1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # RecPlug.pm --
|
---|
4 | # A component of the Greenstone digital library software
|
---|
5 | # from the New Zealand Digital Library Project at the
|
---|
6 | # University of Waikato, New Zealand.
|
---|
7 | #
|
---|
8 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
9 | #
|
---|
10 | # This program is free software; you can redistribute it and/or modify
|
---|
11 | # it under the terms of the GNU General Public License as published by
|
---|
12 | # the Free Software Foundation; either version 2 of the License, or
|
---|
13 | # (at your option) any later version.
|
---|
14 | #
|
---|
15 | # This program is distributed in the hope that it will be useful,
|
---|
16 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
17 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
18 | # GNU General Public License for more details.
|
---|
19 | #
|
---|
20 | # You should have received a copy of the GNU General Public License
|
---|
21 | # along with this program; if not, write to the Free Software
|
---|
22 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
23 | #
|
---|
24 | ###########################################################################
|
---|
25 |
|
---|
26 | # plugin which recurses through directories processing
|
---|
27 | # each file it finds
|
---|
28 |
|
---|
29 | package RecPlug;
|
---|
30 |
|
---|
31 | use BasPlug;
|
---|
32 | use plugin;
|
---|
33 | use util;
|
---|
34 |
|
---|
35 |
|
---|
36 | BEGIN {
|
---|
37 | @ISA = ('BasPlug');
|
---|
38 | }
|
---|
39 |
|
---|
40 | sub new {
|
---|
41 | my ($class) = @_;
|
---|
42 | my $self = new BasPlug ();
|
---|
43 |
|
---|
44 | $self->{'exclude_tail_dirs'} = []; # empty by default
|
---|
45 |
|
---|
46 | return bless $self, $class;
|
---|
47 | }
|
---|
48 |
|
---|
49 | # return 1 if this class might recurse using $pluginfo
|
---|
50 | sub is_recursive {
|
---|
51 | my $self = shift (@_);
|
---|
52 |
|
---|
53 | return 1;
|
---|
54 | }
|
---|
55 |
|
---|
56 |
|
---|
57 | # return number of files processed, undef if can't process
|
---|
58 | # Note that $base_dir might be "" and that $file might
|
---|
59 | # include directories
|
---|
60 | sub read {
|
---|
61 | my $self = shift (@_);
|
---|
62 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs) = @_;
|
---|
63 |
|
---|
64 | foreach $etd ( @{$self->{'exclude_tail_dirs'}} )
|
---|
65 | {
|
---|
66 | return 0 if ($file =~ m/$etd/);
|
---|
67 | }
|
---|
68 |
|
---|
69 | my (@dir, $subfile);
|
---|
70 |
|
---|
71 | my $count = 0;
|
---|
72 |
|
---|
73 | # see if this is a directory
|
---|
74 | $dirname = &util::filename_cat ($base_dir, $file);
|
---|
75 | if (-d $dirname) {
|
---|
76 |
|
---|
77 | # read all the files in the directory
|
---|
78 | if (!opendir (DIR, $dirname))
|
---|
79 | {
|
---|
80 | print STDERR "RecPlug: WARNING - couldn't read directory $dirname\n";
|
---|
81 | return;
|
---|
82 | }
|
---|
83 |
|
---|
84 | @dir = readdir (DIR);
|
---|
85 | closedir (DIR);
|
---|
86 |
|
---|
87 | print STDERR "RecPlug: getting directory $dirname\n";
|
---|
88 |
|
---|
89 | # process each file
|
---|
90 | foreach $subfile (@dir) {
|
---|
91 | last if ($maxdocs != -1 && $count >= $maxdocs);
|
---|
92 |
|
---|
93 | if ($subfile !~ /^\.\.?$/) {
|
---|
94 | # note: metadata is not carried on to the next level
|
---|
95 | $count += &plugin::read ($pluginfo, $base_dir, &util::filename_cat($file, $subfile),
|
---|
96 | {}, $processor, $maxdocs);
|
---|
97 | }
|
---|
98 | }
|
---|
99 | return $count;
|
---|
100 | }
|
---|
101 |
|
---|
102 | # wasn't a directory, someone else will have to process it
|
---|
103 | return undef;
|
---|
104 | }
|
---|
105 |
|
---|
106 |
|
---|
107 | 1;
|
---|