From 10e3a59a25eda2b93c796c47359853c5b8dfc6ea Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sun, 10 Nov 2024 09:40:31 +0100 Subject: Merging upstream version 1.14~rc1. Signed-off-by: Daniel Baumann --- main.c | 101 ++++++++++++++++++++++++++++++++++++----------------------------- 1 file changed, 56 insertions(+), 45 deletions(-) (limited to 'main.c') diff --git a/main.c b/main.c index 6d0fcc1..722ebe3 100644 --- a/main.c +++ b/main.c @@ -28,7 +28,7 @@ #include #include -#include /* SSIZE_MAX */ +#include /* CHAR_BIT, SSIZE_MAX */ #include #include #include /* SIZE_MAX */ @@ -114,18 +114,18 @@ static void show_help( void ) printf( "Pdlzip is a permissively licensed implementation of the lzip data\n" "compressor, intended for those who can't distribute (or even use) GPL\n" "licensed Free Software. The name of pdlzip comes from 'public domain lzip'.\n" - "Pdlzip is written in C and is compatible with lzip 1.4 or newer.\n" + "Pdlzip is written in C.\n" "\nLzip is a lossless data compressor with a user interface similar to the one\n" - "of gzip or bzip2. Lzip uses a simplified form of the 'Lempel-Ziv-Markov\n" - "chain-Algorithm' (LZMA) stream format to maximize interoperability. The\n" - "maximum dictionary size is 512 MiB so that any lzip file can be decompressed\n" - "on 32-bit machines. Lzip provides accurate and robust 3-factor integrity\n" - "checking. Lzip can compress about as fast as gzip (lzip -0) or compress most\n" - "files more than bzip2 (lzip -9). Decompression speed is intermediate between\n" - "gzip and bzip2. Lzip is better than gzip and bzip2 from a data recovery\n" - "perspective. Lzip has been designed, written, and tested with great care to\n" - "replace gzip and bzip2 as the standard general-purpose compressed format for\n" - "Unix-like systems.\n" + "of gzip or bzip2. Lzip uses a simplified form of LZMA (Lempel-Ziv-Markov\n" + "chain-Algorithm) designed to achieve complete interoperability between\n" + "implementations. The maximum dictionary size is 512 MiB so that any lzip\n" + "file can be decompressed on 32-bit machines. Lzip provides accurate and\n" + "robust 3-factor integrity checking. 'lzip -0' compresses about as fast as\n" + "gzip, while 'lzip -9' compresses most files more than bzip2. Decompression\n" + "speed is intermediate between gzip and bzip2. Lzip provides better data\n" + "recovery capabilities than gzip and bzip2. Lzip has been designed, written,\n" + "and tested with great care to replace gzip and bzip2 as general-purpose\n" + "compressed format for Unix-like systems.\n" "\nPdlzip is also able to decompress legacy lzma-alone (.lzma) files.\n" "Lzma-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" @@ -226,6 +226,9 @@ static void Pp_init( struct Pretty_print * const pp, if( pp->longest_name == 0 ) pp->longest_name = stdin_name_len; } +void Pp_free( struct Pretty_print * const pp ) + { if( pp->padded_name ) { free( pp->padded_name ); pp->padded_name = 0; } } + static void Pp_set_name( struct Pretty_print * const pp, const char * const filename ) { @@ -268,7 +271,7 @@ static void show_header( const unsigned dictionary_size ) const char * p = ""; const char * np = " "; unsigned num = dictionary_size; - bool exact = ( num % factor == 0 ); + bool exact = num % factor == 0; int i; for( i = 0; i < n && ( num > 9999 || ( exact && num >= factor ) ); ++i ) { num /= factor; if( num % factor != 0 ) exact = false; @@ -277,7 +280,7 @@ static void show_header( const unsigned dictionary_size ) } -/* separate numbers of 5 or more digits in groups of 3 digits using '_' */ +/* separate numbers of 6 or more digits in groups of 3 digits using '_' */ static const char * format_num3( unsigned long long num ) { enum { buffers = 8, bufsize = 4 * sizeof num, n = 10 }; @@ -289,7 +292,7 @@ static const char * format_num3( unsigned long long num ) char * const buf = buffer[current++]; current %= buffers; char * p = buf + bufsize - 1; /* fill the buffer backwards */ *p = 0; /* terminator */ - if( num > 1024 ) + if( num > 9999 ) { char prefix = 0; /* try binary first, then si */ for( i = 0; i < n && num != 0 && num % 1024 == 0; ++i ) @@ -300,7 +303,7 @@ static const char * format_num3( unsigned long long num ) { num /= 1000; prefix = si_prefix[i]; } if( prefix ) *(--p) = prefix; } - const bool split = num >= 10000; + const bool split = num >= 100000; for( i = 0; ; ) { @@ -335,7 +338,7 @@ static unsigned long getnum( const char * const arg, if( !errno && tail[0] ) { - const unsigned factor = ( tail[1] == 'i' ) ? 1024 : 1000; + const unsigned factor = (tail[1] == 'i') ? 1024 : 1000; int exponent = 0; /* 0 = bad multiplier */ int i; switch( tail[0] ) @@ -458,7 +461,7 @@ static int open_instream( const char * const name, struct stat * const in_statsp if( program_mode == m_compress && !recompress && eindex >= 0 ) { if( verbosity >= 0 ) - fprintf( stderr, "%s: %s: Input file already has '%s' suffix.\n", + fprintf( stderr, "%s: %s: Input file already has '%s' suffix, ignored.\n", program_name, name, known_extensions[eindex].from ); return -1; } @@ -469,9 +472,9 @@ static int open_instream( const char * const name, struct stat * const in_statsp { 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 ) ) ); + const bool can_read = i == 0 && + ( S_ISBLK( mode ) || S_ISCHR( mode ) || + S_ISFIFO( mode ) || S_ISSOCK( mode ) ); if( i != 0 || ( !S_ISREG( mode ) && ( !can_read || one_to_one ) ) ) { if( verbosity >= 0 ) @@ -616,7 +619,7 @@ static int compress( const int infd, const struct Lzma_options * const } if( writeblock( outfd, header, Lh_size ) != Lh_size ) - { show_error( "Can't write output file", errno, false ); retval = 1; } + { show_error( "Write error", errno, false ); retval = 1; } else if( LzmaEnc_Encode( encoder ) != 0 ) { Pp_show_msg( pp, "Encoder error." ); retval = 1; } @@ -684,7 +687,7 @@ static int lzma_decode( uint64_t unpackSize, CLzmaDec *decoder, const int infd, unsigned long long member_size = lzma_header_size, data_size = 0; uint8_t outBuf[OUT_BUF_SIZE]; int outPos = 0; - const bool thereIsSize = (unpackSize != (uint64_t)-1); + const bool thereIsSize = unpackSize != (uint64_t)-1; for (;;) { @@ -711,7 +714,7 @@ static int lzma_decode( uint64_t unpackSize, CLzmaDec *decoder, const int infd, unpackSize -= outProcessed; if( outfd >= 0 && writeblock( outfd, outBuf, outPos ) != outPos ) - { show_error( "Can't write output file", errno, false ); return 1; } + { show_error( "Write error", errno, false ); return 1; } data_size += outPos; outPos = 0; @@ -734,7 +737,7 @@ static int lzma_decode( uint64_t unpackSize, CLzmaDec *decoder, const int infd, 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 ) + const unsigned dictionary_size, bool * const data0p ) { unsigned long long member_size = Lh_size, data_size = 0; uint8_t outBuf[OUT_BUF_SIZE]; @@ -762,7 +765,7 @@ static int lzip_decode( CLzmaDec *decoder, const int infd, outPos += outProcessed; if( outfd >= 0 && writeblock( outfd, outBuf, outPos ) != outPos ) - { show_error( "Can't write output file", errno, false ); return 1; } + { show_error( "Write error", errno, false ); return 1; } CRC32_update_buf( &crc, outBuf, outPos ); data_size += outPos; @@ -830,15 +833,16 @@ static int lzip_decode( CLzmaDec *decoder, const int infd, } if( error ) return 2; show_results( data_size, member_size, td_crc, dictionary_size, true ); + *data0p = data_size == 0; return 0; } } } -static int decompress( const int infd, struct Pretty_print * const pp, - const bool ignore_trailing, const bool loose_trailing, - const bool testing ) +static int decompress( const int infd, const struct Cl_options * const cl_opts, + struct Pretty_print * const pp, + const bool from_stdin, const bool testing ) { uint64_t unpackSize = 0; CLzmaDec decoder; @@ -848,6 +852,7 @@ static int decompress( const int infd, struct Pretty_print * const pp, bool lzip_mode = true; bool first_member; uint8_t raw_props[lzma_header_size]; + bool empty = false, multi = false; for( first_member = true; ; first_member = false ) { @@ -867,7 +872,7 @@ static int decompress( const int infd, struct Pretty_print * const pp, else if( Lh_check_prefix( header, size ) ) { Pp_show_msg( pp, "Truncated header in multimember file." ); retval = 2; } - else if( size > 0 && !ignore_trailing ) + else if( size > 0 && !cl_opts->ignore_trailing ) { Pp_show_msg( pp, trailing_msg ); retval = 2; } break; } @@ -875,10 +880,10 @@ static int decompress( const int infd, struct Pretty_print * const pp, { if( !first_member ) { - if( !loose_trailing && Lh_check_corrupt( header ) ) + if( !cl_opts->loose_trailing && Lh_check_corrupt( header ) ) { Pp_show_msg( pp, "Corrupt header in multimember file." ); retval = 2; } - else if( !ignore_trailing ) + else if( !cl_opts->ignore_trailing ) { Pp_show_msg( pp, trailing_msg ); retval = 2; } break; } @@ -929,19 +934,23 @@ static int decompress( const int infd, struct Pretty_print * const pp, if( !LzmaDec_Init( &decoder, raw_props ) ) { Pp_show_msg( pp, mem_msg ); return 1; } + bool data0 = false; if( lzip_mode ) retval = lzip_decode( &decoder, infd, pp, inBuf, &inPos, &inSize, - dictionary_size ); + dictionary_size, &data0 ); else retval = lzma_decode( unpackSize, &decoder, infd, inBuf, &inPos, &inSize, dictionary_size, testing ); LzmaDec_Free(&decoder); if( retval != 0 || !lzip_mode ) break; + if( !from_stdin ) { multi = !first_member; if( data0 ) empty = true; } if( verbosity >= 2 ) { fputs( testing ? "ok\n" : "done\n", stderr ); Pp_reset( pp ); } } if( lzip_mode && verbosity == 1 && retval == 0 ) fputs( testing ? "ok\n" : "done\n", stderr ); + if( empty && multi && retval == 0 ) + { show_file_error( pp->name, empty_msg, 0 ); retval = 2; } return retval; } @@ -1038,10 +1047,10 @@ int main( const int argc, const char * const argv[] ) const char * default_output_filename = ""; enum Mode program_mode = m_compress; int i; + struct Cl_options cl_opts; /* command-line options */ + Cl_options_init( &cl_opts ); bool force = false; - bool ignore_trailing = true; bool keep_input_files = false; - bool loose_trailing = false; bool recompress = false; bool to_stdout = false; if( argc > 0 ) invocation_name = argv[0]; @@ -1077,7 +1086,7 @@ int main( const int argc, const char * const argv[] ) { 'v', "verbose", ap_no }, { 'V', "version", ap_no }, { opt_lt, "loose-trailing", ap_no }, - { 0, 0, ap_no } }; + { 0, 0, ap_no } }; CRC32_init(); @@ -1097,11 +1106,11 @@ int main( const int argc, const char * const argv[] ) const char * const arg = ap_argument( &parser, argind ); switch( code ) { - case '0': case '1': case '2': case '3': case '4': - case '5': case '6': case '7': case '8': case '9': + 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 'a': ignore_trailing = false; break; - case 'b': break; + case 'a': cl_opts.ignore_trailing = false; break; + case 'b': break; /* ignored */ case 'c': to_stdout = true; break; case 'd': set_mode( &program_mode, m_decompress ); break; case 'f': force = true; break; @@ -1110,17 +1119,17 @@ int main( const int argc, const char * const argv[] ) case 'k': keep_input_files = true; break; case 'm': encoder_options.match_len_limit = getnum( arg, pn, min_match_len_limit, max_match_len ); break; - case 'n': break; + case 'n': break; /* ignored */ case 'o': if( strcmp( arg, "-" ) == 0 ) to_stdout = true; else { default_output_filename = arg; } break; case 'q': verbosity = -1; break; case 's': encoder_options.dictionary_size = get_dict_size( arg, pn ); break; - case 'S': break; + case 'S': break; /* ignored */ case 't': set_mode( &program_mode, m_test ); break; case 'v': if( verbosity < 4 ) ++verbosity; break; case 'V': show_version(); return 0; - case opt_lt: loose_trailing = true; break; + case opt_lt: cl_opts.loose_trailing = true; break; default: internal_error( "uncaught option." ); } } /* end process options */ @@ -1168,9 +1177,10 @@ int main( const int argc, const char * const argv[] ) { const char * input_filename = ""; int infd; + const bool from_stdin = strcmp( filenames[i], "-" ) == 0; Pp_set_name( &pp, filenames[i] ); - if( strcmp( filenames[i], "-" ) == 0 ) + if( from_stdin ) { if( stdin_used ) continue; else stdin_used = true; infd = STDIN_FILENO; @@ -1215,7 +1225,7 @@ int main( const int argc, const char * const argv[] ) if( program_mode == m_compress ) tmp = compress( infd, &encoder_options, &pp ); else - tmp = decompress( infd, &pp, ignore_trailing, loose_trailing, + tmp = decompress( infd, &cl_opts, &pp, from_stdin, program_mode == m_test ); if( close( infd ) != 0 ) { show_file_error( pp.name, "Error closing input file", errno ); @@ -1243,6 +1253,7 @@ int main( const int argc, const char * const argv[] ) program_name, failed_tests, ( failed_tests == 1 ) ? "file" : "files" ); free( output_filename ); + Pp_free( &pp ); free( filenames ); ap_free( &parser ); return retval; -- cgit v1.2.3