[537] | 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 |
|
---|
[4] | 26 | # plugin which recurses through directories processing
|
---|
| 27 | # each file it finds
|
---|
| 28 |
|
---|
| 29 | package RecPlug;
|
---|
| 30 |
|
---|
| 31 | use BasPlug;
|
---|
| 32 | use plugin;
|
---|
[136] | 33 | use util;
|
---|
[4] | 34 |
|
---|
| 35 |
|
---|
| 36 | BEGIN {
|
---|
| 37 | @ISA = ('BasPlug');
|
---|
| 38 | }
|
---|
| 39 |
|
---|
[1279] | 40 | use strict;
|
---|
| 41 |
|
---|
[4] | 42 | sub new {
|
---|
| 43 | my ($class) = @_;
|
---|
[1279] | 44 | my $self = new BasPlug ("RecPlug", @_);
|
---|
[4] | 45 |
|
---|
[620] | 46 | $self->{'exclude_tail_dirs'} = []; # empty by default
|
---|
| 47 |
|
---|
[4] | 48 | return bless $self, $class;
|
---|
| 49 | }
|
---|
| 50 |
|
---|
| 51 | # return 1 if this class might recurse using $pluginfo
|
---|
| 52 | sub is_recursive {
|
---|
| 53 | my $self = shift (@_);
|
---|
| 54 |
|
---|
| 55 | return 1;
|
---|
| 56 | }
|
---|
| 57 |
|
---|
[317] | 58 |
|
---|
| 59 | # return number of files processed, undef if can't process
|
---|
[4] | 60 | # Note that $base_dir might be "" and that $file might
|
---|
| 61 | # include directories
|
---|
| 62 | sub read {
|
---|
| 63 | my $self = shift (@_);
|
---|
[317] | 64 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs) = @_;
|
---|
[4] | 65 |
|
---|
[1279] | 66 | foreach my $etd ( @{$self->{'exclude_tail_dirs'}} )
|
---|
[620] | 67 | {
|
---|
| 68 | return 0 if ($file =~ m/$etd/);
|
---|
| 69 | }
|
---|
| 70 |
|
---|
[4] | 71 | my (@dir, $subfile);
|
---|
| 72 |
|
---|
[317] | 73 | my $count = 0;
|
---|
| 74 |
|
---|
[4] | 75 | # see if this is a directory
|
---|
[1279] | 76 | my $dirname = &util::filename_cat ($base_dir, $file);
|
---|
[136] | 77 | if (-d $dirname) {
|
---|
[4] | 78 |
|
---|
| 79 | # read all the files in the directory
|
---|
[593] | 80 | if (!opendir (DIR, $dirname))
|
---|
| 81 | {
|
---|
| 82 | print STDERR "RecPlug: WARNING - couldn't read directory $dirname\n";
|
---|
| 83 | return;
|
---|
| 84 | }
|
---|
| 85 |
|
---|
[4] | 86 | @dir = readdir (DIR);
|
---|
| 87 | closedir (DIR);
|
---|
| 88 |
|
---|
[317] | 89 | print STDERR "RecPlug: getting directory $dirname\n";
|
---|
| 90 |
|
---|
[4] | 91 | # process each file
|
---|
| 92 | foreach $subfile (@dir) {
|
---|
[809] | 93 | last if ($maxdocs != -1 && $count >= $maxdocs);
|
---|
[317] | 94 |
|
---|
[4] | 95 | if ($subfile !~ /^\.\.?$/) {
|
---|
| 96 | # note: metadata is not carried on to the next level
|
---|
[317] | 97 | $count += &plugin::read ($pluginfo, $base_dir, &util::filename_cat($file, $subfile),
|
---|
| 98 | {}, $processor, $maxdocs);
|
---|
[4] | 99 | }
|
---|
| 100 | }
|
---|
[317] | 101 | return $count;
|
---|
[4] | 102 | }
|
---|
| 103 |
|
---|
| 104 | # wasn't a directory, someone else will have to process it
|
---|
[317] | 105 | return undef;
|
---|
[4] | 106 | }
|
---|
| 107 |
|
---|
| 108 |
|
---|
| 109 | 1;
|
---|