Examples with ContainerExtractor org.apache.tika.extractor.ContainerExtractor used on opensource projects

Example 1 with ContainerExtractor

use of org.apache.tika.extractor.ContainerExtractor in project tika by apache.

the class FictionBookParserTest method testEmbedded.

@Test
public void testEmbedded() throws Exception {
    try (InputStream input = FictionBookParserTest.class.getResourceAsStream("/test-documents/test.fb2")) {
        ContainerExtractor extractor = new ParserContainerExtractor();
        TikaInputStream stream = TikaInputStream.get(input);
        assertEquals(true, extractor.isSupported(stream));
        // Process it
        TrackingHandler handler = new TrackingHandler();
        extractor.extract(stream, null, handler);
        assertEquals(2, handler.filenames.size());
    }
}

Example 2 with ContainerExtractor

use of org.apache.tika.extractor.ContainerExtractor in project tika by apache.

the class POIContainerExtractionTest method testEmbeddedOfficeFilesXML.

@Test
public void testEmbeddedOfficeFilesXML() throws Exception {
    ContainerExtractor extractor = new ParserContainerExtractor();
    TrackingHandler handler;
    handler = process("EmbeddedDocument.docx", extractor, false);
    assertTrue(handler.filenames.contains("Microsoft_Office_Excel_97-2003_Worksheet1.bin"));
    assertEquals(2, handler.filenames.size());
}

Example 3 with ContainerExtractor

use of org.apache.tika.extractor.ContainerExtractor in project tika by apache.

the class TNEFParserTest method testBodyAndAttachments.

/**
     * Check the Rtf and Attachments are returned
     * as expected
     */
@Test
public void testBodyAndAttachments() throws Exception {
    ContainerExtractor extractor = new ParserContainerExtractor();
    // Process it with recursing
    // Will have the message body RTF and the attachments
    TrackingHandler handler = process(file, extractor, true);
    assertEquals(6, handler.filenames.size());
    assertEquals(6, handler.mediaTypes.size());
    // We know the filenames for all of them
    assertEquals("message.rtf", handler.filenames.get(0));
    assertEquals(MediaType.application("rtf"), handler.mediaTypes.get(0));
    assertEquals("quick.doc", handler.filenames.get(1));
    assertEquals(MediaType.application("msword"), handler.mediaTypes.get(1));
    assertEquals("quick.html", handler.filenames.get(2));
    assertEquals(MediaType.text("html"), handler.mediaTypes.get(2));
    assertEquals("quick.pdf", handler.filenames.get(3));
    assertEquals(MediaType.application("pdf"), handler.mediaTypes.get(3));
    assertEquals("quick.txt", handler.filenames.get(4));
    assertEquals(MediaType.text("plain"), handler.mediaTypes.get(4));
    assertEquals("quick.xml", handler.filenames.get(5));
    assertEquals(MediaType.application("xml"), handler.mediaTypes.get(5));
}

Example 4 with ContainerExtractor

use of org.apache.tika.extractor.ContainerExtractor in project tika by apache.

the class PDFParserTest method testEmbeddedPDFEmbeddingAnotherDocument.

//TIKA-1124
@Test
public void testEmbeddedPDFEmbeddingAnotherDocument() throws Exception {
    /* format of test doc:
         docx/
            pdf/
               docx
       */
    String content = getXML("testPDFEmbeddingAndEmbedded.docx").xml;
    int outerHaystack = content.indexOf("Outer_haystack");
    int pdfHaystack = content.indexOf("pdf_haystack");
    int needle = content.indexOf("Needle");
    assertTrue(outerHaystack > -1);
    assertTrue(pdfHaystack > -1);
    assertTrue(needle > -1);
    assertTrue(needle > pdfHaystack && pdfHaystack > outerHaystack);
    TrackingHandler tracker = new TrackingHandler();
    ContainerExtractor ex = new ParserContainerExtractor();
    try (TikaInputStream tis = TikaInputStream.get(getResourceAsStream("/test-documents/testPDFEmbeddingAndEmbedded.docx"))) {
        ex.extract(tis, ex, tracker);
    }
    assertEquals(3, tracker.filenames.size());
    assertEquals(3, tracker.mediaTypes.size());
    assertEquals("image1.emf", tracker.filenames.get(0));
    assertNull(tracker.filenames.get(1));
    assertEquals("Test.docx", tracker.filenames.get(2));
    assertEquals(TYPE_EMF, tracker.mediaTypes.get(0));
    assertEquals(TYPE_PDF, tracker.mediaTypes.get(1));
    assertEquals(TYPE_DOCX, tracker.mediaTypes.get(2));
}

Example 5 with ContainerExtractor

use of org.apache.tika.extractor.ContainerExtractor in project tika by apache.

the class RFC822ParserTest method testGetAttachmentsAsEmbeddedResources.

/**
     * TIKA-1222 When requested, ensure that the various attachments of
     * the mail come through properly as embedded resources
     */
@Test
public void testGetAttachmentsAsEmbeddedResources() throws Exception {
    TrackingHandler tracker = new TrackingHandler();
    ContainerExtractor ex = new ParserContainerExtractor();
    try (TikaInputStream tis = TikaInputStream.get(getStream("test-documents/testRFC822-multipart"))) {
        assertEquals(true, ex.isSupported(tis));
        ex.extract(tis, ex, tracker);
    }
    // Check we found all 3 parts
    assertEquals(3, tracker.filenames.size());
    assertEquals(3, tracker.mediaTypes.size());
    // No filenames available
    assertEquals(null, tracker.filenames.get(0));
    assertEquals(null, tracker.filenames.get(1));
    assertEquals(null, tracker.filenames.get(2));
    // Types are available
    assertEquals(MediaType.TEXT_PLAIN, tracker.mediaTypes.get(0));
    assertEquals(MediaType.TEXT_HTML, tracker.mediaTypes.get(1));
    assertEquals(MediaType.image("gif"), tracker.mediaTypes.get(2));
}