source: main/trunk/greenstone2/bin/script/mirror.pl@ 24362

Last change on this file since 24362 was 24362, checked in by ak19, 12 years ago

The method of locating perl has changed once more: util now defines the fuction get_perl_exec which is used by other scripts to obtain the path to the perl executable they should use.

  • Property svn:executable set to *
  • Property svn:keywords set to Author Date Id Revision
File size: 4.5 KB
Line 
1#!/usr/bin/perl -w
2
3###########################################################################
4#
5# mirror.pl
6#
7# A component of the Greenstone digital library software
8# from the New Zealand Digital Library Project at the
9# University of Waikato, New Zealand.
10#
11# Copyright (C) 1999 New Zealand Digital Library Project
12#
13# This program is free software; you can redistribute it and/or modify
14# it under the terms of the GNU General Public License as published by
15# the Free Software Foundation; either version 2 of the License, or
16# (at your option) any later version.
17#
18# This program is distributed in the hope that it will be useful,
19# but WITHOUT ANY WARRANTY; without even the implied warranty of
20# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21# GNU General Public License for more details.
22#
23# You should have received a copy of the GNU General Public License
24# along with this program; if not, write to the Free Software
25# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
26#
27###########################################################################
28
29
30# This program uses w3mirror to mirror a web site. It looks for a
31# mirror program configuration files in etc, and if it finds them then
32# it runs the mirroring software using this configuration file, and placing
33# the mirror in the import directory.
34#
35# mirror.pl can use the w3mirror program or the wget program if they are
36# installed.
37#
38# To use w3mirror, the configuration file must be in etc/w3mir.cfg.
39# To use GNU wget, the configuration file (i.e. a wgetrc file) must
40# be in etc/wget.cfg and a file of the URLs to read in etc/wget.url
41
42BEGIN {
43 die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
44 die "GSDLOS not set\n" unless defined $ENV{'GSDLOS'};
45 unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
46 unshift (@INC, "$ENV{'GSDLHOME'}/perllib/plugins");
47 unshift (@INC, "$ENV{'GSDLHOME'}/perllib/classify");
48}
49
50use arcinfo;
51use colcfg;
52use util;
53use parsargv;
54
55sub print_usage {
56 print STDERR "\n";
57 print STDERR "mirror.pl: Uses w3mir or wget to sync a collections import data\n";
58 print STDERR " with a website.\n\n";
59 print STDERR " usage: $0 [options] collection-name\n\n";
60 print STDERR " options:\n";
61 print STDERR " -verbosity number 0=none, 3=lots\n";
62 print STDERR " -importdir directory Where to place the mirrored material\n";
63}
64
65
66&main ();
67
68sub main {
69 my ($verbosity, $importdir, $etcdir,
70 $collection, $configfilename, $collectcfg);
71
72 if (!parsargv::parse(\@ARGV,
73 'verbosity/\d+/2', \$verbosity,
74 'importdir/.*/', \$importdir )) {
75 &print_usage();
76 die "\n";
77 }
78
79 # get and check the collection name
80 if (($collection = &util::use_collection(@ARGV)) eq "") {
81 &print_usage();
82 die "\n";
83 }
84
85 # get the etc directory
86 $etcdir = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "etc");
87
88 # check the collection configuration file for options
89 my $interval = 0;
90 $configfilename = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'},
91 "etc", "collect.cfg");
92 if (-e $configfilename) {
93 $collectcfg = &colcfg::read_collect_cfg ($configfilename);
94 if (defined $collectcfg->{'importdir'} && $importdir eq "") {
95 $importdir = $collectcfg->{'importdir'};
96 }
97 } else {
98 die "Couldn't find the configuration file $configfilename\n";
99 }
100
101 # fill in the default import directories if none
102 # were supplied, turn all \ into / and remove trailing /
103 $importdir = "$ENV{'GSDLCOLLECTDIR'}/import" if $importdir eq "";
104 $importdir =~ s/[\\\/]+/\//g;
105 $importdir =~ s/\/$//;
106
107 # make sure there is an import directory
108 if (! -e "$importdir") {
109 &util::mk_dir($importdir);
110 }
111
112 # if w3mir.cfg exists,
113 # then we are using w3mirror to mirror the remote site
114 if (-e "$etcdir/w3mir.cfg") {
115
116 # run the mirror program from the import directory
117 my $cmd = "cd $importdir; ";
118 # need to ensure that the path to perl is quoted (in case there's spaces in it)
119 $cmd .= "\"".&util::get_perl_exec()."\" -S gsw3mir.pl -cfgfile $etcdir/w3mir.cfg";
120 # print "\n$cmd\n";
121 `$cmd`;
122
123 }
124
125 # if wget.cfg and wget.url both exist,
126 # then we are using GNU wget to mirror the remote site
127 elsif ((-e "$etcdir/wget.cfg") && (-e "$etcdir/wget.url")) {
128 $ENV{WGETRC} = "$etcdir/wget.cfg";
129 my $cmd = "\"".&util::get_perl_exec()."\" -S gsWget.pl --input-file=$etcdir/wget.url --directory-prefix=$importdir";
130 system($cmd);
131 }
132
133 # otherwise, there are no mirror copnfiguration files
134 else {
135 die "Couldn't find the mirror configuration files in $etcdir\n";
136 }
137
138
139}
140
141
142
143
144
145
Note: See TracBrowser for help on using the repository browser.