1 | #!/usr/bin/perl -w
|
---|
2 |
|
---|
3 | ###########################################################################
|
---|
4 | #
|
---|
5 | # buildcol.pl -- This program will build a particular collection
|
---|
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) 1999 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 | BEGIN {
|
---|
29 | die "GSDLHOME not set\n" unless defined $ENV{'GSDLHOME'};
|
---|
30 | die "GSDLOS not set\n" unless defined $ENV{'GSDLOS'};
|
---|
31 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib");
|
---|
32 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib/plugins");
|
---|
33 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib/classify");
|
---|
34 | }
|
---|
35 |
|
---|
36 | use colcfg;
|
---|
37 | use parsargv;
|
---|
38 | use util;
|
---|
39 |
|
---|
40 | &main();
|
---|
41 |
|
---|
42 | sub print_usage {
|
---|
43 | print STDERR "\n usage: $0 [options] collection-name\n\n";
|
---|
44 | print STDERR " options:\n";
|
---|
45 | print STDERR " -verbosity number 0=none, 3=lots\n";
|
---|
46 | print STDERR " -archivedir directory Where the archives live\n";
|
---|
47 | print STDERR " -cachedir directory Where to cache the archives\n";
|
---|
48 | print STDERR " -builddir directory Where to put the built indexes\n";
|
---|
49 | print STDERR " -maxdocs number Maximum number of documents to build\n";
|
---|
50 | print STDERR " -debug Print output to STDOUT\n";
|
---|
51 | print STDERR " -mode all|compress_text|build_index|infodb\n";
|
---|
52 | print STDERR " -index indexname Index to build (will build all in\n";
|
---|
53 | print STDERR " config file if not set)\n";
|
---|
54 | print STDERR " -keepold will not destroy the current contents of the\n";
|
---|
55 | print STDERR " building directory\n";
|
---|
56 | print STDERR " -allclassifications Don't remove empty classifications\n\n";
|
---|
57 | }
|
---|
58 |
|
---|
59 |
|
---|
60 | sub main
|
---|
61 | {
|
---|
62 | my ($verbosity, $archivedir, $cachedir, $builddir, $maxdocs,
|
---|
63 | $debug, $mode, $indexname, $keepold, $allclassifications);
|
---|
64 | if (!parsargv::parse(\@ARGV,
|
---|
65 | 'verbosity/\d+/2', \$verbosity,
|
---|
66 | 'archivedir/.*/', \$archivedir,
|
---|
67 | 'cachedir/.*/', \$cachedir,
|
---|
68 | 'builddir/.*/', \$builddir,
|
---|
69 | 'maxdocs/^\-?\d+/-1', \$maxdocs,
|
---|
70 | 'debug', \$debug,
|
---|
71 | 'mode/^(all|compress_text|build_index|infodb)$/all', \$mode,
|
---|
72 | 'index/.*/', \$indexname,
|
---|
73 | 'keepold', \$keepold,
|
---|
74 | 'allclassifications', \$allclassifications)) {
|
---|
75 | &print_usage();
|
---|
76 | die "\n";
|
---|
77 | }
|
---|
78 |
|
---|
79 | # get and check the collection
|
---|
80 | if (($collection = &util::use_collection(@ARGV)) eq "") {
|
---|
81 | &print_usage();
|
---|
82 | die "\n";
|
---|
83 | }
|
---|
84 |
|
---|
85 | # read the configuration file
|
---|
86 | $textindex = "section:text";
|
---|
87 | $configfilename = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "etc/collect.cfg");
|
---|
88 | if (-e $configfilename) {
|
---|
89 | $collectcfg = &colcfg::read_collect_cfg ($configfilename);
|
---|
90 | if (defined $collectcfg->{'archivedir'} && $archivedir eq "") {
|
---|
91 | $archivedir = $collectcfg->{'archivedir'};
|
---|
92 | }
|
---|
93 | if (defined $collectcfg->{'cachedir'} && $cachedir eq "") {
|
---|
94 | $cachedir = $collectcfg->{'cachedir'};
|
---|
95 | }
|
---|
96 | if (defined $collectcfg->{'builddir'} && $builddir eq "") {
|
---|
97 | $builddir = $collectcfg->{'builddir'};
|
---|
98 | }
|
---|
99 | } else {
|
---|
100 | die "Couldn't find the configuration file $configfilename\n";
|
---|
101 | }
|
---|
102 |
|
---|
103 | # fill in the default archives and building directories if none
|
---|
104 | # were supplied, turn all \ into / and remove trailing /
|
---|
105 | $archivedir = "$ENV{'GSDLCOLLECTDIR'}/archives" if $archivedir eq "";
|
---|
106 | $archivedir =~ s/[\\\/]+/\//g;
|
---|
107 | $archivedir =~ s/\/$//;
|
---|
108 | $builddir = "$ENV{'GSDLCOLLECTDIR'}/building" if $builddir eq "";
|
---|
109 | $builddir =~ s/[\\\/]+/\//g;
|
---|
110 | $builddir =~ s/\/$//;
|
---|
111 |
|
---|
112 | # update the archive cache if needed
|
---|
113 | if ($cachedir) {
|
---|
114 | print STDERR "Updating archive cache\n" if ($verbosity >= 1);
|
---|
115 |
|
---|
116 | $cachedir =~ s/[\\\/]+$//;
|
---|
117 | $cachedir .= "/collect/$collection" unless
|
---|
118 | $cachedir =~ /collect\/$collection/;
|
---|
119 |
|
---|
120 | $realarchivedir = "$cachedir/archives";
|
---|
121 | $realbuilddir = "$cachedir/building";
|
---|
122 | &util::mk_all_dir ($realarchivedir);
|
---|
123 | &util::mk_all_dir ($realbuilddir);
|
---|
124 | &util::cachedir ($archivedir, $realarchivedir, $verbosity);
|
---|
125 |
|
---|
126 | } else {
|
---|
127 | $realarchivedir = $archivedir;
|
---|
128 | $realbuilddir = $builddir;
|
---|
129 | }
|
---|
130 |
|
---|
131 | # build it in realbuilddir
|
---|
132 | &util::mk_all_dir ($realbuilddir);
|
---|
133 |
|
---|
134 |
|
---|
135 | # if a builder class has been created for this collection, use it
|
---|
136 | # otherwise, use the mg builder
|
---|
137 | if (-e "$ENV{'GSDLCOLLECTDIR'}/perllib/${collection}builder.pm") {
|
---|
138 | $builderdir = "$ENV{'GSDLCOLLECTDIR'}/perllib";
|
---|
139 | $buildertype = "${collection}builder";
|
---|
140 | } else {
|
---|
141 | $builderdir = "$ENV{'GSDLHOME'}/perllib";
|
---|
142 | $buildertype = "mgbuilder";
|
---|
143 | }
|
---|
144 |
|
---|
145 | require "$builderdir/$buildertype.pm";
|
---|
146 |
|
---|
147 | eval("\$builder = new $buildertype(\$collection, " .
|
---|
148 | "\$realarchivedir, \$realbuilddir, \$verbosity, " .
|
---|
149 | "\$maxdocs, \$debug, \$keepold, \$allclassifications)");
|
---|
150 | die "$@" if $@;
|
---|
151 |
|
---|
152 | $builder->init();
|
---|
153 |
|
---|
154 | if ($mode =~ /^all$/i) {
|
---|
155 | $builder->compress_text($textindex);
|
---|
156 | $builder->build_indexes($indexname);
|
---|
157 | $builder->make_infodatabase();
|
---|
158 | $builder->collect_specific();
|
---|
159 | } elsif ($mode =~ /^compress_text$/i) {
|
---|
160 | $builder->compress_text($textindex);
|
---|
161 | } elsif ($mode =~ /^build_index$/i) {
|
---|
162 | $builder->build_indexes($indexname);
|
---|
163 | } elsif ($mode =~ /^infodb$/i) {
|
---|
164 | $builder->make_infodatabase();
|
---|
165 | } else {
|
---|
166 | die "unknown mode: $mode\n";
|
---|
167 | }
|
---|
168 |
|
---|
169 | $builder->make_auxiliary_files() if !$debug;
|
---|
170 | $builder->deinit();
|
---|
171 |
|
---|
172 | if (($realbuilddir ne $builddir) && !$debug) {
|
---|
173 | print STDERR "Copying back the cached build\n" if ($verbosity >= 1);
|
---|
174 | &util::rm_r ($builddir);
|
---|
175 | &util::cp_r ($realbuilddir, $builddir);
|
---|
176 | }
|
---|
177 | }
|
---|
178 |
|
---|
179 |
|
---|