You are here

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

class HtmlFilter in Search API 8

Strips HTML tags from fulltext fields and decodes HTML entities.

Plugin annotation


@SearchApiProcessor(
  id = "html_filter",
  label = @Translation("HTML filter"),
  description = @Translation("Strips HTML tags from fulltext fields and decodes HTML entities. Use this processor when indexing HTML data – for example, node bodies for certain text formats. The processor also allows to boost (or ignore) the contents of specific elements."),
  stages = {
    "pre_index_save" = 0,
    "preprocess_index" = -15,
    "preprocess_query" = -15,
  }
)

Hierarchy

Expanded class hierarchy of HtmlFilter

1 file declares its use of HtmlFilter
HtmlFilterTest.php in tests/src/Unit/Processor/HtmlFilterTest.php

File

src/Plugin/search_api/processor/HtmlFilter.php, line 32

Namespace

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

  /**
   * The data type helper.
   *
   * @var \Drupal\search_api\Utility\DataTypeHelperInterface|null
   */
  protected $dataTypeHelper;

  /**
   * Retrieves the data type helper.
   *
   * @return \Drupal\search_api\Utility\DataTypeHelperInterface
   *   The data type helper.
   */
  public function getDataTypeHelper() {
    return $this->dataTypeHelper ?: \Drupal::service('search_api.data_type_helper');
  }

  /**
   * Sets the data type helper.
   *
   * @param \Drupal\search_api\Utility\DataTypeHelperInterface $data_type_helper
   *   The new data type helper.
   *
   * @return $this
   */
  public function setDataTypeHelper(DataTypeHelperInterface $data_type_helper) {
    $this->dataTypeHelper = $data_type_helper;
    return $this;
  }

  /**
   * {@inheritdoc}
   */
  public function defaultConfiguration() {
    $configuration = parent::defaultConfiguration();
    $configuration += [
      'title' => TRUE,
      'alt' => TRUE,
      'tags' => [
        'h1' => 5,
        'h2' => 3,
        'h3' => 2,
        'strong' => 2,
        'b' => 2,
        'em' => 1.5,
        'u' => 1.5,
      ],
    ];
    return $configuration;
  }

  /**
   * {@inheritdoc}
   */
  public function buildConfigurationForm(array $form, FormStateInterface $form_state) {
    $form = parent::buildConfigurationForm($form, $form_state);
    $form['title'] = [
      '#type' => 'checkbox',
      '#title' => $this
        ->t('Index title attribute'),
      '#description' => $this
        ->t('If set, the contents of title attributes will be indexed.'),
      '#default_value' => $this->configuration['title'],
    ];
    $form['alt'] = [
      '#type' => 'checkbox',
      '#title' => $this
        ->t('Index alt attribute'),
      '#description' => $this
        ->t('If set, the alternative text of images will be indexed.'),
      '#default_value' => $this->configuration['alt'],
    ];
    $dumper = new Dumper();
    $tags = $dumper
      ->dump($this->configuration['tags'], 2);
    $tags = str_replace('\\r\\n', "\n", $tags);
    $tags = str_replace('"', '', $tags);
    $t_args[':url'] = Url::fromUri('https://en.wikipedia.org/wiki/YAML')
      ->toString();
    $form['tags'] = [
      '#type' => 'textarea',
      '#title' => $this
        ->t('Tag boosts'),
      '#description' => $this
        ->t('Specify special boost values for certain HTML elements, in <a href=":url">YAML file format</a>. The boost values of nested elements are multiplied, elements not mentioned will have the default boost value of 1. Assign a boost of 0 to ignore the text content of that HTML element.', $t_args),
      '#default_value' => $tags,
    ];
    return $form;
  }

  /**
   * {@inheritdoc}
   */
  public function validateConfigurationForm(array &$form, FormStateInterface $form_state) {
    parent::validateConfigurationForm($form, $form_state);
    $tags = trim($form_state
      ->getValue('tags'));
    if (!$tags) {
      $form_state
        ->setValue('tags', []);
      return;
    }
    $errors = [];
    try {
      $parser = new Parser();
      $tags = $parser
        ->parse($tags);
      if (!is_array($tags)) {
        $errors[] = $this
          ->t('Tags is not a valid YAML map. See @link for information on how to write correctly formed YAML.', [
          '@link' => 'http://yaml.org',
        ]);
        $tags = [];
      }
    } catch (ParseException $exception) {
      $errors[] = $this
        ->t('Tags is not a valid YAML map. See @link for information on how to write correctly formed YAML.', [
        '@link' => 'http://yaml.org',
      ]);
      $tags = [];
    }
    foreach ($tags as $key => $value) {
      $tag = "<{$key}>";
      if (is_array($value)) {
        $errors[] = $this
          ->t("Boost value for tag @tag can't be an array.", [
          '@tag' => $tag,
        ]);
      }
      elseif (!is_numeric($value)) {
        $errors[] = $this
          ->t('Boost value for tag @tag must be numeric.', [
          '@tag' => $tag,
        ]);
      }
      elseif ($value < 0) {
        $errors[] = $this
          ->t('Boost value for tag @tag must be non-negative.', [
          '@tag' => $tag,
        ]);
      }
      elseif ($value == 1) {
        unset($tags[$key]);
      }
      else {
        $tags[$key] = (double) $value;
      }
    }
    $form_state
      ->setValue('tags', $tags);
    if ($errors) {
      $message = array_shift($errors);
      foreach ($errors as $error) {
        $args = [
          '@message1' => $message,
          '@message2' => $error,
        ];
        $message = new FormattableMarkup('@message1<br />@message2', $args);
      }
      $form_state
        ->setError($form['tags'], $message);
    }
  }

  /**
   * {@inheritdoc}
   */
  protected function processField(FieldInterface $field) {
    parent::processField($field);
    foreach ($field
      ->getValues() as $value) {
      if ($value instanceof TextValueInterface) {
        $value
          ->setProperty('strip_html');
      }
    }
  }

  /**
   * {@inheritdoc}
   */
  protected function processFieldValue(&$value, $type) {

    // Remove invisible content.
    $text = preg_replace('@<(applet|audio|canvas|command|embed|iframe|map|menu|noembed|noframes|noscript|script|style|svg|video)[^>]*>.*</\\1>@siU', ' ', $value);

    // Let removed tags still delimit words.
    $is_text_type = $this
      ->getDataTypeHelper()
      ->isTextType($type);
    if ($is_text_type) {
      $text = str_replace([
        '<',
        '>',
      ], [
        ' <',
        '> ',
      ], $text);
      if ($this->configuration['title']) {
        $text = preg_replace('/(<[-a-z_]+[^>]*["\\s])title\\s*=\\s*("([^"]+)"|\'([^\']+)\')([^>]*>)/i', '$1 $5 $3$4 ', $text);
      }
      if ($this->configuration['alt']) {
        $text = preg_replace('/<[-a-z_]+[^>]*["\\s]alt\\s*=\\s*("([^"]+)"|\'([^\']+)\')[^>]*>/i', ' <img>$2$3</img> ', $text);
      }
    }
    if ($this->configuration['tags'] && $is_text_type) {
      $text = strip_tags($text, '<' . implode('><', array_keys($this->configuration['tags'])) . '>');
      $value = $this
        ->parseHtml($text);
    }
    else {
      $text = strip_tags($text);
      $value = $this
        ->normalizeText(trim($text));
    }
  }

  /**
   * {@inheritdoc}
   */
  protected function process(&$value) {
    $value = str_replace([
      '<',
      '>',
    ], [
      ' <',
      '> ',
    ], $value);
    $value = strip_tags($value);
    $value = $this
      ->normalizeText($value);
  }

  /**
   * Tokenizes an HTML string according to the HTML elements.
   *
   * Assigns boost values to the elements' contents accordingly.
   *
   * @param string $text
   *   The HTML string to parse, passed by reference. After the method call, the
   *   variable will contain the portion of the string after the current
   *   element, or an empty string (if there is no current element).
   * @param string|null $active_tag
   *   (optional) The currently active tag, for which a closing tag has to be
   *   found. Internal use only.
   * @param float $boost
   *   (optional) The currently active boost value. Internal use only.
   *
   * @return \Drupal\search_api\Plugin\search_api\data_type\value\TextTokenInterface[]
   *   Tokenized text with appropriate scores.
   */
  protected function parseHtml(&$text, $active_tag = NULL, $boost = 1.0) {
    $ret = [];
    while (($pos = strpos($text, '<')) !== FALSE) {
      $text_before = substr($text, 0, $pos);
      $text_after = substr($text, $pos + 1);

      // Attempt some small error tolerance when literal "<" characters aren't
      // escaped properly (and are free-standing).
      if (!preg_match('#^(/?)([-:_a-zA-Z0-9]+)#', $text_after, $m)) {
        $text = $text_before . '&lt;' . $text_after;
        continue;
      }
      if ($boost && $pos > 0) {
        $value = $this
          ->normalizeText($text_before);
        if ($value !== '') {
          $ret[] = Utility::createTextToken($value, $boost);
        }
      }
      $text = $text_after;
      $pos = strpos($text, '>');
      $empty_tag = $text[$pos - 1] == '/';
      $text = substr($text, $pos + 1);
      if ($m[1]) {

        // Closing tag.
        if ($active_tag && $m[2] == $active_tag) {
          return $ret;
        }
      }
      elseif (!$empty_tag) {

        // Opening tag => recursive call.
        $inner_boost = $boost * ($this->configuration['tags'][$m[2]] ?? 1);
        $ret = array_merge($ret, $this
          ->parseHtml($text, $m[2], $inner_boost));
      }
    }
    if ($text) {
      $value = $this
        ->normalizeText($text);
      if ($value !== '') {
        $ret[] = Utility::createTextToken($value, $boost);
      }
      $text = '';
    }
    return $ret;
  }

  /**
   * Removes superfluous whitespace and unescapes HTML entities.
   *
   * @param string $value
   *   The text to process.
   *
   * @return string
   *   The text without unnecessary whitespace and HTML entities transformed
   *   back to plain text.
   */
  protected function normalizeText($value) {
    $value = Html::decodeEntities($value);
    $value = trim($value);
    $value = preg_replace('/\\s+/', ' ', $value);
    return $value;
  }

}

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::$dependencies protected property The object's dependencies.
DependencyTrait::addDependencies protected function Adds multiple dependencies.
DependencyTrait::addDependency protected function Adds a dependency.
FieldsProcessorPluginBase::$elementInfoManager protected property The element info manager.
FieldsProcessorPluginBase::create public static function Creates an instance of the plugin. Overrides ProcessorPluginBase::create 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::processKey protected function Processes a single search keyword. 1
FieldsProcessorPluginBase::processKeys protected function Preprocesses the search keywords.
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
HtmlFilter::$dataTypeHelper protected property The data type helper. Overrides FieldsProcessorPluginBase::$dataTypeHelper
HtmlFilter::buildConfigurationForm public function Form constructor. Overrides FieldsProcessorPluginBase::buildConfigurationForm
HtmlFilter::defaultConfiguration public function Gets default configuration for this plugin. Overrides FieldsProcessorPluginBase::defaultConfiguration
HtmlFilter::getDataTypeHelper public function Retrieves the data type helper. Overrides FieldsProcessorPluginBase::getDataTypeHelper
HtmlFilter::normalizeText protected function Removes superfluous whitespace and unescapes HTML entities.
HtmlFilter::parseHtml protected function Tokenizes an HTML string according to the HTML elements.
HtmlFilter::process protected function Processes a single string value. Overrides FieldsProcessorPluginBase::process
HtmlFilter::processField protected function Processes a single field's value. Overrides FieldsProcessorPluginBase::processField
HtmlFilter::processFieldValue protected function Processes a single text element in a field. Overrides FieldsProcessorPluginBase::processFieldValue
HtmlFilter::setDataTypeHelper public function Sets the data type helper. Overrides FieldsProcessorPluginBase::setDataTypeHelper
HtmlFilter::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
PluginFormTrait::submitConfigurationForm public function Form submission handler. 7
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.