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

Example 1 with BasicContentHandlerFactory

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

the class TikaTest method getRecursiveMetadata.

protected List<Metadata> getRecursiveMetadata(String filePath, ParseContext context) throws Exception {
    Parser p = new AutoDetectParser();
    RecursiveParserWrapper wrapper = new RecursiveParserWrapper(p, new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.XML, -1));
    try (InputStream is = getResourceAsStream("/test-documents/" + filePath)) {
        wrapper.parse(is, new DefaultHandler(), new Metadata(), context);
    }
    return wrapper.getMetadata();
}

Example 2 with BasicContentHandlerFactory

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

the class RecursiveParserWrapperTest method testCharLimit.

@Test
public void testCharLimit() throws Exception {
    ParseContext context = new ParseContext();
    Metadata metadata = new Metadata();
    Parser wrapped = new AutoDetectParser();
    RecursiveParserWrapper wrapper = new RecursiveParserWrapper(wrapped, new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.TEXT, 60));
    InputStream stream = RecursiveParserWrapperTest.class.getResourceAsStream("/test-documents/test_recursive_embedded.docx");
    wrapper.parse(stream, new DefaultHandler(), metadata, context);
    List<Metadata> list = wrapper.getMetadata();
    assertEquals(5, list.size());
    int wlr = 0;
    for (Metadata m : list) {
        String limitReached = m.get(RecursiveParserWrapper.WRITE_LIMIT_REACHED);
        if (limitReached != null && limitReached.equals("true")) {
            wlr++;
        }
    }
    assertEquals(1, wlr);
}

Example 3 with BasicContentHandlerFactory

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

the class RecursiveParserWrapperTest method testBasicHTML.

@Test
public void testBasicHTML() throws Exception {
    List<Metadata> list = getMetadata(new Metadata(), new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.HTML, -1));
    Metadata container = list.get(0);
    String content = container.get(RecursiveParserWrapper.TIKA_CONTENT);
    //not much differentiates html from xml in this test file
    assertTrue(content.indexOf("<p class=\"header\"></p>") > -1);
}

Example 4 with BasicContentHandlerFactory

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

the class RecursiveParserWrapperTest method testIgnoreContent.

@Test
public void testIgnoreContent() throws Exception {
    List<Metadata> list = getMetadata(new Metadata(), new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.IGNORE, -1));
    Metadata container = list.get(0);
    String content = container.get(RecursiveParserWrapper.TIKA_CONTENT);
    assertNull(content);
}

Example 5 with BasicContentHandlerFactory

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

the class RecursiveParserWrapperTest method testEmbeddedResourcePath.

@Test
public void testEmbeddedResourcePath() throws Exception {
    Set<String> targets = new HashSet<String>();
    targets.add("/embed1.zip");
    targets.add("/embed1.zip/embed2.zip");
    targets.add("/embed1.zip/embed2.zip/embed3.zip");
    targets.add("/embed1.zip/embed2.zip/embed3.zip/embed4.zip");
    targets.add("/embed1.zip/embed2.zip/embed3.zip/embed4.zip/embed4.txt");
    targets.add("/embed1.zip/embed2.zip/embed3.zip/embed3.txt");
    targets.add("/embed1.zip/embed2.zip/embed2a.txt");
    targets.add("/embed1.zip/embed2.zip/embed2b.txt");
    targets.add("/embed1.zip/embed1b.txt");
    targets.add("/embed1.zip/embed1a.txt");
    targets.add("/image1.emf");
    Metadata metadata = new Metadata();
    metadata.set(Metadata.RESOURCE_NAME_KEY, "test_recursive_embedded.docx");
    List<Metadata> list = getMetadata(metadata, new BasicContentHandlerFactory(BasicContentHandlerFactory.HANDLER_TYPE.XML, -1));
    Metadata container = list.get(0);
    String content = container.get(RecursiveParserWrapper.TIKA_CONTENT);
    assertTrue(content.indexOf("<p class=\"header\" />") > -1);
    Set<String> seen = new HashSet<String>();
    for (Metadata m : list) {
        String path = m.get(RecursiveParserWrapper.EMBEDDED_RESOURCE_PATH);
        if (path != null) {
            seen.add(path);
        }
    }
    assertEquals(targets, seen);
}