/* Zcat - decompress and concatenate files to standard output
Copyright (C) 2010-2023 Antonio Diaz Diaz.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see .
*/
#define _FILE_OFFSET_BITS 64
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#include
#if defined __MSVCRT__ || defined __OS2__
#include
#endif
#include "arg_parser.h"
#include "rc.h"
#include "zutils.h"
namespace {
#include "recursive.cc"
#include "zcatgrep.cc"
struct Cat_options
{
int number_lines; // 0 = no, 1 = nonblank, 2 = all
bool show_ends;
bool show_nonprinting;
bool show_tabs;
bool squeeze_blank;
Cat_options()
: number_lines( 0 ), show_ends( false ), show_nonprinting( false ),
show_tabs( false ), squeeze_blank( false ) {}
};
class Line_number // unlimited size line counter
{
std::string str;
unsigned first_digit_pos;
public:
Line_number() : str( " 0\t" ), first_digit_pos( 5 ) {}
void next()
{
for( unsigned i = str.size() - 1; i > first_digit_pos; )
{
if( str[--i] < '9' ) { ++str[i]; return; }
str[i] = '0';
}
if( first_digit_pos > 0 ) str[--first_digit_pos] = '1';
else str.insert( str.begin() + first_digit_pos, '1' );
}
int sprint( uint8_t * const buf )
{
std::memcpy( buf, str.c_str(), str.size() );
return str.size();
}
};
Line_number line_number;
void show_help()
{
std::printf( "zcat copies each file argument to standard output in sequence. If any\n"
"file given is compressed, its decompressed content is copied. If a file\n"
"given does not exist, and its name does not end with one of the known\n"
"extensions, zcat tries the compressed file names corresponding to the\n"
"formats supported. If a file fails to decompress, zcat continues copying the\n"
"rest of the files.\n"
"\nIf a file is specified as '-', data are read from standard input,\n"
"decompressed if needed, and sent to standard output. Data read from\n"
"standard input must be of the same type; all uncompressed or all in the\n"
"same compressed format.\n"
"\nIf no files are specified, recursive searches examine the current\n"
"working directory, and nonrecursive searches read standard input.\n"
"\nThe formats supported are bzip2, gzip, lzip, xz, and zstd.\n"
"\nUsage: zcat [options] [files]\n"
"\nExit status is 0 if no errors occurred, 1 otherwise.\n"
"\nOptions:\n"
" -h, --help display this help and exit\n"
" -V, --version output version information and exit\n"
" -A, --show-all equivalent to '-vET'\n"
" -b, --number-nonblank number nonblank output lines\n"
" -e equivalent to '-vE'\n"
" -E, --show-ends display '$' at end of each line\n"
" -M, --format= process only the formats in \n"
" -n, --number number all output lines\n"
" -N, --no-rcfile don't read runtime configuration file\n"
" -O, --force-format= force the input format\n"
" -q, --quiet suppress all messages\n"
" -r, --recursive operate recursively on directories\n"
" -R, --dereference-recursive recursively follow symbolic links\n"
" -s, --squeeze-blank never more than one single blank line\n"
" -t equivalent to '-vT'\n"
" -T, --show-tabs display TAB characters as '^I'\n"
" -v, --show-nonprinting use '^' and 'M-' notation, except for LF and TAB\n"
" --verbose verbose mode (show error messages)\n"
" --bz2= set compressor and options for bzip2 format\n"
" --gz= set compressor and options for gzip format\n"
" --lz= set compressor and options for lzip format\n"
" --xz= set compressor and options for xz format\n"
" --zst= set compressor and options for zstd format\n"
"\nValid formats for options '-M' and '-O' are 'bz2', 'gz', 'lz', 'xz', 'zst',\n"
"and 'un' for uncompressed.\n" );
show_help_addr();
}
bool do_cat( const int infd, const int buffer_size,
uint8_t * const inbuf, uint8_t * const outbuf,
const std::string & input_filename,
const Cat_options & cat_options )
{
static int at_bol = 1; // at begin of line. 0 = false, 1 = true,
// 2 = at begin of second blank line.
int inpos = 0; // positions in buffers
int outpos = 0;
int rd = -1; // bytes read by the last readblock
unsigned char c;
while( true )
{
do {
if( outpos >= buffer_size )
{
if( writeblock( STDOUT_FILENO, outbuf, outpos ) != outpos )
{ show_error( "Write error", errno ); return false; }
outpos = 0;
}
if( inpos > rd ) // inbuf is empty
{
rd = readblock( infd, inbuf, buffer_size );
if( rd != buffer_size && errno )
{
show_file_error( input_filename.c_str(), "Read error", errno );
return false;
}
if( rd == 0 )
{
if( writeblock( STDOUT_FILENO, outbuf, outpos ) != outpos )
{ show_error( "Write error", errno ); return false; }
outpos = 0;
return true;
}
inpos = 0;
inbuf[rd] = '\n'; // sentinel newline
}
else // a real newline was found
{
if( at_bol > 1 )
{
if( cat_options.squeeze_blank ) { c = inbuf[inpos++]; continue; }
}
else ++at_bol;
if( at_bol > 1 && cat_options.number_lines == 2 )
{
line_number.next();
outpos += line_number.sprint( &outbuf[outpos] );
}
if( cat_options.show_ends ) outbuf[outpos++] = '$';
outbuf[outpos++] = '\n'; // output the newline
}
c = inbuf[inpos++];
}
while( c == '\n' );
if( at_bol > 0 && cat_options.number_lines )
{
line_number.next();
outpos += line_number.sprint( &outbuf[outpos] );
}
at_bol = 0;
// the loops below continue until a newline (real or sentinel) is found
if( cat_options.show_nonprinting )
while( true )
{
if( c < 32 || c >= 127 )
{
if( c == '\n' ) break;
if( c != '\t' || cat_options.show_tabs )
{
if( c >= 128 )
{ c -= 128; outbuf[outpos++] = 'M'; outbuf[outpos++] = '-'; }
if( c < 32 ) { c += 64; outbuf[outpos++] = '^'; }
else if( c == 127 ) { c = '?'; outbuf[outpos++] = '^'; }
}
}
outbuf[outpos++] = c;
c = inbuf[inpos++];
}
else // not quoting
while( c != '\n' )
{
if( c == '\t' && cat_options.show_tabs )
{ c += 64; outbuf[outpos++] = '^'; }
outbuf[outpos++] = c;
c = inbuf[inpos++];
}
}
}
bool cat( int infd, const int format_index, const std::string & input_filename,
const Cat_options & cat_options )
{
enum { buffer_size = 4096, outbuf_size = (5 * buffer_size) + 256 + 1 };
// input buffer with space for sentinel newline at the end
uint8_t * const inbuf = new uint8_t[buffer_size+1];
/* output buffer with space for character quoting, 255-digit line number,
worst case flushing respect to inbuf, and a canary byte. */
uint8_t * const outbuf = new uint8_t[outbuf_size];
outbuf[outbuf_size-1] = 0; // canary byte; quoting does not print 0
Children children;
bool error = false;
if( !set_data_feeder( input_filename, &infd, children, format_index ) ||
!do_cat( infd, buffer_size, inbuf, outbuf, input_filename, cat_options ) )
error = true;
if( !good_status( children, !error ) ) error = true;
if( !error && close( infd ) != 0 ) { show_close_error(); error = true; }
if( outbuf[outbuf_size-1] != 0 ) internal_error( "buffer overflow." );
delete[] outbuf; delete[] inbuf;
return !error;
}
} // end namespace
int main( const int argc, const char * const argv[] )
{
enum { verbose_opt = 256, bz2_opt, gz_opt, lz_opt, xz_opt, zst_opt };
int format_index = -1; // undefined
int recursive = 0; // 1 = '-r', 2 = '-R'
std::list< std::string > filenames;
Cat_options cat_options;
program_name = "zcat";
invocation_name = ( argc > 0 ) ? argv[0] : program_name;
const Arg_parser::Option options[] =
{
{ '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
{ 'M', "format", Arg_parser::yes },
{ 'n', "number", Arg_parser::no }, // cat
{ 'N', "no-rcfile", Arg_parser::no },
{ 'O', "force-format", Arg_parser::yes },
{ 'q', "quiet", Arg_parser::no },
{ 'r', "recursive", Arg_parser::no },
{ 'R', "dereference-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 },
{ bz2_opt, "bz2", Arg_parser::yes },
{ gz_opt, "gz", Arg_parser::yes },
{ lz_opt, "lz", Arg_parser::yes },
{ xz_opt, "xz", Arg_parser::yes },
{ zst_opt, "zst", Arg_parser::yes },
{ 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; }
maybe_process_config_file( parser );
int argind = 0;
for( ; argind < parser.arguments(); ++argind )
{
const int code = parser.code( argind );
if( !code ) break; // no more options
const char * const pn = parser.parsed_name( argind ).c_str();
const std::string & arg = parser.argument( argind );
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_help(); return 0;
case 'l': break;
case 'L': break;
case 'M': parse_format_list( arg, pn ); break;
case 'n': if( cat_options.number_lines == 0 )
{ cat_options.number_lines = 2; } break;
case 'N': break;
case 'O': format_index = parse_format_type( arg, pn ); break;
case 'q': verbosity = -1; break;
case 'r': recursive = 1; break;
case 'R': recursive = 2; 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(); return 0;
case verbose_opt: if( verbosity < 4 ) ++verbosity; break;
case bz2_opt: parse_compressor( arg, pn, fmt_bz2, 1 ); break;
case gz_opt: parse_compressor( arg, pn, fmt_gz, 1 ); break;
case lz_opt: parse_compressor( arg, pn, fmt_lz, 1 ); break;
case xz_opt: parse_compressor( arg, pn, fmt_xz, 1 ); break;
case zst_opt: parse_compressor( arg, pn, fmt_zst, 1 ); break;
default : internal_error( "uncaught option." );
}
} // end process options
#if defined __MSVCRT__ || defined __OS2__
setmode( STDIN_FILENO, O_BINARY );
setmode( STDOUT_FILENO, O_BINARY );
#endif
for( ; argind < parser.arguments(); ++argind )
filenames.push_back( parser.argument( argind ) );
if( filenames.empty() ) filenames.push_back( recursive ? "." : "-" );
std::string input_filename;
bool error = false;
bool stdin_used = false;
while( next_filename( filenames, input_filename, error, recursive ) )
{
int infd;
if( input_filename == "." )
{
if( stdin_used ) continue; else stdin_used = true;
infd = STDIN_FILENO; input_filename = "-";
}
else
{
infd = open_instream( input_filename, format_index < 0 );
if( infd < 0 ) { error = true; continue; }
}
if( !cat( infd, format_index, input_filename, cat_options ) ) error = true;
if( close( infd ) != 0 )
{ show_file_error( input_filename.c_str(), "Error closing input file",
errno ); error = true; }
}
if( std::fclose( stdout ) != 0 )
{
show_error( "Error closing stdout", errno );
error = true;
}
return error;
}