Examples with BasicContentHandlerFactory org.apache.tika.sax.BasicContentHandlerFactory used on opensource projects

Example 21 with BasicContentHandlerFactory

use of org.apache.tika.sax.BasicContentHandlerFactory in project tika by apache.

the class ParsingExample method recursiveParserWrapperExample.

/**
     * For documents that may contain embedded documents, it might be helpful
     * to create list of metadata objects, one for the container document and
     * one for each embedded document.  This allows easy access to both the
     * extracted content and the metadata of each embedded document.
     * Note that many document formats can contain embedded documents,
     * including traditional container formats -- zip, tar and others -- but also
     * common office document formats including: MSWord, MSExcel,
     * MSPowerPoint, RTF, PDF, MSG and several others.
     * <p>
     * The "content" format is determined by the ContentHandlerFactory, and
     * the content is stored in {@link org.apache.tika.parser.RecursiveParserWrapper#TIKA_CONTENT}
     * <p>
     * The drawback to the RecursiveParserWrapper is that it caches metadata and contents
     * in memory.  This should not be used on files whose contents are too big to be handled
     * in memory.
     *
     * @return a list of metadata object, one each for the container file and each embedded file
     * @throws IOException
     * @throws SAXException
     * @throws TikaException
     */
public List<Metadata> recursiveParserWrapperExample() throws IOException, SAXException, TikaException {
    Parser p = new AutoDetectParser();
    ContentHandlerFactory factory = new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.HTML, -1);
    RecursiveParserWrapper wrapper = new RecursiveParserWrapper(p, factory);
    Metadata metadata = new Metadata();
    metadata.set(Metadata.RESOURCE_NAME_KEY, "test_recursive_embedded.docx");
    ParseContext context = new ParseContext();
    try (InputStream stream = ParsingExample.class.getResourceAsStream("test_recursive_embedded.docx")) {
        wrapper.parse(stream, new DefaultHandler(), metadata, context);
    }
    return wrapper.getMetadata();
}

Example 22 with BasicContentHandlerFactory

use of org.apache.tika.sax.BasicContentHandlerFactory in project tika by apache.

the class PDFParserTest method testEmbeddedFilesInChildren.

// TIKA-1228, TIKA-1268
@Test
public void testEmbeddedFilesInChildren() throws Exception {
    String xml = getXML("/testPDF_childAttachments.pdf").xml;
    //"regressiveness" exists only in Unit10.doc not in the container pdf document
    assertTrue(xml.contains("regressiveness"));
    RecursiveParserWrapper p = new RecursiveParserWrapper(new AutoDetectParser(), new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.IGNORE, -1));
    ParseContext context = new ParseContext();
    PDFParserConfig config = new PDFParserConfig();
    config.setExtractInlineImages(true);
    config.setExtractUniqueInlineImagesOnly(false);
    context.set(org.apache.tika.parser.pdf.PDFParserConfig.class, config);
    context.set(org.apache.tika.parser.Parser.class, p);
    try (TikaInputStream tis = TikaInputStream.get(getResourceAsStream("/test-documents/testPDF_childAttachments.pdf"))) {
        p.parse(tis, new BodyContentHandler(-1), new Metadata(), context);
    }
    List<Metadata> metadatas = p.getMetadata();
    assertEquals(5, metadatas.size());
    assertNull(metadatas.get(0).get(Metadata.RESOURCE_NAME_KEY));
    assertEquals("image0.jpg", metadatas.get(1).get(Metadata.RESOURCE_NAME_KEY));
    assertEquals("Press Quality(1).joboptions", metadatas.get(3).get(Metadata.RESOURCE_NAME_KEY));
    assertEquals("Unit10.doc", metadatas.get(4).get(Metadata.RESOURCE_NAME_KEY));
    assertEquals(MediaType.image("jpeg").toString(), metadatas.get(1).get(Metadata.CONTENT_TYPE));
    assertEquals(MediaType.image("tiff").toString(), metadatas.get(2).get(Metadata.CONTENT_TYPE));
    assertEquals("text/plain; charset=ISO-8859-1", metadatas.get(3).get(Metadata.CONTENT_TYPE));
    assertEquals(TYPE_DOC.toString(), metadatas.get(4).get(Metadata.CONTENT_TYPE));
}