diff options
Diffstat (limited to '')
| -rw-r--r-- | main.cc | 676 |
1 files changed, 676 insertions, 0 deletions
@@ -0,0 +1,676 @@ +/* Lziprecover - Data recovery tool for lzipped files + Copyright (C) 2009, 2010, 2011 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 3 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 <http://www.gnu.org/licenses/>. +*/ +/* + Return values: 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 lziprecover to panic. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include <algorithm> +#include <cerrno> +#include <climits> +#include <csignal> +#include <cstdio> +#include <cstdlib> +#include <cstring> +#include <string> +#include <vector> +#include <fcntl.h> +#include <stdint.h> +#include <unistd.h> +#include <utime.h> +#include <sys/stat.h> +#if defined(__MSVCRT__) +#define S_IRGRP 0 +#define S_IWGRP 0 +#define S_IROTH 0 +#define S_IWOTH 0 +#endif + +#include "arg_parser.h" +#include "lzip.h" +#include "decoder.h" + +#if CHAR_BIT != 8 +#error "Environments where CHAR_BIT != 8 are not supported." +#endif + + +namespace { + +const char * const Program_name = "Lziprecover"; +const char * const program_name = "lziprecover"; +const char * const program_year = "2011"; +const char * invocation_name = 0; + +#ifdef O_BINARY +const int o_binary = O_BINARY; +#else +const int o_binary = 0; +#endif + +struct { const char * from; const char * to; } const known_extensions[] = { + { ".lz", "" }, + { ".tlz", ".tar" }, + { 0, 0 } }; + +enum Mode { m_none, m_decompress, m_generate, m_merge, m_recover, m_repair, + m_split, m_test, m_update }; + +std::string output_filename; +int outfd = -1; +const mode_t usr_rw = S_IRUSR | S_IWUSR; +const mode_t all_rw = usr_rw | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH; +mode_t outfd_mode = usr_rw; +bool delete_output_on_interrupt = false; + + +void show_help() throw() + { + std::printf( "%s - Data recovery tool and decompressor for lzipped files.\n", Program_name ); + std::printf( "\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" + " -c, --stdout send decompressed output to standard output\n" + " -d, --decompress decompress\n" + " -f, --force overwrite existing output files\n" +// " -g, --generate-recover-file generate a recover file\n" + " -k, --keep keep (don't delete) input files\n" + " -m, --merge correct errors in file using several copies\n" + " -o, --output=<file> place the output into <file>\n" + " -q, --quiet suppress all messages\n" +// " -r, --recover correct errors in file using a recover file\n" + " -R, --repair try to repair a small error in file\n" + " -s, --split split a multimember file in single-member files\n" + " -t, --test test compressed file integrity\n" +// " -u, --update convert file from version 0 to version 1\n" + " -v, --verbose be verbose (a 2nd -v gives more)\n" + "\nReport bugs to lzip-bug@nongnu.org\n" + "Lziprecover home page: http://www.nongnu.org/lzip/lziprecover.html\n" ); + } + + +void show_version() throw() + { + std::printf( "%s %s\n", Program_name, PROGVERSION ); + std::printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year ); + std::printf( "License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>\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" ); + } + + +const char * format_num( long long num ) throw() + { + const char * const prefix[8] = + { "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" }; + enum { buf_size = 16, factor = 1024 }; + static char buf[buf_size]; + const char *p = ""; + bool exact = ( num % factor == 0 ); + + for( int i = 0; i < 8 && ( llabs( num ) > 9999 || + ( exact && llabs( num ) >= factor ) ); ++i ) + { num /= factor; if( num % factor != 0 ) exact = false; p = prefix[i]; } + snprintf( buf, buf_size, "%lld %s", num, p ); + return buf; + } + + +void set_mode( Mode & program_mode, const Mode new_mode ) throw() + { + 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; + } + + +int extension_index( const std::string & name ) throw() + { + for( int i = 0; known_extensions[i].from; ++i ) + { + const std::string ext( known_extensions[i].from ); + if( name.size() > ext.size() && + name.compare( name.size() - ext.size(), ext.size(), ext ) == 0 ) + return i; + } + return -1; + } + + +void set_d_outname( const std::string & name, const int i ) throw() + { + if( i >= 0 ) + { + const std::string from( known_extensions[i].from ); + if( name.size() > from.size() ) + { + output_filename.assign( name, 0, name.size() - from.size() ); + output_filename += known_extensions[i].to; + return; + } + } + output_filename = name; output_filename += ".out"; + if( verbosity >= 1 ) + std::fprintf( stderr, "%s: Can't guess original name for `%s' -- using `%s'.\n", + program_name, name.c_str(), output_filename.c_str() ); + } + + +bool open_outstream( const bool force ) throw() + { + int flags = O_CREAT | O_WRONLY | o_binary; + if( force ) flags |= O_TRUNC; else flags |= O_EXCL; + + outfd = open( output_filename.c_str(), flags, outfd_mode ); + if( outfd < 0 && verbosity >= 0 ) + { + if( errno == EEXIST ) + std::fprintf( stderr, "%s: Output file `%s' already exists, skipping.\n", + program_name, output_filename.c_str() ); + else + std::fprintf( stderr, "%s: Can't create output file `%s': %s.\n", + program_name, output_filename.c_str(), std::strerror( errno ) ); + } + return ( outfd >= 0 ); + } + + +bool check_tty( const int infd ) throw() + { + if( isatty( infd ) ) + { + show_error( "I won't read compressed data from a terminal.", 0, true ); + return false; + } + return true; + } + + +void cleanup_and_fail( const int retval ) throw() + { + if( delete_output_on_interrupt ) + { + delete_output_on_interrupt = false; + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Deleting output file `%s', if it exists.\n", + program_name, output_filename.c_str() ); + if( outfd >= 0 ) { close( outfd ); outfd = -1; } + if( std::remove( output_filename.c_str() ) != 0 && errno != ENOENT ) + show_error( "WARNING: deletion of output file (apparently) failed." ); + } + std::exit( retval ); + } + + + // Set permissions, owner and times. +void close_and_set_permissions( const struct stat * const in_statsp ) + { + bool warning = false; + if( in_statsp ) + { + // fchown will in many cases return with EPERM, which can be safely ignored. + if( ( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) != 0 && + errno != EPERM ) || + fchmod( outfd, in_statsp->st_mode ) != 0 ) warning = true; + } + if( close( outfd ) != 0 ) cleanup_and_fail( 1 ); + 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.c_str(), &t ) != 0 ) warning = true; + } + if( warning && verbosity >= 1 ) + show_error( "Can't change output file attributes." ); + } + + +std::string insert_fixed( std::string name ) throw() + { + if( name.size() > 4 && name.compare( name.size() - 4, 4, ".tlz" ) == 0 ) + name.insert( name.size() - 4, "_fixed" ); + else if( name.size() > 3 && name.compare( name.size() - 3, 3, ".lz" ) == 0 ) + name.insert( name.size() - 3, "_fixed" ); + else name += "_fixed.lz"; + return name; + } + + +unsigned char xdigit( const int value ) throw() + { + if( value >= 0 && value <= 9 ) return '0' + value; + if( value >= 10 && value <= 15 ) return 'A' + value - 10; + return 0; + } + + +void show_trailing_garbage( const uint8_t * const data, const int size, + const Pretty_print & pp, const bool all ) throw() + { + std::string garbage_msg; + if( !all ) garbage_msg = "first bytes of "; + garbage_msg += "trailing garbage found = "; + bool text = true; + for( int i = 0; i < size; ++i ) + if( !std::isprint( data[i] ) ) { text = false; break; } + if( text ) + { + garbage_msg += '`'; + garbage_msg.append( (const char *)data, size ); + garbage_msg += '\''; + } + else + { + for( int i = 0; i < size; ++i ) + { + if( i > 0 ) garbage_msg += ' '; + garbage_msg += xdigit( data[i] >> 4 ); + garbage_msg += xdigit( data[i] & 0x0F ); + } + } + pp( garbage_msg.c_str() ); + } + + +int decompress( const int infd, const Pretty_print & pp, const bool testing ) + { + int retval = 0; + + try { + Range_decoder rdec( infd ); + long long partial_file_pos = 0; + for( bool first_member = true; ; first_member = false, pp.reset() ) + { + File_header header; + int size; + rdec.reset_member_position(); + for( size = 0; size < File_header::size && !rdec.finished(); ++size ) + header.data[size] = rdec.get_byte(); + if( rdec.finished() ) // End Of File + { + if( first_member ) + { pp( "Error reading member header" ); retval = 1; } + else if( verbosity >= 4 && size > 0 ) + show_trailing_garbage( header.data, size, pp, true ); + break; + } + if( !header.verify_magic() ) + { + if( first_member ) + { pp( "Bad magic number (file not in lzip format)" ); retval = 2; } + else if( verbosity >= 4 ) + show_trailing_garbage( header.data, size, pp, false ); + break; + } + if( !header.verify_version() ) + { + if( verbosity >= 0 ) + { pp(); + std::fprintf( stderr, "Version %d member format not supported.\n", + header.version() ); } + retval = 2; break; + } + if( header.dictionary_size() < min_dictionary_size || + header.dictionary_size() > max_dictionary_size ) + { pp( "Invalid dictionary size in member header" ); retval = 2; break; } + + if( verbosity >= 2 || ( verbosity == 1 && first_member ) ) + { + pp(); + if( verbosity >= 2 ) + std::fprintf( stderr, "version %d, dictionary size %7sB. ", + header.version(), + format_num( header.dictionary_size() ) ); + } + LZ_decoder decoder( header, rdec, outfd ); + + const int result = decoder.decode_member( pp ); + partial_file_pos += rdec.member_position(); + if( result != 0 ) + { + if( verbosity >= 0 && result <= 2 ) + { + pp(); + if( result == 2 ) + std::fprintf( stderr, "File ends unexpectedly at pos %lld\n", + partial_file_pos ); + else + std::fprintf( stderr, "Decoder error at pos %lld\n", + partial_file_pos ); + } + retval = 2; break; + } + if( verbosity >= 2 ) + { if( testing ) std::fprintf( stderr, "ok\n" ); + else std::fprintf( stderr, "done\n" ); } + } + } + catch( std::bad_alloc ) + { + pp( "Not enough memory. Find a machine with more memory" ); + retval = 1; + } + catch( Error e ) { pp(); show_error( e.msg, errno ); retval = 1; } + if( verbosity == 1 && retval == 0 ) + { if( testing ) std::fprintf( stderr, "ok\n" ); + else std::fprintf( stderr, "done\n" ); } + return retval; + } + + +extern "C" void signal_handler( int ) throw() + { + show_error( "Control-C or similar caught, quitting." ); + cleanup_and_fail( 1 ); + } + + +void set_signals() throw() + { + std::signal( SIGHUP, signal_handler ); + std::signal( SIGINT, signal_handler ); + std::signal( SIGTERM, signal_handler ); + } + +} // end namespace + + +int verbosity = 0; + + +int open_instream( const std::string & name, struct stat * const in_statsp, + const bool to_stdout, const bool reg_only ) throw() + { + int infd = open( name.c_str(), O_RDONLY | o_binary ); + if( infd < 0 ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Can't open input file `%s': %s.\n", + program_name, name.c_str(), std::strerror( errno ) ); + } + else + { + const int i = fstat( infd, in_statsp ); + const mode_t & mode = in_statsp->st_mode; + const bool can_read = ( i == 0 && !reg_only && + ( S_ISBLK( mode ) || S_ISCHR( mode ) || + S_ISFIFO( mode ) || S_ISSOCK( mode ) ) ); + if( i != 0 || ( !S_ISREG( mode ) && ( !to_stdout || !can_read ) ) ) + { + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Input file `%s' is not a regular file%s.\n", + program_name, name.c_str(), + ( can_read && !to_stdout ) ? + " and `--stdout' was not specified" : "" ); + close( infd ); + infd = -1; + } + } + return infd; + } + + +int open_outstream_rw( const std::string & output_filename, + const bool force ) throw() + { + int flags = O_CREAT | O_RDWR | o_binary; + if( force ) flags |= O_TRUNC; else flags |= O_EXCL; + + int outfd = open( output_filename.c_str(), flags, all_rw ); + if( outfd < 0 && verbosity >= 0 ) + { + if( errno == EEXIST ) + std::fprintf( stderr, "%s: Output file `%s' already exists." + " Use `--force' to overwrite it.\n", + program_name, output_filename.c_str() ); + else + std::fprintf( stderr, "%s: Can't create output file `%s': %s.\n", + program_name, output_filename.c_str(), std::strerror( errno ) ); + } + return outfd; + } + + +void show_error( const char * const msg, const int errcode, const bool help ) throw() + { + if( verbosity >= 0 ) + { + if( msg && msg[0] ) + { + std::fprintf( stderr, "%s: %s", program_name, msg ); + if( errcode > 0 ) + std::fprintf( stderr, ": %s", std::strerror( errcode ) ); + std::fprintf( stderr, "\n" ); + } + if( help && invocation_name && invocation_name[0] ) + std::fprintf( stderr, "Try `%s --help' for more information.\n", + invocation_name ); + } + } + + +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[] ) + { + int infd = -1; + Mode program_mode = m_none; + bool force = false; + bool keep_input_files = false; + bool to_stdout = false; + std::string input_filename; + std::string default_output_filename; + std::vector< std::string > filenames; + invocation_name = argv[0]; + + const Arg_parser::Option options[] = + { + { 'c', "stdout", Arg_parser::no }, + { 'd', "decompress", Arg_parser::no }, + { 'f', "force", Arg_parser::no }, + { 'h', "help", Arg_parser::no }, + { 'k', "keep", Arg_parser::no }, + { 'm', "merge", Arg_parser::no }, + { 'o', "output", Arg_parser::yes }, + { 'q', "quiet", Arg_parser::no }, + { 'R', "repair", Arg_parser::no }, + { 's', "split", Arg_parser::no }, + { 't', "test", Arg_parser::no }, + { 'v', "verbose", Arg_parser::no }, + { 'V', "version", Arg_parser::no }, + { 0 , 0, Arg_parser::no } }; + + const Arg_parser parser( argc, argv, options ); + if( parser.error().size() ) // bad option + { show_error( parser.error().c_str(), 0, true ); return 1; } + + int argind = 0; + for( ; argind < parser.arguments(); ++argind ) + { + const int code = parser.code( argind ); + if( !code ) break; // no more options + switch( code ) + { + case 'c': to_stdout = true; break; + case 'd': set_mode( program_mode, m_decompress ); break; + case 'f': force = true; break; + case 'h': show_help(); return 0; + case 'k': keep_input_files = true; break; + case 'm': set_mode( program_mode, m_merge ); break; + case 'o': default_output_filename = parser.argument( argind ); break; + case 'q': verbosity = -1; break; + case 'R': set_mode( program_mode, m_repair ); break; + case 's': set_mode( program_mode, m_split ); break; + case 't': set_mode( program_mode, m_test ); break; + case 'v': if( verbosity < 4 ) ++verbosity; break; + case 'V': show_version(); return 0; + default : internal_error( "uncaught option" ); + } + } // end process options + + if( program_mode == m_none ) + { + show_error( "You must specify the operation to be performed.", 0, true ); + return 1; + } + + switch( program_mode ) + { + case m_generate: + case m_recover: + case m_update: + case m_none: internal_error( "invalid operation" ); break; + case m_decompress: break; + case m_merge: + { + std::vector< std::string > filenames; + for( ; argind < parser.arguments(); ++argind ) + filenames.push_back( parser.argument( argind ) ); + if( filenames.size() < 2 ) + { show_error( "You must specify at least 2 files.", 0, true ); return 1; } + if( !default_output_filename.size() ) + default_output_filename = insert_fixed( filenames[0] ); + return merge_files( filenames, default_output_filename, force ); + } break; + case m_repair: + { + if( argind + 1 != parser.arguments() ) + { show_error( "You must specify exactly 1 file.", 0, true ); return 1; } + if( !default_output_filename.size() ) + default_output_filename = insert_fixed( parser.argument( argind ) ); + return repair_file( parser.argument( argind ), default_output_filename, force ); + } break; + case m_split: + { + if( argind + 1 != parser.arguments() ) + { show_error( "You must specify exactly 1 file.", 0, true ); return 1; } + return split_file( parser.argument( argind ), default_output_filename, force ); + } break; + case m_test: break; + } + + bool filenames_given = false; + for( ; argind < parser.arguments(); ++argind ) + { + if( parser.argument( argind ) != "-" ) filenames_given = true; + filenames.push_back( parser.argument( argind ) ); + } + + if( filenames.empty() ) filenames.push_back("-"); + if( !to_stdout && program_mode != m_test && + ( filenames_given || default_output_filename.size() ) ) + set_signals(); + + Pretty_print pp( filenames, verbosity ); + if( program_mode == m_test ) + outfd = -1; + else if( program_mode != m_decompress ) + internal_error( "invalid decompressor operation" ); + + int retval = 0; + for( unsigned int i = 0; i < filenames.size(); ++i ) + { + struct stat in_stats; + output_filename.clear(); + + if( !filenames[i].size() || filenames[i] == "-" ) + { + input_filename.clear(); + infd = STDIN_FILENO; + if( program_mode != m_test ) + { + if( to_stdout || !default_output_filename.size() ) + outfd = STDOUT_FILENO; + else + { + output_filename = default_output_filename; + outfd_mode = all_rw; + if( !open_outstream( force ) ) + { + if( outfd == -1 && retval < 1 ) retval = 1; + close( infd ); infd = -1; + continue; + } + } + } + } + else + { + input_filename = filenames[i]; + const int eindex = extension_index( input_filename ); + infd = open_instream( input_filename, &in_stats, to_stdout ); + if( infd < 0 ) { if( retval < 1 ) retval = 1; continue; } + if( program_mode != m_test ) + { + if( to_stdout ) outfd = STDOUT_FILENO; + else + { + set_d_outname( input_filename, eindex ); + outfd_mode = usr_rw; + if( !open_outstream( force ) ) + { + if( outfd == -1 && retval < 1 ) retval = 1; + close( infd ); infd = -1; + continue; + } + } + } + } + + if( !check_tty( infd ) ) return 1; + + if( output_filename.size() && !to_stdout && program_mode != m_test ) + delete_output_on_interrupt = true; + const struct stat * const in_statsp = input_filename.size() ? &in_stats : 0; + pp.set_name( input_filename ); + const int tmp = decompress( infd, pp, program_mode == m_test ); + if( tmp > retval ) retval = tmp; + if( tmp && program_mode != m_test ) cleanup_and_fail( retval ); + + if( delete_output_on_interrupt ) + close_and_set_permissions( in_statsp ); + if( input_filename.size() ) + { + close( infd ); infd = -1; + if( !keep_input_files && !to_stdout && program_mode != m_test ) + std::remove( input_filename.c_str() ); + } + } + if( outfd >= 0 && close( outfd ) != 0 ) + { + show_error( "Can't close stdout", errno ); + if( retval < 1 ) retval = 1; + } + return retval; + } |