1 | #!/usr/bin/perl -w
|
---|
2 |
|
---|
3 | ###########################################################################
|
---|
4 | #
|
---|
5 | # full-import.pl -- runs import.pl with -incremental option on
|
---|
6 | # A component of the Greenstone digital library software
|
---|
7 | # from the New Zealand Digital Library Project at the
|
---|
8 | # University of Waikato, New Zealand.
|
---|
9 | #
|
---|
10 | # Copyright (C) 2009 New Zealand Digital Library Project
|
---|
11 | #
|
---|
12 | # This program is free software; you can redistribute it and/or modify
|
---|
13 | # it under the terms of the GNU General Public License as published by
|
---|
14 | # the Free Software Foundation; either version 2 of the License, or
|
---|
15 | # (at your option) any later version.
|
---|
16 | #
|
---|
17 | # This program is distributed in the hope that it will be useful,
|
---|
18 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
19 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
20 | # GNU General Public License for more details.
|
---|
21 | #
|
---|
22 | # You should have received a copy of the GNU General Public License
|
---|
23 | # along with this program; if not, write to the Free Software
|
---|
24 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
25 | #
|
---|
26 | ###########################################################################
|
---|
27 |
|
---|
28 |
|
---|
29 | # This program is designed to support incremental building of Greenstone
|
---|
30 | # Runs: import.pl -incremental ...
|
---|
31 |
|
---|
32 |
|
---|
33 | BEGIN {
|
---|
34 | die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
|
---|
35 | die "GSDLOS not set\n" unless defined $ENV{'GSDLOS'};
|
---|
36 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
|
---|
37 | }
|
---|
38 |
|
---|
39 | use strict;
|
---|
40 | use dbutil;
|
---|
41 | use util;
|
---|
42 | use colcfg;
|
---|
43 |
|
---|
44 | sub main
|
---|
45 | {
|
---|
46 | my ($argc,@argv) = @_;
|
---|
47 |
|
---|
48 | if (($argc==0) || (($argc==1) && ($argv[0] =~ m/^--?h(elp)?$/))) {
|
---|
49 | my ($progname) = ($0 =~ m/^.*[\/|\\](.*?)$/);
|
---|
50 |
|
---|
51 |
|
---|
52 | print STDERR "\n";
|
---|
53 | print STDERR "Usage: $progname [import.pl options] collection\n";
|
---|
54 | print STDERR "\n";
|
---|
55 |
|
---|
56 | exit(-1);
|
---|
57 | }
|
---|
58 |
|
---|
59 | my $collection = pop @argv;
|
---|
60 |
|
---|
61 | my @filtered_argv = ();
|
---|
62 |
|
---|
63 | my $collect_dir = undef;
|
---|
64 | my $archive_dir = undef;
|
---|
65 | my $site = undef;
|
---|
66 | my $manifest = undef;
|
---|
67 |
|
---|
68 | while (my $arg = shift @argv) {
|
---|
69 | # No actual filtering happens at the moment (@filterd_argv == @argv)
|
---|
70 | # Useful to do it this way if we want incremental-import.pl
|
---|
71 | # to start accepting its own arguments that are different to import.pl
|
---|
72 |
|
---|
73 | if ($arg eq "-collectdir") {
|
---|
74 | $collect_dir = shift @argv;
|
---|
75 | push(@filtered_argv,$arg,$collect_dir);
|
---|
76 | }
|
---|
77 | elsif ($arg eq "-archivedir") {
|
---|
78 | $archive_dir = shift @argv;
|
---|
79 | push(@filtered_argv,$arg,$archive_dir);
|
---|
80 | }
|
---|
81 | elsif ($arg eq "-site") {
|
---|
82 | $site = shift @argv;
|
---|
83 | push(@filtered_argv,$arg,$site);
|
---|
84 | }
|
---|
85 | elsif ($arg eq "-manifest") {
|
---|
86 | $manifest = shift @argv;
|
---|
87 | push(@filtered_argv,$arg,$manifest);
|
---|
88 | }
|
---|
89 | else {
|
---|
90 | push(@filtered_argv,$arg);
|
---|
91 | }
|
---|
92 | }
|
---|
93 |
|
---|
94 | # get and check the collection name
|
---|
95 | if ((&colcfg::use_collection($site, $collection, $collect_dir)) eq "") {
|
---|
96 | print STDERR "Unable to use collection \"$collection\" within \"$collect_dir\"\n";
|
---|
97 | exit -1;
|
---|
98 | }
|
---|
99 | my $gs_mode = "gs2";
|
---|
100 | if ((defined $site) && ($site ne "")) {
|
---|
101 | $gs_mode = "gs3";
|
---|
102 | }
|
---|
103 |
|
---|
104 | if (!defined $archive_dir) {
|
---|
105 | $archive_dir = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "archives");
|
---|
106 | }
|
---|
107 | my $etcdir = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "etc");
|
---|
108 | # BACKWARDS COMPATIBILITY: Just in case there are old .ldb/.bdb files (won't do anything for other infodbtypes)
|
---|
109 | &util::rename_ldb_or_bdb_file(&util::filename_cat($archive_dir, "archiveinf-doc"));
|
---|
110 |
|
---|
111 | my $col_cfg_file;
|
---|
112 | if ($gs_mode eq "gs3") {
|
---|
113 | $col_cfg_file = &util::filename_cat($etcdir, "collectionConfig.xml");
|
---|
114 | } else {
|
---|
115 | $col_cfg_file = &util::filename_cat($etcdir, "collect.cfg");
|
---|
116 | }
|
---|
117 |
|
---|
118 | my $collect_cfg = &colcfg::read_collection_cfg ($col_cfg_file, $gs_mode);
|
---|
119 | # get the database type for this collection from its configuration file (may be undefined)
|
---|
120 | my $infodbtype = $collect_cfg->{'infodbtype'} || &dbutil::get_default_infodb_type();
|
---|
121 | $infodbtype = "gdbm" if $infodbtype eq "gdbm-txtgz";
|
---|
122 | my $archiveinf_doc_file_path = &dbutil::get_infodb_file_path($infodbtype, "archiveinf-doc", $archive_dir);
|
---|
123 |
|
---|
124 | my $quoted_argv = join(" ", map { "\"$_\"" } @filtered_argv);
|
---|
125 |
|
---|
126 | # need to ensure that the path to perl is quoted (in case there's spaces in it)
|
---|
127 | my $import_cmd = "\"".&util::get_perl_exec()."\" -S import.pl";
|
---|
128 |
|
---|
129 | if (defined $manifest) {
|
---|
130 | # manifest files need -keepold not -incremental
|
---|
131 | $import_cmd .= " -keepold";
|
---|
132 | } else {
|
---|
133 | if (-e $archiveinf_doc_file_path) {
|
---|
134 | $import_cmd .= " -incremental";
|
---|
135 |
|
---|
136 | }
|
---|
137 | else {
|
---|
138 | print STDERR "*****\n";
|
---|
139 | print STDERR "First time import. Switching to full import.pl.\n";
|
---|
140 | print STDERR "*****\n";
|
---|
141 | $import_cmd .= " -removeold";
|
---|
142 | }
|
---|
143 | }
|
---|
144 | $import_cmd .= " $quoted_argv \"$collection\"";
|
---|
145 |
|
---|
146 |
|
---|
147 | my $import_status = system($import_cmd)/256;
|
---|
148 |
|
---|
149 | if ($import_status != 0) {
|
---|
150 | print STDERR "Error: Failed to run: $import_cmd\n";
|
---|
151 | print STDERR " $!\n" if ($! ne "");
|
---|
152 | exit(-1);
|
---|
153 | }
|
---|
154 | }
|
---|
155 |
|
---|
156 | &main(scalar(@ARGV),@ARGV);
|
---|