2025-02-23 19:17:42 +01:00
|
|
|
/* Pdlzip - LZMA lossless data compressor
|
2025-02-23 19:16:13 +01:00
|
|
|
2009-08-14 : Igor Pavlov : Public domain
|
2025-02-23 19:23:49 +01:00
|
|
|
Copyright (C) 2010-2018 Antonio Diaz Diaz.
|
2025-02-23 19:16:13 +01:00
|
|
|
|
2025-02-23 19:20:22 +01:00
|
|
|
This program is free software. Redistribution and use in source and
|
|
|
|
binary forms, with or without modification, are permitted provided
|
|
|
|
that the following conditions are met:
|
|
|
|
|
|
|
|
1. Redistributions of source code must retain the above copyright
|
|
|
|
notice, this list of conditions and the following disclaimer.
|
|
|
|
|
|
|
|
2. Redistributions in binary form must reproduce the above copyright
|
|
|
|
notice, this list of conditions and the following disclaimer in the
|
|
|
|
documentation and/or other materials provided with the distribution.
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
This program is distributed in the hope that it will be useful,
|
|
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
|
|
|
|
*/
|
|
|
|
/*
|
2025-02-23 19:16:59 +01:00
|
|
|
Exit status: 0 for a normal exit, 1 for environmental problems
|
2025-02-23 19:16:13 +01:00
|
|
|
(file not found, invalid flags, I/O errors, etc), 2 to indicate a
|
|
|
|
corrupt or invalid input file, 3 for an internal consistency error
|
|
|
|
(eg, bug) which caused pdlzip to panic.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#define _FILE_OFFSET_BITS 64
|
|
|
|
|
|
|
|
#include <errno.h>
|
|
|
|
#include <fcntl.h>
|
|
|
|
#include <limits.h>
|
|
|
|
#include <signal.h>
|
2025-02-23 19:21:39 +01:00
|
|
|
#include <stdbool.h>
|
2025-02-23 19:16:13 +01:00
|
|
|
#include <stdint.h>
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <string.h>
|
|
|
|
#include <unistd.h>
|
|
|
|
#include <utime.h>
|
|
|
|
#include <sys/stat.h>
|
|
|
|
#if defined(__MSVCRT__)
|
|
|
|
#include <io.h>
|
|
|
|
#define fchmod(x,y) 0
|
|
|
|
#define fchown(x,y,z) 0
|
|
|
|
#define SIGHUP SIGTERM
|
|
|
|
#define S_ISSOCK(x) 0
|
|
|
|
#define S_IRGRP 0
|
|
|
|
#define S_IWGRP 0
|
|
|
|
#define S_IROTH 0
|
|
|
|
#define S_IWOTH 0
|
|
|
|
#endif
|
|
|
|
#if defined(__OS2__)
|
|
|
|
#include <io.h>
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#include "carg_parser.h"
|
2025-02-23 19:16:59 +01:00
|
|
|
#include "lzip.h"
|
2025-02-23 19:16:13 +01:00
|
|
|
#include "LzmaDec.h"
|
|
|
|
#include "LzmaEnc.h"
|
|
|
|
|
2025-02-23 19:20:22 +01:00
|
|
|
#ifndef O_BINARY
|
|
|
|
#define O_BINARY 0
|
|
|
|
#endif
|
|
|
|
|
2025-02-23 19:16:13 +01:00
|
|
|
#if CHAR_BIT != 8
|
|
|
|
#error "Environments where CHAR_BIT != 8 are not supported."
|
|
|
|
#endif
|
|
|
|
|
2025-02-23 19:21:39 +01:00
|
|
|
int verbosity = 0;
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
const char * const Program_name = "Pdlzip";
|
|
|
|
const char * const program_name = "pdlzip";
|
2025-02-23 19:23:49 +01:00
|
|
|
const char * const program_year = "2018";
|
2025-02-23 19:16:13 +01:00
|
|
|
const char * invocation_name = 0;
|
|
|
|
|
2025-02-23 19:22:52 +01:00
|
|
|
const struct { const char * from; const char * to; } known_extensions[] = {
|
2025-02-23 19:16:13 +01:00
|
|
|
{ ".lz", "" },
|
|
|
|
{ ".tlz", ".tar" },
|
|
|
|
{ ".lzma", "" },
|
|
|
|
{ 0, 0 } };
|
|
|
|
|
|
|
|
struct Lzma_options
|
|
|
|
{
|
2025-02-23 19:18:05 +01:00
|
|
|
int dictionary_size; /* 4 KiB .. 512 MiB */
|
|
|
|
int match_len_limit; /* 5 .. 273 */
|
2025-02-23 19:16:13 +01:00
|
|
|
};
|
|
|
|
|
|
|
|
enum Mode { m_compress, m_decompress, m_test };
|
|
|
|
|
|
|
|
char * output_filename = 0;
|
|
|
|
int outfd = -1;
|
|
|
|
bool delete_output_on_interrupt = false;
|
|
|
|
|
|
|
|
|
|
|
|
static void show_help( void )
|
|
|
|
{
|
2025-02-23 19:21:39 +01:00
|
|
|
printf( "%s - A permissively licensed implementation of the lzip data\n", Program_name );
|
|
|
|
printf( "compressor also able to decompress legacy lzma-alone (.lzma) files.\n"
|
|
|
|
"\nLzma-alone is a very bad format; it is essentially a raw LZMA stream.\n"
|
|
|
|
"If you keep any lzma-alone files, it is advisable to recompress them to\n"
|
2025-02-23 19:22:52 +01:00
|
|
|
"lzip format. Lziprecover can convert some lzma-alone files to lzip format\n"
|
2025-02-23 19:21:39 +01:00
|
|
|
"without recompressing.\n"
|
2025-02-23 19:16:13 +01:00
|
|
|
"\nUsage: %s [options] [files]\n", invocation_name );
|
|
|
|
printf( "\nOptions:\n"
|
|
|
|
" -h, --help display this help and exit\n"
|
|
|
|
" -V, --version output version information and exit\n"
|
2025-02-23 19:21:39 +01:00
|
|
|
" -a, --trailing-error exit with error status if trailing data\n"
|
|
|
|
" -c, --stdout write to standard output, keep input files\n"
|
2025-02-23 19:16:13 +01:00
|
|
|
" -d, --decompress decompress\n"
|
|
|
|
" -f, --force overwrite existing output files\n"
|
2025-02-23 19:21:02 +01:00
|
|
|
" -F, --recompress force re-compression of compressed files\n"
|
2025-02-23 19:16:13 +01:00
|
|
|
" -k, --keep keep (don't delete) input files\n"
|
|
|
|
" -m, --match-length=<bytes> set match length limit in bytes [36]\n"
|
2025-02-23 19:21:39 +01:00
|
|
|
" -o, --output=<file> if reading standard input, write to <file>\n"
|
2025-02-23 19:16:13 +01:00
|
|
|
" -q, --quiet suppress all messages\n"
|
2025-02-23 19:18:05 +01:00
|
|
|
" -s, --dictionary-size=<bytes> set dictionary size limit in bytes [8 MiB]\n"
|
2025-02-23 19:16:13 +01:00
|
|
|
" -t, --test test compressed file integrity\n"
|
|
|
|
" -v, --verbose be verbose (a 2nd -v gives more)\n"
|
|
|
|
" -1 .. -9 set compression level [default 6]\n"
|
|
|
|
" --fast alias for -1\n"
|
|
|
|
" --best alias for -9\n"
|
2025-02-23 19:23:49 +01:00
|
|
|
" --loose-trailing allow trailing data seeming corrupt header\n"
|
2025-02-23 19:21:39 +01:00
|
|
|
"If no file names are given, or if a file is '-', pdlzip compresses or\n"
|
|
|
|
"decompresses from standard input to standard output.\n"
|
2025-02-23 19:16:13 +01:00
|
|
|
"Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n"
|
|
|
|
"Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n"
|
2025-02-23 19:21:39 +01:00
|
|
|
"Dictionary sizes 12 to 27 are interpreted as powers of two, meaning 2^12\n"
|
|
|
|
"to 2^27 bytes.\n"
|
|
|
|
"\nThe bidimensional parameter space of LZMA can't be mapped to a linear\n"
|
2025-02-23 19:16:13 +01:00
|
|
|
"scale optimal for all files. If your files are large, very repetitive,\n"
|
2025-02-23 19:21:39 +01:00
|
|
|
"etc, you may need to use the --dictionary-size and --match-length\n"
|
2025-02-23 19:18:05 +01:00
|
|
|
"options directly to achieve optimal performance. For example, -9m64\n"
|
|
|
|
"usually compresses executables more (and faster) than -9.\n"
|
2025-02-23 19:16:59 +01:00
|
|
|
"\nExit status: 0 for a normal exit, 1 for environmental problems (file\n"
|
2025-02-23 19:16:35 +01:00
|
|
|
"not found, invalid flags, I/O errors, etc), 2 to indicate a corrupt or\n"
|
|
|
|
"invalid input file, 3 for an internal consistency error (eg, bug) which\n"
|
|
|
|
"caused pdlzip to panic.\n"
|
2025-02-23 19:16:13 +01:00
|
|
|
"\nReport bugs to lzip-bug@nongnu.org\n"
|
|
|
|
"Pdlzip home page: http://www.nongnu.org/lzip/pdlzip.html\n" );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void show_version( void )
|
|
|
|
{
|
2025-02-23 19:20:22 +01:00
|
|
|
printf( "%s %s\n", program_name, PROGVERSION );
|
2025-02-23 19:16:13 +01:00
|
|
|
printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year );
|
|
|
|
printf( "Public Domain 2009 Igor Pavlov.\n"
|
2025-02-23 19:20:22 +01:00
|
|
|
"License 2-clause BSD.\n"
|
2025-02-23 19:16:13 +01:00
|
|
|
"This is free software: you are free to change and redistribute it.\n"
|
|
|
|
"There is NO WARRANTY, to the extent permitted by law.\n" );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:23:49 +01:00
|
|
|
/* assure at least a minimum size for buffer 'buf' */
|
|
|
|
void * resize_buffer( void * buf, const unsigned min_size )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
2025-02-23 19:23:49 +01:00
|
|
|
if( buf ) buf = realloc( buf, min_size );
|
|
|
|
else buf = malloc( min_size );
|
|
|
|
if( !buf )
|
2025-02-23 19:21:39 +01:00
|
|
|
{
|
2025-02-23 19:23:49 +01:00
|
|
|
show_error( "Not enough memory.", 0, false );
|
|
|
|
cleanup_and_fail( 1 );
|
2025-02-23 19:21:39 +01:00
|
|
|
}
|
2025-02-23 19:23:49 +01:00
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
void Pp_show_msg( struct Pretty_print * const pp, const char * const msg )
|
|
|
|
{
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
{
|
|
|
|
if( pp->first_post )
|
|
|
|
{
|
|
|
|
pp->first_post = false;
|
|
|
|
fputs( pp->padded_name, stderr );
|
|
|
|
if( !msg ) fflush( stderr );
|
|
|
|
}
|
|
|
|
if( msg ) fprintf( stderr, "%s\n", msg );
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void show_header( const unsigned dictionary_size )
|
|
|
|
{
|
|
|
|
enum { factor = 1024 };
|
|
|
|
const char * const prefix[8] =
|
|
|
|
{ "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" };
|
|
|
|
const char * p = "";
|
|
|
|
const char * np = " ";
|
|
|
|
unsigned num = dictionary_size;
|
|
|
|
bool exact = ( num % factor == 0 );
|
|
|
|
|
|
|
|
int i; for( i = 0; i < 8 && ( num > 9999 || ( exact && num >= factor ) ); ++i )
|
|
|
|
{ num /= factor; if( num % factor != 0 ) exact = false;
|
|
|
|
p = prefix[i]; np = ""; }
|
|
|
|
fprintf( stderr, "dictionary %s%4u %sB, ", np, num, p );
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static unsigned long getnum( const char * const ptr,
|
|
|
|
const unsigned long llimit,
|
|
|
|
const unsigned long ulimit )
|
|
|
|
{
|
|
|
|
unsigned long result;
|
|
|
|
char * tail;
|
|
|
|
errno = 0;
|
|
|
|
result = strtoul( ptr, &tail, 0 );
|
|
|
|
if( tail == ptr )
|
|
|
|
{
|
|
|
|
show_error( "Bad or missing numerical argument.", 0, true );
|
|
|
|
exit( 1 );
|
|
|
|
}
|
|
|
|
|
|
|
|
if( !errno && tail[0] )
|
|
|
|
{
|
2025-02-23 19:22:52 +01:00
|
|
|
const unsigned factor = ( tail[1] == 'i' ) ? 1024 : 1000;
|
2025-02-23 19:21:39 +01:00
|
|
|
int exponent = 0; /* 0 = bad multiplier */
|
|
|
|
int i;
|
2025-02-23 19:16:13 +01:00
|
|
|
switch( tail[0] )
|
|
|
|
{
|
|
|
|
case 'Y': exponent = 8; break;
|
|
|
|
case 'Z': exponent = 7; break;
|
|
|
|
case 'E': exponent = 6; break;
|
|
|
|
case 'P': exponent = 5; break;
|
|
|
|
case 'T': exponent = 4; break;
|
|
|
|
case 'G': exponent = 3; break;
|
|
|
|
case 'M': exponent = 2; break;
|
2025-02-23 19:21:39 +01:00
|
|
|
case 'K': if( factor == 1024 ) exponent = 1; break;
|
|
|
|
case 'k': if( factor == 1000 ) exponent = 1; break;
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
2025-02-23 19:21:39 +01:00
|
|
|
if( exponent <= 0 )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
show_error( "Bad multiplier in numerical argument.", 0, true );
|
|
|
|
exit( 1 );
|
|
|
|
}
|
|
|
|
for( i = 0; i < exponent; ++i )
|
|
|
|
{
|
|
|
|
if( ulimit / factor >= result ) result *= factor;
|
|
|
|
else { errno = ERANGE; break; }
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if( !errno && ( result < llimit || result > ulimit ) ) errno = ERANGE;
|
|
|
|
if( errno )
|
|
|
|
{
|
|
|
|
show_error( "Numerical argument out of limits.", 0, false );
|
|
|
|
exit( 1 );
|
|
|
|
}
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int get_dict_size( const char * const arg )
|
|
|
|
{
|
|
|
|
char * tail;
|
2025-02-23 19:22:52 +01:00
|
|
|
const long bits = strtol( arg, &tail, 0 );
|
2025-02-23 19:16:13 +01:00
|
|
|
if( bits >= min_dictionary_bits &&
|
2025-02-23 19:22:52 +01:00
|
|
|
bits <= max_dictionary_bits_c && *tail == 0 )
|
2025-02-23 19:16:13 +01:00
|
|
|
return ( 1 << bits );
|
2025-02-23 19:22:52 +01:00
|
|
|
return getnum( arg, min_dictionary_size, max_dictionary_size_c );
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int extension_index( const char * const name )
|
|
|
|
{
|
2025-02-23 19:22:52 +01:00
|
|
|
int eindex;
|
|
|
|
for( eindex = 0; known_extensions[eindex].from; ++eindex )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
2025-02-23 19:22:52 +01:00
|
|
|
const char * const ext = known_extensions[eindex].from;
|
2025-02-23 19:20:22 +01:00
|
|
|
const unsigned name_len = strlen( name );
|
|
|
|
const unsigned ext_len = strlen( ext );
|
|
|
|
if( name_len > ext_len &&
|
|
|
|
strncmp( name + name_len - ext_len, ext, ext_len ) == 0 )
|
2025-02-23 19:22:52 +01:00
|
|
|
return eindex;
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:23:49 +01:00
|
|
|
static void set_c_outname( const char * const name, const bool force_ext )
|
|
|
|
{
|
|
|
|
output_filename = resize_buffer( output_filename, strlen( name ) +
|
|
|
|
strlen( known_extensions[0].from ) + 1 );
|
|
|
|
strcpy( output_filename, name );
|
|
|
|
if( force_ext || extension_index( output_filename ) < 0 )
|
|
|
|
strcat( output_filename, known_extensions[0].from );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void set_d_outname( const char * const name, const int eindex )
|
|
|
|
{
|
|
|
|
const unsigned name_len = strlen( name );
|
|
|
|
if( eindex >= 0 )
|
|
|
|
{
|
|
|
|
const char * const from = known_extensions[eindex].from;
|
|
|
|
const unsigned from_len = strlen( from );
|
|
|
|
if( name_len > from_len )
|
|
|
|
{
|
|
|
|
output_filename = resize_buffer( output_filename, name_len +
|
|
|
|
strlen( known_extensions[eindex].to ) + 1 );
|
|
|
|
strcpy( output_filename, name );
|
|
|
|
strcpy( output_filename + name_len - from_len, known_extensions[eindex].to );
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
output_filename = resize_buffer( output_filename, name_len + 4 + 1 );
|
|
|
|
strcpy( output_filename, name );
|
|
|
|
strcat( output_filename, ".out" );
|
|
|
|
if( verbosity >= 1 )
|
|
|
|
fprintf( stderr, "%s: Can't guess original name for '%s' -- using '%s'\n",
|
|
|
|
program_name, name, output_filename );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:16:13 +01:00
|
|
|
static int open_instream( const char * const name, struct stat * const in_statsp,
|
|
|
|
const enum Mode program_mode, const int eindex,
|
|
|
|
const bool recompress, const bool to_stdout )
|
|
|
|
{
|
|
|
|
int infd = -1;
|
|
|
|
if( program_mode == m_compress && !recompress && eindex >= 0 )
|
|
|
|
{
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "%s: Input file '%s' already has '%s' suffix.\n",
|
|
|
|
program_name, name, known_extensions[eindex].from );
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2025-02-23 19:20:22 +01:00
|
|
|
infd = open( name, O_RDONLY | O_BINARY );
|
2025-02-23 19:16:13 +01:00
|
|
|
if( infd < 0 )
|
2025-02-23 19:22:52 +01:00
|
|
|
show_file_error( name, "Can't open input file", errno );
|
2025-02-23 19:16:13 +01:00
|
|
|
else
|
|
|
|
{
|
|
|
|
const int i = fstat( infd, in_statsp );
|
|
|
|
const mode_t mode = in_statsp->st_mode;
|
|
|
|
const bool can_read = ( i == 0 &&
|
|
|
|
( S_ISBLK( mode ) || S_ISCHR( mode ) ||
|
|
|
|
S_ISFIFO( mode ) || S_ISSOCK( mode ) ) );
|
2025-02-23 19:21:39 +01:00
|
|
|
const bool no_ofile = ( to_stdout || program_mode == m_test );
|
2025-02-23 19:17:42 +01:00
|
|
|
if( i != 0 || ( !S_ISREG( mode ) && ( !can_read || !no_ofile ) ) )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "%s: Input file '%s' is not a regular file%s.\n",
|
|
|
|
program_name, name,
|
2025-02-23 19:17:42 +01:00
|
|
|
( can_read && !no_ofile ) ?
|
2025-02-23 19:21:39 +01:00
|
|
|
",\n and '--stdout' was not specified" : "" );
|
2025-02-23 19:16:13 +01:00
|
|
|
close( infd );
|
|
|
|
infd = -1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return infd;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:21:39 +01:00
|
|
|
static bool open_outstream( const bool force, const bool from_stdin )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
2025-02-23 19:21:39 +01:00
|
|
|
const mode_t usr_rw = S_IRUSR | S_IWUSR;
|
|
|
|
const mode_t all_rw = usr_rw | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH;
|
|
|
|
const mode_t outfd_mode = from_stdin ? all_rw : usr_rw;
|
2025-02-23 19:20:22 +01:00
|
|
|
int flags = O_CREAT | O_WRONLY | O_BINARY;
|
2025-02-23 19:16:13 +01:00
|
|
|
if( force ) flags |= O_TRUNC; else flags |= O_EXCL;
|
|
|
|
|
|
|
|
outfd = open( output_filename, flags, outfd_mode );
|
2025-02-23 19:21:39 +01:00
|
|
|
if( outfd >= 0 ) delete_output_on_interrupt = true;
|
|
|
|
else if( verbosity >= 0 )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
if( errno == EEXIST )
|
|
|
|
fprintf( stderr, "%s: Output file '%s' already exists, skipping.\n",
|
|
|
|
program_name, output_filename );
|
|
|
|
else
|
2025-02-23 19:21:39 +01:00
|
|
|
fprintf( stderr, "%s: Can't create output file '%s': %s\n",
|
2025-02-23 19:16:13 +01:00
|
|
|
program_name, output_filename, strerror( errno ) );
|
|
|
|
}
|
|
|
|
return ( outfd >= 0 );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:22:52 +01:00
|
|
|
static bool check_tty( const char * const input_filename, const int infd,
|
|
|
|
const enum Mode program_mode )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
2025-02-23 19:20:22 +01:00
|
|
|
if( program_mode == m_compress && isatty( outfd ) )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
show_error( "I won't write compressed data to a terminal.", 0, true );
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
if( ( program_mode == m_decompress || program_mode == m_test ) &&
|
|
|
|
isatty( infd ) )
|
|
|
|
{
|
2025-02-23 19:22:52 +01:00
|
|
|
show_file_error( input_filename,
|
|
|
|
"I won't read compressed data from a terminal.", 0 );
|
2025-02-23 19:16:13 +01:00
|
|
|
return false;
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:17:42 +01:00
|
|
|
void cleanup_and_fail( const int retval )
|
|
|
|
{
|
|
|
|
if( delete_output_on_interrupt )
|
|
|
|
{
|
|
|
|
delete_output_on_interrupt = false;
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
fprintf( stderr, "%s: Deleting output file '%s', if it exists.\n",
|
|
|
|
program_name, output_filename );
|
|
|
|
if( outfd >= 0 ) { close( outfd ); outfd = -1; }
|
|
|
|
if( remove( output_filename ) != 0 && errno != ENOENT )
|
|
|
|
show_error( "WARNING: deletion of output file (apparently) failed.", 0, false );
|
|
|
|
}
|
|
|
|
exit( retval );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:16:13 +01:00
|
|
|
/* Set permissions, owner and times. */
|
|
|
|
static void close_and_set_permissions( const struct stat * const in_statsp )
|
|
|
|
{
|
|
|
|
bool warning = false;
|
|
|
|
if( in_statsp )
|
|
|
|
{
|
2025-02-23 19:20:22 +01:00
|
|
|
const mode_t mode = in_statsp->st_mode;
|
2025-02-23 19:16:13 +01:00
|
|
|
/* fchown will in many cases return with EPERM, which can be safely ignored. */
|
2025-02-23 19:20:22 +01:00
|
|
|
if( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) == 0 )
|
|
|
|
{ if( fchmod( outfd, mode ) != 0 ) warning = true; }
|
|
|
|
else
|
|
|
|
if( errno != EPERM ||
|
|
|
|
fchmod( outfd, mode & ~( S_ISUID | S_ISGID | S_ISVTX ) ) != 0 )
|
|
|
|
warning = true;
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
2025-02-23 19:21:39 +01:00
|
|
|
if( close( outfd ) != 0 )
|
|
|
|
{
|
|
|
|
show_error( "Error closing output file", errno, false );
|
|
|
|
cleanup_and_fail( 1 );
|
|
|
|
}
|
2025-02-23 19:16:13 +01:00
|
|
|
outfd = -1;
|
|
|
|
delete_output_on_interrupt = false;
|
|
|
|
if( in_statsp )
|
|
|
|
{
|
|
|
|
struct utimbuf t;
|
|
|
|
t.actime = in_statsp->st_atime;
|
|
|
|
t.modtime = in_statsp->st_mtime;
|
|
|
|
if( utime( output_filename, &t ) != 0 ) warning = true;
|
|
|
|
}
|
|
|
|
if( warning && verbosity >= 1 )
|
|
|
|
show_error( "Can't change output file attributes.", 0, false );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int compress( const struct Lzma_options * const encoder_options,
|
2025-02-23 19:22:52 +01:00
|
|
|
struct Pretty_print * const pp, const int infd )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
int retval = 0;
|
2025-02-23 19:20:22 +01:00
|
|
|
CLzmaEncHandle encoder = 0;
|
2025-02-23 19:17:42 +01:00
|
|
|
File_header header;
|
|
|
|
Fh_set_magic( header );
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
if( verbosity >= 1 ) Pp_show_msg( pp, 0 );
|
2025-02-23 19:20:22 +01:00
|
|
|
if( Fh_set_dictionary_size( header, encoder_options->dictionary_size ) &&
|
|
|
|
encoder_options->match_len_limit >= min_match_len_limit &&
|
|
|
|
encoder_options->match_len_limit <= max_match_len )
|
|
|
|
encoder = LzmaEnc_Init( Fh_get_dictionary_size( header ),
|
|
|
|
encoder_options->match_len_limit, infd, outfd );
|
|
|
|
else internal_error( "invalid argument to encoder." );
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
if( !encoder )
|
|
|
|
{
|
2025-02-23 19:20:22 +01:00
|
|
|
Pp_show_msg( pp, "Not enough memory. Try a smaller dictionary size." );
|
2025-02-23 19:16:13 +01:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if( writeblock( outfd, header, Fh_size ) != Fh_size )
|
2025-02-23 19:21:39 +01:00
|
|
|
{ show_error( "Can't write output file", errno, false ); retval = 1; }
|
2025-02-23 19:16:13 +01:00
|
|
|
else
|
|
|
|
if( LzmaEnc_Encode( encoder ) != 0 )
|
2025-02-23 19:20:22 +01:00
|
|
|
{ Pp_show_msg( pp, "Encoder error." ); retval = 1; }
|
2025-02-23 19:16:13 +01:00
|
|
|
LzmaEnc_Free( encoder );
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
#define IN_BUF_SIZE (1 << 16)
|
|
|
|
#define OUT_BUF_SIZE (1 << 16)
|
|
|
|
|
|
|
|
static bool read_inbuf( const int infd, uint8_t inBuf[],
|
|
|
|
int * const inPos, int * const inSize )
|
|
|
|
{
|
|
|
|
int rest;
|
|
|
|
if( *inPos >= *inSize ) *inSize = 0;
|
|
|
|
else if( *inPos > 0 )
|
|
|
|
{
|
|
|
|
memmove( inBuf, inBuf + *inPos, *inSize - *inPos );
|
|
|
|
*inSize -= *inPos;
|
|
|
|
}
|
|
|
|
*inPos = 0;
|
|
|
|
rest = IN_BUF_SIZE - *inSize;
|
|
|
|
if( rest > 0 )
|
|
|
|
{
|
|
|
|
const int rd = readblock( infd, inBuf + *inSize, rest );
|
|
|
|
if( rd < rest && errno )
|
|
|
|
{ show_error( "Read error", errno, false ); return false; }
|
|
|
|
*inSize += rd;
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:17:42 +01:00
|
|
|
/* 5 bytes of LZMA properties and 8 bytes of uncompressed size */
|
|
|
|
enum { lzma_header_size = LZMA_PROPS_SIZE + 8 };
|
|
|
|
|
2025-02-23 19:16:13 +01:00
|
|
|
static int lzma_decode( uint64_t unpackSize, CLzmaDec *decoder, const int infd,
|
|
|
|
uint8_t inBuf[], int * const inPos,
|
2025-02-23 19:23:49 +01:00
|
|
|
int * const inSize, const unsigned dictionary_size,
|
|
|
|
const bool testing )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
2025-02-23 19:23:49 +01:00
|
|
|
unsigned long long member_size = lzma_header_size, data_size = 0;
|
2025-02-23 19:16:13 +01:00
|
|
|
uint8_t outBuf[OUT_BUF_SIZE];
|
|
|
|
int outPos = 0;
|
|
|
|
const bool thereIsSize = (unpackSize != (uint64_t)-1);
|
|
|
|
|
|
|
|
for (;;)
|
|
|
|
{
|
|
|
|
uint32_t inProcessed;
|
|
|
|
uint32_t outProcessed = OUT_BUF_SIZE - outPos;
|
|
|
|
ELzmaFinishMode finishMode = LZMA_FINISH_ANY;
|
|
|
|
ELzmaStatus status;
|
|
|
|
|
|
|
|
if( *inPos >= *inSize && !read_inbuf( infd, inBuf, inPos, inSize ) )
|
|
|
|
return 1;
|
|
|
|
inProcessed = *inSize - *inPos;
|
|
|
|
if (thereIsSize && outProcessed > unpackSize)
|
|
|
|
{
|
|
|
|
outProcessed = unpackSize;
|
|
|
|
finishMode = LZMA_FINISH_END;
|
|
|
|
}
|
|
|
|
|
|
|
|
if( !LzmaDec_DecodeToBuf( decoder, outBuf + outPos, &outProcessed,
|
|
|
|
inBuf + *inPos, &inProcessed, finishMode, &status ) )
|
2025-02-23 19:16:35 +01:00
|
|
|
{ show_error( "Data error.", 0, false ); return 2; }
|
2025-02-23 19:16:13 +01:00
|
|
|
*inPos += inProcessed;
|
2025-02-23 19:23:49 +01:00
|
|
|
member_size += inProcessed;
|
2025-02-23 19:16:13 +01:00
|
|
|
outPos += outProcessed;
|
|
|
|
unpackSize -= outProcessed;
|
|
|
|
|
|
|
|
if( outfd >= 0 && writeblock( outfd, outBuf, outPos ) != outPos )
|
2025-02-23 19:21:39 +01:00
|
|
|
{ show_error( "Can't write output file", errno, false ); return 1; }
|
2025-02-23 19:16:13 +01:00
|
|
|
|
2025-02-23 19:23:49 +01:00
|
|
|
data_size += outPos;
|
2025-02-23 19:16:13 +01:00
|
|
|
outPos = 0;
|
|
|
|
|
|
|
|
if( ( inProcessed == 0 && outProcessed == 0 ) ||
|
|
|
|
( thereIsSize && unpackSize == 0 ) )
|
|
|
|
{
|
|
|
|
if( ( thereIsSize && unpackSize != 0 ) ||
|
|
|
|
( !thereIsSize && status != LZMA_STATUS_FINISHED_WITH_MARK ) )
|
2025-02-23 19:16:35 +01:00
|
|
|
{ show_error( "Data error.", 0, false ); return 2; }
|
2025-02-23 19:21:39 +01:00
|
|
|
if( verbosity >= 2 )
|
2025-02-23 19:23:49 +01:00
|
|
|
{
|
|
|
|
if( verbosity >= 4 ) show_header( dictionary_size );
|
|
|
|
if( data_size == 0 || member_size == 0 )
|
|
|
|
fputs( "no data compressed. ", stderr );
|
|
|
|
else
|
|
|
|
fprintf( stderr, "%6.3f:1, %5.2f%% ratio, %5.2f%% saved. ",
|
|
|
|
(double)data_size / member_size,
|
|
|
|
( 100.0 * member_size ) / data_size,
|
|
|
|
100.0 - ( ( 100.0 * member_size ) / data_size ) );
|
|
|
|
if( verbosity >= 3 )
|
|
|
|
fprintf( stderr, "decompressed %9llu, compressed %8llu. ",
|
|
|
|
data_size, member_size );
|
2025-02-23 19:21:39 +01:00
|
|
|
fputs( "lzma-alone, ", stderr );
|
2025-02-23 19:23:49 +01:00
|
|
|
}
|
2025-02-23 19:16:13 +01:00
|
|
|
if( verbosity >= 1 )
|
2025-02-23 19:21:39 +01:00
|
|
|
fputs( testing ? "(apparently) ok\n" : "(apparently) done\n", stderr );
|
2025-02-23 19:16:13 +01:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:23:49 +01:00
|
|
|
static int lzip_decode( CLzmaDec *decoder, const int infd,
|
|
|
|
struct Pretty_print * const pp, uint8_t inBuf[],
|
|
|
|
int * const inPos, int * const inSize,
|
|
|
|
const unsigned dictionary_size )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
2025-02-23 19:23:49 +01:00
|
|
|
unsigned long long member_size = Fh_size, data_size = 0;
|
2025-02-23 19:16:13 +01:00
|
|
|
uint8_t outBuf[OUT_BUF_SIZE];
|
|
|
|
int outPos = 0;
|
|
|
|
uint32_t crc = 0xFFFFFFFFU;
|
|
|
|
|
|
|
|
for (;;)
|
|
|
|
{
|
|
|
|
uint32_t inProcessed;
|
|
|
|
uint32_t outProcessed = OUT_BUF_SIZE - outPos;
|
|
|
|
ELzmaFinishMode finishMode = LZMA_FINISH_ANY;
|
|
|
|
ELzmaStatus status;
|
|
|
|
|
|
|
|
if( *inPos >= *inSize && !read_inbuf( infd, inBuf, inPos, inSize ) )
|
|
|
|
return 1;
|
|
|
|
if( *inPos >= *inSize )
|
2025-02-23 19:23:49 +01:00
|
|
|
{ Pp_show_msg( pp, "Unexpected EOF." ); return 2; }
|
2025-02-23 19:16:13 +01:00
|
|
|
inProcessed = *inSize - *inPos;
|
|
|
|
|
|
|
|
if( !LzmaDec_DecodeToBuf( decoder, outBuf + outPos, &outProcessed,
|
|
|
|
inBuf + *inPos, &inProcessed, finishMode, &status ) )
|
2025-02-23 19:23:49 +01:00
|
|
|
{ Pp_show_msg( pp, "Data error." ); return 2; }
|
2025-02-23 19:16:13 +01:00
|
|
|
*inPos += inProcessed;
|
2025-02-23 19:23:49 +01:00
|
|
|
member_size += inProcessed;
|
2025-02-23 19:16:13 +01:00
|
|
|
outPos += outProcessed;
|
|
|
|
|
|
|
|
if( outfd >= 0 && writeblock( outfd, outBuf, outPos ) != outPos )
|
2025-02-23 19:21:39 +01:00
|
|
|
{ show_error( "Can't write output file", errno, false ); return 1; }
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
CRC32_update_buf( &crc, outBuf, outPos );
|
2025-02-23 19:23:49 +01:00
|
|
|
data_size += outPos;
|
2025-02-23 19:16:13 +01:00
|
|
|
outPos = 0;
|
|
|
|
|
|
|
|
if (inProcessed == 0 && outProcessed == 0)
|
|
|
|
{
|
|
|
|
File_trailer trailer;
|
|
|
|
int i;
|
2025-02-23 19:23:49 +01:00
|
|
|
unsigned td_crc;
|
|
|
|
unsigned long long td_size, tm_size;
|
2025-02-23 19:16:13 +01:00
|
|
|
bool error = false;
|
|
|
|
|
|
|
|
if( status != LZMA_STATUS_FINISHED_WITH_MARK )
|
2025-02-23 19:23:49 +01:00
|
|
|
{ Pp_show_msg( pp, "Data error." ); return 2; }
|
2025-02-23 19:17:42 +01:00
|
|
|
if( *inSize - *inPos < Ft_size &&
|
2025-02-23 19:16:13 +01:00
|
|
|
!read_inbuf( infd, inBuf, inPos, inSize ) ) return 1;
|
2025-02-23 19:17:42 +01:00
|
|
|
if( *inSize - *inPos < Ft_size )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
error = true;
|
|
|
|
if( verbosity >= 0 )
|
2025-02-23 19:23:49 +01:00
|
|
|
{
|
|
|
|
Pp_show_msg( pp, 0 );
|
2025-02-23 19:22:52 +01:00
|
|
|
fprintf( stderr, "Trailer truncated at trailer position %d;"
|
|
|
|
" some checks may fail.\n", *inSize - *inPos );
|
2025-02-23 19:23:49 +01:00
|
|
|
}
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
2025-02-23 19:23:49 +01:00
|
|
|
for( i = 0; i < Ft_size && *inPos < *inSize; ++i )
|
2025-02-23 19:16:13 +01:00
|
|
|
trailer[i] = inBuf[(*inPos)++];
|
2025-02-23 19:23:49 +01:00
|
|
|
member_size += i;
|
|
|
|
while( i < Ft_size ) trailer[i++] = 0;
|
2025-02-23 19:21:39 +01:00
|
|
|
crc ^= 0xFFFFFFFFU;
|
2025-02-23 19:23:49 +01:00
|
|
|
td_crc = Ft_get_data_crc( trailer );
|
|
|
|
if( td_crc != crc )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
error = true;
|
|
|
|
if( verbosity >= 0 )
|
2025-02-23 19:23:49 +01:00
|
|
|
{
|
|
|
|
Pp_show_msg( pp, 0 );
|
|
|
|
fprintf( stderr, "CRC mismatch; stored %08X, computed %08X\n",
|
|
|
|
td_crc, crc );
|
|
|
|
}
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
2025-02-23 19:23:49 +01:00
|
|
|
td_size = Ft_get_data_size( trailer );
|
|
|
|
if( td_size != data_size )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
error = true;
|
|
|
|
if( verbosity >= 0 )
|
2025-02-23 19:23:49 +01:00
|
|
|
{
|
|
|
|
Pp_show_msg( pp, 0 );
|
|
|
|
fprintf( stderr, "Data size mismatch; stored %llu (0x%llX), computed %llu (0x%llX)\n",
|
|
|
|
td_size, td_size, data_size, data_size );
|
|
|
|
}
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
2025-02-23 19:23:49 +01:00
|
|
|
tm_size = Ft_get_member_size( trailer );
|
|
|
|
if( tm_size != member_size )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
error = true;
|
|
|
|
if( verbosity >= 0 )
|
2025-02-23 19:23:49 +01:00
|
|
|
{
|
|
|
|
Pp_show_msg( pp, 0 );
|
|
|
|
fprintf( stderr, "Member size mismatch; stored %llu (0x%llX), computed %llu (0x%llX)\n",
|
|
|
|
tm_size, tm_size, member_size, member_size );
|
|
|
|
}
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
|
|
|
if( error ) return 2;
|
2025-02-23 19:23:49 +01:00
|
|
|
if( verbosity >= 2 )
|
|
|
|
{
|
|
|
|
if( verbosity >= 4 ) show_header( dictionary_size );
|
|
|
|
if( data_size == 0 || member_size == 0 )
|
|
|
|
fputs( "no data compressed. ", stderr );
|
|
|
|
else
|
|
|
|
fprintf( stderr, "%6.3f:1, %5.2f%% ratio, %5.2f%% saved. ",
|
|
|
|
(double)data_size / member_size,
|
|
|
|
( 100.0 * member_size ) / data_size,
|
|
|
|
100.0 - ( ( 100.0 * member_size ) / data_size ) );
|
|
|
|
if( verbosity >= 4 ) fprintf( stderr, "CRC %08X, ", td_crc );
|
|
|
|
if( verbosity >= 3 )
|
|
|
|
fprintf( stderr, "decompressed %9llu, compressed %8llu. ",
|
|
|
|
data_size, member_size );
|
|
|
|
}
|
2025-02-23 19:16:13 +01:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int decompress( const int infd, struct Pretty_print * const pp,
|
2025-02-23 19:23:49 +01:00
|
|
|
const bool ignore_trailing, const bool loose_trailing,
|
|
|
|
const bool testing )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
uint64_t unpackSize = 0;
|
|
|
|
CLzmaDec decoder;
|
|
|
|
uint8_t inBuf[IN_BUF_SIZE];
|
|
|
|
int inPos = 0, inSize = 0;
|
|
|
|
int retval = 0;
|
|
|
|
bool lzip_mode = true;
|
|
|
|
bool first_member;
|
2025-02-23 19:17:42 +01:00
|
|
|
uint8_t raw_props[lzma_header_size];
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
for( first_member = true; ; first_member = false )
|
|
|
|
{
|
2025-02-23 19:21:39 +01:00
|
|
|
int i, size;
|
|
|
|
unsigned dictionary_size;
|
2025-02-23 19:16:13 +01:00
|
|
|
File_header header;
|
2025-02-23 19:17:42 +01:00
|
|
|
if( inSize - inPos < lzma_header_size &&
|
2025-02-23 19:16:13 +01:00
|
|
|
!read_inbuf( infd, inBuf, &inPos, &inSize ) ) return 1;
|
2025-02-23 19:21:39 +01:00
|
|
|
size = inSize - inPos;
|
|
|
|
for( i = 0; i < size && i < Fh_size; ++i )
|
|
|
|
raw_props[i] = header[i] = inBuf[inPos++];
|
|
|
|
if( size <= Fh_size ) /* End Of File */
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
2025-02-23 19:23:49 +01:00
|
|
|
if( first_member )
|
|
|
|
{ show_file_error( pp->name, "File ends unexpectedly at member header.", 0 );
|
|
|
|
retval = 2; }
|
|
|
|
else if( Fh_verify_prefix( header, size ) )
|
|
|
|
{ Pp_show_msg( pp, "Truncated header in multimember file." );
|
2025-02-23 19:17:42 +01:00
|
|
|
retval = 2; }
|
2025-02-23 19:22:52 +01:00
|
|
|
else if( size > 0 && !ignore_trailing )
|
2025-02-23 19:23:49 +01:00
|
|
|
{ Pp_show_msg( pp, trailing_msg ); retval = 2; }
|
2025-02-23 19:16:13 +01:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
if( !Fh_verify_magic( header ) )
|
|
|
|
{
|
2025-02-23 19:21:39 +01:00
|
|
|
if( !first_member )
|
|
|
|
{
|
2025-02-23 19:23:49 +01:00
|
|
|
if( !loose_trailing && Fh_verify_corrupt( header ) )
|
|
|
|
{ Pp_show_msg( pp, "Corrupt header in multimember file." );
|
|
|
|
retval = 2; }
|
|
|
|
else if( !ignore_trailing )
|
|
|
|
{ Pp_show_msg( pp, trailing_msg ); retval = 2; }
|
2025-02-23 19:21:39 +01:00
|
|
|
break;
|
|
|
|
}
|
2025-02-23 19:17:42 +01:00
|
|
|
if( inSize - inPos >= lzma_header_size - Fh_size ) /* try lzma-alone */
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
2025-02-23 19:17:42 +01:00
|
|
|
for( i = Fh_size; i < lzma_header_size; ++i )
|
|
|
|
raw_props[i] = inBuf[inPos++];
|
2025-02-23 19:16:13 +01:00
|
|
|
if( ( raw_props[12] == 0 || raw_props[12] == 0xFF ) &&
|
|
|
|
raw_props[12] == raw_props[11] && raw_props[0] < (9 * 5 * 5) )
|
2025-02-23 19:21:39 +01:00
|
|
|
{
|
2025-02-23 19:16:13 +01:00
|
|
|
lzip_mode = false;
|
2025-02-23 19:21:39 +01:00
|
|
|
dictionary_size = 0;
|
|
|
|
for( i = 4; i >= 1; --i )
|
|
|
|
{ dictionary_size <<= 8; dictionary_size += raw_props[i]; }
|
|
|
|
for( i = 7; i >= 0; --i )
|
|
|
|
{ unpackSize <<= 8; unpackSize += raw_props[LZMA_PROPS_SIZE+i]; }
|
|
|
|
}
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
|
|
|
if( lzip_mode )
|
|
|
|
{
|
2025-02-23 19:22:52 +01:00
|
|
|
show_file_error( pp->name,
|
|
|
|
"Bad magic number (file not in lzip format).", 0 );
|
2025-02-23 19:16:13 +01:00
|
|
|
retval = 2; break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if( lzip_mode )
|
|
|
|
{
|
|
|
|
int ds, i;
|
|
|
|
if( !Fh_verify_version( header ) )
|
|
|
|
{
|
|
|
|
if( verbosity >= 0 )
|
|
|
|
{ Pp_show_msg( pp, 0 );
|
|
|
|
fprintf( stderr, "Version %d member format not supported.\n",
|
|
|
|
Fh_version( header ) ); }
|
|
|
|
retval = 2; break;
|
|
|
|
}
|
2025-02-23 19:20:22 +01:00
|
|
|
dictionary_size = Fh_get_dictionary_size( header );
|
2025-02-23 19:21:39 +01:00
|
|
|
if( !isvalid_ds( dictionary_size ) )
|
2025-02-23 19:20:22 +01:00
|
|
|
{ Pp_show_msg( pp, "Invalid dictionary size in member header." );
|
2025-02-23 19:16:13 +01:00
|
|
|
retval = 2; break; }
|
|
|
|
|
|
|
|
raw_props[0] = 93; /* (45 * 2) + (9 * 0) + 3 */
|
2025-02-23 19:20:22 +01:00
|
|
|
ds = dictionary_size;
|
2025-02-23 19:16:13 +01:00
|
|
|
for( i = 1; i <= 4; ++i ) { raw_props[i] = ds & 0xFF; ds >>= 8; }
|
|
|
|
}
|
|
|
|
|
|
|
|
if( verbosity >= 2 || ( verbosity == 1 && first_member ) )
|
2025-02-23 19:23:49 +01:00
|
|
|
Pp_show_msg( pp, 0 );
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
if( !LzmaDec_Init( &decoder, raw_props ) )
|
2025-02-23 19:21:39 +01:00
|
|
|
{ Pp_show_msg( pp, "Not enough memory." ); return 1; }
|
2025-02-23 19:16:13 +01:00
|
|
|
if( lzip_mode )
|
2025-02-23 19:23:49 +01:00
|
|
|
retval = lzip_decode( &decoder, infd, pp, inBuf, &inPos, &inSize,
|
|
|
|
dictionary_size );
|
2025-02-23 19:16:13 +01:00
|
|
|
else
|
2025-02-23 19:23:49 +01:00
|
|
|
retval = lzma_decode( unpackSize, &decoder, infd, inBuf, &inPos,
|
|
|
|
&inSize, dictionary_size, testing );
|
2025-02-23 19:16:13 +01:00
|
|
|
LzmaDec_Free(&decoder);
|
|
|
|
if( retval != 0 || !lzip_mode ) break;
|
|
|
|
if( verbosity >= 2 )
|
2025-02-23 19:21:39 +01:00
|
|
|
{ fputs( testing ? "ok\n" : "done\n", stderr ); Pp_reset( pp ); }
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
|
|
|
if( lzip_mode && verbosity == 1 && retval == 0 )
|
2025-02-23 19:21:39 +01:00
|
|
|
fputs( testing ? "ok\n" : "done\n", stderr );
|
2025-02-23 19:16:13 +01:00
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
void signal_handler( int sig )
|
|
|
|
{
|
|
|
|
if( sig ) {} /* keep compiler happy */
|
|
|
|
show_error( "Control-C or similar caught, quitting.", 0, false );
|
|
|
|
cleanup_and_fail( 1 );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void set_signals( void )
|
|
|
|
{
|
|
|
|
signal( SIGHUP, signal_handler );
|
|
|
|
signal( SIGINT, signal_handler );
|
|
|
|
signal( SIGTERM, signal_handler );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:20:22 +01:00
|
|
|
CRC32 crc32;
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
|
2025-02-23 19:20:22 +01:00
|
|
|
/* Returns the number of bytes really read.
|
|
|
|
If (returned value < size) and (errno == 0), means EOF was reached.
|
|
|
|
*/
|
|
|
|
int readblock( const int fd, uint8_t * const buf, const int size )
|
|
|
|
{
|
|
|
|
int sz = 0;
|
|
|
|
errno = 0;
|
|
|
|
while( sz < size )
|
|
|
|
{
|
|
|
|
const int n = read( fd, buf + sz, size - sz );
|
|
|
|
if( n > 0 ) sz += n;
|
|
|
|
else if( n == 0 ) break; /* EOF */
|
|
|
|
else if( errno != EINTR ) break;
|
|
|
|
errno = 0;
|
|
|
|
}
|
|
|
|
return sz;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* Returns the number of bytes really written.
|
|
|
|
If (returned value < size), it is always an error.
|
|
|
|
*/
|
|
|
|
int writeblock( const int fd, const uint8_t * const buf, const int size )
|
|
|
|
{
|
|
|
|
int sz = 0;
|
|
|
|
errno = 0;
|
|
|
|
while( sz < size )
|
|
|
|
{
|
|
|
|
const int n = write( fd, buf + sz, size - sz );
|
|
|
|
if( n > 0 ) sz += n;
|
|
|
|
else if( n < 0 && errno != EINTR ) break;
|
|
|
|
errno = 0;
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
2025-02-23 19:20:22 +01:00
|
|
|
return sz;
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
void show_error( const char * const msg, const int errcode, const bool help )
|
|
|
|
{
|
2025-02-23 19:21:39 +01:00
|
|
|
if( verbosity < 0 ) return;
|
|
|
|
if( msg && msg[0] )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
2025-02-23 19:21:39 +01:00
|
|
|
fprintf( stderr, "%s: %s", program_name, msg );
|
|
|
|
if( errcode > 0 ) fprintf( stderr, ": %s", strerror( errcode ) );
|
|
|
|
fputc( '\n', stderr );
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
2025-02-23 19:21:39 +01:00
|
|
|
if( help )
|
|
|
|
fprintf( stderr, "Try '%s --help' for more information.\n",
|
|
|
|
invocation_name );
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:22:52 +01:00
|
|
|
void show_file_error( const char * const filename, const char * const msg,
|
|
|
|
const int errcode )
|
|
|
|
{
|
|
|
|
if( verbosity < 0 ) return;
|
|
|
|
fprintf( stderr, "%s: %s: %s", program_name, filename, msg );
|
|
|
|
if( errcode > 0 ) fprintf( stderr, ": %s", strerror( errcode ) );
|
|
|
|
fputc( '\n', stderr );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2025-02-23 19:16:13 +01:00
|
|
|
void internal_error( const char * const msg )
|
|
|
|
{
|
|
|
|
if( verbosity >= 0 )
|
2025-02-23 19:20:22 +01:00
|
|
|
fprintf( stderr, "%s: internal error: %s\n", program_name, msg );
|
2025-02-23 19:16:13 +01:00
|
|
|
exit( 3 );
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
int main( const int argc, const char * const argv[] )
|
|
|
|
{
|
|
|
|
/* Mapping from gzip/bzip2 style 1..9 compression modes
|
|
|
|
to the corresponding LZMA compression modes. */
|
|
|
|
const struct Lzma_options option_mapping[] =
|
|
|
|
{
|
|
|
|
{ 1 << 20, 5 }, /* -0 */
|
|
|
|
{ 1 << 20, 5 }, /* -1 */
|
|
|
|
{ 3 << 19, 6 }, /* -2 */
|
|
|
|
{ 1 << 21, 8 }, /* -3 */
|
|
|
|
{ 3 << 20, 12 }, /* -4 */
|
|
|
|
{ 1 << 22, 20 }, /* -5 */
|
|
|
|
{ 1 << 23, 36 }, /* -6 */
|
|
|
|
{ 1 << 24, 68 }, /* -7 */
|
|
|
|
{ 3 << 23, 132 }, /* -8 */
|
|
|
|
{ 1 << 25, 273 } }; /* -9 */
|
|
|
|
struct Lzma_options encoder_options = option_mapping[6]; /* default = "-6" */
|
|
|
|
const char * default_output_filename = "";
|
|
|
|
const char ** filenames = 0;
|
|
|
|
int num_filenames = 0;
|
|
|
|
enum Mode program_mode = m_compress;
|
|
|
|
int argind = 0;
|
2025-02-23 19:23:49 +01:00
|
|
|
int failed_tests = 0;
|
2025-02-23 19:16:13 +01:00
|
|
|
int retval = 0;
|
|
|
|
int i;
|
|
|
|
bool filenames_given = false;
|
|
|
|
bool force = false;
|
2025-02-23 19:21:39 +01:00
|
|
|
bool ignore_trailing = true;
|
2025-02-23 19:16:13 +01:00
|
|
|
bool keep_input_files = false;
|
2025-02-23 19:23:49 +01:00
|
|
|
bool loose_trailing = false;
|
2025-02-23 19:16:13 +01:00
|
|
|
bool recompress = false;
|
2025-02-23 19:22:52 +01:00
|
|
|
bool stdin_used = false;
|
2025-02-23 19:16:13 +01:00
|
|
|
bool to_stdout = false;
|
|
|
|
struct Pretty_print pp;
|
|
|
|
|
2025-02-23 19:23:49 +01:00
|
|
|
enum { opt_lt = 256 };
|
2025-02-23 19:16:13 +01:00
|
|
|
const struct ap_Option options[] =
|
|
|
|
{
|
2025-02-23 19:23:49 +01:00
|
|
|
{ '0', "fast", ap_no },
|
|
|
|
{ '1', 0, ap_no },
|
|
|
|
{ '2', 0, ap_no },
|
|
|
|
{ '3', 0, ap_no },
|
|
|
|
{ '4', 0, ap_no },
|
|
|
|
{ '5', 0, ap_no },
|
|
|
|
{ '6', 0, ap_no },
|
|
|
|
{ '7', 0, ap_no },
|
|
|
|
{ '8', 0, ap_no },
|
|
|
|
{ '9', "best", ap_no },
|
|
|
|
{ 'a', "trailing-error", ap_no },
|
|
|
|
{ 'b', "member-size", ap_yes },
|
|
|
|
{ 'c', "stdout", ap_no },
|
|
|
|
{ 'd', "decompress", ap_no },
|
|
|
|
{ 'f', "force", ap_no },
|
|
|
|
{ 'F', "recompress", ap_no },
|
|
|
|
{ 'h', "help", ap_no },
|
|
|
|
{ 'k', "keep", ap_no },
|
|
|
|
{ 'm', "match-length", ap_yes },
|
|
|
|
{ 'n', "threads", ap_yes },
|
|
|
|
{ 'o', "output", ap_yes },
|
|
|
|
{ 'q', "quiet", ap_no },
|
|
|
|
{ 's', "dictionary-size", ap_yes },
|
|
|
|
{ 'S', "volume-size", ap_yes },
|
|
|
|
{ 't', "test", ap_no },
|
|
|
|
{ 'v', "verbose", ap_no },
|
|
|
|
{ 'V', "version", ap_no },
|
|
|
|
{ opt_lt, "loose-trailing", ap_no },
|
|
|
|
{ 0 , 0, ap_no } };
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
struct Arg_parser parser;
|
|
|
|
|
|
|
|
invocation_name = argv[0];
|
|
|
|
CRC32_init();
|
|
|
|
|
|
|
|
if( !ap_init( &parser, argc, argv, options, 0 ) )
|
2025-02-23 19:20:22 +01:00
|
|
|
{ show_error( "Not enough memory.", 0, false ); return 1; }
|
2025-02-23 19:16:13 +01:00
|
|
|
if( ap_error( &parser ) ) /* bad option */
|
|
|
|
{ show_error( ap_error( &parser ), 0, true ); return 1; }
|
|
|
|
|
|
|
|
for( ; argind < ap_arguments( &parser ); ++argind )
|
|
|
|
{
|
|
|
|
const int code = ap_code( &parser, argind );
|
|
|
|
const char * const arg = ap_argument( &parser, argind );
|
|
|
|
if( !code ) break; /* no more options */
|
|
|
|
switch( code )
|
|
|
|
{
|
2025-02-23 19:20:22 +01:00
|
|
|
case '0': case '1': case '2': case '3': case '4':
|
2025-02-23 19:16:13 +01:00
|
|
|
case '5': case '6': case '7': case '8': case '9':
|
|
|
|
encoder_options = option_mapping[code-'0']; break;
|
2025-02-23 19:21:39 +01:00
|
|
|
case 'a': ignore_trailing = false; break;
|
2025-02-23 19:16:13 +01:00
|
|
|
case 'b': break;
|
|
|
|
case 'c': to_stdout = true; break;
|
|
|
|
case 'd': program_mode = m_decompress; break;
|
|
|
|
case 'f': force = true; break;
|
|
|
|
case 'F': recompress = true; break;
|
|
|
|
case 'h': show_help(); return 0;
|
|
|
|
case 'k': keep_input_files = true; break;
|
|
|
|
case 'm': encoder_options.match_len_limit =
|
|
|
|
getnum( arg, min_match_len_limit, max_match_len ); break;
|
2025-02-23 19:16:35 +01:00
|
|
|
case 'n': break;
|
2025-02-23 19:16:13 +01:00
|
|
|
case 'o': default_output_filename = arg; break;
|
|
|
|
case 'q': verbosity = -1; break;
|
|
|
|
case 's': encoder_options.dictionary_size = get_dict_size( arg );
|
|
|
|
break;
|
|
|
|
case 'S': break;
|
|
|
|
case 't': program_mode = m_test; break;
|
|
|
|
case 'v': if( verbosity < 4 ) ++verbosity; break;
|
|
|
|
case 'V': show_version(); return 0;
|
2025-02-23 19:23:49 +01:00
|
|
|
case opt_lt: loose_trailing = true; break;
|
2025-02-23 19:20:22 +01:00
|
|
|
default : internal_error( "uncaught option." );
|
2025-02-23 19:16:13 +01:00
|
|
|
}
|
|
|
|
} /* end process options */
|
|
|
|
|
|
|
|
#if defined(__MSVCRT__) || defined(__OS2__)
|
|
|
|
setmode( STDIN_FILENO, O_BINARY );
|
|
|
|
setmode( STDOUT_FILENO, O_BINARY );
|
|
|
|
#endif
|
|
|
|
|
|
|
|
num_filenames = max( 1, ap_arguments( &parser ) - argind );
|
|
|
|
filenames = resize_buffer( filenames, num_filenames * sizeof filenames[0] );
|
|
|
|
filenames[0] = "-";
|
|
|
|
|
|
|
|
for( i = 0; argind + i < ap_arguments( &parser ); ++i )
|
|
|
|
{
|
|
|
|
filenames[i] = ap_argument( &parser, argind + i );
|
|
|
|
if( strcmp( filenames[i], "-" ) != 0 ) filenames_given = true;
|
|
|
|
}
|
|
|
|
|
2025-02-23 19:22:52 +01:00
|
|
|
if( program_mode == m_test )
|
|
|
|
outfd = -1;
|
|
|
|
|
2025-02-23 19:16:13 +01:00
|
|
|
if( !to_stdout && program_mode != m_test &&
|
|
|
|
( filenames_given || default_output_filename[0] ) )
|
|
|
|
set_signals();
|
|
|
|
|
2025-02-23 19:23:49 +01:00
|
|
|
Pp_init( &pp, filenames, num_filenames );
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
output_filename = resize_buffer( output_filename, 1 );
|
|
|
|
for( i = 0; i < num_filenames; ++i )
|
|
|
|
{
|
2025-02-23 19:22:52 +01:00
|
|
|
const char * input_filename = "";
|
2025-02-23 19:23:49 +01:00
|
|
|
int infd;
|
2025-02-23 19:16:13 +01:00
|
|
|
int tmp;
|
|
|
|
struct stat in_stats;
|
|
|
|
const struct stat * in_statsp;
|
|
|
|
output_filename[0] = 0;
|
|
|
|
|
|
|
|
if( !filenames[i][0] || strcmp( filenames[i], "-" ) == 0 )
|
|
|
|
{
|
2025-02-23 19:21:39 +01:00
|
|
|
if( stdin_used ) continue; else stdin_used = true;
|
2025-02-23 19:16:13 +01:00
|
|
|
infd = STDIN_FILENO;
|
|
|
|
if( program_mode != m_test )
|
|
|
|
{
|
|
|
|
if( to_stdout || !default_output_filename[0] )
|
|
|
|
outfd = STDOUT_FILENO;
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if( program_mode == m_compress )
|
2025-02-23 19:23:49 +01:00
|
|
|
set_c_outname( default_output_filename, false );
|
2025-02-23 19:16:13 +01:00
|
|
|
else
|
|
|
|
{
|
|
|
|
output_filename = resize_buffer( output_filename,
|
2025-02-23 19:23:49 +01:00
|
|
|
strlen( default_output_filename ) + 1 );
|
2025-02-23 19:16:13 +01:00
|
|
|
strcpy( output_filename, default_output_filename );
|
|
|
|
}
|
2025-02-23 19:21:39 +01:00
|
|
|
if( !open_outstream( force, true ) )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
if( retval < 1 ) retval = 1;
|
2025-02-23 19:23:49 +01:00
|
|
|
close( infd );
|
2025-02-23 19:16:13 +01:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
2025-02-23 19:22:52 +01:00
|
|
|
const int eindex = extension_index( input_filename = filenames[i] );
|
2025-02-23 19:16:13 +01:00
|
|
|
infd = open_instream( input_filename, &in_stats, program_mode,
|
|
|
|
eindex, recompress, to_stdout );
|
|
|
|
if( infd < 0 ) { if( retval < 1 ) retval = 1; continue; }
|
|
|
|
if( program_mode != m_test )
|
|
|
|
{
|
|
|
|
if( to_stdout ) outfd = STDOUT_FILENO;
|
|
|
|
else
|
|
|
|
{
|
|
|
|
if( program_mode == m_compress )
|
2025-02-23 19:23:49 +01:00
|
|
|
set_c_outname( input_filename, true );
|
2025-02-23 19:16:13 +01:00
|
|
|
else set_d_outname( input_filename, eindex );
|
2025-02-23 19:21:39 +01:00
|
|
|
if( !open_outstream( force, false ) )
|
2025-02-23 19:16:13 +01:00
|
|
|
{
|
|
|
|
if( retval < 1 ) retval = 1;
|
2025-02-23 19:23:49 +01:00
|
|
|
close( infd );
|
2025-02-23 19:16:13 +01:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2025-02-23 19:22:52 +01:00
|
|
|
Pp_set_name( &pp, input_filename );
|
|
|
|
if( !check_tty( pp.name, infd, program_mode ) )
|
2025-02-23 19:21:39 +01:00
|
|
|
{
|
|
|
|
if( retval < 1 ) retval = 1;
|
2025-02-23 19:23:49 +01:00
|
|
|
if( program_mode == m_test ) { close( infd ); continue; }
|
2025-02-23 19:21:39 +01:00
|
|
|
cleanup_and_fail( retval );
|
|
|
|
}
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
in_statsp = input_filename[0] ? &in_stats : 0;
|
|
|
|
if( program_mode == m_compress )
|
2025-02-23 19:22:52 +01:00
|
|
|
tmp = compress( &encoder_options, &pp, infd );
|
2025-02-23 19:16:13 +01:00
|
|
|
else
|
2025-02-23 19:23:49 +01:00
|
|
|
tmp = decompress( infd, &pp, ignore_trailing,
|
|
|
|
loose_trailing, program_mode == m_test );
|
2025-02-23 19:16:13 +01:00
|
|
|
if( tmp > retval ) retval = tmp;
|
2025-02-23 19:23:49 +01:00
|
|
|
if( tmp )
|
|
|
|
{ if( program_mode != m_test ) cleanup_and_fail( retval );
|
|
|
|
else ++failed_tests; }
|
2025-02-23 19:16:13 +01:00
|
|
|
|
|
|
|
if( delete_output_on_interrupt )
|
|
|
|
close_and_set_permissions( in_statsp );
|
|
|
|
if( input_filename[0] )
|
|
|
|
{
|
2025-02-23 19:23:49 +01:00
|
|
|
close( infd );
|
2025-02-23 19:16:13 +01:00
|
|
|
if( !keep_input_files && !to_stdout && program_mode != m_test )
|
|
|
|
remove( input_filename );
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if( outfd >= 0 && close( outfd ) != 0 )
|
|
|
|
{
|
2025-02-23 19:23:49 +01:00
|
|
|
show_error( "Error closing stdout", errno, false );
|
2025-02-23 19:16:13 +01:00
|
|
|
if( retval < 1 ) retval = 1;
|
|
|
|
}
|
2025-02-23 19:23:49 +01:00
|
|
|
if( failed_tests > 0 && verbosity >= 1 && num_filenames > 1 )
|
|
|
|
fprintf( stderr, "%s: warning: %d %s failed the test.\n",
|
|
|
|
program_name, failed_tests,
|
|
|
|
( failed_tests == 1 ) ? "file" : "files" );
|
2025-02-23 19:16:13 +01:00
|
|
|
free( output_filename );
|
|
|
|
free( filenames );
|
|
|
|
ap_free( &parser );
|
|
|
|
return retval;
|
|
|
|
}
|