From ca306bf3f1b348c2f2f36b7188727b594dd2a51b Mon Sep 17 00:00:00 2001
From: Alex Pott <alex.a.pott@googlemail.com>
Date: Thu, 2 Oct 2014 13:35:47 +0200
Subject: [PATCH] Issue #1842226 by jhodgdon | spartlow: Fixed Search OR
statements don't work if same keyword is used.
---
core/modules/search/src/SearchQuery.php | 44 ++++++++++++-------
.../search/src/Tests/SearchMatchTest.php | 26 ++++++-----
2 files changed, 45 insertions(+), 25 deletions(-)
diff --git a/core/modules/search/src/SearchQuery.php b/core/modules/search/src/SearchQuery.php
index 4211bd9c7e72..b3e2cac5eab0 100644
--- a/core/modules/search/src/SearchQuery.php
+++ b/core/modules/search/src/SearchQuery.php
@@ -235,7 +235,7 @@ protected function parseSearchExpression() {
}
// Classify tokens.
- $or = FALSE;
+ $in_or = FALSE;
$limit_combinations = \Drupal::config('search.settings')->get('and_or_limit');
// The first search expression does not count as AND.
$and_count = -1;
@@ -248,13 +248,14 @@ protected function parseSearchExpression() {
break;
}
- $phrase = FALSE;
// Strip off phrase quotes.
+ $phrase = FALSE;
if ($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.
@@ -275,7 +276,7 @@ protected function parseSearchExpression() {
$last = array($last);
}
$this->keys['positive'][] = $last;
- $or = TRUE;
+ $in_or = TRUE;
$or_count++;
continue;
}
@@ -290,7 +291,7 @@ protected function parseSearchExpression() {
// Lower-case "or" instead of "OR" is a warning condition.
$this->status |= SearchQuery::LOWER_CASE_OR;
}
- if ($or) {
+ if ($in_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);
}
@@ -299,33 +300,38 @@ protected function parseSearchExpression() {
$and_count++;
}
}
- $or = FALSE;
+ $in_or = FALSE;
}
// Convert keywords into SQL statements.
- $simple_and = FALSE;
- $simple_or = FALSE;
+ $has_and = FALSE;
+ $has_or = FALSE;
// Positive matches.
foreach ($this->keys['positive'] as $key) {
// Group of ORed terms.
if (is_array($key) && count($key)) {
- $simple_or = TRUE;
- $any = FALSE;
+ // If we had already found one OR, this is another one AND-ed with the
+ // first, meaning it is not a simple query.
+ if ($has_or) {
+ $this->simple = FALSE;
+ }
+ $has_or = TRUE;
+ $has_new_scores = FALSE;
$queryor = db_or();
foreach ($key as $or) {
list($num_new_scores) = $this->parseWord($or);
- $any |= $num_new_scores;
+ $has_new_scores |= $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);
+ $this->matches += ($has_new_scores > 0);
}
}
// Single ANDed term.
else {
- $simple_and = TRUE;
+ $has_and = TRUE;
list($num_new_scores, $num_valid_words) = $this->parseWord($key);
$this->conditions->condition('d.data', "% $key %", 'LIKE');
if (!$num_valid_words) {
@@ -335,9 +341,10 @@ protected function parseSearchExpression() {
$this->matches += $num_new_scores;
}
}
- if ($simple_and && $simple_or) {
+ if ($has_and && $has_or) {
$this->simple = FALSE;
}
+
// Negative matches.
foreach ($this->keys['negative'] as $key) {
$this->conditions->condition('d.data', "% $key %", 'NOT LIKE');
@@ -409,8 +416,15 @@ public function prepareAndNormalize() {
$this
->condition('i.type', $this->type)
->groupBy('i.type')
- ->groupBy('i.sid')
- ->having('COUNT(*) >= :matches', array(':matches' => $this->matches));
+ ->groupBy('i.sid');
+
+ // If the query is simple, we should have calculated the number of
+ // matching words we need to find, so impose that criterion. For non-
+ // simple queries, this condition could lead to incorrectly deciding not
+ // to continue with the full query.
+ if ($this->simple) {
+ $this->having('COUNT(*) >= :matches', array(':matches' => $this->matches));
+ }
// Clone the query object to calculate normalization.
$normalize_query = clone $this->query;
diff --git a/core/modules/search/src/Tests/SearchMatchTest.php b/core/modules/search/src/Tests/SearchMatchTest.php
index 66ec5b137879..929f355c431c 100644
--- a/core/modules/search/src/Tests/SearchMatchTest.php
+++ b/core/modules/search/src/Tests/SearchMatchTest.php
@@ -88,15 +88,13 @@ function getText2($n) {
* Run predefine queries looking for indexed terms.
*/
function _testQueries() {
- /*
- Note: OR queries that include short words in OR groups are only accepted
- if the ORed terms are ANDed with at least one long word in the rest of the query.
-
- e.g. enim dolore OR ut = enim (dolore OR ut) = (enim dolor) OR (enim ut) -> good
- e.g. dolore OR ut = (dolore) OR (ut) -> bad
-
- This is a design limitation to avoid full table scans.
- */
+ // Note: OR queries that include short words in OR groups are only accepted
+ // if the ORed terms are ANDed with at least one long word in the rest of
+ // the query. Examples:
+ // enim dolore OR ut = enim (dolore OR ut) = (enim dolor) OR (enim ut)
+ // is good, and
+ // dolore OR ut = (dolore) OR (ut)
+ // is bad. This is a design limitation to avoid full table scans.
$queries = array(
// Simple AND queries.
'ipsum' => array(1),
@@ -109,7 +107,7 @@ function _testQueries() {
'ut minim' => array(5),
'xx minim' => array(),
'enim veniam am minim ut' => array(5),
- // Simple OR queries.
+ // Simple OR and AND/OR queries.
'dolore OR ipsum' => array(1, 2, 7),
'dolore OR xxxxx' => array(2, 7),
'dolore OR ipsum OR enim' => array(1, 2, 4, 5, 6, 7),
@@ -119,6 +117,14 @@ function _testQueries() {
'minim dolore OR ipsum OR enim' => array(5, 6, 7),
'dolore xx OR yy' => array(),
'xxxxx dolore OR ipsum' => array(),
+ // Sequence of OR queries.
+ 'minim' => array(5, 6, 7),
+ 'minim OR xxxx' => array(5, 6, 7),
+ 'minim OR xxxx OR minim' => array(5, 6, 7),
+ 'minim OR xxxx minim' => array(5, 6, 7),
+ 'minim OR xxxx minim OR yyyy' => array(5, 6, 7),
+ 'minim OR xxxx minim OR cillum' => array(6, 7, 5),
+ 'minim OR xxxx minim OR xxxx' => array(5, 6, 7),
// Negative queries.
'dolore -sit' => array(7),
'dolore -eu' => array(2),
--
GitLab