php-ml/src/Phpml/Tokenization/WhitespaceTokenizer.php

14 lines
252 B
PHP

<?php
declare(strict_types=1);
namespace Phpml\Tokenization;
class WhitespaceTokenizer implements Tokenizer
{
public function tokenize(string $text): array
{
return preg_split('/[\pZ\pC]+/u', $text, -1, PREG_SPLIT_NO_EMPTY);
}
}