of
+ the output, and the gzip trailer is written. crc and tot maintains the
+ crc and length (modulo 2^32) of the output for the trailer. The resulting
+ gzip file is written to out. gzinit() must be called before the first call
+ of gzcopy() to write the gzip header and to initialize crc and tot. */
+local void gzcopy(char *name, int clr, unsigned long *crc, unsigned long *tot,
+ FILE *out)
+{
+ int ret; /* return value from zlib functions */
+ int pos; /* where the "last block" bit is in byte */
+ int last; /* true if processing the last block */
+ bin *in; /* buffered input file */
+ unsigned char *start; /* start of compressed data in buffer */
+ unsigned char *junk; /* buffer for uncompressed data -- discarded */
+ z_off_t len; /* length of uncompressed data (support > 4 GB) */
+ z_stream strm; /* zlib inflate stream */
+
+ /* open gzip file and skip header */
+ in = bopen(name);
+ if (in == NULL)
+ bail("could not open ", name);
+ gzhead(in);
+
+ /* allocate buffer for uncompressed data and initialize raw inflate
+ stream */
+ junk = malloc(CHUNK);
+ strm.zalloc = Z_NULL;
+ strm.zfree = Z_NULL;
+ strm.opaque = Z_NULL;
+ strm.avail_in = 0;
+ strm.next_in = Z_NULL;
+ ret = inflateInit2(&strm, -15);
+ if (junk == NULL || ret != Z_OK)
+ bail("out of memory", "");
+
+ /* inflate and copy compressed data, clear last-block bit if requested */
+ len = 0;
+ zpull(&strm, in);
+ start = strm.next_in;
+ last = start[0] & 1;
+ if (last && clr)
+ start[0] &= ~1;
+ strm.avail_out = 0;
+ for (;;) {
+ /* if input used and output done, write used input and get more */
+ if (strm.avail_in == 0 && strm.avail_out != 0) {
+ fwrite(start, 1, strm.next_in - start, out);
+ start = in->buf;
+ in->left = 0;
+ zpull(&strm, in);
+ }
+
+ /* decompress -- return early when end-of-block reached */
+ strm.avail_out = CHUNK;
+ strm.next_out = junk;
+ ret = inflate(&strm, Z_BLOCK);
+ switch (ret) {
+ case Z_MEM_ERROR:
+ bail("out of memory", "");
+ case Z_DATA_ERROR:
+ bail("invalid compressed data in ", in->name);
+ }
+
+ /* update length of uncompressed data */
+ len += CHUNK - strm.avail_out;
+
+ /* check for block boundary (only get this when block copied out) */
+ if (strm.data_type & 128) {
+ /* if that was the last block, then done */
+ if (last)
+ break;
+
+ /* number of unused bits in last byte */
+ pos = strm.data_type & 7;
+
+ /* find the next last-block bit */
+ if (pos != 0) {
+ /* next last-block bit is in last used byte */
+ pos = 0x100 >> pos;
+ last = strm.next_in[-1] & pos;
+ if (last && clr)
+ strm.next_in[-1] &= ~pos;
+ }
+ else {
+ /* next last-block bit is in next unused byte */
+ if (strm.avail_in == 0) {
+ /* don't have that byte yet -- get it */
+ fwrite(start, 1, strm.next_in - start, out);
+ start = in->buf;
+ in->left = 0;
+ zpull(&strm, in);
+ }
+ last = strm.next_in[0] & 1;
+ if (last && clr)
+ strm.next_in[0] &= ~1;
+ }
+ }
+ }
+
+ /* update buffer with unused input */
+ in->left = strm.avail_in;
+ in->next = strm.next_in;
+
+ /* copy used input, write empty blocks to get to byte boundary */
+ pos = strm.data_type & 7;
+ fwrite(start, 1, in->next - start - 1, out);
+ last = in->next[-1];
+ if (pos == 0 || !clr)
+ /* already at byte boundary, or last file: write last byte */
+ putc(last, out);
+ else {
+ /* append empty blocks to last byte */
+ last &= ((0x100 >> pos) - 1); /* assure unused bits are zero */
+ if (pos & 1) {
+ /* odd -- append an empty stored block */
+ putc(last, out);
+ if (pos == 1)
+ putc(0, out); /* two more bits in block header */
+ fwrite("\0\0\xff\xff", 1, 4, out);
+ }
+ else {
+ /* even -- append 1, 2, or 3 empty fixed blocks */
+ switch (pos) {
+ case 6:
+ putc(last | 8, out);
+ last = 0;
+ case 4:
+ putc(last | 0x20, out);
+ last = 0;
+ case 2:
+ putc(last | 0x80, out);
+ putc(0, out);
+ }
+ }
+ }
+
+ /* update crc and tot */
+ *crc = crc32_combine(*crc, bget4(in), len);
+ *tot += (unsigned long)len;
+
+ /* clean up */
+ inflateEnd(&strm);
+ free(junk);
+ bclose(in);
+
+ /* write trailer if this is the last gzip file */
+ if (!clr) {
+ put4(*crc, out);
+ put4(*tot, out);
+ }
+}
+
+/* join the gzip files on the command line, write result to stdout */
+int main(int argc, char **argv)
+{
+ unsigned long crc, tot; /* running crc and total uncompressed length */
+
+ /* skip command name */
+ argc--;
+ argv++;
+
+ /* show usage if no arguments */
+ if (argc == 0) {
+ fputs("gzjoin usage: gzjoin f1.gz [f2.gz [f3.gz ...]] > fjoin.gz\n",
+ stderr);
+ return 0;
+ }
+
+ /* join gzip files on command line and write to stdout */
+ gzinit(&crc, &tot, stdout);
+ while (argc--)
+ gzcopy(*argv++, argc, &crc, &tot, stdout);
+
+ /* done */
+ return 0;
+}
diff --git a/Modules/zlib/examples/gzlog.c b/Modules/zlib/examples/gzlog.c
new file mode 100644
index 0000000..f71f817
--- /dev/null
+++ b/Modules/zlib/examples/gzlog.c
@@ -0,0 +1,413 @@
+/*
+ * gzlog.c
+ * Copyright (C) 2004 Mark Adler
+ * For conditions of distribution and use, see copyright notice in gzlog.h
+ * version 1.0, 26 Nov 2004
+ *
+ */
+
+#include <string.h> /* memcmp() */
+#include <stdlib.h> /* malloc(), free(), NULL */
+#include <sys/types.h> /* size_t, off_t */
+#include <unistd.h> /* read(), close(), sleep(), ftruncate(), */
+ /* lseek() */
+#include <fcntl.h> /* open() */
+#include <sys/file.h> /* flock() */
+#include "zlib.h" /* deflateInit2(), deflate(), deflateEnd() */
+
+#include "gzlog.h" /* interface */
+#define local static
+
+/* log object structure */
+typedef struct {
+ int id; /* object identifier */
+ int fd; /* log file descriptor */
+ off_t extra; /* offset of extra "ap" subfield */
+ off_t mark_off; /* offset of marked data */
+ off_t last_off; /* offset of last block */
+ unsigned long crc; /* uncompressed crc */
+ unsigned long len; /* uncompressed length (modulo 2^32) */
+ unsigned stored; /* length of current stored block */
+} gz_log;
+
+#define GZLOGID 19334 /* gz_log object identifier */
+
+#define LOCK_RETRY 1 /* retry lock once a second */
+#define LOCK_PATIENCE 1200 /* try about twenty minutes before forcing */
+
+/* acquire a lock on a file */
+local int lock(int fd)
+{
+ int patience;
+
+ /* try to lock every LOCK_RETRY seconds for LOCK_PATIENCE seconds */
+ patience = LOCK_PATIENCE;
+ do {
+ if (flock(fd, LOCK_EX + LOCK_NB) == 0)
+ return 0;
+ (void)sleep(LOCK_RETRY);
+ patience -= LOCK_RETRY;
+ } while (patience > 0);
+
+ /* we've run out of patience -- give up */
+ return -1;
+}
+
+/* release lock */
+local void unlock(int fd)
+{
+ (void)flock(fd, LOCK_UN);
+}
+
+/* release a log object */
+local void log_clean(gz_log *log)
+{
+ unlock(log->fd);
+ (void)close(log->fd);
+ free(log);
+}
+
+/* read an unsigned long from a byte buffer little-endian */
+local unsigned long make_ulg(unsigned char *buf)
+{
+ int n;
+ unsigned long val;
+
+ val = (unsigned long)(*buf++);
+ for (n = 8; n < 32; n += 8)
+ val += (unsigned long)(*buf++) << n;
+ return val;
+}
+
+/* read an off_t from a byte buffer little-endian */
+local off_t make_off(unsigned char *buf)
+{
+ int n;
+ off_t val;
+
+ val = (off_t)(*buf++);
+ for (n = 8; n < 64; n += 8)
+ val += (off_t)(*buf++) << n;
+ return val;
+}
+
+/* write an unsigned long little-endian to byte buffer */
+local void dice_ulg(unsigned long val, unsigned char *buf)
+{
+ int n;
+
+ for (n = 0; n < 4; n++) {
+ *buf++ = val & 0xff;
+ val >>= 8;
+ }
+}
+
+/* write an off_t little-endian to byte buffer */
+local void dice_off(off_t val, unsigned char *buf)
+{
+ int n;
+
+ for (n = 0; n < 8; n++) {
+ *buf++ = val & 0xff;
+ val >>= 8;
+ }
+}
+
+/* initial, empty gzip file for appending */
+local char empty_gz[] = {
+ 0x1f, 0x8b, /* magic gzip id */
+ 8, /* compression method is deflate */
+ 4, /* there is an extra field */
+ 0, 0, 0, 0, /* no modification time provided */
+ 0, 0xff, /* no extra flags, no OS */
+ 20, 0, 'a', 'p', 16, 0, /* extra field with "ap" subfield */
+ 32, 0, 0, 0, 0, 0, 0, 0, /* offset of uncompressed data */
+ 32, 0, 0, 0, 0, 0, 0, 0, /* offset of last block */
+ 1, 0, 0, 0xff, 0xff, /* empty stored block (last) */
+ 0, 0, 0, 0, /* crc */
+ 0, 0, 0, 0 /* uncompressed length */
+};
+
+/* initialize a log object with locking */
+void *gzlog_open(char *path)
+{
+ unsigned xlen;
+ unsigned char temp[20];
+ unsigned sub_len;
+ int good;
+ gz_log *log;
+
+ /* allocate log structure */
+ log = malloc(sizeof(gz_log));
+ if (log == NULL)
+ return NULL;
+ log->id = GZLOGID;
+
+ /* open file, creating it if necessary, and locking it */
+ log->fd = open(path, O_RDWR | O_CREAT, 0600);
+ if (log->fd < 0) {
+ free(log);
+ return NULL;
+ }
+ if (lock(log->fd)) {
+ close(log->fd);
+ free(log);
+ return NULL;
+ }
+
+ /* if file is empty, write new gzip stream */
+ if (lseek(log->fd, 0, SEEK_END) == 0) {
+ if (write(log->fd, empty_gz, sizeof(empty_gz)) != sizeof(empty_gz)) {
+ log_clean(log);
+ return NULL;
+ }
+ }
+
+ /* check gzip header */
+ (void)lseek(log->fd, 0, SEEK_SET);
+ if (read(log->fd, temp, 12) != 12 || temp[0] != 0x1f ||
+ temp[1] != 0x8b || temp[2] != 8 || (temp[3] & 4) == 0) {
+ log_clean(log);
+ return NULL;
+ }
+
+ /* process extra field to find "ap" sub-field */
+ xlen = temp[10] + (temp[11] << 8);
+ good = 0;
+ while (xlen) {
+ if (xlen < 4 || read(log->fd, temp, 4) != 4)
+ break;
+ sub_len = temp[2];
+ sub_len += temp[3] << 8;
+ xlen -= 4;
+ if (memcmp(temp, "ap", 2) == 0 && sub_len == 16) {
+ good = 1;
+ break;
+ }
+ if (xlen < sub_len)
+ break;
+ (void)lseek(log->fd, sub_len, SEEK_CUR);
+ xlen -= sub_len;
+ }
+ if (!good) {
+ log_clean(log);
+ return NULL;
+ }
+
+ /* read in "ap" sub-field */
+ log->extra = lseek(log->fd, 0, SEEK_CUR);
+ if (read(log->fd, temp, 16) != 16) {
+ log_clean(log);
+ return NULL;
+ }
+ log->mark_off = make_off(temp);
+ log->last_off = make_off(temp + 8);
+
+ /* get crc, length of gzip file */
+ (void)lseek(log->fd, log->last_off, SEEK_SET);
+ if (read(log->fd, temp, 13) != 13 ||
+ memcmp(temp, "\001\000\000\377\377", 5) != 0) {
+ log_clean(log);
+ return NULL;
+ }
+ log->crc = make_ulg(temp + 5);
+ log->len = make_ulg(temp + 9);
+
+ /* set up to write over empty last block */
+ (void)lseek(log->fd, log->last_off + 5, SEEK_SET);
+ log->stored = 0;
+ return (void *)log;
+}
+
+/* maximum amount to put in a stored block before starting a new one */
+#define MAX_BLOCK 16384
+
+/* write a block to a log object */
+int gzlog_write(void *obj, char *data, size_t len)
+{
+ size_t some;
+ unsigned char temp[5];
+ gz_log *log;
+
+ /* check object */
+ log = (gz_log *)obj;
+ if (log == NULL || log->id != GZLOGID)
+ return 1;
+
+ /* write stored blocks until all of the input is written */
+ do {
+ some = MAX_BLOCK - log->stored;
+ if (some > len)
+ some = len;
+ if (write(log->fd, data, some) != some)
+ return 1;
+ log->crc = crc32(log->crc, data, some);
+ log->len += some;
+ len -= some;
+ data += some;
+ log->stored += some;
+
+ /* if the stored block is full, end it and start another */
+ if (log->stored == MAX_BLOCK) {
+ (void)lseek(log->fd, log->last_off, SEEK_SET);
+ temp[0] = 0;
+ dice_ulg(log->stored + ((unsigned long)(~log->stored) << 16),
+ temp + 1);
+ if (write(log->fd, temp, 5) != 5)
+ return 1;
+ log->last_off = lseek(log->fd, log->stored, SEEK_CUR);
+ (void)lseek(log->fd, 5, SEEK_CUR);
+ log->stored = 0;
+ }
+ } while (len);
+ return 0;
+}
+
+/* recompress the remaining stored deflate data in place */
+local int recomp(gz_log *log)
+{
+ z_stream strm;
+ size_t len, max;
+ unsigned char *in;
+ unsigned char *out;
+ unsigned char temp[16];
+
+ /* allocate space and read it all in (it's around 1 MB) */
+ len = log->last_off - log->mark_off;
+ max = len + (len >> 12) + (len >> 14) + 11;
+ out = malloc(max);
+ if (out == NULL)
+ return 1;
+ in = malloc(len);
+ if (in == NULL) {
+ free(out);
+ return 1;
+ }
+ (void)lseek(log->fd, log->mark_off, SEEK_SET);
+ if (read(log->fd, in, len) != len) {
+ free(in);
+ free(out);
+ return 1;
+ }
+
+ /* recompress in memory, decoding stored data as we go */
+ /* note: this assumes that unsigned is four bytes or more */
+ /* consider not making that assumption */
+ strm.zalloc = Z_NULL;
+ strm.zfree = Z_NULL;
+ strm.opaque = Z_NULL;
+ if (deflateInit2(&strm, Z_BEST_COMPRESSION, Z_DEFLATED, -15, 8,
+ Z_DEFAULT_STRATEGY) != Z_OK) {
+ free(in);
+ free(out);
+ return 1;
+ }
+ strm.next_in = in;
+ strm.avail_out = max;
+ strm.next_out = out;
+ while (len >= 5) {
+ if (strm.next_in[0] != 0)
+ break;
+ strm.avail_in = strm.next_in[1] + (strm.next_in[2] << 8);
+ strm.next_in += 5;
+ len -= 5;
+ if (strm.avail_in != 0) {
+ if (len < strm.avail_in)
+ break;
+ len -= strm.avail_in;
+ (void)deflate(&strm, Z_NO_FLUSH);
+ if (strm.avail_in != 0 || strm.avail_out == 0)
+ break;
+ }
+ }
+ (void)deflate(&strm, Z_SYNC_FLUSH);
+ (void)deflateEnd(&strm);
+ free(in);
+ if (len != 0 || strm.avail_out == 0) {
+ free(out);
+ return 1;
+ }
+
+ /* overwrite stored data with compressed data */
+ (void)lseek(log->fd, log->mark_off, SEEK_SET);
+ len = max - strm.avail_out;
+ if (write(log->fd, out, len) != len) {
+ free(out);
+ return 1;
+ }
+ free(out);
+
+ /* write last empty block, crc, and length */
+ log->mark_off = log->last_off = lseek(log->fd, 0, SEEK_CUR);
+ temp[0] = 1;
+ dice_ulg(0xffffL << 16, temp + 1);
+ dice_ulg(log->crc, temp + 5);
+ dice_ulg(log->len, temp + 9);
+ if (write(log->fd, temp, 13) != 13)
+ return 1;
+
+ /* truncate file to discard remaining stored data and old trailer */
+ ftruncate(log->fd, lseek(log->fd, 0, SEEK_CUR));
+
+ /* update extra field to point to new last empty block */
+ (void)lseek(log->fd, log->extra, SEEK_SET);
+ dice_off(log->mark_off, temp);
+ dice_off(log->last_off, temp + 8);
+ if (write(log->fd, temp, 16) != 16)
+ return 1;
+ return 0;
+}
+
+/* maximum accumulation of stored blocks before compressing */
+#define MAX_STORED 1048576
+
+/* close log object */
+int gzlog_close(void *obj)
+{
+ unsigned char temp[8];
+ gz_log *log;
+
+ /* check object */
+ log = (gz_log *)obj;
+ if (log == NULL || log->id != GZLOGID)
+ return 1;
+
+ /* go to start of most recent block being written */
+ (void)lseek(log->fd, log->last_off, SEEK_SET);
+
+ /* if some stuff was put there, update block */
+ if (log->stored) {
+ temp[0] = 0;
+ dice_ulg(log->stored + ((unsigned long)(~log->stored) << 16),
+ temp + 1);
+ if (write(log->fd, temp, 5) != 5)
+ return 1;
+ log->last_off = lseek(log->fd, log->stored, SEEK_CUR);
+ }
+
+ /* write last block (empty) */
+ if (write(log->fd, "\001\000\000\377\377", 5) != 5)
+ return 1;
+
+ /* write updated crc and uncompressed length */
+ dice_ulg(log->crc, temp);
+ dice_ulg(log->len, temp + 4);
+ if (write(log->fd, temp, 8) != 8)
+ return 1;
+
+ /* put offset of that last block in gzip extra block */
+ (void)lseek(log->fd, log->extra + 8, SEEK_SET);
+ dice_off(log->last_off, temp);
+ if (write(log->fd, temp, 8) != 8)
+ return 1;
+
+ /* if more than 1 MB stored, then time to compress it */
+ if (log->last_off - log->mark_off > MAX_STORED) {
+ if (recomp(log))
+ return 1;
+ }
+
+ /* unlock and close file */
+ log_clean(log);
+ return 0;
+}
diff --git a/Modules/zlib/examples/gzlog.h b/Modules/zlib/examples/gzlog.h
new file mode 100644
index 0000000..a800bd5
--- /dev/null
+++ b/Modules/zlib/examples/gzlog.h
@@ -0,0 +1,58 @@
+/* gzlog.h
+ Copyright (C) 2004 Mark Adler, all rights reserved
+ version 1.0, 26 Nov 2004
+
+ This software is provided 'as-is', without any express or implied
+ warranty. In no event will the author be held liable for any damages
+ arising from the use of this software.
+
+ Permission is granted to anyone to use this software for any purpose,
+ including commercial applications, and to alter it and redistribute it
+ freely, subject to the following restrictions:
+
+ 1. The origin of this software must not be misrepresented; you must not
+ claim that you wrote the original software. If you use this software
+ in a product, an acknowledgment in the product documentation would be
+ appreciated but is not required.
+ 2. Altered source versions must be plainly marked as such, and must not be
+ misrepresented as being the original software.
+ 3. This notice may not be removed or altered from any source distribution.
+
+ Mark Adler madler@alumni.caltech.edu
+ */
+
+/*
+ The gzlog object allows writing short messages to a gzipped log file,
+ opening the log file locked for small bursts, and then closing it. The log
+ object works by appending stored data to the gzip file until 1 MB has been
+ accumulated. At that time, the stored data is compressed, and replaces the
+ uncompressed data in the file. The log file is truncated to its new size at
+ that time. After closing, the log file is always valid gzip file that can
+ decompressed to recover what was written.
+
+ A gzip header "extra" field contains two file offsets for appending. The
+ first points to just after the last compressed data. The second points to
+ the last stored block in the deflate stream, which is empty. All of the
+ data between those pointers is uncompressed.
+ */
+
+/* Open a gzlog object, creating the log file if it does not exist. Return
+ NULL on error. Note that gzlog_open() could take a long time to return if
+ there is difficulty in locking the file. */
+void *gzlog_open(char *path);
+
+/* Write to a gzlog object. Return non-zero on error. This function will
+ simply write data to the file uncompressed. Compression of the data
+ will not occur until gzlog_close() is called. It is expected that
+ gzlog_write() is used for a short message, and then gzlog_close() is
+ called. If a large amount of data is to be written, then the application
+ should write no more than 1 MB at a time with gzlog_write() before
+ calling gzlog_close() and then gzlog_open() again. */
+int gzlog_write(void *log, char *data, size_t len);
+
+/* Close a gzlog object. Return non-zero on error. The log file is locked
+ until this function is called. This function will compress stored data
+ at the end of the gzip file if at least 1 MB has been accumulated. Note
+ that the file will not be a valid gzip file until this function completes.
+ */
+int gzlog_close(void *log);
diff --git a/Modules/zlib/examples/zlib_how.html b/Modules/zlib/examples/zlib_how.html
new file mode 100644
index 0000000..40998db
--- /dev/null
+++ b/Modules/zlib/examples/zlib_how.html
@@ -0,0 +1,523 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"
+ "http://www.w3.org/TR/REC-html40/loose.dtd">
+<html>
+<head>
+<meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
+<title>zlib Usage Example</title>
+<!-- Copyright (c) 2004 Mark Adler. -->
+</head>
+<body bgcolor="#FFFFFF" text="#000000" link="#0000FF" vlink="#00A000">
+<h2 align="center"> zlib Usage Example </h2>
+We often get questions about how the <tt>deflate()</tt> and <tt>inflate()</tt> functions should be used.
+Users wonder when they should provide more input, when they should use more output,
+what to do with a <tt>Z_BUF_ERROR</tt>, how to make sure the process terminates properly, and
+so on. So for those who have read <tt>zlib.h</tt> (a few times), and
+would like further edification, below is an annotated example in C of simple routines to compress and decompress
+from an input file to an output file using <tt>deflate()</tt> and <tt>inflate()</tt> respectively. The
+annotations are interspersed between lines of the code. So please read between the lines.
+We hope this helps explain some of the intricacies of <em>zlib</em>.
+<p>
+Without further adieu, here is the program <a href="zpipe.c"><tt>zpipe.c</tt></a>:
+<pre><b>
+/* zpipe.c: example of proper use of zlib's inflate() and deflate()
+ Not copyrighted -- provided to the public domain
+ Version 1.2 9 November 2004 Mark Adler */
+
+/* Version history:
+ 1.0 30 Oct 2004 First version
+ 1.1 8 Nov 2004 Add void casting for unused return values
+ Use switch statement for inflate() return values
+ 1.2 9 Nov 2004 Add assertions to document zlib guarantees
+ */
+</b></pre><!-- -->
+We now include the header files for the required definitions. From
+<tt>stdio.h</tt> we use <tt>fopen()</tt>, <tt>fread()</tt>, <tt>fwrite()</tt>,
+<tt>feof()</tt>, <tt>ferror()</tt>, and <tt>fclose()</tt> for file i/o, and
+<tt>fputs()</tt> for error messages. From <tt>string.h</tt> we use
+<tt>strcmp()</tt> for command line argument processing.
+From <tt>assert.h</tt> we use the <tt>assert()</tt> macro.
+From <tt>zlib.h</tt>
+we use the basic compression functions <tt>deflateInit()</tt>,
+<tt>deflate()</tt>, and <tt>deflateEnd()</tt>, and the basic decompression
+functions <tt>inflateInit()</tt>, <tt>inflate()</tt>, and
+<tt>inflateEnd()</tt>.
+<pre><b>
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include "zlib.h"
+</b></pre><!-- -->
+<tt>CHUNK</tt> is simply the buffer size for feeding data to and pulling data
+from the <em>zlib</em> routines. Larger buffer sizes would be more efficient,
+especially for <tt>inflate()</tt>. If the memory is available, buffers sizes
+on the order of 128K or 256K bytes should be used.
+<pre><b>
+#define CHUNK 16384
+</b></pre><!-- -->
+The <tt>def()</tt> routine compresses data from an input file to an output file. The output data
+will be in the <em>zlib</em> format, which is different from the <em>gzip</em> or <em>zip</em>
+formats. The <em>zlib</em> format has a very small header of only two bytes to identify it as
+a <em>zlib</em> stream and to provide decoding information, and a four-byte trailer with a fast
+check value to verify the integrity of the uncompressed data after decoding.
+<pre><b>
+/* Compress from file source to file dest until EOF on source.
+ def() returns Z_OK on success, Z_MEM_ERROR if memory could not be
+ allocated for processing, Z_STREAM_ERROR if an invalid compression
+ level is supplied, Z_VERSION_ERROR if the version of zlib.h and the
+ version of the library linked do not match, or Z_ERRNO if there is
+ an error reading or writing the files. */
+int def(FILE *source, FILE *dest, int level)
+{
+</b></pre>
+Here are the local variables for <tt>def()</tt>. <tt>ret</tt> will be used for <em>zlib</em>
+return codes. <tt>flush</tt> will keep track of the current flushing state for <tt>deflate()</tt>,
+which is either no flushing, or flush to completion after the end of the input file is reached.
+<tt>have</tt> is the amount of data returned from <tt>deflate()</tt>. The <tt>strm</tt> structure
+is used to pass information to and from the <em>zlib</em> routines, and to maintain the
+<tt>deflate()</tt> state. <tt>in</tt> and <tt>out</tt> are the input and output buffers for
+<tt>deflate()</tt>.
+<pre><b>
+ int ret, flush;
+ unsigned have;
+ z_stream strm;
+ char in[CHUNK];
+ char out[CHUNK];
+</b></pre><!-- -->
+The first thing we do is to initialize the <em>zlib</em> state for compression using
+<tt>deflateInit()</tt>. This must be done before the first use of <tt>deflate()</tt>.
+The <tt>zalloc</tt>, <tt>zfree</tt>, and <tt>opaque</tt> fields in the <tt>strm</tt>
+structure must be initialized before calling <tt>deflateInit()</tt>. Here they are
+set to the <em>zlib</em> constant <tt>Z_NULL</tt> to request that <em>zlib</em> use
+the default memory allocation routines. An application may also choose to provide
+custom memory allocation routines here. <tt>deflateInit()</tt> will allocate on the
+order of 256K bytes for the internal state.
+(See <a href="zlib_tech.html"><em>zlib Technical Details</em></a>.)
+<p>
+<tt>deflateInit()</tt> is called with a pointer to the structure to be initialized and
+the compression level, which is an integer in the range of -1 to 9. Lower compression
+levels result in faster execution, but less compression. Higher levels result in
+greater compression, but slower execution. The <em>zlib</em> constant Z_DEFAULT_COMPRESSION,
+equal to -1,
+provides a good compromise between compression and speed and is equivalent to level 6.
+Level 0 actually does no compression at all, and in fact expands the data slightly to produce
+the <em>zlib</em> format (it is not a byte-for-byte copy of the input).
+More advanced applications of <em>zlib</em>
+may use <tt>deflateInit2()</tt> here instead. Such an application may want to reduce how
+much memory will be used, at some price in compression. Or it may need to request a
+<em>gzip</em> header and trailer instead of a <em>zlib</em> header and trailer, or raw
+encoding with no header or trailer at all.
+<p>
+We must check the return value of <tt>deflateInit()</tt> against the <em>zlib</em> constant
+<tt>Z_OK</tt> to make sure that it was able to
+allocate memory for the internal state, and that the provided arguments were valid.
+<tt>deflateInit()</tt> will also check that the version of <em>zlib</em> that the <tt>zlib.h</tt>
+file came from matches the version of <em>zlib</em> actually linked with the program. This
+is especially important for environments in which <em>zlib</em> is a shared library.
+<p>
+Note that an application can initialize multiple, independent <em>zlib</em> streams, which can
+operate in parallel. The state information maintained in the structure allows the <em>zlib</em>
+routines to be reentrant.
+<pre><b>
+ /* allocate deflate state */
+ strm.zalloc = Z_NULL;
+ strm.zfree = Z_NULL;
+ strm.opaque = Z_NULL;
+ ret = deflateInit(&strm, level);
+ if (ret != Z_OK)
+ return ret;
+</b></pre><!-- -->
+With the pleasantries out of the way, now we can get down to business. The outer <tt>do</tt>-loop
+reads all of the input file and exits at the bottom of the loop once end-of-file is reached.
+This loop contains the only call of <tt>deflate()</tt>. So we must make sure that all of the
+input data has been processed and that all of the output data has been generated and consumed
+before we fall out of the loop at the bottom.
+<pre><b>
+ /* compress until end of file */
+ do {
+</b></pre>
+We start off by reading data from the input file. The number of bytes read is put directly
+into <tt>avail_in</tt>, and a pointer to those bytes is put into <tt>next_in</tt>. We also
+check to see if end-of-file on the input has been reached. If we are at the end of file, then <tt>flush</tt> is set to the
+<em>zlib</em> constant <tt>Z_FINISH</tt>, which is later passed to <tt>deflate()</tt> to
+indicate that this is the last chunk of input data to compress. We need to use <tt>feof()</tt>
+to check for end-of-file as opposed to seeing if fewer than <tt>CHUNK</tt> bytes have been read. The
+reason is that if the input file length is an exact multiple of <tt>CHUNK</tt>, we will miss
+the fact that we got to the end-of-file, and not know to tell <tt>deflate()</tt> to finish
+up the compressed stream. If we are not yet at the end of the input, then the <em>zlib</em>
+constant <tt>Z_NO_FLUSH</tt> will be passed to <tt>deflate</tt> to indicate that we are still
+in the middle of the uncompressed data.
+<p>
+If there is an error in reading from the input file, the process is aborted with
+<tt>deflateEnd()</tt> being called to free the allocated <em>zlib</em> state before returning
+the error. We wouldn't want a memory leak, now would we? <tt>deflateEnd()</tt> can be called
+at any time after the state has been initialized. Once that's done, <tt>deflateInit()</tt> (or
+<tt>deflateInit2()</tt>) would have to be called to start a new compression process. There is
+no point here in checking the <tt>deflateEnd()</tt> return code. The deallocation can't fail.
+<pre><b>
+ strm.avail_in = fread(in, 1, CHUNK, source);
+ if (ferror(source)) {
+ (void)deflateEnd(&strm);
+ return Z_ERRNO;
+ }
+ flush = feof(source) ? Z_FINISH : Z_NO_FLUSH;
+ strm.next_in = in;
+</b></pre><!-- -->
+The inner <tt>do</tt>-loop passes our chunk of input data to <tt>deflate()</tt>, and then
+keeps calling <tt>deflate()</tt> until it is done producing output. Once there is no more
+new output, <tt>deflate()</tt> is guaranteed to have consumed all of the input, i.e.,
+<tt>avail_in</tt> will be zero.
+<pre><b>
+ /* run deflate() on input until output buffer not full, finish
+ compression if all of source has been read in */
+ do {
+</b></pre>
+Output space is provided to <tt>deflate()</tt> by setting <tt>avail_out</tt> to the number
+of available output bytes and <tt>next_out</tt> to a pointer to that space.
+<pre><b>
+ strm.avail_out = CHUNK;
+ strm.next_out = out;
+</b></pre>
+Now we call the compression engine itself, <tt>deflate()</tt>. It takes as many of the
+<tt>avail_in</tt> bytes at <tt>next_in</tt> as it can process, and writes as many as
+<tt>avail_out</tt> bytes to <tt>next_out</tt>. Those counters and pointers are then
+updated past the input data consumed and the output data written. It is the amount of
+output space available that may limit how much input is consumed.
+Hence the inner loop to make sure that
+all of the input is consumed by providing more output space each time. Since <tt>avail_in</tt>
+and <tt>next_in</tt> are updated by <tt>deflate()</tt>, we don't have to mess with those
+between <tt>deflate()</tt> calls until it's all used up.
+<p>
+The parameters to <tt>deflate()</tt> are a pointer to the <tt>strm</tt> structure containing
+the input and output information and the internal compression engine state, and a parameter
+indicating whether and how to flush data to the output. Normally <tt>deflate</tt> will consume
+several K bytes of input data before producing any output (except for the header), in order
+to accumulate statistics on the data for optimum compression. It will then put out a burst of
+compressed data, and proceed to consume more input before the next burst. Eventually,
+<tt>deflate()</tt>
+must be told to terminate the stream, complete the compression with provided input data, and
+write out the trailer check value. <tt>deflate()</tt> will continue to compress normally as long
+as the flush parameter is <tt>Z_NO_FLUSH</tt>. Once the <tt>Z_FINISH</tt> parameter is provided,
+<tt>deflate()</tt> will begin to complete the compressed output stream. However depending on how
+much output space is provided, <tt>deflate()</tt> may have to be called several times until it
+has provided the complete compressed stream, even after it has consumed all of the input. The flush
+parameter must continue to be <tt>Z_FINISH</tt> for those subsequent calls.
+<p>
+There are other values of the flush parameter that are used in more advanced applications. You can
+force <tt>deflate()</tt> to produce a burst of output that encodes all of the input data provided
+so far, even if it wouldn't have otherwise, for example to control data latency on a link with
+compressed data. You can also ask that <tt>deflate()</tt> do that as well as erase any history up to
+that point so that what follows can be decompressed independently, for example for random access
+applications. Both requests will degrade compression by an amount depending on how often such
+requests are made.
+<p>
+<tt>deflate()</tt> has a return value that can indicate errors, yet we do not check it here. Why
+not? Well, it turns out that <tt>deflate()</tt> can do no wrong here. Let's go through
+<tt>deflate()</tt>'s return values and dispense with them one by one. The possible values are
+<tt>Z_OK</tt>, <tt>Z_STREAM_END</tt>, <tt>Z_STREAM_ERROR</tt>, or <tt>Z_BUF_ERROR</tt>. <tt>Z_OK</tt>
+is, well, ok. <tt>Z_STREAM_END</tt> is also ok and will be returned for the last call of
+<tt>deflate()</tt>. This is already guaranteed by calling <tt>deflate()</tt> with <tt>Z_FINISH</tt>
+until it has no more output. <tt>Z_STREAM_ERROR</tt> is only possible if the stream is not
+initialized properly, but we did initialize it properly. There is no harm in checking for
+<tt>Z_STREAM_ERROR</tt> here, for example to check for the possibility that some
+other part of the application inadvertently clobbered the memory containing the <em>zlib</em> state.
+<tt>Z_BUF_ERROR</tt> will be explained further below, but
+suffice it to say that this is simply an indication that <tt>deflate()</tt> could not consume
+more input or produce more output. <tt>deflate()</tt> can be called again with more output space
+or more available input, which it will be in this code.
+<pre><b>
+ ret = deflate(&strm, flush); /* no bad return value */
+ assert(ret != Z_STREAM_ERROR); /* state not clobbered */
+</b></pre>
+Now we compute how much output <tt>deflate()</tt> provided on the last call, which is the
+difference between how much space was provided before the call, and how much output space
+is still available after the call. Then that data, if any, is written to the output file.
+We can then reuse the output buffer for the next call of <tt>deflate()</tt>. Again if there
+is a file i/o error, we call <tt>deflateEnd()</tt> before returning to avoid a memory leak.
+<pre><b>
+ have = CHUNK - strm.avail_out;
+ if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
+ (void)deflateEnd(&strm);
+ return Z_ERRNO;
+ }
+</b></pre>
+The inner <tt>do</tt>-loop is repeated until the last <tt>deflate()</tt> call fails to fill the
+provided output buffer. Then we know that <tt>deflate()</tt> has done as much as it can with
+the provided input, and that all of that input has been consumed. We can then fall out of this
+loop and reuse the input buffer.
+<p>
+The way we tell that <tt>deflate()</tt> has no more output is by seeing that it did not fill
+the output buffer, leaving <tt>avail_out</tt> greater than zero. However suppose that
+<tt>deflate()</tt> has no more output, but just so happened to exactly fill the output buffer!
+<tt>avail_out</tt> is zero, and we can't tell that <tt>deflate()</tt> has done all it can.
+As far as we know, <tt>deflate()</tt>
+has more output for us. So we call it again. But now <tt>deflate()</tt> produces no output
+at all, and <tt>avail_out</tt> remains unchanged as <tt>CHUNK</tt>. That <tt>deflate()</tt> call
+wasn't able to do anything, either consume input or produce output, and so it returns
+<tt>Z_BUF_ERROR</tt>. (See, I told you I'd cover this later.) However this is not a problem at
+all. Now we finally have the desired indication that <tt>deflate()</tt> is really done,
+and so we drop out of the inner loop to provide more input to <tt>deflate()</tt>.
+<p>
+With <tt>flush</tt> set to <tt>Z_FINISH</tt>, this final set of <tt>deflate()</tt> calls will
+complete the output stream. Once that is done, subsequent calls of <tt>deflate()</tt> would return
+<tt>Z_STREAM_ERROR</tt> if the flush parameter is not <tt>Z_FINISH</tt>, and do no more processing
+until the state is reinitialized.
+<p>
+Some applications of <em>zlib</em> have two loops that call <tt>deflate()</tt>
+instead of the single inner loop we have here. The first loop would call
+without flushing and feed all of the data to <tt>deflate()</tt>. The second loop would call
+<tt>deflate()</tt> with no more
+data and the <tt>Z_FINISH</tt> parameter to complete the process. As you can see from this
+example, that can be avoided by simply keeping track of the current flush state.
+<pre><b>
+ } while (strm.avail_out == 0);
+ assert(strm.avail_in == 0); /* all input will be used */
+</b></pre><!-- -->
+Now we check to see if we have already processed all of the input file. That information was
+saved in the <tt>flush</tt> variable, so we see if that was set to <tt>Z_FINISH</tt>. If so,
+then we're done and we fall out of the outer loop. We're guaranteed to get <tt>Z_STREAM_END</tt>
+from the last <tt>deflate()</tt> call, since we ran it until the last chunk of input was
+consumed and all of the output was generated.
+<pre><b>
+ /* done when last data in file processed */
+ } while (flush != Z_FINISH);
+ assert(ret == Z_STREAM_END); /* stream will be complete */
+</b></pre><!-- -->
+The process is complete, but we still need to deallocate the state to avoid a memory leak
+(or rather more like a memory hemorrhage if you didn't do this). Then
+finally we can return with a happy return value.
+<pre><b>
+ /* clean up and return */
+ (void)deflateEnd(&strm);
+ return Z_OK;
+}
+</b></pre><!-- -->
+Now we do the same thing for decompression in the <tt>inf()</tt> routine. <tt>inf()</tt>
+decompresses what is hopefully a valid <em>zlib</em> stream from the input file and writes the
+uncompressed data to the output file. Much of the discussion above for <tt>def()</tt>
+applies to <tt>inf()</tt> as well, so the discussion here will focus on the differences between
+the two.
+<pre><b>
+/* Decompress from file source to file dest until stream ends or EOF.
+ inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be
+ allocated for processing, Z_DATA_ERROR if the deflate data is
+ invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and
+ the version of the library linked do not match, or Z_ERRNO if there
+ is an error reading or writing the files. */
+int inf(FILE *source, FILE *dest)
+{
+</b></pre>
+The local variables have the same functionality as they do for <tt>def()</tt>. The
+only difference is that there is no <tt>flush</tt> variable, since <tt>inflate()</tt>
+can tell from the <em>zlib</em> stream itself when the stream is complete.
+<pre><b>
+ int ret;
+ unsigned have;
+ z_stream strm;
+ char in[CHUNK];
+ char out[CHUNK];
+</b></pre><!-- -->
+The initialization of the state is the same, except that there is no compression level,
+of course, and two more elements of the structure are initialized. <tt>avail_in</tt>
+and <tt>next_in</tt> must be initialized before calling <tt>inflateInit()</tt>. This
+is because the application has the option to provide the start of the zlib stream in
+order for <tt>inflateInit()</tt> to have access to information about the compression
+method to aid in memory allocation. In the current implementation of <em>zlib</em>
+(up through versions 1.2.x), the method-dependent memory allocations are deferred to the first call of
+<tt>inflate()</tt> anyway. However those fields must be initialized since later versions
+of <em>zlib</em> that provide more compression methods may take advantage of this interface.
+In any case, no decompression is performed by <tt>inflateInit()</tt>, so the
+<tt>avail_out</tt> and <tt>next_out</tt> fields do not need to be initialized before calling.
+<p>
+Here <tt>avail_in</tt> is set to zero and <tt>next_in</tt> is set to <tt>Z_NULL</tt> to
+indicate that no input data is being provided.
+<pre><b>
+ /* allocate inflate state */
+ strm.zalloc = Z_NULL;
+ strm.zfree = Z_NULL;
+ strm.opaque = Z_NULL;
+ strm.avail_in = 0;
+ strm.next_in = Z_NULL;
+ ret = inflateInit(&strm);
+ if (ret != Z_OK)
+ return ret;
+</b></pre><!-- -->
+The outer <tt>do</tt>-loop decompresses input until <tt>inflate()</tt> indicates
+that it has reached the end of the compressed data and has produced all of the uncompressed
+output. This is in contrast to <tt>def()</tt> which processes all of the input file.
+If end-of-file is reached before the compressed data self-terminates, then the compressed
+data is incomplete and an error is returned.
+<pre><b>
+ /* decompress until deflate stream ends or end of file */
+ do {
+</b></pre>
+We read input data and set the <tt>strm</tt> structure accordingly. If we've reached the
+end of the input file, then we leave the outer loop and report an error, since the
+compressed data is incomplete. Note that we may read more data than is eventually consumed
+by <tt>inflate()</tt>, if the input file continues past the <em>zlib</em> stream.
+For applications where <em>zlib</em> streams are embedded in other data, this routine would
+need to be modified to return the unused data, or at least indicate how much of the input
+data was not used, so the application would know where to pick up after the <em>zlib</em> stream.
+<pre><b>
+ strm.avail_in = fread(in, 1, CHUNK, source);
+ if (ferror(source)) {
+ (void)inflateEnd(&strm);
+ return Z_ERRNO;
+ }
+ if (strm.avail_in == 0)
+ break;
+ strm.next_in = in;
+</b></pre><!-- -->
+The inner <tt>do</tt>-loop has the same function it did in <tt>def()</tt>, which is to
+keep calling <tt>inflate()</tt> until has generated all of the output it can with the
+provided input.
+<pre><b>
+ /* run inflate() on input until output buffer not full */
+ do {
+</b></pre>
+Just like in <tt>def()</tt>, the same output space is provided for each call of <tt>inflate()</tt>.
+<pre><b>
+ strm.avail_out = CHUNK;
+ strm.next_out = out;
+</b></pre>
+Now we run the decompression engine itself. There is no need to adjust the flush parameter, since
+the <em>zlib</em> format is self-terminating. The main difference here is that there are
+return values that we need to pay attention to. <tt>Z_DATA_ERROR</tt>
+indicates that <tt>inflate()</tt> detected an error in the <em>zlib</em> compressed data format,
+which means that either the data is not a <em>zlib</em> stream to begin with, or that the data was
+corrupted somewhere along the way since it was compressed. The other error to be processed is
+<tt>Z_MEM_ERROR</tt>, which can occur since memory allocation is deferred until <tt>inflate()</tt>
+needs it, unlike <tt>deflate()</tt>, whose memory is allocated at the start by <tt>deflateInit()</tt>.
+<p>
+Advanced applications may use
+<tt>deflateSetDictionary()</tt> to prime <tt>deflate()</tt> with a set of likely data to improve the
+first 32K or so of compression. This is noted in the <em>zlib</em> header, so <tt>inflate()</tt>
+requests that that dictionary be provided before it can start to decompress. Without the dictionary,
+correct decompression is not possible. For this routine, we have no idea what the dictionary is,
+so the <tt>Z_NEED_DICT</tt> indication is converted to a <tt>Z_DATA_ERROR</tt>.
+<p>
+<tt>inflate()</tt> can also return <tt>Z_STREAM_ERROR</tt>, which should not be possible here,
+but could be checked for as noted above for <tt>def()</tt>. <tt>Z_BUF_ERROR</tt> does not need to be
+checked for here, for the same reasons noted for <tt>def()</tt>. <tt>Z_STREAM_END</tt> will be
+checked for later.
+<pre><b>
+ ret = inflate(&strm, Z_NO_FLUSH);
+ assert(ret != Z_STREAM_ERROR); /* state not clobbered */
+ switch (ret) {
+ case Z_NEED_DICT:
+ ret = Z_DATA_ERROR; /* and fall through */
+ case Z_DATA_ERROR:
+ case Z_MEM_ERROR:
+ (void)inflateEnd(&strm);
+ return ret;
+ }
+</b></pre>
+The output of <tt>inflate()</tt> is handled identically to that of <tt>deflate()</tt>.
+<pre><b>
+ have = CHUNK - strm.avail_out;
+ if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
+ (void)inflateEnd(&strm);
+ return Z_ERRNO;
+ }
+</b></pre>
+The inner <tt>do</tt>-loop ends when <tt>inflate()</tt> has no more output as indicated
+by not filling the output buffer, just as for <tt>deflate()</tt>. In this case, we cannot
+assert that <tt>strm.avail_in</tt> will be zero, since the deflate stream may end before the file
+does.
+<pre><b>
+ } while (strm.avail_out == 0);
+</b></pre><!-- -->
+The outer <tt>do</tt>-loop ends when <tt>inflate()</tt> reports that it has reached the
+end of the input <em>zlib</em> stream, has completed the decompression and integrity
+check, and has provided all of the output. This is indicated by the <tt>inflate()</tt>
+return value <tt>Z_STREAM_END</tt>. The inner loop is guaranteed to leave <tt>ret</tt>
+equal to <tt>Z_STREAM_END</tt> if the last chunk of the input file read contained the end
+of the <em>zlib</em> stream. So if the return value is not <tt>Z_STREAM_END</tt>, the
+loop continues to read more input.
+<pre><b>
+ /* done when inflate() says it's done */
+ } while (ret != Z_STREAM_END);
+</b></pre><!-- -->
+At this point, decompression successfully completed, or we broke out of the loop due to no
+more data being available from the input file. If the last <tt>inflate()</tt> return value
+is not <tt>Z_STREAM_END</tt>, then the <em>zlib</em> stream was incomplete and a data error
+is returned. Otherwise, we return with a happy return value. Of course, <tt>inflateEnd()</tt>
+is called first to avoid a memory leak.
+<pre><b>
+ /* clean up and return */
+ (void)inflateEnd(&strm);
+ return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR;
+}
+</b></pre><!-- -->
+That ends the routines that directly use <em>zlib</em>. The following routines make this
+a command-line program by running data through the above routines from <tt>stdin</tt> to
+<tt>stdout</tt>, and handling any errors reported by <tt>def()</tt> or <tt>inf()</tt>.
+<p>
+<tt>zerr()</tt> is used to interpret the possible error codes from <tt>def()</tt>
+and <tt>inf()</tt>, as detailed in their comments above, and print out an error message.
+Note that these are only a subset of the possible return values from <tt>deflate()</tt>
+and <tt>inflate()</tt>.
+<pre><b>
+/* report a zlib or i/o error */
+void zerr(int ret)
+{
+ fputs("zpipe: ", stderr);
+ switch (ret) {
+ case Z_ERRNO:
+ if (ferror(stdin))
+ fputs("error reading stdin\n", stderr);
+ if (ferror(stdout))
+ fputs("error writing stdout\n", stderr);
+ break;
+ case Z_STREAM_ERROR:
+ fputs("invalid compression level\n", stderr);
+ break;
+ case Z_DATA_ERROR:
+ fputs("invalid or incomplete deflate data\n", stderr);
+ break;
+ case Z_MEM_ERROR:
+ fputs("out of memory\n", stderr);
+ break;
+ case Z_VERSION_ERROR:
+ fputs("zlib version mismatch!\n", stderr);
+ }
+}
+</b></pre><!-- -->
+Here is the <tt>main()</tt> routine used to test <tt>def()</tt> and <tt>inf()</tt>. The
+<tt>zpipe</tt> command is simply a compression pipe from <tt>stdin</tt> to <tt>stdout</tt>, if
+no arguments are given, or it is a decompression pipe if <tt>zpipe -d</tt> is used. If any other
+arguments are provided, no compression or decompression is performed. Instead a usage
+message is displayed. Examples are <tt>zpipe < foo.txt > foo.txt.z</tt> to compress, and
+<tt>zpipe -d < foo.txt.z > foo.txt</tt> to decompress.
+<pre><b>
+/* compress or decompress from stdin to stdout */
+int main(int argc, char **argv)
+{
+ int ret;
+
+ /* do compression if no arguments */
+ if (argc == 1) {
+ ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION);
+ if (ret != Z_OK)
+ zerr(ret);
+ return ret;
+ }
+
+ /* do decompression if -d specified */
+ else if (argc == 2 && strcmp(argv[1], "-d") == 0) {
+ ret = inf(stdin, stdout);
+ if (ret != Z_OK)
+ zerr(ret);
+ return ret;
+ }
+
+ /* otherwise, report usage */
+ else {
+ fputs("zpipe usage: zpipe [-d] < source > dest\n", stderr);
+ return 1;
+ }
+}
+</b></pre>
+<hr>
+<i>Copyright (c) 2004 by Mark Adler<br>Last modified 13 November 2004</i>
+</body>
+</html>
diff --git a/Modules/zlib/examples/zpipe.c b/Modules/zlib/examples/zpipe.c
new file mode 100644
index 0000000..26abb56
--- /dev/null
+++ b/Modules/zlib/examples/zpipe.c
@@ -0,0 +1,191 @@
+/* zpipe.c: example of proper use of zlib's inflate() and deflate()
+ Not copyrighted -- provided to the public domain
+ Version 1.2 9 November 2004 Mark Adler */
+
+/* Version history:
+ 1.0 30 Oct 2004 First version
+ 1.1 8 Nov 2004 Add void casting for unused return values
+ Use switch statement for inflate() return values
+ 1.2 9 Nov 2004 Add assertions to document zlib guarantees
+ 1.3 6 Apr 2005 Remove incorrect assertion in inf()
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include "zlib.h"
+
+#define CHUNK 16384
+
+/* Compress from file source to file dest until EOF on source.
+ def() returns Z_OK on success, Z_MEM_ERROR if memory could not be
+ allocated for processing, Z_STREAM_ERROR if an invalid compression
+ level is supplied, Z_VERSION_ERROR if the version of zlib.h and the
+ version of the library linked do not match, or Z_ERRNO if there is
+ an error reading or writing the files. */
+int def(FILE *source, FILE *dest, int level)
+{
+ int ret, flush;
+ unsigned have;
+ z_stream strm;
+ char in[CHUNK];
+ char out[CHUNK];
+
+ /* allocate deflate state */
+ strm.zalloc = Z_NULL;
+ strm.zfree = Z_NULL;
+ strm.opaque = Z_NULL;
+ ret = deflateInit(&strm, level);
+ if (ret != Z_OK)
+ return ret;
+
+ /* compress until end of file */
+ do {
+ strm.avail_in = fread(in, 1, CHUNK, source);
+ if (ferror(source)) {
+ (void)deflateEnd(&strm);
+ return Z_ERRNO;
+ }
+ flush = feof(source) ? Z_FINISH : Z_NO_FLUSH;
+ strm.next_in = in;
+
+ /* run deflate() on input until output buffer not full, finish
+ compression if all of source has been read in */
+ do {
+ strm.avail_out = CHUNK;
+ strm.next_out = out;
+ ret = deflate(&strm, flush); /* no bad return value */
+ assert(ret != Z_STREAM_ERROR); /* state not clobbered */
+ have = CHUNK - strm.avail_out;
+ if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
+ (void)deflateEnd(&strm);
+ return Z_ERRNO;
+ }
+ } while (strm.avail_out == 0);
+ assert(strm.avail_in == 0); /* all input will be used */
+
+ /* done when last data in file processed */
+ } while (flush != Z_FINISH);
+ assert(ret == Z_STREAM_END); /* stream will be complete */
+
+ /* clean up and return */
+ (void)deflateEnd(&strm);
+ return Z_OK;
+}
+
+/* Decompress from file source to file dest until stream ends or EOF.
+ inf() returns Z_OK on success, Z_MEM_ERROR if memory could not be
+ allocated for processing, Z_DATA_ERROR if the deflate data is
+ invalid or incomplete, Z_VERSION_ERROR if the version of zlib.h and
+ the version of the library linked do not match, or Z_ERRNO if there
+ is an error reading or writing the files. */
+int inf(FILE *source, FILE *dest)
+{
+ int ret;
+ unsigned have;
+ z_stream strm;
+ char in[CHUNK];
+ char out[CHUNK];
+
+ /* allocate inflate state */
+ strm.zalloc = Z_NULL;
+ strm.zfree = Z_NULL;
+ strm.opaque = Z_NULL;
+ strm.avail_in = 0;
+ strm.next_in = Z_NULL;
+ ret = inflateInit(&strm);
+ if (ret != Z_OK)
+ return ret;
+
+ /* decompress until deflate stream ends or end of file */
+ do {
+ strm.avail_in = fread(in, 1, CHUNK, source);
+ if (ferror(source)) {
+ (void)inflateEnd(&strm);
+ return Z_ERRNO;
+ }
+ if (strm.avail_in == 0)
+ break;
+ strm.next_in = in;
+
+ /* run inflate() on input until output buffer not full */
+ do {
+ strm.avail_out = CHUNK;
+ strm.next_out = out;
+ ret = inflate(&strm, Z_NO_FLUSH);
+ assert(ret != Z_STREAM_ERROR); /* state not clobbered */
+ switch (ret) {
+ case Z_NEED_DICT:
+ ret = Z_DATA_ERROR; /* and fall through */
+ case Z_DATA_ERROR:
+ case Z_MEM_ERROR:
+ (void)inflateEnd(&strm);
+ return ret;
+ }
+ have = CHUNK - strm.avail_out;
+ if (fwrite(out, 1, have, dest) != have || ferror(dest)) {
+ (void)inflateEnd(&strm);
+ return Z_ERRNO;
+ }
+ } while (strm.avail_out == 0);
+
+ /* done when inflate() says it's done */
+ } while (ret != Z_STREAM_END);
+
+ /* clean up and return */
+ (void)inflateEnd(&strm);
+ return ret == Z_STREAM_END ? Z_OK : Z_DATA_ERROR;
+}
+
+/* report a zlib or i/o error */
+void zerr(int ret)
+{
+ fputs("zpipe: ", stderr);
+ switch (ret) {
+ case Z_ERRNO:
+ if (ferror(stdin))
+ fputs("error reading stdin\n", stderr);
+ if (ferror(stdout))
+ fputs("error writing stdout\n", stderr);
+ break;
+ case Z_STREAM_ERROR:
+ fputs("invalid compression level\n", stderr);
+ break;
+ case Z_DATA_ERROR:
+ fputs("invalid or incomplete deflate data\n", stderr);
+ break;
+ case Z_MEM_ERROR:
+ fputs("out of memory\n", stderr);
+ break;
+ case Z_VERSION_ERROR:
+ fputs("zlib version mismatch!\n", stderr);
+ }
+}
+
+/* compress or decompress from stdin to stdout */
+int main(int argc, char **argv)
+{
+ int ret;
+
+ /* do compression if no arguments */
+ if (argc == 1) {
+ ret = def(stdin, stdout, Z_DEFAULT_COMPRESSION);
+ if (ret != Z_OK)
+ zerr(ret);
+ return ret;
+ }
+
+ /* do decompression if -d specified */
+ else if (argc == 2 && strcmp(argv[1], "-d") == 0) {
+ ret = inf(stdin, stdout);
+ if (ret != Z_OK)
+ zerr(ret);
+ return ret;
+ }
+
+ /* otherwise, report usage */
+ else {
+ fputs("zpipe usage: zpipe [-d] < source > dest\n", stderr);
+ return 1;
+ }
+}
diff --git a/Modules/zlib/examples/zran.c b/Modules/zlib/examples/zran.c
new file mode 100644
index 0000000..8c7717e
--- /dev/null
+++ b/Modules/zlib/examples/zran.c
@@ -0,0 +1,404 @@
+/* zran.c -- example of zlib/gzip stream indexing and random access
+ * Copyright (C) 2005 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ Version 1.0 29 May 2005 Mark Adler */
+
+/* Illustrate the use of Z_BLOCK, inflatePrime(), and inflateSetDictionary()
+ for random access of a compressed file. A file containing a zlib or gzip
+ stream is provided on the command line. The compressed stream is decoded in
+ its entirety, and an index built with access points about every SPAN bytes
+ in the uncompressed output. The compressed file is left open, and can then
+ be read randomly, having to decompress on the average SPAN/2 uncompressed
+ bytes before getting to the desired block of data.
+
+ An access point can be created at the start of any deflate block, by saving
+ the starting file offset and bit of that block, and the 32K bytes of
+ uncompressed data that precede that block. Also the uncompressed offset of
+ that block is saved to provide a referece for locating a desired starting
+ point in the uncompressed stream. build_index() works by decompressing the
+ input zlib or gzip stream a block at a time, and at the end of each block
+ deciding if enough uncompressed data has gone by to justify the creation of
+ a new access point. If so, that point is saved in a data structure that
+ grows as needed to accommodate the points.
+
+ To use the index, an offset in the uncompressed data is provided, for which
+ the latest accees point at or preceding that offset is located in the index.
+ The input file is positioned to the specified location in the index, and if
+ necessary the first few bits of the compressed data is read from the file.
+ inflate is initialized with those bits and the 32K of uncompressed data, and
+ the decompression then proceeds until the desired offset in the file is
+ reached. Then the decompression continues to read the desired uncompressed
+ data from the file.
+
+ Another approach would be to generate the index on demand. In that case,
+ requests for random access reads from the compressed data would try to use
+ the index, but if a read far enough past the end of the index is required,
+ then further index entries would be generated and added.
+
+ There is some fair bit of overhead to starting inflation for the random
+ access, mainly copying the 32K byte dictionary. So if small pieces of the
+ file are being accessed, it would make sense to implement a cache to hold
+ some lookahead and avoid many calls to extract() for small lengths.
+
+ Another way to build an index would be to use inflateCopy(). That would
+ not be constrained to have access points at block boundaries, but requires
+ more memory per access point, and also cannot be saved to file due to the
+ use of pointers in the state. The approach here allows for storage of the
+ index in a file.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "zlib.h"
+
+#define local static
+
+#define SPAN 1048576L /* desired distance between access points */
+#define WINSIZE 32768U /* sliding window size */
+#define CHUNK 16384 /* file input buffer size */
+
+/* access point entry */
+struct point {
+ off_t out; /* corresponding offset in uncompressed data */
+ off_t in; /* offset in input file of first full byte */
+ int bits; /* number of bits (1-7) from byte at in - 1, or 0 */
+ unsigned char window[WINSIZE]; /* preceding 32K of uncompressed data */
+};
+
+/* access point list */
+struct access {
+ int have; /* number of list entries filled in */
+ int size; /* number of list entries allocated */
+ struct point *list; /* allocated list */
+};
+
+/* Deallocate an index built by build_index() */
+local void free_index(struct access *index)
+{
+ if (index != NULL) {
+ free(index->list);
+ free(index);
+ }
+}
+
+/* Add an entry to the access point list. If out of memory, deallocate the
+ existing list and return NULL. */
+local struct access *addpoint(struct access *index, int bits,
+ off_t in, off_t out, unsigned left, unsigned char *window)
+{
+ struct point *next;
+
+ /* if list is empty, create it (start with eight points) */
+ if (index == NULL) {
+ index = malloc(sizeof(struct access));
+ if (index == NULL) return NULL;
+ index->list = malloc(sizeof(struct point) << 3);
+ if (index->list == NULL) {
+ free(index);
+ return NULL;
+ }
+ index->size = 8;
+ index->have = 0;
+ }
+
+ /* if list is full, make it bigger */
+ else if (index->have == index->size) {
+ index->size <<= 1;
+ next = realloc(index->list, sizeof(struct point) * index->size);
+ if (next == NULL) {
+ free_index(index);
+ return NULL;
+ }
+ index->list = next;
+ }
+
+ /* fill in entry and increment how many we have */
+ next = index->list + index->have;
+ next->bits = bits;
+ next->in = in;
+ next->out = out;
+ if (left)
+ memcpy(next->window, window + WINSIZE - left, left);
+ if (left < WINSIZE)
+ memcpy(next->window + left, window, WINSIZE - left);
+ index->have++;
+
+ /* return list, possibly reallocated */
+ return index;
+}
+
+/* Make one entire pass through the compressed stream and build an index, with
+ access points about every span bytes of uncompressed output -- span is
+ chosen to balance the speed of random access against the memory requirements
+ of the list, about 32K bytes per access point. Note that data after the end
+ of the first zlib or gzip stream in the file is ignored. build_index()
+ returns the number of access points on success (>= 1), Z_MEM_ERROR for out
+ of memory, Z_DATA_ERROR for an error in the input file, or Z_ERRNO for a
+ file read error. On success, *built points to the resulting index. */
+local int build_index(FILE *in, off_t span, struct access **built)
+{
+ int ret;
+ off_t totin, totout; /* our own total counters to avoid 4GB limit */
+ off_t last; /* totout value of last access point */
+ struct access *index; /* access points being generated */
+ z_stream strm;
+ unsigned char input[CHUNK];
+ unsigned char window[WINSIZE];
+
+ /* initialize inflate */
+ strm.zalloc = Z_NULL;
+ strm.zfree = Z_NULL;
+ strm.opaque = Z_NULL;
+ strm.avail_in = 0;
+ strm.next_in = Z_NULL;
+ ret = inflateInit2(&strm, 47); /* automatic zlib or gzip decoding */
+ if (ret != Z_OK)
+ return ret;
+
+ /* inflate the input, maintain a sliding window, and build an index -- this
+ also validates the integrity of the compressed data using the check
+ information at the end of the gzip or zlib stream */
+ totin = totout = last = 0;
+ index = NULL; /* will be allocated by first addpoint() */
+ strm.avail_out = 0;
+ do {
+ /* get some compressed data from input file */
+ strm.avail_in = fread(input, 1, CHUNK, in);
+ if (ferror(in)) {
+ ret = Z_ERRNO;
+ goto build_index_error;
+ }
+ if (strm.avail_in == 0) {
+ ret = Z_DATA_ERROR;
+ goto build_index_error;
+ }
+ strm.next_in = input;
+
+ /* process all of that, or until end of stream */
+ do {
+ /* reset sliding window if necessary */
+ if (strm.avail_out == 0) {
+ strm.avail_out = WINSIZE;
+ strm.next_out = window;
+ }
+
+ /* inflate until out of input, output, or at end of block --
+ update the total input and output counters */
+ totin += strm.avail_in;
+ totout += strm.avail_out;
+ ret = inflate(&strm, Z_BLOCK); /* return at end of block */
+ totin -= strm.avail_in;
+ totout -= strm.avail_out;
+ if (ret == Z_NEED_DICT)
+ ret = Z_DATA_ERROR;
+ if (ret == Z_MEM_ERROR || ret == Z_DATA_ERROR)
+ goto build_index_error;
+ if (ret == Z_STREAM_END)
+ break;
+
+ /* if at end of block, consider adding an index entry (note that if
+ data_type indicates an end-of-block, then all of the
+ uncompressed data from that block has been delivered, and none
+ of the compressed data after that block has been consumed,
+ except for up to seven bits) -- the totout == 0 provides an
+ entry point after the zlib or gzip header, and assures that the
+ index always has at least one access point; we avoid creating an
+ access point after the last block by checking bit 6 of data_type
+ */
+ if ((strm.data_type & 128) && !(strm.data_type & 64) &&
+ (totout == 0 || totout - last > span)) {
+ index = addpoint(index, strm.data_type & 7, totin,
+ totout, strm.avail_out, window);
+ if (index == NULL) {
+ ret = Z_MEM_ERROR;
+ goto build_index_error;
+ }
+ last = totout;
+ }
+ } while (strm.avail_in != 0);
+ } while (ret != Z_STREAM_END);
+
+ /* clean up and return index (release unused entries in list) */
+ (void)inflateEnd(&strm);
+ index = realloc(index, sizeof(struct point) * index->have);
+ index->size = index->have;
+ *built = index;
+ return index->size;
+
+ /* return error */
+ build_index_error:
+ (void)inflateEnd(&strm);
+ if (index != NULL)
+ free_index(index);
+ return ret;
+}
+
+/* Use the index to read len bytes from offset into buf, return bytes read or
+ negative for error (Z_DATA_ERROR or Z_MEM_ERROR). If data is requested past
+ the end of the uncompressed data, then extract() will return a value less
+ than len, indicating how much as actually read into buf. This function
+ should not return a data error unless the file was modified since the index
+ was generated. extract() may also return Z_ERRNO if there is an error on
+ reading or seeking the input file. */
+local int extract(FILE *in, struct access *index, off_t offset,
+ unsigned char *buf, int len)
+{
+ int ret, skip;
+ z_stream strm;
+ struct point *here;
+ unsigned char input[CHUNK];
+ unsigned char discard[WINSIZE];
+
+ /* proceed only if something reasonable to do */
+ if (len < 0)
+ return 0;
+
+ /* find where in stream to start */
+ here = index->list;
+ ret = index->have;
+ while (--ret && here[1].out <= offset)
+ here++;
+
+ /* initialize file and inflate state to start there */
+ strm.zalloc = Z_NULL;
+ strm.zfree = Z_NULL;
+ strm.opaque = Z_NULL;
+ strm.avail_in = 0;
+ strm.next_in = Z_NULL;
+ ret = inflateInit2(&strm, -15); /* raw inflate */
+ if (ret != Z_OK)
+ return ret;
+ ret = fseeko(in, here->in - (here->bits ? 1 : 0), SEEK_SET);
+ if (ret == -1)
+ goto extract_ret;
+ if (here->bits) {
+ ret = getc(in);
+ if (ret == -1) {
+ ret = ferror(in) ? Z_ERRNO : Z_DATA_ERROR;
+ goto extract_ret;
+ }
+ (void)inflatePrime(&strm, here->bits, ret >> (8 - here->bits));
+ }
+ (void)inflateSetDictionary(&strm, here->window, WINSIZE);
+
+ /* skip uncompressed bytes until offset reached, then satisfy request */
+ offset -= here->out;
+ strm.avail_in = 0;
+ skip = 1; /* while skipping to offset */
+ do {
+ /* define where to put uncompressed data, and how much */
+ if (offset == 0 && skip) { /* at offset now */
+ strm.avail_out = len;
+ strm.next_out = buf;
+ skip = 0; /* only do this once */
+ }
+ if (offset > WINSIZE) { /* skip WINSIZE bytes */
+ strm.avail_out = WINSIZE;
+ strm.next_out = discard;
+ offset -= WINSIZE;
+ }
+ else if (offset != 0) { /* last skip */
+ strm.avail_out = (unsigned)offset;
+ strm.next_out = discard;
+ offset = 0;
+ }
+
+ /* uncompress until avail_out filled, or end of stream */
+ do {
+ if (strm.avail_in == 0) {
+ strm.avail_in = fread(input, 1, CHUNK, in);
+ if (ferror(in)) {
+ ret = Z_ERRNO;
+ goto extract_ret;
+ }
+ if (strm.avail_in == 0) {
+ ret = Z_DATA_ERROR;
+ goto extract_ret;
+ }
+ strm.next_in = input;
+ }
+ ret = inflate(&strm, Z_NO_FLUSH); /* normal inflate */
+ if (ret == Z_NEED_DICT)
+ ret = Z_DATA_ERROR;
+ if (ret == Z_MEM_ERROR || ret == Z_DATA_ERROR)
+ goto extract_ret;
+ if (ret == Z_STREAM_END)
+ break;
+ } while (strm.avail_out != 0);
+
+ /* if reach end of stream, then don't keep trying to get more */
+ if (ret == Z_STREAM_END)
+ break;
+
+ /* do until offset reached and requested data read, or stream ends */
+ } while (skip);
+
+ /* compute number of uncompressed bytes read after offset */
+ ret = skip ? 0 : len - strm.avail_out;
+
+ /* clean up and return bytes read or error */
+ extract_ret:
+ (void)inflateEnd(&strm);
+ return ret;
+}
+
+/* Demonstrate the use of build_index() and extract() by processing the file
+ provided on the command line, and the extracting 16K from about 2/3rds of
+ the way through the uncompressed output, and writing that to stdout. */
+int main(int argc, char **argv)
+{
+ int len;
+ off_t offset;
+ FILE *in;
+ struct access *index;
+ unsigned char buf[CHUNK];
+
+ /* open input file */
+ if (argc != 2) {
+ fprintf(stderr, "usage: zran file.gz\n");
+ return 1;
+ }
+ in = fopen(argv[1], "rb");
+ if (in == NULL) {
+ fprintf(stderr, "zran: could not open %s for reading\n", argv[1]);
+ return 1;
+ }
+
+ /* build index */
+ len = build_index(in, SPAN, &index);
+ if (len < 0) {
+ fclose(in);
+ switch (len) {
+ case Z_MEM_ERROR:
+ fprintf(stderr, "zran: out of memory\n");
+ break;
+ case Z_DATA_ERROR:
+ fprintf(stderr, "zran: compressed data error in %s\n", argv[1]);
+ break;
+ case Z_ERRNO:
+ fprintf(stderr, "zran: read error on %s\n", argv[1]);
+ break;
+ default:
+ fprintf(stderr, "zran: error %d while building index\n", len);
+ }
+ return 1;
+ }
+ fprintf(stderr, "zran: built index with %d access points\n", len);
+
+ /* use index by reading some bytes from an arbitrary offset */
+ offset = (index->list[index->have - 1].out << 1) / 3;
+ len = extract(in, index, offset, buf, CHUNK);
+ if (len < 0)
+ fprintf(stderr, "zran: extraction failed: %s error\n",
+ len == Z_MEM_ERROR ? "out of memory" : "input corrupted");
+ else {
+ fwrite(buf, 1, len, stdout);
+ fprintf(stderr, "zran: extracted %d bytes at %llu\n", len, offset);
+ }
+
+ /* clean up and exit */
+ free_index(index);
+ fclose(in);
+ return 0;
+}