Example usage for org.apache.poi.poifs.filesystem DirectoryNode getEntry

List of usage examples for org.apache.poi.poifs.filesystem DirectoryNode getEntry

  1. HOME
  2. Java
  3. org.apache.poi
  4. org.apache.poi.poifs.filesystem.*
  5. DirectoryNode
  6. getEntry

Introduction

In this page you can find the example usage for org.apache.poi.poifs.filesystem DirectoryNode getEntry.

Prototype


public Entry getEntry(final String name) throws FileNotFoundException

Source Link

Document

get a specified Entry by name

Usage

From source file:NewEmptyJUnitTest.java

/**
 * Test that we can get data from two different
 *  embeded word documents//w w  w.  j a  v a 2  s  . c o m
 * @throws Exception
 */
public void testExtractFromEmbeded() throws Exception {
    POIFSFileSystem fs = new POIFSFileSystem(
            POIDataSamples.getSpreadSheetInstance().openResourceAsStream(filename3));
    HWPFDocument doc;
    WordExtractor extractor3;

    DirectoryNode dirA = (DirectoryNode) fs.getRoot().getEntry("MBD0000A3B7");
    DirectoryNode dirB = (DirectoryNode) fs.getRoot().getEntry("MBD0000A3B2");

    // Should have WordDocument and 1Table
    assertNotNull(dirA.getEntry("1Table"));
    assertNotNull(dirA.getEntry("WordDocument"));

    assertNotNull(dirB.getEntry("1Table"));
    assertNotNull(dirB.getEntry("WordDocument"));

    // Check each in turn
    doc = new HWPFDocument(dirA, fs);
    extractor3 = new WordExtractor(doc);

    assertNotNull(extractor3.getText());
    assertTrue(extractor3.getText().length() > 20);
    assertEquals("I am a sample document\r\nNot much on me\r\nI am document 1\r\n", extractor3.getText());
    assertEquals("Sample Doc 1", extractor3.getSummaryInformation().getTitle());
    assertEquals("Sample Test", extractor3.getSummaryInformation().getSubject());

    doc = new HWPFDocument(dirB, fs);
    extractor3 = new WordExtractor(doc);

    assertNotNull(extractor3.getText());
    assertTrue(extractor3.getText().length() > 20);
    assertEquals("I am another sample document\r\nNot much on me\r\nI am document 2\r\n", extractor3.getText());
    assertEquals("Sample Doc 2", extractor3.getSummaryInformation().getTitle());
    assertEquals("Another Sample Test", extractor3.getSummaryInformation().getSubject());
}

From source file:com.argo.hwp.v5.HwpTextExtractorV5.java

License:Open Source License

/**
 * HWP? FileHeader //ww  w .j a v  a 2 s. c o m
 * 
 * @param fs
 * @return
 * @throws IOException
 */
private static FileHeader getHeader(NPOIFSFileSystem fs) throws IOException {
    DirectoryNode root = fs.getRoot();

    // ??? p.18

    // FileHeader  
    Entry headerEntry = root.getEntry("FileHeader");
    if (!headerEntry.isDocumentEntry())
        return null;

    //  ?
    byte[] header = new byte[256]; // FileHeader ? 256
    DocumentInputStream headerStream = new DocumentInputStream((DocumentEntry) headerEntry);
    try {
        int read = headerStream.read(header);
        if (read != 256
                || !Arrays.equals(HWP_V5_SIGNATURE, Arrays.copyOfRange(header, 0, HWP_V5_SIGNATURE.length)))
            return null;
    } finally {
        headerStream.close();
    }

    FileHeader fileHeader = new FileHeader();

    // . debug
    fileHeader.version = HwpVersion.parseVersion(LittleEndian.getUInt(header, 32));
    long flags = LittleEndian.getUInt(header, 36);
    log.debug("Flags={}", Long.toBinaryString(flags).replace(' ', '0'));

    fileHeader.compressed = (flags & 0x01) == 0x01;
    fileHeader.encrypted = (flags & 0x02) == 0x02;
    fileHeader.viewtext = (flags & 0x04) == 0x04;

    return fileHeader;
}

From source file:com.argo.hwp.v5.HwpTextExtractorV5.java

License:Open Source License

/**
 * ? /*from   w  w  w . j a v a  2s .c  o  m*/
 * 
 * @param writer
 * @param source
 * 
 * @return
 * @throws IOException
 */
private static void extractText(FileHeader header, NPOIFSFileSystem fs, Writer writer) throws IOException {
    DirectoryNode root = fs.getRoot();

    // BodyText ?
    Entry bodyText = root.getEntry("BodyText");
    if (bodyText == null || !bodyText.isDirectoryEntry())
        throw new IOException("Invalid BodyText");

    Iterator<Entry> iterator = ((DirectoryEntry) bodyText).getEntries();
    while (iterator.hasNext()) {
        Entry entry = iterator.next();
        if (entry.getName().startsWith("Section") && entry instanceof DocumentEntry) {
            log.debug("extract {}", entry.getName());

            InputStream input = new NDocumentInputStream((DocumentEntry) entry);
            if (header.compressed)
                input = new InflaterInputStream(input, new Inflater(true));

            HwpStreamReader sectionStream = new HwpStreamReader(input);

            try {
                extractText(sectionStream, writer);
            } finally {
                // ?  ? ?
                try {
                    input.close();
                } catch (IOException e) {
                    log.error("?   ??", e);
                }
            }
        } else {
            log.warn(" Entry '{}'({})", entry.getName(), entry);
        }
    }
}

From source file:com.ezdi.rtf.testRTFParser.RTFObjDataParser.java

License:Apache License

private byte[] handleEmbeddedPOIFS(InputStream is, Metadata metadata, AtomicInteger unknownFilenameCount)
        throws IOException {

    byte[] ret = null;
    try (NPOIFSFileSystem fs = new NPOIFSFileSystem(is)) {

        DirectoryNode root = fs.getRoot();

        if (root == null) {
            return ret;
        }/*  www . ja  v a  2  s .  c o m*/

        if (root.hasEntry("Package")) {
            Entry ooxml = root.getEntry("Package");
            TikaInputStream stream = TikaInputStream.get(new DocumentInputStream((DocumentEntry) ooxml));

            ByteArrayOutputStream out = new ByteArrayOutputStream();

            IOUtils.copy(stream, out);
            ret = out.toByteArray();
        } else {
            // try poifs
            POIFSDocumentType type = POIFSDocumentType.detectType(root);
            if (type == POIFSDocumentType.OLE10_NATIVE) {
                try {
                    // Try to un-wrap the OLE10Native record:
                    Ole10Native ole = Ole10Native.createFromEmbeddedOleObject(root);
                    ret = ole.getDataBuffer();
                } catch (Ole10NativeException ex) {
                    // Not a valid OLE10Native record, skip it
                }
            } else if (type == POIFSDocumentType.COMP_OBJ) {

                DocumentEntry contentsEntry;
                try {
                    contentsEntry = (DocumentEntry) root.getEntry("CONTENTS");
                } catch (FileNotFoundException ioe) {
                    contentsEntry = (DocumentEntry) root.getEntry("Contents");
                }

                try (DocumentInputStream inp = new DocumentInputStream(contentsEntry)) {
                    ret = new byte[contentsEntry.getSize()];
                    inp.readFully(ret);
                }
            } else {

                ByteArrayOutputStream out = new ByteArrayOutputStream();
                is.reset();
                IOUtils.copy(is, out);
                ret = out.toByteArray();
                metadata.set(Metadata.RESOURCE_NAME_KEY,
                        "file_" + unknownFilenameCount.getAndIncrement() + "." + type.getExtension());
                metadata.set(Metadata.CONTENT_TYPE, type.getType().toString());
            }
        }
    }
    return ret;
}

From source file:Coop.argo.hwp.v5.HwpTextExtractorV5.java

License:Apache License

/**
 * ? //from  w ww . j  av  a  2  s  .co  m
 * 
 * @param writer
 * @param source
 * 
 * @return
 * @throws IOException
 */
private static void extractBodyText(FileHeader header, NPOIFSFileSystem fs, Writer writer) throws IOException {
    DirectoryNode root = fs.getRoot();

    // BodyText ?
    Entry bodyText = root.getEntry("BodyText");
    if (bodyText == null || !bodyText.isDirectoryEntry())
        throw new IOException("Invalid BodyText");

    Iterator<Entry> iterator = ((DirectoryEntry) bodyText).getEntries();
    while (iterator.hasNext()) {
        Entry entry = iterator.next();
        if (entry.getName().startsWith("Section") && entry instanceof DocumentEntry) {
            log.debug("extract {}", entry.getName());

            InputStream input = new NDocumentInputStream((DocumentEntry) entry);
            try {
                if (header.compressed)
                    input = new InflaterInputStream(input, new Inflater(true));

                HwpStreamReader sectionStream = new HwpStreamReader(input);

                extractText(sectionStream, writer);
            } finally {
                // ?  ? ?
                try {
                    input.close();
                } catch (IOException e) {
                    log.error("?   ??", e);
                }
            }
        } else {
            log.warn(" Entry '{}'({})", entry.getName(), entry);
        }
    }
}

From source file:Coop.argo.hwp.v5.HwpTextExtractorV5.java

License:Apache License

/**
 * ? //from   ww w  .  j a va2 s.  c om
 * 
 * @param writer
 * @param source
 * 
 * @return
 * @throws IOException
 */
private static void extractViewText(FileHeader header, NPOIFSFileSystem fs, Writer writer) throws IOException {
    DirectoryNode root = fs.getRoot();

    // BodyText ?
    Entry bodyText = root.getEntry("ViewText");
    if (bodyText == null || !bodyText.isDirectoryEntry())
        throw new IOException("Invalid ViewText");

    Iterator<Entry> iterator = ((DirectoryEntry) bodyText).getEntries();
    while (iterator.hasNext()) {
        Entry entry = iterator.next();
        if (entry.getName().startsWith("Section") && entry instanceof DocumentEntry) {
            log.debug("extract {}", entry.getName());

            InputStream input = new NDocumentInputStream((DocumentEntry) entry);

            // FIXME   ?
            Key key = readKey(input);
            try {
                input = createDecryptStream(input, key);
                if (header.compressed)
                    input = new InflaterInputStream(input, new Inflater(true));

                HwpStreamReader sectionStream = new HwpStreamReader(input);
                extractText(sectionStream, writer);
            } catch (InvalidKeyException e) {
                throw new IOException(e);
            } catch (NoSuchAlgorithmException e) {
                throw new IOException(e);
            } catch (NoSuchPaddingException e) {
                throw new IOException(e);
            } finally {
                // ?  ? ?
                try {
                    input.close();
                } catch (IOException e) {
                    log.error("?   ??", e);
                }
            }
        } else {
            log.warn(" Entry '{}'({})", entry.getName(), entry);
        }
    }
}

From source file:mj.ocraptor.extraction.tika.parser.microsoft.SummaryExtractor.java

License:Apache License

private void parseSummaryEntryIfExists(DirectoryNode root, String entryName) throws IOException, TikaException {
    try {//from   ww  w.j a  va  2 s . co  m
        DocumentEntry entry = (DocumentEntry) root.getEntry(entryName);
        PropertySet properties = new PropertySet(new DocumentInputStream(entry));
        if (properties.isSummaryInformation()) {
            parse(new SummaryInformation(properties));
        }
        if (properties.isDocumentSummaryInformation()) {
            parse(new DocumentSummaryInformation(properties));
        }
    } catch (FileNotFoundException e) {
        // entry does not exist, just skip it
    } catch (NoPropertySetStreamException e) {
        // no property stream, just skip it
    } catch (UnexpectedPropertySetTypeException e) {
        throw new TikaException("Unexpected HPSF document", e);
    } catch (MarkUnsupportedException e) {
        throw new TikaException("Invalid DocumentInputStream", e);
    } catch (Exception e) {
        LOGGER.warn("Ignoring unexpected exception while parsing summary entry " + entryName, e);
    }
}

From source file:mj.ocraptor.extraction.tika.parser.microsoft.WordExtractor.java

License:Apache License

protected void parse(DirectoryNode root, XHTMLContentHandler xhtml)
        throws IOException, SAXException, TikaException {
    HWPFDocument document;/* ww  w .java  2s. c o  m*/
    try {
        document = new HWPFDocument(root);
    } catch (OldWordFileFormatException e) {
        parseWord6(root, xhtml);
        return;
    }

    org.apache.poi.hwpf.extractor.WordExtractor wordExtractor = new org.apache.poi.hwpf.extractor.WordExtractor(
            document);

    // mj
    extractImageText(xhtml, document);

    HeaderStories headerFooter = new HeaderStories(document);

    // Grab the list of pictures. As far as we can tell,
    // the pictures should be in order, and may be directly
    // placed or referenced from an anchor
    PicturesTable pictureTable = document.getPicturesTable();
    PicturesSource pictures = new PicturesSource(document);

    // Do any headers, if present
    Range[] headers = new Range[] { headerFooter.getFirstHeaderSubrange(), headerFooter.getEvenHeaderSubrange(),
            headerFooter.getOddHeaderSubrange() };
    handleHeaderFooter(headers, "header", document, pictures, pictureTable, xhtml);

    // Do the main paragraph text
    Range r = document.getRange();
    for (int i = 0; i < r.numParagraphs(); i++) {
        Paragraph p = r.getParagraph(i);
        i += handleParagraph(p, 0, r, document, FieldsDocumentPart.MAIN, pictures, pictureTable, xhtml);
    }

    // Do everything else
    for (String paragraph : wordExtractor.getMainTextboxText()) {
        xhtml.element("p", paragraph);
    }

    for (String paragraph : wordExtractor.getFootnoteText()) {
        xhtml.element("p", paragraph);
    }

    for (String paragraph : wordExtractor.getCommentsText()) {
        xhtml.element("p", paragraph);
    }

    for (String paragraph : wordExtractor.getEndnoteText()) {
        xhtml.element("p", paragraph);
    }

    // Do any footers, if present
    Range[] footers = new Range[] { headerFooter.getFirstFooterSubrange(), headerFooter.getEvenFooterSubrange(),
            headerFooter.getOddFooterSubrange() };
    handleHeaderFooter(footers, "footer", document, pictures, pictureTable, xhtml);

    // Handle any pictures that we haven't output yet
    for (Picture p = pictures.nextUnclaimed(); p != null;) {
        handlePictureCharacterRun(null, p, pictures, xhtml);
        p = pictures.nextUnclaimed();
    }

    // Handle any embeded office documents
    try {
        DirectoryEntry op = (DirectoryEntry) root.getEntry("ObjectPool");
        for (Entry entry : op) {
            if (entry.getName().startsWith("_") && entry instanceof DirectoryEntry) {
                handleEmbeddedOfficeDoc((DirectoryEntry) entry, xhtml);
            }
        }
    } catch (FileNotFoundException e) {
    }
}

From source file:org.apache.tika.parser.microsoft.SummaryExtractor.java

License:Apache License

private void parseSummaryEntryIfExists(DirectoryNode root, String entryName) throws IOException, TikaException {
    try {/*from   www.  j a  va 2  s.  c om*/
        DocumentEntry entry = (DocumentEntry) root.getEntry(entryName);
        PropertySet properties = new PropertySet(new DocumentInputStream(entry));
        if (properties.isSummaryInformation()) {
            parse(new SummaryInformation(properties));
        }
        if (properties.isDocumentSummaryInformation()) {
            parse(new DocumentSummaryInformation(properties));
        }
    } catch (FileNotFoundException e) {
        // entry does not exist, just skip it
    } catch (NoPropertySetStreamException e) {
        // no property stream, just skip it
    } catch (UnexpectedPropertySetTypeException e) {
        throw new TikaException("Unexpected HPSF document", e);
    } catch (MarkUnsupportedException e) {
        throw new TikaException("Invalid DocumentInputStream", e);
    } catch (Exception e) {
        logger.warn("Ignoring unexpected exception while parsing summary entry " + entryName, e);
    }
}

From source file:org.apache.tika.parser.microsoft.WordExtractor.java

License:Apache License

protected void parse(DirectoryNode root, XHTMLContentHandler xhtml)
        throws IOException, SAXException, TikaException {
    HWPFDocument document;//  w  w w  .java  2  s  .com
    try {
        document = new HWPFDocument(root);
    } catch (OldWordFileFormatException e) {
        parseWord6(root, xhtml);
        return;
    }
    org.apache.poi.hwpf.extractor.WordExtractor wordExtractor = new org.apache.poi.hwpf.extractor.WordExtractor(
            document);
    HeaderStories headerFooter = new HeaderStories(document);

    // Grab the list of pictures. As far as we can tell,
    //  the pictures should be in order, and may be directly
    //  placed or referenced from an anchor
    PicturesTable pictureTable = document.getPicturesTable();
    PicturesSource pictures = new PicturesSource(document);

    // Do any headers, if present
    Range[] headers = new Range[] { headerFooter.getFirstHeaderSubrange(), headerFooter.getEvenHeaderSubrange(),
            headerFooter.getOddHeaderSubrange() };
    handleHeaderFooter(headers, "header", document, pictures, pictureTable, xhtml);

    // Do the main paragraph text
    Range r = document.getRange();
    ListManager listManager = new ListManager(document);
    for (int i = 0; i < r.numParagraphs(); i++) {
        Paragraph p = r.getParagraph(i);
        i += handleParagraph(p, 0, r, document, FieldsDocumentPart.MAIN, pictures, pictureTable, listManager,
                xhtml);
    }

    // Do everything else
    for (String paragraph : wordExtractor.getMainTextboxText()) {
        xhtml.element("p", paragraph);
    }

    for (String paragraph : wordExtractor.getFootnoteText()) {
        xhtml.element("p", paragraph);
    }

    for (String paragraph : wordExtractor.getCommentsText()) {
        xhtml.element("p", paragraph);
    }

    for (String paragraph : wordExtractor.getEndnoteText()) {
        xhtml.element("p", paragraph);
    }

    // Do any footers, if present
    Range[] footers = new Range[] { headerFooter.getFirstFooterSubrange(), headerFooter.getEvenFooterSubrange(),
            headerFooter.getOddFooterSubrange() };
    handleHeaderFooter(footers, "footer", document, pictures, pictureTable, xhtml);

    // Handle any pictures that we haven't output yet
    for (Picture p = pictures.nextUnclaimed(); p != null;) {
        handlePictureCharacterRun(null, p, pictures, xhtml);
        p = pictures.nextUnclaimed();
    }

    // Handle any embeded office documents
    try {
        DirectoryEntry op = (DirectoryEntry) root.getEntry("ObjectPool");
        for (Entry entry : op) {
            if (entry.getName().startsWith("_") && entry instanceof DirectoryEntry) {
                handleEmbeddedOfficeDoc((DirectoryEntry) entry, xhtml);
            }
        }
    } catch (FileNotFoundException e) {
    }
}