A modern, accurate HTML parser and serializer for PHP
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

41 lines
1.2 KiB

<?php
declare(strict_types=1);
namespace dW\HTML5\TestCase;
use dW\HTML5\Data;
use dW\HTML5\EOFToken;
use dW\HTML5\OpenElementsStack;
use dW\HTML5\Tokenizer;
class TestTokenizer extends \dW\HTML5\Test\StandardTest {
const DEBUG = false;
public function setUp(): void {
if (self::DEBUG) {
ob_end_clean();
Tokenizer::$debug = true;
}
}
/** @dataProvider provideStandardTokenizerTests */
public function testStandardTokenizerTests(string $input, array $expected, int $state, string $open = null, array $errors) {
$data = new Data($input);
$stack = new OpenElementsStack();
if ($open) {
$stack[] = $open;
}
$tokenizer = new Tokenizer($data, $stack);
$tokenizer->state = $state;
$actual = [];
do {
$t = $tokenizer->createToken();
$actual[] = $t;
} while (!($t instanceof EOFToken));
array_pop($actual);
$this->assertEquals($expected, $actual);
}
public function provideStandardTokenizerTests() {
return $this->makeTokenTests(__DIR__."/../html5lib-tests/tokenizer/test1.test");
}
}