Skip to content

Fix fulltext stripping #826

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
abnegate wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Fix fulltext stripping #826

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ce0334e
(fix): Sanitize fulltext search values with unicode-aware regex and h…
abnegate Mar 5, 2026
f3bdc34
(test): Add regression test for fulltext search with accented and spe…
abnegate Mar 5, 2026
438f97c
fix: preserve underscores in fulltext search value sanitization
abnegate Mar 5, 2026
72c48ad
fix: null-coalesce preg_replace results for malformed UTF-8 safety
abnegate Mar 5, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions src/Database/Adapter/MariaDB.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1593,12 +1593,20 @@ protected function getSQLCondition(Query $query, array &$binds): string
return empty($conditions) ? '' : ' '. $method .' (' . implode(' AND ', $conditions) . ')';

case Query::TYPE_SEARCH:
$binds[":{$placeholder}_0"] = $this->getFulltextValue($query->getValue());
$fulltextValue = $this->getFulltextValue($query->getValue());
if ($fulltextValue === '') {
return '0 = 1';
}
$binds[":{$placeholder}_0"] = $fulltextValue;

return "MATCH({$alias}.{$attribute}) AGAINST (:{$placeholder}_0 IN BOOLEAN MODE)";

case Query::TYPE_NOT_SEARCH:
$binds[":{$placeholder}_0"] = $this->getFulltextValue($query->getValue());
$fulltextValue = $this->getFulltextValue($query->getValue());
if ($fulltextValue === '') {
return '1 = 1';
}
$binds[":{$placeholder}_0"] = $fulltextValue;

return "NOT (MATCH({$alias}.{$attribute}) AGAINST (:{$placeholder}_0 IN BOOLEAN MODE))";

Expand Down
22 changes: 18 additions & 4 deletions src/Database/Adapter/Postgres.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1796,11 +1796,19 @@ protected function getSQLCondition(Query $query, array &$binds): string
return empty($conditions) ? '' : ' ' . $method . ' (' . implode(' AND ', $conditions) . ')';

case Query::TYPE_SEARCH:
$binds[":{$placeholder}_0"] = $this->getFulltextValue($query->getValue());
$fulltextValue = $this->getFulltextValue($query->getValue());
if ($fulltextValue === '') {
return '0 = 1';
}
$binds[":{$placeholder}_0"] = $fulltextValue;
return "to_tsvector(regexp_replace({$attribute}, '[^\w]+',' ','g')) @@ websearch_to_tsquery(:{$placeholder}_0)";

case Query::TYPE_NOT_SEARCH:
$binds[":{$placeholder}_0"] = $this->getFulltextValue($query->getValue());
$fulltextValue = $this->getFulltextValue($query->getValue());
if ($fulltextValue === '') {
return '1 = 1';
}
$binds[":{$placeholder}_0"] = $fulltextValue;
return "NOT (to_tsvector(regexp_replace({$attribute}, '[^\w]+',' ','g')) @@ websearch_to_tsquery(:{$placeholder}_0))";

case Query::TYPE_VECTOR_DOT:
Expand Down Expand Up @@ -1912,10 +1920,16 @@ protected function getVectorDistanceOrder(Query $query, array &$binds, string $a
protected function getFulltextValue(string $value): string
{
$exact = str_ends_with($value, '"') && str_starts_with($value, '"');
$value = str_replace(['@', '+', '-', '*', '.', "'", '"'], ' ', $value);
$value = preg_replace('/\s+/', ' ', $value); // Remove multiple whitespaces

/** Keep only unicode letters, numbers, underscores, and whitespace. */
$value = preg_replace('/[^\p{L}\p{N}_\s]/u', ' ', $value) ?? '';
$value = preg_replace('/\s+/', ' ', $value) ?? '';
$value = trim($value);

if (empty($value)) {
return '';
}

if (!$exact) {
$value = str_replace(' ', ' or ', $value);
}
Expand Down
7 changes: 3 additions & 4 deletions src/Database/Adapter/SQL.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1752,10 +1752,9 @@ protected function getFulltextValue(string $value): string
{
$exact = str_ends_with($value, '"') && str_starts_with($value, '"');

/** Replace reserved chars with space. */
$specialChars = '@,+,-,*,),(,<,>,~,"';
$value = str_replace(explode(',', $specialChars), ' ', $value);
$value = preg_replace('/\s+/', ' ', $value); // Remove multiple whitespaces
/** Keep only unicode letters, numbers, underscores, and whitespace. */
$value = preg_replace('/[^\p{L}\p{N}_\s]/u', ' ', $value) ?? '';
$value = preg_replace('/\s+/', ' ', $value) ?? '';
$value = trim($value);

if (empty($value)) {
Expand Down
89 changes: 89 additions & 0 deletions tests/e2e/Adapter/Scopes/DocumentTests.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2179,6 +2179,95 @@ public function testFindFulltextSpecialChars(): void
$this->assertEquals(1, count($documents));
}

/**
* Regression: accented characters and non-operator special chars
* previously caused SQLSTATE[42000] syntax error in FTS BOOLEAN MODE.
*
* @see https://appwrite.sentry.io/issues/5628237003
*/
public function testFindFulltextAccentedAndSpecialChars(): void
{
/** @var Database $database */
$database = $this->getDatabase();

if (!$database->getAdapter()->getSupportForFulltextIndex()) {
$this->expectNotToPerformAssertions();
return;
}

$collection = 'full_text_unicode';
$database->createCollection($collection, permissions: [
Permission::create(Role::any()),
Permission::update(Role::users())
]);

$this->assertTrue($database->createAttribute($collection, 'nombre', Database::VAR_STRING, 128, true));
$this->assertTrue($database->createIndex($collection, 'nombre-ft', Database::INDEX_FULLTEXT, ['nombre']));

$database->createDocument($collection, new Document([
'$permissions' => [Permission::read(Role::any())],
'nombre' => 'Luis García'
]));

$database->createDocument($collection, new Document([
'$permissions' => [Permission::read(Role::any())],
'nombre' => 'Álvaro Yair Cuéllar'
]));

$database->createDocument($collection, new Document([
'$permissions' => [Permission::read(Role::any())],
'nombre' => 'Fernando naïve über'
]));

/**
* Accented characters must not cause FTS parser errors
*/
$documents = $database->find($collection, [
Query::search('nombre', 'García'),
]);
$this->assertGreaterThanOrEqual(1, count($documents));

$documents = $database->find($collection, [
Query::search('nombre', 'Álvaro'),
]);
$this->assertGreaterThanOrEqual(1, count($documents));

$documents = $database->find($collection, [
Query::search('nombre', 'Cuéllar'),
]);
$this->assertGreaterThanOrEqual(1, count($documents));

/**
* Non-operator special chars (! . #) were not stripped by old code,
* producing values like "!!!...###*" that crash MySQL's FTS parser.
*/
$documents = $database->find($collection, [
Query::search('nombre', '!!!...###'),
]);
$this->assertEquals(0, count($documents));

$documents = $database->find($collection, [
Query::search('nombre', '$$$%%%^^^'),
]);
$this->assertEquals(0, count($documents));

/**
* FTS operator-only input also must not error
*/
$documents = $database->find($collection, [
Query::search('nombre', '+-*@<>~'),
]);
$this->assertEquals(0, count($documents));

/**
* Mixed special chars + accented word should still find results
*/
$documents = $database->find($collection, [
Query::search('nombre', '@García!'),
]);
$this->assertGreaterThanOrEqual(1, count($documents));
}

public function testFindMultipleConditions(): void
{
/** @var Database $database */
Expand Down