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

Example 91 with AutoDetectParser

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

the class ODFParserTest method testODSFooter.

@Test
public void testODSFooter() throws Exception {
    try (InputStream input = ODFParserTest.class.getResourceAsStream("/test-documents/testFooter.ods")) {
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler();
        new AutoDetectParser().parse(input, handler, metadata);
        String content = handler.toString();
        assertContains("Here is a footer in the center area", content);
    }
}

Example 92 with AutoDetectParser

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

the class PDFParserTest method testProtectedPDF.

/**
     * PDFs can be "protected" with the default password. This means
     * they're encrypted (potentially both text and metadata),
     * but we can decrypt them easily.
     */
@Test
public void testProtectedPDF() throws Exception {
    XMLResult r = getXML("testPDF_protected.pdf");
    Metadata metadata = r.metadata;
    assertEquals("true", metadata.get("pdf:encrypted"));
    assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE));
    assertEquals("The Bank of England", metadata.get(TikaCoreProperties.CREATOR));
    assertEquals("The Bank of England", metadata.get(Metadata.AUTHOR));
    assertEquals("Speeches by Andrew G Haldane", metadata.get(OfficeOpenXMLCore.SUBJECT));
    assertEquals("Speeches by Andrew G Haldane", metadata.get(Metadata.SUBJECT));
    assertEquals("Rethinking the Financial Network, Speech by Andrew G Haldane, Executive Director, Financial Stability delivered at the Financial Student Association, Amsterdam on 28 April 2009", metadata.get(TikaCoreProperties.TITLE));
    assertContains("RETHINKING THE FINANCIAL NETWORK", r.xml);
    assertContains("On 16 November 2002", r.xml);
    assertContains("In many important respects", r.xml);
    // Try again with an explicit empty password
    ParseContext context = new ParseContext();
    context.set(PasswordProvider.class, new PasswordProvider() {

        public String getPassword(Metadata metadata) {
            return "";
        }
    });
    r = getXML("testPDF_protected.pdf", context);
    metadata = r.metadata;
    assertEquals("true", metadata.get("pdf:encrypted"));
    assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE));
    assertEquals("The Bank of England", metadata.get(TikaCoreProperties.CREATOR));
    assertEquals("Speeches by Andrew G Haldane", metadata.get(OfficeOpenXMLCore.SUBJECT));
    assertEquals("Speeches by Andrew G Haldane", metadata.get(Metadata.SUBJECT));
    assertEquals("Rethinking the Financial Network, Speech by Andrew G Haldane, Executive Director, Financial Stability delivered at the Financial Student Association, Amsterdam on 28 April 2009", metadata.get(TikaCoreProperties.TITLE));
    assertContains("RETHINKING THE FINANCIAL NETWORK", r.xml);
    assertContains("On 16 November 2002", r.xml);
    assertContains("In many important respects", r.xml);
    //now test wrong password
    context.set(PasswordProvider.class, new PasswordProvider() {

        public String getPassword(Metadata metadata) {
            return "WRONG!!!!";
        }
    });
    boolean ex = false;
    ContentHandler handler = new BodyContentHandler();
    metadata = new Metadata();
    try (InputStream stream = PDFParserTest.class.getResourceAsStream("/test-documents/testPDF_protected.pdf")) {
        Parser parser = new AutoDetectParser();
        parser.parse(stream, handler, metadata, context);
    } catch (EncryptedDocumentException e) {
        ex = true;
    }
    assertTrue("encryption exception", ex);
    assertEquals("application/pdf", metadata.get(Metadata.CONTENT_TYPE));
    assertEquals("true", metadata.get("pdf:encrypted"));
    //pdf:encrypted, X-Parsed-By and Content-Type
    assertEquals("very little metadata should be parsed", 3, metadata.names().length);
    assertEquals(0, handler.toString().length());
}

Example 93 with AutoDetectParser

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

the class RarParserTest method testEmbedded.

/**
     * Tests that the ParseContext parser is correctly
     *  fired for all the embedded entries.
     */
@Test
public void testEmbedded() throws Exception {
    // Should auto-detect!
    Parser parser = new AutoDetectParser();
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    try (InputStream stream = RarParserTest.class.getResourceAsStream("/test-documents/test-documents.rar")) {
        parser.parse(stream, handler, metadata, trackingContext);
    }
    // Should have found all 9 documents, but not the directory
    assertEquals(9, tracker.filenames.size());
    assertEquals(9, tracker.mediatypes.size());
    assertEquals(9, tracker.modifiedAts.size());
    // Should have names but not content types, as rar doesn't
    //  store the content types
    assertEquals("test-documents/testEXCEL.xls", tracker.filenames.get(0));
    assertEquals("test-documents/testHTML.html", tracker.filenames.get(1));
    assertEquals("test-documents/testOpenOffice2.odt", tracker.filenames.get(2));
    assertEquals("test-documents/testPDF.pdf", tracker.filenames.get(3));
    assertEquals("test-documents/testPPT.ppt", tracker.filenames.get(4));
    assertEquals("test-documents/testRTF.rtf", tracker.filenames.get(5));
    assertEquals("test-documents/testTXT.txt", tracker.filenames.get(6));
    assertEquals("test-documents/testWORD.doc", tracker.filenames.get(7));
    assertEquals("test-documents/testXML.xml", tracker.filenames.get(8));
    for (String type : tracker.mediatypes) {
        assertNull(type);
    }
    for (String crt : tracker.createdAts) {
        assertNull(crt);
    }
    for (String mod : tracker.modifiedAts) {
        assertNotNull(mod);
        assertTrue("Modified at " + mod, mod.startsWith("20"));
    }
    // Should have filenames in the content string
    String content = handler.toString();
    assertContains("test-documents/testHTML.html", content);
    assertContains("test-documents/testEXCEL.xls", content);
    assertContains("test-documents/testOpenOffice2.odt", content);
    assertContains("test-documents/testPDF.pdf", content);
    assertContains("test-documents/testPPT.ppt", content);
    assertContains("test-documents/testRTF.rtf", content);
    assertContains("test-documents/testTXT.txt", content);
    assertContains("test-documents/testWORD.doc", content);
    assertContains("test-documents/testXML.xml", content);
}

Example 94 with AutoDetectParser

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

the class RarParserTest method testRarParsing.

@Test
public void testRarParsing() throws Exception {
    // Should auto-detect!
    Parser parser = new AutoDetectParser();
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    try (InputStream stream = RarParserTest.class.getResourceAsStream("/test-documents/test-documents.rar")) {
        parser.parse(stream, handler, metadata, recursingContext);
    }
    assertEquals("application/x-rar-compressed", metadata.get(Metadata.CONTENT_TYPE));
    String content = handler.toString();
    assertContains("test-documents/testEXCEL.xls", content);
    assertContains("Sample Excel Worksheet", content);
    assertContains("test-documents/testHTML.html", content);
    assertContains("Test Indexation Html", content);
    assertContains("test-documents/testOpenOffice2.odt", content);
    assertContains("This is a sample Open Office document", content);
    assertContains("test-documents/testPDF.pdf", content);
    assertContains("Apache Tika", content);
    assertContains("test-documents/testPPT.ppt", content);
    assertContains("Sample Powerpoint Slide", content);
    assertContains("test-documents/testRTF.rtf", content);
    assertContains("indexation Word", content);
    assertContains("test-documents/testTXT.txt", content);
    assertContains("Test d'indexation de Txt", content);
    assertContains("test-documents/testWORD.doc", content);
    assertContains("This is a sample Microsoft Word Document", content);
    assertContains("test-documents/testXML.xml", content);
    assertContains("Rida Benjelloun", content);
}

Example 95 with AutoDetectParser

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

the class TarParserTest method testTarParsing.

@Test
public void testTarParsing() throws Exception {
    // Should auto-detect!
    Parser parser = new AutoDetectParser();
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    try (InputStream stream = TarParserTest.class.getResourceAsStream("/test-documents/test-documents.tar")) {
        parser.parse(stream, handler, metadata, recursingContext);
    }
    assertEquals("application/x-gtar", metadata.get(Metadata.CONTENT_TYPE));
    String content = handler.toString();
    assertContains("test-documents/testEXCEL.xls", content);
    assertContains("Sample Excel Worksheet", content);
    assertContains("test-documents/testHTML.html", content);
    assertContains("Test Indexation Html", content);
    assertContains("test-documents/testOpenOffice2.odt", content);
    assertContains("This is a sample Open Office document", content);
    assertContains("test-documents/testPDF.pdf", content);
    assertContains("Apache Tika", content);
    assertContains("test-documents/testPPT.ppt", content);
    assertContains("Sample Powerpoint Slide", content);
    assertContains("test-documents/testRTF.rtf", content);
    assertContains("indexation Word", content);
    assertContains("test-documents/testTXT.txt", content);
    assertContains("Test d'indexation de Txt", content);
    assertContains("test-documents/testWORD.doc", content);
    assertContains("This is a sample Microsoft Word Document", content);
    assertContains("test-documents/testXML.xml", content);
    assertContains("Rida Benjelloun", content);
}