public TextExtractionResult Extract(string filePath)
{
if (!System.IO.File.Exists(filePath))
throw new System.ArgumentException("File does not exist");
var parser = new AutoDetectParser();
var metadata = new Metadata();
var parseContext = new ParseContext();
Class parserClass = parser.GetType();
parseContext.set(parserClass, parser);
try {
var file = new File(filePath);
var url = file.toURI().toURL();
using (var inputStream = TikaInputStream.get(url, metadata)) {
parser.parse(inputStream, getTransformerHandler(), metadata, parseContext);
inputStream.close();
}
return assembleExtractionResult(_outputWriter.toString(), metadata);
} catch (Exception ex) {
throw new ApplicationException(string.Format("Extraction of text from the file '{0}' failed.", filePath), ex);
}
}
