/// <summary>
/// Provides the means to extract the text to be indexed from the file specified
/// </summary>
/// <param name="file"></param>
/// <returns></returns>
protected virtual string ExtractTextFromFile(FileInfo file)
{
if (!SupportedExtensions.Select(x => x.ToUpper()).Contains(file.Extension.ToUpper()))
{
throw new NotSupportedException("The file with the extension specified is not supported");
}
var mediaParser = new MediaParser();
Action <Exception> onError = (e) => OnIndexingError(new IndexingErrorEventArgs("Could not read media item", -1, e));
var txt = mediaParser.ParseMediaText(file.FullName, onError, out _extractedMetaFromTika);
return(txt);
}
private ExtractionResult ExtractContentFromStream(Stream stream)
{
byte[] data;
var metaData = new Dictionary <string, string>();
var extractionResult = new ExtractionResult();
Action <Exception> onError = (e) => OnIndexingError(new IndexingErrorEventArgs("Could not read media item", -1, e));
using (MemoryStream ms = new MemoryStream())
{
stream.CopyTo(ms);
data = ms.ToArray();
}
if (data != null && data.Length > 0)
{
var mediaParser = new MediaParser();
extractionResult.ExtractedText = mediaParser.ParseMediaText(data, onError, out metaData);
extractionResult.MetaData = metaData;
}
return(extractionResult);
}
