processor_search.inc in Fuzzy Search 7

File

includes/processor_search.inc

<?php

/**
 * Processor to set the index and search settings. Requires FuzzySearchService.
 */
class FuzzysearchSearch extends SearchApiAbstractProcessor {

  /**
   * Checks whether this processor is applicable for a certain index.
   *
   * @param \SearchApiIndex $index
   *   The index to check for.
   *
   * @return bool
   *   TRUE if the processor can run on the given index; FALSE otherwise.
   */
  public function supportsIndex(SearchApiIndex $index) {
    return $index
      ->server() && $index
      ->server()
      ->supportsFeature('fuzzysearch');
  }

  /**
   * Return the processor configuration form.
   *
   * @return array
   *   Associative configuration form array.
   */
  public function configurationForm() {
    $form['ngram_length'] = array(
      '#type' => 'select',
      '#title' => t('Ngram length'),
      '#description' => t('Choose 3 unless you have special requirements.'),
      '#options' => drupal_map_assoc(array(
        2,
        3,
        4,
        5,
        6,
      )),
      '#default_value' => 3,
    );
    $form['missing_letters'] = array(
      '#type' => 'select',
      '#title' => t('Assume missing letters in search terms'),
      '#description' => t('A search term as entered by a user may be missing letters. Up to how many missing letters in the term do you want to assume? 0 means the term will not return longer words in the results. 1 means a 4 letter search term will also check 5 letters words in the index.'),
      '#options' => drupal_map_assoc(range(0, 50)),
      '#default_value' => 5,
    );
    $form['extra_letters'] = array(
      '#type' => 'select',
      '#title' => t('Assume extra letters in search terms'),
      '#description' => t('A search term as entered by a user may have extra letters. Up to how many extra letters in the term do you want to assume? 0 means the term will not return shorter words in the results. 1 means a 4 letter search term will also check 3 letters words in the index.'),
      '#options' => drupal_map_assoc(range(0, 50)),
      '#default_value' => 5,
    );
    $form['completeness'] = array(
      '#type' => 'textfield',
      '#title' => t('Minimum completeness'),
      '#size' => 3,
      '#maxlength' => 3,
      '#description' => t('Enter a value between 0 and 100 to set the minimum match completeness required in the returned results.'),
      '#default_value' => 40,
    );
    $form['sort_score'] = array(
      '#type' => 'checkbox',
      '#title' => t('Sort by score'),
      '#description' => t('If selected, the results will be sorted by score first and completeness second, which can make tag scores even more important. The default is to sort by completeness first.'),
      '#default_value' => FALSE,
    );
    if (!empty($this->options)) {
      $form['ngram_length']['#default_value'] = $this->options['ngram_length'];
      $form['missing_letters']['#default_value'] = $this->options['missing_letters'];
      $form['extra_letters']['#default_value'] = $this->options['extra_letters'];
      $form['completeness']['#default_value'] = $this->options['completeness'];
      $form['sort_score']['#default_value'] = $this->options['sort_score'];
    }
    return $form;
  }

  /**
   * Validate the processor configuration form values.
   *
   * @param array $form
   *   The form array.
   * @param array $values
   *   The form values to validate.
   * @param array $form_state
   *   The form state.
   */
  public function configurationFormValidate(array $form, array &$values, array &$form_state) {
    if (!is_numeric($values['completeness']) || $values['completeness'] < 0 || $values['completeness'] > 100) {
      form_error($form['completeness'], t('The Fuzzy Search processor completeness setting must use a numeric value between 0 and 100.'));
    }
  }

  /**
   * {@inheritdoc}
   */
  public function preprocessIndexItems(array &$items) {
    foreach ($items as &$item) {
      foreach ($item as $name => &$field) {
        if ($this
          ->testField($name, $field)) {
          $this
            ->split($field);
        }
      }
    }
  }

  /**
   * Split token fields into ngrams.
   *
   * @param array $field
   *   Associative array of field information.
   */
  protected function split(array &$field) {
    if ($field['type'] == 'tokens') {
      foreach ($field['value'] as $key => $value) {
        $word = '';
        $word = $value['value'];
        $length = drupal_strlen($word);
        if ($length < $this->options['ngram_length']) {
          continue;
        }

        // Cleanse and remove spaces.
        $ngrams = array(
          'ngrams' => array(),
        );
        $word = str_replace(' ', '', fuzzysearch_cleanse($word));
        $ngrams['completeness'] = $length - $this->options['ngram_length'] + 1 == 0 ? 100 : number_format(100 / ($length - $this->options['ngram_length'] + 1), 3);
        $ngrams['comp_min'] = number_format(100 / ($length - $this->options['ngram_length'] + 1 + $this->options['missing_letters']), 3);
        if ($length - $this->options['ngram_length'] + 1 - $this->options['extra_letters'] <= 0) {
          $ngrams['comp_max'] = number_format(100, 3) + 0.001;
        }
        else {
          $ngrams['comp_max'] = number_format(100 / ($length - $this->options['ngram_length'] + 1 - $this->options['extra_letters']), 3) + 0.001;
        }

        // Split word into ngrams.
        for ($i = 0; $i < $length - $this->options['ngram_length'] + 1; $i++) {
          $ngrams['ngrams'][] = drupal_substr($word, $i, $this->options['ngram_length']);
        }
        $field['value'][$key] += $ngrams;
        $i = 9;
      }
    }
  }

}

Classes

Name	Description
FuzzysearchSearch	Processor to set the index and search settings. Requires FuzzySearchService.