Examples with Metadata org.apache.tika.metadata.Metadata used on opensource projects

Example 36 with Metadata

use of org.apache.tika.metadata.Metadata in project tika by apache.

the class AutoDetectParserTest method testSpecificParserList.

/**
     * Test case for TIKA-514. Provide constructor for AutoDetectParser that has explicit
     * list of supported parsers.
     * @see <a href="https://issues.apache.org/jira/browse/TIKA-514">TIKA-514</a>
     */
@Test
public void testSpecificParserList() throws Exception {
    AutoDetectParser parser = new AutoDetectParser(new MyDetector(), new MyParser());
    InputStream is = new ByteArrayInputStream("test".getBytes(UTF_8));
    Metadata metadata = new Metadata();
    parser.parse(is, new BodyContentHandler(), metadata, new ParseContext());
    assertEquals("value", metadata.get("MyParser"));
}

Example 37 with Metadata

use of org.apache.tika.metadata.Metadata in project tika by apache.

the class TestMimeTypes method assertMagic.

private void assertMagic(String expected, byte[] prefix) throws IOException {
    MediaType type = repo.detect(new ByteArrayInputStream(prefix), new Metadata());
    assertNotNull(type);
    assertEquals(expected, type.toString());
}

Example 38 with Metadata

use of org.apache.tika.metadata.Metadata in project tika by apache.

the class MetadataAwareLuceneIndexer method indexWithDublinCore.

public void indexWithDublinCore(File file) throws Exception {
    Metadata met = new Metadata();
    met.add(Metadata.CREATOR, "Manning");
    met.add(Metadata.CREATOR, "Tika in Action");
    met.set(Metadata.DATE, new Date());
    met.set(Metadata.FORMAT, tika.detect(file));
    met.set(DublinCore.SOURCE, file.toURI().toURL().toString());
    met.add(Metadata.SUBJECT, "File");
    met.add(Metadata.SUBJECT, "Indexing");
    met.add(Metadata.SUBJECT, "Metadata");
    met.set(Property.externalClosedChoise(Metadata.RIGHTS, "public", "private"), "public");
    try (InputStream is = new FileInputStream(file)) {
        tika.parse(is, met);
        Document document = new Document();
        for (String key : met.names()) {
            String[] values = met.getValues(key);
            for (String val : values) {
                document.add(new Field(key, val, Store.YES, Index.ANALYZED));
            }
            writer.addDocument(document);
        }
    }
}

Example 39 with Metadata

use of org.apache.tika.metadata.Metadata in project tika by apache.

the class MyFirstTika method main.

public static void main(String[] args) throws Exception {
    String filename = args[0];
    TikaConfig tikaConfig = TikaConfig.getDefaultConfig();
    Metadata metadata = new Metadata();
    String text = parseUsingComponents(filename, tikaConfig, metadata);
    System.out.println("Parsed Metadata: ");
    System.out.println(metadata);
    System.out.println("Parsed Text: ");
    System.out.println(text);
    System.out.println("-------------------------");
    metadata = new Metadata();
    text = parseUsingAutoDetect(filename, tikaConfig, metadata);
    System.out.println("Parsed Metadata: ");
    System.out.println(metadata);
    System.out.println("Parsed Text: ");
    System.out.println(text);
}

Example 40 with Metadata

use of org.apache.tika.metadata.Metadata in project tika by apache.

the class ParsingExample method parseEmbeddedExample.

/**
     * This example shows how to extract content from the outer document and all
     * embedded documents.  The key is to specify a {@link Parser} in the {@link ParseContext}.
     *
     * @return content, including from embedded documents
     * @throws IOException
     * @throws SAXException
     * @throws TikaException
     */
public String parseEmbeddedExample() throws IOException, SAXException, TikaException {
    AutoDetectParser parser = new AutoDetectParser();
    BodyContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    ParseContext context = new ParseContext();
    context.set(Parser.class, parser);
    try (InputStream stream = ParsingExample.class.getResourceAsStream("test_recursive_embedded.docx")) {
        parser.parse(stream, handler, metadata, context);
        return handler.toString();
    }
}