MensBeam
/
HTML-Parser
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Browse Source

Add more tests

ns
J. King 5 years ago
parent
ab507a177f
commit
1beb934789
2 changed files with 71 additions and 40 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 11
      tests/cases/TestTokenizer.php
  2. 100
      tests/lib/StandardTest.php

11
tests/cases/TestTokenizer.php
View File

@ -21,7 +21,7 @@ class TestTokenizer extends \dW\HTML5\Test\StandardTest {
$data = new Data($input);
$stack = new OpenElementsStack();
if ($open) {
$stack[] = $open;
$stack[] = (new \DOMDocument)->createElement($open);
}
$tokenizer = new Tokenizer($data, $stack);
$tokenizer->state = $state;
@ -35,6 +35,13 @@ class TestTokenizer extends \dW\HTML5\Test\StandardTest {
}
public function provideStandardTokenizerTests() {
return $this->makeTokenTests(__DIR__."/../html5lib-tests/tokenizer/test1.test");
$tests = [];
$blacklist = ["pendingSpecChanges.test", "xmlViolation.test"];
foreach (new \GlobIterator(\dW\HTML5\BASE."tests/html5lib-tests/tokenizer/*.test", \FilesystemIterator::SKIP_DOTS | \FilesystemIterator::CURRENT_AS_PATHNAME) as $file) {
if (!in_array(basename($file), $blacklist)) {
$tests[] = $file;
}
}
return $this->makeTokenTests(...$tests);
}
}

100
tests/lib/StandardTest.php
View File

@ -19,47 +19,71 @@ class StandardTest extends \PHPUnit\Framework\TestCase {
'CDATA section state' => Tokenizer::CDATA_SECTION_STATE,
];
protected function makeTokenTests(string $file): iterable {
$testSet = json_decode(file_get_contents($file), true);
foreach ($testSet['tests'] as $index => $test) {
$test['initialStates'] = $test['initialStates'] ?? ["Data state"];
for ($a = 0; $a < sizeof($test['initialStates']); $a++) {
$tokens = [];
foreach ($test['output'] as $token) {
switch ($token[0]) {
case "DOCTYPE":
$t = new DOCTYPEToken((string) $token[1], (string) $token[2], (string) $token[3]);
$t->forceQuirks = !$token[4];
$tokens[] = $t;
break;
case "StartTag":
$t = new StartTagToken($token[1], $token[3] ?? false);
foreach ($token[2] ?? [] as $name => $value) {
$t->setAttribute($name, $value);
protected function reverseDoubleEscape(string $str): string {
if (preg_match_all("/\\\\u([0-9a-f]{4})/i", $str, $matches)) {
for ($a = 0; $a < sizeof($matches[0]); $a++) {
$esc = $matches[0][$a];
$chr = \MensBeam\Intl\Encoding\UTF8::encode(hexdec($matches[1][$a]));
$str = str_replace($esc, $chr, $str);
}
}
return $str;
}
protected function makeTokenTests(string ...$file): iterable {
foreach ($file as $path) {
$f = basename($path);
$testSet = json_decode(file_get_contents($path), true);
foreach ($testSet['tests'] ?? $testSet['xmlViolationTests'] as $index => $test) {
if ($test['doubleEscaped'] ?? false) {
$test['input'] = $this->reverseDoubleEscape($test['input']);
for ($a = 0; $a < sizeof($test['output']); $a++) {
for ($b = 0; $b < sizeof($test['output'][$a]); $b++) {
if (is_string($test['output'][$a][$b])) {
$test['output'][$a][$b] = $this->reverseDoubleEscape($test['output'][$a][$b]);
}
$tokens[] = $t;
break;
case "EndTag":
$tokens[] = new EndTagToken($token[1]);
break;
case "Character":
$tokens[] = new CharacterToken($token[1]);
break;
case "Comment":
$tokens[] = new CommentToken($token[1]);
break;
default:
throw new \Exception("Token type '{$token[0]}' not implemented in standard test interpreter");
}
}
}
$test['initialStates'] = $test['initialStates'] ?? ["Data state"];
for ($a = 0; $a < sizeof($test['initialStates']); $a++) {
$tokens = [];
foreach ($test['output'] as $token) {
switch ($token[0]) {
case "DOCTYPE":
$t = new DOCTYPEToken((string) $token[1], (string) $token[2], (string) $token[3]);
$t->forceQuirks = !$token[4];
$tokens[] = $t;
break;
case "StartTag":
$t = new StartTagToken($token[1], $token[3] ?? false);
foreach ($token[2] ?? [] as $name => $value) {
$t->setAttribute((string) $name, $value);
}
$tokens[] = $t;
break;
case "EndTag":
$tokens[] = new EndTagToken($token[1]);
break;
case "Character":
$tokens[] = new CharacterToken($token[1]);
break;
case "Comment":
$tokens[] = new CommentToken($token[1]);
break;
default:
throw new \Exception("Token type '{$token[0]}' not implemented in standard test interpreter");
}
unset($t);
}
unset($t);
yield "$f #$index: {$test['description']} ({$test['initialStates'][$a]})" => [
$test['input'], // input
$tokens, // output
self::STATE_MAP[$test['initialStates'][$a]], // initial state
$test['lastStartTag'] ?? null, // open element, if any
$test['errors'] ?? [], // errors, if any
];
}
yield "{$test['description']} ({$test['initialStates'][$a]})" => [
$test['input'], // input
$tokens, // output
self::STATE_MAP[$test['initialStates'][$a]], // initial state
$test['lastStartTag'] ?? null, // open element, if any
$test['errors'] ?? [], // errors, if any
];
}
}
}

Write Preview
Loading…
Cancel
Save