public override string Extract(Stream stream, TextExtractorContext context)
{
Called = true;
using (var reader = new StreamReader(stream))
Extraction = reader.ReadToEnd();
return(Extraction);
}
public override string Extract(Stream stream, TextExtractorContext context)
{
Task.Run(() =>
{
AsposePreviewProvider.CheckLicense(AsposePreviewProvider.LicenseProvider.Words);
var document = new Aspose.Words.Document(stream);
IndexingTools.AddTextExtract(context.VersionId, document.GetText());
});
return(string.Empty);
}
public override string Extract(Stream stream, TextExtractorContext context)
{
Task.Run(() =>
{
AsposePreviewProvider.CheckLicense(AsposePreviewProvider.LicenseProvider.Pdf);
var document = new Aspose.Pdf.Document(stream);
var textAbsorber = new TextAbsorber();
document.Pages.Accept(textAbsorber);
IndexingTools.AddTextExtract(context.VersionId, textAbsorber.Text);
});
return(string.Empty);
}
public override string Extract(Stream stream, TextExtractorContext context)
{
// call base method for iFilter logic
var textExtract = ExtractiFilter(stream, out var success);
if (success)
{
return(textExtract);
}
var text = new StringBuilder();
try
{
var pdfReader = new PdfReader(stream);
for (var page = 1; page <= pdfReader.NumberOfPages; page++)
{
// extract text using the old version (4.1.6) of iTextSharp
var pageText = ExtractTextFromPdfBytes(pdfReader.GetPageContent(page));
if (string.IsNullOrEmpty(pageText))
{
continue;
}
text.Append(pageText);
}
}
catch (OutOfMemoryException ex)
{
SnLog.WriteWarning("Pdf text extract failed with out of memory exception. " + ex,
EventId.Indexing,
properties: new Dictionary <string, object> {
{ "Stream size", stream.Length }
});
}
return(text.ToString());
}
