"; - $FILE = fopen("filetrace.log", 'w'); - fwrite($FILE, $text); - fclose($FILE); - echo "
"; - */ - - if (!empty($CFG->block_search_limit_index_body)){ - $text = shorten_text($text, $CFG->block_search_limit_index_body); - } - return $text; -} -?> \ No newline at end of file diff --git a/search/documents/physical_html.php b/search/documents/physical_html.php deleted file mode 100644 index 9054776edd8..00000000000 --- a/search/documents/physical_html.php +++ /dev/null @@ -1,26 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version revised for Moodle 2.0 -* -* this is a format handler for getting text out of a standard html format -* so it can be indexed by Lucene search engine -*/ - -/** -* @param object $resource -*/ -function get_text_for_indexing_html(&$resource, $directfile = ''){ - - // wraps to htm handler - include_once 'physical_htm.php'; - return get_text_for_indexing_htm($resource, $directfile); -} -?> \ No newline at end of file diff --git a/search/documents/physical_odt.php b/search/documents/physical_odt.php deleted file mode 100644 index 289ed251964..00000000000 --- a/search/documents/physical_odt.php +++ /dev/null @@ -1,62 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version revised for Moodle 2.0 -* -* this is a format handler for getting text out of the opensource ODT binary format -* so it can be indexed by Lucene search engine -*/ - -/** -* OpenOffice Odt extractor -* @param object $resource -* @param string $directfile if the resource is given as a direct file path, use it as reference to the file -* @uses $CFG -*/ -function get_text_for_indexing_odt(&$resource, $directfile = ''){ - global $CFG; - - // SECURITY : do not allow non admin execute anything on system !! - if (!has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) return; - - // adds moodle root switch if none was defined - if (!isset($CFG->block_search_usemoodleroot)){ - set_config('block_search_usemoodleroot', 1); - } - - $moodleroot = ($CFG->block_search_usemoodleroot) ? "{$CFG->dirroot}/" : '' ; - - // just call pdftotext over stdout and capture the output - if (!empty($CFG->block_search_odt_to_text_cmd)){ - if (!file_exists("{$moodleroot}{$CFG->block_search_odt_to_text_cmd}")){ - mtrace('Error with OpenOffice ODT to text converter command : exectuable not found at '.$moodleroot.$CFG->block_search_odt_to_text_cmd); - } else { - if ($directfile == ''){ - $file = escapeshellarg("{$CFG->dataroot}/{$resource->course}/{$resource->reference}"); - } else { - $file = escapeshellarg("{$CFG->dataroot}/{$directfile}"); - } - $command = trim($CFG->block_search_odt_to_text_cmd); - $text_converter_cmd = "{$moodleroot}{$command} --encoding=UTF-8 $file"; - mtrace("Executing : $text_converter_cmd"); - $result = shell_exec($text_converter_cmd); - if ($result){ - return $result; - } else { - mtrace('Error with OpenOffice ODT to text converter command : execution failed. '); - return ''; - } - } - } else { - mtrace('Error with OpenOffice ODT to text converter command : command not set up. Execute once search block configuration.'); - return ''; - } -} -?> \ No newline at end of file diff --git a/search/documents/physical_pdf.php b/search/documents/physical_pdf.php deleted file mode 100644 index e6f7864a311..00000000000 --- a/search/documents/physical_pdf.php +++ /dev/null @@ -1,61 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version revised for Moodle 2.0 -* -* this is a format handler for getting text out of a proprietary binary format -* so it can be indexed by Lucene search engine -*/ - -/** -* @param object $resource -* @param string $directfile if the resource is given as a direct file path, use it as reference to the file -* @uses $CFG -*/ -function get_text_for_indexing_pdf(&$resource, $directfile = ''){ - global $CFG; - - // SECURITY : do not allow non admin execute anything on system !! - if (!has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) return; - - // adds moodle root switch if none was defined - if (!isset($CFG->block_search_usemoodleroot)){ - set_config('block_search_usemoodleroot', 1); - } - - $moodleroot = ($CFG->block_search_usemoodleroot) ? "{$CFG->dirroot}/" : '' ; - - // just call pdftotext over stdout and capture the output - if (!empty($CFG->block_search_pdf_to_text_cmd)){ - preg_match("/^\S+/", $CFG->block_search_pdf_to_text_cmd, $matches); - if (!file_exists("{$moodleroot}{$matches[0]}")){ - mtrace('Error with pdf to text converter command : executable not found at '.$moodleroot.$matches[0]); - } else { - if ($directfile == ''){ - $file = escapeshellarg("{$CFG->dataroot}/{$resource->course}/{$resource->reference}"); - } else { - $file = escapeshellarg("{$CFG->dataroot}/{$directfile}"); - } - $command = trim($CFG->block_search_pdf_to_text_cmd); - $text_converter_cmd = "{$moodleroot}{$command} $file -"; - $result = shell_exec($text_converter_cmd); - if ($result){ - return $result; - } else { - mtrace('Error with pdf to text converter command : execution failed for '.$text_converter_cmd.'. Check for execution permission on pdf converter executable.'); - return ''; - } - } - } else { - mtrace('Error with pdf to text converter command : command not set up. Execute once search block configuration.'); - return ''; - } -} -?> \ No newline at end of file diff --git a/search/documents/physical_ppt.php b/search/documents/physical_ppt.php deleted file mode 100644 index b91628a2f0c..00000000000 --- a/search/documents/physical_ppt.php +++ /dev/null @@ -1,96 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version revised for Moodle 2.0 -* -* this is a format handler for getting text out of a proprietary binary format -* so it can be indexed by Lucene search engine -*/ - -/* -* first implementation is a trivial heuristic based on ppt character stream : -* text sequence always starts with a 00 9F 0F 04 sequence followed by a 15 bytes -* sequence -* In this sequence is a A8 0F or A0 0F or AA 0F followed by a little-indian encoding of text buffer size -* A8 0F denotes for ASCII text (local system monobyte encoding) -* A0 0F denotes for UTF-16 encoding -* AA 0F are non textual sequences -* texts are either in ASCII or UTF-16 -* text ends on a new sequence start, or on a 00 00 NULL UTF-16 end of stream -* -* based on these following rules, here is a little empiric texte extractor for PPT -*/ - -/** -* @param object $resource -* @param string $directfile if the resource is given as a direct file path, use it as reference to the file -* @uses $CFG -*/ -function get_text_for_indexing_ppt(&$resource, $directfile = ''){ - global $CFG; - - $indextext = null; - - // SECURITY : do not allow non admin execute anything on system !! - if (!has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) return; - - if ($directfile == ''){ - $text = implode('', file("{$CFG->dataroot}/{$resource->course}/{$resource->reference}")); - } else { - $text = implode('', file("{$CFG->dataroot}/{$directfile}")); - } - - $remains = $text; - $fragments = array(); - while (preg_match('/\x00\x9F\x0F\x04.{9}(......)(.*)/s', $remains, $matches)){ - $unpacked = unpack("ncode/Llength", $matches[1]); - $sequencecode = $unpacked['code']; - $length = $unpacked['length']; - // print "length : ".$length." ; segment type : ".sprintf("%x", $sequencecode)."
"; - $followup = $matches[2]; - // local system encoding sequence - if ($sequencecode == 0xA80F){ - $aFragment = substr($followup, 0, $length); - $remains = substr($followup, $length); - $fragments[] = $aFragment; - } - // denotes unicode encoded sequence - elseif ($sequencecode == 0xA00F){ - $aFragment = substr($followup, 0, $length); - // $aFragment = mb_convert_encoding($aFragment, 'UTF-16', 'UTF-8'); - $aFragment = preg_replace('/\xA0\x00\x19\x20/s', "'", $aFragment); // some quotes - $aFragment = preg_replace('/\x00/s', "", $aFragment); - $remains = substr($followup, $length); - $fragments[] = $aFragment; - } - else{ - $remains = $followup; - } - } - $indextext = implode(' ', $fragments); - $indextext = preg_replace('/\x19\x20/', "'", $indextext); // some quotes - $indextext = preg_replace('/\x09/', '', $indextext); // some extra chars - $indextext = preg_replace('/\x0D/', "\n", $indextext); // some quotes - $indextext = preg_replace('/\x0A/', "\n", $indextext); // some quotes - $indextextprint = implode('
', $fragments); - - // debug code - // $logppt = fopen("C:/php5/logs/pptlog", "w"); - // fwrite($logppt, $indextext); - // fclose($logppt); - - if (!empty($CFG->block_search_limit_index_body)){ - $indextext = shorten_text($text, $CFG->block_search_limit_index_body); - } - - $indextext = mb_convert_encoding($indextext, 'UTF-8', 'auto'); - return $indextext; -} -?> \ No newline at end of file diff --git a/search/documents/physical_swf.php b/search/documents/physical_swf.php deleted file mode 100644 index 2e027b0ba21..00000000000 --- a/search/documents/physical_swf.php +++ /dev/null @@ -1,71 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version revised for Moodle 2.0 -* -* @note : The Adobe SWF Converters library is not GPL, although it can be of free use in some -* situations. This file is provided for convenience, but should use having a glance at -* {@link http://www.adobe.com/licensing/developer/} -* -* this is a format handler for getting text out of a proprietary binary format -* so it can be indexed by Lucene search engine -*/ - -/** -* @param object $resource -* @param string $directfile if the resource is given as a direct file path, use it as reference to the file -* @uses $CFG -*/ -function get_text_for_indexing_swf(&$resource, $directfile = ''){ - global $CFG; - - // SECURITY : do not allow non admin execute anything on system !! - if (!has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) return; - - // adds moodle root switch if none was defined - if (!isset($CFG->block_search_usemoodleroot)){ - set_config('block_search_usemoodleroot', 1); - } - - $moodleroot = ($CFG->block_search_usemoodleroot) ? "{$CFG->dirroot}/" : '' ; - - // just call pdftotext over stdout and capture the output - if (!empty($CFG->block_search_pdf_to_text_cmd)){ - $command = trim($CFG->block_search_swf_to_text_cmd); - if (!file_exists("{$moodleroot}{$command}")){ - mtrace('Error with swf to text converter command : executable not found as '.$moodleroot.$command); - } else { - if ($directfile == ''){ - $file = escapeshellarg("{$CFG->dataroot}/{$resource->course}/{$resource->reference}"); - } else { - $file = escapeshellarg("{$CFG->dataroot}/{$directfile}"); - } - $text_converter_cmd = "{$moodleroot}{$command} -t $file"; - $result = shell_exec($text_converter_cmd); - - // result is in html. We must strip it off - $result = preg_replace("/<[^>]*>/", '', $result); - $result = preg_replace("//", '', $result); - $result = html_entity_decode($result, ENT_COMPAT, 'UTF-8'); - $result = mb_convert_encoding($result, 'UTF-8', 'auto'); - - if ($result){ - return $result; - } else { - mtrace('Error with swf to text converter command : execution failed for '.$text_converter_cmd.'. Check for execution permission on swf converter executable.'); - return ''; - } - } - } else { - mtrace('Error with swf to text converter command : command not set up. Execute once search block configuration.'); - return ''; - } -} -?> \ No newline at end of file diff --git a/search/documents/physical_txt.php b/search/documents/physical_txt.php deleted file mode 100644 index 1f4d7857469..00000000000 --- a/search/documents/physical_txt.php +++ /dev/null @@ -1,40 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version revised for Moodle 2.0 -* -* this is a format handler for getting text out of a proprietary binary format -* so it can be indexed by Lucene search engine -*/ - -/** -* @param object $resource -* @param string $directfile if the resource is given as a direct file path, use it as reference to the file -* @uses $CFG -*/ -function get_text_for_indexing_txt(&$resource, $directfile = ''){ - global $CFG; - - // SECURITY : do not allow non admin execute anything on system !! - if (!has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) return; - - // just try to get text empirically from ppt binary flow - if ($directfile == ''){ - $text = implode('', file("{$CFG->dataroot}/{$resource->course}/{$resource->reference}")); - } else { - $text = implode('', file("{$CFG->dataroot}/{$directfile}")); - } - - if (!empty($CFG->block_search_limit_index_body)){ - $text = shorten_text($text, $CFG->block_search_limit_index_body); - } - return $text; -} -?> \ No newline at end of file diff --git a/search/documents/physical_xml.php b/search/documents/physical_xml.php deleted file mode 100644 index db4178275b5..00000000000 --- a/search/documents/physical_xml.php +++ /dev/null @@ -1,43 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version revised for Moodle 2.0 -* -* this is a format handler for getting text out of a proprietary binary format -* so it can be indexed by Lucene search engine -*/ - -/** -* @param object $resource -* @param string $directfile if the resource is given as a direct file path, use it as reference to the file -* @uses $CFG -*/ -function get_text_for_indexing_xml(&$resource, $directfile = ''){ - global $CFG; - - // SECURITY : do not allow non admin execute anything on system !! - if (!has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) return; - - // just get text - if ($directfile == ''){ - $text = implode('', file("{$CFG->dataroot}/{$resource->course}/{$resource->reference}")); - } else { - $text = implode('', file("{$CFG->dataroot}/{$directfile}")); - } - - // filter out all xml tags - $text = preg_replace("/<[^>]*>/", ' ', $text); - - if (!empty($CFG->block_search_limit_index_body)){ - $text = shorten_text($text, $CFG->block_search_limit_index_body); - } - return $text; -} -?> \ No newline at end of file diff --git a/search/documents/resource_document.php b/search/documents/resource_document.php deleted file mode 100644 index 529d76243e9..00000000000 --- a/search/documents/resource_document.php +++ /dev/null @@ -1,363 +0,0 @@ - 1.8 -* @contributor Tatsuva Shirai 20090530 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version Moodle 2.0 -* -* document handling for all resources -* This file contains the mapping between a resource and it's indexable counterpart, -* -* Functions for iterating and retrieving the necessary records are now also included -* in this file, rather than mod/resource/lib.php -*/ - -/** -* requires and includes -*/ -require_once($CFG->dirroot.'/search/documents/document.php'); -require_once($CFG->dirroot.'/mod/resource/lib.php'); - -/* * -* a class for representing searchable information -* -*/ -class ResourceSearchDocument extends SearchDocument { - public function __construct(&$resource, $context_id) { - // generic information; required - $doc->docid = $resource['trueid']; - $doc->documenttype = SEARCH_TYPE_RESOURCE; - $doc->itemtype = $resource['type']; - $doc->contextid = $context_id; - - $doc->title = strip_tags($resource['name']); - $doc->date = $resource['timemodified']; - $doc->author = ''; - $doc->contents = strip_tags($resource['summary']).' '.strip_tags($resource['alltext']); - $doc->url = resource_make_link($resource['id']); - - // module specific information; optional - $data = array(); - - // construct the parent class - parent::__construct($doc, $data, $resource['course'], 0, 0, 'mod/'.SEARCH_TYPE_RESOURCE); - } -} - -/** -* constructs valid access links to information -* @param resourceId the of the resource -* @return a full featured link element as a string -*/ -function resource_make_link($resource_id) { - global $CFG; - - return $CFG->wwwroot.'/mod/resource/view.php?id='.$resource_id; -} - -/** -* part of standard API -* -*/ -function resource_iterator() { - //trick to leave search indexer functionality intact, but allow - //this document to only use the below function to return info - //to be searched - return array(true); - } - -/** -* part of standard API -* this function does not need a content iterator, returns all the info -* itself; -* @param void $notneeded to comply API, remember to fake the iterator array though -* @uses $CFG, $DB -* @return an array of searchable documents -*/ -function resource_get_content_for_index(&$notneeded) { - global $CFG, $DB; - - - // starting with Moodle native resources - $documents = array(); - - $dbman = $DB->get_manager(); - if (!$dbman->table_exists('resource_old')) { - return $documents; - } - - // the resources have been moved into modules of their own. indexing need to be created for these. - // for a temporary fix (until MDL-24856 is fixed) pointing this query to a table that is copy of the old resource table schema. - $query = " - SELECT - id as trueid, - r.* - FROM - {resource_old} as r - WHERE - alltext != '' AND - alltext != ' ' AND - alltext != ' ' AND - type != 'file' - "; - if ($resources = $DB->get_records_sql($query)){ - foreach($resources as $aResource){ - $coursemodule = $DB->get_field('modules', 'id', array('name' => 'resource')); - $cm = $DB->get_record('course_modules', array('course' => $aResource->course, 'module' => $coursemodule, 'instance' => $aResource->id)); - $context = get_context_instance(CONTEXT_MODULE, $cm->id); - $aResource->id = $cm->id; - $documents[] = new ResourceSearchDocument(get_object_vars($aResource), $context->id); - mtrace("finished $aResource->name"); - } - } - - // special physical files handling - /** - * this sequence searches for a compatible physical stream handler for getting a text - * equivalence for the content. - * - */ - if (@$CFG->block_search_enable_file_indexing){ - $query = " - SELECT - r.id as trueid, - cm.id as id, - r.course as course, - r.name as name, - r.summary as summary, - r.alltext as alltext, - r.reference as reference, - r.type as type, - r.timemodified as timemodified - FROM - {resource_old} as r, - {course_modules} as cm, - {modules} as m - WHERE - r.type = 'file' AND - cm.instance = r.id AND - cm.course = r.course AND - cm.module = m.id AND - m.name = 'resource' - "; - if ($resources = $DB->get_records_sql($query)){ - // invokes external content extractor if exists. - foreach($resources as $aResource){ - // fetches a physical indexable document and adds it to documents passed by ref - $coursemodule = $DB->get_field('modules', 'id', array('name' => 'resource')); - $cm = $DB->get_record('course_modules', array('id' => $aResource->id)); - $context = get_context_instance(CONTEXT_MODULE, $cm->id); - resource_get_physical_file($aResource, $context->id, false, $documents); - } - } - } - return $documents; -} - -/** -* get text from a physical file -* @uses $CFG -* @param reference $resource a resource for which to fetch some representative text -* @param int $context_id the context associated with the resource -* @param bool $getsingle if true, returns a single search document, elsewhere return the array -* given as documents increased by one -* @param array $documents the array of documents, by ref, where to add the new document. -* @return a search document when unique or false. -*/ -function resource_get_physical_file(&$resource, $context_id, $getsingle, &$documents = null){ - global $CFG; - - // cannot index empty references - if (empty($resource->reference)){ - mtrace("Cannot index, empty reference."); - return false; - } - - // cannot index remote resources - if (resource_is_url($resource->reference)){ - mtrace("Cannot index remote URLs."); - return false; - } - - $fileparts = pathinfo($resource->reference); - // cannot index unknown or masked types - if (empty($fileparts['extension'])) { - mtrace("Cannot index without explicit extension."); - return false; - } - - // cannot index non existent file - $file = "{$CFG->dataroot}/{$resource->course}/{$resource->reference}"; - if (!file_exists($file)){ - mtrace("Missing resource file $file : will not be indexed."); - return false; - } - - $ext = strtolower($fileparts['extension']); - - // cannot index unallowed or unhandled types - if (!preg_match("/\b$ext\b/i", $CFG->block_search_filetypes)) { - mtrace($fileparts['extension'] . ' is not an allowed extension for indexing'); - return false; - } - if (file_exists($CFG->dirroot.'/search/documents/physical_'.$ext.'.php')){ - include_once($CFG->dirroot.'/search/documents/physical_'.$ext.'.php'); - $function_name = 'get_text_for_indexing_'.$ext; - $resource->alltext = $function_name($resource); - if (!empty($resource->alltext)){ - if ($getsingle){ - $single = new ResourceSearchDocument(get_object_vars($resource), $context_id); - mtrace("finished file $resource->name as {$resource->reference}"); - return $single; - } else { - $documents[] = new ResourceSearchDocument(get_object_vars($resource), $context_id); - } - mtrace("finished file $resource->name as {$resource->reference}"); - } - } else { - mtrace("fulltext handler not found for $ext type"); - } - return false; -} - -/** -* part of standard API. -* returns a single resource search document based on a resource_entry id -* @uses $CFG, $DB -* @param id the id of the accessible document -* @return a searchable object or null if failure -*/ -function resource_single_document($id, $itemtype) { - global $CFG, $DB; - - // rewriting with legacy moodle databse API - $query = " - SELECT - r.id as trueid, - cm.id as id, - r.course as course, - r.name as name, - r.summary as summary, - r.alltext as alltext, - r.reference as reference, - r.type as type, - r.timemodified as timemodified - FROM - {resource} as r, - {course_modules} as cm, - {modules} as m - WHERE - cm.instance = r.id AND - cm.course = r.course AND - cm.module = m.id AND - m.name = 'resource' AND - ((r.type != 'file' AND - r.alltext != '' AND - r.alltext != ' ' AND - r.alltext != ' ') OR - r.type = 'file') AND - r.id = '?' - "; - $resource = $DB->get_record_sql($query, array($id)); - - if ($resource){ - $coursemodule = $DB->get_field('modules', 'id', array('name' => 'resource')); - $cm = $DB->get_record('course_modules', array('id' => $resource->id)); - $context = get_context_instance(CONTEXT_MODULE, $cm->id); - if ($resource->type == 'file' && @$CFG->block_search_enable_file_indexing){ - $document = resource_get_physical_file($resource, true, $context->id); - if (!$document) mtrace("Warning : this document {$resource->name} will not be indexed"); - return $document; - } else { - return new ResourceSearchDocument(get_object_vars($resource), $context->id); - } - } - mtrace('null resource'); - return null; -} - -/** -* dummy delete function that aggregates id with itemtype. -* this was here for a reason, but I can't remember it at the moment. -* -*/ -function resource_delete($info, $itemtype) { - $object->id = $info; - $object->itemtype = $itemtype; - return $object; -} - -/** -* returns the var names needed to build a sql query for addition/deletions -* -*/ -function resource_db_names() { - //[primary id], [table name], [time created field name], [time modified field name], [additional where conditions for sql] - return array(array('id', 'resource_old', 'timemodified', 'timemodified', 'any', " (alltext != '' AND alltext != ' ' AND alltext != ' ' AND TYPE != 'file') OR TYPE = 'file' ")); -} - -/** -* this function handles the access policy to contents indexed as searchable documents. If this -* function does not exist, the search engine assumes access is allowed. -* @uses $CFG, $DB -* @param path the access path to the module script code -* @param itemtype the information subclassing (usefull for complex modules, defaults to 'standard') -* @param this_id the item id within the information class denoted by itemtype. In resources, this id -* points to the resource record and not to the module that shows it. -* @param user the user record denoting the user who searches -* @param group_id the current group used by the user when searching -* @return true if access is allowed, false elsewhere -*/ -function resource_check_text_access($path, $itemtype, $this_id, $user, $group_id, $context_id){ - global $CFG, $DB; - - // include_once("{$CFG->dirroot}/{$path}/lib.php"); - - $r = $DB->get_record('resource', array('id' => $this_id)); - $module_context = $DB->get_record('context', array('id' => $context_id)); - $cm = $DB->get_record('course_modules', array('id' => $module_context->instanceid)); - - if (empty($cm)) return false; // Shirai 20090530 - MDL19342 - course module might have been delete - - $course = $DB->get_record('course', array('id' => $r->course)); - $course_context = get_context_instance(CONTEXT_COURSE, $r->course); - $course = $DB->get_record('course', array('id' => $r->course)); - - //check if course is visible - if (!$course->visible && !has_capability('moodle/course:viewhiddencourses', $course_context)) { - return false; - } - - //check if user is registered in course or course is open to guests - if (!is_enrolled($course_context) and !is_viewing($course_context)) { //TODO: guest course access is gone, this needs a different solution - return false; - } - - - //check if found course module is visible - if (!$cm->visible and !has_capability('moodle/course:viewhiddenactivities', $module_context)){ - return false; - } - - return true; -} - -/** -* post processes the url for cleaner output. -* @param string $title -*/ -function resource_link_post_processing($title){ - global $CFG; - - if ($CFG->block_search_utf8dir){ - return mb_convert_encoding($title, 'UTF-8', 'auto'); - } - return mb_convert_encoding($title, 'auto', 'UTF-8'); -} -?> \ No newline at end of file diff --git a/search/documents/user_document.php b/search/documents/user_document.php deleted file mode 100644 index 418193e798f..00000000000 --- a/search/documents/user_document.php +++ /dev/null @@ -1,385 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version Moodle 2.0 -* -* special (EXTRA) document handling for user related data -* -*/ - -/** -* includes and requires -*/ -require_once($CFG->dirroot.'/search/documents/document.php'); -require_once($CFG->dirroot.'/blog/lib.php'); - -/** -* a class for representing searchable information in user metadata -* -*/ -class UserSearchDocument extends SearchDocument { - - /** - * constructor - * @uses $DB - */ - public function __construct(&$userhash, $user_id, $context_id) { - global $DB; - - // generic information; required - $doc->docid = $userhash['id']; - $doc->documenttype = SEARCH_TYPE_USER; - $doc->itemtype = 'user'; - $doc->contextid = $context_id; - - $user = $DB->get_record('user', array('id' => $user_id)); - $doc->title = get_string('user').': '.fullname($user); - $doc->date = ($userhash['lastaccess']) ? $userhash['lastaccess'] : time() ; - - //remove '(ip.ip.ip.ip)' from chat author list - $doc->author = $user->id; - $doc->contents = $userhash['description']; - $doc->url = user_make_link($user_id, 'user'); - - // module specific information; optional - - // construct the parent class - parent::__construct($doc, $data, 0, 0, $user_id, PATH_FOR_SEARCH_TYPE_USER); - } -} - -/** -* a class for representing searchable information in user metadata -* -*/ -class UserPostSearchDocument extends SearchDocument { - - /** - * constructor - * @uses $DB - */ - public function __construct(&$post, $user_id, $context_id) { - global $DB; - - // generic information; required - $doc->docid = $post['id']; - $doc->documenttype = SEARCH_TYPE_USER; - $doc->itemtype = 'post'; - $doc->contextid = $context_id; - - $user = $DB->get_record('user', array('id' => $user_id)); - - // we cannot call userdate with relevant locale at indexing time. - //$doc->title = get_string('post').': '.fullname($user); - $doc->title = $post['subject']; - $doc->date = $post['created']; - - //remove '(ip.ip.ip.ip)' from chat author list - $doc->author = fullname($user); - $doc->contents = $post['description']; - // $doc->url = user_make_link($user_id, 'post'); - $doc->url = user_make_link($post['id'], 'post'); - - // module specific information; optional - - // construct the parent class - parent::__construct($doc, $data, 0, 0, $user_id, PATH_FOR_SEARCH_TYPE_USER); - } -} - -/** -* a class for representing searchable information in user metadata -* -*/ -class UserBlogAttachmentSearchDocument extends SearchDocument { - - /** - * constructor - * @uses $DB - */ - public function __construct(&$post, $context_id) { - global $DB; - - // generic information; required - $doc->docid = $post['id']; - $doc->documenttype = SEARCH_TYPE_USER; - $doc->itemtype = 'attachment'; - $doc->contextid = $context_id; - - $user = $DB->get_record('user', 'id', $post['userid']); - - // we cannot call userdate with relevant locale at indexing time. - $doc->title = get_string('file').' : '.$post['subject']; - $doc->date = $post['created']; - - //remove '(ip.ip.ip.ip)' from chat author list - $doc->author = fullname($user); - $doc->contents = $post['alltext']; - $doc->url = user_make_link($post['id'], 'attachment'); - - // module specific information; optional - - // construct the parent class - parent::__construct($doc, $data, 0, 0, $post['userid'], PATH_FOR_SEARCH_TYPE_USER); - } -} - - -/** -* constructs a valid link to a user record -* @param int $userid the user -* @param string $itemtype -* @uses $CFG, $DB -* @return a well formed link to user information -*/ -function user_make_link($itemid, $itemtype) { - global $CFG, $DB; - - if ($itemtype == 'user'){ - return $CFG->wwwroot.'/user/view.php?id='.$itemid; - } elseif ($itemtype == 'post') { - return $CFG->wwwroot.'/blog/index.php?postid='.$itemid; - } elseif ($itemtype == 'attachment') { - $post = $DB->get_record('post', array('id' => $itemid)); - if (!$CFG->slasharguments){ - return $CFG->wwwroot."/file.php?file=/blog/attachments/{$post->id}/{$post->attachment}"; - } else { - return $CFG->wwwroot."/file.php/blog/attachments/{$post->id}/{$post->attachment}"; - } - } else { - return null; - } -} - -/** -* part of search engine API -* @uses $DB -* -*/ -function user_iterator() { - global $DB; - - $users = $DB->get_records('user'); - return $users; -} - -/** -* part of search engine API -* @uses $CFG, $DB -* @param reference $user a user record -* @return an array of documents generated from data -*/ -function user_get_content_for_index(&$user) { - global $CFG, $DB; - - $documents = array(); - - $userhash = get_object_vars($user); - $documents[] = new UserSearchDocument($userhash, $user->id, null); - - if ($posts = $DB->get_records('post', array('userid' => $user->id), 'created')){ - foreach($posts as $post){ - $texts = array(); - $texts[] = $post->subject; - $texts[] = $post->summary; - $texts[] = $post->content; - $post->description = implode(' ', $texts); - - // record the attachment if any and physical files can be indexed - if (@$CFG->block_search_enable_file_indexing){ - if ($post->attachment){ - user_get_physical_file($post, null, false, $documents); - } - } - - $posthash = get_object_vars($post); - $documents[] = new UserPostSearchDocument($posthash, $user->id, null); - } - } - return $documents; -} - -/** -* get text from a physical file -* @uses $CFG -* @param object $post a post to whech the file is attached to -* @param boolean $context_id if in future we need recording a context along with the search document, pass it here -* @param boolean $getsingle if true, returns a single search document, elsewhere return the array -* given as documents increased by one -* @param array $documents the array of documents, by ref, where to add the new document. -* @return a search document when unique or false. -*/ -function user_get_physical_file(&$post, $context_id, $getsingle, &$documents = null){ - global $CFG; - - // cannot index empty references - if (empty($post->attachment)){ - mtrace("Cannot index, empty reference."); - return false; - } - - $fileparts = pathinfo($post->attachment); - // cannot index unknown or masked types - if (empty($fileparts['extension'])) { - mtrace("Cannot index without explicit extension."); - return false; - } - - // cannot index non existent file - $file = "{$CFG->dataroot}/blog/attachments/{$post->id}/{$post->attachment}"; - if (!file_exists($file)){ - mtrace("Missing attachment file $file : will not be indexed."); - return false; - } - - $ext = strtolower($fileparts['extension']); - - // cannot index unallowed or unhandled types - if (!preg_match("/\b$ext\b/i", $CFG->block_search_filetypes)) { - mtrace($fileparts['extension'] . ' is not an allowed extension for indexing'); - return false; - } - if (file_exists($CFG->dirroot.'/search/documents/physical_'.$ext.'.php')){ - include_once($CFG->dirroot.'/search/documents/physical_'.$ext.'.php'); - $function_name = 'get_text_for_indexing_'.$ext; - $directfile = "blog/attachments/{$post->id}/{$post->attachment}"; - $post->alltext = $function_name($post, $directfile); - if (!empty($post->alltext)){ - if ($getsingle){ - $posthash = get_object_vars($post); - $single = new UserBlogAttachmentSearchDocument($posthash, $context_id); - mtrace("finished attachment {$post->attachment} in {$post->title}"); - return $single; - } else { - $posthash = get_object_vars($post); - $documents[] = new UserBlogAttachmentSearchDocument($posthash, $context_id); - } - mtrace("finished attachment {$post->attachment} in {$post->subject}"); - } - } else { - mtrace("fulltext handler not found for $ext type"); - } - return false; -} - -/** -* returns a single user search document -* @uses $DB -* @param composite $id a unique document id made with -* @param itemtype the type of information (session is the only type) -*/ -function user_single_document($id, $itemtype) { - global $DB; - - if ($itemtype == 'user'){ - if ($user = $DB->get_record('user', array('id' => $id))){ - $userhash = get_object_vars($user); - return new UserSearchDocument($userhash, $user->id, 'user', null); - } - } elseif ($itemtype == 'post') { - if ($post = $DB->get_record('post', array('id' => $id))){ - $texts = array(); - $texts[] = $post->subject; - $texts[] = $post->summary; - $texts[] = $post->content; - $post->description = implode(" ", $texts); - $posthash = get_object_vars($post); - return new UserPostSearchDocument($posthash, $post->userid, 'post', null); - } - } elseif ($itemtype == 'attachment' && @$CFG->block_search_enable_file_indexing) { - if ($post = $DB->get_records('post', array('id' => $id))){ - if ($post->attachment){ - return user_get_physical_file($post, null, true); - } - } - } - return null; -} - -/** -* dummy delete function that packs id with itemtype. -* this was here for a reason, but I can't remember it at the moment. -* -*/ -function user_delete($info, $itemtype) { - $object->id = $info; - $object->itemtype = $itemtype; - return $object; -} - -/** -* returns the var names needed to build a sql query for addition/deletions -* attachments are indirect records, linked to its post -*/ -function user_db_names() { - //[primary id], [table name], [time created field name], [time modified field name] [itemtype] [select restriction clause] - return array( - array('id', 'user', 'firstaccess', 'timemodified', 'user'), - array('id', 'post', 'created', 'lastmodified', 'post'), - array('id', 'post', 'created', 'lastmodified', 'attachment') - ); -} - -/** -* this function handles the access policy to contents indexed as searchable documents. If this -* function does not exist, the search engine assumes access is allowed. -* When this point is reached, we already know that : -* - user is legitimate in the surrounding context -* - user may be guest and guest access is allowed to the module -* - the function may perform local checks within the module information logic -* @param string $path the access path to the module script code -* @param string $itemtype the information subclassing (usefull for complex modules, defaults to 'standard') -* @param int $this_id the item id within the information class denoted by entry_type. In chats, this id -* points out a session history which is a close sequence of messages. -* @param object $user the user record denoting the user who searches -* @param int $group_id the current group used by the user when searching -* @uses $CFG, $DB -* @return true if access is allowed, false elsewhere -*/ -function user_check_text_access($path, $itemtype, $this_id, $user, $group_id, $context_id){ - global $CFG, $DB; - - include_once("{$CFG->dirroot}/{$path}/lib.php"); - - if ($itemtype == 'user'){ - // get the user - $userrecord = $DB->get_record('user', array('id' => $this_id)); - - // we cannot see nothing from unconfirmed users - if (!$userrecord->confirmed and !has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))){ - if (!empty($CFG->search_access_debug)) echo "search reject : unconfirmed user "; - return false; - } - } elseif ($itemtype == 'post' || $itemtype == 'attachment'){ - // get the post - $post = $DB->get_record('post', array('id' => $this_id)); - $userrecord = $DB->get_record('user', array('id' => $post->userid)); - - // we can try using blog visibility check - return blog_user_can_view_user_post($user->id, $post); - } - $context = $DB->get_record('context', array('id' => $context_id)); - - return true; -} - -/** -* this call back is called when displaying the link for some last post processing -* -*/ -function user_link_post_processing($title){ - global $CFG; - - if ($CFG->block_search_utf8dir){ - return mb_convert_encoding($title, 'UTF-8', 'auto'); - } - return mb_convert_encoding($title, 'auto', 'UTF-8'); -} -?> \ No newline at end of file diff --git a/search/documents/wiki_document.php b/search/documents/wiki_document.php deleted file mode 100644 index 0643c0a021f..00000000000 --- a/search/documents/wiki_document.php +++ /dev/null @@ -1,324 +0,0 @@ - 1.8 -* @contributor Tatsuva Shirai 20090530 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* @version Moodle 2.0 -* -* document handling for wiki activity module -* This file contains the mapping between a wiki page and it's indexable counterpart, -* e.g. searchdocument->title = wikipage->pagename -* -* Functions for iterating and retrieving the necessary records are now also included -* in this file, rather than mod/wiki/lib.php -*/ - -/** -* includes and requires -*/ -require_once($CFG->dirroot.'/search/documents/document.php'); -require_once($CFG->dirroot.'/mod/wiki/lib.php'); - -/** -* All the $doc->___ fields are required by the base document class! -* Each and every module that requires search functionality must correctly -* map their internal fields to the five $doc fields (id, title, author, contents -* and url). Any module specific data can be added to the $data object, which is -* serialised into a binary field in the index. -*/ -class WikiSearchDocument extends SearchDocument { - public function __construct(&$page, $wiki_id, $course_id, $group_id, $user_id, $context_id) { - // generic information; required - $doc->docid = $page['id']; - $doc->documenttype = SEARCH_TYPE_WIKI; - $doc->itemtype = 'standard'; - $doc->contextid = $context_id; - - $doc->title = $page['title']; - $doc->date = $page['timemodified']; - //remove '(ip.ip.ip.ip)' from wiki author field - $doc->author = $page['author']; - $doc->contents = $page['cachedcontent']; - $doc->url = wiki_make_link($page['id']); - - // module specific information; optional - //$data->version = $page['version']; - $data->wiki = $wiki_id; - - // construct the parent class - parent::__construct($doc, $data, $course_id, $group_id, $user_id, 'mod/'.SEARCH_TYPE_WIKI); - } -} - -/** -* converts a page name to cope Wiki constraints. Transforms spaces in plus. -* @param str the name to convert -* @return the converted name -*/ -function wiki_name_convert($str) { - return str_replace(' ', '+', $str); -} - -/** -* constructs a valid link to a wiki content -* @param int $wikiId -* @param string $title -* @param int $version -* @uses $CFG -*/ -function wiki_make_link($pageid) { - global $CFG; - - return $CFG->wwwroot.'/mod/wiki/view.php?pageid='.$pageid; -} - -/** -* rescued and converted from ewikimoodlelib.php -* retrieves latest version of a page -* @uses $DB -* @param object $entry the wiki object as a reference -* @param string $pagename the name of the page known by the wiki engine -* @param int $version -*/ -function wiki_get_latest_page(&$entry, $pagename, $version = 0) { - global $DB; - - $params = array('title' => $pagename, 'subwikiid' => $entry->id); - - if ($version > 0 && is_int($version)) { - $versionclause = "AND ( version = :version )"; - $sort = 'version DESC'; - $params['version'] = $version; - } else { - $versionclause = ''; - $sort = ''; - } - - $select = "( title = :title ) AND subwikiid = :subwikiid $versionclause "; - - //change this to recordset_select, as per http://docs.moodle.org/en/Datalib_Notes - if ($result_arr = $DB->get_records_select('wiki_pages', $select, $params, $sort, '*', 0, 1)) { - foreach ($result_arr as $obj) { - $result_obj = $obj; - } - } - - if (isset($result_obj)) { - $result_obj->meta = @unserialize($result_obj->meta); - return $result_obj; - } else { - return false; - } -} - -/** -* fetches all pages, including old versions -* @uses $DB -* @param object $entry the wiki object as a reference -* @return an array of record objects that represents pages of this wiki object -*/ -function wiki_get_pages(&$entry) { - global $DB; - - return $DB->get_records('wiki_pages', array('wiki', $entry->id)); -} - -/** -* fetches all the latest versions of all the pages -* @uses $DB -* @param reference $entry -*/ -function wiki_get_latest_pages(&$entry) { - global $DB; - - //== (My)SQL for this - /* select * from wiki_pages - inner join - (select wiki_pages.pagename, max(wiki_pages.version) as ver - from wiki_pages group by pagename) as a - on ((wiki_pages.version = a.ver) and - (wiki_pages.pagename like a.pagename)) */ - - $pages = array(); - - //http://moodle.org/bugs/bug.php?op=show&bugid=5877&pos=0 - if ($ids = $DB->get_records('wiki_pages', array('subwikiid' => $entry->id), '', 'distinct title')) { - if ($pagesets = $DB->get_records('wiki_pages', array('subwikiid' => $entry->id), '', 'distinct title')) { - foreach ($pagesets as $aPageset) { - $pages[] = wiki_get_latest_page($entry, $aPageset->title); - } - } else { - return false; - } - } - return $pages; -} - -/** -* part of search engine API -* @uses $DB; -* -*/ -function wiki_iterator() { - global $DB; - - $wikis = $DB->get_records('wiki'); - return $wikis; -} - -/** -* part of search engine API -* @uses $DB -* @param reference $wiki a wiki instance -* @return an array of searchable deocuments -*/ -function wiki_get_content_for_index(&$wiki) { - global $CFG, $DB; - require_once($CFG->dirroot . '/mod/wiki/locallib.php'); - - $documents = array(); - $entries = wiki_get_subwikis($wiki->id); - if ($entries){ - $coursemodule = $DB->get_field('modules', 'id', array('name' => 'wiki')); - $cm = $DB->get_record('course_modules', array('course' => $wiki->course, 'module' => $coursemodule, 'instance' => $wiki->id)); - $context = get_context_instance(CONTEXT_MODULE, $cm->id); - foreach($entries as $entry) { - - //all pages - //$pages = wiki_get_pages($entry); - - //latest pages - $pages = wiki_get_latest_pages($entry); - if (is_array($pages)) { - foreach($pages as $page) { - if (strlen($page->title) > 0) { - $owner = $DB->get_record('user', array('id' => $page->userid)); - $page->author = fullname($owner); - $documents[] = new WikiSearchDocument(get_object_vars($page), $entry->wikiid, $wiki->course, $entry->groupid, $page->userid, $context->id); - } - } - } - } - } - return $documents; -} - -/** -* returns a single wiki search document based on a wiki_entry id -* @uses $DB; -* @param int $id the id of the wiki -* @param string $itemtype the type of information (standard) -* @return a searchable document -*/ -function wiki_single_document($id, $itemtype) { - global $DB; - - $page = $DB->get_record('wiki_pages', array('id' => $id)); - $entry = $DB->get_record('wiki_subwikis', array('id' => $page->subwikiid)); - $wiki = $DB->get_record('wiki', array('id' => $entry->wikiid)); - $coursemodule = $DB->get_field('modules', 'id', array('name' => 'wiki')); - $cm = $DB->get_record('course_modules', array('course' => $wiki->course, 'module' => $coursemodule, 'instance' => $entry->wikiid)); - $context = get_context_instance(CONTEXT_MODULE, $cm->id); - $user = $DB->get_record('user', array('id' => $page->userid)); - $page->author = fullname($user); - return new WikiSearchDocument(get_object_vars($page), $entry->wikiid, $wiki->course, $entry->groupid, $page->userid, $context->id); -} - -/** -* dummy delete function that packs id with itemtype. -* this was here for a reason, but I can't remember it at the moment. -* -*/ -function wiki_delete($info, $itemtype) { - $object->id = $info; - $object->itemtype = $itemtype; - return $object; -} - -//returns the var names needed to build a sql query for addition/deletions -function wiki_db_names() { - //[primary id], [table name], [time created field name], [time modified field name], [docsubtype], [additional where conditions for sql] - return array(array('id', 'wiki_pages', 'timecreated', 'timemodified', 'standard')); -} - -/** -* this function handles the access policy to contents indexed as searchable documents. If this -* function does not exist, the search engine assumes access is allowed. -* When this point is reached, we already know that : -* - user is legitimate in the surrounding context -* - user may be guest and guest access is allowed to the module -* - the function may perform local checks within the module information logic -* @param string $path the access path to the module script code -* @param string $itemtype the information subclassing (usefull for complex modules, defaults to 'standard') -* @param int $this_id the item id within the information class denoted by itemtype. In wikies, this id -* points out the indexed wiki page. -* @param object $user the user record denoting the user who searches -* @param int $group_id the current group used by the user when searching -* @param int $context_id a context that eventually comes with the object -* @uses $CFG, $DB -* @return true if access is allowed, false elsewhere -*/ -function wiki_check_text_access($path, $itemtype, $this_id, $user, $group_id, $context_id){ - global $CFG, $DB, $SESSION; - - // get the wiki object and all related stuff - $page = $DB->get_record('wiki_pages', array('id' => $this_id)); - $wiki = $DB->get_record('wiki', array('id' => $page->wiki)); - $course = $DB->get_record('course', array('id' => $wiki->course)); - $context = $DB->get_record('context', array('id' => $context_id)); - $cm = $DB->get_record('course_modules', array('id' => $context->instanceid)); - - if (empty($cm)) return false; // Shirai 20090530 - MDL19342 - course module might have been delete - - if (!$cm->visible && !has_capability('moodle/course:viewhiddenactivities', $context)) { - if (!empty($CFG->search_access_debug)) echo "search reject : hidden wiki "; - return false; - } - - //group consistency check : checks the following situations about groups - // trap if user is not same group and groups are separated - if (isset($SESSION->currentgroup[$course->id])) { - $current_group = $SESSION->currentgroup[$course->id]; - } else { - $current_group = groups_get_all_groups($course->id, $USER->id); - if (is_array($current_group)) { - $current_group = array_shift(array_keys($current_group)); - $SESSION->currentgroup[$course->id] = $current_group; - } else { - $current_group = 0; - } - } - - if (isset($cm->groupmode) && empty($course->groupmodeforce)) { - $groupmode = $cm->groupmode; - } else { - $groupmode = $course->groupmode; - } - if (($groupmode == SEPARATEGROUPS) && $group_id != $current_group && !has_capability('moodle/site:accessallgroups', $context)) { - if (!empty($CFG->search_access_debug)) echo "search reject : separated group owner wiki "; - return false; - } - - return true; -} - -/** -* this call back is called when displaying the link for some last post processing -* -*/ -function wiki_link_post_processing($title){ - global $CFG; - - if ($CFG->block_search_utf8dir){ - return mb_convert_encoding($title, 'UTF-8', 'auto'); - } - return mb_convert_encoding($title, 'auto', 'UTF-8'); -} - -?> \ No newline at end of file diff --git a/search/index.php b/search/index.php deleted file mode 100644 index 089688c9659..00000000000 --- a/search/index.php +++ /dev/null @@ -1,18 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* -* Entry page for /search -* Redirects to query.php, because that is the most likely place a -* user intended to go to when typing moodle.site/search -*/ - -header("Location: query.php"); -?> \ No newline at end of file diff --git a/search/indexer.php b/search/indexer.php deleted file mode 100644 index 8f2b9e31c4d..00000000000 --- a/search/indexer.php +++ /dev/null @@ -1,225 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @version prepared for Moodle 2.0 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* -* 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/
Sorry, you need to confirm indexing via indexersplash.php" - .". (Back to query page)."); - - exit(0); - } - -/// check for php5 (lib.php) - - //php5 found, continue including php5-only files - //require_once("$CFG->dirroot/search/Zend/Search/Lucene.php"); - require_once($CFG->dirroot.'/search/indexlib.php'); - - mtrace(''); - mtrace('
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
-
- 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, $CFG->directorypermissions)) {
- search_pexit("Error creating data directory at: $index_path. Please correct.");
- }
- else {
- mtrace("Directory successfully created.");
- }
- }
- else {
- mtrace("Using {$index_path} as data directory.");
- }
-
- Zend_Search_Lucene_Analysis_Analyzer::setDefault(new Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8_CaseInsensitive());
- $index = new Zend_Search_Lucene($index_path, true);
-
-/// New regeneration
-
- mtrace('Deleting old index entries.');
- $DB->delete_records(SEARCH_DATABASE_TABLE);
-
-/// begin timer
-
- 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.
-
- $searchables = search_collect_searchables();
-
-/// start indexation
-
- if ($searchables){
- foreach ($searchables as $mod) {
-
- //mark last update times for mods to now.
- $indexdatestring = 'search_indexer_update_date_'.$mod->name;
- set_config($indexdatestring, time());
- $indexdatestring = 'search_indexer_run_date_'.$mod->name;
- set_config($indexdatestring, time());
-
- mtrace("starting indexing {$mod->name}\n");
-
- $key = 'search_in_'.$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)) {
- 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) {
- $counter++;
-
- // temporary fix until MDL-24822 is resolved
- if ($document->group_id == -1 and $mod->name ='forum') {
- $document->group_id = 0;
- }
- //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");
- }
- }
- }
- //end transaction
- }
- }
-
- //commit left over documents, and finish up
- $index->commit();
-
- mtrace("-- $counter documents indexed");
- mtrace("done.\n");
- }
- } else {
- mtrace ("No search document found for plugin {$mod->name}. Ignoring.");
- }
- }
- }
-
-/// finished modules
-
- mtrace('Finished activity modules');
- search_stopwatch();
-
- mtrace(".
Back to query page.");
- mtrace('');
-
-/// finished, turn busy flag off
-
- set_config('search_indexer_busy', '0');
-
-/// mark the time we last updated
-
- set_config('search_indexer_run_date', time());
-
-/// and the index size
-
- set_config('search_index_size', (int)$index->count());
-
-?>
\ No newline at end of file
diff --git a/search/indexersplash.php b/search/indexersplash.php
deleted file mode 100644
index 78ac128d71f..00000000000
--- a/search/indexersplash.php
+++ /dev/null
@@ -1,77 +0,0 @@
- 1.8
- * @date 2008/03/31
- * @version prepared for 2.0
- * @license http://www.gnu.org/copyleft/gpl.html GNU Public License
- *
- * This file serves as a splash-screen (entry page) to the indexer script -
- * it is in place to prevent accidental reindexing which can lead to a loss
- * of time, amongst other things.
- */
-
- /**
- * includes and requires
- */
- require_once('../config.php');
-
- /// makes inclusions of the Zend Engine more reliable
- ini_set('include_path', $CFG->dirroot.DIRECTORY_SEPARATOR.'search'.PATH_SEPARATOR.ini_get('include_path'));
-
- require_once($CFG->dirroot.'/search/lib.php');
-
- /// check global search is enabled
-
- require_login();
-
- if (empty($CFG->enableglobalsearch)) {
- print_error('globalsearchdisabled', 'search');
- }
-
- if (!has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) {
- print_error('beadmin', 'search', get_login_url());
- }
-
- require_once("$CFG->dirroot/search/indexlib.php");
- $indexinfo = new IndexInfo();
-
- if ($indexinfo->valid()) {
- $strsearch = get_string('search', 'search');
- $strquery = get_string('stats');
-
- // print page header
- $site = get_site();
-
- $PAGE->set_url('/search/indexersplash.php');
- $PAGE->set_context(get_context_instance(CONTEXT_SYSTEM));
- $PAGE->navbar->add($strsearch, new moodle_url('/search/index.php'));
- $PAGE->navbar->add($strquery, new moodle_url('/search/stats.php'));
- $PAGE->navbar->add(get_string('runindexer','search'));
- $PAGE->set_title($strsearch);
- $PAGE->set_heading($site->fullname);
- echo $OUTPUT->header();
-
- mtrace("The data directory ($indexinfo->path) contains $indexinfo->filecount files, and\n" - ."there are ".$indexinfo->dbcount." records in the block_search_documents table.\n" - ."\n" - ."This indicates that you have already succesfully indexed this site. Follow the link\n" - ."if you are sure that you want to continue indexing - this will replace any existing\n" - ."index data (no Moodle data is affected).\n" - ."\n" - ."You are encouraged to use the 'Test indexing' script before continuing onto\n" - ."indexing - this will check if the modules are set up correctly. Please correct\n" - ."any errors before proceeding.\n" - ."\n" - ."Test indexing or " - ."Continue indexing or Back to query page." - .""); - echo $OUTPUT->footer(); - } else { - header('Location: indexer.php?areyousure=yes'); - } -?> diff --git a/search/indexlib.php b/search/indexlib.php deleted file mode 100644 index 3c2075ef291..00000000000 --- a/search/indexlib.php +++ /dev/null @@ -1,262 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @version prepared for 2.0 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* -* Index info class -* -* Used to retrieve information about an index. -* Has methods to check for valid database and data directory, -* and the index itself. -*/ - -/** -* includes and requires -*/ -require_once($CFG->dirroot.'/search/lib.php'); -require_once($CFG->dirroot.'/search/Zend/Search/Lucene.php'); - -/** -* main class for searchable information in the Lucene index -*/ -class IndexInfo { - - private $path, //index data directory - $size, //size of directory (i.e. the whole index) - $filecount, //number of files - $indexcount, //number of docs in index - $dbcount, //number of docs in db - $types, //array of [document types => count] - $complete, //is index completely formed? - $time; //date index was generated - - public function __construct($path = SEARCH_INDEX_PATH) { - global $CFG, $DB; - - $this->path = $path; - - //test to see if there is a valid index on disk, at the specified path - try { - $test_index = new Zend_Search_Lucene($this->path, false); - $validindex = true; - } catch(Exception $e) { - $validindex = false; - } - - //retrieve file system info about the index if it is valid - if ($validindex) { - $this->size = display_size(get_directory_size($this->path)); - $index_dir = get_directory_list($this->path, '', false, false); - $this->filecount = count($index_dir); - $this->indexcount = $test_index->count(); - } - else { - $this->size = 0; - $this->filecount = 0; - $this->indexcount = 0; - } - - $db_exists = false; //for now - - //get all the current tables in moodle - $admin_tables = $DB->get_tables(); - - //check if our search table exists - if (in_array(SEARCH_DATABASE_TABLE, $admin_tables)) { - //retrieve database information if it does - $db_exists = true; - - //total documents - $this->dbcount = $DB->count_records(SEARCH_DATABASE_TABLE); - - //individual document types - $types = search_collect_searchables(false, false); - asort($types); - - foreach(array_keys($types) as $type) { - $c = $DB->count_records(SEARCH_DATABASE_TABLE, array('doctype' => $type)); - $types[$type]->records = (int)$c; - } - $this->types = $types; - } else { - $this->dbcount = 0; - $this->types = array(); - } - - //check if the busy flag is set - if (isset($CFG->search_indexer_busy) && $CFG->search_indexer_busy == '1') { - $this->complete = false; - } else { - $this->complete = true; - } - - //get the last run date for the indexer - if ($this->valid() && $CFG->search_indexer_run_date) { - $this->time = $CFG->search_indexer_run_date; - } else { - $this->time = 0; - } - } - - /** - * returns false on error, and the error message via referenced variable $err - * @param array $err array of errors - */ - public function valid(&$err = null) { - $err = array(); - $ret = true; - - if (!$this->is_valid_dir()) { - $err['dir'] = get_string('invalidindexerror', 'search'); - $ret = false; - } - - if (!$this->is_valid_db()) { - $err['db'] = get_string('emptydatabaseerror', 'search'); - $ret = false; - } - - if (!$this->complete) { - $err['index'] = get_string('uncompleteindexingerror','search'); - $ret = false; - } - - return $ret; - } - - /** - * is the index dir valid - * - */ - public function is_valid_dir() { - if ($this->filecount > 0) { - return true; - } else { - return false; - } - } - - /** - * is the db table valid - * - */ - public function is_valid_db() { - if ($this->dbcount > 0) { - return true; - } else { - return false; - } - } - - /** - * shorthand get method for the class variables - * @param object $var - */ - public function __get($var) { - if (in_array($var, array_keys(get_class_vars(get_class($this))))) { - return $this->$var; - } - } -} - - -/** -* DB Index control class -* -* Used to control the search index database table -*/ -class IndexDBControl { - - /** - * does the table exist? - * @deprecated - * @uses $CFG, $DB - */ - public function checkTableExists() { - global $CFG, $DB; - - $tables = $DB->get_tables(); - if (in_array(SEARCH_DATABASE_TABLE, $tables)) { - return true; - } - else { - return false; - } - } //checkTableExists - - /** - * NEVER USED - * - * is our database setup valid? - * @uses db, CFG - * @deprecated Database is installed at install and should not be dropped out - * - public function checkDB() { - global $CFG, $db; - - $sqlfile = "{$CFG->dirroot}/search/db/$CFG->dbtype.sql"; - $ret = false; - if ($this->checkTableExists()) { - execute_sql('drop table '.SEARCH_DATABASE_TABLE, false); - } - - //turn output buffering on - to hide modify_database() output - ob_start(); - $ret = modify_database($sqlfile, '', false); - - //chuck the buffer and resume normal operation - ob_end_clean(); - return $ret; - } //checkDB */ - - /** - * add a document record to the table - * @param document must be a Lucene SearchDocument instance - * @uses $CFG, $DB - */ - public function addDocument($document=null) { - global $DB, $CFG; - - if ($document == null) { - return false; - } - - // object to insert into db - $doc->doctype = $document->doctype; - $doc->docid = $document->docid; - $doc->itemtype = $document->itemtype; - $doc->title = $document->title; - $doc->url = $document->url; - $doc->updated = time(); - $doc->docdate = $document->date; - $doc->courseid = $document->course_id; - $doc->groupid = $document->group_id; - - //insert summary into db - $table = SEARCH_DATABASE_TABLE; - $id = $DB->insert_record($table, $doc); - - return $id; - } - - /** - * remove a document record from the index - * @param document must be a Lucene document instance, or at least a dbid enveloppe - * @uses $DB - */ - public function delDocument($document) { - global $DB; - - $table = SEARCH_DATABASE_TABLE; - $DB->delete_records($table, array('id' => $document->dbid)); - } -} - -?> \ No newline at end of file diff --git a/search/lib.php b/search/lib.php deleted file mode 100644 index d93a633f810..00000000000 --- a/search/lib.php +++ /dev/null @@ -1,197 +0,0 @@ - 1.8 -* @date 2008/03/31 -* @version prepared for 2.0 -* @license http://www.gnu.org/copyleft/gpl.html GNU Public License -* -* General function library -* -* This file must not contain any PHP 5, because it is used to test for PHP 5 -* itself, and needs to be able to be executed on PHP 4 installations. -* -*/ - -/** -* Constants -*/ -define('SEARCH_INDEX_PATH', $CFG->dataroot.'/search'); -define('SEARCH_DATABASE_TABLE', 'block_search_documents'); - -// get document types -include_once $CFG->dirroot.'/search/searchtypes.php'; - -/** -* collects all searchable items identities -* @param boolean $namelist if true, only returns list of names of searchable items -* @param boolean $verbose if true, prints a discovering status -* @return an array of names or an array of type descriptors -*/ -function search_collect_searchables($namelist=false, $verbose=true){ - global $CFG, $DB; - - $searchables = array(); - $searchables_names = array(); - -/// get all installed modules - if ($mods = $DB->get_records('modules', null, 'name', 'id,name')){ - - $searchabletypes = array_values(search_get_document_types()); - - foreach($mods as $mod){ - $plugin = new StdClass(); - $plugin->name = $mod->name; - $plugin->type = 'mod'; - if (in_array($mod->name, $searchabletypes)){ - $plugin->location = 'internal'; - $searchables[$plugin->name] = $plugin; - $searchables_names[] = $mod->name; - } else { - $documentfile = $CFG->dirroot."/mod/{$mod->name}/search_document.php"; - $plugin->location = 'mod'; - if (file_exists($documentfile)){ - $searchables[$plugin->name] = $plugin; - $searchables_names[] = $mod->name; - } - } - } - if ($verbose) mtrace(count($searchables).' modules to search in / '.count($mods).' modules found.'); - } - -/// collects blocks as indexable information may be found in blocks either - if ($blocks = $DB->get_records('block', null, 'name', 'id,name')) { - $blocks_searchables = array(); - // prepend the "block_" prefix to discriminate document type plugins - foreach($blocks as $block){ - $plugin = new StdClass(); - $plugin->dirname = $block->name; - $plugin->name = 'block_'.$block->name; - if (in_array('SEARCH_TYPE_'.strtoupper($block->name), $searchabletypes)){ - $plugin->location = 'internal'; - $plugin->type = 'block'; - $blocks_searchables[$plugin->name] = $plugin; - $searchables_names[] = $plugin->name; - } else { - $documentfile = $CFG->dirroot."/blocks/{$plugin->dirname}/search_document.php"; - if (file_exists($documentfile)){ - $plugin->location = 'blocks'; - $plugin->type = 'block'; - $blocks_searchables[$plugin->name] = $plugin; - $searchables_names[] = $plugin->name; - } - } - } - if ($verbose) mtrace(count($blocks_searchables).' blocks to search in / '.count($blocks).' blocks found.'); - $searchables = array_merge($searchables, $blocks_searchables); - } - -/// add virtual modules onto the back of the array - - $additional = search_get_additional_modules($searchables_names); - if (!empty($additional)){ - if ($verbose) mtrace(count($additional).' additional to search in.'); - $searchables = array_merge($searchables, $additional); - } - - if ($namelist) - return $searchables_names; - return $searchables; -} - -/** -* returns all the document type constants that are known in core implementation -* @param prefix a pattern for recognizing constants -* @return an array of type labels -*/ -function search_get_document_types($prefix = 'SEARCH_TYPE_') { - $ret = array(); - foreach (get_defined_constants() as $key => $value) { - if (preg_match("/^{$prefix}/", $key)){ - $ret[$key] = $value; - } - } - sort($ret); - return $ret; -} - -/** -* additional virtual modules to index -* -* By adding 'moo' to the extras array, an additional document type -* documents/moo_document.php will be indexed - this allows for -* virtual modules to be added to the index, i.e. non-module specific -* information. -*/ -function search_get_additional_modules(&$searchables_names) { - $extras = array(/* additional keywords go here */); - if (defined('SEARCH_EXTRAS')){ - $extras = explode(',', SEARCH_EXTRAS); - } - - $ret = array(); - $temp = new StdClass; - foreach($extras as $extra) { - $plugin = new StdClass(); - $plugin->name = $extra; - $plugin->location = 'internal'; - eval('$plugin->type = TYPE_FOR_SEARCH_TYPE_'.strtoupper($extra).';'); - $ret[$plugin->name] = $plugin; - $searchables_names[] = $extra; - } - - return $ret; -} - -/** -* shortens a url so it can fit on the results page -* @param url the url -* @param length the size limit we want -*/ -function search_shorten_url($url, $length=30) { - return substr($url, 0, $length)."..."; -} - -/** -* simple timer function, on first call, records a current microtime stamp, outputs result on 2nd call -* @param cli an output formatting switch -* @return void -*/ -function search_stopwatch($cli = false) { - if (!empty($GLOBALS['search_script_start_time'])) { - if (!$cli) print ''; - print round(microtime(true) - $GLOBALS['search_script_start_time'], 6).' '.get_string('seconds', 'search'); - if (!$cli) print ''; - unset($GLOBALS['search_script_start_time']); - } else { - $GLOBALS['search_script_start_time'] = microtime(true); - } -} - -/** -* print and exit (for debugging) -* @param str a variable to explore -* @return void -*/ -function search_pexit($str = "") { - if (is_array($str) or is_object($str)) { - print_r($str); - } else if ($str) { - print $str."
"; - } - exit(0); -} - -function search_updatedcallback($name) { - global $CFG, $DB; - // set block to hidden when global search is disabled. - if ($CFG->enableglobalsearch != 1) { - $DB->set_field('block', 'visible', 0, array('name'=>'search')); // Hide block - } -} - -?> diff --git a/search/query.php b/search/query.php deleted file mode 100644 index 2af22bd2b12..00000000000 --- a/search/query.php +++ /dev/null @@ -1,414 +0,0 @@ - 1.8 - * @date 2008/03/31 - * @license http://www.gnu.org/copyleft/gpl.html GNU Public License - * - * The query page - accepts a user-entered query string and returns results. - * - * Queries are boolean-aware, e.g.: - * - * '+' term required - * '-' term must not be present - * '' (no modifier) term's presence increases rank, but isn't required - * 'field:' search this field - * - * Examples: - * - * 'earthquake +author:michael' - * Searches for documents written by 'michael' that contain 'earthquake' - * - * 'earthquake +doctype:wiki' - * Search all wiki pages for 'earthquake' - * - * '+author:helen +author:foster' - * All articles written by Helen Foster - * - */ - - /** - * includes and requires - */ - require_once('../config.php'); - require_once($CFG->dirroot.'/search/lib.php'); - - $block_instanceid = required_param('block_instanceid', PARAM_INT);// Block Instance ID - - if ($CFG->forcelogin) { - require_login(); - } - - if (empty($CFG->enableglobalsearch)) { - print_error('globalsearchdisabled', 'search'); - } - //Check user's permissions against the block instance from which the user came - if (empty($block_instanceid)) { - print_error('searchnotpermitted', 'search'); - } - if (!$DB->record_exists('block_instances', array('id' => $block_instanceid, 'blockname' => 'search'))) { - print_error('searchnotpermitted', 'search'); - } - $contextblock = get_context_instance(CONTEXT_BLOCK, $block_instanceid); - require_capability('moodle/block:view', $contextblock); - - $adv = new stdClass(); - -/// check for php5, but don't die yet (see line 52) - - require_once($CFG->dirroot.'/search/querylib.php'); - - $page_number = optional_param('page', -1, PARAM_INT); - $pages = ($page_number == -1) ? false : true; - $advanced = (optional_param('a', '0', PARAM_INT) == '1') ? true : false; - $query_string = optional_param('query_string', '', PARAM_CLEAN); - - $url = new moodle_url('/search/query.php'); - if ($page_number !== -1) { - $url->param('page', $page_number); - } - if ($advanced) { - $url->param('a', '1'); - } - $url->param('block_instanceid', $block_instanceid); - $PAGE->set_url($url); - -/// discard harmfull searches - - if (!isset($CFG->block_search_utf8dir)){ - set_config('block_search_utf8dir', 1); - } - -/// discard harmfull searches - - if (preg_match("/^[\*\?]+$/", $query_string)){ - $query_string = ''; - $error = get_string('fullwildcardquery','search'); - } - - - if ($pages && isset($_SESSION['search_advanced_query'])) { - // if both are set, then we are busy browsing through the result pages of an advanced query - $adv = unserialize($_SESSION['search_advanced_query']); - } elseif ($advanced) { - // otherwise we are dealing with a new advanced query - unset($_SESSION['search_advanced_query']); - session_unregister('search_advanced_query'); - - // chars to strip from strings (whitespace) - $chars = " \t\n\r\0\x0B,-+"; - - // retrieve advanced query variables - $adv->mustappear = trim(optional_param('mustappear', '', PARAM_CLEAN), $chars); - $adv->notappear = trim(optional_param('notappear', '', PARAM_CLEAN), $chars); - $adv->canappear = trim(optional_param('canappear', '', PARAM_CLEAN), $chars); - $adv->module = optional_param('module', '', PARAM_CLEAN); - $adv->title = trim(optional_param('title', '', PARAM_CLEAN), $chars); - $adv->author = trim(optional_param('author', '', PARAM_CLEAN), $chars); - } - - if ($advanced) { - //parse the advanced variables into a query string - //TODO: move out to external query class (QueryParse?) - - $query_string = ''; - - // get all available module types adding third party modules - $module_types = array_merge(array('all'), array_values(search_get_document_types())); - $module_types = array_merge($module_types, array_values(search_get_document_types('X_SEARCH_TYPE'))); - $adv->module = in_array($adv->module, $module_types) ? $adv->module : 'all'; - - // convert '1 2' into '+1 +2' for required words field - if (strlen(trim($adv->mustappear)) > 0) { - $query_string = ' +'.implode(' +', preg_split("/[\s,;]+/", $adv->mustappear)); - } - - // convert '1 2' into '-1 -2' for not wanted words field - if (strlen(trim($adv->notappear)) > 0) { - $query_string .= ' -'.implode(' -', preg_split("/[\s,;]+/", $adv->notappear)); - } - - // this field is left untouched, apart from whitespace being stripped - if (strlen(trim($adv->canappear)) > 0) { - $query_string .= ' '.implode(' ', preg_split("/[\s,;]+/", $adv->canappear)); - } - - // add module restriction - $doctypestr = 'doctype'; - $titlestr = 'title'; - $authorstr = 'author'; - if ($adv->module != 'all') { - $query_string .= " +{$doctypestr}:".$adv->module; - } - - // create title search string - if (strlen(trim($adv->title)) > 0) { - $query_string .= " +{$titlestr}:".implode(" +{$titlestr}:", preg_split("/[\s,;]+/", $adv->title)); - } - - // create author search string - if (strlen(trim($adv->author)) > 0) { - $query_string .= " +{$authorstr}:".implode(" +{$authorstr}:", preg_split("/[\s,;]+/", $adv->author)); - } - - // save our options if the query is valid - if (!empty($query_string)) { - $_SESSION['search_advanced_query'] = serialize($adv); - } - } - - // normalise page number - if ($page_number < 1) { - $page_number = 1; - } - - //run the query against the index ensuring internal coding works in UTF-8 - Zend_Search_Lucene_Analysis_Analyzer::setDefault(new Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8_CaseInsensitive()); - $sq = new SearchQuery($query_string, $page_number, 10, false); - - $site = get_site(); - - $strsearch = get_string('search', 'search'); - $strquery = get_string('enteryoursearchquery', 'search'); - - // print the header - $site = get_site(); - $PAGE->set_context(get_context_instance(CONTEXT_SYSTEM)); - $PAGE->navbar->add($strsearch, new moodle_url('/search/query.php?block_instanceid=' . $block_instanceid)); - $PAGE->navbar->add($strquery, new moodle_url('/search/stats.php?block_instanceid=' . $block_instanceid)); - $PAGE->set_title($strsearch); - $PAGE->set_heading($site->fullname); - echo $OUTPUT->header(); - - if (!empty($error)){ - notice ($error); - } - - echo $OUTPUT->box_start(); - echo $OUTPUT->heading($strquery); - - echo $OUTPUT->box_start(); - - $vars = get_object_vars($adv); - - if (isset($vars)) { - foreach ($vars as $key => $value) { - // htmlentities breaks non-ascii chars ?? - $adv->key = $value; - //$adv->$key = htmlentities($value); - } - } - ?> - -
- -
- is_valid_index()) {
- //use cached variable to show up-to-date index size (takes deletions into account)
- print $CFG->search_index_size;
- }
- else {
- print "0";
- }
-
- print ' ';
- print_string('documents', 'search');
- print '.';
-
- if (!$sq->is_valid_index() and has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) {
- print '
- box_end();
-
-/// prints all the results in a box
-
- if ($sq->is_valid()) {
- echo $OUTPUT->box_start();
-
- search_stopwatch();
- $hit_count = $sq->count();
-
- print "' . get_string('noindexmessage', 'search') . '' . get_string('createanindex', 'search')."
\n"; - } - - ?> -"; - - print $hit_count.' '.get_string('resultsreturnedfor', 'search') . " '".s($query_string)."'."; - print "
"; - - if ($hit_count > 0) { - $page_links = $sq->page_numbers(); - $hits = $sq->results(); - - if ($advanced) { - // if in advanced mode, search options are saved in the session, so - // we can remove the query string var from the page links, and replace - // it with a=1 (Advanced = on) instead - $page_links = preg_replace("/query_string=[^&]+/", 'a=1', $page_links); - } - - print "
- ";
-
- $typestr = get_string('type', 'search');
- $scorestr = get_string('score', 'search');
- $authorstr = get_string('author', 'search');
-
- $searchables = search_collect_searchables(false, false);
-
- //build a list of distinct user objects needed for results listing.
- $hitusers = array();
- foreach ($hits as $listing) {
- if ($listing->doctype == 'user' and !isset($hitusers[$listing->userid])) {
- $hitusers[$listing->userid] = $DB->get_record('user', array('id' => $listing->userid));
- }
- }
-
- foreach ($hits as $listing) {
-
- if ($listing->doctype == 'user') { // A special handle for users
- $icon = $OUTPUT->user_picture($hitusers[$listing->userid]);
- } else {
- $iconpath = $OUTPUT->pix_url('icon', $listing->doctype);
- $icon = "
- url)
- ."'>$icon $listing->title $course
\n"; - echo "{$typestr}: " . $listing->doctype . ", {$scorestr}: " . round($listing->score, 3); - if (!empty($listing->author) && !is_numeric($listing->author)){ - echo ", {$authorstr}: ".$listing->author."\n" - ." \n";
- }
- }
- echo "
- .
-
-
- box_end();
- echo $OUTPUT->footer();
-?>
diff --git a/search/querylib.php b/search/querylib.php
deleted file mode 100644
index 6f91f92dd4b..00000000000
--- a/search/querylib.php
+++ /dev/null
@@ -1,495 +0,0 @@
- 1.8
-* @date 2008/03/31
-* @license http://www.gnu.org/copyleft/gpl.html GNU Public License
-*/
-
-/**
-* includes and requires
-*/
-require_once($CFG->dirroot.'/search/Zend/Search/Lucene.php');
-
-define('DEFAULT_POPUP_SETTINGS', "\"menubar=0,location=0,scrollbars,resizable,width=600,height=450\"");
-
-/**
-* a class that represents a single result record of the search engine
-*/
-class SearchResult {
-public $url,
- $title,
- $doctype,
- $author,
- $score,
- $number,
- $courseid;
-}
-
-
-/**
-* split this into Cache class and extend to SearchCache?
-*/
-class SearchCache {
-private $mode,
- $valid;
-
- // foresees other caching locations
- public function __construct($mode = 'session') {
- $accepted_modes = array('session');
-
- if (in_array($mode, $accepted_modes)) {
- $this->mode = $mode;
- } else {
- $this->mode = 'session';
- } //else
-
- $this->valid = true;
- }
-
- /**
- * returns the search cache status
- * @return boolean
- */
- public function can_cache() {
- return $this->valid;
- }
-
- /**
- *
- *
- */
- public function cache($id = false, $object = false) {
- //see if there was a previous query
- $last_term = $this->fetch('search_last_term');
-
- //if this query is different from the last, clear out the last one
- if ($id != false && $last_term != $id) {
- $this->clear($last_term);
- }
-
- //store the new query if id and object are passed in
- if ($object && $id) {
- $this->store('search_last_term', $id);
- $this->store($id, $object);
- return true;
- //otherwise return the stored results
- } else if ($id && $this->exists($id)) {
- return $this->fetch($id);
- }
- }
-
- /**
- * do key exist in cache ?
- * @param id the object key
- * @return boolean
- */
- private function exists($id) {
- switch ($this->mode) {
- case 'session' :
- return isset($_SESSION[$id]);
- }
- }
-
- /**
- * clears a cached object in cache
- * @param the object key to clear
- * @return void
- */
- private function clear($id) {
- switch ($this->mode) {
- case 'session' :
- unset($_SESSION[$id]);
- session_unregister($id);
- return;
- }
- }
-
- /**
- * fetches a cached object
- * @param id the object identifier
- * @return the object cached
- */
- private function fetch($id) {
- switch ($this->mode) {
- case 'session' :
- return ($this->exists($id)) ? unserialize($_SESSION[$id]) : false;
- }
- }
-
- /**
- * put an object in cache
- * @param id the key for that object
- * @param object the object to cache as a serialized value
- * @return void
- */
- private function store($id, $object) {
- switch ($this->mode) {
- case 'session' :
- $_SESSION[$id] = serialize($object);
- return;
- }
- }
-}
-
-/**
-* Represents a single query with results
-*
-*/
-class SearchQuery {
- private $index,
- $term,
- $pagenumber,
- $cache,
- $validquery,
- $validindex,
- $results,
- $results_per_page,
- $total_results;
-
- /**
- * constructor records query parameters
- *
- */
- public function __construct($term = '', $page = 1, $results_per_page = 10, $cache = false) {
- global $CFG;
-
- $this->term = $term;
- $this->pagenumber = $page;
- $this->cache = $cache;
- $this->validquery = true;
- $this->validindex = true;
- $this->results_per_page = $results_per_page;
-
- $index_path = SEARCH_INDEX_PATH;
-
- try {
- $this->index = new Zend_Search_Lucene($index_path, false);
- } catch(Exception $e) {
- $this->validindex = false;
- return;
- }
-
- if (empty($this->term)) {
- $this->validquery = false;
- } else {
- $this->set_query($this->term);
- }
- }
-
- /**
- * determines state of query object depending on query entry and
- * tries to lauch search if all is OK
- * @return void (this is only a state changing trigger).
- */
- public function set_query($term = '') {
- if (!empty($term)) {
- $this->term = $term;
- }
-
- if (empty($this->term)) {
- $this->validquery = false;
- } else {
- $this->validquery = true;
- }
-
- if ($this->validquery and $this->validindex) {
- $this->results = $this->get_results();
- } else {
- $this->results = array();
- }
- }
-
- /**
- * accessor to the result table.
- * @return an array of result records
- */
- public function results() {
- return $this->results;
- }
-
- /**
- * do the effective collection of results
- * @param boolean $all
- * @uses USER
- */
- private function process_results($all=false) {
- global $USER;
-
- // unneeded since changing the default Zend Lexer
- // $term = mb_convert_case($this->term, MB_CASE_LOWER, 'UTF-8');
- $term = $this->term;
- $page = optional_param('page', 1, PARAM_INT);
-
- //experimental - return more results
- // $strip_arr = array('author:', 'title:', '+', '-', 'doctype:');
- // $stripped_term = str_replace($strip_arr, '', $term);
-
- // $search_string = $term." title:".$stripped_term." author:".$stripped_term;
- $search_string = $term;
- $hits = $this->index->find($search_string);
- //--
-
- $hitcount = count($hits);
- $this->total_results = $hitcount;
-
- if ($hitcount == 0) return array();
-
- $resultdoc = new SearchResult();
- $resultdocs = array();
- $searchables = search_collect_searchables(false, false);
-
- $realindex = 0;
-
- /**
- if (!$all) {
- if ($finalresults < $this->results_per_page) {
- $this->pagenumber = 1;
- } elseif ($this->pagenumber > $totalpages) {
- $this->pagenumber = $totalpages;
- }
-
- $start = ($this->pagenumber - 1) * $this->results_per_page;
- $end = $start + $this->results_per_page;
-
- if ($end > $finalresults) {
- $end = $finalresults;
- }
- } else {
- $start = 0;
- $end = $finalresults;
- } */
-
- for ($i = 0; $i < min($hitcount, ($page) * $this->results_per_page); $i++) {
- $hit = $hits[$i];
-
- //check permissions on each result
- if ($this->can_display($USER, $hit->docid, $hit->doctype, $hit->course_id, $hit->group_id, $hit->path, $hit->itemtype, $hit->context_id, $searchables )) {
- if ($i >= ($page - 1) * $this->results_per_page){
- $resultdoc->number = $realindex;
- $resultdoc->url = $hit->url;
- $resultdoc->title = $hit->title;
- $resultdoc->score = $hit->score;
- $resultdoc->doctype = $hit->doctype;
- $resultdoc->author = $hit->author;
- $resultdoc->courseid = $hit->course_id;
- $resultdoc->userid = $hit->user_id;
-
- //and store it
- $resultdocs[] = clone($resultdoc);
- }
- $realindex++;
- } else {
- // lowers total_results one unit
- $this->total_results--;
- }
- }
-
- $totalpages = ceil($this->total_results/$this->results_per_page);
-
-
- return $resultdocs;
- }
-
- /**
- * get results of a search query using a caching strategy if available
- * @return the result documents as an array of search objects
- */
- private function get_results() {
- $cache = new SearchCache();
-
- if ($this->cache && $cache->can_cache()) {
- if (!($resultdocs = $cache->cache($this->term))) {
- $resultdocs = $this->process_results();
- //cache the results so we don't have to compute this on every page-load
- $cache->cache($this->term, $resultdocs);
- //print "Using new results.";
- } else {
- //There was something in the cache, so we're using that to save time
- //print "Using cached results.";
- }
- } else {
- //no caching :(
- // print "Caching disabled!";
- $resultdocs = $this->process_results();
- }
- return $resultdocs;
- }
-
- /**
- * constructs the results paging links on results.
- * @return string the results paging links
- */
- public function page_numbers() {
- $pages = $this->total_pages();
- $query = htmlentities($this->term,ENT_NOQUOTES,'utf-8');
- $page = $this->pagenumber;
- $next = get_string('next', 'search');
- $back = get_string('back', 'search');
-
- $ret = "";
-
- //Back is disabled if we're on page 1
- if ($page > 1) {
- $ret .= "< {$back} ";
- } else {
- $ret .= "< {$back} ";
- }
-
- //don't the current page
- for ($i = 1; $i <= $pages; $i++) {
- if ($page == $i) {
- $ret .= "($i) ";
- } else {
- $ret .= "{$i} ";
- }
- }
-
- //Next disabled if we're on the last page
- if ($page < $pages) {
- $ret .= "{$next} > ";
- } else {
- $ret .= "{$next} > ";
- }
-
- $ret .= "
";
-
- //shorten really long page lists, to stop table distorting width-ways
- if (strlen($ret) > 70) {
- $start = 4;
- $end = $page - 5;
- $ret = preg_replace("/'; - } - -/// this is the standard summary table for normal users, shows document counts - - $table = new html_table(); - $table->tablealign = 'center'; - $table->align = array ('right', 'left'); - $table->wrap = array ('nowrap', 'nowrap'); - $table->cellpadding = 5; - $table->cellspacing = 0; - $table->width = '500'; - - $table->data[] = array("{$databasestr}", "{$CFG->prefix}".SEARCH_DATABASE_TABLE.''); - -/// add extra fields if we're admin - - if (has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) { - //don't want to confuse users if the two totals don't match (hint: they should) - $table->data[] = array($documentsinindexstr, $indexinfo->indexcount); - - //*cough* they should match if deletions were actually removed from the index, - //as it turns out, they're only marked as deleted and not returned in search results - $table->data[] = array($deletionsinindexstr, (int)$indexinfo->indexcount - (int)$indexinfo->dbcount); - } - - $table->data[] = array($documentsindatabasestr, $indexinfo->dbcount); - - foreach($indexinfo->types as $type) { - if ($type->type == 'mod'){ - $table->data[] = array(get_string('documentsfor', 'search') . " '".get_string('modulenameplural', $type->name)."'", $type->records); - } else if ($type->type == 'block') { - $table->data[] = array(get_string('documentsfor', 'search') . " '".get_string('pluginname', $type->name)."'", $type->records); - } else { - $table->data[] = array(get_string('documentsfor', 'search') . " '".get_string($type->name)."'", $type->records); - } - - } - - echo $OUTPUT->heading($databasestatestr); - echo html_writer::table($table); - - echo $OUTPUT->box_end(); - echo $OUTPUT->box_end(); - echo $OUTPUT->footer(); -?> diff --git a/search/tests/index.php b/search/tests/index.php deleted file mode 100644 index 594fd6330b3..00000000000 --- a/search/tests/index.php +++ /dev/null @@ -1,152 +0,0 @@ - 1.8 - * @date 2008/03/31 - * @license http://www.gnu.org/copyleft/gpl.html GNU Public License - * @version Moodle 2.0 - **/ - - define('NO_OUTPUT_BUFFERING', true); - - require_once('../../config.php'); - - @set_time_limit(0); -/// makes inclusions of the Zend Engine more reliable - ini_set('include_path', $CFG->dirroot.DIRECTORY_SEPARATOR.'search'.PATH_SEPARATOR.ini_get('include_path')); - - require_once($CFG->dirroot.'/search/lib.php'); - - require_login(); - - if (empty($CFG->enableglobalsearch)) { - print_error('globalsearchdisabled', 'search'); - } - - if (!has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) { - print_error('onlyadmins', 'error', get_login_url()); - } - - mtrace('
Server Time: '.date('r',time()));
- mtrace("Testing global search capabilities:\n");
-
- //fix paths for testing
- set_include_path(get_include_path().":../");
- require_once("$CFG->dirroot/search/Zend/Search/Lucene.php");
-
- mtrace("Checking 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.
-
-/// get all installed modules
- if ($mods = $DB->get_records('modules', null, 'name', 'id, name')){
-
- $searchabletypes = array_values(search_get_document_types());
-
- foreach($mods as $mod){
- if (in_array($mod->name, $searchabletypes)){
- $mod->location = 'internal';
- $searchables[] = $mod;
- } else {
- $documentfile = $CFG->dirroot."/mod/{$mod->name}/search_document.php";
- $mod->location = 'mod';
- if (file_exists($documentfile)){
- $searchables[] = $mod;
- }
- }
- }
- mtrace(count($searchables).' modules to search in / '.count($mods).' modules found.');
- }
-
-/// collects blocks as indexable information may be found in blocks either
- if ($blocks = $DB->get_records('block', null, 'name', 'id,name')) {
- $blocks_searchables = array();
- // prepend the "block_" prefix to discriminate document type plugins
- foreach($blocks as $block){
- $block->dirname = $block->name;
- $block->name = 'block_'.$block->name;
- if (in_array('SEARCH_TYPE_'.strtoupper($block->name), $searchabletypes)){
- $mod->location = 'internal';
- $blocks_searchables[] = $block;
- } else {
- $documentfile = $CFG->dirroot."/blocks/{$block->dirname}/search_document.php";
- if (file_exists($documentfile)){
- $mod->location = 'blocks';
- $blocks_searchables[] = $block;
- }
- }
- }
- mtrace(count($blocks_searchables).' blocks to search in / '.count($blocks).' blocks found.');
- $searchables = array_merge($searchables, $blocks_searchables);
- }
-
-/// add virtual modules onto the back of the array
-
- $additional = search_get_additional_modules();
- mtrace(count($additional).' additional to search in.');
- $searchables = array_merge($searchables, $additional);
-
- foreach ($searchables as $mod) {
-
- $key = 'search_in_'.$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)) {
- include_once($class_file);
-
- if ($mod->location != 'internal' && !defined('X_SEARCH_TYPE_'.strtoupper($mod->name))) {
- mtrace("ERROR: Constant 'X_SEARCH_TYPE_".strtoupper($mod->name)."' is not defined in search/searchtypes.php or in module");
- continue;
- }
-
- $iter_function = $mod->name.'_iterator';
- $index_function = $mod->name.'_get_content_for_index';
-
- if (function_exists($index_function) && function_exists($iter_function)) {
- $entries = $iter_function();
- if (!empty($entries)) {
- $documents = $index_function(array_pop($entries));
-
- if (is_array($documents)) {
- mtrace("Success: '$mod->name' module seems to be ready for indexing.");
- } else {
- mtrace("ERROR: $index_function() doesn't seem to be returning an array.");
- }
- } else {
- mtrace("Success : '$mod->name' has nothing to index.");
- }
- } else {
- mtrace("ERROR: $iter_function() and/or $index_function() does not exist in $class_file");
- }
- } else {
- mtrace("Notice: $class_file does not exist, this module will not be indexed.");
- }
- }
-
- mtrace("\nFinished checking for searcheable items.");
-
- mtrace("
Back to query page or Start indexing.");
- mtrace('');
-?>
\ No newline at end of file
diff --git a/search/update.php b/search/update.php
deleted file mode 100644
index eb75f555ad6..00000000000
--- a/search/update.php
+++ /dev/null
@@ -1,200 +0,0 @@
- 1.8
- * @date 2008/03/31
- * @version prepared for 2.0
- * @license http://www.gnu.org/copyleft/gpl.html GNU Public License
- *
- * Index asynchronous updator
- *
- * Major chages in this review is passing the xxxx_db_names return to
- * multiple arity to handle multiple document types modules
- */
-
- /**
- * includes and requires
- */
- require_once('../config.php');
-
- if (!defined('MOODLE_INTERNAL')) {
- die('Direct access to this script is forbidden.'); /// It must be included from the cron script
- }
-
- global $DB;
-
-/// makes inclusions of the Zend Engine more reliable
- ini_set('include_path', $CFG->dirroot.DIRECTORY_SEPARATOR.'search'.PATH_SEPARATOR.ini_get('include_path'));
-
- require_once($CFG->dirroot.'/search/lib.php');
- require_once($CFG->dirroot.'/search/indexlib.php');
-
-/// checks global search activation
-
- // require_login();
-
- if (empty($CFG->enableglobalsearch)) {
- print_error('globalsearchdisabled', 'search');
- }
-
- /*
- Obsolete with the MOODLE INTERNAL check
- if (!has_capability('moodle/site:config', get_context_instance(CONTEXT_SYSTEM))) {
- print_error('beadmin', 'search', get_login_url());
- }
- */
-
- try {
- $index = new Zend_Search_Lucene(SEARCH_INDEX_PATH);
- } catch(LuceneException $e) {
- mtrace("Could not construct a valid index. Maybe the first indexation was never made, or files might be corrupted. Run complete indexation again.");
- return;
- }
- $dbcontrol = new IndexDBControl();
- $update_count = 0;
- $mainstartupdatedate = time();
-
-/// indexing changed resources
-
- mtrace("Starting index update (updates)...\n");
-
- if ($mods = search_collect_searchables(false, true)){
-
- foreach ($mods as $mod) {
- $indexdate = 0;
- $indexdatestring = 'search_indexer_update_date_'.$mod->name;
- $startupdatedate = time();
- if (isset($CFG->$indexdatestring)) {
- $indexdate = $CFG->$indexdatestring;
- }
-
- $class_file = $CFG->dirroot.'/search/documents/'.$mod->name.'_document.php';
- $get_document_function = $mod->name.'_single_document';
- $delete_function = $mod->name.'_delete';
- $db_names_function = $mod->name.'_db_names';
- $updates = array();
-
- if (file_exists($class_file)) {
- require_once($class_file);
-
- //if both required functions exist
- if (function_exists($delete_function) and function_exists($db_names_function) and function_exists($get_document_function)) {
- mtrace("Checking $mod->name module for updates.");
- $valuesArray = $db_names_function();
- if ($valuesArray){
- foreach($valuesArray as $values){
- $where = (isset($values[5]) and $values[5]!='') ? 'AND ('.$values[5].')' : '';
- $itemtypes = ($values[4] != '*' && $values[4] != 'any') ? " AND itemtype = '{$values[4]}' " : '' ;
-
- //TODO: check 'in' syntax with other RDBMS' (add and update.php as well)
- $table = SEARCH_DATABASE_TABLE;
- $query = "
- SELECT
- docid,
- itemtype
- FROM
- {{$table}}
- WHERE
- doctype = ?
- $itemtypes
- ";
- $docIds = $DB->get_records_sql_menu($query, array($mod->name));
- if (!empty($docIds)){
- list($usql, $params) = $DB->get_in_or_equal(array_keys($docIds));
- $query = "
- SELECT
- id,
- $values[0] as docid
- FROM
- {{$values[1]}}
- WHERE
- $values[3] > $indexdate AND
- id $usql
- $where
- ";
- $records = $DB->get_records_sql($query, $params);
- } else {
- $records = array();
- }
-
- foreach($records as $record) {
- $updates[] = $delete_function($record->docid, $docIds[$record->docid]);
- }
- }
-
- foreach ($updates as $update) {
- ++$update_count;
- $added_doc = false;
-
- //get old document for deletion later
- // change from default text only search to include numerals for this search.
- Zend_Search_Lucene_Analysis_Analyzer::setDefault(new Zend_Search_Lucene_Analysis_Analyzer_Common_TextNum_CaseInsensitive());
- $doc = $index->find("+docid:{$update->id} +doctype:{$mod->name} +itemtype:{$update->itemtype}");
-
- try {
- //add new modified document back into index
- $add = $get_document_function($update->id, $update->itemtype);
-
- //object to insert into db
- $dbid = $dbcontrol->addDocument($add);
-
- //synchronise db with index
- $add->addField(Zend_Search_Lucene_Field::Keyword('dbid', $dbid));
- mtrace(" Add: $add->title (database id = $add->dbid, moodle instance id = $add->docid)");
- $index->addDocument($add);
- $added_doc = true;
- }
-
- catch (dml_write_exception $e) {
- mtrace(" Add: FAILED adding '$add->title' , moodle instance id = $add->docid , Error: $e->error ");
- mtrace($e);
- $added_doc = false;
- }
-
- if ($added_doc) {
- // ok we've successfully added the new document so far
- // delete single previous old document
- try {
- //get the record, should only be one
- foreach ($doc as $thisdoc) {
- mtrace(" Delete: $thisdoc->title (database id = $thisdoc->dbid, index id = $thisdoc->id, moodle instance id = $thisdoc->docid)");
- $dbcontrol->delDocument($thisdoc);
- $index->delete($thisdoc->id);
- }
- }
-
- catch (dml_write_exception $e) {
- mtrace(" Delete: FAILED deleting '$thisdoc->title' , moodle instance id = $thisdoc->docid , Error: $e->error ");
- mtrace($e);
- }
- }
- }
- }
- else{
- mtrace("No types to update.\n");
- }
- //commit changes
- $index->commit();
-
- //update index date
- set_config($indexdatestring, $startupdatedate);
-
- mtrace("Finished $mod->name.\n");
- }
- }
- }
- }
-
- //commit changes
- $index->commit();
-
- //update index date
- set_config('search_indexer_update_date', $mainstartupdatedate);
-
- mtrace("Finished $update_count updates");
-
-?>
\ No newline at end of file
diff --git a/version.php b/version.php
index 6bcc026af5b..a8ec5fc4c2b 100644
--- a/version.php
+++ b/version.php
@@ -31,7 +31,7 @@ defined('MOODLE_INTERNAL') || die();
-$version = 2011102700.00; // YYYYMMDD = weekly release date of this DEV branch
+$version = 2011102700.01; // YYYYMMDD = weekly release date of this DEV branch
// RR = release increments - 00 in DEV branches
// .XX = incremental changes