Issue #3261239 by andypost, longwave: Remove deprecations from search module

use Drupal\Core\Url;

use Drupal\search\SearchTextProcessorInterface;

/**

 * Matches all 'N' Unicode character classes (numbers)

 *

 * @deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use

 *   \Drupal\search\SearchTextProcessorInterface::PREG_CLASS_NUMBERS instead.

 *

 * @see https://www.drupal.org/node/3078162

 */

define('PREG_CLASS_NUMBERS', SearchTextProcessorInterface::PREG_CLASS_NUMBERS);

/**

 * Matches all 'P' Unicode character classes (punctuation)

 *

 * @deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use

 *   \Drupal\search\SearchTextProcessorInterface::PREG_CLASS_PUNCTUATION

 *   instead.

 *

 * @see https://www.drupal.org/node/3078162

 */

define('PREG_CLASS_PUNCTUATION', SearchTextProcessorInterface::PREG_CLASS_PUNCTUATION);

/**

 * Matches CJK (Chinese, Japanese, Korean) letter-like characters.

 *

 * This list is derived from the "East Asian Scripts" section of

 * http://www.unicode.org/charts/index.html, as well as a comment on

 * http://unicode.org/reports/tr11/tr11-11.html listing some character

 * ranges that are reserved for additional CJK ideographs.

 *

 * The character ranges do not include numbers, punctuation, or symbols, since

 * these are handled separately in search. Note that radicals and strokes are

 * considered symbols. (See

 * http://www.unicode.org/Public/UNIDATA/extracted/DerivedGeneralCategory.txt)

 *

 * @deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use

 *   \Drupal\search\SearchTextProcessorInterface::PREG_CLASS_CJK instead.

 *

 * @see https://www.drupal.org/node/3078162

 */

define('PREG_CLASS_CJK', SearchTextProcessorInterface::PREG_CLASS_CJK);

/**

 * Implements hook_help().

 */

  }

}

/**

 * Simplifies and preprocesses text for searching.

 *

 * Processing steps:

 * - Entities are decoded.

 * - Text is lower-cased and diacritics (accents) are removed.

 * - hook_search_preprocess() is invoked.

 * - CJK (Chinese, Japanese, Korean) characters are processed, depending on

 *   the search settings.

 * - Punctuation is processed (removed or replaced with spaces, depending on

 *   where it is; see code for details).

 * - Words are truncated to 50 characters maximum.

 *

 * @param string $text

 *   Text to simplify.

 * @param string|null $langcode

 *   Language code for the language of $text, if known.

 *

 * @return string

 *   Simplified and processed text.

 *

 * @deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use

 *   \Drupal\search\SearchTextProcessorInterface::analyze() instead.

 *

 * @see https://www.drupal.org/node/3078162

 * @see hook_search_preprocess()

 */

function search_simplify($text, $langcode = NULL) {

  @trigger_error('search_simplify() is deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use \Drupal\search\SearchTextProcessorInterface::analyze() instead. See https://www.drupal.org/node/3078162', E_USER_DEPRECATED);

  return \Drupal::service('search.text_processor')->analyze($text, $langcode);

}

/**

 * Splits CJK (Chinese, Japanese, Korean) text into tokens.

 *

 * The Search module matches exact words, where a word is defined to be a

 * sequence of characters delimited by spaces or punctuation. CJK languages are

 * written in long strings of characters, though, not split up into words. So

 * in order to allow search matching, we split up CJK text into tokens

 * consisting of consecutive, overlapping sequences of characters whose length

 * is equal to the 'minimum_word_size' variable. This tokenizing is only done

 * if the 'overlap_cjk' variable is TRUE.

 *

 * @param array $matches

 *   This function is a callback for preg_replace_callback(), which is called

 *   from search_simplify(). So, $matches is an array of regular expression

 *   matches, which means that $matches[0] contains the matched text -- a

 *   string of CJK characters to tokenize.

 *

 * @return string

 *   Tokenized text, starting and ending with a space character.

 *

 * @deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use a

 *   custom implementation of SearchTextProcessorInterface instead.

 *

 * @see https://www.drupal.org/node/3078162

 */

function search_expand_cjk($matches) {

  @trigger_error('search_expand_cjk() is deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use a custom implementation of SearchTextProcessorInterface instead. instead. See https://www.drupal.org/node/3078162', E_USER_DEPRECATED);

  $min = \Drupal::config('search.settings')->get('index.minimum_word_size');

  $str = $matches[0];

  $length = mb_strlen($str);

  // If the text is shorter than the minimum word size, don't tokenize it.

  if ($length <= $min) {

    return ' ' . $str . ' ';

  }

  $tokens = ' ';

  // Build a FIFO queue of characters.

  $chars = [];

  for ($i = 0; $i < $length; $i++) {

    // Add the next character off the beginning of the string to the queue.

    $current = mb_substr($str, 0, 1);

    $str = substr($str, strlen($current));

    $chars[] = $current;

    if ($i >= $min - 1) {

      // Make a token of $min characters, and add it to the token string.

      $tokens .= implode('', $chars) . ' ';

      // Shift out the first character in the queue.

      array_shift($chars);

    }

  }

  return $tokens;

}

/**

 * Simplifies and splits a string into words for indexing.

 *

 * @param string $text

 *   Text to process.

 * @param string|null $langcode

 *   Language code for the language of $text, if known.

 *

 * @return array

 *   Array of words in the simplified, preprocessed text.

 *

 * @deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use a

 *   \Drupal\search\SearchTextProcessorInterface::process() instead.

 *

 * @see https://www.drupal.org/node/3078162

 * @see search_simplify()

 */

function search_index_split($text, $langcode = NULL) {

  @trigger_error('search_index_split() is deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use \Drupal\search\SearchTextProcessorInterface::process() instead. See https://www.drupal.org/node/3078162', E_USER_DEPRECATED);

  return \Drupal::service('search.text_processor')->process($text, $langcode);

}

/**

 * Invokes hook_search_preprocess() to simplify text.

 *

 * @param string $text

 *   Text to preprocess, passed by reference and altered in place.

 * @param string|null $langcode

 *   Language code for the language of $text, if known.

 *

 * @deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use a

 *   custom implementation of SearchTextProcessor instead.

 *

 * @see https://www.drupal.org/node/3078162

 */

function search_invoke_preprocess(&$text, $langcode = NULL) {

  @trigger_error('search_invoke_preprocess() is deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use a custom implementation of SearchTextProcessorInterface instead. See https://www.drupal.org/node/3078162', E_USER_DEPRECATED);

  foreach (\Drupal::moduleHandler()->getImplementations('search_preprocess') as $module) {

    $text = \Drupal::moduleHandler()->invoke($module, 'search_preprocess', [$text, $langcode]);

  }

}

/**

 * @defgroup search Search interface

 * @{

 */

function search_excerpt($keys, $text, $langcode = NULL) {

  // We highlight around non-indexable or CJK characters.

  $boundary_character = '[' . Unicode::PREG_CLASS_WORD_BOUNDARY . PREG_CLASS_CJK . ']';

  $boundary_character = '[' . Unicode::PREG_CLASS_WORD_BOUNDARY . SearchTextProcessorInterface::PREG_CLASS_CJK . ']';

  $preceded_by_boundary = '(?<=' . $boundary_character . ')';

  $followed_by_boundary = '(?=' . $boundary_character . ')';

   * @param \Drupal\search\SearchTextProcessorInterface $text_processor

   *   The text processor.

   */

  public function __construct(ConfigFactoryInterface $config_factory, Connection $connection, Connection $replica, CacheTagsInvalidatorInterface $cache_tags_invalidator, SearchTextProcessorInterface $text_processor = NULL) {

  public function __construct(ConfigFactoryInterface $config_factory, Connection $connection, Connection $replica, CacheTagsInvalidatorInterface $cache_tags_invalidator, SearchTextProcessorInterface $text_processor) {

    $this->configFactory = $config_factory;

    $this->connection = $connection;

    $this->replica = $replica;

    $this->cacheTagsInvalidator = $cache_tags_invalidator;

    if ($text_processor === NULL) {

      @trigger_error('Calling ' . __METHOD__ . ' without $text_processor argument is deprecated in drupal:9.1.0 and will be required in drupal:10.0.0. See https://www.drupal.org/node/3078162', E_USER_DEPRECATED);

      $text_processor = \Drupal::service('search.text_processor');

    }

    $this->textProcessor = $text_processor;

  }

<?php

namespace Drupal\Tests\search\Kernel;

use Drupal\KernelTests\KernelTestBase;

/**

 * Tests deprecated search methods.

 *

 * @group legacy

 * @group search

 */

class SearchDeprecationTest extends KernelTestBase {

  /**

   * {@inheritdoc}

   */

  protected static $modules = ['search'];

  /**

   * {@inheritdoc}

   */

  protected function setUp(): void {

    parent::setUp();

    $this->installSchema('search', [

      'search_index',

      'search_dataset',

      'search_total',

    ]);

    $this->installConfig(['search']);

  }

  public function testDeprecatedIndexSplit() {

    $this->expectDeprecation('search_index_split() is deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use \Drupal\search\SearchTextProcessorInterface::process() instead. See https://www.drupal.org/node/3078162');

    $this->assertEquals(["two", "words"], search_index_split("two words"));

  }

  public function testDeprecatedSimplify() {

    $this->expectDeprecation('search_simplify() is deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use \Drupal\search\SearchTextProcessorInterface::analyze() instead. See https://www.drupal.org/node/3078162');

    // cSpell:disable-next-line

    $this->assertEquals("vogel", search_simplify("Vögel"));

  }

  public function testExpandCjk() {

    $this->expectDeprecation('search_expand_cjk() is deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use a custom implementation of SearchTextProcessorInterface instead. instead. See https://www.drupal.org/node/3078162');

    $this->assertEquals(" 이런 ", search_expand_cjk(["이런"]));

  }

  public function testInvokePreprocess() {

    $this->expectDeprecation('search_invoke_preprocess() is deprecated in drupal:9.1.0 and is removed from drupal:10.0.0. Use a custom implementation of SearchTextProcessorInterface instead. See https://www.drupal.org/node/3078162');

    $text = $this->randomString();

    search_invoke_preprocess($text);

    $this->assertIsString($text);

  }

}