/* (non-Javadoc)
* @see com.itextpdf.html2pdf.css.resolve.HtmlStylesToCssConverter.IAttributeConverter#convert(com.itextpdf.styledxmlparser.html.node.IElementNode, java.lang.String)
*/
public virtual IList <CssDeclaration> Convert(IElementNode element, String value)
{
String cssValueEquivalent = null;
String cssPropertyEquivalent = null;
String elementName = element.Name();
if (TagConstants.FONT.Equals(elementName))
{
cssPropertyEquivalent = CssConstants.FONT_SIZE;
try {
bool signedValue = value.Contains("-") || value.Contains("+");
int htmlFontSize = System.Convert.ToInt32(value, System.Globalization.CultureInfo.InvariantCulture);
if (signedValue)
{
htmlFontSize = 3 + htmlFontSize;
}
if (htmlFontSize < 2)
{
cssValueEquivalent = CssConstants.X_SMALL;
}
else
{
if (htmlFontSize > 6)
{
cssValueEquivalent = "48px";
}
else
{
if (htmlFontSize == 2)
{
cssValueEquivalent = CssConstants.SMALL;
}
else
{
if (htmlFontSize == 3)
{
cssValueEquivalent = CssConstants.MEDIUM;
}
else
{
if (htmlFontSize == 4)
{
cssValueEquivalent = CssConstants.LARGE;
}
else
{
if (htmlFontSize == 5)
{
cssValueEquivalent = CssConstants.X_LARGE;
}
else
{
if (htmlFontSize == 6)
{
cssValueEquivalent = CssConstants.XX_LARGE;
}
}
}
}
}
}
}
}
catch (FormatException) {
cssValueEquivalent = CssConstants.MEDIUM;
}
}
else
{
if (TagConstants.HR.Equals(elementName))
{
cssPropertyEquivalent = CssConstants.HEIGHT;
cssValueEquivalent = value + CssConstants.PX;
}
}
return(JavaUtil.ArraysAsList(new CssDeclaration(cssPropertyEquivalent, cssValueEquivalent)));
}
public PageRangePartAnd(params PageRange.IPageRangePart[] conditions)
{
this.conditions.AddAll(JavaUtil.ArraysAsList(conditions));
}
public virtual void TestEquals()
{
Glyph glyph = new Glyph(200, 200, 200);
GlyphLine.ActualText actualText = new GlyphLine.ActualText("-");
GlyphLine one = new GlyphLine(new List <Glyph>(JavaUtil.ArraysAsList(glyph)), new List <GlyphLine.ActualText
>(JavaUtil.ArraysAsList(actualText)), 0, 1);
GlyphLine two = new GlyphLine(new List <Glyph>(JavaUtil.ArraysAsList(glyph)), new List <GlyphLine.ActualText
>(JavaUtil.ArraysAsList(actualText)), 0, 1);
one.Add(glyph);
two.Add(glyph);
one.end++;
two.end++;
NUnit.Framework.Assert.IsTrue(one.Equals(two));
}
/// <summary>Constructs a PDF Collection Sort Dictionary.</summary>
/// <param name="keys">the keys of the fields that will be used to sort entries</param>
public PdfCollectionSort(String[] keys)
: this(new PdfDictionary())
{
GetPdfObject().Put(PdfName.S, new PdfArray(JavaUtil.ArraysAsList(keys), true));
}
public virtual void SplitDocumentTest04()
{
String inputFileName = sourceFolder + "iphone_user_guide.pdf";
PdfDocument inputPdfDoc = new PdfDocument(new PdfReader(inputFileName));
PageRange pageRange1 = new PageRange("even & 80-").AddPageSequence(4, 15).AddSinglePage(18).AddPageSequence
(1, 2);
PageRange pageRange2 = new PageRange("99,98").AddPageSequence(70, 99);
IList <PdfDocument> splitDocuments = new _PdfSplitter_188(inputPdfDoc).ExtractPageRanges(JavaUtil.ArraysAsList
(pageRange1, pageRange2));
foreach (PdfDocument pdfDocument in splitDocuments)
{
pdfDocument.Close();
}
for (int i = 1; i <= 2; i++)
{
NUnit.Framework.Assert.IsNull(new CompareTool().CompareByContent(destinationFolder + "splitDocument4_" + i
+ ".pdf", sourceFolder + "cmp/" + "cmp_splitDocument4_" + i.ToString() + ".pdf", destinationFolder, "diff_"
));
}
}
private static PdfDictionary CopyObject(PdfDictionary source, PdfDictionary destPage, bool parentChangePg,
StructureTreeCopier.StructElemCopyingParams copyingParams) {
PdfDictionary copied;
if (copyingParams.IsCopyFromDestDocument()) {
//TODO: detect wether object is needed to be cloned at all
copied = source.Clone(ignoreKeysForClone);
if (source.IsIndirect()) {
copied.MakeIndirect(copyingParams.GetToDocument());
}
PdfDictionary pg = source.GetAsDictionary(PdfName.Pg);
if (pg != null) {
if (copyingParams.IsCopyFromDestDocument()) {
if (pg != destPage) {
copied.Put(PdfName.Pg, destPage);
parentChangePg = true;
}
else {
parentChangePg = false;
}
}
}
}
else {
copied = source.CopyTo(copyingParams.GetToDocument(), ignoreKeysForCopy, true);
PdfDictionary obj = source.GetAsDictionary(PdfName.Obj);
if (obj != null) {
// Link annotations could be not added to the toDocument, so we need to identify this case.
// When obj.copyTo is called, and annotation was already copied, we would get this already created copy.
// If it was already copied and added, /P key would be set. Otherwise /P won't be set.
obj = obj.CopyTo(copyingParams.GetToDocument(), JavaUtil.ArraysAsList(PdfName.P), false);
copied.Put(PdfName.Obj, obj);
}
PdfDictionary nsDict = source.GetAsDictionary(PdfName.NS);
if (nsDict != null) {
PdfDictionary copiedNsDict = CopyNamespaceDict(nsDict, copyingParams);
copied.Put(PdfName.NS, copiedNsDict);
}
PdfDictionary pg = source.GetAsDictionary(PdfName.Pg);
if (pg != null) {
PdfDictionary pageAnalog = copyingParams.GetPage2page().Get(pg);
if (pageAnalog == null) {
pageAnalog = destPage;
parentChangePg = true;
}
else {
parentChangePg = false;
}
copied.Put(PdfName.Pg, pageAnalog);
}
}
PdfObject k = source.Get(PdfName.K);
if (k != null) {
if (k.IsArray()) {
PdfArray kArr = (PdfArray)k;
PdfArray newArr = new PdfArray();
for (int i = 0; i < kArr.Size(); i++) {
PdfObject copiedKid = CopyObjectKid(kArr.Get(i), copied, destPage, parentChangePg, copyingParams);
if (copiedKid != null) {
newArr.Add(copiedKid);
}
}
if (!newArr.IsEmpty()) {
if (newArr.Size() == 1) {
copied.Put(PdfName.K, newArr.Get(0));
}
else {
copied.Put(PdfName.K, newArr);
}
}
}
else {
PdfObject copiedKid = CopyObjectKid(k, copied, destPage, parentChangePg, copyingParams);
if (copiedKid != null) {
copied.Put(PdfName.K, copiedKid);
}
}
}
return copied;
}
public override IList <Rectangle> InitElementAreas(LayoutArea area)
{
return(JavaUtil.ArraysAsList(new Rectangle(area.GetBBox()).SetWidth(area.GetBBox().GetWidth() / 2), new Rectangle
(area.GetBBox()).SetWidth(area.GetBBox().GetWidth() / 2).MoveRight(area.GetBBox().GetWidth() / 2)));
}
public virtual void TestBengaliScript()
{
String imgPath = TEST_IMAGES_DIRECTORY + "bengali_01.jpeg";
FileInfo file = new FileInfo(imgPath);
String expected = "ইংরজে";
tesseractReader.SetTesseract4OcrEngineProperties(tesseractReader.GetTesseract4OcrEngineProperties().SetPathToTessData
(new FileInfo(SCRIPT_TESS_DATA_DIRECTORY)));
// correct result with specified spanish language
NUnit.Framework.Assert.IsTrue(GetTextFromPdf(tesseractReader, file, 1, JavaCollectionsUtil.SingletonList <String
>("Bengali"), JavaUtil.ArraysAsList(FREE_SANS_FONT_PATH, KOSUGI_FONT_PATH)).StartsWith(expected));
}
public virtual void TextJapaneseText()
{
String imgPath = TEST_IMAGES_DIRECTORY + "japanese_01.png";
FileInfo file = new FileInfo(imgPath);
String expected = "日 本 語\n文法";
// correct result with specified japanese language
NUnit.Framework.Assert.AreEqual(expected, GetTextFromPdf(tesseractReader, file, JavaUtil.ArraysAsList("jpn"
), KOSUGI_FONT_PATH));
}
public virtual void TestChinese()
{
String imgPath = TEST_IMAGES_DIRECTORY + "chinese_01.jpg";
FileInfo file = new FileInfo(imgPath);
String expected = "你 好\nni hao";
// correct result with specified spanish language
NUnit.Framework.Assert.AreEqual(expected, GetTextFromPdf(tesseractReader, file, JavaUtil.ArraysAsList("chi_sim"
, "chi_tra"), NOTO_SANS_SC_FONT_PATH));
NUnit.Framework.Assert.AreEqual(expected, GetTextFromPdf(tesseractReader, file, JavaCollectionsUtil.SingletonList
<String>("chi_sim"), NOTO_SANS_SC_FONT_PATH));
NUnit.Framework.Assert.AreEqual(expected, GetTextFromPdf(tesseractReader, file, JavaCollectionsUtil.SingletonList
<String>("chi_tra"), NOTO_SANS_SC_FONT_PATH));
// incorrect result when languages are not specified
// or languages were specified in the wrong order
NUnit.Framework.Assert.AreNotEqual(expected, GetTextFromPdf(tesseractReader, file, JavaCollectionsUtil.SingletonList
<String>("chi_sim")));
NUnit.Framework.Assert.AreNotEqual(expected, GetTextFromPdf(tesseractReader, file, JavaCollectionsUtil.SingletonList
<String>("chi_tra")));
NUnit.Framework.Assert.AreNotEqual(expected, GetTextFromPdf(tesseractReader, file, JavaUtil.ArraysAsList("chi_sim"
, "chi_tra")));
NUnit.Framework.Assert.IsFalse(GetTextFromPdf(tesseractReader, file, new List <String>()).Contains(expected
));
}
public virtual void TestSpanishWithTessData()
{
String imgPath = TEST_IMAGES_DIRECTORY + "spanish_01.jpg";
FileInfo file = new FileInfo(imgPath);
String expectedSpanish = "Aquí\nhablamos\nespañol";
// correct result with specified spanish language
NUnit.Framework.Assert.AreEqual(expectedSpanish, GetTextFromPdf(tesseractReader, file, JavaCollectionsUtil
.SingletonList <String>("spa")));
NUnit.Framework.Assert.AreEqual(expectedSpanish, GetTextFromPdf(tesseractReader, file, JavaUtil.ArraysAsList
("spa", "eng")));
NUnit.Framework.Assert.AreEqual(expectedSpanish, GetTextFromPdf(tesseractReader, file, JavaUtil.ArraysAsList
("eng", "spa")));
// incorrect result when languages are not specified
// or languages were specified in the wrong order
NUnit.Framework.Assert.AreNotEqual(expectedSpanish, GetTextFromPdf(tesseractReader, file, JavaCollectionsUtil
.SingletonList <String>("eng")));
NUnit.Framework.Assert.AreNotEqual(expectedSpanish, GetTextFromPdf(tesseractReader, file, new List <String>
()));
}
public virtual void TestHindiTextWithEng()
{
String imgPath = TEST_IMAGES_DIRECTORY + "hindi_02.jpg";
FileInfo file = new FileInfo(imgPath);
String expected = "मानक हनिदी\nHindi";
// correct result with specified arabic+english languages
NUnit.Framework.Assert.AreEqual(expected, GetTextFromPdf(tesseractReader, file, JavaUtil.ArraysAsList("hin"
, "eng"), NOTO_SANS_FONT_PATH));
// incorrect result without specified english language
NUnit.Framework.Assert.AreNotEqual(expected, GetTextFromPdf(tesseractReader, file, JavaCollectionsUtil.SingletonList
<String>("hin"), NOTO_SANS_FONT_PATH));
// incorrect result when languages are not specified
// or languages were specified in the wrong order
NUnit.Framework.Assert.AreNotEqual(expected, GetTextFromPdf(tesseractReader, file, JavaCollectionsUtil.SingletonList
<String>("eng"), NOTO_SANS_FONT_PATH));
NUnit.Framework.Assert.AreNotEqual(expected, GetTextFromPdf(tesseractReader, file));
NUnit.Framework.Assert.AreNotEqual(expected, GetTextFromPdf(tesseractReader, file, new List <String>(), NOTO_SANS_FONT_PATH
));
}
public virtual void CompareMultiLangImage()
{
String testName = "compareMultiLangImage";
String filename = "multilang";
String expectedPdfPath = TEST_DOCUMENTS_DIRECTORY + filename + "_" + testFileTypeName + ".pdf";
String resultPdfPath = GetTargetDirectory() + filename + "_" + testName + "_" + testFileTypeName + ".pdf";
try {
Tesseract4OcrEngineProperties properties = tesseractReader.GetTesseract4OcrEngineProperties();
properties.SetTextPositioning(TextPositioning.BY_WORDS);
properties.SetPathToTessData(GetTessDataDirectory());
properties.SetPageSegMode(3);
tesseractReader.SetTesseract4OcrEngineProperties(properties);
DoOcrAndSavePdfToPath(tesseractReader, TEST_IMAGES_DIRECTORY + filename + ".jpg", resultPdfPath, JavaUtil.ArraysAsList
("eng", "deu", "spa"), DeviceCmyk.BLACK);
NUnit.Framework.Assert.IsNull(new CompareTool().CompareByContent(resultPdfPath, expectedPdfPath, TEST_DOCUMENTS_DIRECTORY
, "diff_"));
}
finally {
NUnit.Framework.Assert.AreEqual(TextPositioning.BY_WORDS, tesseractReader.GetTesseract4OcrEngineProperties
().GetTextPositioning());
NUnit.Framework.Assert.AreEqual(3, tesseractReader.GetTesseract4OcrEngineProperties().GetPageSegMode().Value
);
}
}
/// <summary>Adds an unspecified amount of tabstop elements as properties to the Paragraph.</summary>
/// <param name="tabStops">
/// the
/// <see cref="TabStop">tabstop(s)</see>
/// to be added as properties
/// </param>
/// <returns>this Paragraph</returns>
/// <seealso cref="TabStop"/>
public virtual iText.Layout.Element.Paragraph AddTabStops(params TabStop[] tabStops)
{
AddTabStopsAsProperty(JavaUtil.ArraysAsList(tabStops));
return(this);
}
/* (non-Javadoc)
* @see com.itextpdf.html2pdf.css.resolve.HtmlStylesToCssConverter.IAttributeConverter#convert(com.itextpdf.styledxmlparser.html.node.IElementNode, java.lang.String)
*/
public virtual IList <CssDeclaration> Convert(IElementNode element, String value)
{
return(JavaUtil.ArraysAsList(new CssDeclaration(CssConstants.DIRECTION, value)));
}
public UncoloredTilingPattern(PdfColorSpace underlyingColorSpace)
: base(new PdfArray(JavaUtil.ArraysAsList(PdfName.Pattern, underlyingColorSpace.GetPdfObject())))
{
}
/* (non-Javadoc)
* @see com.itextpdf.html2pdf.css.resolve.HtmlStylesToCssConverter.IAttributeConverter#convert(com.itextpdf.styledxmlparser.html.node.IElementNode, java.lang.String)
*/
public virtual IList <CssDeclaration> Convert(IElementNode element, String value)
{
return(JavaUtil.ArraysAsList(new CssDeclaration(CssConstants.HEIGHT, "2px"), new CssDeclaration(CssConstants
.BORDER_WIDTH, "0"), new CssDeclaration(CssConstants.BACKGROUND_COLOR, "gray")));
}
private static void DoImageToPdfOcr(IOcrEngine tesseractReader, FileInfo imageFile)
{
OcrPdfCreator ocrPdfCreator = new OcrPdfCreator(tesseractReader);
ocrPdfCreator.CreatePdf(JavaUtil.ArraysAsList(imageFile), new PdfWriter(new MemoryStream()));
}
