You are here

Home » API reference » Search API 8 » IgnoreCharacters.php

class IgnoreCharacters in Search API 8

Configure types of characters which should be ignored for searches.

Plugin annotation


@SearchApiProcessor(
  id = "ignore_character",
  label = @Translation("Ignore characters"),
  description = @Translation("Configure types of characters which should be ignored for searches."),
  stages = {
    "pre_index_save" = 0,
    "preprocess_index" = -10,
    "preprocess_query" = -10,
  }
)

Hierarchy

Expanded class hierarchy of IgnoreCharacters

1 file declares its use of IgnoreCharacters
IgnoreCharacterTest.php in tests/src/Unit/Processor/IgnoreCharacterTest.php

File

src/Plugin/search_api/processor/IgnoreCharacters.php, line 23

Namespace

Drupal\search_api\Plugin\search_api\processor
View source 
class IgnoreCharacters extends FieldsProcessorPluginBase {

  /**
   * The escaped regular expression for ignorable characters.
   *
   * @var string
   */
  protected $ignorable;

  /**
   * {@inheritdoc}
   */
  public function defaultConfiguration() {
    $configuration = parent::defaultConfiguration();
    $configuration += [
      'ignorable' => "['¿¡!?,.:;]",
      'ignorable_classes' => [
        'Pc',
        'Pd',
        'Pe',
        'Pf',
        'Pi',
        'Po',
        'Ps',
      ],
    ];
    return $configuration;
  }

  /**
   * {@inheritdoc}
   */
  public function buildConfigurationForm(array $form, FormStateInterface $form_state) {
    $form = parent::buildConfigurationForm($form, $form_state);
    $form['ignorable'] = [
      '#type' => 'textfield',
      '#title' => $this
        ->t('Strip by regular expression'),
      '#description' => $this
        ->t('Specify characters which should be removed from fulltext fields and search strings, as a <a href=":url">PCRE regular expression</a>.', [
        ':url' => Url::fromUri('https://secure.php.net/manual/reference.pcre.pattern.syntax.php')
          ->toString(),
      ]),
      '#default_value' => $this->configuration['ignorable'],
      '#maxlength' => 1000,
    ];
    $character_sets = $this
      ->getCharacterSets();
    $form['strip'] = [
      '#type' => 'details',
      '#title' => $this
        ->t('Strip by character property'),
      '#description' => $this
        ->t('Specify <a href=":url">Unicode character properties</a> of characters to be ignored.', [
        ':url' => Url::fromUri('https://en.wikipedia.org/wiki/Unicode_character_property')
          ->toString(),
      ]),
      '#open' => FALSE,
      '#maxlength' => 300,
    ];
    $classes = $this->configuration['ignorable_classes'];
    $form['strip']['character_sets'] = [
      '#type' => 'checkboxes',
      '#title' => $this
        ->t('Ignored character properties'),
      '#options' => $character_sets,
      '#default_value' => array_combine($classes, $classes),
      '#multiple' => TRUE,
    ];
    return $form;
  }

  /**
   * {@inheritdoc}
   */
  public function validateConfigurationForm(array &$form, FormStateInterface $form_state) {
    parent::validateConfigurationForm($form, $form_state);
    $ignorable = str_replace('/', '\\/', $form_state
      ->getValue('ignorable', ''));
    if ($ignorable !== '' && @preg_match('/(' . $ignorable . ')+/u', '') === FALSE) {
      $el = $form['ignorable'];
      $form_state
        ->setError($el, $el['#title'] . ': ' . $this
        ->t('The entered text is no valid regular expression.'));
    }
  }

  /**
   * {@inheritdoc}
   */
  public function submitConfigurationForm(array &$form, FormStateInterface $form_state) {
    $config = $form_state
      ->getValues();
    unset($config['strip']);

    // Get our own version of 'ignorable_classes' from form values.
    $classes = $form_state
      ->getValue([
      'strip',
      'character_sets',
    ], []);
    $config['ignorable_classes'] = array_values(array_filter($classes));
    $this
      ->setConfiguration($config);
  }

  /**
   * {@inheritdoc}
   */
  protected function process(&$value) {
    if ($this->configuration['ignorable']) {
      if (!isset($this->ignorable)) {
        $this->ignorable = str_replace('/', '\\/', $this->configuration['ignorable']);
      }
      $value = preg_replace('/' . $this->ignorable . '+/u', '', $value);
    }

    // Loop over the character sets and strip the characters from the text.
    foreach ($this->configuration['ignorable_classes'] as $character_set) {
      $regex = $this
        ->getFormatRegularExpression($character_set);
      if ($regex) {
        $value = preg_replace('/[' . $regex . ']+/u', '', $value);
      }
    }
  }

  /**
   * Retrieves an options list for available Unicode character properties.
   *
   * @return string[]
   *   An options list with all available Unicode character properties.
   */
  protected function getCharacterSets() {
    return [
      'Pc' => $this
        ->t('Punctuation, Connector Characters'),
      'Pd' => $this
        ->t('Punctuation, Dash Characters'),
      'Pe' => $this
        ->t('Punctuation, Close Characters'),
      'Pf' => $this
        ->t('Punctuation, Final quote Characters'),
      'Pi' => $this
        ->t('Punctuation, Initial quote Characters'),
      'Po' => $this
        ->t('Punctuation, Other Characters'),
      'Ps' => $this
        ->t('Punctuation, Open Characters'),
      'Cc' => $this
        ->t('Other, Control Characters'),
      'Cf' => $this
        ->t('Other, Format Characters'),
      'Co' => $this
        ->t('Other, Private Use Characters'),
      'Mc' => $this
        ->t('Mark, Spacing Combining Characters'),
      'Me' => $this
        ->t('Mark, Enclosing Characters'),
      'Mn' => $this
        ->t('Mark, Nonspacing Characters'),
      'Sc' => $this
        ->t('Symbol, Currency Characters'),
      'Sk' => $this
        ->t('Symbol, Modifier Characters'),
      'Sm' => $this
        ->t('Symbol, Math Characters'),
      'So' => $this
        ->t('Symbol, Other Characters'),
      'Zl' => $this
        ->t('Separator, Line Characters'),
      'Zp' => $this
        ->t('Separator, Paragraph Characters'),
      'Zs' => $this
        ->t('Separator, Space Characters'),
    ];
  }

  /**
   * Retrieves a regular expression for a certain Unicode character property.
   *
   * @param string $property
   *   The abbreviation of the character property for which to get the regular
   *   expression.
   *
   * @return string|null
   *   The regular expression for the property, or NULL if it could not be
   *   found.
   */
  protected function getFormatRegularExpression($property) {
    $class = 'Drupal\\search_api\\Plugin\\search_api\\processor\\Resources\\' . $property;
    if (class_exists($class) && in_array('Drupal\\search_api\\Plugin\\search_api\\processor\\Resources\\UnicodeCharacterPropertyInterface', class_implements($class))) {
      return $class::getRegularExpression();
    }
    return NULL;
  }

}

Members

Namesort descending Modifiers Type Description Overrides
ConfigurablePluginBase::calculateDependencies public function Calculates dependencies for the configured plugin. Overrides DependentPluginInterface::calculateDependencies 6
ConfigurablePluginBase::calculatePluginDependencies Deprecated protected function Calculates and adds dependencies of a specific plugin instance.
ConfigurablePluginBase::getConfiguration public function Gets this plugin's configuration. Overrides ConfigurableInterface::getConfiguration
ConfigurablePluginBase::getDescription public function Returns the plugin's description. Overrides ConfigurablePluginInterface::getDescription
ConfigurablePluginBase::getPluginDependencies Deprecated protected function Calculates and returns dependencies of a specific plugin instance.
ConfigurablePluginBase::label public function Returns the label for use on the administration pages. Overrides ConfigurablePluginInterface::label
ConfigurablePluginBase::moduleHandler Deprecated protected function Wraps the module handler.
ConfigurablePluginBase::onDependencyRemoval public function Informs the plugin that some of its dependencies are being removed. Overrides ConfigurablePluginInterface::onDependencyRemoval 5
ConfigurablePluginBase::setConfiguration public function Sets the configuration for this plugin instance. Overrides ConfigurableInterface::setConfiguration 3
ConfigurablePluginBase::themeHandler Deprecated protected function Wraps the theme handler.
DependencySerializationTrait::$_entityStorages protected property An array of entity type IDs keyed by the property name of their storages.
DependencySerializationTrait::$_serviceIds protected property An array of service IDs keyed by property name used for serialization.
DependencySerializationTrait::__sleep public function 1
DependencySerializationTrait::__wakeup public function 2
DependencyTrait::$dependencies protected property The object's dependencies.
DependencyTrait::addDependencies protected function Adds multiple dependencies.
DependencyTrait::addDependency protected function Adds a dependency.
FieldsProcessorPluginBase::$dataTypeHelper protected property The data type helper. 1
FieldsProcessorPluginBase::$elementInfoManager protected property The element info manager.
FieldsProcessorPluginBase::create public static function Creates an instance of the plugin. Overrides ProcessorPluginBase::create 1
FieldsProcessorPluginBase::getDataTypeHelper public function Retrieves the data type helper. 1
FieldsProcessorPluginBase::getElementInfoManager public function Retrieves the element info manager.
FieldsProcessorPluginBase::preIndexSave public function Preprocesses the search index entity before it is saved. Overrides ProcessorPluginBase::preIndexSave
FieldsProcessorPluginBase::preprocessIndexItems public function Preprocesses search items for indexing. Overrides ProcessorPluginBase::preprocessIndexItems 1
FieldsProcessorPluginBase::preprocessSearchQuery public function Preprocesses a search query. Overrides ProcessorPluginBase::preprocessSearchQuery 2
FieldsProcessorPluginBase::preRenderFieldsCheckboxes public static function Preprocesses the "fields" checkboxes before rendering.
FieldsProcessorPluginBase::processConditions protected function Preprocesses the query conditions.
FieldsProcessorPluginBase::processConditionValue protected function Processes a single condition value. 1
FieldsProcessorPluginBase::processField protected function Processes a single field's value. 3
FieldsProcessorPluginBase::processFieldValue protected function Processes a single text element in a field. 3
FieldsProcessorPluginBase::processKey protected function Processes a single search keyword. 1
FieldsProcessorPluginBase::processKeys protected function Preprocesses the search keywords.
FieldsProcessorPluginBase::setDataTypeHelper public function Sets the data type helper. 1
FieldsProcessorPluginBase::setElementInfoManager public function Sets the element info manager.
FieldsProcessorPluginBase::shouldProcess protected function Determines whether a single value (not an array) should be processed. 1
FieldsProcessorPluginBase::testField protected function Tests whether a certain field should be processed. 1
FieldsProcessorPluginBase::testType protected function Determines whether a field of a certain type should be preprocessed. 4
FieldsProcessorPluginBase::trustedCallbacks public static function Lists the trusted callbacks provided by the implementing class. Overrides TrustedCallbackInterface::trustedCallbacks
IgnoreCharacters::$ignorable protected property The escaped regular expression for ignorable characters.
IgnoreCharacters::buildConfigurationForm public function Form constructor. Overrides FieldsProcessorPluginBase::buildConfigurationForm
IgnoreCharacters::defaultConfiguration public function Gets default configuration for this plugin. Overrides FieldsProcessorPluginBase::defaultConfiguration
IgnoreCharacters::getCharacterSets protected function Retrieves an options list for available Unicode character properties.
IgnoreCharacters::getFormatRegularExpression protected function Retrieves a regular expression for a certain Unicode character property.
IgnoreCharacters::process protected function Processes a single string value. Overrides FieldsProcessorPluginBase::process
IgnoreCharacters::submitConfigurationForm public function Form submission handler. Overrides PluginFormTrait::submitConfigurationForm
IgnoreCharacters::validateConfigurationForm public function Form validation handler. Overrides FieldsProcessorPluginBase::validateConfigurationForm
IndexPluginBase::$index protected property The index this processor is configured for.
IndexPluginBase::getIndex public function Retrieves the index this plugin is configured for. Overrides IndexPluginInterface::getIndex
IndexPluginBase::setIndex public function Sets the index this plugin is configured for. Overrides IndexPluginInterface::setIndex
IndexPluginBase::__construct public function Constructs a \Drupal\Component\Plugin\PluginBase object. Overrides ConfigurablePluginBase::__construct 2
MessengerTrait::$messenger protected property The messenger. 29
MessengerTrait::messenger public function Gets the messenger. 29
MessengerTrait::setMessenger public function Sets the messenger.
PluginBase::$configuration protected property Configuration information passed into the plugin. 1
PluginBase::$pluginDefinition protected property The plugin implementation definition. 1
PluginBase::$pluginId protected property The plugin_id.
PluginBase::DERIVATIVE_SEPARATOR constant A string which is used to separate base plugin IDs from the derivative ID.
PluginBase::getBaseId public function Gets the base_plugin_id of the plugin instance. Overrides DerivativeInspectionInterface::getBaseId
PluginBase::getDerivativeId public function Gets the derivative_id of the plugin instance. Overrides DerivativeInspectionInterface::getDerivativeId
PluginBase::getPluginDefinition public function Gets the definition of the plugin implementation. Overrides PluginInspectionInterface::getPluginDefinition 3
PluginBase::getPluginId public function Gets the plugin_id of the plugin instance. Overrides PluginInspectionInterface::getPluginId
PluginBase::isConfigurable public function Determines if the plugin is configurable.
PluginDependencyTrait::calculatePluginDependencies protected function Calculates and adds dependencies of a specific plugin instance. Aliased as: traitCalculatePluginDependencies 1
PluginDependencyTrait::getPluginDependencies protected function Calculates and returns dependencies of a specific plugin instance. Aliased as: traitGetPluginDependencies
PluginDependencyTrait::moduleHandler protected function Wraps the module handler. Aliased as: traitModuleHandler 1
PluginDependencyTrait::themeHandler protected function Wraps the theme handler. Aliased as: traitThemeHandler 1
ProcessorInterface::STAGE_ADD_PROPERTIES constant Processing stage: add properties.
ProcessorInterface::STAGE_ALTER_ITEMS constant Processing stage: alter indexed items.
ProcessorInterface::STAGE_POSTPROCESS_QUERY constant Processing stage: postprocess query.
ProcessorInterface::STAGE_PREPROCESS_INDEX constant Processing stage: preprocess index.
ProcessorInterface::STAGE_PREPROCESS_QUERY constant Processing stage: preprocess query.
ProcessorInterface::STAGE_PRE_INDEX_SAVE constant Processing stage: preprocess index.
ProcessorPluginBase::$fieldsHelper protected property The fields helper. 1
ProcessorPluginBase::addFieldValues public function Adds the values of properties defined by this processor to the item. Overrides ProcessorInterface::addFieldValues 8
ProcessorPluginBase::alterIndexedItems public function Alter the items to be indexed. Overrides ProcessorInterface::alterIndexedItems 3
ProcessorPluginBase::ensureField protected function Ensures that a field with certain properties is indexed on the index.
ProcessorPluginBase::findField protected function Finds a certain field in the index.
ProcessorPluginBase::getFieldsHelper public function Retrieves the fields helper. 1
ProcessorPluginBase::getPropertyDefinitions public function Retrieves the properties this processor defines for the given datasource. Overrides ProcessorInterface::getPropertyDefinitions 8
ProcessorPluginBase::getWeight public function Returns the weight for a specific processing stage. Overrides ProcessorInterface::getWeight
ProcessorPluginBase::isHidden public function Determines whether this plugin should be hidden in the UI. Overrides HideablePluginBase::isHidden
ProcessorPluginBase::isLocked public function Determines whether this processor should always be enabled. Overrides ProcessorInterface::isLocked
ProcessorPluginBase::postprocessSearchResults public function Postprocess search results before they are returned by the query. Overrides ProcessorInterface::postprocessSearchResults 2
ProcessorPluginBase::requiresReindexing public function Determines whether re-indexing is required after a settings change. Overrides ProcessorInterface::requiresReindexing
ProcessorPluginBase::setFieldsHelper public function Sets the fields helper. 1
ProcessorPluginBase::setWeight public function Sets the weight for a specific processing stage. Overrides ProcessorInterface::setWeight
ProcessorPluginBase::supportsIndex public static function Checks whether this processor is applicable for a certain index. Overrides ProcessorInterface::supportsIndex 8
ProcessorPluginBase::supportsStage public function Checks whether this processor implements a particular stage. Overrides ProcessorInterface::supportsStage 2
StringTranslationTrait::$stringTranslation protected property The string translation service. 1
StringTranslationTrait::formatPlural protected function Formats a string containing a count of items.
StringTranslationTrait::getNumberOfPlurals protected function Returns the number of plurals supported by a given language.
StringTranslationTrait::getStringTranslation protected function Gets the string translation service.
StringTranslationTrait::setStringTranslation public function Sets the string translation service to use. 2
StringTranslationTrait::t protected function Translates a string to the current language or to a given language.
TrustedCallbackInterface::THROW_EXCEPTION constant Untrusted callbacks throw exceptions.
TrustedCallbackInterface::TRIGGER_SILENCED_DEPRECATION constant Untrusted callbacks trigger silenced E_USER_DEPRECATION errors.
TrustedCallbackInterface::TRIGGER_WARNING constant Untrusted callbacks trigger E_USER_WARNING errors.