use 5.006;
use strict;
use warnings;
-our $VERSION = '1.02';
+use warnings::register;
+our $VERSION = '1.09';
require Exporter;
require Cwd;
-=head1 NAME
+#
+# Modified to ensure sub-directory traversal order is not inverded by stack
+# push and pops. That is remains in the same order as in the directory file,
+# or user pre-processing (EG:sorted).
+#
-find - traverse a file tree
+=head1 NAME
-finddepth - traverse a directory structure depth-first
+File::Find - Traverse a directory tree.
=head1 SYNOPSIS
use File::Find;
- find(\&wanted, '/foo', '/bar');
+ find(\&wanted, @directories_to_search);
sub wanted { ... }
use File::Find;
- finddepth(\&wanted, '/foo', '/bar');
+ finddepth(\&wanted, @directories_to_search);
sub wanted { ... }
use File::Find;
=head1 DESCRIPTION
-The first argument to find() is either a hash reference describing the
-operations to be performed for each file, or a code reference.
+These are functions for searching through directory trees doing work
+on each file found similar to the Unix I<find> command. File::Find
+exports two functions, C<find> and C<finddepth>. They work similarly
+but have subtle differences.
+
+=over 4
+
+=item B<find>
+
+ find(\&wanted, @directories);
+ find(\%options, @directories);
+
+C<find()> does a depth-first search over the given C<@directories> in
+the order they are given. For each file or directory found, it calls
+the C<&wanted> subroutine. (See below for details on how to use the
+C<&wanted> function). Additionally, for each directory found, it will
+C<chdir()> into that directory and continue the search, invoking the
+C<&wanted> function on each file or subdirectory in the directory.
+
+=item B<finddepth>
+
+ finddepth(\&wanted, @directories);
+ finddepth(\%options, @directories);
+
+C<finddepth()> works just like C<find()> except that is invokes the
+C<&wanted> function for a directory I<after> invoking it for the
+directory's contents. It does a postorder traversal instead of a
+preorder traversal, working from the bottom of the directory tree up
+where C<find()> works from the top of the tree down.
+
+=back
+
+=head2 %options
+
+The first argument to C<find()> is either a code reference to your
+C<&wanted> function, or a hash reference describing the operations
+to be performed for each file. The
+code reference is described in L<The wanted function> below.
Here are the possible keys for the hash:
=item C<wanted>
-The value should be a code reference. This code reference is called
-I<the wanted() function> below.
+The value should be a code reference. This code reference is
+described in L<The wanted function> below.
=item C<bydepth>
Reports the name of a directory only AFTER all its entries
-have been reported. Entry point finddepth() is a shortcut for
-specifying C<{ bydepth => 1 }> in the first argument of find().
+have been reported. Entry point C<finddepth()> is a shortcut for
+specifying C<<{ bydepth => 1 }>> in the first argument of C<find()>.
=item C<preprocess>
The value should be a code reference. This code reference is used to
-preprocess the current directory. The name of currently processed
-directory is in $File::Find::dir. Your preprocessing function is
-called after readdir() but before the loop that calls the wanted()
+preprocess the current directory. The name of the currently processed
+directory is in C<$File::Find::dir>. Your preprocessing function is
+called after C<readdir()>, but before the loop that calls the C<wanted()>
function. It is called with a list of strings (actually file/directory
names) and is expected to return a list of strings. The code can be
used to sort the file/directory names alphabetically, numerically,
The value should be a code reference. It is invoked just before leaving
the currently processed directory. It is called in void context with no
-arguments. The name of the current directory is in $File::Find::dir. This
+arguments. The name of the current directory is in C<$File::Find::dir>. This
hook is handy for summarizing a directory, such as calculating its disk
usage. When I<follow> or I<follow_fast> are in effect, C<postprocess> is a
no-op.
=item *
It is guaranteed that an I<lstat> has been called before the user's
-I<wanted()> function is called. This enables fast file checks involving S< _>.
+C<wanted()> function is called. This enables fast file checks involving S< _>.
=item *
There is a variable C<$File::Find::fullname> which holds the absolute
-pathname of the file with all symbolic links resolved
+pathname of the file with all symbolic links resolved. If the link is
+a dangling symbolic link, then fullname will be set to C<undef>.
=back
This is similar to I<follow> except that it may report some files more
than once. It does detect cycles, however. Since only symbolic links
have to be hashed, this is much cheaper both in space and time. If
-processing a file more than once (by the user's I<wanted()> function)
+processing a file more than once (by the user's C<wanted()> function)
is worse than just taking time, the option I<follow> should be used.
=item C<follow_skip>
neither directories nor symbolic links to be ignored if they are about
to be processed a second time. If a directory or a symbolic link
are about to be processed a second time, File::Find dies.
+
C<follow_skip==0> causes File::Find to die if any file is about to be
processed a second time.
+
C<follow_skip==2> causes File::Find to ignore any duplicate files and
directories but to proceed normally otherwise.
=item C<no_chdir>
-Does not C<chdir()> to each directory as it recurses. The wanted()
+Does not C<chdir()> to each directory as it recurses. The C<wanted()>
function will need to be aware of this, of course. In this case,
C<$_> will be the same as C<$File::Find::name>.
=back
-The wanted() function does whatever verifications you want.
-C<$File::Find::dir> contains the current directory name, and C<$_> the
-current filename within that directory. C<$File::Find::name> contains
-the complete pathname to the file. You are chdir()'d to
-C<$File::Find::dir> when the function is called, unless C<no_chdir>
-was specified. When C<follow> or C<follow_fast> are in effect, there is
+=head2 The wanted function
+
+The C<wanted()> function does whatever verifications you want on
+each file and directory. Note that despite its name, the C<wanted()>
+function is a generic callback function, and does B<not> tell
+File::Find if a file is "wanted" or not. In fact, its return value
+is ignored.
+
+The wanted function takes no arguments but rather does its work
+through a collection of variables.
+
+=over 4
+
+=item C<$File::Find::dir> is the current directory name,
+
+=item C<$_> is the current filename within that directory
+
+=item C<$File::Find::name> is the complete pathname to the file.
+
+=back
+
+Don't modify these variables.
+
+For example, when examining the file F</some/path/foo.ext> you will have:
+
+ $File::Find::dir = /some/path/
+ $_ = foo.ext
+ $File::Find::name = /some/path/foo.ext
+
+You are chdir()'d toC<$File::Find::dir> when the function is called,
+unless C<no_chdir> was specified. Note that when changing to
+directories is in effect the root directory (F</>) is a somewhat
+special case inasmuch as the concatenation of C<$File::Find::dir>,
+C<'/'> and C<$_> is not literally equal to C<$File::Find::name>. The
+table below summarizes all variants:
+
+ $File::Find::name $File::Find::dir $_
+ default / / .
+ no_chdir=>0 /etc / etc
+ /etc/x /etc x
+
+ no_chdir=>1 / / /
+ /etc / /etc
+ /etc/x /etc /etc/x
+
+
+When <follow> or <follow_fast> are in effect, there is
also a C<$File::Find::fullname>. The function may set
C<$File::Find::prune> to prune the tree unless C<bydepth> was
specified. Unless C<follow> or C<follow_fast> is specified, for
Notice the C<_> in the above C<int(-M _)>: the C<_> is a magical
filehandle that caches the information from the preceding
-stat(), lstat(), or filetest.
-
-Set the variable C<$File::Find::dont_use_nlink> if you're using AFS,
-since AFS cheats.
+C<stat()>, C<lstat()>, or filetest.
Here's another interesting wanted function. It will find all symbolic
links that don't resolve:
See also the script C<pfind> on CPAN for a nice application of this
module.
+=head1 WARNINGS
+
+If you run your program with the C<-w> switch, or if you use the
+C<warnings> pragma, File::Find will report warnings for several weird
+situations. You can disable these warnings by putting the statement
+
+ no warnings 'File::Find';
+
+in the appropriate scope. See L<perllexwarn> for more info about lexical
+warnings.
+
=head1 CAVEAT
+=over 2
+
+=item $dont_use_nlink
+
+You can set the variable C<$File::Find::dont_use_nlink> to 1, if you want to
+force File::Find to always stat directories. This was used for file systems
+that do not have an C<nlink> count matching the number of sub-directories.
+Examples are ISO-9660 (CD-ROM), AFS, HPFS (OS/2 file system), FAT (DOS file
+system) and a couple of others.
+
+You shouldn't need to set this variable, since File::Find should now detect
+such file systems on-the-fly and switch itself to using stat. This works even
+for parts of your file system, like a mounted CD-ROM.
+
+If you do set C<$File::Find::dont_use_nlink> to 1, you will notice slow-downs.
+
+=item symlinks
+
Be aware that the option to follow symbolic links can be dangerous.
Depending on the structure of the directory tree (including symbolic
links to directories) you might traverse a given (physical) directory
might cause very unpleasant surprises, since you delete or change files
in an unknown directory.
+=back
+
=head1 NOTES
=over 4
=back
+=head1 BUGS AND CAVEATS
+
+Despite the name of the C<finddepth()> function, both C<find()> and
+C<finddepth()> perform a depth-first search of the directory
+hierarchy.
+
=head1 HISTORY
File::Find used to produce incorrect results if called recursively.
return undef unless defined $DEV; # dangling symbolic link
}
- if ($full_check && $SLnkSeen{$DEV, $INO}++) {
+ if ($full_check && defined $DEV && $SLnkSeen{$DEV, $INO}++) {
if ( ($follow_skip < 1) || ((-d _) && ($follow_skip < 2)) ) {
die "$AbsName encountered a second time";
}
$follow_skip, $full_check, $untaint, $untaint_skip, $untaint_pat,
$pre_process, $post_process, $dangling_symlinks);
local($dir, $name, $fullname, $prune);
+ local *_ = \my $a;
my $cwd = $wanted->{bydepth} ? Cwd::fastcwd() : Cwd::getcwd();
my $cwd_untainted = $cwd;
else {
$abs_dir = contract_name_Mac($cwd, $top_item);
unless (defined $abs_dir) {
- warn "Can't determine absolute path for $top_item (No such file or directory)\n" if $^W;
+ warnings::warnif "Can't determine absolute path for $top_item (No such file or directory)\n";
next Proc_Top_Item;
}
}
if (ref $dangling_symlinks eq 'CODE') {
$dangling_symlinks->($top_item, $cwd);
} else {
- warn "$top_item is a dangling symbolic link\n" if $^W;
+ warnings::warnif "$top_item is a dangling symbolic link\n";
}
}
next Proc_Top_Item;
else { # no follow
$topdir = $top_item;
unless (defined $topnlink) {
- warn "Can't stat $top_item: $!\n" if $^W;
+ warnings::warnif "Can't stat $top_item: $!\n";
next Proc_Top_Item;
}
if (-d _) {
- $top_item =~ s/\.dir\z// if $Is_VMS;
+ $top_item =~ s/\.dir\z//i if $Is_VMS;
_find_dir($wanted, $top_item, $topnlink);
$Is_Dir= 1;
}
}
unless ($no_chdir || chdir $abs_dir) {
- warn "Couldn't chdir $abs_dir: $!\n" if $^W;
+ warnings::warnif "Couldn't chdir $abs_dir: $!\n";
next Proc_Top_Item;
}
$name = $abs_dir . $_; # $File::Find::name
+ $_ = $name if $no_chdir;
- { &$wanted_callback }; # protect against wild "next"
+ { $wanted_callback->() }; # protect against wild "next"
}
my $dir_pref;
my $dir_rel = $File::Find::current_dir;
my $tainted = 0;
+ my $no_nlink;
if ($Is_MacOS) {
$dir_pref= ($p_dir =~ /:$/) ? $p_dir : "$p_dir:"; # preface
}
}
}
- unless (chdir $udir) {
- warn "Can't cd to $udir: $!\n" if $^W;
+ unless (chdir ($Is_VMS && $udir !~ /[\/\[<]+/ ? "./$udir" : $udir)) {
+ warnings::warnif "Can't cd to $udir: $!\n";
return;
}
}
$_= ($no_chdir ? $dir_name : $dir_rel ); # $_
# prune may happen here
$prune= 0;
- { &$wanted_callback }; # protect against wild "next"
+ { $wanted_callback->() }; # protect against wild "next"
next if $prune;
}
}
}
}
- unless (chdir $udir) {
+ unless (chdir ($Is_VMS && $udir !~ /[\/\[<]+/ ? "./$udir" : $udir)) {
if ($Is_MacOS) {
- warn "Can't cd to ($p_dir) $udir: $!\n" if $^W;
+ warnings::warnif "Can't cd to ($p_dir) $udir: $!\n";
}
else {
- warn "Can't cd to (" . ($p_dir ne '/' ? $p_dir : '') . "/) $udir: $!\n" if $^W;
+ warnings::warnif "Can't cd to (" .
+ ($p_dir ne '/' ? $p_dir : '') . "/) $udir: $!\n";
}
next;
}
# Get the list of files in the current directory.
unless (opendir DIR, ($no_chdir ? $dir_name : $File::Find::current_dir)) {
- warn "Can't opendir($dir_name): $!\n" if $^W;
+ warnings::warnif "Can't opendir($dir_name): $!\n";
next;
}
@filenames = readdir DIR;
closedir(DIR);
- @filenames = &$pre_process(@filenames) if $pre_process;
+ @filenames = $pre_process->(@filenames) if $pre_process;
push @Stack,[$CdLvl,$dir_name,"",-2] if $post_process;
- if ($nlink == 2 && !$avoid_nlink) {
+ # default: use whatever was specifid
+ # (if $nlink >= 2, and $avoid_nlink == 0, this will switch back)
+ $no_nlink = $avoid_nlink;
+ # if dir has wrong nlink count, force switch to slower stat method
+ $no_nlink = 1 if ($nlink < 2);
+
+ if ($nlink == 2 && !$no_nlink) {
# This dir has no subdirectories.
for my $FN (@filenames) {
next if $FN =~ $File::Find::skip_pattern;
$name = $dir_pref . $FN; # $File::Find::name
$_ = ($no_chdir ? $name : $FN); # $_
- { &$wanted_callback }; # protect against wild "next"
+ { $wanted_callback->() }; # protect against wild "next"
}
}
# This dir has subdirectories.
$subcount = $nlink - 2;
+ # HACK: insert directories at this position. so as to preserve
+ # the user pre-processed ordering of files.
+ # EG: directory traversal is in user sorted order, not at random.
+ my $stack_top = @Stack;
+
for my $FN (@filenames) {
next if $FN =~ $File::Find::skip_pattern;
- if ($subcount > 0 || $avoid_nlink) {
+ if ($subcount > 0 || $no_nlink) {
# Seen all the subdirs?
# check for directoriness.
# stat is faster for a file in the current directory
if (-d _) {
--$subcount;
- $FN =~ s/\.dir\z// if $Is_VMS;
- push @Stack,[$CdLvl,$dir_name,$FN,$sub_nlink];
+ $FN =~ s/\.dir\z//i if $Is_VMS;
+ # HACK: replace push to preserve dir traversal order
+ #push @Stack,[$CdLvl,$dir_name,$FN,$sub_nlink];
+ splice @Stack, $stack_top, 0,
+ [$CdLvl,$dir_name,$FN,$sub_nlink];
}
else {
$name = $dir_pref . $FN; # $File::Find::name
$_= ($no_chdir ? $name : $FN); # $_
- { &$wanted_callback }; # protect against wild "next"
+ { $wanted_callback->() }; # protect against wild "next"
}
}
else {
$name = $dir_pref . $FN; # $File::Find::name
$_= ($no_chdir ? $name : $FN); # $_
- { &$wanted_callback }; # protect against wild "next"
+ { $wanted_callback->() }; # protect against wild "next"
}
}
}
if ( $nlink == -2 ) {
$name = $dir = $p_dir; # $File::Find::name / dir
$_ = $File::Find::current_dir;
- &$post_process; # End-of-directory processing
+ $post_process->(); # End-of-directory processing
}
elsif ( $nlink < 0 ) { # must be finddepth, report dirname now
$name = $dir_name;
}
else {
if ( substr($name,-2) eq '/.' ) {
- $name =~ s|/\.$||;
+ substr($name, length($name) == 2 ? -1 : -2) = '';
}
$dir = $p_dir;
$_ = ($no_chdir ? $dir_name : $dir_rel );
if ( substr($_,-2) eq '/.' ) {
- s|/\.$||;
+ substr($_, length($_) == 2 ? -1 : -2) = '';
}
}
- { &$wanted_callback }; # protect against wild "next"
+ { $wanted_callback->() }; # protect against wild "next"
}
else {
push @Stack,[$CdLvl,$p_dir,$dir_rel,-1] if $bydepth;
}
$ok = chdir($updir_loc) unless ($p_dir eq $File::Find::current_dir);
unless ($ok) {
- warn "Can't cd to $updir_loc: $!\n" if $^W;
+ warnings::warnif "Can't cd to $updir_loc: $!\n";
return;
}
}
# change (back) to parent directory (always untainted)
unless ($no_chdir) {
unless (chdir $updir_loc) {
- warn "Can't cd to $updir_loc: $!\n" if $^W;
+ warnings::warnif "Can't cd to $updir_loc: $!\n";
next;
}
}
# prune may happen here
$prune= 0;
lstat($_); # make sure file tests with '_' work
- { &$wanted_callback }; # protect against wild "next"
+ { $wanted_callback->() }; # protect against wild "next"
next if $prune;
}
}
}
unless (chdir $updir_loc) {
- warn "Can't cd to $updir_loc: $!\n" if $^W;
+ warnings::warnif "Can't cd to $updir_loc: $!\n";
next;
}
}
# Get the list of files in the current directory.
unless (opendir DIR, ($no_chdir ? $dir_loc : $File::Find::current_dir)) {
- warn "Can't opendir($dir_loc): $!\n" if $^W;
+ warnings::warnif "Can't opendir($dir_loc): $!\n";
next;
}
@filenames = readdir DIR;
$new_loc = Follow_SymLink($loc_pref.$FN);
# ignore if invalid symlink
- next unless defined $new_loc;
+ unless (defined $new_loc) {
+ if ($dangling_symlinks) {
+ if (ref $dangling_symlinks eq 'CODE') {
+ $dangling_symlinks->($FN, $dir_pref);
+ } else {
+ warnings::warnif "$dir_pref$FN is a dangling symbolic link\n";
+ }
+ }
+
+ $fullname = undef;
+ $name = $dir_pref . $FN;
+ $_ = ($no_chdir ? $name : $FN);
+ { $wanted_callback->() };
+ next;
+ }
if (-d _) {
push @Stack,[$new_loc,$updir_loc,$dir_name,$FN,1];
$fullname = $new_loc; # $File::Find::fullname
$name = $dir_pref . $FN; # $File::Find::name
$_ = ($no_chdir ? $name : $FN); # $_
- { &$wanted_callback }; # protect against wild "next"
+ { $wanted_callback->() }; # protect against wild "next"
}
}
if ( $byd_flag < 0 ) { # must be finddepth, report dirname now
unless ($no_chdir || ($dir_rel eq $File::Find::current_dir)) {
unless (chdir $updir_loc) { # $updir_loc (parent dir) is always untainted
- warn "Can't cd to $updir_loc: $!\n" if $^W;
+ warnings::warnif "Can't cd to $updir_loc: $!\n";
next;
}
}
}
else {
if ( substr($name,-2) eq '/.' ) {
- $name =~ s|/\.$||; # $File::Find::name
+ substr($name, length($name) == 2 ? -1 : -2) = ''; # $File::Find::name
}
$dir = $p_dir; # $File::Find::dir
$_ = ($no_chdir ? $dir_name : $dir_rel); # $_
if ( substr($_,-2) eq '/.' ) {
- s|/\.$||;
+ substr($_, length($_) == 2 ? -1 : -2) = '';
}
}
lstat($_); # make sure file tests with '_' work
- { &$wanted_callback }; # protect against wild "next"
+ { $wanted_callback->() }; # protect against wild "next"
}
else {
push @Stack,[$dir_loc, $updir_loc, $p_dir, $dir_rel,-1] if $bydepth;
$File::Find::dont_use_nlink = 1
if $^O eq 'os2' || $^O eq 'dos' || $^O eq 'amigaos' || $^O eq 'MSWin32' ||
- $^O eq 'cygwin' || $^O eq 'epoc' || $^O eq 'NetWare';
+ $^O eq 'interix' || $^O eq 'cygwin' || $^O eq 'epoc' || $^O eq 'qnx' ||
+ $^O eq 'nto';
# 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