[14028] | 1 | #!/usr/bin/perl -w
|
---|
| 2 |
|
---|
[22743] | 3 | ###########################################################################
|
---|
| 4 | #
|
---|
| 5 | # buildcol.pl --
|
---|
[14028] | 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 | #
|
---|
[22743] | 10 | # Copyright (C) 1999 New Zealand Digital Library Project
|
---|
| 11 | #
|
---|
[14028] | 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 | #
|
---|
[22743] | 26 | ###########################################################################
|
---|
| 27 |
|
---|
| 28 |
|
---|
| 29 | # This program will build a particular collection.
|
---|
| 30 |
|
---|
[14028] | 31 | package buildcol;
|
---|
| 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 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib/cpan");
|
---|
| 38 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib/cpan/XML/XPath");
|
---|
| 39 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib/plugins");
|
---|
| 40 | unshift (@INC, "$ENV{'GSDLHOME'}/perllib/classify");
|
---|
[14942] | 41 |
|
---|
| 42 | if (defined $ENV{'GSDLEXTS'}) {
|
---|
| 43 | my @extensions = split(/:/,$ENV{'GSDLEXTS'});
|
---|
| 44 | foreach my $e (@extensions) {
|
---|
| 45 | my $ext_prefix = "$ENV{'GSDLHOME'}/ext/$e";
|
---|
| 46 |
|
---|
| 47 | unshift (@INC, "$ext_prefix/perllib");
|
---|
| 48 | unshift (@INC, "$ext_prefix/perllib/cpan");
|
---|
[16788] | 49 | unshift (@INC, "$ext_prefix/perllib/plugins");
|
---|
| 50 | unshift (@INC, "$ext_prefix/perllib/classify");
|
---|
[14942] | 51 | }
|
---|
| 52 | }
|
---|
[21292] | 53 | if (defined $ENV{'GSDL3EXTS'}) {
|
---|
| 54 | my @extensions = split(/:/,$ENV{'GSDL3EXTS'});
|
---|
| 55 | foreach my $e (@extensions) {
|
---|
| 56 | my $ext_prefix = "$ENV{'GSDL3SRCHOME'}/ext/$e";
|
---|
| 57 |
|
---|
| 58 | unshift (@INC, "$ext_prefix/perllib");
|
---|
| 59 | unshift (@INC, "$ext_prefix/perllib/cpan");
|
---|
| 60 | unshift (@INC, "$ext_prefix/perllib/plugins");
|
---|
| 61 | unshift (@INC, "$ext_prefix/perllib/classify");
|
---|
| 62 | }
|
---|
| 63 | }
|
---|
| 64 |
|
---|
[14028] | 65 | }
|
---|
| 66 |
|
---|
| 67 | use colcfg;
|
---|
[21633] | 68 | use dbutil;
|
---|
[14028] | 69 | use util;
|
---|
| 70 | use scriptutil;
|
---|
| 71 | use FileHandle;
|
---|
| 72 | use gsprintf;
|
---|
| 73 | use printusage;
|
---|
| 74 | use parse2;
|
---|
| 75 |
|
---|
| 76 | use strict;
|
---|
| 77 | no strict 'refs'; # allow filehandles to be variables and vice versa
|
---|
| 78 | no strict 'subs'; # allow barewords (eg STDERR) as function arguments
|
---|
| 79 |
|
---|
| 80 |
|
---|
| 81 | my $mode_list =
|
---|
| 82 | [ { 'name' => "all",
|
---|
| 83 | 'desc' => "{buildcol.mode.all}" },
|
---|
| 84 | { 'name' => "compress_text",
|
---|
| 85 | 'desc' => "{buildcol.mode.compress_text}" },
|
---|
| 86 | { 'name' => "build_index",
|
---|
| 87 | 'desc' => "{buildcol.mode.build_index}" },
|
---|
| 88 | { 'name' => "infodb",
|
---|
| 89 | 'desc' => "{buildcol.mode.infodb}" } ];
|
---|
| 90 |
|
---|
| 91 | my $sec_index_list =
|
---|
| 92 | [ {'name' => "never",
|
---|
| 93 | 'desc' => "{buildcol.sections_index_document_metadata.never}" },
|
---|
| 94 | {'name' => "always",
|
---|
| 95 | 'desc' => "{buildcol.sections_index_document_metadata.always}" },
|
---|
| 96 | {'name' => "unless_section_metadata_exists",
|
---|
| 97 | 'desc' => "{buildcol.sections_index_document_metadata.unless_section_metadata_exists}" }
|
---|
| 98 | ];
|
---|
| 99 |
|
---|
| 100 | my $arguments =
|
---|
[14247] | 101 | [ { 'name' => "remove_empty_classifications",
|
---|
[14028] | 102 | 'desc' => "{buildcol.remove_empty_classifications}",
|
---|
| 103 | 'type' => "flag",
|
---|
| 104 | 'reqd' => "no",
|
---|
| 105 | 'modegli' => "2" },
|
---|
| 106 | { 'name' => "archivedir",
|
---|
| 107 | 'desc' => "{buildcol.archivedir}",
|
---|
| 108 | 'type' => "string",
|
---|
| 109 | 'reqd' => "no",
|
---|
| 110 | 'hiddengli' => "yes" },
|
---|
| 111 | { 'name' => "builddir",
|
---|
| 112 | 'desc' => "{buildcol.builddir}",
|
---|
| 113 | 'type' => "string",
|
---|
| 114 | 'reqd' => "no",
|
---|
| 115 | 'hiddengli' => "yes" },
|
---|
| 116 | # { 'name' => "cachedir",
|
---|
| 117 | # 'desc' => "{buildcol.cachedir}",
|
---|
| 118 | # 'type' => "string",
|
---|
| 119 | # 'reqd' => "no" },
|
---|
| 120 | { 'name' => "collectdir",
|
---|
| 121 | 'desc' => "{buildcol.collectdir}",
|
---|
| 122 | 'type' => "string",
|
---|
| 123 | # parsearg left "" as default
|
---|
| 124 | #'deft' => &util::filename_cat ($ENV{'GSDLHOME'}, "collect"),
|
---|
| 125 | 'reqd' => "no",
|
---|
| 126 | 'hiddengli' => "yes" },
|
---|
[14925] | 127 | { 'name' => "site",
|
---|
| 128 | 'desc' => "{buildcol.site}",
|
---|
| 129 | 'type' => "string",
|
---|
| 130 | 'deft' => "",
|
---|
| 131 | 'reqd' => "no",
|
---|
| 132 | 'hiddengli' => "yes" },
|
---|
[14028] | 133 | { 'name' => "debug",
|
---|
| 134 | 'desc' => "{buildcol.debug}",
|
---|
| 135 | 'type' => "flag",
|
---|
| 136 | 'reqd' => "no",
|
---|
| 137 | 'hiddengli' => "yes" },
|
---|
| 138 | { 'name' => "faillog",
|
---|
| 139 | 'desc' => "{buildcol.faillog}",
|
---|
| 140 | 'type' => "string",
|
---|
| 141 | # parsearg left "" as default
|
---|
| 142 | #'deft' => &util::filename_cat("<collectdir>", "colname", "etc", "fail.log"),
|
---|
| 143 | 'reqd' => "no",
|
---|
[18590] | 144 | 'modegli' => "3" },
|
---|
[14028] | 145 | { 'name' => "index",
|
---|
| 146 | 'desc' => "{buildcol.index}",
|
---|
| 147 | 'type' => "string",
|
---|
| 148 | 'reqd' => "no",
|
---|
[18590] | 149 | 'modegli' => "3" },
|
---|
[14028] | 150 | { 'name' => "incremental",
|
---|
| 151 | 'desc' => "{buildcol.incremental}",
|
---|
| 152 | 'type' => "flag",
|
---|
| 153 | 'hiddengli' => "yes" },
|
---|
| 154 | { 'name' => "keepold",
|
---|
| 155 | 'desc' => "{buildcol.keepold}",
|
---|
| 156 | 'type' => "flag",
|
---|
| 157 | 'reqd' => "no",
|
---|
| 158 | #'modegli' => "3",
|
---|
| 159 | 'hiddengli' => "yes" },
|
---|
| 160 | { 'name' => "removeold",
|
---|
| 161 | 'desc' => "{buildcol.removeold}",
|
---|
| 162 | 'type' => "flag",
|
---|
| 163 | 'reqd' => "no",
|
---|
| 164 | #'modegli' => "3",
|
---|
| 165 | 'hiddengli' => "yes" },
|
---|
| 166 | { 'name' => "language",
|
---|
| 167 | 'desc' => "{scripts.language}",
|
---|
| 168 | 'type' => "string",
|
---|
| 169 | 'reqd' => "no",
|
---|
[18590] | 170 | 'modegli' => "3" },
|
---|
[14028] | 171 | { 'name' => "maxdocs",
|
---|
| 172 | 'desc' => "{buildcol.maxdocs}",
|
---|
| 173 | 'type' => "int",
|
---|
| 174 | 'reqd' => "no",
|
---|
| 175 | 'hiddengli' => "yes" },
|
---|
| 176 | { 'name' => "maxnumeric",
|
---|
| 177 | 'desc' => "{buildcol.maxnumeric}",
|
---|
| 178 | 'type' => "int",
|
---|
| 179 | 'reqd' => "no",
|
---|
| 180 | 'deft' => "4",
|
---|
| 181 | 'range' => "4,512",
|
---|
| 182 | 'modegli' => "3" },
|
---|
| 183 | { 'name' => "mode",
|
---|
| 184 | 'desc' => "{buildcol.mode}",
|
---|
| 185 | 'type' => "enum",
|
---|
| 186 | 'list' => $mode_list,
|
---|
| 187 | # parsearg left "" as default
|
---|
| 188 | # 'deft' => "all",
|
---|
| 189 | 'reqd' => "no",
|
---|
[18590] | 190 | 'modegli' => "3" },
|
---|
[14028] | 191 | { 'name' => "no_strip_html",
|
---|
| 192 | 'desc' => "{buildcol.no_strip_html}",
|
---|
| 193 | 'type' => "flag",
|
---|
| 194 | 'reqd' => "no",
|
---|
[18590] | 195 | 'modegli' => "3" },
|
---|
[14028] | 196 | { 'name' => "no_text",
|
---|
| 197 | 'desc' => "{buildcol.no_text}",
|
---|
| 198 | 'type' => "flag",
|
---|
| 199 | 'reqd' => "no",
|
---|
[18590] | 200 | 'modegli' => "2" },
|
---|
[14028] | 201 | { 'name' => "sections_index_document_metadata",
|
---|
| 202 | 'desc' => "{buildcol.sections_index_document_metadata}",
|
---|
| 203 | 'type' => "enum",
|
---|
| 204 | 'list' => $sec_index_list,
|
---|
| 205 | 'reqd' => "no",
|
---|
[18590] | 206 | 'modegli' => "2" },
|
---|
[14028] | 207 | { 'name' => "out",
|
---|
| 208 | 'desc' => "{buildcol.out}",
|
---|
| 209 | 'type' => "string",
|
---|
| 210 | 'deft' => "STDERR",
|
---|
| 211 | 'reqd' => "no",
|
---|
| 212 | 'hiddengli' => "yes" },
|
---|
| 213 | { 'name' => "verbosity",
|
---|
| 214 | 'desc' => "{buildcol.verbosity}",
|
---|
| 215 | 'type' => "int",
|
---|
| 216 | # parsearg left "" as default
|
---|
| 217 | #'deft' => "2",
|
---|
| 218 | 'reqd' => "no",
|
---|
[18590] | 219 | 'modegli' => "3" },
|
---|
[14028] | 220 | { 'name' => "gli",
|
---|
| 221 | 'desc' => "",
|
---|
| 222 | 'type' => "flag",
|
---|
| 223 | 'reqd' => "no",
|
---|
| 224 | 'hiddengli' => "yes" },
|
---|
| 225 | { 'name' => "xml",
|
---|
| 226 | 'desc' => "{scripts.xml}",
|
---|
| 227 | 'type' => "flag",
|
---|
| 228 | 'reqd' => "no",
|
---|
[14247] | 229 | 'hiddengli' => "yes" },
|
---|
[14028] | 230 | ];
|
---|
| 231 |
|
---|
| 232 | my $options = { 'name' => "buildcol.pl",
|
---|
| 233 | 'desc' => "{buildcol.desc}",
|
---|
| 234 | 'args' => $arguments };
|
---|
| 235 |
|
---|
| 236 |
|
---|
| 237 | # globals
|
---|
| 238 | my $collection;
|
---|
| 239 | my $configfilename;
|
---|
| 240 | my $out;
|
---|
| 241 |
|
---|
| 242 | # used to signify "gs2"(default) or "gs3"
|
---|
| 243 | my $gs_mode = "gs2";
|
---|
| 244 |
|
---|
| 245 | ## @method gsprintf()
|
---|
| 246 | # Print a string to the screen after looking it up from a locale dependant
|
---|
| 247 | # strings file. This function is losely based on the idea of resource
|
---|
| 248 | # bundles as used in Java.
|
---|
| 249 | #
|
---|
| 250 | # @param $error The STDERR stream.
|
---|
| 251 | # @param $text The string containing GS keys that should be replaced with
|
---|
| 252 | # their locale dependant equivilents.
|
---|
| 253 | # @param $out The output stream.
|
---|
| 254 | # @return The locale-based string to output.
|
---|
| 255 | #
|
---|
| 256 | sub gsprintf()
|
---|
| 257 | {
|
---|
| 258 | return &gsprintf::gsprintf(@_);
|
---|
| 259 | }
|
---|
| 260 | ## gsprintf() ##
|
---|
| 261 |
|
---|
| 262 | &main();
|
---|
| 263 |
|
---|
| 264 | ## @method main()
|
---|
| 265 | #
|
---|
| 266 | # [Parses up and validates the arguments to the build process before creating
|
---|
| 267 | # the appropriate build process to do the actual work - John]
|
---|
| 268 | #
|
---|
| 269 | # @note Added true incremental support - John Thompson, DL Consulting Ltd.
|
---|
| 270 | # @note There were several bugs regarding using directories other than
|
---|
| 271 | # "import" or "archives" during import and build quashed. - John
|
---|
| 272 | # Thompson, DL Consulting Ltd.
|
---|
| 273 | #
|
---|
[16259] | 274 | # @param $incremental If true indicates this build should not regenerate all
|
---|
[14028] | 275 | # the index and metadata files, and should instead just
|
---|
| 276 | # append the information found in the archives directory
|
---|
| 277 | # to the existing files. If this requires some complex
|
---|
| 278 | # work so as to correctly insert into a classifier so be
|
---|
| 279 | # it. Of course none of this is done here - instead the
|
---|
| 280 | # incremental argument is passed to the document
|
---|
| 281 | # processor.
|
---|
| 282 | #
|
---|
| 283 | sub main
|
---|
| 284 | {
|
---|
| 285 | # command line args
|
---|
[14925] | 286 | my ($verbosity, $archivedir, $cachedir, $builddir, $site, $maxdocs,
|
---|
[20571] | 287 | $debug, $mode, $indexname, $removeold, $keepold,
|
---|
| 288 | $incremental, $incremental_mode,
|
---|
[14028] | 289 | $remove_empty_classifications,
|
---|
[17570] | 290 | $collectdir, $build, $type, $textindex,
|
---|
[14028] | 291 | $no_strip_html, $no_text, $faillog, $gli, $index, $language,
|
---|
[21786] | 292 | $sections_index_document_metadata, $maxnumeric);
|
---|
[14028] | 293 |
|
---|
| 294 | my $xml = 0;
|
---|
| 295 | my $hashParsingResult = {};
|
---|
| 296 | # general options available to all plugins
|
---|
| 297 | my $intArgLeftinAfterParsing = parse2::parse(\@ARGV,$arguments,$hashParsingResult,"allow_extra_options");
|
---|
| 298 |
|
---|
| 299 | # If parse returns -1 then something has gone wrong
|
---|
| 300 | if ($intArgLeftinAfterParsing == -1)
|
---|
| 301 | {
|
---|
| 302 | &PrintUsage::print_txt_usage($options, "{buildcol.params}");
|
---|
| 303 | die "\n";
|
---|
| 304 | }
|
---|
| 305 |
|
---|
| 306 | foreach my $strVariable (keys %$hashParsingResult)
|
---|
| 307 | {
|
---|
| 308 | eval "\$$strVariable = \$hashParsingResult->{\"\$strVariable\"}";
|
---|
| 309 | }
|
---|
| 310 |
|
---|
| 311 | # If $language has been specified, load the appropriate resource bundle
|
---|
| 312 | # (Otherwise, the default resource bundle will be loaded automatically)
|
---|
| 313 | if ($language && $language =~ /\S/) {
|
---|
| 314 | &gsprintf::load_language_specific_resource_bundle($language);
|
---|
| 315 | }
|
---|
| 316 |
|
---|
| 317 | if ($xml) {
|
---|
| 318 | &PrintUsage::print_xml_usage($options);
|
---|
| 319 | print "\n";
|
---|
| 320 | return;
|
---|
| 321 | }
|
---|
| 322 |
|
---|
| 323 | if ($gli) { # the gli wants strings to be in UTF-8
|
---|
| 324 | &gsprintf::output_strings_in_UTF8;
|
---|
| 325 | }
|
---|
| 326 |
|
---|
| 327 | # now check that we had exactly one leftover arg, which should be
|
---|
| 328 | # the collection name. We don't want to do this earlier, cos
|
---|
| 329 | # -xml arg doesn't need a collection name
|
---|
| 330 | # Or if the user specified -h, then we output the usage also
|
---|
| 331 | if ($intArgLeftinAfterParsing != 1 || (@ARGV && $ARGV[0] =~ /^\-+h/))
|
---|
| 332 | {
|
---|
| 333 | &PrintUsage::print_txt_usage($options, "{buildcol.params}");
|
---|
| 334 | die "\n";
|
---|
| 335 | }
|
---|
| 336 |
|
---|
| 337 | $textindex = "";
|
---|
| 338 | my $close_out = 0;
|
---|
| 339 | if ($out !~ /^(STDERR|STDOUT)$/i) {
|
---|
| 340 | open (OUT, ">$out") ||
|
---|
| 341 | (&gsprintf(STDERR, "{common.cannot_open_output_file}\n", $out) && die);
|
---|
| 342 | $out = "buildcol::OUT";
|
---|
| 343 | $close_out = 1;
|
---|
| 344 | }
|
---|
| 345 | $out->autoflush(1);
|
---|
| 346 |
|
---|
| 347 | # get and check the collection
|
---|
[14925] | 348 | if (($collection = &colcfg::use_collection($site, @ARGV, $collectdir)) eq "") {
|
---|
[14028] | 349 | &PrintUsage::print_txt_usage($options, "{buildcol.params}");
|
---|
| 350 | die "\n";
|
---|
| 351 | }
|
---|
| 352 |
|
---|
| 353 | if ($faillog eq "") {
|
---|
| 354 | $faillog = &util::filename_cat($ENV{'GSDLCOLLECTDIR'}, "etc", "fail.log");
|
---|
| 355 | }
|
---|
| 356 | # note that we're appending to the faillog here (import.pl clears it each time)
|
---|
| 357 | # this could potentially create a situation where the faillog keeps being added
|
---|
| 358 | # to over multiple builds (if the import process is being skipped)
|
---|
| 359 | open (FAILLOG, ">>$faillog") ||
|
---|
| 360 | (&gsprintf(STDERR, "{common.cannot_open_fail_log}\n", $faillog) && die);
|
---|
| 361 | $faillog = 'buildcol::FAILLOG';
|
---|
| 362 | $faillog->autoflush(1);
|
---|
| 363 |
|
---|
| 364 | unshift (@INC, "$ENV{'GSDLCOLLECTDIR'}/perllib");
|
---|
| 365 | # Don't know why this didn't already happen, but now collection specific
|
---|
| 366 | # classify and plugins directory also added to include path
|
---|
| 367 | unshift (@INC, "$ENV{'GSDLCOLLECTDIR'}/perllib/classify");
|
---|
| 368 | unshift (@INC, "$ENV{'GSDLCOLLECTDIR'}/perllib/plugins");
|
---|
| 369 |
|
---|
[14247] | 370 | # Read in the collection configuration file.
|
---|
[24463] | 371 | my ($collectcfg, $buildtype, $orthogonalbuildtypes);
|
---|
[14247] | 372 | ($configfilename, $gs_mode) = &colcfg::get_collect_cfg_name($out);
|
---|
[20098] | 373 | $collectcfg = &colcfg::read_collection_cfg ($configfilename, $gs_mode);
|
---|
[21613] | 374 |
|
---|
| 375 | # If the infodbtype value wasn't defined in the collect.cfg file, use the default
|
---|
| 376 | if (!defined($collectcfg->{'infodbtype'}))
|
---|
| 377 | {
|
---|
| 378 | $collectcfg->{'infodbtype'} = &dbutil::get_default_infodb_type();
|
---|
| 379 | }
|
---|
[14247] | 380 |
|
---|
[14028] | 381 | if ($verbosity !~ /\d+/) {
|
---|
| 382 | if (defined $collectcfg->{'verbosity'} && $collectcfg->{'verbosity'} =~ /\d+/) {
|
---|
| 383 | $verbosity = $collectcfg->{'verbosity'};
|
---|
| 384 | } else {
|
---|
| 385 | $verbosity = 2; # the default
|
---|
| 386 | }
|
---|
| 387 | }
|
---|
| 388 | # we use searchtype for determining buildtype, but for old versions, use buildtype
|
---|
| 389 | if (defined $collectcfg->{'buildtype'}) {
|
---|
| 390 | $buildtype = $collectcfg->{'buildtype'};
|
---|
| 391 | } elsif (defined $collectcfg->{'searchtypes'} || defined $collectcfg->{'searchtype'}) {
|
---|
| 392 | $buildtype = "mgpp";
|
---|
| 393 | } else {
|
---|
| 394 | $buildtype = "mg"; #mg is the default
|
---|
| 395 | }
|
---|
[24463] | 396 |
|
---|
| 397 | if (defined $collectcfg->{'orthogonalbuildtypes'}) {
|
---|
| 398 | $orthogonalbuildtypes = $collectcfg->{'orthogonalbuildtypes'};
|
---|
| 399 | }
|
---|
| 400 |
|
---|
[14028] | 401 | if (defined $collectcfg->{'archivedir'} && $archivedir eq "") {
|
---|
| 402 | $archivedir = $collectcfg->{'archivedir'};
|
---|
| 403 | }
|
---|
| 404 | if (defined $collectcfg->{'cachedir'} && $cachedir eq "") {
|
---|
| 405 | $cachedir = $collectcfg->{'cachedir'};
|
---|
| 406 | }
|
---|
| 407 | if (defined $collectcfg->{'builddir'} && $builddir eq "") {
|
---|
| 408 | $builddir = $collectcfg->{'builddir'};
|
---|
| 409 | }
|
---|
| 410 | if ($maxdocs !~ /\-?\d+/) {
|
---|
| 411 | if (defined $collectcfg->{'maxdocs'} && $collectcfg->{'maxdocs'} =~ /\-?\d+/) {
|
---|
| 412 | $maxdocs = $collectcfg->{'maxdocs'};
|
---|
| 413 | } else {
|
---|
| 414 | $maxdocs = -1; # the default
|
---|
| 415 | }
|
---|
| 416 | }
|
---|
| 417 | if (defined $collectcfg->{'maxnumeric'} && $collectcfg->{'maxnumeric'} =~ /\d+/) {
|
---|
| 418 | $maxnumeric = $collectcfg->{'maxnumeric'};
|
---|
| 419 | }
|
---|
| 420 |
|
---|
| 421 | if ($maxnumeric < 4 || $maxnumeric > 512) {
|
---|
| 422 | $maxnumeric = 4;
|
---|
| 423 | }
|
---|
| 424 |
|
---|
| 425 | if (defined $collectcfg->{'debug'} && $collectcfg->{'debug'} =~ /^true$/i) {
|
---|
| 426 | $debug = 1;
|
---|
| 427 | }
|
---|
| 428 | if ($mode !~ /^(all|compress_text|build_index|infodb)$/) {
|
---|
| 429 | if (defined $collectcfg->{'mode'} && $collectcfg->{'mode'} =~ /^(all|compress_text|build_index|infodb)$/) {
|
---|
| 430 | $mode = $collectcfg->{'mode'};
|
---|
| 431 | } else {
|
---|
| 432 | $mode = "all"; # the default
|
---|
| 433 | }
|
---|
| 434 | }
|
---|
| 435 | if (defined $collectcfg->{'index'} && $indexname eq "") {
|
---|
| 436 | $indexname = $collectcfg->{'index'};
|
---|
| 437 | }
|
---|
| 438 | if (defined $collectcfg->{'no_text'} && $no_text == 0) {
|
---|
| 439 | if ($collectcfg->{'no_text'} =~ /^true$/i) {
|
---|
| 440 | $no_text = 1;
|
---|
| 441 | }
|
---|
| 442 | }
|
---|
| 443 | if (defined $collectcfg->{'no_strip_html'} && $no_strip_html == 0) {
|
---|
| 444 | if ($collectcfg->{'no_strip_html'} =~ /^true$/i) {
|
---|
| 445 | $no_strip_html = 1;
|
---|
| 446 | }
|
---|
| 447 | }
|
---|
| 448 | if (defined $collectcfg->{'remove_empty_classifications'} && $remove_empty_classifications == 0) {
|
---|
| 449 | if ($collectcfg->{'remove_empty_classifications'} =~ /^true$/i) {
|
---|
| 450 | $remove_empty_classifications = 1;
|
---|
| 451 | }
|
---|
[14247] | 452 | }
|
---|
[14028] | 453 |
|
---|
| 454 | if ($buildtype eq "mgpp" && defined $collectcfg->{'textcompress'}) {
|
---|
| 455 | $textindex = $collectcfg->{'textcompress'};
|
---|
| 456 | }
|
---|
| 457 | if (defined $collectcfg->{'gli'} && $collectcfg->{'gli'} =~ /^true$/i) {
|
---|
| 458 | $gli = 1;
|
---|
| 459 | }
|
---|
| 460 |
|
---|
| 461 | if ($sections_index_document_metadata !~ /\S/ && defined $collectcfg->{'sections_index_document_metadata'}) {
|
---|
| 462 | $sections_index_document_metadata = $collectcfg->{'sections_index_document_metadata'};
|
---|
| 463 | }
|
---|
| 464 |
|
---|
| 465 | if ($sections_index_document_metadata !~ /^(never|always|unless_section_metadata_exists)$/) {
|
---|
| 466 | $sections_index_document_metadata = "never";
|
---|
| 467 | }
|
---|
| 468 |
|
---|
[20571] | 469 | ($removeold, $keepold, $incremental, $incremental_mode)
|
---|
| 470 | = &scriptutil::check_removeold_and_keepold($removeold, $keepold,
|
---|
| 471 | $incremental, "building",
|
---|
| 472 | $collectcfg);
|
---|
[14028] | 473 |
|
---|
| 474 | $gli = 0 unless defined $gli;
|
---|
[14247] | 475 |
|
---|
[14028] | 476 | # New argument to track whether build is incremental
|
---|
| 477 | $incremental = 0 unless defined $incremental;
|
---|
| 478 |
|
---|
| 479 | print STDERR "<Build>\n" if $gli;
|
---|
| 480 |
|
---|
| 481 | #set the text index
|
---|
| 482 | if (($buildtype eq "mgpp") || ($buildtype eq "lucene")) {
|
---|
| 483 | if ($textindex eq "") {
|
---|
| 484 | $textindex = "text";
|
---|
| 485 | }
|
---|
| 486 | }
|
---|
| 487 | else {
|
---|
| 488 | $textindex = "section:text";
|
---|
| 489 | }
|
---|
| 490 |
|
---|
| 491 | # fill in the default archives and building directories if none
|
---|
| 492 | # were supplied, turn all \ into / and remove trailing /
|
---|
| 493 |
|
---|
| 494 | my ($realarchivedir, $realbuilddir);
|
---|
| 495 | # Modified so that the archivedir, if provided as an argument, is made
|
---|
| 496 | # absolute if it isn't already
|
---|
| 497 | if ($archivedir eq "")
|
---|
| 498 | {
|
---|
| 499 | $archivedir = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "archives");
|
---|
| 500 | }
|
---|
| 501 | else
|
---|
| 502 | {
|
---|
[17571] | 503 | $archivedir = &util::make_absolute($ENV{'GSDLCOLLECTDIR'}, $archivedir);
|
---|
[14028] | 504 | }
|
---|
| 505 | # End Mod
|
---|
| 506 | $archivedir =~ s/[\\\/]+/\//g;
|
---|
| 507 | $archivedir =~ s/\/$//;
|
---|
[17585] | 508 |
|
---|
| 509 | if ($builddir eq "") {
|
---|
| 510 | $builddir = &util::filename_cat ($ENV{'GSDLCOLLECTDIR'}, "building");
|
---|
| 511 | if ($incremental) {
|
---|
| 512 | &gsprintf($out, "{buildcol.incremental_default_builddir}\n");
|
---|
| 513 | }
|
---|
| 514 | }
|
---|
[14028] | 515 | $builddir =~ s/[\\\/]+/\//g;
|
---|
| 516 | $builddir =~ s/\/$//;
|
---|
| 517 |
|
---|
| 518 | # update the archive cache if needed
|
---|
| 519 | if ($cachedir) {
|
---|
| 520 | &gsprintf($out, "{buildcol.updating_archive_cache}\n")
|
---|
| 521 | if ($verbosity >= 1);
|
---|
| 522 |
|
---|
| 523 | $cachedir =~ s/[\\\/]+$//;
|
---|
| 524 | $cachedir .= "/collect/$collection" unless
|
---|
| 525 | $cachedir =~ /collect\/$collection/;
|
---|
| 526 |
|
---|
| 527 | $realarchivedir = "$cachedir/archives";
|
---|
| 528 | $realbuilddir = "$cachedir/building";
|
---|
| 529 | &util::mk_all_dir ($realarchivedir);
|
---|
| 530 | &util::mk_all_dir ($realbuilddir);
|
---|
| 531 | &util::cachedir ($archivedir, $realarchivedir, $verbosity);
|
---|
| 532 |
|
---|
| 533 | } else {
|
---|
| 534 | $realarchivedir = $archivedir;
|
---|
| 535 | $realbuilddir = $builddir;
|
---|
| 536 | }
|
---|
| 537 |
|
---|
| 538 | # build it in realbuilddir
|
---|
| 539 | &util::mk_all_dir ($realbuilddir);
|
---|
| 540 |
|
---|
| 541 | my ($buildertype, $builderdir, $builder);
|
---|
| 542 | # if a builder class has been created for this collection, use it
|
---|
| 543 | # otherwise, use the mg or mgpp builder
|
---|
[14247] | 544 | if (-e "$ENV{'GSDLCOLLECTDIR'}/custom/${collection}/perllib/custombuilder.pm") {
|
---|
| 545 | $builderdir = "$ENV{'GSDLCOLLECTDIR'}/custom/${collection}/perllib";
|
---|
| 546 | $buildertype = "custombuilder";
|
---|
| 547 | } elsif (-e "$ENV{'GSDLCOLLECTDIR'}/perllib/custombuilder.pm") {
|
---|
[14028] | 548 | $builderdir = "$ENV{'GSDLCOLLECTDIR'}/perllib";
|
---|
[14247] | 549 | $buildertype = "custombuilder";
|
---|
| 550 | } elsif (-e "$ENV{'GSDLCOLLECTDIR'}/perllib/${collection}builder.pm") {
|
---|
| 551 | $builderdir = "$ENV{'GSDLCOLLECTDIR'}/perllib";
|
---|
[14028] | 552 | $buildertype = "${collection}builder";
|
---|
[24343] | 553 | } else {
|
---|
| 554 |
|
---|
[24459] | 555 | $builderdir = undef;
|
---|
| 556 | if ($buildtype ne "") {
|
---|
| 557 | # caters for extension-based build types, such as 'solr'
|
---|
| 558 | $buildertype = $buildtype."builder";
|
---|
[14028] | 559 | }
|
---|
[24459] | 560 | else {
|
---|
| 561 | # Default to mgpp
|
---|
[14028] | 562 | $buildertype = "mgppbuilder";
|
---|
| 563 | }
|
---|
| 564 | }
|
---|
[24343] | 565 | # check for extension specific builders
|
---|
| 566 | # (that will then be run after main builder.pm
|
---|
| 567 |
|
---|
| 568 | my @builderdir_list = ($builderdir);
|
---|
| 569 | my @buildertype_list = ($buildertype);
|
---|
| 570 |
|
---|
[24463] | 571 | if (defined $orthogonalbuildtypes) {
|
---|
| 572 | foreach my $obt (@$orthogonalbuildtypes) {
|
---|
[14028] | 573 |
|
---|
[24463] | 574 | push(@builderdir_list,undef); # rely on @INC to find it
|
---|
| 575 | push(@buildertype_list,$obt."Builder");
|
---|
[24343] | 576 | }
|
---|
| 577 | }
|
---|
[14028] | 578 |
|
---|
[24343] | 579 | # Set up array of the main builder.pm, followed by any ones
|
---|
| 580 | # from the extension folders
|
---|
[14028] | 581 |
|
---|
[24343] | 582 | my $num_builders = scalar(@buildertype_list);
|
---|
| 583 | my @builders = ();
|
---|
| 584 |
|
---|
| 585 |
|
---|
| 586 | for (my $i=0; $i<$num_builders; $i++) {
|
---|
| 587 | my $this_builder;
|
---|
| 588 | my $this_buildertype = $buildertype_list[$i];
|
---|
| 589 | my $this_builderdir = $builderdir_list[$i];
|
---|
| 590 |
|
---|
[24459] | 591 | if ((defined $this_builderdir) && ($this_builderdir ne "")) {
|
---|
| 592 | require "$this_builderdir/$this_buildertype.pm";
|
---|
| 593 | }
|
---|
| 594 | else {
|
---|
| 595 | require "$this_buildertype.pm";
|
---|
| 596 | }
|
---|
[24343] | 597 |
|
---|
| 598 | eval("\$this_builder = new $this_buildertype(\$collection, " .
|
---|
| 599 | "\$realarchivedir, \$realbuilddir, \$verbosity, " .
|
---|
| 600 | "\$maxdocs, \$debug, \$keepold, \$incremental, \$incremental_mode, " .
|
---|
| 601 | "\$remove_empty_classifications, " .
|
---|
| 602 | "\$out, \$no_text, \$faillog, \$gli)");
|
---|
| 603 | die "$@" if $@;
|
---|
| 604 |
|
---|
| 605 | push(@builders,$this_builder);
|
---|
[14028] | 606 | }
|
---|
[24343] | 607 |
|
---|
| 608 | # Init phase for builders
|
---|
| 609 | for (my $i=0; $i<$num_builders; $i++) {
|
---|
| 610 | my $this_buildertype = $buildertype_list[$i];
|
---|
| 611 | my $this_builderdir = $builderdir_list[$i];
|
---|
| 612 | my $this_builder = $builders[$i];
|
---|
| 613 |
|
---|
| 614 | $this_builder->init();
|
---|
| 615 | $this_builder->set_maxnumeric($maxnumeric);
|
---|
| 616 |
|
---|
| 617 | if (($this_buildertype eq "mgppbuilder") && $no_strip_html) {
|
---|
| 618 | $this_builder->set_strip_html(0);
|
---|
| 619 | }
|
---|
| 620 | if ($sections_index_document_metadata ne "never") {
|
---|
| 621 | $this_builder->set_sections_index_document_metadata($sections_index_document_metadata);
|
---|
| 622 | }
|
---|
[14028] | 623 | }
|
---|
| 624 |
|
---|
[24343] | 625 | # Run the requested passes
|
---|
| 626 |
|
---|
[14028] | 627 | if ($mode =~ /^all$/i) {
|
---|
[24343] | 628 |
|
---|
| 629 | # 'map' modifies the elements of the original array, so calling
|
---|
| 630 | # methods -- as done below -- will cause (by default) @builders
|
---|
| 631 | # to be changed to whatever these functions return (which is *not*
|
---|
| 632 | # what we want -- we want to leave the values unchanged)
|
---|
| 633 | # => Use 'local' (dynamic scoping) to give each 'map' call its
|
---|
| 634 | # own local copy This could also be done with:
|
---|
| 635 | # (my $new =$_)->method(); $new
|
---|
| 636 | # but is a bit more cumbersome to write
|
---|
[24459] | 637 |
|
---|
[24343] | 638 | map { local $_=$_; $_->compress_text($textindex); } @builders;
|
---|
| 639 | map { local $_=$_; $_->build_indexes($indexname); } @builders;
|
---|
| 640 | map { local $_=$_; $_->make_infodatabase(); } @builders;
|
---|
| 641 | map { local $_=$_; $_->collect_specific(); } @builders;
|
---|
[14028] | 642 | } elsif ($mode =~ /^compress_text$/i) {
|
---|
[24343] | 643 | map { local $_=$_; $_->compress_text($textindex); } @builders;
|
---|
[14028] | 644 | } elsif ($mode =~ /^build_index$/i) {
|
---|
[24343] | 645 | map { local $_=$_; $_->build_indexes($indexname); } @builders;
|
---|
[14028] | 646 | } elsif ($mode =~ /^infodb$/i) {
|
---|
[24343] | 647 | map { local $_=$_; $_->make_infodatabase(); } @builders;
|
---|
[14028] | 648 | } else {
|
---|
| 649 | (&gsprintf(STDERR, "{buildcol.unknown_mode}\n", $mode) && die);
|
---|
| 650 | }
|
---|
| 651 |
|
---|
[24343] | 652 | if (!$debug) {
|
---|
| 653 | map {local $_=$_; $_->make_auxiliary_files(); } @builders;
|
---|
| 654 | }
|
---|
| 655 | map {local $_=$_; $_->deinit(); } @builders;
|
---|
[14028] | 656 |
|
---|
| 657 | if (($realbuilddir ne $builddir) && !$debug) {
|
---|
| 658 | &gsprintf($out, "{buildcol.copying_back_cached_build}\n")
|
---|
| 659 | if ($verbosity >= 1);
|
---|
| 660 | &util::rm_r ($builddir);
|
---|
| 661 | &util::cp_r ($realbuilddir, $builddir);
|
---|
| 662 | }
|
---|
| 663 |
|
---|
| 664 | close OUT if $close_out;
|
---|
| 665 | close FAILLOG;
|
---|
| 666 |
|
---|
| 667 | print STDERR "</Build>\n" if $gli;
|
---|
| 668 | }
|
---|
| 669 |
|
---|
| 670 |
|
---|
[24343] | 671 |
|
---|