public string GetCode(PdfDocument document)
{
string xmlHeader = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
xmlHeader += "\n<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\"\n\t\"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">\n";
string html = "<html xmlns=\"http://www.w3.org/1999/xhtml\" xml:lang=\"en\" lang=\"en\">\n";
string head =
_indent + "<head>" +
"\n" + _indent + _indent + "<title></title>" +
"\n" + _indent + _indent + "<meta http-equiv='Content-Type' content='text/html;charset=utf-8' />" +
"\n" + _indent + _indent + "<meta name='ocr-system' content='" + _pageSegmenter.GetType().Name + "|" + _wordExtractor.GetType().Name + "' />" +
"\n" + _indent + _indent + "<meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word' />" +
"\n" + _indent + "</head>\n";
string hocr = head + _indent + "<body>\n";
for (var i = 0; i < document.NumberOfPages; i++)
{
var page = document.GetPage(i + 1);
hocr += GetCode(page, GetPageImagePath(_documentPath, i + 1)) + "\n";
}
hocr = hocr + _indent + "<script src='https://unpkg.com/hocrjs'></script>\n" + _indent + "</body>";
hocr = xmlHeader + html + hocr + "\n</html>";
return(hocr);
}
/// <summary>
/// Get the PAGE-XML (XML) string of the pages layout.
/// </summary>
/// <param name="page"></param>
/// <param name="includePaths">Draw PdfPaths present in the page.</param>
public string Get(Page page, bool includePaths)
{
lineCount = 0;
wordCount = 0;
glyphCount = 0;
regionCount = 0;
groupOrderCount = 0;
orderedRegions = new List <PageXmlDocument.PageXmlRegionRefIndexed>();
PageXmlDocument pageXmlDocument = new PageXmlDocument()
{
Metadata = new PageXmlDocument.PageXmlMetadata()
{
Created = DateTime.UtcNow,
LastChange = DateTime.UtcNow,
Creator = "PdfPig",
Comments = pageSegmenter.GetType().Name + "|" + wordExtractor.GetType().Name,
},
PcGtsId = "pc-" + page.GetHashCode()
};
pageXmlDocument.Page = ToPageXmlPage(page, includePaths);
return(Serialize(pageXmlDocument));
}
private AltoDocument.AltoDescription GetAltoDescription(string fileName)
{
var processing = new AltoDocument.AltoDescriptionProcessing
{
ProcessingAgency = null,
ProcessingCategory = AltoDocument.AltoProcessingCategory.Other,
ProcessingDateTime = DateTime.UtcNow.ToString(CultureInfo.InvariantCulture),
ProcessingSoftware = new AltoDocument.AltoProcessingSoftware
{
SoftwareName = "PdfPig",
SoftwareCreator = @"https://github.com/UglyToad/PdfPig",
ApplicationDescription = "Read and extract text and other content from PDFs in C# (port of PdfBox)",
SoftwareVersion = "x.x.xx"
},
ProcessingStepDescription = null,
ProcessingStepSettings = pageSegmenter.GetType().Name + "|" + wordExtractor.GetType().Name,
Id = "P" + pageCount + "_D1"
};
var documentIdentifier = new AltoDocument.AltoDocumentIdentifier
{
DocumentIdentifierLocation = null,
Value = null
};
var fileIdentifier = new AltoDocument.AltoFileIdentifier
{
FileIdentifierLocation = null,
Value = null
};
return(new AltoDocument.AltoDescription
{
MeasurementUnit = AltoDocument.AltoMeasurementUnit.Pixel,
Processings = new[] { processing },
SourceImageInformation = new AltoDocument.AltoSourceImageInformation
{
DocumentIdentifiers = new [] { documentIdentifier },
FileIdentifiers = new [] { fileIdentifier },
FileName = fileName
}
});
}
private string GetHead()
{
return(indentChar + "<head>" +
"\n" + indentChar + indentChar + "<title></title>" +
"\n" + indentChar + indentChar + "<meta http-equiv='Content-Type' content='text/html;charset=utf-8' />" +
"\n" + indentChar + indentChar + "<meta name='ocr-system' content='" + pageSegmenter.GetType().Name + "|" + wordExtractor.GetType().Name + "' />" +
"\n" + indentChar + indentChar + "<meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocr_linedrawing' />" +
"\n" + indentChar + "</head>\n");
}