Changes to these settings will only apply to content that is indexed after the change. If you want them to apply to everything, you need to wipe the index with the button below.
'); case 'search#noresults': return t(''. t('Approximately %percentage of the site has been indexed.', array('%percentage' => $percentage)) .'
'; $status .= ''. form_button(t('Wipe index')) . '
'; $output .= form_group('Indexing status', $status); print theme('page', system_settings_form($output)); } /** * Wipes a part of or the entire search index. * * @param $sid * (optional) The SID of the item to wipe. If specified, $type must be passed * too. * @param $type * (optional) The type of item to wipe. * */ function search_wipe($sid = NULL, $type = NULL) { if ($type == NULL && $sid == NULL) { db_query('DELETE FROM {search_index}'); db_query('DELETE FROM {search_total}'); module_invoke_all('search', 'reset'); } else { db_query("DELETE FROM {search_index} WHERE sid = %d AND type = '%s'", $sid, $type); db_query("DELETE FROM {search_index} WHERE fromsid = %d AND fromtype = '%s'", $sid, $type); } } /** * Marks a word as dirty (or retrieves the list of dirty words). This is used * during indexing (cron). Words which are dirty have outdated total counts in * the search_total table, and need to be recounted. */ function search_dirty($word = null) { static $dirty = array(); if ($word !== null) { $dirty[$word] = true; } else { return $dirty; } } /** * Implementation of hook_cron(). * * Fires hook_update_index() in all modules and cleans up dirty words (see * search_dirty). */ function search_cron() { // Update word index foreach (module_list() as $module) { module_invoke($module, 'update_index'); } // Update word counts for new/changed words foreach (search_dirty() as $word => $dummy) { $total = db_result(db_query("SELECT SUM(score) FROM {search_index} WHERE word = '%s'", $word)); db_query("UPDATE {search_total} SET count = %d WHERE word = '%s'", $total, $word); if (!db_affected_rows()) { db_query("INSERT INTO {search_total} (word, count) VALUES ('%s', %d)", $word, $total); } } // Find words that were deleted from search_index, but are still in // search_total. We use a LEFT JOIN between the two tables and keep only the // rows which fail to join. $result = db_query("SELECT t.word AS realword, i.word FROM {search_total} t LEFT JOIN {search_index} i ON t.word = i.word WHERE i.word IS NULL"); while ($word = db_fetch_object($result)) { db_query("DELETE FROM {search_total} WHERE word = '%s'", $word->realword); } // Count indexed items (for administration screen) $indexed = db_result(db_query('SELECT COUNT(DISTINCT sid) FROM {search_index}')); variable_set('search_indexed', $indexed); } /** * Splits a string into component words according to indexing rules. */ function search_keywords_split($text) { static $last = null; static $lastsplit = null; if ($last == $text) { return $lastsplit; } // Decode entities to UTF-8 $text = decode_entities($text); // Call an external processor for word handling. search_preprocess($text); // To improve searching for numerical data such as dates, IP addresses // or version numbers, we consider a group of numerical characters // separated only by punctuation characters to be one piece. // This also means that searching for e.g. '20/03/1984' also returns // results with '20-03-1984' in them. // Readable regexp: ([number]+)[punctuation]+(?=[number]) $text = preg_replace('/(['. PREG_CLASS_NUMBERS .']+)['. PREG_CLASS_PUNCTUATION .']+(?=['. PREG_CLASS_NUMBERS .'])/u', '\1', $text); // The dot, underscore and dash are simply removed. This allows meaningful // search behaviour with acronyms and URLs. $text = preg_replace('/[._-]+/', '', $text); // With the exception of the rules above, we consider all punctuation, // marks, spacers, etc, to be a word boundary. $text = preg_replace('/['. PREG_CLASS_SEARCH_EXCLUDE . ']+/u', ' ', $text); // Process words $words = explode(' ', $text); // Save last keyword result $last = $text; $lastsplit = $words; return $words; } /** * Invokes hook_search_preprocess() in modules. */ function search_preprocess(&$text) { static $modules = null; // Cache list of modules which implement this hook. This function gets called // a lot during reindexing. if (!is_array($modules)) { $modules = array(); foreach (module_list() as $module) { if (module_hook($module, 'search_preprocess')) { $modules[] = $module; } } } // Process $text if (count($modules) > 0) { foreach ($modules as $module) { $text = module_invoke($module, 'search_preprocess', $text); } } } /** * Update the search index for a particular item. * * @param $sid * A number identifying this particular item (e.g. node id). * * @param $type * A string defining this type of item (e.g. 'node') * * @param $text * The content of this item. Must be a piece of HTML text. */ function search_index($sid, $type, $text) { $minimum_word_size = variable_get('minimum_word_size', 3); global $base_url; $node_regexp = '!href=[\'"]?(?:'. preg_quote($base_url) .'/)?(?:\?q=)?([^\'">]+)[\'">]!i'; // Multipliers for scores of words inside certain HTML tags. // Note: 'a' must be included for link ranking to work. $tags = array('h1' => 21, 'h2' => 18, 'h3' => 15, 'h4' => 12, 'h5' => 9, 'h6' => 6, 'u' => 5, 'b' => 5, 'strong' => 5, 'em' => 5, 'a' => 10); // Strip off all ignored tags to speed up processing, but insert space before/after // them to keep word boundaries. $text = str_replace(array('<', '>'), array(' <', '> '), $text); $text = strip_tags($text, '<'. implode('><', array_keys($tags)) .'>'); // Split HTML tags from plain text. $split = preg_split('/\s*<([^>]+?)>\s*/', $text, -1, PREG_SPLIT_DELIM_CAPTURE); // Note: PHP ensures the array consists of alternating delimiters and literals // and begins and ends with a literal (inserting $null as required). $tag = false; // Odd/even counter. Tag or no tag. $link = false; // State variable for link analyser $score = 1; // Starting score per word $results = array(0 => array()); foreach ($split as $value) { if ($tag) { // Increase or decrease score per word based on tag list($tagname) = explode(' ', $value, 2); $tagname = strtolower($tagname); if ($tagname{0} == '/') { $score -= $tags[substr($tagname, 1)]; if ($score < 1) { // possible due to bad HTML $score = 1; } if ($tagname == '/a') { $link = false; } } else { if ($tagname == 'a') { // Check if link points to a node on this site if (preg_match($node_regexp, $value, $match)) { $path = drupal_get_normal_path($match[1]); if (preg_match('!(node|book)/(?:view/)?([0-9]+)!i', $path, $match)) { $linknid = $match[1]; if ($linknid > 0) { $link = true; } } } } $score += $tags[$tagname]; } } else { // Note: use of PREG_SPLIT_DELIM_CAPTURE above will introduce empty values if ($value != '') { $words = search_keywords_split($value); foreach ($words as $word) { // Check wordlength if (string_length($word) >= $minimum_word_size) { $word = strtolower($word); if ($link) { if (!isset($results[$linknid])) { $results[$linknid] = array(); } $results[$linknid][$word] += $score; } else { $results[0][$word] += $score; } } } } } $tag = !$tag; } search_wipe($sid, $type); // Insert results into search index foreach ($results[0] as $word => $score) { db_query("INSERT INTO {search_index} (word, sid, type, score) VALUES ('%s', %d, '%s', %d)", $word, $sid, $type, $score); search_dirty($word); } unset($results[0]); // Now insert links to nodes foreach ($results as $nid => $words) { foreach ($words as $word => $score) { db_query("INSERT INTO {search_index} (word, sid, type, fromsid, fromtype, score) VALUES ('%s', %d, '%s', %d, '%s', %d)", $word, $nid, 'node', $sid, $type, $score); search_dirty($word); } } } /** * Perform a search on a word or words. * * This function is called by each module that supports the indexed search. * * The end result is an SQL select on the search_index table. As a guide for * writing the optional extra SQL fragments (see below), use this query: * * SELECT i.type, i.sid, i.word, SUM(i.score/t.count) AS score * FROM {search_index} i * $join INNER JOIN {search_total} t ON i.word = t.word * WHERE $where AND (i.word = '...' OR ...) * GROUP BY i.type, i.sid * ORDER BY score DESC"; * * @param $keys * A search string as entered by the user. * * @param $type * A string identifying the calling module. * * @param $join * (optional) A string to be inserted into the JOIN part of the SQL query. * For example "INNER JOIN {node} n ON n.nid = i.sid". * * @param $where * (optional) A string to be inserted into the WHERE part of the SQL query. * For example "(n.status > 0)". * * @return * An array of SIDs for the search results. */ function do_search($keys, $type, $join = '', $where = '1') { // Note, we replace the wildcards with U+FFFD (Replacement character) to pass // through the keyword extractor. $keys = str_replace('*', '�', $keys); // Split into words $keys = search_keywords_split($keys); // Lowercase foreach ($keys as $k => $v) { $keys[$k] = strtolower($v); } $words = array(); $arguments = array(); // Build WHERE clause foreach ($keys as $word) { if (string_length($word) < variable_get('remove_short', 3)) { continue; } if (strpos($word, '�') !== false) { $words[] = "i.word LIKE '%s'"; $arguments[] = str_replace('�', '%', $word); } else { $words[] = "i.word = '%s'"; $arguments[] = $word; } } if (count($words) == 0) { return array(); } $where .= ' AND ('. implode(' OR ', $words) .')'; // Get result count (for pager) $count = db_result(db_query("SELECT COUNT(DISTINCT i.sid, i.type) FROM {search_index} i $join WHERE $where", $arguments)); if ($count == 0) { return array(); } $count_query = "SELECT $count"; // Do pager query $query = "SELECT i.type, i.sid, i.word, SUM(i.score/t.count) AS score FROM {search_index} i $join INNER JOIN {search_total} t ON i.word = t.word WHERE $where GROUP BY i.type, i.sid ORDER BY score DESC"; $result = pager_query($query, 15, 0, $count_query, $arguments); $results = array(); while ($item = db_fetch_object($result)) { $results[] = $item->sid; } return $results; } /** * Menu callback; presents the search form and/or search results. */ function search_view() { $keys = isset($_GET['keys']) ? $_GET['keys'] : $_POST['edit']['keys']; $type = isset($_GET['type']) ? $_GET['type'] : ($_POST['edit']['type'] ? $_POST['edit']['type'] : 'node'); if (user_access('search content')) { // Only perform search if there is non-whitespace search term: if (trim($keys)) { // Log the search keys: watchdog('search', t('Search: %keys (%type).', array('%keys' => "$keys", '%type' => module_invoke($type, 'search', 'name'))), l(t('results'), 'search', NULL, 'keys='. urlencode($keys) . '&type='. urlencode($type)) ); // Collect the search results: $results = search_data($keys, $type); if ($results) { $results = theme('box', t('Search results'), $results); } else { $results = theme('box', t('Your search yielded no results'), search_help('search#noresults')); } } else if (isset($_POST['edit'])) { form_set_error('keys', t('Please enter some keywords.')); } // Construct the search form. // Note, we do this last because of the form_set_error() above. $output = search_form(NULL, $keys, $type, TRUE); $output .= $results; print theme('page', $output, t('Search')); } else { drupal_access_denied(); } } /** * @defgroup search Search interface * @{ * The Drupal search interface manages a global search mechanism. * * Modules may plug into this system to provide searches of different types of * data. Most of the system is handled by search.module, so this must be enabled * for all of the search features to work. */ /** * Render a search form. * * This form must be usable not only within "http://example.com/search", but also * as a simple search box (without "Restrict search to", help text, etc.), in the * theme's header, and so forth. This means we must provide options to * conditionally render certain parts of this form. * * @param $action * Form action. Defaults to "search". * @param $keys * The search string entered by the user, containing keywords for the search. * @param $options * Whether to render the optional form fields and text ("Restrict search * to", help text, etc.). * @return * An HTML string containing the search form. */ function search_form($action = '', $keys = '', $type = null, $options = FALSE) { $edit = $_POST['edit']; if (!$action) { $action = url('search'); } $output = ''. $item['snippet'] . '
' : '') . '' . implode(' - ', $info) .'