diff options
Diffstat (limited to 'main.cc')
-rw-r--r-- | main.cc | 996 |
1 files changed, 306 insertions, 690 deletions
@@ -1,5 +1,5 @@ -/* Zutils - A file format detector for compressed files - Copyright (C) 2009 Antonio Diaz Diaz. +/* Zutils - Utilities dealing with compressed files + Copyright (C) 2009, 2010 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 @@ -14,257 +14,69 @@ 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 zutils to panic. -*/ #define _FILE_OFFSET_BITS 64 -#include <algorithm> #include <cerrno> #include <climits> #include <csignal> #include <cstdio> #include <cstdlib> #include <cstring> +#include <list> #include <string> #include <vector> +#include <dirent.h> #include <fcntl.h> #include <stdint.h> #include <unistd.h> -#include <utime.h> #include <sys/stat.h> -#include <sys/time.h> +#if defined(__MSVCRT__) || defined(__OS2__) +#include <io.h> +#endif #include "arg_parser.h" +#include "zutils.h" -#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 +#if CHAR_BIT != 8 +#error "Environments where CHAR_BIT != 8 are not supported." #endif namespace { -const char * invocation_name = 0; -const char * const Program_name = "Zutils"; -const char * const program_name = "zutils"; -const char * const program_year = "2009"; - -struct { const char * from; const char * to; } const known_extensions[] = { - { ".zf", "" }, - { 0, 0 } }; - -enum Mode { m_compress = 0, m_decompress, m_test }; - -std::string output_filename; -int outhandle = -1; -int verbosity = 0; -bool delete_output_on_interrupt = false; - - -class Pretty_print - { - const char * const stdin_name; - const unsigned int stdin_name_len; - unsigned int longest_name; - std::string name_; - mutable bool first_post; - -public: - Pretty_print( const std::vector< std::string > & filenames ) - : stdin_name( "(stdin)" ), stdin_name_len( std::strlen( stdin_name ) ), - longest_name( 0 ), first_post( false ) - { - 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(); - }; - +#ifdef O_BINARY +const int o_binary = O_BINARY; +#else +const int o_binary = 0; +#endif -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 ); - } - } +enum Mode { m_none, m_zcat, m_zgrep, m_ztest }; void show_help() throw() { - std::printf( "%s - A file format detector for compressed files.\n", Program_name ); - std::printf( "\nUsage: %s [options] [files]\n", invocation_name ); - std::printf( "\nOptions:\n" ); + std::printf( "Zutils is a collection of utilities able to deal with any combination of\n" ); + std::printf( "compressed and non-compressed files transparently. If any given file,\n" ); + std::printf( "including standard input, is compressed, its uncompressed content is used.\n" ); + std::printf( "The supported compressors are bzip2, gzip, lzip and xz.\n" ); + std::printf( "\nUsage: %s <operation> [options] [files]\n", invocation_name ); + std::printf( "\nTry `%s <operation> --help' for more specific help.\n", invocation_name ); + std::printf( "\nOperations:\n" ); std::printf( " -h, --help display this help and exit\n" ); std::printf( " -V, --version output version information and exit\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( " -k, --keep keep (don't delete) input files\n" ); - std::printf( " -m, --magic=<type> output magic bytes for given file type\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( " -t, --test test compressed file type\n" ); - std::printf( " -v, --verbose be verbose (a 2nd -v gives more)\n" ); - std::printf( "\nReport bugs to zutils-bug@nongnu.org\n" ); - std::printf( "Zutils home page: http://www.nongnu.org/zutils/zutils.html\n" ); + std::printf( " --zcat zcat operation\n" ); + std::printf( " --zgrep zgrep operation\n" ); + std::printf( " --ztest ztest operation\n" ); + show_help_addr(); } -void show_version() throw() +int simple_extension_index( const std::string & name ) 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" ); - } - - -void show_error( const char * msg, const int errcode = 0, const bool help = false ) throw() - { - if( verbosity >= 0 ) + for( int i = 0; simple_extensions[i]; ++i ) { - if( msg && msg[0] != 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] != 0 ) - std::fprintf( stderr, "Try `%s --help' for more information.\n", invocation_name ); - } - } - - -void internal_error( const char * msg ) - { - std::string s( "internal error: " ); s += msg; - show_error( s.c_str() ); - std::exit( 3 ); - } - - -const char * format_num( long long num, long long limit = 9999, - const int set_prefix = 0 ) throw() - { - const char * const si_prefix[8] = - { "k", "M", "G", "T", "P", "E", "Z", "Y" }; - const char * const binary_prefix[8] = - { "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi" }; - static bool si = false; - static char buf[16]; - - if( set_prefix ) si = ( set_prefix > 0 ); - const int factor = ( si ) ? 1000 : 1024; - const char * const *prefix = ( si ) ? si_prefix : binary_prefix; - const char *p = ""; - limit = std::max( 999LL, std::min( 999999LL, limit ) ); - - for( int i = 0; i < 8 && ( llabs( num ) > limit || - ( llabs( num ) >= factor && num % factor == 0 ) ); ++i ) - { num /= factor; p = prefix[i]; } - snprintf( buf, sizeof buf, "%lld %s", num, p ); - return buf; - } - - -long long getnum( const char * ptr, const int bs, - 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 'b': if( bs > 0 ) { factor = bs; exponent = 1; } - else bad_multiplier = true; - 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 extension_index( const std::string & name ) throw() - { - for( int i = 0; known_extensions[i].from; ++i ) - { - const std::string ext( known_extensions[i].from ); + const std::string ext( simple_extensions[i] ); if( name.size() > ext.size() && name.compare( name.size() - ext.size(), ext.size(), ext ) == 0 ) return i; @@ -273,449 +85,262 @@ int extension_index( const std::string & name ) throw() } -int open_instream( const std::string & name, struct stat * in_statsp, - const Mode program_mode, const int eindex, - const bool force, const bool to_stdout ) throw() +int open_instream( std::string & input_filename, const Mode program_mode ) throw() { - int inhandle = -1; - if( program_mode == m_compress && !force && 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 + int infd = open( input_filename.c_str(), O_RDONLY | o_binary ); + if( infd < 0 ) { - inhandle = open( name.c_str(), O_RDONLY ); - if( inhandle < 0 ) + if( ( program_mode == m_zcat || program_mode == m_zgrep ) + && simple_extension_index( input_filename ) < 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( inhandle, in_statsp ); - const mode_t & mode = in_statsp->st_mode; - if( i < 0 || !( S_ISREG( mode ) || ( to_stdout && - ( S_ISFIFO( mode ) || S_ISSOCK( mode ) || - S_ISBLK( mode ) || S_ISCHR( mode ) ) ) ) ) + for( int i = 0; simple_extensions[i]; ++i ) { - if( verbosity >= 0 ) - std::fprintf( stderr, "%s: input file `%s' is not a regular file%s.\n", - program_name, name.c_str(), - to_stdout ? "" : " and `--stdout' was not specified" ); - close( inhandle ); - inhandle = -1; + const std::string name( input_filename + simple_extensions[i] ); + infd = open( name.c_str(), O_RDONLY | o_binary ); + if( infd >= 0 ) { input_filename = name; break; } } } + if( infd < 0 && verbosity >= 0 ) + std::fprintf( stderr, "%s: Can't open input file `%s': %s.\n", + util_name, input_filename.c_str(), std::strerror( errno ) ); } - return inhandle; - } - - -void set_c_outname( const std::string & name ) throw() - { - output_filename = name; - 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 >= 0 ) - 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() - { -/* if( force ) - outhandle = open( output_filename.c_str(), O_CREAT | O_TRUNC | O_WRONLY, - S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH ); - else outhandle = open( output_filename.c_str(), O_CREAT | O_EXCL | O_WRONLY, - S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH ); - if( outhandle < 0 ) - { - if( errno == EEXIST ) outhandle = -2; else outhandle = -1; - if( verbosity >= 0 ) - { - if( outhandle == -2 ) - 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 ( outhandle >= 0 ); - } - - -bool check_tty( const int inhandle, const Mode program_mode ) throw() - { - if( program_mode == m_compress && isatty( outhandle ) ) - { - 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( inhandle ) ) - { - show_error( "I won't read compressed data from a terminal.", 0, true ); - return false; - } - return true; + return infd; } +#include "zcat.cc" +#include "zgrep.cc" +#include "ztest.cc" -void cleanup_and_fail( const int retval ) throw() - { - if( delete_output_on_interrupt ) - { - if( verbosity >= 0 ) - std::fprintf( stderr, "%s: Deleting output file `%s', if it exists.\n", - program_name, output_filename.c_str() ); - if( outhandle >= 0 ) { close( outhandle ); outhandle = -1; } - if( std::remove( output_filename.c_str() ) != 0 ) - 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 * in_statsp, int * retvalp ) - { - int tmp = 0; - if( in_statsp ) - { - if( fchmod( outhandle, in_statsp->st_mode ) != 0 ) tmp = 1; - if( !tmp ) (void)fchown( outhandle, in_statsp->st_uid, in_statsp->st_gid ); - // fchown will in many cases return with EPERM, which can be safely ignored. - } - if( close( outhandle ) == 0 ) outhandle = -1; - else cleanup_and_fail( 1 ); - delete_output_on_interrupt = false; - if( !in_statsp ) return; - if( !tmp ) - { - struct utimbuf t; - t.actime = in_statsp->st_atime; - t.modtime = in_statsp->st_mtime; - tmp = utime( output_filename.c_str(), &t ); - } - if( tmp ) - { - if( tmp > *retvalp ) *retvalp = tmp; - show_error( "I can't change output file attributes." ); - cleanup_and_fail( *retvalp ); - } - } +} // end namespace -// Returns the number of bytes really read. -// If (returned value < size) and (errno == 0), means EOF was reached. -// -int readblock( const int fd, char * buf, const int size ) throw() +int main( const int argc, const char * const argv[] ) { - 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; - } - + enum { help_opt = 256, verbose_opt, zcat_opt, zgrep_opt, ztest_opt }; + const Arg_parser::Option * options = 0; + int infd = -1; + Mode program_mode = m_none; + bool recursive = false; + std::string input_filename; + std::list< std::string > filenames; + Cat_options cat_options; + std::vector< const char * > grep_args; // args to grep, maybe empty + std::vector< const char * > ztest_args; // args to ztest, maybe empty + invocation_name = argv[0]; -// Returns the number of bytes really written. -// If (returned value < size), it is always an error. -// -int writeblock( const int fd, const char * buf, const int size ) throw() - { - int rest = size; - errno = 0; - while( rest > 0 ) + const Arg_parser::Option m_zcat_options[] = { - 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 compress( const int inhandle, const Pretty_print & pp, - const struct stat * in_statsp, int * retvalp ) - { - long long in_size = 0, out_size = 0; - if( verbosity >= 1 ) + { 'A', "show-all", Arg_parser::no }, // cat + { 'b', "number-nonblank", Arg_parser::no }, // cat + { 'c', "stdout", Arg_parser::no }, // gzip + { 'd', "decompress", Arg_parser::no }, // gzip + { 'e', 0, Arg_parser::no }, // cat + { 'E', "show-ends", Arg_parser::no }, // cat + { 'f', "force", Arg_parser::no }, // gzip + { 'h', "help", Arg_parser::no }, + { 'l', "list", Arg_parser::no }, // gzip + { 'L', "license", Arg_parser::no }, // gzip + { 'n', "number", Arg_parser::no }, // cat + { 'q', "quiet", Arg_parser::no }, + { 'r', "recursive", Arg_parser::no }, + { 's', "squeeze-blank", Arg_parser::no }, // cat + { 't', 0, Arg_parser::no }, // cat + { 'T', "show-tabs", Arg_parser::no }, // cat + { 'v', "show-nonprinting", Arg_parser::no }, // cat + { 'V', "version", Arg_parser::no }, + { verbose_opt, "verbose", Arg_parser::no }, + { zcat_opt, "zcat", Arg_parser::no }, + { 0 , 0, Arg_parser::no } }; + + const Arg_parser::Option m_zgrep_options[] = { - pp(); - 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 decompress( const int inhandle, const Pretty_print & pp ) - { - if( verbosity >= 1 ) - std::fprintf( stderr, "done\n" ); - return 0; - } -*/ - -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; - } - - -int xtoi( const unsigned char ch ) throw() - { - switch( ch ) + { 'a', "text", Arg_parser::no }, // grep GNU + { 'A', "after-context", Arg_parser::yes }, // grep GNU + { 'b', "byte-offset", Arg_parser::no }, // grep GNU + { 'B', "before-context", Arg_parser::yes }, // grep GNU + { 'c', "count", Arg_parser::no }, // grep + { 'C', "context", Arg_parser::yes }, // grep GNU + { 'e', "regexp", Arg_parser::yes }, // grep + { 'E', "extended-regexp", Arg_parser::no }, // grep + { 'f', "file ", Arg_parser::yes }, // grep + { 'F', "fixed-strings", Arg_parser::no }, // grep + { 'h', "no-filename", Arg_parser::no }, // grep GNU + { 'H', "with-filename", Arg_parser::no }, // grep GNU + { 'i', "ignore-case", Arg_parser::no }, // grep + { 'I', 0, Arg_parser::no }, // grep GNU + { 'l', "files-with-matches", Arg_parser::no }, // grep + { 'L', "files-without-match", Arg_parser::no }, // grep GNU + { 'm', "max-count", Arg_parser::yes }, // grep GNU + { 'n', "line-number", Arg_parser::no }, // grep + { 'o', "only-matching", Arg_parser::no }, // grep + { 'q', "quiet", Arg_parser::no }, + { 'r', "recursive", Arg_parser::no }, + { 's', "no-messages", Arg_parser::no }, // grep + { 'v', "invert-match", Arg_parser::no }, // grep + { 'V', "version", Arg_parser::no }, + { 'w', "word-regexp", Arg_parser::no }, // grep GNU + { 'x', "line-regexp", Arg_parser::no }, // grep + { help_opt, "help", Arg_parser::no }, + { verbose_opt, "verbose", Arg_parser::no }, + { zgrep_opt, "zgrep", Arg_parser::no }, + { 0 , 0, Arg_parser::no } }; + + const Arg_parser::Option m_ztest_options[] = { - case '0': return 0; - case '1': return 1; - case '2': return 2; - case '3': return 3; - case '4': return 4; - case '5': return 5; - case '6': return 6; - case '7': return 7; - case '8': return 8; - case '9': return 9; - case 'a': - case 'A': return 0x0A; - case 'b': - case 'B': return 0x0B; - case 'c': - case 'C': return 0x0C; - case 'd': - case 'D': return 0x0D; - case 'e': - case 'E': return 0x0E; - case 'f': - case 'F': return 0x0F; - default: return -1; - } - } - - -bool hex_to_data( const std::string & hex, std::string & data ) - { - data.clear(); - if( hex.size() == 0 || hex.size() % 2 != 0 ) return false; - for( unsigned int i = 0; 2 * i + 1 < hex.size(); ++i ) + { 'h', "help", Arg_parser::no }, + { 'q', "quiet", Arg_parser::no }, + { 'r', "recursive", Arg_parser::no }, + { 'v', "verbose", Arg_parser::no }, + { 'V', "version", Arg_parser::no }, + { ztest_opt, "ztest", Arg_parser::no }, + { 0 , 0, Arg_parser::no } }; + + { // parse operation + const Arg_parser::Option operations[] = { - int uch = xtoi( hex[2*i] ); - int lch = xtoi( hex[2*i+1] ); - if( uch < 0 || lch < 0 ) return false; - data.push_back( ( uch << 4 ) | lch ); - } - return true; - } - - -int print_magic_type( const std::string & magic_type ) - { - std::string data; - - if( magic_type == "bzip2" ) std::printf( "BZh" ); - else if( magic_type == "gzip" ) std::printf( "\x1F\x8B" ); - else if( magic_type == "lzip" ) std::printf( "LZIP" ); - else if( magic_type == "xz" ) std::printf( "%c7zXZ", '\xFD' ); - else if( hex_to_data( magic_type, data ) ) std::printf( data.c_str() ); - else return 1; - return 0; - } - + { 'h', "help", Arg_parser::no }, + { 'V', "version", Arg_parser::no }, + { zcat_opt, "zcat", Arg_parser::no }, + { zgrep_opt, "zgrep", Arg_parser::no }, + { ztest_opt, "ztest", Arg_parser::no }, + { 0 , 0, Arg_parser::no } }; + + const Arg_parser parser( argv[1], ( argc > 2 ) ? argv[2] : 0, operations ); + if( parser.error().size() ) // bad operation + { show_error( parser.error().c_str(), 0, true ); return 1; } -int test_stdin_type( const int inhandle, const Pretty_print & pp ) - { - unsigned char buf[5]; - const char * msg = 0; - int i = 0; - if( readblock( inhandle, (char *)buf, 1 ) == 1 ) + if( parser.arguments() > 0 ) { - if( buf[0] == 0x1F ) + switch( parser.code( 0 ) ) { - if( readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == 0x8B ) - msg = "gzip"; - } - else if( buf[0] == 'B' ) - { - if( readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == 'Z' && - readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == 'h' ) - msg = "bzip2"; - } - else if( buf[0] == 'L' ) - { - if( readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == 'Z' && - readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == 'I' && - readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == 'P' ) - msg = "lzip"; - } - else if( buf[0] == 0xFD ) - { - if( readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == '7' && - readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == 'z' && - readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == 'X' && - readblock( inhandle, (char *)&buf[++i], 1 ) == 1 && buf[i] == 'Z' ) - msg = "xz"; - } - } - const int retval = ( msg ? 0 : 1 ); - if( verbosity >= 0 ) - { - if( verbosity >= 1 ) pp(); - if( !msg ) - { - char hexmsg[(2*sizeof buf)+1]; - for( int j = 0; j <= i; ++j ) - { - hexmsg[2*j] = xdigit( buf[j] >> 4 ); - hexmsg[2*j+1] = xdigit( buf[j] & 0x0F ); - } - hexmsg[2*i+2] = 0; - msg = hexmsg; + case 0 : break; + case 'h': show_help(); return 0; + case 'V': show_version(); return 0; + case zcat_opt : program_mode = m_zcat; options = m_zcat_options; + util_name = "zcat"; break; + case zgrep_opt : program_mode = m_zgrep; options = m_zgrep_options; + util_name = "zgrep"; break; + case ztest_opt : program_mode = m_ztest; options = m_ztest_options; + util_name = "ztest"; break; + default : internal_error( "uncaught option" ); } - std::printf( "%s\n", msg ); } - return retval; - } +#if defined(__MSVCRT__) || defined(__OS2__) + _setmode( STDIN_FILENO, O_BINARY ); + _setmode( STDOUT_FILENO, O_BINARY ); +#endif -int test_type( const int inhandle, const Pretty_print & pp ) - { - unsigned char buf[5]; - const char * msg = 0; - const int size = readblock( inhandle, (char *)buf, sizeof buf ); - if( size == (int)sizeof buf ) - { - if( buf[0] == 0x1F && buf[1] == 0x8B ) - msg = "gzip"; - else if( buf[0] == 'B' && buf[1] == 'Z' && buf[2] == 'h' ) - msg = "bzip2"; - else if( buf[0] == 'L' && buf[1] == 'Z' && buf[2] == 'I' && buf[3] == 'P' ) - msg = "lzip"; - else if( buf[0] == 0xFD && buf[1] == '7' && buf[2] == 'z' && buf[3] == 'X' && buf[4] == 'Z' ) - msg = "xz"; - } - const int retval = ( msg ? 0 : 1 ); - if( verbosity >= 0 ) + if( program_mode == m_none ) { - if( verbosity >= 1 ) pp(); - if( !msg ) msg = "unknown"; - std::printf( "%s\n", msg ); + show_error( "You must specify the operation to be performed.", 0, true ); + return 1; } - return retval; - } - - -extern "C" void signal_handler( int ) throw() - { - show_error( "Control-C or similar caught, quitting." ); - cleanup_and_fail( 0 ); - } - + } // end parse operation -void set_signals() throw() - { - signal( SIGHUP, signal_handler ); - signal( SIGINT, signal_handler ); - signal( SIGTERM, signal_handler ); - } - -} // end namespace - - -int main( const int argc, const char * argv[] ) - { - int inhandle = -1; - Mode program_mode = m_compress; - 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; - std::string magic_type; - 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', "magic", Arg_parser::yes }, - { 'o', "output", Arg_parser::yes }, - { 'q', "quiet", Arg_parser::no }, - { 't', "test", Arg_parser::no }, - { 'v', "verbose", Arg_parser::no }, - { 'V', "version", Arg_parser::no }, - { 0 , 0, Arg_parser::no } }; - - Arg_parser parser( argc, argv, options ); + const Arg_parser parser( argc, argv, options ); if( parser.error().size() ) // bad option - { show_error( parser.error().c_str(), 0, true ); return 1; } + { show_error( parser.error().c_str(), 0, true ); + return ( program_mode == m_zcat ) ? 1 : 2; } int argind = 0; + bool grep_list = false; + bool grep_show_name = true; + bool grep_pattern_found = false; for( ; argind < parser.arguments(); ++argind ) { const int code = parser.code( argind ); - if( !code ) break; // no more options - const std::string & arg = parser.argument( argind ); - switch( code ) + const char * arg = parser.argument( argind ).c_str(); + if( !code ) { - case 'c': to_stdout = true; break; - case 'd': 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': magic_type = arg; break; - case 'o': default_output_filename = arg; break; - case 'q': verbosity = -1; 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" ); + if( program_mode == m_zgrep && !grep_pattern_found ) + { grep_args.push_back( arg ); grep_pattern_found = true; continue; } + else break; // no more options } - } + switch( program_mode ) + { + case m_none: internal_error( "invalid operation" ); + case m_zcat: + switch( code ) + { + case 'A': cat_options.show_ends = true; + cat_options.show_nonprinting = true; + cat_options.show_tabs = true; break; + case 'b': cat_options.number_lines = 1; break; + case 'c': break; + case 'd': break; + case 'e': cat_options.show_nonprinting = true; // fall through + case 'E': cat_options.show_ends = true; break; + case 'f': break; + case 'h': show_zcat_help(); return 0; + case 'l': break; + case 'L': break; + case 'n': if( cat_options.number_lines == 0 ) + { cat_options.number_lines = 2; } break; + case 'q': verbosity = -1; break; + case 'r': recursive = true; break; + case 's': cat_options.squeeze_blank = true; break; + case 't': cat_options.show_nonprinting = true; // fall through + case 'T': cat_options.show_tabs = true; break; + case 'v': cat_options.show_nonprinting = true; break; + case 'V': show_version( "Zcat" ); return 0; + case verbose_opt : if( verbosity < 4 ) ++verbosity; break; + case zcat_opt : break; + default : internal_error( "uncaught option" ); + } break; + case m_zgrep: + switch( code ) + { + case 'a': grep_args.push_back( "-a" ); break; + case 'A': grep_args.push_back( "-A" ); grep_args.push_back( arg ); break; + case 'b': grep_args.push_back( "-b" ); break; + case 'B': grep_args.push_back( "-B" ); grep_args.push_back( arg ); break; + case 'c': grep_args.push_back( "-c" ); break; + case 'C': grep_args.push_back( "-C" ); grep_args.push_back( arg ); break; + case 'e': grep_args.push_back( "-e" ); grep_args.push_back( arg ); + grep_pattern_found = true; break; + case 'E': grep_args.push_back( "-E" ); break; + case 'f': grep_args.push_back( "-f" ); grep_args.push_back( arg ); + grep_pattern_found = true; break; + case 'F': grep_args.push_back( "-F" ); break; + case 'h': grep_show_name = false; break; + case 'H': grep_show_name = true; break; + case 'i': grep_args.push_back( "-i" ); break; + case 'I': grep_args.push_back( "-I" ); break; + case 'l': grep_args.push_back( "-l" ); grep_list = true; break; + case 'L': grep_args.push_back( "-L" ); grep_list = true; break; + case 'm': grep_args.push_back( "-m" ); grep_args.push_back( arg ); break; + case 'n': grep_args.push_back( "-n" ); break; + case 'o': grep_args.push_back( "-o" ); break; + case 'q': grep_args.push_back( "-q" ); verbosity = -1; break; + case 'r': recursive = true; break; + case 's': grep_args.push_back( "-s" ); verbosity = -1; break; + case 'v': grep_args.push_back( "-v" ); break; + case 'V': show_version( "Zgrep" ); return 0; + case 'w': grep_args.push_back( "-w" ); break; + case 'x': grep_args.push_back( "-x" ); break; + case help_opt : show_zgrep_help(); return 0; + case verbose_opt : if( verbosity < 4 ) ++verbosity; break; + case zgrep_opt : break; + default : internal_error( "uncaught option" ); + } break; + case m_ztest: + switch( code ) + { + case 'h': show_ztest_help(); return 0; + case 'q': verbosity = -1; ztest_args.push_back( "-q" ); break; + case 'r': recursive = true; break; + case 'v': if( verbosity < 4 ) ++verbosity; + ztest_args.push_back( "-v" ); break; + case 'V': show_version( "Ztest" ); return 0; + case ztest_opt : break; + default : internal_error( "uncaught option" ); + } break; + } + } // end process options - if( magic_type.size() ) return print_magic_type( magic_type ); + if( program_mode == m_zgrep && !grep_pattern_found ) + { show_error( "Pattern not found.", 0, true ); return 2; } bool filenames_given = false; for( ; argind < parser.arguments(); ++argind ) @@ -725,96 +350,87 @@ int main( const int argc, const char * argv[] ) } if( filenames.empty() ) filenames.push_back("-"); - if( filenames_given ) set_signals(); - Pretty_print pp( filenames ); - if( program_mode == m_test ) - outhandle = -1; - - int retval = 0; - for( unsigned int i = 0; i < filenames.size(); ++i ) + int retval = ( ( program_mode == m_zgrep ) ? 1 : 0 ); + while( !filenames.empty() ) { - struct stat in_stats; - output_filename.clear(); - - if( !filenames[i].size() || filenames[i] == "-" ) + input_filename = filenames.front(); + filenames.pop_front(); + if( !input_filename.size() || input_filename == "-" ) { input_filename.clear(); - inhandle = STDIN_FILENO; - if( program_mode != m_test ) - { - if( to_stdout || !default_output_filename.size() ) - outhandle = STDOUT_FILENO; - else - { - if( program_mode == m_compress ) - set_c_outname( default_output_filename ); - else output_filename = default_output_filename; - if( !open_outstream( force ) ) - { - if( outhandle == -1 && retval < 1 ) retval = 1; - close( inhandle ); inhandle = -1; - continue; - } - } - } + infd = STDIN_FILENO; } else { - input_filename = filenames[i]; - const int eindex = extension_index( input_filename ); - inhandle = open_instream( input_filename, &in_stats, program_mode, - eindex, force, to_stdout ); - if( inhandle < 0 ) { if( retval < 1 ) retval = 1; continue; } - if( program_mode != m_test ) + if( recursive ) { - if( to_stdout ) outhandle = STDOUT_FILENO; - else + struct stat st; + if( !stat( input_filename.c_str(), &st ) && S_ISDIR( st.st_mode ) ) { - if( program_mode == m_compress ) - set_c_outname( input_filename ); - else set_d_outname( input_filename, eindex ); - if( !open_outstream( force ) ) + DIR * const dirp = opendir( input_filename.c_str() ); + if( !dirp ) { - if( outhandle == -1 && retval < 1 ) retval = 1; - close( inhandle ); inhandle = -1; - continue; + if( verbosity >= 0 ) + std::fprintf( stderr, "%s: Can't open directory `%s': %s.\n", + util_name, input_filename.c_str(), std::strerror( errno ) ); + if( retval < 1 ) retval = 1; continue; } + std::list< std::string > tmp_list; + while( true ) + { + const struct dirent * const entryp = readdir( dirp ); + if( !entryp ) { closedir( dirp ); break; } + std::string tmp_name( entryp->d_name ); + if( tmp_name != "." && tmp_name != ".." ) + tmp_list.push_back( input_filename + "/" + tmp_name ); + } + filenames.splice( filenames.begin(), tmp_list ); + continue; } } + infd = open_instream( input_filename, program_mode ); + if( infd < 0 ) { if( retval < 1 ) retval = 1; continue; } } - if( !check_tty( inhandle, program_mode ) ) return 1; - - if( output_filename.size() && !to_stdout && program_mode != m_test ) - delete_output_on_interrupt = true; -// const struct stat * in_statsp = input_filename.size() ? &in_stats : 0; - pp.set_name( input_filename ); int tmp = 0; switch( program_mode ) { - case m_compress: - /*tmp = compress( inhandle, pp, in_statsp, &retval );*/ break; - case m_decompress: - /*tmp = decompress( inhandle, pp );*/ break; - case m_test: - if( inhandle == STDIN_FILENO ) - tmp = test_stdin_type( inhandle, pp ); - else tmp = test_type( inhandle, pp ); + case m_none: + break; + case m_zcat: + tmp = cat( infd, input_filename, cat_options ); + break; + case m_zgrep: + if( infd == STDIN_FILENO ) + tmp = zgrep_stdin( infd, grep_args ); + else tmp = zgrep_file( infd, input_filename, grep_args, + grep_list, grep_show_name ); + break; + case m_ztest: + if( infd == STDIN_FILENO ) + tmp = ztest_stdin( infd, ztest_args ); + else tmp = ztest_file( infd, input_filename, ztest_args ); break; } - if( tmp > retval ) retval = tmp; - if( tmp && program_mode != m_test ) cleanup_and_fail( retval ); + if( program_mode == m_zgrep ) + { if( tmp == 0 || ( tmp == 2 && retval == 1 ) ) retval = tmp; } + else if( tmp > retval ) retval = tmp; -// if( delete_output_on_interrupt ) -// close_and_set_permissions( in_statsp, &retval ); if( input_filename.size() ) + { close( infd ); infd = -1; } + } + + if( std::fclose( stdout ) != 0 ) + { + show_error( "Can't close stdout", errno ); + switch( program_mode ) { - close( inhandle ); inhandle = -1; - if( !keep_input_files && !to_stdout && program_mode != m_test ) - std::remove( input_filename.c_str() ); + case m_none: break; + case m_zcat: retval = 1; break; + case m_zgrep: if( retval != 0 || verbosity >= 0 ) retval = 2; break; + case m_ztest: if( retval == 0 ) retval = 1; break; } } - if( outhandle >= 0 ) close( outhandle ); return retval; } |