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(Func<Metadata, InputStream> streamFactory)
{
try
{
var parser = new AutoDetectParser();
var metadata = new Metadata();
var outputWriter = new StringWriter();
var parseContext = new ParseContext();
//use the base class type for the key or parts of Tika won't find a usable parser
parseContext.set(typeof(org.apache.tika.parser.Parser), parser);
using (var inputStream = streamFactory(metadata))
{
try
{
parser.parse(inputStream, getTransformerHandler(outputWriter), metadata, parseContext);
}
finally
{
inputStream.close();
}
}
return assembleExtractionResult(outputWriter.ToString(), metadata);
}
catch (Exception ex)
{
throw new TextExtractionException("Extraction failed.", ex);
}
}
public Metadata Extract(Func <Metadata, InputStream> streamFactory, System.IO.Stream outputStream)
{
try
{
var parser = new AutoDetectParser();
var metadata = new Metadata();
var parseContext = new ParseContext();
var handler = GetTransformerHandler(outputStream);
//use the base class type for the key or parts of Tika won't find a usable parser
parseContext.set(typeof(org.apache.tika.parser.Parser), parser);
using (var inputStream = streamFactory(metadata))
{
try
{
parser.parse(inputStream, handler, metadata, parseContext);
}
finally
{
inputStream.close();
}
}
return(metadata);
}
catch (Exception ex)
{
throw new TextExtractionException("Extraction failed.", ex);
}
}
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);
}
}
public TextExtractionResult Extract(Func <Metadata, InputStream> streamFactory)
{
try
{
var parser = new AutoDetectParser();
var metadata = new Metadata();
var outputWriter = new StringWriter();
var parseContext = new ParseContext();
//use the base class type for the key or parts of Tika won't find a usable parser
parseContext.set(typeof(Parser), parser);
using (var inputStream = streamFactory(metadata))
{
try
{
parser.parse(inputStream, getTransformerHandler(outputWriter), metadata, parseContext);
}
finally
{
inputStream.close();
}
}
return(AssembleExtractionResult(outputWriter.ToString(), metadata));
}
catch (Exception ex)
{
throw new TextExtractionException("Extraction failed.", ex);
}
}
public void Convert()
{
byte[] file = Files.toByteArray(new File(@"filename.doc"));
AutoDetectParser tikaParser = new AutoDetectParser();
ByteArrayOutputStream output = new ByteArrayOutputStream();
SAXTransformerFactory factory = (SAXTransformerFactory)TransformerFactory.newInstance();
var inputStream = new ByteArrayInputStream(file);
// ToHTMLContentHandler handler = new ToHTMLContentHandler();
var metaData = new Metadata();
EncodingDetector encodingDetector = new UniversalEncodingDetector();
var encode = encodingDetector.detect(inputStream, metaData) ?? new UTF_32();
TransformerHandler handler = factory.newTransformerHandler();
handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
handler.getTransformer().setOutputProperty(OutputKeys.ENCODING, encode.toString());
handler.setResult(new StreamResult(output));
ContentHandler imageRewriting = new ImageRewritingContentHandler(handler);
// ExpandedTitleContentHandler handler1 = new ExpandedTitleContentHandler(handler);
ParseContext context = new ParseContext();
context.set(typeof(EmbeddedDocumentExtractor), new FileEmbeddedDocumentEtractor());
tikaParser.parse(inputStream, imageRewriting, new Metadata(), context);
byte[] array = output.toByteArray();
System.IO.File.WriteAllBytes(@"C:\toHtml\text.html", array);
}
public TextExtractionResult Extract(Func<Metadata, InputStream> streamFactory)
{
try
{
var parser = new AutoDetectParser();
var metadata = new Metadata();
var parseContext = new ParseContext();
//use the base class type for the key or parts of Tika won't find a usable parser
parseContext.set(typeof(Parser), parser);
var content = new System.IO.StringWriter();
var contentHandlerResult = new TextExtractorContentHandler(content);
using (var inputStream = streamFactory(metadata))
{
try
{
parser.parse(inputStream, contentHandlerResult, metadata, parseContext);
}
finally
{
inputStream.close();
}
}
return AssembleExtractionResult(content.ToString(), metadata);
}
catch (Exception ex)
{
throw new TextExtractionException("Extraction failed.", ex);
}
}
public string ExtractText(byte[] data)
{
var parser = new AutoDetectParser();
var handler = new BodyContentHandler();
var context = new ParseContext();
context.set(parser.getClass(), parser);
var metadata = new Metadata();
using (var output = new StringWriter()) {
var transformerHandler = CreateTransformerHandler(output);
using (var inputStream = TikaInputStream.get(data, metadata)) {
parser.parse(inputStream, transformerHandler, metadata, context);
inputStream.close();
}
return output.toString();
}
}
private static string GetContent(string fileName)
{
using (InputStream stream = new FileInputStream(new File(fileName)))
{
AutoDetectParser parser = new AutoDetectParser();
BodyContentHandler handler = new BodyContentHandler();
Metadata metadata = new Metadata();
var xpsParser = new XpsParser();
parser.setParsers(new java.util.HashMap { { MediaType.application("vnd.ms-xpsdocument"), xpsParser } });
parser.setParsers(new java.util.HashMap { { MediaType.application("x-tika-ooxml"), xpsParser } });
parser.parse(stream, handler, metadata);
return handler.toString();
}
}
private string Extract(Func <Metadata, InputStream> streamFactory)
{
try
{
Logger.Debug("Autodetect parser");
var autoDetectParser = new AutoDetectParser();
Logger.Debug("MetaData");
var metadata = new Metadata();
Logger.Debug("ToXMLContentHandler");
var handler = new ToXMLContentHandler();
Logger.Debug("Reading stream");
using (InputStream inputStream = streamFactory(metadata))
{
try
{
autoDetectParser.parse(
inputStream,
handler,
metadata
);
}
finally
{
Logger.Debug("Closing Stream after auto-detect parser");
inputStream.close();
}
}
var content = handler.ToString();
return(content);
}
catch (System.Exception ex)
{
Logger.ErrorFormat(ex, "Extract error: {0}", ex.Message);
if (ex.InnerException != null)
{
Logger.ErrorFormat(ex.InnerException, "Extract inner error: {0}", ex.InnerException.Message);
}
throw new TextExtractionException("Extraction failed.", ex);
}
}
private string Extract(Func<Metadata, InputStream> streamFactory)
{
try
{
Logger.Debug("Autodetect parser");
var autoDetectParser = new AutoDetectParser();
Logger.Debug("MetaData");
var metadata = new Metadata();
Logger.Debug("ToXMLContentHandler");
var handler = new ToXMLContentHandler();
Logger.Debug("Reading stream");
using (InputStream inputStream = streamFactory(metadata))
{
try
{
autoDetectParser.parse(
inputStream,
handler,
metadata
);
}
finally
{
Logger.Debug("Closing Stream after auto-detect parser");
inputStream.close();
}
}
var content = handler.ToString();
return content;
}
catch (System.Exception ex)
{
Logger.ErrorFormat(ex,"Extract {0}",ex.Message);
throw new TextExtractionException("Extraction failed.", ex);
}
}
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 void Get(object threadname)
{
System.Console.WriteLine("Wait for file path 3 second ..");
Thread.Sleep(3000);
Stopwatch s = new Stopwatch();
s.Start();//開始計時
Dictionary <string, string> value;
while (Program.File_Dir.Count != 0)
{
Parser parser = new AutoDetectParser();
Metadata metadata = new Metadata();
ParseContext pcontext = new ParseContext();
BodyContentHandler handler = new BodyContentHandler(-1);
//System.Console.WriteLine(threadname.ToString());
string filename = "";
System.Console.WriteLine();
try
{
filename = Program.File_Dir.Pop();
java.io.File document = new java.io.File(filename);
//System.Console.WriteLine("========Read======="+filename);
parser.parse(new FileInputStream(document), handler, metadata, pcontext);
}
catch (InvalidOperationException)
{
System.Console.WriteLine("堆疊為空");
break;
}
catch (Exception ex)
{
System.Console.WriteLine(filename + ": parser error" + ex);
System.Console.WriteLine();
continue;
}
value = new Dictionary <string, string>();
value.Add("id", filename);
foreach (var prop in metadata.names())
{
if (prop.Contains("TRC") || prop.Contains("Byte"))
{
continue;
}
value.Add(prop, metadata.get(prop).ToString());
//System.Console.WriteLine($"{prop} = {metadata.get(prop)}");
}
if (handler.toString() != "")
{
var str = Regex.Replace(handler.ToString(), @"\s", "");
//string str = handler.ToString();
if (str.Length < 65535)
{
value.Add("content", str);
}
}
//PostData(filename, value);
Program.JSON_Data.Push(JsonConvert.SerializeObject(value));
if (Program.Post_Thread.ThreadState == System.Threading.ThreadState.Unstarted && Program.JSON_Data.Count > 10)
{
//System.Console.WriteLine("POST" + " : " + Program.Post_Thread.ThreadState);
Program.Post_Thread.Start("POST");
//System.Console.WriteLine("POST" + " : " + Program.Post_Thread.ThreadState);
}
if (Program.Post_Thread.ThreadState == System.Threading.ThreadState.Suspended)
{
//System.Console.WriteLine("POST" + " : " + Program.Post_Thread.ThreadState);
Program.Post_Thread.Resume();
//System.Console.WriteLine("POST" + " : " + Program.Post_Thread.ThreadState);
}
}
s.Stop();
System.Console.WriteLine(threadname.ToString() + "," + (s.Elapsed).ToString());
}
public StreamTextExtractor()
{
Config = TikaConfig.getDefaultConfig();
Parser = new AutoDetectParser();
}
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);
}
}
