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

Example 61 with AutoDetectParser

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

the class TIAParsingExample method testTeeContentHandler.

public static void testTeeContentHandler(String filename) throws Exception {
    InputStream stream = new ByteArrayInputStream(new byte[0]);
    Metadata metadata = new Metadata();
    ParseContext context = new ParseContext();
    Parser parser = new AutoDetectParser();
    LinkContentHandler linkCollector = new LinkContentHandler();
    try (OutputStream output = new FileOutputStream(new File(filename))) {
        ContentHandler handler = new TeeContentHandler(new BodyContentHandler(output), linkCollector);
        parser.parse(stream, handler, metadata, context);
    }
}

Example 62 with AutoDetectParser

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

the class PhoneExtractingContentHandlerTest method testExtractPhoneNumbers.

@Test
public void testExtractPhoneNumbers() throws Exception {
    Parser parser = new AutoDetectParser();
    Metadata metadata = new Metadata();
    // The PhoneExtractingContentHandler will examine any characters for phone numbers before passing them
    // to the underlying Handler.
    PhoneExtractingContentHandler handler = new PhoneExtractingContentHandler(new BodyContentHandler(), metadata);
    try (InputStream stream = PhoneExtractingContentHandlerTest.class.getResourceAsStream("/test-documents/testPhoneNumberExtractor.odt")) {
        parser.parse(stream, handler, metadata, new ParseContext());
    }
    String[] phoneNumbers = metadata.getValues("phonenumbers");
    assertContains("9498888888", phoneNumbers[0]);
    assertContains("9497777777", phoneNumbers[1]);
    assertContains("9496666666", phoneNumbers[2]);
    assertContains("9495555555", phoneNumbers[3]);
    assertContains("4193404645", phoneNumbers[4]);
    assertContains("9044687081", phoneNumbers[5]);
    assertContains("2604094811", phoneNumbers[6]);
}

Example 63 with AutoDetectParser

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

the class RTFParserTest method testConfig.

@Test
public void testConfig() throws Exception {
    //test that memory allocation of the bin element is limited
    //via the config file.  Unfortunately, this test file's bin embedding contains 10 bytes
    //so we had to set the config to 0.
    InputStream is = getClass().getResourceAsStream("/org/apache/tika/parser/rtf/tika-config.xml");
    assertNotNull(is);
    TikaConfig tikaConfig = new TikaConfig(is);
    Parser p = new AutoDetectParser(tikaConfig);
    List<Metadata> metadataList = getRecursiveMetadata("testBinControlWord.rtf", p);
    assertEquals(1, metadataList.size());
    assertContains("TikaMemoryLimitException", metadataList.get(0).get(TikaCoreProperties.TIKA_META_EXCEPTION_EMBEDDED_STREAM));
}

Example 64 with AutoDetectParser

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

the class Seven7ParserTest method test7ZParsing.

@Test
public void test7ZParsing() throws Exception {
    // Should auto-detect!
    Parser parser = new AutoDetectParser();
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    // Ensure 7zip is a parsable format
    assertTrue("No 7zip parser found", parser.getSupportedTypes(recursingContext).contains(TYPE_7ZIP));
    // Parse
    try (InputStream stream = Seven7ParserTest.class.getResourceAsStream("/test-documents/test-documents.7z")) {
        parser.parse(stream, handler, metadata, recursingContext);
    }
    assertEquals(TYPE_7ZIP.toString(), 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 65 with AutoDetectParser

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

the class Seven7ParserTest 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 = Seven7ParserTest.class.getResourceAsStream("/test-documents/test-documents.7z")) {
        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 7z 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 mod : tracker.modifiedAts) {
        assertNotNull(mod);
        assertTrue("Modified at " + mod, mod.startsWith("20"));
    }
}