package File::Find; require 5.000; require Exporter; use Config; require Cwd; require File::Basename; =head1 NAME find - traverse a file tree finddepth - traverse a directory structure depth-first =head1 SYNOPSIS use File::Find; find(\&wanted, '/foo','/bar'); sub wanted { ... } use File::Find; finddepth(\&wanted, '/foo','/bar'); sub wanted { ... } use File::Find; find3(\&wanted, \&dir_start, \&dir_end, '/foo','/bar'); sub dir_start { sort @_; } sub dir_end { ... } sub wanted { ... } =head1 DESCRIPTION The wanted() function does whatever verifications you want. $File::Find::dir contains the current directory name, and $_ the current filename within that directory. $File::Find::name contains C<"$File::Find::dir/$_">. You are chdir()'d to $File::Find::dir when the function is called. The function may set $File::Find::prune to prune the tree. File::Find assumes that you don't alter the $_ variable. If you do then make sure you return it to its original value before exiting your function. This library is primarily for the C tool, which when fed, find2perl / -name .nfs\* -mtime +7 \ -exec rm -f {} \; -o -fstype nfs -prune produces something like: sub wanted { /^\.nfs.*$/ && (($dev,$ino,$mode,$nlink,$uid,$gid) = lstat($_)) && int(-M _) > 7 && unlink($_) || ($nlink || (($dev,$ino,$mode,$nlink,$uid,$gid) = lstat($_))) && $dev < 0 && ($File::Find::prune = 1); } Set the variable $File::Find::dont_use_nlink if you're using AFS, since AFS cheats. Set the variable $File::Find::topdir_symlink if you want C or C to handle arguments which are symlinks to directories. (To avoid infinite loops, symlinks found inside lower directories are not followed; you'll have to call C from inside &wanted if you want that functionality.) C is just like C, except that it does a depth-first search. Here's another interesting wanted function. It will find all symlinks that don't resolve: sub wanted { -l && !-e && print "bogus link: $File::Find::name\n"; } To limit recursion, increment and test a level counter in the start-of-directory function (and decrement it in the end-of-directory function): sub dir_start { $recursion_depth++ < $maximum_depth ? sort(@_) : (); } sub dir_end { --$recursion_depth; } $maximum_depth = 7; # Descend up to 7 levels of subdirectories $recursion_depth = 0; # Set global counter find3(\&wanted, \&dir_start, \&dir_end, @ARGV); =head1 BUGS There is no way to make find or finddepth follow symlinks except for symlink names passed as arguments to these functions. =cut @ISA = qw(Exporter); @EXPORT = qw(find finddepth find3); sub find { my $wanted = shift; &find3($wanted, undef, undef, @_); } sub find3 { my $wanted = shift; my $start = shift; # Gets called with @files, must return same my $end = shift; # Also gets called with @files at end of dir my $cwd = Cwd::cwd(); # Localize these rather than lexicalizing them for backwards # compatibility. local($topdir,$topdev,$topino,$topmode,$topnlink); foreach $topdir (@_) { (($topdev,$topino,$topmode,$topnlink) = (($Is_VMS or $topdir_symlink) ? stat($topdir) : lstat($topdir))) || (warn("Can't stat $topdir: $!\n"), next); if (-d _) { if (chdir($topdir)) { ($dir,$_) = ($topdir,'.'); $name = $topdir; $prune = 0; &$wanted; if (!$prune) { my $fixtopdir = $topdir; $fixtopdir =~ s,/$,, ; $fixtopdir =~ s/\.dir$// if $Is_VMS; $fixtopdir =~ s/\\dir$// if $Is_NT; &finddir($wanted,$start,$end,$fixtopdir,$topnlink); } } else { warn "Can't cd to $topdir: $!\n"; } } else { unless (($_,$dir) = File::Basename::fileparse($topdir)) { ($dir,$_) = ('.', $topdir); } $name = $topdir; chdir $dir && &$wanted; } chdir $cwd; } } sub finddir { my($wanted, $dir_start, $dir_end, $nlink); local($dir, $name); ($wanted, $dir_start, $dir_end, $dir, $nlink) = @_; my($dev, $ino, $mode, $subcount); # Get the list of files in the current directory. opendir(DIR,'.') || (warn "Can't open $dir: $!\n", return); my(@filenames) = readdir(DIR); closedir(DIR); @filenames = &$dir_start(@filenames) if $dir_start; # Pre-process if ($nlink == 2 && !$dont_use_nlink) { # This dir has no subdirectories. for (@filenames) { next if $_ eq '.'; next if $_ eq '..'; $name = "$dir/$_"; $nlink = 0; &$wanted; } } else { # This dir has subdirectories. $subcount = $nlink - 2; for (@filenames) { next if $_ eq '.'; next if $_ eq '..'; $nlink = $prune = 0; $name = "$dir/$_"; &$wanted; if ($subcount > 0 || $dont_use_nlink) { # Seen all the subdirs? # Get link count and check for directoriness. ($dev,$ino,$mode,$nlink) = ($Is_VMS ? stat($_) : lstat($_)); # unless ($nlink || $dont_use_nlink); if (-d _) { # It really is a directory, so do it recursively. if (!$prune && chdir $_) { $name =~ s/\.dir$// if $Is_VMS; $name =~ s/\\dir$// if $Is_NT; &finddir($wanted,$dir_start,$dir_end,$name,$nlink); chdir '..'; } --$subcount; } } } } &$dir_end(@filenames) if $dir_end; # Post-process this directory } sub finddepth { my $wanted = shift; $cwd = Cwd::fastcwd();; # Localize these rather than lexicalizing them for backwards # compatibility. local($topdir, $topdev, $topino, $topmode, $topnlink); foreach $topdir (@_) { (($topdev,$topino,$topmode,$topnlink) = ($Is_VMS ? stat($topdir) : lstat($topdir))) || (warn("Can't stat $topdir: $!\n"), next); if (-d _) { if (chdir($topdir)) { my $fixtopdir = $topdir; $fixtopdir =~ s,/$,, ; $fixtopdir =~ s/\.dir$// if $Is_VMS; $fixtopdir =~ s/\\dir$// if $Is_NT; &finddepthdir($wanted,$fixtopdir,$topnlink); ($dir,$_) = ($fixtopdir,'.'); $name = $fixtopdir; &$wanted; } else { warn "Can't cd to $topdir: $!\n"; } } else { unless (($_,$dir) = File::Basename::fileparse($topdir)) { ($dir,$_) = ('.', $topdir); } $name = $topdir; chdir $dir && &$wanted; } chdir $cwd; } } sub finddepthdir { my($wanted, $nlink); local($dir, $name); ($wanted,$dir,$nlink) = @_; my($dev, $ino, $mode, $subcount); # Get the list of files in the current directory. opendir(DIR,'.') || warn "Can't open $dir: $!\n"; my(@filenames) = readdir(DIR); closedir(DIR); if ($nlink == 2 && !$dont_use_nlink) { # This dir has no subdirectories. for (@filenames) { next if $_ eq '.'; next if $_ eq '..'; $name = "$dir/$_"; $nlink = 0; &$wanted; } } else { # This dir has subdirectories. $subcount = $nlink - 2; for (@filenames) { next if $_ eq '.'; next if $_ eq '..'; $nlink = 0; $name = "$dir/$_"; if ($subcount > 0 || $dont_use_nlink) { # Seen all the subdirs? # Get link count and check for directoriness. ($dev,$ino,$mode,$nlink) = ($Is_VMS ? stat($_) : lstat($_)); if (-d _) { # It really is a directory, so do it recursively. if (chdir $_) { $name =~ s/\.dir$// if $Is_VMS; $name =~ s/\\dir$// if $Is_NT; &finddepthdir($wanted,$name,$nlink); chdir '..'; } --$subcount; } } &$wanted; } } } # Set dont_use_nlink in your hint file if your system's stat doesn't # report the number of links in a directory as an indication # of the number of files. # See, e.g. hints/machten.sh for MachTen 2.2. $dont_use_nlink = 1 if ($Config::Config{'dont_use_nlink'}); # These are hard-coded for now, but may move to hint files. if ($^O eq 'VMS') { $Is_VMS = 1; $dont_use_nlink = 1; } if ($^O =~ m:^mswin32:i) { $Is_NT = 1; $dont_use_nlink = 1; } $dont_use_nlink = 1 if $^O eq 'os2' || $^O eq 'msdos' || $^O eq 'amigaos'; $topdir_symlink = 0; # Set to 1 to follow top-level symlinks 1;