diff options
Diffstat (limited to '')
| -rw-r--r-- | main.c | 1036 | ||||
| -rw-r--r-- | main.cc | 966 |
2 files changed, 1036 insertions, 966 deletions
@@ -0,0 +1,1036 @@ +/* Minilzip - A test program for the lzlib library + Copyright (C) 2009, 2010, 2011, 2012 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 minilzip to panic. +*/ + +#define _FILE_OFFSET_BITS 64 + +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <signal.h> +#include <stdbool.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <utime.h> +#include <sys/stat.h> + +#include "carg_parser.h" +#include "lzlib.h" + +#if CHAR_BIT != 8 +#error "Environments where CHAR_BIT != 8 are not supported." +#endif + +#ifndef LLONG_MAX +#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL +#endif +#ifndef LLONG_MIN +#define LLONG_MIN (-LLONG_MAX - 1LL) +#endif +#ifndef ULLONG_MAX +#define ULLONG_MAX 0xFFFFFFFFFFFFFFFFULL +#endif + +#ifndef min + #define min(x,y) ((x) <= (y) ? (x) : (y)) +#endif + +long long int llabs( long long int number ); + + +const char * const Program_name = "Minilzip"; +const char * const program_name = "minilzip"; +const char * const program_year = "2012"; +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 } }; + +struct Lzma_options + { + int dictionary_size; /* 4KiB..512MiB */ + int match_len_limit; /* 5..273 */ + }; + +enum Mode { m_compress, m_decompress, m_test }; + +char * output_filename = 0; +int outfd = -1; +int verbosity = 0; +const mode_t usr_rw = S_IRUSR | S_IWUSR; +const mode_t all_rw = S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH; +mode_t outfd_mode = S_IRUSR | S_IWUSR; +bool delete_output_on_interrupt = false; + + +struct Pretty_print + { + const char * name; + const char * stdin_name; + int longest_name; + bool first_post; + }; + +static void Pp_init( struct Pretty_print * const pp, + const char * const filenames[], const int num_filenames ) + { + unsigned int stdin_name_len; + int i; + pp->name = 0; + pp->stdin_name = "(stdin)"; + pp->longest_name = 0; + pp->first_post = false; + stdin_name_len = strlen( pp->stdin_name ); + + for( i = 0; i < num_filenames; ++i ) + { + const char * const s = filenames[i]; + const int len = ( !strcmp( s, "-" ) ? stdin_name_len : strlen( s ) ); + if( len > pp->longest_name ) pp->longest_name = len; + } + if( pp->longest_name == 0 ) pp->longest_name = stdin_name_len; + } + + +static inline void Pp_set_name( struct Pretty_print * const pp, + const char * const filename ) + { + if( filename && filename[0] && strcmp( filename, "-" ) ) + pp->name = filename; + else pp->name = pp->stdin_name; + pp->first_post = true; + } + + +static inline void Pp_reset( struct Pretty_print * const pp ) + { if( pp->name && pp->name[0] ) pp->first_post = true; } + + +static void Pp_show_msg( struct Pretty_print * const pp, const char * const msg ) + { + if( verbosity >= 0 ) + { + if( pp->first_post ) + { + int i, len; + pp->first_post = false; + fprintf( stderr, " %s: ", pp->name ); + len = pp->longest_name - strlen( pp->name ); + for( i = 0; i < len; ++i ) fprintf( stderr, " " ); + if( !msg ) fflush( stderr ); + } + if( msg ) fprintf( stderr, "%s.\n", msg ); + } + } + + +static void show_help( void ) + { + printf( "%s - A test program for the lzlib library.\n", Program_name ); + printf( "\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" + " -b, --member-size=<bytes> set member size limit in bytes\n" + " -c, --stdout send output to standard output\n" + " -d, --decompress decompress\n" + " -f, --force overwrite existing output files\n" + " -F, --recompress force recompression of compressed files\n" + " -k, --keep keep (don't delete) input files\n" + " -m, --match-length=<bytes> set match length limit in bytes [36]\n" + " -o, --output=<file> if reading stdin, place the output into <file>\n" + " -q, --quiet suppress all messages\n" + " -s, --dictionary-size=<bytes> set dictionary size limit in bytes [8MiB]\n" + " -S, --volume-size=<bytes> set volume size limit in bytes\n" + " -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" + "If no file names are given, minilzip compresses or decompresses\n" + "from standard input to standard output.\n" + "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" + "The bidimensional parameter space of LZMA can't be mapped to a linear\n" + "scale optimal for all files. If your files are large, very repetitive,\n" + "etc, you may need to use the --match-length and --dictionary-size\n" + "options directly to achieve optimal performance.\n" + "\nReport bugs to lzip-bug@nongnu.org\n" + "Lzlib home page: http://www.nongnu.org/lzip/lzlib.html\n" ); + } + + +static void show_version( void ) + { + printf( "%s %s\n", Program_name, PROGVERSION ); + printf( "Copyright (C) %s Antonio Diaz Diaz.\n", program_year ); + printf( "Using Lzlib %s\n", LZ_version() ); + 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" ); + } + + +void show_error( const char * const msg, const int errcode, const bool help ) + { + if( verbosity >= 0 ) + { + if( msg && msg[0] ) + { + fprintf( stderr, "%s: %s", program_name, msg ); + if( errcode > 0 ) fprintf( stderr, ": %s", strerror( errcode ) ); + fprintf( stderr, "\n" ); + } + if( help && invocation_name && invocation_name[0] ) + fprintf( stderr, "Try '%s --help' for more information.\n", + invocation_name ); + } + } + + +void internal_error( const char * const msg ) + { + if( verbosity >= 0 ) + fprintf( stderr, "%s: internal error: %s.\n", program_name, msg ); + exit( 3 ); + } + + +static const char * format_num( long long num ) + { + 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 ); + int i; + + for( 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; + } + + +static long long getnum( const char * const ptr, + const long long llimit, const long long ulimit ) + { + long long result; + char *tail; + errno = 0; + result = strtoll( ptr, &tail, 0 ); + if( tail == ptr ) + { + show_error( "Bad or missing numerical argument.", 0, true ); + exit( 1 ); + } + + if( !errno && tail[0] ) + { + int factor = ( tail[1] == 'i' ) ? 1024 : 1000; + int exponent = 0; + int i; + bool bad_multiplier = false; + switch( tail[0] ) + { + case ' ': break; + 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; else bad_multiplier = true; + break; + case 'k': if( factor == 1000 ) exponent = 1; else bad_multiplier = true; + break; + default : bad_multiplier = true; + } + if( bad_multiplier ) + { + show_error( "Bad multiplier in numerical argument.", 0, true ); + exit( 1 ); + } + for( i = 0; i < exponent; ++i ) + { + if( LLONG_MAX / factor >= llabs( 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; + int bits = strtol( arg, &tail, 0 ); + if( bits >= LZ_min_dictionary_bits() && + bits <= LZ_max_dictionary_bits() && *tail == 0 ) + return ( 1 << bits ); + return getnum( arg, LZ_min_dictionary_size(), LZ_max_dictionary_size() ); + } + + +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 + { + infd = open( name, O_RDONLY | o_binary ); + if( infd < 0 ) + { + if( verbosity >= 0 ) + fprintf( stderr, "%s: Can't open input file '%s': %s.\n", + program_name, name, strerror( errno ) ); + } + 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 ) ) ); + if( i != 0 || ( !S_ISREG( mode ) && ( !to_stdout || !can_read ) ) ) + { + if( verbosity >= 0 ) + fprintf( stderr, "%s: Input file '%s' is not a regular file%s.\n", + program_name, name, + ( can_read && !to_stdout ) ? + " and '--stdout' was not specified" : "" ); + close( infd ); + infd = -1; + } + } + } + return infd; + } + + +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 ); + } + + +/* assure at least a minimum size for buffer 'buf' */ +static void * resize_buffer( void * buf, const int min_size ) + { + if( buf ) buf = realloc( buf, min_size ); + else buf = malloc( min_size ); + if( !buf ) + { + show_error( "Not enough memory.", 0, false ); + cleanup_and_fail( 1 ); + } + return buf; + } + + +static void set_c_outname( const char * const name, const bool multifile ) + { + output_filename = resize_buffer( output_filename, strlen( name ) + 5 + + strlen( known_extensions[0].from ) + 1 ); + strcpy( output_filename, name ); + if( multifile ) strcat( output_filename, "00001" ); + strcat( output_filename, known_extensions[0].from ); + } + + +static int extension_index( const char * const name ) + { + int i; + for( i = 0; known_extensions[i].from; ++i ) + { + const char * const ext = known_extensions[i].from; + if( strlen( name ) > strlen( ext ) && + strncmp( name + strlen( name ) - strlen( ext ), ext, strlen( ext ) ) == 0 ) + return i; + } + return -1; + } + + +static void set_d_outname( const char * const name, const int i ) + { + if( i >= 0 ) + { + const char * const from = known_extensions[i].from; + if( strlen( name ) > strlen( from ) ) + { + output_filename = resize_buffer( output_filename, strlen( name ) + + strlen( known_extensions[0].to ) + 1 ); + strcpy( output_filename, name ); + strcpy( output_filename + strlen( name ) - strlen( from ), + known_extensions[i].to ); + return; + } + } + output_filename = resize_buffer( output_filename, strlen( name ) + 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 ); + } + + +static bool open_outstream( const bool force ) + { + int flags = O_CREAT | O_WRONLY | o_binary; + if( force ) flags |= O_TRUNC; else flags |= O_EXCL; + + outfd = open( output_filename, flags, outfd_mode ); + if( outfd < 0 && verbosity >= 0 ) + { + if( errno == EEXIST ) + fprintf( stderr, "%s: Output file '%s' already exists, skipping.\n", + program_name, output_filename ); + else + fprintf( stderr, "%s: Can't create output file '%s': %s.\n", + program_name, output_filename, strerror( errno ) ); + } + return ( outfd >= 0 ); + } + + +static bool check_tty( const int infd, const enum Mode program_mode ) + { + if( program_mode == m_compress && outfd >= 0 && isatty( outfd ) ) + { + 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 ) ) + { + show_error( "I won't read compressed data from a terminal.", 0, true ); + return false; + } + return true; + } + + + /* Set permissions, owner and times. */ +static 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, &t ) != 0 ) warning = true; + } + if( warning && verbosity >= 1 ) + show_error( "Can't change output file attributes.", 0, false ); + } + + +/* 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 rest = size; + errno = 0; + while( rest > 0 ) + { + errno = 0; + const int n = read( fd, buf + size - rest, rest ); + if( n > 0 ) rest -= n; + else if( n == 0 ) break; + else if( errno != EINTR && errno != EAGAIN ) break; + } + return ( rest > 0 ) ? size - rest : size; + } + + +/* 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 rest = size; + errno = 0; + while( rest > 0 ) + { + errno = 0; + const int n = write( fd, buf + size - rest, rest ); + if( n > 0 ) rest -= n; + else if( n < 0 && errno != EINTR && errno != EAGAIN ) break; + } + return ( rest > 0 ) ? size - rest : size; + } + + +static bool next_filename( void ) + { + const unsigned int len = strlen( known_extensions[0].from ); + int i, j; + + if( strlen( output_filename ) >= len + 5 ) /* "*00001.lz" */ + for( i = strlen( output_filename ) - len - 1, j = 0; j < 5; --i, ++j ) + { + if( output_filename[i] < '9' ) { ++output_filename[i]; return true; } + else output_filename[i] = '0'; + } + return false; + } + + +static int do_compress( struct LZ_Encoder * const encoder, const long long member_size, + const long long volume_size, const int infd, + struct Pretty_print * const pp, + const struct stat * const in_statsp ) + { + long long partial_volume_size = 0; + enum { buffer_size = 65536 }; + uint8_t buffer[buffer_size]; + + if( verbosity >= 1 ) Pp_show_msg( pp, 0 ); + while( true ) + { + int in_size = 0; + while( LZ_compress_write_size( encoder ) > 0 ) + { + const int size = min( LZ_compress_write_size( encoder ), buffer_size ); + const int rd = readblock( infd, buffer, size ); + if( rd != size && errno ) + { + Pp_show_msg( pp, 0 ); show_error( "Read error", errno, false ); + return 1; + } + if( rd > 0 && rd != LZ_compress_write( encoder, buffer, rd ) ) + internal_error( "library error (LZ_compress_write)" ); + if( rd < size ) LZ_compress_finish( encoder ); +/* else LZ_compress_sync_flush( encoder ); */ + in_size += rd; + } + const int out_size = LZ_compress_read( encoder, buffer, buffer_size ); + if( out_size < 0 ) + { + Pp_show_msg( pp, 0 ); + if( verbosity >= 0 ) + fprintf( stderr, "%s: LZ_compress_read error: %s.\n", + program_name, LZ_strerror( LZ_compress_errno( encoder ) ) ); + return 1; + } + else if( out_size > 0 ) + { + const int wr = writeblock( outfd, buffer, out_size ); + if( wr != out_size ) + { + Pp_show_msg( pp, 0 ); show_error( "Write error", errno, false ); + return 1; + } + } + else if( in_size == 0 ) internal_error( "library error (LZ_compress_read)" ); + if( LZ_compress_member_finished( encoder ) ) + { + if( LZ_compress_finished( encoder ) == 1 ) break; + partial_volume_size += LZ_compress_member_position( encoder ); + if( partial_volume_size >= volume_size - LZ_min_dictionary_size() ) + { + partial_volume_size = 0; + if( delete_output_on_interrupt ) + { + close_and_set_permissions( in_statsp ); + if( !next_filename() ) + { Pp_show_msg( pp, "Too many volume files" ); return 1; } + if( !open_outstream( true ) ) return 1; + delete_output_on_interrupt = true; + } + } + const long long size = + min( member_size, volume_size - partial_volume_size ); + if( LZ_compress_restart_member( encoder, size ) < 0 ) + { + Pp_show_msg( pp, 0 ); + if( verbosity >= 0 ) + fprintf( stderr, "%s: LZ_compress_restart_member error: %s.\n", + program_name, LZ_strerror( LZ_compress_errno( encoder ) ) ); + return 1; + } + } + } + + if( verbosity >= 1 ) + { + const long long in_size = LZ_compress_total_in_size( encoder ); + const long long out_size = LZ_compress_total_out_size( encoder ); + if( in_size <= 0 || out_size <= 0 ) + fprintf( stderr, " no data compressed.\n" ); + else + fprintf( stderr, "%6.3f:1, %6.3f bits/byte, " + "%5.2f%% saved, %lld in, %lld out.\n", + (double)in_size / out_size, + ( 8.0 * out_size ) / in_size, + 100.0 * ( 1.0 - ( (double)out_size / in_size ) ), + in_size, out_size ); + } + return 0; + } + + +int compress( const long long member_size, const long long volume_size, + const struct Lzma_options * const encoder_options, const int infd, + struct Pretty_print * const pp, const struct stat * const in_statsp ) + { + struct LZ_Encoder * const encoder = + LZ_compress_open( encoder_options->dictionary_size, + encoder_options->match_len_limit, + min( member_size, volume_size ) ); + int retval; + + if( !encoder || LZ_compress_errno( encoder ) != LZ_ok ) + { + if( !encoder || LZ_compress_errno( encoder ) == LZ_mem_error ) + Pp_show_msg( pp, "Not enough memory. Try a smaller dictionary size" ); + else + internal_error( "invalid argument to encoder" ); + retval = 1; + } + else retval = do_compress( encoder, member_size, volume_size, + infd, pp, in_statsp ); + LZ_compress_close( encoder ); + return retval; + } + + +int do_decompress( struct LZ_Decoder * const decoder, const int infd, + struct Pretty_print * const pp, const bool testing ) + { + enum { buffer_size = 65536 }; + uint8_t buffer[buffer_size]; + bool first_member; + + for( first_member = true; ; ) + { + int in_size = min( LZ_decompress_write_size( decoder ), buffer_size ); + if( in_size > 0 ) + { + const int max_in_size = in_size; + in_size = readblock( infd, buffer, max_in_size ); + if( in_size != max_in_size && errno ) + { + Pp_show_msg( pp, 0 ); show_error( "Read error", errno, false ); + return 1; + } + if( in_size > 0 && in_size != LZ_decompress_write( decoder, buffer, in_size ) ) + internal_error( "library error (LZ_decompress_write)" ); + if( in_size < max_in_size ) LZ_decompress_finish( decoder ); + } + int out_size = 0; + while( true ) + { + const int rd = LZ_decompress_read( decoder, buffer, buffer_size ); + if( rd > 0 ) + { + out_size += rd; + if( outfd >= 0 ) + { + const int wr = writeblock( outfd, buffer, rd ); + if( wr != rd ) + { + Pp_show_msg( pp, 0 ); show_error( "Write error", errno, false ); + return 1; + } + } + } + else if( rd < 0 ) { out_size = rd; break; } + if( verbosity >= 1 && LZ_decompress_member_finished( decoder ) == 1 ) + { + const long long data_position = LZ_decompress_data_position( decoder ); + const long long member_size = LZ_decompress_member_position( decoder ); + Pp_show_msg( pp, 0 ); + if( verbosity >= 2 ) + fprintf( stderr, "version %d, dictionary size %7sB. ", + LZ_decompress_member_version( decoder ), + format_num( LZ_decompress_dictionary_size( decoder ) ) ); + if( verbosity >= 3 && data_position > 0 && member_size > 0 ) + fprintf( stderr, "%6.3f:1, %6.3f bits/byte, %5.2f%% saved. ", + (double)data_position / member_size, + ( 8.0 * member_size ) / data_position, + 100.0 * ( 1.0 - ( (double)member_size / data_position ) ) ); + if( verbosity >= 4 ) + fprintf( stderr, "data CRC %08X, data size %9lld, member size %8lld. ", + LZ_decompress_data_crc( decoder ), + data_position, member_size ); + if( testing ) fprintf( stderr, "ok\n" ); + else fprintf( stderr, "done\n" ); + } + if( LZ_decompress_member_finished( decoder ) == 1 ) + { first_member = false; Pp_reset( pp ); } + if( rd <= 0 ) break; + } + if( out_size < 0 ) + { + const enum LZ_Errno lz_errno = LZ_decompress_errno( decoder ); + if( lz_errno == LZ_header_error ) + { + if( !first_member ) break; /* trailing garbage */ + Pp_show_msg( pp, "Error reading member header" ); + return 1; + } + if( lz_errno == LZ_mem_error ) + { + Pp_show_msg( pp, "Not enough memory. Find a machine with more memory" ); + return 1; + } + Pp_show_msg( pp, 0 ); + if( lz_errno == LZ_unexpected_eof ) + { + if( verbosity >= 0 ) + fprintf( stderr, "File ends unexpectedly at pos %lld\n", + LZ_decompress_total_in_size( decoder ) ); + return 2; + } + if( verbosity >= 0 ) + fprintf( stderr, "LZ_decompress_read error: %s.\n", + LZ_strerror( LZ_decompress_errno( decoder ) ) ); + return 1; + } + if( LZ_decompress_finished( decoder ) == 1 ) break; + if( in_size == 0 && out_size == 0 ) + internal_error( "library error (LZ_decompress_read)" ); + } + return 0; + } + + +int decompress( const int infd, struct Pretty_print * const pp, + const bool testing ) + { + struct LZ_Decoder * const decoder = LZ_decompress_open(); + int retval; + + if( !decoder || LZ_decompress_errno( decoder ) != LZ_ok ) + { + Pp_show_msg( pp, "Not enough memory. Find a machine with more memory" ); + retval = 1; + } + else retval = do_decompress( decoder, infd, pp, testing ); + + LZ_decompress_close( decoder ); + return retval; + } + + +void signal_handler( int sig ) + { + sig = 0; /* 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 ); + } + + +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" */ + long long member_size = LLONG_MAX; + long long volume_size = LLONG_MAX; + const char * input_filename = ""; + const char * default_output_filename = ""; + const char ** filenames = 0; + int num_filenames = 0; + int infd = -1; + enum Mode program_mode = m_compress; + int argind = 0; + int retval = 0; + int i; + bool filenames_given = false; + bool force = false; + bool keep_input_files = false; + bool recompress = false; + bool to_stdout = false; + struct Pretty_print pp; + + const struct ap_Option options[] = + { + { '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 }, + { '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 }, + { '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 }, + { 0 , 0, ap_no } }; + + struct Arg_parser parser; + + invocation_name = argv[0]; + if( LZ_version()[0] != LZ_version_string[0] ) + internal_error( "bad library version" ); + if( strcmp( PROGVERSION, LZ_version_string ) ) + internal_error( "bad library version_string" ); + + if( !ap_init( &parser, argc, argv, options, 0 ) ) + { show_error( "Memory exhausted.", 0, false ); return 1; } + 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 ) + { + case '0': + case '1': case '2': case '3': case '4': + case '5': case '6': case '7': case '8': case '9': + encoder_options = option_mapping[code-'0']; break; + case 'b': member_size = getnum( arg, 100000, LLONG_MAX / 2 ); 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, LZ_min_match_len_limit(), + LZ_max_match_len_limit() ); break; + 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': volume_size = getnum( arg, 100000, LLONG_MAX / 2 ); break; + case 't': 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 defined(__OS2__) + _fsetmode( stdin, "b" ); + _fsetmode( stdout, "b" ); +#endif + + if( program_mode == m_test ) + outfd = -1; + + for( ; argind < ap_arguments( &parser ); ++argind ) + { + if( strcmp( ap_argument( &parser, argind ), "-" ) ) + filenames_given = true; + ++num_filenames; + filenames = resize_buffer( filenames, num_filenames * sizeof (char *) ); + filenames[num_filenames-1] = ap_argument( &parser, argind ); + } + + if( num_filenames == 0 ) + { + ++num_filenames; + filenames = resize_buffer( filenames, sizeof (char *) ); + filenames[num_filenames-1] = "-"; + } + if( !to_stdout && program_mode != m_test && + ( filenames_given || default_output_filename[0] ) ) + set_signals(); + + Pp_init( &pp, filenames, num_filenames ); + + output_filename = resize_buffer( output_filename, 1 ); + for( i = 0; i < num_filenames; ++i ) + { + int tmp; + struct stat in_stats; + const struct stat * in_statsp; + output_filename[0] = 0; + + if( !filenames[i][0] || !strcmp( filenames[i], "-" ) ) + { + input_filename = ""; + infd = STDIN_FILENO; + if( program_mode != m_test ) + { + if( to_stdout || !default_output_filename[0] ) + outfd = STDOUT_FILENO; + else + { + if( program_mode == m_compress ) + set_c_outname( default_output_filename, volume_size != LLONG_MAX ); + else + { + output_filename = resize_buffer( output_filename, + strlen( default_output_filename ) + 1 ); + strcpy( 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 + { + const int eindex = extension_index( filenames[i] ); + input_filename = filenames[i]; + 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 ) + set_c_outname( input_filename, volume_size != LLONG_MAX ); + 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, program_mode ) ) return 1; + + if( output_filename[0] && !to_stdout && program_mode != m_test ) + delete_output_on_interrupt = true; + in_statsp = input_filename[0] ? &in_stats : 0; + Pp_set_name( &pp, input_filename ); + if( program_mode == m_compress ) + tmp = compress( member_size, volume_size, &encoder_options, infd, + &pp, in_statsp ); + else + 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[0] ) + { + close( infd ); infd = -1; + if( !keep_input_files && !to_stdout && program_mode != m_test ) + remove( input_filename ); + } + } + if( outfd >= 0 && close( outfd ) != 0 ) + { + show_error( "Can't close stdout", errno, false ); + if( retval < 1 ) retval = 1; + } + free( output_filename ); + free( filenames ); + ap_free( &parser ); + return retval; + } diff --git a/main.cc b/main.cc deleted file mode 100644 index 5c5d572..0000000 --- a/main.cc +++ /dev/null @@ -1,966 +0,0 @@ -/* Minilzip - A test program for the lzlib library - 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 minilzip 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> - -#include "arg_parser.h" -#include "lzlib.h" - -#if CHAR_BIT != 8 -#error "Environments where CHAR_BIT != 8 are not supported." -#endif - -#ifndef LLONG_MAX -#define LLONG_MAX 0x7FFFFFFFFFFFFFFFLL -#endif -#ifndef LLONG_MIN -#define LLONG_MIN (-LLONG_MAX - 1LL) -#endif -#ifndef ULLONG_MAX -#define ULLONG_MAX 0xFFFFFFFFFFFFFFFFULL -#endif - -void show_error( const char * const msg, const int errcode = 0, const bool help = false ) throw(); -void internal_error( const char * const msg ); -int readblock( const int fd, uint8_t * const buf, const int size ) throw(); -int writeblock( const int fd, const uint8_t * const buf, const int size ) throw(); - - -namespace { - -const char * const Program_name = "Minilzip"; -const char * const program_name = "minilzip"; -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 } }; - -struct Lzma_options - { - int dictionary_size; // 4KiB..512MiB - int match_len_limit; // 5..273 - }; - -enum Mode { m_compress, m_decompress, m_test }; - -std::string output_filename; -int outfd = -1; -int verbosity = 0; -mode_t outfd_mode = S_IRUSR | S_IWUSR; -bool delete_output_on_interrupt = false; - -class Pretty_print - { - const char * const stdin_name; - unsigned int longest_name; - std::string name_; - mutable bool first_post; - -public: - Pretty_print( const std::vector< std::string > & filenames ) - : stdin_name( "(stdin)" ), longest_name( 0 ), first_post( false ) - { - const unsigned int stdin_name_len = std::strlen( stdin_name ); - for( unsigned int i = 0; i < filenames.size(); ++i ) - { - const std::string & s = filenames[i]; - const unsigned int len = ( ( s == "-" ) ? stdin_name_len : s.size() ); - if( len > longest_name ) longest_name = len; - } - if( longest_name == 0 ) longest_name = stdin_name_len; - } - - void set_name( const std::string & filename ) - { - if( filename.size() && filename != "-" ) name_ = filename; - else name_ = stdin_name; - first_post = true; - } - - void reset() const throw() { if( name_.size() ) first_post = true; } - const char * name() const throw() { return name_.c_str(); } - void operator()( const char * const msg = 0 ) const throw(); - }; - - -void show_help() throw() - { - std::printf( "%s - A test program for the lzlib library.\n", Program_name ); - std::printf( "\nUsage: %s [options] [files]\n", invocation_name ); - std::printf( "\nOptions:\n" ); - std::printf( " -h, --help display this help and exit\n" ); - std::printf( " -V, --version output version information and exit\n" ); - std::printf( " -b, --member-size=<n> set member size limit in bytes\n" ); - std::printf( " -c, --stdout send output to standard output\n" ); - std::printf( " -d, --decompress decompress\n" ); - std::printf( " -f, --force overwrite existing output files\n" ); - std::printf( " -F, --recompress force recompression of compressed files\n" ); - std::printf( " -k, --keep keep (don't delete) input files\n" ); - std::printf( " -m, --match-length=<n> set match length limit in bytes [36]\n" ); - std::printf( " -o, --output=<file> if reading stdin, place the output into <file>\n" ); - std::printf( " -q, --quiet suppress all messages\n" ); - std::printf( " -s, --dictionary-size=<n> set dictionary size limit in bytes [8MiB]\n" ); - std::printf( " -S, --volume-size=<n> set volume size limit in bytes\n" ); - std::printf( " -t, --test test compressed file integrity\n" ); - std::printf( " -v, --verbose be verbose (a 2nd -v gives more)\n" ); - std::printf( " -1 .. -9 set compression level [default 6]\n" ); - std::printf( " --fast alias for -1\n" ); - std::printf( " --best alias for -9\n" ); - std::printf( "If no file names are given, %s compresses or decompresses\n", program_name ); - std::printf( "from standard input to standard output.\n" ); - std::printf( "Numbers may be followed by a multiplier: k = kB = 10^3 = 1000,\n" ); - std::printf( "Ki = KiB = 2^10 = 1024, M = 10^6, Mi = 2^20, G = 10^9, Gi = 2^30, etc...\n" ); - std::printf( "\nReport bugs to lzip-bug@nongnu.org\n" ); - std::printf( "Lzlib home page: http://www.nongnu.org/lzip/lzlib.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" ); - std::printf( "This is free software: you are free to change and redistribute it.\n" ); - std::printf( "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 = ""; - - for( int i = 0; i < 8 && ( llabs( num ) > 9999 || - ( llabs( num ) >= factor && num % factor == 0 ) ); ++i ) - { num /= factor; p = prefix[i]; } - snprintf( buf, buf_size, "%lld %s", num, p ); - return buf; - } - - -long long getnum( const char * const ptr, - const long long llimit = LLONG_MIN + 1, - const long long ulimit = LLONG_MAX ) throw() - { - errno = 0; - char *tail; - long long result = strtoll( ptr, &tail, 0 ); - if( tail == ptr ) - { - show_error( "Bad or missing numerical argument.", 0, true ); - std::exit( 1 ); - } - - if( !errno && tail[0] ) - { - int factor = ( tail[1] == 'i' ) ? 1024 : 1000; - int exponent = 0; - bool bad_multiplier = false; - switch( tail[0] ) - { - case ' ': break; - 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; else bad_multiplier = true; - break; - case 'k': if( factor == 1000 ) exponent = 1; else bad_multiplier = true; - break; - default : bad_multiplier = true; - } - if( bad_multiplier ) - { - show_error( "Bad multiplier in numerical argument.", 0, true ); - std::exit( 1 ); - } - for( int i = 0; i < exponent; ++i ) - { - if( LLONG_MAX / factor >= llabs( 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; - } - - -int get_dict_size( const char * const arg ) throw() - { - char *tail; - int bits = std::strtol( arg, &tail, 0 ); - if( bits >= LZ_min_dictionary_bits() && - bits <= LZ_max_dictionary_bits() && *tail == 0 ) - return ( 1 << bits ); - return getnum( arg, LZ_min_dictionary_size(), LZ_max_dictionary_size() ); - } - - -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; - } - - -int open_instream( const std::string & name, struct stat * const in_statsp, - const Mode program_mode, const int eindex, - const bool recompress, const bool to_stdout ) throw() - { - int infd = -1; - if( program_mode == m_compress && !recompress && eindex >= 0 ) - { - if( verbosity >= 0 ) - std::fprintf( stderr, "%s: Input file `%s' already has `%s' suffix.\n", - program_name, name.c_str(), - known_extensions[eindex].from ); - } - else - { - 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 && - ( 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; - } - - -void set_c_outname( const std::string & name, const bool multifile ) throw() - { - output_filename = name; - if( multifile ) output_filename += "00001"; - output_filename += known_extensions[0].from; - } - - -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, const Mode program_mode ) throw() - { - if( program_mode == m_compress && outfd >= 0 && isatty( outfd ) ) - { - 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 ) ) - { - 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 error = false; - if( in_statsp ) - { - if( ( fchown( outfd, in_statsp->st_uid, in_statsp->st_gid ) != 0 && - errno != EPERM ) || - fchmod( outfd, in_statsp->st_mode ) != 0 ) - error = true; - // fchown will in many cases return with EPERM, which can be safely ignored. - } - if( close( outfd ) == 0 ) outfd = -1; - else cleanup_and_fail( 1 ); - delete_output_on_interrupt = false; - if( !in_statsp ) return; - if( !error ) - { - struct utimbuf t; - t.actime = in_statsp->st_atime; - t.modtime = in_statsp->st_mtime; - if( utime( output_filename.c_str(), &t ) != 0 ) error = true; - } - if( error ) - { - show_error( "Can't change output file attributes." ); - cleanup_and_fail( 1 ); - } - } - - -bool next_filename() - { - const unsigned int len = std::strlen( known_extensions[0].from ); - if( output_filename.size() >= len + 5 ) // "*00001.lz" - for( int i = output_filename.size() - len - 1, j = 0; j < 5; --i, ++j ) - { - if( output_filename[i] < '9' ) { ++output_filename[i]; return true; } - else output_filename[i] = '0'; - } - return false; - } - - -int do_compress( LZ_Encoder * const encoder, const long long member_size, - const long long volume_size, const int infd, - const Pretty_print & pp, const struct stat * const in_statsp ) - { - long long partial_volume_size = 0; - const int buffer_size = 65536; - uint8_t buffer[buffer_size]; - - if( verbosity >= 1 ) pp(); - while( true ) - { - int in_size = 0; - while( LZ_compress_write_size( encoder ) > 0 ) - { - const int size = std::min( LZ_compress_write_size( encoder ), - buffer_size ); - const int rd = readblock( infd, buffer, size ); - if( rd != size && errno ) - { pp(); show_error( "Read error", errno ); return 1; } - if( rd > 0 && rd != LZ_compress_write( encoder, buffer, rd ) ) - internal_error( "library error (LZ_compress_write)" ); - if( rd < size ) LZ_compress_finish( encoder ); -// else LZ_compress_sync_flush( encoder ); - in_size += rd; - } - const int out_size = LZ_compress_read( encoder, buffer, buffer_size ); - if( out_size < 0 ) - { - pp(); - if( verbosity >= 0 ) - std::fprintf( stderr, "%s: LZ_compress_read error: %s.\n", - program_name, LZ_strerror( LZ_compress_errno( encoder ) ) ); - return 1; - } - else if( out_size > 0 ) - { - const int wr = writeblock( outfd, buffer, out_size ); - if( wr != out_size ) - { pp(); show_error( "Write error", errno ); return 1; } - } - else if( in_size == 0 ) internal_error( "library error (LZ_compress_read)" ); - if( LZ_compress_member_finished( encoder ) ) - { - if( LZ_compress_finished( encoder ) == 1 ) break; - partial_volume_size += LZ_compress_member_position( encoder ); - if( partial_volume_size >= volume_size - LZ_min_dictionary_size() ) - { - partial_volume_size = 0; - if( delete_output_on_interrupt ) - { - close_and_set_permissions( in_statsp ); - if( !next_filename() ) - { pp( "Too many volume files." ); return 1; } - if( !open_outstream( true ) ) return 1; - delete_output_on_interrupt = true; - } - } - const long long size = - std::min( member_size, volume_size - partial_volume_size ); - if( LZ_compress_restart_member( encoder, size ) < 0 ) - { - pp(); - if( verbosity >= 0 ) - std::fprintf( stderr, "%s: LZ_compress_restart_member error: %s.\n", - program_name, LZ_strerror( LZ_compress_errno( encoder ) ) ); - return 1; - } - } - } - - if( verbosity >= 1 ) - { - const long long in_size = LZ_compress_total_in_size( encoder ); - const long long out_size = LZ_compress_total_out_size( encoder ); - if( in_size <= 0 || out_size <= 0 ) - std::fprintf( stderr, "No data compressed.\n" ); - else - std::fprintf( stderr, "%6.3f:1, %6.3f bits/byte, " - "%5.2f%% saved, %lld in, %lld out.\n", - (double)in_size / out_size, - ( 8.0 * out_size ) / in_size, - 100.0 * ( 1.0 - ( (double)out_size / in_size ) ), - in_size, out_size ); - } - return 0; - } - - -int compress( const long long member_size, const long long volume_size, - const Lzma_options & encoder_options, const int infd, - const Pretty_print & pp, const struct stat * const in_statsp ) - { - LZ_Encoder * const encoder = - LZ_compress_open( encoder_options.dictionary_size, - encoder_options.match_len_limit, - std::min( member_size, volume_size ) ); - int retval; - - if( !encoder || LZ_compress_errno( encoder ) != LZ_ok ) - { - if( !encoder || LZ_compress_errno( encoder ) == LZ_mem_error ) - pp( "Not enough memory. Try a smaller dictionary size" ); - else - internal_error( "invalid argument to encoder" ); - retval = 1; - } - else retval = do_compress( encoder, member_size, volume_size, - infd, pp, in_statsp ); - LZ_compress_close( encoder ); - return retval; - } - - -int do_decompress( LZ_Decoder * const decoder, const int infd, - const Pretty_print & pp, const bool testing ) - { - const int buffer_size = 65536; - uint8_t buffer[buffer_size]; - - while( true ) - { - int in_size = std::min( LZ_decompress_write_size( decoder ), buffer_size ); - if( in_size > 0 ) - { - const int max_in_size = in_size; - in_size = readblock( infd, buffer, max_in_size ); - if( in_size != max_in_size && errno ) - { pp(); show_error( "Read error", errno ); return 1; } - if( in_size > 0 && in_size != LZ_decompress_write( decoder, buffer, in_size ) ) - internal_error( "library error (LZ_decompress_write)" ); - if( in_size < max_in_size ) LZ_decompress_finish( decoder ); - } - int out_size = 0; - while( true ) - { - const int rd = LZ_decompress_read( decoder, buffer, buffer_size ); - if( rd > 0 ) - { - out_size += rd; - if( outfd >= 0 ) - { - const int wr = writeblock( outfd, buffer, rd ); - if( wr != rd ) - { pp(); show_error( "Write error", errno ); return 1; } - } - } - else if( rd < 0 ) { out_size = rd; break; } - if( verbosity >= 1 && LZ_decompress_member_finished( decoder ) == 1 ) - { - const long long data_position = LZ_decompress_data_position( decoder ); - const long long member_size = LZ_decompress_member_position( decoder ); - pp(); - if( verbosity >= 2 ) - std::fprintf( stderr, "version %d, dictionary size %7sB. ", - LZ_decompress_member_version( decoder ), - format_num( LZ_decompress_dictionary_size( decoder ) ) ); - if( verbosity >= 3 && data_position > 0 && member_size > 0 ) - std::fprintf( stderr, "%6.3f:1, %6.3f bits/byte, %5.2f%% saved. ", - (double)data_position / member_size, - ( 8.0 * member_size ) / data_position, - 100.0 * ( 1.0 - ( (double)member_size / data_position ) ) ); - if( verbosity >= 4 ) - std::fprintf( stderr, "data CRC %08X, data size %9lld, member size %8lld. ", - LZ_decompress_data_crc( decoder ), - data_position, member_size ); - if( testing ) std::fprintf( stderr, "ok\n" ); - else std::fprintf( stderr, "done\n" ); - pp.reset(); - } - if( rd <= 0 ) break; - } - if( out_size < 0 ) - { - const LZ_Errno lz_errno = LZ_decompress_errno( decoder ); - if( lz_errno == LZ_header_error ) - { - if( LZ_decompress_total_out_size( decoder ) > 0 ) - break; // trailing garbage - pp( "Error reading member header" ); - return 1; - } - if( lz_errno == LZ_mem_error ) - { - pp( "Not enough memory. Find a machine with more memory" ); - return 1; - } - pp(); - if( lz_errno == LZ_unexpected_eof ) - { - if( verbosity >= 0 ) - std::fprintf( stderr, "File ends unexpectedly at pos %lld\n", - LZ_decompress_total_in_size( decoder ) ); - return 2; - } - if( verbosity >= 0 ) - std::fprintf( stderr, "LZ_decompress_read error: %s.\n", - LZ_strerror( LZ_decompress_errno( decoder ) ) ); - return 1; - } - if( LZ_decompress_finished( decoder ) == 1 ) break; - if( in_size == 0 && out_size == 0 ) - internal_error( "library error (LZ_decompress_read)" ); - } - return 0; - } - - -int decompress( const int infd, const Pretty_print & pp, - const bool testing ) - { - LZ_Decoder * const decoder = LZ_decompress_open(); - int retval; - - if( !decoder || LZ_decompress_errno( decoder ) != LZ_ok ) - { - pp( "Not enough memory. Find a machine with more memory" ); - retval = 1; - } - else retval = do_decompress( decoder, infd, pp, testing ); - - LZ_decompress_close( decoder ); - 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 - - -void Pretty_print::operator()( const char * const msg ) const throw() - { - if( verbosity >= 0 ) - { - if( first_post ) - { - first_post = false; - std::fprintf( stderr, " %s: ", name_.c_str() ); - for( unsigned int i = 0; i < longest_name - name_.size(); ++i ) - std::fprintf( stderr, " " ); - if( !msg ) std::fflush( stderr ); - } - if( msg ) std::fprintf( stderr, "%s.\n", msg ); - } - } - - -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 ); - } - - -// 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 ) throw() - { - int rest = size; - errno = 0; - while( rest > 0 ) - { - errno = 0; - const int n = read( fd, buf + size - rest, rest ); - if( n > 0 ) rest -= n; - else if( n == 0 ) break; - else if( errno != EINTR && errno != EAGAIN ) break; - } - return ( rest > 0 ) ? size - rest : size; - } - - -// 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 ) throw() - { - int rest = size; - errno = 0; - while( rest > 0 ) - { - errno = 0; - const int n = write( fd, buf + size - rest, rest ); - if( n > 0 ) rest -= n; - else if( errno && errno != EINTR && errno != EAGAIN ) break; - } - return ( rest > 0 ) ? size - rest : size; - } - - -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 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 - Lzma_options encoder_options = option_mapping[6]; // default = "-6" - long long member_size = LLONG_MAX; - long long volume_size = LLONG_MAX; - int infd = -1; - Mode program_mode = m_compress; - bool force = false; - bool keep_input_files = false; - bool recompress = false; - bool to_stdout = false; - std::string input_filename; - std::string default_output_filename; - std::vector< std::string > filenames; - invocation_name = argv[0]; - - if( LZ_version()[0] != LZ_version_string[0] ) - internal_error( "bad library version" ); - - if( std::strcmp( PROGVERSION, LZ_version_string ) ) - internal_error( "bad library version_string" ); - - const Arg_parser::Option options[] = - { - { '0', "fast", 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', "best", Arg_parser::no }, - { 'b', "member-size", Arg_parser::yes }, - { 'c', "stdout", Arg_parser::no }, - { 'd', "decompress", Arg_parser::no }, - { 'e', "extreme", Arg_parser::no }, - { 'f', "force", Arg_parser::no }, - { 'F', "recompress", Arg_parser::no }, - { 'h', "help", Arg_parser::no }, - { 'k', "keep", Arg_parser::no }, - { 'm', "match-length", Arg_parser::yes }, - { 'o', "output", Arg_parser::yes }, - { 'q', "quiet", Arg_parser::no }, - { 's', "dictionary-size", Arg_parser::yes }, - { 'S', "volume-size", Arg_parser::yes }, - { '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 - const char * const arg = parser.argument( argind ).c_str(); - switch( code ) - { - case '0': case '1': case '2': case '3': case '4': - case '5': case '6': case '7': case '8': case '9': - encoder_options = option_mapping[code-'0']; break; - case 'b': member_size = getnum( arg, 100000, LLONG_MAX / 2 ); break; - case 'c': to_stdout = true; break; - case 'd': program_mode = m_decompress; break; - case 'e': break; // ignored by now - 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, LZ_min_match_len_limit(), - LZ_max_match_len_limit() ); break; - 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': volume_size = getnum( arg, 100000, LLONG_MAX / 2 ); break; - case 't': 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 defined(__OS2__) - _fsetmode( stdin, "b" ); - _fsetmode( stdout, "b" ); -#endif - - 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 ); - if( program_mode == m_test ) - outfd = -1; - - 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 - { - if( program_mode == m_compress ) - set_c_outname( default_output_filename, volume_size != LLONG_MAX ); - else output_filename = default_output_filename; - outfd_mode = S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH | S_IWOTH; - 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, 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 ) - set_c_outname( input_filename, volume_size != LLONG_MAX ); - else set_d_outname( input_filename, eindex ); - outfd_mode = S_IRUSR | S_IWUSR; - if( !open_outstream( force ) ) - { - if( outfd == -1 && retval < 1 ) retval = 1; - close( infd ); infd = -1; - continue; - } - } - } - } - - if( !check_tty( infd, program_mode ) ) 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 ); - int tmp = 0; - if( program_mode == m_compress ) - tmp = compress( member_size, volume_size, encoder_options, infd, - pp, in_statsp ); - else - 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; - } |