1
0
Fork 0

Merging upstream version 1.8.

Signed-off-by: Daniel Baumann <daniel@debian.org>
This commit is contained in:
Daniel Baumann 2025-02-24 05:58:06 +01:00
parent 482a36ad54
commit 0b238fdfef
Signed by: daniel
GPG key ID: FBB4F0E80A80222F
34 changed files with 858 additions and 455 deletions

184
zgrep.cc
View file

@ -1,5 +1,5 @@
/* Zgrep - search compressed files for a regular expression
Copyright (C) 2010-2018 Antonio Diaz Diaz.
Copyright (C) 2010-2019 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
@ -52,51 +52,54 @@ void show_help()
"file is compressed, its decompressed content is used. If a given file\n"
"does not exist, and its name does not end with one of the known\n"
"extensions, zgrep tries the compressed file names corresponding to the\n"
"supported formats.\n"
"\nIf no files are specified, or if a file is specified as '-', data are\n"
"read from standard input, decompressed if needed, and fed to grep. Data\n"
"read from standard input must be of the same type; all uncompressed or\n"
"all in the same compression format.\n"
"\nThe supported formats are bzip2, gzip, lzip and xz.\n"
"formats supported.\n"
"\nIf a file is specified as '-', data are read from standard input,\n"
"decompressed if needed, and fed to grep. Data read from standard input\n"
"must be of the same type; all uncompressed or all in the same\n"
"compression 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 and xz.\n"
"\nUsage: zgrep [options] <pattern> [files]\n"
"\nExit status is 0 if match, 1 if no match, 2 if trouble.\n"
"\nOptions:\n"
" --help display this help and exit\n"
" -V, --version output version information and exit\n"
" -a, --text treat all files as text\n"
" -A, --after-context=<n> print <n> lines of trailing context\n"
" -b, --byte-offset print the byte offset of each line\n"
" -B, --before-context=<n> print <n> lines of leading context\n"
" -c, --count only print a count of matching lines per file\n"
" -C, --context=<n> print <n> lines of output context\n"
" --color[=<when>] show matched strings in color\n"
" -e, --regexp=<pattern> use <pattern> as the pattern to match\n"
" -E, --extended-regexp <pattern> is an extended regular expression\n"
" -f, --file=<file> obtain patterns from <file>\n"
" -F, --fixed-strings <pattern> is a set of newline-separated strings\n"
" -h, --no-filename suppress the prefixing filename on output\n"
" -H, --with-filename print the filename for each match\n"
" -i, --ignore-case ignore case distinctions\n"
" -I ignore binary files\n"
" -l, --files-with-matches only print names of files containing matches\n"
" -L, --files-without-match only print names of files containing no matches\n"
" -m, --max-count=<n> stop after <n> matches\n"
" -M, --format=<list> process only the formats in <list>\n"
" -n, --line-number print the line number of each line\n"
" -N, --no-rcfile don't read runtime configuration file\n"
" -o, --only-matching show only the part of a line matching <pattern>\n"
" -O, --force-format=<fmt> force given format (bz2, gz, lz, xz)\n"
" -q, --quiet suppress all messages\n"
" -r, --recursive operate recursively on directories\n"
" -s, --no-messages suppress error messages\n"
" -v, --invert-match select non-matching lines\n"
" --verbose verbose mode (show error messages)\n"
" -w, --word-regexp match only whole words\n"
" -x, --line-regexp match only whole lines\n"
" --bz2=<command> set compressor and options for bzip2 format\n"
" --gz=<command> set compressor and options for gzip format\n"
" --lz=<command> set compressor and options for lzip format\n"
" --xz=<command> set compressor and options for xz format\n"
" --help display this help and exit\n"
" -V, --version output version information and exit\n"
" -a, --text treat all files as text\n"
" -A, --after-context=<n> print <n> lines of trailing context\n"
" -b, --byte-offset print the byte offset of each line\n"
" -B, --before-context=<n> print <n> lines of leading context\n"
" -c, --count only print a count of matching lines per file\n"
" -C, --context=<n> print <n> lines of output context\n"
" --color[=<when>] show matched strings in color\n"
" -e, --regexp=<pattern> use <pattern> as the pattern to match\n"
" -E, --extended-regexp <pattern> is an extended regular expression\n"
" -f, --file=<file> obtain patterns from <file>\n"
" -F, --fixed-strings <pattern> is a set of newline-separated strings\n"
" -h, --no-filename suppress the prefixing filename on output\n"
" -H, --with-filename print the filename for each match\n"
" -i, --ignore-case ignore case distinctions\n"
" -I ignore binary files\n"
" -l, --files-with-matches only print names of files containing matches\n"
" -L, --files-without-match only print names of files containing no matches\n"
" -m, --max-count=<n> stop after <n> matches\n"
" -M, --format=<list> process only the formats in <list>\n"
" -n, --line-number print the line number of each line\n"
" -N, --no-rcfile don't read runtime configuration file\n"
" -o, --only-matching show only the part of a line matching <pattern>\n"
" -O, --force-format=<fmt> force given format (bz2, gz, lz, xz)\n"
" -q, --quiet suppress all messages\n"
" -r, --recursive operate recursively on directories\n"
" -R, --dereference-recursive recursively follow symbolic links\n"
" -s, --no-messages suppress error messages\n"
" -v, --invert-match select non-matching lines\n"
" --verbose verbose mode (show error messages)\n"
" -w, --word-regexp match only whole words\n"
" -x, --line-regexp match only whole lines\n"
" --bz2=<command> set compressor and options for bzip2 format\n"
" --gz=<command> set compressor and options for gzip format\n"
" --lz=<command> set compressor and options for lzip format\n"
" --xz=<command> set compressor and options for xz format\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" );
show_help_addr();
@ -187,7 +190,8 @@ int zgrep_file( int infd, const int format_index,
putchar( buffer[i] );
}
else if( std::fwrite( buffer, 1, size, stdout ) != (unsigned)size )
{ show_error( "Write error", errno ); return 2; }
{ std::fflush( stdout ); show_error( "Write error", errno ); return 2; }
std::fflush( stdout );
}
if( size < buffer_size ) break;
}
@ -197,7 +201,7 @@ int zgrep_file( int infd, const int format_index,
if( !good_status( children, retval == 1 ) ) retval = 2;
if( list_mode && (retval == 0) == (list_mode == 1) )
std::printf( "%s\n", input_filename.c_str() );
{ std::printf( "%s\n", input_filename.c_str() ); std::fflush( stdout ); }
if( close( infd ) != 0 )
{ show_close_error(); return 2; }
if( close( fda[0] ) != 0 )
@ -213,12 +217,10 @@ int main( const int argc, const char * const argv[] )
enum { help_opt = 256, verbose_opt, color_opt,
bz2_opt, gz_opt, lz_opt, xz_opt };
int format_index = -1;
int infd = -1;
int list_mode = 0; // 1 = list matches, -1 = list non matches
int recursive = 0; // 1 = '-r', 2 = '-R'
int show_name = -1; // tri-state bool
bool no_messages = false;
bool recursive = false;
std::string input_filename;
std::list< std::string > filenames;
std::vector< const char * > grep_args; // args to grep, maybe empty
std::string color_option; // needed because of optional arg
@ -227,43 +229,44 @@ int main( const int argc, const char * const argv[] )
const Arg_parser::Option options[] =
{
{ '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
{ 'M', "format", Arg_parser::yes },
{ 'n', "line-number", Arg_parser::no }, // grep
{ 'N', "no-rcfile", Arg_parser::no },
{ 'o', "only-matching", Arg_parser::no }, // grep
{ 'O', "force-format", Arg_parser::yes },
{ '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 },
{ color_opt, "color", Arg_parser::maybe },
{ bz2_opt, "bz2", Arg_parser::yes },
{ gz_opt, "gz", Arg_parser::yes },
{ lz_opt, "lz", Arg_parser::yes },
{ xz_opt, "xz", Arg_parser::yes },
{ 0 , 0, Arg_parser::no } };
{ '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
{ 'M', "format", Arg_parser::yes },
{ 'n', "line-number", Arg_parser::no }, // grep
{ 'N', "no-rcfile", Arg_parser::no },
{ 'o', "only-matching", Arg_parser::no }, // grep
{ 'O', "force-format", Arg_parser::yes },
{ 'q', "quiet", Arg_parser::no },
{ 'r', "recursive", Arg_parser::no },
{ 'R', "dereference-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 },
{ color_opt, "color", Arg_parser::maybe },
{ bz2_opt, "bz2", Arg_parser::yes },
{ gz_opt, "gz", Arg_parser::yes },
{ lz_opt, "lz", Arg_parser::yes },
{ xz_opt, "xz", Arg_parser::yes },
{ 0 , 0, Arg_parser::no } };
const Arg_parser parser( argc, argv, options );
if( parser.error().size() ) // bad option
@ -309,7 +312,8 @@ int main( const int argc, const char * const argv[] )
case 'o': grep_args.push_back( "-o" ); break;
case 'O': format_index = parse_format_type( arg ); break;
case 'q': grep_args.push_back( "-q" ); verbosity = -1; break;
case 'r': recursive = true; break;
case 'r': recursive = 1; break;
case 'R': recursive = 2; break;
case 's': grep_args.push_back( "-s" ); no_messages = true; break;
case 'v': grep_args.push_back( "-v" ); break;
case 'V': show_version(); return 0;
@ -349,16 +353,18 @@ int main( const int argc, const char * const argv[] )
for( ; argind < parser.arguments(); ++argind )
filenames.push_back( parser.argument( argind ) );
if( filenames.empty() ) filenames.push_back( "-" );
if( filenames.empty() ) filenames.push_back( recursive ? "." : "-" );
if( show_name < 0 ) show_name = ( filenames.size() != 1 || recursive );
std::string input_filename;
int retval = 1;
bool error = false;
bool stdin_used = false;
while( next_filename( filenames, input_filename, error, recursive,
false, no_messages ) )
{
int infd;
if( input_filename.empty() )
{
if( stdin_used ) continue; else stdin_used = true;
@ -377,13 +383,13 @@ int main( const int argc, const char * const argv[] )
list_mode, show_name );
if( tmp == 0 || ( tmp == 2 && retval == 1 ) ) retval = tmp;
if( input_filename.size() ) { close( infd ); infd = -1; }
if( input_filename.size() ) close( infd );
if( retval == 0 && verbosity < 0 ) break;
}
if( std::fclose( stdout ) != 0 )
{
show_error( "Can't close stdout", errno );
show_error( "Error closing stdout", errno );
error = true;
}
if( error && ( retval != 0 || verbosity >= 0 ) ) retval = 2;