Examples with TikaInputStream org.apache.tika.io.TikaInputStream used on opensource projects

Example 51 with TikaInputStream

use of org.apache.tika.io.TikaInputStream in project tika by apache.

the class OldExcelParserTest method testPlainText.

/**
     * Check we can get the plain text properly
     */
@Test
public void testPlainText() throws Exception {
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    try (TikaInputStream stream = getTestFile(file)) {
        new OldExcelParser().parse(stream, handler, metadata, new ParseContext());
    }
    String text = handler.toString();
    // Check we find a few words we expect in there
    assertContains("Size", text);
    assertContains("Returns", text);
    // Check we find a few numbers we expect in there
    assertContains("11", text);
    assertContains("784", text);
}

Example 52 with TikaInputStream

use of org.apache.tika.io.TikaInputStream in project tika by apache.

the class AbstractPOIContainerExtractionTest method process.

protected TrackingHandler process(String filename, ContainerExtractor extractor, boolean recurse) throws Exception {
    try (TikaInputStream stream = getTestFile(filename)) {
        assertEquals(true, extractor.isSupported(stream));
        // Process it
        TrackingHandler handler = new TrackingHandler();
        if (recurse) {
            extractor.extract(stream, extractor, handler);
        } else {
            extractor.extract(stream, null, handler);
        }
        // So they can check what happened
        return handler;
    }
}

Example 53 with TikaInputStream

use of org.apache.tika.io.TikaInputStream in project tika by apache.

the class FSBatchProcessCLI method execute.

private void execute(String[] args) throws Exception {
    CommandLineParser cliParser = new DefaultParser();
    CommandLine line = cliParser.parse(options, args);
    if (line.hasOption("help")) {
        usage();
        System.exit(BatchProcessDriverCLI.PROCESS_NO_RESTART_EXIT_CODE);
    }
    Map<String, String> mapArgs = new HashMap<String, String>();
    for (Option option : line.getOptions()) {
        String v = option.getValue();
        if (v == null || v.equals("")) {
            v = "true";
        }
        mapArgs.put(option.getOpt(), v);
    }
    BatchProcessBuilder b = new BatchProcessBuilder();
    TikaInputStream is = null;
    BatchProcess process = null;
    try {
        is = getConfigInputStream(args, false);
        process = b.build(is, mapArgs);
    } finally {
        IOUtils.closeQuietly(is);
    }
    final Thread mainThread = Thread.currentThread();
    ExecutorService executor = Executors.newSingleThreadExecutor();
    Future<ParallelFileProcessingResult> futureResult = executor.submit(process);
    ParallelFileProcessingResult result = futureResult.get();
    System.out.println(FINISHED_STRING);
    System.out.println("\n");
    System.out.println(result.toString());
    System.exit(result.getExitStatus());
}

Example 54 with TikaInputStream

use of org.apache.tika.io.TikaInputStream in project tika by apache.

the class TikaGUI method handleStream.

private void handleStream(InputStream input, Metadata md) throws Exception {
    StringWriter htmlBuffer = new StringWriter();
    StringWriter textBuffer = new StringWriter();
    StringWriter textMainBuffer = new StringWriter();
    StringWriter xmlBuffer = new StringWriter();
    StringBuilder metadataBuffer = new StringBuilder();
    ContentHandler handler = new TeeContentHandler(getHtmlHandler(htmlBuffer), getTextContentHandler(textBuffer), getTextMainContentHandler(textMainBuffer), getXmlContentHandler(xmlBuffer));
    context.set(DocumentSelector.class, new ImageDocumentSelector());
    input = TikaInputStream.get(new ProgressMonitorInputStream(this, "Parsing stream", input));
    if (input.markSupported()) {
        int mark = -1;
        if (input instanceof TikaInputStream) {
            if (((TikaInputStream) input).hasFile()) {
                mark = (int) ((TikaInputStream) input).getLength();
            }
        }
        if (mark == -1) {
            mark = MAX_MARK;
        }
        input.mark(mark);
    }
    parser.parse(input, handler, md, context);
    String[] names = md.names();
    Arrays.sort(names);
    for (String name : names) {
        for (String val : md.getValues(name)) {
            metadataBuffer.append(name);
            metadataBuffer.append(": ");
            metadataBuffer.append(val);
            metadataBuffer.append("\n");
        }
    }
    String name = md.get(Metadata.RESOURCE_NAME_KEY);
    if (name != null && name.length() > 0) {
        setTitle("Apache Tika: " + name);
    } else {
        setTitle("Apache Tika: unnamed document");
    }
    setText(metadata, metadataBuffer.toString());
    setText(xml, xmlBuffer.toString());
    setText(text, textBuffer.toString());
    setText(textMain, textMainBuffer.toString());
    setText(html, htmlBuffer.toString());
    if (!input.markSupported()) {
        setText(json, "InputStream does not support mark/reset for Recursive Parsing");
        layout.show(cards, "metadata");
        return;
    }
    boolean isReset = false;
    try {
        input.reset();
        isReset = true;
    } catch (IOException e) {
        setText(json, "Error during stream reset.\n" + "There's a limit of " + MAX_MARK + " bytes for this type of processing in the GUI.\n" + "Try the app with command line argument of -J.");
    }
    if (isReset) {
        RecursiveParserWrapper wrapper = new RecursiveParserWrapper(parser, new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.BODY, -1));
        wrapper.parse(input, null, new Metadata(), new ParseContext());
        StringWriter jsonBuffer = new StringWriter();
        JsonMetadataList.setPrettyPrinting(true);
        JsonMetadataList.toJson(wrapper.getMetadata(), jsonBuffer);
        setText(json, jsonBuffer.toString());
    }
    layout.show(cards, "metadata");
}

Example 55 with TikaInputStream

use of org.apache.tika.io.TikaInputStream in project tika by apache.

the class OfficeParser method parse.

/**
     * Extracts properties and text from an MS Document input stream
     */
public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    configure(context);
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    final DirectoryNode root;
    TikaInputStream tstream = TikaInputStream.cast(stream);
    NPOIFSFileSystem mustCloseFs = null;
    try {
        if (tstream == null) {
            mustCloseFs = new NPOIFSFileSystem(new CloseShieldInputStream(stream));
            root = mustCloseFs.getRoot();
        } else {
            final Object container = tstream.getOpenContainer();
            if (container instanceof NPOIFSFileSystem) {
                root = ((NPOIFSFileSystem) container).getRoot();
            } else if (container instanceof DirectoryNode) {
                root = (DirectoryNode) container;
            } else {
                NPOIFSFileSystem fs = null;
                if (tstream.hasFile()) {
                    fs = new NPOIFSFileSystem(tstream.getFile(), true);
                } else {
                    fs = new NPOIFSFileSystem(new CloseShieldInputStream(tstream));
                }
                //tstream will close the fs, no need to close this below
                tstream.setOpenContainer(fs);
                root = fs.getRoot();
            }
        }
        parse(root, context, metadata, xhtml);
        OfficeParserConfig officeParserConfig = context.get(OfficeParserConfig.class);
        if (officeParserConfig.getExtractMacros()) {
            //now try to get macros
            extractMacros(root.getNFileSystem(), xhtml, EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context));
        }
    } finally {
        IOUtils.closeQuietly(mustCloseFs);
    }
    xhtml.endDocument();
}