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

Example 1 with EmbeddedDocumentExtractor

use of org.apache.tika.extractor.EmbeddedDocumentExtractor 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 2 with EmbeddedDocumentExtractor

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

the class MockParser method handleEmbedded.

private void handleEmbedded(Node action, XHTMLContentHandler handler, ParseContext context) throws TikaException, SAXException, IOException {
    String fileName = "";
    String contentType = "";
    NamedNodeMap attrs = action.getAttributes();
    if (attrs != null) {
        Node n = attrs.getNamedItem("filename");
        if (n != null) {
            fileName = n.getNodeValue();
        }
        n = attrs.getNamedItem("content-type");
        if (n != null) {
            contentType = n.getNodeValue();
        }
    }
    String embeddedText = action.getTextContent();
    EmbeddedDocumentExtractor extractor = getEmbeddedDocumentExtractor(context);
    Metadata m = new Metadata();
    m.set(TikaMetadataKeys.RESOURCE_NAME_KEY, fileName);
    if (!"".equals(contentType)) {
        m.set(Metadata.CONTENT_TYPE, contentType);
    }
    InputStream is = new ByteArrayInputStream(embeddedText.getBytes(UTF_8));
    extractor.parseEmbedded(is, new EmbeddedContentHandler(handler), m, true);
}

Example 3 with EmbeddedDocumentExtractor

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

the class RarParser method parse.

@Override
public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, SAXException, TikaException {
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    EmbeddedDocumentExtractor extractor = EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
    Archive rar = null;
    try (TemporaryResources tmp = new TemporaryResources()) {
        TikaInputStream tis = TikaInputStream.get(stream, tmp);
        rar = new Archive(tis.getFile());
        if (rar.isEncrypted()) {
            throw new EncryptedDocumentException();
        }
        //Without this BodyContentHandler does not work
        xhtml.element("div", " ");
        FileHeader header = rar.nextFileHeader();
        while (header != null && !Thread.currentThread().isInterrupted()) {
            if (!header.isDirectory()) {
                try (InputStream subFile = rar.getInputStream(header)) {
                    Metadata entrydata = PackageParser.handleEntryMetadata("".equals(header.getFileNameW()) ? header.getFileNameString() : header.getFileNameW(), header.getCTime(), header.getMTime(), header.getFullUnpackSize(), xhtml);
                    if (extractor.shouldParseEmbedded(entrydata)) {
                        extractor.parseEmbedded(subFile, handler, entrydata, true);
                    }
                }
            }
            header = rar.nextFileHeader();
        }
    } catch (RarException e) {
        throw new TikaException("RarParser Exception", e);
    } finally {
        if (rar != null)
            rar.close();
    }
    xhtml.endDocument();
}

Example 4 with EmbeddedDocumentExtractor

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

the class RFC822ParserTest method testExtractAttachments.

@Test
public void testExtractAttachments() throws Exception {
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    Parser p = new RFC822Parser();
    ParseContext context = new ParseContext();
    try (InputStream stream = getStream("test-documents/testEmailWithPNGAtt.eml")) {
        p.parse(stream, handler, metadata, context);
    }
    // Check we go the metadata
    assertEquals("Tika Test <XXXX@apache.org>", metadata.get(Metadata.MESSAGE_FROM));
    assertEquals("Test Attachment Email", metadata.get(TikaCoreProperties.TITLE));
    // Try again with attachment detecting and fetching
    final Detector detector = new DefaultDetector();
    final Parser extParser = new AutoDetectParser();
    final List<MediaType> seenTypes = new ArrayList<MediaType>();
    final List<String> seenText = new ArrayList<String>();
    EmbeddedDocumentExtractor ext = new EmbeddedDocumentExtractor() {

        @Override
        public boolean shouldParseEmbedded(Metadata metadata) {
            return true;
        }

        @Override
        public void parseEmbedded(InputStream stream, ContentHandler handler, Metadata metadata, boolean outputHtml) throws SAXException, IOException {
            seenTypes.add(detector.detect(stream, metadata));
            ContentHandler h = new BodyContentHandler();
            try {
                extParser.parse(stream, h, metadata, new ParseContext());
            } catch (TikaException e) {
                throw new RuntimeException(e);
            }
            seenText.add(h.toString());
        }
    };
    context.set(EmbeddedDocumentExtractor.class, ext);
    try (InputStream stream = getStream("test-documents/testEmailWithPNGAtt.eml")) {
        p.parse(stream, handler, metadata, context);
    }
    // Check we go the metadata
    assertEquals("Tika Test <XXXX@apache.org>", metadata.get(Metadata.MESSAGE_FROM));
    assertEquals("Test Attachment Email", metadata.get(TikaCoreProperties.TITLE));
    // Check attachments
    assertEquals(2, seenTypes.size());
    assertEquals(2, seenText.size());
    assertEquals("text/plain", seenTypes.get(0).toString());
    assertEquals("image/png", seenTypes.get(1).toString());
    assertEquals("This email has a PNG attachment included in it\n\n", seenText.get(0));
}

Example 5 with EmbeddedDocumentExtractor

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

the class MboxParser method parse.

public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context) throws IOException, TikaException, SAXException {
    EmbeddedDocumentExtractor extractor = EmbeddedDocumentUtil.getEmbeddedDocumentExtractor(context);
    String charsetName = "windows-1252";
    metadata.set(Metadata.CONTENT_TYPE, MBOX_MIME_TYPE);
    metadata.set(Metadata.CONTENT_ENCODING, charsetName);
    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();
    InputStreamReader isr = new InputStreamReader(stream, charsetName);
    try (BufferedReader reader = new BufferedReader(isr)) {
        String curLine = reader.readLine();
        int mailItem = 0;
        do {
            if (curLine.startsWith(MBOX_RECORD_DIVIDER)) {
                Metadata mailMetadata = new Metadata();
                Queue<String> multiline = new LinkedList<String>();
                mailMetadata.add(EMAIL_FROMLINE_METADATA, curLine.substring(MBOX_RECORD_DIVIDER.length()));
                mailMetadata.set(Metadata.CONTENT_TYPE, "message/rfc822");
                curLine = reader.readLine();
                if (curLine == null) {
                    break;
                }
                ByteArrayOutputStream message = new ByteArrayOutputStream(100000);
                do {
                    if (curLine.startsWith(" ") || curLine.startsWith("\t")) {
                        String latestLine = multiline.poll();
                        latestLine += " " + curLine.trim();
                        multiline.add(latestLine);
                    } else {
                        multiline.add(curLine);
                    }
                    message.write(curLine.getBytes(charsetName));
                    message.write(0x0A);
                    curLine = reader.readLine();
                } while (curLine != null && !curLine.startsWith(MBOX_RECORD_DIVIDER) && message.size() < MAIL_MAX_SIZE);
                for (String item : multiline) {
                    saveHeaderInMetadata(mailMetadata, item);
                }
                ByteArrayInputStream messageStream = new ByteArrayInputStream(message.toByteArray());
                message = null;
                if (extractor.shouldParseEmbedded(mailMetadata)) {
                    extractor.parseEmbedded(messageStream, xhtml, mailMetadata, true);
                }
                if (tracking) {
                    getTrackingMetadata().put(mailItem++, mailMetadata);
                }
            } else {
                curLine = reader.readLine();
            }
        } while (curLine != null && !Thread.currentThread().isInterrupted());
    }
    xhtml.endDocument();
}