Java TikaException类代码示例

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
/**
 * Converts a .docx document into HTML markup. This code
 * is based on <a href="http://stackoverflow.com/a/9053258/313554">this StackOverflow</a> answer.
 *
 * @param wordDocument  The converted .docx document.
 * @return
 */
public ConvertedDocumentDTO convertWordDocumentIntoHtml(MultipartFile wordDocument) {
    LOGGER.info("Converting word document: {} into HTML", wordDocument.getOriginalFilename());
    try {
        InputStream input = wordDocument.getInputStream();
        Parser parser = new OOXMLParser();

        StringWriter sw = new StringWriter();
        SAXTransformerFactory factory = (SAXTransformerFactory)
                SAXTransformerFactory.newInstance();
        TransformerHandler handler = factory.newTransformerHandler();
        handler.getTransformer().setOutputProperty(OutputKeys.ENCODING, "utf-8");
        handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
        handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
        handler.setResult(new StreamResult(sw));

        Metadata metadata = new Metadata();
        metadata.add(Metadata.CONTENT_TYPE, "text/html;charset=utf-8");
        parser.parse(input, handler, metadata, new ParseContext());
        return new ConvertedDocumentDTO(wordDocument.getOriginalFilename(), sw.toString());
    }
    catch (IOException | SAXException | TransformerException | TikaException ex) {
        LOGGER.error("Conversion failed because an exception was thrown", ex);
        throw new DocumentConversionException(ex.getMessage(), ex);
    }
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
private static String getFullText(final String filepath) throws IOException, SAXException, TikaException {
    StringWriter writer = new StringWriter();
    
    final TikaInputStream inputStream =  TikaInputStream.get(new File(filepath));
    try {
        final Detector detector = new DefaultDetector();
        final Parser parser = new AutoDetectParser(detector);

        final Metadata metadata = new Metadata();
        final ParseContext parseContext = new ParseContext();
        parseContext.set(Parser.class, parser);

        
        ContentHandler contentHandler = new BodyContentHandler(writer);
        parser.parse(inputStream, contentHandler, metadata, parseContext);
    }
    finally {
        inputStream.close();
    }
    
    return writer.toString();
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
public void parse(
        InputStream stream, ContentHandler handler,
        Metadata metadata, ParseContext context)
        throws IOException, SAXException, TikaException {
    TemporaryResources tmp = new TemporaryResources();
    try {
        TikaInputStream tis = TikaInputStream.get(stream, tmp);
        new ImageMetadataExtractor(metadata).parseJpeg(tis.getFile());
        new JempboxExtractor(metadata).parse(tis);
    } finally {
        tmp.dispose();
    }

    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    xhtml.endDocument();
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
/**
 * parses with tika, throwing any exception hit while parsing the document
 */
// only package private for testing!
static String parse(final byte content[], final Metadata metadata, final int limit) throws TikaException, IOException {
    // check that its not unprivileged code like a script
    SpecialPermission.check();

    try {
        return AccessController.doPrivileged((PrivilegedExceptionAction<String>)
            () -> TIKA_INSTANCE.parseToString(new ByteArrayInputStream(content), metadata, limit), RESTRICTED_CONTEXT);
    } catch (PrivilegedActionException e) {
        // checked exception from tika: unbox it
        Throwable cause = e.getCause();
        if (cause instanceof TikaException) {
            throw (TikaException) cause;
        } else if (cause instanceof IOException) {
            throw (IOException) cause;
        } else {
            throw new AssertionError(cause);
        }
    }
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
@Before
public void setUp() throws IOException, TikaException, SAXException {
    MockitoAnnotations.initMocks(this);

    store = new FileRefStore();
    store.setEntityManager(getEm());
    store.setQueryFactory(new JPAQueryFactory(getEm()));
    store.setTemplate(template);

    createDirectories(Paths.get("fileTestFiles"));

    TikaProvider tikaProvider = new TikaProvider();
    TikaTransformer transformer = new TikaTransformer();
    transformer.setTika(tikaProvider.tika());

    repository = new FileRepository();
    repository.setStore(store);
    repository.setBasePath("fileTestFiles");
    repository.setTransformer(transformer);
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
@Before
public void setUp() throws TikaException, IOException, SAXException {
    VelocityEngine engine = new VelocityEngine();
    engine.setProperty(RuntimeConstants.RESOURCE_LOADER, "classpath");
    engine.setProperty("classpath.resource.loader.class", ClasspathResourceLoader.class.getName());
    engine.init();

    Templater templater = new Templater();
    templater.setEngine(engine);

    exporter = new HtmlExporter();
    exporter.setTemplater(templater);

    TikaProvider provider = new TikaProvider();
    Tika tika = provider.tika();

    transformer = new TikaTransformer();
    transformer.setTika(tika);
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
@Before
public void setUp() throws TikaException, IOException, SAXException {
    VelocityEngine engine = new VelocityEngine();
    engine.setProperty(RuntimeConstants.RESOURCE_LOADER, "classpath");
    engine.setProperty("classpath.resource.loader.class", ClasspathResourceLoader.class.getName());
    engine.init();

    Templater templater = new Templater();
    templater.setEngine(engine);

    exporter = new PdfExporter();
    exporter.setTemplater(templater);

    TikaProvider provider = new TikaProvider();
    Tika tika = provider.tika();

    transformer = new TikaTransformer();
    transformer.setTika(tika);
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
@Override
public void process(ProcessingContext<Corpus> ctx, Corpus corpus) throws ModuleException {
	Logger.getLogger("org.apache.pdfbox").setLevel(Level.OFF);
	AutoDetectParser parser = new AutoDetectParser();
	ParseContext parseContext = new ParseContext();
	try {
		for (InputStream is : Iterators.loop(source.getInputStreams())) {
			TikaReaderHandler handler = parse(parser, parseContext, is);
			Document doc = createDocument(corpus, handler);
			createTagAnnotations(doc, handler);
		}
	}
	catch (IOException|SAXException|TikaException e) {
		rethrow(e);
	}
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
@Test
public void testParseDamagedPdfFile() throws IOException {
  String path = getClass().getResource("/damaged.pdf").getPath();
  PCollection<ParseResult> res = p.apply("ParseInvalidPdfFile", TikaIO.parse().filepattern(path));

  PAssert.thatSingleton(res)
      .satisfies(
          new SerializableFunction<ParseResult, Void>() {
            @Override
            public Void apply(ParseResult input) {
              assertEquals(path, input.getFileLocation());
              assertFalse(input.isSuccess());
              assertTrue(input.getError() instanceof TikaException);
              return null;
            }
          });
  p.run();
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
/**
 * Ritorna una vista HTML sul file processato. L'estrazione del testo fa
 * perdere di fatto la formattazione contenuta nel word o nel PDF. La
 * versione HTML è una versione processabile ma che mantiene il formato
 *
 * @param file file da parsare
 * @return vista HTML formattato del contenuto del documento (privato delle
 * immagini)
 */
public String getHtmlFromFile(File file) {
    try {
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        SAXTransformerFactory factory = (SAXTransformerFactory) SAXTransformerFactory.newInstance();
        TransformerHandler handler = factory.newTransformerHandler();
        handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
        handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
        handler.getTransformer().setOutputProperty(OutputKeys.ENCODING, "UTF-8");
        handler.setResult(new StreamResult(out));
        ExpandedTitleContentHandler handler1 = new ExpandedTitleContentHandler(handler);
        InputStream is = file.toURI().toURL().openStream();
        adp.parse(is, handler1, new Metadata());
        is.close();
        return new String(out.toByteArray(), "UTF-8").replaceAll("<img .*?</img>", "").replaceAll("<img .*?/>", "");
    } catch (TransformerConfigurationException | IllegalArgumentException | IOException | SAXException | TikaException ex) {
        return "!ERROR: " + ex.getLocalizedMessage();
    }
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
public static void main(String[] args) throws IOException, TikaException {
    //Tomcat changes the working dir, so we make this absolute
    ResourceManager.setDataDir(new File(dataDir).getAbsoluteFile());

    //noinspection ResultOfMethodCallIgnored
    ResourceManager.getDataDir().mkdirs();

    SpringApplication.run(SpringController.class, args);

    new Caddy().start();

    if(VirusScanner.isAvInstalled()) {
        log.info("Virus scanning available");
        virusScanner = new VirusScanner();
        virusScanner.start();
    } else {
        log.warn("Virus scanning unavailable. Skipping...");
    }
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
private static Charset detectCharset(final Path path, final Metadata metadata) throws IOException {
	final Charset charset;

	// Try to parse the character set from the content-encoding.
	String orig = metadata.get(Metadata.CONTENT_ENCODING);

	// Try to detect the character set.
	if (null != orig && Charset.isSupported(orig)) {
		return Charset.forName(orig);
	}

	try (
		final InputStream input = new BufferedInputStream(Files.newInputStream(path));
		final AutoDetectReader detector = new AutoDetectReader(input, metadata)
	) {
		charset = detector.getCharset();
	} catch (TikaException e) {
		throw new IOException("Unable to detect charset.", e);
	}

	return charset;
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
@Test
public void testWrite() throws IOException, TikaException {
	final ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
	final PrintStream printStream = new PrintStream(outputStream);
	final Spewer spewer = new PrintStreamSpewer(printStream, new FieldNames());

	final String buffer = "$";
	final String name = "imaginary-file.txt";
	final InputStream inputStream = new ByteArrayInputStream(buffer.getBytes(StandardCharsets.UTF_8));
	final ParsingReader reader = new ParsingReader(inputStream, name);

	spewer.outputMetadata(false);
	spewer.write(factory.create(name), reader);

	Assert.assertEquals("$\n\n", outputStream.toString(StandardCharsets.UTF_8.name()));
	Assert.assertArrayEquals(new byte[] {0x24, 0x0A}, Arrays.copyOfRange(outputStream.toByteArray(), 0, 2));
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
@Test
public void testWriteFromUTF16LE() throws IOException, TikaException {
	final ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
	final PrintStream printStream = new PrintStream(outputStream);
	final Spewer spewer = new PrintStreamSpewer(printStream, new FieldNames());

	final byte[] buffer = new byte[] {(byte) 0xFF, (byte) 0xFE, 0x24, 0x00};
	final String name = "imaginary-file.txt";
	final InputStream inputStream = new ByteArrayInputStream(buffer);
	final ParsingReader reader = new ParsingReader(inputStream, name);

	spewer.outputMetadata(false);
	spewer.write(factory.create(name), reader);

	Assert.assertEquals("$\n\n", outputStream.toString(StandardCharsets.UTF_8.name()));
	Assert.assertArrayEquals(new byte[] {0x24, 0x0A}, Arrays.copyOfRange(outputStream.toByteArray(), 0, 2));
}
 

import org.apache.tika.exception.TikaException; //导入依赖的package包/类
@Test
public void testWriteFromUTF16BE() throws IOException, TikaException {
	final ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
	final PrintStream printStream = new PrintStream(outputStream);
	final Spewer spewer = new PrintStreamSpewer(printStream, new FieldNames());

	final byte[] buffer = new byte[] {(byte) 0xFE, (byte) 0xFF, 0x00, 0x24};
	final String name = "imaginary-file.txt";
	final InputStream inputStream = new ByteArrayInputStream(buffer);
	final ParsingReader reader = new ParsingReader(inputStream, name);

	spewer.outputMetadata(false);
	spewer.write(factory.create(name), reader);

	Assert.assertEquals("$\n\n", outputStream.toString(StandardCharsets.UTF_8.name()));
	Assert.assertArrayEquals(new byte[] {0x24, 0x0A}, Arrays.copyOfRange(outputStream.toByteArray(), 0, 2));
}