rgrep 5.97 KB
Newer Older
1 2
#!/vobs/wds/swt/bin/perl

3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
# Copyright (C) 2004 MySQL AB
# 
# 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; version 2 of the License.
# 
# 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, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209
die "Usage: rgrep [-iredblLn] regexp filepat ...\n       rgrep -h for help\n"
    if $#ARGV < $[;

# Written by Piet van Oostrum <piet@cs.ruu.nl>
# This is really free software

# Mats Lidell added support for gzip.
# Mats Lidell added support for skipping line numbers.

$nextopt = 1;
$igncase = '';
$regpat = 0;
$links = 0;
$error = 0;
$skipbin = 1;
$havenl = 1;
$debug = 0;

do { $regexp = shift (@ARGV); } while &checkopt ($regexp);
$icreg = $igncase;
$igncase = '';

eval 'sub grep_file {
	    while (<F>) {
		$ln++;
		if (/$regexp/o' . $icreg .') {
			print "$file:$ln:" if $havenl;
			print "$_";
			print "\n" if substr($_, -1, 1) ne "\n";
		}
	    }
}';

for (@ARGV) {
    if (! &checkopt ($_)) {
        if ($igncase || $regpat || /[?*[]/ || ! -e) {
	    if ($regpat) {
		s/#/\\#/g;
		$_ = "#$_#";
	    } else { # translate File pattern into regexp
                $re = '#($|/)'; $save = $_;
	        while (/[[*?+()|.^$#]/) {
		    $re .= $`;
		    $c = $&;
		    $_ = $';
		    if ($c eq '*') { $c = '[^/]*'; }
		    elsif ($c eq '?') { $c = '[^/]'; }
		    elsif ($c eq '[') {
		    	if (/.\]/) { $c = "[$`$&"; $_ = $'; }
			else {
			    $error++;
			    printf stderr "Illegal filepattern %s\n", $save;
			}
		    } else { $c = "\\$c"; }
		    $re .= $c;
		}
		$_ = "$re$_\$#$igncase";
	    }
	    print "filepat: $_\n" if $debug;
            push (@filepat, $_);
	}
        else { push (@files, $_); print "file: $_\n" if $debug; }
    }
}

exit 1 if $errors ;

if ($#filepat < $[) {
    eval "sub in_pat {1;}" ;
}
else {
    $subtxt = 'sub in_pat { local ($f) = @_;';
    $or = "";
    for (@filepat) {
	$subtxt .= $or . '$f =~ m' . $_;
	$or = " || ";
    }
    $subtxt .= ';};1';

    if (! eval $subtxt) {
    	print $@;
    	exit 1;
    }
} 

@files = (".") if $#files < $[;

for $file (@files) {
    &do_grep ($file);
}

sub do_grep {
    local ($file) = @_;
    local (*F, $ln, $f, $g, @dirfiles);
    if (-f $file) {
	if (open (F, $file)) {
	    if (-B F) { # binary file --  may be compressed/compacted/gziped
		if (($cx1 = getc(F)) eq "\377" && (getc(F) eq "\037")) {
		    open (F, "uncompact < $file|");
		    if ($skipbin && -B F) { close (F); return; }
		}
		elsif ($cx1 eq "\037" && (($cx2 = getc(F)) eq "\235")) {
		    open (F, "uncompress < $file|");
		    if ($skipbin && -B F) { close (F); return; }
		}
		elsif ($cx1 eq "\037" && $cx2 eq "\213") {
		    open (F, "gzip -d < $file|");
		    if ($skipbin && -B F) { close (F); return; }
		}
		elsif ($skipbin) {
		    close (F); return;
		}
	    }
	    print "Reading $file\n" if $debug;
	    &grep_file;
	} else {
	    print stderr "Cannot open $file\n";
	}
    }
    elsif (-d $file) {
	print "Entering $file\n" if $debug;
	if (opendir (F, $file)) {
	    @dirfiles = readdir (F);
	    closedir (F);
	    for $f (@dirfiles) {
		next if ($f eq '.' || $f eq '..');
		$g = "$file/$f";
		next if (-l $g && ($links < 1 || $links == 1 && -d $g));
		if (-f $g && &in_pat ($g) || -d _) {
		    &do_grep ($g);
		}
	    }
	} else {
	    print stderr "Can't open $file\n";
	}
    }
}

sub checkopt {
    local ($_) = $_[0];
    if (/^-/ && $nextopt) {
        $nextopt = 1;
	@opt = split (/-*/,$_); shift (@opt);
    	for $opt (@opt) {
	    if ($opt eq 'i') { $igncase = 'i'; }
	    elsif ($opt eq 'd') { $debug = 1; }
	    elsif ($opt eq 'l') { $links = 1; }
	    elsif ($opt eq 'L') { $links = 2; }
	    elsif ($opt eq 'b') { $skipbin = 0; }
	    elsif ($opt eq 'r') { $regpat = 1; }
	    elsif ($opt eq 'e') { $nextopt = 0; }
	    elsif ($opt eq 'n') { $havenl = 0; }
	    elsif ($opt eq 'h' || $opt eq 'H') { & help; }
	    else { $error++; printf stderr "Unknown option -%s\n", $opt; }
	}
    	return 1;
    }
    $nextopt = 1;
    return 0;
}

sub help {
    print <<'HELP'; exit 0;
Usage: rgrep [-iredblL] regexp filepat ...
  regexp = perl regular expression to search
  filepat ... = a list of files and directories to be searched or
      file patterns to match filenames.
      filepat will be interpreted as file or directory name if it exists
      as such, and does not contain the metacharacters [ ] ? or *. After
      the options -i and -r all filepats will be considered patterns.
      rgrep will search all files in any of the directories given (and its
      subdirectories) that match any of the filepats, except binary files.
      Compressed files will be searched in uncompressed form.
      Note: filepats may contain / contrary to find usage.
  -b  Don't skip binary files.
  -i  Ignore case, either in the regexp or in filename matching (depending
      on the location). Before the regexp only applies to the regexp,
      otherwise to the filepats following it.
  -r  The following filepats are treated as real perl regexps rather than
      shell style filename patterns. In this case / is not a special
      character, i.e. it is matched by . and matching is not anchored (you
      must supply ^ and $ yourself). E.g. a.b matches the file /xa/by/zz.
  -l  Do follow symbolic links only for files (default is do not follow).
  -L  Do follow symbolic links for files and directories.
  -e  Do not interpret following argument as option. Useful if regexp or
      filepat starts with a -.
  -d  Debugging: Give a lot of output on what happens.
  -n  Don't precede each line by its relative line number in the file.
  -h  print this message and exit.
Piet van Oostrum <piet@cs.ruu.nl>
HELP
}