Merge pull request #28608 from nextcloud/path-prefix-filter

generate a better optimized query for path prefix search filters

5 files changed, 158 insertions, 0 deletions

diff --git a/lib/private/Files/Search/QueryOptimizer/PathPrefixOptimizer.php b/lib/private/Files/Search/QueryOptimizer/PathPrefixOptimizer.php
new file mode 100644
index 00000000000..eea4b430578
--- /dev/null
+++ b/lib/private/Files/Search/QueryOptimizer/PathPrefixOptimizer.php
@@ -0,0 +1,58 @@
+<?php
+
+declare(strict_types=1);
+/**
+ * @copyright Copyright (c) 2021 Robin Appelman <robin@icewind.nl>
+ *
+ * @license GNU AGPL version 3 or any later version
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as
+ * published by the Free Software Foundation, either version 3 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+namespace OC\Files\Search\QueryOptimizer;
+
+use OCP\Files\Search\ISearchBinaryOperator;
+use OCP\Files\Search\ISearchComparison;
+use OCP\Files\Search\ISearchOperator;
+
+class PathPrefixOptimizer extends QueryOptimizerStep {
+	public function escapeLikeParameter(string $param): string {
+		return addcslashes($param, '\\_%');
+	}
+
+	public function processOperator(ISearchOperator &$operator) {
+		// normally the `path = "$prefix"` search query part of the prefix filter would be generated as an `path_hash = md5($prefix)` sql query
+		// since the `path_hash` sql column usually provides much faster querying that selecting on the `path` sql column
+		//
+		// however, since we're already doing a filter on the `path` column in the form of `path LIKE "$prefix/%"`
+		// generating a `path = "$prefix"` sql query lets the database handle use the same column for both expressions and potentially use the same index
+		if ($operator instanceof ISearchBinaryOperator && $operator->getType() === ISearchBinaryOperator::OPERATOR_OR && count($operator->getArguments()) == 2) {
+			$a = $operator->getArguments()[0];
+			$b = $operator->getArguments()[1];
+			if ($a instanceof ISearchComparison && $b instanceof ISearchComparison && $a->getField() === 'path' && $b->getField() === 'path') {
+				if ($a->getType() === ISearchComparison::COMPARE_LIKE_CASE_SENSITIVE && $b->getType() === ISearchComparison::COMPARE_EQUAL
+					&& $a->getValue() === $this->escapeLikeParameter($b->getValue()) . '/%') {
+					$b->setQueryHint(ISearchComparison::HINT_PATH_EQ_HASH, false);
+				}
+				if ($b->getType() === ISearchComparison::COMPARE_LIKE_CASE_SENSITIVE && $a->getType() === ISearchComparison::COMPARE_EQUAL
+					&& $b->getValue() === $this->escapeLikeParameter($a->getValue()) . '/%') {
+					$a->setQueryHint(ISearchComparison::HINT_PATH_EQ_HASH, false);
+				}
+			}
+		}
+
+		parent::processOperator($operator);
+	}
+}
diff --git a/lib/private/Files/Search/QueryOptimizer/QueryOptimizer.php b/lib/private/Files/Search/QueryOptimizer/QueryOptimizer.php
new file mode 100644
index 00000000000..1635e50335a
--- /dev/null
+++ b/lib/private/Files/Search/QueryOptimizer/QueryOptimizer.php
@@ -0,0 +1,45 @@
+<?php
+
+declare(strict_types=1);
+/**
+ * @copyright Copyright (c) 2021 Robin Appelman <robin@icewind.nl>
+ *
+ * @license GNU AGPL version 3 or any later version
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as
+ * published by the Free Software Foundation, either version 3 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+namespace OC\Files\Search\QueryOptimizer;
+
+use OCP\Files\Search\ISearchOperator;
+
+class QueryOptimizer {
+	/** @var QueryOptimizerStep[] */
+	private $steps = [];
+
+	public function __construct(
+		PathPrefixOptimizer $pathPrefixOptimizer
+	) {
+		$this->steps = [
+			$pathPrefixOptimizer
+		];
+	}
+
+	public function processOperator(ISearchOperator $operator) {
+		foreach ($this->steps as $step) {
+			$step->processOperator($operator);
+		}
+	}
+}
diff --git a/lib/private/Files/Search/QueryOptimizer/QueryOptimizerStep.php b/lib/private/Files/Search/QueryOptimizer/QueryOptimizerStep.php
new file mode 100644
index 00000000000..4f683899723
--- /dev/null
+++ b/lib/private/Files/Search/QueryOptimizer/QueryOptimizerStep.php
@@ -0,0 +1,37 @@
+<?php
+
+declare(strict_types=1);
+/**
+ * @copyright Copyright (c) 2021 Robin Appelman <robin@icewind.nl>
+ *
+ * @license GNU AGPL version 3 or any later version
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as
+ * published by the Free Software Foundation, either version 3 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+namespace OC\Files\Search\QueryOptimizer;
+
+use OCP\Files\Search\ISearchBinaryOperator;
+use OCP\Files\Search\ISearchOperator;
+
+class QueryOptimizerStep {
+	public function processOperator(ISearchOperator &$operator) {
+		if ($operator instanceof ISearchBinaryOperator) {
+			foreach ($operator->getArguments() as $argument) {
+				$this->processOperator($argument);
+			}
+		}
+	}
+}
diff --git a/lib/private/Files/Search/SearchBinaryOperator.php b/lib/private/Files/Search/SearchBinaryOperator.php
index 3ebbae06e3e..d7bba8f1b4e 100644
--- a/lib/private/Files/Search/SearchBinaryOperator.php
+++ b/lib/private/Files/Search/SearchBinaryOperator.php
@@ -30,6 +30,7 @@ class SearchBinaryOperator implements ISearchBinaryOperator {
 	private $type;
 	/** @var ISearchOperator[] */
 	private $arguments;
+	private $hints = [];
 
 	/**
 	 * SearchBinaryOperator constructor.
@@ -55,4 +56,12 @@ class SearchBinaryOperator implements ISearchBinaryOperator {
 	public function getArguments() {
 		return $this->arguments;
 	}
+
+	public function getQueryHint(string $name, $default) {
+		return $this->hints[$name] ?? $default;
+	}
+
+	public function setQueryHint(string $name, $value): void {
+		$this->hints[$name] = $value;
+	}
 }
diff --git a/lib/private/Files/Search/SearchComparison.php b/lib/private/Files/Search/SearchComparison.php
index 83d8904776a..ab5a4d0ed73 100644
--- a/lib/private/Files/Search/SearchComparison.php
+++ b/lib/private/Files/Search/SearchComparison.php
@@ -31,6 +31,7 @@ class SearchComparison implements ISearchComparison {
 	private $field;
 	/** @var string|integer|\DateTime */
 	private $value;
+	private $hints = [];
 
 	/**
 	 * SearchComparison constructor.
@@ -65,4 +66,12 @@ class SearchComparison implements ISearchComparison {
 	public function getValue() {
 		return $this->value;
 	}
+
+	public function getQueryHint(string $name, $default) {
+		return $this->hints[$name] ?? $default;
+	}
+
+	public function setQueryHint(string $name, $value): void {
+		$this->hints[$name] = $value;
+	}
 }