0
0
mirror of https://github.com/ezyang/htmlpurifier.git synced 2024-11-08 14:58:42 +00:00
htmlpurifier/tests/HTMLPurifier/EncoderTest.php

177 lines
6.2 KiB
PHP

<?php
class HTMLPurifier_EncoderTest extends HTMLPurifier_Harness
{
protected $_entity_lookup;
function setUp() {
$this->_entity_lookup = HTMLPurifier_EntityLookup::instance();
parent::setUp();
}
function assertCleanUTF8($string, $expect = null) {
if ($expect === null) $expect = $string;
$this->assertIdentical(HTMLPurifier_Encoder::cleanUTF8($string), $expect, 'iconv: %s');
$this->assertIdentical(HTMLPurifier_Encoder::cleanUTF8($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
// invalid codepoints
$this->assertCleanUTF8("\xED\xB0\x80", '');
}
function test_convertToUTF8_noConvert() {
// UTF-8 means that we don't touch it
$this->assertIdentical(
HTMLPurifier_Encoder::convertToUTF8("\xF6", $this->config, $this->context),
"\xF6", // this is invalid
'Expected identical [Binary: F6]'
);
}
function test_convertToUTF8_iso8859_1() {
$this->config->set('Core', 'Encoding', 'ISO-8859-1');
$this->assertIdentical(
HTMLPurifier_Encoder::convertToUTF8("\xF6", $this->config, $this->context),
"\xC3\xB6"
);
}
function test_convertToUTF8_withoutIconv() {
$this->config->set('Core', 'Encoding', 'ISO-8859-1');
$this->config->set('Test', 'ForceNoIconv', true);
$this->assertIdentical(
HTMLPurifier_Encoder::convertToUTF8("\xF6", $this->config, $this->context),
"\xC3\xB6"
);
}
function getZhongWen() {
return "\xE4\xB8\xAD\xE6\x96\x87 (Chinese)";
}
function test_convertFromUTF8_utf8() {
// UTF-8 means that we don't touch it
$this->assertIdentical(
HTMLPurifier_Encoder::convertFromUTF8("\xC3\xB6", $this->config, $this->context),
"\xC3\xB6"
);
}
function test_convertFromUTF8_iso8859_1() {
$this->config->set('Core', 'Encoding', 'ISO-8859-1');
$this->assertIdentical(
HTMLPurifier_Encoder::convertFromUTF8("\xC3\xB6", $this->config, $this->context),
"\xF6",
'Expected identical [Binary: F6]'
);
}
function test_convertFromUTF8_iconvNoChars() {
if (!function_exists('iconv')) return;
$this->config->set('Core', 'Encoding', 'ISO-8859-1');
$this->assertIdentical(
HTMLPurifier_Encoder::convertFromUTF8($this->getZhongWen(), $this->config, $this->context),
" (Chinese)"
);
}
function test_convertFromUTF8_phpNormal() {
// Plain PHP implementation has slightly different behavior
$this->config->set('Core', 'Encoding', 'ISO-8859-1');
$this->config->set('Test', 'ForceNoIconv', true);
$this->assertIdentical(
HTMLPurifier_Encoder::convertFromUTF8("\xC3\xB6", $this->config, $this->context),
"\xF6",
'Expected identical [Binary: F6]'
);
}
function test_convertFromUTF8_phpNoChars() {
$this->config->set('Core', 'Encoding', 'ISO-8859-1');
$this->config->set('Test', 'ForceNoIconv', true);
$this->assertIdentical(
HTMLPurifier_Encoder::convertFromUTF8($this->getZhongWen(), $this->config, $this->context),
"?? (Chinese)"
);
}
function test_convertFromUTF8_withProtection() {
// Preserve the characters!
$this->config->set('Core', 'Encoding', 'ISO-8859-1');
$this->config->set('Core', 'EscapeNonASCIICharacters', true);
$this->assertIdentical(
HTMLPurifier_Encoder::convertFromUTF8($this->getZhongWen(), $this->config, $this->context),
"&#20013;&#25991; (Chinese)"
);
}
function test_convertToASCIIDumbLossless() {
// Uppercase thorn letter
$this->assertIdentical(
HTMLPurifier_Encoder::convertToASCIIDumbLossless("\xC3\x9Eorn"),
"&#222;orn"
);
$this->assertIdentical(
HTMLPurifier_Encoder::convertToASCIIDumbLossless("an"),
"an"
);
// test up to four bytes
$this->assertIdentical(
HTMLPurifier_Encoder::convertToASCIIDumbLossless("\xF3\xA0\x80\xA0"),
"&#917536;"
);
}
function assertASCIISupportCheck($enc, $ret) {
$test = HTMLPurifier_Encoder::testEncodingSupportsASCII($enc, true);
if ($test === false) return;
$this->assertIdentical(
HTMLPurifier_Encoder::testEncodingSupportsASCII($enc),
$ret
);
$this->assertIdentical(
HTMLPurifier_Encoder::testEncodingSupportsASCII($enc, true),
$ret
);
}
function test_testEncodingSupportsASCII() {
$this->assertASCIISupportCheck('Shift_JIS', array("\xC2\xA5" => '\\', "\xE2\x80\xBE" => '~'));
$this->assertASCIISupportCheck('JOHAB', array("\xE2\x82\xA9" => '\\'));
$this->assertASCIISupportCheck('ISO-8859-1', array());
$this->assertASCIISupportCheck('dontexist', array()); // canary
}
function testShiftJIS() {
if (!function_exists('iconv')) return;
$this->config->set('Core', 'Encoding', 'Shift_JIS');
// This actually looks like a Yen, but we're going to treat it differently
$this->assertIdentical(
HTMLPurifier_Encoder::convertFromUTF8('\\~', $this->config, $this->context),
'\\~'
);
$this->assertIdentical(
HTMLPurifier_Encoder::convertToUTF8('\\~', $this->config, $this->context),
'\\~'
);
}
}