/// <summary>
/// Get text from the binary using our custom HTML utilities
/// </summary>
/// <returns>The text of the HTML file or null if we could not process the text</returns>
public override string GetTextFromDocumentBinary()
{
string text = null;
// If we have no bytes then we can't do anything.
if (Bytes == null || Bytes.Length == 0)
{
// Log the problem.
log.Error("Tried to extract text from empty bytes for file " + Name);
return(null);
}
try
{
System.IO.StreamReader theReader = new StreamReader(new MemoryStream(Bytes));
text = DocUtils.StripHTML(theReader.ReadToEnd());
}
catch (Exception e)
{
log.Error("Failed to get the text from the HTML file " + Name, e);
}
return(text);
}
