mirror of
https://github.com/ezyang/htmlpurifier.git
synced 2024-11-08 23:08:42 +00:00
8f515b9cda
- Partially finished migrating to new Context object (done in r485). - Created HTMLPurifier_Harness to assist with testing, ChildDefTest migrated to that framework. git-svn-id: http://htmlpurifier.org/svnroot/htmlpurifier/trunk@484 48356398-32a2-884e-a903-53898d9a118a
89 lines
2.8 KiB
PHP
89 lines
2.8 KiB
PHP
<?php
|
|
|
|
require_once 'HTMLPurifier/Encoder.php';
|
|
|
|
class HTMLPurifier_EncoderTest extends UnitTestCase
|
|
{
|
|
|
|
var $Encoder;
|
|
|
|
function setUp() {
|
|
$this->Encoder = new HTMLPurifier_Encoder();
|
|
$this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
|
|
}
|
|
|
|
function assertCleanUTF8($string, $expect = null) {
|
|
if ($expect === null) $expect = $string;
|
|
$this->assertIdentical($this->Encoder->cleanUTF8($string), $expect, 'iconv: %s');
|
|
$this->assertIdentical($this->Encoder->cleanUTF8($string, true), $expect, 'PHP: %s');
|
|
}
|
|
|
|
function test_cleanUTF8() {
|
|
$this->assertCleanUTF8('Normal string.');
|
|
$this->assertCleanUTF8("Test\tAllowed\nControl\rCharacters");
|
|
$this->assertCleanUTF8("null byte: \0", 'null byte: ');
|
|
$this->assertCleanUTF8("\1\2\3\4\5\6\7", '');
|
|
$this->assertCleanUTF8("\x7F", ''); // one byte invalid SGML char
|
|
$this->assertCleanUTF8("\xC2\x80", ''); // two byte invalid SGML
|
|
$this->assertCleanUTF8("\xF3\xBF\xBF\xBF"); // valid four byte
|
|
$this->assertCleanUTF8("\xDF\xFF", ''); // malformed UTF8
|
|
}
|
|
|
|
function test_convertToUTF8() {
|
|
$config = HTMLPurifier_Config::createDefault();
|
|
$context = new HTMLPurifier_Context();
|
|
|
|
// UTF-8 means that we don't touch it
|
|
$this->assertIdentical(
|
|
$this->Encoder->convertToUTF8("\xF6", $config, $context),
|
|
"\xF6" // this is invalid
|
|
);
|
|
$this->assertNoErrors();
|
|
|
|
$config->set('Core', 'Encoding', 'ISO-8859-1');
|
|
|
|
// Now it gets converted
|
|
$this->assertIdentical(
|
|
$this->Encoder->convertToUTF8("\xF6", $config, $context),
|
|
"\xC3\xB6"
|
|
);
|
|
|
|
$config->set('Test', 'ForceNoIconv', true);
|
|
|
|
$this->assertIdentical(
|
|
$this->Encoder->convertToUTF8("\xF6", $config, $context),
|
|
"\xC3\xB6"
|
|
);
|
|
|
|
}
|
|
|
|
function test_convertFromUTF8() {
|
|
$config = HTMLPurifier_Config::createDefault();
|
|
$context = new HTMLPurifier_Context();
|
|
|
|
// UTF-8 means that we don't touch it
|
|
$this->assertIdentical(
|
|
$this->Encoder->convertFromUTF8("\xC3\xB6", $config, $context),
|
|
"\xC3\xB6"
|
|
);
|
|
|
|
$config->set('Core', 'Encoding', 'ISO-8859-1');
|
|
|
|
// Now it gets converted
|
|
$this->assertIdentical(
|
|
$this->Encoder->convertFromUTF8("\xC3\xB6", $config, $context),
|
|
"\xF6"
|
|
);
|
|
|
|
$config->set('Test', 'ForceNoIconv', true);
|
|
|
|
$this->assertIdentical(
|
|
$this->Encoder->convertFromUTF8("\xC3\xB6", $config, $context),
|
|
"\xF6"
|
|
);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
?>
|