2006-06-25 23:07:36 +00:00
|
|
|
<?php
|
2007-07-09 21:12:16 +00:00
|
|
|
/**
|
|
|
|
|
* Global Search Engine for Moodle
|
2008-03-31 22:21:42 +00:00
|
|
|
*
|
|
|
|
|
* @package search
|
|
|
|
|
* @category core
|
|
|
|
|
* @subpackage search_engine
|
|
|
|
|
* @author Michael Champanis (mchampan) [cynnical@gmail.com], Valery Fremaux [valery.fremaux@club-internet.fr] > 1.8
|
|
|
|
|
* @date 2008/03/31
|
|
|
|
|
* @license http://www.gnu.org/copyleft/gpl.html GNU Public License
|
2007-07-09 21:12:16 +00:00
|
|
|
*
|
|
|
|
|
* The indexer logic -
|
|
|
|
|
*
|
|
|
|
|
* Look through each installed module's or block's search document class file (/search/documents)
|
|
|
|
|
* for necessary search functions, and if they're present add the content to the index.
|
|
|
|
|
* Repeat this for blocks.
|
|
|
|
|
*
|
|
|
|
|
* Because the iterator/retrieval functions are now stored in /search/documents/<mod>_document.php,
|
|
|
|
|
* /mod/mod/lib.php doesn't have to be modified - and thus the search module becomes quite
|
|
|
|
|
* self-sufficient. URL's are now stored in the index, stopping us from needing to require
|
|
|
|
|
* the class files to generate a results page.
|
|
|
|
|
*
|
|
|
|
|
* Along with the index data, each document's summary gets stored in the database
|
|
|
|
|
* and synchronised to the index (flat file) via the primary key ('id') which is mapped
|
|
|
|
|
* to the 'dbid' field in the index
|
|
|
|
|
* */
|
|
|
|
|
|
|
|
|
|
//this'll take some time, set up the environment
|
|
|
|
|
@set_time_limit(0);
|
|
|
|
|
@ob_implicit_flush(true);
|
|
|
|
|
@ob_end_flush();
|
|
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
/**
|
|
|
|
|
* includes and requires
|
|
|
|
|
*/
|
2007-07-09 21:12:16 +00:00
|
|
|
require_once('../config.php');
|
|
|
|
|
require_once("$CFG->dirroot/search/lib.php");
|
2008-05-25 10:08:05 +00:00
|
|
|
//require_once("debugging.php");
|
|
|
|
|
|
|
|
|
|
$separator = (array_key_exists('WINDIR', $_SERVER)) ? ';' : ':' ;
|
|
|
|
|
ini_set('include_path', $CFG->dirroot.'\search'.$separator.ini_get('include_path'));
|
2007-07-09 21:12:16 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
/// only administrators can index the moodle installation, because access to all pages is required
|
2006-09-20 21:00:45 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
require_login();
|
|
|
|
|
|
|
|
|
|
if (empty($CFG->enableglobalsearch)) {
|
|
|
|
|
error(get_string('globalsearchdisabled', 'search'));
|
|
|
|
|
}
|
|
|
|
|
|
2008-05-25 10:08:05 +00:00
|
|
|
if (!has_capability('moodle/site:doanything', get_context_instance(CONTEXT_SYSTEM))) {
|
2008-03-31 22:21:42 +00:00
|
|
|
error(get_string('beadmin', 'search'), "$CFG->wwwroot/login/index.php");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// confirmation flag to prevent accidental reindexing (indexersplash.php is the correct entry point)
|
2006-09-20 21:00:45 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
$sure = strtolower(optional_param('areyousure', '', PARAM_ALPHA));
|
|
|
|
|
|
|
|
|
|
if ($sure != 'yes') {
|
|
|
|
|
mtrace("<pre>Sorry, you need to confirm indexing via <a href='indexersplash.php'>indexersplash.php</a>"
|
|
|
|
|
.". (<a href='index.php'>Back to query page</a>).</pre>");
|
|
|
|
|
|
|
|
|
|
exit(0);
|
|
|
|
|
}
|
|
|
|
|
|
2008-05-25 10:08:05 +00:00
|
|
|
/// check for php5 (lib.php)
|
|
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
//php5 found, continue including php5-only files
|
|
|
|
|
//require_once("$CFG->dirroot/search/Zend/Search/Lucene.php");
|
|
|
|
|
require_once("$CFG->dirroot/search/indexlib.php");
|
|
|
|
|
|
|
|
|
|
mtrace('<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8" /></head><body>');
|
|
|
|
|
mtrace('<pre>Server Time: '.date('r',time())."\n");
|
|
|
|
|
|
|
|
|
|
if (isset($CFG->search_indexer_busy) && $CFG->search_indexer_busy == '1') {
|
|
|
|
|
//means indexing was not finished previously
|
|
|
|
|
mtrace("Warning: Indexing was not successfully completed last time, restarting.\n");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/// turn on busy flag
|
2006-09-20 21:00:45 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
set_config('search_indexer_busy', '1');
|
|
|
|
|
|
|
|
|
|
//paths
|
|
|
|
|
$index_path = SEARCH_INDEX_PATH;
|
|
|
|
|
$index_db_file = "{$CFG->dirroot}/search/db/$CFG->dbtype.sql";
|
|
|
|
|
$dbcontrol = new IndexDBControl();
|
|
|
|
|
|
|
|
|
|
/// setup directory in data root
|
|
|
|
|
|
|
|
|
|
if (!file_exists($index_path)) {
|
|
|
|
|
mtrace("Data directory ($index_path) does not exist, attempting to create.");
|
|
|
|
|
if (!mkdir($index_path)) {
|
|
|
|
|
search_pexit("Error creating data directory at: $index_path. Please correct.");
|
2008-05-25 10:08:05 +00:00
|
|
|
}
|
|
|
|
|
else {
|
2008-03-31 22:21:42 +00:00
|
|
|
mtrace("Directory successfully created.");
|
|
|
|
|
}
|
2008-05-25 10:08:05 +00:00
|
|
|
}
|
|
|
|
|
else {
|
2008-03-31 22:21:42 +00:00
|
|
|
mtrace("Using $index_path as data directory.");
|
|
|
|
|
}
|
|
|
|
|
|
2008-05-25 10:08:05 +00:00
|
|
|
Zend_Search_Lucene_Analysis_Analyzer::setDefault(new Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8());
|
2008-03-31 22:21:42 +00:00
|
|
|
$index = new Zend_Search_Lucene($index_path, true);
|
|
|
|
|
|
|
|
|
|
/// New regeneration
|
2006-07-25 17:23:10 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
mtrace('Deleting old index entries.');
|
|
|
|
|
delete_records(SEARCH_DATABASE_TABLE);
|
|
|
|
|
|
|
|
|
|
/// begin timer
|
2006-09-20 21:00:45 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
search_stopwatch();
|
|
|
|
|
mtrace("Starting activity modules\n");
|
|
|
|
|
|
|
|
|
|
//the presence of the required search functions -
|
|
|
|
|
// * mod_iterator
|
|
|
|
|
// * mod_get_content_for_index
|
|
|
|
|
//are the sole basis for including a module in the index at the moment.
|
2006-09-20 21:00:45 +00:00
|
|
|
|
2008-05-25 10:08:05 +00:00
|
|
|
$searchables = search_collect_searchables();
|
|
|
|
|
|
|
|
|
|
/// start indexation
|
2008-03-31 22:21:42 +00:00
|
|
|
|
|
|
|
|
if ($searchables){
|
|
|
|
|
foreach ($searchables as $mod) {
|
2008-05-25 10:08:05 +00:00
|
|
|
|
|
|
|
|
$key = 'search_in_'.$mod->name;
|
|
|
|
|
if (isset($CFG->$key) && !$CFG->$key) {
|
|
|
|
|
mtrace("module $key has been administratively disabled. Skipping...\n");
|
|
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if ($mod->location == 'internal'){
|
|
|
|
|
$class_file = $CFG->dirroot.'/search/documents/'.$mod->name.'_document.php';
|
|
|
|
|
} else {
|
|
|
|
|
$class_file = $CFG->dirroot.'/'.$mod->location.'/'.$mod->name.'/search_document.php';
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
if (!file_exists($class_file)){
|
|
|
|
|
if (defined("PATH_FOR_SEARCH_TYPE_{$mod->name}")){
|
|
|
|
|
eval("\$pluginpath = PATH_FOR_SEARCH_TYPE_{$mod->name}");
|
|
|
|
|
$class_file = "{$CFG->dirroot}/{$pluginpath}/searchlib.php";
|
|
|
|
|
} else {
|
|
|
|
|
mtrace ("No search document found for plugin {$mod->name}. Ignoring.");
|
|
|
|
|
continue;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
*/
|
2008-03-31 22:21:42 +00:00
|
|
|
|
|
|
|
|
if (file_exists($class_file)) {
|
|
|
|
|
include_once($class_file);
|
|
|
|
|
|
|
|
|
|
//build function names
|
|
|
|
|
$iter_function = $mod->name.'_iterator';
|
|
|
|
|
$index_function = $mod->name.'_get_content_for_index';
|
|
|
|
|
$counter = 0;
|
|
|
|
|
if (function_exists($index_function) && function_exists($iter_function)) {
|
|
|
|
|
mtrace("Processing module function $index_function ...");
|
|
|
|
|
$sources = $iter_function();
|
|
|
|
|
if ($sources){
|
|
|
|
|
foreach ($sources as $i) {
|
|
|
|
|
$documents = $index_function($i);
|
|
|
|
|
|
|
|
|
|
//begin transaction
|
|
|
|
|
if ($documents){
|
|
|
|
|
foreach($documents as $document) {
|
|
|
|
|
$counter++;
|
|
|
|
|
|
|
|
|
|
//object to insert into db
|
|
|
|
|
$dbid = $dbcontrol->addDocument($document);
|
|
|
|
|
|
|
|
|
|
//synchronise db with index
|
|
|
|
|
$document->addField(Zend_Search_Lucene_Field::Keyword('dbid', $dbid));
|
|
|
|
|
|
|
|
|
|
//add document to index
|
|
|
|
|
$index->addDocument($document);
|
|
|
|
|
|
|
|
|
|
//commit every x new documents, and print a status message
|
|
|
|
|
if (($counter % 2000) == 0) {
|
|
|
|
|
$index->commit();
|
|
|
|
|
mtrace(".. $counter");
|
|
|
|
|
}
|
|
|
|
|
}
|
2007-07-09 21:12:16 +00:00
|
|
|
}
|
2008-03-31 22:21:42 +00:00
|
|
|
//end transaction
|
2007-07-09 21:12:16 +00:00
|
|
|
}
|
|
|
|
|
}
|
2008-03-31 22:21:42 +00:00
|
|
|
|
|
|
|
|
//commit left over documents, and finish up
|
|
|
|
|
$index->commit();
|
|
|
|
|
|
|
|
|
|
mtrace("-- $counter documents indexed");
|
|
|
|
|
mtrace("done.\n");
|
2007-07-09 21:12:16 +00:00
|
|
|
}
|
2008-05-25 10:08:05 +00:00
|
|
|
} else {
|
|
|
|
|
mtrace ("No search document found for plugin {$mod->name}. Ignoring.");
|
2007-07-09 21:12:16 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
2008-03-31 22:21:42 +00:00
|
|
|
|
|
|
|
|
/// finished modules
|
|
|
|
|
|
|
|
|
|
mtrace('Finished activity modules');
|
|
|
|
|
search_stopwatch();
|
|
|
|
|
|
|
|
|
|
mtrace(".<br/><a href='index.php'>Back to query page</a>.");
|
|
|
|
|
mtrace('</pre>');
|
2007-07-09 21:12:16 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
/// finished, turn busy flag off
|
2007-07-09 21:12:16 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
set_config('search_indexer_busy', '0');
|
|
|
|
|
|
|
|
|
|
/// mark the time we last updated
|
2007-07-09 21:12:16 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
set_config('search_indexer_run_date', time());
|
|
|
|
|
|
|
|
|
|
/// and the index size
|
2007-07-09 21:12:16 +00:00
|
|
|
|
2008-03-31 22:21:42 +00:00
|
|
|
set_config('search_index_size', (int)$index->count());
|
2006-09-20 21:00:45 +00:00
|
|
|
|
2006-06-25 23:07:36 +00:00
|
|
|
?>
|
