summaryrefslogtreecommitdiff
path: root/lib/File/Basename.pm
blob: 4b4fe95cfd7cffb8e4b9e2dcab13d665ec9f36d6 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
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
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
=head1 NAME

File::Basename - Parse file paths into directory, filename and suffix.

=head1 SYNOPSIS

    use File::Basename;

    ($name,$path,$suffix) = fileparse($fullname,@suffixlist);
    $name = fileparse($fullname,@suffixlist);

    $basename = basename($fullname,@suffixlist);
    $dirname  = dirname($fullname);


=head1 DESCRIPTION

These routines allow you to parse file paths into their directory, filename
and suffix.

B<NOTE>: C<dirname()> and C<basename()> emulate the behaviours, and
quirks, of the shell and C functions of the same name.  See each
function's documentation for details.  If your concern is just parsing
paths it is safer to use L<File::Spec>'s C<splitpath()> and
C<splitdir()> methods.

It is guaranteed that

    # Where $path_separator is / for Unix, \ for Windows, etc...
    dirname($path) . $path_separator . basename($path);

is equivalent to the original path for all systems but VMS.


=cut


package File::Basename;

# File::Basename is used during the Perl build, when the re extension may
# not be available, but we only actually need it if running under tainting.
BEGIN {
  if (${^TAINT}) {
    require re;
    re->import('taint');
  }
}


use strict;
use 5.006;
use warnings;
our(@ISA, @EXPORT, $VERSION, $Fileparse_fstype, $Fileparse_igncase);
require Exporter;
@ISA = qw(Exporter);
@EXPORT = qw(fileparse fileparse_set_fstype basename dirname);
$VERSION = "2.85";

fileparse_set_fstype($^O);


=over 4

=item C<fileparse>
X<fileparse>

    my($filename, $dirs, $suffix) = fileparse($path);
    my($filename, $dirs, $suffix) = fileparse($path, @suffixes);
    my $filename                  = fileparse($path, @suffixes);

The C<fileparse()> routine divides a file path into its $dirs, $filename
and (optionally) the filename $suffix.

$dirs contains everything up to and including the last
directory separator in the $path including the volume (if applicable).
The remainder of the $path is the $filename.

     # On Unix returns ("baz", "/foo/bar/", "")
     fileparse("/foo/bar/baz");

     # On Windows returns ("baz", 'C:\foo\bar\', "")
     fileparse('C:\foo\bar\baz');

     # On Unix returns ("", "/foo/bar/baz/", "")
     fileparse("/foo/bar/baz/");

If @suffixes are given each element is a pattern (either a string or a
C<qr//>) matched against the end of the $filename.  The matching
portion is removed and becomes the $suffix.

     # On Unix returns ("baz", "/foo/bar/", ".txt")
     fileparse("/foo/bar/baz.txt", qr/\.[^.]*/);

If type is non-Unix (see L</fileparse_set_fstype>) then the pattern
matching for suffix removal is performed case-insensitively, since
those systems are not case-sensitive when opening existing files.

You are guaranteed that C<$dirs . $filename . $suffix> will
denote the same location as the original $path.

=cut


sub fileparse {
  my($fullname,@suffices) = @_;

  unless (defined $fullname) {
      require Carp;
      Carp::croak("fileparse(): need a valid pathname");
  }

  my $orig_type = '';
  my($type,$igncase) = ($Fileparse_fstype, $Fileparse_igncase);

  my($taint) = substr($fullname,0,0);  # Is $fullname tainted?

  if ($type eq "VMS" and $fullname =~ m{/} ) {
    # We're doing Unix emulation
    $orig_type = $type;
    $type = 'Unix';
  }

  my($dirpath, $basename);

  if (grep { $type eq $_ } qw(MSDOS DOS MSWin32 Epoc)) {
    ($dirpath,$basename) = ($fullname =~ /^((?:.*[:\\\/])?)(.*)/s);
    $dirpath .= '.\\' unless $dirpath =~ /[\\\/]\z/;
  }
  elsif ($type eq "OS2") {
    ($dirpath,$basename) = ($fullname =~ m#^((?:.*[:\\/])?)(.*)#s);
    $dirpath = './' unless $dirpath;	# Can't be 0
    $dirpath .= '/' unless $dirpath =~ m#[\\/]\z#;
  }
  elsif ($type eq "MacOS") {
    ($dirpath,$basename) = ($fullname =~ /^(.*:)?(.*)/s);
    $dirpath = ':' unless $dirpath;
  }
  elsif ($type eq "AmigaOS") {
    ($dirpath,$basename) = ($fullname =~ /(.*[:\/])?(.*)/s);
    $dirpath = './' unless $dirpath;
  }
  elsif ($type eq 'VMS' ) {
    ($dirpath,$basename) = ($fullname =~ /^(.*[:>\]])?(.*)/s);
    $dirpath ||= '';  # should always be defined
  }
  else { # Default to Unix semantics.
    ($dirpath,$basename) = ($fullname =~ m{^(.*/)?(.*)}s);
    if ($orig_type eq 'VMS' and $fullname =~ m{^(/[^/]+/000000(/|$))(.*)}) {
      # dev:[000000] is top of VMS tree, similar to Unix '/'
      # so strip it off and treat the rest as "normal"
      my $devspec  = $1;
      my $remainder = $3;
      ($dirpath,$basename) = ($remainder =~ m{^(.*/)?(.*)}s);
      $dirpath ||= '';  # should always be defined
      $dirpath = $devspec.$dirpath;
    }
    $dirpath = './' unless $dirpath;
  }
      

  my $tail   = '';
  my $suffix = '';
  if (@suffices) {
    foreach $suffix (@suffices) {
      my $pat = ($igncase ? '(?i)' : '') . "($suffix)\$";
      if ($basename =~ s/$pat//s) {
        $taint .= substr($suffix,0,0);
        $tail = $1 . $tail;
      }
    }
  }

  # Ensure taint is propagated from the path to its pieces.
  $tail .= $taint;
  wantarray ? ($basename .= $taint, $dirpath .= $taint, $tail)
            : ($basename .= $taint);
}



=item C<basename>
X<basename> X<filename>

    my $filename = basename($path);
    my $filename = basename($path, @suffixes);

This function is provided for compatibility with the Unix shell command
C<basename(1)>.  It does B<NOT> always return the file name portion of a
path as you might expect.  To be safe, if you want the file name portion of
a path use C<fileparse()>.

C<basename()> returns the last level of a filepath even if the last
level is clearly directory.  In effect, it is acting like C<pop()> for
paths.  This differs from C<fileparse()>'s behaviour.

    # Both return "bar"
    basename("/foo/bar");
    basename("/foo/bar/");

@suffixes work as in C<fileparse()> except all regex metacharacters are
quoted.

    # These two function calls are equivalent.
    my $filename = basename("/foo/bar/baz.txt",  ".txt");
    my $filename = fileparse("/foo/bar/baz.txt", qr/\Q.txt\E/);

Also note that in order to be compatible with the shell command,
C<basename()> does not strip off a suffix if it is identical to the
remaining characters in the filename.

=cut


sub basename {
  my($path) = shift;

  # From BSD basename(1)
  # The basename utility deletes any prefix ending with the last slash '/'
  # character present in string (after first stripping trailing slashes)
  _strip_trailing_sep($path);

  my($basename, $dirname, $suffix) = fileparse( $path, map("\Q$_\E",@_) );

  # From BSD basename(1)
  # The suffix is not stripped if it is identical to the remaining 
  # characters in string.
  if( length $suffix and !length $basename ) {
      $basename = $suffix;
  }
  
  # Ensure that basename '/' == '/'
  if( !length $basename ) {
      $basename = $dirname;
  }

  return $basename;
}



=item C<dirname>
X<dirname>

This function is provided for compatibility with the Unix shell
command C<dirname(1)> and has inherited some of its quirks.  In spite of
its name it does B<NOT> always return the directory name as you might
expect.  To be safe, if you want the directory name of a path use
C<fileparse()>.

Only on VMS (where there is no ambiguity between the file and directory
portions of a path) and AmigaOS (possibly due to an implementation quirk in
this module) does C<dirname()> work like C<fileparse($path)>, returning just the
$dirs.

    # On VMS and AmigaOS
    my $dirs = dirname($path);

When using Unix or MSDOS syntax this emulates the C<dirname(1)> shell function
which is subtly different from how C<fileparse()> works.  It returns all but
the last level of a file path even if the last level is clearly a directory.
In effect, it is not returning the directory portion but simply the path one
level up acting like C<chop()> for file paths.

Also unlike C<fileparse()>, C<dirname()> does not include a trailing slash on
its returned path.

    # returns /foo/bar.  fileparse() would return /foo/bar/
    dirname("/foo/bar/baz");

    # also returns /foo/bar despite the fact that baz is clearly a 
    # directory.  fileparse() would return /foo/bar/baz/
    dirname("/foo/bar/baz/");

    # returns '.'.  fileparse() would return 'foo/'
    dirname("foo/");

Under VMS, if there is no directory information in the $path, then the
current default device and directory is used.

=cut


sub dirname {
    my $path = shift;

    my($type) = $Fileparse_fstype;

    if( $type eq 'VMS' and $path =~ m{/} ) {
        # Parse as Unix
        local($File::Basename::Fileparse_fstype) = '';
        return dirname($path);
    }

    my($basename, $dirname) = fileparse($path);

    if ($type eq 'VMS') { 
        $dirname ||= $ENV{DEFAULT};
    }
    elsif ($type eq 'MacOS') {
	if( !length($basename) && $dirname !~ /^[^:]+:\z/) {
            _strip_trailing_sep($dirname);
	    ($basename,$dirname) = fileparse $dirname;
	}
	$dirname .= ":" unless $dirname =~ /:\z/;
    }
    elsif (grep { $type eq $_ } qw(MSDOS DOS MSWin32 OS2)) { 
        _strip_trailing_sep($dirname);
        unless( length($basename) ) {
	    ($basename,$dirname) = fileparse $dirname;
	    _strip_trailing_sep($dirname);
	}
    }
    elsif ($type eq 'AmigaOS') {
        if ( $dirname =~ /:\z/) { return $dirname }
        chop $dirname;
        $dirname =~ s{[^:/]+\z}{} unless length($basename);
    }
    else {
        _strip_trailing_sep($dirname);
        unless( length($basename) ) {
	    ($basename,$dirname) = fileparse $dirname;
	    _strip_trailing_sep($dirname);
	}
    }

    $dirname;
}


# Strip the trailing path separator.
sub _strip_trailing_sep  {
    my $type = $Fileparse_fstype;

    if ($type eq 'MacOS') {
        $_[0] =~ s/([^:]):\z/$1/s;
    }
    elsif (grep { $type eq $_ } qw(MSDOS DOS MSWin32 OS2)) { 
        $_[0] =~ s/([^:])[\\\/]*\z/$1/;
    }
    else {
        $_[0] =~ s{(.)/*\z}{$1}s;
    }
}


=item C<fileparse_set_fstype>
X<filesystem>

  my $type = fileparse_set_fstype();
  my $previous_type = fileparse_set_fstype($type);

Normally File::Basename will assume a file path type native to your current
operating system (ie. /foo/bar style on Unix, \foo\bar on Windows, etc...).
With this function you can override that assumption.

Valid $types are "MacOS", "VMS", "AmigaOS", "OS2", "RISCOS",
"MSWin32", "DOS" (also "MSDOS" for backwards bug compatibility),
"Epoc" and "Unix" (all case-insensitive).  If an unrecognized $type is
given "Unix" will be assumed.

If you've selected VMS syntax, and the file specification you pass to
one of these routines contains a "/", they assume you are using Unix
emulation and apply the Unix syntax rules instead, for that function
call only.

=back

=cut


BEGIN {

my @Ignore_Case = qw(MacOS VMS AmigaOS OS2 RISCOS MSWin32 MSDOS DOS Epoc);
my @Types = (@Ignore_Case, qw(Unix));

sub fileparse_set_fstype {
    my $old = $Fileparse_fstype;

    if (@_) {
        my $new_type = shift;

        $Fileparse_fstype = 'Unix';  # default
        foreach my $type (@Types) {
            $Fileparse_fstype = $type if $new_type =~ /^$type/i;
        }

        $Fileparse_igncase = 
          (grep $Fileparse_fstype eq $_, @Ignore_Case) ? 1 : 0;
    }

    return $old;
}

}


1;


=head1 SEE ALSO

L<dirname(1)>, L<basename(1)>, L<File::Spec>