diff options
| -rw-r--r-- | isys/gzlib/Makefile | 11 | ||||
| -rw-r--r-- | isys/gzlib/binding.c | 67 | ||||
| -rw-r--r-- | isys/gzlib/bits.c | 206 | ||||
| -rw-r--r-- | isys/gzlib/config.h | 95 | ||||
| -rw-r--r-- | isys/gzlib/gzip.c | 568 | ||||
| -rw-r--r-- | isys/gzlib/gzip.h | 315 | ||||
| -rw-r--r-- | isys/gzlib/gzlib.h | 10 | ||||
| -rw-r--r-- | isys/gzlib/inflate.c | 957 | ||||
| -rw-r--r-- | isys/gzlib/lzw.c | 27 | ||||
| -rw-r--r-- | isys/gzlib/lzw.h | 42 | ||||
| -rw-r--r-- | isys/gzlib/tailor.h | 315 | ||||
| -rw-r--r-- | isys/gzlib/trees.c | 1069 | ||||
| -rw-r--r-- | isys/gzlib/unzip.c | 204 | ||||
| -rw-r--r-- | isys/gzlib/util.c | 538 | ||||
| -rw-r--r-- | isys/gzlib/zip.c | 52 |
15 files changed, 4476 insertions, 0 deletions
diff --git a/isys/gzlib/Makefile b/isys/gzlib/Makefile new file mode 100644 index 000000000..5f2fa85b3 --- /dev/null +++ b/isys/gzlib/Makefile @@ -0,0 +1,11 @@ +include ../../Makefile.inc + +CC = diet gcc +CFLAGS += -I . -g +SOURCES = bits.c gzip.c inflate.c lzw.c trees.c unzip.c util.c zip.c binding.c +OBJS = bits.o gzip.o inflate.o lzw.o trees.o unzip.o util.o zip.o binding.o + +all: libgunzip.a($(OBJS)) + +clean: + rm -f libgunzip.a $(OBJS) diff --git a/isys/gzlib/binding.c b/isys/gzlib/binding.c new file mode 100644 index 000000000..ca93153a0 --- /dev/null +++ b/isys/gzlib/binding.c @@ -0,0 +1,67 @@ +#include <sys/signal.h> +#include <unistd.h> +#include <fcntl.h> +#include <stdlib.h> + +#include "gzlib.h" + +struct gzFile_s { + int fd; +}; + +gzFile gunzip_open(const char * file) { + int fd; + int p[2]; + void * oldsig; + pid_t child; + gzFile str; + + fd = open(file, O_RDONLY); + if (fd < 0) return NULL; + + pipe(p); + + oldsig = signal(SIGCLD, SIG_IGN); + + child = fork(); + if (!child) { + if (fork()) exit(0); + + dup2(fd, 0); + dup2(p[1], 1); + close(p[0]); + close(p[1]); + gunzip_main(); + exit(0); + } + + waitpid(child, NULL, 0); + signal(SIGCLD, oldsig); + + close(p[1]); + + str = malloc(sizeof(*str)); + str->fd = p[0]; + + return str; +} + +int gunzip_read(gzFile str, void * buf, int bytes) { + int pos = 0; + int i; + + while ((pos != bytes) && + (i = read(str->fd, ((char *) buf) + pos, bytes - pos)) > 0) + pos += i; + + if (i < 0) return -1; + + return pos; +} + +int gunzip_close(gzFile str) { + close(str->fd); + + return 0; +} + diff --git a/isys/gzlib/bits.c b/isys/gzlib/bits.c new file mode 100644 index 000000000..3745a9ef3 --- /dev/null +++ b/isys/gzlib/bits.c @@ -0,0 +1,206 @@ +/* bits.c -- output variable-length bit strings + * 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 + * + * Output variable-length bit strings. Compression can be done + * to a file or to memory. (The latter is not supported in this version.) + * + * DISCUSSION + * + * The PKZIP "deflate" file format interprets compressed file data + * as a sequence of bits. Multi-bit strings in the file may cross + * byte boundaries without restriction. + * + * The first bit of each byte is the low-order bit. + * + * The routines in this file allow a variable-length bit value to + * be output right-to-left (useful for literal values). For + * left-to-right output (useful for code strings from the tree routines), + * the bits must have been reversed first with bi_reverse(). + * + * For in-memory compression, the compressed bit stream goes directly + * into the requested output buffer. The input data is read in blocks + * by the mem_read() function. The buffer is limited to 64K on 16 bit + * machines. + * + * INTERFACE + * + * void bi_init (FILE *zipfile) + * Initialize the bit string routines. + * + * void send_bits (int value, int length) + * Write out a bit string, taking the source bits right to + * left. + * + * int bi_reverse (int value, int length) + * Reverse the bits of a bit string, taking the source bits left to + * right and emitting them right to left. + * + * void bi_windup (void) + * Write out any remaining bits in an incomplete byte. + * + * void copy_block(char *buf, unsigned len, int header) + * Copy a stored block to the zip file, storing first the length and + * its one's complement if requested. + * + */ + +#include <config.h> +#include "tailor.h" +#include "gzip.h" +#include "crypt.h" + +#ifdef DEBUG +# include <stdio.h> +#endif + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +/* =========================================================================== + * Local data used by the "bit string" routines. + */ + +local file_t zfile; /* output gzip file */ + +local unsigned short bi_buf; +/* Output buffer. bits are inserted starting at the bottom (least significant + * bits). + */ + +#define Buf_size (8 * 2*sizeof(char)) +/* Number of bits used within bi_buf. (bi_buf might be implemented on + * more than 16 bits on some systems.) + */ + +local int bi_valid; +/* Number of valid bits in bi_buf. All bits above the last valid bit + * are always zero. + */ + +int (*read_buf) OF((char *buf, unsigned size)); +/* Current input function. Set to mem_read for in-memory compression */ + +#ifdef DEBUG + off_t bits_sent; /* bit length of the compressed data */ +#endif + +/* =========================================================================== + * Initialize the bit string routines. + */ +void bi_init (zipfile) + file_t zipfile; /* output zip file, NO_FILE for in-memory compression */ +{ + zfile = zipfile; + bi_buf = 0; + bi_valid = 0; +#ifdef DEBUG + bits_sent = 0L; +#endif + + /* Set the defaults for file compression. They are set by memcompress + * for in-memory compression. + */ + if (zfile != NO_FILE) { + read_buf = file_read; + } +} + +/* =========================================================================== + * Send a value on a given number of bits. + * IN assertion: length <= 16 and value fits in length bits. + */ +void send_bits(value, length) + int value; /* value to send */ + int length; /* number of bits */ +{ +#ifdef DEBUG + Tracev((stderr," l %2d v %4x ", length, value)); + Assert(length > 0 && length <= 15, "invalid length"); + bits_sent += (off_t)length; +#endif + /* If not enough room in bi_buf, use (valid) bits from bi_buf and + * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid)) + * unused bits in value. + */ + if (bi_valid > (int)Buf_size - length) { + bi_buf |= (value << bi_valid); + put_short(bi_buf); + bi_buf = (ush)value >> (Buf_size - bi_valid); + bi_valid += length - Buf_size; + } else { + bi_buf |= value << bi_valid; + bi_valid += length; + } +} + +/* =========================================================================== + * Reverse the first len bits of a code, using straightforward code (a faster + * method would use a table) + * IN assertion: 1 <= len <= 15 + */ +unsigned bi_reverse(code, len) + unsigned code; /* the value to invert */ + int len; /* its bit length */ +{ + register unsigned res = 0; + do { + res |= code & 1; + code >>= 1, res <<= 1; + } while (--len > 0); + return res >> 1; +} + +/* =========================================================================== + * Write out any remaining bits in an incomplete byte. + */ +void bi_windup() +{ + if (bi_valid > 8) { + put_short(bi_buf); + } else if (bi_valid > 0) { + put_byte(bi_buf); + } + bi_buf = 0; + bi_valid = 0; +#ifdef DEBUG + bits_sent = (bits_sent+7) & ~7; +#endif +} + +/* =========================================================================== + * Copy a stored block to the zip file, storing first the length and its + * one's complement if requested. + */ +void copy_block(buf, len, header) + char *buf; /* the input data */ + unsigned len; /* its length */ + int header; /* true if block header must be written */ +{ + bi_windup(); /* align on byte boundary */ + + if (header) { + put_short((ush)len); + put_short((ush)~len); +#ifdef DEBUG + bits_sent += 2*16; +#endif + } +#ifdef DEBUG + bits_sent += (off_t)len<<3; +#endif + while (len--) { +#ifdef CRYPT + int t; + if (key) zencode(*buf, t); +#endif + put_byte(*buf++); + } +} diff --git a/isys/gzlib/config.h b/isys/gzlib/config.h new file mode 100644 index 000000000..f578992c2 --- /dev/null +++ b/isys/gzlib/config.h @@ -0,0 +1,95 @@ +/* config.h. Generated automatically by configure. */ +/* config.h.in. Generated automatically from configure.in by autoheader. */ + +/* Define if on AIX 3. + System headers sometimes define this. + We just want to avoid a redefinition error message. */ +#ifndef _ALL_SOURCE +/* #undef _ALL_SOURCE */ +#endif + +/* Define to empty if the keyword does not work. */ +/* #undef const */ + +/* Define if on MINIX. */ +/* #undef _MINIX */ + +/* Define to `long' if <sys/types.h> doesn't define. */ +/* #undef off_t */ + +/* Define if the system does not provide POSIX.1 features except + with this defined. */ +/* #undef _POSIX_1_SOURCE */ + +/* Define if you need to in order for stat and other things to work. */ +/* #undef _POSIX_SOURCE */ + +/* Define as the return type of signal handlers (int or void). */ +#define RETSIGTYPE void + +/* Define to `unsigned' if <sys/types.h> doesn't define. */ +/* #undef size_t */ + +/* Define if you have the ANSI C header files. */ +#define STDC_HEADERS 1 + +/* Define if you have the utime function. */ +#define HAVE_UTIME 1 + +/* Define if you have the <dirent.h> header file. */ +#define HAVE_DIRENT_H 1 + +/* Define if you have the <fcntl.h> header file. */ +#define HAVE_FCNTL_H 1 + +/* Define if you have the <limits.h> header file. */ +#define HAVE_LIMITS_H 1 + +/* Define if you have the <memory.h> header file. */ +#define HAVE_MEMORY_H 1 + +/* Define if you have the <ndir.h> header file. */ +/* #undef HAVE_NDIR_H */ + +/* Define if you have the <stdlib.h> header file. */ +#define HAVE_STDLIB_H 1 + +/* Define if you have the <string.h> header file. */ +#define HAVE_STRING_H 1 + +/* Define if you have the <sys/dir.h> header file. */ +/* #undef HAVE_SYS_DIR_H */ + +/* Define if you have the <sys/ndir.h> header file. */ +/* #undef HAVE_SYS_NDIR_H */ + +/* Define if you have the <sys/utime.h> header file. */ +/* #undef HAVE_SYS_UTIME_H */ + +/* Define if you have the <time.h> header file. */ +#define HAVE_TIME_H 1 + +/* Define if you have the <unistd.h> header file. */ +#define HAVE_UNISTD_H 1 + +/* Define if you have the <utime.h> header file. */ +#define HAVE_UTIME_H 1 + +/* Name of package */ +#define PACKAGE "gzip" + +/* Version number of package */ +#define VERSION "1.3" + +/* Number of bits in a file offset, on hosts where this is settable. */ +#define _FILE_OFFSET_BITS 64 + +/* Define to make fseeko etc. visible, on some hosts. */ +/* #undef _LARGEFILE_SOURCE */ + +/* Define for large files, on AIX-style hosts. */ +/* #undef _LARGE_FILES */ + +/* Define if an assembler version of longest_match is available. */ +/* #undef ASMV */ + diff --git a/isys/gzlib/gzip.c b/isys/gzlib/gzip.c new file mode 100644 index 000000000..36eca62c2 --- /dev/null +++ b/isys/gzlib/gzip.c @@ -0,0 +1,568 @@ +/* gzip (GNU zip) -- compress files with zip algorithm and 'compress' interface + * Copyright (C) 1992-1993 Jean-loup Gailly + * The unzip code was written and put in the public domain by Mark Adler. + * Portions of the lzw code are derived from the public domain 'compress' + * written by Spencer Thomas, Joe Orost, James Woods, Jim McKie, Steve Davies, + * Ken Turkowski, Dave Mack and Peter Jannesen. + * + * See the license_msg below and the file COPYING for the software license. + * See the file algorithm.doc for the compression algorithms and file formats. + */ + + +/* Compress files with zip algorithm and 'compress' interface. + * See usage() and help() functions below for all options. + * Outputs: + * file.gz: compressed file with same mode, owner, and utimes + * or stdout with -c option or if stdin used as input. + * If the output file name had to be truncated, the original name is kept + * in the compressed file. + * On MSDOS, file.tmp -> file.tmz. On VMS, file.tmp -> file.tmp-gz. + * + * Using gz on MSDOS would create too many file name conflicts. For + * example, foo.txt -> foo.tgz (.tgz must be reserved as shorthand for + * tar.gz). Similarly, foo.dir and foo.doc would both be mapped to foo.dgz. + * I also considered 12345678.txt -> 12345txt.gz but this truncates the name + * too heavily. There is no ideal solution given the MSDOS 8+3 limitation. + * + * For the meaning of all compilation flags, see comments in Makefile.in. + */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +#include <config.h> +#include <ctype.h> +#include <sys/types.h> +#include <signal.h> +#include <sys/stat.h> +#include <errno.h> + +#include "tailor.h" +#include "gzip.h" +#include "lzw.h" + + /* configuration */ + +#ifdef HAVE_TIME_H +# include <time.h> +#else +# include <sys/time.h> +#endif + +#ifdef HAVE_FCNTL_H +# include <fcntl.h> +#endif + +#ifdef HAVE_LIMITS_H +# include <limits.h> +#endif + +#ifdef HAVE_UNISTD_H +# include <unistd.h> +#endif + +#if defined STDC_HEADERS || defined HAVE_STDLIB_H +# include <stdlib.h> +#else + extern int errno; +#endif + +#ifdef HAVE_DIRENT_H +# include <dirent.h> +# define NAMLEN(direct) strlen((direct)->d_name) +# define DIR_OPT "DIRENT" +#else +# define dirent direct +# define NAMLEN(direct) ((direct)->d_namlen) +# ifdef HAVE_SYS_NDIR_H +# include <sys/ndir.h> +# define DIR_OPT "SYS_NDIR" +# endif +# ifdef HAVE_SYS_DIR_H +# include <sys/dir.h> +# define DIR_OPT "SYS_DIR" +# endif +# ifdef HAVE_NDIR_H +# include <ndir.h> +# define DIR_OPT "NDIR" +# endif +# ifndef DIR_OPT +# define DIR_OPT "NO_DIR" +# endif +#endif + +#ifdef CLOSEDIR_VOID +# define CLOSEDIR(d) (closedir(d), 0) +#else +# define CLOSEDIR(d) closedir(d) +#endif + +#ifdef HAVE_UTIME +# ifdef HAVE_UTIME_H +# include <utime.h> +# define TIME_OPT "UTIME" +# else +# ifdef HAVE_SYS_UTIME_H +# include <sys/utime.h> +# define TIME_OPT "SYS_UTIME" +# else + struct utimbuf { + time_t actime; + time_t modtime; + }; +# define TIME_OPT "STRUCT_UTIMBUF" +# endif +# endif +#else +# define TIME_OPT "NO_UTIME" +#endif + +#if !defined(S_ISDIR) && defined(S_IFDIR) +# define S_ISDIR(m) (((m) & S_IFMT) == S_IFDIR) +#endif +#if !defined(S_ISREG) && defined(S_IFREG) +# define S_ISREG(m) (((m) & S_IFMT) == S_IFREG) +#endif + +typedef RETSIGTYPE (*sig_type) OF((int)); + +#ifndef O_BINARY +# define O_BINARY 0 /* creation mode for open() */ +#endif + +#ifndef O_CREAT + /* Pure BSD system? */ +# include <sys/file.h> +# ifndef O_CREAT +# define O_CREAT FCREAT +# endif +# ifndef O_EXCL +# define O_EXCL FEXCL +# endif +#endif + +#ifndef S_IRUSR +# define S_IRUSR 0400 +#endif +#ifndef S_IWUSR +# define S_IWUSR 0200 +#endif +#define RW_USER (S_IRUSR | S_IWUSR) /* creation mode for open() */ + +#ifndef MAX_PATH_LEN +# define MAX_PATH_LEN 1024 /* max pathname length */ +#endif + +#ifndef SEEK_END +# define SEEK_END 2 +#endif + +#ifndef CHAR_BIT +# define CHAR_BIT 8 +#endif + +#ifdef off_t + off_t lseek OF((int fd, off_t offset, int whence)); +#endif + +#ifndef OFF_T_MIN +#define OFF_T_MIN (~ (off_t) 0 << (sizeof (off_t) * CHAR_BIT - 1)) +#endif + +#ifndef OFF_T_MAX +#define OFF_T_MAX (~ (off_t) 0 - OFF_T_MIN) +#endif + + /* global buffers */ + +DECLARE(uch, inbuf, INBUFSIZ +INBUF_EXTRA); +DECLARE(uch, outbuf, OUTBUFSIZ+OUTBUF_EXTRA); +DECLARE(ush, d_buf, DIST_BUFSIZE); +DECLARE(uch, window, 2L*WSIZE); +#ifndef MAXSEG_64K + DECLARE(ush, tab_prefix, 1L<<BITS); +#else + DECLARE(ush, tab_prefix0, 1L<<(BITS-1)); + DECLARE(ush, tab_prefix1, 1L<<(BITS-1)); +#endif + + /* local variables */ + +long block_start; +unsigned strstart; /* start of string to insert */ + +int to_stdout = 0; /* output to stdout (-c) */ +int decompress = 0; /* decompress (-d) */ +int force = 0; /* don't ask questions, compress links (-f) */ +int no_name = -1; /* don't save or restore the original file name */ +int no_time = -1; /* don't save or restore the original file time */ +int recursive = 0; /* recurse through directories (-r) */ +int list = 0; /* list the file contents (-l) */ +int quiet = 0; /* be very quiet (-q) */ +int do_lzw = 0; /* generate output compatible with old compress (-Z) */ +int test = 0; /* test .gz file integrity */ +int foreground; /* set if program run in foreground */ +char *progname; /* program name */ +int maxbits = BITS; /* max bits per code for LZW */ +int method = DEFLATED;/* compression method */ +int level = 6; /* compression level */ +int exit_code = OK; /* program exit code */ +int save_orig_name; /* set if original name must be saved */ +int last_member; /* set for .zip and .Z files */ +int part_nb; /* number of parts in .gz file */ +time_t time_stamp; /* original time stamp (modification time) */ +off_t ifile_size; /* input file size, -1 for devices (debug only) */ +char *env; /* contents of GZIP env variable */ +char **args = NULL; /* argv pointer if GZIP env variable defined */ +char *z_suffix; /* default suffix (can be set with --suffix) */ +int z_len; /* strlen(z_suffix) */ + +off_t bytes_in; /* number of input bytes */ +off_t bytes_out; /* number of output bytes */ +off_t total_in; /* input bytes for all files */ +off_t total_out; /* output bytes for all files */ +char ifname[MAX_PATH_LEN]; /* input file name */ +char ofname[MAX_PATH_LEN]; /* output file name */ +int remove_ofname = 0; /* remove output file on error */ +struct stat istat; /* status for input file */ +int ifd; /* input file descriptor */ +int ofd; /* output file descriptor */ +unsigned insize; /* valid bytes in inbuf */ +unsigned inptr; /* index of next byte to be processed in inbuf */ +unsigned outcnt; /* bytes in output buffer */ + +/* local functions */ + +local int input_eof OF((void)); +local void treat_stdin OF((void)); +local int get_method OF((int in)); +local void do_exit OF((int exitcode)); +int (*work) OF((int infile, int outfile)) = NULL; + +#define strequ(s1, s2) (strcmp((s1),(s2)) == 0) + +local void progerror (string) + char *string; +{ + int e = errno; + fprintf(stderr, "%s: ", progname); + errno = e; + perror(string); + exit_code = ERROR; +} + +/* ======================================================================== */ +int gunzip_main (void) +{ + int file_count; /* number of files to precess */ + int proglen; /* length of progname */ + int optc; /* current option */ + int argc = 1; + char *argv[] = { "gunzip ", NULL }; + + EXPAND(argc, argv); /* wild card expansion if necessary */ + + progname = base_name (argv[0]); + proglen = strlen(progname); + + /* Suppress .exe for MSDOS, OS/2 and VMS: */ + if (proglen > 4 && strequ(progname+proglen-4, ".exe")) { + progname[proglen-4] = '\0'; + } + + /* Add options in GZIP environment variable if there is one */ + env = add_envopt(&argc, &argv, OPTIONS_VAR); + if (env != NULL) args = argv; + + foreground = signal(SIGINT, SIG_IGN) != SIG_IGN; + if (foreground) { + (void) signal (SIGINT, (sig_type)abort_gzip); + } +#ifdef SIGTERM + if (signal(SIGTERM, SIG_IGN) != SIG_IGN) { + (void) signal(SIGTERM, (sig_type)abort_gzip); + } +#endif +#ifdef SIGHUP + if (signal(SIGHUP, SIG_IGN) != SIG_IGN) { + (void) signal(SIGHUP, (sig_type)abort_gzip); + } +#endif + +#ifndef GNU_STANDARD + /* For compatibility with old compress, use program name as an option. + * If you compile with -DGNU_STANDARD, this program will behave as + * gzip even if it is invoked under the name gunzip or zcat. + * + * Systems which do not support links can still use -d or -dc. + * Ignore an .exe extension for MSDOS, OS/2 and VMS. + */ + if ( strncmp(progname, "un", 2) == 0 /* ungzip, uncompress */ + || strncmp(progname, "gun", 3) == 0) { /* gunzip */ + decompress = 1; + } else if (strequ(progname+1, "cat") /* zcat, pcat, gcat */ + || strequ(progname, "gzcat")) { /* gzcat */ + decompress = to_stdout = 1; + } +#endif + + z_suffix = Z_SUFFIX; + z_len = strlen(z_suffix); + +#ifdef SIGPIPE + /* Ignore "Broken Pipe" message with --quiet */ + if (quiet && signal (SIGPIPE, SIG_IGN) != SIG_IGN) + signal (SIGPIPE, (sig_type) abort_gzip); +#endif + + /* By default, save name and timestamp on compression but do not + * restore them on decompression. + */ + if (no_time < 0) no_time = decompress; + if (no_name < 0) no_name = decompress; + + file_count = argc - optind; + + /* Allocate all global buffers (for DYN_ALLOC option) */ + ALLOC(uch, inbuf, INBUFSIZ +INBUF_EXTRA); + ALLOC(uch, outbuf, OUTBUFSIZ+OUTBUF_EXTRA); + ALLOC(ush, d_buf, DIST_BUFSIZE); + ALLOC(uch, window, 2L*WSIZE); +#ifndef MAXSEG_64K + ALLOC(ush, tab_prefix, 1L<<BITS); +#else + ALLOC(ush, tab_prefix0, 1L<<(BITS-1)); + ALLOC(ush, tab_prefix1, 1L<<(BITS-1)); +#endif + + treat_stdin(); + + do_exit(exit_code); + return exit_code; /* just to avoid lint warning */ +} + +/* Return nonzero when at end of file on input. */ +local int +input_eof () +{ + if (!decompress || last_member) + return 1; + + if (inptr == insize) + { + if (insize != INBUFSIZ || fill_inbuf (1) == EOF) + return 1; + + /* Unget the char that fill_inbuf got. */ + inptr = 0; + } + + return 0; +} + +/* ======================================================================== + * Compress or decompress stdin + */ +local void treat_stdin() +{ + strcpy(ifname, "stdin"); + strcpy(ofname, "stdout"); + + /* Get the time stamp on the input file. */ + time_stamp = 0; /* time unknown by default */ + + ifile_size = -1L; /* convention for unknown size */ + + clear_bufs(); /* clear input and output buffers */ + to_stdout = 1; + part_nb = 0; + + method = get_method(ifd); + if (method < 0) { + do_exit(exit_code); /* error message already emitted */ + } + + /* Actually do the compression/decompression. Loop over zipped members. + */ + for (;;) { + if ((*work)(fileno(stdin), fileno(stdout)) != OK) return; + + if (input_eof ()) + break; + + method = get_method(ifd); + if (method < 0) return; /* error message already emitted */ + bytes_out = 0; /* required for length check */ + } + +} + + +/* ======================================================================== + * Check the magic number of the input file and update ofname if an + * original name was given and to_stdout is not set. + * Return the compression method, -1 for error, -2 for warning. + * Set inptr to the offset of the next byte to be processed. + * Updates time_stamp if there is one and --no-time is not used. + * This function may be called repeatedly for an input file consisting + * of several contiguous gzip'ed members. + * IN assertions: there is at least one remaining compressed member. + * If the member is a zip file, it must be the only one. + */ +local int get_method(in) + int in; /* input file descriptor */ +{ + uch flags; /* compression flags */ + char magic[2]; /* magic header */ + int imagic1; /* like magic[1], but can represent EOF */ + ulg stamp; /* time stamp */ + + /* If --force and --stdout, zcat == cat, so do not complain about + * premature end of file: use try_byte instead of get_byte. + */ + if (force && to_stdout) { + magic[0] = (char)try_byte(); + imagic1 = try_byte (); + magic[1] = (char) imagic1; + /* If try_byte returned EOF, magic[1] == (char) EOF. */ + } else { + magic[0] = (char)get_byte(); + magic[1] = (char)get_byte(); + imagic1 = 0; /* avoid lint warning */ + } + method = -1; /* unknown yet */ + part_nb++; /* number of parts in gzip file */ + header_bytes = 0; + last_member = RECORD_IO; + /* assume multiple members in gzip file except for record oriented I/O */ + + if (memcmp(magic, GZIP_MAGIC, 2) == 0 + || memcmp(magic, OLD_GZIP_MAGIC, 2) == 0) { + + method = (int)get_byte(); + if (method != DEFLATED) { + fprintf(stderr, + "%s: %s: unknown method %d -- get newer version of gzip\n", + progname, ifname, method); + exit_code = ERROR; + return -1; + } + work = unzip; + flags = (uch)get_byte(); + + stamp = (ulg)get_byte(); + stamp |= ((ulg)get_byte()) << 8; + stamp |= ((ulg)get_byte()) << 16; + stamp |= ((ulg)get_byte()) << 24; + if (stamp != 0 && !no_time) time_stamp = stamp; + + (void)get_byte(); /* Ignore extra flags for the moment */ + (void)get_byte(); /* Ignore OS type for the moment */ + + if ((flags & CONTINUATION) != 0) { + unsigned part = (unsigned)get_byte(); + part |= ((unsigned)get_byte())<<8; + } + if ((flags & EXTRA_FIELD) != 0) { + unsigned len = (unsigned)get_byte(); + len |= ((unsigned)get_byte())<<8; + while (len--) (void)get_byte(); + } + + /* Get original file name if it was truncated */ + if ((flags & ORIG_NAME) != 0) { + if (no_name || (to_stdout && !list) || part_nb > 1) { + /* Discard the old name */ + char c; /* dummy used for NeXTstep 3.0 cc optimizer bug */ + do {c=get_byte();} while (c != 0); + } else { + /* Copy the base name. Keep a directory prefix intact. */ + char *p = base_name (ofname); + char *base = p; + for (;;) { + *p = (char)get_char(); + if (*p++ == '\0') break; + if (p >= ofname+sizeof(ofname)) { + gzerror("corrupted input -- file name too large"); + } + } + /* If necessary, adapt the name to local OS conventions: */ + if (!list) { + MAKE_LEGAL_NAME(base); + if (base) list=0; /* avoid warning about unused variable */ + } + } /* no_name || to_stdout */ + } /* ORIG_NAME */ + + /* Discard file comment if any */ + if ((flags & COMMENT) != 0) { + while (get_char() != 0) /* null */ ; + } + if (part_nb == 1) { + header_bytes = inptr + 2*sizeof(long); /* include crc and size */ + } + + } + + if (method >= 0) return method; + + if (part_nb == 1) { + fprintf(stderr, "\n%s: %s: not in gzip format\n", progname, ifname); + exit_code = ERROR; + return -1; + } else { + if (magic[0] == 0) + { + int inbyte; + for (inbyte = imagic1; inbyte == 0; inbyte = try_byte ()) + continue; + if (inbyte == EOF) + { + return -3; + } + } + + WARN((stderr, "\n%s: %s: decompression OK, trailing garbage ignored\n", + progname, ifname)); + return -2; + } +} + +/* ======================================================================== + * Free all dynamically allocated variables and exit with the given code. + */ +local void do_exit(exitcode) + int exitcode; +{ + static int in_exit = 0; + + if (in_exit) exit(exitcode); + in_exit = 1; + if (env != NULL) free(env), env = NULL; + if (args != NULL) free((char*)args), args = NULL; + FREE(inbuf); + FREE(outbuf); + FREE(d_buf); + FREE(window); +#ifndef MAXSEG_64K + FREE(tab_prefix); +#else + FREE(tab_prefix0); + FREE(tab_prefix1); +#endif + exit(exitcode); +} + +/* ======================================================================== + * Signal and error handler. + */ +RETSIGTYPE abort_gzip() +{ + if (remove_ofname) { + close(ofd); + xunlink (ofname); + } + do_exit(ERROR); +} diff --git a/isys/gzlib/gzip.h b/isys/gzlib/gzip.h new file mode 100644 index 000000000..7f8613866 --- /dev/null +++ b/isys/gzlib/gzip.h @@ -0,0 +1,315 @@ +/* gzip.h -- common declarations for all gzip modules + * 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. + */ + +#if defined(__STDC__) || defined(PROTO) +# define OF(args) args +#else +# define OF(args) () +#endif + +#ifdef __STDC__ + typedef void *voidp; +#else + typedef char *voidp; +#endif + +/* I don't like nested includes, but the following headers are used + * too often + */ +#include <stdio.h> +#include <sys/types.h> /* for off_t, time_t */ +#if defined HAVE_STRING_H || defined STDC_HEADERS +# include <string.h> +# if !defined STDC_HEADERS && defined HAVE_MEMORY_H && !defined __GNUC__ +# include <memory.h> +# endif +# define memzero(s, n) memset ((voidp)(s), 0, (n)) +#else +# include <strings.h> +# define strchr index +# define strrchr rindex +# define memcpy(d, s, n) bcopy((s), (d), (n)) +# define memcmp(s1, s2, n) bcmp((s1), (s2), (n)) +# define memzero(s, n) bzero((s), (n)) +#endif + +#ifndef RETSIGTYPE +# define RETSIGTYPE void +#endif + +#define local static + +typedef unsigned char uch; +typedef unsigned short ush; +typedef unsigned long ulg; + +/* Return codes from gzip */ +#define OK 0 +#define ERROR 1 +#define WARNING 2 + +/* Compression methods (see algorithm.doc) */ +#define STORED 0 +#define COMPRESSED 1 +#define PACKED 2 +#define LZHED 3 +/* methods 4 to 7 reserved */ +#define DEFLATED 8 +#define MAX_METHODS 9 +extern int method; /* compression method */ + +/* To save memory for 16 bit systems, some arrays are overlaid between + * the various modules: + * deflate: prev+head window d_buf l_buf outbuf + * unlzw: tab_prefix tab_suffix stack inbuf outbuf + * inflate: window inbuf + * unpack: window inbuf prefix_len + * unlzh: left+right window c_table inbuf c_len + * For compression, input is done in window[]. For decompression, output + * is done in window except for unlzw. + */ + +#ifndef INBUFSIZ +# ifdef SMALL_MEM +# define INBUFSIZ 0x2000 /* input buffer size */ +# else +# define INBUFSIZ 0x8000 /* input buffer size */ +# endif +#endif +#define INBUF_EXTRA 64 /* required by unlzw() */ + +#ifndef OUTBUFSIZ +# ifdef SMALL_MEM +# define OUTBUFSIZ 8192 /* output buffer size */ +# else +# define OUTBUFSIZ 16384 /* output buffer size */ +# endif +#endif +#define OUTBUF_EXTRA 2048 /* required by unlzw() */ + +#ifndef DIST_BUFSIZE +# ifdef SMALL_MEM +# define DIST_BUFSIZE 0x2000 /* buffer for distances, see trees.c */ +# else +# define DIST_BUFSIZE 0x8000 /* buffer for distances, see trees.c */ +# endif +#endif + +#ifdef DYN_ALLOC +# define EXTERN(type, array) extern type * near array +# define DECLARE(type, array, size) type * near array +# define ALLOC(type, array, size) { \ + array = (type*)fcalloc((size_t)(((size)+1L)/2), 2*sizeof(type)); \ + if (array == NULL) gzerror("insufficient memory"); \ + } +# define FREE(array) {if (array != NULL) fcfree(array), array=NULL;} +#else +# define EXTERN(type, array) extern type array[] +# define DECLARE(type, array, size) type array[size] +# define ALLOC(type, array, size) +# define FREE(array) +#endif + +EXTERN(uch, inbuf); /* input buffer */ +EXTERN(uch, outbuf); /* output buffer */ +EXTERN(ush, d_buf); /* buffer for distances, see trees.c */ +EXTERN(uch, window); /* Sliding window and suffix table (unlzw) */ +#define tab_suffix window +#ifndef MAXSEG_64K +# define tab_prefix prev /* hash link (see deflate.c) */ +# define head (prev+WSIZE) /* hash head (see deflate.c) */ + EXTERN(ush, tab_prefix); /* prefix code (see unlzw.c) */ +#else +# define tab_prefix0 prev +# define head tab_prefix1 + EXTERN(ush, tab_prefix0); /* prefix for even codes */ + EXTERN(ush, tab_prefix1); /* prefix for odd codes */ +#endif + +extern unsigned insize; /* valid bytes in inbuf */ +extern unsigned inptr; /* index of next byte to be processed in inbuf */ +extern unsigned outcnt; /* bytes in output buffer */ + +extern off_t bytes_in; /* number of input bytes */ +extern off_t bytes_out; /* number of output bytes */ +extern off_t header_bytes;/* number of bytes in gzip header */ + +extern int ifd; /* input file descriptor */ +extern int ofd; /* output file descriptor */ +extern char ifname[]; /* input file name or "stdin" */ +extern char ofname[]; /* output file name or "stdout" */ +extern char *progname; /* program name */ + +extern time_t time_stamp; /* original time stamp (modification time) */ +extern off_t ifile_size; /* input file size, -1 for devices (debug only) */ + +typedef int file_t; /* Do not use stdio */ +#define NO_FILE (-1) /* in memory compression */ + + +#define PACK_MAGIC "\037\036" /* Magic header for packed files */ +#define GZIP_MAGIC "\037\213" /* Magic header for gzip files, 1F 8B */ +#define OLD_GZIP_MAGIC "\037\236" /* Magic header for gzip 0.5 = freeze 1.x */ +#define LZH_MAGIC "\037\240" /* Magic header for SCO LZH Compress files*/ +#define PKZIP_MAGIC "\120\113\003\004" /* Magic header for pkzip files */ + +/* gzip flag byte */ +#define ASCII_FLAG 0x01 /* bit 0 set: file probably ascii text */ +#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */ +#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */ +#define ORIG_NAME 0x08 /* bit 3 set: original file name present */ +#define COMMENT 0x10 /* bit 4 set: file comment present */ +#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ +#define RESERVED 0xC0 /* bit 6,7: reserved */ + +/* internal file attribute */ +#define UNKNOWN 0xffff +#define BINARY 0 +#define ASCII 1 + +#ifndef WSIZE +# define WSIZE 0x8000 /* window size--must be a power of two, and */ +#endif /* at least 32K for zip's deflate method */ + +#define MIN_MATCH 3 +#define MAX_MATCH 258 +/* The minimum and maximum match lengths */ + +#define MIN_LOOKAHEAD (MAX_MATCH+MIN_MATCH+1) +/* Minimum amount of lookahead, except at the end of the input file. + * See deflate.c for comments about the MIN_MATCH+1. + */ + +#define MAX_DIST (WSIZE-MIN_LOOKAHEAD) +/* In order to simplify the code, particularly on 16 bit machines, match + * distances are limited to MAX_DIST instead of WSIZE. + */ + +extern int decrypt; /* flag to turn on decryption */ +extern int exit_code; /* program exit code */ +extern int verbose; /* be verbose (-v) */ +extern int quiet; /* be quiet (-q) */ +extern int level; /* compression level */ +extern int test; /* check .z file integrity */ +extern int to_stdout; /* output to stdout (-c) */ +extern int save_orig_name; /* set if original name must be saved */ + +#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf(0)) +#define try_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf(1)) + +/* put_byte is used for the compressed output, put_ubyte for the + * uncompressed output. However unlzw() uses window for its + * suffix table instead of its output buffer, so it does not use put_ubyte + * (to be cleaned up). + */ +#define put_byte(c) {outbuf[outcnt++]=(uch)(c); if (outcnt==OUTBUFSIZ)\ + flush_outbuf();} +#define put_ubyte(c) {window[outcnt++]=(uch)(c); if (outcnt==WSIZE)\ + flush_window();} + +/* Output a 16 bit value, lsb first */ +#define put_short(w) \ +{ if (outcnt < OUTBUFSIZ-2) { \ + outbuf[outcnt++] = (uch) ((w) & 0xff); \ + outbuf[outcnt++] = (uch) ((ush)(w) >> 8); \ + } else { \ + put_byte((uch)((w) & 0xff)); \ + put_byte((uch)((ush)(w) >> 8)); \ + } \ +} + +/* Output a 32 bit value to the bit stream, lsb first */ +#define put_long(n) { \ + put_short((n) & 0xffff); \ + put_short(((ulg)(n)) >> 16); \ +} + +#define seekable() 0 /* force sequential output */ +#define translate_eol 0 /* no option -a yet */ + +#define tolow(c) (isupper (c) ? tolower (c) : (c)) /* force to lower case */ + +/* Macros for getting two-byte and four-byte header values */ +#define SH(p) ((ush)(uch)((p)[0]) | ((ush)(uch)((p)[1]) << 8)) +#define LG(p) ((ulg)(SH(p)) | ((ulg)(SH((p)+2)) << 16)) + +/* Diagnostic functions */ +#ifdef DEBUG +# define Assert(cond,msg) {if(!(cond)) gzerror(msg);} +# define Trace(x) fprintf x +# define Tracev(x) {if (verbose) fprintf x ;} +# define Tracevv(x) {if (verbose>1) fprintf x ;} +# define Tracec(c,x) {if (verbose && (c)) fprintf x ;} +# define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;} +#else +# define Assert(cond,msg) +# define Trace(x) +# define Tracev(x) +# define Tracevv(x) +# define Tracec(c,x) +# define Tracecv(c,x) +#endif + +#define WARN(msg) {if (!quiet) fprintf msg ; \ + if (exit_code == OK) exit_code = WARNING;} + + /* in zip.c: */ +extern int zip OF((int in, int out)); +extern int file_read OF((char *buf, unsigned size)); + + /* in unzip.c */ +extern int unzip OF((int in, int out)); +extern int check_zipfile OF((int in)); + + /* in unpack.c */ +extern int unpack OF((int in, int out)); + + /* in unlzh.c */ +extern int unlzh OF((int in, int out)); + + /* in gzip.c */ +RETSIGTYPE abort_gzip OF((void)); + + /* in deflate.c */ +void lm_init OF((int pack_level, ush *flags)); +off_t deflate OF((void)); + + /* in trees.c */ +void ct_init OF((ush *attr, int *method)); +int ct_tally OF((int dist, int lc)); +off_t flush_block OF((char *buf, ulg stored_len, int eof)); + + /* in bits.c */ +void bi_init OF((file_t zipfile)); +void send_bits OF((int value, int length)); +unsigned bi_reverse OF((unsigned value, int length)); +void bi_windup OF((void)); +void copy_block OF((char *buf, unsigned len, int header)); +extern int (*read_buf) OF((char *buf, unsigned size)); + + /* in util.c: */ +extern int copy OF((int in, int out)); +extern ulg updcrc OF((uch *s, unsigned n)); +extern void clear_bufs OF((void)); +extern int fill_inbuf OF((int eof_ok)); +extern void flush_outbuf OF((void)); +extern void flush_window OF((void)); +extern void write_buf OF((int fd, voidp buf, unsigned cnt)); +extern char *strlwr OF((char *s)); +extern char *base_name OF((char *fname)); +extern int xunlink OF((char *fname)); +extern void make_simple_name OF((char *name)); +extern char *add_envopt OF((int *argcp, char ***argvp, char *env)); +extern void gzerror OF((char *m)); +extern void warning OF((char *m)); +extern void read_error OF((void)); +extern void write_error OF((void)); +extern void display_ratio OF((off_t num, off_t den, FILE *file)); +extern void fprint_off OF((FILE *, off_t, int)); +extern voidp gzxmalloc OF((unsigned int size)); + + /* in inflate.c */ +extern int inflate OF((void)); diff --git a/isys/gzlib/gzlib.h b/isys/gzlib/gzlib.h new file mode 100644 index 000000000..5de4117d8 --- /dev/null +++ b/isys/gzlib/gzlib.h @@ -0,0 +1,10 @@ +#ifndef H_GZFILE +#define H_GZFILE + +typedef struct gzFile_s * gzFile; + +gzFile gunzip_open(const char * file); +int gunzip_read(gzFile str, void * buf, int bytes); +int gunzip_close(gzFile str); + +#endif diff --git a/isys/gzlib/inflate.c b/isys/gzlib/inflate.c new file mode 100644 index 000000000..293aa1f34 --- /dev/null +++ b/isys/gzlib/inflate.c @@ -0,0 +1,957 @@ +/* inflate.c -- Not copyrighted 1992 by Mark Adler + version c10p1, 10 January 1993 */ + +/* You can do whatever you like with this source file, though I would + prefer that if you modify it and redistribute it that you include + comments to that effect with your name and the date. Thank you. + [The history has been moved to the file ChangeLog.] + */ + +/* + Inflate deflated (PKZIP's method 8 compressed) data. The compression + method searches for as much of the current string of bytes (up to a + length of 258) in the previous 32K bytes. If it doesn't find any + matches (of at least length 3), it codes the next byte. Otherwise, it + codes the length of the matched string and its distance backwards from + the current position. There is a single Huffman code that codes both + single bytes (called "literals") and match lengths. A second Huffman + code codes the distance information, which follows a length code. Each + length or distance code actually represents a base value and a number + of "extra" (sometimes zero) bits to get to add to the base value. At + the end of each deflated block is a special end-of-block (EOB) literal/ + length code. The decoding process is basically: get a literal/length + code; if EOB then done; if a literal, emit the decoded byte; if a + length then get the distance and emit the referred-to bytes from the + sliding window of previously emitted data. + + There are (currently) three kinds of inflate blocks: stored, fixed, and + dynamic. The compressor deals with some chunk of data at a time, and + decides which method to use on a chunk-by-chunk basis. A chunk might + typically be 32K or 64K. If the chunk is uncompressible, then the + "stored" method is used. In this case, the bytes are simply stored as + is, eight bits per byte, with none of the above coding. The bytes are + preceded by a count, since there is no longer an EOB code. + + If the data is compressible, then either the fixed or dynamic methods + are used. In the dynamic method, the compressed data is preceded by + an encoding of the literal/length and distance Huffman codes that are + to be used to decode this block. The representation is itself Huffman + coded, and so is preceded by a description of that code. These code + descriptions take up a little space, and so for small blocks, there is + a predefined set of codes, called the fixed codes. The fixed method is + used if the block codes up smaller that way (usually for quite small + chunks), otherwise the dynamic method is used. In the latter case, the + codes are customized to the probabilities in the current block, and so + can code it much better than the pre-determined fixed codes. + + The Huffman codes themselves are decoded using a mutli-level table + lookup, in order to maximize the speed of decoding plus the speed of + building the decoding tables. See the comments below that precede the + lbits and dbits tuning parameters. + */ + + +/* + Notes beyond the 1.93a appnote.txt: + + 1. Distance pointers never point before the beginning of the output + stream. + 2. Distance pointers can point back across blocks, up to 32k away. + 3. There is an implied maximum of 7 bits for the bit length table and + 15 bits for the actual data. + 4. If only one code exists, then it is encoded using one bit. (Zero + would be more efficient, but perhaps a little confusing.) If two + codes exist, they are coded using one bit each (0 and 1). + 5. There is no way of sending zero distance codes--a dummy must be + sent if there are none. (History: a pre 2.0 version of PKZIP would + store blocks with no distance codes, but this was discovered to be + too harsh a criterion.) Valid only for 1.93a. 2.04c does allow + zero distance codes, which is sent as one code of zero bits in + length. + 6. There are up to 286 literal/length codes. Code 256 represents the + end-of-block. Note however that the static length tree defines + 288 codes just to fill out the Huffman codes. Codes 286 and 287 + cannot be used though, since there is no length base or extra bits + defined for them. Similarly, there are up to 30 distance codes. + However, static trees define 32 codes (all 5 bits) to fill out the + Huffman codes, but the last two had better not show up in the data. + 7. Unzip can check dynamic Huffman blocks for complete code sets. + The exception is that a single code would not be complete (see #4). + 8. The five bits following the block type is really the number of + literal codes sent minus 257. + 9. Length codes 8,16,16 are interpreted as 13 length codes of 8 bits + (1+6+6). Therefore, to output three times the length, you output + three codes (1+1+1), whereas to output four times the same length, + you only need two codes (1+3). Hmm. + 10. In the tree reconstruction algorithm, Code = Code + Increment + only if BitLength(i) is not zero. (Pretty obvious.) + 11. Correction: 4 Bits: # of Bit Length codes - 4 (4 - 19) + 12. Note: length code 284 can represent 227-258, but length code 285 + really is 258. The last length deserves its own, short code + since it gets used a lot in very redundant files. The length + 258 is special since 258 - 3 (the min match length) is 255. + 13. The literal/length and distance code bit lengths are read as a + single stream of lengths. It is possible (and advantageous) for + a repeat code (16, 17, or 18) to go across the boundary between + the two sets of lengths. + */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +#include <config.h> +#include "tailor.h" + +#if defined STDC_HEADERS || defined HAVE_STDLIB_H +# include <stdlib.h> +#endif + +#include "gzip.h" +#define slide window + +/* Huffman code lookup table entry--this entry is four bytes for machines + that have 16-bit pointers (e.g. PC's in the small or medium model). + Valid extra bits are 0..13. e == 15 is EOB (end of block), e == 16 + means that v is a literal, 16 < e < 32 means that v is a pointer to + the next table, which codes e - 16 bits, and lastly e == 99 indicates + an unused code. If a code with e == 99 is looked up, this implies an + error in the data. */ +struct huft { + uch e; /* number of extra bits or operation */ + uch b; /* number of bits in this code or subcode */ + union { + ush n; /* literal, length base, or distance base */ + struct huft *t; /* pointer to next level of table */ + } v; +}; + + +/* Function prototypes */ +int huft_build OF((unsigned *, unsigned, unsigned, ush *, ush *, + struct huft **, int *)); +int huft_free OF((struct huft *)); +int inflate_codes OF((struct huft *, struct huft *, int, int)); +int inflate_stored OF((void)); +int inflate_fixed OF((void)); +int inflate_dynamic OF((void)); +int inflate_block OF((int *)); +int inflate OF((void)); + + +/* The inflate algorithm uses a sliding 32K byte window on the uncompressed + stream to find repeated byte strings. This is implemented here as a + circular buffer. The index is updated simply by incrementing and then + and'ing with 0x7fff (32K-1). */ +/* It is left to other modules to supply the 32K area. It is assumed + to be usable as if it were declared "uch slide[32768];" or as just + "uch *slide;" and then malloc'ed in the latter case. The definition + must be in unzip.h, included above. */ +/* unsigned wp; current position in slide */ +#define wp outcnt +#define flush_output(w) (wp=(w),flush_window()) + +/* Tables for deflate from PKZIP's appnote.txt. */ +static unsigned border[] = { /* Order of the bit length code lengths */ + 16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; +static ush cplens[] = { /* Copy lengths for literal codes 257..285 */ + 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, + 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; + /* note: see note #13 above about the 258 in this list. */ +static ush cplext[] = { /* Extra bits for literal codes 257..285 */ + 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, + 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5, 0, 99, 99}; /* 99==invalid */ +static ush cpdist[] = { /* Copy offsets for distance codes 0..29 */ + 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, + 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, + 8193, 12289, 16385, 24577}; +static ush cpdext[] = { /* Extra bits for distance codes */ + 0, 0, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, + 7, 7, 8, 8, 9, 9, 10, 10, 11, 11, + 12, 12, 13, 13}; + + + +/* Macros for inflate() bit peeking and grabbing. + The usage is: + + NEEDBITS(j) + x = b & mask_bits[j]; + DUMPBITS(j) + + where NEEDBITS makes sure that b has at least j bits in it, and + DUMPBITS removes the bits from b. The macros use the variable k + for the number of bits in b. Normally, b and k are register + variables for speed, and are initialized at the beginning of a + routine that uses these macros from a global bit buffer and count. + + If we assume that EOB will be the longest code, then we will never + ask for bits with NEEDBITS that are beyond the end of the stream. + So, NEEDBITS should not read any more bytes than are needed to + meet the request. Then no bytes need to be "returned" to the buffer + at the end of the last block. + + However, this assumption is not true for fixed blocks--the EOB code + is 7 bits, but the other literal/length codes can be 8 or 9 bits. + (The EOB code is shorter than other codes because fixed blocks are + generally short. So, while a block always has an EOB, many other + literal/length codes have a significantly lower probability of + showing up at all.) However, by making the first table have a + lookup of seven bits, the EOB code will be found in that first + lookup, and so will not require that too many bits be pulled from + the stream. + */ + +ulg bb; /* bit buffer */ +unsigned bk; /* bits in bit buffer */ + +ush mask_bits[] = { + 0x0000, + 0x0001, 0x0003, 0x0007, 0x000f, 0x001f, 0x003f, 0x007f, 0x00ff, + 0x01ff, 0x03ff, 0x07ff, 0x0fff, 0x1fff, 0x3fff, 0x7fff, 0xffff +}; + +#ifdef CRYPT + uch cc; +# define NEXTBYTE() \ + (decrypt ? (cc = get_byte(), zdecode(cc), cc) : get_byte()) +#else +# define NEXTBYTE() (uch)get_byte() +#endif +#define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE())<<k;k+=8;}} +#define DUMPBITS(n) {b>>=(n);k-=(n);} + + +/* + Huffman code decoding is performed using a multi-level table lookup. + The fastest way to decode is to simply build a lookup table whose + size is determined by the longest code. However, the time it takes + to build this table can also be a factor if the data being decoded + is not very long. The most common codes are necessarily the + shortest codes, so those codes dominate the decoding time, and hence + the speed. The idea is you can have a shorter table that decodes the + shorter, more probable codes, and then point to subsidiary tables for + the longer codes. The time it costs to decode the longer codes is + then traded against the time it takes to make longer tables. + + This results of this trade are in the variables lbits and dbits + below. lbits is the number of bits the first level table for literal/ + length codes can decode in one step, and dbits is the same thing for + the distance codes. Subsequent tables are also less than or equal to + those sizes. These values may be adjusted either when all of the + codes are shorter than that, in which case the longest code length in + bits is used, or when the shortest code is *longer* than the requested + table size, in which case the length of the shortest code in bits is + used. + + There are two different values for the two tables, since they code a + different number of possibilities each. The literal/length table + codes 286 possible values, or in a flat code, a little over eight + bits. The distance table codes 30 possible values, or a little less + than five bits, flat. The optimum values for speed end up being + about one bit more than those, so lbits is 8+1 and dbits is 5+1. + The optimum values may differ though from machine to machine, and + possibly even between compilers. Your mileage may vary. + */ + + +int lbits = 9; /* bits in base literal/length lookup table */ +int dbits = 6; /* bits in base distance lookup table */ + + +/* If BMAX needs to be larger than 16, then h and x[] should be ulg. */ +#define BMAX 16 /* maximum bit length of any code (16 for explode) */ +#define N_MAX 288 /* maximum number of codes in any set */ + + +unsigned hufts; /* track memory usage */ + + +int huft_build(b, n, s, d, e, t, m) +unsigned *b; /* code lengths in bits (all assumed <= BMAX) */ +unsigned n; /* number of codes (assumed <= N_MAX) */ +unsigned s; /* number of simple-valued codes (0..s-1) */ +ush *d; /* list of base values for non-simple codes */ +ush *e; /* list of extra bits for non-simple codes */ +struct huft **t; /* result: starting table */ +int *m; /* maximum lookup bits, returns actual */ +/* Given a list of code lengths and a maximum table size, make a set of + tables to decode that set of codes. Return zero on success, one if + the given code set is incomplete (the tables are still built in this + case), two if the input is invalid (all zero length codes or an + oversubscribed set of lengths), and three if not enough memory. */ +{ + unsigned a; /* counter for codes of length k */ + unsigned c[BMAX+1]; /* bit length count table */ + unsigned f; /* i repeats in table every f entries */ + int g; /* maximum code length */ + int h; /* table level */ + register unsigned i; /* counter, current code */ + register unsigned j; /* counter */ + register int k; /* number of bits in current code */ + int l; /* bits per table (returned in m) */ + register unsigned *p; /* pointer into c[], b[], or v[] */ + register struct huft *q; /* points to current table */ + struct huft r; /* table entry for structure assignment */ + struct huft *u[BMAX]; /* table stack */ + unsigned v[N_MAX]; /* values in order of bit length */ + register int w; /* bits before this table == (l * h) */ + unsigned x[BMAX+1]; /* bit offsets, then code stack */ + unsigned *xp; /* pointer into x */ + int y; /* number of dummy codes added */ + unsigned z; /* number of entries in current table */ + + + /* Generate counts for each bit length */ + memzero(c, sizeof(c)); + p = b; i = n; + do { + Tracecv(*p, (stderr, (n-i >= ' ' && n-i <= '~' ? "%c %d\n" : "0x%x %d\n"), + n-i, *p)); + c[*p]++; /* assume all entries <= BMAX */ + p++; /* Can't combine with above line (Solaris bug) */ + } while (--i); + if (c[0] == n) /* null input--all zero length codes */ + { + *t = (struct huft *)NULL; + *m = 0; + return 0; + } + + + /* Find minimum and maximum length, bound *m by those */ + l = *m; + for (j = 1; j <= BMAX; j++) + if (c[j]) + break; + k = j; /* minimum code length */ + if ((unsigned)l < j) + l = j; + for (i = BMAX; i; i--) + if (c[i]) + break; + g = i; /* maximum code length */ + if ((unsigned)l > i) + l = i; + *m = l; + + + /* Adjust last length count to fill out codes, if needed */ + for (y = 1 << j; j < i; j++, y <<= 1) + if ((y -= c[j]) < 0) + return 2; /* bad input: more codes than bits */ + if ((y -= c[i]) < 0) + return 2; + c[i] += y; + + + /* Generate starting offsets into the value table for each length */ + x[1] = j = 0; + p = c + 1; xp = x + 2; + while (--i) { /* note that i == g from above */ + *xp++ = (j += *p++); + } + + + /* Make a table of values in order of bit lengths */ + p = b; i = 0; + do { + if ((j = *p++) != 0) + v[x[j]++] = i; + } while (++i < n); + n = x[g]; /* set n to length of v */ + + + /* Generate the Huffman codes and for each, make the table entries */ + x[0] = i = 0; /* first Huffman code is zero */ + p = v; /* grab values in bit order */ + h = -1; /* no tables yet--level -1 */ + w = -l; /* bits decoded == (l * h) */ + u[0] = (struct huft *)NULL; /* just to keep compilers happy */ + q = (struct huft *)NULL; /* ditto */ + z = 0; /* ditto */ + + /* go through the bit lengths (k already is bits in shortest code) */ + for (; k <= g; k++) + { + a = c[k]; + while (a--) + { + /* here i is the Huffman code of length k bits for value *p */ + /* make tables up to required level */ + while (k > w + l) + { + h++; + w += l; /* previous table always l bits */ + + /* compute minimum size table less than or equal to l bits */ + z = (z = g - w) > (unsigned)l ? l : z; /* upper limit on table size */ + if ((f = 1 << (j = k - w)) > a + 1) /* try a k-w bit table */ + { /* too few codes for k-w bit table */ + f -= a + 1; /* deduct codes from patterns left */ + xp = c + k; + if (j < z) + while (++j < z) /* try smaller tables up to z bits */ + { + if ((f <<= 1) <= *++xp) + break; /* enough codes to use up j bits */ + f -= *xp; /* else deduct codes from patterns */ + } + } + z = 1 << j; /* table entries for j-bit table */ + + /* allocate and link in new table */ + if ((q = (struct huft *)malloc((z + 1)*sizeof(struct huft))) == + (struct huft *)NULL) + { + if (h) + huft_free(u[0]); + return 3; /* not enough memory */ + } + hufts += z + 1; /* track memory usage */ + *t = q + 1; /* link to list for huft_free() */ + *(t = &(q->v.t)) = (struct huft *)NULL; + u[h] = ++q; /* table starts after link */ + + /* connect to last table, if there is one */ + if (h) + { + x[h] = i; /* save pattern for backing up */ + r.b = (uch)l; /* bits to dump before this table */ + r.e = (uch)(16 + j); /* bits in this table */ + r.v.t = q; /* pointer to this table */ + j = i >> (w - l); /* (get around Turbo C bug) */ + u[h-1][j] = r; /* connect to last table */ + } + } + + /* set up table entry in r */ + r.b = (uch)(k - w); + if (p >= v + n) + r.e = 99; /* out of values--invalid code */ + else if (*p < s) + { + r.e = (uch)(*p < 256 ? 16 : 15); /* 256 is end-of-block code */ + r.v.n = (ush)(*p); /* simple code is just the value */ + p++; /* one compiler does not like *p++ */ + } + else + { + r.e = (uch)e[*p - s]; /* non-simple--look up in lists */ + r.v.n = d[*p++ - s]; + } + + /* fill code-like entries with r */ + f = 1 << (k - w); + for (j = i >> w; j < z; j += f) + q[j] = r; + + /* backwards increment the k-bit code i */ + for (j = 1 << (k - 1); i & j; j >>= 1) + i ^= j; + i ^= j; + + /* backup over finished tables */ + while ((i & ((1 << w) - 1)) != x[h]) + { + h--; /* don't need to update q */ + w -= l; + } + } + } + + + /* Return true (1) if we were given an incomplete table */ + return y != 0 && g != 1; +} + + + +int huft_free(t) +struct huft *t; /* table to free */ +/* Free the malloc'ed tables built by huft_build(), which makes a linked + list of the tables it made, with the links in a dummy first entry of + each table. */ +{ + register struct huft *p, *q; + + + /* Go through linked list, freeing from the malloced (t[-1]) address. */ + p = t; + while (p != (struct huft *)NULL) + { + q = (--p)->v.t; + free((char*)p); + p = q; + } + return 0; +} + + +int inflate_codes(tl, td, bl, bd) +struct huft *tl, *td; /* literal/length and distance decoder tables */ +int bl, bd; /* number of bits decoded by tl[] and td[] */ +/* inflate (decompress) the codes in a deflated (compressed) block. + Return an error code or zero if it all goes ok. */ +{ + register unsigned e; /* table entry flag/number of extra bits */ + unsigned n, d; /* length and index for copy */ + unsigned w; /* current window position */ + struct huft *t; /* pointer to table entry */ + unsigned ml, md; /* masks for bl and bd bits */ + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + + /* make local copies of globals */ + b = bb; /* initialize bit buffer */ + k = bk; + w = wp; /* initialize window position */ + + /* inflate the coded data */ + ml = mask_bits[bl]; /* precompute masks for speed */ + md = mask_bits[bd]; + for (;;) /* do until end of block */ + { + NEEDBITS((unsigned)bl) + if ((e = (t = tl + ((unsigned)b & ml))->e) > 16) + do { + if (e == 99) + return 1; + DUMPBITS(t->b) + e -= 16; + NEEDBITS(e) + } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16); + DUMPBITS(t->b) + if (e == 16) /* then it's a literal */ + { + slide[w++] = (uch)t->v.n; + Tracevv((stderr, "%c", slide[w-1])); + if (w == WSIZE) + { + flush_output(w); + w = 0; + } + } + else /* it's an EOB or a length */ + { + /* exit if end of block */ + if (e == 15) + break; + + /* get length of block to copy */ + NEEDBITS(e) + n = t->v.n + ((unsigned)b & mask_bits[e]); + DUMPBITS(e); + + /* decode distance of block to copy */ + NEEDBITS((unsigned)bd) + if ((e = (t = td + ((unsigned)b & md))->e) > 16) + do { + if (e == 99) + return 1; + DUMPBITS(t->b) + e -= 16; + NEEDBITS(e) + } while ((e = (t = t->v.t + ((unsigned)b & mask_bits[e]))->e) > 16); + DUMPBITS(t->b) + NEEDBITS(e) + d = w - t->v.n - ((unsigned)b & mask_bits[e]); + DUMPBITS(e) + Tracevv((stderr,"\\[%d,%d]", w-d, n)); + + /* do the copy */ + do { + n -= (e = (e = WSIZE - ((d &= WSIZE-1) > w ? d : w)) > n ? n : e); +#if !defined(NOMEMCPY) && !defined(DEBUG) + if (w - d >= e) /* (this test assumes unsigned comparison) */ + { + memcpy(slide + w, slide + d, e); + w += e; + d += e; + } + else /* do it slow to avoid memcpy() overlap */ +#endif /* !NOMEMCPY */ + do { + slide[w++] = slide[d++]; + Tracevv((stderr, "%c", slide[w-1])); + } while (--e); + if (w == WSIZE) + { + flush_output(w); + w = 0; + } + } while (n); + } + } + + + /* restore the globals from the locals */ + wp = w; /* restore global window pointer */ + bb = b; /* restore global bit buffer */ + bk = k; + + /* done */ + return 0; +} + + + +int inflate_stored() +/* "decompress" an inflated type 0 (stored) block. */ +{ + unsigned n; /* number of bytes in block */ + unsigned w; /* current window position */ + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + + /* make local copies of globals */ + b = bb; /* initialize bit buffer */ + k = bk; + w = wp; /* initialize window position */ + + + /* go to byte boundary */ + n = k & 7; + DUMPBITS(n); + + + /* get the length and its complement */ + NEEDBITS(16) + n = ((unsigned)b & 0xffff); + DUMPBITS(16) + NEEDBITS(16) + if (n != (unsigned)((~b) & 0xffff)) + return 1; /* error in compressed data */ + DUMPBITS(16) + + + /* read and output the compressed data */ + while (n--) + { + NEEDBITS(8) + slide[w++] = (uch)b; + if (w == WSIZE) + { + flush_output(w); + w = 0; + } + DUMPBITS(8) + } + + + /* restore the globals from the locals */ + wp = w; /* restore global window pointer */ + bb = b; /* restore global bit buffer */ + bk = k; + return 0; +} + + + +int inflate_fixed() +/* decompress an inflated type 1 (fixed Huffman codes) block. We should + either replace this with a custom decoder, or at least precompute the + Huffman tables. */ +{ + int i; /* temporary variable */ + struct huft *tl; /* literal/length code table */ + struct huft *td; /* distance code table */ + int bl; /* lookup bits for tl */ + int bd; /* lookup bits for td */ + unsigned l[288]; /* length list for huft_build */ + + + /* set up literal table */ + for (i = 0; i < 144; i++) + l[i] = 8; + for (; i < 256; i++) + l[i] = 9; + for (; i < 280; i++) + l[i] = 7; + for (; i < 288; i++) /* make a complete, but wrong code set */ + l[i] = 8; + bl = 7; + if ((i = huft_build(l, 288, 257, cplens, cplext, &tl, &bl)) != 0) + return i; + + + /* set up distance table */ + for (i = 0; i < 30; i++) /* make an incomplete code set */ + l[i] = 5; + bd = 5; + if ((i = huft_build(l, 30, 0, cpdist, cpdext, &td, &bd)) > 1) + { + huft_free(tl); + return i; + } + + + /* decompress until an end-of-block code */ + if (inflate_codes(tl, td, bl, bd)) + return 1; + + + /* free the decoding tables, return */ + huft_free(tl); + huft_free(td); + return 0; +} + + + +int inflate_dynamic() +/* decompress an inflated type 2 (dynamic Huffman codes) block. */ +{ + int i; /* temporary variables */ + unsigned j; + unsigned l; /* last length */ + unsigned m; /* mask for bit lengths table */ + unsigned n; /* number of lengths to get */ + struct huft *tl; /* literal/length code table */ + struct huft *td; /* distance code table */ + int bl; /* lookup bits for tl */ + int bd; /* lookup bits for td */ + unsigned nb; /* number of bit length codes */ + unsigned nl; /* number of literal/length codes */ + unsigned nd; /* number of distance codes */ +#ifdef PKZIP_BUG_WORKAROUND + unsigned ll[288+32]; /* literal/length and distance code lengths */ +#else + unsigned ll[286+30]; /* literal/length and distance code lengths */ +#endif + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + + /* make local bit buffer */ + b = bb; + k = bk; + + + /* read in table lengths */ + NEEDBITS(5) + nl = 257 + ((unsigned)b & 0x1f); /* number of literal/length codes */ + DUMPBITS(5) + NEEDBITS(5) + nd = 1 + ((unsigned)b & 0x1f); /* number of distance codes */ + DUMPBITS(5) + NEEDBITS(4) + nb = 4 + ((unsigned)b & 0xf); /* number of bit length codes */ + DUMPBITS(4) +#ifdef PKZIP_BUG_WORKAROUND + if (nl > 288 || nd > 32) +#else + if (nl > 286 || nd > 30) +#endif + return 1; /* bad lengths */ + + + /* read in bit-length-code lengths */ + for (j = 0; j < nb; j++) + { + NEEDBITS(3) + ll[border[j]] = (unsigned)b & 7; + DUMPBITS(3) + } + for (; j < 19; j++) + ll[border[j]] = 0; + + + /* build decoding table for trees--single level, 7 bit lookup */ + bl = 7; + if ((i = huft_build(ll, 19, 19, NULL, NULL, &tl, &bl)) != 0) + { + if (i == 1) + huft_free(tl); + return i; /* incomplete code set */ + } + + if (tl == NULL) /* Grrrhhh */ + return 2; + + /* read in literal and distance code lengths */ + n = nl + nd; + m = mask_bits[bl]; + i = l = 0; + while ((unsigned)i < n) + { + NEEDBITS((unsigned)bl) + j = (td = tl + ((unsigned)b & m))->b; + DUMPBITS(j) + j = td->v.n; + if (j < 16) /* length of code in bits (0..15) */ + ll[i++] = l = j; /* save last length in l */ + else if (j == 16) /* repeat last length 3 to 6 times */ + { + NEEDBITS(2) + j = 3 + ((unsigned)b & 3); + DUMPBITS(2) + if ((unsigned)i + j > n) + return 1; + while (j--) + ll[i++] = l; + } + else if (j == 17) /* 3 to 10 zero length codes */ + { + NEEDBITS(3) + j = 3 + ((unsigned)b & 7); + DUMPBITS(3) + if ((unsigned)i + j > n) + return 1; + while (j--) + ll[i++] = 0; + l = 0; + } + else /* j == 18: 11 to 138 zero length codes */ + { + NEEDBITS(7) + j = 11 + ((unsigned)b & 0x7f); + DUMPBITS(7) + if ((unsigned)i + j > n) + return 1; + while (j--) + ll[i++] = 0; + l = 0; + } + } + + + /* free decoding table for trees */ + huft_free(tl); + + + /* restore the global bit buffer */ + bb = b; + bk = k; + + + /* build the decoding tables for literal/length and distance codes */ + bl = lbits; + if ((i = huft_build(ll, nl, 257, cplens, cplext, &tl, &bl)) != 0) + { + if (i == 1) { + fprintf(stderr, " incomplete literal tree\n"); + huft_free(tl); + } + return i; /* incomplete code set */ + } + bd = dbits; + if ((i = huft_build(ll + nl, nd, 0, cpdist, cpdext, &td, &bd)) != 0) + { + if (i == 1) { + fprintf(stderr, " incomplete distance tree\n"); +#ifdef PKZIP_BUG_WORKAROUND + i = 0; + } +#else + huft_free(td); + } + huft_free(tl); + return i; /* incomplete code set */ +#endif + } + + + /* decompress until an end-of-block code */ + if (inflate_codes(tl, td, bl, bd)) + return 1; + + + /* free the decoding tables, return */ + huft_free(tl); + huft_free(td); + return 0; +} + + + +int inflate_block(e) +int *e; /* last block flag */ +/* decompress an inflated block */ +{ + unsigned t; /* block type */ + register ulg b; /* bit buffer */ + register unsigned k; /* number of bits in bit buffer */ + + + /* make local bit buffer */ + b = bb; + k = bk; + + + /* read in last block bit */ + NEEDBITS(1) + *e = (int)b & 1; + DUMPBITS(1) + + + /* read in block type */ + NEEDBITS(2) + t = (unsigned)b & 3; + DUMPBITS(2) + + + /* restore the global bit buffer */ + bb = b; + bk = k; + + + /* inflate that block type */ + if (t == 2) + return inflate_dynamic(); + if (t == 0) + return inflate_stored(); + if (t == 1) + return inflate_fixed(); + + + /* bad block type */ + return 2; +} + + + +int inflate() +/* decompress an inflated entry */ +{ + int e; /* last block flag */ + int r; /* result code */ + unsigned h; /* maximum struct huft's malloc'ed */ + + + /* initialize window, bit buffer */ + wp = 0; + bk = 0; + bb = 0; + + + /* decompress until the last block */ + h = 0; + do { + hufts = 0; + if ((r = inflate_block(&e)) != 0) + return r; + if (hufts > h) + h = hufts; + } while (!e); + + /* Undo too much lookahead. The next read will be byte aligned so we + * can discard unused bits in the last meaningful byte. + */ + while (bk >= 8) { + bk -= 8; + inptr--; + } + + /* flush out slide */ + flush_output(wp); + + + /* return success */ +#ifdef DEBUG + fprintf(stderr, "<%u> ", h); +#endif /* DEBUG */ + return 0; +} diff --git a/isys/gzlib/lzw.c b/isys/gzlib/lzw.c new file mode 100644 index 000000000..0dc2fe063 --- /dev/null +++ b/isys/gzlib/lzw.c @@ -0,0 +1,27 @@ +/* lzw.c -- compress files in LZW format. + * This is a dummy version avoiding patent problems. + */ + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +#include <config.h> +#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/isys/gzlib/lzw.h b/isys/gzlib/lzw.h new file mode 100644 index 000000000..4b7ac8680 --- /dev/null +++ b/isys/gzlib/lzw.h @@ -0,0 +1,42 @@ +/* lzw.h -- define the lzw functions. + * 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. + */ + +#if !defined(OF) && defined(lint) +# include "gzip.h" +#endif + +#ifndef BITS +# define BITS 16 +#endif +#define INIT_BITS 9 /* Initial number of bits per code */ + +#define LZW_MAGIC "\037\235" /* Magic header for lzw files, 1F 9D */ + +#define BIT_MASK 0x1f /* Mask for 'number of compression bits' */ +/* Mask 0x20 is reserved to mean a fourth header byte, and 0x40 is free. + * It's a pity that old uncompress does not check bit 0x20. That makes + * extension of the format actually undesirable because old compress + * would just crash on the new format instead of giving a meaningful + * error message. It does check the number of bits, but it's more + * helpful to say "unsupported format, get a new version" than + * "can only handle 16 bits". + */ + +#define BLOCK_MODE 0x80 +/* Block compression: if table is full and compression rate is dropping, + * clear the dictionary. + */ + +#define LZW_RESERVED 0x60 /* reserved bits */ + +#define CLEAR 256 /* flush the dictionary */ +#define FIRST (CLEAR+1) /* first free entry */ + +extern int maxbits; /* max bits per code for LZW */ +extern int block_mode; /* block compress mode -C compatible with 2.0 */ + +extern int lzw OF((int in, int out)); +extern int unlzw OF((int in, int out)); diff --git a/isys/gzlib/tailor.h b/isys/gzlib/tailor.h new file mode 100644 index 000000000..3e45e12c1 --- /dev/null +++ b/isys/gzlib/tailor.h @@ -0,0 +1,315 @@ +/* tailor.h -- target dependent definitions + * 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 target dependent definitions should be defined here only. + * The target dependent functions should be defined in tailor.c. + */ + +/* $Id$ */ + +#if defined(__MSDOS__) && !defined(MSDOS) +# define MSDOS +#endif + +#if defined(__OS2__) && !defined(OS2) +# define OS2 +#endif + +#if defined(OS2) && defined(MSDOS) /* MS C under OS/2 */ +# undef MSDOS +#endif + +#ifdef MSDOS +# ifdef __GNUC__ + /* DJGPP version 1.09+ on MS-DOS. + * The DJGPP 1.09 stat() function must be upgraded before gzip will + * fully work. + * No need for HAVE_DIRENT_H, since <unistd.h> defines POSIX_SOURCE which + * implies HAVE_DIRENT_H. + */ +# define near +# else +# define MAXSEG_64K +# ifdef __TURBOC__ +# define off_t long +# ifdef __BORLANDC__ +# define HAVE_DIRENT_H +# define HAVE_UTIME +# endif +# define HAVE_UTIME_H +# else /* MSC */ +# define HAVE_SYS_UTIME_H +# endif +# endif +# define PATH_SEP2 '\\' +# define PATH_SEP3 ':' +# define MAX_PATH_LEN 128 +# define NO_MULTIPLE_DOTS +# define MAX_EXT_CHARS 3 +# define Z_SUFFIX "z" +# define PROTO +# define STDC_HEADERS +# define NO_SIZE_CHECK +# define UNLINK_READONLY_BUG +# define casemap(c) tolow(c) /* Force file names to lower case */ +# include <io.h> +# define OS_CODE 0x00 +# define SET_BINARY_MODE(fd) setmode(fd, O_BINARY) +# if !defined(NO_ASM) && !defined(ASMV) +# define ASMV +# endif +#else +# define near +#endif + +#ifdef OS2 +# define PATH_SEP2 '\\' +# define PATH_SEP3 ':' +# define MAX_PATH_LEN 260 +# ifdef OS2FAT +# define NO_MULTIPLE_DOTS +# define MAX_EXT_CHARS 3 +# define Z_SUFFIX "z" +# define casemap(c) tolow(c) +# endif +# define PROTO +# define STDC_HEADERS +# define UNLINK_READONLY_BUG +# include <io.h> +# define OS_CODE 0x06 +# define SET_BINARY_MODE(fd) setmode(fd, O_BINARY) +# ifdef _MSC_VER +# define HAVE_SYS_UTIME_H +# define MAXSEG_64K +# undef near +# define near _near +# endif +# ifdef __EMX__ +# define HAVE_SYS_UTIME_H +# define HAVE_DIRENT_H +# define EXPAND(argc,argv) \ + {_response(&argc, &argv); _wildcard(&argc, &argv);} +# endif +# ifdef __BORLANDC__ +# define HAVE_DIRENT_H +# define HAVE_UTIME_H +# endif +# ifdef __ZTC__ +# define NO_DIR +# include <dos.h> +# define EXPAND(argc,argv) \ + {response_expand(&argc, &argv);} +# endif +#endif + +#ifdef WIN32 /* Windows NT */ +# define HAVE_SYS_UTIME_H +# define PATH_SEP2 '\\' +# define PATH_SEP3 ':' +# define MAX_PATH_LEN 260 +# define PROTO +# define STDC_HEADERS +# define SET_BINARY_MODE(fd) setmode(fd, O_BINARY) +# define UNLINK_READONLY_BUG +# include <io.h> +# include <malloc.h> +# ifdef NTFAT +# define NO_MULTIPLE_DOTS +# define MAX_EXT_CHARS 3 +# define Z_SUFFIX "z" +# define casemap(c) tolow(c) /* Force file names to lower case */ +# endif +# define OS_CODE 0x0b +#endif + +#ifdef MSDOS +# ifdef __TURBOC__ +# include <alloc.h> +# define DYN_ALLOC + /* Turbo C 2.0 does not accept static allocations of large arrays */ + void * fcalloc (unsigned items, unsigned size); + void fcfree (void *ptr); +# else /* MSC */ +# include <malloc.h> +# define fcalloc(nitems,itemsize) halloc((long)(nitems),(itemsize)) +# define fcfree(ptr) hfree(ptr) +# endif +#else +# ifdef MAXSEG_64K +# define fcalloc(items,size) calloc((items),(size)) +# else +# define fcalloc(items,size) malloc((size_t)(items)*(size_t)(size)) +# endif +# define fcfree(ptr) free(ptr) +#endif + +#if defined(VAXC) || defined(VMS) +# define PATH_SEP ']' +# define PATH_SEP2 ':' +# define SUFFIX_SEP ';' +# define NO_MULTIPLE_DOTS +# define Z_SUFFIX "-gz" +# define RECORD_IO 1 +# define casemap(c) tolow(c) +# define OS_CODE 0x02 +# define OPTIONS_VAR "GZIP_OPT" +# define STDC_HEADERS +# define EXPAND(argc,argv) vms_expand_args(&argc,&argv); +# include <file.h> +# define unlink delete +# ifdef VAXC +# include <unixio.h> +# else +# define HAVE_FCNTL_H +# endif +#endif + +#ifdef AMIGA +# define PATH_SEP2 ':' +# define STDC_HEADERS +# define OS_CODE 0x01 +# define ASMV +# ifdef __GNUC__ +# define HAVE_DIRENT_H +# define HAVE_FCNTL_H +# define HAVE_UNISTD_H +# define HAVE_CHOWN +# define HAVE_LSTAT +# else /* SASC */ +# define NO_STDIN_FSTAT +# define HAVE_SYS_DIR_H +# include <fcntl.h> /* for read() and write() */ +# define direct dirent + extern void _expand_args(int *argc, char ***argv); +# define EXPAND(argc,argv) _expand_args(&argc,&argv); +# undef O_BINARY /* disable useless --ascii option */ +# endif +#endif + +#if defined(ATARI) || defined(atarist) +# ifndef STDC_HEADERS +# define STDC_HEADERS +# define HAVE_UNISTD_H +# define HAVE_DIRENT_H +# endif +# define ASMV +# define OS_CODE 0x05 +# ifdef TOSFS +# define PATH_SEP2 '\\' +# define PATH_SEP3 ':' +# define MAX_PATH_LEN 128 +# define NO_MULTIPLE_DOTS +# define MAX_EXT_CHARS 3 +# define Z_SUFFIX "z" +# define casemap(c) tolow(c) /* Force file names to lower case */ +# endif +#endif + +#ifdef MACOS +# define PATH_SEP ':' +# define DYN_ALLOC +# define PROTO +# define NO_STDIN_FSTAT +# define chmod(file, mode) (0) +# define OPEN(name, flags, mode) open(name, flags) +# define OS_CODE 0x07 +# ifdef MPW +# define isatty(fd) ((fd) <= 2) +# endif +#endif + +#ifdef __50SERIES /* Prime/PRIMOS */ +# define PATH_SEP '>' +# define STDC_HEADERS +# define NO_STDIN_FSTAT +# define NO_SIZE_CHECK +# define RECORD_IO 1 +# define casemap(c) tolow(c) /* Force file names to lower case */ +# define put_char(c) put_byte((c) & 0x7F) +# define get_char(c) ascii2pascii(get_byte()) +# define OS_CODE 0x0F /* temporary, subject to change */ +# ifdef SIGTERM +# undef SIGTERM /* We don't want a signal handler for SIGTERM */ +# endif +#endif + +#if defined(pyr) && !defined(NOMEMCPY) /* Pyramid */ +# define NOMEMCPY /* problem with overlapping copies */ +#endif + +#ifdef TOPS20 +# define OS_CODE 0x0a +#endif + +#ifndef unix +# define NO_ST_INO /* don't rely on inode numbers */ +#endif + + + /* Common defaults */ + +#ifndef OS_CODE +# define OS_CODE 0x03 /* assume Unix */ +#endif + +#ifndef PATH_SEP +# define PATH_SEP '/' +#endif + +#ifndef casemap +# define casemap(c) (c) +#endif + +#ifndef OPTIONS_VAR +# define OPTIONS_VAR "GZIP" +#endif + +#ifndef Z_SUFFIX +# define Z_SUFFIX ".gz" +#endif + +#ifdef MAX_EXT_CHARS +# define MAX_SUFFIX MAX_EXT_CHARS +#else +# define MAX_SUFFIX 30 +#endif + +#ifndef MAKE_LEGAL_NAME +# ifdef NO_MULTIPLE_DOTS +# define MAKE_LEGAL_NAME(name) make_simple_name(name) +# else +# define MAKE_LEGAL_NAME(name) +# endif +#endif + +#ifndef MIN_PART +# define MIN_PART 3 + /* keep at least MIN_PART chars between dots in a file name. */ +#endif + +#ifndef EXPAND +# define EXPAND(argc,argv) +#endif + +#ifndef RECORD_IO +# define RECORD_IO 0 +#endif + +#ifndef SET_BINARY_MODE +# define SET_BINARY_MODE(fd) +#endif + +#ifndef OPEN +# define OPEN(name, flags, mode) open(name, flags, mode) +#endif + +#ifndef get_char +# define get_char() get_byte() +#endif + +#ifndef put_char +# define put_char(c) put_byte(c) +#endif diff --git a/isys/gzlib/trees.c b/isys/gzlib/trees.c new file mode 100644 index 000000000..71659a5ac --- /dev/null +++ b/isys/gzlib/trees.c @@ -0,0 +1,1069 @@ +/* trees.c -- output deflated data using Huffman coding + * 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 + * + * Encode various sets of source values using variable-length + * binary code trees. + * + * DISCUSSION + * + * The PKZIP "deflation" process uses several Huffman trees. The more + * common source values are represented by shorter bit sequences. + * + * Each code tree is stored in the ZIP file in a compressed form + * which is itself a Huffman encoding of the lengths of + * all the code strings (in ascending order by source values). + * The actual code strings are reconstructed from the lengths in + * the UNZIP process, as described in the "application note" + * (APPNOTE.TXT) distributed as part of PKWARE's PKZIP program. + * + * REFERENCES + * + * Lynch, Thomas J. + * Data Compression: Techniques and Applications, pp. 53-55. + * Lifetime Learning Publications, 1985. ISBN 0-534-03418-7. + * + * Storer, James A. + * Data Compression: Methods and Theory, pp. 49-50. + * Computer Science Press, 1988. ISBN 0-7167-8156-5. + * + * Sedgewick, R. + * Algorithms, p290. + * Addison-Wesley, 1983. ISBN 0-201-06672-6. + * + * INTERFACE + * + * void ct_init (ush *attr, int *methodp) + * Allocate the match buffer, initialize the various tables and save + * the location of the internal file attribute (ascii/binary) and + * method (DEFLATE/STORE) + * + * void ct_tally (int dist, int lc); + * Save the match info and tally the frequency counts. + * + * off_t flush_block (char *buf, ulg stored_len, int eof) + * Determine the best encoding for the current block: dynamic trees, + * static trees or store, and output the encoded block to the zip + * file. Returns the total compressed length for the file so far. + * + */ + +#include <config.h> +#include <ctype.h> + +#include "tailor.h" +#include "gzip.h" + +#ifdef RCSID +static char rcsid[] = "$Id$"; +#endif + +/* =========================================================================== + * Constants + */ + +#define MAX_BITS 15 +/* All codes must not exceed MAX_BITS bits */ + +#define MAX_BL_BITS 7 +/* Bit length codes must not exceed MAX_BL_BITS bits */ + +#define LENGTH_CODES 29 +/* number of length codes, not counting the special END_BLOCK code */ + +#define LITERALS 256 +/* number of literal bytes 0..255 */ + +#define END_BLOCK 256 +/* end of block literal code */ + +#define L_CODES (LITERALS+1+LENGTH_CODES) +/* number of Literal or Length codes, including the END_BLOCK code */ + +#define D_CODES 30 +/* number of distance codes */ + +#define BL_CODES 19 +/* number of codes used to transfer the bit lengths */ + + +local int near extra_lbits[LENGTH_CODES] /* extra bits for each length code */ + = {0,0,0,0,0,0,0,0,1,1,1,1,2,2,2,2,3,3,3,3,4,4,4,4,5,5,5,5,0}; + +local int near extra_dbits[D_CODES] /* extra bits for each distance code */ + = {0,0,0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7,8,8,9,9,10,10,11,11,12,12,13,13}; + +local int near extra_blbits[BL_CODES]/* extra bits for each bit length code */ + = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2,3,7}; + +#define STORED_BLOCK 0 +#define STATIC_TREES 1 +#define DYN_TREES 2 +/* The three kinds of block type */ + +#ifndef LIT_BUFSIZE +# ifdef SMALL_MEM +# define LIT_BUFSIZE 0x2000 +# else +# ifdef MEDIUM_MEM +# define LIT_BUFSIZE 0x4000 +# else +# define LIT_BUFSIZE 0x8000 +# endif +# endif +#endif +#ifndef DIST_BUFSIZE +# define DIST_BUFSIZE LIT_BUFSIZE +#endif +/* Sizes of match buffers for literals/lengths and distances. There are + * 4 reasons for limiting LIT_BUFSIZE to 64K: + * - frequencies can be kept in 16 bit counters + * - if compression is not successful for the first block, all input data is + * still in the window so we can still emit a stored block even when input + * comes from standard input. (This can also be done for all blocks if + * LIT_BUFSIZE is not greater than 32K.) + * - if compression is not successful for a file smaller than 64K, we can + * even emit a stored file instead of a stored block (saving 5 bytes). + * - creating new Huffman trees less frequently may not provide fast + * adaptation to changes in the input data statistics. (Take for + * example a binary file with poorly compressible code followed by + * a highly compressible string table.) Smaller buffer sizes give + * fast adaptation but have of course the overhead of transmitting trees + * more frequently. + * - I can't count above 4 + * The current code is general and allows DIST_BUFSIZE < LIT_BUFSIZE (to save + * memory at the expense of compression). Some optimizations would be possible + * if we rely on DIST_BUFSIZE == LIT_BUFSIZE. + */ +#if LIT_BUFSIZE > INBUFSIZ + error cannot overlay l_buf and inbuf +#endif + +#define REP_3_6 16 +/* repeat previous bit length 3-6 times (2 bits of repeat count) */ + +#define REPZ_3_10 17 +/* repeat a zero length 3-10 times (3 bits of repeat count) */ + +#define REPZ_11_138 18 +/* repeat a zero length 11-138 times (7 bits of repeat count) */ + +/* =========================================================================== + * Local data + */ + +/* Data structure describing a single value and its code string. */ +typedef struct ct_data { + union { + ush freq; /* frequency count */ + ush code; /* bit string */ + } fc; + union { + ush dad; /* father node in Huffman tree */ + ush len; /* length of bit string */ + } dl; +} ct_data; + +#define Freq fc.freq +#define Code fc.code +#define Dad dl.dad +#define Len dl.len + +#define HEAP_SIZE (2*L_CODES+1) +/* maximum heap size */ + +local ct_data near dyn_ltree[HEAP_SIZE]; /* literal and length tree */ +local ct_data near dyn_dtree[2*D_CODES+1]; /* distance tree */ + +local ct_data near static_ltree[L_CODES+2]; +/* The static literal tree. Since the bit lengths are imposed, there is no + * need for the L_CODES extra codes used during heap construction. However + * The codes 286 and 287 are needed to build a canonical tree (see ct_init + * below). + */ + +local ct_data near static_dtree[D_CODES]; +/* The static distance tree. (Actually a trivial tree since all codes use + * 5 bits.) + */ + +local ct_data near bl_tree[2*BL_CODES+1]; +/* Huffman tree for the bit lengths */ + +typedef struct tree_desc { + ct_data near *dyn_tree; /* the dynamic tree */ + ct_data near *static_tree; /* corresponding static tree or NULL */ + int near *extra_bits; /* extra bits for each code or NULL */ + int extra_base; /* base index for extra_bits */ + int elems; /* max number of elements in the tree */ + int max_length; /* max bit length for the codes */ + int max_code; /* largest code with non zero frequency */ +} tree_desc; + +local tree_desc near l_desc = +{dyn_ltree, static_ltree, extra_lbits, LITERALS+1, L_CODES, MAX_BITS, 0}; + +local tree_desc near d_desc = +{dyn_dtree, static_dtree, extra_dbits, 0, D_CODES, MAX_BITS, 0}; + +local tree_desc near bl_desc = +{bl_tree, (ct_data near *)0, extra_blbits, 0, BL_CODES, MAX_BL_BITS, 0}; + + +local ush near bl_count[MAX_BITS+1]; +/* number of codes at each bit length for an optimal tree */ + +local uch near bl_order[BL_CODES] + = {16,17,18,0,8,7,9,6,10,5,11,4,12,3,13,2,14,1,15}; +/* The lengths of the bit length codes are sent in order of decreasing + * probability, to avoid transmitting the lengths for unused bit length codes. + */ + +local int near heap[2*L_CODES+1]; /* heap used to build the Huffman trees */ +local int heap_len; /* number of elements in the heap */ +local int heap_max; /* element of largest frequency */ +/* The sons of heap[n] are heap[2*n] and heap[2*n+1]. heap[0] is not used. + * The same heap array is used to build all trees. + */ + +local uch near depth[2*L_CODES+1]; +/* Depth of each subtree used as tie breaker for trees of equal frequency */ + +local uch length_code[MAX_MATCH-MIN_MATCH+1]; +/* length code for each normalized match length (0 == MIN_MATCH) */ + +local uch dist_code[512]; +/* distance codes. The first 256 values correspond to the distances + * 3 .. 258, the last 256 values correspond to the top 8 bits of + * the 15 bit distances. + */ + +local int near base_length[LENGTH_CODES]; +/* First normalized length for each code (0 = MIN_MATCH) */ + +local int near base_dist[D_CODES]; +/* First normalized distance for each code (0 = distance of 1) */ + +#define l_buf inbuf +/* DECLARE(uch, l_buf, LIT_BUFSIZE); buffer for literals or lengths */ + +/* DECLARE(ush, d_buf, DIST_BUFSIZE); buffer for distances */ + +local uch near flag_buf[(LIT_BUFSIZE/8)]; +/* flag_buf is a bit array distinguishing literals from lengths in + * l_buf, thus indicating the presence or absence of a distance. + */ + +local unsigned last_lit; /* running index in l_buf */ +local unsigned last_dist; /* running index in d_buf */ +local unsigned last_flags; /* running index in flag_buf */ +local uch flags; /* current flags not yet saved in flag_buf */ +local uch flag_bit; /* current bit used in flags */ +/* bits are filled in flags starting at bit 0 (least significant). + * Note: these flags are overkill in the current code since we don't + * take advantage of DIST_BUFSIZE == LIT_BUFSIZE. + */ + +local ulg opt_len; /* bit length of current block with optimal trees */ +local ulg static_len; /* bit length of current block with static trees */ + +local off_t compressed_len; /* total bit length of compressed file */ + +local off_t input_len; /* total byte length of input file */ +/* input_len is for debugging only since we can get it by other means. */ + +ush *file_type; /* pointer to UNKNOWN, BINARY or ASCII */ +int *file_method; /* pointer to DEFLATE or STORE */ + +#ifdef DEBUG +extern off_t bits_sent; /* bit length of the compressed data */ +#endif + +extern long block_start; /* window offset of current block */ +extern unsigned near strstart; /* window offset of current string */ + +/* =========================================================================== + * Local (static) routines in this file. + */ + +local void init_block OF((void)); +local void pqdownheap OF((ct_data near *tree, int k)); +local void gen_bitlen OF((tree_desc near *desc)); +local void gen_codes OF((ct_data near *tree, int max_code)); +local void build_tree OF((tree_desc near *desc)); +local void scan_tree OF((ct_data near *tree, int max_code)); +local void send_tree OF((ct_data near *tree, int max_code)); +local int build_bl_tree OF((void)); +local void send_all_trees OF((int lcodes, int dcodes, int blcodes)); +local void compress_block OF((ct_data near *ltree, ct_data near *dtree)); +local void set_file_type OF((void)); + + +#ifndef DEBUG +# define send_code(c, tree) send_bits(tree[c].Code, tree[c].Len) + /* Send a code of the given tree. c and tree must not have side effects */ + +#else /* DEBUG */ +# define send_code(c, tree) \ + { send_bits(tree[c].Code, tree[c].Len); } +#endif + +#define d_code(dist) \ + ((dist) < 256 ? dist_code[dist] : dist_code[256+((dist)>>7)]) +/* Mapping from a distance to a distance code. dist is the distance - 1 and + * must not have side effects. dist_code[256] and dist_code[257] are never + * used. + */ + +#define MAX(a,b) (a >= b ? a : b) +/* the arguments must not have side effects */ + +/* =========================================================================== + * Allocate the match buffer, initialize the various tables and save the + * location of the internal file attribute (ascii/binary) and method + * (DEFLATE/STORE). + */ +void ct_init(attr, methodp) + ush *attr; /* pointer to internal file attribute */ + int *methodp; /* pointer to compression method */ +{ + int n; /* iterates over tree elements */ + int bits; /* bit counter */ + int length; /* length value */ + int code; /* code value */ + int dist; /* distance index */ + + file_type = attr; + file_method = methodp; + compressed_len = input_len = 0L; + + if (static_dtree[0].Len != 0) return; /* ct_init already called */ + + /* Initialize the mapping length (0..255) -> length code (0..28) */ + length = 0; + for (code = 0; code < LENGTH_CODES-1; code++) { + base_length[code] = length; + for (n = 0; n < (1<<extra_lbits[code]); n++) { + length_code[length++] = (uch)code; + } + } + Assert (length == 256, "ct_init: length != 256"); + /* Note that the length 255 (match length 258) can be represented + * in two different ways: code 284 + 5 bits or code 285, so we + * overwrite length_code[255] to use the best encoding: + */ + length_code[length-1] = (uch)code; + + /* Initialize the mapping dist (0..32K) -> dist code (0..29) */ + dist = 0; + for (code = 0 ; code < 16; code++) { + base_dist[code] = dist; + for (n = 0; n < (1<<extra_dbits[code]); n++) { + dist_code[dist++] = (uch)code; + } + } + Assert (dist == 256, "ct_init: dist != 256"); + dist >>= 7; /* from now on, all distances are divided by 128 */ + for ( ; code < D_CODES; code++) { + base_dist[code] = dist << 7; + for (n = 0; n < (1<<(extra_dbits[code]-7)); n++) { + dist_code[256 + dist++] = (uch)code; + } + } + Assert (dist == 256, "ct_init: 256+dist != 512"); + + /* Construct the codes of the static literal tree */ + for (bits = 0; bits <= MAX_BITS; bits++) bl_count[bits] = 0; + n = 0; + while (n <= 143) static_ltree[n++].Len = 8, bl_count[8]++; + while (n <= 255) static_ltree[n++].Len = 9, bl_count[9]++; + while (n <= 279) static_ltree[n++].Len = 7, bl_count[7]++; + while (n <= 287) static_ltree[n++].Len = 8, bl_count[8]++; + /* Codes 286 and 287 do not exist, but we must include them in the + * tree construction to get a canonical Huffman tree (longest code + * all ones) + */ + gen_codes((ct_data near *)static_ltree, L_CODES+1); + + /* The static distance tree is trivial: */ + for (n = 0; n < D_CODES; n++) { + static_dtree[n].Len = 5; + static_dtree[n].Code = bi_reverse(n, 5); + } + + /* Initialize the first block of the first file: */ + init_block(); +} + +/* =========================================================================== + * Initialize a new block. + */ +local void init_block() +{ + int n; /* iterates over tree elements */ + + /* Initialize the trees. */ + for (n = 0; n < L_CODES; n++) dyn_ltree[n].Freq = 0; + for (n = 0; n < D_CODES; n++) dyn_dtree[n].Freq = 0; + for (n = 0; n < BL_CODES; n++) bl_tree[n].Freq = 0; + + dyn_ltree[END_BLOCK].Freq = 1; + opt_len = static_len = 0L; + last_lit = last_dist = last_flags = 0; + flags = 0; flag_bit = 1; +} + +#define SMALLEST 1 +/* Index within the heap array of least frequent node in the Huffman tree */ + + +/* =========================================================================== + * Remove the smallest element from the heap and recreate the heap with + * one less element. Updates heap and heap_len. + */ +#define pqremove(tree, top) \ +{\ + top = heap[SMALLEST]; \ + heap[SMALLEST] = heap[heap_len--]; \ + pqdownheap(tree, SMALLEST); \ +} + +/* =========================================================================== + * Compares to subtrees, using the tree depth as tie breaker when + * the subtrees have equal frequency. This minimizes the worst case length. + */ +#define smaller(tree, n, m) \ + (tree[n].Freq < tree[m].Freq || \ + (tree[n].Freq == tree[m].Freq && depth[n] <= depth[m])) + +/* =========================================================================== + * Restore the heap property by moving down the tree starting at node k, + * exchanging a node with the smallest of its two sons if necessary, stopping + * when the heap property is re-established (each father smaller than its + * two sons). + */ +local void pqdownheap(tree, k) + ct_data near *tree; /* the tree to restore */ + int k; /* node to move down */ +{ + int v = heap[k]; + int j = k << 1; /* left son of k */ + while (j <= heap_len) { + /* Set j to the smallest of the two sons: */ + if (j < heap_len && smaller(tree, heap[j+1], heap[j])) j++; + + /* Exit if v is smaller than both sons */ + if (smaller(tree, v, heap[j])) break; + + /* Exchange v with the smallest son */ + heap[k] = heap[j]; k = j; + + /* And continue down the tree, setting j to the left son of k */ + j <<= 1; + } + heap[k] = v; +} + +/* =========================================================================== + * Compute the optimal bit lengths for a tree and update the total bit length + * for the current block. + * IN assertion: the fields freq and dad are set, heap[heap_max] and + * above are the tree nodes sorted by increasing frequency. + * OUT assertions: the field len is set to the optimal bit length, the + * array bl_count contains the frequencies for each bit length. + * The length opt_len is updated; static_len is also updated if stree is + * not null. + */ +local void gen_bitlen(desc) + tree_desc near *desc; /* the tree descriptor */ +{ + ct_data near *tree = desc->dyn_tree; + int near *extra = desc->extra_bits; + int base = desc->extra_base; + int max_code = desc->max_code; + int max_length = desc->max_length; + ct_data near *stree = desc->static_tree; + int h; /* heap index */ + int n, m; /* iterate over the tree elements */ + int bits; /* bit length */ + int xbits; /* extra bits */ + ush f; /* frequency */ + int overflow = 0; /* number of elements with bit length too large */ + + for (bits = 0; bits <= MAX_BITS; bits++) bl_count[bits] = 0; + + /* In a first pass, compute the optimal bit lengths (which may + * overflow in the case of the bit length tree). + */ + tree[heap[heap_max]].Len = 0; /* root of the heap */ + + for (h = heap_max+1; h < HEAP_SIZE; h++) { + n = heap[h]; + bits = tree[tree[n].Dad].Len + 1; + if (bits > max_length) bits = max_length, overflow++; + tree[n].Len = (ush)bits; + /* We overwrite tree[n].Dad which is no longer needed */ + + if (n > max_code) continue; /* not a leaf node */ + + bl_count[bits]++; + xbits = 0; + if (n >= base) xbits = extra[n-base]; + f = tree[n].Freq; + opt_len += (ulg)f * (bits + xbits); + if (stree) static_len += (ulg)f * (stree[n].Len + xbits); + } + if (overflow == 0) return; + + Trace((stderr,"\nbit length overflow\n")); + /* This happens for example on obj2 and pic of the Calgary corpus */ + + /* Find the first bit length which could increase: */ + do { + bits = max_length-1; + while (bl_count[bits] == 0) bits--; + bl_count[bits]--; /* move one leaf down the tree */ + bl_count[bits+1] += 2; /* move one overflow item as its brother */ + bl_count[max_length]--; + /* The brother of the overflow item also moves one step up, + * but this does not affect bl_count[max_length] + */ + overflow -= 2; + } while (overflow > 0); + + /* Now recompute all bit lengths, scanning in increasing frequency. + * h is still equal to HEAP_SIZE. (It is simpler to reconstruct all + * lengths instead of fixing only the wrong ones. This idea is taken + * from 'ar' written by Haruhiko Okumura.) + */ + for (bits = max_length; bits != 0; bits--) { + n = bl_count[bits]; + while (n != 0) { + m = heap[--h]; + if (m > max_code) continue; + if (tree[m].Len != (unsigned) bits) { + Trace((stderr,"code %d bits %d->%d\n", m, tree[m].Len, bits)); + opt_len += ((long)bits-(long)tree[m].Len)*(long)tree[m].Freq; + tree[m].Len = (ush)bits; + } + n--; + } + } +} + +/* =========================================================================== + * Generate the codes for a given tree and bit counts (which need not be + * optimal). + * IN assertion: the array bl_count contains the bit length statistics for + * the given tree and the field len is set for all tree elements. + * OUT assertion: the field code is set for all tree elements of non + * zero code length. + */ +local void gen_codes (tree, max_code) + ct_data near *tree; /* the tree to decorate */ + int max_code; /* largest code with non zero frequency */ +{ + ush next_code[MAX_BITS+1]; /* next code value for each bit length */ + ush code = 0; /* running code value */ + int bits; /* bit index */ + int n; /* code index */ + + /* The distribution counts are first used to generate the code values + * without bit reversal. + */ + for (bits = 1; bits <= MAX_BITS; bits++) { + next_code[bits] = code = (code + bl_count[bits-1]) << 1; + } + /* Check that the bit counts in bl_count are consistent. The last code + * must be all ones. + */ + Assert (code + bl_count[MAX_BITS]-1 == (1<<MAX_BITS)-1, + "inconsistent bit counts"); + Tracev((stderr,"\ngen_codes: max_code %d ", max_code)); + + for (n = 0; n <= max_code; n++) { + int len = tree[n].Len; + if (len == 0) continue; + /* Now reverse the bits */ + tree[n].Code = bi_reverse(next_code[len]++, len); + + Tracec(tree != static_ltree, (stderr,"\nn %3d %c l %2d c %4x (%x) ", + n, (isgraph(n) ? n : ' '), len, tree[n].Code, next_code[len]-1)); + } +} + +/* =========================================================================== + * Construct one Huffman tree and assigns the code bit strings and lengths. + * Update the total bit length for the current block. + * IN assertion: the field freq is set for all tree elements. + * OUT assertions: the fields len and code are set to the optimal bit length + * and corresponding code. The length opt_len is updated; static_len is + * also updated if stree is not null. The field max_code is set. + */ +local void build_tree(desc) + tree_desc near *desc; /* the tree descriptor */ +{ + ct_data near *tree = desc->dyn_tree; + ct_data near *stree = desc->static_tree; + int elems = desc->elems; + int n, m; /* iterate over heap elements */ + int max_code = -1; /* largest code with non zero frequency */ + int node = elems; /* next internal node of the tree */ + + /* Construct the initial heap, with least frequent element in + * heap[SMALLEST]. The sons of heap[n] are heap[2*n] and heap[2*n+1]. + * heap[0] is not used. + */ + heap_len = 0, heap_max = HEAP_SIZE; + + for (n = 0; n < elems; n++) { + if (tree[n].Freq != 0) { + heap[++heap_len] = max_code = n; + depth[n] = 0; + } else { + tree[n].Len = 0; + } + } + + /* The pkzip format requires that at least one distance code exists, + * and that at least one bit should be sent even if there is only one + * possible code. So to avoid special checks later on we force at least + * two codes of non zero frequency. + */ + while (heap_len < 2) { + int new = heap[++heap_len] = (max_code < 2 ? ++max_code : 0); + tree[new].Freq = 1; + depth[new] = 0; + opt_len--; if (stree) static_len -= stree[new].Len; + /* new is 0 or 1 so it does not have extra bits */ + } + desc->max_code = max_code; + + /* The elements heap[heap_len/2+1 .. heap_len] are leaves of the tree, + * establish sub-heaps of increasing lengths: + */ + for (n = heap_len/2; n >= 1; n--) pqdownheap(tree, n); + + /* Construct the Huffman tree by repeatedly combining the least two + * frequent nodes. + */ + do { + pqremove(tree, n); /* n = node of least frequency */ + m = heap[SMALLEST]; /* m = node of next least frequency */ + + heap[--heap_max] = n; /* keep the nodes sorted by frequency */ + heap[--heap_max] = m; + + /* Create a new node father of n and m */ + tree[node].Freq = tree[n].Freq + tree[m].Freq; + depth[node] = (uch) (MAX(depth[n], depth[m]) + 1); + tree[n].Dad = tree[m].Dad = (ush)node; +#ifdef DUMP_BL_TREE + if (tree == bl_tree) { + fprintf(stderr,"\nnode %d(%d), sons %d(%d) %d(%d)", + node, tree[node].Freq, n, tree[n].Freq, m, tree[m].Freq); + } +#endif + /* and insert the new node in the heap */ + heap[SMALLEST] = node++; + pqdownheap(tree, SMALLEST); + + } while (heap_len >= 2); + + heap[--heap_max] = heap[SMALLEST]; + + /* At this point, the fields freq and dad are set. We can now + * generate the bit lengths. + */ + gen_bitlen((tree_desc near *)desc); + + /* The field len is now set, we can generate the bit codes */ + gen_codes ((ct_data near *)tree, max_code); +} + +/* =========================================================================== + * Scan a literal or distance tree to determine the frequencies of the codes + * in the bit length tree. Updates opt_len to take into account the repeat + * counts. (The contribution of the bit length codes will be added later + * during the construction of bl_tree.) + */ +local void scan_tree (tree, max_code) + ct_data near *tree; /* the tree to be scanned */ + int max_code; /* and its largest code of non zero frequency */ +{ + int n; /* iterates over all tree elements */ + int prevlen = -1; /* last emitted length */ + int curlen; /* length of current code */ + int nextlen = tree[0].Len; /* length of next code */ + int count = 0; /* repeat count of the current code */ + int max_count = 7; /* max repeat count */ + int min_count = 4; /* min repeat count */ + + if (nextlen == 0) max_count = 138, min_count = 3; + tree[max_code+1].Len = (ush)0xffff; /* guard */ + + for (n = 0; n <= max_code; n++) { + curlen = nextlen; nextlen = tree[n+1].Len; + if (++count < max_count && curlen == nextlen) { + continue; + } else if (count < min_count) { + bl_tree[curlen].Freq += count; + } else if (curlen != 0) { + if (curlen != prevlen) bl_tree[curlen].Freq++; + bl_tree[REP_3_6].Freq++; + } else if (count <= 10) { + bl_tree[REPZ_3_10].Freq++; + } else { + bl_tree[REPZ_11_138].Freq++; + } + count = 0; prevlen = curlen; + if (nextlen == 0) { + max_count = 138, min_count = 3; + } else if (curlen == nextlen) { + max_count = 6, min_count = 3; + } else { + max_count = 7, min_count = 4; + } + } +} + +/* =========================================================================== + * Send a literal or distance tree in compressed form, using the codes in + * bl_tree. + */ +local void send_tree (tree, max_code) + ct_data near *tree; /* the tree to be scanned */ + int max_code; /* and its largest code of non zero frequency */ +{ + int n; /* iterates over all tree elements */ + int prevlen = -1; /* last emitted length */ + int curlen; /* length of current code */ + int nextlen = tree[0].Len; /* length of next code */ + int count = 0; /* repeat count of the current code */ + int max_count = 7; /* max repeat count */ + int min_count = 4; /* min repeat count */ + + /* tree[max_code+1].Len = -1; */ /* guard already set */ + if (nextlen == 0) max_count = 138, min_count = 3; + + for (n = 0; n <= max_code; n++) { + curlen = nextlen; nextlen = tree[n+1].Len; + if (++count < max_count && curlen == nextlen) { + continue; + } else if (count < min_count) { + do { send_code(curlen, bl_tree); } while (--count != 0); + + } else if (curlen != 0) { + if (curlen != prevlen) { + send_code(curlen, bl_tree); count--; + } + Assert(count >= 3 && count <= 6, " 3_6?"); + send_code(REP_3_6, bl_tree); send_bits(count-3, 2); + + } else if (count <= 10) { + send_code(REPZ_3_10, bl_tree); send_bits(count-3, 3); + + } else { + send_code(REPZ_11_138, bl_tree); send_bits(count-11, 7); + } + count = 0; prevlen = curlen; + if (nextlen == 0) { + max_count = 138, min_count = 3; + } else if (curlen == nextlen) { + max_count = 6, min_count = 3; + } else { + max_count = 7, min_count = 4; + } + } +} + +/* =========================================================================== + * Construct the Huffman tree for the bit lengths and return the index in + * bl_order of the last bit length code to send. + */ +local int build_bl_tree() +{ + int max_blindex; /* index of last bit length code of non zero freq */ + + /* Determine the bit length frequencies for literal and distance trees */ + scan_tree((ct_data near *)dyn_ltree, l_desc.max_code); + scan_tree((ct_data near *)dyn_dtree, d_desc.max_code); + + /* Build the bit length tree: */ + build_tree((tree_desc near *)(&bl_desc)); + /* opt_len now includes the length of the tree representations, except + * the lengths of the bit lengths codes and the 5+5+4 bits for the counts. + */ + + /* Determine the number of bit length codes to send. The pkzip format + * requires that at least 4 bit length codes be sent. (appnote.txt says + * 3 but the actual value used is 4.) + */ + for (max_blindex = BL_CODES-1; max_blindex >= 3; max_blindex--) { + if (bl_tree[bl_order[max_blindex]].Len != 0) break; + } + /* Update opt_len to include the bit length tree and counts */ + opt_len += 3*(max_blindex+1) + 5+5+4; + Tracev((stderr, "\ndyn trees: dyn %lu, stat %lu", opt_len, static_len)); + + return max_blindex; +} + +/* =========================================================================== + * Send the header for a block using dynamic Huffman trees: the counts, the + * lengths of the bit length codes, the literal tree and the distance tree. + * IN assertion: lcodes >= 257, dcodes >= 1, blcodes >= 4. + */ +local void send_all_trees(lcodes, dcodes, blcodes) + int lcodes, dcodes, blcodes; /* number of codes for each tree */ +{ + int rank; /* index in bl_order */ + + Assert (lcodes >= 257 && dcodes >= 1 && blcodes >= 4, "not enough codes"); + Assert (lcodes <= L_CODES && dcodes <= D_CODES && blcodes <= BL_CODES, + "too many codes"); + Tracev((stderr, "\nbl counts: ")); + send_bits(lcodes-257, 5); /* not +255 as stated in appnote.txt */ + send_bits(dcodes-1, 5); + send_bits(blcodes-4, 4); /* not -3 as stated in appnote.txt */ + for (rank = 0; rank < blcodes; rank++) { + Tracev((stderr, "\nbl code %2d ", bl_order[rank])); + send_bits(bl_tree[bl_order[rank]].Len, 3); + } + + send_tree((ct_data near *)dyn_ltree, lcodes-1); /* send the literal tree */ + + send_tree((ct_data near *)dyn_dtree, dcodes-1); /* send the distance tree */ +} + +/* =========================================================================== + * Determine the best encoding for the current block: dynamic trees, static + * trees or store, and output the encoded block to the zip file. This function + * returns the total compressed length for the file so far. + */ +off_t flush_block(buf, stored_len, eof) + char *buf; /* input block, or NULL if too old */ + ulg stored_len; /* length of input block */ + int eof; /* true if this is the last block for a file */ +{ + ulg opt_lenb, static_lenb; /* opt_len and static_len in bytes */ + int max_blindex; /* index of last bit length code of non zero freq */ + + flag_buf[last_flags] = flags; /* Save the flags for the last 8 items */ + + /* Check if the file is ascii or binary */ + if (*file_type == (ush)UNKNOWN) set_file_type(); + + /* Construct the literal and distance trees */ + build_tree((tree_desc near *)(&l_desc)); + Tracev((stderr, "\nlit data: dyn %lu, stat %lu", opt_len, static_len)); + + build_tree((tree_desc near *)(&d_desc)); + Tracev((stderr, "\ndist data: dyn %lu, stat %lu", opt_len, static_len)); + /* At this point, opt_len and static_len are the total bit lengths of + * the compressed block data, excluding the tree representations. + */ + + /* Build the bit length tree for the above two trees, and get the index + * in bl_order of the last bit length code to send. + */ + max_blindex = build_bl_tree(); + + /* Determine the best encoding. Compute first the block length in bytes */ + opt_lenb = (opt_len+3+7)>>3; + static_lenb = (static_len+3+7)>>3; + input_len += stored_len; /* for debugging only */ + + Trace((stderr, "\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u dist %u ", + opt_lenb, opt_len, static_lenb, static_len, stored_len, + last_lit, last_dist)); + + if (static_lenb <= opt_lenb) opt_lenb = static_lenb; + + /* If compression failed and this is the first and last block, + * and if the zip file can be seeked (to rewrite the local header), + * the whole file is transformed into a stored file: + */ +#ifdef FORCE_METHOD + if (level == 1 && eof && compressed_len == 0L) { /* force stored file */ +#else + if (stored_len <= opt_lenb && eof && compressed_len == 0L && seekable()) { +#endif + /* Since LIT_BUFSIZE <= 2*WSIZE, the input data must be there: */ + if (buf == (char*)0) error ("block vanished"); + + copy_block(buf, (unsigned)stored_len, 0); /* without header */ + compressed_len = stored_len << 3; + *file_method = STORED; + +#ifdef FORCE_METHOD + } else if (level == 2 && buf != (char*)0) { /* force stored block */ +#else + } else if (stored_len+4 <= opt_lenb && buf != (char*)0) { + /* 4: two words for the lengths */ +#endif + /* The test buf != NULL is only necessary if LIT_BUFSIZE > WSIZE. + * Otherwise we can't have processed more than WSIZE input bytes since + * the last block flush, because compression would have been + * successful. If LIT_BUFSIZE <= WSIZE, it is never too late to + * transform a block into a stored block. + */ + send_bits((STORED_BLOCK<<1)+eof, 3); /* send block type */ + compressed_len = (compressed_len + 3 + 7) & ~7L; + compressed_len += (stored_len + 4) << 3; + + copy_block(buf, (unsigned)stored_len, 1); /* with header */ + +#ifdef FORCE_METHOD + } else if (level == 3) { /* force static trees */ +#else + } else if (static_lenb == opt_lenb) { +#endif + send_bits((STATIC_TREES<<1)+eof, 3); + compress_block((ct_data near *)static_ltree, (ct_data near *)static_dtree); + compressed_len += 3 + static_len; + } else { + send_bits((DYN_TREES<<1)+eof, 3); + send_all_trees(l_desc.max_code+1, d_desc.max_code+1, max_blindex+1); + compress_block((ct_data near *)dyn_ltree, (ct_data near *)dyn_dtree); + compressed_len += 3 + opt_len; + } + Assert (compressed_len == bits_sent, "bad compressed size"); + init_block(); + + if (eof) { + Assert (input_len == bytes_in, "bad input size"); + bi_windup(); + compressed_len += 7; /* align on byte boundary */ + } + + return compressed_len >> 3; +} + +/* =========================================================================== + * Save the match info and tally the frequency counts. Return true if + * the current block must be flushed. + */ +int ct_tally (dist, lc) + int dist; /* distance of matched string */ + int lc; /* match length-MIN_MATCH or unmatched char (if dist==0) */ +{ + l_buf[last_lit++] = (uch)lc; + if (dist == 0) { + /* lc is the unmatched char */ + dyn_ltree[lc].Freq++; + } else { + /* Here, lc is the match length - MIN_MATCH */ + dist--; /* dist = match distance - 1 */ + Assert((ush)dist < (ush)MAX_DIST && + (ush)lc <= (ush)(MAX_MATCH-MIN_MATCH) && + (ush)d_code(dist) < (ush)D_CODES, "ct_tally: bad match"); + + dyn_ltree[length_code[lc]+LITERALS+1].Freq++; + dyn_dtree[d_code(dist)].Freq++; + + d_buf[last_dist++] = (ush)dist; + flags |= flag_bit; + } + flag_bit <<= 1; + + /* Output the flags if they fill a byte: */ + if ((last_lit & 7) == 0) { + flag_buf[last_flags++] = flags; + flags = 0, flag_bit = 1; + } + /* Try to guess if it is profitable to stop the current block here */ + if (level > 2 && (last_lit & 0xfff) == 0) { + /* Compute an upper bound for the compressed length */ + ulg out_length = (ulg)last_lit*8L; + ulg in_length = (ulg)strstart-block_start; + int dcode; + for (dcode = 0; dcode < D_CODES; dcode++) { + out_length += (ulg)dyn_dtree[dcode].Freq*(5L+extra_dbits[dcode]); + } + out_length >>= 3; + Trace((stderr,"\nlast_lit %u, last_dist %u, in %ld, out ~%ld(%ld%%) ", + last_lit, last_dist, in_length, out_length, + 100L - out_length*100L/in_length)); + if (last_dist < last_lit/2 && out_length < in_length/2) return 1; + } + return (last_lit == LIT_BUFSIZE-1 || last_dist == DIST_BUFSIZE); + /* We avoid equality with LIT_BUFSIZE because of wraparound at 64K + * on 16 bit machines and because stored blocks are restricted to + * 64K-1 bytes. + */ +} + +/* =========================================================================== + * Send the block data compressed using the given Huffman trees + */ +local void compress_block(ltree, dtree) + ct_data near *ltree; /* literal tree */ + ct_data near *dtree; /* distance tree */ +{ + unsigned dist; /* distance of matched string */ + int lc; /* match length or unmatched char (if dist == 0) */ + unsigned lx = 0; /* running index in l_buf */ + unsigned dx = 0; /* running index in d_buf */ + unsigned fx = 0; /* running index in flag_buf */ + uch flag = 0; /* current flags */ + unsigned code; /* the code to send */ + int extra; /* number of extra bits to send */ + + if (last_lit != 0) do { + if ((lx & 7) == 0) flag = flag_buf[fx++]; + lc = l_buf[lx++]; + if ((flag & 1) == 0) { + send_code(lc, ltree); /* send a literal byte */ + Tracecv(isgraph(lc), (stderr," '%c' ", lc)); + } else { + /* Here, lc is the match length - MIN_MATCH */ + code = length_code[lc]; + send_code(code+LITERALS+1, ltree); /* send the length code */ + extra = extra_lbits[code]; + if (extra != 0) { + lc -= base_length[code]; + send_bits(lc, extra); /* send the extra length bits */ + } + dist = d_buf[dx++]; + /* Here, dist is the match distance - 1 */ + code = d_code(dist); + Assert (code < D_CODES, "bad d_code"); + + send_code(code, dtree); /* send the distance code */ + extra = extra_dbits[code]; + if (extra != 0) { + dist -= base_dist[code]; + send_bits(dist, extra); /* send the extra distance bits */ + } + } /* literal or match pair ? */ + flag >>= 1; + } while (lx < last_lit); + + send_code(END_BLOCK, ltree); +} + +/* =========================================================================== + * Set the file type to ASCII or BINARY, using a crude approximation: + * binary if more than 20% of the bytes are <= 6 or >= 128, ascii otherwise. + * IN assertion: the fields freq of dyn_ltree are set and the total of all + * frequencies does not exceed 64K (to fit in an int on 16 bit machines). + */ +local void set_file_type() +{ + int n = 0; + unsigned ascii_freq = 0; + unsigned bin_freq = 0; + while (n < 7) bin_freq += dyn_ltree[n++].Freq; + while (n < 128) ascii_freq += dyn_ltree[n++].Freq; + while (n < LITERALS) bin_freq += dyn_ltree[n++].Freq; + *file_type = bin_freq > (ascii_freq >> 2) ? BINARY : ASCII; + if (*file_type == BINARY && translate_eol) { + warning ("-l used on binary file"); + } +} diff --git a/isys/gzlib/unzip.c b/isys/gzlib/unzip.c new file mode 100644 index 000000000..a672b62d0 --- /dev/null +++ b/isys/gzlib/unzip.c @@ -0,0 +1,204 @@ +/* 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 <config.h> +#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 */ +#define RAND_HEAD_LEN 12 /* length of encryption random header */ + + +/* 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 */ + int err = OK; + + 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) { + gzerror("out of memory"); + } else if (res != 0) { + gzerror("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)); + gzerror("invalid compressed data--length mismatch"); + } + while (n--) { + uch c = (uch)get_byte(); + put_ubyte(c); + } + flush_window(); + } else { + gzerror("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)) { + fprintf(stderr, "\n%s: %s: invalid compressed data--crc error\n", + progname, ifname); + err = ERROR; + } + if (orig_len != (ulg)(bytes_out & 0xffffffff)) { + fprintf(stderr, "\n%s: %s: invalid compressed data--length error\n", + progname, ifname); + err = 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); + err = ERROR; + } + } + ext_header = pkzip = 0; /* for next file */ + if (err == OK) return OK; + exit_code = ERROR; + if (!test) abort_gzip(); + return err; +} diff --git a/isys/gzlib/util.c b/isys/gzlib/util.c new file mode 100644 index 000000000..93e8b823a --- /dev/null +++ b/isys/gzlib/util.c @@ -0,0 +1,538 @@ +/* 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 <config.h> +#include <ctype.h> +#include <errno.h> + +#include "tailor.h" + +#ifdef HAVE_LIMITS_H +# include <limits.h> +#endif +#ifdef HAVE_UNISTD_H +# include <unistd.h> +#endif +#ifdef HAVE_FCNTL_H +# include <fcntl.h> +#endif + +#if defined STDC_HEADERS || defined HAVE_STDLIB_H +# include <stdlib.h> +#else + extern int errno; +#endif + +#include "gzip.h" +#include "crypt.h" + +#ifndef CHAR_BIT +# define CHAR_BIT 8 +#endif + +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 != -1) { + write_buf(out, (char*)inbuf, insize); + bytes_out += insize; + insize = read(in, (char*)inbuf, INBUFSIZ); + } + if ((int)insize == -1) { + 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; + do { + len = read(ifd, (char*)inbuf+insize, INBUFSIZ-insize); + if (len == 0) break; + if (len == -1) { + read_error(); + break; + } + insize += len; + } while (insize < INBUFSIZ); + + if (insize == 0) { + if (eof_ok) return EOF; + flush_window(); + errno = 0; + read_error(); + } + bytes_in += (off_t)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 += (off_t)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 += (off_t)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 ((unsigned char) *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 *base_name(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; +} + +/* ======================================================================== + * Unlink a file, working around the unlink readonly bug (if present). + */ +int xunlink (filename) + char *filename; +{ + int r = unlink (filename); + +#ifdef UNLINK_READONLY_BUG + if (r != 0) + { + int e = errno; + if (chmod (filename, S_IWUSR) != 0) + { + errno = e; + return -1; + } + + r = unlink (filename); + } +#endif + + return r; +} + +/* ======================================================================== + * 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 HAVE_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 + +/* ======================================================================== + * 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*)gzxmalloc(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) gzerror("out of memory"); + oargv = *argvp; + *argvp = nargv; + + /* Copy the program name first */ + if (oargc-- < 0) gzerror("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 gzerror(m) + char *m; +{ + fprintf(stderr, "\n%s: %s: %s\n", progname, ifname, m); + abort_gzip(); +} + +void warning (m) + char *m; +{ + WARN ((stderr, "%s: %s: warning: %s\n", progname, ifname, m)); +} + +void read_error() +{ + int e = errno; + fprintf(stderr, "\n%s: ", progname); + if (e != 0) { + errno = e; + perror(ifname); + } else { + fprintf(stderr, "%s: unexpected end of file\n", ifname); + } + abort_gzip(); +} + +void write_error() +{ + int e = errno; + fprintf(stderr, "\n%s: ", progname); + errno = e; + perror(ofname); + abort_gzip(); +} + +/* ======================================================================== + * Display compression ratio on the given stream on 6 characters. + */ +void display_ratio(num, den, file) + off_t num; + off_t 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); + } + fprint_off(file, ratio / 10, 2); + fprintf(file, ".%d%%", (int) (ratio % 10)); +} + +/* ======================================================================== + * Print an off_t. There's no completely portable way to use printf, + * so we do it ourselves. + */ +void fprint_off(file, offset, width) + FILE *file; + off_t offset; + int width; +{ + char buf[CHAR_BIT * sizeof (off_t)]; + char *p = buf + sizeof buf; + int negative = offset < 0; + /* Don't negate offset here; it might overflow. */ + do { + int remainder = offset % 10; + int quotient = offset / 10; + if (offset < 0 && 0 < remainder) { + remainder -= 10; + quotient++; + } + *--p = (remainder < 0 ? -remainder : remainder) + '0'; + width--; + offset = quotient; + } while (offset != 0); + for (width -= negative; 0 < width; width--) { + putc (' ', file); + } + if (negative) { + putc ('-', file); + } + for (; p < buf + sizeof buf; p++) + putc (*p, file); +} + +/* ======================================================================== + * Semi-safe malloc -- never returns NULL. + */ +voidp gzxmalloc (size) + unsigned size; +{ + voidp cp = (voidp)malloc (size); + + if (cp == NULL) gzerror("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/isys/gzlib/zip.c b/isys/gzlib/zip.c new file mode 100644 index 000000000..3c1b49773 --- /dev/null +++ b/isys/gzlib/zip.c @@ -0,0 +1,52 @@ +/* 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 <config.h> +#include <ctype.h> + +#include "tailor.h" +#include "gzip.h" +#include "crypt.h" + +#ifdef HAVE_UNISTD_H +# include <unistd.h> +#endif +#ifdef HAVE_FCNTL_H +# include <fcntl.h> +#endif + +local ulg crc; /* crc on uncompressed file data */ +off_t header_bytes; /* number of bytes in gzip header */ + + +/* =========================================================================== + * 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 == 0) return (int)len; + if (len == (unsigned)-1) { + read_error(); + return EOF; + } + + crc = updcrc((uch*)buf, len); + bytes_in += (off_t)len; + return (int)len; +} |