/* Tarlz - Archiver with multimember lzip compression
Copyright (C) 2013-2018 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 2 of the License, or
(at your option) any later version.
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. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see .
*/
/*
Exit status: 0 for a normal exit, 1 for environmental problems
(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 tarlz to panic.
*/
#define _FILE_OFFSET_BITS 64
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#if defined(__OS2__)
#include
#endif
#include
#include "arg_parser.h"
#include "tarlz.h"
#ifndef O_BINARY
#define O_BINARY 0
#endif
#if CHAR_BIT != 8
#error "Environments where CHAR_BIT != 8 are not supported."
#endif
int verbosity = 0;
namespace {
const char * const program_name = "tarlz";
const char * const program_year = "2018";
const char * invocation_name = 0;
enum Mode { m_none, m_append, m_concatenate, m_create, m_extract, m_list };
void show_help()
{
std::printf( "Tarlz is a small and simple implementation of the tar archiver. By default\n"
"tarlz creates, lists and extracts archives in a simplified posix pax format\n"
"compressed with lzip on a per file basis. Each tar member is compressed in\n"
"its own lzip member, as well as the end-of-file blocks. This method is fully\n"
"backward compatible with standard tar tools like GNU tar, which treat the\n"
"resulting multimember tar.lz archive like any other tar.lz archive. Tarlz\n"
"can append files to the end of such compressed archives.\n"
"\nThe tarlz file format is a safe posix-style backup format. In case of\n"
"corruption, tarlz can extract all the undamaged members from the tar.lz\n"
"archive, skipping over the damaged members, just like the standard\n"
"(uncompressed) tar. Moreover, the option '--keep-damaged' can be used to\n"
"recover as much data as possible from each damaged member, and lziprecover\n"
"can be used to recover some of the damaged members.\n"
"\nUsage: %s [options] [files]\n", invocation_name );
std::printf( "\nOptions:\n"
" -h, --help display this help and exit\n"
" -V, --version output version information and exit\n"
" -A, --concatenate append tar.lz archives to the end of an archive\n"
" -c, --create create a new archive\n"
" -C, --directory= change to directory \n"
" -f, --file= use archive file \n"
" -q, --quiet suppress all messages\n"
" -r, --append append files to the end of an archive\n"
" -t, --list list the contents of an archive\n"
" -v, --verbose verbosely list files processed\n"
" -x, --extract extract files from an archive\n"
" -0 .. -9 set compression level [default 6]\n"
" --asolid create solidly compressed appendable archive\n"
" --dsolid create per-directory compressed archive\n"
" --no-solid create per-file compressed archive (default)\n"
" --solid create solidly compressed archive\n"
" --anonymous equivalent to '--owner=root --group=root'\n"
" --owner= use name/ID for files added\n"
" --group= use name/ID for files added\n"
" --keep-damaged don't delete partially extracted files\n"
" --missing-crc exit with error status if missing extended CRC\n"
// " --permissive allow repeated extended headers and records\n"
" --uncompressed don't compress the archive created\n"
"\nExit status: 0 for a normal exit, 1 for environmental problems (file\n"
"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 tarlz to panic.\n"
"\nReport bugs to lzip-bug@nongnu.org\n"
"Tarlz home page: http://www.nongnu.org/lzip/tarlz.html\n" );
}
void show_version()
{
std::printf( "%s %s\n", program_name, PROGVERSION );
std::printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year );
std::printf( "Using lzlib %s\n", LZ_version() );
std::printf( "License GPLv2+: GNU GPL version 2 or later \n"
"This is free software: you are free to change and redistribute it.\n"
"There is NO WARRANTY, to the extent permitted by law.\n" );
}
unsigned long long getnum( const char * const ptr,
const unsigned long long llimit,
const unsigned long long ulimit )
{
char * tail;
errno = 0;
unsigned long long result = strtoull( ptr, &tail, 0 );
if( tail == ptr )
{
show_error( "Bad or missing numerical argument.", 0, true );
std::exit( 1 );
}
if( !errno && tail[0] )
{
const unsigned factor = ( tail[1] == 'i' ) ? 1024 : 1000;
int exponent = 0; // 0 = bad multiplier
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;
case 'K': if( factor == 1024 ) exponent = 1; break;
case 'k': if( factor == 1000 ) exponent = 1; break;
}
if( exponent <= 0 )
{
show_error( "Bad multiplier in numerical argument.", 0, true );
std::exit( 1 );
}
for( int 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." );
std::exit( 1 );
}
return result;
}
void set_mode( Mode & program_mode, const Mode new_mode )
{
if( program_mode != m_none && program_mode != new_mode )
{
show_error( "Only one operation can be specified.", 0, true );
std::exit( 1 );
}
program_mode = new_mode;
}
void set_owner( const char * const arg )
{
const struct passwd * const pw = getpwnam( arg );
if( pw ) cl_owner = pw->pw_uid;
else if( std::isdigit( arg[0] ) ) cl_owner = getnum( arg, 0, INT_MAX );
else { show_file_error( arg, "Invalid owner" ); std::exit( 1 ); }
}
void set_group( const char * const arg )
{
const struct group * const gr = getgrnam( arg );
if( gr ) cl_group = gr->gr_gid;
else if( std::isdigit( arg[0] ) ) cl_group = getnum( arg, 0, INT_MAX );
else { show_file_error( arg, "Invalid group" ); std::exit( 1 ); }
}
} // end namespace
int open_instream( const std::string & name )
{
const int infd = open( name.c_str(), O_RDONLY | O_BINARY );
if( infd < 0 )
show_file_error( name.c_str(), "Can't open for reading", errno );
return infd;
}
int open_outstream( const std::string & name, const bool create )
{
const int flags = (create ? O_CREAT | O_WRONLY | O_TRUNC : O_RDWR) | O_BINARY;
const mode_t outfd_mode = S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH;
const int outfd = open( name.c_str(), flags, outfd_mode );
if( outfd < 0 )
show_file_error( name.c_str(), create ?
"Can't create file" : "Error opening file", errno );
return outfd;
}
/* 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;
}
return sz;
}
void show_error( const char * const msg, const int errcode, const bool help )
{
if( verbosity < 0 ) return;
if( msg && msg[0] )
std::fprintf( stderr, "%s: %s%s%s\n", program_name, msg,
( errcode > 0 ) ? ": " : "",
( errcode > 0 ) ? std::strerror( errcode ) : "" );
if( help )
std::fprintf( stderr, "Try '%s --help' for more information.\n",
invocation_name );
}
void show_file_error( const char * const filename, const char * const msg,
const int errcode )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: %s: %s%s%s\n", program_name, filename, msg,
( errcode > 0 ) ? ": " : "",
( errcode > 0 ) ? std::strerror( errcode ) : "" );
}
void internal_error( const char * const msg )
{
if( verbosity >= 0 )
std::fprintf( stderr, "%s: internal error: %s\n", program_name, msg );
std::exit( 3 );
}
int main( const int argc, const char * const argv[] )
{
std::string archive_name;
Mode program_mode = m_none;
int level = 6; // compression level, < 0 = uncompressed
bool keep_damaged = false;
bool missing_crc = false;
bool permissive = false;
invocation_name = argv[0];
if( LZ_version()[0] < '1' )
{ show_error( "Bad library version. At least lzlib 1.0 is required." );
return 1; }
enum { opt_ano = 256, opt_aso, opt_crc, opt_dso, opt_grp, opt_kd, opt_nso,
opt_own, opt_per, opt_sol, opt_un };
const Arg_parser::Option options[] =
{
{ '0', 0, Arg_parser::no },
{ '1', 0, Arg_parser::no },
{ '2', 0, Arg_parser::no },
{ '3', 0, Arg_parser::no },
{ '4', 0, Arg_parser::no },
{ '5', 0, Arg_parser::no },
{ '6', 0, Arg_parser::no },
{ '7', 0, Arg_parser::no },
{ '8', 0, Arg_parser::no },
{ '9', 0, Arg_parser::no },
{ 'A', "concatenate", Arg_parser::no },
{ 'c', "create", Arg_parser::no },
{ 'C', "directory", Arg_parser::yes },
{ 'f', "file", Arg_parser::yes },
{ 'h', "help", Arg_parser::no },
{ 'H', "format", Arg_parser::yes },
{ 'q', "quiet", Arg_parser::no },
{ 'r', "append", Arg_parser::no },
{ 't', "list", Arg_parser::no },
{ 'v', "verbose", Arg_parser::no },
{ 'V', "version", Arg_parser::no },
{ 'x', "extract", Arg_parser::no },
{ opt_ano, "anonymous", Arg_parser::no },
{ opt_aso, "asolid", Arg_parser::no },
{ opt_dso, "dsolid", Arg_parser::no },
{ opt_grp, "group", Arg_parser::yes },
{ opt_kd, "keep-damaged", Arg_parser::no },
{ opt_crc, "missing-crc", Arg_parser::no },
{ opt_nso, "no-solid", Arg_parser::no },
{ opt_own, "owner", Arg_parser::yes },
{ opt_per, "permissive", Arg_parser::no },
{ opt_sol, "solid", Arg_parser::no },
{ opt_un, "uncompressed", Arg_parser::no },
{ 0 , 0, Arg_parser::no } };
const Arg_parser parser( argc, argv, options, true );
if( parser.error().size() ) // bad option
{ show_error( parser.error().c_str(), 0, true ); return 1; }
int filenames = 0;
for( int argind = 0; argind < parser.arguments(); ++argind )
{
const int code = parser.code( argind );
if( !code ) { ++filenames; continue; } // skip non-options
const std::string & sarg = parser.argument( argind );
const char * const arg = sarg.c_str();
switch( code )
{
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7': case '8': case '9':
level = code - '0'; break;
case 'A': set_mode( program_mode, m_concatenate ); break;
case 'c': set_mode( program_mode, m_create ); break;
case 'C': break; // skip chdir
case 'f': if( sarg != "-" ) archive_name = sarg; break;
case 'h': show_help(); return 0;
case 'H': break; // ignore format
case 'q': verbosity = -1; break;
case 'r': set_mode( program_mode, m_append ); break;
case 't': set_mode( program_mode, m_list ); break;
case 'v': if( verbosity < 4 ) ++verbosity; break;
case 'V': show_version(); return 0;
case 'x': set_mode( program_mode, m_extract ); break;
case opt_ano: set_owner( "root" ); set_group( "root" ); break;
case opt_aso: cl_solid = 2; break;
case opt_crc: missing_crc = true; break;
case opt_dso: cl_solid = 1; break;
case opt_grp: set_group( arg ); break;
case opt_kd: keep_damaged = true; break;
case opt_nso: cl_solid = 0; break;
case opt_own: set_owner( arg ); break;
case opt_per: permissive = true; break;
case opt_sol: cl_solid = 3; break;
case opt_un: level = -1; break;
default : internal_error( "uncaught option" );
}
} // end process options
#if defined(__MSVCRT__) || defined(__OS2__)
setmode( STDIN_FILENO, O_BINARY );
setmode( STDOUT_FILENO, O_BINARY );
#endif
switch( program_mode )
{
case m_none: show_error( "Missing operation.", 0, true ); return 2;
case m_append:
case m_create: return encode( archive_name, parser, filenames, level,
program_mode == m_append );
case m_concatenate: return concatenate( archive_name, parser, filenames );
case m_extract:
case m_list: return decode( archive_name, parser, filenames,
keep_damaged, program_mode == m_list,
missing_crc, permissive );
}
}