config->set('Core.MaintainLineNumbers', true);
$lexer = HTMLPurifier_Lexer::create($this->config);
$this->assertIsA($lexer, 'HTMLPurifier_Lexer_DirectLex');
}
function test_create_objectLexerImpl() {
$this->config->set('Core.LexerImpl', new HTMLPurifier_Lexer_DirectLex());
$lexer = HTMLPurifier_Lexer::create($this->config);
$this->assertIsA($lexer, 'HTMLPurifier_Lexer_DirectLex');
}
function test_create_unknownLexer() {
$this->config->set('Core.LexerImpl', 'AsdfAsdf');
$this->expectException(new HTMLPurifier_Exception('Cannot instantiate unrecognized Lexer type AsdfAsdf'));
HTMLPurifier_Lexer::create($this->config);
}
function test_create_incompatibleLexer() {
$this->config->set('Core.LexerImpl', 'DOMLex');
$this->config->set('Core.MaintainLineNumbers', true);
$this->expectException(new HTMLPurifier_Exception('Cannot use lexer that does not support line numbers with Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)'));
HTMLPurifier_Lexer::create($this->config);
}
// HTMLPurifier_Lexer->parseData() -----------------------------------------
function assertParseData($input, $expect = true) {
if ($expect === true) $expect = $input;
$lexer = new HTMLPurifier_Lexer();
$this->assertIdentical($expect, $lexer->parseData($input));
}
function test_parseData_plainText() {
$this->assertParseData('asdf');
}
function test_parseData_ampersandEntity() {
$this->assertParseData('&', '&');
}
function test_parseData_quotEntity() {
$this->assertParseData('"', '"');
}
function test_parseData_aposNumericEntity() {
$this->assertParseData(''', "'");
}
function test_parseData_aposCompactNumericEntity() {
$this->assertParseData(''', "'");
}
function test_parseData_adjacentAmpersandEntities() {
$this->assertParseData('&&&', '&&&');
}
function test_parseData_trailingUnescapedAmpersand() {
$this->assertParseData('&&', '&&');
}
function test_parseData_internalUnescapedAmpersand() {
$this->assertParseData('Procter & Gamble');
}
function test_parseData_improperEntityFaultToleranceTest() {
$this->assertParseData('-');
}
// HTMLPurifier_Lexer->extractBody() ---------------------------------------
function assertExtractBody($text, $extract = true) {
$lexer = new HTMLPurifier_Lexer();
$result = $lexer->extractBody($text);
if ($extract === true) $extract = $text;
$this->assertIdentical($extract, $result);
}
function test_extractBody_noBodyTags() {
$this->assertExtractBody('Bold');
}
function test_extractBody_lowercaseBodyTags() {
$this->assertExtractBody('Bold', 'Bold');
}
function test_extractBody_uppercaseBodyTags() {
$this->assertExtractBody('Bold', 'Bold');
}
function test_extractBody_realisticUseCase() {
$this->assertExtractBody(
'
xyz
',
'
');
}
function test_extractBody_bodyWithAttributes() {
$this->assertExtractBody('Bold', 'Bold');
}
function test_extractBody_preserveUnclosedBody() {
$this->assertExtractBody('asdf'); // not closed, don't accept
}
function test_extractBody_useLastBody() {
$this->assertExtractBody('foobar', 'foo bar');
}
// HTMLPurifier_Lexer->tokenizeHTML() --------------------------------------
function assertTokenization($input, $expect, $alt_expect = array()) {
$lexers = array();
$lexers['DirectLex'] = new HTMLPurifier_Lexer_DirectLex();
if (class_exists('DOMDocument')) {
$lexers['DOMLex'] = new HTMLPurifier_Lexer_DOMLex();
$lexers['PH5P'] = new HTMLPurifier_Lexer_PH5P();
}
foreach ($lexers as $name => $lexer) {
$result = $lexer->tokenizeHTML($input, $this->config, $this->context);
if (isset($alt_expect[$name])) {
if ($alt_expect[$name] === false) continue;
$t_expect = $alt_expect[$name];
$this->assertIdentical($result, $alt_expect[$name], "$name: %s");
} else {
$t_expect = $expect;
$this->assertIdentical($result, $expect, "$name: %s");
}
if ($t_expect != $result) {
printTokens($result);
}
}
}
function test_tokenizeHTML_emptyInput() {
$this->assertTokenization('', array());
}
function test_tokenizeHTML_plainText() {
$this->assertTokenization(
'This is regular text.',
array(
new HTMLPurifier_Token_Text('This is regular text.')
)
);
}
function test_tokenizeHTML_textAndTags() {
$this->assertTokenization(
'This is