/**
* {@inheritdoc}
*/
public function query($query, array $args = array(), $options = array())
{
try {
return parent::query($query, $args, $options);
} catch (DatabaseException $e) {
if ($e->getPrevious()->errorInfo[1] == 1153) {
// If a max_allowed_packet error occurs the message length is truncated.
// This should prevent the error from recurring if the exception is
// logged to the database using dblog or the like.
$message = Unicode::truncateBytes($e->getMessage(), self::MIN_MAX_ALLOWED_PACKET);
$e = new DatabaseExceptionWrapper($message, $e->getCode(), $e->getPrevious());
}
throw $e;
}
}
/**
* Converts a value between two search types.
*
* @param mixed $value
* The value to convert.
* @param string $type
* The type to convert to. One of the keys from
* search_api_default_field_types().
* @param string $original_type
* The value's original type.
* @param \Drupal\search_api\IndexInterface $index
* The index for which this conversion takes place.
*
* @return mixed
* The converted value.
*
* @throws \Drupal\search_api\SearchApiException
* Thrown if $type is unknown.
*/
protected function convert($value, $type, $original_type, IndexInterface $index) {
if (!isset($value)) {
// For text fields, we have to return an array even if the value is NULL.
return Utility::isTextType($type, array('text', 'tokenized_text')) ? array() : NULL;
}
switch ($type) {
case 'text':
// For dates, splitting the timestamp makes no sense.
if ($original_type == 'date') {
$value = format_date($value, 'custom', 'Y y F M n m j d l D');
}
$ret = array();
foreach (preg_split('/[^\p{L}\p{N}]+/u', $value, -1, PREG_SPLIT_NO_EMPTY) as $v) {
if ($v) {
if (strlen($v) > 50) {
$this->getLogger()->warning('An overlong word (more than 50 characters) was encountered while indexing: %word.<br />Database search servers currently cannot index such words correctly – the word was therefore trimmed to the allowed length. Ensure you are using a tokenizer preprocessor.', array('%word' => $v));
$v = Unicode::truncateBytes($v, 50);
}
$ret[] = array(
'value' => $v,
'score' => 1,
);
}
}
// This used to fall through the tokenized case
return $ret;
case 'tokenized_text':
while (TRUE) {
foreach ($value as $i => $v) {
// Check for over-long tokens.
$score = $v['score'];
$v = $v['value'];
if (strlen($v) > 50) {
$words = preg_split('/[^\p{L}\p{N}]+/u', $v, -1, PREG_SPLIT_NO_EMPTY);
if (count($words) > 1 && max(array_map('strlen', $words)) <= 50) {
// Overlong token is due to bad tokenizing.
// Check for "Tokenizer" preprocessor on index.
if (empty($index->getOption('processors')['search_api_tokenizer']['status'])) {
$this->getLogger()->warning('An overlong word (more than 50 characters) was encountered while indexing, due to bad tokenizing. It is recommended to enable the "Tokenizer" preprocessor for indexes using database servers. Otherwise, the backend class has to use its own, fixed tokenizing.');
}
else {
$this->getLogger()->warning('An overlong word (more than 50 characters) was encountered while indexing, due to bad tokenizing. Please check your settings for the "Tokenizer" preprocessor to ensure that data is tokenized correctly.');
}
}
$tokens = array();
foreach ($words as $word) {
if (strlen($word) > 50) {
$this->getLogger()->warning('An overlong word (more than 50 characters) was encountered while indexing: %word.<br />Database search servers currently cannot index such words correctly – the word was therefore trimmed to the allowed length.', array('%word' => $word));
$word = Unicode::truncateBytes($word, 50);
}
$tokens[] = array(
'value' => $word,
'score' => $score,
);
}
array_splice($value, $i, 1, $tokens);
// Restart the loop looking through all the tokens.
continue 2;
}
}
break;
}
return $value;
case 'string':
case 'uri':
// For non-dates, PHP can handle this well enough.
if ($original_type == 'date') {
return date('c', $value);
}
if (strlen($value) > 255) {
$value = Unicode::truncateBytes($value, 255);
$this->getLogger()->warning('An overlong value (more than 255 characters) was encountered while indexing: %value.<br />Database search servers currently cannot index such values correctly – the value was therefore trimmed to the allowed length.', array('%value' => $value));
}
return $value;
case 'integer':
case 'duration':
case 'decimal':
return 0 + $value;
case 'boolean':
return $value ? 1 : 0;
case 'date':
if (is_numeric($value) || !$value) {
return 0 + $value;
}
return strtotime($value);
default:
throw new SearchApiException(new FormattableMarkup('Unknown field type @type. Database search module might be out of sync with Search API.', array('@type' => $type)));
}
}
/**
* Tests multibyte truncate bytes.
*
* @dataProvider providerTestTruncateBytes
* @covers ::truncateBytes
*
* @param string $text
* The string to truncate.
* @param int $max_length
* The upper limit on the returned string length.
* @param string $expected
* The expected return from Unicode::truncateBytes().
*/
public function testTruncateBytes($text, $max_length, $expected)
{
$this->assertEquals($expected, Unicode::truncateBytes($text, $max_length), 'The string was not correctly truncated.');
}
public function prepareComment($comment, $length = NULL) {
// Truncate comment to maximum comment length.
if (isset($length)) {
// Add table prefixes before truncating.
$comment = Unicode::truncateBytes($this->connection->prefixTables($comment), $length, TRUE, TRUE);
}
return $this->connection->quote($comment);
}
