static void Main()
{
//Initialise the MuPDF context. This is needed to open or create documents.
using MuPDFContext ctx = new MuPDFContext();
//Open a PDF document
using MuPDFDocument doc1 = new MuPDFDocument(ctx, "Document1.pdf");
//Save the page as a PNG image with transparency, at a 1x zoom level (1pt = 1px).
doc1.SaveImage(0, 1, PixelFormats.RGBA, "Raster1.png", RasterOutputFileTypes.PNG);
//Open an Open XPS document
using MuPDFDocument doc2 = new MuPDFDocument(ctx, "Document2.oxps");
//Save only part of the page as a PNG image with transparency, at a 2x zoom level (1pt = 2px).
doc2.SaveImage(0, new Rectangle(87, 360, 517, 790), 2, PixelFormats.RGBA, "Raster2.png", RasterOutputFileTypes.PNG);
//Merge the two documents into a single document.
MuPDFDocument.CreateDocument(ctx, "Merged.pdf", DocumentOutputFileTypes.PDF, true,
//We take the full page from the first document
(doc1.Pages[0], doc1.Pages[0].Bounds, 1),
//We only take a region of the page from the second document
(doc2.Pages[0], new Rectangle(87, 360, 517, 790), 1)
);
}
static void Main()
{
//Initialise the MuPDF context. This is needed to open or create documents.
using MuPDFContext ctx = new MuPDFContext();
//Open a PDF document
using MuPDFDocument doc1 = new MuPDFDocument(ctx, "Document1.pdf");
//Save the page as a PNG image with transparency, at a 1x zoom level (1pt = 1px).
doc1.SaveImage(0, 1, PixelFormats.RGBA, "Raster1.png", RasterOutputFileTypes.PNG);
//Open an Open XPS document
using MuPDFDocument doc2 = new MuPDFDocument(ctx, "Document2.oxps");
//Save only part of the page as a PNG image with transparency, at a 2x zoom level (1pt = 2px).
doc2.SaveImage(0, new Rectangle(87, 360, 517, 790), 2, PixelFormats.RGBA, "Raster2.png", RasterOutputFileTypes.PNG);
//Merge the two documents into a single document.
MuPDFDocument.CreateDocument(ctx, "Merged.pdf", DocumentOutputFileTypes.PDF, true,
//We take the full page from the first document
(doc1.Pages[0], doc1.Pages[0].Bounds, 1),
//We only take a region of the page from the second document
(doc2.Pages[0], new Rectangle(87, 360, 517, 790), 1)
);
//Open the rasterised page so that we can try using the OCR.
using MuPDFDocument doc3 = new MuPDFDocument(ctx, "Raster1.png");
//Get a structured text representation of the page using OCR.
MuPDFStructuredTextPage page = doc3.GetStructuredTextPage(0, new TesseractLanguage(TesseractLanguage.Fast.Eng));
//Print all the text lines.
foreach (MuPDFStructuredTextBlock blk in page)
{
foreach (MuPDFStructuredTextLine line in blk)
{
System.Console.WriteLine(line.Text);
}
}
}
/// <summary>
/// Parses an image URI into a page. This is intended to replace the default image URI interpreter in <c>VectSharp.SVG.Parser.ParseImageURI</c>. To do this, use something like:
/// <code>VectSharp.SVG.Parser.ParseImageURI = VectSharp.MuPDFUtils.ImageURIParser.Parser(VectSharp.SVG.Parser.ParseSVGURI);</code>
/// </summary>
/// <param name="parseSVG">A function to parse an SVG image uri into a page. You should pass <c>VectSharp.SVG.Parser.ParseSVGURI</c> as this argument.</param>
/// <returns>A function to parse an image URI into a page.</returns>
public static Func <string, bool, Page> Parser(Func <string, bool, Page> parseSVG)
{
return((string uri, bool interpolate) =>
{
if (uri.StartsWith("data:"))
{
string mimeType = uri.Substring(uri.IndexOf(":") + 1, uri.IndexOf(";") - uri.IndexOf(":") - 1);
string type = uri.Substring(uri.IndexOf(";") + 1, uri.IndexOf(",") - uri.IndexOf(";") - 1);
if (mimeType != "image/svg+xml")
{
int offset = uri.IndexOf(",") + 1;
byte[] parsed;
bool isVector = false;
InputFileTypes fileType;
switch (mimeType)
{
case "image/png":
fileType = InputFileTypes.PNG;
break;
case "image/jpeg":
case "image/jpg":
fileType = InputFileTypes.JPEG;
break;
case "image/gif":
fileType = InputFileTypes.GIF;
break;
case "image/bmp":
fileType = InputFileTypes.BMP;
break;
case "image/tiff":
case "image/tif":
fileType = InputFileTypes.TIFF;
break;
case "application/oxps":
case "application/vnd.ms-xpsdocument":
fileType = InputFileTypes.XPS;
isVector = true;
break;
case "application/x-cbz":
fileType = InputFileTypes.CBZ;
break;
case "application/epub+zip":
fileType = InputFileTypes.EPUB;
isVector = true;
break;
case "text/fb2+xml":
fileType = InputFileTypes.FB2;
break;
case "image/x-portable-anymap":
fileType = InputFileTypes.PNM;
break;
case "image/x-portable-arbitrarymap":
fileType = InputFileTypes.PAM;
break;
case "application/pdf":
fileType = InputFileTypes.PDF;
isVector = true;
break;
default:
fileType = InputFileTypes.PDF;
break;
}
string substring = uri.Substring(offset);
switch (type)
{
case "base64":
parsed = Convert.FromBase64String(uri.Substring(offset));
break;
case "":
parsed = (from el in System.Web.HttpUtility.UrlDecode(uri.Substring(offset)) select(byte) el).ToArray();
break;
default:
throw new InvalidDataException("Unknown data stream type!");
}
if (!isVector)
{
GCHandle handle = GCHandle.Alloc(parsed, GCHandleType.Pinned);
RasterImageStream img = new RasterImageStream(handle.AddrOfPinnedObject(), parsed.Length, fileType, interpolate: interpolate);
handle.Free();
Page pag = new Page(img.Width, img.Height);
pag.Graphics.DrawRasterImage(0, 0, img);
return pag;
}
else
{
string tempFile = Path.GetTempFileName();
using (MuPDFContext context = new MuPDFContext())
{
using (MuPDFDocument document = new MuPDFDocument(context, parsed, fileType))
{
MuPDFDocument.CreateDocument(context, tempFile, DocumentOutputFileTypes.SVG, true, document.Pages[0]);
}
}
string tbr = "data:image/svg+xml;," + System.Web.HttpUtility.UrlEncode(File.ReadAllText(tempFile));
File.Delete(tempFile);
return parseSVG(tbr, interpolate);
}
}
else
{
return parseSVG(uri, interpolate);
}
}
return null;
});
}
