diff options
Diffstat (limited to 'cpukit/zlib/examples')
-rw-r--r-- | cpukit/zlib/examples/enough.c | 569 | ||||
-rw-r--r-- | cpukit/zlib/examples/gun.c | 701 | ||||
-rw-r--r-- | cpukit/zlib/examples/zran.c | 404 |
3 files changed, 0 insertions, 1674 deletions
diff --git a/cpukit/zlib/examples/enough.c b/cpukit/zlib/examples/enough.c deleted file mode 100644 index c40410bade..0000000000 --- a/cpukit/zlib/examples/enough.c +++ /dev/null @@ -1,569 +0,0 @@ -/* enough.c -- determine the maximum size of inflate's Huffman code tables over - * all possible valid and complete Huffman codes, subject to a length limit. - * Copyright (C) 2007, 2008 Mark Adler - * Version 1.3 17 February 2008 Mark Adler - */ - -/* Version history: - 1.0 3 Jan 2007 First version (derived from codecount.c version 1.4) - 1.1 4 Jan 2007 Use faster incremental table usage computation - Prune examine() search on previously visited states - 1.2 5 Jan 2007 Comments clean up - As inflate does, decrease root for short codes - Refuse cases where inflate would increase root - 1.3 17 Feb 2008 Add argument for initial root table size - Fix bug for initial root table size == max - 1 - Use a macro to compute the history index - */ - -/* - Examine all possible Huffman codes for a given number of symbols and a - maximum code length in bits to determine the maximum table size for zilb's - inflate. Only complete Huffman codes are counted. - - Two codes are considered distinct if the vectors of the number of codes per - length are not identical. So permutations of the symbol assignments result - in the same code for the counting, as do permutations of the assignments of - the bit values to the codes (i.e. only canonical codes are counted). - - We build a code from shorter to longer lengths, determining how many symbols - are coded at each length. At each step, we have how many symbols remain to - be coded, what the last code length used was, and how many bit patterns of - that length remain unused. Then we add one to the code length and double the - number of unused patterns to graduate to the next code length. We then - assign all portions of the remaining symbols to that code length that - preserve the properties of a correct and eventually complete code. Those - properties are: we cannot use more bit patterns than are available; and when - all the symbols are used, there are exactly zero possible bit patterns - remaining. - - The inflate Huffman decoding algorithm uses two-level lookup tables for - speed. There is a single first-level table to decode codes up to root bits - in length (root == 9 in the current inflate implementation). The table - has 1 << root entries and is indexed by the next root bits of input. Codes - shorter than root bits have replicated table entries, so that the correct - entry is pointed to regardless of the bits that follow the short code. If - the code is longer than root bits, then the table entry points to a second- - level table. The size of that table is determined by the longest code with - that root-bit prefix. If that longest code has length len, then the table - has size 1 << (len - root), to index the remaining bits in that set of - codes. Each subsequent root-bit prefix then has its own sub-table. The - total number of table entries required by the code is calculated - incrementally as the number of codes at each bit length is populated. When - all of the codes are shorter than root bits, then root is reduced to the - longest code length, resulting in a single, smaller, one-level table. - - The inflate algorithm also provides for small values of root (relative to - the log2 of the number of symbols), where the shortest code has more bits - than root. In that case, root is increased to the length of the shortest - code. This program, by design, does not handle that case, so it is verified - that the number of symbols is less than 2^(root + 1). - - In order to speed up the examination (by about ten orders of magnitude for - the default arguments), the intermediate states in the build-up of a code - are remembered and previously visited branches are pruned. The memory - required for this will increase rapidly with the total number of symbols and - the maximum code length in bits. However this is a very small price to pay - for the vast speedup. - - First, all of the possible Huffman codes are counted, and reachable - intermediate states are noted by a non-zero count in a saved-results array. - Second, the intermediate states that lead to (root + 1) bit or longer codes - are used to look at all sub-codes from those junctures for their inflate - memory usage. (The amount of memory used is not affected by the number of - codes of root bits or less in length.) Third, the visited states in the - construction of those sub-codes and the associated calculation of the table - size is recalled in order to avoid recalculating from the same juncture. - Beginning the code examination at (root + 1) bit codes, which is enabled by - identifying the reachable nodes, accounts for about six of the orders of - magnitude of improvement for the default arguments. About another four - orders of magnitude come from not revisiting previous states. Out of - approximately 2x10^16 possible Huffman codes, only about 2x10^6 sub-codes - need to be examined to cover all of the possible table memory usage cases - for the default arguments of 286 symbols limited to 15-bit codes. - - Note that an unsigned long long type is used for counting. It is quite easy - to exceed the capacity of an eight-byte integer with a large number of - symbols and a large maximum code length, so multiple-precision arithmetic - would need to replace the unsigned long long arithmetic in that case. This - program will abort if an overflow occurs. The big_t type identifies where - the counting takes place. - - An unsigned long long type is also used for calculating the number of - possible codes remaining at the maximum length. This limits the maximum - code length to the number of bits in a long long minus the number of bits - needed to represent the symbols in a flat code. The code_t type identifies - where the bit pattern counting takes place. - */ - -#include <stdio.h> -#include <stdlib.h> -#include <string.h> -#include <assert.h> - -#define local static - -/* special data types */ -typedef unsigned long long big_t; /* type for code counting */ -typedef unsigned long long code_t; /* type for bit pattern counting */ -struct tab { /* type for been here check */ - size_t len; /* length of bit vector in char's */ - char *vec; /* allocated bit vector */ -}; - -/* The array for saving results, num[], is indexed with this triplet: - - syms: number of symbols remaining to code - left: number of available bit patterns at length len - len: number of bits in the codes currently being assigned - - Those indices are constrained thusly when saving results: - - syms: 3..totsym (totsym == total symbols to code) - left: 2..syms - 1, but only the evens (so syms == 8 -> 2, 4, 6) - len: 1..max - 1 (max == maximum code length in bits) - - syms == 2 is not saved since that immediately leads to a single code. left - must be even, since it represents the number of available bit patterns at - the current length, which is double the number at the previous length. - left ends at syms-1 since left == syms immediately results in a single code. - (left > sym is not allowed since that would result in an incomplete code.) - len is less than max, since the code completes immediately when len == max. - - The offset into the array is calculated for the three indices with the - first one (syms) being outermost, and the last one (len) being innermost. - We build the array with length max-1 lists for the len index, with syms-3 - of those for each symbol. There are totsym-2 of those, with each one - varying in length as a function of sym. See the calculation of index in - count() for the index, and the calculation of size in main() for the size - of the array. - - For the deflate example of 286 symbols limited to 15-bit codes, the array - has 284,284 entries, taking up 2.17 MB for an 8-byte big_t. More than - half of the space allocated for saved results is actually used -- not all - possible triplets are reached in the generation of valid Huffman codes. - */ - -/* The array for tracking visited states, done[], is itself indexed identically - to the num[] array as described above for the (syms, left, len) triplet. - Each element in the array is further indexed by the (mem, rem) doublet, - where mem is the amount of inflate table space used so far, and rem is the - remaining unused entries in the current inflate sub-table. Each indexed - element is simply one bit indicating whether the state has been visited or - not. Since the ranges for mem and rem are not known a priori, each bit - vector is of a variable size, and grows as needed to accommodate the visited - states. mem and rem are used to calculate a single index in a triangular - array. Since the range of mem is expected in the default case to be about - ten times larger than the range of rem, the array is skewed to reduce the - memory usage, with eight times the range for mem than for rem. See the - calculations for offset and bit in beenhere() for the details. - - For the deflate example of 286 symbols limited to 15-bit codes, the bit - vectors grow to total approximately 21 MB, in addition to the 4.3 MB done[] - array itself. - */ - -/* Globals to avoid propagating constants or constant pointers recursively */ -local int max; /* maximum allowed bit length for the codes */ -local int root; /* size of base code table in bits */ -local int large; /* largest code table so far */ -local size_t size; /* number of elements in num and done */ -local int *code; /* number of symbols assigned to each bit length */ -local big_t *num; /* saved results array for code counting */ -local struct tab *done; /* states already evaluated array */ - -/* Index function for num[] and done[] */ -#define INDEX(i,j,k) (((size_t)((i-1)>>1)*((i-2)>>1)+(j>>1)-1)*(max-1)+k-1) - -/* Free allocated space. Uses globals code, num, and done. */ -local void cleanup(void) -{ - size_t n; - - if (done != NULL) { - for (n = 0; n < size; n++) - if (done[n].len) - free(done[n].vec); - free(done); - } - if (num != NULL) - free(num); - if (code != NULL) - free(code); -} - -/* Return the number of possible Huffman codes using bit patterns of lengths - len through max inclusive, coding syms symbols, with left bit patterns of - length len unused -- return -1 if there is an overflow in the counting. - Keep a record of previous results in num to prevent repeating the same - calculation. Uses the globals max and num. */ -local big_t count(int syms, int len, int left) -{ - big_t sum; /* number of possible codes from this juncture */ - big_t got; /* value returned from count() */ - int least; /* least number of syms to use at this juncture */ - int most; /* most number of syms to use at this juncture */ - int use; /* number of bit patterns to use in next call */ - size_t index; /* index of this case in *num */ - - /* see if only one possible code */ - if (syms == left) - return 1; - - /* note and verify the expected state */ - assert(syms > left && left > 0 && len < max); - - /* see if we've done this one already */ - index = INDEX(syms, left, len); - got = num[index]; - if (got) - return got; /* we have -- return the saved result */ - - /* we need to use at least this many bit patterns so that the code won't be - incomplete at the next length (more bit patterns than symbols) */ - least = (left << 1) - syms; - if (least < 0) - least = 0; - - /* we can use at most this many bit patterns, lest there not be enough - available for the remaining symbols at the maximum length (if there were - no limit to the code length, this would become: most = left - 1) */ - most = (((code_t)left << (max - len)) - syms) / - (((code_t)1 << (max - len)) - 1); - - /* count all possible codes from this juncture and add them up */ - sum = 0; - for (use = least; use <= most; use++) { - got = count(syms - use, len + 1, (left - use) << 1); - sum += got; - if (got == -1 || sum < got) /* overflow */ - return -1; - } - - /* verify that all recursive calls are productive */ - assert(sum != 0); - - /* save the result and return it */ - num[index] = sum; - return sum; -} - -/* Return true if we've been here before, set to true if not. Set a bit in a - bit vector to indicate visiting this state. Each (syms,len,left) state - has a variable size bit vector indexed by (mem,rem). The bit vector is - lengthened if needed to allow setting the (mem,rem) bit. */ -local int beenhere(int syms, int len, int left, int mem, int rem) -{ - size_t index; /* index for this state's bit vector */ - size_t offset; /* offset in this state's bit vector */ - int bit; /* mask for this state's bit */ - size_t length; /* length of the bit vector in bytes */ - char *vector; /* new or enlarged bit vector */ - - /* point to vector for (syms,left,len), bit in vector for (mem,rem) */ - index = INDEX(syms, left, len); - mem -= 1 << root; - offset = (mem >> 3) + rem; - offset = ((offset * (offset + 1)) >> 1) + rem; - bit = 1 << (mem & 7); - - /* see if we've been here */ - length = done[index].len; - if (offset < length && (done[index].vec[offset] & bit) != 0) - return 1; /* done this! */ - - /* we haven't been here before -- set the bit to show we have now */ - - /* see if we need to lengthen the vector in order to set the bit */ - if (length <= offset) { - /* if we have one already, enlarge it, zero out the appended space */ - if (length) { - do { - length <<= 1; - } while (length <= offset); - vector = realloc(done[index].vec, length); - if (vector != NULL) - memset(vector + done[index].len, 0, length - done[index].len); - } - - /* otherwise we need to make a new vector and zero it out */ - else { - length = 1 << (len - root); - while (length <= offset) - length <<= 1; - vector = calloc(length, sizeof(char)); - } - - /* in either case, bail if we can't get the memory */ - if (vector == NULL) { - fputs("abort: unable to allocate enough memory\n", stderr); - cleanup(); - exit(1); - } - - /* install the new vector */ - done[index].len = length; - done[index].vec = vector; - } - - /* set the bit */ - done[index].vec[offset] |= bit; - return 0; -} - -/* Examine all possible codes from the given node (syms, len, left). Compute - the amount of memory required to build inflate's decoding tables, where the - number of code structures used so far is mem, and the number remaining in - the current sub-table is rem. Uses the globals max, code, root, large, and - done. */ -local void examine(int syms, int len, int left, int mem, int rem) -{ - int least; /* least number of syms to use at this juncture */ - int most; /* most number of syms to use at this juncture */ - int use; /* number of bit patterns to use in next call */ - - /* see if we have a complete code */ - if (syms == left) { - /* set the last code entry */ - code[len] = left; - - /* complete computation of memory used by this code */ - while (rem < left) { - left -= rem; - rem = 1 << (len - root); - mem += rem; - } - assert(rem == left); - - /* if this is a new maximum, show the entries used and the sub-code */ - if (mem > large) { - large = mem; - printf("max %d: ", mem); - for (use = root + 1; use <= max; use++) - if (code[use]) - printf("%d[%d] ", code[use], use); - putchar('\n'); - fflush(stdout); - } - - /* remove entries as we drop back down in the recursion */ - code[len] = 0; - return; - } - - /* prune the tree if we can */ - if (beenhere(syms, len, left, mem, rem)) - return; - - /* we need to use at least this many bit patterns so that the code won't be - incomplete at the next length (more bit patterns than symbols) */ - least = (left << 1) - syms; - if (least < 0) - least = 0; - - /* we can use at most this many bit patterns, lest there not be enough - available for the remaining symbols at the maximum length (if there were - no limit to the code length, this would become: most = left - 1) */ - most = (((code_t)left << (max - len)) - syms) / - (((code_t)1 << (max - len)) - 1); - - /* occupy least table spaces, creating new sub-tables as needed */ - use = least; - while (rem < use) { - use -= rem; - rem = 1 << (len - root); - mem += rem; - } - rem -= use; - - /* examine codes from here, updating table space as we go */ - for (use = least; use <= most; use++) { - code[len] = use; - examine(syms - use, len + 1, (left - use) << 1, - mem + (rem ? 1 << (len - root) : 0), rem << 1); - if (rem == 0) { - rem = 1 << (len - root); - mem += rem; - } - rem--; - } - - /* remove entries as we drop back down in the recursion */ - code[len] = 0; -} - -/* Look at all sub-codes starting with root + 1 bits. Look at only the valid - intermediate code states (syms, left, len). For each completed code, - calculate the amount of memory required by inflate to build the decoding - tables. Find the maximum amount of memory required and show the code that - requires that maximum. Uses the globals max, root, and num. */ -local void enough(int syms) -{ - int n; /* number of remaing symbols for this node */ - int left; /* number of unused bit patterns at this length */ - size_t index; /* index of this case in *num */ - - /* clear code */ - for (n = 0; n <= max; n++) - code[n] = 0; - - /* look at all (root + 1) bit and longer codes */ - large = 1 << root; /* base table */ - if (root < max) /* otherwise, there's only a base table */ - for (n = 3; n <= syms; n++) - for (left = 2; left < n; left += 2) - { - /* look at all reachable (root + 1) bit nodes, and the - resulting codes (complete at root + 2 or more) */ - index = INDEX(n, left, root + 1); - if (root + 1 < max && num[index]) /* reachable node */ - examine(n, root + 1, left, 1 << root, 0); - - /* also look at root bit codes with completions at root + 1 - bits (not saved in num, since complete), just in case */ - if (num[index - 1] && n <= left << 1) - examine((n - left) << 1, root + 1, (n - left) << 1, - 1 << root, 0); - } - - /* done */ - printf("done: maximum of %d table entries\n", large); -} - -/* - Examine and show the total number of possible Huffman codes for a given - maximum number of symbols, initial root table size, and maximum code length - in bits -- those are the command arguments in that order. The default - values are 286, 9, and 15 respectively, for the deflate literal/length code. - The possible codes are counted for each number of coded symbols from two to - the maximum. The counts for each of those and the total number of codes are - shown. The maximum number of inflate table entires is then calculated - across all possible codes. Each new maximum number of table entries and the - associated sub-code (starting at root + 1 == 10 bits) is shown. - - To count and examine Huffman codes that are not length-limited, provide a - maximum length equal to the number of symbols minus one. - - For the deflate literal/length code, use "enough". For the deflate distance - code, use "enough 30 6". - - This uses the %llu printf format to print big_t numbers, which assumes that - big_t is an unsigned long long. If the big_t type is changed (for example - to a multiple precision type), the method of printing will also need to be - updated. - */ -int main(int argc, char **argv) -{ - int syms; /* total number of symbols to code */ - int n; /* number of symbols to code for this run */ - big_t got; /* return value of count() */ - big_t sum; /* accumulated number of codes over n */ - - /* set up globals for cleanup() */ - code = NULL; - num = NULL; - done = NULL; - - /* get arguments -- default to the deflate literal/length code */ - syms = 286; - root = 9; - max = 15; - if (argc > 1) { - syms = atoi(argv[1]); - if (argc > 2) { - root = atoi(argv[2]); - if (argc > 3) - max = atoi(argv[3]); - } - } - if (argc > 4 || syms < 2 || root < 1 || max < 1) { - fputs("invalid arguments, need: [sym >= 2 [root >= 1 [max >= 1]]]\n", - stderr); - return 1; - } - - /* if not restricting the code length, the longest is syms - 1 */ - if (max > syms - 1) - max = syms - 1; - - /* determine the number of bits in a code_t */ - n = 0; - while (((code_t)1 << n) != 0) - n++; - - /* make sure that the calculation of most will not overflow */ - if (max > n || syms - 2 >= (((code_t)0 - 1) >> (max - 1))) { - fputs("abort: code length too long for internal types\n", stderr); - return 1; - } - - /* reject impossible code requests */ - if (syms - 1 > ((code_t)1 << max) - 1) { - fprintf(stderr, "%d symbols cannot be coded in %d bits\n", - syms, max); - return 1; - } - - /* allocate code vector */ - code = calloc(max + 1, sizeof(int)); - if (code == NULL) { - fputs("abort: unable to allocate enough memory\n", stderr); - return 1; - } - - /* determine size of saved results array, checking for overflows, - allocate and clear the array (set all to zero with calloc()) */ - if (syms == 2) /* iff max == 1 */ - num = NULL; /* won't be saving any results */ - else { - size = syms >> 1; - if (size > ((size_t)0 - 1) / (n = (syms - 1) >> 1) || - (size *= n, size > ((size_t)0 - 1) / (n = max - 1)) || - (size *= n, size > ((size_t)0 - 1) / sizeof(big_t)) || - (num = calloc(size, sizeof(big_t))) == NULL) { - fputs("abort: unable to allocate enough memory\n", stderr); - cleanup(); - return 1; - } - } - - /* count possible codes for all numbers of symbols, add up counts */ - sum = 0; - for (n = 2; n <= syms; n++) { - got = count(n, 1, 2); - sum += got; - if (got == -1 || sum < got) { /* overflow */ - fputs("abort: can't count that high!\n", stderr); - cleanup(); - return 1; - } - printf("%llu %d-codes\n", got, n); - } - printf("%llu total codes for 2 to %d symbols", sum, syms); - if (max < syms - 1) - printf(" (%d-bit length limit)\n", max); - else - puts(" (no length limit)"); - - /* allocate and clear done array for beenhere() */ - if (syms == 2) - done = NULL; - else if (size > ((size_t)0 - 1) / sizeof(struct tab) || - (done = calloc(size, sizeof(struct tab))) == NULL) { - fputs("abort: unable to allocate enough memory\n", stderr); - cleanup(); - return 1; - } - - /* find and show maximum inflate table usage */ - if (root > max) /* reduce root to max length */ - root = max; - if (syms < ((code_t)1 << (root + 1))) - enough(syms); - else - puts("cannot handle minimum code lengths > root"); - - /* done */ - cleanup(); - return 0; -} diff --git a/cpukit/zlib/examples/gun.c b/cpukit/zlib/examples/gun.c deleted file mode 100644 index 72b0882ab8..0000000000 --- a/cpukit/zlib/examples/gun.c +++ /dev/null @@ -1,701 +0,0 @@ -/* gun.c -- simple gunzip to give an example of the use of inflateBack() - * Copyright (C) 2003, 2005, 2008, 2010 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - Version 1.6 17 January 2010 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] - 1.4 8 Dec 2006 LZW decompression speed improvements - 1.5 9 Feb 2008 Avoid warning in latest version of gcc - 1.6 17 Jan 2010 Avoid signed/unsigned comparison warnings - */ - -/* - 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 */ - unsigned 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 */ - unsigned 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 */ - unsigned char *p; - - /* 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 */ - p = match + stack; - while (code >= 256) { - *p++ = suffix[code]; - code = prefix[code]; - } - stack = p - match; - 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; - } - p = match + stack; - do { - outbuf[outcnt++] = *--p; - } while (p > match); - stack = 0; - - /* 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 = NULL; - 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() != (int)(outd.crc & 0xff) || - NEXT() != (int)((outd.crc >> 8) & 0xff) || - NEXT() != (int)((outd.crc >> 16) & 0xff) || - NEXT() != (int)((outd.crc >> 24) & 0xff)) { - /* crc error */ - if (last != -1) { - strm->msg = (char *)"incorrect data check"; - ret = Z_DATA_ERROR; - } - break; - } - if (NEXT() != (int)(outd.total & 0xff) || - NEXT() != (int)((outd.total >> 8) & 0xff) || - NEXT() != (int)((outd.total >> 16) & 0xff) || - NEXT() != (int)((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 1.6 (17 Jan 2010)\n"); - fprintf(stderr, "Copyright (C) 2003-2010 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/cpukit/zlib/examples/zran.c b/cpukit/zlib/examples/zran.c deleted file mode 100644 index 617a13086f..0000000000 --- a/cpukit/zlib/examples/zran.c +++ /dev/null @@ -1,404 +0,0 @@ -/* 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 = NULL; - 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; -} |