Examples with AutoDetectParser org.apache.tika.parser.AutoDetectParser used on opensource projects

Example 71 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser in project tika by apache.

the class SQLite3ParserTest method testNotAddingEmbeddedParserToParseContext.

//test what happens if the user does not want embedded docs handled
@Test
public void testNotAddingEmbeddedParserToParseContext() throws Exception {
    Parser p = new AutoDetectParser();
    ContentHandler handler = new ToXMLContentHandler();
    Metadata metadata = new Metadata();
    ParseContext parseContext = new ParseContext();
    parseContext.set(Parser.class, new EmptyParser());
    try (InputStream is = getResourceAsStream(TEST_FILE1)) {
        metadata.set(Metadata.RESOURCE_NAME_KEY, TEST_FILE_NAME);
        p.parse(is, handler, metadata, parseContext);
    }
    String xml = handler.toString();
    //just includes headers for embedded documents
    assertContains("<table name=\"my_table1\"><thead><tr>", xml);
    assertContains("<td><span type=\"blob\" column_name=\"BYTES_COL\" row_number=\"0\"><div class=\"package-entry\"><h1>BYTES_COL_0.doc</h1>", xml);
    //but no other content
    assertNotContained("dog", xml);
    assertNotContained("alt=\"image1.png\"", xml);
    //second embedded doc's image tag
    assertNotContained("alt=\"A description...\"", xml);
}

Example 72 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser 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 73 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser in project tika by apache.

the class IWorkParserTest method setUp.

@Before
public void setUp() {
    iWorkParser = new IWorkPackageParser();
    parseContext = new ParseContext();
    parseContext.set(Parser.class, new AutoDetectParser());
}

Example 74 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser in project winery by eclipse.

the class BackendUtils method getMimeType.

/**
 * Detect the mime type of the stream. The stream is marked at the beginning and reset at the end
 *
 * @param bis the stream
 * @param fn  the fileName of the file belonging to the stream
 */
public static MediaType getMimeType(BufferedInputStream bis, String fn) throws IOException {
    AutoDetectParser parser = new AutoDetectParser();
    Detector detector = parser.getDetector();
    Metadata md = new Metadata();
    md.add(Metadata.RESOURCE_NAME_KEY, fn);
    final MediaType mediaType = detector.detect(bis, md);
    return mediaType;
}

Example 75 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser 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;
}