From: Jean-loup Gailly Date: Fri, 13 Aug 1993 12:35:31 +0000 (+0000) Subject: gzip 1.2.4 X-Git-Tag: v1.3.12~139 X-Git-Url: https://git.gag.com/?a=commitdiff_plain;h=95ace546d3f6c5909a636017f141784105f9dab2;p=debian%2Fgzip gzip 1.2.4 --- diff --git a/deflate.c b/deflate.c new file mode 100644 index 0000000..d818248 --- /dev/null +++ b/deflate.c @@ -0,0 +1,763 @@ +/* deflate.c -- compress data using the deflation algorithm + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +/* + * PURPOSE + * + * Identify new text as repetitions of old text within a fixed- + * length sliding window trailing behind the new text. + * + * DISCUSSION + * + * The "deflation" process depends on being able to identify portions + * of the input text which are identical to earlier input (within a + * sliding window trailing behind the input currently being processed). + * + * The most straightforward technique turns out to be the fastest for + * most input files: try all possible matches and select the longest. + * The key feature of this algorithm is that insertions into the string + * dictionary are very simple and thus fast, and deletions are avoided + * completely. Insertions are performed at each input character, whereas + * string matches are performed only when the previous match ends. So it + * is preferable to spend more time in matches to allow very fast string + * insertions and avoid deletions. The matching algorithm for small + * strings is inspired from that of Rabin & Karp. A brute force approach + * is used to find longer strings when a small match has been found. + * A similar algorithm is used in comic (by Jan-Mark Wams) and freeze + * (by Leonid Broukhis). + * A previous version of this file used a more sophisticated algorithm + * (by Fiala and Greene) which is guaranteed to run in linear amortized + * time, but has a larger average cost, uses more memory and is patented. + * However the F&G algorithm may be faster for some highly redundant + * files if the parameter max_chain_length (described below) is too large. + * + * ACKNOWLEDGEMENTS + * + * The idea of lazy evaluation of matches is due to Jan-Mark Wams, and + * I found it in 'freeze' written by Leonid Broukhis. + * Thanks to many info-zippers for bug reports and testing. + * + * REFERENCES + * + * APPNOTE.TXT documentation file in PKZIP 1.93a distribution. + * + * A description of the Rabin and Karp algorithm is given in the book + * "Algorithms" by R. Sedgewick, Addison-Wesley, p252. + * + * Fiala,E.R., and Greene,D.H. + * Data Compression with Finite Windows, Comm.ACM, 32,4 (1989) 490-595 + * + * INTERFACE + * + * void lm_init (int pack_level, ush *flags) + * Initialize the "longest match" routines for a new file + * + * ulg deflate (void) + * Processes a new input file and return its compressed length. Sets + * the compressed length, crc, deflate flags and internal file + * attributes. + */ + +#include + +#include "tailor.h" +#include "gzip.h" +#include "lzw.h" /* just for consistency checking */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +/* =========================================================================== + * Configuration parameters + */ + +/* Compile with MEDIUM_MEM to reduce the memory requirements or + * with SMALL_MEM to use as little memory as possible. Use BIG_MEM if the + * entire input file can be held in memory (not possible on 16 bit systems). + * Warning: defining these symbols affects HASH_BITS (see below) and thus + * affects the compression ratio. The compressed output + * is still correct, and might even be smaller in some cases. + */ + +#ifdef SMALL_MEM +# define HASH_BITS 13 /* Number of bits used to hash strings */ +#endif +#ifdef MEDIUM_MEM +# define HASH_BITS 14 +#endif +#ifndef HASH_BITS +# define HASH_BITS 15 + /* For portability to 16 bit machines, do not use values above 15. */ +#endif + +/* To save space (see unlzw.c), we overlay prev+head with tab_prefix and + * window with tab_suffix. Check that we can do this: + */ +#if (WSIZE<<1) > (1< BITS-1 + error: cannot overlay head with tab_prefix1 +#endif + +#define HASH_SIZE (unsigned)(1<= HASH_BITS + */ + +unsigned int near prev_length; +/* Length of the best match at previous step. Matches not greater than this + * are discarded. This is used in the lazy match evaluation. + */ + + unsigned near strstart; /* start of string to insert */ + unsigned near match_start; /* start of matching string */ +local int eofile; /* flag set at end of input file */ +local unsigned lookahead; /* number of valid bytes ahead in window */ + +unsigned near max_chain_length; +/* To speed up deflation, hash chains are never searched beyond this length. + * A higher limit improves compression ratio but degrades the speed. + */ + +local unsigned int max_lazy_match; +/* Attempt to find a better match only when the current match is strictly + * smaller than this value. This mechanism is used only for compression + * levels >= 4. + */ +#define max_insert_length max_lazy_match +/* Insert new strings in the hash table only if the match length + * is not greater than this length. This saves time but degrades compression. + * max_insert_length is used only for compression levels <= 3. + */ + +local int compr_level; +/* compression level (1..9) */ + +unsigned near good_match; +/* Use a faster search when the previous match is longer than this */ + + +/* Values for max_lazy_match, good_match and max_chain_length, depending on + * the desired pack level (0..9). The values given below have been tuned to + * exclude worst case performance for pathological files. Better values may be + * found for specific files. + */ + +typedef struct config { + ush good_length; /* reduce lazy search above this match length */ + ush max_lazy; /* do not perform lazy search above this match length */ + ush nice_length; /* quit search above this match length */ + ush max_chain; +} config; + +#ifdef FULL_SEARCH +# define nice_match MAX_MATCH +#else + int near nice_match; /* Stop searching when current match exceeds this */ +#endif + +local config configuration_table[10] = { +/* good lazy nice chain */ +/* 0 */ {0, 0, 0, 0}, /* store only */ +/* 1 */ {4, 4, 8, 4}, /* maximum speed, no lazy matches */ +/* 2 */ {4, 5, 16, 8}, +/* 3 */ {4, 6, 32, 32}, + +/* 4 */ {4, 4, 16, 16}, /* lazy matches */ +/* 5 */ {8, 16, 32, 32}, +/* 6 */ {8, 16, 128, 128}, +/* 7 */ {8, 32, 128, 256}, +/* 8 */ {32, 128, 258, 1024}, +/* 9 */ {32, 258, 258, 4096}}; /* maximum compression */ + +/* Note: the deflate() code requires max_lazy >= MIN_MATCH and max_chain >= 4 + * For deflate_fast() (levels <= 3) good is ignored and lazy has a different + * meaning. + */ + +#define EQUAL 0 +/* result of memcmp for equal strings */ + +/* =========================================================================== + * Prototypes for local functions. + */ +local void fill_window OF((void)); +local ulg deflate_fast OF((void)); + + int longest_match OF((IPos cur_match)); +#ifdef ASMV + void match_init OF((void)); /* asm code initialization */ +#endif + +#ifdef DEBUG +local void check_match OF((IPos start, IPos match, int length)); +#endif + +/* =========================================================================== + * Update a hash value with the given input byte + * IN assertion: all calls to to UPDATE_HASH are made with consecutive + * input characters, so that a running hash key can be computed from the + * previous key instead of complete recalculation each time. + */ +#define UPDATE_HASH(h,c) (h = (((h)< 9) error("bad pack level"); + compr_level = pack_level; + + /* Initialize the hash table. */ +#if defined(MAXSEG_64K) && HASH_BITS == 15 + for (j = 0; j < HASH_SIZE; j++) head[j] = NIL; +#else + memzero((char*)head, HASH_SIZE*sizeof(*head)); +#endif + /* prev will be initialized on the fly */ + + /* Set the default configuration parameters: + */ + max_lazy_match = configuration_table[pack_level].max_lazy; + good_match = configuration_table[pack_level].good_length; +#ifndef FULL_SEARCH + nice_match = configuration_table[pack_level].nice_length; +#endif + max_chain_length = configuration_table[pack_level].max_chain; + if (pack_level == 1) { + *flags |= FAST; + } else if (pack_level == 9) { + *flags |= SLOW; + } + /* ??? reduce max_chain_length for binary files */ + + strstart = 0; + block_start = 0L; +#ifdef ASMV + match_init(); /* initialize the asm code */ +#endif + + lookahead = read_buf((char*)window, + sizeof(int) <= 2 ? (unsigned)WSIZE : 2*WSIZE); + + if (lookahead == 0 || lookahead == (unsigned)EOF) { + eofile = 1, lookahead = 0; + return; + } + eofile = 0; + /* Make sure that we always have enough lookahead. This is important + * if input comes from a device such as a tty. + */ + while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window(); + + ins_h = 0; + for (j=0; j= 1 + */ +#ifndef ASMV +/* For MSDOS, OS/2 and 386 Unix, an optimized version is in match.asm or + * match.s. The code is functionally equivalent, so you can use the C version + * if desired. + */ +int longest_match(cur_match) + IPos cur_match; /* current match */ +{ + unsigned chain_length = max_chain_length; /* max hash chain length */ + register uch *scan = window + strstart; /* current string */ + register uch *match; /* matched string */ + register int len; /* length of current match */ + int best_len = prev_length; /* best match length so far */ + IPos limit = strstart > (IPos)MAX_DIST ? strstart - (IPos)MAX_DIST : NIL; + /* Stop when cur_match becomes <= limit. To simplify the code, + * we prevent matches with the string of window index 0. + */ + +/* The code is optimized for HASH_BITS >= 8 and MAX_MATCH-2 multiple of 16. + * It is easy to get rid of this optimization if necessary. + */ +#if HASH_BITS < 8 || MAX_MATCH != 258 + error: Code too clever +#endif + +#ifdef UNALIGNED_OK + /* Compare two bytes at a time. Note: this is not always beneficial. + * Try with and without -DUNALIGNED_OK to check. + */ + register uch *strend = window + strstart + MAX_MATCH - 1; + register ush scan_start = *(ush*)scan; + register ush scan_end = *(ush*)(scan+best_len-1); +#else + register uch *strend = window + strstart + MAX_MATCH; + register uch scan_end1 = scan[best_len-1]; + register uch scan_end = scan[best_len]; +#endif + + /* Do not waste too much time if we already have a good match: */ + if (prev_length >= good_match) { + chain_length >>= 2; + } + Assert(strstart <= window_size-MIN_LOOKAHEAD, "insufficient lookahead"); + + do { + Assert(cur_match < strstart, "no future"); + match = window + cur_match; + + /* Skip to next match if the match length cannot increase + * or if the match length is less than 2: + */ +#if (defined(UNALIGNED_OK) && MAX_MATCH == 258) + /* This code assumes sizeof(unsigned short) == 2. Do not use + * UNALIGNED_OK if your compiler uses a different size. + */ + if (*(ush*)(match+best_len-1) != scan_end || + *(ush*)match != scan_start) continue; + + /* It is not necessary to compare scan[2] and match[2] since they are + * always equal when the other bytes match, given that the hash keys + * are equal and that HASH_BITS >= 8. Compare 2 bytes at a time at + * strstart+3, +5, ... up to strstart+257. We check for insufficient + * lookahead only every 4th comparison; the 128th check will be made + * at strstart+257. If MAX_MATCH-2 is not a multiple of 8, it is + * necessary to put more guard bytes at the end of the window, or + * to check more often for insufficient lookahead. + */ + scan++, match++; + do { + } while (*(ush*)(scan+=2) == *(ush*)(match+=2) && + *(ush*)(scan+=2) == *(ush*)(match+=2) && + *(ush*)(scan+=2) == *(ush*)(match+=2) && + *(ush*)(scan+=2) == *(ush*)(match+=2) && + scan < strend); + /* The funny "do {}" generates better code on most compilers */ + + /* Here, scan <= window+strstart+257 */ + Assert(scan <= window+(unsigned)(window_size-1), "wild scan"); + if (*scan == *match) scan++; + + len = (MAX_MATCH - 1) - (int)(strend-scan); + scan = strend - (MAX_MATCH-1); + +#else /* UNALIGNED_OK */ + + if (match[best_len] != scan_end || + match[best_len-1] != scan_end1 || + *match != *scan || + *++match != scan[1]) continue; + + /* The check at best_len-1 can be removed because it will be made + * again later. (This heuristic is not always a win.) + * It is not necessary to compare scan[2] and match[2] since they + * are always equal when the other bytes match, given that + * the hash keys are equal and that HASH_BITS >= 8. + */ + scan += 2, match++; + + /* We check for insufficient lookahead only every 8th comparison; + * the 256th check will be made at strstart+258. + */ + do { + } while (*++scan == *++match && *++scan == *++match && + *++scan == *++match && *++scan == *++match && + *++scan == *++match && *++scan == *++match && + *++scan == *++match && *++scan == *++match && + scan < strend); + + len = MAX_MATCH - (int)(strend - scan); + scan = strend - MAX_MATCH; + +#endif /* UNALIGNED_OK */ + + if (len > best_len) { + match_start = cur_match; + best_len = len; + if (len >= nice_match) break; +#ifdef UNALIGNED_OK + scan_end = *(ush*)(scan+best_len-1); +#else + scan_end1 = scan[best_len-1]; + scan_end = scan[best_len]; +#endif + } + } while ((cur_match = prev[cur_match & WMASK]) > limit + && --chain_length != 0); + + return best_len; +} +#endif /* ASMV */ + +#ifdef DEBUG +/* =========================================================================== + * Check that the match at match_start is indeed a match. + */ +local void check_match(start, match, length) + IPos start, match; + int length; +{ + /* check that the match is indeed a match */ + if (memcmp((char*)window + match, + (char*)window + start, length) != EQUAL) { + fprintf(stderr, + " start %d, match %d, length %d\n", + start, match, length); + error("invalid match"); + } + if (verbose > 1) { + fprintf(stderr,"\\[%d,%d]", start-match, length); + do { putc(window[start++], stderr); } while (--length != 0); + } +} +#else +# define check_match(start, match, length) +#endif + +/* =========================================================================== + * Fill the window when the lookahead becomes insufficient. + * Updates strstart and lookahead, and sets eofile if end of input file. + * IN assertion: lookahead < MIN_LOOKAHEAD && strstart + lookahead > 0 + * OUT assertions: at least one byte has been read, or eofile is set; + * file reads are performed for at least two bytes (required for the + * translate_eol option). + */ +local void fill_window() +{ + register unsigned n, m; + unsigned more = (unsigned)(window_size - (ulg)lookahead - (ulg)strstart); + /* Amount of free space at the end of the window. */ + + /* If the window is almost full and there is insufficient lookahead, + * move the upper half to the lower one to make room in the upper half. + */ + if (more == (unsigned)EOF) { + /* Very unlikely, but possible on 16 bit machine if strstart == 0 + * and lookahead == 1 (input done one byte at time) + */ + more--; + } else if (strstart >= WSIZE+MAX_DIST) { + /* By the IN assertion, the window is not empty so we can't confuse + * more == 0 with more == 64K on a 16 bit machine. + */ + Assert(window_size == (ulg)2*WSIZE, "no sliding with BIG_MEM"); + + memcpy((char*)window, (char*)window+WSIZE, (unsigned)WSIZE); + match_start -= WSIZE; + strstart -= WSIZE; /* we now have strstart >= MAX_DIST: */ + + block_start -= (long) WSIZE; + + for (n = 0; n < HASH_SIZE; n++) { + m = head[n]; + head[n] = (Pos)(m >= WSIZE ? m-WSIZE : NIL); + } + for (n = 0; n < WSIZE; n++) { + m = prev[n]; + prev[n] = (Pos)(m >= WSIZE ? m-WSIZE : NIL); + /* If n is not on any hash chain, prev[n] is garbage but + * its value will never be used. + */ + } + more += WSIZE; + } + /* At this point, more >= 2 */ + if (!eofile) { + n = read_buf((char*)window+strstart+lookahead, more); + if (n == 0 || n == (unsigned)EOF) { + eofile = 1; + } else { + lookahead += n; + } + } +} + +/* =========================================================================== + * Flush the current block, with given end-of-file flag. + * IN assertion: strstart is set to the end of the current match. + */ +#define FLUSH_BLOCK(eof) \ + flush_block(block_start >= 0L ? (char*)&window[(unsigned)block_start] : \ + (char*)NULL, (long)strstart - block_start, (eof)) + +/* =========================================================================== + * Processes a new input file and return its compressed length. This + * function does not perform lazy evaluationof matches and inserts + * new strings in the dictionary only for unmatched strings or for short + * matches. It is used only for the fast compression options. + */ +local ulg deflate_fast() +{ + IPos hash_head; /* head of the hash chain */ + int flush; /* set if current block must be flushed */ + unsigned match_length = 0; /* length of best match */ + + prev_length = MIN_MATCH-1; + while (lookahead != 0) { + /* Insert the string window[strstart .. strstart+2] in the + * dictionary, and set hash_head to the head of the hash chain: + */ + INSERT_STRING(strstart, hash_head); + + /* Find the longest match, discarding those <= prev_length. + * At this point we have always match_length < MIN_MATCH + */ + if (hash_head != NIL && strstart - hash_head <= MAX_DIST) { + /* To simplify the code, we prevent matches with the string + * of window index 0 (in particular we have to avoid a match + * of the string with itself at the start of the input file). + */ + match_length = longest_match (hash_head); + /* longest_match() sets match_start */ + if (match_length > lookahead) match_length = lookahead; + } + if (match_length >= MIN_MATCH) { + check_match(strstart, match_start, match_length); + + flush = ct_tally(strstart-match_start, match_length - MIN_MATCH); + + lookahead -= match_length; + + /* Insert new strings in the hash table only if the match length + * is not too large. This saves time but degrades compression. + */ + if (match_length <= max_insert_length) { + match_length--; /* string at strstart already in hash table */ + do { + strstart++; + INSERT_STRING(strstart, hash_head); + /* strstart never exceeds WSIZE-MAX_MATCH, so there are + * always MIN_MATCH bytes ahead. If lookahead < MIN_MATCH + * these bytes are garbage, but it does not matter since + * the next lookahead bytes will be emitted as literals. + */ + } while (--match_length != 0); + strstart++; + } else { + strstart += match_length; + match_length = 0; + ins_h = window[strstart]; + UPDATE_HASH(ins_h, window[strstart+1]); +#if MIN_MATCH != 3 + Call UPDATE_HASH() MIN_MATCH-3 more times +#endif + } + } else { + /* No match, output a literal byte */ + Tracevv((stderr,"%c",window[strstart])); + flush = ct_tally (0, window[strstart]); + lookahead--; + strstart++; + } + if (flush) FLUSH_BLOCK(0), block_start = strstart; + + /* Make sure that we always have enough lookahead, except + * at the end of the input file. We need MAX_MATCH bytes + * for the next match, plus MIN_MATCH bytes to insert the + * string following the next match. + */ + while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window(); + + } + return FLUSH_BLOCK(1); /* eof */ +} + +/* =========================================================================== + * Same as above, but achieves better compression. We use a lazy + * evaluation for matches: a match is finally adopted only if there is + * no better match at the next window position. + */ +ulg deflate() +{ + IPos hash_head; /* head of hash chain */ + IPos prev_match; /* previous match */ + int flush; /* set if current block must be flushed */ + int match_available = 0; /* set if previous match exists */ + register unsigned match_length = MIN_MATCH-1; /* length of best match */ +#ifdef DEBUG + extern long isize; /* byte length of input file, for debug only */ +#endif + + if (compr_level <= 3) return deflate_fast(); /* optimized for speed */ + + /* Process the input block. */ + while (lookahead != 0) { + /* Insert the string window[strstart .. strstart+2] in the + * dictionary, and set hash_head to the head of the hash chain: + */ + INSERT_STRING(strstart, hash_head); + + /* Find the longest match, discarding those <= prev_length. + */ + prev_length = match_length, prev_match = match_start; + match_length = MIN_MATCH-1; + + if (hash_head != NIL && prev_length < max_lazy_match && + strstart - hash_head <= MAX_DIST) { + /* To simplify the code, we prevent matches with the string + * of window index 0 (in particular we have to avoid a match + * of the string with itself at the start of the input file). + */ + match_length = longest_match (hash_head); + /* longest_match() sets match_start */ + if (match_length > lookahead) match_length = lookahead; + + /* Ignore a length 3 match if it is too distant: */ + if (match_length == MIN_MATCH && strstart-match_start > TOO_FAR){ + /* If prev_match is also MIN_MATCH, match_start is garbage + * but we will ignore the current match anyway. + */ + match_length--; + } + } + /* If there was a match at the previous step and the current + * match is not better, output the previous match: + */ + if (prev_length >= MIN_MATCH && match_length <= prev_length) { + + check_match(strstart-1, prev_match, prev_length); + + flush = ct_tally(strstart-1-prev_match, prev_length - MIN_MATCH); + + /* Insert in hash table all strings up to the end of the match. + * strstart-1 and strstart are already inserted. + */ + lookahead -= prev_length-1; + prev_length -= 2; + do { + strstart++; + INSERT_STRING(strstart, hash_head); + /* strstart never exceeds WSIZE-MAX_MATCH, so there are + * always MIN_MATCH bytes ahead. If lookahead < MIN_MATCH + * these bytes are garbage, but it does not matter since the + * next lookahead bytes will always be emitted as literals. + */ + } while (--prev_length != 0); + match_available = 0; + match_length = MIN_MATCH-1; + strstart++; + if (flush) FLUSH_BLOCK(0), block_start = strstart; + + } else if (match_available) { + /* If there was no match at the previous position, output a + * single literal. If there was a match but the current match + * is longer, truncate the previous match to a single literal. + */ + Tracevv((stderr,"%c",window[strstart-1])); + if (ct_tally (0, window[strstart-1])) { + FLUSH_BLOCK(0), block_start = strstart; + } + strstart++; + lookahead--; + } else { + /* There is no previous match to compare with, wait for + * the next step to decide. + */ + match_available = 1; + strstart++; + lookahead--; + } + Assert (strstart <= isize && lookahead <= isize, "a bit too far"); + + /* Make sure that we always have enough lookahead, except + * at the end of the input file. We need MAX_MATCH bytes + * for the next match, plus MIN_MATCH bytes to insert the + * string following the next match. + */ + while (lookahead < MIN_LOOKAHEAD && !eofile) fill_window(); + } + if (match_available) ct_tally (0, window[strstart-1]); + + return FLUSH_BLOCK(1); /* eof */ +} diff --git a/lzw.c b/lzw.c new file mode 100644 index 0000000..eb67d46 --- /dev/null +++ b/lzw.c @@ -0,0 +1,26 @@ +/* lzw.c -- compress files in LZW format. + * This is a dummy version avoiding patent problems. + */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +#include "tailor.h" +#include "gzip.h" +#include "lzw.h" + +static int msg_done = 0; + +/* Compress in to out with lzw method. */ +int lzw(in, out) + int in, out; +{ + if (msg_done) return ERROR; + msg_done = 1; + fprintf(stderr,"output in compress .Z format not supported\n"); + if (in != out) { /* avoid warnings on unused variables */ + exit_code = ERROR; + } + return ERROR; +} diff --git a/unlzh.c b/unlzh.c new file mode 100644 index 0000000..f639911 --- /dev/null +++ b/unlzh.c @@ -0,0 +1,401 @@ +/* unlzh.c -- decompress files in SCO compress -H (LZH) format. + * The code in this file is directly derived from the public domain 'ar002' + * written by Haruhiko Okumura. + */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +#include + +#include "tailor.h" +#include "gzip.h" +#include "lzw.h" /* just for consistency checking */ + +/* decode.c */ + +local unsigned decode OF((unsigned count, uch buffer[])); +local void decode_start OF((void)); + +/* huf.c */ +local void huf_decode_start OF((void)); +local unsigned decode_c OF((void)); +local unsigned decode_p OF((void)); +local void read_pt_len OF((int nn, int nbit, int i_special)); +local void read_c_len OF((void)); + +/* io.c */ +local void fillbuf OF((int n)); +local unsigned getbits OF((int n)); +local void init_getbits OF((void)); + +/* maketbl.c */ + +local void make_table OF((int nchar, uch bitlen[], + int tablebits, ush table[])); + + +#define DICBIT 13 /* 12(-lh4-) or 13(-lh5-) */ +#define DICSIZ ((unsigned) 1 << DICBIT) + +#ifndef CHAR_BIT +# define CHAR_BIT 8 +#endif + +#ifndef UCHAR_MAX +# define UCHAR_MAX 255 +#endif + +#define BITBUFSIZ (CHAR_BIT * 2 * sizeof(char)) +/* Do not use CHAR_BIT * sizeof(bitbuf), does not work on machines + * for which short is not on 16 bits (Cray). + */ + +/* encode.c and decode.c */ + +#define MAXMATCH 256 /* formerly F (not more than UCHAR_MAX + 1) */ +#define THRESHOLD 3 /* choose optimal value */ + +/* huf.c */ + +#define NC (UCHAR_MAX + MAXMATCH + 2 - THRESHOLD) + /* alphabet = {0, 1, 2, ..., NC - 1} */ +#define CBIT 9 /* $\lfloor \log_2 NC \rfloor + 1$ */ +#define CODE_BIT 16 /* codeword length */ + +#define NP (DICBIT + 1) +#define NT (CODE_BIT + 3) +#define PBIT 4 /* smallest integer such that (1U << PBIT) > NP */ +#define TBIT 5 /* smallest integer such that (1U << TBIT) > NT */ +#if NT > NP +# define NPT NT +#else +# define NPT NP +#endif + +/* local ush left[2 * NC - 1]; */ +/* local ush right[2 * NC - 1]; */ +#define left prev +#define right head +#if NC > (1<<(BITS-2)) + error cannot overlay left+right and prev +#endif + +/* local uch c_len[NC]; */ +#define c_len outbuf +#if NC > OUTBUFSIZ + error cannot overlay c_len and outbuf +#endif + +local uch pt_len[NPT]; +local unsigned blocksize; +local ush pt_table[256]; + +/* local ush c_table[4096]; */ +#define c_table d_buf +#if (DIST_BUFSIZE-1) < 4095 + error cannot overlay c_table and d_buf +#endif + +/*********************************************************** + io.c -- input/output +***********************************************************/ + +local ush bitbuf; +local unsigned subbitbuf; +local int bitcount; + +local void fillbuf(n) /* Shift bitbuf n bits left, read n bits */ + int n; +{ + bitbuf <<= n; + while (n > bitcount) { + bitbuf |= subbitbuf << (n -= bitcount); + subbitbuf = (unsigned)try_byte(); + if ((int)subbitbuf == EOF) subbitbuf = 0; + bitcount = CHAR_BIT; + } + bitbuf |= subbitbuf >> (bitcount -= n); +} + +local unsigned getbits(n) + int n; +{ + unsigned x; + + x = bitbuf >> (BITBUFSIZ - n); fillbuf(n); + return x; +} + +local void init_getbits() +{ + bitbuf = 0; subbitbuf = 0; bitcount = 0; + fillbuf(BITBUFSIZ); +} + +/*********************************************************** + maketbl.c -- make table for decoding +***********************************************************/ + +local void make_table(nchar, bitlen, tablebits, table) + int nchar; + uch bitlen[]; + int tablebits; + ush table[]; +{ + ush count[17], weight[17], start[18], *p; + unsigned i, k, len, ch, jutbits, avail, nextcode, mask; + + for (i = 1; i <= 16; i++) count[i] = 0; + for (i = 0; i < (unsigned)nchar; i++) count[bitlen[i]]++; + + start[1] = 0; + for (i = 1; i <= 16; i++) + start[i + 1] = start[i] + (count[i] << (16 - i)); + if ((start[17] & 0xffff) != 0) + error("Bad table\n"); + + jutbits = 16 - tablebits; + for (i = 1; i <= (unsigned)tablebits; i++) { + start[i] >>= jutbits; + weight[i] = (unsigned) 1 << (tablebits - i); + } + while (i <= 16) { + weight[i] = (unsigned) 1 << (16 - i); + i++; + } + + i = start[tablebits + 1] >> jutbits; + if (i != 0) { + k = 1 << tablebits; + while (i != k) table[i++] = 0; + } + + avail = nchar; + mask = (unsigned) 1 << (15 - tablebits); + for (ch = 0; ch < (unsigned)nchar; ch++) { + if ((len = bitlen[ch]) == 0) continue; + nextcode = start[len] + weight[len]; + if (len <= (unsigned)tablebits) { + for (i = start[len]; i < nextcode; i++) table[i] = ch; + } else { + k = start[len]; + p = &table[k >> jutbits]; + i = len - tablebits; + while (i != 0) { + if (*p == 0) { + right[avail] = left[avail] = 0; + *p = avail++; + } + if (k & mask) p = &right[*p]; + else p = &left[*p]; + k <<= 1; i--; + } + *p = ch; + } + start[len] = nextcode; + } +} + +/*********************************************************** + huf.c -- static Huffman +***********************************************************/ + +local void read_pt_len(nn, nbit, i_special) + int nn; + int nbit; + int i_special; +{ + int i, c, n; + unsigned mask; + + n = getbits(nbit); + if (n == 0) { + c = getbits(nbit); + for (i = 0; i < nn; i++) pt_len[i] = 0; + for (i = 0; i < 256; i++) pt_table[i] = c; + } else { + i = 0; + while (i < n) { + c = bitbuf >> (BITBUFSIZ - 3); + if (c == 7) { + mask = (unsigned) 1 << (BITBUFSIZ - 1 - 3); + while (mask & bitbuf) { mask >>= 1; c++; } + } + fillbuf((c < 7) ? 3 : c - 3); + pt_len[i++] = c; + if (i == i_special) { + c = getbits(2); + while (--c >= 0) pt_len[i++] = 0; + } + } + while (i < nn) pt_len[i++] = 0; + make_table(nn, pt_len, 8, pt_table); + } +} + +local void read_c_len() +{ + int i, c, n; + unsigned mask; + + n = getbits(CBIT); + if (n == 0) { + c = getbits(CBIT); + for (i = 0; i < NC; i++) c_len[i] = 0; + for (i = 0; i < 4096; i++) c_table[i] = c; + } else { + i = 0; + while (i < n) { + c = pt_table[bitbuf >> (BITBUFSIZ - 8)]; + if (c >= NT) { + mask = (unsigned) 1 << (BITBUFSIZ - 1 - 8); + do { + if (bitbuf & mask) c = right[c]; + else c = left [c]; + mask >>= 1; + } while (c >= NT); + } + fillbuf((int) pt_len[c]); + if (c <= 2) { + if (c == 0) c = 1; + else if (c == 1) c = getbits(4) + 3; + else c = getbits(CBIT) + 20; + while (--c >= 0) c_len[i++] = 0; + } else c_len[i++] = c - 2; + } + while (i < NC) c_len[i++] = 0; + make_table(NC, c_len, 12, c_table); + } +} + +local unsigned decode_c() +{ + unsigned j, mask; + + if (blocksize == 0) { + blocksize = getbits(16); + if (blocksize == 0) { + return NC; /* end of file */ + } + read_pt_len(NT, TBIT, 3); + read_c_len(); + read_pt_len(NP, PBIT, -1); + } + blocksize--; + j = c_table[bitbuf >> (BITBUFSIZ - 12)]; + if (j >= NC) { + mask = (unsigned) 1 << (BITBUFSIZ - 1 - 12); + do { + if (bitbuf & mask) j = right[j]; + else j = left [j]; + mask >>= 1; + } while (j >= NC); + } + fillbuf((int) c_len[j]); + return j; +} + +local unsigned decode_p() +{ + unsigned j, mask; + + j = pt_table[bitbuf >> (BITBUFSIZ - 8)]; + if (j >= NP) { + mask = (unsigned) 1 << (BITBUFSIZ - 1 - 8); + do { + if (bitbuf & mask) j = right[j]; + else j = left [j]; + mask >>= 1; + } while (j >= NP); + } + fillbuf((int) pt_len[j]); + if (j != 0) j = ((unsigned) 1 << (j - 1)) + getbits((int) (j - 1)); + return j; +} + +local void huf_decode_start() +{ + init_getbits(); blocksize = 0; +} + +/*********************************************************** + decode.c +***********************************************************/ + +local int j; /* remaining bytes to copy */ +local int done; /* set at end of input */ + +local void decode_start() +{ + huf_decode_start(); + j = 0; + done = 0; +} + +/* Decode the input and return the number of decoded bytes put in buffer + */ +local unsigned decode(count, buffer) + unsigned count; + uch buffer[]; + /* The calling function must keep the number of + bytes to be processed. This function decodes + either 'count' bytes or 'DICSIZ' bytes, whichever + is smaller, into the array 'buffer[]' of size + 'DICSIZ' or more. + Call decode_start() once for each new file + before calling this function. + */ +{ + local unsigned i; + unsigned r, c; + + r = 0; + while (--j >= 0) { + buffer[r] = buffer[i]; + i = (i + 1) & (DICSIZ - 1); + if (++r == count) return r; + } + for ( ; ; ) { + c = decode_c(); + if (c == NC) { + done = 1; + return r; + } + if (c <= UCHAR_MAX) { + buffer[r] = c; + if (++r == count) return r; + } else { + j = c - (UCHAR_MAX + 1 - THRESHOLD); + i = (r - decode_p() - 1) & (DICSIZ - 1); + while (--j >= 0) { + buffer[r] = buffer[i]; + i = (i + 1) & (DICSIZ - 1); + if (++r == count) return r; + } + } + } +} + + +/* =========================================================================== + * Unlzh in to out. Return OK or ERROR. + */ +int unlzh(in, out) + int in; + int out; +{ + unsigned n; + ifd = in; + ofd = out; + + decode_start(); + while (!done) { + n = decode((unsigned) DICSIZ, window); + if (!test && n > 0) { + write_buf(out, (char*)window, n); + } + } + return OK; +} diff --git a/unpack.c b/unpack.c new file mode 100644 index 0000000..a9bc18e --- /dev/null +++ b/unpack.c @@ -0,0 +1,239 @@ +/* unpack.c -- decompress files in pack format. + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +#include "tailor.h" +#include "gzip.h" +#include "crypt.h" + +#define MIN(a,b) ((a) <= (b) ? (a) : (b)) +/* The arguments must not have side effects. */ + +#define MAX_BITLEN 25 +/* Maximum length of Huffman codes. (Minor modifications to the code + * would be needed to support 32 bits codes, but pack never generates + * more than 24 bits anyway.) + */ + +#define LITERALS 256 +/* Number of literals, excluding the End of Block (EOB) code */ + +#define MAX_PEEK 12 +/* Maximum number of 'peek' bits used to optimize traversal of the + * Huffman tree. + */ + +local ulg orig_len; /* original uncompressed length */ +local int max_len; /* maximum bit length of Huffman codes */ + +local uch literal[LITERALS]; +/* The literal bytes present in the Huffman tree. The EOB code is not + * represented. + */ + +local int lit_base[MAX_BITLEN+1]; +/* All literals of a given bit length are contiguous in literal[] and + * have contiguous codes. literal[code+lit_base[len]] is the literal + * for a code of len bits. + */ + +local int leaves [MAX_BITLEN+1]; /* Number of leaves for each bit length */ +local int parents[MAX_BITLEN+1]; /* Number of parents for each bit length */ + +local int peek_bits; /* Number of peek bits currently used */ + +/* local uch prefix_len[1 << MAX_PEEK]; */ +#define prefix_len outbuf +/* For each bit pattern b of peek_bits bits, prefix_len[b] is the length + * of the Huffman code starting with a prefix of b (upper bits), or 0 + * if all codes of prefix b have more than peek_bits bits. It is not + * necessary to have a huge table (large MAX_PEEK) because most of the + * codes encountered in the input stream are short codes (by construction). + * So for most codes a single lookup will be necessary. + */ +#if (1< OUTBUFSIZ + error cannot overlay prefix_len and outbuf +#endif + +local ulg bitbuf; +/* Bits are added on the low part of bitbuf and read from the high part. */ + +local int valid; /* number of valid bits in bitbuf */ +/* all bits above the last valid bit are always zero */ + +/* Set code to the next 'bits' input bits without skipping them. code + * must be the name of a simple variable and bits must not have side effects. + * IN assertions: bits <= 25 (so that we still have room for an extra byte + * when valid is only 24), and mask = (1<> (valid-(bits))) & (mask); \ +} + +/* Skip the given number of bits (after having peeked at them): */ +#define skip_bits(bits) (valid -= (bits)) + +#define clear_bitbuf() (valid = 0, bitbuf = 0) + +/* Local functions */ + +local void read_tree OF((void)); +local void build_tree OF((void)); + +/* =========================================================================== + * Read the Huffman tree. + */ +local void read_tree() +{ + int len; /* bit length */ + int base; /* base offset for a sequence of leaves */ + int n; + + /* Read the original input size, MSB first */ + orig_len = 0; + for (n = 1; n <= 4; n++) orig_len = (orig_len << 8) | (ulg)get_byte(); + + max_len = (int)get_byte(); /* maximum bit length of Huffman codes */ + if (max_len > MAX_BITLEN) { + error("invalid compressed data -- Huffman code > 32 bits"); + } + + /* Get the number of leaves at each bit length */ + n = 0; + for (len = 1; len <= max_len; len++) { + leaves[len] = (int)get_byte(); + n += leaves[len]; + } + if (n > LITERALS) { + error("too many leaves in Huffman tree"); + } + Trace((stderr, "orig_len %ld, max_len %d, leaves %d\n", + orig_len, max_len, n)); + /* There are at least 2 and at most 256 leaves of length max_len. + * (Pack arbitrarily rejects empty files and files consisting of + * a single byte even repeated.) To fit the last leaf count in a + * byte, it is offset by 2. However, the last literal is the EOB + * code, and is not transmitted explicitly in the tree, so we must + * adjust here by one only. + */ + leaves[max_len]++; + + /* Now read the leaves themselves */ + base = 0; + for (len = 1; len <= max_len; len++) { + /* Remember where the literals of this length start in literal[] : */ + lit_base[len] = base; + /* And read the literals: */ + for (n = leaves[len]; n > 0; n--) { + literal[base++] = (uch)get_byte(); + } + } + leaves[max_len]++; /* Now include the EOB code in the Huffman tree */ +} + +/* =========================================================================== + * Build the Huffman tree and the prefix table. + */ +local void build_tree() +{ + int nodes = 0; /* number of nodes (parents+leaves) at current bit length */ + int len; /* current bit length */ + uch *prefixp; /* pointer in prefix_len */ + + for (len = max_len; len >= 1; len--) { + /* The number of parent nodes at this level is half the total + * number of nodes at parent level: + */ + nodes >>= 1; + parents[len] = nodes; + /* Update lit_base by the appropriate bias to skip the parent nodes + * (which are not represented in the literal array): + */ + lit_base[len] -= nodes; + /* Restore nodes to be parents+leaves: */ + nodes += leaves[len]; + } + /* Construct the prefix table, from shortest leaves to longest ones. + * The shortest code is all ones, so we start at the end of the table. + */ + peek_bits = MIN(max_len, MAX_PEEK); + prefixp = &prefix_len[1< prefix_len) *--prefixp = 0; +} + +/* =========================================================================== + * Unpack in to out. This routine does not support the old pack format + * with magic header \037\037. + * + * IN assertions: the buffer inbuf contains already the beginning of + * the compressed data, from offsets inptr to insize-1 included. + * The magic header has already been checked. The output buffer is cleared. + */ +int unpack(in, out) + int in, out; /* input and output file descriptors */ +{ + int len; /* Bit length of current code */ + unsigned eob; /* End Of Block code */ + register unsigned peek; /* lookahead bits */ + unsigned peek_mask; /* Mask for peek_bits bits */ + + ifd = in; + ofd = out; + + read_tree(); /* Read the Huffman tree */ + build_tree(); /* Build the prefix table */ + clear_bitbuf(); /* Initialize bit input */ + peek_mask = (1< 0) { + peek >>= peek_bits - len; /* discard the extra bits */ + } else { + /* Code of more than peek_bits bits, we must traverse the tree */ + ulg mask = peek_mask; + len = peek_bits; + do { + len++, mask = (mask<<1)+1; + look_bits(peek, len, mask); + } while (peek < (unsigned)parents[len]); + /* loop as long as peek is a parent node */ + } + /* At this point, peek is the next complete code, of len bits */ + if (peek == eob && len == max_len) break; /* end of file? */ + put_ubyte(literal[peek+lit_base[len]]); + Tracev((stderr,"%02d %04x %c\n", len, peek, + literal[peek+lit_base[len]])); + skip_bits(len); + } /* for (;;) */ + + flush_window(); + Trace((stderr, "bytes_out %ld\n", bytes_out)); + if (orig_len != (ulg)bytes_out) { + error("invalid compressed data--length error"); + } + return OK; +} diff --git a/unzip.c b/unzip.c new file mode 100644 index 0000000..cd3d50e --- /dev/null +++ b/unzip.c @@ -0,0 +1,199 @@ +/* unzip.c -- decompress files in gzip or pkzip format. + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + * + * The code in this file is derived from the file funzip.c written + * and put in the public domain by Mark Adler. + */ + +/* + This version can extract files in gzip or pkzip format. + For the latter, only the first entry is extracted, and it has to be + either deflated or stored. + */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +#include "tailor.h" +#include "gzip.h" +#include "crypt.h" + +/* PKZIP header definitions */ +#define LOCSIG 0x04034b50L /* four-byte lead-in (lsb first) */ +#define LOCFLG 6 /* offset of bit flag */ +#define CRPFLG 1 /* bit for encrypted entry */ +#define EXTFLG 8 /* bit for extended local header */ +#define LOCHOW 8 /* offset of compression method */ +#define LOCTIM 10 /* file mod time (for decryption) */ +#define LOCCRC 14 /* offset of crc */ +#define LOCSIZ 18 /* offset of compressed size */ +#define LOCLEN 22 /* offset of uncompressed length */ +#define LOCFIL 26 /* offset of file name field length */ +#define LOCEXT 28 /* offset of extra field length */ +#define LOCHDR 30 /* size of local header, including sig */ +#define EXTHDR 16 /* size of extended local header, inc sig */ + + +/* Globals */ + +int decrypt; /* flag to turn on decryption */ +char *key; /* not used--needed to link crypt.c */ +int pkzip = 0; /* set for a pkzip file */ +int ext_header = 0; /* set if extended local header */ + +/* =========================================================================== + * Check zip file and advance inptr to the start of the compressed data. + * Get ofname from the local header if necessary. + */ +int check_zipfile(in) + int in; /* input file descriptors */ +{ + uch *h = inbuf + inptr; /* first local header */ + + ifd = in; + + /* Check validity of local header, and skip name and extra fields */ + inptr += LOCHDR + SH(h + LOCFIL) + SH(h + LOCEXT); + + if (inptr > insize || LG(h) != LOCSIG) { + fprintf(stderr, "\n%s: %s: not a valid zip file\n", + progname, ifname); + exit_code = ERROR; + return ERROR; + } + method = h[LOCHOW]; + if (method != STORED && method != DEFLATED) { + fprintf(stderr, + "\n%s: %s: first entry not deflated or stored -- use unzip\n", + progname, ifname); + exit_code = ERROR; + return ERROR; + } + + /* If entry encrypted, decrypt and validate encryption header */ + if ((decrypt = h[LOCFLG] & CRPFLG) != 0) { + fprintf(stderr, "\n%s: %s: encrypted file -- use unzip\n", + progname, ifname); + exit_code = ERROR; + return ERROR; + } + + /* Save flags for unzip() */ + ext_header = (h[LOCFLG] & EXTFLG) != 0; + pkzip = 1; + + /* Get ofname and time stamp from local header (to be done) */ + return OK; +} + +/* =========================================================================== + * Unzip in to out. This routine works on both gzip and pkzip files. + * + * IN assertions: the buffer inbuf contains already the beginning of + * the compressed data, from offsets inptr to insize-1 included. + * The magic header has already been checked. The output buffer is cleared. + */ +int unzip(in, out) + int in, out; /* input and output file descriptors */ +{ + ulg orig_crc = 0; /* original crc */ + ulg orig_len = 0; /* original uncompressed length */ + int n; + uch buf[EXTHDR]; /* extended local header */ + + ifd = in; + ofd = out; + + updcrc(NULL, 0); /* initialize crc */ + + if (pkzip && !ext_header) { /* crc and length at the end otherwise */ + orig_crc = LG(inbuf + LOCCRC); + orig_len = LG(inbuf + LOCLEN); + } + + /* Decompress */ + if (method == DEFLATED) { + + int res = inflate(); + + if (res == 3) { + error("out of memory"); + } else if (res != 0) { + error("invalid compressed data--format violated"); + } + + } else if (pkzip && method == STORED) { + + register ulg n = LG(inbuf + LOCLEN); + + if (n != LG(inbuf + LOCSIZ) - (decrypt ? RAND_HEAD_LEN : 0)) { + + fprintf(stderr, "len %ld, siz %ld\n", n, LG(inbuf + LOCSIZ)); + error("invalid compressed data--length mismatch"); + } + while (n--) { + uch c = (uch)get_byte(); +#ifdef CRYPT + if (decrypt) zdecode(c); +#endif + put_ubyte(c); + } + flush_window(); + } else { + error("internal error, invalid method"); + } + + /* Get the crc and original length */ + if (!pkzip) { + /* crc32 (see algorithm.doc) + * uncompressed input size modulo 2^32 + */ + for (n = 0; n < 8; n++) { + buf[n] = (uch)get_byte(); /* may cause an error if EOF */ + } + orig_crc = LG(buf); + orig_len = LG(buf+4); + + } else if (ext_header) { /* If extended header, check it */ + /* signature - 4bytes: 0x50 0x4b 0x07 0x08 + * CRC-32 value + * compressed size 4-bytes + * uncompressed size 4-bytes + */ + for (n = 0; n < EXTHDR; n++) { + buf[n] = (uch)get_byte(); /* may cause an error if EOF */ + } + orig_crc = LG(buf+4); + orig_len = LG(buf+12); + } + + /* Validate decompression */ + if (orig_crc != updcrc(outbuf, 0)) { + error("invalid compressed data--crc error"); + } + if (orig_len != (ulg)bytes_out) { + error("invalid compressed data--length error"); + } + + /* Check if there are more entries in a pkzip file */ + if (pkzip && inptr + 4 < insize && LG(inbuf+inptr) == LOCSIG) { + if (to_stdout) { + WARN((stderr, + "%s: %s has more than one entry--rest ignored\n", + progname, ifname)); + } else { + /* Don't destroy the input zip file */ + fprintf(stderr, + "%s: %s has more than one entry -- unchanged\n", + progname, ifname); + exit_code = ERROR; + ext_header = pkzip = 0; + return ERROR; + } + } + ext_header = pkzip = 0; /* for next file */ + return OK; +} diff --git a/util.c b/util.c new file mode 100644 index 0000000..123f845 --- /dev/null +++ b/util.c @@ -0,0 +1,462 @@ +/* util.c -- utility functions for gzip support + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +#include +#include +#include + +#include "tailor.h" + +#ifdef HAVE_UNISTD_H +# include +#endif +#ifndef NO_FCNTL_H +# include +#endif + +#if defined(STDC_HEADERS) || !defined(NO_STDLIB_H) +# include +#else + extern int errno; +#endif + +#include "gzip.h" +#include "crypt.h" + +extern ulg crc_32_tab[]; /* crc table, defined below */ + +/* =========================================================================== + * Copy input to output unchanged: zcat == cat with --force. + * IN assertion: insize bytes have already been read in inbuf. + */ +int copy(in, out) + int in, out; /* input and output file descriptors */ +{ + errno = 0; + while (insize != 0 && (int)insize != EOF) { + write_buf(out, (char*)inbuf, insize); + bytes_out += insize; + insize = read(in, (char*)inbuf, INBUFSIZ); + } + if ((int)insize == EOF && errno != 0) { + read_error(); + } + bytes_in = bytes_out; + return OK; +} + +/* =========================================================================== + * Run a set of bytes through the crc shift register. If s is a NULL + * pointer, then initialize the crc shift register contents instead. + * Return the current crc in either case. + */ +ulg updcrc(s, n) + uch *s; /* pointer to bytes to pump through */ + unsigned n; /* number of bytes in s[] */ +{ + register ulg c; /* temporary variable */ + + static ulg crc = (ulg)0xffffffffL; /* shift register contents */ + + if (s == NULL) { + c = 0xffffffffL; + } else { + c = crc; + if (n) do { + c = crc_32_tab[((int)c ^ (*s++)) & 0xff] ^ (c >> 8); + } while (--n); + } + crc = c; + return c ^ 0xffffffffL; /* (instead of ~c for 64-bit machines) */ +} + +/* =========================================================================== + * Clear input and output buffers + */ +void clear_bufs() +{ + outcnt = 0; + insize = inptr = 0; + bytes_in = bytes_out = 0L; +} + +/* =========================================================================== + * Fill the input buffer. This is called only when the buffer is empty. + */ +int fill_inbuf(eof_ok) + int eof_ok; /* set if EOF acceptable as a result */ +{ + int len; + + /* Read as much as possible */ + insize = 0; + errno = 0; + do { + len = read(ifd, (char*)inbuf+insize, INBUFSIZ-insize); + if (len == 0 || len == EOF) break; + insize += len; + } while (insize < INBUFSIZ); + + if (insize == 0) { + if (eof_ok) return EOF; + read_error(); + } + bytes_in += (ulg)insize; + inptr = 1; + return inbuf[0]; +} + +/* =========================================================================== + * Write the output buffer outbuf[0..outcnt-1] and update bytes_out. + * (used for the compressed data only) + */ +void flush_outbuf() +{ + if (outcnt == 0) return; + + write_buf(ofd, (char *)outbuf, outcnt); + bytes_out += (ulg)outcnt; + outcnt = 0; +} + +/* =========================================================================== + * Write the output window window[0..outcnt-1] and update crc and bytes_out. + * (Used for the decompressed data only.) + */ +void flush_window() +{ + if (outcnt == 0) return; + updcrc(window, outcnt); + + if (!test) { + write_buf(ofd, (char *)window, outcnt); + } + bytes_out += (ulg)outcnt; + outcnt = 0; +} + +/* =========================================================================== + * Does the same as write(), but also handles partial pipe writes and checks + * for error return. + */ +void write_buf(fd, buf, cnt) + int fd; + voidp buf; + unsigned cnt; +{ + unsigned n; + + while ((n = write(fd, buf, cnt)) != cnt) { + if (n == (unsigned)(-1)) { + write_error(); + } + cnt -= n; + buf = (voidp)((char*)buf+n); + } +} + +/* ======================================================================== + * Put string s in lower case, return s. + */ +char *strlwr(s) + char *s; +{ + char *t; + for (t = s; *t; t++) *t = tolow(*t); + return s; +} + +/* ======================================================================== + * Return the base name of a file (remove any directory prefix and + * any version suffix). For systems with file names that are not + * case sensitive, force the base name to lower case. + */ +char *basename(fname) + char *fname; +{ + char *p; + + if ((p = strrchr(fname, PATH_SEP)) != NULL) fname = p+1; +#ifdef PATH_SEP2 + if ((p = strrchr(fname, PATH_SEP2)) != NULL) fname = p+1; +#endif +#ifdef PATH_SEP3 + if ((p = strrchr(fname, PATH_SEP3)) != NULL) fname = p+1; +#endif +#ifdef SUFFIX_SEP + if ((p = strrchr(fname, SUFFIX_SEP)) != NULL) *p = '\0'; +#endif + if (casemap('A') == 'a') strlwr(fname); + return fname; +} + +/* ======================================================================== + * Make a file name legal for file systems not allowing file names with + * multiple dots or starting with a dot (such as MSDOS), by changing + * all dots except the last one into underlines. A target dependent + * function can be used instead of this simple function by defining the macro + * MAKE_LEGAL_NAME in tailor.h and providing the function in a target + * dependent module. + */ +void make_simple_name(name) + char *name; +{ + char *p = strrchr(name, '.'); + if (p == NULL) return; + if (p == name) p++; + do { + if (*--p == '.') *p = '_'; + } while (p != name); +} + + +#if defined(NO_STRING_H) && !defined(STDC_HEADERS) + +/* Provide missing strspn and strcspn functions. */ + +# ifndef __STDC__ +# define const +# endif + +int strspn OF((const char *s, const char *accept)); +int strcspn OF((const char *s, const char *reject)); + +/* ======================================================================== + * Return the length of the maximum initial segment + * of s which contains only characters in accept. + */ +int strspn(s, accept) + const char *s; + const char *accept; +{ + register const char *p; + register const char *a; + register int count = 0; + + for (p = s; *p != '\0'; ++p) { + for (a = accept; *a != '\0'; ++a) { + if (*p == *a) break; + } + if (*a == '\0') return count; + ++count; + } + return count; +} + +/* ======================================================================== + * Return the length of the maximum inital segment of s + * which contains no characters from reject. + */ +int strcspn(s, reject) + const char *s; + const char *reject; +{ + register int count = 0; + + while (*s != '\0') { + if (strchr(reject, *s++) != NULL) return count; + ++count; + } + return count; +} + +#endif /* NO_STRING_H */ + +/* ======================================================================== + * Add an environment variable (if any) before argv, and update argc. + * Return the expanded environment variable to be freed later, or NULL + * if no options were added to argv. + */ +#define SEPARATOR " \t" /* separators in env variable */ + +char *add_envopt(argcp, argvp, env) + int *argcp; /* pointer to argc */ + char ***argvp; /* pointer to argv */ + char *env; /* name of environment variable */ +{ + char *p; /* running pointer through env variable */ + char **oargv; /* runs through old argv array */ + char **nargv; /* runs through new argv array */ + int oargc = *argcp; /* old argc */ + int nargc = 0; /* number of arguments in env variable */ + + env = (char*)getenv(env); + if (env == NULL) return NULL; + + p = (char*)xmalloc(strlen(env)+1); + env = strcpy(p, env); /* keep env variable intact */ + + for (p = env; *p; nargc++ ) { /* move through env */ + p += strspn(p, SEPARATOR); /* skip leading separators */ + if (*p == '\0') break; + + p += strcspn(p, SEPARATOR); /* find end of word */ + if (*p) *p++ = '\0'; /* mark it */ + } + if (nargc == 0) { + free(env); + return NULL; + } + *argcp += nargc; + /* Allocate the new argv array, with an extra element just in case + * the original arg list did not end with a NULL. + */ + nargv = (char**)calloc(*argcp+1, sizeof(char *)); + if (nargv == NULL) error("out of memory"); + oargv = *argvp; + *argvp = nargv; + + /* Copy the program name first */ + if (oargc-- < 0) error("argc<=0"); + *(nargv++) = *(oargv++); + + /* Then copy the environment args */ + for (p = env; nargc > 0; nargc--) { + p += strspn(p, SEPARATOR); /* skip separators */ + *(nargv++) = p; /* store start */ + while (*p++) ; /* skip over word */ + } + + /* Finally copy the old args and add a NULL (usual convention) */ + while (oargc--) *(nargv++) = *(oargv++); + *nargv = NULL; + return env; +} + +/* ======================================================================== + * Error handlers. + */ +void error(m) + char *m; +{ + fprintf(stderr, "\n%s: %s: %s\n", progname, ifname, m); + abort_gzip(); +} + +void warn(a, b) + char *a, *b; /* message strings juxtaposed in output */ +{ + WARN((stderr, "%s: %s: warning: %s%s\n", progname, ifname, a, b)); +} + +void read_error() +{ + fprintf(stderr, "\n%s: ", progname); + if (errno != 0) { + perror(ifname); + } else { + fprintf(stderr, "%s: unexpected end of file\n", ifname); + } + abort_gzip(); +} + +void write_error() +{ + fprintf(stderr, "\n%s: ", progname); + perror(ofname); + abort_gzip(); +} + +/* ======================================================================== + * Display compression ratio on the given stream on 6 characters. + */ +void display_ratio(num, den, file) + long num; + long den; + FILE *file; +{ + long ratio; /* 1000 times the compression ratio */ + + if (den == 0) { + ratio = 0; /* no compression */ + } else if (den < 2147483L) { /* (2**31 -1)/1000 */ + ratio = 1000L*num/den; + } else { + ratio = num/(den/1000L); + } + if (ratio < 0) { + putc('-', file); + ratio = -ratio; + } else { + putc(' ', file); + } + fprintf(file, "%2ld.%1ld%%", ratio / 10L, ratio % 10L); +} + + +/* ======================================================================== + * Semi-safe malloc -- never returns NULL. + */ +voidp xmalloc (size) + unsigned size; +{ + voidp cp = (voidp)malloc (size); + + if (cp == NULL) error("out of memory"); + return cp; +} + +/* ======================================================================== + * Table of CRC-32's of all single-byte values (made by makecrc.c) + */ +ulg crc_32_tab[] = { + 0x00000000L, 0x77073096L, 0xee0e612cL, 0x990951baL, 0x076dc419L, + 0x706af48fL, 0xe963a535L, 0x9e6495a3L, 0x0edb8832L, 0x79dcb8a4L, + 0xe0d5e91eL, 0x97d2d988L, 0x09b64c2bL, 0x7eb17cbdL, 0xe7b82d07L, + 0x90bf1d91L, 0x1db71064L, 0x6ab020f2L, 0xf3b97148L, 0x84be41deL, + 0x1adad47dL, 0x6ddde4ebL, 0xf4d4b551L, 0x83d385c7L, 0x136c9856L, + 0x646ba8c0L, 0xfd62f97aL, 0x8a65c9ecL, 0x14015c4fL, 0x63066cd9L, + 0xfa0f3d63L, 0x8d080df5L, 0x3b6e20c8L, 0x4c69105eL, 0xd56041e4L, + 0xa2677172L, 0x3c03e4d1L, 0x4b04d447L, 0xd20d85fdL, 0xa50ab56bL, + 0x35b5a8faL, 0x42b2986cL, 0xdbbbc9d6L, 0xacbcf940L, 0x32d86ce3L, + 0x45df5c75L, 0xdcd60dcfL, 0xabd13d59L, 0x26d930acL, 0x51de003aL, + 0xc8d75180L, 0xbfd06116L, 0x21b4f4b5L, 0x56b3c423L, 0xcfba9599L, + 0xb8bda50fL, 0x2802b89eL, 0x5f058808L, 0xc60cd9b2L, 0xb10be924L, + 0x2f6f7c87L, 0x58684c11L, 0xc1611dabL, 0xb6662d3dL, 0x76dc4190L, + 0x01db7106L, 0x98d220bcL, 0xefd5102aL, 0x71b18589L, 0x06b6b51fL, + 0x9fbfe4a5L, 0xe8b8d433L, 0x7807c9a2L, 0x0f00f934L, 0x9609a88eL, + 0xe10e9818L, 0x7f6a0dbbL, 0x086d3d2dL, 0x91646c97L, 0xe6635c01L, + 0x6b6b51f4L, 0x1c6c6162L, 0x856530d8L, 0xf262004eL, 0x6c0695edL, + 0x1b01a57bL, 0x8208f4c1L, 0xf50fc457L, 0x65b0d9c6L, 0x12b7e950L, + 0x8bbeb8eaL, 0xfcb9887cL, 0x62dd1ddfL, 0x15da2d49L, 0x8cd37cf3L, + 0xfbd44c65L, 0x4db26158L, 0x3ab551ceL, 0xa3bc0074L, 0xd4bb30e2L, + 0x4adfa541L, 0x3dd895d7L, 0xa4d1c46dL, 0xd3d6f4fbL, 0x4369e96aL, + 0x346ed9fcL, 0xad678846L, 0xda60b8d0L, 0x44042d73L, 0x33031de5L, + 0xaa0a4c5fL, 0xdd0d7cc9L, 0x5005713cL, 0x270241aaL, 0xbe0b1010L, + 0xc90c2086L, 0x5768b525L, 0x206f85b3L, 0xb966d409L, 0xce61e49fL, + 0x5edef90eL, 0x29d9c998L, 0xb0d09822L, 0xc7d7a8b4L, 0x59b33d17L, + 0x2eb40d81L, 0xb7bd5c3bL, 0xc0ba6cadL, 0xedb88320L, 0x9abfb3b6L, + 0x03b6e20cL, 0x74b1d29aL, 0xead54739L, 0x9dd277afL, 0x04db2615L, + 0x73dc1683L, 0xe3630b12L, 0x94643b84L, 0x0d6d6a3eL, 0x7a6a5aa8L, + 0xe40ecf0bL, 0x9309ff9dL, 0x0a00ae27L, 0x7d079eb1L, 0xf00f9344L, + 0x8708a3d2L, 0x1e01f268L, 0x6906c2feL, 0xf762575dL, 0x806567cbL, + 0x196c3671L, 0x6e6b06e7L, 0xfed41b76L, 0x89d32be0L, 0x10da7a5aL, + 0x67dd4accL, 0xf9b9df6fL, 0x8ebeeff9L, 0x17b7be43L, 0x60b08ed5L, + 0xd6d6a3e8L, 0xa1d1937eL, 0x38d8c2c4L, 0x4fdff252L, 0xd1bb67f1L, + 0xa6bc5767L, 0x3fb506ddL, 0x48b2364bL, 0xd80d2bdaL, 0xaf0a1b4cL, + 0x36034af6L, 0x41047a60L, 0xdf60efc3L, 0xa867df55L, 0x316e8eefL, + 0x4669be79L, 0xcb61b38cL, 0xbc66831aL, 0x256fd2a0L, 0x5268e236L, + 0xcc0c7795L, 0xbb0b4703L, 0x220216b9L, 0x5505262fL, 0xc5ba3bbeL, + 0xb2bd0b28L, 0x2bb45a92L, 0x5cb36a04L, 0xc2d7ffa7L, 0xb5d0cf31L, + 0x2cd99e8bL, 0x5bdeae1dL, 0x9b64c2b0L, 0xec63f226L, 0x756aa39cL, + 0x026d930aL, 0x9c0906a9L, 0xeb0e363fL, 0x72076785L, 0x05005713L, + 0x95bf4a82L, 0xe2b87a14L, 0x7bb12baeL, 0x0cb61b38L, 0x92d28e9bL, + 0xe5d5be0dL, 0x7cdcefb7L, 0x0bdbdf21L, 0x86d3d2d4L, 0xf1d4e242L, + 0x68ddb3f8L, 0x1fda836eL, 0x81be16cdL, 0xf6b9265bL, 0x6fb077e1L, + 0x18b74777L, 0x88085ae6L, 0xff0f6a70L, 0x66063bcaL, 0x11010b5cL, + 0x8f659effL, 0xf862ae69L, 0x616bffd3L, 0x166ccf45L, 0xa00ae278L, + 0xd70dd2eeL, 0x4e048354L, 0x3903b3c2L, 0xa7672661L, 0xd06016f7L, + 0x4969474dL, 0x3e6e77dbL, 0xaed16a4aL, 0xd9d65adcL, 0x40df0b66L, + 0x37d83bf0L, 0xa9bcae53L, 0xdebb9ec5L, 0x47b2cf7fL, 0x30b5ffe9L, + 0xbdbdf21cL, 0xcabac28aL, 0x53b39330L, 0x24b4a3a6L, 0xbad03605L, + 0xcdd70693L, 0x54de5729L, 0x23d967bfL, 0xb3667a2eL, 0xc4614ab8L, + 0x5d681b02L, 0x2a6f2b94L, 0xb40bbe37L, 0xc30c8ea1L, 0x5a05df1bL, + 0x2d02ef8dL +}; diff --git a/zip.c b/zip.c new file mode 100644 index 0000000..145116d --- /dev/null +++ b/zip.c @@ -0,0 +1,117 @@ +/* zip.c -- compress files to the gzip or pkzip format + * Copyright (C) 1992-1993 Jean-loup Gailly + * This is free software; you can redistribute it and/or modify it under the + * terms of the GNU General Public License, see the file COPYING. + */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +#include +#include + +#include "tailor.h" +#include "gzip.h" +#include "crypt.h" + +#ifdef HAVE_UNISTD_H +# include +#endif +#ifndef NO_FCNTL_H +# include +#endif + +local ulg crc; /* crc on uncompressed file data */ +long header_bytes; /* number of bytes in gzip header */ + +/* =========================================================================== + * Deflate in to out. + * IN assertions: the input and output buffers are cleared. + * The variables time_stamp and save_orig_name are initialized. + */ +int zip(in, out) + int in, out; /* input and output file descriptors */ +{ + uch flags = 0; /* general purpose bit flags */ + ush attr = 0; /* ascii/binary flag */ + ush deflate_flags = 0; /* pkzip -es, -en or -ex equivalent */ + + ifd = in; + ofd = out; + outcnt = 0; + + /* Write the header to the gzip file. See algorithm.doc for the format */ + + method = DEFLATED; + put_byte(GZIP_MAGIC[0]); /* magic header */ + put_byte(GZIP_MAGIC[1]); + put_byte(DEFLATED); /* compression method */ + + if (save_orig_name) { + flags |= ORIG_NAME; + } + put_byte(flags); /* general flags */ + put_long(time_stamp); + + /* Write deflated file to zip file */ + crc = updcrc(0, 0); + + bi_init(out); + ct_init(&attr, &method); + lm_init(level, &deflate_flags); + + put_byte((uch)deflate_flags); /* extra flags */ + put_byte(OS_CODE); /* OS identifier */ + + if (save_orig_name) { + char *p = basename(ifname); /* Don't save the directory part. */ + do { + put_char(*p); + } while (*p++); + } + header_bytes = (long)outcnt; + + (void)deflate(); + +#if !defined(NO_SIZE_CHECK) && !defined(RECORD_IO) + /* Check input size (but not in VMS -- variable record lengths mess it up) + * and not on MSDOS -- diet in TSR mode reports an incorrect file size) + */ + if (ifile_size != -1L && isize != (ulg)ifile_size) { + Trace((stderr, " actual=%ld, read=%ld ", ifile_size, isize)); + fprintf(stderr, "%s: %s: file size changed while zipping\n", + progname, ifname); + } +#endif + + /* Write the crc and uncompressed size */ + put_long(crc); + put_long(isize); + header_bytes += 2*sizeof(long); + + flush_outbuf(); + return OK; +} + + +/* =========================================================================== + * Read a new buffer from the current input file, perform end-of-line + * translation, and update the crc and input file size. + * IN assertion: size >= 2 (for end-of-line translation) + */ +int file_read(buf, size) + char *buf; + unsigned size; +{ + unsigned len; + + Assert(insize == 0, "inbuf not empty"); + + len = read(ifd, buf, size); + if (len == (unsigned)(-1) || len == 0) return (int)len; + + crc = updcrc((uch*)buf, len); + isize += (ulg)len; + return (int)len; +}