public function SearchTokenizerTest::testTokenizer in Drupal 10

Same name and namespace in other branches

1. 8 core/modules/search/tests/src/Kernel/SearchTokenizerTest.php \Drupal\Tests\search\Kernel\SearchTokenizerTest::testTokenizer()
2. 9 core/modules/search/tests/src/Kernel/SearchTokenizerTest.php \Drupal\Tests\search\Kernel\SearchTokenizerTest::testTokenizer()

Verifies that strings of CJK characters are tokenized.

The text analysis function does special things with numbers, symbols and punctuation. So we only test that CJK characters that are not in these character classes are tokenized properly. See PREG_CLASS_CKJ for more information.

File

core/modules/search/tests/src/Kernel/SearchTokenizerTest.php, line 28

Class

SearchTokenizerTest

Tests that CJK tokenizer works as intended.

Namespace

Drupal\Tests\search\Kernel

Code

public function testTokenizer() {

  // Set the minimum word size to 1 (to split all CJK characters) and make
  // sure CJK tokenizing is turned on.
  $this
    ->config('search.settings')
    ->set('index.minimum_word_size', 1)
    ->set('index.overlap_cjk', TRUE)
    ->save();

  // Create a string of CJK characters from various character ranges in the
  // Unicode tables.
  // Beginnings of the character ranges.
  $starts = [
    'CJK unified' => 0x4e00,
    'CJK Ext A' => 0x3400,
    'CJK Compat' => 0xf900,
    'Hangul Jamo' => 0x1100,
    'Hangul Ext A' => 0xa960,
    'Hangul Ext B' => 0xd7b0,
    'Hangul Compat' => 0x3131,
    'Half non-punct 1' => 0xff21,
    'Half non-punct 2' => 0xff41,
    'Half non-punct 3' => 0xff66,
    'Hangul Syllables' => 0xac00,
    'Hiragana' => 0x3040,
    'Katakana' => 0x30a1,
    'Katakana Ext' => 0x31f0,
    'CJK Reserve 1' => 0x20000,
    'CJK Reserve 2' => 0x30000,
    'Bomofo' => 0x3100,
    'Bomofo Ext' => 0x31a0,
    'Lisu' => 0xa4d0,
    'Yi' => 0xa000,
  ];

  // Ends of the character ranges.
  $ends = [
    'CJK unified' => 0x9fcf,
    'CJK Ext A' => 0x4dbf,
    'CJK Compat' => 0xfaff,
    'Hangul Jamo' => 0x11ff,
    'Hangul Ext A' => 0xa97f,
    'Hangul Ext B' => 0xd7ff,
    'Hangul Compat' => 0x318e,
    'Half non-punct 1' => 0xff3a,
    'Half non-punct 2' => 0xff5a,
    'Half non-punct 3' => 0xffdc,
    'Hangul Syllables' => 0xd7af,
    'Hiragana' => 0x309f,
    'Katakana' => 0x30ff,
    'Katakana Ext' => 0x31ff,
    'CJK Reserve 1' => 0x2fffd,
    'CJK Reserve 2' => 0x3fffd,
    'Bomofo' => 0x312f,
    'Bomofo Ext' => 0x31b7,
    'Lisu' => 0xa4fd,
    'Yi' => 0xa48f,
  ];

  // Generate characters consisting of starts, midpoints, and ends.
  $chars = [];
  foreach ($starts as $key => $value) {
    $chars[] = $this
      ->code2utf($starts[$key]);
    $mid = round(0.5 * ($starts[$key] + $ends[$key]));
    $chars[] = $this
      ->code2utf($mid);
    $chars[] = $this
      ->code2utf($ends[$key]);
  }

  // Merge into a string and tokenize.
  $string = implode('', $chars);
  $text_processor = \Drupal::service('search.text_processor');
  assert($text_processor instanceof SearchTextProcessorInterface);
  $out = trim($text_processor
    ->analyze($string));
  $expected = mb_strtolower(implode(' ', $chars));

  // Verify that the output matches what we expect.
  $this
    ->assertEquals($expected, $out, 'CJK tokenizer worked on all supplied CJK characters');
}