public virtual void HtmlToElementsTest02()
{
String html = "<table style=\"font-size: 2em\"><tr><td>123</td><td><456></td></tr><tr><td>Long cell</td></tr></table>";
IList <IElement> lst = HtmlConverter.ConvertToElements(html);
NUnit.Framework.Assert.IsTrue(lst.Count == 1);
NUnit.Framework.Assert.IsTrue(lst[0] is Table);
Table t = (Table)lst[0];
NUnit.Framework.Assert.AreEqual(2, t.GetNumberOfRows());
NUnit.Framework.Assert.AreEqual("123", ((Text)(((Paragraph)t.GetCell(0, 0).GetChildren()[0]).GetChildren()
[0])).GetText());
NUnit.Framework.Assert.AreEqual(24f, t.GetProperty <UnitValue>(Property.FONT_SIZE).GetValue(), 1e-10);
}
/// <exception cref="System.IO.IOException"/>
private void WriteToDocument(Document doc, byte[] bytes)
{
Stream @in = new MemoryStream(bytes);
IList <IElement> arrayList = HtmlConverter.ConvertToElements(@in);
foreach (IElement element in arrayList)
{
if (element is IBlockElement)
{
doc.Add((IBlockElement)element);
}
}
doc.Close();
}
public void ResourceResolverIncorrectSyntaxTest()
{
//this test is inconsistent with java
String baseUri = sourceFolder;
String outPdf = destinationFolder + "resourceResolverIncorrectSyntaxObject.pdf";
String cmpPdf = sourceFolder + "cmp_resourceResolverIncorrectSyntaxObject.pdf";
String inHtml = sourceFolder + "resourceResolverIncorrectSyntaxObject.html";
using (FileStream fileInputStream = new FileStream(inHtml, FileMode.Open, FileAccess.Read),
fileOutputStream = new FileStream(outPdf, FileMode.Create)) {
HtmlConverter.ConvertToPdf(fileInputStream, fileOutputStream, new ConverterProperties().SetBaseUri(baseUri));
}
NUnit.Framework.Assert.IsNull(new CompareTool().CompareByContent(outPdf, cmpPdf, destinationFolder, "diffIncorrectSyntax_"));
}
public void ResourceResolverSvgWithImageBackgroundTest()
{
//Browsers do not render this
String baseUri = sourceFolder;
String outPdf = destinationFolder + "resourceResolverSvgWithImageBackground.pdf";
String cmpPdf = sourceFolder + "cmp_resourceResolverSvgWithImageBackground.pdf";
String inHtml = sourceFolder + "resourceResolverSvgWithImageBackground.html";
using (FileStream fileInputStream = new FileStream(inHtml, FileMode.Open, FileAccess.Read),
fileOutputStream = new FileStream(outPdf, FileMode.Create)) {
HtmlConverter.ConvertToPdf(fileInputStream, fileOutputStream, new ConverterProperties().SetBaseUri(baseUri));
}
NUnit.Framework.Assert.IsNull(
new CompareTool().CompareByContent(outPdf, cmpPdf, destinationFolder, "diffSvgWithImg_"));
}
public virtual void ResourceResolverTest11()
{
String outPdf = destinationFolder + "resourceResolverTest11.pdf";
String cmpPdf = sourceFolder + "cmp_resourceResolverTest11.pdf";
using (
FileStream fileInputStream = new FileStream(sourceFolder + "resourceResolverTest11.html", FileMode.Open,
FileAccess.Read),
fileOutputStream = new FileStream(outPdf, FileMode.Create))
{
HtmlConverter.ConvertToPdf(fileInputStream, fileOutputStream,
new ConverterProperties().SetBaseUri("https://en.wikipedia.org/wiki/Welsh_Corgi"));
NUnit.Framework.Assert.IsNull(
new CompareTool().CompareByContent(outPdf, cmpPdf, destinationFolder, "diff11_"));
}
}
public virtual void LeadingInDefaultRenderingModeTest()
{
String html = "This text is directly in body. It should have the same default LEADING property as everything else.\n"
+ "<p>This text is in paragraph.</p>";
IList <IElement> elements = HtmlConverter.ConvertToElements(html);
NUnit.Framework.Assert.AreEqual(2, elements.Count);
IElement anonymousParagraph = elements[0];
// TODO DEVSIX-3873 anonymous paragraph inherited styles should be applied in general way
NUnit.Framework.Assert.IsNull(anonymousParagraph.GetProperty <Leading>(Property.LEADING));
IElement normalParagraph = elements[1];
NUnit.Framework.Assert.AreEqual(new Leading(Leading.MULTIPLIED, 1.2f), normalParagraph.GetProperty <Leading
>(Property.LEADING));
}
public virtual void BodyFontFamilyTest()
{
String html = "<!DOCTYPE html>\n" + "<html>\n" + "<body style=\"font-family: monospace\">\n" + "This text is directly in body and should be monospaced.\n"
+ "<p>This text is in paragraph and should be monospaced.</p>\n" + "</body>\n" + "</html>";
IList <IElement> elements = HtmlConverter.ConvertToElements(html);
NUnit.Framework.Assert.AreEqual(2, elements.Count);
IElement anonymousParagraph = elements[0];
NUnit.Framework.Assert.AreEqual(new String[] { "monospace" }, anonymousParagraph.GetProperty <String[]>(Property
.FONT));
IElement normalParagraph = elements[1];
NUnit.Framework.Assert.AreEqual(new String[] { "monospace" }, normalParagraph.GetProperty <String[]>(Property
.FONT));
}
public virtual void HtmlToElementsVsHtmlToPdfTest()
{
String src = sourceFolder + "basic.html";
String outConvertToPdf = destinationFolder + "basicCovertToPdfResult.pdf";
String outConvertToElements = destinationFolder + "basicCovertToElementsResult.pdf";
HtmlConverter.ConvertToPdf(new FileInfo(src), new FileInfo(outConvertToPdf));
IList <IElement> elements = HtmlConverter.ConvertToElements(new FileStream(src, FileMode.Open, FileAccess.Read
));
Document document = new Document(new PdfDocument(new PdfWriter(outConvertToElements)));
// In order to collapse margins between the direct children of root element
// it's required to manually enable collapsing on root element. This is because siblings
// margins collapsing is controlled by the parent element.
// This leads to the difference between pure convertToPdf/Document and convertToElements methods.
document.SetProperty(Property.COLLAPSING_MARGINS, true);
foreach (IElement elem in elements)
{
if (elem is IBlockElement)
{
document.Add((IBlockElement)elem);
}
else
{
if (elem is Image)
{
document.Add((Image)elem);
}
else
{
if (elem is AreaBreak)
{
document.Add((AreaBreak)elem);
}
else
{
NUnit.Framework.Assert.Fail("The #convertToElements method gave element which is unsupported as root element, it's unexpected."
);
}
}
}
}
document.Close();
System.Console.Out.WriteLine("html: " + UrlUtil.GetNormalizedFileUriString(src) + "\n");
NUnit.Framework.Assert.IsNull(new CompareTool().CompareByContent(outConvertToElements, outConvertToPdf, destinationFolder
));
}
public void ResourceResolverTest18()
{
String baseUri = sourceFolder;
String outPdf = destinationFolder + "resourceResolverTest18.pdf";
String cmpPdf = sourceFolder + "cmp_resourceResolverTest18.pdf";
using (
FileStream fileInputStream = new FileStream(sourceFolder + "resourceResolverTest18.html", FileMode.Open,
FileAccess.Read),
fileOutputStream = new FileStream(outPdf, FileMode.Create))
{
HtmlConverter.ConvertToPdf(fileInputStream, fileOutputStream,
new ConverterProperties().SetBaseUri(baseUri));
NUnit.Framework.Assert.IsNull(
new CompareTool().CompareByContent(outPdf, cmpPdf, destinationFolder, "diff18_"));
}
}
public virtual void HtmlToElementsTest09()
{
//Test OutlineHandler exception throwing
/*
* Outlines require a PdfDocument, and OutlineHandler is based around its availability
* Any convert to elements workflow of course doesn't have a PdfDocument.
* Instead of throwing an NPE when trying it, the OutlineHandler will check for the existence of a pdfDocument
* If no PdfDocument is found, the handler will do nothing silently
*/
String html = "<html><p>Hello world!</p><meta name=\"author\" content=\"Bruno\"><table><tr><td>123</td><td><456></td></tr><tr><td>Long cell</td></tr></table><p>Hello world!</p></html>";
ConverterProperties props = new ConverterProperties();
OutlineHandler outlineHandler = new OutlineHandler();
outlineHandler.PutTagPriorityMapping("h1", 1);
outlineHandler.PutTagPriorityMapping("h3", 2);
outlineHandler.PutTagPriorityMapping("p", 3);
props.SetOutlineHandler(outlineHandler);
HtmlConverter.ConvertToElements(html);
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.Exception"/>
public virtual void ConvertToPdfAndCompare(String name, String sourceFolder, String destinationFolder, bool
tagged, String fontsFolder)
{
String sourceHtml = sourceFolder + name + ".html";
String cmpPdf = sourceFolder + "cmp_" + name + ".pdf";
String destinationPdf = destinationFolder + name + ".pdf";
ConverterProperties converterProperties = GetConverterProperties(fontsFolder);
PdfDocument pdfDocument = new PdfDocument(new PdfWriter(destinationPdf));
if (tagged)
{
pdfDocument.SetTagged();
}
using (FileStream fileInputStream = new FileStream(sourceHtml, FileMode.Open, FileAccess.Read)) {
HtmlConverter.ConvertToPdf(fileInputStream, pdfDocument, converterProperties);
}
System.Console.Out.WriteLine("html: file:///" + UrlUtil.ToNormalizedURI(sourceHtml).AbsolutePath + "\n");
NUnit.Framework.Assert.IsNull(new CompareTool().CompareByContent(destinationPdf, cmpPdf, destinationFolder
, "diff_" + name + "_"));
}
public virtual void ConvertToElementsAndCreateTwoDocumentsTest()
{
String html = "This text is directly in body. It should have the same default LEADING property as everything else.\n"
+ "<p>This text is in paragraph.</p>";
IList <IElement> iElementList = HtmlConverter.ConvertToElements(html);
using (PdfDocument pdfDocument = new PdfDocument(new PdfWriter(new ByteArrayOutputStream()))) {
using (Document document = new Document(pdfDocument)) {
AddElementsToDocument(document, iElementList);
}
}
PdfDocument pdfDocument_1 = new PdfDocument(new PdfWriter(new ByteArrayOutputStream()));
Document document_1 = new Document(pdfDocument_1);
AddElementsToDocument(document_1, iElementList);
// TODO DEVSIX-5753 error should not be thrown here
Exception e = NUnit.Framework.Assert.Catch(typeof(PdfException), () => document_1.Close());
NUnit.Framework.Assert.AreEqual(KernelExceptionMessageConstant.PDF_INDIRECT_OBJECT_BELONGS_TO_OTHER_PDF_DOCUMENT
, e.Message);
}
public virtual void EventGenerationTest()
{
Html2ElementsTest.StoreEventsHandler handler = new Html2ElementsTest.StoreEventsHandler();
try {
EventManager.GetInstance().Register(handler);
String html = "<table><tr><td>123</td><td><456></td></tr><tr><td>789</td></tr></table><p>Hello world!</p>";
IList <IElement> elements = HtmlConverter.ConvertToElements(html);
NUnit.Framework.Assert.AreEqual(1, handler.GetEvents().Count);
NUnit.Framework.Assert.IsTrue(handler.GetEvents()[0] is PdfHtmlProductEvent);
SequenceId expectedSequenceId = ((PdfHtmlProductEvent)handler.GetEvents()[0]).GetSequenceId();
int validationsCount = ValidateSequenceIds(expectedSequenceId, elements);
// Table 1
// Cell -> Paragraph -> Text [123] 3
// Cell -> Paragraph -> Text [456] 3
// Cell -> Paragraph -> Text [789] 3
// Paragraph -> Text [Hello world!] 2
//--------------------------------------------
// 12
NUnit.Framework.Assert.AreEqual(12, validationsCount);
}
finally {
EventManager.GetInstance().Unregister(handler);
}
}
/// <exception cref="System.IO.IOException"/>
/// <exception cref="System.Exception"/>
/// <exception cref="Javax.Xml.Parsers.ParserConfigurationException"/>
/// <exception cref="Org.Xml.Sax.SAXException"/>
public virtual void ConvertToPdfAcroformFlattenAndCompare(String name, String sourceFolder, String destinationFolder
, bool tagged)
{
String sourceHtml = sourceFolder + name + ".html";
if (tagged)
{
name = name + "Tagged";
}
String outPdfPath = destinationFolder + name + ".pdf";
String outPdfPathAcro = destinationFolder + name + "_acro.pdf";
String outPdfPathFlatted = destinationFolder + name + "_acro_flatten.pdf";
String cmpPdfPath = sourceFolder + "cmp_" + name + ".pdf";
String cmpPdfPathAcro = sourceFolder + "cmp_" + name + "_acro.pdf";
String cmpPdfPathAcroFlatten = sourceFolder + "cmp_" + name + "_acro_flatten.pdf";
String diff1 = "diff1_" + name;
String diff2 = "diff2_" + name;
String diff3 = "diff3_" + name;
//convert tagged PDF without acroform (from html with form elements)
PdfWriter taggedWriter = new PdfWriter(outPdfPath);
PdfDocument pdfTagged = new PdfDocument(taggedWriter);
if (tagged)
{
pdfTagged.SetTagged();
}
HtmlConverter.ConvertToPdf(new FileStream(sourceHtml, FileMode.Open, FileAccess.Read), pdfTagged, new ConverterProperties
().SetBaseUri(sourceFolder));
//convert PDF with acroform
PdfWriter writerAcro = new PdfWriter(outPdfPathAcro);
PdfDocument pdfTaggedAcro = new PdfDocument(writerAcro);
if (tagged)
{
pdfTaggedAcro.SetTagged();
}
ConverterProperties converterPropertiesAcro = new ConverterProperties();
converterPropertiesAcro.SetBaseUri(sourceFolder);
converterPropertiesAcro.SetCreateAcroForm(true);
HtmlConverter.ConvertToPdf(new FileStream(sourceHtml, FileMode.Open, FileAccess.Read), pdfTaggedAcro, converterPropertiesAcro
);
System.Console.Out.WriteLine("html: file:///" + UrlUtil.ToNormalizedURI(sourceHtml).AbsolutePath + "\n");
//flatted created tagged PDF with acroform
PdfDocument document = new PdfDocument(new PdfReader(outPdfPathAcro), new PdfWriter(outPdfPathFlatted));
PdfAcroForm acroForm = PdfAcroForm.GetAcroForm(document, false);
acroForm.FlattenFields();
document.Close();
//compare with cmp
NUnit.Framework.Assert.IsNull(new CompareTool().CompareByContent(outPdfPath, cmpPdfPath, destinationFolder
, diff1));
NUnit.Framework.Assert.IsNull(new CompareTool().CompareByContent(outPdfPathAcro, cmpPdfPathAcro, destinationFolder
, diff2));
NUnit.Framework.Assert.IsNull(new CompareTool().CompareByContent(outPdfPathFlatted, cmpPdfPathAcroFlatten,
destinationFolder, diff3));
//compare tags structure if tagged
if (tagged)
{
CompareTagStructure(outPdfPath, cmpPdfPath);
CompareTagStructure(outPdfPathAcro, cmpPdfPathAcro);
CompareTagStructure(outPdfPathFlatted, cmpPdfPathAcroFlatten);
}
}
