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

Example 6 with BodyContentHandler

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

the class ParsingExample method parseEmbeddedExample.

/**
     * This example shows how to extract content from the outer document and all
     * embedded documents.  The key is to specify a {@link Parser} in the {@link ParseContext}.
     *
     * @return content, including from embedded documents
     * @throws IOException
     * @throws SAXException
     * @throws TikaException
     */
public String parseEmbeddedExample() throws IOException, SAXException, TikaException {
    AutoDetectParser parser = new AutoDetectParser();
    BodyContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    ParseContext context = new ParseContext();
    context.set(Parser.class, parser);
    try (InputStream stream = ParsingExample.class.getResourceAsStream("test_recursive_embedded.docx")) {
        parser.parse(stream, handler, metadata, context);
        return handler.toString();
    }
}

Example 7 with BodyContentHandler

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

the class ExtractEmbeddedFiles method extract.

public void extract(InputStream is, Path outputDir) throws SAXException, TikaException, IOException {
    Metadata m = new Metadata();
    ParseContext c = new ParseContext();
    ContentHandler h = new BodyContentHandler(-1);
    c.set(Parser.class, parser);
    EmbeddedDocumentExtractor ex = new MyEmbeddedDocumentExtractor(outputDir, c);
    c.set(EmbeddedDocumentExtractor.class, ex);
    parser.parse(is, h, m, c);
}

Example 8 with BodyContentHandler

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

the class ContentHandlerExample method parseBodyToHTML.

/**
     * Example of extracting just the body as HTML, without the
     * head part, as a string
     */
public String parseBodyToHTML() throws IOException, SAXException, TikaException {
    ContentHandler handler = new BodyContentHandler(new ToXMLContentHandler());
    AutoDetectParser parser = new AutoDetectParser();
    Metadata metadata = new Metadata();
    try (InputStream stream = ContentHandlerExample.class.getResourceAsStream("test.doc")) {
        parser.parse(stream, handler, metadata);
        return handler.toString();
    }
}

Example 9 with BodyContentHandler

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

the class DisplayMetInstance method getMet.

public static Metadata getMet(URL url) throws IOException, SAXException, TikaException {
    Metadata met = new Metadata();
    PDFParser parser = new PDFParser();
    parser.parse(url.openStream(), new BodyContentHandler(), met, new ParseContext());
    return met;
}

Example 10 with BodyContentHandler

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

the class FontParsersTest method testTTFParsing.

@Test
public void testTTFParsing() throws Exception {
    // Should auto-detect!
    Parser parser = new AutoDetectParser();
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    ParseContext context = new ParseContext();
    try (TikaInputStream stream = TikaInputStream.get(FontParsersTest.class.getResource("/test-documents/testTrueType3.ttf"))) {
        parser.parse(stream, handler, metadata, context);
    }
    assertEquals("application/x-font-ttf", metadata.get(Metadata.CONTENT_TYPE));
    assertEquals("Open Sans Bold", metadata.get(TikaCoreProperties.TITLE));
    assertEquals("2010-12-30T11:04:00Z", metadata.get(Metadata.CREATION_DATE));
    assertEquals("2010-12-30T11:04:00Z", metadata.get(TikaCoreProperties.CREATED));
    assertEquals("2011-05-05T12:37:53Z", metadata.get(TikaCoreProperties.MODIFIED));
    assertEquals("Open Sans Bold", metadata.get(MET_FONT_NAME));
    assertEquals("Open Sans", metadata.get(MET_FONT_FAMILY_NAME));
    assertEquals("Bold", metadata.get(MET_FONT_SUB_FAMILY_NAME));
    assertEquals("OpenSans-Bold", metadata.get(MET_PS_NAME));
    assertEquals("Digitized", metadata.get("Copyright").substring(0, 9));
    assertEquals("Open Sans", metadata.get("Trademark").substring(0, 9));
    // Not extracted
    assertEquals(null, metadata.get(MET_FONT_FULL_NAME));
    assertEquals(null, metadata.get(MET_FONT_WEIGHT));
    assertEquals(null, metadata.get(MET_FONT_VERSION));
    // Currently, the parser doesn't extract any contents
    String content = handler.toString();
    assertEquals("", content);
}