Parses the search query into SQL conditions.
We build two queries that match the dataset bodies.
protected function parseSearchExpression() {
// Matchs words optionally prefixed by a dash. A word in this case is
// something between two spaces, optionally quoted.
preg_match_all('/ (-?)("[^"]+"|[^" ]+)/i', ' ' . $this->searchExpression, $keywords, PREG_SET_ORDER);
if (count($keywords) == 0) {
return;
}
// Classify tokens.
$or = FALSE;
$warning = '';
$limit_combinations = config('search.settings')
->get('and_or_limit');
// The first search expression does not count as AND.
$and_count = -1;
$or_count = 0;
foreach ($keywords as $match) {
if ($or_count && $and_count + $or_count >= $limit_combinations) {
// Ignore all further search expressions to prevent Denial-of-Service
// attacks using a high number of AND/OR combinations.
$this->expressionsIgnored = TRUE;
break;
}
$phrase = FALSE;
// Strip off phrase quotes.
if ($match[2][0] == '"') {
$match[2] = substr($match[2], 1, -1);
$phrase = TRUE;
$this->simple = FALSE;
}
// Simplify keyword according to indexing rules and external
// preprocessors. Use same process as during search indexing, so it
// will match search index.
$words = search_simplify($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] == '-') {
$this->keys['negative'] = array_merge($this->keys['negative'], $words);
}
elseif ($match[2] == 'OR' && count($this->keys['positive'])) {
$last = array_pop($this->keys['positive']);
// Starting a new OR?
if (!is_array($last)) {
$last = array(
$last,
);
}
$this->keys['positive'][] = $last;
$or = TRUE;
$or_count++;
continue;
}
elseif ($match[2] == 'AND' || $match[2] == 'and') {
$warning = $match[2];
continue;
}
else {
if ($match[2] == 'or') {
$warning = $match[2];
}
if ($or) {
// Add to last element (which is an array).
$this->keys['positive'][count($this->keys['positive']) - 1] = array_merge($this->keys['positive'][count($this->keys['positive']) - 1], $words);
}
else {
$this->keys['positive'] = array_merge($this->keys['positive'], $words);
$and_count++;
}
}
$or = FALSE;
}
// Convert keywords into SQL statements.
$this->conditions = db_and();
$simple_and = FALSE;
$simple_or = FALSE;
// Positive matches.
foreach ($this->keys['positive'] as $key) {
// Group of ORed terms.
if (is_array($key) && count($key)) {
$simple_or = TRUE;
$any = FALSE;
$queryor = db_or();
foreach ($key as $or) {
list($num_new_scores) = $this
->parseWord($or);
$any |= $num_new_scores;
$queryor
->condition('d.data', "% {$or} %", 'LIKE');
}
if (count($queryor)) {
$this->conditions
->condition($queryor);
// A group of OR keywords only needs to match once.
$this->matches += $any > 0;
}
}
else {
$simple_and = TRUE;
list($num_new_scores, $num_valid_words) = $this
->parseWord($key);
$this->conditions
->condition('d.data', "% {$key} %", 'LIKE');
if (!$num_valid_words) {
$this->simple = FALSE;
}
// Each AND keyword needs to match at least once.
$this->matches += $num_new_scores;
}
}
if ($simple_and && $simple_or) {
$this->simple = FALSE;
}
// Negative matches.
foreach ($this->keys['negative'] as $key) {
$this->conditions
->condition('d.data', "% {$key} %", 'NOT LIKE');
$this->simple = FALSE;
}
if ($warning == 'or') {
drupal_set_message(t('Search for either of the two terms with uppercase <strong>OR</strong>. For example, <strong>cats OR dogs</strong>.'));
}
}