public TextExtractionResult Extract(string filePath)
{
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 (InputStream inputStream = TikaInputStream.get(url, metadata))
{
parser.parse(inputStream, getTransformerHandler(), metadata, parseContext);
inputStream.close();
}
return(assembleExtractionResult(_outputWriter.toString(), metadata));
}
catch (Exception ex)
{
throw new ApplicationException("Extraction of text from the file '{0}' failed.".ToFormat(filePath), ex);
}
}
/// <summary>
///
/// </summary>
/// <param name="filePath"></param>
/// <param name="password">Optional password to open the file.</param>
/// <returns></returns>
public string GetHtmlContent(string filePath, String password)
{
try
{
Logger.DebugFormat("GetHtmlContent for filePath: {0}", filePath);
var file = new File(filePath);
return(this.Extract((Func <Metadata, InputStream>)(metadata =>
{
Logger.DebugFormat("Extract metadata for {0}", filePath);
if (!String.IsNullOrEmpty(password))
{
metadata.add("org.apache.tika.parser.pdf.password", password);
}
var tikaInputStream = TikaInputStream.get(file, metadata);
Logger.DebugFormat("Return tikaInputStream for {0}", filePath);
return (InputStream)tikaInputStream;
})));
}
catch (System.Exception ex)
{
Logger.ErrorFormat(ex, "Error on GetHtmlContent for {0}", filePath);
throw new TextExtractionException(
StringExtrensions.ToFormat(
"Extraction of text from the file '{0}' failed.",
new object[] { (object)filePath }
), ex
);
}
}
public TextExtractionResult Extract(Guid applicationId, DocFileInfo file, ref bool succeed, ref string errorText)
{
try
{
AutoDetectParser parser = new AutoDetectParser();
Metadata metadata = new Metadata();
ParseContext parseContext = new ParseContext();
Class parserClass = parser.GetType();
parseContext.set(parserClass, parser);
byte[] fileContent = file.toByteArray(applicationId);
using (InputStream inputStream = TikaInputStream.get(fileContent, metadata))
{
parser.parse(inputStream, getTransformerHandler(), metadata, parseContext);
inputStream.close();
}
return(assembleExtractionResult(_outputWriter.toString(), metadata));
}
catch (Exception ex)
{
errorText = ex.StackTrace.ToString();
succeed = false;
return(null);
}
}
public TextExtractionResult Extract(Uri uri)
{
return(Extract(metadata =>
{
metadata.add("Uri", uri.ToString());
var pageBytes = new WebClient().DownloadData(uri);
return TikaInputStream.get(pageBytes, metadata);
}));
}
public void should_throw_when_given_closed_stream()
{
var closedStream = new MemoryStream();
closedStream.Dispose();
var bytes = new byte[] { 0, 1, 2, 3 };
Action act = () => _cut.Extract(metadata => TikaInputStream.get(bytes, metadata), closedStream);
act.ShouldThrow <TextExtractionException>().WithInnerException <ArgumentException>();
}
public TextExtractionResult Extract(Uri uri)
{
var jUri = new java.net.URI(uri.ToString());
return(Extract(metadata =>
{
var result = TikaInputStream.get(jUri, metadata);
metadata.add("Uri", uri.ToString());
return result;
}));
}
public void should_throw_when_given_a_disposed_stream()
{
var disposedStream = new MemoryStream();
disposedStream.Dispose();
var bytes = new byte[] { 0, 1, 2, 3 };
Action act = () => _cut.Extract(metadata => TikaInputStream.get(bytes, metadata), disposedStream);
act.Should().Throw <TextExtractionException>();
//act.ShouldThrow<TextExtractionException>();
}
public void should_throw_when_given_a_closed_stream()
{
var file = Path.GetTempFileName();
const int bufferSize = 4096;
var bytes = new byte[] { 0, 1, 2, 3 };
var closedStream = File.Create(file, bufferSize, FileOptions.DeleteOnClose);
closedStream.Close();
Action act = () => _cut.Extract(metadata => TikaInputStream.get(bytes, metadata), closedStream);
act.ShouldThrow <TextExtractionException>();
}
public TExtractionResult Extract <TExtractionResult>(
Uri uri,
Func <string, Metadata, TExtractionResult> extractionResultAssembler
)
{
return(Extract(UrlStreamFactory, extractionResultAssembler));
InputStream UrlStreamFactory(Metadata metadata)
{
metadata.add("Uri", uri.ToString());
var pageBytes = new WebClient().DownloadData(uri);
return(TikaInputStream.get(pageBytes, metadata));
}
}
public TextExtractionResult Extract(string filePath)
{
try
{
var file = new File(filePath);
return(Extract(metadata =>
{
var result = TikaInputStream.get(file, metadata);
metadata.add("FilePath", filePath);
return result;
}));
}
catch (Exception ex)
{
throw new TextExtractionException("Extraction of text from the file '{0}' failed.".ToFormat(filePath), ex);
}
}
public TExtractionResult Parse <TExtractionResult>(
System.IO.Stream inputStream,
Func <string, Metadata, TExtractionResult> extractionResultAssembler
)
{
try
{
return(Parse(SystemStreamFactory, extractionResultAssembler));
}
catch (Exception ex)
{
throw new TextExtractionException("Extraction of text from stream failed.", ex);
}
InputStream SystemStreamFactory(Metadata metadata)
{
var ioStream = new ikvm.io.InputStreamWrapper(inputStream);
var result = TikaInputStream.get(ioStream);
return(result);
}
}
public TExtractionResult Extract <TExtractionResult>(
string filePath,
Func <string, Metadata, TExtractionResult> extractionResultAssembler
)
{
try
{
return(Extract(FileStreamFactory, extractionResultAssembler));
}
catch (Exception ex)
{
throw new TextExtractionException("Extraction of text from the file '{0}' failed.".ToFormat(filePath), ex);
}
InputStream FileStreamFactory(Metadata metadata)
{
var inputStream = new FileInputStream(filePath);
var result = TikaInputStream.get(inputStream);
metadata.add("FilePath", filePath);
return(result);
}
}
public TextExtractionResult Extract(byte[] data)
{
var parser = new AutoDetectParser();
var metadata = new Metadata();
var parseContext = new ParseContext();
Class parserClass = parser.GetType();
parseContext.set(parserClass, parser);
try
{
using (InputStream inputStream = TikaInputStream.get(data, metadata))
{
parser.parse(inputStream, getTransformerHandler(), metadata, parseContext);
inputStream.close();
}
return(assembleExtractionResult(_outputWriter.ToString(), metadata));
}
catch (Exception ex)
{
throw new ApplicationException("Extraction of text from the byte array failed.", ex);
}
}
public TExtractionResult Extract <TExtractionResult>(byte[] data, Func <string, Metadata, TExtractionResult> extractionResultAssembler)
{
return(Extract(metadata => TikaInputStream.get(data, metadata), extractionResultAssembler));
}
public TextExtractionResult Extract(byte[] data)
{
return(Extract(metadata => TikaInputStream.get(data, metadata)));
}
