source: main/trunk/greenstone2/bin/script/incremental-import.pl@ 23218

Last change on this file since 23218 was 23218, checked in by kjdon, 14 years ago

fixed up -manifest use with this script. -manifest needs -keepold instead of -incremental

  • Property svn:executable set to *
File size: 5.2 KB
Line 
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
34BEGIN {
35 die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
36 die "GSDLOS not set\n" unless defined $ENV{'GSDLOS'};
37 unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
38}
39
40
41use strict;
42
43use dbutil;
44use util;
45use colcfg;
46
47sub main
48{
49 my ($argc,@argv) = @_;
50
51 if (($argc==0) || (($argc==1) && ($argv[0] =~ m/^--?h(elp)?$/))) {
52 my ($progname) = ($0 =~ m/^.*[\/|\\](.*?)$/);
53
54
55 print STDERR "\n";
56 print STDERR "Usage: $progname [import.pl options] collection\n";
57 print STDERR "\n";
58
59 exit(-1);
60 }
61
62
63 my $collection = pop @argv;
64
65 my @filtered_argv = ();
66
67 my $collect_dir = undef;
68 my $archive_dir = undef;
69 my $site = undef;
70 my $manifest = undef;
71
72 while (my $arg = shift @argv) {
73 # No actual filtering happens at the moment (@filterd_argv == @argv)
74 # Useful to do it this way if we want incremental-import.pl
75 # to start accepting its own arguments that are different to import.pl
76
77 if ($arg eq "-collectdir") {
78 $collect_dir = shift @argv;
79 push(@filtered_argv,$arg,$collect_dir);
80 }
81 elsif ($arg eq "-archivedir") {
82 $archive_dir = shift @argv;
83 push(@filtered_argv,$arg,$archive_dir);
84 }
85 elsif ($arg eq "-site") {
86 $site = shift @argv;
87 push(@filtered_argv,$arg,$site);
88 }
89 elsif ($arg eq "-manifest") {
90 $manifest = shift @argv;
91 push(@filtered_argv,$arg,$manifest);
92 }
93 else {
94 push(@filtered_argv,$arg);
95 }
96 }
97
98 # get and check the collection name
99 if ((&colcfg::use_collection($site, $collection, $collect_dir)) eq "") {
100 print STDERR "Unable to use collection \"$collection\" within \"$collect_dir\"\n";
101 exit -1;
102 }
103 my $gs_mode = "gs2";
104 if ((defined $site) && ($site ne "")) {
105 $gs_mode = "gs3";
106 }
107
108 if (!defined $archive_dir) {
109 $archive_dir = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "archives");
110 }
111 my $etcdir = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "etc");
112 # BACKWARDS COMPATIBILITY: Just in case there are old .ldb/.bdb files (won't do anything for other infodbtypes)
113 &util::rename_ldb_or_bdb_file(&util::filename_cat($archive_dir, "archiveinf-doc"));
114
115 my $col_cfg_file;
116 if ($gs_mode eq "gs3") {
117 $col_cfg_file = &util::filename_cat($etcdir, "collectionConfig.xml");
118 } else {
119 $col_cfg_file = &util::filename_cat($etcdir, "collect.cfg");
120 }
121
122 my $collect_cfg = &colcfg::read_collection_cfg ($col_cfg_file, $gs_mode);
123 # get the database type for this collection from its configuration file (may be undefined)
124 my $infodbtype = $collect_cfg->{'infodbtype'} || &dbutil::get_default_infodb_type();
125 $infodbtype = "gdbm" if $infodbtype eq "gdbm-txtgz";
126 my $archiveinf_doc_file_path = &dbutil::get_infodb_file_path($infodbtype, "archiveinf-doc", $archive_dir);
127
128 my $quoted_argv = join(" ", map { "\"$_\"" } @filtered_argv);
129
130
131 my $import_cmd = "import.pl";
132 if($ENV{'PERLPATH'}) {
133 # need to ensure that the path to perl is quoted (in case there's spaces in it)
134 if($ENV{'GSDLOS'} =~ m/windows/) {
135 $import_cmd = "\"$ENV{'PERLPATH'}\\Perl.exe\" -S $import_cmd";
136 } else {
137 $import_cmd = "\"$ENV{'PERLPATH'}/perl\" -S $import_cmd";
138 }
139 } else {
140 $import_cmd = "perl -S $import_cmd";
141 }
142
143 if (defined $manifest) {
144 # manifest files need -keepold not -incremental
145 $import_cmd .= " -keepold";
146 } else {
147 if (-e $archiveinf_doc_file_path) {
148 $import_cmd .= " -incremental";
149
150 }
151 else {
152 print STDERR "*****\n";
153 print STDERR "First time import. Switching to full import.pl.\n";
154 print STDERR "*****\n";
155 $import_cmd .= " -removeold";
156 }
157 }
158 $import_cmd .= " $quoted_argv \"$collection\"";
159
160
161 my $import_status = system($import_cmd)/256;
162
163 if ($import_status != 0) {
164 print STDERR "Error: Failed to run: $import_cmd\n";
165 print STDERR " $!\n" if ($! ne "");
166 exit(-1);
167 }
168}
169
170&main(scalar(@ARGV),@ARGV);
Note: See TracBrowser for help on using the repository browser.