diff options
Diffstat (limited to 'modules/search/search.module')
| -rw-r--r-- | modules/search/search.module | 380 |
1 files changed, 78 insertions, 302 deletions
diff --git a/modules/search/search.module b/modules/search/search.module index 5ac6fbacc..e80eddacc 100644 --- a/modules/search/search.module +++ b/modules/search/search.module @@ -253,11 +253,20 @@ function search_reindex($sid = NULL, $type = NULL, $reindex = FALSE) { module_invoke_all('search', 'reset'); } else { - db_query("DELETE FROM {search_dataset} WHERE sid = %d AND type = '%s'", $sid, $type); - db_query("DELETE FROM {search_index} WHERE sid = %d AND type = '%s'", $sid, $type); + db_delete('search_dataset') + ->condition('sid', $sid) + ->condition('type', $type) + ->execute(); + db_delete('search_index') + ->condition('sid', $sid) + ->condition('type', $type) + ->execute(); // Don't remove links if re-indexing. if (!$reindex) { - db_query("DELETE FROM {search_node_links} WHERE sid = %d AND type = '%s'", $sid, $type); + db_delete('search_node_links') + ->condition('sid', $sid) + ->condition('type', $type) + ->execute(); } } } @@ -297,20 +306,29 @@ function search_cron() { * up to date (even if cron times out or otherwise fails). */ function search_update_totals() { - // Update word IDF (Inverse Document Frequency) counts for new/changed words + // Update word IDF (Inverse Document Frequency) counts for new/changed words. foreach (search_dirty() as $word => $dummy) { // Get total count - $total = db_result(db_query("SELECT SUM(score) FROM {search_index} WHERE word = '%s'", $word)); - // Apply Zipf's law to equalize the probability distribution + $total = db_query("SELECT SUM(score) FROM {search_index} WHERE word = :word", array(':word' => $word))->fetchField(); + // Apply Zipf's law to equalize the probability distribution. $total = log10(1 + 1/(max(1, $total))); - db_merge('search_total')->key(array('word' => $word))->fields(array('count' => $total))->execute(); + db_merge('search_total') + ->key(array('word' => $word)) + ->fields(array('count' => $total)) + ->execute(); } // 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); + $or = db_or(); + foreach ($result as $word) { + $or->condition('word', $word->realword); + } + if (count($or) > 0) { + db_delete('search_total') + ->condition($or) + ->execute(); } } @@ -583,27 +601,40 @@ function search_index($sid, $type, $text) { search_reindex($sid, $type, TRUE); // Insert cleaned up data into dataset - db_query("INSERT INTO {search_dataset} (sid, type, data, reindex) VALUES (%d, '%s', '%s', %d)", $sid, $type, $accum, 0); + db_insert('search_dataset') + ->fields(array( + 'sid' => $sid, + 'type' => $type, + 'data' => $accum, + 'reindex' => 0, + )) + ->execute(); // Insert results into search index foreach ($results[0] as $word => $score) { // If a word already exists in the database, its score gets increased // appropriately. If not, we create a new record with the appropriate // starting score. - db_merge('search_index')->key(array( - 'word' => $word, - 'sid' => $sid, - 'type' => $type, - ))->fields(array('score' => $score))->expression('score', 'score + :score', array(':score' => $score)) - ->execute(); + db_merge('search_index') + ->key(array( + 'word' => $word, + 'sid' => $sid, + 'type' => $type, + )) + ->fields(array('score' => $score)) + ->expression('score', 'score + :score', array(':score' => $score)) + ->execute(); search_dirty($word); } unset($results[0]); // Get all previous links from this item. - $result = db_query("SELECT nid, caption FROM {search_node_links} WHERE sid = %d AND type = '%s'", $sid, $type); + $result = db_query("SELECT nid, caption FROM {search_node_links} WHERE sid = :sid AND type = :type", array( + ':sid' => $sid, + ':type' => $type + )); $links = array(); - while ($link = db_fetch_object($result)) { + foreach ($result as $link) { $links[$link->nid] = $link->caption; } @@ -613,7 +644,12 @@ function search_index($sid, $type, $text) { if (isset($links[$nid])) { if ($links[$nid] != $caption) { // Update the existing link and mark the node for reindexing. - db_query("UPDATE {search_node_links} SET caption = '%s' WHERE sid = %d AND type = '%s' AND nid = %d", $caption, $sid, $type, $nid); + db_update('search_node_links') + ->fields(array('caption' => $caption)) + ->condition('sid', $sid) + ->condition('type', $type) + ->condition('nid', $nid) + ->execute(); search_touch_node($nid); } // Unset the link to mark it as processed. @@ -621,13 +657,24 @@ function search_index($sid, $type, $text) { } else { // Insert the existing link and mark the node for reindexing. - db_query("INSERT INTO {search_node_links} (caption, sid, type, nid) VALUES ('%s', %d, '%s', %d)", $caption, $sid, $type, $nid); + db_insert('search_node_links') + ->fields(array( + 'caption' => $caption, + 'sid' => $sid, + 'type' => $type, + 'nid' => $nid, + )) + ->execute(); search_touch_node($nid); } } // Any left-over links in $links no longer exist. Delete them and mark the nodes for reindexing. foreach ($links as $nid => $caption) { - db_query("DELETE FROM {search_node_links} WHERE sid = %d AND type = '%s' AND nid = %d", $sid, $type, $nid); + db_delete('search_node_links') + ->condition('sid', $sid) + ->condition('type', $type) + ->condition('nid', $nid) + ->execute(); search_touch_node($nid); } } @@ -639,7 +686,11 @@ function search_index($sid, $type, $text) { * The nid of the node that needs reindexing. */ function search_touch_node($nid) { - db_query("UPDATE {search_dataset} SET reindex = %d WHERE sid = %d AND type = 'node'", REQUEST_TIME, $nid); + db_update('search_dataset') + ->fields(array('reindex' => REQUEST_TIME)) + ->condition('type', 'node') + ->condition('sid', $nid) + ->execute(); } /** @@ -647,9 +698,9 @@ function search_touch_node($nid) { */ function search_node_update_index($node) { // Transplant links to a node into the target node. - $result = db_query("SELECT caption FROM {search_node_links} WHERE nid = %d", $node->nid); + $result = db_query("SELECT caption FROM {search_node_links} WHERE nid = :nid", array(':nid' => $node->nid)); $output = array(); - while ($link = db_fetch_object($result)) { + foreach ($result as $link) { $output[] = $link->caption; } if (count($output)) { @@ -709,7 +760,7 @@ function search_comment_unpublish($comment) { /** * Extract a module-specific search option from a search query. e.g. 'type:book' */ -function search_query_extract($keys, $option) { +function search_expression_extract($keys, $option) { if (preg_match('/(^| )' . $option . ':([^ ]*)( |$)/i', $keys, $matches)) { return $matches[2]; } @@ -719,8 +770,8 @@ function search_query_extract($keys, $option) { * Return a query with the given module-specific search option inserted in. * e.g. 'type:book'. */ -function search_query_insert($keys, $option, $value = '') { - if (search_query_extract($keys, $option)) { +function search_expression_insert($keys, $option, $value = '') { + if (search_expression_extract($keys, $option)) { $keys = trim(preg_replace('/(^| )' . $option . ':[^ ]*/i', '', $keys)); } if ($value != '') { @@ -730,281 +781,6 @@ function search_query_insert($keys, $option, $value = '') { } /** - * Parse a search query into SQL conditions. - * - * We build two queries that matches the dataset bodies. @See do_search for - * more about these. - * - * @param $text - * The search keys. - * @return - * A list of six elements. - * * A series of statements AND'd together which will be used to provide all - * possible matches. - * * Arguments for this query part. - * * A series of exact word matches OR'd together. - * * Arguments for this query part. - * * A boolean indicating whether this is a simple query or not. Negative - * terms, presence of both AND / OR make this FALSE. - * * A boolean indicating the presence of a lowercase or. Maybe the user - * wanted to use OR. - */ -function search_parse_query($text) { - $keys = array('positive' => array(), 'negative' => array()); - - // Tokenize query string - preg_match_all('/ (-?)("[^"]+"|[^" ]+)/i', ' ' . $text, $matches, PREG_SET_ORDER); - - if (count($matches) < 1) { - return NULL; - } - - // Classify tokens - $or = FALSE; - $warning = ''; - $simple = TRUE; - foreach ($matches as $match) { - $phrase = FALSE; - // Strip off phrase quotes - if ($match[2]{0} == '"') { - $match[2] = substr($match[2], 1, -1); - $phrase = TRUE; - $simple = FALSE; - } - // Simplify keyword according to indexing rules and external preprocessors - $words = search_simplify($match[2]); - // Re-explode in case simplification added more words, except when matching a phrase - $words = $phrase ? array($words) : preg_split('/ /', $words, -1, PREG_SPLIT_NO_EMPTY); - // Negative matches - if ($match[1] == '-') { - $keys['negative'] = array_merge($keys['negative'], $words); - } - // OR operator: instead of a single keyword, we store an array of all - // OR'd keywords. - elseif ($match[2] == 'OR' && count($keys['positive'])) { - $last = array_pop($keys['positive']); - // Starting a new OR? - if (!is_array($last)) { - $last = array($last); - } - $keys['positive'][] = $last; - $or = TRUE; - continue; - } - // AND operator: implied, so just ignore it - elseif ($match[2] == 'AND' || $match[2] == 'and') { - $warning = $match[2]; - continue; - } - - // Plain keyword - else { - if ($match[2] == 'or') { - $warning = $match[2]; - } - if ($or) { - // Add to last element (which is an array) - $keys['positive'][count($keys['positive']) - 1] = array_merge($keys['positive'][count($keys['positive']) - 1], $words); - } - else { - $keys['positive'] = array_merge($keys['positive'], $words); - } - } - $or = FALSE; - } - - // Convert keywords into SQL statements. - $query = array(); - $query2 = array(); - $arguments = array(); - $arguments2 = array(); - $matches = 0; - $simple_and = FALSE; - $simple_or = FALSE; - // Positive matches - foreach ($keys['positive'] as $key) { - // Group of ORed terms - if (is_array($key) && count($key)) { - $simple_or = TRUE; - $queryor = array(); - $any = FALSE; - foreach ($key as $or) { - list($q, $num_new_scores) = _search_parse_query($or, $arguments2); - $any |= $num_new_scores; - if ($q) { - $queryor[] = $q; - $arguments[] = "% $or %"; - } - } - if (count($queryor)) { - $query[] = '(' . implode(' OR ', $queryor) . ')'; - // A group of OR keywords only needs to match once - $matches += ($any > 0); - } - } - // Single ANDed term - else { - $simple_and = TRUE; - list($q, $num_new_scores, $num_valid_words) = _search_parse_query($key, $arguments2); - if ($q) { - $query[] = $q; - $arguments[] = "% $key %"; - if (!$num_valid_words) { - $simple = FALSE; - } - // Each AND keyword needs to match at least once - $matches += $num_new_scores; - } - } - } - if ($simple_and && $simple_or) { - $simple = FALSE; - } - // Negative matches - foreach ($keys['negative'] as $key) { - list($q) = _search_parse_query($key, $arguments2, TRUE); - if ($q) { - $query[] = $q; - $arguments[] = "% $key %"; - $simple = FALSE; - } - } - $query = implode(' AND ', $query); - - // Build word-index conditions for the first pass - $query2 = substr(str_repeat("i.word = '%s' OR ", count($arguments2)), 0, -4); - - return array($query, $arguments, $query2, $arguments2, $matches, $simple, $warning); -} - -/** - * Helper function for search_parse_query(); - */ -function _search_parse_query(&$word, &$scores, $not = FALSE) { - $num_new_scores = 0; - $num_valid_words = 0; - // Determine the scorewords of this word/phrase - if (!$not) { - $split = explode(' ', $word); - foreach ($split as $s) { - $num = is_numeric($s); - if ($num || drupal_strlen($s) >= variable_get('minimum_word_size', 3)) { - $s = $num ? ((int)ltrim($s, '-0')) : $s; - if (!isset($scores[$s])) { - $scores[$s] = $s; - $num_new_scores++; - } - $num_valid_words++; - } - } - } - // Return matching snippet and number of added words - return array("d.data " . ($not ? 'NOT ' : '') . "LIKE '%s'", $num_new_scores, $num_valid_words); -} - -/** - * Do a query on the full-text search index for a word or words. - * - * This function is normally only called by each module that support the - * indexed search (and thus, implements hook_update_index()). - * - * Results are retrieved in two logical passes. However, the two passes are - * joined together into a single query. And in the case of most simple - * queries the second pass is not even used. - * - * The first pass selects a set of all possible matches, which has the benefit - * of also providing the exact result set for simple "AND" or "OR" searches. - * - * The second portion of the query further refines this set by verifying - * advanced text conditions (such negative or phrase matches) - * - * @param $keywords - * A search string as entered by the user. - * - * @param $type - * A string identifying the calling module. - * - * @param $join1 - * (optional) Inserted into the JOIN part of the first SQL query. - * For example "INNER JOIN {node} n ON n.nid = i.sid". - * - * @param $where1 - * (optional) Inserted into the WHERE part of the first SQL query. - * For example "(n.status > %d)". - * - * @param $arguments1 - * (optional) Extra SQL arguments belonging to the first query. - * - * @param $columns2 - * (optional) Inserted into the SELECT pat of the second query. Must contain - * a column selected as 'calculated_score'. - * defaults to 'SUM(i.relevance) AS calculated_score' - * - * @param $join2 - * (optional) Inserted into the JOIN par of the second SQL query. - * For example "INNER JOIN {node_comment_statistics} n ON n.nid = i.sid" - * - * @param $arguments2 - * (optional) Extra SQL arguments belonging to the second query parameter. - * - * @param $sort_parameters - * (optional) SQL arguments for sorting the final results. - * Default: 'ORDER BY calculated_score DESC' - * - * @return - * An array of SIDs for the search results. - * - * @ingroup search - */ -function do_search($keywords, $type, $join1 = '', $where1 = '1 = 1', $arguments1 = array(), $columns2 = 'SUM(i.relevance) AS calculated_score', $join2 = '', $arguments2 = array(), $sort_parameters = 'ORDER BY calculated_score DESC') { - $query = search_parse_query($keywords); - - if ($query[2] == '') { - form_set_error('keys', format_plural(variable_get('minimum_word_size', 3), 'You must include at least one positive keyword with 1 character or more.', 'You must include at least one positive keyword with @count characters or more.')); - } - if ($query[6]) { - if ($query[6] == 'or') { - drupal_set_message(t('Search for either of the two terms with uppercase <strong>OR</strong>. For example, <strong>cats OR dogs</strong>.')); - } - } - if ($query === NULL || $query[0] == '' || $query[2] == '') { - return array(); - } - - // Build query for keyword normalization. - $conditions = "$where1 AND ($query[2]) AND i.type = '%s'"; - $arguments1 = array_merge($arguments1, $query[3], array($type)); - $join = "INNER JOIN {search_total} t ON i.word = t.word $join1"; - if (!$query[5]) { - $conditions .= " AND ($query[0])"; - $arguments1 = array_merge($arguments1, $query[1]); - $join .= " INNER JOIN {search_dataset} d ON i.sid = d.sid AND i.type = d.type"; - } - - // Calculate maximum keyword relevance, to normalize it. - $select = "SELECT SUM(i.score * t.count) AS calculated_score FROM {search_index} i $join WHERE $conditions GROUP BY i.type, i.sid HAVING COUNT(*) >= %d ORDER BY calculated_score DESC"; - $arguments = array_merge($arguments1, array($query[4])); - $normalize = db_result(db_query_range($select, $arguments, 0, 1)); - if (!$normalize) { - return array(); - } - $columns2 = str_replace('i.relevance', '(' . (1.0 / $normalize) . ' * i.score * t.count)', $columns2); - - // Build query to retrieve results. - $select = "SELECT i.type, i.sid, $columns2 FROM {search_index} i $join $join2 WHERE $conditions GROUP BY i.type, i.sid HAVING COUNT(*) >= %d"; - $count_select = "SELECT COUNT(*) FROM ($select) n1"; - $arguments = array_values(array_merge($arguments2, $arguments1, array($query[4]))); - - // Do actual search query - $result = pager_query("$select $sort_parameters", 10, 0, $count_select, $arguments); - $results = array(); - while ($item = db_fetch_object($result)) { - $results[] = $item; - } - return $results; -} - -/** * Helper function for grabbing search keys. */ function search_get_keys() { |