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

Example 11 with AutoDetectParser

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

the class FontParsersTest method testTTFParsing.

@Test
public void testTTFParsing() throws Exception {
    // Should auto-detect!
    Parser parser = new AutoDetectParser();
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    ParseContext context = new ParseContext();
    try (TikaInputStream stream = TikaInputStream.get(FontParsersTest.class.getResource("/test-documents/testTrueType3.ttf"))) {
        parser.parse(stream, handler, metadata, context);
    }
    assertEquals("application/x-font-ttf", metadata.get(Metadata.CONTENT_TYPE));
    assertEquals("Open Sans Bold", metadata.get(TikaCoreProperties.TITLE));
    assertEquals("2010-12-30T11:04:00Z", metadata.get(Metadata.CREATION_DATE));
    assertEquals("2010-12-30T11:04:00Z", metadata.get(TikaCoreProperties.CREATED));
    assertEquals("2011-05-05T12:37:53Z", metadata.get(TikaCoreProperties.MODIFIED));
    assertEquals("Open Sans Bold", metadata.get(MET_FONT_NAME));
    assertEquals("Open Sans", metadata.get(MET_FONT_FAMILY_NAME));
    assertEquals("Bold", metadata.get(MET_FONT_SUB_FAMILY_NAME));
    assertEquals("OpenSans-Bold", metadata.get(MET_PS_NAME));
    assertEquals("Digitized", metadata.get("Copyright").substring(0, 9));
    assertEquals("Open Sans", metadata.get("Trademark").substring(0, 9));
    // Not extracted
    assertEquals(null, metadata.get(MET_FONT_FULL_NAME));
    assertEquals(null, metadata.get(MET_FONT_WEIGHT));
    assertEquals(null, metadata.get(MET_FONT_VERSION));
    // Currently, the parser doesn't extract any contents
    String content = handler.toString();
    assertEquals("", content);
}

Example 12 with AutoDetectParser

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

the class DBFParserTest method testVariants.

@Test
public void testVariants() throws Exception {
    ByteArrayOutputStream bos = new ByteArrayOutputStream();
    try (InputStream is = getResourceAsStream("/test-documents/testDBF.dbf")) {
        IOUtils.copy(is, bos);
    }
    byte[] bytes = bos.toByteArray();
    for (DBFReader.Version version : DBFReader.Version.values()) {
        //this cast happens to work because of the range of possible values
        bytes[0] = (byte) version.getId();
        XMLResult r = getXML(TikaInputStream.get(bytes), new AutoDetectParser(), new Metadata());
        assertEquals(version.getFullMimeString(), r.metadata.get(Metadata.CONTENT_TYPE));
    }
}

Example 13 with AutoDetectParser

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

the class TikaResource method createParser.

@SuppressWarnings("serial")
public static Parser createParser() {
    final Parser parser = new AutoDetectParser(tikaConfig);
    Map<MediaType, Parser> parsers = ((AutoDetectParser) parser).getParsers();
    parsers.put(MediaType.APPLICATION_XML, new HtmlParser());
    ((AutoDetectParser) parser).setParsers(parsers);
    ((AutoDetectParser) parser).setFallback(new Parser() {

        public Set<MediaType> getSupportedTypes(ParseContext parseContext) {
            return parser.getSupportedTypes(parseContext);
        }

        public void parse(InputStream inputStream, ContentHandler contentHandler, Metadata metadata, ParseContext parseContext) {
            throw new WebApplicationException(Response.Status.UNSUPPORTED_MEDIA_TYPE);
        }
    });
    if (digester != null) {
        return new DigestingParser(parser, digester);
    }
    return parser;
}

Example 14 with AutoDetectParser

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

the class TikaEngine method activate.

@Override
protected void activate(ComponentContext ctx) throws ConfigurationException {
    super.activate(ctx);
    config = TikaConfig.getDefaultConfig();
    this.detector = config.getDetector();
    this.parser = new AutoDetectParser(config);
    this.skipLinebreaks = getBoolean(ctx.getProperties(), SKIP_LINEBREAKS_WITHIN_CONTENT, DEFAULT_SKIP_LINEBREAKS);
    this.ontologyMappings = new OntologyMappings();
    if (getBoolean(ctx.getProperties(), MAPPING_MEDIA_RESOURCE, DEFAULT_MAPPING_MEDIA_RESOURCE_STATE)) {
        addMediaResourceOntologyMappings(ontologyMappings);
    }
    if (getBoolean(ctx.getProperties(), MAPPING_DUBLIN_CORE_TERMS, DEFAULT_MAPPING_DUBLIN_CORE_TERMS_STATE)) {
        addDcMappings(ontologyMappings);
    }
    if (getBoolean(ctx.getProperties(), MAPPING_NEPOMUK_MESSAGE, DEFAULT_MAPPING_NEPOMUK_MESSAGE_STATE)) {
        addNepomukMessageMappings(ontologyMappings);
    }
    if (getBoolean(ctx.getProperties(), MAPPING_NEPOMUK_EXIF, DEFAULT_MAPPING_NEPOMUK_EXIF_STATE)) {
        addNepomukExifMappings(ontologyMappings);
    }
    if (getBoolean(ctx.getProperties(), MAPPING_SKOS, DEFAULT_MAPPING_SKOS_STATE)) {
        addSkosMappings(ontologyMappings);
    }
    if (getBoolean(ctx.getProperties(), MAPPING_RDFS, DEFAULT_MAPPING_RDFS_STATE)) {
        addRdfsMappings(ontologyMappings);
    }
    if (getBoolean(ctx.getProperties(), MAPPING_GEO, DEFAULT_MAPPING_GEO_STATE)) {
        addGeoMappings(ontologyMappings);
    }
    includeUnmappedProperties = getBoolean(ctx.getProperties(), UNMAPPED_PROPERTIES, DEFAULT_UNMAPPED_PROPERTIES_STATE);
}

Example 15 with AutoDetectParser

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

the class TIAParsingExample method testHtmlMapper.

public static void testHtmlMapper() throws Exception {
    InputStream stream = new ByteArrayInputStream(new byte[0]);
    ContentHandler handler = new DefaultHandler();
    Metadata metadata = new Metadata();
    Parser parser = new AutoDetectParser();
    ParseContext context = new ParseContext();
    context.set(HtmlMapper.class, new IdentityHtmlMapper());
    parser.parse(stream, handler, metadata, context);
}