Examples with TikaException org.apache.tika.exception.TikaException used on opensource projects

Example 66 with TikaException

use of org.apache.tika.exception.TikaException in project tika by apache.

the class RFC822ParserTest method testExtractAttachments.

@Test
public void testExtractAttachments() throws Exception {
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    Parser p = new RFC822Parser();
    ParseContext context = new ParseContext();
    try (InputStream stream = getStream("test-documents/testEmailWithPNGAtt.eml")) {
        p.parse(stream, handler, metadata, context);
    }
    // Check we go the metadata
    assertEquals("Tika Test <XXXX@apache.org>", metadata.get(Metadata.MESSAGE_FROM));
    assertEquals("Test Attachment Email", metadata.get(TikaCoreProperties.TITLE));
    // Try again with attachment detecting and fetching
    final Detector detector = new DefaultDetector();
    final Parser extParser = new AutoDetectParser();
    final List<MediaType> seenTypes = new ArrayList<MediaType>();
    final List<String> seenText = new ArrayList<String>();
    EmbeddedDocumentExtractor ext = new EmbeddedDocumentExtractor() {

        @Override
        public boolean shouldParseEmbedded(Metadata metadata) {
            return true;
        }

        @Override
        public void parseEmbedded(InputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml) throws SAXException, IOException {
            seenTypes.add(detector.detect(stream, metadata));
            ContentHandler h = new BodyContentHandler();
            try {
                extParser.parse(stream, h, metadata, new ParseContext());
            } catch (TikaException e) {
                throw new RuntimeException(e);
            }
            seenText.add(h.toString());
        }
    };
    context.set(EmbeddedDocumentExtractor.class, ext);
    try (InputStream stream = getStream("test-documents/testEmailWithPNGAtt.eml")) {
        p.parse(stream, handler, metadata, context);
    }
    // Check we go the metadata
    assertEquals("Tika Test <XXXX@apache.org>", metadata.get(Metadata.MESSAGE_FROM));
    assertEquals("Test Attachment Email", metadata.get(TikaCoreProperties.TITLE));
    // Check attachments
    assertEquals(2, seenTypes.size());
    assertEquals(2, seenText.size());
    assertEquals("text/plain", seenTypes.get(0).toString());
    assertEquals("image/png", seenTypes.get(1).toString());
    assertEquals("This email has a PNG attachment included in it\n\n", seenText.get(0));
}

Example 67 with TikaException

use of org.apache.tika.exception.TikaException in project cxf by apache.

the class TikaContentExtractor method extract.

/**
 * Extract the content and metadata from the input stream with a media type hint
 * type of content.
 * @param in input stream to extract the metadata from
 * @param handler custom ContentHandler
 * @param mt JAX-RS MediaType of the stream content
 * @param context custom context
 * @return the extracted content and metadata or null if extraction is not possible
 *         or was unsuccessful
 */
public TikaContent extract(final InputStream in, ContentHandler handler, javax.ws.rs.core.MediaType mtHint, ParseContext context) {
    if (in == null) {
        return null;
    }
    final Metadata metadata = new Metadata();
    try {
        // Try to validate that input stream media type is supported by the parser
        MediaType mediaType = null;
        if (mtHint != null) {
            mediaType = MediaType.parse(mtHint.toString());
        } else if (detector != null && in.markSupported()) {
            mediaType = detector.detect(in, metadata);
        }
        if (mediaType != null) {
            metadata.set(HttpHeaders.CONTENT_TYPE, mediaType.toString());
        }
        Parser parser = null;
        if (parsers.size() == 1) {
            parser = parsers.get(0);
        } else {
            for (Parser p : parsers) {
                if (mediaType != null && !p.getSupportedTypes(context).contains(mediaType)) {
                    continue;
                }
                parser = p;
                break;
            }
        }
        if (parser == null) {
            return null;
        }
        if (context == null) {
            context = new ParseContext();
        }
        if (context.get(Parser.class) == null) {
            // to process the embedded attachments
            context.set(Parser.class, parser instanceof AutoDetectParser ? parser : new AutoDetectParser());
        }
        try {
            parser.parse(in, handler, metadata, context);
        } catch (Exception ex) {
            // not ready to accept null handlers so lets retry with IgnoreContentHandler.
            if (handler == null) {
                handler = new IgnoreContentHandler();
                parser.parse(in, handler, metadata, context);
            } else {
                throw ex;
            }
        }
        return new TikaContent(handler, metadata, mediaType);
    } catch (final IOException ex) {
        LOG.log(Level.WARNING, "Unable to extract media type from input stream", ex);
    } catch (final SAXException ex) {
        LOG.log(Level.WARNING, "Unable to parse input stream", ex);
    } catch (final TikaException ex) {
        LOG.log(Level.WARNING, "Unable to parse input stream", ex);
    }
    return null;
}

Example 68 with TikaException

use of org.apache.tika.exception.TikaException in project tika by apache.

the class Tika method parseToString.

/**
     * Parses the given document and returns the extracted text content.
     * The given input stream is closed by this method.
     * <p>
     * To avoid unpredictable excess memory use, the returned string contains
     * only up to {@link #getMaxStringLength()} first characters extracted
     * from the input document. Use the {@link #setMaxStringLength(int)}
     * method to adjust this limitation.
     * <p>
     * <strong>NOTE:</strong> Unlike most other Tika methods that take an
     * {@link InputStream}, this method will close the given stream for
     * you as a convenience. With other methods you are still responsible
     * for closing the stream or a wrapper instance returned by Tika.
     *
     * @param stream the document to be parsed
     * @param metadata document metadata
     * @return extracted text content
     * @throws IOException if the document can not be read
     * @throws TikaException if the document can not be parsed
     */
public String parseToString(InputStream stream, Metadata metadata) throws IOException, TikaException {
    WriteOutContentHandler handler = new WriteOutContentHandler(maxStringLength);
    try {
        ParseContext context = new ParseContext();
        context.set(Parser.class, parser);
        parser.parse(stream, new BodyContentHandler(handler), metadata, context);
    } catch (SAXException e) {
        if (!handler.isWriteLimitReached(e)) {
            // This should never happen with BodyContentHandler...
            throw new TikaException("Unexpected SAX processing failure", e);
        }
    } finally {
        stream.close();
    }
    return handler.toString();
}

Example 69 with TikaException

use of org.apache.tika.exception.TikaException in project tika by apache.

the class ExternalEmbedderTest method embedInTempFile.

/**
     * Tests embedding metadata then reading metadata to verify the results.
     *
     * @param isResultExpectedInOutput whether or not results are expected in command line output
     */
protected void embedInTempFile(InputStream sourceInputStream, boolean isResultExpectedInOutput) {
    Embedder embedder = getEmbedder();
    // TODO Move this check to ExternalEmbedder
    String os = System.getProperty("os.name", "");
    if (os.contains("Windows")) {
        // Skip test on Windows
        return;
    }
    Date timestamp = new Date();
    Metadata metadataToEmbed = getMetadataToEmbed(timestamp);
    try {
        File tempOutputFile = tmp.createTemporaryFile();
        FileOutputStream tempFileOutputStream = new FileOutputStream(tempOutputFile);
        // Embed the metadata into a copy of the original output stream
        embedder.embed(metadataToEmbed, sourceInputStream, tempFileOutputStream, null);
        ParseContext context = new ParseContext();
        Parser parser = getParser();
        context.set(Parser.class, parser);
        // Setup the extracting content handler
        ByteArrayOutputStream result = new ByteArrayOutputStream();
        OutputStreamWriter outputWriter = new OutputStreamWriter(result, DEFAULT_CHARSET);
        ContentHandler handler = new BodyContentHandler(outputWriter);
        // Create a new metadata object to read the new metadata into
        Metadata embeddedMetadata = new Metadata();
        // Setup a re-read of the now embeded temp file
        FileInputStream embeddedFileInputStream = new FileInputStream(tempOutputFile);
        parser.parse(embeddedFileInputStream, handler, embeddedMetadata, context);
        tmp.dispose();
        String outputString = null;
        if (isResultExpectedInOutput) {
            outputString = result.toString(DEFAULT_CHARSET);
        } else {
            assertTrue("no metadata found", embeddedMetadata.size() > 0);
        }
        // Check each metadata property for the expected value
        for (String metadataName : metadataToEmbed.names()) {
            if (metadataToEmbed.get(metadataName) != null) {
                String expectedValue = metadataToEmbed.get(metadataName);
                boolean foundExpectedValue = false;
                if (isResultExpectedInOutput) {
                    // just check that the entire output contains the expected string
                    foundExpectedValue = outputString.contains(expectedValue);
                } else {
                    if (embeddedMetadata.isMultiValued(metadataName)) {
                        for (String embeddedValue : embeddedMetadata.getValues(metadataName)) {
                            if (embeddedValue != null) {
                                if (embeddedValue.contains(expectedValue)) {
                                    foundExpectedValue = true;
                                    break;
                                }
                            }
                        }
                    } else {
                        String embeddedValue = embeddedMetadata.get(metadataName);
                        assertNotNull("expected metadata for " + metadataName + " not found", embeddedValue);
                        foundExpectedValue = embeddedValue.contains(expectedValue);
                    }
                }
                assertTrue("result did not contain expected appended metadata " + metadataName + "=" + expectedValue, foundExpectedValue);
            }
        }
    } catch (IOException e) {
        fail(e.getMessage());
    } catch (TikaException e) {
        fail(e.getMessage());
    } catch (SAXException e) {
        fail(e.getMessage());
    }
}

Example 70 with TikaException

use of org.apache.tika.exception.TikaException in project tika by apache.

the class AutoDetectParserTest method testZipBombPrevention.

/**
     * Make sure that zip bomb attacks are prevented.
     *
     * @see <a href="https://issues.apache.org/jira/browse/TIKA-216">TIKA-216</a>
     */
@Test
public void testZipBombPrevention() throws Exception {
    try (InputStream tgz = AutoDetectParserTest.class.getResourceAsStream("/test-documents/TIKA-216.tgz")) {
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler(-1);
        new AutoDetectParser(tika).parse(tgz, handler, metadata);
        fail("Zip bomb was not detected");
    } catch (TikaException e) {
    // expected
    }
}