/**
* Test for issue #18149: some special characters breaks the HTML to eZXML
* transformation
*
* @link http://issues.ez.no/18149
* @group issue18149
*/
public function testIssue18149()
{
$parser = new eZSimplifiedXMLInputParser( 0 );
$html = 'beforeafter';
$dom = $parser->process( $html );
$this->assertInstanceOf( 'DomDocument', $dom );
$paragraphs = $dom->getElementsByTagName( 'paragraph' );
$this->assertEquals( 1, $paragraphs->length );
$this->assertEquals( 'before after', $paragraphs->item( 0 )->textContent );
$this->assertEquals( 1, count( $parser->getMessages() ) );
}
/**
* Test scenario for issue #015023: <header level="-1"> generate fatal error taking a lot of server resource
*
* Test Outline
* ------------
* 1. Parse invalid xml using eZSimplifiedXMLInputParser
* 2. Make sure we get a valid DOMDocument back with content
* 3. Make sure resulting xmlText string matches a valid type
*
* @result: Error will be thrown in parser
* @expected: level should be corrected to level 1 resulting in one section tag
* @link http://issues.ez.no/015023
*/
public function testInvalidHeaderLevel()
{
$parser = new eZSimplifiedXMLInputParser(2, eZXMLInputParser::ERROR_ALL, eZXMLInputParser::ERROR_ALL, true);
$document = $parser->process('<header level="-1">Fatal error test</header>');
$this->assertTrue($document instanceof DOMDocument, 'Parser error: ' . join(", ", $parser->getMessages()));
$root = $document->documentElement;
$this->assertTrue($root->hasChildNodes(), 'Content missing, xml document is empty');
$xmlString = eZXMLTextType::domString($document);
$this->assertEquals('<?xml version="1.0" encoding="utf-8"?>
<section xmlns:image="http://ez.no/namespaces/ezpublish3/image/" xmlns:xhtml="http://ez.no/namespaces/ezpublish3/xhtml/" xmlns:custom="http://ez.no/namespaces/ezpublish3/custom/"><section><header>Fatal error test</header></section></section>
', $xmlString);
}
function validateInput($http, $base, $contentObjectAttribute)
{
$contentObjectID = $contentObjectAttribute->attribute('contentobject_id');
$contentObjectAttributeID = $contentObjectAttribute->attribute('id');
$contentObjectAttributeVersion = $contentObjectAttribute->attribute('version');
if ($http->hasPostVariable($base . '_data_text_' . $contentObjectAttributeID)) {
$data = $http->postVariable($base . '_data_text_' . $contentObjectAttributeID);
// Set original input to a global variable
$originalInput = 'originalInput_' . $contentObjectAttributeID;
$GLOBALS[$originalInput] = $data;
// Set input valid true to a global variable
$isInputValid = 'isInputValid_' . $contentObjectAttributeID;
$GLOBALS[$isInputValid] = true;
$text = $data;
$text = preg_replace('/\\r/', '', $text);
$text = preg_replace('/\\t/', ' ', $text);
// first empty paragraph
$text = preg_replace('/^\\n/', '<p></p>', $text);
eZDebugSetting::writeDebug('kernel-datatype-ezxmltext', $text, 'eZSimplifiedXMLInput::validateInput text');
$parser = new eZSimplifiedXMLInputParser($contentObjectID, true, eZXMLInputParser::ERROR_ALL, true);
$document = $parser->process($text);
if (!is_object($document)) {
$GLOBALS[$isInputValid] = false;
$errorMessage = implode(' ', $parser->getMessages());
$contentObjectAttribute->setValidationError($errorMessage);
return eZInputValidator::STATE_INVALID;
}
if ($contentObjectAttribute->validateIsRequired()) {
$root = $document->documentElement;
if (!$root->hasChildNodes()) {
$contentObjectAttribute->setValidationError(ezpI18n::tr('kernel/classes/datatypes', 'Content required'));
return eZInputValidator::STATE_INVALID;
}
}
$contentObjectAttribute->setValidationLog($parser->getMessages());
$xmlString = eZXMLTextType::domString($document);
$urlIDArray = $parser->getUrlIDArray();
if (count($urlIDArray) > 0) {
$this->updateUrlObjectLinks($contentObjectAttribute, $urlIDArray);
}
$contentObject = $contentObjectAttribute->attribute('object');
$contentObject->appendInputRelationList($parser->getRelatedObjectIDArray(), eZContentObject::RELATION_EMBED);
$contentObject->appendInputRelationList($parser->getLinkedObjectIDArray(), eZContentObject::RELATION_LINK);
$contentObjectAttribute->setAttribute('data_text', $xmlString);
return eZInputValidator::STATE_ACCEPTED;
}
return eZInputValidator::STATE_ACCEPTED;
}
function setEZXMLAttribute($attribute, $attributeValue, $link = false)
{
$contentObjectID = $attribute->attribute("contentobject_id");
$parser = new eZSimplifiedXMLInputParser($contentObjectID, false, 0, false);
$attributeValue = str_replace("\r", '', $attributeValue);
$attributeValue = str_replace("\n", '', $attributeValue);
$attributeValue = str_replace("\t", ' ', $attributeValue);
$document = $parser->process($attributeValue);
if (!is_object($document)) {
$cli = eZCLI::instance();
$cli->output('Error in xml parsing');
return;
}
$domString = eZXMLTextType::domString($document);
$attribute->setAttribute('data_text', $domString);
$attribute->store();
}
$dataMap = $contentObject->attribute('data_map');
$map = $mapSettings->variable('NewsletterAutomapping', $class->attribute('identifier'));
foreach ($map as $objectAttribute => $typeSource) {
// Check if attribute has content
if (0 < strlen(trim($newsletterType->attribute($typeSource)))) {
$attribute = $dataMap[$objectAttribute];
if ('ezxmltext' === $attribute->DataTypeString) {
$inputData = '<section xmlns:image="http://ez.no/namespaces/ezpublish3/image/" xmlns:xhtml="http://ez.no/namespaces/ezpublish3/xhtml/" xmlns:custom="http://ez.no/namespaces/ezpublish3/custom/" >';
$inputData .= '<paragraph>';
$inputData .= html_entity_decode($newsletterType->attribute($typeSource));
$inputData .= '</paragraph>';
$inputData .= '</section>';
try {
$parser = new eZSimplifiedXMLInputParser($attribute->ContentObjectID);
$parser->setParseLineBreaks(true);
$document = $parser->process($inputData);
$input = $document->saveXML();
if ($input === false) {
throw new Exception();
}
} catch (Exception $e) {
eZDebug::writeError("Invalid XML input data.", 'view_newslettertype');
$input = "";
}
} else {
$input = $newsletterType->attribute($typeSource);
}
$attribute->setAttribute('data_text', $input);
$attribute->store();
}
}
private function processXmlTextData($xml, $attribute)
{
$parser = new eZSimplifiedXMLInputParser($this->object->attribute('id'));
$parser->ParseLineBreaks = true;
$xml = $parser->process($xml);
$xml = eZXMLTextType::domString($xml);
$urlIdArray = $parser->getUrlIDArray();
if (count($urlIdArray) > 0) {
eZSimplifiedXMLInput::updateUrlObjectLinks($attribute, $urlIdArray);
}
return $xml;
}
/**
* Test for EZP-22563
*
* Make sure an header without break is still parsed without any line
* element.
*
* @link https://jira.ez.no/browse/EZP-22563
*/
public function testHeaderNoBreak()
{
$parser = new eZSimplifiedXMLInputParser(0);
$input = '<header level="1">Franz Ferdinand - Love Illumination</header>';
$dom = $parser->process($input);
self::assertInstanceOf('DomDocument', $dom);
$lines = $dom->getElementsByTagName('line');
$header = $dom->getElementsByTagName('header');
self::assertEquals(0, $lines->length);
self::assertEquals(1, $header->length);
self::assertEquals("Franz Ferdinand - Love Illumination", $header->item(0)->textContent);
}
/**
* Convert input to XML format used by eZ for article ingress and body
* @param String $content
* @return String
*/
protected function xmlConvert($content)
{
$parser = new eZSimplifiedXMLInputParser();
$parser->setParseLineBreaks(true);
$document = $parser->process($content);
return eZXMLTextType::domString($document);
}